diff options
792 files changed, 40030 insertions, 9293 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-btf b/Documentation/ABI/testing/sysfs-kernel-btf new file mode 100644 index 000000000000..2c9744b2cd59 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-btf @@ -0,0 +1,17 @@ +What: /sys/kernel/btf +Date: Aug 2019 +KernelVersion: 5.5 +Contact: bpf@vger.kernel.org +Description: + Contains BTF type information and related data for kernel and + kernel modules. + +What: /sys/kernel/btf/vmlinux +Date: Aug 2019 +KernelVersion: 5.5 +Contact: bpf@vger.kernel.org +Description: + Read-only binary attribute exposing kernel's own BTF type + information with description of all internal kernel types. See + Documentation/bpf/btf.rst for detailed description of format + itself. diff --git a/Documentation/PCI/pci-error-recovery.rst b/Documentation/PCI/pci-error-recovery.rst index e5d450df06b4..13beee23cb04 100644 --- a/Documentation/PCI/pci-error-recovery.rst +++ b/Documentation/PCI/pci-error-recovery.rst @@ -421,7 +421,6 @@ That is, the recovery API only requires that: - drivers/net/ixgbe - drivers/net/cxgb3 - drivers/net/s2io.c - - drivers/net/qlge The End ------- diff --git a/Documentation/bpf/prog_flow_dissector.rst b/Documentation/bpf/prog_flow_dissector.rst index ed343abe541e..a78bf036cadd 100644 --- a/Documentation/bpf/prog_flow_dissector.rst +++ b/Documentation/bpf/prog_flow_dissector.rst @@ -26,6 +26,7 @@ The inputs are: * ``nhoff`` - initial offset of the networking header * ``thoff`` - initial offset of the transport header, initialized to nhoff * ``n_proto`` - L3 protocol type, parsed out of L2 header + * ``flags`` - optional flags Flow dissector BPF program should fill out the rest of the ``struct bpf_flow_keys`` fields. Input arguments ``nhoff/thoff/n_proto`` should be @@ -101,6 +102,23 @@ can be called for both cases and would have to be written carefully to handle both cases. +Flags +===== + +``flow_keys->flags`` might contain optional input flags that work as follows: + +* ``BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG`` - tells BPF flow dissector to + continue parsing first fragment; the default expected behavior is that + flow dissector returns as soon as it finds out that the packet is fragmented; + used by ``eth_get_headlen`` to estimate length of all headers for GRO. +* ``BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL`` - tells BPF flow dissector to + stop parsing as soon as it reaches IPv6 flow label; used by + ``___skb_get_hash`` and ``__skb_get_hash_symmetric`` to get flow hash. +* ``BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP`` - tells BPF flow dissector to stop + parsing as soon as it reaches encapsulated headers; used by routing + infrastructure. + + Reference Implementation ======================== diff --git a/Documentation/devicetree/bindings/net/adi,adin.yaml b/Documentation/devicetree/bindings/net/adi,adin.yaml new file mode 100644 index 000000000000..69375cb28e92 --- /dev/null +++ b/Documentation/devicetree/bindings/net/adi,adin.yaml @@ -0,0 +1,73 @@ +# SPDX-License-Identifier: GPL-2.0+ +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/adi,adin.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Analog Devices ADIN1200/ADIN1300 PHY + +maintainers: + - Alexandru Ardelean <alexandru.ardelean@analog.com> + +description: | + Bindings for Analog Devices Industrial Ethernet PHYs + +allOf: + - $ref: ethernet-phy.yaml# + +properties: + adi,rx-internal-delay-ps: + description: | + RGMII RX Clock Delay used only when PHY operates in RGMII mode with + internal delay (phy-mode is 'rgmii-id' or 'rgmii-rxid') in pico-seconds. + enum: [ 1600, 1800, 2000, 2200, 2400 ] + default: 2000 + + adi,tx-internal-delay-ps: + description: | + RGMII TX Clock Delay used only when PHY operates in RGMII mode with + internal delay (phy-mode is 'rgmii-id' or 'rgmii-txid') in pico-seconds. + enum: [ 1600, 1800, 2000, 2200, 2400 ] + default: 2000 + + adi,fifo-depth-bits: + description: | + When operating in RMII mode, this option configures the FIFO depth. + enum: [ 4, 8, 12, 16, 20, 24 ] + default: 8 + + adi,disable-energy-detect: + description: | + Disables Energy Detect Powerdown Mode (default disabled, i.e energy detect + is enabled if this property is unspecified) + type: boolean + +examples: + - | + ethernet { + #address-cells = <1>; + #size-cells = <0>; + + phy-mode = "rgmii-id"; + + ethernet-phy@0 { + reg = <0>; + + adi,rx-internal-delay-ps = <1800>; + adi,tx-internal-delay-ps = <2200>; + }; + }; + - | + ethernet { + #address-cells = <1>; + #size-cells = <0>; + + phy-mode = "rmii"; + + ethernet-phy@1 { + reg = <1>; + + adi,fifo-depth-bits = <16>; + adi,disable-energy-detect; + }; + }; diff --git a/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml b/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml new file mode 100644 index 000000000000..71808e78a495 --- /dev/null +++ b/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/aspeed,ast2600-mdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ASPEED AST2600 MDIO Controller + +maintainers: + - Andrew Jeffery <andrew@aj.id.au> + +description: |+ + The ASPEED AST2600 MDIO controller is the third iteration of ASPEED's MDIO + bus register interface, this time also separating out the controller from the + MAC. + +allOf: + - $ref: "mdio.yaml#" + +properties: + compatible: + const: aspeed,ast2600-mdio + reg: + maxItems: 1 + description: The register range of the MDIO controller instance + +required: + - compatible + - reg + - "#address-cells" + - "#size-cells" + +examples: + - | + mdio0: mdio@1e650000 { + compatible = "aspeed,ast2600-mdio"; + reg = <0x1e650000 0x8>; + #address-cells = <1>; + #size-cells = <0>; + + ethphy0: ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt index bc77477c6878..94c0f8bf4deb 100644 --- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt +++ b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt @@ -32,6 +32,15 @@ Optional properties: ack_gpr is the gpr register offset of CAN stop acknowledge. ack_bit is the bit offset of CAN stop acknowledge. +- fsl,clk-source: Select the clock source to the CAN Protocol Engine (PE). + It's SoC Implementation dependent. Refer to RM for detailed + definition. If this property is not set in device tree node + then driver selects clock source 1 by default. + 0: clock source 0 (oscillator clock) + 1: clock source 1 (peripheral clock) + +- wakeup-source: enable CAN remote wakeup + Example: can@1c000 { @@ -40,4 +49,5 @@ Example: interrupts = <48 0x2>; interrupt-parent = <&mpic>; clock-frequency = <200000000>; // filled in by bootloader + fsl,clk-source = <0>; // select clock source 0 for PE }; diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt new file mode 100644 index 000000000000..c388f7d9feb1 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -0,0 +1,37 @@ +Texas Instruments TCAN4x5x CAN Controller +================================================ + +This file provides device node information for the TCAN4x5x interface contains. + +Required properties: + - compatible: "ti,tcan4x5x" + - reg: 0 + - #address-cells: 1 + - #size-cells: 0 + - spi-max-frequency: Maximum frequency of the SPI bus the chip can + operate at should be less than or equal to 18 MHz. + - data-ready-gpios: Interrupt GPIO for data and error reporting. + - device-wake-gpios: Wake up GPIO to wake up the TCAN device. + +See Documentation/devicetree/bindings/net/can/m_can.txt for additional +required property details. + +Optional properties: + - reset-gpios: Hardwired output GPIO. If not defined then software + reset. + - device-state-gpios: Input GPIO that indicates if the device is in + a sleep state or if the device is active. + +Example: +tcan4x5x: tcan4x5x@0 { + compatible = "ti,tcan4x5x"; + reg = <0>; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <10000000>; + bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; + data-ready-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; + device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>; +}; diff --git a/Documentation/devicetree/bindings/net/dsa/ksz.txt b/Documentation/devicetree/bindings/net/dsa/ksz.txt index 4ac21cef370e..5e8429b6f9ca 100644 --- a/Documentation/devicetree/bindings/net/dsa/ksz.txt +++ b/Documentation/devicetree/bindings/net/dsa/ksz.txt @@ -5,6 +5,9 @@ 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" diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt index 6f9538974bb9..30c11fea491b 100644 --- a/Documentation/devicetree/bindings/net/dsa/marvell.txt +++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt @@ -22,7 +22,7 @@ which is at a different MDIO base address in different switch families. - "marvell,mv88e6190" : Switch has base address 0x00. Use with models: 6190, 6190X, 6191, 6290, 6390, 6390X - "marvell,mv88e6250" : Switch has base address 0x08 or 0x18. Use with model: - 6250 + 6220, 6250 Required properties: - compatible : Should be one of "marvell,mv88e6085", diff --git a/Documentation/devicetree/bindings/net/fsl-enetc.txt b/Documentation/devicetree/bindings/net/fsl-enetc.txt index 25fc687419db..b7034ccbc1bd 100644 --- a/Documentation/devicetree/bindings/net/fsl-enetc.txt +++ b/Documentation/devicetree/bindings/net/fsl-enetc.txt @@ -11,7 +11,9 @@ Required properties: to parent node bindings. - compatible : Should be "fsl,enetc". -1) The ENETC external port is connected to a MDIO configurable phy: +1. The ENETC external port is connected to a MDIO configurable phy + +1.1. Using the local ENETC Port MDIO interface In this case, the ENETC node should include a "mdio" sub-node that in turn should contain the "ethernet-phy" node describing the @@ -47,8 +49,42 @@ Example: }; }; -2) The ENETC port is an internal port or has a fixed-link external -connection: +1.2. Using the central MDIO PCIe endpoint device + +In this case, the mdio node should be defined as another PCIe +endpoint node, at the same level with the ENETC port nodes. + +Required properties: + +- reg : Specifies PCIe Device Number and Function + Number of the ENETC endpoint device, according + to parent node bindings. +- compatible : Should be "fsl,enetc-mdio". + +The remaining required mdio bus properties are standard, their bindings +already defined in Documentation/devicetree/bindings/net/mdio.txt. + +Example: + + ethernet@0,0 { + compatible = "fsl,enetc"; + reg = <0x000000 0 0 0 0>; + phy-handle = <&sgmii_phy0>; + phy-connection-type = "sgmii"; + }; + + mdio@0,3 { + compatible = "fsl,enetc-mdio"; + reg = <0x000300 0 0 0 0>; + #address-cells = <1>; + #size-cells = <0>; + sgmii_phy0: ethernet-phy@2 { + reg = <0x2>; + }; + }; + +2. The ENETC port is an internal port or has a fixed-link external +connection In this case, the ENETC port node defines a fixed link connection, as specified by Documentation/devicetree/bindings/net/fixed-link.txt. diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt index 770ff98d4524..72d03e07cf7c 100644 --- a/Documentation/devicetree/bindings/net/mediatek-net.txt +++ b/Documentation/devicetree/bindings/net/mediatek-net.txt @@ -12,6 +12,7 @@ Required properties: "mediatek,mt7623-eth", "mediatek,mt2701-eth": for MT7623 SoC "mediatek,mt7622-eth": for MT7622 SoC "mediatek,mt7629-eth": for MT7629 SoC + "ralink,rt5350-eth": for Ralink Rt5350F and MT7628/88 SoC - reg: Address and length of the register set for the device - interrupts: Should contain the three frame engines interrupts in numeric order. These are fe_int0, fe_int1 and fe_int2. diff --git a/Documentation/devicetree/bindings/net/mscc-ocelot.txt b/Documentation/devicetree/bindings/net/mscc-ocelot.txt index 9e5c17d426ce..3b6290b45ce5 100644 --- a/Documentation/devicetree/bindings/net/mscc-ocelot.txt +++ b/Documentation/devicetree/bindings/net/mscc-ocelot.txt @@ -12,13 +12,15 @@ Required properties: - "sys" - "rew" - "qs" + - "ptp" (optional due to backward compatibility) - "qsys" - "ana" - "portX" with X from 0 to the number of last port index available on that switch -- interrupts: Should contain the switch interrupts for frame extraction and - frame injection -- interrupt-names: should contain the interrupt names: "xtr", "inj" +- interrupts: Should contain the switch interrupts for frame extraction, + frame injection and PTP ready. +- interrupt-names: should contain the interrupt names: "xtr", "inj". Can contain + "ptp_rdy" which is optional due to backward compatibility. - ethernet-ports: A container for child nodes representing switch ports. The ethernet-ports container has the following properties @@ -44,6 +46,7 @@ Example: reg = <0x1010000 0x10000>, <0x1030000 0x10000>, <0x1080000 0x100>, + <0x10e0000 0x10000>, <0x11e0000 0x100>, <0x11f0000 0x100>, <0x1200000 0x100>, @@ -57,11 +60,12 @@ Example: <0x1280000 0x100>, <0x1800000 0x80000>, <0x1880000 0x10000>; - reg-names = "sys", "rew", "qs", "port0", "port1", "port2", - "port3", "port4", "port5", "port6", "port7", - "port8", "port9", "port10", "qsys", "ana"; - interrupts = <21 22>; - interrupt-names = "xtr", "inj"; + reg-names = "sys", "rew", "qs", "ptp", "port0", "port1", + "port2", "port3", "port4", "port5", "port6", + "port7", "port8", "port9", "port10", "qsys", + "ana"; + interrupts = <18 21 22>; + interrupt-names = "ptp_rdy", "xtr", "inj"; ethernet-ports { #address-cells = <1>; diff --git a/Documentation/networking/devlink-trap-netdevsim.rst b/Documentation/networking/devlink-trap-netdevsim.rst new file mode 100644 index 000000000000..b721c9415473 --- /dev/null +++ b/Documentation/networking/devlink-trap-netdevsim.rst @@ -0,0 +1,20 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================== +Devlink Trap netdevsim +====================== + +Driver-specific Traps +===================== + +.. list-table:: List of Driver-specific Traps Registered by ``netdevsim`` + :widths: 5 5 90 + + * - Name + - Type + - Description + * - ``fid_miss`` + - ``exception`` + - When a packet enters the device it is classified to a filtering + indentifier (FID) based on the ingress port and VLAN. This trap is used + to trap packets for which a FID could not be found diff --git a/Documentation/networking/devlink-trap.rst b/Documentation/networking/devlink-trap.rst new file mode 100644 index 000000000000..c20c7c483664 --- /dev/null +++ b/Documentation/networking/devlink-trap.rst @@ -0,0 +1,208 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============ +Devlink Trap +============ + +Background +========== + +Devices capable of offloading the kernel's datapath and perform functions such +as bridging and routing must also be able to send specific packets to the +kernel (i.e., the CPU) for processing. + +For example, a device acting as a multicast-aware bridge must be able to send +IGMP membership reports to the kernel for processing by the bridge module. +Without processing such packets, the bridge module could never populate its +MDB. + +As another example, consider a device acting as router which has received an IP +packet with a TTL of 1. Upon routing the packet the device must send it to the +kernel so that it will route it as well and generate an ICMP Time Exceeded +error datagram. Without letting the kernel route such packets itself, utilities +such as ``traceroute`` could never work. + +The fundamental ability of sending certain packets to the kernel for processing +is called "packet trapping". + +Overview +======== + +The ``devlink-trap`` mechanism allows capable device drivers to register their +supported packet traps with ``devlink`` and report trapped packets to +``devlink`` for further analysis. + +Upon receiving trapped packets, ``devlink`` will perform a per-trap packets and +bytes accounting and potentially report the packet to user space via a netlink +event along with all the provided metadata (e.g., trap reason, timestamp, input +port). This is especially useful for drop traps (see :ref:`Trap-Types`) +as it allows users to obtain further visibility into packet drops that would +otherwise be invisible. + +The following diagram provides a general overview of ``devlink-trap``:: + + Netlink event: Packet w/ metadata + Or a summary of recent drops + ^ + | + Userspace | + +---------------------------------------------------+ + Kernel | + | + +-------+--------+ + | | + | drop_monitor | + | | + +-------^--------+ + | + | + | + +----+----+ + | | Kernel's Rx path + | devlink | (non-drop traps) + | | + +----^----+ ^ + | | + +-----------+ + | + +-------+-------+ + | | + | Device driver | + | | + +-------^-------+ + Kernel | + +---------------------------------------------------+ + Hardware | + | Trapped packet + | + +--+---+ + | | + | ASIC | + | | + +------+ + +.. _Trap-Types: + +Trap Types +========== + +The ``devlink-trap`` mechanism supports the following packet trap types: + + * ``drop``: Trapped packets were dropped by the underlying device. Packets + are only processed by ``devlink`` and not injected to the kernel's Rx path. + The trap action (see :ref:`Trap-Actions`) can be changed. + * ``exception``: Trapped packets were not forwarded as intended by the + underlying device due to an exception (e.g., TTL error, missing neighbour + entry) and trapped to the control plane for resolution. Packets are + processed by ``devlink`` and injected to the kernel's Rx path. Changing the + action of such traps is not allowed, as it can easily break the control + plane. + +.. _Trap-Actions: + +Trap Actions +============ + +The ``devlink-trap`` mechanism supports the following packet trap actions: + + * ``trap``: The sole copy of the packet is sent to the CPU. + * ``drop``: The packet is dropped by the underlying device and a copy is not + sent to the CPU. + +Generic Packet Traps +==================== + +Generic packet traps are used to describe traps that trap well-defined packets +or packets that are trapped due to well-defined conditions (e.g., TTL error). +Such traps can be shared by multiple device drivers and their description must +be added to the following table: + +.. list-table:: List of Generic Packet Traps + :widths: 5 5 90 + + * - Name + - Type + - Description + * - ``source_mac_is_multicast`` + - ``drop`` + - Traps incoming packets that the device decided to drop because of a + multicast source MAC + * - ``vlan_tag_mismatch`` + - ``drop`` + - Traps incoming packets that the device decided to drop in case of VLAN + tag mismatch: The ingress bridge port is not configured with a PVID and + the packet is untagged or prio-tagged + * - ``ingress_vlan_filter`` + - ``drop`` + - Traps incoming packets that the device decided to drop in case they are + tagged with a VLAN that is not configured on the ingress bridge port + * - ``ingress_spanning_tree_filter`` + - ``drop`` + - Traps incoming packets that the device decided to drop in case the STP + state of the ingress bridge port is not "forwarding" + * - ``port_list_is_empty`` + - ``drop`` + - Traps packets that the device decided to drop in case they need to be + flooded and the flood list is empty + * - ``port_loopback_filter`` + - ``drop`` + - Traps packets that the device decided to drop in case after layer 2 + forwarding the only port from which they should be transmitted through + is the port from which they were received + * - ``blackhole_route`` + - ``drop`` + - Traps packets that the device decided to drop in case they hit a + blackhole route + * - ``ttl_value_is_too_small`` + - ``exception`` + - Traps unicast packets that should be forwarded by the device whose TTL + was decremented to 0 or less + * - ``tail_drop`` + - ``drop`` + - Traps packets that the device decided to drop because they could not be + enqueued to a transmission queue which is full + +Driver-specific Packet Traps +============================ + +Device drivers can register driver-specific packet traps, but these must be +clearly documented. Such traps can correspond to device-specific exceptions and +help debug packet drops caused by these exceptions. The following list includes +links to the description of driver-specific traps registered by various device +drivers: + + * :doc:`/devlink-trap-netdevsim` + +Generic Packet Trap Groups +========================== + +Generic packet trap groups are used to aggregate logically related packet +traps. These groups allow the user to batch operations such as setting the trap +action of all member traps. In addition, ``devlink-trap`` can report aggregated +per-group packets and bytes statistics, in case per-trap statistics are too +narrow. The description of these groups must be added to the following table: + +.. list-table:: List of Generic Packet Trap Groups + :widths: 10 90 + + * - Name + - Description + * - ``l2_drops`` + - Contains packet traps for packets that were dropped by the device during + layer 2 forwarding (i.e., bridge) + * - ``l3_drops`` + - Contains packet traps for packets that were dropped by the device or hit + an exception (e.g., TTL error) during layer 3 forwarding + * - ``buffer_drops`` + - Contains packet traps for packets that were dropped by the device due to + an enqueue decision + +Testing +======= + +See ``tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh`` for a +test covering the core infrastructure. Test cases should be added for any new +functionality. + +Device drivers should focus their tests on device-specific functionality, such +as the triggering of supported packet traps. diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index a46fca264bee..37eabc17894c 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -14,6 +14,8 @@ Contents: device_drivers/index dsa/index devlink-info-versions + devlink-trap + devlink-trap-netdevsim ieee802154 kapi z8530book diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index df33674799b5..49e95f438ed7 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -256,6 +256,12 @@ tcp_base_mss - INTEGER Path MTU discovery (MTU probing). If MTU probing is enabled, this is the initial MSS used by the connection. +tcp_mtu_probe_floor - INTEGER + If MTU probing is enabled this caps the minimum MSS used for search_low + for the connection. + + Default : 48 + tcp_min_snd_mss - INTEGER TCP SYN and SYNACK messages usually advertise an ADVMSS option, as described in RFC 1122 and RFC 6691. diff --git a/MAINTAINERS b/MAINTAINERS index 08176d64eed5..a406947b369e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -938,6 +938,14 @@ S: Supported F: drivers/mux/adgs1408.c F: Documentation/devicetree/bindings/mux/adi,adgs1408.txt +ANALOG DEVICES INC ADIN DRIVER +M: Alexandru Ardelean <alexaundru.ardelean@analog.com> +L: netdev@vger.kernel.org +W: http://ez.analog.com/community/linux-device-drivers +S: Supported +F: drivers/net/phy/adin.c +F: Documentation/devicetree/bindings/net/adi,adin.yaml + ANALOG DEVICES INC ADIS DRIVER LIBRARY M: Alexandru Ardelean <alexandru.ardelean@analog.com> S: Supported @@ -3635,9 +3643,12 @@ S: Maintained F: Documentation/devicetree/bindings/net/can/ F: drivers/net/can/ F: include/linux/can/dev.h +F: include/linux/can/led.h +F: include/linux/can/rx-offload.h F: include/linux/can/platform/ F: include/uapi/linux/can/error.h F: include/uapi/linux/can/netlink.h +F: include/uapi/linux/can/vxcan.h CAN NETWORK LAYER M: Oliver Hartkopp <socketcan@hartkopp.net> @@ -3650,6 +3661,8 @@ S: Maintained F: Documentation/networking/can.rst F: net/can/ F: include/linux/can/core.h +F: include/linux/can/skb.h +F: include/net/netns/can.h F: include/uapi/linux/can.h F: include/uapi/linux/can/bcm.h F: include/uapi/linux/can/raw.h @@ -11158,6 +11171,7 @@ S: Maintained W: https://fedorahosted.org/dropwatch/ F: net/core/drop_monitor.c F: include/uapi/linux/net_dropmon.h +F: include/net/drop_monitor.h NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> @@ -11337,7 +11351,6 @@ F: include/net/nfc/ F: include/uapi/linux/nfc.h F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h -F: include/linux/platform_data/nxp-nci.h F: Documentation/devicetree/bindings/net/nfc/ NFS, SUNRPC, AND LOCKD CLIENTS @@ -13232,7 +13245,7 @@ M: Manish Chopra <manishc@marvell.com> M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org S: Supported -F: drivers/net/ethernet/qlogic/qlge/ +F: drivers/staging/qlge/ QM1D1B0004 MEDIA DRIVER M: Akihiro Tsukada <tskd08@gmail.com> diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts index de6ef39f3118..663c4b728c07 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts @@ -85,6 +85,26 @@ system-clock-frequency = <25000000>; }; }; + + mdio-mux { + compatible = "mdio-mux-multiplexer"; + mux-controls = <&mux 0>; + mdio-parent-bus = <&enetc_mdio_pf3>; + #address-cells=<1>; + #size-cells = <0>; + + /* on-board RGMII PHY */ + mdio@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + qds_phy1: ethernet-phy@5 { + /* Atheros 8035 */ + reg = <5>; + }; + }; + }; }; &duart0 { @@ -164,6 +184,26 @@ }; }; }; + + fpga@66 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,ls1028aqds-fpga", "fsl,fpga-qixis-i2c", + "simple-mfd"; + reg = <0x66>; + + mux: mux-controller { + compatible = "reg-mux"; + #mux-control-cells = <1>; + mux-reg-masks = <0x54 0xf0>; /* 0: reg 0x54, bits 7:4 */ + }; + }; + +}; + +&enetc_port1 { + phy-handle = <&qds_phy1>; + phy-connection-type = "rgmii-id"; }; &sai1 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 7975519b4f56..de71153fda00 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -536,6 +536,12 @@ compatible = "fsl,enetc"; reg = <0x000100 0 0 0 0>; }; + enetc_mdio_pf3: mdio@0,3 { + compatible = "fsl,enetc-mdio"; + reg = <0x000300 0 0 0 0>; + #address-cells = <1>; + #size-cells = <0>; + }; ethernet@0,4 { compatible = "fsl,enetc-ptp"; reg = <0x000400 0 0 0 0>; diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 79b718430cd1..b23d1e4bad33 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -1136,7 +1136,7 @@ DPRINTK("doing direct send\n"); /* @@@ well, this doesn't work anyway */ else put_dma(tx->index,eni_dev->dma,&j,(unsigned long) skb_frag_page(&skb_shinfo(skb)->frags[i]) + - skb_shinfo(skb)->frags[i].page_offset, + skb_frag_off(&skb_shinfo(skb)->frags[i]), skb_frag_size(&skb_shinfo(skb)->frags[i])); } if (skb->len & 3) { diff --git a/drivers/atm/he.c b/drivers/atm/he.c index 211607986134..70b00ae4ec38 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -2580,10 +2580,9 @@ he_send(struct atm_vcc *vcc, struct sk_buff *skb) slot = 0; } - tpd->iovec[slot].addr = dma_map_single(&he_dev->pci_dev->dev, - (void *) page_address(frag->page) + frag->page_offset, - frag->size, DMA_TO_DEVICE); - tpd->iovec[slot].len = frag->size; + tpd->iovec[slot].addr = skb_frag_dma_map(&he_dev->pci_dev->dev, + frag, 0, skb_frag_size(frag), DMA_TO_DEVICE); + tpd->iovec[slot].len = skb_frag_size(frag); ++slot; } diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 5c4c6eeb505c..c32f7dd9879a 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -516,9 +516,8 @@ struct geos_gpio_attr { static ssize_t geos_gpio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct pci_dev *pdev = to_pci_dev(dev); struct geos_gpio_attr *gattr = container_of(attr, struct geos_gpio_attr, attr); - struct solos_card *card = pci_get_drvdata(pdev); + struct solos_card *card = dev_get_drvdata(dev); uint32_t data32; if (count != 1 && (count != 2 || buf[1] != '\n')) @@ -542,9 +541,8 @@ static ssize_t geos_gpio_store(struct device *dev, struct device_attribute *attr static ssize_t geos_gpio_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct pci_dev *pdev = to_pci_dev(dev); struct geos_gpio_attr *gattr = container_of(attr, struct geos_gpio_attr, attr); - struct solos_card *card = pci_get_drvdata(pdev); + struct solos_card *card = dev_get_drvdata(dev); uint32_t data32; data32 = ioread32(card->config_regs + GPIO_STATUS); @@ -556,9 +554,8 @@ static ssize_t geos_gpio_show(struct device *dev, struct device_attribute *attr, static ssize_t hardware_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct pci_dev *pdev = to_pci_dev(dev); struct geos_gpio_attr *gattr = container_of(attr, struct geos_gpio_attr, attr); - struct solos_card *card = pci_get_drvdata(pdev); + struct solos_card *card = dev_get_drvdata(dev); uint32_t data32; data32 = ioread32(card->config_regs + GPIO_STATUS); diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index 551bca6fef24..c70cb5f272cf 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -1134,7 +1134,9 @@ copy: } /* Update the skb. */ if (merge) { - skb_shinfo(skb)->frags[i - 1].size += copy; + skb_frag_size_add( + &skb_shinfo(skb)->frags[i - 1], + copy); } else { skb_fill_page_desc(skb, i, page, off, copy); if (off + copy < pg_size) { @@ -1247,7 +1249,7 @@ new_buf: i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { - skb_shinfo(skb)->frags[i - 1].size += copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else if (i < MAX_SKB_FRAGS) { get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c index 9aeed98b87a1..0253e76f1df2 100644 --- a/drivers/hsi/clients/ssi_protocol.c +++ b/drivers/hsi/clients/ssi_protocol.c @@ -181,7 +181,8 @@ static void ssip_skb_to_msg(struct sk_buff *skb, struct hsi_msg *msg) sg = sg_next(sg); BUG_ON(!sg); frag = &skb_shinfo(skb)->frags[i]; - sg_set_page(sg, frag->page.p, frag->size, frag->page_offset); + sg_set_page(sg, skb_frag_page(frag), skb_frag_size(frag), + skb_frag_off(frag)); } } diff --git a/drivers/infiniband/hw/hfi1/vnic_sdma.c b/drivers/infiniband/hw/hfi1/vnic_sdma.c index af1b1ffcb38e..7d90b900131b 100644 --- a/drivers/infiniband/hw/hfi1/vnic_sdma.c +++ b/drivers/infiniband/hw/hfi1/vnic_sdma.c @@ -102,13 +102,13 @@ static noinline int build_vnic_ulp_payload(struct sdma_engine *sde, goto bail_txadd; for (i = 0; i < skb_shinfo(tx->skb)->nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(tx->skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(tx->skb)->frags[i]; /* combine physically continuous fragments later? */ ret = sdma_txadd_page(sde->dd, &tx->txreq, skb_frag_page(frag), - frag->page_offset, + skb_frag_off(frag), skb_frag_size(frag)); if (unlikely(ret)) goto bail_txadd; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 78fa777c87b1..c332b4761816 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -293,7 +293,8 @@ int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req) const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; mapping[i + off] = ib_dma_map_page(ca, skb_frag_page(frag), - frag->page_offset, skb_frag_size(frag), + skb_frag_off(frag), + skb_frag_size(frag), DMA_TO_DEVICE); if (unlikely(ib_dma_mapping_error(ca, mapping[i + off]))) goto partial_error; diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 1360f1ffe070..f3f86ef68ae0 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -55,11 +55,6 @@ void bond_debug_register(struct bonding *bond) bond->debug_dir = debugfs_create_dir(bond->dev->name, bonding_debug_root); - if (!bond->debug_dir) { - netdev_warn(bond->dev, "failed to register to debugfs\n"); - return; - } - debugfs_create_file("rlb_hash_table", 0400, bond->debug_dir, bond, &bond_debug_rlb_hash_fops); } diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index ed3c437063dc..40b079162804 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -94,26 +94,20 @@ static inline void update_tty_status(struct ser_device *ser) } static inline void debugfs_init(struct ser_device *ser, struct tty_struct *tty) { - ser->debugfs_tty_dir = - debugfs_create_dir(tty->name, debugfsdir); - if (!IS_ERR(ser->debugfs_tty_dir)) { - debugfs_create_blob("last_tx_msg", 0400, - ser->debugfs_tty_dir, - &ser->tx_blob); + ser->debugfs_tty_dir = debugfs_create_dir(tty->name, debugfsdir); - debugfs_create_blob("last_rx_msg", 0400, - ser->debugfs_tty_dir, - &ser->rx_blob); + debugfs_create_blob("last_tx_msg", 0400, ser->debugfs_tty_dir, + &ser->tx_blob); - debugfs_create_x32("ser_state", 0400, - ser->debugfs_tty_dir, - (u32 *)&ser->state); + debugfs_create_blob("last_rx_msg", 0400, ser->debugfs_tty_dir, + &ser->rx_blob); - debugfs_create_x8("tty_status", 0400, - ser->debugfs_tty_dir, - &ser->tty_status); + debugfs_create_x32("ser_state", 0400, ser->debugfs_tty_dir, + (u32 *)&ser->state); + + debugfs_create_x8("tty_status", 0400, ser->debugfs_tty_dir, + &ser->tty_status); - } ser->tx_blob.data = ser->tx_data; ser->tx_blob.size = 0; ser->rx_blob.data = ser->rx_data; diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index 27e93a438dd9..eb426822ad06 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -623,11 +623,7 @@ static void cfv_netdev_setup(struct net_device *netdev) /* Create debugfs counters for the device */ static inline void debugfs_init(struct cfv_info *cfv) { - cfv->debugfs = - debugfs_create_dir(netdev_name(cfv->ndev), NULL); - - if (IS_ERR(cfv->debugfs)) - return; + cfv->debugfs = debugfs_create_dir(netdev_name(cfv->ndev), NULL); debugfs_create_u32("rx-napi-complete", 0400, cfv->debugfs, &cfv->stats.rx_napi_complete); diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index ab585900a057..17c166cc8482 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -120,6 +120,19 @@ config CAN_JANZ_ICAN3 This driver can also be built as a module. If so, the module will be called janz-ican3.ko. +config CAN_KVASER_PCIEFD + depends on PCI + tristate "Kvaser PCIe FD cards" + help + This is a driver for the Kvaser PCI Express CAN FD family. + + Supported devices: + Kvaser PCIEcan 4xHS + Kvaser PCIEcan 2xHS v2 + Kvaser PCIEcan HS v2 + Kvaser Mini PCI Express HS v2 + Kvaser Mini PCI Express 2xHS v2 + config CAN_SUN4I tristate "Allwinner A10 CAN controller" depends on MACH_SUN4I || MACH_SUN7I || COMPILE_TEST diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index 44922bf29b6a..22164300122d 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_CAN_FLEXCAN) += flexcan.o obj-$(CONFIG_CAN_GRCAN) += grcan.o obj-$(CONFIG_CAN_IFI_CANFD) += ifi_canfd/ obj-$(CONFIG_CAN_JANZ_ICAN3) += janz-ican3.o +obj-$(CONFIG_CAN_KVASER_PCIEFD) += kvaser_pciefd.o obj-$(CONFIG_CAN_MSCAN) += mscan/ obj-$(CONFIG_CAN_M_CAN) += m_can/ obj-$(CONFIG_CAN_PEAK_PCIEFD) += peak_canfd/ diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index fcec8bcb53d6..dc5695dffc2e 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -24,6 +24,7 @@ #include <linux/of.h> #include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> #include <linux/regmap.h> @@ -266,6 +267,7 @@ struct flexcan_stop_mode { struct flexcan_priv { struct can_priv can; struct can_rx_offload offload; + struct device *dev; struct flexcan_regs __iomem *regs; struct flexcan_mb __iomem *tx_mb; @@ -273,6 +275,8 @@ struct flexcan_priv { u8 tx_mb_idx; u8 mb_count; u8 mb_size; + u8 clk_src; /* clock source of CAN Protocol Engine */ + u32 reg_ctrl_default; u32 reg_imask1_default; u32 reg_imask2_default; @@ -462,6 +466,27 @@ static inline void flexcan_error_irq_disable(const struct flexcan_priv *priv) priv->write(reg_ctrl, ®s->ctrl); } +static int flexcan_clks_enable(const struct flexcan_priv *priv) +{ + int err; + + err = clk_prepare_enable(priv->clk_ipg); + if (err) + return err; + + err = clk_prepare_enable(priv->clk_per); + if (err) + clk_disable_unprepare(priv->clk_ipg); + + return err; +} + +static void flexcan_clks_disable(const struct flexcan_priv *priv) +{ + clk_disable_unprepare(priv->clk_per); + clk_disable_unprepare(priv->clk_ipg); +} + static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv) { if (!priv->reg_xceiver) @@ -588,19 +613,13 @@ static int flexcan_get_berr_counter(const struct net_device *dev, const struct flexcan_priv *priv = netdev_priv(dev); int err; - err = clk_prepare_enable(priv->clk_ipg); - if (err) + err = pm_runtime_get_sync(priv->dev); + if (err < 0) return err; - err = clk_prepare_enable(priv->clk_per); - if (err) - goto out_disable_ipg; - err = __flexcan_get_berr_counter(dev, bec); - clk_disable_unprepare(priv->clk_per); - out_disable_ipg: - clk_disable_unprepare(priv->clk_ipg); + pm_runtime_put(priv->dev); return err; } @@ -1233,17 +1252,13 @@ static int flexcan_open(struct net_device *dev) struct flexcan_priv *priv = netdev_priv(dev); int err; - err = clk_prepare_enable(priv->clk_ipg); - if (err) + err = pm_runtime_get_sync(priv->dev); + if (err < 0) return err; - err = clk_prepare_enable(priv->clk_per); - if (err) - goto out_disable_ipg; - err = open_candev(dev); if (err) - goto out_disable_per; + goto out_runtime_put; err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); if (err) @@ -1306,10 +1321,8 @@ static int flexcan_open(struct net_device *dev) free_irq(dev->irq, dev); out_close: close_candev(dev); - out_disable_per: - clk_disable_unprepare(priv->clk_per); - out_disable_ipg: - clk_disable_unprepare(priv->clk_ipg); + out_runtime_put: + pm_runtime_put(priv->dev); return err; } @@ -1324,10 +1337,9 @@ static int flexcan_close(struct net_device *dev) can_rx_offload_del(&priv->offload); free_irq(dev->irq, dev); - clk_disable_unprepare(priv->clk_per); - clk_disable_unprepare(priv->clk_ipg); close_candev(dev); + pm_runtime_put(priv->dev); can_led_event(dev, CAN_LED_EVENT_STOP); @@ -1367,20 +1379,20 @@ static int register_flexcandev(struct net_device *dev) struct flexcan_regs __iomem *regs = priv->regs; u32 reg, err; - err = clk_prepare_enable(priv->clk_ipg); + err = flexcan_clks_enable(priv); if (err) return err; - err = clk_prepare_enable(priv->clk_per); - if (err) - goto out_disable_ipg; - /* select "bus clock", chip must be disabled */ err = flexcan_chip_disable(priv); if (err) - goto out_disable_per; + goto out_clks_disable; + reg = priv->read(®s->ctrl); - reg |= FLEXCAN_CTRL_CLK_SRC; + if (priv->clk_src) + reg |= FLEXCAN_CTRL_CLK_SRC; + else + reg &= ~FLEXCAN_CTRL_CLK_SRC; priv->write(reg, ®s->ctrl); err = flexcan_chip_enable(priv); @@ -1406,15 +1418,21 @@ static int register_flexcandev(struct net_device *dev) } err = register_candev(dev); + if (err) + goto out_chip_disable; - /* disable core and turn off clocks */ - out_chip_disable: + /* Disable core and let pm_runtime_put() disable the clocks. + * If CONFIG_PM is not enabled, the clocks will stay powered. + */ flexcan_chip_disable(priv); - out_disable_per: - clk_disable_unprepare(priv->clk_per); - out_disable_ipg: - clk_disable_unprepare(priv->clk_ipg); + pm_runtime_put(priv->dev); + return 0; + + out_chip_disable: + flexcan_chip_disable(priv); + out_clks_disable: + flexcan_clks_disable(priv); return err; } @@ -1473,6 +1491,11 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, true); + if (of_property_read_bool(np, "wakeup-source")) + device_set_wakeup_enable(&pdev->dev, true); + + return 0; + out_put_node: of_node_put(gpr_np); return ret; @@ -1508,6 +1531,7 @@ static int flexcan_probe(struct platform_device *pdev) struct clk *clk_ipg = NULL, *clk_per = NULL; struct flexcan_regs __iomem *regs; int err, irq; + u8 clk_src = 1; u32 clock_freq = 0; reg_xceiver = devm_regulator_get(&pdev->dev, "xceiver"); @@ -1516,9 +1540,12 @@ static int flexcan_probe(struct platform_device *pdev) else if (IS_ERR(reg_xceiver)) reg_xceiver = NULL; - if (pdev->dev.of_node) + if (pdev->dev.of_node) { of_property_read_u32(pdev->dev.of_node, "clock-frequency", &clock_freq); + of_property_read_u8(pdev->dev.of_node, + "fsl,clk-source", &clk_src); + } if (!clock_freq) { clk_ipg = devm_clk_get(&pdev->dev, "ipg"); @@ -1576,6 +1603,7 @@ static int flexcan_probe(struct platform_device *pdev) priv->write = flexcan_write_le; } + priv->dev = &pdev->dev; priv->can.clock.freq = clock_freq; priv->can.bittiming_const = &flexcan_bittiming_const; priv->can.do_set_mode = flexcan_set_mode; @@ -1586,9 +1614,14 @@ static int flexcan_probe(struct platform_device *pdev) priv->regs = regs; priv->clk_ipg = clk_ipg; priv->clk_per = clk_per; + priv->clk_src = clk_src; priv->devtype_data = devtype_data; priv->reg_xceiver = reg_xceiver; + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + err = register_flexcandev(dev); if (err) { dev_err(&pdev->dev, "registering netdev failed\n"); @@ -1615,6 +1648,7 @@ static int flexcan_remove(struct platform_device *pdev) struct net_device *dev = platform_get_drvdata(pdev); unregister_flexcandev(dev); + pm_runtime_disable(&pdev->dev); free_candev(dev); return 0; @@ -1624,7 +1658,7 @@ static int __maybe_unused flexcan_suspend(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); - int err; + int err = 0; if (netif_running(dev)) { /* if wakeup is enabled, enter stop mode @@ -1639,20 +1673,22 @@ static int __maybe_unused flexcan_suspend(struct device *device) err = flexcan_chip_disable(priv); if (err) return err; + + err = pm_runtime_force_suspend(device); } netif_stop_queue(dev); netif_device_detach(dev); } priv->can.state = CAN_STATE_SLEEPING; - return 0; + return err; } static int __maybe_unused flexcan_resume(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); - int err; + int err = 0; priv->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(dev)) { @@ -1661,14 +1697,35 @@ static int __maybe_unused flexcan_resume(struct device *device) if (device_may_wakeup(device)) { disable_irq_wake(dev->irq); } else { - err = flexcan_chip_enable(priv); + err = pm_runtime_force_resume(device); if (err) return err; + + err = flexcan_chip_enable(priv); } } + + return err; +} + +static int __maybe_unused flexcan_runtime_suspend(struct device *device) +{ + struct net_device *dev = dev_get_drvdata(device); + struct flexcan_priv *priv = netdev_priv(dev); + + flexcan_clks_disable(priv); + return 0; } +static int __maybe_unused flexcan_runtime_resume(struct device *device) +{ + struct net_device *dev = dev_get_drvdata(device); + struct flexcan_priv *priv = netdev_priv(dev); + + return flexcan_clks_enable(priv); +} + static int __maybe_unused flexcan_noirq_suspend(struct device *device) { struct net_device *dev = dev_get_drvdata(device); @@ -1698,6 +1755,7 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) static const struct dev_pm_ops flexcan_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(flexcan_suspend, flexcan_resume) + SET_RUNTIME_PM_OPS(flexcan_runtime_suspend, flexcan_runtime_resume, NULL) SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(flexcan_noirq_suspend, flexcan_noirq_resume) }; diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 19d4f52a8f90..a761092e6ac9 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1936,7 +1936,6 @@ static int ican3_probe(struct platform_device *pdev) /* find our IRQ number */ mod->irq = platform_get_irq(pdev, 0); if (mod->irq < 0) { - dev_err(dev, "IRQ line not found\n"); ret = -ENODEV; goto out_free_ndev; } diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c new file mode 100644 index 000000000000..f9815fda8840 --- /dev/null +++ b/drivers/net/can/kvaser_pciefd.c @@ -0,0 +1,1907 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause +/* Copyright (C) 2018 KVASER AB, Sweden. All rights reserved. + * Parts of this driver are based on the following: + * - Kvaser linux pciefd driver (version 5.25) + * - PEAK linux canfd driver + * - Altera Avalon EPCS flash controller driver + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/pci.h> +#include <linux/can/dev.h> +#include <linux/timer.h> +#include <linux/netdevice.h> +#include <linux/crc32.h> +#include <linux/iopoll.h> + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Kvaser AB <support@kvaser.com>"); +MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); + +#define KVASER_PCIEFD_DRV_NAME "kvaser_pciefd" + +#define KVASER_PCIEFD_WAIT_TIMEOUT msecs_to_jiffies(1000) +#define KVASER_PCIEFD_BEC_POLL_FREQ (jiffies + msecs_to_jiffies(200)) +#define KVASER_PCIEFD_MAX_ERR_REP 256 +#define KVASER_PCIEFD_CAN_TX_MAX_COUNT 17 +#define KVASER_PCIEFD_MAX_CAN_CHANNELS 4 +#define KVASER_PCIEFD_DMA_COUNT 2 + +#define KVASER_PCIEFD_DMA_SIZE (4 * 1024) +#define KVASER_PCIEFD_64BIT_DMA_BIT BIT(0) + +#define KVASER_PCIEFD_VENDOR 0x1a07 +#define KVASER_PCIEFD_4HS_ID 0x0d +#define KVASER_PCIEFD_2HS_ID 0x0e +#define KVASER_PCIEFD_HS_ID 0x0f +#define KVASER_PCIEFD_MINIPCIE_HS_ID 0x10 +#define KVASER_PCIEFD_MINIPCIE_2HS_ID 0x11 + +/* PCIe IRQ registers */ +#define KVASER_PCIEFD_IRQ_REG 0x40 +#define KVASER_PCIEFD_IEN_REG 0x50 +/* DMA map */ +#define KVASER_PCIEFD_DMA_MAP_BASE 0x1000 +/* Kvaser KCAN CAN controller registers */ +#define KVASER_PCIEFD_KCAN0_BASE 0x10000 +#define KVASER_PCIEFD_KCAN_BASE_OFFSET 0x1000 +#define KVASER_PCIEFD_KCAN_FIFO_REG 0x100 +#define KVASER_PCIEFD_KCAN_FIFO_LAST_REG 0x180 +#define KVASER_PCIEFD_KCAN_CTRL_REG 0x2c0 +#define KVASER_PCIEFD_KCAN_CMD_REG 0x400 +#define KVASER_PCIEFD_KCAN_IEN_REG 0x408 +#define KVASER_PCIEFD_KCAN_IRQ_REG 0x410 +#define KVASER_PCIEFD_KCAN_TX_NPACKETS_REG 0x414 +#define KVASER_PCIEFD_KCAN_STAT_REG 0x418 +#define KVASER_PCIEFD_KCAN_MODE_REG 0x41c +#define KVASER_PCIEFD_KCAN_BTRN_REG 0x420 +#define KVASER_PCIEFD_KCAN_BTRD_REG 0x428 +#define KVASER_PCIEFD_KCAN_PWM_REG 0x430 +/* Loopback control register */ +#define KVASER_PCIEFD_LOOP_REG 0x1f000 +/* System identification and information registers */ +#define KVASER_PCIEFD_SYSID_BASE 0x1f020 +#define KVASER_PCIEFD_SYSID_VERSION_REG (KVASER_PCIEFD_SYSID_BASE + 0x8) +#define KVASER_PCIEFD_SYSID_CANFREQ_REG (KVASER_PCIEFD_SYSID_BASE + 0xc) +#define KVASER_PCIEFD_SYSID_BUILD_REG (KVASER_PCIEFD_SYSID_BASE + 0x14) +/* Shared receive buffer registers */ +#define KVASER_PCIEFD_SRB_BASE 0x1f200 +#define KVASER_PCIEFD_SRB_CMD_REG (KVASER_PCIEFD_SRB_BASE + 0x200) +#define KVASER_PCIEFD_SRB_IEN_REG (KVASER_PCIEFD_SRB_BASE + 0x204) +#define KVASER_PCIEFD_SRB_IRQ_REG (KVASER_PCIEFD_SRB_BASE + 0x20c) +#define KVASER_PCIEFD_SRB_STAT_REG (KVASER_PCIEFD_SRB_BASE + 0x210) +#define KVASER_PCIEFD_SRB_CTRL_REG (KVASER_PCIEFD_SRB_BASE + 0x218) +/* EPCS flash controller registers */ +#define KVASER_PCIEFD_SPI_BASE 0x1fc00 +#define KVASER_PCIEFD_SPI_RX_REG KVASER_PCIEFD_SPI_BASE +#define KVASER_PCIEFD_SPI_TX_REG (KVASER_PCIEFD_SPI_BASE + 0x4) +#define KVASER_PCIEFD_SPI_STATUS_REG (KVASER_PCIEFD_SPI_BASE + 0x8) +#define KVASER_PCIEFD_SPI_CTRL_REG (KVASER_PCIEFD_SPI_BASE + 0xc) +#define KVASER_PCIEFD_SPI_SSEL_REG (KVASER_PCIEFD_SPI_BASE + 0x14) + +#define KVASER_PCIEFD_IRQ_ALL_MSK 0x1f +#define KVASER_PCIEFD_IRQ_SRB BIT(4) + +#define KVASER_PCIEFD_SYSID_NRCHAN_SHIFT 24 +#define KVASER_PCIEFD_SYSID_MAJOR_VER_SHIFT 16 +#define KVASER_PCIEFD_SYSID_BUILD_VER_SHIFT 1 + +/* Reset DMA buffer 0, 1 and FIFO offset */ +#define KVASER_PCIEFD_SRB_CMD_RDB0 BIT(4) +#define KVASER_PCIEFD_SRB_CMD_RDB1 BIT(5) +#define KVASER_PCIEFD_SRB_CMD_FOR BIT(0) + +/* DMA packet done, buffer 0 and 1 */ +#define KVASER_PCIEFD_SRB_IRQ_DPD0 BIT(8) +#define KVASER_PCIEFD_SRB_IRQ_DPD1 BIT(9) +/* DMA overflow, buffer 0 and 1 */ +#define KVASER_PCIEFD_SRB_IRQ_DOF0 BIT(10) +#define KVASER_PCIEFD_SRB_IRQ_DOF1 BIT(11) +/* DMA underflow, buffer 0 and 1 */ +#define KVASER_PCIEFD_SRB_IRQ_DUF0 BIT(12) +#define KVASER_PCIEFD_SRB_IRQ_DUF1 BIT(13) + +/* DMA idle */ +#define KVASER_PCIEFD_SRB_STAT_DI BIT(15) +/* DMA support */ +#define KVASER_PCIEFD_SRB_STAT_DMA BIT(24) + +/* DMA Enable */ +#define KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE BIT(0) + +/* EPCS flash controller definitions */ +#define KVASER_PCIEFD_CFG_IMG_SZ (64 * 1024) +#define KVASER_PCIEFD_CFG_IMG_OFFSET (31 * 65536L) +#define KVASER_PCIEFD_CFG_MAX_PARAMS 256 +#define KVASER_PCIEFD_CFG_MAGIC 0xcafef00d +#define KVASER_PCIEFD_CFG_PARAM_MAX_SZ 24 +#define KVASER_PCIEFD_CFG_SYS_VER 1 +#define KVASER_PCIEFD_CFG_PARAM_NR_CHAN 130 +#define KVASER_PCIEFD_SPI_TMT BIT(5) +#define KVASER_PCIEFD_SPI_TRDY BIT(6) +#define KVASER_PCIEFD_SPI_RRDY BIT(7) +#define KVASER_PCIEFD_FLASH_ID_EPCS16 0x14 +/* Commands for controlling the onboard flash */ +#define KVASER_PCIEFD_FLASH_RES_CMD 0xab +#define KVASER_PCIEFD_FLASH_READ_CMD 0x3 +#define KVASER_PCIEFD_FLASH_STATUS_CMD 0x5 + +/* Kvaser KCAN definitions */ +#define KVASER_PCIEFD_KCAN_CTRL_EFLUSH (4 << 29) +#define KVASER_PCIEFD_KCAN_CTRL_EFRAME (5 << 29) + +#define KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT 16 +/* Request status packet */ +#define KVASER_PCIEFD_KCAN_CMD_SRQ BIT(0) +/* Abort, flush and reset */ +#define KVASER_PCIEFD_KCAN_CMD_AT BIT(1) + +/* Tx FIFO unaligned read */ +#define KVASER_PCIEFD_KCAN_IRQ_TAR BIT(0) +/* Tx FIFO unaligned end */ +#define KVASER_PCIEFD_KCAN_IRQ_TAE BIT(1) +/* Bus parameter protection error */ +#define KVASER_PCIEFD_KCAN_IRQ_BPP BIT(2) +/* FDF bit when controller is in classic mode */ +#define KVASER_PCIEFD_KCAN_IRQ_FDIC BIT(3) +/* Rx FIFO overflow */ +#define KVASER_PCIEFD_KCAN_IRQ_ROF BIT(5) +/* Abort done */ +#define KVASER_PCIEFD_KCAN_IRQ_ABD BIT(13) +/* Tx buffer flush done */ +#define KVASER_PCIEFD_KCAN_IRQ_TFD BIT(14) +/* Tx FIFO overflow */ +#define KVASER_PCIEFD_KCAN_IRQ_TOF BIT(15) +/* Tx FIFO empty */ +#define KVASER_PCIEFD_KCAN_IRQ_TE BIT(16) +/* Transmitter unaligned */ +#define KVASER_PCIEFD_KCAN_IRQ_TAL BIT(17) + +#define KVASER_PCIEFD_KCAN_TX_NPACKETS_MAX_SHIFT 16 + +#define KVASER_PCIEFD_KCAN_STAT_SEQNO_SHIFT 24 +/* Abort request */ +#define KVASER_PCIEFD_KCAN_STAT_AR BIT(7) +/* Idle state. Controller in reset mode and no abort or flush pending */ +#define KVASER_PCIEFD_KCAN_STAT_IDLE BIT(10) +/* Bus off */ +#define KVASER_PCIEFD_KCAN_STAT_BOFF BIT(11) +/* Reset mode request */ +#define KVASER_PCIEFD_KCAN_STAT_RMR BIT(14) +/* Controller in reset mode */ +#define KVASER_PCIEFD_KCAN_STAT_IRM BIT(15) +/* Controller got one-shot capability */ +#define KVASER_PCIEFD_KCAN_STAT_CAP BIT(16) +/* Controller got CAN FD capability */ +#define KVASER_PCIEFD_KCAN_STAT_FD BIT(19) +#define KVASER_PCIEFD_KCAN_STAT_BUS_OFF_MSK (KVASER_PCIEFD_KCAN_STAT_AR | \ + KVASER_PCIEFD_KCAN_STAT_BOFF | KVASER_PCIEFD_KCAN_STAT_RMR | \ + KVASER_PCIEFD_KCAN_STAT_IRM) + +/* Reset mode */ +#define KVASER_PCIEFD_KCAN_MODE_RM BIT(8) +/* Listen only mode */ +#define KVASER_PCIEFD_KCAN_MODE_LOM BIT(9) +/* Error packet enable */ +#define KVASER_PCIEFD_KCAN_MODE_EPEN BIT(12) +/* CAN FD non-ISO */ +#define KVASER_PCIEFD_KCAN_MODE_NIFDEN BIT(15) +/* Acknowledgment packet type */ +#define KVASER_PCIEFD_KCAN_MODE_APT BIT(20) +/* Active error flag enable. Clear to force error passive */ +#define KVASER_PCIEFD_KCAN_MODE_EEN BIT(23) +/* Classic CAN mode */ +#define KVASER_PCIEFD_KCAN_MODE_CCM BIT(31) + +#define KVASER_PCIEFD_KCAN_BTRN_SJW_SHIFT 13 +#define KVASER_PCIEFD_KCAN_BTRN_TSEG1_SHIFT 17 +#define KVASER_PCIEFD_KCAN_BTRN_TSEG2_SHIFT 26 + +#define KVASER_PCIEFD_KCAN_PWM_TOP_SHIFT 16 + +/* Kvaser KCAN packet types */ +#define KVASER_PCIEFD_PACK_TYPE_DATA 0 +#define KVASER_PCIEFD_PACK_TYPE_ACK 1 +#define KVASER_PCIEFD_PACK_TYPE_TXRQ 2 +#define KVASER_PCIEFD_PACK_TYPE_ERROR 3 +#define KVASER_PCIEFD_PACK_TYPE_EFLUSH_ACK 4 +#define KVASER_PCIEFD_PACK_TYPE_EFRAME_ACK 5 +#define KVASER_PCIEFD_PACK_TYPE_ACK_DATA 6 +#define KVASER_PCIEFD_PACK_TYPE_STATUS 8 +#define KVASER_PCIEFD_PACK_TYPE_BUS_LOAD 9 + +/* Kvaser KCAN packet common definitions */ +#define KVASER_PCIEFD_PACKET_SEQ_MSK 0xff +#define KVASER_PCIEFD_PACKET_CHID_SHIFT 25 +#define KVASER_PCIEFD_PACKET_TYPE_SHIFT 28 + +/* Kvaser KCAN TDATA and RDATA first word */ +#define KVASER_PCIEFD_RPACKET_IDE BIT(30) +#define KVASER_PCIEFD_RPACKET_RTR BIT(29) +/* Kvaser KCAN TDATA and RDATA second word */ +#define KVASER_PCIEFD_RPACKET_ESI BIT(13) +#define KVASER_PCIEFD_RPACKET_BRS BIT(14) +#define KVASER_PCIEFD_RPACKET_FDF BIT(15) +#define KVASER_PCIEFD_RPACKET_DLC_SHIFT 8 +/* Kvaser KCAN TDATA second word */ +#define KVASER_PCIEFD_TPACKET_SMS BIT(16) +#define KVASER_PCIEFD_TPACKET_AREQ BIT(31) + +/* Kvaser KCAN APACKET */ +#define KVASER_PCIEFD_APACKET_FLU BIT(8) +#define KVASER_PCIEFD_APACKET_CT BIT(9) +#define KVASER_PCIEFD_APACKET_ABL BIT(10) +#define KVASER_PCIEFD_APACKET_NACK BIT(11) + +/* Kvaser KCAN SPACK first word */ +#define KVASER_PCIEFD_SPACK_RXERR_SHIFT 8 +#define KVASER_PCIEFD_SPACK_BOFF BIT(16) +#define KVASER_PCIEFD_SPACK_IDET BIT(20) +#define KVASER_PCIEFD_SPACK_IRM BIT(21) +#define KVASER_PCIEFD_SPACK_RMCD BIT(22) +/* Kvaser KCAN SPACK second word */ +#define KVASER_PCIEFD_SPACK_AUTO BIT(21) +#define KVASER_PCIEFD_SPACK_EWLR BIT(23) +#define KVASER_PCIEFD_SPACK_EPLR BIT(24) + +struct kvaser_pciefd; + +struct kvaser_pciefd_can { + struct can_priv can; + struct kvaser_pciefd *kv_pcie; + void __iomem *reg_base; + struct can_berr_counter bec; + u8 cmd_seq; + int err_rep_cnt; + int echo_idx; + spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */ + spinlock_t echo_lock; /* Locks the message echo buffer */ + struct timer_list bec_poll_timer; + struct completion start_comp, flush_comp; +}; + +struct kvaser_pciefd { + struct pci_dev *pci; + void __iomem *reg_base; + struct kvaser_pciefd_can *can[KVASER_PCIEFD_MAX_CAN_CHANNELS]; + void *dma_data[KVASER_PCIEFD_DMA_COUNT]; + u8 nr_channels; + u32 freq; + u32 freq_to_ticks_div; +}; + +struct kvaser_pciefd_rx_packet { + u32 header[2]; + u64 timestamp; +}; + +struct kvaser_pciefd_tx_packet { + u32 header[2]; + u8 data[64]; +}; + +static const struct can_bittiming_const kvaser_pciefd_bittiming_const = { + .name = KVASER_PCIEFD_DRV_NAME, + .tseg1_min = 1, + .tseg1_max = 255, + .tseg2_min = 1, + .tseg2_max = 32, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 4096, + .brp_inc = 1, +}; + +struct kvaser_pciefd_cfg_param { + __le32 magic; + __le32 nr; + __le32 len; + u8 data[KVASER_PCIEFD_CFG_PARAM_MAX_SZ]; +}; + +struct kvaser_pciefd_cfg_img { + __le32 version; + __le32 magic; + __le32 crc; + struct kvaser_pciefd_cfg_param params[KVASER_PCIEFD_CFG_MAX_PARAMS]; +}; + +static struct pci_device_id kvaser_pciefd_id_table[] = { + { PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_4HS_ID), }, + { PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_2HS_ID), }, + { PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_HS_ID), }, + { PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_MINIPCIE_HS_ID), }, + { PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_MINIPCIE_2HS_ID), }, + { 0,}, +}; +MODULE_DEVICE_TABLE(pci, kvaser_pciefd_id_table); + +/* Onboard flash memory functions */ +static int kvaser_pciefd_spi_wait_loop(struct kvaser_pciefd *pcie, int msk) +{ + u32 res; + int ret; + + ret = readl_poll_timeout(pcie->reg_base + KVASER_PCIEFD_SPI_STATUS_REG, + res, res & msk, 0, 10); + + return ret; +} + +static int kvaser_pciefd_spi_cmd(struct kvaser_pciefd *pcie, const u8 *tx, + u32 tx_len, u8 *rx, u32 rx_len) +{ + int c; + + iowrite32(BIT(0), pcie->reg_base + KVASER_PCIEFD_SPI_SSEL_REG); + iowrite32(BIT(10), pcie->reg_base + KVASER_PCIEFD_SPI_CTRL_REG); + ioread32(pcie->reg_base + KVASER_PCIEFD_SPI_RX_REG); + + c = tx_len; + while (c--) { + if (kvaser_pciefd_spi_wait_loop(pcie, KVASER_PCIEFD_SPI_TRDY)) + return -EIO; + + iowrite32(*tx++, pcie->reg_base + KVASER_PCIEFD_SPI_TX_REG); + + if (kvaser_pciefd_spi_wait_loop(pcie, KVASER_PCIEFD_SPI_RRDY)) + return -EIO; + + ioread32(pcie->reg_base + KVASER_PCIEFD_SPI_RX_REG); + } + + c = rx_len; + while (c-- > 0) { + if (kvaser_pciefd_spi_wait_loop(pcie, KVASER_PCIEFD_SPI_TRDY)) + return -EIO; + + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SPI_TX_REG); + + if (kvaser_pciefd_spi_wait_loop(pcie, KVASER_PCIEFD_SPI_RRDY)) + return -EIO; + + *rx++ = ioread32(pcie->reg_base + KVASER_PCIEFD_SPI_RX_REG); + } + + if (kvaser_pciefd_spi_wait_loop(pcie, KVASER_PCIEFD_SPI_TMT)) + return -EIO; + + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SPI_CTRL_REG); + + if (c != -1) { + dev_err(&pcie->pci->dev, "Flash SPI transfer failed\n"); + return -EIO; + } + + return 0; +} + +static int kvaser_pciefd_cfg_read_and_verify(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_cfg_img *img) +{ + int offset = KVASER_PCIEFD_CFG_IMG_OFFSET; + int res, crc; + u8 *crc_buff; + + u8 cmd[] = { + KVASER_PCIEFD_FLASH_READ_CMD, + (u8)((offset >> 16) & 0xff), + (u8)((offset >> 8) & 0xff), + (u8)(offset & 0xff) + }; + + res = kvaser_pciefd_spi_cmd(pcie, cmd, ARRAY_SIZE(cmd), (u8 *)img, + KVASER_PCIEFD_CFG_IMG_SZ); + if (res) + return res; + + crc_buff = (u8 *)img->params; + + if (le32_to_cpu(img->version) != KVASER_PCIEFD_CFG_SYS_VER) { + dev_err(&pcie->pci->dev, + "Config flash corrupted, version number is wrong\n"); + return -ENODEV; + } + + if (le32_to_cpu(img->magic) != KVASER_PCIEFD_CFG_MAGIC) { + dev_err(&pcie->pci->dev, + "Config flash corrupted, magic number is wrong\n"); + return -ENODEV; + } + + crc = ~crc32_be(0xffffffff, crc_buff, sizeof(img->params)); + if (le32_to_cpu(img->crc) != crc) { + dev_err(&pcie->pci->dev, + "Stored CRC does not match flash image contents\n"); + return -EIO; + } + + return 0; +} + +static void kvaser_pciefd_cfg_read_params(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_cfg_img *img) +{ + struct kvaser_pciefd_cfg_param *param; + + param = &img->params[KVASER_PCIEFD_CFG_PARAM_NR_CHAN]; + memcpy(&pcie->nr_channels, param->data, le32_to_cpu(param->len)); +} + +static int kvaser_pciefd_read_cfg(struct kvaser_pciefd *pcie) +{ + int res; + struct kvaser_pciefd_cfg_img *img; + + /* Read electronic signature */ + u8 cmd[] = {KVASER_PCIEFD_FLASH_RES_CMD, 0, 0, 0}; + + res = kvaser_pciefd_spi_cmd(pcie, cmd, ARRAY_SIZE(cmd), cmd, 1); + if (res) + return -EIO; + + img = kmalloc(KVASER_PCIEFD_CFG_IMG_SZ, GFP_KERNEL); + if (!img) + return -ENOMEM; + + if (cmd[0] != KVASER_PCIEFD_FLASH_ID_EPCS16) { + dev_err(&pcie->pci->dev, + "Flash id is 0x%x instead of expected EPCS16 (0x%x)\n", + cmd[0], KVASER_PCIEFD_FLASH_ID_EPCS16); + + res = -ENODEV; + goto image_free; + } + + cmd[0] = KVASER_PCIEFD_FLASH_STATUS_CMD; + res = kvaser_pciefd_spi_cmd(pcie, cmd, 1, cmd, 1); + if (res) { + goto image_free; + } else if (cmd[0] & 1) { + res = -EIO; + /* No write is ever done, the WIP should never be set */ + dev_err(&pcie->pci->dev, "Unexpected WIP bit set in flash\n"); + goto image_free; + } + + res = kvaser_pciefd_cfg_read_and_verify(pcie, img); + if (res) { + res = -EIO; + goto image_free; + } + + kvaser_pciefd_cfg_read_params(pcie, img); + +image_free: + kfree(img); + return res; +} + +static void kvaser_pciefd_request_status(struct kvaser_pciefd_can *can) +{ + u32 cmd; + + cmd = KVASER_PCIEFD_KCAN_CMD_SRQ; + cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; + iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); +} + +static void kvaser_pciefd_enable_err_gen(struct kvaser_pciefd_can *can) +{ + u32 mode; + unsigned long irq; + + spin_lock_irqsave(&can->lock, irq); + mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + if (!(mode & KVASER_PCIEFD_KCAN_MODE_EPEN)) { + mode |= KVASER_PCIEFD_KCAN_MODE_EPEN; + iowrite32(mode, can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + } + spin_unlock_irqrestore(&can->lock, irq); +} + +static void kvaser_pciefd_disable_err_gen(struct kvaser_pciefd_can *can) +{ + u32 mode; + unsigned long irq; + + spin_lock_irqsave(&can->lock, irq); + mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + mode &= ~KVASER_PCIEFD_KCAN_MODE_EPEN; + iowrite32(mode, can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + spin_unlock_irqrestore(&can->lock, irq); +} + +static int kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) +{ + u32 msk; + + msk = KVASER_PCIEFD_KCAN_IRQ_TE | KVASER_PCIEFD_KCAN_IRQ_ROF | + KVASER_PCIEFD_KCAN_IRQ_TOF | KVASER_PCIEFD_KCAN_IRQ_ABD | + KVASER_PCIEFD_KCAN_IRQ_TAE | KVASER_PCIEFD_KCAN_IRQ_TAL | + KVASER_PCIEFD_KCAN_IRQ_FDIC | KVASER_PCIEFD_KCAN_IRQ_BPP | + KVASER_PCIEFD_KCAN_IRQ_TAR | KVASER_PCIEFD_KCAN_IRQ_TFD; + + iowrite32(msk, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + + return 0; +} + +static void kvaser_pciefd_setup_controller(struct kvaser_pciefd_can *can) +{ + u32 mode; + unsigned long irq; + + spin_lock_irqsave(&can->lock, irq); + + mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + if (can->can.ctrlmode & CAN_CTRLMODE_FD) { + mode &= ~KVASER_PCIEFD_KCAN_MODE_CCM; + if (can->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) + mode |= KVASER_PCIEFD_KCAN_MODE_NIFDEN; + else + mode &= ~KVASER_PCIEFD_KCAN_MODE_NIFDEN; + } else { + mode |= KVASER_PCIEFD_KCAN_MODE_CCM; + mode &= ~KVASER_PCIEFD_KCAN_MODE_NIFDEN; + } + + if (can->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + mode |= KVASER_PCIEFD_KCAN_MODE_LOM; + + mode |= KVASER_PCIEFD_KCAN_MODE_EEN; + mode |= KVASER_PCIEFD_KCAN_MODE_EPEN; + /* Use ACK packet type */ + mode &= ~KVASER_PCIEFD_KCAN_MODE_APT; + mode &= ~KVASER_PCIEFD_KCAN_MODE_RM; + iowrite32(mode, can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + + spin_unlock_irqrestore(&can->lock, irq); +} + +static void kvaser_pciefd_start_controller_flush(struct kvaser_pciefd_can *can) +{ + u32 status; + unsigned long irq; + + spin_lock_irqsave(&can->lock, irq); + iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + + status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); + if (status & KVASER_PCIEFD_KCAN_STAT_IDLE) { + u32 cmd; + + /* If controller is already idle, run abort, flush and reset */ + cmd = KVASER_PCIEFD_KCAN_CMD_AT; + cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; + iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); + } else if (!(status & KVASER_PCIEFD_KCAN_STAT_RMR)) { + u32 mode; + + /* Put controller in reset mode */ + mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + mode |= KVASER_PCIEFD_KCAN_MODE_RM; + iowrite32(mode, can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + } + + spin_unlock_irqrestore(&can->lock, irq); +} + +static int kvaser_pciefd_bus_on(struct kvaser_pciefd_can *can) +{ + u32 mode; + unsigned long irq; + + del_timer(&can->bec_poll_timer); + + if (!completion_done(&can->flush_comp)) + kvaser_pciefd_start_controller_flush(can); + + if (!wait_for_completion_timeout(&can->flush_comp, + KVASER_PCIEFD_WAIT_TIMEOUT)) { + netdev_err(can->can.dev, "Timeout during bus on flush\n"); + return -ETIMEDOUT; + } + + spin_lock_irqsave(&can->lock, irq); + iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); + + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + + mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + mode &= ~KVASER_PCIEFD_KCAN_MODE_RM; + iowrite32(mode, can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + spin_unlock_irqrestore(&can->lock, irq); + + if (!wait_for_completion_timeout(&can->start_comp, + KVASER_PCIEFD_WAIT_TIMEOUT)) { + netdev_err(can->can.dev, "Timeout during bus on reset\n"); + return -ETIMEDOUT; + } + /* Reset interrupt handling */ + iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); + + kvaser_pciefd_set_tx_irq(can); + kvaser_pciefd_setup_controller(can); + + can->can.state = CAN_STATE_ERROR_ACTIVE; + netif_wake_queue(can->can.dev); + can->bec.txerr = 0; + can->bec.rxerr = 0; + can->err_rep_cnt = 0; + + return 0; +} + +static void kvaser_pciefd_pwm_stop(struct kvaser_pciefd_can *can) +{ + u8 top; + u32 pwm_ctrl; + unsigned long irq; + + spin_lock_irqsave(&can->lock, irq); + pwm_ctrl = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_PWM_REG); + top = (pwm_ctrl >> KVASER_PCIEFD_KCAN_PWM_TOP_SHIFT) & 0xff; + + /* Set duty cycle to zero */ + pwm_ctrl |= top; + iowrite32(pwm_ctrl, can->reg_base + KVASER_PCIEFD_KCAN_PWM_REG); + spin_unlock_irqrestore(&can->lock, irq); +} + +static void kvaser_pciefd_pwm_start(struct kvaser_pciefd_can *can) +{ + int top, trigger; + u32 pwm_ctrl; + unsigned long irq; + + kvaser_pciefd_pwm_stop(can); + spin_lock_irqsave(&can->lock, irq); + + /* Set frequency to 500 KHz*/ + top = can->can.clock.freq / (2 * 500000) - 1; + + pwm_ctrl = top & 0xff; + pwm_ctrl |= (top & 0xff) << KVASER_PCIEFD_KCAN_PWM_TOP_SHIFT; + iowrite32(pwm_ctrl, can->reg_base + KVASER_PCIEFD_KCAN_PWM_REG); + + /* Set duty cycle to 95 */ + trigger = (100 * top - 95 * (top + 1) + 50) / 100; + pwm_ctrl = trigger & 0xff; + pwm_ctrl |= (top & 0xff) << KVASER_PCIEFD_KCAN_PWM_TOP_SHIFT; + iowrite32(pwm_ctrl, can->reg_base + KVASER_PCIEFD_KCAN_PWM_REG); + spin_unlock_irqrestore(&can->lock, irq); +} + +static int kvaser_pciefd_open(struct net_device *netdev) +{ + int err; + struct kvaser_pciefd_can *can = netdev_priv(netdev); + + err = open_candev(netdev); + if (err) + return err; + + err = kvaser_pciefd_bus_on(can); + if (err) + return err; + + return 0; +} + +static int kvaser_pciefd_stop(struct net_device *netdev) +{ + struct kvaser_pciefd_can *can = netdev_priv(netdev); + int ret = 0; + + /* Don't interrupt ongoing flush */ + if (!completion_done(&can->flush_comp)) + kvaser_pciefd_start_controller_flush(can); + + if (!wait_for_completion_timeout(&can->flush_comp, + KVASER_PCIEFD_WAIT_TIMEOUT)) { + netdev_err(can->can.dev, "Timeout during stop\n"); + ret = -ETIMEDOUT; + } else { + iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + del_timer(&can->bec_poll_timer); + } + close_candev(netdev); + + return ret; +} + +static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p, + struct kvaser_pciefd_can *can, + struct sk_buff *skb) +{ + struct canfd_frame *cf = (struct canfd_frame *)skb->data; + int packet_size; + int seq = can->echo_idx; + + memset(p, 0, sizeof(*p)); + + if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + p->header[1] |= KVASER_PCIEFD_TPACKET_SMS; + + if (cf->can_id & CAN_RTR_FLAG) + p->header[0] |= KVASER_PCIEFD_RPACKET_RTR; + + if (cf->can_id & CAN_EFF_FLAG) + 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] |= KVASER_PCIEFD_TPACKET_AREQ; + + if (can_is_canfd_skb(skb)) { + p->header[1] |= KVASER_PCIEFD_RPACKET_FDF; + if (cf->flags & CANFD_BRS) + p->header[1] |= KVASER_PCIEFD_RPACKET_BRS; + if (cf->flags & CANFD_ESI) + p->header[1] |= KVASER_PCIEFD_RPACKET_ESI; + } + + p->header[1] |= seq & KVASER_PCIEFD_PACKET_SEQ_MSK; + + packet_size = cf->len; + memcpy(p->data, cf->data, packet_size); + + return DIV_ROUND_UP(packet_size, 4); +} + +static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct kvaser_pciefd_can *can = netdev_priv(netdev); + unsigned long irq_flags; + struct kvaser_pciefd_tx_packet packet; + int nwords; + u8 count; + + if (can_dropped_invalid_skb(netdev, skb)) + return NETDEV_TX_OK; + + nwords = kvaser_pciefd_prepare_tx_packet(&packet, can, skb); + + spin_lock_irqsave(&can->echo_lock, irq_flags); + + /* Prepare and save echo skb in internal slot */ + can_put_echo_skb(skb, netdev, can->echo_idx); + + /* Move echo index to the next slot */ + can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max; + + /* Write header to fifo */ + iowrite32(packet.header[0], + can->reg_base + KVASER_PCIEFD_KCAN_FIFO_REG); + iowrite32(packet.header[1], + can->reg_base + KVASER_PCIEFD_KCAN_FIFO_REG); + + if (nwords) { + u32 data_last = ((u32 *)packet.data)[nwords - 1]; + + /* Write data to fifo, except last word */ + iowrite32_rep(can->reg_base + + KVASER_PCIEFD_KCAN_FIFO_REG, packet.data, + nwords - 1); + /* Write last word to end of fifo */ + __raw_writel(data_last, can->reg_base + + KVASER_PCIEFD_KCAN_FIFO_LAST_REG); + } else { + /* Complete write to fifo */ + __raw_writel(0, can->reg_base + + KVASER_PCIEFD_KCAN_FIFO_LAST_REG); + } + + count = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG); + /* No room for a new message, stop the queue until at least one + * successful transmit + */ + if (count >= KVASER_PCIEFD_CAN_TX_MAX_COUNT || + can->can.echo_skb[can->echo_idx]) + netif_stop_queue(netdev); + + spin_unlock_irqrestore(&can->echo_lock, irq_flags); + + return NETDEV_TX_OK; +} + +static int kvaser_pciefd_set_bittiming(struct kvaser_pciefd_can *can, bool data) +{ + u32 mode, test, btrn; + unsigned long irq_flags; + int ret; + struct can_bittiming *bt; + + if (data) + bt = &can->can.data_bittiming; + else + bt = &can->can.bittiming; + + btrn = ((bt->phase_seg2 - 1) & 0x1f) << + KVASER_PCIEFD_KCAN_BTRN_TSEG2_SHIFT | + (((bt->prop_seg + bt->phase_seg1) - 1) & 0x1ff) << + KVASER_PCIEFD_KCAN_BTRN_TSEG1_SHIFT | + ((bt->sjw - 1) & 0xf) << KVASER_PCIEFD_KCAN_BTRN_SJW_SHIFT | + ((bt->brp - 1) & 0x1fff); + + spin_lock_irqsave(&can->lock, irq_flags); + mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + + /* Put the circuit in reset mode */ + iowrite32(mode | KVASER_PCIEFD_KCAN_MODE_RM, + can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + + /* Can only set bittiming if in reset mode */ + ret = readl_poll_timeout(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG, + test, test & KVASER_PCIEFD_KCAN_MODE_RM, + 0, 10); + + if (ret) { + spin_unlock_irqrestore(&can->lock, irq_flags); + return -EBUSY; + } + + if (data) + iowrite32(btrn, can->reg_base + KVASER_PCIEFD_KCAN_BTRD_REG); + else + iowrite32(btrn, can->reg_base + KVASER_PCIEFD_KCAN_BTRN_REG); + + /* Restore previous reset mode status */ + iowrite32(mode, can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); + + spin_unlock_irqrestore(&can->lock, irq_flags); + return 0; +} + +static int kvaser_pciefd_set_nominal_bittiming(struct net_device *ndev) +{ + return kvaser_pciefd_set_bittiming(netdev_priv(ndev), false); +} + +static int kvaser_pciefd_set_data_bittiming(struct net_device *ndev) +{ + return kvaser_pciefd_set_bittiming(netdev_priv(ndev), true); +} + +static int kvaser_pciefd_set_mode(struct net_device *ndev, enum can_mode mode) +{ + struct kvaser_pciefd_can *can = netdev_priv(ndev); + int ret = 0; + + switch (mode) { + case CAN_MODE_START: + if (!can->can.restart_ms) + ret = kvaser_pciefd_bus_on(can); + break; + default: + return -EOPNOTSUPP; + } + + return ret; +} + +static int kvaser_pciefd_get_berr_counter(const struct net_device *ndev, + struct can_berr_counter *bec) +{ + struct kvaser_pciefd_can *can = netdev_priv(ndev); + + bec->rxerr = can->bec.rxerr; + bec->txerr = can->bec.txerr; + return 0; +} + +static void kvaser_pciefd_bec_poll_timer(struct timer_list *data) +{ + struct kvaser_pciefd_can *can = from_timer(can, data, bec_poll_timer); + + kvaser_pciefd_enable_err_gen(can); + kvaser_pciefd_request_status(can); + can->err_rep_cnt = 0; +} + +static const struct net_device_ops kvaser_pciefd_netdev_ops = { + .ndo_open = kvaser_pciefd_open, + .ndo_stop = kvaser_pciefd_stop, + .ndo_start_xmit = kvaser_pciefd_start_xmit, + .ndo_change_mtu = can_change_mtu, +}; + +static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) +{ + int i; + + for (i = 0; i < pcie->nr_channels; i++) { + struct net_device *netdev; + struct kvaser_pciefd_can *can; + u32 status, tx_npackets; + + netdev = alloc_candev(sizeof(struct kvaser_pciefd_can), + KVASER_PCIEFD_CAN_TX_MAX_COUNT); + if (!netdev) + return -ENOMEM; + + can = netdev_priv(netdev); + netdev->netdev_ops = &kvaser_pciefd_netdev_ops; + can->reg_base = pcie->reg_base + KVASER_PCIEFD_KCAN0_BASE + + i * KVASER_PCIEFD_KCAN_BASE_OFFSET; + + can->kv_pcie = pcie; + can->cmd_seq = 0; + can->err_rep_cnt = 0; + can->bec.txerr = 0; + can->bec.rxerr = 0; + + init_completion(&can->start_comp); + init_completion(&can->flush_comp); + timer_setup(&can->bec_poll_timer, kvaser_pciefd_bec_poll_timer, + 0); + + tx_npackets = ioread32(can->reg_base + + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG); + if (((tx_npackets >> KVASER_PCIEFD_KCAN_TX_NPACKETS_MAX_SHIFT) & + 0xff) < KVASER_PCIEFD_CAN_TX_MAX_COUNT) { + dev_err(&pcie->pci->dev, + "Max Tx count is smaller than expected\n"); + + free_candev(netdev); + return -ENODEV; + } + + can->can.clock.freq = pcie->freq; + can->can.echo_skb_max = KVASER_PCIEFD_CAN_TX_MAX_COUNT; + can->echo_idx = 0; + spin_lock_init(&can->echo_lock); + spin_lock_init(&can->lock); + can->can.bittiming_const = &kvaser_pciefd_bittiming_const; + can->can.data_bittiming_const = &kvaser_pciefd_bittiming_const; + + can->can.do_set_bittiming = kvaser_pciefd_set_nominal_bittiming; + can->can.do_set_data_bittiming = + kvaser_pciefd_set_data_bittiming; + + can->can.do_set_mode = kvaser_pciefd_set_mode; + can->can.do_get_berr_counter = kvaser_pciefd_get_berr_counter; + + can->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY | + CAN_CTRLMODE_FD | + CAN_CTRLMODE_FD_NON_ISO; + + status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); + if (!(status & KVASER_PCIEFD_KCAN_STAT_FD)) { + dev_err(&pcie->pci->dev, + "CAN FD not supported as expected %d\n", i); + + free_candev(netdev); + return -ENODEV; + } + + if (status & KVASER_PCIEFD_KCAN_STAT_CAP) + can->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT; + + netdev->flags |= IFF_ECHO; + + SET_NETDEV_DEV(netdev, &pcie->pci->dev); + + iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | + KVASER_PCIEFD_KCAN_IRQ_TFD, + can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + + pcie->can[i] = can; + kvaser_pciefd_pwm_start(can); + } + + return 0; +} + +static int kvaser_pciefd_reg_candev(struct kvaser_pciefd *pcie) +{ + int i; + + for (i = 0; i < pcie->nr_channels; i++) { + int err = register_candev(pcie->can[i]->can.dev); + + if (err) { + int j; + + /* Unregister all successfully registered devices. */ + for (j = 0; j < i; j++) + unregister_candev(pcie->can[j]->can.dev); + return err; + } + } + + return 0; +} + +static void kvaser_pciefd_write_dma_map(struct kvaser_pciefd *pcie, + dma_addr_t addr, int offset) +{ + u32 word1, word2; + +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + word1 = addr | KVASER_PCIEFD_64BIT_DMA_BIT; + word2 = addr >> 32; +#else + word1 = addr; + word2 = 0; +#endif + iowrite32(word1, pcie->reg_base + offset); + iowrite32(word2, pcie->reg_base + offset + 4); +} + +static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) +{ + int i; + u32 srb_status; + dma_addr_t dma_addr[KVASER_PCIEFD_DMA_COUNT]; + + /* Disable the DMA */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG); + for (i = 0; i < KVASER_PCIEFD_DMA_COUNT; i++) { + unsigned int offset = KVASER_PCIEFD_DMA_MAP_BASE + 8 * i; + + pcie->dma_data[i] = + dmam_alloc_coherent(&pcie->pci->dev, + KVASER_PCIEFD_DMA_SIZE, + &dma_addr[i], + GFP_KERNEL); + + if (!pcie->dma_data[i] || !dma_addr[i]) { + dev_err(&pcie->pci->dev, "Rx dma_alloc(%u) failure\n", + KVASER_PCIEFD_DMA_SIZE); + return -ENOMEM; + } + + kvaser_pciefd_write_dma_map(pcie, dma_addr[i], offset); + } + + /* Reset Rx FIFO, and both DMA buffers */ + iowrite32(KVASER_PCIEFD_SRB_CMD_FOR | KVASER_PCIEFD_SRB_CMD_RDB0 | + KVASER_PCIEFD_SRB_CMD_RDB1, + pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + + srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG); + if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DI)) { + dev_err(&pcie->pci->dev, "DMA not idle before enabling\n"); + return -EIO; + } + + /* Enable the DMA */ + iowrite32(KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE, + pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG); + + return 0; +} + +static int kvaser_pciefd_setup_board(struct kvaser_pciefd *pcie) +{ + u32 sysid, srb_status, build; + u8 sysid_nr_chan; + int ret; + + ret = kvaser_pciefd_read_cfg(pcie); + if (ret) + return ret; + + sysid = ioread32(pcie->reg_base + KVASER_PCIEFD_SYSID_VERSION_REG); + sysid_nr_chan = (sysid >> KVASER_PCIEFD_SYSID_NRCHAN_SHIFT) & 0xff; + if (pcie->nr_channels != sysid_nr_chan) { + dev_err(&pcie->pci->dev, + "Number of channels does not match: %u vs %u\n", + pcie->nr_channels, + sysid_nr_chan); + return -ENODEV; + } + + if (pcie->nr_channels > KVASER_PCIEFD_MAX_CAN_CHANNELS) + pcie->nr_channels = KVASER_PCIEFD_MAX_CAN_CHANNELS; + + build = ioread32(pcie->reg_base + KVASER_PCIEFD_SYSID_BUILD_REG); + dev_dbg(&pcie->pci->dev, "Version %u.%u.%u\n", + (sysid >> KVASER_PCIEFD_SYSID_MAJOR_VER_SHIFT) & 0xff, + sysid & 0xff, + (build >> KVASER_PCIEFD_SYSID_BUILD_VER_SHIFT) & 0x7fff); + + srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG); + if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DMA)) { + dev_err(&pcie->pci->dev, + "Hardware without DMA is not supported\n"); + return -ENODEV; + } + + pcie->freq = ioread32(pcie->reg_base + KVASER_PCIEFD_SYSID_CANFREQ_REG); + pcie->freq_to_ticks_div = pcie->freq / 1000000; + if (pcie->freq_to_ticks_div == 0) + pcie->freq_to_ticks_div = 1; + + /* Turn off all loopback functionality */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_LOOP_REG); + return ret; +} + +static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_rx_packet *p, + __le32 *data) +{ + struct sk_buff *skb; + struct canfd_frame *cf; + struct can_priv *priv; + struct net_device_stats *stats; + struct skb_shared_hwtstamps *shhwtstamps; + u8 ch_id = (p->header[1] >> KVASER_PCIEFD_PACKET_CHID_SHIFT) & 0x7; + + if (ch_id >= pcie->nr_channels) + return -EIO; + + priv = &pcie->can[ch_id]->can; + stats = &priv->dev->stats; + + if (p->header[1] & KVASER_PCIEFD_RPACKET_FDF) { + skb = alloc_canfd_skb(priv->dev, &cf); + if (!skb) { + stats->rx_dropped++; + return -ENOMEM; + } + + if (p->header[1] & KVASER_PCIEFD_RPACKET_BRS) + cf->flags |= CANFD_BRS; + + if (p->header[1] & KVASER_PCIEFD_RPACKET_ESI) + cf->flags |= CANFD_ESI; + } else { + skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf); + if (!skb) { + stats->rx_dropped++; + return -ENOMEM; + } + } + + cf->can_id = p->header[0] & CAN_EFF_MASK; + 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); + + if (p->header[0] & KVASER_PCIEFD_RPACKET_RTR) + cf->can_id |= CAN_RTR_FLAG; + else + memcpy(cf->data, data, cf->len); + + shhwtstamps = skb_hwtstamps(skb); + + shhwtstamps->hwtstamp = + ns_to_ktime(div_u64(p->timestamp * 1000, + pcie->freq_to_ticks_div)); + + stats->rx_bytes += cf->len; + stats->rx_packets++; + + return netif_rx(skb); +} + +static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can, + struct can_frame *cf, + enum can_state new_state, + enum can_state tx_state, + enum can_state rx_state) +{ + can_change_state(can->can.dev, cf, tx_state, rx_state); + + if (new_state == CAN_STATE_BUS_OFF) { + struct net_device *ndev = can->can.dev; + unsigned long irq_flags; + + spin_lock_irqsave(&can->lock, irq_flags); + netif_stop_queue(can->can.dev); + spin_unlock_irqrestore(&can->lock, irq_flags); + + /* Prevent CAN controller from auto recover from bus off */ + if (!can->can.restart_ms) { + kvaser_pciefd_start_controller_flush(can); + can_bus_off(ndev); + } + } +} + +static void kvaser_pciefd_packet_to_state(struct kvaser_pciefd_rx_packet *p, + struct can_berr_counter *bec, + enum can_state *new_state, + enum can_state *tx_state, + enum can_state *rx_state) +{ + if (p->header[0] & KVASER_PCIEFD_SPACK_BOFF || + p->header[0] & KVASER_PCIEFD_SPACK_IRM) + *new_state = CAN_STATE_BUS_OFF; + else if (bec->txerr >= 255 || bec->rxerr >= 255) + *new_state = CAN_STATE_BUS_OFF; + else if (p->header[1] & KVASER_PCIEFD_SPACK_EPLR) + *new_state = CAN_STATE_ERROR_PASSIVE; + else if (bec->txerr >= 128 || bec->rxerr >= 128) + *new_state = CAN_STATE_ERROR_PASSIVE; + else if (p->header[1] & KVASER_PCIEFD_SPACK_EWLR) + *new_state = CAN_STATE_ERROR_WARNING; + else if (bec->txerr >= 96 || bec->rxerr >= 96) + *new_state = CAN_STATE_ERROR_WARNING; + else + *new_state = CAN_STATE_ERROR_ACTIVE; + + *tx_state = bec->txerr >= bec->rxerr ? *new_state : 0; + *rx_state = bec->txerr <= bec->rxerr ? *new_state : 0; +} + +static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, + struct kvaser_pciefd_rx_packet *p) +{ + struct can_berr_counter bec; + enum can_state old_state, new_state, tx_state, rx_state; + struct net_device *ndev = can->can.dev; + struct sk_buff *skb; + struct can_frame *cf = NULL; + struct skb_shared_hwtstamps *shhwtstamps; + struct net_device_stats *stats = &ndev->stats; + + old_state = can->can.state; + + bec.txerr = p->header[0] & 0xff; + bec.rxerr = (p->header[0] >> KVASER_PCIEFD_SPACK_RXERR_SHIFT) & 0xff; + + kvaser_pciefd_packet_to_state(p, &bec, &new_state, &tx_state, + &rx_state); + + skb = alloc_can_err_skb(ndev, &cf); + + if (new_state != old_state) { + kvaser_pciefd_change_state(can, cf, new_state, tx_state, + rx_state); + + if (old_state == CAN_STATE_BUS_OFF && + new_state == CAN_STATE_ERROR_ACTIVE && + can->can.restart_ms) { + can->can.can_stats.restarts++; + if (skb) + cf->can_id |= CAN_ERR_RESTARTED; + } + } + + can->err_rep_cnt++; + can->can.can_stats.bus_error++; + stats->rx_errors++; + + can->bec.txerr = bec.txerr; + can->bec.rxerr = bec.rxerr; + + if (!skb) { + stats->rx_dropped++; + return -ENOMEM; + } + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = + ns_to_ktime(div_u64(p->timestamp * 1000, + can->kv_pcie->freq_to_ticks_div)); + cf->can_id |= CAN_ERR_BUSERROR; + + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + + netif_rx(skb); + return 0; +} + +static int kvaser_pciefd_handle_error_packet(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_rx_packet *p) +{ + struct kvaser_pciefd_can *can; + u8 ch_id = (p->header[1] >> KVASER_PCIEFD_PACKET_CHID_SHIFT) & 0x7; + + if (ch_id >= pcie->nr_channels) + return -EIO; + + can = pcie->can[ch_id]; + + kvaser_pciefd_rx_error_frame(can, p); + if (can->err_rep_cnt >= KVASER_PCIEFD_MAX_ERR_REP) + /* Do not report more errors, until bec_poll_timer expires */ + kvaser_pciefd_disable_err_gen(can); + /* Start polling the error counters */ + mod_timer(&can->bec_poll_timer, KVASER_PCIEFD_BEC_POLL_FREQ); + return 0; +} + +static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can, + struct kvaser_pciefd_rx_packet *p) +{ + struct can_berr_counter bec; + enum can_state old_state, new_state, tx_state, rx_state; + + old_state = can->can.state; + + bec.txerr = p->header[0] & 0xff; + bec.rxerr = (p->header[0] >> KVASER_PCIEFD_SPACK_RXERR_SHIFT) & 0xff; + + kvaser_pciefd_packet_to_state(p, &bec, &new_state, &tx_state, + &rx_state); + + if (new_state != old_state) { + struct net_device *ndev = can->can.dev; + struct sk_buff *skb; + struct can_frame *cf; + struct skb_shared_hwtstamps *shhwtstamps; + + skb = alloc_can_err_skb(ndev, &cf); + if (!skb) { + struct net_device_stats *stats = &ndev->stats; + + stats->rx_dropped++; + return -ENOMEM; + } + + kvaser_pciefd_change_state(can, cf, new_state, tx_state, + rx_state); + + if (old_state == CAN_STATE_BUS_OFF && + new_state == CAN_STATE_ERROR_ACTIVE && + can->can.restart_ms) { + can->can.can_stats.restarts++; + cf->can_id |= CAN_ERR_RESTARTED; + } + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = + ns_to_ktime(div_u64(p->timestamp * 1000, + can->kv_pcie->freq_to_ticks_div)); + + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + + netif_rx(skb); + } + can->bec.txerr = bec.txerr; + can->bec.rxerr = bec.rxerr; + /* Check if we need to poll the error counters */ + if (bec.txerr || bec.rxerr) + mod_timer(&can->bec_poll_timer, KVASER_PCIEFD_BEC_POLL_FREQ); + + return 0; +} + +static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_rx_packet *p) +{ + struct kvaser_pciefd_can *can; + u8 cmdseq; + u32 status; + u8 ch_id = (p->header[1] >> KVASER_PCIEFD_PACKET_CHID_SHIFT) & 0x7; + + if (ch_id >= pcie->nr_channels) + return -EIO; + + can = pcie->can[ch_id]; + + status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); + cmdseq = (status >> KVASER_PCIEFD_KCAN_STAT_SEQNO_SHIFT) & 0xff; + + /* Reset done, start abort and flush */ + if (p->header[0] & KVASER_PCIEFD_SPACK_IRM && + p->header[0] & KVASER_PCIEFD_SPACK_RMCD && + p->header[1] & KVASER_PCIEFD_SPACK_AUTO && + cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK) && + status & KVASER_PCIEFD_KCAN_STAT_IDLE) { + u32 cmd; + + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, + can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); + cmd = KVASER_PCIEFD_KCAN_CMD_AT; + cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; + iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); + + iowrite32(KVASER_PCIEFD_KCAN_IRQ_TFD, + can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + } else if (p->header[0] & KVASER_PCIEFD_SPACK_IDET && + p->header[0] & KVASER_PCIEFD_SPACK_IRM && + cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK) && + status & KVASER_PCIEFD_KCAN_STAT_IDLE) { + /* Reset detected, send end of flush if no packet are in FIFO */ + u8 count = ioread32(can->reg_base + + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; + + if (!count) + iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, + can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); + } else if (!(p->header[1] & KVASER_PCIEFD_SPACK_AUTO) && + cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK)) { + /* Response to status request received */ + kvaser_pciefd_handle_status_resp(can, p); + if (can->can.state != CAN_STATE_BUS_OFF && + can->can.state != CAN_STATE_ERROR_ACTIVE) { + mod_timer(&can->bec_poll_timer, + KVASER_PCIEFD_BEC_POLL_FREQ); + } + } else if (p->header[0] & KVASER_PCIEFD_SPACK_RMCD && + !(status & KVASER_PCIEFD_KCAN_STAT_BUS_OFF_MSK)) { + /* Reset to bus on detected */ + if (!completion_done(&can->start_comp)) + complete(&can->start_comp); + } + + return 0; +} + +static int kvaser_pciefd_handle_eack_packet(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_rx_packet *p) +{ + struct kvaser_pciefd_can *can; + u8 ch_id = (p->header[1] >> KVASER_PCIEFD_PACKET_CHID_SHIFT) & 0x7; + + if (ch_id >= pcie->nr_channels) + return -EIO; + + can = pcie->can[ch_id]; + + /* If this is the last flushed packet, send end of flush */ + if (p->header[0] & KVASER_PCIEFD_APACKET_FLU) { + u8 count = ioread32(can->reg_base + + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; + + if (count == 0) + iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, + can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); + } else { + int echo_idx = p->header[0] & KVASER_PCIEFD_PACKET_SEQ_MSK; + int dlc = can_get_echo_skb(can->can.dev, echo_idx); + struct net_device_stats *stats = &can->can.dev->stats; + + stats->tx_bytes += dlc; + stats->tx_packets++; + + if (netif_queue_stopped(can->can.dev)) + netif_wake_queue(can->can.dev); + } + + return 0; +} + +static void kvaser_pciefd_handle_nack_packet(struct kvaser_pciefd_can *can, + struct kvaser_pciefd_rx_packet *p) +{ + struct sk_buff *skb; + struct net_device_stats *stats = &can->can.dev->stats; + struct can_frame *cf; + + skb = alloc_can_err_skb(can->can.dev, &cf); + + stats->tx_errors++; + if (p->header[0] & KVASER_PCIEFD_APACKET_ABL) { + if (skb) + cf->can_id |= CAN_ERR_LOSTARB; + can->can.can_stats.arbitration_lost++; + } else if (skb) { + cf->can_id |= CAN_ERR_ACK; + } + + if (skb) { + cf->can_id |= CAN_ERR_BUSERROR; + stats->rx_bytes += cf->can_dlc; + stats->rx_packets++; + netif_rx(skb); + } else { + stats->rx_dropped++; + netdev_warn(can->can.dev, "No memory left for err_skb\n"); + } +} + +static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_rx_packet *p) +{ + struct kvaser_pciefd_can *can; + bool one_shot_fail = false; + u8 ch_id = (p->header[1] >> KVASER_PCIEFD_PACKET_CHID_SHIFT) & 0x7; + + if (ch_id >= pcie->nr_channels) + return -EIO; + + can = pcie->can[ch_id]; + /* Ignore control packet ACK */ + if (p->header[0] & KVASER_PCIEFD_APACKET_CT) + return 0; + + if (p->header[0] & KVASER_PCIEFD_APACKET_NACK) { + kvaser_pciefd_handle_nack_packet(can, p); + one_shot_fail = true; + } + + if (p->header[0] & KVASER_PCIEFD_APACKET_FLU) { + netdev_dbg(can->can.dev, "Packet was flushed\n"); + } else { + int echo_idx = p->header[0] & KVASER_PCIEFD_PACKET_SEQ_MSK; + int dlc = can_get_echo_skb(can->can.dev, echo_idx); + u8 count = ioread32(can->reg_base + + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; + + if (count < KVASER_PCIEFD_CAN_TX_MAX_COUNT && + netif_queue_stopped(can->can.dev)) + netif_wake_queue(can->can.dev); + + if (!one_shot_fail) { + struct net_device_stats *stats = &can->can.dev->stats; + + stats->tx_bytes += dlc; + stats->tx_packets++; + } + } + + return 0; +} + +static int kvaser_pciefd_handle_eflush_packet(struct kvaser_pciefd *pcie, + struct kvaser_pciefd_rx_packet *p) +{ + struct kvaser_pciefd_can *can; + u8 ch_id = (p->header[1] >> KVASER_PCIEFD_PACKET_CHID_SHIFT) & 0x7; + + if (ch_id >= pcie->nr_channels) + return -EIO; + + can = pcie->can[ch_id]; + + if (!completion_done(&can->flush_comp)) + complete(&can->flush_comp); + + return 0; +} + +static int kvaser_pciefd_read_packet(struct kvaser_pciefd *pcie, int *start_pos, + int dma_buf) +{ + __le32 *buffer = pcie->dma_data[dma_buf]; + __le64 timestamp; + struct kvaser_pciefd_rx_packet packet; + struct kvaser_pciefd_rx_packet *p = &packet; + u8 type; + int pos = *start_pos; + int size; + int ret = 0; + + size = le32_to_cpu(buffer[pos++]); + if (!size) { + *start_pos = 0; + return 0; + } + + p->header[0] = le32_to_cpu(buffer[pos++]); + p->header[1] = le32_to_cpu(buffer[pos++]); + + /* Read 64-bit timestamp */ + memcpy(×tamp, &buffer[pos], sizeof(__le64)); + pos += 2; + p->timestamp = le64_to_cpu(timestamp); + + type = (p->header[1] >> KVASER_PCIEFD_PACKET_TYPE_SHIFT) & 0xf; + switch (type) { + case KVASER_PCIEFD_PACK_TYPE_DATA: + ret = kvaser_pciefd_handle_data_packet(pcie, p, &buffer[pos]); + if (!(p->header[0] & KVASER_PCIEFD_RPACKET_RTR)) { + u8 data_len; + + data_len = can_dlc2len(p->header[1] >> + KVASER_PCIEFD_RPACKET_DLC_SHIFT); + pos += DIV_ROUND_UP(data_len, 4); + } + break; + + case KVASER_PCIEFD_PACK_TYPE_ACK: + ret = kvaser_pciefd_handle_ack_packet(pcie, p); + break; + + case KVASER_PCIEFD_PACK_TYPE_STATUS: + ret = kvaser_pciefd_handle_status_packet(pcie, p); + break; + + case KVASER_PCIEFD_PACK_TYPE_ERROR: + ret = kvaser_pciefd_handle_error_packet(pcie, p); + break; + + case KVASER_PCIEFD_PACK_TYPE_EFRAME_ACK: + ret = kvaser_pciefd_handle_eack_packet(pcie, p); + break; + + case KVASER_PCIEFD_PACK_TYPE_EFLUSH_ACK: + ret = kvaser_pciefd_handle_eflush_packet(pcie, p); + break; + + case KVASER_PCIEFD_PACK_TYPE_ACK_DATA: + case KVASER_PCIEFD_PACK_TYPE_BUS_LOAD: + case KVASER_PCIEFD_PACK_TYPE_TXRQ: + dev_info(&pcie->pci->dev, + "Received unexpected packet type 0x%08X\n", type); + break; + + default: + dev_err(&pcie->pci->dev, "Unknown packet type 0x%08X\n", type); + ret = -EIO; + break; + } + + if (ret) + return ret; + + /* Position does not point to the end of the package, + * corrupted packet size? + */ + if ((*start_pos + size) != pos) + return -EIO; + + /* Point to the next packet header, if any */ + *start_pos = pos; + + return ret; +} + +static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf) +{ + int pos = 0; + int res = 0; + + do { + res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf); + } while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE); + + return res; +} + +static int kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie) +{ + u32 irq; + + irq = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) { + kvaser_pciefd_read_buffer(pcie, 0); + /* Reset DMA buffer 0 */ + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, + pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + } + + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) { + kvaser_pciefd_read_buffer(pcie, 1); + /* Reset DMA buffer 1 */ + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, + pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + } + + if (irq & KVASER_PCIEFD_SRB_IRQ_DOF0 || + irq & KVASER_PCIEFD_SRB_IRQ_DOF1 || + irq & KVASER_PCIEFD_SRB_IRQ_DUF0 || + irq & KVASER_PCIEFD_SRB_IRQ_DUF1) + dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq); + + iowrite32(irq, pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); + return 0; +} + +static int kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) +{ + u32 irq = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); + + if (irq & KVASER_PCIEFD_KCAN_IRQ_TOF) + netdev_err(can->can.dev, "Tx FIFO overflow\n"); + + if (irq & KVASER_PCIEFD_KCAN_IRQ_TFD) { + u8 count = ioread32(can->reg_base + + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; + + if (count == 0) + iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, + can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); + } + + if (irq & KVASER_PCIEFD_KCAN_IRQ_BPP) + netdev_err(can->can.dev, + "Fail to change bittiming, when not in reset mode\n"); + + if (irq & KVASER_PCIEFD_KCAN_IRQ_FDIC) + netdev_err(can->can.dev, "CAN FD frame in CAN mode\n"); + + if (irq & KVASER_PCIEFD_KCAN_IRQ_ROF) + netdev_err(can->can.dev, "Rx FIFO overflow\n"); + + iowrite32(irq, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); + return 0; +} + +static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev) +{ + struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev; + u32 board_irq; + int i; + + board_irq = ioread32(pcie->reg_base + KVASER_PCIEFD_IRQ_REG); + + if (!(board_irq & KVASER_PCIEFD_IRQ_ALL_MSK)) + return IRQ_NONE; + + if (board_irq & KVASER_PCIEFD_IRQ_SRB) + kvaser_pciefd_receive_irq(pcie); + + for (i = 0; i < pcie->nr_channels; i++) { + if (!pcie->can[i]) { + dev_err(&pcie->pci->dev, + "IRQ mask points to unallocated controller\n"); + break; + } + + /* Check that mask matches channel (i) IRQ mask */ + if (board_irq & (1 << i)) + kvaser_pciefd_transmit_irq(pcie->can[i]); + } + + iowrite32(board_irq, pcie->reg_base + KVASER_PCIEFD_IRQ_REG); + return IRQ_HANDLED; +} + +static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie) +{ + int i; + struct kvaser_pciefd_can *can; + + for (i = 0; i < pcie->nr_channels; i++) { + can = pcie->can[i]; + if (can) { + iowrite32(0, + can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + kvaser_pciefd_pwm_stop(can); + free_candev(can->can.dev); + } + } +} + +static int kvaser_pciefd_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + int err; + struct kvaser_pciefd *pcie; + + pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci_set_drvdata(pdev, pcie); + pcie->pci = pdev; + + err = pci_enable_device(pdev); + if (err) + return err; + + err = pci_request_regions(pdev, KVASER_PCIEFD_DRV_NAME); + if (err) + goto err_disable_pci; + + pcie->reg_base = pci_iomap(pdev, 0, 0); + if (!pcie->reg_base) { + err = -ENOMEM; + goto err_release_regions; + } + + err = kvaser_pciefd_setup_board(pcie); + if (err) + goto err_pci_iounmap; + + err = kvaser_pciefd_setup_dma(pcie); + if (err) + goto err_pci_iounmap; + + pci_set_master(pdev); + + err = kvaser_pciefd_setup_can_ctrls(pcie); + if (err) + goto err_teardown_can_ctrls; + + iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1, + pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); + + iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1 | + KVASER_PCIEFD_SRB_IRQ_DOF0 | KVASER_PCIEFD_SRB_IRQ_DOF1 | + KVASER_PCIEFD_SRB_IRQ_DUF0 | KVASER_PCIEFD_SRB_IRQ_DUF1, + pcie->reg_base + KVASER_PCIEFD_SRB_IEN_REG); + + /* Reset IRQ handling, expected to be off before */ + iowrite32(KVASER_PCIEFD_IRQ_ALL_MSK, + pcie->reg_base + KVASER_PCIEFD_IRQ_REG); + iowrite32(KVASER_PCIEFD_IRQ_ALL_MSK, + pcie->reg_base + KVASER_PCIEFD_IEN_REG); + + /* Ready the DMA buffers */ + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, + pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, + pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + + err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, + IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); + if (err) + goto err_teardown_can_ctrls; + + err = kvaser_pciefd_reg_candev(pcie); + if (err) + goto err_free_irq; + + return 0; + +err_free_irq: + free_irq(pcie->pci->irq, pcie); + +err_teardown_can_ctrls: + kvaser_pciefd_teardown_can_ctrls(pcie); + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG); + pci_clear_master(pdev); + +err_pci_iounmap: + pci_iounmap(pdev, pcie->reg_base); + +err_release_regions: + pci_release_regions(pdev); + +err_disable_pci: + pci_disable_device(pdev); + + return err; +} + +static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie) +{ + struct kvaser_pciefd_can *can; + int i; + + for (i = 0; i < pcie->nr_channels; i++) { + can = pcie->can[i]; + if (can) { + iowrite32(0, + can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); + unregister_candev(can->can.dev); + del_timer(&can->bec_poll_timer); + kvaser_pciefd_pwm_stop(can); + free_candev(can->can.dev); + } + } +} + +static void kvaser_pciefd_remove(struct pci_dev *pdev) +{ + struct kvaser_pciefd *pcie = pci_get_drvdata(pdev); + + kvaser_pciefd_remove_all_ctrls(pcie); + + /* Turn off IRQ generation */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_SRB_CTRL_REG); + iowrite32(KVASER_PCIEFD_IRQ_ALL_MSK, + pcie->reg_base + KVASER_PCIEFD_IRQ_REG); + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG); + + free_irq(pcie->pci->irq, pcie); + + pci_clear_master(pdev); + pci_iounmap(pdev, pcie->reg_base); + pci_release_regions(pdev); + pci_disable_device(pdev); +} + +static struct pci_driver kvaser_pciefd = { + .name = KVASER_PCIEFD_DRV_NAME, + .id_table = kvaser_pciefd_id_table, + .probe = kvaser_pciefd_probe, + .remove = kvaser_pciefd_remove, +}; + +module_pci_driver(kvaser_pciefd) diff --git a/drivers/net/can/m_can/Kconfig b/drivers/net/can/m_can/Kconfig index ec4b2e117f66..1ff0b7fe81d6 100644 --- a/drivers/net/can/m_can/Kconfig +++ b/drivers/net/can/m_can/Kconfig @@ -1,6 +1,24 @@ # SPDX-License-Identifier: GPL-2.0-only config 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. + +config CAN_M_CAN_PLATFORM + tristate "Bosch M_CAN support for io-mapped devices" depends on HAS_IOMEM - tristate "Bosch M_CAN devices" + 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 REGMAP_SPI + tristate "TCAN4X5X M_CAN device" ---help--- - Say Y here if you want to support for Bosch M_CAN controller. + Say Y here if you want support for Texas Instruments TCAN4x5x + M_CAN controller. This device is a peripherial device that uses the + SPI bus for communication. diff --git a/drivers/net/can/m_can/Makefile b/drivers/net/can/m_can/Makefile index 599ae69cb4a1..52a4a6fbe527 100644 --- a/drivers/net/can/m_can/Makefile +++ b/drivers/net/can/m_can/Makefile @@ -4,3 +4,5 @@ # obj-$(CONFIG_CAN_M_CAN) += m_can.o +obj-$(CONFIG_CAN_M_CAN_PLATFORM) += m_can_platform.o +obj-$(CONFIG_CAN_M_CAN_TCAN4X5X) += tcan4x5x.o diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index deb274a19ba0..562c8317e3aa 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1,20 +1,14 @@ -/* - * CAN bus driver for Bosch M_CAN controller - * - * Copyright (C) 2014 Freescale Semiconductor, Inc. - * Dong Aisheng <b29396@freescale.com> - * - * Bosch M_CAN user manual can be obtained from: +// SPDX-License-Identifier: GPL-2.0 +// CAN bus driver for Bosch M_CAN controller +// Copyright (C) 2014 Freescale Semiconductor, Inc. +// Dong Aisheng <b29396@freescale.com> +// Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/ + +/* Bosch M_CAN user manual can be obtained from: * http://www.bosch-semiconductors.de/media/pdf_1/ipmodules_1/m_can/ * mcan_users_manual_v302.pdf - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ -#include <linux/clk.h> -#include <linux/delay.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> @@ -28,11 +22,7 @@ #include <linux/can/dev.h> #include <linux/pinctrl/consumer.h> -/* napi related */ -#define M_CAN_NAPI_WEIGHT 64 - -/* message ram configuration data length */ -#define MRAM_CFG_LEN 8 +#include "m_can.h" /* registers definition */ enum m_can_reg { @@ -86,28 +76,11 @@ enum m_can_reg { M_CAN_TXEFA = 0xf8, }; -/* m_can lec values */ -enum m_can_lec_type { - LEC_NO_ERROR = 0, - LEC_STUFF_ERROR, - LEC_FORM_ERROR, - LEC_ACK_ERROR, - LEC_BIT1_ERROR, - LEC_BIT0_ERROR, - LEC_CRC_ERROR, - LEC_UNUSED, -}; +/* napi related */ +#define M_CAN_NAPI_WEIGHT 64 -enum m_can_mram_cfg { - MRAM_SIDF = 0, - MRAM_XIDF, - MRAM_RXF0, - MRAM_RXF1, - MRAM_RXB, - MRAM_TXE, - MRAM_TXB, - MRAM_CFG_NUM, -}; +/* message ram configuration data length */ +#define MRAM_CFG_LEN 8 /* Core Release Register (CREL) */ #define CREL_REL_SHIFT 28 @@ -347,90 +320,85 @@ enum m_can_mram_cfg { #define TX_EVENT_MM_SHIFT TX_BUF_MM_SHIFT #define TX_EVENT_MM_MASK (0xff << TX_EVENT_MM_SHIFT) -/* address offset and element number for each FIFO/Buffer in the Message RAM */ -struct mram_cfg { - u16 off; - u8 num; -}; - -/* m_can private data structure */ -struct m_can_priv { - struct can_priv can; /* must be the first member */ - struct napi_struct napi; - struct net_device *dev; - struct device *device; - struct clk *hclk; - struct clk *cclk; - void __iomem *base; - u32 irqstatus; - int version; - - /* message ram configuration */ - void __iomem *mram_base; - struct mram_cfg mcfg[MRAM_CFG_NUM]; -}; +static inline u32 m_can_read(struct m_can_classdev *cdev, enum m_can_reg reg) +{ + return cdev->ops->read_reg(cdev, reg); +} -static inline u32 m_can_read(const struct m_can_priv *priv, enum m_can_reg reg) +static inline void m_can_write(struct m_can_classdev *cdev, enum m_can_reg reg, + u32 val) { - return readl(priv->base + reg); + cdev->ops->write_reg(cdev, reg, val); } -static inline void m_can_write(const struct m_can_priv *priv, - enum m_can_reg reg, u32 val) +static u32 m_can_fifo_read(struct m_can_classdev *cdev, + u32 fgi, unsigned int offset) { - writel(val, priv->base + reg); + u32 addr_offset = cdev->mcfg[MRAM_RXF0].off + fgi * RXF0_ELEMENT_SIZE + + offset; + + return cdev->ops->read_fifo(cdev, addr_offset); } -static inline u32 m_can_fifo_read(const struct m_can_priv *priv, - u32 fgi, unsigned int offset) +static void m_can_fifo_write(struct m_can_classdev *cdev, + u32 fpi, unsigned int offset, u32 val) { - return readl(priv->mram_base + priv->mcfg[MRAM_RXF0].off + - fgi * RXF0_ELEMENT_SIZE + offset); + u32 addr_offset = cdev->mcfg[MRAM_TXB].off + fpi * TXB_ELEMENT_SIZE + + offset; + + cdev->ops->write_fifo(cdev, addr_offset, val); } -static inline void m_can_fifo_write(const struct m_can_priv *priv, - u32 fpi, unsigned int offset, u32 val) +static inline void m_can_fifo_write_no_off(struct m_can_classdev *cdev, + u32 fpi, u32 val) { - writel(val, priv->mram_base + priv->mcfg[MRAM_TXB].off + - fpi * TXB_ELEMENT_SIZE + offset); + cdev->ops->write_fifo(cdev, fpi, val); } -static inline u32 m_can_txe_fifo_read(const struct m_can_priv *priv, - u32 fgi, - u32 offset) { - return readl(priv->mram_base + priv->mcfg[MRAM_TXE].off + - fgi * TXE_ELEMENT_SIZE + offset); +static u32 m_can_txe_fifo_read(struct m_can_classdev *cdev, u32 fgi, u32 offset) +{ + u32 addr_offset = cdev->mcfg[MRAM_TXE].off + fgi * TXE_ELEMENT_SIZE + + offset; + + return cdev->ops->read_fifo(cdev, addr_offset); } -static inline bool m_can_tx_fifo_full(const struct m_can_priv *priv) +static inline bool m_can_tx_fifo_full(struct m_can_classdev *cdev) { - return !!(m_can_read(priv, M_CAN_TXFQS) & TXFQS_TFQF); + return !!(m_can_read(cdev, M_CAN_TXFQS) & TXFQS_TFQF); } -static inline void m_can_config_endisable(const struct m_can_priv *priv, - bool enable) +void m_can_config_endisable(struct m_can_classdev *cdev, bool enable) { - u32 cccr = m_can_read(priv, M_CAN_CCCR); + u32 cccr = m_can_read(cdev, M_CAN_CCCR); u32 timeout = 10; u32 val = 0; + /* Clear the Clock stop request if it was set */ + if (cccr & CCCR_CSR) + cccr &= ~CCCR_CSR; + if (enable) { + /* Clear the Clock stop request if it was set */ + if (cccr & CCCR_CSR) + cccr &= ~CCCR_CSR; + /* enable m_can configuration */ - m_can_write(priv, M_CAN_CCCR, cccr | CCCR_INIT); + m_can_write(cdev, M_CAN_CCCR, cccr | CCCR_INIT); udelay(5); /* CCCR.CCE can only be set/reset while CCCR.INIT = '1' */ - m_can_write(priv, M_CAN_CCCR, cccr | CCCR_INIT | CCCR_CCE); + m_can_write(cdev, M_CAN_CCCR, cccr | CCCR_INIT | CCCR_CCE); } else { - m_can_write(priv, M_CAN_CCCR, cccr & ~(CCCR_INIT | CCCR_CCE)); + m_can_write(cdev, M_CAN_CCCR, cccr & ~(CCCR_INIT | CCCR_CCE)); } /* there's a delay for module initialization */ if (enable) val = CCCR_INIT | CCCR_CCE; - while ((m_can_read(priv, M_CAN_CCCR) & (CCCR_INIT | CCCR_CCE)) != val) { + while ((m_can_read(cdev, M_CAN_CCCR) & (CCCR_INIT | CCCR_CCE)) != val) { if (timeout == 0) { - netdev_warn(priv->dev, "Failed to init module\n"); + netdev_warn(cdev->net, "Failed to init module\n"); return; } timeout--; @@ -438,21 +406,38 @@ static inline void m_can_config_endisable(const struct m_can_priv *priv, } } -static inline void m_can_enable_all_interrupts(const struct m_can_priv *priv) +static inline void m_can_enable_all_interrupts(struct m_can_classdev *cdev) { /* Only interrupt line 0 is used in this driver */ - m_can_write(priv, M_CAN_ILE, ILE_EINT0); + m_can_write(cdev, M_CAN_ILE, ILE_EINT0); } -static inline void m_can_disable_all_interrupts(const struct m_can_priv *priv) +static inline void m_can_disable_all_interrupts(struct m_can_classdev *cdev) { - m_can_write(priv, M_CAN_ILE, 0x0); + m_can_write(cdev, M_CAN_ILE, 0x0); +} + +static void m_can_clean(struct net_device *net) +{ + struct m_can_classdev *cdev = netdev_priv(net); + + if (cdev->tx_skb) { + int putidx = 0; + + net->stats.tx_errors++; + if (cdev->version > 30) + putidx = ((m_can_read(cdev, M_CAN_TXFQS) & + TXFQS_TFQPI_MASK) >> TXFQS_TFQPI_SHIFT); + + can_free_echo_skb(cdev->net, putidx); + cdev->tx_skb = NULL; + } } static void m_can_read_fifo(struct net_device *dev, u32 rxfs) { struct net_device_stats *stats = &dev->stats; - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); struct canfd_frame *cf; struct sk_buff *skb; u32 id, fgi, dlc; @@ -460,7 +445,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs) /* calculate the fifo get index for where to read data */ fgi = (rxfs & RXFS_FGI_MASK) >> RXFS_FGI_SHIFT; - dlc = m_can_fifo_read(priv, fgi, M_CAN_FIFO_DLC); + dlc = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DLC); if (dlc & RX_BUF_FDF) skb = alloc_canfd_skb(dev, &cf); else @@ -475,7 +460,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs) else cf->len = get_can_dlc((dlc >> 16) & 0x0F); - id = m_can_fifo_read(priv, fgi, M_CAN_FIFO_ID); + id = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_ID); if (id & RX_BUF_XTD) cf->can_id = (id & CAN_EFF_MASK) | CAN_EFF_FLAG; else @@ -494,12 +479,12 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs) for (i = 0; i < cf->len; i += 4) *(u32 *)(cf->data + i) = - m_can_fifo_read(priv, fgi, + m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DATA(i / 4)); } /* acknowledge rx fifo 0 */ - m_can_write(priv, M_CAN_RXF0A, fgi); + m_can_write(cdev, M_CAN_RXF0A, fgi); stats->rx_packets++; stats->rx_bytes += cf->len; @@ -509,11 +494,11 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs) static int m_can_do_rx_poll(struct net_device *dev, int quota) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); u32 pkts = 0; u32 rxfs; - rxfs = m_can_read(priv, M_CAN_RXF0S); + rxfs = m_can_read(cdev, M_CAN_RXF0S); if (!(rxfs & RXFS_FFL_MASK)) { netdev_dbg(dev, "no messages in fifo0\n"); return 0; @@ -527,7 +512,7 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota) quota--; pkts++; - rxfs = m_can_read(priv, M_CAN_RXF0S); + rxfs = m_can_read(cdev, M_CAN_RXF0S); } if (pkts) @@ -562,12 +547,12 @@ static int m_can_handle_lost_msg(struct net_device *dev) static int m_can_handle_lec_err(struct net_device *dev, enum m_can_lec_type lec_type) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; struct can_frame *cf; struct sk_buff *skb; - priv->can.can_stats.bus_error++; + cdev->can.can_stats.bus_error++; stats->rx_errors++; /* propagate the error condition to the CAN stack */ @@ -619,47 +604,51 @@ static int m_can_handle_lec_err(struct net_device *dev, static int __m_can_get_berr_counter(const struct net_device *dev, struct can_berr_counter *bec) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); unsigned int ecr; - ecr = m_can_read(priv, M_CAN_ECR); + ecr = m_can_read(cdev, M_CAN_ECR); bec->rxerr = (ecr & ECR_REC_MASK) >> ECR_REC_SHIFT; bec->txerr = (ecr & ECR_TEC_MASK) >> ECR_TEC_SHIFT; return 0; } -static int m_can_clk_start(struct m_can_priv *priv) +static int m_can_clk_start(struct m_can_classdev *cdev) { int err; - err = pm_runtime_get_sync(priv->device); + if (cdev->pm_clock_support == 0) + return 0; + + err = pm_runtime_get_sync(cdev->dev); if (err < 0) { - pm_runtime_put_noidle(priv->device); + pm_runtime_put_noidle(cdev->dev); return err; } return 0; } -static void m_can_clk_stop(struct m_can_priv *priv) +static void m_can_clk_stop(struct m_can_classdev *cdev) { - pm_runtime_put_sync(priv->device); + if (cdev->pm_clock_support) + pm_runtime_put_sync(cdev->dev); } static int m_can_get_berr_counter(const struct net_device *dev, struct can_berr_counter *bec) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); int err; - err = m_can_clk_start(priv); + err = m_can_clk_start(cdev); if (err) return err; __m_can_get_berr_counter(dev, bec); - m_can_clk_stop(priv); + m_can_clk_stop(cdev); return 0; } @@ -667,7 +656,7 @@ static int m_can_get_berr_counter(const struct net_device *dev, static int m_can_handle_state_change(struct net_device *dev, enum can_state new_state) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; struct can_frame *cf; struct sk_buff *skb; @@ -677,19 +666,19 @@ static int m_can_handle_state_change(struct net_device *dev, switch (new_state) { case CAN_STATE_ERROR_ACTIVE: /* error warning state */ - priv->can.can_stats.error_warning++; - priv->can.state = CAN_STATE_ERROR_WARNING; + cdev->can.can_stats.error_warning++; + cdev->can.state = CAN_STATE_ERROR_WARNING; break; case CAN_STATE_ERROR_PASSIVE: /* error passive state */ - priv->can.can_stats.error_passive++; - priv->can.state = CAN_STATE_ERROR_PASSIVE; + cdev->can.can_stats.error_passive++; + cdev->can.state = CAN_STATE_ERROR_PASSIVE; break; case CAN_STATE_BUS_OFF: /* bus-off state */ - priv->can.state = CAN_STATE_BUS_OFF; - m_can_disable_all_interrupts(priv); - priv->can.can_stats.bus_off++; + cdev->can.state = CAN_STATE_BUS_OFF; + m_can_disable_all_interrupts(cdev); + cdev->can.can_stats.bus_off++; can_bus_off(dev); break; default: @@ -716,7 +705,7 @@ static int m_can_handle_state_change(struct net_device *dev, case CAN_STATE_ERROR_PASSIVE: /* error passive state */ cf->can_id |= CAN_ERR_CRTL; - ecr = m_can_read(priv, M_CAN_ECR); + ecr = m_can_read(cdev, M_CAN_ECR); if (ecr & ECR_RP) cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE; if (bec.txerr > 127) @@ -741,25 +730,22 @@ static int m_can_handle_state_change(struct net_device *dev, static int m_can_handle_state_errors(struct net_device *dev, u32 psr) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); int work_done = 0; - if ((psr & PSR_EW) && - (priv->can.state != CAN_STATE_ERROR_WARNING)) { + if (psr & PSR_EW && cdev->can.state != CAN_STATE_ERROR_WARNING) { netdev_dbg(dev, "entered error warning state\n"); work_done += m_can_handle_state_change(dev, CAN_STATE_ERROR_WARNING); } - if ((psr & PSR_EP) && - (priv->can.state != CAN_STATE_ERROR_PASSIVE)) { + if (psr & PSR_EP && cdev->can.state != CAN_STATE_ERROR_PASSIVE) { netdev_dbg(dev, "entered error passive state\n"); work_done += m_can_handle_state_change(dev, CAN_STATE_ERROR_PASSIVE); } - if ((psr & PSR_BO) && - (priv->can.state != CAN_STATE_BUS_OFF)) { + if (psr & PSR_BO && cdev->can.state != CAN_STATE_BUS_OFF) { netdev_dbg(dev, "entered error bus off state\n"); work_done += m_can_handle_state_change(dev, CAN_STATE_BUS_OFF); @@ -794,14 +780,14 @@ static inline bool is_lec_err(u32 psr) static int m_can_handle_bus_errors(struct net_device *dev, u32 irqstatus, u32 psr) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); int work_done = 0; if (irqstatus & IR_RF0L) work_done += m_can_handle_lost_msg(dev); /* handle lec errors on the bus */ - if ((priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) && + if ((cdev->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) && is_lec_err(psr)) work_done += m_can_handle_lec_err(dev, psr & LEC_UNUSED); @@ -811,14 +797,13 @@ static int m_can_handle_bus_errors(struct net_device *dev, u32 irqstatus, return work_done; } -static int m_can_poll(struct napi_struct *napi, int quota) +static int m_can_rx_handler(struct net_device *dev, int quota) { - struct net_device *dev = napi->dev; - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); int work_done = 0; u32 irqstatus, psr; - irqstatus = priv->irqstatus | m_can_read(priv, M_CAN_IR); + irqstatus = cdev->irqstatus | m_can_read(cdev, M_CAN_IR); if (!irqstatus) goto end; @@ -832,18 +817,19 @@ static int m_can_poll(struct napi_struct *napi, int quota) * whether MCAN_ECR.RP = ’1’ and MCAN_ECR.REC = 127. * In this case, reset MCAN_IR.MRAF. No further action is required. */ - if ((priv->version <= 31) && (irqstatus & IR_MRAF) && - (m_can_read(priv, M_CAN_ECR) & ECR_RP)) { + if (cdev->version <= 31 && irqstatus & IR_MRAF && + m_can_read(cdev, M_CAN_ECR) & ECR_RP) { struct can_berr_counter bec; __m_can_get_berr_counter(dev, &bec); if (bec.rxerr == 127) { - m_can_write(priv, M_CAN_IR, IR_MRAF); + m_can_write(cdev, M_CAN_IR, IR_MRAF); irqstatus &= ~IR_MRAF; } } - psr = m_can_read(priv, M_CAN_PSR); + psr = m_can_read(cdev, M_CAN_PSR); + if (irqstatus & IR_ERR_STATE) work_done += m_can_handle_state_errors(dev, psr); @@ -852,13 +838,33 @@ static int m_can_poll(struct napi_struct *napi, int quota) if (irqstatus & IR_RF0N) work_done += m_can_do_rx_poll(dev, (quota - work_done)); +end: + return work_done; +} + +static int m_can_rx_peripheral(struct net_device *dev) +{ + struct m_can_classdev *cdev = netdev_priv(dev); + + m_can_rx_handler(dev, 1); + + m_can_enable_all_interrupts(cdev); + + return 0; +} +static int m_can_poll(struct napi_struct *napi, int quota) +{ + struct net_device *dev = napi->dev; + struct m_can_classdev *cdev = netdev_priv(dev); + int work_done; + + work_done = m_can_rx_handler(dev, quota); if (work_done < quota) { napi_complete_done(napi, work_done); - m_can_enable_all_interrupts(priv); + m_can_enable_all_interrupts(cdev); } -end: return work_done; } @@ -870,11 +876,11 @@ static void m_can_echo_tx_event(struct net_device *dev) int i = 0; unsigned int msg_mark; - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; /* read tx event fifo status */ - m_can_txefs = m_can_read(priv, M_CAN_TXEFS); + m_can_txefs = m_can_read(cdev, M_CAN_TXEFS); /* Get Tx Event fifo element count */ txe_count = (m_can_txefs & TXEFS_EFFL_MASK) @@ -883,15 +889,15 @@ static void m_can_echo_tx_event(struct net_device *dev) /* Get and process all sent elements */ for (i = 0; i < txe_count; i++) { /* retrieve get index */ - fgi = (m_can_read(priv, M_CAN_TXEFS) & TXEFS_EFGI_MASK) + fgi = (m_can_read(cdev, M_CAN_TXEFS) & TXEFS_EFGI_MASK) >> TXEFS_EFGI_SHIFT; /* get message marker */ - msg_mark = (m_can_txe_fifo_read(priv, fgi, 4) & + msg_mark = (m_can_txe_fifo_read(cdev, fgi, 4) & TX_EVENT_MM_MASK) >> TX_EVENT_MM_SHIFT; /* ack txe element */ - m_can_write(priv, M_CAN_TXEFA, (TXEFA_EFAI_MASK & + m_can_write(cdev, M_CAN_TXEFA, (TXEFA_EFAI_MASK & (fgi << TXEFA_EFAI_SHIFT))); /* update stats */ @@ -903,17 +909,20 @@ static void m_can_echo_tx_event(struct net_device *dev) static irqreturn_t m_can_isr(int irq, void *dev_id) { struct net_device *dev = (struct net_device *)dev_id; - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; u32 ir; - ir = m_can_read(priv, M_CAN_IR); + ir = m_can_read(cdev, M_CAN_IR); if (!ir) return IRQ_NONE; /* ACK all irqs */ if (ir & IR_ALL_INT) - m_can_write(priv, M_CAN_IR, ir); + m_can_write(cdev, M_CAN_IR, ir); + + if (cdev->ops->clear_interrupts) + cdev->ops->clear_interrupts(cdev); /* schedule NAPI in case of * - rx IRQ @@ -921,12 +930,15 @@ static irqreturn_t m_can_isr(int irq, void *dev_id) * - bus error IRQ and bus error reporting */ if ((ir & IR_RF0N) || (ir & IR_ERR_ALL_30X)) { - priv->irqstatus = ir; - m_can_disable_all_interrupts(priv); - napi_schedule(&priv->napi); + cdev->irqstatus = ir; + m_can_disable_all_interrupts(cdev); + if (!cdev->is_peripheral) + napi_schedule(&cdev->napi); + else + m_can_rx_peripheral(dev); } - if (priv->version == 30) { + if (cdev->version == 30) { if (ir & IR_TC) { /* Transmission Complete Interrupt*/ stats->tx_bytes += can_get_echo_skb(dev, 0); @@ -940,7 +952,7 @@ static irqreturn_t m_can_isr(int irq, void *dev_id) m_can_echo_tx_event(dev); can_led_event(dev, CAN_LED_EVENT_TX); if (netif_queue_stopped(dev) && - !m_can_tx_fifo_full(priv)) + !m_can_tx_fifo_full(cdev)) netif_wake_queue(dev); } } @@ -998,9 +1010,9 @@ static const struct can_bittiming_const m_can_data_bittiming_const_31X = { static int m_can_set_bittiming(struct net_device *dev) { - struct m_can_priv *priv = netdev_priv(dev); - const struct can_bittiming *bt = &priv->can.bittiming; - const struct can_bittiming *dbt = &priv->can.data_bittiming; + struct m_can_classdev *cdev = netdev_priv(dev); + const struct can_bittiming *bt = &cdev->can.bittiming; + const struct can_bittiming *dbt = &cdev->can.data_bittiming; u16 brp, sjw, tseg1, tseg2; u32 reg_btp; @@ -1010,9 +1022,9 @@ static int m_can_set_bittiming(struct net_device *dev) tseg2 = bt->phase_seg2 - 1; reg_btp = (brp << NBTP_NBRP_SHIFT) | (sjw << NBTP_NSJW_SHIFT) | (tseg1 << NBTP_NTSEG1_SHIFT) | (tseg2 << NBTP_NTSEG2_SHIFT); - m_can_write(priv, M_CAN_NBTP, reg_btp); + m_can_write(cdev, M_CAN_NBTP, reg_btp); - if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { + if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) { reg_btp = 0; brp = dbt->brp - 1; sjw = dbt->sjw - 1; @@ -1034,7 +1046,7 @@ static int m_can_set_bittiming(struct net_device *dev) /* Equation based on Bosch's M_CAN User Manual's * Transmitter Delay Compensation Section */ - tdco = (priv->can.clock.freq / 1000) * + tdco = (cdev->can.clock.freq / 1000) * ssp / dbt->bitrate; /* Max valid TDCO value is 127 */ @@ -1045,7 +1057,7 @@ static int m_can_set_bittiming(struct net_device *dev) } reg_btp |= DBTP_TDC; - m_can_write(priv, M_CAN_TDCR, + m_can_write(cdev, M_CAN_TDCR, tdco << TDCR_TDCO_SHIFT); } @@ -1054,7 +1066,7 @@ static int m_can_set_bittiming(struct net_device *dev) (tseg1 << DBTP_DTSEG1_SHIFT) | (tseg2 << DBTP_DTSEG2_SHIFT); - m_can_write(priv, M_CAN_DBTP, reg_btp); + m_can_write(cdev, M_CAN_DBTP, reg_btp); } return 0; @@ -1071,63 +1083,63 @@ static int m_can_set_bittiming(struct net_device *dev) */ static void m_can_chip_config(struct net_device *dev) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); u32 cccr, test; - m_can_config_endisable(priv, true); + m_can_config_endisable(cdev, true); /* RX Buffer/FIFO Element Size 64 bytes data field */ - m_can_write(priv, M_CAN_RXESC, M_CAN_RXESC_64BYTES); + m_can_write(cdev, M_CAN_RXESC, M_CAN_RXESC_64BYTES); /* Accept Non-matching Frames Into FIFO 0 */ - m_can_write(priv, M_CAN_GFC, 0x0); + m_can_write(cdev, M_CAN_GFC, 0x0); - if (priv->version == 30) { + if (cdev->version == 30) { /* only support one Tx Buffer currently */ - m_can_write(priv, M_CAN_TXBC, (1 << TXBC_NDTB_SHIFT) | - priv->mcfg[MRAM_TXB].off); + m_can_write(cdev, M_CAN_TXBC, (1 << TXBC_NDTB_SHIFT) | + cdev->mcfg[MRAM_TXB].off); } else { /* TX FIFO is used for newer IP Core versions */ - m_can_write(priv, M_CAN_TXBC, - (priv->mcfg[MRAM_TXB].num << TXBC_TFQS_SHIFT) | - (priv->mcfg[MRAM_TXB].off)); + m_can_write(cdev, M_CAN_TXBC, + (cdev->mcfg[MRAM_TXB].num << TXBC_TFQS_SHIFT) | + (cdev->mcfg[MRAM_TXB].off)); } /* support 64 bytes payload */ - m_can_write(priv, M_CAN_TXESC, TXESC_TBDS_64BYTES); + m_can_write(cdev, M_CAN_TXESC, TXESC_TBDS_64BYTES); /* TX Event FIFO */ - if (priv->version == 30) { - m_can_write(priv, M_CAN_TXEFC, (1 << TXEFC_EFS_SHIFT) | - priv->mcfg[MRAM_TXE].off); + if (cdev->version == 30) { + m_can_write(cdev, M_CAN_TXEFC, (1 << TXEFC_EFS_SHIFT) | + cdev->mcfg[MRAM_TXE].off); } else { /* Full TX Event FIFO is used */ - m_can_write(priv, M_CAN_TXEFC, - ((priv->mcfg[MRAM_TXE].num << TXEFC_EFS_SHIFT) + m_can_write(cdev, M_CAN_TXEFC, + ((cdev->mcfg[MRAM_TXE].num << TXEFC_EFS_SHIFT) & TXEFC_EFS_MASK) | - priv->mcfg[MRAM_TXE].off); + cdev->mcfg[MRAM_TXE].off); } /* rx fifo configuration, blocking mode, fifo size 1 */ - m_can_write(priv, M_CAN_RXF0C, - (priv->mcfg[MRAM_RXF0].num << RXFC_FS_SHIFT) | - priv->mcfg[MRAM_RXF0].off); + m_can_write(cdev, M_CAN_RXF0C, + (cdev->mcfg[MRAM_RXF0].num << RXFC_FS_SHIFT) | + cdev->mcfg[MRAM_RXF0].off); - m_can_write(priv, M_CAN_RXF1C, - (priv->mcfg[MRAM_RXF1].num << RXFC_FS_SHIFT) | - priv->mcfg[MRAM_RXF1].off); + m_can_write(cdev, M_CAN_RXF1C, + (cdev->mcfg[MRAM_RXF1].num << RXFC_FS_SHIFT) | + cdev->mcfg[MRAM_RXF1].off); - cccr = m_can_read(priv, M_CAN_CCCR); - test = m_can_read(priv, M_CAN_TEST); + cccr = m_can_read(cdev, M_CAN_CCCR); + test = m_can_read(cdev, M_CAN_TEST); test &= ~TEST_LBCK; - if (priv->version == 30) { + if (cdev->version == 30) { /* Version 3.0.x */ cccr &= ~(CCCR_TEST | CCCR_MON | (CCCR_CMR_MASK << CCCR_CMR_SHIFT) | (CCCR_CME_MASK << CCCR_CME_SHIFT)); - if (priv->can.ctrlmode & CAN_CTRLMODE_FD) + if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) cccr |= CCCR_CME_CANFD_BRS << CCCR_CME_SHIFT; } else { @@ -1136,64 +1148,68 @@ static void m_can_chip_config(struct net_device *dev) CCCR_NISO); /* Only 3.2.x has NISO Bit implemented */ - if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) + if (cdev->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) cccr |= CCCR_NISO; - if (priv->can.ctrlmode & CAN_CTRLMODE_FD) + if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) cccr |= (CCCR_BRSE | CCCR_FDOE); } /* Loopback Mode */ - if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) { + if (cdev->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) { cccr |= CCCR_TEST | CCCR_MON; test |= TEST_LBCK; } /* Enable Monitoring (all versions) */ - if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + if (cdev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) cccr |= CCCR_MON; /* Write config */ - m_can_write(priv, M_CAN_CCCR, cccr); - m_can_write(priv, M_CAN_TEST, test); + m_can_write(cdev, M_CAN_CCCR, cccr); + m_can_write(cdev, M_CAN_TEST, test); /* Enable interrupts */ - m_can_write(priv, M_CAN_IR, IR_ALL_INT); - if (!(priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) - if (priv->version == 30) - m_can_write(priv, M_CAN_IE, IR_ALL_INT & + m_can_write(cdev, M_CAN_IR, IR_ALL_INT); + if (!(cdev->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)) + if (cdev->version == 30) + m_can_write(cdev, M_CAN_IE, IR_ALL_INT & ~(IR_ERR_LEC_30X)); else - m_can_write(priv, M_CAN_IE, IR_ALL_INT & + m_can_write(cdev, M_CAN_IE, IR_ALL_INT & ~(IR_ERR_LEC_31X)); else - m_can_write(priv, M_CAN_IE, IR_ALL_INT); + m_can_write(cdev, M_CAN_IE, IR_ALL_INT); /* route all interrupts to INT0 */ - m_can_write(priv, M_CAN_ILS, ILS_ALL_INT0); + m_can_write(cdev, M_CAN_ILS, ILS_ALL_INT0); /* set bittiming params */ m_can_set_bittiming(dev); - m_can_config_endisable(priv, false); + m_can_config_endisable(cdev, false); + + if (cdev->ops->init) + cdev->ops->init(cdev); } static void m_can_start(struct net_device *dev) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); /* basic m_can configuration */ m_can_chip_config(dev); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + cdev->can.state = CAN_STATE_ERROR_ACTIVE; - m_can_enable_all_interrupts(priv); + m_can_enable_all_interrupts(cdev); } static int m_can_set_mode(struct net_device *dev, enum can_mode mode) { switch (mode) { case CAN_MODE_START: + m_can_clean(dev); m_can_start(dev); netif_wake_queue(dev); break; @@ -1209,20 +1225,17 @@ static int m_can_set_mode(struct net_device *dev, enum can_mode mode) * else it returns the release and step coded as: * return value = 10 * <release> + 1 * <step> */ -static int m_can_check_core_release(void __iomem *m_can_base) +static int m_can_check_core_release(struct m_can_classdev *cdev) { u32 crel_reg; u8 rel; u8 step; int res; - struct m_can_priv temp_priv = { - .base = m_can_base - }; /* Read Core Release Version and split into version number * Example: Version 3.2.1 => rel = 3; step = 2; substep = 1; */ - crel_reg = m_can_read(&temp_priv, M_CAN_CREL); + crel_reg = m_can_read(cdev, M_CAN_CREL); rel = (u8)((crel_reg & CREL_REL_MASK) >> CREL_REL_SHIFT); step = (u8)((crel_reg & CREL_STEP_MASK) >> CREL_STEP_SHIFT); @@ -1240,152 +1253,142 @@ static int m_can_check_core_release(void __iomem *m_can_base) /* Selectable Non ISO support only in version 3.2.x * This function checks if the bit is writable. */ -static bool m_can_niso_supported(const struct m_can_priv *priv) +static bool m_can_niso_supported(struct m_can_classdev *cdev) { - u32 cccr_reg, cccr_poll; - int niso_timeout; + u32 cccr_reg, cccr_poll = 0; + int niso_timeout = -ETIMEDOUT; + int i; - m_can_config_endisable(priv, true); - cccr_reg = m_can_read(priv, M_CAN_CCCR); + m_can_config_endisable(cdev, true); + cccr_reg = m_can_read(cdev, M_CAN_CCCR); cccr_reg |= CCCR_NISO; - m_can_write(priv, M_CAN_CCCR, cccr_reg); + m_can_write(cdev, M_CAN_CCCR, cccr_reg); - niso_timeout = readl_poll_timeout((priv->base + M_CAN_CCCR), cccr_poll, - (cccr_poll == cccr_reg), 0, 10); + for (i = 0; i <= 10; i++) { + cccr_poll = m_can_read(cdev, M_CAN_CCCR); + if (cccr_poll == cccr_reg) { + niso_timeout = 0; + break; + } + + usleep_range(1, 5); + } /* Clear NISO */ cccr_reg &= ~(CCCR_NISO); - m_can_write(priv, M_CAN_CCCR, cccr_reg); + m_can_write(cdev, M_CAN_CCCR, cccr_reg); - m_can_config_endisable(priv, false); + m_can_config_endisable(cdev, false); /* return false if time out (-ETIMEDOUT), else return true */ return !niso_timeout; } -static int m_can_dev_setup(struct platform_device *pdev, struct net_device *dev, - void __iomem *addr) +static int m_can_dev_setup(struct m_can_classdev *m_can_dev) { - struct m_can_priv *priv; + struct net_device *dev = m_can_dev->net; int m_can_version; - m_can_version = m_can_check_core_release(addr); + m_can_version = m_can_check_core_release(m_can_dev); /* return if unsupported version */ if (!m_can_version) { - dev_err(&pdev->dev, "Unsupported version number: %2d", + dev_err(m_can_dev->dev, "Unsupported version number: %2d", m_can_version); return -EINVAL; } - priv = netdev_priv(dev); - netif_napi_add(dev, &priv->napi, m_can_poll, M_CAN_NAPI_WEIGHT); + if (!m_can_dev->is_peripheral) + netif_napi_add(dev, &m_can_dev->napi, + m_can_poll, M_CAN_NAPI_WEIGHT); /* Shared properties of all M_CAN versions */ - priv->version = m_can_version; - priv->dev = dev; - priv->base = addr; - priv->can.do_set_mode = m_can_set_mode; - priv->can.do_get_berr_counter = m_can_get_berr_counter; + m_can_dev->version = m_can_version; + m_can_dev->can.do_set_mode = m_can_set_mode; + m_can_dev->can.do_get_berr_counter = m_can_get_berr_counter; /* Set M_CAN supported operations */ - priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | + m_can_dev->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_FD; /* Set properties depending on M_CAN version */ - switch (priv->version) { + switch (m_can_dev->version) { case 30: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */ can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); - priv->can.bittiming_const = &m_can_bittiming_const_30X; - priv->can.data_bittiming_const = - &m_can_data_bittiming_const_30X; + m_can_dev->can.bittiming_const = m_can_dev->bit_timing ? + m_can_dev->bit_timing : &m_can_bittiming_const_30X; + + m_can_dev->can.data_bittiming_const = m_can_dev->data_timing ? + m_can_dev->data_timing : + &m_can_data_bittiming_const_30X; break; case 31: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */ can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); - priv->can.bittiming_const = &m_can_bittiming_const_31X; - priv->can.data_bittiming_const = - &m_can_data_bittiming_const_31X; + m_can_dev->can.bittiming_const = m_can_dev->bit_timing ? + m_can_dev->bit_timing : &m_can_bittiming_const_31X; + + m_can_dev->can.data_bittiming_const = m_can_dev->data_timing ? + m_can_dev->data_timing : + &m_can_data_bittiming_const_31X; break; case 32: - priv->can.bittiming_const = &m_can_bittiming_const_31X; - priv->can.data_bittiming_const = - &m_can_data_bittiming_const_31X; - priv->can.ctrlmode_supported |= (m_can_niso_supported(priv) + m_can_dev->can.bittiming_const = m_can_dev->bit_timing ? + m_can_dev->bit_timing : &m_can_bittiming_const_31X; + + m_can_dev->can.data_bittiming_const = m_can_dev->data_timing ? + m_can_dev->data_timing : + &m_can_data_bittiming_const_31X; + + m_can_dev->can.ctrlmode_supported |= + (m_can_niso_supported(m_can_dev) ? CAN_CTRLMODE_FD_NON_ISO : 0); break; default: - dev_err(&pdev->dev, "Unsupported version number: %2d", - priv->version); + dev_err(m_can_dev->dev, "Unsupported version number: %2d", + m_can_dev->version); return -EINVAL; } - return 0; -} - -static int m_can_open(struct net_device *dev) -{ - struct m_can_priv *priv = netdev_priv(dev); - int err; - - err = m_can_clk_start(priv); - if (err) - return err; - - /* open the can device */ - err = open_candev(dev); - if (err) { - netdev_err(dev, "failed to open can device\n"); - goto exit_disable_clks; - } - - /* register interrupt handler */ - err = request_irq(dev->irq, m_can_isr, IRQF_SHARED, dev->name, - dev); - if (err < 0) { - netdev_err(dev, "failed to request interrupt\n"); - goto exit_irq_fail; - } - - /* start the m_can controller */ - m_can_start(dev); - - can_led_event(dev, CAN_LED_EVENT_OPEN); - napi_enable(&priv->napi); - netif_start_queue(dev); + if (m_can_dev->ops->init) + m_can_dev->ops->init(m_can_dev); return 0; - -exit_irq_fail: - close_candev(dev); -exit_disable_clks: - m_can_clk_stop(priv); - return err; } static void m_can_stop(struct net_device *dev) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); /* disable all interrupts */ - m_can_disable_all_interrupts(priv); + m_can_disable_all_interrupts(cdev); /* set the state as STOPPED */ - priv->can.state = CAN_STATE_STOPPED; + cdev->can.state = CAN_STATE_STOPPED; } static int m_can_close(struct net_device *dev) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); netif_stop_queue(dev); - napi_disable(&priv->napi); + + if (!cdev->is_peripheral) + napi_disable(&cdev->napi); + m_can_stop(dev); - m_can_clk_stop(priv); + m_can_clk_stop(cdev); free_irq(dev->irq, dev); + + if (cdev->is_peripheral) { + cdev->tx_skb = NULL; + destroy_workqueue(cdev->tx_wq); + cdev->tx_wq = NULL; + } + close_candev(dev); can_led_event(dev, CAN_LED_EVENT_STOP); @@ -1394,30 +1397,27 @@ static int m_can_close(struct net_device *dev) static int m_can_next_echo_skb_occupied(struct net_device *dev, int putidx) { - struct m_can_priv *priv = netdev_priv(dev); + struct m_can_classdev *cdev = netdev_priv(dev); /*get wrap around for loopback skb index */ - unsigned int wrap = priv->can.echo_skb_max; + unsigned int wrap = cdev->can.echo_skb_max; int next_idx; /* calculate next index */ next_idx = (++putidx >= wrap ? 0 : putidx); /* check if occupied */ - return !!priv->can.echo_skb[next_idx]; + return !!cdev->can.echo_skb[next_idx]; } -static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, - struct net_device *dev) +static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev) { - struct m_can_priv *priv = netdev_priv(dev); - struct canfd_frame *cf = (struct canfd_frame *)skb->data; + struct canfd_frame *cf = (struct canfd_frame *)cdev->tx_skb->data; + struct net_device *dev = cdev->net; + struct sk_buff *skb = cdev->tx_skb; u32 id, cccr, fdflags; int i; int putidx; - if (can_dropped_invalid_skb(dev, skb)) - return NETDEV_TX_OK; - /* Generate ID field for TX buffer Element */ /* Common to all supported M_CAN versions */ if (cf->can_id & CAN_EFF_FLAG) { @@ -1430,23 +1430,23 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, if (cf->can_id & CAN_RTR_FLAG) id |= TX_BUF_RTR; - if (priv->version == 30) { + if (cdev->version == 30) { netif_stop_queue(dev); /* message ram configuration */ - m_can_fifo_write(priv, 0, M_CAN_FIFO_ID, id); - m_can_fifo_write(priv, 0, M_CAN_FIFO_DLC, + 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); for (i = 0; i < cf->len; i += 4) - m_can_fifo_write(priv, 0, + m_can_fifo_write(cdev, 0, M_CAN_FIFO_DATA(i / 4), *(u32 *)(cf->data + i)); can_put_echo_skb(skb, dev, 0); - if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { - cccr = m_can_read(priv, M_CAN_CCCR); + if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) { + cccr = m_can_read(cdev, M_CAN_CCCR); cccr &= ~(CCCR_CMR_MASK << CCCR_CMR_SHIFT); if (can_is_canfd_skb(skb)) { if (cf->flags & CANFD_BRS) @@ -1458,28 +1458,35 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, } else { cccr |= CCCR_CMR_CAN << CCCR_CMR_SHIFT; } - m_can_write(priv, M_CAN_CCCR, cccr); + m_can_write(cdev, M_CAN_CCCR, cccr); } - m_can_write(priv, M_CAN_TXBTIE, 0x1); - m_can_write(priv, M_CAN_TXBAR, 0x1); + m_can_write(cdev, M_CAN_TXBTIE, 0x1); + m_can_write(cdev, M_CAN_TXBAR, 0x1); /* End of xmit function for version 3.0.x */ } else { /* Transmit routine for version >= v3.1.x */ /* Check if FIFO full */ - if (m_can_tx_fifo_full(priv)) { + if (m_can_tx_fifo_full(cdev)) { /* This shouldn't happen */ netif_stop_queue(dev); netdev_warn(dev, "TX queue active although FIFO is full."); - return NETDEV_TX_BUSY; + + if (cdev->is_peripheral) { + kfree_skb(skb); + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } else { + return NETDEV_TX_BUSY; + } } /* get put index for frame */ - putidx = ((m_can_read(priv, M_CAN_TXFQS) & TXFQS_TFQPI_MASK) + putidx = ((m_can_read(cdev, M_CAN_TXFQS) & TXFQS_TFQPI_MASK) >> TXFQS_TFQPI_SHIFT); /* Write ID Field to FIFO Element */ - m_can_fifo_write(priv, putidx, M_CAN_FIFO_ID, id); + m_can_fifo_write(cdev, putidx, M_CAN_FIFO_ID, id); /* get CAN FD configuration of frame */ fdflags = 0; @@ -1494,14 +1501,14 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, * it is used in TX interrupt for * sending the correct echo frame */ - m_can_fifo_write(priv, putidx, M_CAN_FIFO_DLC, + m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DLC, ((putidx << TX_BUF_MM_SHIFT) & TX_BUF_MM_MASK) | (can_len2dlc(cf->len) << 16) | fdflags | TX_BUF_EFC); for (i = 0; i < cf->len; i += 4) - m_can_fifo_write(priv, putidx, M_CAN_FIFO_DATA(i / 4), + m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DATA(i / 4), *(u32 *)(cf->data + i)); /* Push loopback echo. @@ -1510,17 +1517,123 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, can_put_echo_skb(skb, dev, putidx); /* Enable TX FIFO element to start transfer */ - m_can_write(priv, M_CAN_TXBAR, (1 << putidx)); + m_can_write(cdev, M_CAN_TXBAR, (1 << putidx)); /* stop network queue if fifo full */ - if (m_can_tx_fifo_full(priv) || - m_can_next_echo_skb_occupied(dev, putidx)) - netif_stop_queue(dev); + if (m_can_tx_fifo_full(cdev) || + m_can_next_echo_skb_occupied(dev, putidx)) + netif_stop_queue(dev); } return NETDEV_TX_OK; } +static void m_can_tx_work_queue(struct work_struct *ws) +{ + struct m_can_classdev *cdev = container_of(ws, struct m_can_classdev, + tx_work); + + m_can_tx_handler(cdev); + cdev->tx_skb = NULL; +} + +static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct m_can_classdev *cdev = netdev_priv(dev); + + if (can_dropped_invalid_skb(dev, skb)) + return NETDEV_TX_OK; + + if (cdev->is_peripheral) { + if (cdev->tx_skb) { + netdev_err(dev, "hard_xmit called while tx busy\n"); + return NETDEV_TX_BUSY; + } + + if (cdev->can.state == CAN_STATE_BUS_OFF) { + m_can_clean(dev); + } else { + /* Need to stop the queue to avoid numerous requests + * from being sent. Suggested improvement is to create + * a queueing mechanism that will queue the skbs and + * process them in order. + */ + cdev->tx_skb = skb; + netif_stop_queue(cdev->net); + queue_work(cdev->tx_wq, &cdev->tx_work); + } + } else { + cdev->tx_skb = skb; + return m_can_tx_handler(cdev); + } + + return NETDEV_TX_OK; +} + +static int m_can_open(struct net_device *dev) +{ + struct m_can_classdev *cdev = netdev_priv(dev); + int err; + + err = m_can_clk_start(cdev); + if (err) + return err; + + /* open the can device */ + err = open_candev(dev); + if (err) { + netdev_err(dev, "failed to open can device\n"); + goto exit_disable_clks; + } + + /* register interrupt handler */ + if (cdev->is_peripheral) { + cdev->tx_skb = NULL; + cdev->tx_wq = alloc_workqueue("mcan_wq", + WQ_FREEZABLE | WQ_MEM_RECLAIM, 0); + if (!cdev->tx_wq) { + err = -ENOMEM; + goto out_wq_fail; + } + + INIT_WORK(&cdev->tx_work, m_can_tx_work_queue); + + err = request_threaded_irq(dev->irq, NULL, m_can_isr, + IRQF_ONESHOT | IRQF_TRIGGER_FALLING, + dev->name, dev); + } else { + err = request_irq(dev->irq, m_can_isr, IRQF_SHARED, dev->name, + dev); + } + + if (err < 0) { + netdev_err(dev, "failed to request interrupt\n"); + goto exit_irq_fail; + } + + /* start the m_can controller */ + m_can_start(dev); + + can_led_event(dev, CAN_LED_EVENT_OPEN); + + if (!cdev->is_peripheral) + napi_enable(&cdev->napi); + + netif_start_queue(dev); + + return 0; + +exit_irq_fail: + if (cdev->is_peripheral) + destroy_workqueue(cdev->tx_wq); +out_wq_fail: + close_candev(dev); +exit_disable_clks: + m_can_clk_stop(cdev); + return err; +} + static const struct net_device_ops m_can_netdev_ops = { .ndo_open = m_can_open, .ndo_stop = m_can_close, @@ -1536,114 +1649,91 @@ static int register_m_can_dev(struct net_device *dev) return register_candev(dev); } -static void m_can_init_ram(struct m_can_priv *priv) -{ - int end, i, start; - - /* initialize the entire Message RAM in use to avoid possible - * ECC/parity checksum errors when reading an uninitialized buffer - */ - start = priv->mcfg[MRAM_SIDF].off; - end = priv->mcfg[MRAM_TXB].off + - priv->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE; - for (i = start; i < end; i += 4) - writel(0x0, priv->mram_base + i); -} - -static void m_can_of_parse_mram(struct m_can_priv *priv, +static void m_can_of_parse_mram(struct m_can_classdev *cdev, const u32 *mram_config_vals) { - priv->mcfg[MRAM_SIDF].off = mram_config_vals[0]; - priv->mcfg[MRAM_SIDF].num = mram_config_vals[1]; - priv->mcfg[MRAM_XIDF].off = priv->mcfg[MRAM_SIDF].off + - priv->mcfg[MRAM_SIDF].num * SIDF_ELEMENT_SIZE; - priv->mcfg[MRAM_XIDF].num = mram_config_vals[2]; - priv->mcfg[MRAM_RXF0].off = priv->mcfg[MRAM_XIDF].off + - priv->mcfg[MRAM_XIDF].num * XIDF_ELEMENT_SIZE; - priv->mcfg[MRAM_RXF0].num = mram_config_vals[3] & + cdev->mcfg[MRAM_SIDF].off = mram_config_vals[0]; + cdev->mcfg[MRAM_SIDF].num = mram_config_vals[1]; + cdev->mcfg[MRAM_XIDF].off = cdev->mcfg[MRAM_SIDF].off + + cdev->mcfg[MRAM_SIDF].num * SIDF_ELEMENT_SIZE; + cdev->mcfg[MRAM_XIDF].num = mram_config_vals[2]; + cdev->mcfg[MRAM_RXF0].off = cdev->mcfg[MRAM_XIDF].off + + cdev->mcfg[MRAM_XIDF].num * XIDF_ELEMENT_SIZE; + cdev->mcfg[MRAM_RXF0].num = mram_config_vals[3] & (RXFC_FS_MASK >> RXFC_FS_SHIFT); - priv->mcfg[MRAM_RXF1].off = priv->mcfg[MRAM_RXF0].off + - priv->mcfg[MRAM_RXF0].num * RXF0_ELEMENT_SIZE; - priv->mcfg[MRAM_RXF1].num = mram_config_vals[4] & + cdev->mcfg[MRAM_RXF1].off = cdev->mcfg[MRAM_RXF0].off + + cdev->mcfg[MRAM_RXF0].num * RXF0_ELEMENT_SIZE; + cdev->mcfg[MRAM_RXF1].num = mram_config_vals[4] & (RXFC_FS_MASK >> RXFC_FS_SHIFT); - priv->mcfg[MRAM_RXB].off = priv->mcfg[MRAM_RXF1].off + - priv->mcfg[MRAM_RXF1].num * RXF1_ELEMENT_SIZE; - priv->mcfg[MRAM_RXB].num = mram_config_vals[5]; - priv->mcfg[MRAM_TXE].off = priv->mcfg[MRAM_RXB].off + - priv->mcfg[MRAM_RXB].num * RXB_ELEMENT_SIZE; - priv->mcfg[MRAM_TXE].num = mram_config_vals[6]; - priv->mcfg[MRAM_TXB].off = priv->mcfg[MRAM_TXE].off + - priv->mcfg[MRAM_TXE].num * TXE_ELEMENT_SIZE; - priv->mcfg[MRAM_TXB].num = mram_config_vals[7] & + cdev->mcfg[MRAM_RXB].off = cdev->mcfg[MRAM_RXF1].off + + cdev->mcfg[MRAM_RXF1].num * RXF1_ELEMENT_SIZE; + cdev->mcfg[MRAM_RXB].num = mram_config_vals[5]; + cdev->mcfg[MRAM_TXE].off = cdev->mcfg[MRAM_RXB].off + + cdev->mcfg[MRAM_RXB].num * RXB_ELEMENT_SIZE; + cdev->mcfg[MRAM_TXE].num = mram_config_vals[6]; + cdev->mcfg[MRAM_TXB].off = cdev->mcfg[MRAM_TXE].off + + cdev->mcfg[MRAM_TXE].num * TXE_ELEMENT_SIZE; + cdev->mcfg[MRAM_TXB].num = mram_config_vals[7] & (TXBC_NDTB_MASK >> TXBC_NDTB_SHIFT); - dev_dbg(priv->device, - "mram_base %p sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n", - priv->mram_base, - priv->mcfg[MRAM_SIDF].off, priv->mcfg[MRAM_SIDF].num, - priv->mcfg[MRAM_XIDF].off, priv->mcfg[MRAM_XIDF].num, - priv->mcfg[MRAM_RXF0].off, priv->mcfg[MRAM_RXF0].num, - priv->mcfg[MRAM_RXF1].off, priv->mcfg[MRAM_RXF1].num, - priv->mcfg[MRAM_RXB].off, priv->mcfg[MRAM_RXB].num, - priv->mcfg[MRAM_TXE].off, priv->mcfg[MRAM_TXE].num, - priv->mcfg[MRAM_TXB].off, priv->mcfg[MRAM_TXB].num); - - m_can_init_ram(priv); + dev_dbg(cdev->dev, + "sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n", + cdev->mcfg[MRAM_SIDF].off, cdev->mcfg[MRAM_SIDF].num, + cdev->mcfg[MRAM_XIDF].off, cdev->mcfg[MRAM_XIDF].num, + cdev->mcfg[MRAM_RXF0].off, cdev->mcfg[MRAM_RXF0].num, + cdev->mcfg[MRAM_RXF1].off, cdev->mcfg[MRAM_RXF1].num, + cdev->mcfg[MRAM_RXB].off, cdev->mcfg[MRAM_RXB].num, + cdev->mcfg[MRAM_TXE].off, cdev->mcfg[MRAM_TXE].num, + cdev->mcfg[MRAM_TXB].off, cdev->mcfg[MRAM_TXB].num); } -static int m_can_plat_probe(struct platform_device *pdev) +void m_can_init_ram(struct m_can_classdev *cdev) { - struct net_device *dev; - struct m_can_priv *priv; - struct resource *res; - void __iomem *addr; - void __iomem *mram_addr; - struct clk *hclk, *cclk; - int irq, ret; - struct device_node *np; - u32 mram_config_vals[MRAM_CFG_LEN]; - u32 tx_fifo_size; - - np = pdev->dev.of_node; + int end, i, start; - hclk = devm_clk_get(&pdev->dev, "hclk"); - cclk = devm_clk_get(&pdev->dev, "cclk"); + /* initialize the entire Message RAM in use to avoid possible + * ECC/parity checksum errors when reading an uninitialized buffer + */ + start = cdev->mcfg[MRAM_SIDF].off; + end = cdev->mcfg[MRAM_TXB].off + + cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE; - if (IS_ERR(hclk) || IS_ERR(cclk)) { - dev_err(&pdev->dev, "no clock found\n"); - ret = -ENODEV; - goto failed_ret; - } + for (i = start; i < end; i += 4) + m_can_fifo_write_no_off(cdev, i, 0x0); +} +EXPORT_SYMBOL_GPL(m_can_init_ram); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can"); - addr = devm_ioremap_resource(&pdev->dev, res); - irq = platform_get_irq_byname(pdev, "int0"); +int m_can_class_get_clocks(struct m_can_classdev *m_can_dev) +{ + int ret = 0; - if (IS_ERR(addr) || irq < 0) { - ret = -EINVAL; - goto failed_ret; - } + m_can_dev->hclk = devm_clk_get(m_can_dev->dev, "hclk"); + m_can_dev->cclk = devm_clk_get(m_can_dev->dev, "cclk"); - /* message ram could be shared */ - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram"); - if (!res) { + if (IS_ERR(m_can_dev->cclk)) { + dev_err(m_can_dev->dev, "no clock found\n"); ret = -ENODEV; - goto failed_ret; } - mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res)); - if (!mram_addr) { - ret = -ENOMEM; - goto failed_ret; - } + return ret; +} +EXPORT_SYMBOL_GPL(m_can_class_get_clocks); - /* get message ram configuration */ - ret = of_property_read_u32_array(np, "bosch,mram-cfg", - mram_config_vals, - sizeof(mram_config_vals) / 4); +struct m_can_classdev *m_can_class_allocate_dev(struct device *dev) +{ + struct m_can_classdev *class_dev = NULL; + u32 mram_config_vals[MRAM_CFG_LEN]; + struct net_device *net_dev; + u32 tx_fifo_size; + int ret; + + ret = fwnode_property_read_u32_array(dev_fwnode(dev), + "bosch,mram-cfg", + mram_config_vals, + sizeof(mram_config_vals) / 4); if (ret) { - dev_err(&pdev->dev, "Could not get Message RAM configuration."); - goto failed_ret; + dev_err(dev, "Could not get Message RAM configuration."); + goto out; } /* Get TX FIFO size @@ -1652,101 +1742,110 @@ static int m_can_plat_probe(struct platform_device *pdev) tx_fifo_size = mram_config_vals[7]; /* allocate the m_can device */ - dev = alloc_candev(sizeof(*priv), tx_fifo_size); - if (!dev) { - ret = -ENOMEM; - goto failed_ret; + net_dev = alloc_candev(sizeof(*class_dev), tx_fifo_size); + if (!net_dev) { + dev_err(dev, "Failed to allocate CAN device"); + goto out; } - priv = netdev_priv(dev); - dev->irq = irq; - priv->device = &pdev->dev; - priv->hclk = hclk; - priv->cclk = cclk; - priv->can.clock.freq = clk_get_rate(cclk); - priv->mram_base = mram_addr; + class_dev = netdev_priv(net_dev); + if (!class_dev) { + dev_err(dev, "Failed to init netdev cdevate"); + goto out; + } - platform_set_drvdata(pdev, dev); - SET_NETDEV_DEV(dev, &pdev->dev); + class_dev->net = net_dev; + class_dev->dev = dev; + SET_NETDEV_DEV(net_dev, dev); - /* Enable clocks. Necessary to read Core Release in order to determine - * M_CAN version - */ - pm_runtime_enable(&pdev->dev); - ret = m_can_clk_start(priv); - if (ret) - goto pm_runtime_fail; + m_can_of_parse_mram(class_dev, mram_config_vals); +out: + return class_dev; +} +EXPORT_SYMBOL_GPL(m_can_class_allocate_dev); + +int m_can_class_register(struct m_can_classdev *m_can_dev) +{ + int ret; - ret = m_can_dev_setup(pdev, dev, addr); + if (m_can_dev->pm_clock_support) { + pm_runtime_enable(m_can_dev->dev); + ret = m_can_clk_start(m_can_dev); + if (ret) + goto pm_runtime_fail; + } + + ret = m_can_dev_setup(m_can_dev); if (ret) goto clk_disable; - ret = register_m_can_dev(dev); + ret = register_m_can_dev(m_can_dev->net); if (ret) { - dev_err(&pdev->dev, "registering %s failed (err=%d)\n", - KBUILD_MODNAME, ret); + dev_err(m_can_dev->dev, "registering %s failed (err=%d)\n", + m_can_dev->net->name, ret); goto clk_disable; } - m_can_of_parse_mram(priv, mram_config_vals); - - devm_can_led_init(dev); + devm_can_led_init(m_can_dev->net); - of_can_transceiver(dev); + of_can_transceiver(m_can_dev->net); - dev_info(&pdev->dev, "%s device registered (irq=%d, version=%d)\n", - KBUILD_MODNAME, dev->irq, priv->version); + dev_info(m_can_dev->dev, "%s device registered (irq=%d, version=%d)\n", + KBUILD_MODNAME, m_can_dev->net->irq, m_can_dev->version); /* Probe finished * Stop clocks. They will be reactivated once the M_CAN device is opened */ clk_disable: - m_can_clk_stop(priv); + m_can_clk_stop(m_can_dev); pm_runtime_fail: if (ret) { - pm_runtime_disable(&pdev->dev); - free_candev(dev); + if (m_can_dev->pm_clock_support) + pm_runtime_disable(m_can_dev->dev); + free_candev(m_can_dev->net); } -failed_ret: + return ret; } +EXPORT_SYMBOL_GPL(m_can_class_register); -static __maybe_unused int m_can_suspend(struct device *dev) +int m_can_class_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); - struct m_can_priv *priv = netdev_priv(ndev); + struct m_can_classdev *cdev = netdev_priv(ndev); if (netif_running(ndev)) { netif_stop_queue(ndev); netif_device_detach(ndev); m_can_stop(ndev); - m_can_clk_stop(priv); + m_can_clk_stop(cdev); } pinctrl_pm_select_sleep_state(dev); - priv->can.state = CAN_STATE_SLEEPING; + cdev->can.state = CAN_STATE_SLEEPING; return 0; } +EXPORT_SYMBOL_GPL(m_can_class_suspend); -static __maybe_unused int m_can_resume(struct device *dev) +int m_can_class_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); - struct m_can_priv *priv = netdev_priv(ndev); + struct m_can_classdev *cdev = netdev_priv(ndev); pinctrl_pm_select_default_state(dev); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + cdev->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(ndev)) { int ret; - ret = m_can_clk_start(priv); + ret = m_can_clk_start(cdev); if (ret) return ret; - m_can_init_ram(priv); + m_can_init_ram(cdev); m_can_start(ndev); netif_device_attach(ndev); netif_start_queue(ndev); @@ -1754,79 +1853,19 @@ static __maybe_unused int m_can_resume(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(m_can_class_resume); -static void unregister_m_can_dev(struct net_device *dev) +void m_can_class_unregister(struct m_can_classdev *m_can_dev) { - unregister_candev(dev); -} + unregister_candev(m_can_dev->net); -static int m_can_plat_remove(struct platform_device *pdev) -{ - struct net_device *dev = platform_get_drvdata(pdev); + m_can_clk_stop(m_can_dev); - unregister_m_can_dev(dev); - - pm_runtime_disable(&pdev->dev); - - platform_set_drvdata(pdev, NULL); - - free_candev(dev); - - return 0; -} - -static int __maybe_unused m_can_runtime_suspend(struct device *dev) -{ - struct net_device *ndev = dev_get_drvdata(dev); - struct m_can_priv *priv = netdev_priv(ndev); - - clk_disable_unprepare(priv->cclk); - clk_disable_unprepare(priv->hclk); - - return 0; -} - -static int __maybe_unused m_can_runtime_resume(struct device *dev) -{ - struct net_device *ndev = dev_get_drvdata(dev); - struct m_can_priv *priv = netdev_priv(ndev); - int err; - - err = clk_prepare_enable(priv->hclk); - if (err) - return err; - - err = clk_prepare_enable(priv->cclk); - if (err) - clk_disable_unprepare(priv->hclk); - - return err; + free_candev(m_can_dev->net); } - -static const struct dev_pm_ops m_can_pmops = { - SET_RUNTIME_PM_OPS(m_can_runtime_suspend, - m_can_runtime_resume, NULL) - SET_SYSTEM_SLEEP_PM_OPS(m_can_suspend, m_can_resume) -}; - -static const struct of_device_id m_can_of_table[] = { - { .compatible = "bosch,m_can", .data = NULL }, - { /* sentinel */ }, -}; -MODULE_DEVICE_TABLE(of, m_can_of_table); - -static struct platform_driver m_can_plat_driver = { - .driver = { - .name = KBUILD_MODNAME, - .of_match_table = m_can_of_table, - .pm = &m_can_pmops, - }, - .probe = m_can_plat_probe, - .remove = m_can_plat_remove, -}; - -module_platform_driver(m_can_plat_driver); +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"); MODULE_DESCRIPTION("CAN bus driver for Bosch M_CAN controller"); diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h new file mode 100644 index 000000000000..49f42b50627a --- /dev/null +++ b/drivers/net/can/m_can/m_can.h @@ -0,0 +1,110 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* CAN bus driver for Bosch M_CAN controller + * Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/ + */ + +#ifndef _CAN_M_CAN_H_ +#define _CAN_M_CAN_H_ + +#include <linux/can/core.h> +#include <linux/can/led.h> +#include <linux/completion.h> +#include <linux/device.h> +#include <linux/dma-mapping.h> +#include <linux/freezer.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/pm_runtime.h> +#include <linux/iopoll.h> +#include <linux/can/dev.h> +#include <linux/pinctrl/consumer.h> + +/* m_can lec values */ +enum m_can_lec_type { + LEC_NO_ERROR = 0, + LEC_STUFF_ERROR, + LEC_FORM_ERROR, + LEC_ACK_ERROR, + LEC_BIT1_ERROR, + LEC_BIT0_ERROR, + LEC_CRC_ERROR, + LEC_UNUSED, +}; + +enum m_can_mram_cfg { + MRAM_SIDF = 0, + MRAM_XIDF, + MRAM_RXF0, + MRAM_RXF1, + MRAM_RXB, + MRAM_TXE, + MRAM_TXB, + MRAM_CFG_NUM, +}; + +/* address offset and element number for each FIFO/Buffer in the Message RAM */ +struct mram_cfg { + u16 off; + u8 num; +}; + +struct m_can_classdev; +struct m_can_ops { + /* Device specific call backs */ + int (*clear_interrupts)(struct m_can_classdev *cdev); + u32 (*read_reg)(struct m_can_classdev *cdev, int reg); + int (*write_reg)(struct m_can_classdev *cdev, int reg, int val); + u32 (*read_fifo)(struct m_can_classdev *cdev, int addr_offset); + int (*write_fifo)(struct m_can_classdev *cdev, int addr_offset, + int val); + int (*init)(struct m_can_classdev *cdev); +}; + +struct m_can_classdev { + struct can_priv can; + struct napi_struct napi; + struct net_device *net; + struct device *dev; + struct clk *hclk; + struct clk *cclk; + + struct workqueue_struct *tx_wq; + struct work_struct tx_work; + struct sk_buff *tx_skb; + + struct can_bittiming_const *bit_timing; + struct can_bittiming_const *data_timing; + + struct m_can_ops *ops; + + void *device_data; + + int version; + int freq; + u32 irqstatus; + + int pm_clock_support; + int is_peripheral; + + struct mram_cfg mcfg[MRAM_CFG_NUM]; +}; + +struct m_can_classdev *m_can_class_allocate_dev(struct device *dev); +int m_can_class_register(struct m_can_classdev *cdev); +void m_can_class_unregister(struct m_can_classdev *cdev); +int m_can_class_get_clocks(struct m_can_classdev *cdev); +void m_can_init_ram(struct m_can_classdev *priv); +void m_can_config_endisable(struct m_can_classdev *priv, bool enable); + +int m_can_class_suspend(struct device *dev); +int m_can_class_resume(struct device *dev); +#endif /* _CAN_M_H_ */ diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c new file mode 100644 index 000000000000..c2989e0431f2 --- /dev/null +++ b/drivers/net/can/m_can/m_can_platform.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +// IOMapped CAN bus driver for Bosch M_CAN controller +// Copyright (C) 2014 Freescale Semiconductor, Inc. +// Dong Aisheng <b29396@freescale.com> +// +// Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/ + +#include <linux/platform_device.h> + +#include "m_can.h" + +struct m_can_plat_priv { + void __iomem *base; + void __iomem *mram_base; +}; + +static u32 iomap_read_reg(struct m_can_classdev *cdev, int reg) +{ + struct m_can_plat_priv *priv = + (struct m_can_plat_priv *)cdev->device_data; + + return readl(priv->base + reg); +} + +static u32 iomap_read_fifo(struct m_can_classdev *cdev, int offset) +{ + struct m_can_plat_priv *priv = + (struct m_can_plat_priv *)cdev->device_data; + + return readl(priv->mram_base + offset); +} + +static int iomap_write_reg(struct m_can_classdev *cdev, int reg, int val) +{ + struct m_can_plat_priv *priv = + (struct m_can_plat_priv *)cdev->device_data; + + writel(val, priv->base + reg); + + return 0; +} + +static int iomap_write_fifo(struct m_can_classdev *cdev, int offset, int val) +{ + struct m_can_plat_priv *priv = + (struct m_can_plat_priv *)cdev->device_data; + + writel(val, priv->mram_base + offset); + + return 0; +} + +static struct m_can_ops m_can_plat_ops = { + .read_reg = iomap_read_reg, + .write_reg = iomap_write_reg, + .write_fifo = iomap_write_fifo, + .read_fifo = iomap_read_fifo, +}; + +static int m_can_plat_probe(struct platform_device *pdev) +{ + struct m_can_classdev *mcan_class; + struct m_can_plat_priv *priv; + struct resource *res; + void __iomem *addr; + void __iomem *mram_addr; + int irq, ret = 0; + + mcan_class = m_can_class_allocate_dev(&pdev->dev); + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + mcan_class->device_data = priv; + + m_can_class_get_clocks(mcan_class); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can"); + addr = devm_ioremap_resource(&pdev->dev, res); + irq = platform_get_irq_byname(pdev, "int0"); + if (IS_ERR(addr) || irq < 0) { + ret = -EINVAL; + goto failed_ret; + } + + /* message ram could be shared */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram"); + if (!res) { + ret = -ENODEV; + goto failed_ret; + } + + mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res)); + if (!mram_addr) { + ret = -ENOMEM; + goto failed_ret; + } + + priv->base = addr; + priv->mram_base = mram_addr; + + mcan_class->net->irq = irq; + mcan_class->pm_clock_support = 1; + mcan_class->can.clock.freq = clk_get_rate(mcan_class->cclk); + mcan_class->dev = &pdev->dev; + + mcan_class->ops = &m_can_plat_ops; + + mcan_class->is_peripheral = false; + + platform_set_drvdata(pdev, mcan_class->dev); + + m_can_init_ram(mcan_class); + + ret = m_can_class_register(mcan_class); + +failed_ret: + return ret; +} + +static __maybe_unused int m_can_suspend(struct device *dev) +{ + return m_can_class_suspend(dev); +} + +static __maybe_unused int m_can_resume(struct device *dev) +{ + return m_can_class_resume(dev); +} + +static int m_can_plat_remove(struct platform_device *pdev) +{ + struct net_device *dev = platform_get_drvdata(pdev); + struct m_can_classdev *mcan_class = netdev_priv(dev); + + m_can_class_unregister(mcan_class); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static int __maybe_unused m_can_runtime_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct m_can_classdev *mcan_class = netdev_priv(ndev); + + m_can_class_suspend(dev); + + clk_disable_unprepare(mcan_class->cclk); + clk_disable_unprepare(mcan_class->hclk); + + return 0; +} + +static int __maybe_unused m_can_runtime_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct m_can_classdev *mcan_class = netdev_priv(ndev); + int err; + + err = clk_prepare_enable(mcan_class->hclk); + if (err) + return err; + + err = clk_prepare_enable(mcan_class->cclk); + if (err) + clk_disable_unprepare(mcan_class->hclk); + + m_can_class_resume(dev); + + return err; +} + +static const struct dev_pm_ops m_can_pmops = { + SET_RUNTIME_PM_OPS(m_can_runtime_suspend, + m_can_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(m_can_suspend, m_can_resume) +}; + +static const struct of_device_id m_can_of_table[] = { + { .compatible = "bosch,m_can", .data = NULL }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, m_can_of_table); + +static struct platform_driver m_can_plat_driver = { + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = m_can_of_table, + .pm = &m_can_pmops, + }, + .probe = m_can_plat_probe, + .remove = m_can_plat_remove, +}; + +module_platform_driver(m_can_plat_driver); + +MODULE_AUTHOR("Dong Aisheng <b29396@freescale.com>"); +MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("M_CAN driver for IO Mapped Bosch controllers"); diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c new file mode 100644 index 000000000000..b115b2e5333f --- /dev/null +++ b/drivers/net/can/m_can/tcan4x5x.c @@ -0,0 +1,532 @@ +// SPDX-License-Identifier: GPL-2.0 +// SPI to CAN driver for the Texas Instruments TCAN4x5x +// Copyright (C) 2018-19 Texas Instruments Incorporated - http://www.ti.com/ + +#include <linux/regmap.h> +#include <linux/spi/spi.h> + +#include <linux/regulator/consumer.h> +#include <linux/gpio/consumer.h> + +#include "m_can.h" + +#define DEVICE_NAME "tcan4x5x" +#define TCAN4X5X_EXT_CLK_DEF 40000000 + +#define TCAN4X5X_DEV_ID0 0x00 +#define TCAN4X5X_DEV_ID1 0x04 +#define TCAN4X5X_REV 0x08 +#define TCAN4X5X_STATUS 0x0C +#define TCAN4X5X_ERROR_STATUS 0x10 +#define TCAN4X5X_CONTROL 0x14 + +#define TCAN4X5X_CONFIG 0x800 +#define TCAN4X5X_TS_PRESCALE 0x804 +#define TCAN4X5X_TEST_REG 0x808 +#define TCAN4X5X_INT_FLAGS 0x820 +#define TCAN4X5X_MCAN_INT_REG 0x824 +#define TCAN4X5X_INT_EN 0x830 + +/* Interrupt bits */ +#define TCAN4X5X_CANBUSTERMOPEN_INT_EN BIT(30) +#define TCAN4X5X_CANHCANL_INT_EN BIT(29) +#define TCAN4X5X_CANHBAT_INT_EN BIT(28) +#define TCAN4X5X_CANLGND_INT_EN BIT(27) +#define TCAN4X5X_CANBUSOPEN_INT_EN BIT(26) +#define TCAN4X5X_CANBUSGND_INT_EN BIT(25) +#define TCAN4X5X_CANBUSBAT_INT_EN BIT(24) +#define TCAN4X5X_UVSUP_INT_EN BIT(22) +#define TCAN4X5X_UVIO_INT_EN BIT(21) +#define TCAN4X5X_TSD_INT_EN BIT(19) +#define TCAN4X5X_ECCERR_INT_EN BIT(16) +#define TCAN4X5X_CANINT_INT_EN BIT(15) +#define TCAN4X5X_LWU_INT_EN BIT(14) +#define TCAN4X5X_CANSLNT_INT_EN BIT(10) +#define TCAN4X5X_CANDOM_INT_EN BIT(8) +#define TCAN4X5X_CANBUS_ERR_INT_EN BIT(5) +#define TCAN4X5X_BUS_FAULT BIT(4) +#define TCAN4X5X_MCAN_INT BIT(1) +#define TCAN4X5X_ENABLE_TCAN_INT \ + (TCAN4X5X_MCAN_INT | TCAN4X5X_BUS_FAULT | \ + TCAN4X5X_CANBUS_ERR_INT_EN | TCAN4X5X_CANINT_INT_EN) + +/* MCAN Interrupt bits */ +#define TCAN4X5X_MCAN_IR_ARA BIT(29) +#define TCAN4X5X_MCAN_IR_PED BIT(28) +#define TCAN4X5X_MCAN_IR_PEA BIT(27) +#define TCAN4X5X_MCAN_IR_WD BIT(26) +#define TCAN4X5X_MCAN_IR_BO BIT(25) +#define TCAN4X5X_MCAN_IR_EW BIT(24) +#define TCAN4X5X_MCAN_IR_EP BIT(23) +#define TCAN4X5X_MCAN_IR_ELO BIT(22) +#define TCAN4X5X_MCAN_IR_BEU BIT(21) +#define TCAN4X5X_MCAN_IR_BEC BIT(20) +#define TCAN4X5X_MCAN_IR_DRX BIT(19) +#define TCAN4X5X_MCAN_IR_TOO BIT(18) +#define TCAN4X5X_MCAN_IR_MRAF BIT(17) +#define TCAN4X5X_MCAN_IR_TSW BIT(16) +#define TCAN4X5X_MCAN_IR_TEFL BIT(15) +#define TCAN4X5X_MCAN_IR_TEFF BIT(14) +#define TCAN4X5X_MCAN_IR_TEFW BIT(13) +#define TCAN4X5X_MCAN_IR_TEFN BIT(12) +#define TCAN4X5X_MCAN_IR_TFE BIT(11) +#define TCAN4X5X_MCAN_IR_TCF BIT(10) +#define TCAN4X5X_MCAN_IR_TC BIT(9) +#define TCAN4X5X_MCAN_IR_HPM BIT(8) +#define TCAN4X5X_MCAN_IR_RF1L BIT(7) +#define TCAN4X5X_MCAN_IR_RF1F BIT(6) +#define TCAN4X5X_MCAN_IR_RF1W BIT(5) +#define TCAN4X5X_MCAN_IR_RF1N BIT(4) +#define TCAN4X5X_MCAN_IR_RF0L BIT(3) +#define TCAN4X5X_MCAN_IR_RF0F BIT(2) +#define TCAN4X5X_MCAN_IR_RF0W BIT(1) +#define TCAN4X5X_MCAN_IR_RF0N BIT(0) +#define TCAN4X5X_ENABLE_MCAN_INT \ + (TCAN4X5X_MCAN_IR_TC | TCAN4X5X_MCAN_IR_RF0N | \ + TCAN4X5X_MCAN_IR_RF1N | TCAN4X5X_MCAN_IR_RF0F | \ + TCAN4X5X_MCAN_IR_RF1F) + +#define TCAN4X5X_MRAM_START 0x8000 +#define TCAN4X5X_MCAN_OFFSET 0x1000 +#define TCAN4X5X_MAX_REGISTER 0x8fff + +#define TCAN4X5X_CLEAR_ALL_INT 0xffffffff +#define TCAN4X5X_SET_ALL_INT 0xffffffff + +#define TCAN4X5X_WRITE_CMD (0x61 << 24) +#define TCAN4X5X_READ_CMD (0x41 << 24) + +#define TCAN4X5X_MODE_SEL_MASK (BIT(7) | BIT(6)) +#define TCAN4X5X_MODE_SLEEP 0x00 +#define TCAN4X5X_MODE_STANDBY BIT(6) +#define TCAN4X5X_MODE_NORMAL BIT(7) + +#define TCAN4X5X_SW_RESET BIT(2) + +#define TCAN4X5X_MCAN_CONFIGURED BIT(5) +#define TCAN4X5X_WATCHDOG_EN BIT(3) +#define TCAN4X5X_WD_60_MS_TIMER 0 +#define TCAN4X5X_WD_600_MS_TIMER BIT(28) +#define TCAN4X5X_WD_3_S_TIMER BIT(29) +#define TCAN4X5X_WD_6_S_TIMER (BIT(28) | BIT(29)) + +struct tcan4x5x_priv { + struct regmap *regmap; + struct spi_device *spi; + struct mutex tcan4x5x_lock; /* SPI device lock */ + + struct m_can_classdev *mcan_dev; + + struct gpio_desc *reset_gpio; + struct gpio_desc *interrupt_gpio; + 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 = { + .name = DEVICE_NAME, + .tseg1_min = 2, + .tseg1_max = 31, + .tseg2_min = 2, + .tseg2_max = 16, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 32, + .brp_inc = 1, +}; + +static struct can_bittiming_const tcan4x5x_data_bittiming_const = { + .name = DEVICE_NAME, + .tseg1_min = 1, + .tseg1_max = 32, + .tseg2_min = 1, + .tseg2_max = 16, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 32, + .brp_inc = 1, +}; + +static void tcan4x5x_check_wake(struct tcan4x5x_priv *priv) +{ + int wake_state = 0; + + if (priv->device_state_gpio) + wake_state = gpiod_get_value(priv->device_state_gpio); + + if (priv->device_wake_gpio && wake_state) { + gpiod_set_value(priv->device_wake_gpio, 0); + usleep_range(5, 50); + gpiod_set_value(priv->device_wake_gpio, 1); + } +} + +static int regmap_spi_gather_write(void *context, const void *reg, + size_t reg_len, const void *val, + size_t val_len) +{ + struct device *dev = context; + struct spi_device *spi = to_spi_device(dev); + struct spi_message m; + u32 addr; + struct spi_transfer t[2] = { + { .tx_buf = &addr, .len = reg_len, .cs_change = 0,}, + { .tx_buf = val, .len = val_len, }, + }; + + addr = TCAN4X5X_WRITE_CMD | (*((u16 *)reg) << 8) | val_len >> 3; + + spi_message_init(&m); + spi_message_add_tail(&t[0], &m); + spi_message_add_tail(&t[1], &m); + + return spi_sync(spi, &m); +} + +static int tcan4x5x_regmap_write(void *context, const void *data, size_t count) +{ + u16 *reg = (u16 *)(data); + const u32 *val = data + 4; + + return regmap_spi_gather_write(context, reg, 4, val, count); +} + +static int regmap_spi_async_write(void *context, + const void *reg, size_t reg_len, + const void *val, size_t val_len, + struct regmap_async *a) +{ + return -ENOTSUPP; +} + +static struct regmap_async *regmap_spi_async_alloc(void) +{ + return NULL; +} + +static int tcan4x5x_regmap_read(void *context, + const void *reg, size_t reg_size, + void *val, size_t val_size) +{ + struct device *dev = context; + struct spi_device *spi = to_spi_device(dev); + + u32 addr = TCAN4X5X_READ_CMD | (*((u16 *)reg) << 8) | val_size >> 2; + + return spi_write_then_read(spi, &addr, reg_size, (u32 *)val, val_size); +} + +static struct regmap_bus tcan4x5x_bus = { + .write = tcan4x5x_regmap_write, + .gather_write = regmap_spi_gather_write, + .async_write = regmap_spi_async_write, + .async_alloc = regmap_spi_async_alloc, + .read = tcan4x5x_regmap_read, + .read_flag_mask = 0x00, + .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, + .val_format_endian_default = REGMAP_ENDIAN_NATIVE, +}; + +static u32 tcan4x5x_read_reg(struct m_can_classdev *cdev, int reg) +{ + struct tcan4x5x_priv *priv = (struct tcan4x5x_priv *)cdev->device_data; + u32 val; + + tcan4x5x_check_wake(priv); + + regmap_read(priv->regmap, priv->reg_offset + reg, &val); + + return val; +} + +static u32 tcan4x5x_read_fifo(struct m_can_classdev *cdev, int addr_offset) +{ + struct tcan4x5x_priv *priv = (struct tcan4x5x_priv *)cdev->device_data; + u32 val; + + tcan4x5x_check_wake(priv); + + regmap_read(priv->regmap, priv->mram_start + addr_offset, &val); + + return val; +} + +static int tcan4x5x_write_reg(struct m_can_classdev *cdev, int reg, int val) +{ + struct tcan4x5x_priv *priv = (struct tcan4x5x_priv *)cdev->device_data; + + tcan4x5x_check_wake(priv); + + return regmap_write(priv->regmap, priv->reg_offset + reg, val); +} + +static int tcan4x5x_write_fifo(struct m_can_classdev *cdev, + int addr_offset, int val) +{ + struct tcan4x5x_priv *priv = + (struct tcan4x5x_priv *)cdev->device_data; + + tcan4x5x_check_wake(priv); + + return regmap_write(priv->regmap, priv->mram_start + addr_offset, val); +} + +static int tcan4x5x_power_enable(struct regulator *reg, int enable) +{ + if (IS_ERR_OR_NULL(reg)) + return 0; + + if (enable) + return regulator_enable(reg); + else + return regulator_disable(reg); +} + +static int tcan4x5x_write_tcan_reg(struct m_can_classdev *cdev, + int reg, int val) +{ + struct tcan4x5x_priv *priv = + (struct tcan4x5x_priv *)cdev->device_data; + + tcan4x5x_check_wake(priv); + + return regmap_write(priv->regmap, reg, val); +} + +static int tcan4x5x_clear_interrupts(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = + (struct tcan4x5x_priv *)cdev->device_data; + int ret; + + tcan4x5x_check_wake(tcan4x5x); + + ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_STATUS, + TCAN4X5X_CLEAR_ALL_INT); + if (ret) + return ret; + + ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_MCAN_INT_REG, + TCAN4X5X_ENABLE_MCAN_INT); + if (ret) + return ret; + + ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_INT_FLAGS, + TCAN4X5X_CLEAR_ALL_INT); + if (ret) + return ret; + + ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_ERROR_STATUS, + TCAN4X5X_CLEAR_ALL_INT); + if (ret) + return ret; + + return ret; +} + +static int tcan4x5x_init(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = + (struct tcan4x5x_priv *)cdev->device_data; + int ret; + + tcan4x5x_check_wake(tcan4x5x); + + ret = tcan4x5x_clear_interrupts(cdev); + if (ret) + return ret; + + ret = tcan4x5x_write_tcan_reg(cdev, TCAN4X5X_INT_EN, + TCAN4X5X_ENABLE_TCAN_INT); + if (ret) + return ret; + + ret = regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG, + TCAN4X5X_MODE_SEL_MASK, TCAN4X5X_MODE_NORMAL); + if (ret) + return ret; + + /* Zero out the MCAN buffers */ + m_can_init_ram(cdev); + + return ret; +} + +static int tcan4x5x_parse_config(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = + (struct tcan4x5x_priv *)cdev->device_data; + + tcan4x5x->interrupt_gpio = devm_gpiod_get(cdev->dev, "data-ready", + GPIOD_IN); + if (IS_ERR(tcan4x5x->interrupt_gpio)) { + dev_err(cdev->dev, "data-ready gpio not defined\n"); + return -EINVAL; + } + + tcan4x5x->device_wake_gpio = devm_gpiod_get(cdev->dev, "device-wake", + GPIOD_OUT_HIGH); + if (IS_ERR(tcan4x5x->device_wake_gpio)) { + dev_err(cdev->dev, "device-wake gpio not defined\n"); + return -EINVAL; + } + + tcan4x5x->reset_gpio = devm_gpiod_get_optional(cdev->dev, "reset", + GPIOD_OUT_LOW); + if (IS_ERR(tcan4x5x->reset_gpio)) + tcan4x5x->reset_gpio = NULL; + + tcan4x5x->device_state_gpio = devm_gpiod_get_optional(cdev->dev, + "device-state", + GPIOD_IN); + if (IS_ERR(tcan4x5x->device_state_gpio)) + tcan4x5x->device_state_gpio = NULL; + + cdev->net->irq = gpiod_to_irq(tcan4x5x->interrupt_gpio); + + tcan4x5x->power = devm_regulator_get_optional(cdev->dev, + "vsup"); + if (PTR_ERR(tcan4x5x->power) == -EPROBE_DEFER) + return -EPROBE_DEFER; + + return 0; +} + +static const struct regmap_config tcan4x5x_regmap = { + .reg_bits = 32, + .val_bits = 32, + .cache_type = REGCACHE_NONE, + .max_register = TCAN4X5X_MAX_REGISTER, +}; + +static struct m_can_ops tcan4x5x_ops = { + .init = tcan4x5x_init, + .read_reg = tcan4x5x_read_reg, + .write_reg = tcan4x5x_write_reg, + .write_fifo = tcan4x5x_write_fifo, + .read_fifo = tcan4x5x_read_fifo, + .clear_interrupts = tcan4x5x_clear_interrupts, +}; + +static int tcan4x5x_can_probe(struct spi_device *spi) +{ + struct tcan4x5x_priv *priv; + struct m_can_classdev *mcan_class; + int freq, ret; + + mcan_class = m_can_class_allocate_dev(&spi->dev); + priv = devm_kzalloc(&spi->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + mcan_class->device_data = priv; + + m_can_class_get_clocks(mcan_class); + if (IS_ERR(mcan_class->cclk)) { + dev_err(&spi->dev, "no CAN clock source defined\n"); + freq = TCAN4X5X_EXT_CLK_DEF; + } else { + freq = clk_get_rate(mcan_class->cclk); + } + + /* Sanity check */ + if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) + return -ERANGE; + + priv->reg_offset = TCAN4X5X_MCAN_OFFSET; + priv->mram_start = TCAN4X5X_MRAM_START; + priv->spi = spi; + priv->mcan_dev = mcan_class; + + mcan_class->pm_clock_support = 0; + mcan_class->can.clock.freq = freq; + mcan_class->dev = &spi->dev; + mcan_class->ops = &tcan4x5x_ops; + mcan_class->is_peripheral = true; + mcan_class->bit_timing = &tcan4x5x_bittiming_const; + mcan_class->data_timing = &tcan4x5x_data_bittiming_const; + + spi_set_drvdata(spi, priv); + + ret = tcan4x5x_parse_config(mcan_class); + if (ret) + goto out_clk; + + /* Configure the SPI bus */ + spi->bits_per_word = 32; + ret = spi_setup(spi); + if (ret) + goto out_clk; + + priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus, + &spi->dev, &tcan4x5x_regmap); + + mutex_init(&priv->tcan4x5x_lock); + + tcan4x5x_power_enable(priv->power, 1); + + ret = m_can_class_register(mcan_class); + if (ret) + goto out_power; + + netdev_info(mcan_class->net, "TCAN4X5X successfully initialized.\n"); + return 0; + +out_power: + tcan4x5x_power_enable(priv->power, 0); +out_clk: + if (!IS_ERR(mcan_class->cclk)) { + clk_disable_unprepare(mcan_class->cclk); + clk_disable_unprepare(mcan_class->hclk); + } + + dev_err(&spi->dev, "Probe failed, err=%d\n", ret); + return ret; +} + +static int tcan4x5x_can_remove(struct spi_device *spi) +{ + struct tcan4x5x_priv *priv = spi_get_drvdata(spi); + + tcan4x5x_power_enable(priv->power, 0); + + m_can_class_unregister(priv->mcan_dev); + + return 0; +} + +static const struct of_device_id tcan4x5x_of_match[] = { + { .compatible = "ti,tcan4x5x", }, + { } +}; +MODULE_DEVICE_TABLE(of, tcan4x5x_of_match); + +static const struct spi_device_id tcan4x5x_id_table[] = { + { + .name = "tcan4x5x", + .driver_data = 0, + }, + { } +}; +MODULE_DEVICE_TABLE(spi, tcan4x5x_id_table); + +static struct spi_driver tcan4x5x_can_driver = { + .driver = { + .name = DEVICE_NAME, + .of_match_table = tcan4x5x_of_match, + .pm = NULL, + }, + .id_table = tcan4x5x_id_table, + .probe = tcan4x5x_can_probe, + .remove = tcan4x5x_can_remove, +}; +module_spi_driver(tcan4x5x_can_driver); + +MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>"); +MODULE_DESCRIPTION("Texas Instruments TCAN4x5x CAN driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 13e66297b65f..cf218949a8fb 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -759,7 +759,6 @@ static int rcar_can_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "No IRQ resource\n"); err = irq; goto fail; } diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index de34a4b82d4a..edaa1ca972c1 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1652,14 +1652,12 @@ static int rcar_canfd_probe(struct platform_device *pdev) ch_irq = platform_get_irq(pdev, 0); if (ch_irq < 0) { - dev_err(&pdev->dev, "no Channel IRQ resource\n"); err = ch_irq; goto fail_dev; } g_irq = platform_get_irq(pdev, 1); if (g_irq < 0) { - dev_err(&pdev->dev, "no Global IRQ resource\n"); err = g_irq; goto fail_dev; } diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig index 6b72da2f18a6..32d242dc0d9f 100644 --- a/drivers/net/can/sja1000/Kconfig +++ b/drivers/net/can/sja1000/Kconfig @@ -1,26 +1,18 @@ # SPDX-License-Identifier: GPL-2.0-only + menuconfig CAN_SJA1000 tristate "Philips/NXP SJA1000 devices" depends on HAS_IOMEM if CAN_SJA1000 -config CAN_SJA1000_ISA - tristate "ISA Bus based legacy SJA1000 driver" - ---help--- - This driver adds legacy support for SJA1000 chips connected to - the ISA bus using I/O port, memory mapped or indirect access. - -config CAN_SJA1000_PLATFORM - tristate "Generic Platform Bus based SJA1000 driver" +config CAN_EMS_PCI + tristate "EMS CPC-PCI, CPC-PCIe and CPC-104P Card" + depends on PCI ---help--- - This driver adds support for the SJA1000 chips connected to - the "platform bus" (Linux abstraction for directly to the - processor attached devices). Which can be found on various - boards from Phytec (http://www.phytec.de) like the PCM027, - PCM038. It also provides the OpenFirmware "platform bus" found - on embedded systems with OpenFirmware bindings, e.g. if you - have a PowerPC based system you may want to enable this option. + This driver is for the one, two or four channel CPC-PCI, + CPC-PCIe and CPC-104P cards from EMS Dr. Thomas Wuensche + (http://www.ems-wuensche.de). config CAN_EMS_PCMCIA tristate "EMS CPC-CARD Card" @@ -29,23 +21,22 @@ config CAN_EMS_PCMCIA This driver is for the one or two channel CPC-CARD cards from EMS Dr. Thomas Wuensche (http://www.ems-wuensche.de). -config CAN_EMS_PCI - tristate "EMS CPC-PCI, CPC-PCIe and CPC-104P Card" +config CAN_F81601 + tristate "Fintek F81601 PCIE to 2 CAN Controller" depends on PCI - ---help--- - This driver is for the one, two or four channel CPC-PCI, - CPC-PCIe and CPC-104P cards from EMS Dr. Thomas Wuensche - (http://www.ems-wuensche.de). + help + This driver adds support for Fintek F81601 PCIE to 2 CAN + Controller. It had internal 24MHz clock source, but it can + be changed by manufacturer. Use modinfo to get usage for + parameters. Visit http://www.fintek.com.tw to get more + information. -config CAN_PEAK_PCMCIA - tristate "PEAK PCAN-PC Card" - depends on PCMCIA - depends on HAS_IOPORT_MAP +config CAN_KVASER_PCI + tristate "Kvaser PCIcanx and Kvaser PCIcan PCI Cards" + depends on PCI ---help--- - This driver is for the PCAN-PC Card PCMCIA adapter (1 or 2 channels) - from PEAK-System (http://www.peak-system.com). To compile this - driver as a module, choose M here: the module will be called - peak_pcmcia. + This driver is for the PCIcanx and PCIcan cards (1, 2 or + 4 channel) from Kvaser (http://www.kvaser.com). config CAN_PEAK_PCI tristate "PEAK PCAN-PCI/PCIe/miniPCI Cards" @@ -66,12 +57,15 @@ config CAN_PEAK_PCIEC Technik. This will also automatically select I2C and I2C_ALGO configuration options. -config CAN_KVASER_PCI - tristate "Kvaser PCIcanx and Kvaser PCIcan PCI Cards" - depends on PCI +config CAN_PEAK_PCMCIA + tristate "PEAK PCAN-PC Card" + depends on PCMCIA + depends on HAS_IOPORT_MAP ---help--- - This driver is for the PCIcanx and PCIcan cards (1, 2 or - 4 channel) from Kvaser (http://www.kvaser.com). + This driver is for the PCAN-PC Card PCMCIA adapter (1 or 2 channels) + from PEAK-System (http://www.peak-system.com). To compile this + driver as a module, choose M here: the module will be called + peak_pcmcia. config CAN_PLX_PCI tristate "PLX90xx PCI-bridge based Cards" @@ -91,6 +85,23 @@ config CAN_PLX_PCI - Connect Tech Inc. CANpro/104-Plus Opto (CRG001) card (http://www.connecttech.com) - ASEM CAN raw - 2 isolated CAN channels (www.asem.it) +config CAN_SJA1000_ISA + tristate "ISA Bus based legacy SJA1000 driver" + ---help--- + This driver adds legacy support for SJA1000 chips connected to + the ISA bus using I/O port, memory mapped or indirect access. + +config CAN_SJA1000_PLATFORM + tristate "Generic Platform Bus based SJA1000 driver" + ---help--- + This driver adds support for the SJA1000 chips connected to + the "platform bus" (Linux abstraction for directly to the + processor attached devices). Which can be found on various + boards from Phytec (http://www.phytec.de) like the PCM027, + PCM038. It also provides the OpenFirmware "platform bus" found + on embedded systems with OpenFirmware bindings, e.g. if you + have a PowerPC based system you may want to enable this option. + config CAN_TSCAN1 tristate "TS-CAN1 PC104 boards" depends on ISA diff --git a/drivers/net/can/sja1000/Makefile b/drivers/net/can/sja1000/Makefile index 9253aaf9e739..500ce1dddaec 100644 --- a/drivers/net/can/sja1000/Makefile +++ b/drivers/net/can/sja1000/Makefile @@ -3,13 +3,14 @@ # Makefile for the SJA1000 CAN controller drivers. # -obj-$(CONFIG_CAN_SJA1000) += sja1000.o -obj-$(CONFIG_CAN_SJA1000_ISA) += sja1000_isa.o -obj-$(CONFIG_CAN_SJA1000_PLATFORM) += sja1000_platform.o -obj-$(CONFIG_CAN_EMS_PCMCIA) += ems_pcmcia.o obj-$(CONFIG_CAN_EMS_PCI) += ems_pci.o +obj-$(CONFIG_CAN_EMS_PCMCIA) += ems_pcmcia.o +obj-$(CONFIG_CAN_F81601) += f81601.o obj-$(CONFIG_CAN_KVASER_PCI) += kvaser_pci.o -obj-$(CONFIG_CAN_PEAK_PCMCIA) += peak_pcmcia.o obj-$(CONFIG_CAN_PEAK_PCI) += peak_pci.o +obj-$(CONFIG_CAN_PEAK_PCMCIA) += peak_pcmcia.o obj-$(CONFIG_CAN_PLX_PCI) += plx_pci.o +obj-$(CONFIG_CAN_SJA1000) += sja1000.o +obj-$(CONFIG_CAN_SJA1000_ISA) += sja1000_isa.o +obj-$(CONFIG_CAN_SJA1000_PLATFORM) += sja1000_platform.o obj-$(CONFIG_CAN_TSCAN1) += tscan1.o diff --git a/drivers/net/can/sja1000/f81601.c b/drivers/net/can/sja1000/f81601.c new file mode 100644 index 000000000000..8f25e95814ef --- /dev/null +++ b/drivers/net/can/sja1000/f81601.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Fintek F81601 PCIE to 2 CAN controller driver + * + * Copyright (C) 2019 Peter Hong <peter_hong@fintek.com.tw> + * Copyright (C) 2019 Linux Foundation + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/netdevice.h> +#include <linux/delay.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/can/dev.h> +#include <linux/io.h> + +#include "sja1000.h" + +#define F81601_PCI_MAX_CHAN 2 + +#define F81601_DECODE_REG 0x209 +#define F81601_IO_MODE BIT(7) +#define F81601_MEM_MODE BIT(6) +#define F81601_CFG_MODE BIT(5) +#define F81601_CAN2_INTERNAL_CLK BIT(3) +#define F81601_CAN1_INTERNAL_CLK BIT(2) +#define F81601_CAN2_EN BIT(1) +#define F81601_CAN1_EN BIT(0) + +#define F81601_TRAP_REG 0x20a +#define F81601_CAN2_HAS_EN BIT(4) + +struct f81601_pci_card { + void __iomem *addr; + spinlock_t lock; /* use this spin lock only for write access */ + struct pci_dev *dev; + struct net_device *net_dev[F81601_PCI_MAX_CHAN]; +}; + +static const struct pci_device_id f81601_pci_tbl[] = { + { PCI_DEVICE(0x1c29, 0x1703) }, + { /* sentinel */ }, +}; + +MODULE_DEVICE_TABLE(pci, f81601_pci_tbl); + +static bool internal_clk = true; +module_param(internal_clk, bool, 0444); +MODULE_PARM_DESC(internal_clk, "Use internal clock, default true (24MHz)"); + +static unsigned int external_clk; +module_param(external_clk, uint, 0444); +MODULE_PARM_DESC(external_clk, "External clock when internal_clk disabled"); + +static u8 f81601_pci_read_reg(const struct sja1000_priv *priv, int port) +{ + return readb(priv->reg_base + port); +} + +static void f81601_pci_write_reg(const struct sja1000_priv *priv, int port, + u8 val) +{ + struct f81601_pci_card *card = priv->priv; + unsigned long flags; + + spin_lock_irqsave(&card->lock, flags); + writeb(val, priv->reg_base + port); + readb(priv->reg_base); + spin_unlock_irqrestore(&card->lock, flags); +} + +static void f81601_pci_remove(struct pci_dev *pdev) +{ + struct f81601_pci_card *card = pci_get_drvdata(pdev); + struct net_device *dev; + int i; + + for (i = 0; i < ARRAY_SIZE(card->net_dev); i++) { + dev = card->net_dev[i]; + if (!dev) + continue; + + dev_info(&pdev->dev, "%s: Removing %s\n", __func__, dev->name); + + unregister_sja1000dev(dev); + free_sja1000dev(dev); + } +} + +/* Probe F81601 based device for the SJA1000 chips and register each + * available CAN channel to SJA1000 Socket-CAN subsystem. + */ +static int f81601_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct sja1000_priv *priv; + struct net_device *dev; + struct f81601_pci_card *card; + int err, i, count; + u8 tmp; + + if (pcim_enable_device(pdev) < 0) { + dev_err(&pdev->dev, "Failed to enable PCI device\n"); + return -ENODEV; + } + + dev_info(&pdev->dev, "Detected card at slot #%i\n", + PCI_SLOT(pdev->devfn)); + + card = devm_kzalloc(&pdev->dev, sizeof(*card), GFP_KERNEL); + if (!card) + return -ENOMEM; + + card->dev = pdev; + spin_lock_init(&card->lock); + + pci_set_drvdata(pdev, card); + + tmp = F81601_IO_MODE | F81601_MEM_MODE | F81601_CFG_MODE | + F81601_CAN2_EN | F81601_CAN1_EN; + + if (internal_clk) { + tmp |= F81601_CAN2_INTERNAL_CLK | F81601_CAN1_INTERNAL_CLK; + + dev_info(&pdev->dev, + "F81601 running with internal clock: 24Mhz\n"); + } else { + dev_info(&pdev->dev, + "F81601 running with external clock: %dMhz\n", + external_clk / 1000000); + } + + pci_write_config_byte(pdev, F81601_DECODE_REG, tmp); + + card->addr = pcim_iomap(pdev, 0, pci_resource_len(pdev, 0)); + + if (!card->addr) { + err = -ENOMEM; + dev_err(&pdev->dev, "%s: Failed to remap BAR\n", __func__); + goto failure_cleanup; + } + + /* read CAN2_HW_EN strap pin to detect how many CANBUS do we have */ + count = ARRAY_SIZE(card->net_dev); + pci_read_config_byte(pdev, F81601_TRAP_REG, &tmp); + if (!(tmp & F81601_CAN2_HAS_EN)) + count = 1; + + for (i = 0; i < count; i++) { + dev = alloc_sja1000dev(0); + if (!dev) { + err = -ENOMEM; + goto failure_cleanup; + } + + priv = netdev_priv(dev); + priv->priv = card; + priv->irq_flags = IRQF_SHARED; + priv->reg_base = card->addr + 0x80 * i; + priv->read_reg = f81601_pci_read_reg; + priv->write_reg = f81601_pci_write_reg; + + if (internal_clk) + priv->can.clock.freq = 24000000 / 2; + else + priv->can.clock.freq = external_clk / 2; + + priv->ocr = OCR_TX0_PUSHPULL | OCR_TX1_PUSHPULL; + priv->cdr = CDR_CBP; + + SET_NETDEV_DEV(dev, &pdev->dev); + dev->dev_id = i; + dev->irq = pdev->irq; + + /* Register SJA1000 device */ + err = register_sja1000dev(dev); + if (err) { + dev_err(&pdev->dev, + "%s: Registering device failed: %x\n", __func__, + err); + free_sja1000dev(dev); + goto failure_cleanup; + } + + card->net_dev[i] = dev; + dev_info(&pdev->dev, "Channel #%d, %s at 0x%p, irq %d\n", i, + dev->name, priv->reg_base, dev->irq); + } + + return 0; + + failure_cleanup: + dev_err(&pdev->dev, "%s: failed: %d. Cleaning Up.\n", __func__, err); + f81601_pci_remove(pdev); + + return err; +} + +static struct pci_driver f81601_pci_driver = { + .name = "f81601", + .id_table = f81601_pci_tbl, + .probe = f81601_pci_probe, + .remove = f81601_pci_remove, +}; + +MODULE_DESCRIPTION("Fintek F81601 PCIE to 2 CANBUS adaptor driver"); +MODULE_AUTHOR("Peter Hong <peter_hong@fintek.com.tw>"); +MODULE_LICENSE("GPL v2"); + +module_pci_driver(f81601_pci_driver); diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 093fc9a529f0..f4cd88196404 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -787,7 +787,6 @@ static int sun4ican_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "could not get a valid irq\n"); err = -ENODEV; goto exit; } diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index db6ea936dc3f..f8b19eef5d26 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -5,6 +5,7 @@ * specs for the same is available at <http://www.ti.com> * * Copyright (C) 2009 Texas Instruments Incorporated - http://www.ti.com/ + * Copyright (C) 2019 Jeroen Hofstee <jhofstee@victronenergy.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as @@ -34,6 +35,7 @@ #include <linux/can/dev.h> #include <linux/can/error.h> #include <linux/can/led.h> +#include <linux/can/rx-offload.h> #define DRV_NAME "ti_hecc" #define HECC_MODULE_VERSION "0.7" @@ -44,8 +46,7 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_MAX_MAILBOXES 32 /* hardware mailboxes - do not change */ #define MAX_TX_PRIO 0x3F /* hardware value - do not change */ -/* - * Important Note: TX mailbox configuration +/* Important Note: TX mailbox configuration * TX mailboxes should be restricted to the number of SKB buffers to avoid * maintaining SKB buffers separately. TX mailboxes should be a power of 2 * for the mailbox logic to work. Top mailbox numbers are reserved for RX @@ -63,29 +64,15 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_TX_PRIO_MASK (MAX_TX_PRIO << HECC_MB_TX_SHIFT) #define HECC_TX_MB_MASK (HECC_MAX_TX_MBOX - 1) #define HECC_TX_MASK ((HECC_MAX_TX_MBOX - 1) | HECC_TX_PRIO_MASK) -#define HECC_TX_MBOX_MASK (~(BIT(HECC_MAX_TX_MBOX) - 1)) -#define HECC_DEF_NAPI_WEIGHT HECC_MAX_RX_MBOX -/* - * Important Note: RX mailbox configuration - * RX mailboxes are further logically split into two - main and buffer - * mailboxes. The goal is to get all packets into main mailboxes as - * driven by mailbox number and receive priority (higher to lower) and - * buffer mailboxes are used to receive pkts while main mailboxes are being - * processed. This ensures in-order packet reception. +/* RX mailbox configuration * - * Here are the recommended values for buffer mailbox. Note that RX mailboxes - * start after TX mailboxes: - * - * HECC_MAX_RX_MBOX HECC_RX_BUFFER_MBOX No of buffer mailboxes - * 28 12 8 - * 16 20 4 + * The remaining mailboxes are used for reception and are delivered + * based on their timestamp, to avoid a hardware race when CANME is + * changed while CAN-bus traffic is being received. */ - #define HECC_MAX_RX_MBOX (HECC_MAX_MAILBOXES - HECC_MAX_TX_MBOX) -#define HECC_RX_BUFFER_MBOX 12 /* as per table above */ #define HECC_RX_FIRST_MBOX (HECC_MAX_MAILBOXES - 1) -#define HECC_RX_HIGH_MBOX_MASK (~(BIT(HECC_RX_BUFFER_MBOX) - 1)) /* TI HECC module registers */ #define HECC_CANME 0x0 /* Mailbox enable */ @@ -117,6 +104,9 @@ MODULE_VERSION(HECC_MODULE_VERSION); #define HECC_CANTIOCE 0x68 /* SCC only:Enhanced TX I/O control */ #define HECC_CANRIOCE 0x6C /* SCC only:Enhanced RX I/O control */ +/* TI HECC RAM registers */ +#define HECC_CANMOTS 0x80 /* Message object time stamp */ + /* Mailbox registers */ #define HECC_CANMID 0x0 #define HECC_CANMCF 0x4 @@ -193,7 +183,7 @@ static const struct can_bittiming_const ti_hecc_bittiming_const = { struct ti_hecc_priv { struct can_priv can; /* MUST be first member/field */ - struct napi_struct napi; + struct can_rx_offload offload; struct net_device *ndev; struct clk *clk; void __iomem *base; @@ -203,7 +193,6 @@ struct ti_hecc_priv { spinlock_t mbx_lock; /* CANME register needs protection */ u32 tx_head; u32 tx_tail; - u32 rx_next; struct regulator *reg_xceiver; }; @@ -227,8 +216,13 @@ static inline void hecc_write_lam(struct ti_hecc_priv *priv, u32 mbxno, u32 val) __raw_writel(val, priv->hecc_ram + mbxno * 4); } +static inline u32 hecc_read_stamp(struct ti_hecc_priv *priv, u32 mbxno) +{ + return __raw_readl(priv->hecc_ram + HECC_CANMOTS + mbxno * 4); +} + static inline void hecc_write_mbx(struct ti_hecc_priv *priv, u32 mbxno, - u32 reg, u32 val) + u32 reg, u32 val) { __raw_writel(val, priv->mbx + mbxno * 0x10 + reg); } @@ -249,13 +243,13 @@ static inline u32 hecc_read(struct ti_hecc_priv *priv, int reg) } static inline void hecc_set_bit(struct ti_hecc_priv *priv, int reg, - u32 bit_mask) + u32 bit_mask) { hecc_write(priv, reg, hecc_read(priv, reg) | bit_mask); } static inline void hecc_clear_bit(struct ti_hecc_priv *priv, int reg, - u32 bit_mask) + u32 bit_mask) { hecc_write(priv, reg, hecc_read(priv, reg) & ~bit_mask); } @@ -277,8 +271,8 @@ static int ti_hecc_set_btc(struct ti_hecc_priv *priv) if (bit_timing->brp > 4) can_btc |= HECC_CANBTC_SAM; else - netdev_warn(priv->ndev, "WARN: Triple" - "sampling not set due to h/w limitations"); + netdev_warn(priv->ndev, + "WARN: Triple sampling not set due to h/w limitations"); } can_btc |= ((bit_timing->sjw - 1) & 0x3) << 8; can_btc |= ((bit_timing->brp - 1) & 0xFF) << 16; @@ -314,8 +308,7 @@ static void ti_hecc_reset(struct net_device *ndev) /* Set change control request and wait till enabled */ hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_CCR); - /* - * INFO: It has been observed that at times CCE bit may not be + /* INFO: It has been observed that at times CCE bit may not be * set and hw seems to be ok even if this bit is not set so * timing out with a timing of 1ms to respect the specs */ @@ -325,8 +318,7 @@ static void ti_hecc_reset(struct net_device *ndev) udelay(10); } - /* - * Note: On HECC, BTC can be programmed only in initialization mode, so + /* Note: On HECC, BTC can be programmed only in initialization mode, so * it is expected that the can bittiming parameters are set via ip * utility before the device is opened */ @@ -335,13 +327,11 @@ static void ti_hecc_reset(struct net_device *ndev) /* Clear CCR (and CANMC register) and wait for CCE = 0 enable */ hecc_write(priv, HECC_CANMC, 0); - /* - * INFO: CAN net stack handles bus off and hence disabling auto-bus-on + /* INFO: CAN net stack handles bus off and hence disabling auto-bus-on * hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_ABO); */ - /* - * INFO: It has been observed that at times CCE bit may not be + /* INFO: It has been observed that at times CCE bit may not be * set and hw seems to be ok even if this bit is not set so */ cnt = HECC_CCE_WAIT_COUNT; @@ -374,8 +364,8 @@ static void ti_hecc_start(struct net_device *ndev) /* put HECC in initialization mode and set btc */ ti_hecc_reset(ndev); - priv->tx_head = priv->tx_tail = HECC_TX_MASK; - priv->rx_next = HECC_RX_FIRST_MBOX; + priv->tx_head = HECC_TX_MASK; + priv->tx_tail = HECC_TX_MASK; /* Enable local and global acceptance mask registers */ hecc_write(priv, HECC_CANGAM, HECC_SET_REG); @@ -401,7 +391,7 @@ static void ti_hecc_start(struct net_device *ndev) } else { hecc_write(priv, HECC_CANMIL, 0); hecc_write(priv, HECC_CANGIM, - HECC_CANGIM_DEF_MASK | HECC_CANGIM_I0EN); + HECC_CANGIM_DEF_MASK | HECC_CANGIM_I0EN); } priv->can.state = CAN_STATE_ERROR_ACTIVE; } @@ -435,7 +425,7 @@ static int ti_hecc_do_set_mode(struct net_device *ndev, enum can_mode mode) } static int ti_hecc_get_berr_counter(const struct net_device *ndev, - struct can_berr_counter *bec) + struct can_berr_counter *bec) { struct ti_hecc_priv *priv = netdev_priv(ndev); @@ -445,8 +435,7 @@ static int ti_hecc_get_berr_counter(const struct net_device *ndev, return 0; } -/* - * ti_hecc_xmit: HECC Transmit +/* ti_hecc_xmit: HECC Transmit * * The transmit mailboxes start from 0 to HECC_MAX_TX_MBOX. In HECC the * priority of the mailbox for tranmission is dependent upon priority setting @@ -484,8 +473,8 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev) spin_unlock_irqrestore(&priv->mbx_lock, flags); netif_stop_queue(ndev); netdev_err(priv->ndev, - "BUG: TX mbx not ready tx_head=%08X, tx_tail=%08X\n", - priv->tx_head, priv->tx_tail); + "BUG: TX mbx not ready tx_head=%08X, tx_tail=%08X\n", + priv->tx_head, priv->tx_tail); return NETDEV_TX_BUSY; } spin_unlock_irqrestore(&priv->mbx_lock, flags); @@ -502,10 +491,10 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev) data = (cf->can_id & CAN_SFF_MASK) << 18; hecc_write_mbx(priv, mbxno, HECC_CANMID, data); hecc_write_mbx(priv, mbxno, HECC_CANMDL, - be32_to_cpu(*(__be32 *)(cf->data))); + be32_to_cpu(*(__be32 *)(cf->data))); if (cf->can_dlc > 4) hecc_write_mbx(priv, mbxno, HECC_CANMDH, - be32_to_cpu(*(__be32 *)(cf->data + 4))); + be32_to_cpu(*(__be32 *)(cf->data + 4))); else *(u32 *)(cf->data + 4) = 0; can_put_echo_skb(skb, ndev, mbxno); @@ -513,7 +502,7 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev) spin_lock_irqsave(&priv->mbx_lock, flags); --priv->tx_head; if ((hecc_read(priv, HECC_CANME) & BIT(get_tx_head_mb(priv))) || - (priv->tx_head & HECC_TX_MASK) == HECC_TX_MASK) { + (priv->tx_head & HECC_TX_MASK) == HECC_TX_MASK) { netif_stop_queue(ndev); } hecc_set_bit(priv, HECC_CANME, mbx_mask); @@ -526,139 +515,57 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } -static int ti_hecc_rx_pkt(struct ti_hecc_priv *priv, int mbxno) +static inline +struct ti_hecc_priv *rx_offload_to_priv(struct can_rx_offload *offload) { - struct net_device_stats *stats = &priv->ndev->stats; - struct can_frame *cf; - struct sk_buff *skb; - u32 data, mbx_mask; - unsigned long flags; + return container_of(offload, struct ti_hecc_priv, offload); +} - skb = alloc_can_skb(priv->ndev, &cf); - if (!skb) { - if (printk_ratelimit()) - netdev_err(priv->ndev, - "ti_hecc_rx_pkt: alloc_can_skb() failed\n"); - return -ENOMEM; - } +static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload, + struct can_frame *cf, + u32 *timestamp, unsigned int mbxno) +{ + struct ti_hecc_priv *priv = rx_offload_to_priv(offload); + u32 data; - mbx_mask = BIT(mbxno); data = hecc_read_mbx(priv, mbxno, HECC_CANMID); if (data & HECC_CANMID_IDE) cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG; else cf->can_id = (data >> 18) & CAN_SFF_MASK; + 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); + data = hecc_read_mbx(priv, mbxno, HECC_CANMDL); *(__be32 *)(cf->data) = cpu_to_be32(data); if (cf->can_dlc > 4) { data = hecc_read_mbx(priv, mbxno, HECC_CANMDH); *(__be32 *)(cf->data + 4) = cpu_to_be32(data); } - spin_lock_irqsave(&priv->mbx_lock, flags); - hecc_clear_bit(priv, HECC_CANME, mbx_mask); - hecc_write(priv, HECC_CANRMP, mbx_mask); - /* enable mailbox only if it is part of rx buffer mailboxes */ - if (priv->rx_next < HECC_RX_BUFFER_MBOX) - hecc_set_bit(priv, HECC_CANME, mbx_mask); - spin_unlock_irqrestore(&priv->mbx_lock, flags); - stats->rx_bytes += cf->can_dlc; - can_led_event(priv->ndev, CAN_LED_EVENT_RX); - netif_receive_skb(skb); - stats->rx_packets++; + *timestamp = hecc_read_stamp(priv, mbxno); - return 0; -} - -/* - * ti_hecc_rx_poll - HECC receive pkts - * - * The receive mailboxes start from highest numbered mailbox till last xmit - * mailbox. On CAN frame reception the hardware places the data into highest - * numbered mailbox that matches the CAN ID filter. Since all receive mailboxes - * have same filtering (ALL CAN frames) packets will arrive in the highest - * available RX mailbox and we need to ensure in-order packet reception. - * - * To ensure the packets are received in the right order we logically divide - * the RX mailboxes into main and buffer mailboxes. Packets are received as per - * mailbox priotity (higher to lower) in the main bank and once it is full we - * disable further reception into main mailboxes. While the main mailboxes are - * processed in NAPI, further packets are received in buffer mailboxes. - * - * We maintain a RX next mailbox counter to process packets and once all main - * mailboxe packets are passed to the upper stack we enable all of them but - * continue to process packets received in buffer mailboxes. With each packet - * received from buffer mailbox we enable it immediately so as to handle the - * overflow from higher mailboxes. - */ -static int ti_hecc_rx_poll(struct napi_struct *napi, int quota) -{ - struct net_device *ndev = napi->dev; - struct ti_hecc_priv *priv = netdev_priv(ndev); - u32 num_pkts = 0; - u32 mbx_mask; - unsigned long pending_pkts, flags; - - if (!netif_running(ndev)) - return 0; - - while ((pending_pkts = hecc_read(priv, HECC_CANRMP)) && - num_pkts < quota) { - mbx_mask = BIT(priv->rx_next); /* next rx mailbox to process */ - if (mbx_mask & pending_pkts) { - if (ti_hecc_rx_pkt(priv, priv->rx_next) < 0) - return num_pkts; - ++num_pkts; - } else if (priv->rx_next > HECC_RX_BUFFER_MBOX) { - break; /* pkt not received yet */ - } - --priv->rx_next; - if (priv->rx_next == HECC_RX_BUFFER_MBOX) { - /* enable high bank mailboxes */ - spin_lock_irqsave(&priv->mbx_lock, flags); - mbx_mask = hecc_read(priv, HECC_CANME); - mbx_mask |= HECC_RX_HIGH_MBOX_MASK; - hecc_write(priv, HECC_CANME, mbx_mask); - spin_unlock_irqrestore(&priv->mbx_lock, flags); - } else if (priv->rx_next == HECC_MAX_TX_MBOX - 1) { - priv->rx_next = HECC_RX_FIRST_MBOX; - break; - } - } - - /* Enable packet interrupt if all pkts are handled */ - if (hecc_read(priv, HECC_CANRMP) == 0) { - napi_complete(napi); - /* Re-enable RX mailbox interrupts */ - mbx_mask = hecc_read(priv, HECC_CANMIM); - mbx_mask |= HECC_TX_MBOX_MASK; - hecc_write(priv, HECC_CANMIM, mbx_mask); - } else { - /* repoll is done only if whole budget is used */ - num_pkts = quota; - } - - return num_pkts; + return 1; } static int ti_hecc_error(struct net_device *ndev, int int_status, - int err_status) + int err_status) { struct ti_hecc_priv *priv = netdev_priv(ndev); - struct net_device_stats *stats = &ndev->stats; struct can_frame *cf; struct sk_buff *skb; + u32 timestamp; /* propagate the error condition to the can stack */ skb = alloc_can_err_skb(ndev, &cf); if (!skb) { if (printk_ratelimit()) netdev_err(priv->ndev, - "ti_hecc_error: alloc_can_err_skb() failed\n"); + "%s: alloc_can_err_skb() failed\n", + __func__); return -ENOMEM; } @@ -692,8 +599,7 @@ static int ti_hecc_error(struct net_device *ndev, int int_status, hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR); } - /* - * Need to check busoff condition in error status register too to + /* Need to check busoff condition in error status register too to * ensure warning interrupts don't hog the system */ if ((int_status & HECC_CANGIF_BOIF) || (err_status & HECC_CANES_BO)) { @@ -732,9 +638,8 @@ static int ti_hecc_error(struct net_device *ndev, int int_status, } } - stats->rx_packets++; - stats->rx_bytes += cf->can_dlc; - netif_rx(skb); + timestamp = hecc_read(priv, HECC_CANLNT); + can_rx_offload_queue_sorted(&priv->offload, skb, timestamp); return 0; } @@ -744,19 +649,20 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) struct net_device *ndev = (struct net_device *)dev_id; struct ti_hecc_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; - u32 mbxno, mbx_mask, int_status, err_status; - unsigned long ack, flags; + u32 mbxno, mbx_mask, int_status, err_status, stamp; + unsigned long flags, rx_pending; int_status = hecc_read(priv, - (priv->use_hecc1int) ? HECC_CANGIF1 : HECC_CANGIF0); + priv->use_hecc1int ? + HECC_CANGIF1 : HECC_CANGIF0); if (!int_status) return IRQ_NONE; err_status = hecc_read(priv, HECC_CANES); if (err_status & (HECC_BUS_ERROR | HECC_CANES_BO | - HECC_CANES_EP | HECC_CANES_EW)) - ti_hecc_error(ndev, int_status, err_status); + HECC_CANES_EP | HECC_CANES_EW)) + ti_hecc_error(ndev, int_status, err_status); if (int_status & HECC_CANGIF_GMIF) { while (priv->tx_tail - priv->tx_head > 0) { @@ -769,27 +675,27 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id) spin_lock_irqsave(&priv->mbx_lock, flags); hecc_clear_bit(priv, HECC_CANME, mbx_mask); spin_unlock_irqrestore(&priv->mbx_lock, flags); - stats->tx_bytes += hecc_read_mbx(priv, mbxno, - HECC_CANMCF) & 0xF; + stamp = hecc_read_stamp(priv, mbxno); + stats->tx_bytes += + can_rx_offload_get_echo_skb(&priv->offload, + mbxno, stamp); stats->tx_packets++; can_led_event(ndev, CAN_LED_EVENT_TX); - can_get_echo_skb(ndev, mbxno); --priv->tx_tail; } /* restart queue if wrap-up or if queue stalled on last pkt */ - if (((priv->tx_head == priv->tx_tail) && - ((priv->tx_head & HECC_TX_MASK) != HECC_TX_MASK)) || - (((priv->tx_tail & HECC_TX_MASK) == HECC_TX_MASK) && - ((priv->tx_head & HECC_TX_MASK) == HECC_TX_MASK))) + if ((priv->tx_head == priv->tx_tail && + ((priv->tx_head & HECC_TX_MASK) != HECC_TX_MASK)) || + (((priv->tx_tail & HECC_TX_MASK) == HECC_TX_MASK) && + ((priv->tx_head & HECC_TX_MASK) == HECC_TX_MASK))) netif_wake_queue(ndev); - /* Disable RX mailbox interrupts and let NAPI reenable them */ - if (hecc_read(priv, HECC_CANRMP)) { - ack = hecc_read(priv, HECC_CANMIM); - ack &= BIT(HECC_MAX_TX_MBOX) - 1; - hecc_write(priv, HECC_CANMIM, ack); - napi_schedule(&priv->napi); + /* offload RX mailboxes and let NAPI deliver them */ + while ((rx_pending = hecc_read(priv, HECC_CANRMP))) { + can_rx_offload_irq_offload_timestamp(&priv->offload, + rx_pending); + hecc_write(priv, HECC_CANRMP, rx_pending); } } @@ -811,7 +717,7 @@ static int ti_hecc_open(struct net_device *ndev) int err; err = request_irq(ndev->irq, ti_hecc_interrupt, IRQF_SHARED, - ndev->name, ndev); + ndev->name, ndev); if (err) { netdev_err(ndev, "error requesting interrupt\n"); return err; @@ -831,7 +737,7 @@ static int ti_hecc_open(struct net_device *ndev) can_led_event(ndev, CAN_LED_EVENT_OPEN); ti_hecc_start(ndev); - napi_enable(&priv->napi); + can_rx_offload_enable(&priv->offload); netif_start_queue(ndev); return 0; @@ -842,7 +748,7 @@ static int ti_hecc_close(struct net_device *ndev) struct ti_hecc_priv *priv = netdev_priv(ndev); netif_stop_queue(ndev); - napi_disable(&priv->napi); + can_rx_offload_disable(&priv->offload); ti_hecc_stop(ndev); free_irq(ndev->irq, ndev); close_candev(ndev); @@ -962,8 +868,6 @@ static int ti_hecc_probe(struct platform_device *pdev) goto probe_exit_candev; } priv->can.clock.freq = clk_get_rate(priv->clk); - netif_napi_add(ndev, &priv->napi, ti_hecc_rx_poll, - HECC_DEF_NAPI_WEIGHT); err = clk_prepare_enable(priv->clk); if (err) { @@ -971,19 +875,30 @@ static int ti_hecc_probe(struct platform_device *pdev) goto probe_exit_clk; } + priv->offload.mailbox_read = ti_hecc_mailbox_read; + priv->offload.mb_first = HECC_RX_FIRST_MBOX; + priv->offload.mb_last = HECC_MAX_TX_MBOX; + err = can_rx_offload_add_timestamp(ndev, &priv->offload); + if (err) { + dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n"); + goto probe_exit_clk; + } + err = register_candev(ndev); if (err) { dev_err(&pdev->dev, "register_candev() failed\n"); - goto probe_exit_clk; + goto probe_exit_offload; } devm_can_led_init(ndev); dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%u)\n", - priv->base, (u32) ndev->irq); + priv->base, (u32)ndev->irq); return 0; +probe_exit_offload: + can_rx_offload_del(&priv->offload); probe_exit_clk: clk_put(priv->clk); probe_exit_candev: @@ -1000,6 +915,7 @@ static int ti_hecc_remove(struct platform_device *pdev) unregister_candev(ndev); clk_disable_unprepare(priv->clk); clk_put(priv->clk); + can_rx_offload_del(&priv->offload); free_candev(ndev); return 0; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index c89c7d4900d7..0f1d3e807d63 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -643,8 +643,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, return err; } - netdev = alloc_candev(sizeof(*priv) + - dev->max_tx_urbs * sizeof(*priv->tx_contexts), + netdev = alloc_candev(struct_size(priv, tx_contexts, dev->max_tx_urbs), dev->max_tx_urbs); if (!netdev) { dev_err(&dev->intf->dev, "Cannot alloc candev\n"); diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index d200a5b0651c..daf27133887b 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -1,5 +1,4 @@ -/* - * vcan.c - Virtual CAN interface +/* vcan.c - Virtual CAN interface * * Copyright (c) 2002-2017 Volkswagen Group Electronic Research * All rights reserved. @@ -39,6 +38,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/init.h> #include <linux/netdevice.h> @@ -57,9 +58,7 @@ MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); - -/* - * CAN test feature: +/* CAN test feature: * Enable the echo on driver level for testing the CAN core echo modes. * See Documentation/networking/can.rst for details. */ @@ -68,7 +67,6 @@ static bool echo; /* echo testing. Default: 0 (Off) */ module_param(echo, bool, 0444); MODULE_PARM_DESC(echo, "Echo sent frames (for testing). Default: 0 (Off)"); - static void vcan_rx(struct sk_buff *skb, struct net_device *dev) { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; @@ -101,10 +99,8 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) if (!echo) { /* no echo handling available inside this driver */ - if (loop) { - /* - * only count the packets here, because the + /* only count the packets here, because the * CAN core already did the echo for us */ stats->rx_packets++; @@ -117,7 +113,6 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) /* perform standard echo handling for CAN network interfaces */ if (loop) { - skb = can_create_echo_skb(skb); if (!skb) return NETDEV_TX_OK; @@ -173,10 +168,10 @@ static struct rtnl_link_ops vcan_link_ops __read_mostly = { static __init int vcan_init_module(void) { - pr_info("vcan: Virtual CAN interface driver\n"); + pr_info("Virtual CAN interface driver\n"); if (echo) - printk(KERN_INFO "vcan: enabled echo on driver level.\n"); + pr_info("enabled echo on driver level.\n"); return rtnl_link_register(&vcan_link_ops); } diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 63203ff452b5..911b34316c9d 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -50,6 +50,10 @@ enum xcan_reg { XCAN_AFR_OFFSET = 0x60, /* Acceptance Filter */ /* only on CAN FD cores */ + XCAN_F_BRPR_OFFSET = 0x088, /* Data Phase Baud Rate + * Prescalar + */ + XCAN_F_BTR_OFFSET = 0x08C, /* Data Phase Bit Timing */ XCAN_TRR_OFFSET = 0x0090, /* TX Buffer Ready Request */ XCAN_AFR_EXT_OFFSET = 0x00E0, /* Acceptance Filter */ XCAN_FSR_OFFSET = 0x00E8, /* RX FIFO Status */ @@ -62,6 +66,7 @@ enum xcan_reg { #define XCAN_FRAME_DLC_OFFSET(frame_base) ((frame_base) + 0x04) #define XCAN_FRAME_DW1_OFFSET(frame_base) ((frame_base) + 0x08) #define XCAN_FRAME_DW2_OFFSET(frame_base) ((frame_base) + 0x0C) +#define XCANFD_FRAME_DW_OFFSET(frame_base) ((frame_base) + 0x08) #define XCAN_CANFD_FRAME_SIZE 0x48 #define XCAN_TXMSG_FRAME_OFFSET(n) (XCAN_TXMSG_BASE_OFFSET + \ @@ -118,8 +123,12 @@ enum xcan_reg { #define XCAN_IDR_RTR_MASK 0x00000001 /* Remote TX request */ #define XCAN_DLCR_DLC_MASK 0xF0000000 /* Data length code */ #define XCAN_FSR_FL_MASK 0x00003F00 /* RX Fill Level */ +#define XCAN_2_FSR_FL_MASK 0x00007F00 /* RX Fill Level */ #define XCAN_FSR_IRI_MASK 0x00000080 /* RX Increment Read Index */ #define XCAN_FSR_RI_MASK 0x0000001F /* RX Read Index */ +#define XCAN_2_FSR_RI_MASK 0x0000003F /* RX Read Index */ +#define XCAN_DLCR_EDL_MASK 0x08000000 /* EDL Mask in DLC */ +#define XCAN_DLCR_BRS_MASK 0x04000000 /* BRS Mask in DLC */ /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */ #define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */ @@ -133,6 +142,7 @@ enum xcan_reg { /* CAN frame length constants */ #define XCAN_FRAME_MAX_DATA_LEN 8 +#define XCANFD_DW_BYTES 4 #define XCAN_TIMEOUT (1 * HZ) /* TX-FIFO-empty interrupt available */ @@ -149,7 +159,15 @@ enum xcan_reg { #define XCAN_FLAG_RX_FIFO_MULTI 0x0010 #define XCAN_FLAG_CANFD_2 0x0020 +enum xcan_ip_type { + XAXI_CAN = 0, + XZYNQ_CANPS, + XAXI_CANFD, + XAXI_CANFD_2_0, +}; + struct xcan_devtype_data { + enum xcan_ip_type cantype; unsigned int flags; const struct can_bittiming_const *bittiming_const; const char *bus_clk_name; @@ -183,7 +201,7 @@ struct xcan_priv { struct napi_struct napi; u32 (*read_reg)(const struct xcan_priv *priv, enum xcan_reg reg); void (*write_reg)(const struct xcan_priv *priv, enum xcan_reg reg, - u32 val); + u32 val); struct device *dev; void __iomem *reg_base; unsigned long irq_flags; @@ -205,6 +223,7 @@ static const struct can_bittiming_const xcan_bittiming_const = { .brp_inc = 1, }; +/* AXI CANFD Arbitration Bittiming constants as per AXI CANFD 1.0 spec */ static const struct can_bittiming_const xcan_bittiming_const_canfd = { .name = DRIVER_NAME, .tseg1_min = 1, @@ -217,6 +236,20 @@ static const struct can_bittiming_const xcan_bittiming_const_canfd = { .brp_inc = 1, }; +/* AXI CANFD Data Bittiming constants as per AXI CANFD 1.0 specs */ +static struct can_bittiming_const xcan_data_bittiming_const_canfd = { + .name = DRIVER_NAME, + .tseg1_min = 1, + .tseg1_max = 16, + .tseg2_min = 1, + .tseg2_max = 8, + .sjw_max = 8, + .brp_min = 1, + .brp_max = 256, + .brp_inc = 1, +}; + +/* AXI CANFD 2.0 Arbitration Bittiming constants as per AXI CANFD 2.0 spec */ static const struct can_bittiming_const xcan_bittiming_const_canfd2 = { .name = DRIVER_NAME, .tseg1_min = 1, @@ -229,6 +262,19 @@ static const struct can_bittiming_const xcan_bittiming_const_canfd2 = { .brp_inc = 1, }; +/* AXI CANFD 2.0 Data Bittiming constants as per AXI CANFD 2.0 spec */ +static struct can_bittiming_const xcan_data_bittiming_const_canfd2 = { + .name = DRIVER_NAME, + .tseg1_min = 1, + .tseg1_max = 32, + .tseg2_min = 1, + .tseg2_max = 16, + .sjw_max = 16, + .brp_min = 1, + .brp_max = 256, + .brp_inc = 1, +}; + /** * xcan_write_reg_le - Write a value to the device register little endian * @priv: Driver private data structure @@ -238,7 +284,7 @@ static const struct can_bittiming_const xcan_bittiming_const_canfd2 = { * Write data to the paricular CAN register */ static void xcan_write_reg_le(const struct xcan_priv *priv, enum xcan_reg reg, - u32 val) + u32 val) { iowrite32(val, priv->reg_base + reg); } @@ -265,7 +311,7 @@ static u32 xcan_read_reg_le(const struct xcan_priv *priv, enum xcan_reg reg) * Write data to the paricular CAN register */ static void xcan_write_reg_be(const struct xcan_priv *priv, enum xcan_reg reg, - u32 val) + u32 val) { iowrite32be(val, priv->reg_base + reg); } @@ -343,6 +389,7 @@ static int xcan_set_bittiming(struct net_device *ndev) { struct xcan_priv *priv = netdev_priv(ndev); struct can_bittiming *bt = &priv->can.bittiming; + struct can_bittiming *dbt = &priv->can.data_bittiming; u32 btr0, btr1; u32 is_config_mode; @@ -372,9 +419,27 @@ static int xcan_set_bittiming(struct net_device *ndev) priv->write_reg(priv, XCAN_BRPR_OFFSET, btr0); priv->write_reg(priv, XCAN_BTR_OFFSET, btr1); + if (priv->devtype.cantype == XAXI_CANFD || + priv->devtype.cantype == XAXI_CANFD_2_0) { + /* Setting Baud Rate prescalar value in F_BRPR Register */ + btr0 = dbt->brp - 1; + + /* Setting Time Segment 1 in BTR Register */ + btr1 = dbt->prop_seg + dbt->phase_seg1 - 1; + + /* Setting Time Segment 2 in BTR Register */ + btr1 |= (dbt->phase_seg2 - 1) << priv->devtype.btr_ts2_shift; + + /* Setting Synchronous jump width in BTR Register */ + btr1 |= (dbt->sjw - 1) << priv->devtype.btr_sjw_shift; + + priv->write_reg(priv, XCAN_F_BRPR_OFFSET, btr0); + priv->write_reg(priv, XCAN_F_BTR_OFFSET, btr1); + } + netdev_dbg(ndev, "BRPR=0x%08x, BTR=0x%08x\n", - priv->read_reg(priv, XCAN_BRPR_OFFSET), - priv->read_reg(priv, XCAN_BTR_OFFSET)); + priv->read_reg(priv, XCAN_BRPR_OFFSET), + priv->read_reg(priv, XCAN_BTR_OFFSET)); return 0; } @@ -392,9 +457,8 @@ static int xcan_set_bittiming(struct net_device *ndev) static int xcan_chip_start(struct net_device *ndev) { struct xcan_priv *priv = netdev_priv(ndev); - u32 reg_msr, reg_sr_mask; + u32 reg_msr; int err; - unsigned long timeout; u32 ier; /* Check if it is in reset mode */ @@ -420,10 +484,8 @@ static int xcan_chip_start(struct net_device *ndev) /* Check whether it is loopback mode or normal mode */ if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) { reg_msr = XCAN_MSR_LBACK_MASK; - reg_sr_mask = XCAN_SR_LBACK_MASK; } else { reg_msr = 0x0; - reg_sr_mask = XCAN_SR_NORMAL_MASK; } /* enable the first extended filter, if any, as cores with extended @@ -435,16 +497,8 @@ static int xcan_chip_start(struct net_device *ndev) priv->write_reg(priv, XCAN_MSR_OFFSET, reg_msr); priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_CEN_MASK); - timeout = jiffies + XCAN_TIMEOUT; - while (!(priv->read_reg(priv, XCAN_SR_OFFSET) & reg_sr_mask)) { - if (time_after(jiffies, timeout)) { - netdev_warn(ndev, - "timed out for correct mode\n"); - return -ETIMEDOUT; - } - } netdev_dbg(ndev, "status:#x%08x\n", - priv->read_reg(priv, XCAN_SR_OFFSET)); + priv->read_reg(priv, XCAN_SR_OFFSET)); priv->can.state = CAN_STATE_ERROR_ACTIVE; return 0; @@ -483,6 +537,7 @@ static int xcan_do_set_mode(struct net_device *ndev, enum can_mode mode) /** * xcan_write_frame - Write a frame to HW + * @priv: Driver private data structure * @skb: sk_buff pointer that contains data to be Txed * @frame_offset: Register offset to write the frame to */ @@ -490,7 +545,8 @@ static void xcan_write_frame(struct xcan_priv *priv, struct sk_buff *skb, int frame_offset) { u32 id, dlc, data[2] = {0, 0}; - struct can_frame *cf = (struct can_frame *)skb->data; + struct canfd_frame *cf = (struct canfd_frame *)skb->data; + u32 ramoff, dwindex = 0, i; /* Watch carefully on the bit sequence */ if (cf->can_id & CAN_EFF_FLAG) { @@ -498,7 +554,7 @@ static void xcan_write_frame(struct xcan_priv *priv, struct sk_buff *skb, id = ((cf->can_id & CAN_EFF_MASK) << XCAN_IDR_ID2_SHIFT) & XCAN_IDR_ID2_MASK; id |= (((cf->can_id & CAN_EFF_MASK) >> - (CAN_EFF_ID_BITS-CAN_SFF_ID_BITS)) << + (CAN_EFF_ID_BITS - CAN_SFF_ID_BITS)) << XCAN_IDR_ID1_SHIFT) & XCAN_IDR_ID1_MASK; /* The substibute remote TX request bit should be "1" @@ -519,31 +575,51 @@ static void xcan_write_frame(struct xcan_priv *priv, struct sk_buff *skb, id |= XCAN_IDR_SRR_MASK; } - dlc = cf->can_dlc << XCAN_DLCR_DLC_SHIFT; - - if (cf->can_dlc > 0) - data[0] = be32_to_cpup((__be32 *)(cf->data + 0)); - if (cf->can_dlc > 4) - data[1] = be32_to_cpup((__be32 *)(cf->data + 4)); + dlc = can_len2dlc(cf->len) << XCAN_DLCR_DLC_SHIFT; + if (can_is_canfd_skb(skb)) { + if (cf->flags & CANFD_BRS) + dlc |= XCAN_DLCR_BRS_MASK; + dlc |= XCAN_DLCR_EDL_MASK; + } priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id); /* If the CAN frame is RTR frame this write triggers transmission * (not on CAN FD) */ priv->write_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_offset), dlc); - if (!(cf->can_id & CAN_RTR_FLAG)) { - priv->write_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_offset), - data[0]); - /* If the CAN frame is Standard/Extended frame this - * write triggers transmission (not on CAN FD) - */ - priv->write_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_offset), - data[1]); + if (priv->devtype.cantype == XAXI_CANFD || + priv->devtype.cantype == XAXI_CANFD_2_0) { + for (i = 0; i < cf->len; i += 4) { + ramoff = XCANFD_FRAME_DW_OFFSET(frame_offset) + + (dwindex * XCANFD_DW_BYTES); + priv->write_reg(priv, ramoff, + be32_to_cpup((__be32 *)(cf->data + i))); + dwindex++; + } + } else { + if (cf->len > 0) + data[0] = be32_to_cpup((__be32 *)(cf->data + 0)); + if (cf->len > 4) + data[1] = be32_to_cpup((__be32 *)(cf->data + 4)); + + if (!(cf->can_id & CAN_RTR_FLAG)) { + priv->write_reg(priv, + XCAN_FRAME_DW1_OFFSET(frame_offset), + data[0]); + /* If the CAN frame is Standard/Extended frame this + * write triggers transmission (not on CAN FD) + */ + priv->write_reg(priv, + XCAN_FRAME_DW2_OFFSET(frame_offset), + data[1]); + } } } /** * xcan_start_xmit_fifo - Starts the transmission (FIFO mode) + * @skb: sk_buff pointer that contains data to be Txed + * @ndev: Pointer to net_device structure * * Return: 0 on success, -ENOSPC if FIFO is full. */ @@ -580,6 +656,8 @@ static int xcan_start_xmit_fifo(struct sk_buff *skb, struct net_device *ndev) /** * xcan_start_xmit_mailbox - Starts the transmission (mailbox mode) + * @skb: sk_buff pointer that contains data to be Txed + * @ndev: Pointer to net_device structure * * Return: 0 on success, -ENOSPC if there is no space */ @@ -712,6 +790,88 @@ static int xcan_rx(struct net_device *ndev, int frame_base) } /** + * xcanfd_rx - Is called from CAN isr to complete the received + * frame processing + * @ndev: Pointer to net_device structure + * @frame_base: Register offset to the frame to be read + * + * This function is invoked from the CAN isr(poll) to process the Rx frames. It + * does minimal processing and invokes "netif_receive_skb" to complete further + * processing. + * Return: 1 on success and 0 on failure. + */ +static int xcanfd_rx(struct net_device *ndev, int frame_base) +{ + struct xcan_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &ndev->stats; + struct canfd_frame *cf; + struct sk_buff *skb; + u32 id_xcan, dlc, data[2] = {0, 0}, dwindex = 0, i, dw_offset; + + id_xcan = priv->read_reg(priv, XCAN_FRAME_ID_OFFSET(frame_base)); + dlc = priv->read_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_base)); + if (dlc & XCAN_DLCR_EDL_MASK) + skb = alloc_canfd_skb(ndev, &cf); + else + skb = alloc_can_skb(ndev, (struct can_frame **)&cf); + + if (unlikely(!skb)) { + stats->rx_dropped++; + return 0; + } + + /* Change Xilinx CANFD data length format to socketCAN data + * format + */ + if (dlc & XCAN_DLCR_EDL_MASK) + cf->len = can_dlc2len((dlc & XCAN_DLCR_DLC_MASK) >> + XCAN_DLCR_DLC_SHIFT); + else + cf->len = get_can_dlc((dlc & XCAN_DLCR_DLC_MASK) >> + XCAN_DLCR_DLC_SHIFT); + + /* Change Xilinx CAN ID format to socketCAN ID format */ + if (id_xcan & XCAN_IDR_IDE_MASK) { + /* The received frame is an Extended format frame */ + cf->can_id = (id_xcan & XCAN_IDR_ID1_MASK) >> 3; + cf->can_id |= (id_xcan & XCAN_IDR_ID2_MASK) >> + XCAN_IDR_ID2_SHIFT; + cf->can_id |= CAN_EFF_FLAG; + if (id_xcan & XCAN_IDR_RTR_MASK) + cf->can_id |= CAN_RTR_FLAG; + } else { + /* The received frame is a standard format frame */ + cf->can_id = (id_xcan & XCAN_IDR_ID1_MASK) >> + XCAN_IDR_ID1_SHIFT; + if (!(dlc & XCAN_DLCR_EDL_MASK) && (id_xcan & + XCAN_IDR_SRR_MASK)) + cf->can_id |= CAN_RTR_FLAG; + } + + /* Check the frame received is FD or not*/ + if (dlc & XCAN_DLCR_EDL_MASK) { + for (i = 0; i < cf->len; i += 4) { + dw_offset = XCANFD_FRAME_DW_OFFSET(frame_base) + + (dwindex * XCANFD_DW_BYTES); + data[0] = priv->read_reg(priv, dw_offset); + *(__be32 *)(cf->data + i) = cpu_to_be32(data[0]); + dwindex++; + } + } else { + for (i = 0; i < cf->len; i += 4) { + dw_offset = XCANFD_FRAME_DW_OFFSET(frame_base); + data[0] = priv->read_reg(priv, dw_offset + i); + *(__be32 *)(cf->data + i) = cpu_to_be32(data[0]); + } + } + stats->rx_bytes += cf->len; + stats->rx_packets++; + netif_receive_skb(skb); + + return 1; +} + +/** * xcan_current_error_state - Get current error state from HW * @ndev: Pointer to net_device structure * @@ -924,7 +1084,7 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ; } } - priv->can.can_stats.bus_error++; + priv->can.can_stats.bus_error++; } if (skb) { @@ -934,7 +1094,7 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) } netdev_dbg(ndev, "%s: error status register:0x%x\n", - __func__, priv->read_reg(priv, XCAN_ESR_OFFSET)); + __func__, priv->read_reg(priv, XCAN_ESR_OFFSET)); } /** @@ -960,6 +1120,7 @@ static void xcan_state_interrupt(struct net_device *ndev, u32 isr) /** * xcan_rx_fifo_get_next_frame - Get register offset of next RX frame + * @priv: Driver private data structure * * Return: Register offset of the next frame in RX FIFO. */ @@ -968,7 +1129,7 @@ static int xcan_rx_fifo_get_next_frame(struct xcan_priv *priv) int offset; if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI) { - u32 fsr; + u32 fsr, mask; /* clear RXOK before the is-empty check so that any newly * received frame will reassert it without a race @@ -978,13 +1139,20 @@ static int xcan_rx_fifo_get_next_frame(struct xcan_priv *priv) fsr = priv->read_reg(priv, XCAN_FSR_OFFSET); /* check if RX FIFO is empty */ - if (!(fsr & XCAN_FSR_FL_MASK)) + if (priv->devtype.flags & XCAN_FLAG_CANFD_2) + mask = XCAN_2_FSR_FL_MASK; + else + mask = XCAN_FSR_FL_MASK; + + if (!(fsr & mask)) return -ENOENT; if (priv->devtype.flags & XCAN_FLAG_CANFD_2) - offset = XCAN_RXMSG_2_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK); + offset = + XCAN_RXMSG_2_FRAME_OFFSET(fsr & XCAN_2_FSR_RI_MASK); else - offset = XCAN_RXMSG_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK); + offset = + XCAN_RXMSG_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK); } else { /* check if RX FIFO is empty */ @@ -1019,7 +1187,10 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) while ((frame_offset = xcan_rx_fifo_get_next_frame(priv)) >= 0 && (work_done < quota)) { - work_done += xcan_rx(ndev, frame_offset); + if (xcan_rx_int_mask(priv) & XCAN_IXR_RXOK_MASK) + work_done += xcanfd_rx(ndev, frame_offset); + else + work_done += xcan_rx(ndev, frame_offset); if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI) /* increment read index */ @@ -1094,8 +1265,10 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr) * via TXFEMP handling as we read TXFEMP *after* TXOK * clear to satisfy (1). */ - while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) { - priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + while ((isr & XCAN_IXR_TXOK_MASK) && + !WARN_ON(++retries == 100)) { + priv->write_reg(priv, XCAN_ICR_OFFSET, + XCAN_IXR_TXOK_MASK); isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } @@ -1208,12 +1381,12 @@ static int xcan_open(struct net_device *ndev) ret = pm_runtime_get_sync(priv->dev); if (ret < 0) { netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n", - __func__, ret); + __func__, ret); return ret; } ret = request_irq(ndev->irq, xcan_interrupt, priv->irq_flags, - ndev->name, ndev); + ndev->name, ndev); if (ret < 0) { netdev_err(ndev, "irq allocation for CAN failed\n"); goto err; @@ -1284,7 +1457,7 @@ static int xcan_close(struct net_device *ndev) * Return: 0 on success and failure value on error */ static int xcan_get_berr_counter(const struct net_device *ndev, - struct can_berr_counter *bec) + struct can_berr_counter *bec) { struct xcan_priv *priv = netdev_priv(ndev); int ret; @@ -1292,7 +1465,7 @@ static int xcan_get_berr_counter(const struct net_device *ndev, ret = pm_runtime_get_sync(priv->dev); if (ret < 0) { netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n", - __func__, ret); + __func__, ret); return ret; } @@ -1305,7 +1478,6 @@ static int xcan_get_berr_counter(const struct net_device *ndev, return 0; } - static const struct net_device_ops xcan_netdev_ops = { .ndo_open = xcan_open, .ndo_stop = xcan_close, @@ -1417,6 +1589,8 @@ static const struct dev_pm_ops xcan_dev_pm_ops = { }; static const struct xcan_devtype_data xcan_zynq_data = { + .cantype = XZYNQ_CANPS, + .flags = XCAN_FLAG_TXFEMP, .bittiming_const = &xcan_bittiming_const, .btr_ts2_shift = XCAN_BTR_TS2_SHIFT, .btr_sjw_shift = XCAN_BTR_SJW_SHIFT, @@ -1424,6 +1598,8 @@ static const struct xcan_devtype_data xcan_zynq_data = { }; static const struct xcan_devtype_data xcan_axi_data = { + .cantype = XAXI_CAN, + .flags = XCAN_FLAG_TXFEMP, .bittiming_const = &xcan_bittiming_const, .btr_ts2_shift = XCAN_BTR_TS2_SHIFT, .btr_sjw_shift = XCAN_BTR_SJW_SHIFT, @@ -1431,6 +1607,7 @@ static const struct xcan_devtype_data xcan_axi_data = { }; static const struct xcan_devtype_data xcan_canfd_data = { + .cantype = XAXI_CANFD, .flags = XCAN_FLAG_EXT_FILTERS | XCAN_FLAG_RXMNF | XCAN_FLAG_TX_MAILBOXES | @@ -1442,6 +1619,7 @@ static const struct xcan_devtype_data xcan_canfd_data = { }; static const struct xcan_devtype_data xcan_canfd2_data = { + .cantype = XAXI_CANFD_2_0, .flags = XCAN_FLAG_EXT_FILTERS | XCAN_FLAG_RXMNF | XCAN_FLAG_TX_MAILBOXES | @@ -1554,6 +1732,19 @@ static int xcan_probe(struct platform_device *pdev) priv->can.do_get_berr_counter = xcan_get_berr_counter; priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_BERR_REPORTING; + + if (devtype->cantype == XAXI_CANFD) + priv->can.data_bittiming_const = + &xcan_data_bittiming_const_canfd; + + if (devtype->cantype == XAXI_CANFD_2_0) + priv->can.data_bittiming_const = + &xcan_data_bittiming_const_canfd2; + + if (devtype->cantype == XAXI_CANFD || + devtype->cantype == XAXI_CANFD_2_0) + priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD; + priv->reg_base = addr; priv->tx_max = tx_max; priv->devtype = *devtype; @@ -1570,7 +1761,8 @@ static int xcan_probe(struct platform_device *pdev) /* Getting the CAN can_clk info */ priv->can_clk = devm_clk_get(&pdev->dev, "can_clk"); if (IS_ERR(priv->can_clk)) { - dev_err(&pdev->dev, "Device clock not found.\n"); + if (PTR_ERR(priv->can_clk) != -EPROBE_DEFER) + dev_err(&pdev->dev, "Device clock not found.\n"); ret = PTR_ERR(priv->can_clk); goto err_free; } @@ -1589,7 +1781,7 @@ static int xcan_probe(struct platform_device *pdev) ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) { netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n", - __func__, ret); + __func__, ret); goto err_pmdisable; } diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index d9c56a779c08..0a1be5259be0 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -536,7 +536,6 @@ static void b53_srab_mux_init(struct platform_device *pdev) struct b53_device *dev = platform_get_drvdata(pdev); struct b53_srab_priv *priv = dev->priv; struct b53_srab_port_priv *p; - struct resource *r; unsigned int port; u32 reg, off = 0; int ret; @@ -544,8 +543,7 @@ static void b53_srab_mux_init(struct platform_device *pdev) if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) return; - r = platform_get_resource(pdev, IORESOURCE_MEM, 1); - priv->mux_config = devm_ioremap_resource(&pdev->dev, r); + priv->mux_config = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(priv->mux_config)) return; @@ -593,7 +591,6 @@ static int b53_srab_probe(struct platform_device *pdev) const struct of_device_id *of_id = NULL; struct b53_srab_priv *priv; struct b53_device *dev; - struct resource *r; if (dn) of_id = of_match_node(b53_srab_of_match, dn); @@ -610,8 +607,7 @@ static int b53_srab_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(&pdev->dev, r); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return -ENOMEM; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 3811fdbda13e..49f99436018a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1041,7 +1041,6 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) struct b53_device *dev; struct dsa_switch *ds; void __iomem **base; - struct resource *r; unsigned int i; u32 reg, rev; int ret; @@ -1107,8 +1106,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) base = &priv->core; for (i = 0; i < BCM_SF2_REGS_NUM; i++) { - r = platform_get_resource(pdev, IORESOURCE_MEM, i); - *base = devm_ioremap_resource(&pdev->dev, r); + *base = devm_platform_ioremap_resource(pdev, i); if (IS_ERR(*base)) { pr_err("unable to find register: %s\n", reg_names[i]); return PTR_ERR(*base); diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 4e64835deac2..2175ec13bb2c 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1822,7 +1822,6 @@ remove_gphy: static int gswip_probe(struct platform_device *pdev) { struct gswip_priv *priv; - struct resource *gswip_res, *mdio_res, *mii_res; struct device_node *mdio_np, *gphy_fw_np; struct device *dev = &pdev->dev; int err; @@ -1833,18 +1832,15 @@ static int gswip_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - gswip_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->gswip = devm_ioremap_resource(dev, gswip_res); + priv->gswip = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->gswip)) return PTR_ERR(priv->gswip); - mdio_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - priv->mdio = devm_ioremap_resource(dev, mdio_res); + priv->mdio = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(priv->mdio)) return PTR_ERR(priv->mdio); - mii_res = platform_get_resource(pdev, IORESOURCE_MEM, 2); - priv->mii = devm_ioremap_resource(dev, mii_res); + priv->mii = devm_platform_ioremap_resource(pdev, 2); if (IS_ERR(priv->mii)) return PTR_ERR(priv->mii); diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig index fe0a13b79c4b..e1c23d1e91e6 100644 --- a/drivers/net/dsa/microchip/Kconfig +++ b/drivers/net/dsa/microchip/Kconfig @@ -5,7 +5,6 @@ config NET_DSA_MICROCHIP_KSZ_COMMON menuconfig NET_DSA_MICROCHIP_KSZ9477 tristate "Microchip KSZ9477 series switch support" depends on NET_DSA - select NET_DSA_TAG_KSZ9477 select NET_DSA_MICROCHIP_KSZ_COMMON help This driver adds support for Microchip KSZ9477 switch chips. @@ -16,3 +15,20 @@ config NET_DSA_MICROCHIP_KSZ9477_SPI select REGMAP_SPI help Select to enable support for registering switches configured through SPI. + +menuconfig NET_DSA_MICROCHIP_KSZ8795 + tristate "Microchip KSZ8795 series switch support" + depends on NET_DSA + select NET_DSA_MICROCHIP_KSZ_COMMON + help + This driver adds support for Microchip KSZ8795 switch chips. + +config NET_DSA_MICROCHIP_KSZ8795_SPI + tristate "KSZ8795 series SPI connected switch driver" + depends on NET_DSA_MICROCHIP_KSZ8795 && SPI + select REGMAP_SPI + help + This driver accesses KSZ8795 chip through SPI. + + It is required to use the KSZ8795 switch driver as the only access + is through SPI. diff --git a/drivers/net/dsa/microchip/Makefile b/drivers/net/dsa/microchip/Makefile index 68451b02f775..e3d799b95d7d 100644 --- a/drivers/net/dsa/microchip/Makefile +++ b/drivers/net/dsa/microchip/Makefile @@ -2,3 +2,5 @@ obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ_COMMON) += ksz_common.o obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477) += ksz9477.o obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ9477_SPI) += ksz9477_spi.o +obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ8795) += ksz8795.o +obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ8795_SPI) += ksz8795_spi.o diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c new file mode 100644 index 000000000000..a23d3ffdf0c4 --- /dev/null +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -0,0 +1,1310 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Microchip KSZ8795 switch driver + * + * Copyright (C) 2017 Microchip Technology Inc. + * Tristram Ha <Tristram.Ha@microchip.com> + */ + +#include <linux/delay.h> +#include <linux/export.h> +#include <linux/gpio.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/platform_data/microchip-ksz.h> +#include <linux/phy.h> +#include <linux/etherdevice.h> +#include <linux/if_bridge.h> +#include <net/dsa.h> +#include <net/switchdev.h> + +#include "ksz_common.h" +#include "ksz8795_reg.h" + +static const struct { + char string[ETH_GSTRING_LEN]; +} mib_names[TOTAL_SWITCH_COUNTER_NUM] = { + { "rx_hi" }, + { "rx_undersize" }, + { "rx_fragments" }, + { "rx_oversize" }, + { "rx_jabbers" }, + { "rx_symbol_err" }, + { "rx_crc_err" }, + { "rx_align_err" }, + { "rx_mac_ctrl" }, + { "rx_pause" }, + { "rx_bcast" }, + { "rx_mcast" }, + { "rx_ucast" }, + { "rx_64_or_less" }, + { "rx_65_127" }, + { "rx_128_255" }, + { "rx_256_511" }, + { "rx_512_1023" }, + { "rx_1024_1522" }, + { "rx_1523_2000" }, + { "rx_2001" }, + { "tx_hi" }, + { "tx_late_col" }, + { "tx_pause" }, + { "tx_bcast" }, + { "tx_mcast" }, + { "tx_ucast" }, + { "tx_deferred" }, + { "tx_total_col" }, + { "tx_exc_col" }, + { "tx_single_col" }, + { "tx_mult_col" }, + { "rx_total" }, + { "tx_total" }, + { "rx_discards" }, + { "tx_discards" }, +}; + +static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) +{ + regmap_update_bits(dev->regmap[0], addr, bits, set ? bits : 0); +} + +static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, + bool set) +{ + regmap_update_bits(dev->regmap[0], PORT_CTRL_ADDR(port, offset), + bits, set ? bits : 0); +} + +static int ksz8795_reset_switch(struct ksz_device *dev) +{ + /* reset switch */ + ksz_write8(dev, REG_POWER_MANAGEMENT_1, + SW_SOFTWARE_POWER_DOWN << SW_POWER_MANAGEMENT_MODE_S); + ksz_write8(dev, REG_POWER_MANAGEMENT_1, 0); + + return 0; +} + +static void ksz8795_set_prio_queue(struct ksz_device *dev, int port, int queue) +{ + u8 hi, lo; + + /* Number of queues can only be 1, 2, or 4. */ + switch (queue) { + case 4: + case 3: + queue = PORT_QUEUE_SPLIT_4; + break; + case 2: + queue = PORT_QUEUE_SPLIT_2; + break; + default: + queue = PORT_QUEUE_SPLIT_1; + } + ksz_pread8(dev, port, REG_PORT_CTRL_0, &lo); + ksz_pread8(dev, port, P_DROP_TAG_CTRL, &hi); + lo &= ~PORT_QUEUE_SPLIT_L; + if (queue & PORT_QUEUE_SPLIT_2) + lo |= PORT_QUEUE_SPLIT_L; + hi &= ~PORT_QUEUE_SPLIT_H; + if (queue & PORT_QUEUE_SPLIT_4) + hi |= PORT_QUEUE_SPLIT_H; + ksz_pwrite8(dev, port, REG_PORT_CTRL_0, lo); + ksz_pwrite8(dev, port, P_DROP_TAG_CTRL, hi); + + /* Default is port based for egress rate limit. */ + if (queue != PORT_QUEUE_SPLIT_1) + ksz_cfg(dev, REG_SW_CTRL_19, SW_OUT_RATE_LIMIT_QUEUE_BASED, + true); +} + +static void ksz8795_r_mib_cnt(struct ksz_device *dev, int port, u16 addr, + u64 *cnt) +{ + u16 ctrl_addr; + u32 data; + u8 check; + int loop; + + ctrl_addr = addr + SWITCH_COUNTER_NUM * port; + ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ); + + mutex_lock(&dev->alu_mutex); + ksz_write16(dev, REG_IND_CTRL_0, ctrl_addr); + + /* It is almost guaranteed to always read the valid bit because of + * slow SPI speed. + */ + for (loop = 2; loop > 0; loop--) { + ksz_read8(dev, REG_IND_MIB_CHECK, &check); + + if (check & MIB_COUNTER_VALID) { + ksz_read32(dev, REG_IND_DATA_LO, &data); + if (check & MIB_COUNTER_OVERFLOW) + *cnt += MIB_COUNTER_VALUE + 1; + *cnt += data & MIB_COUNTER_VALUE; + break; + } + } + mutex_unlock(&dev->alu_mutex); +} + +static void ksz8795_r_mib_pkt(struct ksz_device *dev, int port, u16 addr, + u64 *dropped, u64 *cnt) +{ + u16 ctrl_addr; + u32 data; + u8 check; + int loop; + + addr -= SWITCH_COUNTER_NUM; + 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); + + mutex_lock(&dev->alu_mutex); + ksz_write16(dev, REG_IND_CTRL_0, ctrl_addr); + + /* It is almost guaranteed to always read the valid bit because of + * slow SPI speed. + */ + for (loop = 2; loop > 0; loop--) { + ksz_read8(dev, REG_IND_MIB_CHECK, &check); + + if (check & MIB_COUNTER_VALID) { + ksz_read32(dev, REG_IND_DATA_LO, &data); + if (addr < 2) { + u64 total; + + total = check & MIB_TOTAL_BYTES_H; + total <<= 32; + *cnt += total; + *cnt += data; + if (check & MIB_COUNTER_OVERFLOW) { + total = MIB_TOTAL_BYTES_H + 1; + total <<= 32; + *cnt += total; + } + } else { + if (check & MIB_COUNTER_OVERFLOW) + *cnt += MIB_PACKET_DROPPED + 1; + *cnt += data & MIB_PACKET_DROPPED; + } + break; + } + } + mutex_unlock(&dev->alu_mutex); +} + +static void ksz8795_freeze_mib(struct ksz_device *dev, int port, bool freeze) +{ + /* enable the port for flush/freeze function */ + if (freeze) + ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true); + ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FREEZE, freeze); + + /* disable the port after freeze is done */ + if (!freeze) + ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), false); +} + +static void ksz8795_port_init_cnt(struct ksz_device *dev, int port) +{ + struct ksz_port_mib *mib = &dev->ports[port].mib; + + /* flush all enabled port MIB counters */ + ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true); + ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FLUSH, true); + ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), false); + + mib->cnt_ptr = 0; + + /* Some ports may not have MIB counters before SWITCH_COUNTER_NUM. */ + while (mib->cnt_ptr < dev->reg_mib_cnt) { + dev->dev_ops->r_mib_cnt(dev, port, mib->cnt_ptr, + &mib->counters[mib->cnt_ptr]); + ++mib->cnt_ptr; + } + + /* Some ports may not have MIB counters after SWITCH_COUNTER_NUM. */ + while (mib->cnt_ptr < dev->mib_cnt) { + dev->dev_ops->r_mib_pkt(dev, port, mib->cnt_ptr, + NULL, &mib->counters[mib->cnt_ptr]); + ++mib->cnt_ptr; + } + mib->cnt_ptr = 0; + memset(mib->counters, 0, dev->mib_cnt * sizeof(u64)); +} + +static void ksz8795_r_table(struct ksz_device *dev, int table, u16 addr, + u64 *data) +{ + u16 ctrl_addr; + + ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr; + + mutex_lock(&dev->alu_mutex); + ksz_write16(dev, REG_IND_CTRL_0, ctrl_addr); + ksz_read64(dev, REG_IND_DATA_HI, data); + mutex_unlock(&dev->alu_mutex); +} + +static void ksz8795_w_table(struct ksz_device *dev, int table, u16 addr, + u64 data) +{ + u16 ctrl_addr; + + ctrl_addr = IND_ACC_TABLE(table) | addr; + + mutex_lock(&dev->alu_mutex); + ksz_write64(dev, REG_IND_DATA_HI, data); + ksz_write16(dev, REG_IND_CTRL_0, ctrl_addr); + mutex_unlock(&dev->alu_mutex); +} + +static int ksz8795_valid_dyn_entry(struct ksz_device *dev, u8 *data) +{ + int timeout = 100; + + do { + ksz_read8(dev, REG_IND_DATA_CHECK, data); + timeout--; + } while ((*data & DYNAMIC_MAC_TABLE_NOT_READY) && timeout); + + /* Entry is not ready for accessing. */ + if (*data & DYNAMIC_MAC_TABLE_NOT_READY) { + return -EAGAIN; + /* Entry is ready for accessing. */ + } else { + ksz_read8(dev, REG_IND_DATA_8, data); + + /* There is no valid entry in the table. */ + if (*data & DYNAMIC_MAC_TABLE_MAC_EMPTY) + return -ENXIO; + } + return 0; +} + +static int ksz8795_r_dyn_mac_table(struct ksz_device *dev, u16 addr, + u8 *mac_addr, u8 *fid, u8 *src_port, + u8 *timestamp, u16 *entries) +{ + u32 data_hi, data_lo; + u16 ctrl_addr; + u8 data; + int rc; + + ctrl_addr = IND_ACC_TABLE(TABLE_DYNAMIC_MAC | TABLE_READ) | addr; + + mutex_lock(&dev->alu_mutex); + ksz_write16(dev, REG_IND_CTRL_0, ctrl_addr); + + rc = ksz8795_valid_dyn_entry(dev, &data); + if (rc == -EAGAIN) { + if (addr == 0) + *entries = 0; + } else if (rc == -ENXIO) { + *entries = 0; + /* At least one valid entry in the table. */ + } else { + u64 buf = 0; + int cnt; + + ksz_read64(dev, REG_IND_DATA_HI, &buf); + data_hi = (u32)(buf >> 32); + data_lo = (u32)buf; + + /* Check out how many valid entry in the table. */ + cnt = data & DYNAMIC_MAC_TABLE_ENTRIES_H; + cnt <<= DYNAMIC_MAC_ENTRIES_H_S; + cnt |= (data_hi & DYNAMIC_MAC_TABLE_ENTRIES) >> + DYNAMIC_MAC_ENTRIES_S; + *entries = cnt + 1; + + *fid = (data_hi & DYNAMIC_MAC_TABLE_FID) >> + DYNAMIC_MAC_FID_S; + *src_port = (data_hi & DYNAMIC_MAC_TABLE_SRC_PORT) >> + DYNAMIC_MAC_SRC_PORT_S; + *timestamp = (data_hi & DYNAMIC_MAC_TABLE_TIMESTAMP) >> + DYNAMIC_MAC_TIMESTAMP_S; + + mac_addr[5] = (u8)data_lo; + mac_addr[4] = (u8)(data_lo >> 8); + mac_addr[3] = (u8)(data_lo >> 16); + mac_addr[2] = (u8)(data_lo >> 24); + + mac_addr[1] = (u8)data_hi; + mac_addr[0] = (u8)(data_hi >> 8); + rc = 0; + } + mutex_unlock(&dev->alu_mutex); + + return rc; +} + +static int ksz8795_r_sta_mac_table(struct ksz_device *dev, u16 addr, + struct alu_struct *alu) +{ + u32 data_hi, data_lo; + u64 data; + + ksz8795_r_table(dev, TABLE_STATIC_MAC, addr, &data); + data_hi = data >> 32; + data_lo = (u32)data; + if (data_hi & (STATIC_MAC_TABLE_VALID | STATIC_MAC_TABLE_OVERRIDE)) { + alu->mac[5] = (u8)data_lo; + alu->mac[4] = (u8)(data_lo >> 8); + alu->mac[3] = (u8)(data_lo >> 16); + alu->mac[2] = (u8)(data_lo >> 24); + alu->mac[1] = (u8)data_hi; + alu->mac[0] = (u8)(data_hi >> 8); + alu->port_forward = (data_hi & STATIC_MAC_TABLE_FWD_PORTS) >> + STATIC_MAC_FWD_PORTS_S; + alu->is_override = + (data_hi & STATIC_MAC_TABLE_OVERRIDE) ? 1 : 0; + data_hi >>= 1; + alu->is_use_fid = (data_hi & STATIC_MAC_TABLE_USE_FID) ? 1 : 0; + alu->fid = (data_hi & STATIC_MAC_TABLE_FID) >> + STATIC_MAC_FID_S; + return 0; + } + return -ENXIO; +} + +static void ksz8795_w_sta_mac_table(struct ksz_device *dev, u16 addr, + struct alu_struct *alu) +{ + u32 data_hi, data_lo; + u64 data; + + data_lo = ((u32)alu->mac[2] << 24) | + ((u32)alu->mac[3] << 16) | + ((u32)alu->mac[4] << 8) | alu->mac[5]; + data_hi = ((u32)alu->mac[0] << 8) | alu->mac[1]; + data_hi |= (u32)alu->port_forward << STATIC_MAC_FWD_PORTS_S; + + if (alu->is_override) + data_hi |= STATIC_MAC_TABLE_OVERRIDE; + if (alu->is_use_fid) { + data_hi |= STATIC_MAC_TABLE_USE_FID; + data_hi |= (u32)alu->fid << STATIC_MAC_FID_S; + } + if (alu->is_static) + data_hi |= STATIC_MAC_TABLE_VALID; + else + data_hi &= ~STATIC_MAC_TABLE_OVERRIDE; + + data = (u64)data_hi << 32 | data_lo; + ksz8795_w_table(dev, TABLE_STATIC_MAC, addr, data); +} + +static void ksz8795_from_vlan(u16 vlan, u8 *fid, u8 *member, u8 *valid) +{ + *fid = vlan & VLAN_TABLE_FID; + *member = (vlan & VLAN_TABLE_MEMBERSHIP) >> VLAN_TABLE_MEMBERSHIP_S; + *valid = !!(vlan & VLAN_TABLE_VALID); +} + +static void ksz8795_to_vlan(u8 fid, u8 member, u8 valid, u16 *vlan) +{ + *vlan = fid; + *vlan |= (u16)member << VLAN_TABLE_MEMBERSHIP_S; + if (valid) + *vlan |= VLAN_TABLE_VALID; +} + +static void ksz8795_r_vlan_entries(struct ksz_device *dev, u16 addr) +{ + u64 data; + int i; + + ksz8795_r_table(dev, TABLE_VLAN, addr, &data); + addr *= 4; + for (i = 0; i < 4; i++) { + dev->vlan_cache[addr + i].table[0] = (u16)data; + data >>= VLAN_TABLE_S; + } +} + +static void ksz8795_r_vlan_table(struct ksz_device *dev, u16 vid, u16 *vlan) +{ + int index; + u16 *data; + u16 addr; + u64 buf; + + data = (u16 *)&buf; + addr = vid / 4; + index = vid & 3; + ksz8795_r_table(dev, TABLE_VLAN, addr, &buf); + *vlan = data[index]; +} + +static void ksz8795_w_vlan_table(struct ksz_device *dev, u16 vid, u16 vlan) +{ + int index; + u16 *data; + u16 addr; + u64 buf; + + data = (u16 *)&buf; + addr = vid / 4; + index = vid & 3; + ksz8795_r_table(dev, TABLE_VLAN, addr, &buf); + data[index] = vlan; + dev->vlan_cache[vid].table[0] = vlan; + ksz8795_w_table(dev, TABLE_VLAN, addr, buf); +} + +static void ksz8795_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val) +{ + u8 restart, speed, ctrl, link; + int processed = true; + u16 data = 0; + u8 p = phy; + + switch (reg) { + case PHY_REG_CTRL: + ksz_pread8(dev, p, P_NEG_RESTART_CTRL, &restart); + ksz_pread8(dev, p, P_SPEED_STATUS, &speed); + ksz_pread8(dev, p, P_FORCE_CTRL, &ctrl); + if (restart & PORT_PHY_LOOPBACK) + data |= PHY_LOOPBACK; + if (ctrl & PORT_FORCE_100_MBIT) + data |= PHY_SPEED_100MBIT; + if (!(ctrl & PORT_AUTO_NEG_DISABLE)) + data |= PHY_AUTO_NEG_ENABLE; + if (restart & PORT_POWER_DOWN) + data |= PHY_POWER_DOWN; + if (restart & PORT_AUTO_NEG_RESTART) + data |= PHY_AUTO_NEG_RESTART; + if (ctrl & PORT_FORCE_FULL_DUPLEX) + data |= PHY_FULL_DUPLEX; + if (speed & PORT_HP_MDIX) + data |= PHY_HP_MDIX; + if (restart & PORT_FORCE_MDIX) + data |= PHY_FORCE_MDIX; + if (restart & PORT_AUTO_MDIX_DISABLE) + data |= PHY_AUTO_MDIX_DISABLE; + if (restart & PORT_TX_DISABLE) + data |= PHY_TRANSMIT_DISABLE; + if (restart & PORT_LED_OFF) + data |= PHY_LED_DISABLE; + break; + case PHY_REG_STATUS: + ksz_pread8(dev, p, P_LINK_STATUS, &link); + data = PHY_100BTX_FD_CAPABLE | + PHY_100BTX_CAPABLE | + PHY_10BT_FD_CAPABLE | + PHY_10BT_CAPABLE | + PHY_AUTO_NEG_CAPABLE; + if (link & PORT_AUTO_NEG_COMPLETE) + data |= PHY_AUTO_NEG_ACKNOWLEDGE; + if (link & PORT_STAT_LINK_GOOD) + data |= PHY_LINK_STATUS; + break; + case PHY_REG_ID_1: + data = KSZ8795_ID_HI; + break; + case PHY_REG_ID_2: + data = KSZ8795_ID_LO; + break; + case PHY_REG_AUTO_NEGOTIATION: + ksz_pread8(dev, p, P_LOCAL_CTRL, &ctrl); + data = PHY_AUTO_NEG_802_3; + if (ctrl & PORT_AUTO_NEG_SYM_PAUSE) + data |= PHY_AUTO_NEG_SYM_PAUSE; + if (ctrl & PORT_AUTO_NEG_100BTX_FD) + data |= PHY_AUTO_NEG_100BTX_FD; + if (ctrl & PORT_AUTO_NEG_100BTX) + data |= PHY_AUTO_NEG_100BTX; + if (ctrl & PORT_AUTO_NEG_10BT_FD) + data |= PHY_AUTO_NEG_10BT_FD; + if (ctrl & PORT_AUTO_NEG_10BT) + data |= PHY_AUTO_NEG_10BT; + break; + case PHY_REG_REMOTE_CAPABILITY: + ksz_pread8(dev, p, P_REMOTE_STATUS, &link); + data = PHY_AUTO_NEG_802_3; + if (link & PORT_REMOTE_SYM_PAUSE) + data |= PHY_AUTO_NEG_SYM_PAUSE; + if (link & PORT_REMOTE_100BTX_FD) + data |= PHY_AUTO_NEG_100BTX_FD; + if (link & PORT_REMOTE_100BTX) + data |= PHY_AUTO_NEG_100BTX; + if (link & PORT_REMOTE_10BT_FD) + data |= PHY_AUTO_NEG_10BT_FD; + if (link & PORT_REMOTE_10BT) + data |= PHY_AUTO_NEG_10BT; + if (data & ~PHY_AUTO_NEG_802_3) + data |= PHY_REMOTE_ACKNOWLEDGE_NOT; + break; + default: + processed = false; + break; + } + if (processed) + *val = data; +} + +static void ksz8795_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) +{ + u8 p = phy; + u8 restart, speed, ctrl, data; + + switch (reg) { + case PHY_REG_CTRL: + + /* Do not support PHY reset function. */ + if (val & PHY_RESET) + break; + ksz_pread8(dev, p, P_SPEED_STATUS, &speed); + data = speed; + if (val & PHY_HP_MDIX) + data |= PORT_HP_MDIX; + else + data &= ~PORT_HP_MDIX; + if (data != speed) + ksz_pwrite8(dev, p, P_SPEED_STATUS, data); + ksz_pread8(dev, p, P_FORCE_CTRL, &ctrl); + data = ctrl; + if (!(val & PHY_AUTO_NEG_ENABLE)) + data |= PORT_AUTO_NEG_DISABLE; + else + data &= ~PORT_AUTO_NEG_DISABLE; + + /* Fiber port does not support auto-negotiation. */ + if (dev->ports[p].fiber) + data |= PORT_AUTO_NEG_DISABLE; + if (val & PHY_SPEED_100MBIT) + data |= PORT_FORCE_100_MBIT; + else + data &= ~PORT_FORCE_100_MBIT; + if (val & PHY_FULL_DUPLEX) + data |= PORT_FORCE_FULL_DUPLEX; + else + data &= ~PORT_FORCE_FULL_DUPLEX; + if (data != ctrl) + ksz_pwrite8(dev, p, P_FORCE_CTRL, data); + ksz_pread8(dev, p, P_NEG_RESTART_CTRL, &restart); + data = restart; + if (val & PHY_LED_DISABLE) + data |= PORT_LED_OFF; + else + data &= ~PORT_LED_OFF; + if (val & PHY_TRANSMIT_DISABLE) + data |= PORT_TX_DISABLE; + else + data &= ~PORT_TX_DISABLE; + if (val & PHY_AUTO_NEG_RESTART) + data |= PORT_AUTO_NEG_RESTART; + else + data &= ~(PORT_AUTO_NEG_RESTART); + if (val & PHY_POWER_DOWN) + data |= PORT_POWER_DOWN; + else + data &= ~PORT_POWER_DOWN; + if (val & PHY_AUTO_MDIX_DISABLE) + data |= PORT_AUTO_MDIX_DISABLE; + else + data &= ~PORT_AUTO_MDIX_DISABLE; + if (val & PHY_FORCE_MDIX) + data |= PORT_FORCE_MDIX; + else + data &= ~PORT_FORCE_MDIX; + if (val & PHY_LOOPBACK) + data |= PORT_PHY_LOOPBACK; + else + data &= ~PORT_PHY_LOOPBACK; + if (data != restart) + ksz_pwrite8(dev, p, P_NEG_RESTART_CTRL, data); + break; + case PHY_REG_AUTO_NEGOTIATION: + ksz_pread8(dev, p, P_LOCAL_CTRL, &ctrl); + data = ctrl; + data &= ~(PORT_AUTO_NEG_SYM_PAUSE | + PORT_AUTO_NEG_100BTX_FD | + PORT_AUTO_NEG_100BTX | + PORT_AUTO_NEG_10BT_FD | + PORT_AUTO_NEG_10BT); + if (val & PHY_AUTO_NEG_SYM_PAUSE) + data |= PORT_AUTO_NEG_SYM_PAUSE; + if (val & PHY_AUTO_NEG_100BTX_FD) + data |= PORT_AUTO_NEG_100BTX_FD; + if (val & PHY_AUTO_NEG_100BTX) + data |= PORT_AUTO_NEG_100BTX; + if (val & PHY_AUTO_NEG_10BT_FD) + data |= PORT_AUTO_NEG_10BT_FD; + if (val & PHY_AUTO_NEG_10BT) + data |= PORT_AUTO_NEG_10BT; + if (data != ctrl) + ksz_pwrite8(dev, p, P_LOCAL_CTRL, data); + break; + default: + break; + } +} + +static enum dsa_tag_protocol ksz8795_get_tag_protocol(struct dsa_switch *ds, + int port) +{ + return DSA_TAG_PROTO_KSZ8795; +} + +static void ksz8795_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *buf) +{ + int i; + + for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) { + memcpy(buf + i * ETH_GSTRING_LEN, mib_names[i].string, + ETH_GSTRING_LEN); + } +} + +static void ksz8795_cfg_port_member(struct ksz_device *dev, int port, + u8 member) +{ + u8 data; + + ksz_pread8(dev, port, P_MIRROR_CTRL, &data); + data &= ~PORT_VLAN_MEMBERSHIP; + data |= (member & dev->port_mask); + ksz_pwrite8(dev, port, P_MIRROR_CTRL, data); + dev->ports[port].member = member; +} + +static void ksz8795_port_stp_state_set(struct dsa_switch *ds, int port, + u8 state) +{ + struct ksz_device *dev = ds->priv; + int forward = dev->member; + struct ksz_port *p; + int member = -1; + u8 data; + + p = &dev->ports[port]; + + ksz_pread8(dev, port, P_STP_CTRL, &data); + data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); + + switch (state) { + case BR_STATE_DISABLED: + data |= PORT_LEARN_DISABLE; + if (port < SWITCH_PORT_NUM) + member = 0; + break; + case BR_STATE_LISTENING: + data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE); + if (port < SWITCH_PORT_NUM && + p->stp_state == BR_STATE_DISABLED) + member = dev->host_mask | p->vid_member; + break; + case BR_STATE_LEARNING: + data |= PORT_RX_ENABLE; + break; + case BR_STATE_FORWARDING: + data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); + + /* This function is also used internally. */ + if (port == dev->cpu_port) + break; + + /* Port is a member of a bridge. */ + if (dev->br_member & BIT(port)) { + dev->member |= BIT(port); + member = dev->member; + } else { + member = dev->host_mask | p->vid_member; + } + break; + case BR_STATE_BLOCKING: + data |= PORT_LEARN_DISABLE; + if (port < SWITCH_PORT_NUM && + p->stp_state == BR_STATE_DISABLED) + member = dev->host_mask | p->vid_member; + break; + default: + dev_err(ds->dev, "invalid STP state: %d\n", state); + return; + } + + ksz_pwrite8(dev, port, P_STP_CTRL, data); + p->stp_state = state; + if (data & PORT_RX_ENABLE) + dev->rx_ports |= BIT(port); + else + dev->rx_ports &= ~BIT(port); + if (data & PORT_TX_ENABLE) + dev->tx_ports |= BIT(port); + else + dev->tx_ports &= ~BIT(port); + + /* Port membership may share register with STP state. */ + if (member >= 0 && member != p->member) + ksz8795_cfg_port_member(dev, port, (u8)member); + + /* Check if forwarding needs to be updated. */ + if (state != BR_STATE_FORWARDING) { + if (dev->br_member & BIT(port)) + dev->member &= ~BIT(port); + } + + /* When topology has changed the function ksz_update_port_member + * should be called to modify port forwarding behavior. + */ + if (forward != dev->member) + ksz_update_port_member(dev, port); +} + +static void ksz8795_flush_dyn_mac_table(struct ksz_device *dev, int port) +{ + u8 learn[TOTAL_PORT_NUM]; + int first, index, cnt; + struct ksz_port *p; + + if ((uint)port < TOTAL_PORT_NUM) { + first = port; + cnt = port + 1; + } else { + /* Flush all ports. */ + first = 0; + cnt = dev->mib_port_cnt; + } + for (index = first; index < cnt; index++) { + p = &dev->ports[index]; + if (!p->on) + continue; + ksz_pread8(dev, index, P_STP_CTRL, &learn[index]); + if (!(learn[index] & PORT_LEARN_DISABLE)) + ksz_pwrite8(dev, index, P_STP_CTRL, + learn[index] | PORT_LEARN_DISABLE); + } + ksz_cfg(dev, S_FLUSH_TABLE_CTRL, SW_FLUSH_DYN_MAC_TABLE, true); + for (index = first; index < cnt; index++) { + p = &dev->ports[index]; + if (!p->on) + continue; + if (!(learn[index] & PORT_LEARN_DISABLE)) + ksz_pwrite8(dev, index, P_STP_CTRL, learn[index]); + } +} + +static int ksz8795_port_vlan_filtering(struct dsa_switch *ds, int port, + bool flag) +{ + struct ksz_device *dev = ds->priv; + + ksz_cfg(dev, S_MIRROR_CTRL, SW_VLAN_ENABLE, flag); + + return 0; +} + +static void ksz8795_port_vlan_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; + struct ksz_device *dev = ds->priv; + u16 data, vid, new_pvid = 0; + u8 fid, member, valid; + + ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { + ksz8795_r_vlan_table(dev, vid, &data); + ksz8795_from_vlan(data, &fid, &member, &valid); + + /* First time to setup the VLAN entry. */ + if (!valid) { + /* Need to find a way to map VID to FID. */ + fid = 1; + valid = 1; + } + member |= BIT(port); + + ksz8795_to_vlan(fid, member, valid, &data); + ksz8795_w_vlan_table(dev, vid, data); + + /* change PVID */ + if (vlan->flags & BRIDGE_VLAN_INFO_PVID) + new_pvid = vid; + } + + if (new_pvid) { + ksz_pread16(dev, port, REG_PORT_CTRL_VID, &vid); + vid &= 0xfff; + vid |= new_pvid; + ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, vid); + } +} + +static int ksz8795_port_vlan_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; + struct ksz_device *dev = ds->priv; + u16 data, vid, pvid, new_pvid = 0; + u8 fid, member, valid; + + ksz_pread16(dev, port, REG_PORT_CTRL_VID, &pvid); + pvid = pvid & 0xFFF; + + ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged); + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { + ksz8795_r_vlan_table(dev, vid, &data); + ksz8795_from_vlan(data, &fid, &member, &valid); + + member &= ~BIT(port); + + /* Invalidate the entry if no more member. */ + if (!member) { + fid = 0; + valid = 0; + } + + if (pvid == vid) + new_pvid = 1; + + ksz8795_to_vlan(fid, member, valid, &data); + ksz8795_w_vlan_table(dev, vid, data); + } + + if (new_pvid != pvid) + ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, pvid); + + return 0; +} + +static int ksz8795_port_mirror_add(struct dsa_switch *ds, int port, + struct dsa_mall_mirror_tc_entry *mirror, + bool ingress) +{ + struct ksz_device *dev = ds->priv; + + if (ingress) { + ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true); + dev->mirror_rx |= BIT(port); + } else { + ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true); + dev->mirror_tx |= BIT(port); + } + + ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false); + + /* configure mirror port */ + if (dev->mirror_rx || dev->mirror_tx) + ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL, + PORT_MIRROR_SNIFFER, true); + + return 0; +} + +static void ksz8795_port_mirror_del(struct dsa_switch *ds, int port, + struct dsa_mall_mirror_tc_entry *mirror) +{ + struct ksz_device *dev = ds->priv; + u8 data; + + if (mirror->ingress) { + ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false); + dev->mirror_rx &= ~BIT(port); + } else { + ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false); + dev->mirror_tx &= ~BIT(port); + } + + ksz_pread8(dev, port, P_MIRROR_CTRL, &data); + + if (!dev->mirror_rx && !dev->mirror_tx) + ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL, + PORT_MIRROR_SNIFFER, false); +} + +static void ksz8795_port_setup(struct ksz_device *dev, int port, bool cpu_port) +{ + struct ksz_port *p = &dev->ports[port]; + u8 data8, member; + + /* enable broadcast storm limit */ + ksz_port_cfg(dev, port, P_BCAST_STORM_CTRL, PORT_BROADCAST_STORM, true); + + ksz8795_set_prio_queue(dev, port, 4); + + /* disable DiffServ priority */ + ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_DIFFSERV_ENABLE, false); + + /* replace priority */ + ksz_port_cfg(dev, port, P_802_1P_CTRL, PORT_802_1P_REMAPPING, false); + + /* enable 802.1p priority */ + ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_ENABLE, true); + + if (cpu_port) { + /* Configure MII interface for proper network communication. */ + ksz_read8(dev, REG_PORT_5_CTRL_6, &data8); + data8 &= ~PORT_INTERFACE_TYPE; + data8 &= ~PORT_GMII_1GPS_MODE; + switch (dev->interface) { + case PHY_INTERFACE_MODE_MII: + p->phydev.speed = SPEED_100; + break; + case PHY_INTERFACE_MODE_RMII: + data8 |= PORT_INTERFACE_RMII; + p->phydev.speed = SPEED_100; + break; + case PHY_INTERFACE_MODE_GMII: + data8 |= PORT_GMII_1GPS_MODE; + data8 |= PORT_INTERFACE_GMII; + p->phydev.speed = SPEED_1000; + break; + default: + data8 &= ~PORT_RGMII_ID_IN_ENABLE; + data8 &= ~PORT_RGMII_ID_OUT_ENABLE; + if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || + dev->interface == PHY_INTERFACE_MODE_RGMII_RXID) + data8 |= PORT_RGMII_ID_IN_ENABLE; + if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || + dev->interface == PHY_INTERFACE_MODE_RGMII_TXID) + data8 |= PORT_RGMII_ID_OUT_ENABLE; + data8 |= PORT_GMII_1GPS_MODE; + data8 |= PORT_INTERFACE_RGMII; + p->phydev.speed = SPEED_1000; + break; + } + ksz_write8(dev, REG_PORT_5_CTRL_6, data8); + p->phydev.duplex = 1; + + member = dev->port_mask; + dev->on_ports = dev->host_mask; + dev->live_ports = dev->host_mask; + } else { + member = dev->host_mask | p->vid_member; + dev->on_ports |= BIT(port); + + /* Link was detected before port is enabled. */ + if (p->phydev.link) + dev->live_ports |= BIT(port); + } + ksz8795_cfg_port_member(dev, port, member); +} + +static void ksz8795_config_cpu_port(struct dsa_switch *ds) +{ + struct ksz_device *dev = ds->priv; + struct ksz_port *p; + 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); + + p = &dev->ports[dev->cpu_port]; + p->vid_member = dev->port_mask; + p->on = 1; + + ksz8795_port_setup(dev, dev->cpu_port, true); + dev->member = dev->host_mask; + + for (i = 0; i < SWITCH_PORT_NUM; i++) { + p = &dev->ports[i]; + + /* Initialize to non-zero so that ksz_cfg_port_member() will + * be called. + */ + p->vid_member = BIT(i); + p->member = dev->port_mask; + ksz8795_port_stp_state_set(ds, i, BR_STATE_DISABLED); + + /* Last port may be disabled. */ + if (i == dev->port_cnt) + break; + p->on = 1; + p->phy = 1; + } + for (i = 0; i < dev->phy_port_cnt; i++) { + p = &dev->ports[i]; + if (!p->on) + continue; + ksz_pread8(dev, i, P_REMOTE_STATUS, &remote); + if (remote & PORT_FIBER_MODE) + p->fiber = 1; + if (p->fiber) + ksz_port_cfg(dev, i, P_STP_CTRL, PORT_FORCE_FLOW_CTRL, + true); + else + ksz_port_cfg(dev, i, P_STP_CTRL, PORT_FORCE_FLOW_CTRL, + false); + } +} + +static int ksz8795_setup(struct dsa_switch *ds) +{ + struct ksz_device *dev = ds->priv; + struct alu_struct alu; + int i, ret = 0; + + dev->vlan_cache = devm_kcalloc(dev->dev, sizeof(struct vlan_table), + dev->num_vlans, GFP_KERNEL); + if (!dev->vlan_cache) + return -ENOMEM; + + ret = ksz8795_reset_switch(dev); + if (ret) { + dev_err(ds->dev, "failed to reset switch\n"); + return ret; + } + + ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_FLOW_CTRL, true); + + /* Enable automatic fast aging when link changed detected. */ + ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true); + + /* Enable aggressive back off algorithm in half duplex mode. */ + regmap_update_bits(dev->regmap[0], REG_SW_CTRL_1, + SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); + + /* + * Make sure unicast VLAN boundary is set as default and + * enable no excessive collision drop. + */ + regmap_update_bits(dev->regmap[0], REG_SW_CTRL_2, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); + + ksz8795_config_cpu_port(ds); + + ksz_cfg(dev, REG_SW_CTRL_2, MULTICAST_STORM_DISABLE, true); + + ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false); + + ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false); + + /* set broadcast storm protection 10% rate */ + regmap_update_bits(dev->regmap[1], S_REPLACE_VID_CTRL, + BROADCAST_STORM_RATE, + (BROADCAST_STORM_VALUE * + BROADCAST_STORM_PROT_RATE) / 100); + + for (i = 0; i < VLAN_TABLE_ENTRIES; i++) + ksz8795_r_vlan_entries(dev, i); + + /* Setup STP address for STP operation. */ + memset(&alu, 0, sizeof(alu)); + ether_addr_copy(alu.mac, eth_stp_addr); + alu.is_static = true; + alu.is_override = true; + alu.port_forward = dev->host_mask; + + ksz8795_w_sta_mac_table(dev, 0, &alu); + + ksz_init_mib_timer(dev); + + return 0; +} + +static const struct dsa_switch_ops ksz8795_switch_ops = { + .get_tag_protocol = ksz8795_get_tag_protocol, + .setup = ksz8795_setup, + .phy_read = ksz_phy_read16, + .phy_write = ksz_phy_write16, + .adjust_link = ksz_adjust_link, + .port_enable = ksz_enable_port, + .port_disable = ksz_disable_port, + .get_strings = ksz8795_get_strings, + .get_ethtool_stats = ksz_get_ethtool_stats, + .get_sset_count = ksz_sset_count, + .port_bridge_join = ksz_port_bridge_join, + .port_bridge_leave = ksz_port_bridge_leave, + .port_stp_state_set = ksz8795_port_stp_state_set, + .port_fast_age = ksz_port_fast_age, + .port_vlan_filtering = ksz8795_port_vlan_filtering, + .port_vlan_prepare = ksz_port_vlan_prepare, + .port_vlan_add = ksz8795_port_vlan_add, + .port_vlan_del = ksz8795_port_vlan_del, + .port_fdb_dump = ksz_port_fdb_dump, + .port_mdb_prepare = ksz_port_mdb_prepare, + .port_mdb_add = ksz_port_mdb_add, + .port_mdb_del = ksz_port_mdb_del, + .port_mirror_add = ksz8795_port_mirror_add, + .port_mirror_del = ksz8795_port_mirror_del, +}; + +static u32 ksz8795_get_port_addr(int port, int offset) +{ + return PORT_CTRL_ADDR(port, offset); +} + +static int ksz8795_switch_detect(struct ksz_device *dev) +{ + u8 id1, id2; + u16 id16; + int ret; + + /* read chip id */ + ret = ksz_read16(dev, REG_CHIP_ID0, &id16); + if (ret) + return ret; + + id1 = id16 >> 8; + id2 = id16 & SW_CHIP_ID_M; + if (id1 != FAMILY_ID || + (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; + + id2 = 0x95; + ksz_read8(dev, REG_PORT_1_STATUS_0, &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; +} + +struct ksz_chip_data { + u16 chip_id; + const char *dev_name; + int num_vlans; + int num_alus; + int num_statics; + int cpu_ports; + int port_cnt; +}; + +static const struct ksz_chip_data ksz8795_switch_chips[] = { + { + .chip_id = 0x8795, + .dev_name = "KSZ8795", + .num_vlans = 4096, + .num_alus = 0, + .num_statics = 8, + .cpu_ports = 0x10, /* can be configured as cpu port */ + .port_cnt = 4, /* total physical port count */ + }, + { + .chip_id = 0x8794, + .dev_name = "KSZ8794", + .num_vlans = 4096, + .num_alus = 0, + .num_statics = 8, + .cpu_ports = 0x10, /* can be configured as cpu port */ + .port_cnt = 3, /* total physical port count */ + }, + { + .chip_id = 0x8765, + .dev_name = "KSZ8765", + .num_vlans = 4096, + .num_alus = 0, + .num_statics = 8, + .cpu_ports = 0x10, /* can be configured as cpu port */ + .port_cnt = 4, /* total physical port count */ + }, +}; + +static int ksz8795_switch_init(struct ksz_device *dev) +{ + int i; + + mutex_init(&dev->stats_mutex); + mutex_init(&dev->alu_mutex); + mutex_init(&dev->vlan_mutex); + + dev->ds->ops = &ksz8795_switch_ops; + + for (i = 0; i < ARRAY_SIZE(ksz8795_switch_chips); i++) { + const struct ksz_chip_data *chip = &ksz8795_switch_chips[i]; + + if (dev->chip_id == chip->chip_id) { + dev->name = chip->dev_name; + dev->num_vlans = chip->num_vlans; + dev->num_alus = chip->num_alus; + dev->num_statics = chip->num_statics; + dev->port_cnt = chip->port_cnt; + dev->cpu_ports = chip->cpu_ports; + + break; + } + } + + /* no switch found */ + if (!dev->cpu_ports) + return -ENODEV; + + 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; + + i = dev->mib_port_cnt; + dev->ports = devm_kzalloc(dev->dev, sizeof(struct ksz_port) * i, + GFP_KERNEL); + if (!dev->ports) + return -ENOMEM; + for (i = 0; i < dev->mib_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), + GFP_KERNEL); + if (!dev->ports[i].mib.counters) + return -ENOMEM; + } + + return 0; +} + +static void ksz8795_switch_exit(struct ksz_device *dev) +{ + ksz8795_reset_switch(dev); +} + +static const struct ksz_dev_ops ksz8795_dev_ops = { + .get_port_addr = ksz8795_get_port_addr, + .cfg_port_member = ksz8795_cfg_port_member, + .flush_dyn_mac_table = ksz8795_flush_dyn_mac_table, + .port_setup = ksz8795_port_setup, + .r_phy = ksz8795_r_phy, + .w_phy = ksz8795_w_phy, + .r_dyn_mac_table = ksz8795_r_dyn_mac_table, + .r_sta_mac_table = ksz8795_r_sta_mac_table, + .w_sta_mac_table = ksz8795_w_sta_mac_table, + .r_mib_cnt = ksz8795_r_mib_cnt, + .r_mib_pkt = ksz8795_r_mib_pkt, + .freeze_mib = ksz8795_freeze_mib, + .port_init_cnt = ksz8795_port_init_cnt, + .shutdown = ksz8795_reset_switch, + .detect = ksz8795_switch_detect, + .init = ksz8795_switch_init, + .exit = ksz8795_switch_exit, +}; + +int ksz8795_switch_register(struct ksz_device *dev) +{ + return ksz_switch_register(dev, &ksz8795_dev_ops); +} +EXPORT_SYMBOL(ksz8795_switch_register); + +MODULE_AUTHOR("Tristram Ha <Tristram.Ha@microchip.com>"); +MODULE_DESCRIPTION("Microchip KSZ8795 Series Switch DSA Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h new file mode 100644 index 000000000000..3a50462df8fa --- /dev/null +++ b/drivers/net/dsa/microchip/ksz8795_reg.h @@ -0,0 +1,1004 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Microchip KSZ8795 register definitions + * + * Copyright (c) 2017 Microchip Technology Inc. + * Tristram Ha <Tristram.Ha@microchip.com> + */ + +#ifndef __KSZ8795_REG_H +#define __KSZ8795_REG_H + +#define KS_PORT_M 0x1F + +#define KS_PRIO_M 0x3 +#define KS_PRIO_S 2 + +#define REG_CHIP_ID0 0x00 + +#define FAMILY_ID 0x87 + +#define REG_CHIP_ID1 0x01 + +#define SW_CHIP_ID_M 0xF0 +#define SW_CHIP_ID_S 4 +#define SW_REVISION_M 0x0E +#define SW_REVISION_S 1 +#define SW_START 0x01 + +#define CHIP_ID_94 0x60 +#define CHIP_ID_95 0x90 + +#define REG_SW_CTRL_0 0x02 + +#define SW_NEW_BACKOFF BIT(7) +#define SW_GLOBAL_RESET BIT(6) +#define SW_FLUSH_DYN_MAC_TABLE BIT(5) +#define SW_FLUSH_STA_MAC_TABLE BIT(4) +#define SW_LINK_AUTO_AGING BIT(0) + +#define REG_SW_CTRL_1 0x03 + +#define SW_HUGE_PACKET BIT(6) +#define SW_TX_FLOW_CTRL_DISABLE BIT(5) +#define SW_RX_FLOW_CTRL_DISABLE BIT(4) +#define SW_CHECK_LENGTH BIT(3) +#define SW_AGING_ENABLE BIT(2) +#define SW_FAST_AGING BIT(1) +#define SW_AGGR_BACKOFF BIT(0) + +#define REG_SW_CTRL_2 0x04 + +#define UNICAST_VLAN_BOUNDARY BIT(7) +#define MULTICAST_STORM_DISABLE BIT(6) +#define SW_BACK_PRESSURE BIT(5) +#define FAIR_FLOW_CTRL BIT(4) +#define NO_EXC_COLLISION_DROP BIT(3) +#define SW_LEGAL_PACKET_DISABLE BIT(1) + +#define REG_SW_CTRL_3 0x05 + #define WEIGHTED_FAIR_QUEUE_ENABLE BIT(3) + +#define SW_VLAN_ENABLE BIT(7) +#define SW_IGMP_SNOOP BIT(6) +#define SW_MIRROR_RX_TX BIT(0) + +#define REG_SW_CTRL_4 0x06 + +#define SW_HALF_DUPLEX_FLOW_CTRL BIT(7) +#define SW_HALF_DUPLEX BIT(6) +#define SW_FLOW_CTRL BIT(5) +#define SW_10_MBIT BIT(4) +#define SW_REPLACE_VID BIT(3) +#define BROADCAST_STORM_RATE_HI 0x07 + +#define REG_SW_CTRL_5 0x07 + +#define BROADCAST_STORM_RATE_LO 0xFF +#define BROADCAST_STORM_RATE 0x07FF + +#define REG_SW_CTRL_6 0x08 + +#define SW_MIB_COUNTER_FLUSH BIT(7) +#define SW_MIB_COUNTER_FREEZE BIT(6) +#define SW_MIB_COUNTER_CTRL_ENABLE KS_PORT_M + +#define REG_SW_CTRL_9 0x0B + +#define SPI_CLK_125_MHZ 0x80 +#define SPI_CLK_62_5_MHZ 0x40 +#define SPI_CLK_31_25_MHZ 0x00 + +#define SW_LED_MODE_M 0x3 +#define SW_LED_MODE_S 4 +#define SW_LED_LINK_ACT_SPEED 0 +#define SW_LED_LINK_ACT 1 +#define SW_LED_LINK_ACT_DUPLEX 2 +#define SW_LED_LINK_DUPLEX 3 + +#define REG_SW_CTRL_10 0x0C + +#define SW_TAIL_TAG_ENABLE BIT(1) +#define SW_PASS_PAUSE BIT(0) + +#define REG_SW_CTRL_11 0x0D + +#define REG_POWER_MANAGEMENT_1 0x0E + +#define SW_PLL_POWER_DOWN BIT(5) +#define SW_POWER_MANAGEMENT_MODE_M 0x3 +#define SW_POWER_MANAGEMENT_MODE_S 3 +#define SW_POWER_NORMAL 0 +#define SW_ENERGY_DETECTION 1 +#define SW_SOFTWARE_POWER_DOWN 2 + +#define REG_POWER_MANAGEMENT_2 0x0F + +#define REG_PORT_1_CTRL_0 0x10 +#define REG_PORT_2_CTRL_0 0x20 +#define REG_PORT_3_CTRL_0 0x30 +#define REG_PORT_4_CTRL_0 0x40 +#define REG_PORT_5_CTRL_0 0x50 + +#define PORT_BROADCAST_STORM BIT(7) +#define PORT_DIFFSERV_ENABLE BIT(6) +#define PORT_802_1P_ENABLE BIT(5) +#define PORT_BASED_PRIO_S 3 +#define PORT_BASED_PRIO_M KS_PRIO_M +#define PORT_BASED_PRIO_0 0 +#define PORT_BASED_PRIO_1 1 +#define PORT_BASED_PRIO_2 2 +#define PORT_BASED_PRIO_3 3 +#define PORT_INSERT_TAG BIT(2) +#define PORT_REMOVE_TAG BIT(1) +#define PORT_QUEUE_SPLIT_L BIT(0) + +#define REG_PORT_1_CTRL_1 0x11 +#define REG_PORT_2_CTRL_1 0x21 +#define REG_PORT_3_CTRL_1 0x31 +#define REG_PORT_4_CTRL_1 0x41 +#define REG_PORT_5_CTRL_1 0x51 + +#define PORT_MIRROR_SNIFFER BIT(7) +#define PORT_MIRROR_RX BIT(6) +#define PORT_MIRROR_TX BIT(5) +#define PORT_VLAN_MEMBERSHIP KS_PORT_M + +#define REG_PORT_1_CTRL_2 0x12 +#define REG_PORT_2_CTRL_2 0x22 +#define REG_PORT_3_CTRL_2 0x32 +#define REG_PORT_4_CTRL_2 0x42 +#define REG_PORT_5_CTRL_2 0x52 + +#define PORT_802_1P_REMAPPING BIT(7) +#define PORT_INGRESS_FILTER BIT(6) +#define PORT_DISCARD_NON_VID BIT(5) +#define PORT_FORCE_FLOW_CTRL BIT(4) +#define PORT_BACK_PRESSURE BIT(3) +#define PORT_TX_ENABLE BIT(2) +#define PORT_RX_ENABLE BIT(1) +#define PORT_LEARN_DISABLE BIT(0) + +#define REG_PORT_1_CTRL_3 0x13 +#define REG_PORT_2_CTRL_3 0x23 +#define REG_PORT_3_CTRL_3 0x33 +#define REG_PORT_4_CTRL_3 0x43 +#define REG_PORT_5_CTRL_3 0x53 +#define REG_PORT_1_CTRL_4 0x14 +#define REG_PORT_2_CTRL_4 0x24 +#define REG_PORT_3_CTRL_4 0x34 +#define REG_PORT_4_CTRL_4 0x44 +#define REG_PORT_5_CTRL_4 0x54 + +#define PORT_DEFAULT_VID 0x0001 + +#define REG_PORT_1_CTRL_5 0x15 +#define REG_PORT_2_CTRL_5 0x25 +#define REG_PORT_3_CTRL_5 0x35 +#define REG_PORT_4_CTRL_5 0x45 +#define REG_PORT_5_CTRL_5 0x55 + +#define PORT_ACL_ENABLE BIT(2) +#define PORT_AUTHEN_MODE 0x3 +#define PORT_AUTHEN_PASS 0 +#define PORT_AUTHEN_BLOCK 1 +#define PORT_AUTHEN_TRAP 2 + +#define REG_PORT_5_CTRL_6 0x56 + +#define PORT_MII_INTERNAL_CLOCK BIT(7) +#define PORT_GMII_1GPS_MODE BIT(6) +#define PORT_RGMII_ID_IN_ENABLE BIT(4) +#define PORT_RGMII_ID_OUT_ENABLE BIT(3) +#define PORT_GMII_MAC_MODE BIT(2) +#define PORT_INTERFACE_TYPE 0x3 +#define PORT_INTERFACE_MII 0 +#define PORT_INTERFACE_RMII 1 +#define PORT_INTERFACE_GMII 2 +#define PORT_INTERFACE_RGMII 3 + +#define REG_PORT_1_CTRL_7 0x17 +#define REG_PORT_2_CTRL_7 0x27 +#define REG_PORT_3_CTRL_7 0x37 +#define REG_PORT_4_CTRL_7 0x47 + +#define PORT_AUTO_NEG_ASYM_PAUSE BIT(5) +#define PORT_AUTO_NEG_SYM_PAUSE BIT(4) +#define PORT_AUTO_NEG_100BTX_FD BIT(3) +#define PORT_AUTO_NEG_100BTX BIT(2) +#define PORT_AUTO_NEG_10BT_FD BIT(1) +#define PORT_AUTO_NEG_10BT BIT(0) + +#define REG_PORT_1_STATUS_0 0x18 +#define REG_PORT_2_STATUS_0 0x28 +#define REG_PORT_3_STATUS_0 0x38 +#define REG_PORT_4_STATUS_0 0x48 + +/* For KSZ8765. */ +#define PORT_FIBER_MODE BIT(7) + +#define PORT_REMOTE_ASYM_PAUSE BIT(5) +#define PORT_REMOTE_SYM_PAUSE BIT(4) +#define PORT_REMOTE_100BTX_FD BIT(3) +#define PORT_REMOTE_100BTX BIT(2) +#define PORT_REMOTE_10BT_FD BIT(1) +#define PORT_REMOTE_10BT BIT(0) + +#define REG_PORT_1_STATUS_1 0x19 +#define REG_PORT_2_STATUS_1 0x29 +#define REG_PORT_3_STATUS_1 0x39 +#define REG_PORT_4_STATUS_1 0x49 + +#define PORT_HP_MDIX BIT(7) +#define PORT_REVERSED_POLARITY BIT(5) +#define PORT_TX_FLOW_CTRL BIT(4) +#define PORT_RX_FLOW_CTRL BIT(3) +#define PORT_STAT_SPEED_100MBIT BIT(2) +#define PORT_STAT_FULL_DUPLEX BIT(1) + +#define PORT_REMOTE_FAULT BIT(0) + +#define REG_PORT_1_LINK_MD_CTRL 0x1A +#define REG_PORT_2_LINK_MD_CTRL 0x2A +#define REG_PORT_3_LINK_MD_CTRL 0x3A +#define REG_PORT_4_LINK_MD_CTRL 0x4A + +#define PORT_CABLE_10M_SHORT BIT(7) +#define PORT_CABLE_DIAG_RESULT_M 0x3 +#define PORT_CABLE_DIAG_RESULT_S 5 +#define PORT_CABLE_STAT_NORMAL 0 +#define PORT_CABLE_STAT_OPEN 1 +#define PORT_CABLE_STAT_SHORT 2 +#define PORT_CABLE_STAT_FAILED 3 +#define PORT_START_CABLE_DIAG BIT(4) +#define PORT_FORCE_LINK BIT(3) +#define PORT_POWER_SAVING BIT(2) +#define PORT_PHY_REMOTE_LOOPBACK BIT(1) +#define PORT_CABLE_FAULT_COUNTER_H 0x01 + +#define REG_PORT_1_LINK_MD_RESULT 0x1B +#define REG_PORT_2_LINK_MD_RESULT 0x2B +#define REG_PORT_3_LINK_MD_RESULT 0x3B +#define REG_PORT_4_LINK_MD_RESULT 0x4B + +#define PORT_CABLE_FAULT_COUNTER_L 0xFF +#define PORT_CABLE_FAULT_COUNTER 0x1FF + +#define REG_PORT_1_CTRL_9 0x1C +#define REG_PORT_2_CTRL_9 0x2C +#define REG_PORT_3_CTRL_9 0x3C +#define REG_PORT_4_CTRL_9 0x4C + +#define PORT_AUTO_NEG_DISABLE BIT(7) +#define PORT_FORCE_100_MBIT BIT(6) +#define PORT_FORCE_FULL_DUPLEX BIT(5) + +#define REG_PORT_1_CTRL_10 0x1D +#define REG_PORT_2_CTRL_10 0x2D +#define REG_PORT_3_CTRL_10 0x3D +#define REG_PORT_4_CTRL_10 0x4D + +#define PORT_LED_OFF BIT(7) +#define PORT_TX_DISABLE BIT(6) +#define PORT_AUTO_NEG_RESTART BIT(5) +#define PORT_POWER_DOWN BIT(3) +#define PORT_AUTO_MDIX_DISABLE BIT(2) +#define PORT_FORCE_MDIX BIT(1) +#define PORT_MAC_LOOPBACK BIT(0) + +#define REG_PORT_1_STATUS_2 0x1E +#define REG_PORT_2_STATUS_2 0x2E +#define REG_PORT_3_STATUS_2 0x3E +#define REG_PORT_4_STATUS_2 0x4E + +#define PORT_MDIX_STATUS BIT(7) +#define PORT_AUTO_NEG_COMPLETE BIT(6) +#define PORT_STAT_LINK_GOOD BIT(5) + +#define REG_PORT_1_STATUS_3 0x1F +#define REG_PORT_2_STATUS_3 0x2F +#define REG_PORT_3_STATUS_3 0x3F +#define REG_PORT_4_STATUS_3 0x4F + +#define PORT_PHY_LOOPBACK BIT(7) +#define PORT_PHY_ISOLATE BIT(5) +#define PORT_PHY_SOFT_RESET BIT(4) +#define PORT_PHY_FORCE_LINK BIT(3) +#define PORT_PHY_MODE_M 0x7 +#define PHY_MODE_IN_AUTO_NEG 1 +#define PHY_MODE_10BT_HALF 2 +#define PHY_MODE_100BT_HALF 3 +#define PHY_MODE_10BT_FULL 5 +#define PHY_MODE_100BT_FULL 6 +#define PHY_MODE_ISOLDATE 7 + +#define REG_PORT_CTRL_0 0x00 +#define REG_PORT_CTRL_1 0x01 +#define REG_PORT_CTRL_2 0x02 +#define REG_PORT_CTRL_VID 0x03 + +#define REG_PORT_CTRL_5 0x05 + +#define REG_PORT_CTRL_7 0x07 +#define REG_PORT_STATUS_0 0x08 +#define REG_PORT_STATUS_1 0x09 +#define REG_PORT_LINK_MD_CTRL 0x0A +#define REG_PORT_LINK_MD_RESULT 0x0B +#define REG_PORT_CTRL_9 0x0C +#define REG_PORT_CTRL_10 0x0D +#define REG_PORT_STATUS_2 0x0E +#define REG_PORT_STATUS_3 0x0F + +#define REG_PORT_CTRL_12 0xA0 +#define REG_PORT_CTRL_13 0xA1 +#define REG_PORT_RATE_CTRL_3 0xA2 +#define REG_PORT_RATE_CTRL_2 0xA3 +#define REG_PORT_RATE_CTRL_1 0xA4 +#define REG_PORT_RATE_CTRL_0 0xA5 +#define REG_PORT_RATE_LIMIT 0xA6 +#define REG_PORT_IN_RATE_0 0xA7 +#define REG_PORT_IN_RATE_1 0xA8 +#define REG_PORT_IN_RATE_2 0xA9 +#define REG_PORT_IN_RATE_3 0xAA +#define REG_PORT_OUT_RATE_0 0xAB +#define REG_PORT_OUT_RATE_1 0xAC +#define REG_PORT_OUT_RATE_2 0xAD +#define REG_PORT_OUT_RATE_3 0xAE + +#define PORT_CTRL_ADDR(port, addr) \ + ((addr) + REG_PORT_1_CTRL_0 + (port) * \ + (REG_PORT_2_CTRL_0 - REG_PORT_1_CTRL_0)) + +#define REG_SW_MAC_ADDR_0 0x68 +#define REG_SW_MAC_ADDR_1 0x69 +#define REG_SW_MAC_ADDR_2 0x6A +#define REG_SW_MAC_ADDR_3 0x6B +#define REG_SW_MAC_ADDR_4 0x6C +#define REG_SW_MAC_ADDR_5 0x6D + +#define REG_IND_CTRL_0 0x6E + +#define TABLE_EXT_SELECT_S 5 +#define TABLE_EEE_V 1 +#define TABLE_ACL_V 2 +#define TABLE_PME_V 4 +#define TABLE_LINK_MD_V 5 +#define TABLE_EEE (TABLE_EEE_V << TABLE_EXT_SELECT_S) +#define TABLE_ACL (TABLE_ACL_V << TABLE_EXT_SELECT_S) +#define TABLE_PME (TABLE_PME_V << TABLE_EXT_SELECT_S) +#define TABLE_LINK_MD (TABLE_LINK_MD << TABLE_EXT_SELECT_S) +#define TABLE_READ BIT(4) +#define TABLE_SELECT_S 2 +#define TABLE_STATIC_MAC_V 0 +#define TABLE_VLAN_V 1 +#define TABLE_DYNAMIC_MAC_V 2 +#define TABLE_MIB_V 3 +#define TABLE_STATIC_MAC (TABLE_STATIC_MAC_V << TABLE_SELECT_S) +#define TABLE_VLAN (TABLE_VLAN_V << TABLE_SELECT_S) +#define TABLE_DYNAMIC_MAC (TABLE_DYNAMIC_MAC_V << TABLE_SELECT_S) +#define TABLE_MIB (TABLE_MIB_V << TABLE_SELECT_S) + +#define REG_IND_CTRL_1 0x6F + +#define TABLE_ENTRY_MASK 0x03FF +#define TABLE_EXT_ENTRY_MASK 0x0FFF + +#define REG_IND_DATA_8 0x70 +#define REG_IND_DATA_7 0x71 +#define REG_IND_DATA_6 0x72 +#define REG_IND_DATA_5 0x73 +#define REG_IND_DATA_4 0x74 +#define REG_IND_DATA_3 0x75 +#define REG_IND_DATA_2 0x76 +#define REG_IND_DATA_1 0x77 +#define REG_IND_DATA_0 0x78 + +#define REG_IND_DATA_PME_EEE_ACL 0xA0 + +#define REG_IND_DATA_CHECK REG_IND_DATA_6 +#define REG_IND_MIB_CHECK REG_IND_DATA_4 +#define REG_IND_DATA_HI REG_IND_DATA_7 +#define REG_IND_DATA_LO REG_IND_DATA_3 + +#define REG_INT_STATUS 0x7C +#define REG_INT_ENABLE 0x7D + +#define INT_PME BIT(4) + +#define REG_ACL_INT_STATUS 0x7E +#define REG_ACL_INT_ENABLE 0x7F + +#define INT_PORT_5 BIT(4) +#define INT_PORT_4 BIT(3) +#define INT_PORT_3 BIT(2) +#define INT_PORT_2 BIT(1) +#define INT_PORT_1 BIT(0) + +#define INT_PORT_ALL \ + (INT_PORT_5 | INT_PORT_4 | INT_PORT_3 | INT_PORT_2 | INT_PORT_1) + +#define REG_SW_CTRL_12 0x80 +#define REG_SW_CTRL_13 0x81 + +#define SWITCH_802_1P_MASK 3 +#define SWITCH_802_1P_BASE 3 +#define SWITCH_802_1P_SHIFT 2 + +#define SW_802_1P_MAP_M KS_PRIO_M +#define SW_802_1P_MAP_S KS_PRIO_S + +#define REG_SWITCH_CTRL_14 0x82 + +#define SW_PRIO_MAPPING_M KS_PRIO_M +#define SW_PRIO_MAPPING_S 6 +#define SW_PRIO_MAP_3_HI 0 +#define SW_PRIO_MAP_2_HI 2 +#define SW_PRIO_MAP_0_LO 3 + +#define REG_SW_CTRL_15 0x83 +#define REG_SW_CTRL_16 0x84 +#define REG_SW_CTRL_17 0x85 +#define REG_SW_CTRL_18 0x86 + +#define SW_SELF_ADDR_FILTER_ENABLE BIT(6) + +#define REG_SW_UNK_UCAST_CTRL 0x83 +#define REG_SW_UNK_MCAST_CTRL 0x84 +#define REG_SW_UNK_VID_CTRL 0x85 +#define REG_SW_UNK_IP_MCAST_CTRL 0x86 + +#define SW_UNK_FWD_ENABLE BIT(5) +#define SW_UNK_FWD_MAP KS_PORT_M + +#define REG_SW_CTRL_19 0x87 + +#define SW_IN_RATE_LIMIT_PERIOD_M 0x3 +#define SW_IN_RATE_LIMIT_PERIOD_S 4 +#define SW_IN_RATE_LIMIT_16_MS 0 +#define SW_IN_RATE_LIMIT_64_MS 1 +#define SW_IN_RATE_LIMIT_256_MS 2 +#define SW_OUT_RATE_LIMIT_QUEUE_BASED BIT(3) +#define SW_INS_TAG_ENABLE BIT(2) + +#define REG_TOS_PRIO_CTRL_0 0x90 +#define REG_TOS_PRIO_CTRL_1 0x91 +#define REG_TOS_PRIO_CTRL_2 0x92 +#define REG_TOS_PRIO_CTRL_3 0x93 +#define REG_TOS_PRIO_CTRL_4 0x94 +#define REG_TOS_PRIO_CTRL_5 0x95 +#define REG_TOS_PRIO_CTRL_6 0x96 +#define REG_TOS_PRIO_CTRL_7 0x97 +#define REG_TOS_PRIO_CTRL_8 0x98 +#define REG_TOS_PRIO_CTRL_9 0x99 +#define REG_TOS_PRIO_CTRL_10 0x9A +#define REG_TOS_PRIO_CTRL_11 0x9B +#define REG_TOS_PRIO_CTRL_12 0x9C +#define REG_TOS_PRIO_CTRL_13 0x9D +#define REG_TOS_PRIO_CTRL_14 0x9E +#define REG_TOS_PRIO_CTRL_15 0x9F + +#define TOS_PRIO_M KS_PRIO_M +#define TOS_PRIO_S KS_PRIO_S + +#define REG_SW_CTRL_20 0xA3 + +#define SW_GMII_DRIVE_STRENGTH_S 4 +#define SW_DRIVE_STRENGTH_M 0x7 +#define SW_DRIVE_STRENGTH_2MA 0 +#define SW_DRIVE_STRENGTH_4MA 1 +#define SW_DRIVE_STRENGTH_8MA 2 +#define SW_DRIVE_STRENGTH_12MA 3 +#define SW_DRIVE_STRENGTH_16MA 4 +#define SW_DRIVE_STRENGTH_20MA 5 +#define SW_DRIVE_STRENGTH_24MA 6 +#define SW_DRIVE_STRENGTH_28MA 7 +#define SW_MII_DRIVE_STRENGTH_S 0 + +#define REG_SW_CTRL_21 0xA4 + +#define SW_IPV6_MLD_OPTION BIT(3) +#define SW_IPV6_MLD_SNOOP BIT(2) + +#define REG_PORT_1_CTRL_12 0xB0 +#define REG_PORT_2_CTRL_12 0xC0 +#define REG_PORT_3_CTRL_12 0xD0 +#define REG_PORT_4_CTRL_12 0xE0 +#define REG_PORT_5_CTRL_12 0xF0 + +#define PORT_PASS_ALL BIT(6) +#define PORT_INS_TAG_FOR_PORT_5_S 3 +#define PORT_INS_TAG_FOR_PORT_5 BIT(3) +#define PORT_INS_TAG_FOR_PORT_4 BIT(2) +#define PORT_INS_TAG_FOR_PORT_3 BIT(1) +#define PORT_INS_TAG_FOR_PORT_2 BIT(0) + +#define REG_PORT_1_CTRL_13 0xB1 +#define REG_PORT_2_CTRL_13 0xC1 +#define REG_PORT_3_CTRL_13 0xD1 +#define REG_PORT_4_CTRL_13 0xE1 +#define REG_PORT_5_CTRL_13 0xF1 + +#define PORT_QUEUE_SPLIT_H BIT(1) +#define PORT_QUEUE_SPLIT_1 0 +#define PORT_QUEUE_SPLIT_2 1 +#define PORT_QUEUE_SPLIT_4 2 +#define PORT_DROP_TAG BIT(0) + +#define REG_PORT_1_CTRL_14 0xB2 +#define REG_PORT_2_CTRL_14 0xC2 +#define REG_PORT_3_CTRL_14 0xD2 +#define REG_PORT_4_CTRL_14 0xE2 +#define REG_PORT_5_CTRL_14 0xF2 +#define REG_PORT_1_CTRL_15 0xB3 +#define REG_PORT_2_CTRL_15 0xC3 +#define REG_PORT_3_CTRL_15 0xD3 +#define REG_PORT_4_CTRL_15 0xE3 +#define REG_PORT_5_CTRL_15 0xF3 +#define REG_PORT_1_CTRL_16 0xB4 +#define REG_PORT_2_CTRL_16 0xC4 +#define REG_PORT_3_CTRL_16 0xD4 +#define REG_PORT_4_CTRL_16 0xE4 +#define REG_PORT_5_CTRL_16 0xF4 +#define REG_PORT_1_CTRL_17 0xB5 +#define REG_PORT_2_CTRL_17 0xC5 +#define REG_PORT_3_CTRL_17 0xD5 +#define REG_PORT_4_CTRL_17 0xE5 +#define REG_PORT_5_CTRL_17 0xF5 + +#define REG_PORT_1_RATE_CTRL_3 0xB2 +#define REG_PORT_1_RATE_CTRL_2 0xB3 +#define REG_PORT_1_RATE_CTRL_1 0xB4 +#define REG_PORT_1_RATE_CTRL_0 0xB5 +#define REG_PORT_2_RATE_CTRL_3 0xC2 +#define REG_PORT_2_RATE_CTRL_2 0xC3 +#define REG_PORT_2_RATE_CTRL_1 0xC4 +#define REG_PORT_2_RATE_CTRL_0 0xC5 +#define REG_PORT_3_RATE_CTRL_3 0xD2 +#define REG_PORT_3_RATE_CTRL_2 0xD3 +#define REG_PORT_3_RATE_CTRL_1 0xD4 +#define REG_PORT_3_RATE_CTRL_0 0xD5 +#define REG_PORT_4_RATE_CTRL_3 0xE2 +#define REG_PORT_4_RATE_CTRL_2 0xE3 +#define REG_PORT_4_RATE_CTRL_1 0xE4 +#define REG_PORT_4_RATE_CTRL_0 0xE5 +#define REG_PORT_5_RATE_CTRL_3 0xF2 +#define REG_PORT_5_RATE_CTRL_2 0xF3 +#define REG_PORT_5_RATE_CTRL_1 0xF4 +#define REG_PORT_5_RATE_CTRL_0 0xF5 + +#define RATE_CTRL_ENABLE BIT(7) +#define RATE_RATIO_M (BIT(7) - 1) + +#define PORT_OUT_RATE_ENABLE BIT(7) + +#define REG_PORT_1_RATE_LIMIT 0xB6 +#define REG_PORT_2_RATE_LIMIT 0xC6 +#define REG_PORT_3_RATE_LIMIT 0xD6 +#define REG_PORT_4_RATE_LIMIT 0xE6 +#define REG_PORT_5_RATE_LIMIT 0xF6 + +#define PORT_IN_PORT_BASED_S 6 +#define PORT_RATE_PACKET_BASED_S 5 +#define PORT_IN_FLOW_CTRL_S 4 +#define PORT_IN_LIMIT_MODE_M 0x3 +#define PORT_IN_LIMIT_MODE_S 2 +#define PORT_COUNT_IFG_S 1 +#define PORT_COUNT_PREAMBLE_S 0 +#define PORT_IN_PORT_BASED BIT(PORT_IN_PORT_BASED_S) +#define PORT_RATE_PACKET_BASED BIT(PORT_RATE_PACKET_BASED_S) +#define PORT_IN_FLOW_CTRL BIT(PORT_IN_FLOW_CTRL_S) +#define PORT_IN_ALL 0 +#define PORT_IN_UNICAST 1 +#define PORT_IN_MULTICAST 2 +#define PORT_IN_BROADCAST 3 +#define PORT_COUNT_IFG BIT(PORT_COUNT_IFG_S) +#define PORT_COUNT_PREAMBLE BIT(PORT_COUNT_PREAMBLE_S) + +#define REG_PORT_1_IN_RATE_0 0xB7 +#define REG_PORT_2_IN_RATE_0 0xC7 +#define REG_PORT_3_IN_RATE_0 0xD7 +#define REG_PORT_4_IN_RATE_0 0xE7 +#define REG_PORT_5_IN_RATE_0 0xF7 +#define REG_PORT_1_IN_RATE_1 0xB8 +#define REG_PORT_2_IN_RATE_1 0xC8 +#define REG_PORT_3_IN_RATE_1 0xD8 +#define REG_PORT_4_IN_RATE_1 0xE8 +#define REG_PORT_5_IN_RATE_1 0xF8 +#define REG_PORT_1_IN_RATE_2 0xB9 +#define REG_PORT_2_IN_RATE_2 0xC9 +#define REG_PORT_3_IN_RATE_2 0xD9 +#define REG_PORT_4_IN_RATE_2 0xE9 +#define REG_PORT_5_IN_RATE_2 0xF9 +#define REG_PORT_1_IN_RATE_3 0xBA +#define REG_PORT_2_IN_RATE_3 0xCA +#define REG_PORT_3_IN_RATE_3 0xDA +#define REG_PORT_4_IN_RATE_3 0xEA +#define REG_PORT_5_IN_RATE_3 0xFA + +#define PORT_IN_RATE_ENABLE BIT(7) +#define PORT_RATE_LIMIT_M (BIT(7) - 1) + +#define REG_PORT_1_OUT_RATE_0 0xBB +#define REG_PORT_2_OUT_RATE_0 0xCB +#define REG_PORT_3_OUT_RATE_0 0xDB +#define REG_PORT_4_OUT_RATE_0 0xEB +#define REG_PORT_5_OUT_RATE_0 0xFB +#define REG_PORT_1_OUT_RATE_1 0xBC +#define REG_PORT_2_OUT_RATE_1 0xCC +#define REG_PORT_3_OUT_RATE_1 0xDC +#define REG_PORT_4_OUT_RATE_1 0xEC +#define REG_PORT_5_OUT_RATE_1 0xFC +#define REG_PORT_1_OUT_RATE_2 0xBD +#define REG_PORT_2_OUT_RATE_2 0xCD +#define REG_PORT_3_OUT_RATE_2 0xDD +#define REG_PORT_4_OUT_RATE_2 0xED +#define REG_PORT_5_OUT_RATE_2 0xFD +#define REG_PORT_1_OUT_RATE_3 0xBE +#define REG_PORT_2_OUT_RATE_3 0xCE +#define REG_PORT_3_OUT_RATE_3 0xDE +#define REG_PORT_4_OUT_RATE_3 0xEE +#define REG_PORT_5_OUT_RATE_3 0xFE + +/* PME */ + +#define SW_PME_OUTPUT_ENABLE BIT(1) +#define SW_PME_ACTIVE_HIGH BIT(0) + +#define PORT_MAGIC_PACKET_DETECT BIT(2) +#define PORT_LINK_UP_DETECT BIT(1) +#define PORT_ENERGY_DETECT BIT(0) + +/* ACL */ + +#define ACL_FIRST_RULE_M 0xF + +#define ACL_MODE_M 0x3 +#define ACL_MODE_S 4 +#define ACL_MODE_DISABLE 0 +#define ACL_MODE_LAYER_2 1 +#define ACL_MODE_LAYER_3 2 +#define ACL_MODE_LAYER_4 3 +#define ACL_ENABLE_M 0x3 +#define ACL_ENABLE_S 2 +#define ACL_ENABLE_2_COUNT 0 +#define ACL_ENABLE_2_TYPE 1 +#define ACL_ENABLE_2_MAC 2 +#define ACL_ENABLE_2_BOTH 3 +#define ACL_ENABLE_3_IP 1 +#define ACL_ENABLE_3_SRC_DST_COMP 2 +#define ACL_ENABLE_4_PROTOCOL 0 +#define ACL_ENABLE_4_TCP_PORT_COMP 1 +#define ACL_ENABLE_4_UDP_PORT_COMP 2 +#define ACL_ENABLE_4_TCP_SEQN_COMP 3 +#define ACL_SRC BIT(1) +#define ACL_EQUAL BIT(0) + +#define ACL_MAX_PORT 0xFFFF + +#define ACL_MIN_PORT 0xFFFF +#define ACL_IP_ADDR 0xFFFFFFFF +#define ACL_TCP_SEQNUM 0xFFFFFFFF + +#define ACL_RESERVED 0xF8 +#define ACL_PORT_MODE_M 0x3 +#define ACL_PORT_MODE_S 1 +#define ACL_PORT_MODE_DISABLE 0 +#define ACL_PORT_MODE_EITHER 1 +#define ACL_PORT_MODE_IN_RANGE 2 +#define ACL_PORT_MODE_OUT_OF_RANGE 3 + +#define ACL_TCP_FLAG_ENABLE BIT(0) + +#define ACL_TCP_FLAG_M 0xFF + +#define ACL_TCP_FLAG 0xFF +#define ACL_ETH_TYPE 0xFFFF +#define ACL_IP_M 0xFFFFFFFF + +#define ACL_PRIO_MODE_M 0x3 +#define ACL_PRIO_MODE_S 6 +#define ACL_PRIO_MODE_DISABLE 0 +#define ACL_PRIO_MODE_HIGHER 1 +#define ACL_PRIO_MODE_LOWER 2 +#define ACL_PRIO_MODE_REPLACE 3 +#define ACL_PRIO_M 0x7 +#define ACL_PRIO_S 3 +#define ACL_VLAN_PRIO_REPLACE BIT(2) +#define ACL_VLAN_PRIO_M 0x7 +#define ACL_VLAN_PRIO_HI_M 0x3 + +#define ACL_VLAN_PRIO_LO_M 0x8 +#define ACL_VLAN_PRIO_S 7 +#define ACL_MAP_MODE_M 0x3 +#define ACL_MAP_MODE_S 5 +#define ACL_MAP_MODE_DISABLE 0 +#define ACL_MAP_MODE_OR 1 +#define ACL_MAP_MODE_AND 2 +#define ACL_MAP_MODE_REPLACE 3 +#define ACL_MAP_PORT_M 0x1F + +#define ACL_CNT_M (BIT(11) - 1) +#define ACL_CNT_S 5 +#define ACL_MSEC_UNIT BIT(4) +#define ACL_INTR_MODE BIT(3) + +#define REG_PORT_ACL_BYTE_EN_MSB 0x10 + +#define ACL_BYTE_EN_MSB_M 0x3F + +#define REG_PORT_ACL_BYTE_EN_LSB 0x11 + +#define ACL_ACTION_START 0xA +#define ACL_ACTION_LEN 2 +#define ACL_INTR_CNT_START 0xB +#define ACL_RULESET_START 0xC +#define ACL_RULESET_LEN 2 +#define ACL_TABLE_LEN 14 + +#define ACL_ACTION_ENABLE 0x000C +#define ACL_MATCH_ENABLE 0x1FF0 +#define ACL_RULESET_ENABLE 0x2003 +#define ACL_BYTE_ENABLE ((ACL_BYTE_EN_MSB_M << 8) | 0xFF) +#define ACL_MODE_ENABLE (0x10 << 8) + +#define REG_PORT_ACL_CTRL_0 0x12 + +#define PORT_ACL_WRITE_DONE BIT(6) +#define PORT_ACL_READ_DONE BIT(5) +#define PORT_ACL_WRITE BIT(4) +#define PORT_ACL_INDEX_M 0xF + +#define REG_PORT_ACL_CTRL_1 0x13 + +#define PORT_ACL_FORCE_DLR_MISS BIT(0) + +#ifndef PHY_REG_CTRL +#define PHY_REG_CTRL 0 + +#define PHY_RESET BIT(15) +#define PHY_LOOPBACK BIT(14) +#define PHY_SPEED_100MBIT BIT(13) +#define PHY_AUTO_NEG_ENABLE BIT(12) +#define PHY_POWER_DOWN BIT(11) +#define PHY_MII_DISABLE BIT(10) +#define PHY_AUTO_NEG_RESTART BIT(9) +#define PHY_FULL_DUPLEX BIT(8) +#define PHY_COLLISION_TEST_NOT BIT(7) +#define PHY_HP_MDIX BIT(5) +#define PHY_FORCE_MDIX BIT(4) +#define PHY_AUTO_MDIX_DISABLE BIT(3) +#define PHY_REMOTE_FAULT_DISABLE BIT(2) +#define PHY_TRANSMIT_DISABLE BIT(1) +#define PHY_LED_DISABLE BIT(0) + +#define PHY_REG_STATUS 1 + +#define PHY_100BT4_CAPABLE BIT(15) +#define PHY_100BTX_FD_CAPABLE BIT(14) +#define PHY_100BTX_CAPABLE BIT(13) +#define PHY_10BT_FD_CAPABLE BIT(12) +#define PHY_10BT_CAPABLE BIT(11) +#define PHY_MII_SUPPRESS_CAPABLE_NOT BIT(6) +#define PHY_AUTO_NEG_ACKNOWLEDGE BIT(5) +#define PHY_REMOTE_FAULT BIT(4) +#define PHY_AUTO_NEG_CAPABLE BIT(3) +#define PHY_LINK_STATUS BIT(2) +#define PHY_JABBER_DETECT_NOT BIT(1) +#define PHY_EXTENDED_CAPABILITY BIT(0) + +#define PHY_REG_ID_1 2 +#define PHY_REG_ID_2 3 + +#define PHY_REG_AUTO_NEGOTIATION 4 + +#define PHY_AUTO_NEG_NEXT_PAGE_NOT BIT(15) +#define PHY_AUTO_NEG_REMOTE_FAULT_NOT BIT(13) +#define PHY_AUTO_NEG_SYM_PAUSE BIT(10) +#define PHY_AUTO_NEG_100BT4 BIT(9) +#define PHY_AUTO_NEG_100BTX_FD BIT(8) +#define PHY_AUTO_NEG_100BTX BIT(7) +#define PHY_AUTO_NEG_10BT_FD BIT(6) +#define PHY_AUTO_NEG_10BT BIT(5) +#define PHY_AUTO_NEG_SELECTOR 0x001F +#define PHY_AUTO_NEG_802_3 0x0001 + +#define PHY_REG_REMOTE_CAPABILITY 5 + +#define PHY_REMOTE_NEXT_PAGE_NOT BIT(15) +#define PHY_REMOTE_ACKNOWLEDGE_NOT BIT(14) +#define PHY_REMOTE_REMOTE_FAULT_NOT BIT(13) +#define PHY_REMOTE_SYM_PAUSE BIT(10) +#define PHY_REMOTE_100BTX_FD BIT(8) +#define PHY_REMOTE_100BTX BIT(7) +#define PHY_REMOTE_10BT_FD BIT(6) +#define PHY_REMOTE_10BT BIT(5) +#endif + +#define KSZ8795_ID_HI 0x0022 +#define KSZ8795_ID_LO 0x1550 + +#define KSZ8795_SW_ID 0x8795 + +#define PHY_REG_LINK_MD 0x1D + +#define PHY_START_CABLE_DIAG BIT(15) +#define PHY_CABLE_DIAG_RESULT 0x6000 +#define PHY_CABLE_STAT_NORMAL 0x0000 +#define PHY_CABLE_STAT_OPEN 0x2000 +#define PHY_CABLE_STAT_SHORT 0x4000 +#define PHY_CABLE_STAT_FAILED 0x6000 +#define PHY_CABLE_10M_SHORT BIT(12) +#define PHY_CABLE_FAULT_COUNTER 0x01FF + +#define PHY_REG_PHY_CTRL 0x1F + +#define PHY_MODE_M 0x7 +#define PHY_MODE_S 8 +#define PHY_STAT_REVERSED_POLARITY BIT(5) +#define PHY_STAT_MDIX BIT(4) +#define PHY_FORCE_LINK BIT(3) +#define PHY_POWER_SAVING_ENABLE BIT(2) +#define PHY_REMOTE_LOOPBACK BIT(1) + +/* Chip resource */ + +#define PRIO_QUEUES 4 + +#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 P_BCAST_STORM_CTRL REG_PORT_CTRL_0 +#define P_PRIO_CTRL REG_PORT_CTRL_0 +#define P_TAG_CTRL REG_PORT_CTRL_0 +#define P_MIRROR_CTRL REG_PORT_CTRL_1 +#define P_802_1P_CTRL REG_PORT_CTRL_2 +#define P_STP_CTRL REG_PORT_CTRL_2 +#define P_LOCAL_CTRL REG_PORT_CTRL_7 +#define P_REMOTE_STATUS REG_PORT_STATUS_0 +#define P_FORCE_CTRL REG_PORT_CTRL_9 +#define P_NEG_RESTART_CTRL REG_PORT_CTRL_10 +#define P_SPEED_STATUS REG_PORT_STATUS_1 +#define P_LINK_STATUS REG_PORT_STATUS_2 +#define P_PASS_ALL_CTRL REG_PORT_CTRL_12 +#define P_INS_SRC_PVID_CTRL REG_PORT_CTRL_12 +#define P_DROP_TAG_CTRL REG_PORT_CTRL_13 +#define P_RATE_LIMIT_CTRL REG_PORT_RATE_LIMIT + +#define S_UNKNOWN_DA_CTRL REG_SWITCH_CTRL_12 +#define S_FORWARD_INVALID_VID_CTRL REG_FORWARD_INVALID_VID + +#define S_FLUSH_TABLE_CTRL REG_SW_CTRL_0 +#define S_LINK_AGING_CTRL REG_SW_CTRL_0 +#define S_HUGE_PACKET_CTRL REG_SW_CTRL_1 +#define S_MIRROR_CTRL REG_SW_CTRL_3 +#define S_REPLACE_VID_CTRL REG_SW_CTRL_4 +#define S_PASS_PAUSE_CTRL REG_SW_CTRL_10 +#define S_TAIL_TAG_CTRL REG_SW_CTRL_10 +#define S_802_1P_PRIO_CTRL REG_SW_CTRL_12 +#define S_TOS_PRIO_CTRL REG_TOS_PRIO_CTRL_0 +#define S_IPV6_MLD_CTRL REG_SW_CTRL_21 + +#define IND_ACC_TABLE(table) ((table) << 8) + +/* Driver set switch broadcast storm protection at 10% rate. */ +#define BROADCAST_STORM_PROT_RATE 10 + +/* 148,800 frames * 67 ms / 100 */ +#define BROADCAST_STORM_VALUE 9969 + +/** + * STATIC_MAC_TABLE_ADDR 00-0000FFFF-FFFFFFFF + * STATIC_MAC_TABLE_FWD_PORTS 00-001F0000-00000000 + * STATIC_MAC_TABLE_VALID 00-00200000-00000000 + * STATIC_MAC_TABLE_OVERRIDE 00-00400000-00000000 + * STATIC_MAC_TABLE_USE_FID 00-00800000-00000000 + * STATIC_MAC_TABLE_FID 00-7F000000-00000000 + */ + +#define STATIC_MAC_TABLE_ADDR 0x0000FFFF +#define STATIC_MAC_TABLE_FWD_PORTS 0x001F0000 +#define STATIC_MAC_TABLE_VALID 0x00200000 +#define STATIC_MAC_TABLE_OVERRIDE 0x00400000 +#define STATIC_MAC_TABLE_USE_FID 0x00800000 +#define STATIC_MAC_TABLE_FID 0x7F000000 + +#define STATIC_MAC_FWD_PORTS_S 16 +#define STATIC_MAC_FID_S 24 + +/** + * VLAN_TABLE_FID 00-007F007F-007F007F + * VLAN_TABLE_MEMBERSHIP 00-0F800F80-0F800F80 + * VLAN_TABLE_VALID 00-10001000-10001000 + */ + +#define VLAN_TABLE_FID 0x007F +#define VLAN_TABLE_MEMBERSHIP 0x0F80 +#define VLAN_TABLE_VALID 0x1000 + +#define VLAN_TABLE_MEMBERSHIP_S 7 +#define VLAN_TABLE_S 16 + +/** + * DYNAMIC_MAC_TABLE_ADDR 00-0000FFFF-FFFFFFFF + * DYNAMIC_MAC_TABLE_FID 00-007F0000-00000000 + * DYNAMIC_MAC_TABLE_NOT_READY 00-00800000-00000000 + * DYNAMIC_MAC_TABLE_SRC_PORT 00-07000000-00000000 + * DYNAMIC_MAC_TABLE_TIMESTAMP 00-18000000-00000000 + * DYNAMIC_MAC_TABLE_ENTRIES 7F-E0000000-00000000 + * DYNAMIC_MAC_TABLE_MAC_EMPTY 80-00000000-00000000 + */ + +#define DYNAMIC_MAC_TABLE_ADDR 0x0000FFFF +#define DYNAMIC_MAC_TABLE_FID 0x007F0000 +#define DYNAMIC_MAC_TABLE_SRC_PORT 0x07000000 +#define DYNAMIC_MAC_TABLE_TIMESTAMP 0x18000000 +#define DYNAMIC_MAC_TABLE_ENTRIES 0xE0000000 + +#define DYNAMIC_MAC_TABLE_NOT_READY 0x80 + +#define DYNAMIC_MAC_TABLE_ENTRIES_H 0x7F +#define DYNAMIC_MAC_TABLE_MAC_EMPTY 0x80 + +#define DYNAMIC_MAC_FID_S 16 +#define DYNAMIC_MAC_SRC_PORT_S 24 +#define DYNAMIC_MAC_TIMESTAMP_S 27 +#define DYNAMIC_MAC_ENTRIES_S 29 +#define DYNAMIC_MAC_ENTRIES_H_S 3 + +/** + * MIB_COUNTER_VALUE 00-00000000-3FFFFFFF + * MIB_TOTAL_BYTES 00-0000000F-FFFFFFFF + * MIB_PACKET_DROPPED 00-00000000-0000FFFF + * MIB_COUNTER_VALID 00-00000020-00000000 + * MIB_COUNTER_OVERFLOW 00-00000040-00000000 + */ + +#define MIB_COUNTER_OVERFLOW BIT(6) +#define MIB_COUNTER_VALID BIT(5) + +#define MIB_COUNTER_VALUE 0x3FFFFFFF + +#define KS_MIB_TOTAL_RX_0 0x100 +#define KS_MIB_TOTAL_TX_0 0x101 +#define KS_MIB_PACKET_DROPPED_RX_0 0x102 +#define KS_MIB_PACKET_DROPPED_TX_0 0x103 +#define KS_MIB_TOTAL_RX_1 0x104 +#define KS_MIB_TOTAL_TX_1 0x105 +#define KS_MIB_PACKET_DROPPED_TX_1 0x106 +#define KS_MIB_PACKET_DROPPED_RX_1 0x107 +#define KS_MIB_TOTAL_RX_2 0x108 +#define KS_MIB_TOTAL_TX_2 0x109 +#define KS_MIB_PACKET_DROPPED_TX_2 0x10A +#define KS_MIB_PACKET_DROPPED_RX_2 0x10B +#define KS_MIB_TOTAL_RX_3 0x10C +#define KS_MIB_TOTAL_TX_3 0x10D +#define KS_MIB_PACKET_DROPPED_TX_3 0x10E +#define KS_MIB_PACKET_DROPPED_RX_3 0x10F +#define KS_MIB_TOTAL_RX_4 0x110 +#define KS_MIB_TOTAL_TX_4 0x111 +#define KS_MIB_PACKET_DROPPED_TX_4 0x112 +#define KS_MIB_PACKET_DROPPED_RX_4 0x113 + +#define MIB_PACKET_DROPPED 0x0000FFFF + +#define MIB_TOTAL_BYTES_H 0x0000000F + +#define TAIL_TAG_OVERRIDE BIT(6) +#define TAIL_TAG_LOOKUP BIT(7) + +#define VLAN_TABLE_ENTRIES (4096 / 4) +#define FID_ENTRIES 128 + +#endif diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c new file mode 100644 index 000000000000..d0f8153e86b7 --- /dev/null +++ b/drivers/net/dsa/microchip/ksz8795_spi.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Microchip KSZ8795 series register access through SPI + * + * Copyright (C) 2017 Microchip Technology Inc. + * Tristram Ha <Tristram.Ha@microchip.com> + */ + +#include <asm/unaligned.h> + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/regmap.h> +#include <linux/spi/spi.h> + +#include "ksz_common.h" + +#define SPI_ADDR_SHIFT 12 +#define SPI_ADDR_ALIGN 3 +#define SPI_TURNAROUND_SHIFT 1 + +KSZ_REGMAP_TABLE(ksz8795, 16, SPI_ADDR_SHIFT, + SPI_TURNAROUND_SHIFT, SPI_ADDR_ALIGN); + +static int ksz8795_spi_probe(struct spi_device *spi) +{ + struct ksz_device *dev; + int i, ret; + + dev = ksz_switch_alloc(&spi->dev, spi); + if (!dev) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(ksz8795_regmap_config); i++) { + dev->regmap[i] = devm_regmap_init_spi(spi, + &ksz8795_regmap_config + [i]); + if (IS_ERR(dev->regmap[i])) { + ret = PTR_ERR(dev->regmap[i]); + dev_err(&spi->dev, + "Failed to initialize regmap%i: %d\n", + ksz8795_regmap_config[i].val_bits, ret); + return ret; + } + } + + if (spi->dev.platform_data) + dev->pdata = spi->dev.platform_data; + + ret = ksz8795_switch_register(dev); + + /* Main DSA driver may not be started yet. */ + if (ret) + return ret; + + spi_set_drvdata(spi, dev); + + return 0; +} + +static int ksz8795_spi_remove(struct spi_device *spi) +{ + struct ksz_device *dev = spi_get_drvdata(spi); + + if (dev) + ksz_switch_remove(dev); + + return 0; +} + +static void ksz8795_spi_shutdown(struct spi_device *spi) +{ + struct ksz_device *dev = spi_get_drvdata(spi); + + if (dev && dev->dev_ops->shutdown) + dev->dev_ops->shutdown(dev); +} + +static const struct of_device_id ksz8795_dt_ids[] = { + { .compatible = "microchip,ksz8765" }, + { .compatible = "microchip,ksz8794" }, + { .compatible = "microchip,ksz8795" }, + {}, +}; +MODULE_DEVICE_TABLE(of, ksz8795_dt_ids); + +static struct spi_driver ksz8795_spi_driver = { + .driver = { + .name = "ksz8795-switch", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(ksz8795_dt_ids), + }, + .probe = ksz8795_spi_probe, + .remove = ksz8795_spi_remove, + .shutdown = ksz8795_spi_shutdown, +}; + +module_spi_driver(ksz8795_spi_driver); + +MODULE_AUTHOR("Tristram Ha <Tristram.Ha@microchip.com>"); +MODULE_DESCRIPTION("Microchip KSZ8795 Series Switch SPI Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index a8c97f7a79b7..187be42de5f1 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -14,7 +14,6 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" #include "ksz9477_reg.h" #include "ksz_common.h" diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index 5a9e27b337a8..a226b389e12d 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -13,7 +13,6 @@ #include <linux/regmap.h> #include <linux/spi/spi.h> -#include "ksz_priv.h" #include "ksz_common.h" #define SPI_ADDR_SHIFT 24 diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index a3d2d67894bd..b45c7b972cec 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -18,17 +18,7 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" - -void ksz_port_cleanup(struct ksz_device *dev, int port) -{ - /* Common code for port cleanup. */ - mutex_lock(&dev->dev_mutex); - dev->on_ports &= ~(1 << port); - dev->live_ports &= ~(1 << port); - mutex_unlock(&dev->dev_mutex); -} -EXPORT_SYMBOL_GPL(ksz_port_cleanup); +#include "ksz_common.h" void ksz_update_port_member(struct ksz_device *dev, int port) { @@ -373,7 +363,8 @@ int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) /* setup slave port */ dev->dev_ops->port_setup(dev, port, false); - dev->dev_ops->phy_setup(dev, port, phy); + if (dev->dev_ops->phy_setup) + dev->dev_ops->phy_setup(dev, port, phy); /* port_stp_state_set() will be called after to enable the port so * there is no need to do anything. diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index ee7096d8af07..c44a8d23d973 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -7,9 +7,152 @@ #ifndef __KSZ_COMMON_H #define __KSZ_COMMON_H +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/phy.h> #include <linux/regmap.h> +#include <net/dsa.h> + +struct vlan_table { + u32 table[3]; +}; + +struct ksz_port_mib { + struct mutex cnt_mutex; /* structure access */ + u8 cnt_ptr; + u64 *counters; +}; + +struct ksz_port { + u16 member; + u16 vid_member; + int stp_state; + struct phy_device phydev; + + u32 on:1; /* port is not disabled by hardware */ + u32 phy:1; /* port has a PHY */ + u32 fiber:1; /* port is fiber */ + u32 sgmii:1; /* port is SGMII */ + u32 force:1; + u32 read:1; /* read MIB counters in background */ + u32 freeze:1; /* MIB counter freeze is enabled */ + + struct ksz_port_mib mib; +}; + +struct ksz_device { + struct dsa_switch *ds; + struct ksz_platform_data *pdata; + const char *name; + + struct mutex dev_mutex; /* device access */ + struct mutex stats_mutex; /* status access */ + struct mutex alu_mutex; /* ALU access */ + struct mutex vlan_mutex; /* vlan access */ + const struct ksz_dev_ops *dev_ops; + + struct device *dev; + struct regmap *regmap[3]; + + void *priv; + + struct gpio_desc *reset_gpio; /* Optional reset GPIO */ + + /* chip specific data */ + u32 chip_id; + int num_vlans; + int num_alus; + int num_statics; + int cpu_port; /* port connected to CPU */ + int cpu_ports; /* port bitmap can be cpu port */ + int phy_port_cnt; + 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 interface; + u32 regs_size; + bool phy_errata_9477; + bool synclko_125; + + struct vlan_table *vlan_cache; + + struct ksz_port *ports; + struct timer_list mib_read_timer; + struct work_struct mib_read; + unsigned long mib_read_interval; + u16 br_member; + u16 member; + u16 live_ports; + u16 on_ports; /* ports enabled by DSA */ + u16 rx_ports; + u16 tx_ports; + u16 mirror_rx; + u16 mirror_tx; + u32 features; /* chip specific features */ + u32 overrides; /* chip functions set by user */ + u16 host_mask; + u16 port_mask; +}; + +struct alu_struct { + /* entry 1 */ + u8 is_static:1; + u8 is_src_filter:1; + u8 is_dst_filter:1; + u8 prio_age:3; + u32 _reserv_0_1:23; + u8 mstp:3; + /* entry 2 */ + u8 is_override:1; + u8 is_use_fid:1; + u32 _reserv_1_1:23; + u8 port_forward:7; + /* entry 3 & 4*/ + u32 _reserv_2_1:9; + u8 fid:7; + u8 mac[ETH_ALEN]; +}; + +struct ksz_dev_ops { + u32 (*get_port_addr)(int port, int offset); + void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); + void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); + void (*phy_setup)(struct ksz_device *dev, int port, + struct phy_device *phy); + void (*port_cleanup)(struct ksz_device *dev, int port); + void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); + void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); + void (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val); + int (*r_dyn_mac_table)(struct ksz_device *dev, u16 addr, u8 *mac_addr, + u8 *fid, u8 *src_port, u8 *timestamp, + u16 *entries); + int (*r_sta_mac_table)(struct ksz_device *dev, u16 addr, + struct alu_struct *alu); + void (*w_sta_mac_table)(struct ksz_device *dev, u16 addr, + struct alu_struct *alu); + void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr, + u64 *cnt); + void (*r_mib_pkt)(struct ksz_device *dev, int port, u16 addr, + u64 *dropped, u64 *cnt); + void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); + void (*port_init_cnt)(struct ksz_device *dev, int port); + int (*shutdown)(struct ksz_device *dev); + int (*detect)(struct ksz_device *dev); + int (*init)(struct ksz_device *dev); + void (*exit)(struct ksz_device *dev); +}; + +struct ksz_device *ksz_switch_alloc(struct device *base, void *priv); +int ksz_switch_register(struct ksz_device *dev, + const struct ksz_dev_ops *ops); +void ksz_switch_remove(struct ksz_device *dev); + +int ksz8795_switch_register(struct ksz_device *dev); +int ksz9477_switch_register(struct ksz_device *dev); -void ksz_port_cleanup(struct ksz_device *dev, int port); void ksz_update_port_member(struct ksz_device *dev, int port); void ksz_init_mib_timer(struct ksz_device *dev); @@ -68,6 +211,22 @@ static inline int ksz_read32(struct ksz_device *dev, u32 reg, u32 *val) return ret; } +static inline int ksz_read64(struct ksz_device *dev, u32 reg, u64 *val) +{ + u32 value[2]; + int ret; + + ret = regmap_bulk_read(dev->regmap[2], reg, value, 2); + if (!ret) { + /* Ick! ToDo: Add 64bit R/W to regmap on 32bit systems */ + value[0] = swab32(value[0]); + value[1] = swab32(value[1]); + *val = swab64((u64)*value); + } + + return ret; +} + static inline int ksz_write8(struct ksz_device *dev, u32 reg, u8 value) { return regmap_write(dev->regmap[0], reg, value); @@ -83,6 +242,18 @@ static inline int ksz_write32(struct ksz_device *dev, u32 reg, u32 value) return regmap_write(dev->regmap[2], reg, value); } +static inline int ksz_write64(struct ksz_device *dev, u32 reg, u64 value) +{ + u32 val[2]; + + /* Ick! ToDo: Add 64bit R/W to regmap on 32bit systems */ + value = swab64(value); + val[0] = swab32(value & 0xffffffffULL); + val[1] = swab32(value >> 32ULL); + + return regmap_bulk_write(dev->regmap[2], reg, val, 2); +} + static inline void ksz_pread8(struct ksz_device *dev, int port, int offset, u8 *data) { diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h deleted file mode 100644 index beacf0e40f42..000000000000 --- a/drivers/net/dsa/microchip/ksz_priv.h +++ /dev/null @@ -1,155 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * - * Microchip KSZ series switch common definitions - * - * Copyright (C) 2017-2019 Microchip Technology Inc. - */ - -#ifndef __KSZ_PRIV_H -#define __KSZ_PRIV_H - -#include <linux/kernel.h> -#include <linux/mutex.h> -#include <linux/phy.h> -#include <linux/etherdevice.h> -#include <net/dsa.h> - -struct vlan_table { - u32 table[3]; -}; - -struct ksz_port_mib { - struct mutex cnt_mutex; /* structure access */ - u8 cnt_ptr; - u64 *counters; -}; - -struct ksz_port { - u16 member; - u16 vid_member; - int stp_state; - struct phy_device phydev; - - u32 on:1; /* port is not disabled by hardware */ - u32 phy:1; /* port has a PHY */ - u32 fiber:1; /* port is fiber */ - u32 sgmii:1; /* port is SGMII */ - u32 force:1; - u32 read:1; /* read MIB counters in background */ - u32 freeze:1; /* MIB counter freeze is enabled */ - - struct ksz_port_mib mib; -}; - -struct ksz_device { - struct dsa_switch *ds; - struct ksz_platform_data *pdata; - const char *name; - - struct mutex dev_mutex; /* device access */ - struct mutex stats_mutex; /* status access */ - struct mutex alu_mutex; /* ALU access */ - struct mutex vlan_mutex; /* vlan access */ - const struct ksz_dev_ops *dev_ops; - - struct device *dev; - struct regmap *regmap[3]; - - void *priv; - - struct gpio_desc *reset_gpio; /* Optional reset GPIO */ - - /* chip specific data */ - u32 chip_id; - int num_vlans; - int num_alus; - int num_statics; - int cpu_port; /* port connected to CPU */ - int cpu_ports; /* port bitmap can be cpu port */ - int phy_port_cnt; - 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 interface; - u32 regs_size; - bool phy_errata_9477; - bool synclko_125; - - struct vlan_table *vlan_cache; - - struct ksz_port *ports; - struct timer_list mib_read_timer; - struct work_struct mib_read; - unsigned long mib_read_interval; - u16 br_member; - u16 member; - u16 live_ports; - u16 on_ports; /* ports enabled by DSA */ - u16 rx_ports; - u16 tx_ports; - u16 mirror_rx; - u16 mirror_tx; - u32 features; /* chip specific features */ - u32 overrides; /* chip functions set by user */ - u16 host_mask; - u16 port_mask; -}; - -struct alu_struct { - /* entry 1 */ - u8 is_static:1; - u8 is_src_filter:1; - u8 is_dst_filter:1; - u8 prio_age:3; - u32 _reserv_0_1:23; - u8 mstp:3; - /* entry 2 */ - u8 is_override:1; - u8 is_use_fid:1; - u32 _reserv_1_1:23; - u8 port_forward:7; - /* entry 3 & 4*/ - u32 _reserv_2_1:9; - u8 fid:7; - u8 mac[ETH_ALEN]; -}; - -struct ksz_dev_ops { - u32 (*get_port_addr)(int port, int offset); - void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); - void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); - void (*phy_setup)(struct ksz_device *dev, int port, - struct phy_device *phy); - void (*port_cleanup)(struct ksz_device *dev, int port); - void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); - void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); - void (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val); - int (*r_dyn_mac_table)(struct ksz_device *dev, u16 addr, u8 *mac_addr, - u8 *fid, u8 *src_port, u8 *timestamp, - u16 *entries); - int (*r_sta_mac_table)(struct ksz_device *dev, u16 addr, - struct alu_struct *alu); - void (*w_sta_mac_table)(struct ksz_device *dev, u16 addr, - struct alu_struct *alu); - void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr, - u64 *cnt); - void (*r_mib_pkt)(struct ksz_device *dev, int port, u16 addr, - u64 *dropped, u64 *cnt); - void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); - void (*port_init_cnt)(struct ksz_device *dev, int port); - int (*shutdown)(struct ksz_device *dev); - int (*detect)(struct ksz_device *dev); - int (*init)(struct ksz_device *dev); - void (*exit)(struct ksz_device *dev); -}; - -struct ksz_device *ksz_switch_alloc(struct device *base, void *priv); -int ksz_switch_register(struct ksz_device *dev, - const struct ksz_dev_ops *ops); -void ksz_switch_remove(struct ksz_device *dev); - -int ksz9477_switch_register(struct ksz_device *dev); - -#endif diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d0a97eb73a37..9b3ad22a5b98 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -10,6 +10,7 @@ * Vivien Didelot <vivien.didelot@savoirfairelinux.com> */ +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> @@ -80,6 +81,36 @@ int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val) return 0; } +int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, + u16 mask, u16 val) +{ + u16 data; + int err; + int i; + + /* There's no bus specific operation to wait for a mask */ + for (i = 0; i < 16; i++) { + err = mv88e6xxx_read(chip, addr, reg, &data); + if (err) + return err; + + if ((data & mask) == val) + return 0; + + usleep_range(1000, 2000); + } + + dev_err(chip->dev, "Timeout while waiting for switch\n"); + return -ETIMEDOUT; +} + +int mv88e6xxx_wait_bit(struct mv88e6xxx_chip *chip, int addr, int reg, + int bit, int val) +{ + return mv88e6xxx_wait_mask(chip, addr, reg, BIT(bit), + val ? BIT(bit) : 0x0000); +} + struct mii_bus *mv88e6xxx_default_mdio_bus(struct mv88e6xxx_chip *chip) { struct mv88e6xxx_mdio_bus *mdio_bus; @@ -363,45 +394,6 @@ static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) mv88e6xxx_reg_unlock(chip); } -int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) -{ - int i; - - for (i = 0; i < 16; i++) { - u16 val; - int err; - - err = mv88e6xxx_read(chip, addr, reg, &val); - if (err) - return err; - - if (!(val & mask)) - return 0; - - usleep_range(1000, 2000); - } - - dev_err(chip->dev, "Timeout while waiting for switch\n"); - return -ETIMEDOUT; -} - -/* Indirect write to single pointer-data register with an Update bit */ -int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, u16 update) -{ - u16 val; - int err; - - /* Wait until the previous operation is completed */ - err = mv88e6xxx_wait(chip, addr, reg, BIT(15)); - if (err) - return err; - - /* Set the Update bit to trigger a write operation */ - val = BIT(15) | update; - - return mv88e6xxx_write(chip, addr, reg, val); -} - int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, int speed, int duplex, int pause, phy_interface_t mode) @@ -425,7 +417,9 @@ int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, */ if (state.link == link && state.speed == speed && - state.duplex == duplex) + state.duplex == duplex && + (state.interface == mode || + state.interface == PHY_INTERFACE_MODE_NA)) return 0; /* Port's MAC control must not be changed unless the link is down */ @@ -1336,9 +1330,7 @@ static int mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_chip *chip, static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) { DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID); - struct mv88e6xxx_vtu_entry vlan = { - .vid = chip->info->max_vid, - }; + struct mv88e6xxx_vtu_entry vlan; int i, err; bitmap_zero(fid_bitmap, MV88E6XXX_N_FID); @@ -1353,6 +1345,9 @@ static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) } /* Set every FID bit used by the VLAN entries */ + vlan.vid = chip->info->max_vid; + vlan.valid = false; + do { err = mv88e6xxx_vtu_getnext(chip, &vlan); if (err) @@ -1375,51 +1370,11 @@ static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) return mv88e6xxx_g1_atu_flush(chip, *fid, true); } -static int mv88e6xxx_vtu_get(struct mv88e6xxx_chip *chip, u16 vid, - struct mv88e6xxx_vtu_entry *entry, bool new) -{ - int err; - - if (!vid) - return -EOPNOTSUPP; - - entry->vid = vid - 1; - entry->valid = false; - - err = mv88e6xxx_vtu_getnext(chip, entry); - if (err) - return err; - - if (entry->vid == vid && entry->valid) - return 0; - - if (new) { - int i; - - /* Initialize a fresh VLAN entry */ - memset(entry, 0, sizeof(*entry)); - entry->valid = true; - entry->vid = vid; - - /* Exclude all ports */ - for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) - entry->member[i] = - MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER; - - return mv88e6xxx_atu_new(chip, &entry->fid); - } - - /* switchdev expects -EOPNOTSUPP to honor software VLANs */ - return -EOPNOTSUPP; -} - static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, u16 vid_begin, u16 vid_end) { struct mv88e6xxx_chip *chip = ds->priv; - struct mv88e6xxx_vtu_entry vlan = { - .vid = vid_begin - 1, - }; + struct mv88e6xxx_vtu_entry vlan; int i, err; /* DSA and CPU ports have to be members of multiple vlans */ @@ -1429,12 +1384,13 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, if (!vid_begin) return -EOPNOTSUPP; - mv88e6xxx_reg_lock(chip); + vlan.vid = vid_begin - 1; + vlan.valid = false; do { err = mv88e6xxx_vtu_getnext(chip, &vlan); if (err) - goto unlock; + return err; if (!vlan.valid) break; @@ -1463,15 +1419,11 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, dev_err(ds->dev, "p%d: hw VLAN %d already used by port %d in %s\n", port, vlan.vid, i, netdev_name(dsa_to_port(ds, i)->bridge_dev)); - err = -EOPNOTSUPP; - goto unlock; + return -EOPNOTSUPP; } } while (vlan.vid < vid_end); -unlock: - mv88e6xxx_reg_unlock(chip); - - return err; + return 0; } static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port, @@ -1505,38 +1457,51 @@ mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port, /* If the requested port doesn't belong to the same bridge as the VLAN * members, do not support it (yet) and fallback to software VLAN. */ + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_check_hw_vlan(ds, port, vlan->vid_begin, vlan->vid_end); - if (err) - return err; + mv88e6xxx_reg_unlock(chip); /* We don't need any dynamic resource from the kernel (yet), * so skip the prepare phase. */ - return 0; + return err; } static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, const unsigned char *addr, u16 vid, u8 state) { - struct mv88e6xxx_vtu_entry vlan; struct mv88e6xxx_atu_entry entry; + struct mv88e6xxx_vtu_entry vlan; + u16 fid; int err; /* Null VLAN ID corresponds to the port private database */ - if (vid == 0) - err = mv88e6xxx_port_get_fid(chip, port, &vlan.fid); - else - err = mv88e6xxx_vtu_get(chip, vid, &vlan, false); - if (err) - return err; + if (vid == 0) { + err = mv88e6xxx_port_get_fid(chip, port, &fid); + if (err) + return err; + } else { + vlan.vid = vid - 1; + vlan.valid = false; + + err = mv88e6xxx_vtu_getnext(chip, &vlan); + if (err) + return err; + + /* switchdev expects -EOPNOTSUPP to honor software VLANs */ + if (vlan.vid != vid || !vlan.valid) + return -EOPNOTSUPP; + + fid = vlan.fid; + } entry.state = MV88E6XXX_G1_ATU_DATA_STATE_UNUSED; ether_addr_copy(entry.mac, addr); eth_addr_dec(entry.mac); - err = mv88e6xxx_g1_atu_getnext(chip, vlan.fid, &entry); + err = mv88e6xxx_g1_atu_getnext(chip, fid, &entry); if (err) return err; @@ -1557,7 +1522,7 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, entry.state = state; } - return mv88e6xxx_g1_atu_loadpurge(chip, vlan.fid, &entry); + return mv88e6xxx_g1_atu_loadpurge(chip, fid, &entry); } static int mv88e6xxx_port_add_broadcast(struct mv88e6xxx_chip *chip, int port, @@ -1583,23 +1548,58 @@ static int mv88e6xxx_broadcast_setup(struct mv88e6xxx_chip *chip, u16 vid) return 0; } -static int _mv88e6xxx_port_vlan_add(struct mv88e6xxx_chip *chip, int port, +static int mv88e6xxx_port_vlan_join(struct mv88e6xxx_chip *chip, int port, u16 vid, u8 member) { + const u8 non_member = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER; struct mv88e6xxx_vtu_entry vlan; - int err; + int i, err; - err = mv88e6xxx_vtu_get(chip, vid, &vlan, true); - if (err) - return err; + if (!vid) + return -EOPNOTSUPP; - vlan.member[port] = member; + vlan.vid = vid - 1; + vlan.valid = false; - err = mv88e6xxx_vtu_loadpurge(chip, &vlan); + err = mv88e6xxx_vtu_getnext(chip, &vlan); if (err) return err; - return mv88e6xxx_broadcast_setup(chip, vid); + if (vlan.vid != vid || !vlan.valid) { + memset(&vlan, 0, sizeof(vlan)); + + err = mv88e6xxx_atu_new(chip, &vlan.fid); + if (err) + return err; + + for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) + if (i == port) + vlan.member[i] = member; + else + vlan.member[i] = non_member; + + vlan.vid = vid; + vlan.valid = true; + + err = mv88e6xxx_vtu_loadpurge(chip, &vlan); + if (err) + return err; + + err = mv88e6xxx_broadcast_setup(chip, vlan.vid); + if (err) + return err; + } else if (vlan.member[port] != member) { + vlan.member[port] = member; + + err = mv88e6xxx_vtu_loadpurge(chip, &vlan); + if (err) + return err; + } else { + dev_info(chip->dev, "p%d: already a member of VLAN %d\n", + port, vid); + } + + return 0; } static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, @@ -1624,7 +1624,7 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, mv88e6xxx_reg_lock(chip); for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) - if (_mv88e6xxx_port_vlan_add(chip, port, vid, member)) + if (mv88e6xxx_port_vlan_join(chip, port, vid, member)) dev_err(ds->dev, "p%d: failed to add VLAN %d%c\n", port, vid, untagged ? 'u' : 't'); @@ -1635,18 +1635,27 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, mv88e6xxx_reg_unlock(chip); } -static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip, - int port, u16 vid) +static int mv88e6xxx_port_vlan_leave(struct mv88e6xxx_chip *chip, + int port, u16 vid) { struct mv88e6xxx_vtu_entry vlan; int i, err; - err = mv88e6xxx_vtu_get(chip, vid, &vlan, false); + if (!vid) + return -EOPNOTSUPP; + + vlan.vid = vid - 1; + vlan.valid = false; + + err = mv88e6xxx_vtu_getnext(chip, &vlan); if (err) return err; - /* Tell switchdev if this VLAN is handled in software */ - if (vlan.member[port] == MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER) + /* If the VLAN doesn't exist in hardware or the port isn't a member, + * tell switchdev that this VLAN is likely handled in software. + */ + if (vlan.vid != vid || !vlan.valid || + vlan.member[port] == MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER) return -EOPNOTSUPP; vlan.member[port] = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER; @@ -1685,7 +1694,7 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, goto unlock; for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { - err = _mv88e6xxx_port_vlan_del(chip, port, vid); + err = mv88e6xxx_port_vlan_leave(chip, port, vid); if (err) goto unlock; @@ -1768,9 +1777,7 @@ static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, dsa_fdb_dump_cb_t *cb, void *data) { - struct mv88e6xxx_vtu_entry vlan = { - .vid = chip->info->max_vid, - }; + struct mv88e6xxx_vtu_entry vlan; u16 fid; int err; @@ -1784,6 +1791,9 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, return err; /* Dump VLANs' Filtering Information Databases */ + vlan.vid = chip->info->max_vid; + vlan.valid = false; + do { err = mv88e6xxx_vtu_getnext(chip, &vlan); if (err) @@ -2227,9 +2237,11 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } - err = mv88e6xxx_setup_message_port(chip, port); - if (err) - return err; + if (chip->info->ops->port_setup_message_port) { + err = chip->info->ops->port_setup_message_port(chip, port); + if (err) + return err; + } /* Port based VLAN map: give each port the same default address * database, and allow bidirectional communication between the @@ -2336,8 +2348,10 @@ static int mv88e6390_hidden_write(struct mv88e6xxx_chip *chip, int port, static int mv88e6390_hidden_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_wait(chip, PORT_RESERVED_1A_CTRL_PORT, - PORT_RESERVED_1A, PORT_RESERVED_1A_BUSY); + int bit = __bf_shf(PORT_RESERVED_1A_BUSY); + + return mv88e6xxx_wait_bit(chip, PORT_RESERVED_1A_CTRL_PORT, + PORT_RESERVED_1A, bit, 0); } @@ -2444,6 +2458,14 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) /* Setup Switch Port Registers */ for (i = 0; i < mv88e6xxx_num_ports(chip); i++) { + /* Prevent the use of an invalid port. */ + if (mv88e6xxx_is_invalid_port(chip, i) && + !dsa_is_unused_port(ds, i)) { + dev_err(chip->dev, "port %d is invalid\n", i); + err = -EINVAL; + goto unlock; + } + if (dsa_is_unused_port(ds, i)) { err = mv88e6xxx_port_set_state(chip, i, BR_STATE_DISABLED); @@ -2773,6 +2795,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -2807,6 +2830,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = { .port_set_upstream_port = mv88e6095_port_set_upstream_port, .port_link_state = mv88e6185_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -2843,6 +2867,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -2877,6 +2902,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -2914,6 +2940,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = { .port_set_pause = mv88e6185_port_set_pause, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -2958,6 +2985,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -2998,6 +3026,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3031,6 +3060,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3072,6 +3102,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3113,6 +3144,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3155,6 +3187,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3196,6 +3229,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3234,6 +3268,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = { .port_set_pause = mv88e6185_port_set_pause, .port_link_state = mv88e6185_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3276,6 +3311,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, .port_set_cmode = mv88e6390_port_set_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3321,6 +3357,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, .port_set_cmode = mv88e6390x_port_set_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3366,6 +3403,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, .port_set_cmode = mv88e6390_port_set_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3413,6 +3451,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3471,6 +3510,8 @@ static const struct mv88e6xxx_ops mv88e6250_ops = { .reset = mv88e6250_g1_reset, .vtu_getnext = mv88e6250_g1_vtu_getnext, .vtu_loadpurge = mv88e6250_g1_vtu_loadpurge, + .avb_ops = &mv88e6352_avb_ops, + .ptp_ops = &mv88e6250_ptp_ops, .phylink_validate = mv88e6065_phylink_validate, }; @@ -3498,6 +3539,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, .port_set_cmode = mv88e6390_port_set_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3545,6 +3587,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3588,6 +3631,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3631,6 +3675,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3674,6 +3719,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3713,6 +3759,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3756,6 +3803,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6320_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, @@ -3808,6 +3856,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, .port_set_cmode = mv88e6390_port_set_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -3857,6 +3906,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6352_port_get_cmode, .port_set_cmode = mv88e6390x_port_set_cmode, + .port_setup_message_port = mv88e6xxx_setup_message_port, .stats_snapshot = mv88e6390_g1_stats_snapshot, .stats_set_histogram = mv88e6390_g1_stats_set_histogram, .stats_get_sset_count = mv88e6320_stats_get_sset_count, @@ -4235,6 +4285,33 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .ops = &mv88e6191_ops, }, + [MV88E6220] = { + .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6220, + .family = MV88E6XXX_FAMILY_6250, + .name = "Marvell 88E6220", + .num_databases = 64, + + /* Ports 2-4 are not routed to pins + * => usable ports 0, 1, 5, 6 + */ + .num_ports = 7, + .num_internal_phys = 2, + .invalid_port_mask = BIT(2) | BIT(3) | BIT(4), + .max_vid = 4095, + .port_base_addr = 0x08, + .phy_base_addr = 0x00, + .global1_addr = 0x0f, + .global2_addr = 0x07, + .age_time_coeff = 15000, + .g1_irqs = 9, + .g2_irqs = 10, + .atu_move_port_mask = 0xf, + .dual_chip = true, + .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, + .ops = &mv88e6250_ops, + }, + [MV88E6240] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6240, .family = MV88E6XXX_FAMILY_6352, @@ -4277,6 +4354,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .atu_move_port_mask = 0xf, .dual_chip = true, .tag_protocol = DSA_TAG_PROTO_DSA, + .ptp_support = true, .ops = &mv88e6250_ops, }, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 4646e46d47f2..a406be2f5652 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -57,6 +57,7 @@ enum mv88e6xxx_model { MV88E6190, MV88E6190X, MV88E6191, + MV88E6220, MV88E6240, MV88E6250, MV88E6290, @@ -77,7 +78,7 @@ enum mv88e6xxx_family { MV88E6XXX_FAMILY_6097, /* 6046 6085 6096 6097 */ MV88E6XXX_FAMILY_6165, /* 6123 6161 6165 */ MV88E6XXX_FAMILY_6185, /* 6108 6121 6122 6131 6152 6155 6182 6185 */ - MV88E6XXX_FAMILY_6250, /* 6250 */ + MV88E6XXX_FAMILY_6250, /* 6220 6250 */ MV88E6XXX_FAMILY_6320, /* 6320 6321 */ MV88E6XXX_FAMILY_6341, /* 6141 6341 */ MV88E6XXX_FAMILY_6351, /* 6171 6175 6350 6351 */ @@ -105,6 +106,11 @@ struct mv88e6xxx_info { unsigned int g2_irqs; bool pvt; + /* Mark certain ports as invalid. This is required for example for the + * MV88E6220 (which is in general a MV88E6250 with 7 ports) but the + * ports 2-4 are not routet to pins. + */ + unsigned int invalid_port_mask; /* Multi-chip Addressing Mode. * Some chips respond to only 2 registers of its own SMI device address * when it is non-zero, and use indirect access to internal registers. @@ -389,6 +395,7 @@ struct mv88e6xxx_ops { u8 out); int (*port_disable_learn_limit)(struct mv88e6xxx_chip *chip, int port); int (*port_disable_pri_override)(struct mv88e6xxx_chip *chip, int port); + int (*port_setup_message_port)(struct mv88e6xxx_chip *chip, int port); /* CMODE control what PHY mode the MAC will use, eg. SGMII, RGMII, etc. * Some chips allow this to be configured on specific ports. @@ -532,6 +539,10 @@ struct mv88e6xxx_ptp_ops { int arr1_sts_reg; int dep_sts_reg; u32 rx_filters; + u32 cc_shift; + u32 cc_mult; + u32 cc_mult_num; + u32 cc_mult_dem; }; #define STATS_TYPE_PORT BIT(0) @@ -570,11 +581,17 @@ static inline unsigned int mv88e6xxx_num_gpio(struct mv88e6xxx_chip *chip) return chip->info->num_gpio; } +static inline bool mv88e6xxx_is_invalid_port(struct mv88e6xxx_chip *chip, int port) +{ + return (chip->info->invalid_port_mask & BIT(port)) != 0; +} + int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); -int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, - u16 update); -int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask); +int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, + u16 mask, u16 val); +int mv88e6xxx_wait_bit(struct mv88e6xxx_chip *chip, int addr, int reg, + int bit, int val); int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, int speed, int duplex, int pause, phy_interface_t mode); diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 1323ef30a5e9..25ec4c0ac589 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -27,100 +27,52 @@ int mv88e6xxx_g1_write(struct mv88e6xxx_chip *chip, int reg, u16 val) return mv88e6xxx_write(chip, addr, reg, val); } -int mv88e6xxx_g1_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +int mv88e6xxx_g1_wait_bit(struct mv88e6xxx_chip *chip, int reg, int + bit, int val) { - return mv88e6xxx_wait(chip, chip->info->global1_addr, reg, mask); + return mv88e6xxx_wait_bit(chip, chip->info->global1_addr, reg, + bit, val); +} + +int mv88e6xxx_g1_wait_mask(struct mv88e6xxx_chip *chip, int reg, + u16 mask, u16 val) +{ + return mv88e6xxx_wait_mask(chip, chip->info->global1_addr, reg, + mask, val); } /* Offset 0x00: Switch Global Status Register */ static int mv88e6185_g1_wait_ppu_disabled(struct mv88e6xxx_chip *chip) { - u16 state; - int i, err; - - for (i = 0; i < 16; i++) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &state); - if (err) - return err; - - /* Check the value of the PPUState bits 15:14 */ - state &= MV88E6185_G1_STS_PPU_STATE_MASK; - if (state != MV88E6185_G1_STS_PPU_STATE_POLLING) - return 0; - - usleep_range(1000, 2000); - } - - return -ETIMEDOUT; + return mv88e6xxx_g1_wait_mask(chip, MV88E6XXX_G1_STS, + MV88E6185_G1_STS_PPU_STATE_MASK, + MV88E6185_G1_STS_PPU_STATE_DISABLED); } static int mv88e6185_g1_wait_ppu_polling(struct mv88e6xxx_chip *chip) { - u16 state; - int i, err; - - for (i = 0; i < 16; ++i) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &state); - if (err) - return err; - - /* Check the value of the PPUState bits 15:14 */ - state &= MV88E6185_G1_STS_PPU_STATE_MASK; - if (state == MV88E6185_G1_STS_PPU_STATE_POLLING) - return 0; - - usleep_range(1000, 2000); - } - - return -ETIMEDOUT; + return mv88e6xxx_g1_wait_mask(chip, MV88E6XXX_G1_STS, + MV88E6185_G1_STS_PPU_STATE_MASK, + MV88E6185_G1_STS_PPU_STATE_POLLING); } static int mv88e6352_g1_wait_ppu_polling(struct mv88e6xxx_chip *chip) { - u16 state; - int i, err; + int bit = __bf_shf(MV88E6352_G1_STS_PPU_STATE); - for (i = 0; i < 16; ++i) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &state); - if (err) - return err; - - /* Check the value of the PPUState (or InitState) bit 15 */ - if (state & MV88E6352_G1_STS_PPU_STATE) - return 0; - - usleep_range(1000, 2000); - } - - return -ETIMEDOUT; + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) { - const unsigned long timeout = jiffies + 1 * HZ; - u16 val; - int err; + int bit = __bf_shf(MV88E6XXX_G1_STS_INIT_READY); /* Wait up to 1 second for the switch to be ready. The InitReady bit 11 * is set to a one when all units inside the device (ATU, VTU, etc.) * have finished their initialization and are ready to accept frames. */ - while (time_before(jiffies, timeout)) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); - if (err) - return err; - - if (val & MV88E6XXX_G1_STS_INIT_READY) - break; - - usleep_range(1000, 2000); - } - - if (time_after(jiffies, timeout)) - return -ETIMEDOUT; - - return 0; + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 @@ -476,8 +428,9 @@ int mv88e6xxx_g1_set_device_number(struct mv88e6xxx_chip *chip, int index) static int mv88e6xxx_g1_stats_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g1_wait(chip, MV88E6XXX_G1_STATS_OP, - MV88E6XXX_G1_STATS_OP_BUSY); + int bit = __bf_shf(MV88E6XXX_G1_STATS_OP_BUSY); + + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STATS_OP, bit, 0); } int mv88e6095_g1_stats_set_histogram(struct mv88e6xxx_chip *chip) diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index d444266f7d78..78b9ae22d18c 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -249,7 +249,10 @@ int mv88e6xxx_g1_read(struct mv88e6xxx_chip *chip, int reg, u16 *val); int mv88e6xxx_g1_write(struct mv88e6xxx_chip *chip, int reg, u16 val); -int mv88e6xxx_g1_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask); +int mv88e6xxx_g1_wait_bit(struct mv88e6xxx_chip *chip, int reg, int + bit, int val); +int mv88e6xxx_g1_wait_mask(struct mv88e6xxx_chip *chip, int reg, + u16 mask, u16 val); int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 1cf388e9bd94..18b86515b6bc 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -5,6 +5,8 @@ * Copyright (c) 2008 Marvell Semiconductor * Copyright (c) 2017 Savoir-faire Linux, Inc. */ + +#include <linux/bitfield.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> @@ -75,8 +77,9 @@ int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, static int mv88e6xxx_g1_atu_op_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g1_wait(chip, MV88E6XXX_G1_ATU_OP, - MV88E6XXX_G1_ATU_OP_BUSY); + int bit = __bf_shf(MV88E6XXX_G1_ATU_OP_BUSY); + + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_ATU_OP, bit, 0); } static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op) diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c index 6cac997360e8..33056a609e96 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c @@ -7,6 +7,7 @@ * Copyright (c) 2017 Savoir-faire Linux, Inc. */ +#include <linux/bitfield.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> @@ -67,8 +68,9 @@ static int mv88e6xxx_g1_vtu_sid_write(struct mv88e6xxx_chip *chip, static int mv88e6xxx_g1_vtu_op_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g1_wait(chip, MV88E6XXX_G1_VTU_OP, - MV88E6XXX_G1_VTU_OP_BUSY); + int bit = __bf_shf(MV88E6XXX_G1_VTU_OP_BUSY); + + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_VTU_OP, bit, 0); } static int mv88e6xxx_g1_vtu_op(struct mv88e6xxx_chip *chip, u16 op) diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 2305b94b3051..bdbb72fc20ed 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -26,14 +26,11 @@ int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) return mv88e6xxx_write(chip, chip->info->global2_addr, reg, val); } -int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) +int mv88e6xxx_g2_wait_bit(struct mv88e6xxx_chip *chip, int reg, int + bit, int val) { - return mv88e6xxx_update(chip, chip->info->global2_addr, reg, update); -} - -int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) -{ - return mv88e6xxx_wait(chip, chip->info->global2_addr, reg, mask); + return mv88e6xxx_wait_bit(chip, chip->info->global2_addr, reg, + bit, val); } /* Offset 0x00: Interrupt Source Register */ @@ -123,7 +120,8 @@ int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target, * but bit 4 is reserved on older chips, so it is safe to use. */ - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_DEVICE_MAPPING, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_DEVICE_MAPPING, + MV88E6XXX_G2_DEVICE_MAPPING_UPDATE | val); } /* Offset 0x07: Trunk Mask Table register */ @@ -136,7 +134,8 @@ static int mv88e6xxx_g2_trunk_mask_write(struct mv88e6xxx_chip *chip, int num, if (hash) val |= MV88E6XXX_G2_TRUNK_MASK_HASH; - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_TRUNK_MASK, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_TRUNK_MASK, + MV88E6XXX_G2_TRUNK_MASK_UPDATE | val); } /* Offset 0x08: Trunk Mapping Table register */ @@ -147,7 +146,8 @@ static int mv88e6xxx_g2_trunk_mapping_write(struct mv88e6xxx_chip *chip, int id, const u16 port_mask = BIT(mv88e6xxx_num_ports(chip)) - 1; u16 val = (id << 11) | (map & port_mask); - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_TRUNK_MAPPING, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_TRUNK_MAPPING, + MV88E6XXX_G2_TRUNK_MAPPING_UPDATE | val); } int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip) @@ -178,8 +178,9 @@ int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip) static int mv88e6xxx_g2_irl_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_IRL_CMD, - MV88E6XXX_G2_IRL_CMD_BUSY); + int bit = __bf_shf(MV88E6XXX_G2_IRL_CMD_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_IRL_CMD, bit, 0); } static int mv88e6xxx_g2_irl_op(struct mv88e6xxx_chip *chip, u16 op, int port, @@ -214,8 +215,9 @@ int mv88e6390_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port) static int mv88e6xxx_g2_pvt_op_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_PVT_ADDR, - MV88E6XXX_G2_PVT_ADDR_BUSY); + int bit = __bf_shf(MV88E6XXX_G2_PVT_ADDR_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_PVT_ADDR, bit, 0); } static int mv88e6xxx_g2_pvt_op(struct mv88e6xxx_chip *chip, int src_dev, @@ -261,7 +263,8 @@ static int mv88e6xxx_g2_switch_mac_write(struct mv88e6xxx_chip *chip, { u16 val = (pointer << 8) | data; - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_SWITCH_MAC, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SWITCH_MAC, + MV88E6XXX_G2_SWITCH_MAC_UPDATE | val); } int mv88e6xxx_g2_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr) @@ -284,7 +287,8 @@ static int mv88e6xxx_g2_pot_write(struct mv88e6xxx_chip *chip, int pointer, { u16 val = (pointer << 8) | (data & 0x7); - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_PRIO_OVERRIDE, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_PRIO_OVERRIDE, + MV88E6XXX_G2_PRIO_OVERRIDE_UPDATE | val); } int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) @@ -308,9 +312,16 @@ int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) static int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_EEPROM_CMD, - MV88E6XXX_G2_EEPROM_CMD_BUSY | - MV88E6XXX_G2_EEPROM_CMD_RUNNING); + int bit = __bf_shf(MV88E6XXX_G2_EEPROM_CMD_BUSY); + int err; + + err = mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_EEPROM_CMD, bit, 0); + if (err) + return err; + + bit = __bf_shf(MV88E6XXX_G2_EEPROM_CMD_RUNNING); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_EEPROM_CMD, bit, 0); } static int mv88e6xxx_g2_eeprom_cmd(struct mv88e6xxx_chip *chip, u16 cmd) @@ -572,8 +583,9 @@ int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip, static int mv88e6xxx_g2_smi_phy_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_SMI_PHY_CMD, - MV88E6XXX_G2_SMI_PHY_CMD_BUSY); + int bit = __bf_shf(MV88E6XXX_G2_SMI_PHY_CMD_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_SMI_PHY_CMD, bit, 0); } static int mv88e6xxx_g2_smi_phy_cmd(struct mv88e6xxx_chip *chip, u16 cmd) @@ -840,12 +852,13 @@ const struct mv88e6xxx_irq_ops mv88e6250_watchdog_ops = { static int mv88e6390_watchdog_setup(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_update(chip, MV88E6390_G2_WDOG_CTL, - MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE | - MV88E6390_G2_WDOG_CTL_CUT_THROUGH | - MV88E6390_G2_WDOG_CTL_QUEUE_CONTROLLER | - MV88E6390_G2_WDOG_CTL_EGRESS | - MV88E6390_G2_WDOG_CTL_FORCE_IRQ); + return mv88e6xxx_g2_write(chip, MV88E6390_G2_WDOG_CTL, + MV88E6390_G2_WDOG_CTL_UPDATE | + MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE | + MV88E6390_G2_WDOG_CTL_CUT_THROUGH | + MV88E6390_G2_WDOG_CTL_QUEUE_CONTROLLER | + MV88E6390_G2_WDOG_CTL_EGRESS | + MV88E6390_G2_WDOG_CTL_FORCE_IRQ); } static int mv88e6390_watchdog_action(struct mv88e6xxx_chip *chip, int irq) @@ -878,8 +891,9 @@ static int mv88e6390_watchdog_action(struct mv88e6xxx_chip *chip, int irq) static void mv88e6390_watchdog_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g2_update(chip, MV88E6390_G2_WDOG_CTL, - MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE); + mv88e6xxx_g2_write(chip, MV88E6390_G2_WDOG_CTL, + MV88E6390_G2_WDOG_CTL_UPDATE | + MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE); } const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops = { diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index a664fc25f132..42da4bca73e8 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -295,8 +295,8 @@ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val); int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val); -int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update); -int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask); +int mv88e6xxx_g2_wait_bit(struct mv88e6xxx_chip *chip, int reg, + int bit, int val); int mv88e6352_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); @@ -376,12 +376,8 @@ static inline int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 v return -EOPNOTSUPP; } -static inline int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) -{ - return -EOPNOTSUPP; -} - -static inline int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +static inline int mv88e6xxx_g2_wait_bit(struct mv88e6xxx_chip *chip, + int reg, int bit, int val) { return -EOPNOTSUPP; } diff --git a/drivers/net/dsa/mv88e6xxx/global2_avb.c b/drivers/net/dsa/mv88e6xxx/global2_avb.c index 116b8cf5a6e3..657783e043ff 100644 --- a/drivers/net/dsa/mv88e6xxx/global2_avb.c +++ b/drivers/net/dsa/mv88e6xxx/global2_avb.c @@ -11,6 +11,8 @@ * Brandon Streiff <brandon.streiff@ni.com> */ +#include <linux/bitfield.h> + #include "global2.h" /* Offset 0x16: AVB Command Register @@ -27,17 +29,33 @@ /* mv88e6xxx_g2_avb_read -- Read one or multiple 16-bit words. * The hardware supports snapshotting up to four contiguous registers. */ +static int mv88e6xxx_g2_avb_wait(struct mv88e6xxx_chip *chip) +{ + int bit = __bf_shf(MV88E6352_G2_AVB_CMD_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6352_G2_AVB_CMD, bit, 0); +} + static int mv88e6xxx_g2_avb_read(struct mv88e6xxx_chip *chip, u16 readop, u16 *data, int len) { int err; int i; + err = mv88e6xxx_g2_avb_wait(chip); + if (err) + return err; + /* Hardware can only snapshot four words. */ if (len > 4) return -E2BIG; - err = mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, readop); + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_CMD, + MV88E6352_G2_AVB_CMD_BUSY | readop); + if (err) + return err; + + err = mv88e6xxx_g2_avb_wait(chip); if (err) return err; @@ -57,11 +75,18 @@ static int mv88e6xxx_g2_avb_write(struct mv88e6xxx_chip *chip, u16 writeop, { int err; + err = mv88e6xxx_g2_avb_wait(chip); + if (err) + return err; + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_DATA, data); if (err) return err; - return mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, writeop); + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_CMD, + MV88E6352_G2_AVB_CMD_BUSY | writeop); + + return mv88e6xxx_g2_avb_wait(chip); } static int mv88e6352_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip, diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c index baddecadd8be..33b7b9570d29 100644 --- a/drivers/net/dsa/mv88e6xxx/global2_scratch.c +++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c @@ -37,7 +37,8 @@ static int mv88e6xxx_g2_scratch_write(struct mv88e6xxx_chip *chip, int reg, { u16 value = (reg << 8) | data; - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, value); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, + MV88E6XXX_G2_SCRATCH_MISC_UPDATE | value); } /** diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 04309ef0a1cc..c95cdb73e5a2 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -590,6 +590,7 @@ int mv88e6250_port_link_state(struct mv88e6xxx_chip *chip, int port, state->link = !!(reg & MV88E6250_PORT_STS_LINK); state->an_enabled = 1; state->an_complete = state->link; + state->interface = PHY_INTERFACE_MODE_NA; return 0; } @@ -600,6 +601,43 @@ int mv88e6352_port_link_state(struct mv88e6xxx_chip *chip, int port, int err; u16 reg; + switch (chip->ports[port].cmode) { + case MV88E6XXX_PORT_STS_CMODE_RGMII: + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_MAC_CTL, + ®); + if (err) + return err; + + if ((reg & MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_RXCLK) && + (reg & MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_TXCLK)) + state->interface = PHY_INTERFACE_MODE_RGMII_ID; + else if (reg & MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_RXCLK) + state->interface = PHY_INTERFACE_MODE_RGMII_RXID; + else if (reg & MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_TXCLK) + state->interface = PHY_INTERFACE_MODE_RGMII_TXID; + else + state->interface = PHY_INTERFACE_MODE_RGMII; + break; + case MV88E6XXX_PORT_STS_CMODE_1000BASE_X: + state->interface = PHY_INTERFACE_MODE_1000BASEX; + break; + case MV88E6XXX_PORT_STS_CMODE_SGMII: + state->interface = PHY_INTERFACE_MODE_SGMII; + break; + case MV88E6XXX_PORT_STS_CMODE_2500BASEX: + state->interface = PHY_INTERFACE_MODE_2500BASEX; + break; + case MV88E6XXX_PORT_STS_CMODE_XAUI: + state->interface = PHY_INTERFACE_MODE_XAUI; + break; + case MV88E6XXX_PORT_STS_CMODE_RXAUI: + state->interface = PHY_INTERFACE_MODE_RXAUI; + break; + default: + /* we do not support other cmode values here */ + state->interface = PHY_INTERFACE_MODE_NA; + } + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 8d5a6cd6fb19..1abf5ea033e2 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -42,6 +42,7 @@ #define MV88E6XXX_PORT_STS_TX_PAUSED 0x0020 #define MV88E6XXX_PORT_STS_FLOW_CTL 0x0010 #define MV88E6XXX_PORT_STS_CMODE_MASK 0x000f +#define MV88E6XXX_PORT_STS_CMODE_RGMII 0x0007 #define MV88E6XXX_PORT_STS_CMODE_100BASE_X 0x0008 #define MV88E6XXX_PORT_STS_CMODE_1000BASE_X 0x0009 #define MV88E6XXX_PORT_STS_CMODE_SGMII 0x000a @@ -117,6 +118,7 @@ #define MV88E6XXX_PORT_SWITCH_ID_PROD_6190 0x1900 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6191 0x1910 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6185 0x1a70 +#define MV88E6XXX_PORT_SWITCH_ID_PROD_6220 0x2200 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6240 0x2400 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6250 0x2500 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6290 0x2900 diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c index 768d256f7c9f..073cbd0bb91b 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.c +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -15,11 +15,31 @@ #include "hwtstamp.h" #include "ptp.h" -/* Raw timestamps are in units of 8-ns clock periods. */ -#define CC_SHIFT 28 -#define CC_MULT (8 << CC_SHIFT) -#define CC_MULT_NUM (1 << 9) -#define CC_MULT_DEM 15625ULL +#define MV88E6XXX_MAX_ADJ_PPB 1000000 + +/* Family MV88E6250: + * Raw timestamps are in units of 10-ns clock periods. + * + * clkadj = scaled_ppm * 10*2^28 / (10^6 * 2^16) + * simplifies to + * clkadj = scaled_ppm * 2^7 / 5^5 + */ +#define MV88E6250_CC_SHIFT 28 +#define MV88E6250_CC_MULT (10 << MV88E6250_CC_SHIFT) +#define MV88E6250_CC_MULT_NUM (1 << 7) +#define MV88E6250_CC_MULT_DEM 3125ULL + +/* Other families: + * Raw timestamps are in units of 8-ns clock periods. + * + * clkadj = scaled_ppm * 8*2^28 / (10^6 * 2^16) + * simplifies to + * clkadj = scaled_ppm * 2^9 / 5^6 + */ +#define MV88E6XXX_CC_SHIFT 28 +#define MV88E6XXX_CC_MULT (8 << MV88E6XXX_CC_SHIFT) +#define MV88E6XXX_CC_MULT_NUM (1 << 9) +#define MV88E6XXX_CC_MULT_DEM 15625ULL #define TAI_EVENT_WORK_INTERVAL msecs_to_jiffies(100) @@ -179,6 +199,7 @@ out: static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct mv88e6xxx_chip *chip = ptp_to_chip(ptp); + const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops; int neg_adj = 0; u32 diff, mult; u64 adj; @@ -187,10 +208,11 @@ static int mv88e6xxx_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) neg_adj = 1; scaled_ppm = -scaled_ppm; } - mult = CC_MULT; - adj = CC_MULT_NUM; + + mult = ptp_ops->cc_mult; + adj = ptp_ops->cc_mult_num; adj *= scaled_ppm; - diff = div_u64(adj, CC_MULT_DEM); + diff = div_u64(adj, ptp_ops->cc_mult_dem); mv88e6xxx_reg_lock(chip); @@ -310,7 +332,27 @@ static int mv88e6352_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, return 0; } -const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = { +const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = { + .clock_read = mv88e6165_ptp_clock_read, + .global_enable = mv88e6165_global_enable, + .global_disable = mv88e6165_global_disable, + .arr0_sts_reg = MV88E6165_PORT_PTP_ARR0_STS, + .arr1_sts_reg = MV88E6165_PORT_PTP_ARR1_STS, + .dep_sts_reg = MV88E6165_PORT_PTP_DEP_STS, + .rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), + .cc_shift = MV88E6XXX_CC_SHIFT, + .cc_mult = MV88E6XXX_CC_MULT, + .cc_mult_num = MV88E6XXX_CC_MULT_NUM, + .cc_mult_dem = MV88E6XXX_CC_MULT_DEM, +}; + +const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = { .clock_read = mv88e6352_ptp_clock_read, .ptp_enable = mv88e6352_ptp_enable, .ptp_verify = mv88e6352_ptp_verify, @@ -331,22 +373,37 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = { (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), + .cc_shift = MV88E6250_CC_SHIFT, + .cc_mult = MV88E6250_CC_MULT, + .cc_mult_num = MV88E6250_CC_MULT_NUM, + .cc_mult_dem = MV88E6250_CC_MULT_DEM, }; -const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = { - .clock_read = mv88e6165_ptp_clock_read, - .global_enable = mv88e6165_global_enable, - .global_disable = mv88e6165_global_disable, - .arr0_sts_reg = MV88E6165_PORT_PTP_ARR0_STS, - .arr1_sts_reg = MV88E6165_PORT_PTP_ARR1_STS, - .dep_sts_reg = MV88E6165_PORT_PTP_DEP_STS, +const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = { + .clock_read = mv88e6352_ptp_clock_read, + .ptp_enable = mv88e6352_ptp_enable, + .ptp_verify = mv88e6352_ptp_verify, + .event_work = mv88e6352_tai_event_work, + .port_enable = mv88e6352_hwtstamp_port_enable, + .port_disable = mv88e6352_hwtstamp_port_disable, + .n_ext_ts = 1, + .arr0_sts_reg = MV88E6XXX_PORT_PTP_ARR0_STS, + .arr1_sts_reg = MV88E6XXX_PORT_PTP_ARR1_STS, + .dep_sts_reg = MV88E6XXX_PORT_PTP_DEP_STS, .rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ), + .cc_shift = MV88E6XXX_CC_SHIFT, + .cc_mult = MV88E6XXX_CC_MULT, + .cc_mult_num = MV88E6XXX_CC_MULT_NUM, + .cc_mult_dem = MV88E6XXX_CC_MULT_DEM, }; static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc) @@ -384,8 +441,8 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) memset(&chip->tstamp_cc, 0, sizeof(chip->tstamp_cc)); chip->tstamp_cc.read = mv88e6xxx_ptp_clock_read; chip->tstamp_cc.mask = CYCLECOUNTER_MASK(32); - chip->tstamp_cc.mult = CC_MULT; - chip->tstamp_cc.shift = CC_SHIFT; + chip->tstamp_cc.mult = ptp_ops->cc_mult; + chip->tstamp_cc.shift = ptp_ops->cc_shift; timecounter_init(&chip->tstamp_tc, &chip->tstamp_cc, ktime_to_ns(ktime_get_real())); @@ -397,7 +454,6 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) chip->ptp_clock_info.owner = THIS_MODULE; snprintf(chip->ptp_clock_info.name, sizeof(chip->ptp_clock_info.name), "%s", dev_name(chip->dev)); - chip->ptp_clock_info.max_adj = 1000000; chip->ptp_clock_info.n_ext_ts = ptp_ops->n_ext_ts; chip->ptp_clock_info.n_per_out = 0; @@ -413,6 +469,7 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip) } chip->ptp_clock_info.pin_config = chip->pin_config; + chip->ptp_clock_info.max_adj = MV88E6XXX_MAX_ADJ_PPB; chip->ptp_clock_info.adjfine = mv88e6xxx_ptp_adjfine; chip->ptp_clock_info.adjtime = mv88e6xxx_ptp_adjtime; chip->ptp_clock_info.gettime64 = mv88e6xxx_ptp_gettime; diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h index 0a1f8de8f062..269d5d16a466 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.h +++ b/drivers/net/dsa/mv88e6xxx/ptp.h @@ -148,8 +148,9 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip); #define ptp_to_chip(ptp) container_of(ptp, struct mv88e6xxx_chip, \ ptp_clock_info) -extern const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops; extern const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops; +extern const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops; +extern const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops; #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */ @@ -167,8 +168,9 @@ static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip) { } -static const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {}; static const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {}; +static const struct mv88e6xxx_ptp_ops mv88e6250_ptp_ops = {}; +static const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {}; #endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */ diff --git a/drivers/net/dsa/mv88e6xxx/smi.c b/drivers/net/dsa/mv88e6xxx/smi.c index 5fc78a063843..282fe08db050 100644 --- a/drivers/net/dsa/mv88e6xxx/smi.c +++ b/drivers/net/dsa/mv88e6xxx/smi.c @@ -64,8 +64,10 @@ static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, if (err) return err; - if (!!(data >> bit) == !!val) + if (!!(data & BIT(bit)) == !!val) return 0; + + usleep_range(1000, 2000); } return -ETIMEDOUT; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 147051404194..8785c2ff3825 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -847,8 +847,7 @@ static void poll_vortex(struct net_device *dev) static int vortex_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *ndev = pci_get_drvdata(pdev); + struct net_device *ndev = dev_get_drvdata(dev); if (!ndev || !netif_running(ndev)) return 0; @@ -861,8 +860,7 @@ static int vortex_suspend(struct device *dev) static int vortex_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *ndev = pci_get_drvdata(pdev); + struct net_device *ndev = dev_get_drvdata(dev); int err; if (!ndev || !netif_running(ndev)) @@ -2175,7 +2173,7 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev) dma_addr = skb_frag_dma_map(vp->gendev, frag, 0, - frag->size, + skb_frag_size(frag), DMA_TO_DEVICE); if (dma_mapping_error(vp->gendev, dma_addr)) { for(i = i-1; i >= 0; i--) diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 010a2f48aea5..2a9f8643629c 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -110,7 +110,7 @@ static void greth_print_tx_packet(struct sk_buff *skb) print_hex_dump(KERN_DEBUG, "TX: ", DUMP_PREFIX_OFFSET, 16, 1, skb_frag_address(&skb_shinfo(skb)->frags[i]), - skb_shinfo(skb)->frags[i].size, true); + skb_frag_size(&skb_shinfo(skb)->frags[i]), true); } } diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index edbb4b3604c7..174344c450af 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2426,7 +2426,7 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) u32 thiscopy, remainder; struct sk_buff *skb = tcb->skb; u32 nr_frags = skb_shinfo(skb)->nr_frags + 1; - struct skb_frag_struct *frags = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frags = &skb_shinfo(skb)->frags[0]; struct phy_device *phydev = adapter->netdev->phydev; dma_addr_t dma_addr; struct tx_ring *tx_ring = &adapter->tx_ring; @@ -2488,11 +2488,11 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) frag++; } } else { - desc[frag].len_vlan = frags[i - 1].size; + desc[frag].len_vlan = skb_frag_size(&frags[i - 1]); dma_addr = skb_frag_dma_map(&adapter->pdev->dev, &frags[i - 1], 0, - frags[i - 1].size, + desc[frag].len_vlan, DMA_TO_DEVICE); desc[frag].addr_lo = lower_32_bits(dma_addr); desc[frag].addr_hi = upper_32_bits(dma_addr); diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 650d1bae5f56..1793950f0582 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -1100,7 +1100,6 @@ static int au1000_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "failed to retrieve IRQ\n"); err = -ENODEV; goto out; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index b91143947ed2..b0a6c96b6ef4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -438,7 +438,6 @@ static const struct file_operations xi2c_reg_value_fops = { void xgbe_debugfs_init(struct xgbe_prv_data *pdata) { - struct dentry *pfile; char *buf; /* Set defaults */ @@ -451,88 +450,48 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata) return; pdata->xgbe_debugfs = debugfs_create_dir(buf, NULL); - if (!pdata->xgbe_debugfs) { - netdev_err(pdata->netdev, "debugfs_create_dir failed\n"); - kfree(buf); - return; - } - pfile = debugfs_create_file("xgmac_register", 0600, - pdata->xgbe_debugfs, pdata, - &xgmac_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xgmac_register", 0600, pdata->xgbe_debugfs, pdata, + &xgmac_reg_addr_fops); - pfile = debugfs_create_file("xgmac_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xgmac_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xgmac_register_value", 0600, pdata->xgbe_debugfs, + pdata, &xgmac_reg_value_fops); - pfile = debugfs_create_file("xpcs_mmd", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_mmd_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_mmd", 0600, pdata->xgbe_debugfs, pdata, + &xpcs_mmd_fops); - pfile = debugfs_create_file("xpcs_register", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_register", 0600, pdata->xgbe_debugfs, pdata, + &xpcs_reg_addr_fops); - pfile = debugfs_create_file("xpcs_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_register_value", 0600, pdata->xgbe_debugfs, + pdata, &xpcs_reg_value_fops); if (pdata->xprop_regs) { - pfile = debugfs_create_file("xprop_register", 0600, - pdata->xgbe_debugfs, pdata, - &xprop_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); - - pfile = debugfs_create_file("xprop_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xprop_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); + debugfs_create_file("xprop_register", 0600, pdata->xgbe_debugfs, + pdata, &xprop_reg_addr_fops); + + debugfs_create_file("xprop_register_value", 0600, + pdata->xgbe_debugfs, pdata, + &xprop_reg_value_fops); } if (pdata->xi2c_regs) { - pfile = debugfs_create_file("xi2c_register", 0600, - pdata->xgbe_debugfs, pdata, - &xi2c_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); - - pfile = debugfs_create_file("xi2c_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xi2c_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); + debugfs_create_file("xi2c_register", 0600, pdata->xgbe_debugfs, + pdata, &xi2c_reg_addr_fops); + + debugfs_create_file("xi2c_register_value", 0600, + pdata->xgbe_debugfs, pdata, + &xi2c_reg_value_fops); } if (pdata->vdata->an_cdr_workaround) { - pfile = debugfs_create_bool("an_cdr_workaround", 0600, - pdata->xgbe_debugfs, - &pdata->debugfs_an_cdr_workaround); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_bool failed\n"); - - pfile = debugfs_create_bool("an_cdr_track_early", 0600, - pdata->xgbe_debugfs, - &pdata->debugfs_an_cdr_track_early); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_bool failed\n"); + debugfs_create_bool("an_cdr_workaround", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_workaround); + + debugfs_create_bool("an_cdr_track_early", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_track_early); } kfree(buf); @@ -546,7 +505,6 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) { - struct dentry *pfile; char *buf; if (!pdata->xgbe_debugfs) @@ -559,11 +517,8 @@ void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf)) goto out; - pfile = debugfs_rename(pdata->xgbe_debugfs->d_parent, - pdata->xgbe_debugfs, - pdata->xgbe_debugfs->d_parent, buf); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_rename failed\n"); + debugfs_rename(pdata->xgbe_debugfs->d_parent, pdata->xgbe_debugfs, + pdata->xgbe_debugfs->d_parent, buf); out: kfree(buf); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c index 533094233659..230726d7b74f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c @@ -526,7 +526,7 @@ static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb) struct xgbe_ring *ring = channel->tx_ring; struct xgbe_ring_data *rdata; struct xgbe_packet_data *packet; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t skb_dma; unsigned int start_index, cur_index; unsigned int offset, tso, vlan, datalen, len; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 3dd0cecddba8..98f8f2033154 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1833,7 +1833,7 @@ static void xgbe_packet_info(struct xgbe_prv_data *pdata, struct xgbe_ring *ring, struct sk_buff *skb, struct xgbe_packet_data *packet) { - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int context_desc; unsigned int len; unsigned int i; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c index d0f3dfb88202..dce9e59e8881 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c @@ -467,10 +467,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) /* Get the device interrupt */ ret = platform_get_irq(pdev, 0); - if (ret < 0) { - dev_err(dev, "platform_get_irq 0 failed\n"); + if (ret < 0) goto err_io; - } pdata->dev_irq = ret; /* Get the per channel DMA interrupts */ @@ -479,12 +477,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) for (i = 0; (i < max) && (dma_irqnum < dma_irqend); i++) { ret = platform_get_irq(pdata->platdev, dma_irqnum++); - if (ret < 0) { - netdev_err(pdata->netdev, - "platform_get_irq %u failed\n", - dma_irqnum - 1); + if (ret < 0) goto err_io; - } pdata->channel_irq[i] = ret; } @@ -496,10 +490,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) /* Get the auto-negotiation interrupt */ ret = platform_get_irq(phy_pdev, phy_irqnum++); - if (ret < 0) { - dev_err(dev, "platform_get_irq phy 0 failed\n"); + if (ret < 0) goto err_io; - } pdata->an_irq = ret; /* Configure the netdev resource */ diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index 79048cc46703..02b4f3af02b5 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -54,10 +54,8 @@ static int xge_get_resources(struct xge_pdata *pdata) } ret = platform_get_irq(pdev, 0); - if (ret < 0) { - dev_err(dev, "Unable to get irq\n"); + if (ret < 0) return ret; - } pdata->resources.irq = ret; return 0; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 61a465097cb8..5f657879134e 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -712,11 +712,11 @@ static int xgene_enet_reset(struct xgene_enet_pdata *pdata) udelay(5); } else { #ifdef CONFIG_ACPI - if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), "_RST")) { - acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), - "_RST", NULL, NULL); - } else if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), - "_INI")) { + acpi_status status; + + status = acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), + "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), "_INI", NULL, NULL); } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 10b1c053e70a..d8612131c55e 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -340,7 +340,8 @@ static int xgene_enet_work_msg(struct sk_buff *skb, u64 *hopinfo) nr_frags = skb_shinfo(skb)->nr_frags; for (i = 0; i < 2 && i < nr_frags; i++) - len += skb_shinfo(skb)->frags[i].size; + len += skb_frag_size( + &skb_shinfo(skb)->frags[i]); /* HW requires header must reside in 3 buffer */ if (unlikely(hdr_len > len)) { @@ -1616,7 +1617,6 @@ static int xgene_get_rx_delay(struct xgene_enet_pdata *pdata) static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata) { struct platform_device *pdev = pdata->pdev; - struct device *dev = &pdev->dev; int i, ret, max_irqs; if (phy_interface_mode_is_rgmii(pdata->phy_mode)) @@ -1636,9 +1636,7 @@ static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata) pdata->cq_cnt = max_irqs / 2; break; } - dev_err(dev, "Unable to get ENET IRQ\n"); - ret = ret ? : -ENXIO; - return ret; + return ret ? : -ENXIO; } pdata->irqs[i] = ret; } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c index 6453fc2ebb1f..f482ced2cadd 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c @@ -460,12 +460,14 @@ static int xgene_enet_reset(struct xgene_enet_pdata *p) } } else { #ifdef CONFIG_ACPI - if (acpi_has_method(ACPI_HANDLE(&p->pdev->dev), "_RST")) - acpi_evaluate_object(ACPI_HANDLE(&p->pdev->dev), - "_RST", NULL, NULL); - else if (acpi_has_method(ACPI_HANDLE(&p->pdev->dev), "_INI")) + acpi_status status; + + status = acpi_evaluate_object(ACPI_HANDLE(&p->pdev->dev), + "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { acpi_evaluate_object(ACPI_HANDLE(&p->pdev->dev), "_INI", NULL, NULL); + } #endif } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c index 133eb91c542e..304b5d43f236 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c @@ -393,11 +393,11 @@ static int xgene_enet_reset(struct xgene_enet_pdata *pdata) udelay(5); } else { #ifdef CONFIG_ACPI - if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), "_RST")) { - acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), - "_RST", NULL, NULL); - } else if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), - "_INI")) { + acpi_status status; + + status = acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), + "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), "_INI", NULL, NULL); } diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index c40daad515d5..a58185b1d8bf 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -815,8 +815,8 @@ static int reverse6[64] = { static unsigned int crc416(unsigned int curval, unsigned short nxtval) { - register unsigned int counter, cur = curval, next = nxtval; - register int high_crc_set, low_data_set; + unsigned int counter, cur = curval, next = nxtval; + int high_crc_set, low_data_set; /* Swap bytes */ next = ((next & 0x00FF) << 8) | (next >> 8); diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 6703960c7cf5..7548247455d7 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1148,7 +1148,7 @@ static int ag71xx_rings_init(struct ag71xx *ag) return -ENOMEM; } - rx->buf = &tx->buf[BIT(tx->order)]; + rx->buf = &tx->buf[tx_size]; rx->descs_cpu = ((void *)tx->descs_cpu) + tx_size * AG71XX_DESC_SIZE; rx->descs_dma = tx->descs_dma + tx_size * AG71XX_DESC_SIZE; @@ -1686,7 +1686,7 @@ static int ag71xx_probe(struct platform_device *pdev) } ag->mac_base = devm_ioremap_nocache(&pdev->dev, res->start, - res->end - res->start + 1); + resource_size(res)); if (!ag->mac_base) { err = -ENOMEM; goto err_free; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index e3538ba7d0e7..d4bbcdfd691a 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1465,9 +1465,7 @@ static int alx_map_tx_skb(struct alx_tx_queue *txq, struct sk_buff *skb) tpd->len = cpu_to_le16(maplen); for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { - struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[f]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; if (++txq->write_idx == txq->count) txq->write_idx = 0; @@ -1879,8 +1877,7 @@ static void alx_remove(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int alx_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct alx_priv *alx = pci_get_drvdata(pdev); + struct alx_priv *alx = dev_get_drvdata(dev); if (!netif_running(alx->dev)) return 0; @@ -1891,8 +1888,7 @@ static int alx_suspend(struct device *dev) static int alx_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct alx_priv *alx = pci_get_drvdata(pdev); + struct alx_priv *alx = dev_get_drvdata(dev); struct alx_hw *hw = &alx->hw; int err; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index be7f9cebb675..2b239ecea05f 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2150,9 +2150,7 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, } for (f = 0; f < nr_frags; f++) { - struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[f]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; use_tpd = atl1c_get_tpd(adapter, type); memcpy(use_tpd, tpd, sizeof(struct atl1c_tpd_desc)); @@ -2422,8 +2420,7 @@ static int atl1c_close(struct net_device *netdev) static int atl1c_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1c_adapter *adapter = netdev_priv(netdev); struct atl1c_hw *hw = &adapter->hw; u32 wufc = adapter->wol; @@ -2437,7 +2434,7 @@ static int atl1c_suspend(struct device *dev) if (wufc) if (atl1c_phy_to_ps_link(hw) != 0) - dev_dbg(&pdev->dev, "phy power saving failed"); + dev_dbg(dev, "phy power saving failed"); atl1c_power_saving(hw, wufc); @@ -2447,8 +2444,7 @@ static int atl1c_suspend(struct device *dev) #ifdef CONFIG_PM_SLEEP static int atl1c_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1c_adapter *adapter = netdev_priv(netdev); AT_WRITE_REG(&adapter->hw, REG_WOL_CTRL, 0); diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 7f14e010bfeb..4f7b65825c15 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -1770,11 +1770,10 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; u16 i; u16 seg_num; - frag = &skb_shinfo(skb)->frags[f]; buf_len = skb_frag_size(frag); seg_num = (buf_len + MAX_TX_BUF_LEN - 1) / MAX_TX_BUF_LEN; diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b5c6dc914720..b498fd6a47d0 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -2256,10 +2256,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; u16 i, nseg; - frag = &skb_shinfo(skb)->frags[f]; buf_len = skb_frag_size(frag); nseg = (buf_len + ATL1_MAX_TX_BUF_LEN - 1) / @@ -2754,8 +2753,7 @@ static int atl1_close(struct net_device *netdev) #ifdef CONFIG_PM_SLEEP static int atl1_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1_adapter *adapter = netdev_priv(netdev); struct atl1_hw *hw = &adapter->hw; u32 ctrl = 0; @@ -2780,7 +2778,7 @@ static int atl1_suspend(struct device *dev) val = atl1_get_speed_and_duplex(hw, &speed, &duplex); if (val) { if (netif_msg_ifdown(adapter)) - dev_printk(KERN_DEBUG, &pdev->dev, + dev_printk(KERN_DEBUG, dev, "error getting speed/duplex\n"); goto disable_wol; } @@ -2837,8 +2835,7 @@ static int atl1_suspend(struct device *dev) static int atl1_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1_adapter *adapter = netdev_priv(netdev); iowrite32(0, adapter->hw.hw_addr + REG_WOL_CTRL); diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 3b3370a94a9c..37752d9514e7 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1351,10 +1351,8 @@ static int nb8800_probe(struct platform_device *pdev) ops = match->data; irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(&pdev->dev, "No IRQ\n"); + if (irq <= 0) return -EINVAL; - } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); base = devm_ioremap_resource(&pdev->dev, res); diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 291e4afd4a1a..620cd3fc1fbc 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1693,7 +1693,7 @@ static int bcm_enet_probe(struct platform_device *pdev) struct bcm_enet_priv *priv; struct net_device *dev; struct bcm63xx_enet_platform_data *pd; - struct resource *res_mem, *res_irq, *res_irq_rx, *res_irq_tx; + struct resource *res_irq, *res_irq_rx, *res_irq_tx; struct mii_bus *bus; int i, ret; @@ -1719,8 +1719,7 @@ static int bcm_enet_probe(struct platform_device *pdev) if (ret) goto out; - res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(&pdev->dev, res_mem); + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { ret = PTR_ERR(priv->base); goto out; @@ -2762,15 +2761,13 @@ struct platform_driver bcm63xx_enetsw_driver = { /* reserve & remap memory space shared between all macs */ static int bcm_enet_shared_probe(struct platform_device *pdev) { - struct resource *res; void __iomem *p[3]; unsigned int i; memset(bcm_enet_shared_base, 0, sizeof(bcm_enet_shared_base)); for (i = 0; i < 3; i++) { - res = platform_get_resource(pdev, IORESOURCE_MEM, i); - p[i] = devm_ioremap_resource(&pdev->dev, res); + p[i] = devm_platform_ioremap_resource(pdev, i); if (IS_ERR(p[i])) return PTR_ERR(p[i]); } diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 6dc0dd91ad11..c46c1b1416f7 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -199,10 +199,8 @@ static int bgmac_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "MAC address not present in device tree\n"); bgmac->irq = platform_get_irq(pdev, 0); - if (bgmac->irq < 0) { - dev_err(&pdev->dev, "Unable to obtain IRQ\n"); + if (bgmac->irq < 0) return bgmac->irq; - } regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "amac_base"); if (!regs) { diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 4632dd5dbad1..148734b166f0 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -172,7 +172,7 @@ static netdev_tx_t bgmac_dma_tx_add(struct bgmac *bgmac, flags = 0; for (i = 0; i < nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int len = skb_frag_size(frag); index = (index + 1) % BGMAC_TX_RING_SLOTS; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index dfdd14eadd57..fbc196b480b6 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8673,8 +8673,7 @@ bnx2_remove_one(struct pci_dev *pdev) static int bnx2_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnx2 *bp = netdev_priv(dev); if (netif_running(dev)) { @@ -8693,8 +8692,7 @@ bnx2_suspend(struct device *device) static int bnx2_resume(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnx2 *bp = netdev_priv(dev); if (!netif_running(dev)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8dce4069472b..4c790ffa1a73 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -116,6 +116,9 @@ enum board_idx { BCM57508, BCM57504, BCM57502, + BCM57508_NPAR, + BCM57504_NPAR, + BCM57502_NPAR, BCM58802, BCM58804, BCM58808, @@ -161,6 +164,9 @@ static const struct { [BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" }, [BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" }, [BCM57502] = { "Broadcom BCM57502 NetXtreme-E 10Gb/25Gb/50Gb Ethernet" }, + [BCM57508_NPAR] = { "Broadcom BCM57508 NetXtreme-E Ethernet Partition" }, + [BCM57504_NPAR] = { "Broadcom BCM57504 NetXtreme-E Ethernet Partition" }, + [BCM57502_NPAR] = { "Broadcom BCM57502 NetXtreme-E Ethernet Partition" }, [BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" }, [BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, [BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, @@ -209,6 +215,12 @@ static const struct pci_device_id bnxt_pci_tbl[] = { { PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 }, { PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 }, { PCI_VDEVICE(BROADCOM, 0x1752), .driver_data = BCM57502 }, + { PCI_VDEVICE(BROADCOM, 0x1800), .driver_data = BCM57508_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1801), .driver_data = BCM57504_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1802), .driver_data = BCM57502_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1803), .driver_data = BCM57508_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1804), .driver_data = BCM57504_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1805), .driver_data = BCM57502_NPAR }, { PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 }, { PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 }, #ifdef CONFIG_BNXT_SRIOV @@ -828,16 +840,41 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, return 0; } -static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 cp_cons, - u32 agg_bufs) +static struct rx_agg_cmp *bnxt_get_agg(struct bnxt *bp, + struct bnxt_cp_ring_info *cpr, + u16 cp_cons, u16 curr) +{ + struct rx_agg_cmp *agg; + + cp_cons = RING_CMP(ADV_RAW_CMP(cp_cons, curr)); + agg = (struct rx_agg_cmp *) + &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + return agg; +} + +static struct rx_agg_cmp *bnxt_get_tpa_agg_p5(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + u16 agg_id, u16 curr) +{ + struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[agg_id]; + + return &tpa_info->agg_arr[curr]; +} + +static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx, + u16 start, u32 agg_bufs, bool tpa) { struct bnxt_napi *bnapi = cpr->bnapi; struct bnxt *bp = bnapi->bp; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u16 prod = rxr->rx_agg_prod; u16 sw_prod = rxr->rx_sw_agg_prod; + bool p5_tpa = false; u32 i; + if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa) + p5_tpa = true; + for (i = 0; i < agg_bufs; i++) { u16 cons; struct rx_agg_cmp *agg; @@ -845,8 +882,10 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 cp_cons, struct rx_bd *prod_bd; struct page *page; - agg = (struct rx_agg_cmp *) - &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + if (p5_tpa) + agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i); + else + agg = bnxt_get_agg(bp, cpr, idx, start + i); cons = agg->rx_agg_cmp_opaque; __clear_bit(cons, rxr->rx_agg_bmap); @@ -874,7 +913,6 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 cp_cons, prod = NEXT_RX_AGG(prod); sw_prod = NEXT_RX_AGG(sw_prod); - cp_cons = NEXT_CMP(cp_cons); } rxr->rx_agg_prod = prod; rxr->rx_sw_agg_prod = sw_prod; @@ -888,7 +926,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, { unsigned int payload = offset_and_len >> 16; unsigned int len = offset_and_len & 0xffff; - struct skb_frag_struct *frag; + skb_frag_t *frag; struct page *page = data; u16 prod = rxr->rx_prod; struct sk_buff *skb; @@ -919,7 +957,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, frag = &skb_shinfo(skb)->frags[0]; skb_frag_size_sub(frag, payload); - frag->page_offset += payload; + skb_frag_off_add(frag, payload); skb->data_len -= payload; skb->tail += payload; @@ -957,15 +995,19 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp, static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, - struct sk_buff *skb, u16 cp_cons, - u32 agg_bufs) + struct sk_buff *skb, u16 idx, + u32 agg_bufs, bool tpa) { struct bnxt_napi *bnapi = cpr->bnapi; struct pci_dev *pdev = bp->pdev; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u16 prod = rxr->rx_agg_prod; + bool p5_tpa = false; u32 i; + if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa) + p5_tpa = true; + for (i = 0; i < agg_bufs; i++) { u16 cons, frag_len; struct rx_agg_cmp *agg; @@ -973,8 +1015,10 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct page *page; dma_addr_t mapping; - agg = (struct rx_agg_cmp *) - &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + if (p5_tpa) + agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, i); + else + agg = bnxt_get_agg(bp, cpr, idx, i); cons = agg->rx_agg_cmp_opaque; frag_len = (le32_to_cpu(agg->rx_agg_cmp_len_flags_type) & RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT; @@ -1008,7 +1052,7 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, * allocated already. */ rxr->rx_agg_prod = prod; - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs - i); + bnxt_reuse_rx_agg_bufs(cpr, idx, i, agg_bufs - i, tpa); return NULL; } @@ -1021,7 +1065,6 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, skb->truesize += PAGE_SIZE; prod = NEXT_RX_AGG(prod); - cp_cons = NEXT_CMP(cp_cons); } rxr->rx_agg_prod = prod; return skb; @@ -1081,9 +1124,10 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) { struct rx_tpa_end_cmp *tpa_end = cmp; - agg_bufs = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) & - RX_TPA_END_CMP_AGG_BUFS) >> - RX_TPA_END_CMP_AGG_BUFS_SHIFT; + if (bp->flags & BNXT_FLAG_CHIP_P5) + return 0; + + agg_bufs = TPA_END_AGG_BUFS(tpa_end); } if (agg_bufs) { @@ -1120,26 +1164,60 @@ static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) rxr->rx_next_cons = 0xffff; } +static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) +{ + struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; + u16 idx = agg_id & MAX_TPA_P5_MASK; + + if (test_bit(idx, map->agg_idx_bmap)) + idx = find_first_zero_bit(map->agg_idx_bmap, + BNXT_AGG_IDX_BMAP_SIZE); + __set_bit(idx, map->agg_idx_bmap); + map->agg_id_tbl[agg_id] = idx; + return idx; +} + +static void bnxt_free_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx) +{ + struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; + + __clear_bit(idx, map->agg_idx_bmap); +} + +static u16 bnxt_lookup_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) +{ + struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; + + return map->agg_id_tbl[agg_id]; +} + static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, struct rx_tpa_start_cmp *tpa_start, struct rx_tpa_start_cmp_ext *tpa_start1) { - u8 agg_id = TPA_START_AGG_ID(tpa_start); - u16 cons, prod; - struct bnxt_tpa_info *tpa_info; struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf; + struct bnxt_tpa_info *tpa_info; + u16 cons, prod, agg_id; struct rx_bd *prod_bd; dma_addr_t mapping; + if (bp->flags & BNXT_FLAG_CHIP_P5) { + agg_id = TPA_START_AGG_ID_P5(tpa_start); + agg_id = bnxt_alloc_agg_idx(rxr, agg_id); + } else { + agg_id = TPA_START_AGG_ID(tpa_start); + } cons = tpa_start->rx_tpa_start_cmp_opaque; prod = rxr->rx_prod; cons_rx_buf = &rxr->rx_buf_ring[cons]; prod_rx_buf = &rxr->rx_buf_ring[prod]; tpa_info = &rxr->rx_tpa[agg_id]; - if (unlikely(cons != rxr->rx_next_cons)) { - netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n", - cons, rxr->rx_next_cons); + if (unlikely(cons != rxr->rx_next_cons || + TPA_START_ERROR(tpa_start))) { + netdev_warn(bp->dev, "TPA cons %x, expected cons %x, error code %x\n", + cons, rxr->rx_next_cons, + TPA_START_ERROR_CODE(tpa_start1)); bnxt_sched_reset(bp, rxr); return; } @@ -1184,6 +1262,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2); tpa_info->metadata = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata); tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info); + tpa_info->agg_count = 0; rxr->rx_prod = NEXT_RX(prod); cons = NEXT_RX(cons); @@ -1195,13 +1274,37 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, cons_rx_buf->data = NULL; } -static void bnxt_abort_tpa(struct bnxt_cp_ring_info *cpr, u16 cp_cons, - u32 agg_bufs) +static void bnxt_abort_tpa(struct bnxt_cp_ring_info *cpr, u16 idx, u32 agg_bufs) { if (agg_bufs) - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs); + bnxt_reuse_rx_agg_bufs(cpr, idx, 0, agg_bufs, true); } +#ifdef CONFIG_INET +static void bnxt_gro_tunnel(struct sk_buff *skb, __be16 ip_proto) +{ + struct udphdr *uh = NULL; + + if (ip_proto == htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)skb->data; + + if (iph->protocol == IPPROTO_UDP) + uh = (struct udphdr *)(iph + 1); + } else { + struct ipv6hdr *iph = (struct ipv6hdr *)skb->data; + + if (iph->nexthdr == IPPROTO_UDP) + uh = (struct udphdr *)(iph + 1); + } + if (uh) { + if (uh->check) + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + else + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; + } +} +#endif + static struct sk_buff *bnxt_gro_func_5731x(struct bnxt_tpa_info *tpa_info, int payload_off, int tcp_ts, struct sk_buff *skb) @@ -1259,28 +1362,39 @@ static struct sk_buff *bnxt_gro_func_5731x(struct bnxt_tpa_info *tpa_info, } if (inner_mac_off) { /* tunnel */ - struct udphdr *uh = NULL; __be16 proto = *((__be16 *)(skb->data + outer_ip_off - ETH_HLEN - 2)); - if (proto == htons(ETH_P_IP)) { - struct iphdr *iph = (struct iphdr *)skb->data; + bnxt_gro_tunnel(skb, proto); + } +#endif + return skb; +} - if (iph->protocol == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } else { - struct ipv6hdr *iph = (struct ipv6hdr *)skb->data; +static struct sk_buff *bnxt_gro_func_5750x(struct bnxt_tpa_info *tpa_info, + int payload_off, int tcp_ts, + struct sk_buff *skb) +{ +#ifdef CONFIG_INET + u16 outer_ip_off, inner_ip_off, inner_mac_off; + u32 hdr_info = tpa_info->hdr_info; + int iphdr_len, nw_off; - if (iph->nexthdr == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } - if (uh) { - if (uh->check) - skb_shinfo(skb)->gso_type |= - SKB_GSO_UDP_TUNNEL_CSUM; - else - skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; - } + inner_ip_off = BNXT_TPA_INNER_L3_OFF(hdr_info); + inner_mac_off = BNXT_TPA_INNER_L2_OFF(hdr_info); + outer_ip_off = BNXT_TPA_OUTER_L3_OFF(hdr_info); + + nw_off = inner_ip_off - ETH_HLEN; + skb_set_network_header(skb, nw_off); + iphdr_len = (tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_IP_TYPE) ? + sizeof(struct ipv6hdr) : sizeof(struct iphdr); + skb_set_transport_header(skb, nw_off + iphdr_len); + + if (inner_mac_off) { /* tunnel */ + __be16 proto = *((__be16 *)(skb->data + outer_ip_off - + ETH_HLEN - 2)); + + bnxt_gro_tunnel(skb, proto); } #endif return skb; @@ -1327,28 +1441,8 @@ static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info, return NULL; } - if (nw_off) { /* tunnel */ - struct udphdr *uh = NULL; - - if (skb->protocol == htons(ETH_P_IP)) { - struct iphdr *iph = (struct iphdr *)skb->data; - - if (iph->protocol == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } else { - struct ipv6hdr *iph = (struct ipv6hdr *)skb->data; - - if (iph->nexthdr == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } - if (uh) { - if (uh->check) - skb_shinfo(skb)->gso_type |= - SKB_GSO_UDP_TUNNEL_CSUM; - else - skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; - } - } + if (nw_off) /* tunnel */ + bnxt_gro_tunnel(skb, skb->protocol); #endif return skb; } @@ -1371,9 +1465,10 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp, skb_shinfo(skb)->gso_size = le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len); skb_shinfo(skb)->gso_type = tpa_info->gso_type; - payload_off = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) & - RX_TPA_END_CMP_PAYLOAD_OFFSET) >> - RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT; + if (bp->flags & BNXT_FLAG_CHIP_P5) + payload_off = TPA_END_PAYLOAD_OFF_P5(tpa_end1); + else + payload_off = TPA_END_PAYLOAD_OFF(tpa_end); skb = bp->gro_func(tpa_info, payload_off, TPA_END_GRO_TS(tpa_end), skb); if (likely(skb)) tcp_gro_complete(skb); @@ -1401,14 +1496,14 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, { struct bnxt_napi *bnapi = cpr->bnapi; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; - u8 agg_id = TPA_END_AGG_ID(tpa_end); u8 *data_ptr, agg_bufs; - u16 cp_cons = RING_CMP(*raw_cons); unsigned int len; struct bnxt_tpa_info *tpa_info; dma_addr_t mapping; struct sk_buff *skb; + u16 idx = 0, agg_id; void *data; + bool gro; if (unlikely(bnapi->in_reset)) { int rc = bnxt_discard_rx(bp, cpr, raw_cons, tpa_end); @@ -1418,26 +1513,43 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, return NULL; } - tpa_info = &rxr->rx_tpa[agg_id]; + if (bp->flags & BNXT_FLAG_CHIP_P5) { + agg_id = TPA_END_AGG_ID_P5(tpa_end); + agg_id = bnxt_lookup_agg_idx(rxr, agg_id); + agg_bufs = TPA_END_AGG_BUFS_P5(tpa_end1); + tpa_info = &rxr->rx_tpa[agg_id]; + if (unlikely(agg_bufs != tpa_info->agg_count)) { + netdev_warn(bp->dev, "TPA end agg_buf %d != expected agg_bufs %d\n", + agg_bufs, tpa_info->agg_count); + agg_bufs = tpa_info->agg_count; + } + tpa_info->agg_count = 0; + *event |= BNXT_AGG_EVENT; + bnxt_free_agg_idx(rxr, agg_id); + idx = agg_id; + gro = !!(bp->flags & BNXT_FLAG_GRO); + } else { + agg_id = TPA_END_AGG_ID(tpa_end); + agg_bufs = TPA_END_AGG_BUFS(tpa_end); + tpa_info = &rxr->rx_tpa[agg_id]; + idx = RING_CMP(*raw_cons); + if (agg_bufs) { + if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, raw_cons)) + return ERR_PTR(-EBUSY); + + *event |= BNXT_AGG_EVENT; + idx = NEXT_CMP(idx); + } + gro = !!TPA_END_GRO(tpa_end); + } data = tpa_info->data; data_ptr = tpa_info->data_ptr; prefetch(data_ptr); len = tpa_info->len; mapping = tpa_info->mapping; - agg_bufs = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) & - RX_TPA_END_CMP_AGG_BUFS) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT; - - if (agg_bufs) { - if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, raw_cons)) - return ERR_PTR(-EBUSY); - - *event |= BNXT_AGG_EVENT; - cp_cons = NEXT_CMP(cp_cons); - } - if (unlikely(agg_bufs > MAX_SKB_FRAGS || TPA_END_ERRORS(tpa_end1))) { - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); if (agg_bufs > MAX_SKB_FRAGS) netdev_warn(bp->dev, "TPA frags %d exceeded MAX_SKB_FRAGS %d\n", agg_bufs, (int)MAX_SKB_FRAGS); @@ -1447,7 +1559,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, if (len <= bp->rx_copy_thresh) { skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping); if (!skb) { - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); return NULL; } } else { @@ -1456,7 +1568,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, new_data = __bnxt_alloc_rx_data(bp, &new_mapping, GFP_ATOMIC); if (!new_data) { - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); return NULL; } @@ -1471,7 +1583,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, if (!skb) { kfree(data); - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); return NULL; } skb_reserve(skb, bp->rx_offset); @@ -1479,7 +1591,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, } if (agg_bufs) { - skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs); + skb = bnxt_rx_pages(bp, cpr, skb, idx, agg_bufs, true); if (!skb) { /* Page reuse already handled by bnxt_rx_pages(). */ return NULL; @@ -1508,12 +1620,24 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, (tpa_info->flags2 & RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3; } - if (TPA_END_GRO(tpa_end)) + if (gro) skb = bnxt_gro_skb(bp, tpa_info, tpa_end, tpa_end1, skb); return skb; } +static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, + struct rx_agg_cmp *rx_agg) +{ + u16 agg_id = TPA_AGG_AGG_ID(rx_agg); + struct bnxt_tpa_info *tpa_info; + + agg_id = bnxt_lookup_agg_idx(rxr, agg_id); + tpa_info = &rxr->rx_tpa[agg_id]; + BUG_ON(tpa_info->agg_count >= MAX_SKB_FRAGS); + tpa_info->agg_arr[tpa_info->agg_count++] = *rx_agg; +} + static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi, struct sk_buff *skb) { @@ -1555,6 +1679,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, rxcmp = (struct rx_cmp *) &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + cmp_type = RX_CMP_TYPE(rxcmp); + + if (cmp_type == CMP_TYPE_RX_TPA_AGG_CMP) { + bnxt_tpa_agg(bp, rxr, (struct rx_agg_cmp *)rxcmp); + goto next_rx_no_prod_no_len; + } + tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons); cp_cons = RING_CMP(tmp_raw_cons); rxcmp1 = (struct rx_cmp_ext *) @@ -1563,8 +1694,6 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons)) return -EBUSY; - cmp_type = RX_CMP_TYPE(rxcmp); - prod = rxr->rx_prod; if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP) { @@ -1623,7 +1752,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, bnxt_reuse_rx_data(rxr, cons, data); if (agg_bufs) - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs); + bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0, agg_bufs, + false); rc = -EIO; if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) { @@ -1646,7 +1776,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, bnxt_reuse_rx_data(rxr, cons, data); if (!skb) { if (agg_bufs) - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs); + bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0, + agg_bufs, false); rc = -ENOMEM; goto next_rx; } @@ -1666,7 +1797,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } if (agg_bufs) { - skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs); + skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs, false); if (!skb) { rc = -ENOMEM; goto next_rx; @@ -2325,10 +2456,11 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) max_agg_idx = bp->rx_agg_nr_pages * RX_DESC_CNT; for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_tpa_idx_map *map; int j; if (rxr->rx_tpa) { - for (j = 0; j < MAX_TPA; j++) { + for (j = 0; j < bp->max_tpa; j++) { struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[j]; u8 *data = tpa_info->data; @@ -2395,6 +2527,9 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) __free_page(rxr->rx_page); rxr->rx_page = NULL; } + map = rxr->rx_tpa_idx_map; + if (map) + memset(map->agg_idx_bmap, 0, sizeof(map->agg_idx_bmap)); } } @@ -2483,6 +2618,61 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) return 0; } +static void bnxt_free_tpa_info(struct bnxt *bp) +{ + int i; + + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + + kfree(rxr->rx_tpa_idx_map); + rxr->rx_tpa_idx_map = NULL; + if (rxr->rx_tpa) { + kfree(rxr->rx_tpa[0].agg_arr); + rxr->rx_tpa[0].agg_arr = NULL; + } + kfree(rxr->rx_tpa); + rxr->rx_tpa = NULL; + } +} + +static int bnxt_alloc_tpa_info(struct bnxt *bp) +{ + int i, j, total_aggs = 0; + + bp->max_tpa = MAX_TPA; + if (bp->flags & BNXT_FLAG_CHIP_P5) { + if (!bp->max_tpa_v2) + return 0; + bp->max_tpa = max_t(u16, bp->max_tpa_v2, MAX_TPA_P5); + total_aggs = bp->max_tpa * MAX_SKB_FRAGS; + } + + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct rx_agg_cmp *agg; + + rxr->rx_tpa = kcalloc(bp->max_tpa, sizeof(struct bnxt_tpa_info), + GFP_KERNEL); + if (!rxr->rx_tpa) + return -ENOMEM; + + if (!(bp->flags & BNXT_FLAG_CHIP_P5)) + continue; + agg = kcalloc(total_aggs, sizeof(*agg), GFP_KERNEL); + rxr->rx_tpa[0].agg_arr = agg; + if (!agg) + return -ENOMEM; + for (j = 1; j < bp->max_tpa; j++) + rxr->rx_tpa[j].agg_arr = agg + j * MAX_SKB_FRAGS; + rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map), + GFP_KERNEL); + if (!rxr->rx_tpa_idx_map) + return -ENOMEM; + } + return 0; +} + static void bnxt_free_rx_rings(struct bnxt *bp) { int i; @@ -2490,6 +2680,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp) if (!bp->rx_ring) return; + bnxt_free_tpa_info(bp); for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring; @@ -2503,9 +2694,6 @@ static void bnxt_free_rx_rings(struct bnxt *bp) page_pool_destroy(rxr->page_pool); rxr->page_pool = NULL; - kfree(rxr->rx_tpa); - rxr->rx_tpa = NULL; - kfree(rxr->rx_agg_bmap); rxr->rx_agg_bmap = NULL; @@ -2539,7 +2727,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, static int bnxt_alloc_rx_rings(struct bnxt *bp) { - int i, rc, agg_rings = 0, tpa_rings = 0; + int i, rc = 0, agg_rings = 0; if (!bp->rx_ring) return -ENOMEM; @@ -2547,9 +2735,6 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) if (bp->flags & BNXT_FLAG_AGG_RINGS) agg_rings = 1; - if (bp->flags & BNXT_FLAG_TPA) - tpa_rings = 1; - for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring; @@ -2591,17 +2776,11 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL); if (!rxr->rx_agg_bmap) return -ENOMEM; - - if (tpa_rings) { - rxr->rx_tpa = kcalloc(MAX_TPA, - sizeof(struct bnxt_tpa_info), - GFP_KERNEL); - if (!rxr->rx_tpa) - return -ENOMEM; - } } } - return 0; + if (bp->flags & BNXT_FLAG_TPA) + rc = bnxt_alloc_tpa_info(bp); + return rc; } static void bnxt_free_tx_rings(struct bnxt *bp) @@ -2953,7 +3132,7 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) u8 *data; dma_addr_t mapping; - for (i = 0; i < MAX_TPA; i++) { + for (i = 0; i < bp->max_tpa; i++) { data = __bnxt_alloc_rx_data(bp, &mapping, GFP_KERNEL); if (!data) @@ -3468,7 +3647,7 @@ static void bnxt_free_ring_stats(struct bnxt *bp) if (!bp->bnapi) return; - size = sizeof(struct ctx_hw_stats); + size = bp->hw_ring_stats_size; for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; @@ -3487,7 +3666,7 @@ static int bnxt_alloc_stats(struct bnxt *bp) u32 size, i; struct pci_dev *pdev = bp->pdev; - size = sizeof(struct ctx_hw_stats); + size = bp->hw_ring_stats_size; for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; @@ -4414,6 +4593,7 @@ static int bnxt_hwrm_clear_vnic_filter(struct bnxt *bp) static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) { struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; + u16 max_aggs = VNIC_TPA_CFG_REQ_MAX_AGGS_MAX; struct hwrm_vnic_tpa_cfg_input req = {0}; if (vnic->fw_vnic_id == INVALID_HW_RING_ID) @@ -4453,9 +4633,14 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) nsegs = (MAX_SKB_FRAGS - n) / n; } - segs = ilog2(nsegs); + if (bp->flags & BNXT_FLAG_CHIP_P5) { + segs = MAX_TPA_SEGS_P5; + max_aggs = bp->max_tpa; + } else { + segs = ilog2(nsegs); + } req.max_agg_segs = cpu_to_le16(segs); - req.max_aggs = cpu_to_le16(VNIC_TPA_CFG_REQ_MAX_AGGS_MAX); + req.max_aggs = cpu_to_le16(max_aggs); req.min_agg_len = cpu_to_le32(512); } @@ -4815,6 +5000,12 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) if (flags & VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP) bp->flags |= BNXT_FLAG_ROCE_MIRROR_CAP; + bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported); + if (bp->max_tpa_v2) + bp->hw_ring_stats_size = + sizeof(struct ctx_hw_stats_ext); + else + bp->hw_ring_stats_size = sizeof(struct ctx_hw_stats); } mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -6016,6 +6207,7 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp) bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_ALLOC, -1, -1); + req.stats_dma_length = cpu_to_le16(bp->hw_ring_stats_size); req.update_period_ms = cpu_to_le32(bp->stats_coal_ticks / 1000); mutex_lock(&bp->hwrm_cmd_lock); @@ -9306,7 +9498,8 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) if (changes & BNXT_FLAG_TPA) { update_tpa = true; if ((bp->flags & BNXT_FLAG_TPA) == 0 || - (flags & BNXT_FLAG_TPA) == 0) + (flags & BNXT_FLAG_TPA) == 0 || + (bp->flags & BNXT_FLAG_CHIP_P5)) re_init = true; } @@ -9316,9 +9509,8 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) if (flags != bp->flags) { u32 old_flags = bp->flags; - bp->flags = flags; - if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { + bp->flags = flags; if (update_tpa) bnxt_set_ring_params(bp); return rc; @@ -9326,12 +9518,14 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) if (re_init) { bnxt_close_nic(bp, false, false); + bp->flags = flags; if (update_tpa) bnxt_set_ring_params(bp); return bnxt_open_nic(bp, false, false); } if (update_tpa) { + bp->flags = flags; rc = bnxt_set_tpa(bp, (flags & BNXT_FLAG_TPA) ? true : false); @@ -9728,6 +9922,68 @@ static void bnxt_init_dflt_coal(struct bnxt *bp) bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS; } +static int bnxt_fw_init_one_p1(struct bnxt *bp) +{ + int rc; + + bp->fw_cap = 0; + rc = bnxt_hwrm_ver_get(bp); + if (rc) + return rc; + + if (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL) { + rc = bnxt_alloc_kong_hwrm_resources(bp); + if (rc) + bp->fw_cap &= ~BNXT_FW_CAP_KONG_MB_CHNL; + } + + if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) || + bp->hwrm_max_ext_req_len > BNXT_HWRM_MAX_REQ_LEN) { + rc = bnxt_alloc_hwrm_short_cmd_req(bp); + if (rc) + return rc; + } + rc = bnxt_hwrm_func_reset(bp); + if (rc) + return -ENODEV; + + bnxt_hwrm_fw_set_time(bp); + return 0; +} + +static int bnxt_fw_init_one_p2(struct bnxt *bp) +{ + int rc; + + /* Get the MAX capabilities for this function */ + rc = bnxt_hwrm_func_qcaps(bp); + if (rc) { + netdev_err(bp->dev, "hwrm query capability failure rc: %x\n", + rc); + return -ENODEV; + } + + rc = bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(bp); + if (rc) + netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n", + rc); + + rc = bnxt_hwrm_func_drv_rgtr(bp); + if (rc) + return -ENODEV; + + rc = bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0); + if (rc) + return -ENODEV; + + bnxt_hwrm_func_qcfg(bp); + bnxt_hwrm_vnic_qcaps(bp); + bnxt_hwrm_port_led_qcaps(bp); + bnxt_ethtool_init(bp); + bnxt_dcb_init(bp); + return 0; +} + static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) { int rc; @@ -10683,32 +10939,18 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto init_err_pci_clean; mutex_init(&bp->hwrm_cmd_lock); - rc = bnxt_hwrm_ver_get(bp); + + rc = bnxt_fw_init_one_p1(bp); if (rc) goto init_err_pci_clean; - if (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL) { - rc = bnxt_alloc_kong_hwrm_resources(bp); - if (rc) - bp->fw_cap &= ~BNXT_FW_CAP_KONG_MB_CHNL; - } - - if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) || - bp->hwrm_max_ext_req_len > BNXT_HWRM_MAX_REQ_LEN) { - rc = bnxt_alloc_hwrm_short_cmd_req(bp); - if (rc) - goto init_err_pci_clean; - } - if (BNXT_CHIP_P5(bp)) bp->flags |= BNXT_FLAG_CHIP_P5; - rc = bnxt_hwrm_func_reset(bp); + rc = bnxt_fw_init_one_p2(bp); if (rc) goto init_err_pci_clean; - bnxt_hwrm_fw_set_time(bp); - dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | @@ -10746,41 +10988,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bp->gro_func = bnxt_gro_func_5730x; if (BNXT_CHIP_P4(bp)) bp->gro_func = bnxt_gro_func_5731x; + else if (BNXT_CHIP_P5(bp)) + bp->gro_func = bnxt_gro_func_5750x; } if (!BNXT_CHIP_P4_PLUS(bp)) bp->flags |= BNXT_FLAG_DOUBLE_DB; - rc = bnxt_hwrm_func_drv_rgtr(bp); - if (rc) - goto init_err_pci_clean; - - rc = bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0); - if (rc) - goto init_err_pci_clean; - bp->ulp_probe = bnxt_ulp_probe; - rc = bnxt_hwrm_queue_qportcfg(bp); - if (rc) { - netdev_err(bp->dev, "hwrm query qportcfg failure rc: %x\n", - rc); - rc = -1; - goto init_err_pci_clean; - } - /* Get the MAX capabilities for this function */ - rc = bnxt_hwrm_func_qcaps(bp); - if (rc) { - netdev_err(bp->dev, "hwrm query capability failure rc: %x\n", - rc); - rc = -1; - goto init_err_pci_clean; - } - - rc = bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(bp); - if (rc) - netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n", - rc); - rc = bnxt_init_mac_addr(bp); if (rc) { dev_err(&pdev->dev, "Unable to initialize mac address.\n"); @@ -10794,11 +11009,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_pci_clean; } - bnxt_hwrm_func_qcfg(bp); - bnxt_hwrm_vnic_qcaps(bp); - bnxt_hwrm_port_led_qcaps(bp); - bnxt_ethtool_init(bp); - bnxt_dcb_init(bp); /* MTU range: 60 - FW defined max */ dev->min_mtu = ETH_ZLEN; @@ -10934,8 +11144,7 @@ shutdown_exit: #ifdef CONFIG_PM_SLEEP static int bnxt_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnxt *bp = netdev_priv(dev); int rc = 0; @@ -10951,8 +11160,7 @@ static int bnxt_suspend(struct device *device) static int bnxt_resume(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnxt *bp = netdev_priv(dev); int rc = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 16694b704d15..1b1610d5b573 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -113,6 +113,7 @@ struct tx_cmp { #define CMP_TYPE_RX_AGG_CMP 18 #define CMP_TYPE_RX_L2_TPA_START_CMP 19 #define CMP_TYPE_RX_L2_TPA_END_CMP 21 + #define CMP_TYPE_RX_TPA_AGG_CMP 22 #define CMP_TYPE_STATUS_CMP 32 #define CMP_TYPE_REMOTE_DRIVER_REQ 34 #define CMP_TYPE_REMOTE_DRIVER_RESP 36 @@ -263,14 +264,21 @@ struct rx_agg_cmp { u32 rx_agg_cmp_opaque; __le32 rx_agg_cmp_v; #define RX_AGG_CMP_V (1 << 0) + #define RX_AGG_CMP_AGG_ID (0xffff << 16) + #define RX_AGG_CMP_AGG_ID_SHIFT 16 __le32 rx_agg_cmp_unused; }; +#define TPA_AGG_AGG_ID(rx_agg) \ + ((le32_to_cpu((rx_agg)->rx_agg_cmp_v) & \ + RX_AGG_CMP_AGG_ID) >> RX_AGG_CMP_AGG_ID_SHIFT) + struct rx_tpa_start_cmp { __le32 rx_tpa_start_cmp_len_flags_type; #define RX_TPA_START_CMP_TYPE (0x3f << 0) #define RX_TPA_START_CMP_FLAGS (0x3ff << 6) #define RX_TPA_START_CMP_FLAGS_SHIFT 6 + #define RX_TPA_START_CMP_FLAGS_ERROR (0x1 << 6) #define RX_TPA_START_CMP_FLAGS_PLACEMENT (0x7 << 7) #define RX_TPA_START_CMP_FLAGS_PLACEMENT_SHIFT 7 #define RX_TPA_START_CMP_FLAGS_PLACEMENT_JUMBO (0x1 << 7) @@ -278,6 +286,7 @@ struct rx_tpa_start_cmp { #define RX_TPA_START_CMP_FLAGS_PLACEMENT_GRO_JUMBO (0x5 << 7) #define RX_TPA_START_CMP_FLAGS_PLACEMENT_GRO_HDS (0x6 << 7) #define RX_TPA_START_CMP_FLAGS_RSS_VALID (0x1 << 10) + #define RX_TPA_START_CMP_FLAGS_TIMESTAMP (0x1 << 11) #define RX_TPA_START_CMP_FLAGS_ITYPES (0xf << 12) #define RX_TPA_START_CMP_FLAGS_ITYPES_SHIFT 12 #define RX_TPA_START_CMP_FLAGS_ITYPE_TCP (0x2 << 12) @@ -291,6 +300,8 @@ struct rx_tpa_start_cmp { #define RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT 9 #define RX_TPA_START_CMP_AGG_ID (0x7f << 25) #define RX_TPA_START_CMP_AGG_ID_SHIFT 25 + #define RX_TPA_START_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5 16 __le32 rx_tpa_start_cmp_rss_hash; }; @@ -308,6 +319,14 @@ struct rx_tpa_start_cmp { ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ RX_TPA_START_CMP_AGG_ID) >> RX_TPA_START_CMP_AGG_ID_SHIFT) +#define TPA_START_AGG_ID_P5(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ + RX_TPA_START_CMP_AGG_ID_P5) >> RX_TPA_START_CMP_AGG_ID_SHIFT_P5) + +#define TPA_START_ERROR(rx_tpa_start) \ + ((rx_tpa_start)->rx_tpa_start_cmp_len_flags_type & \ + cpu_to_le32(RX_TPA_START_CMP_FLAGS_ERROR)) + struct rx_tpa_start_cmp_ext { __le32 rx_tpa_start_cmp_flags2; #define RX_TPA_START_CMP_FLAGS2_IP_CS_CALC (0x1 << 0) @@ -315,10 +334,20 @@ struct rx_tpa_start_cmp_ext { #define RX_TPA_START_CMP_FLAGS2_T_IP_CS_CALC (0x1 << 2) #define RX_TPA_START_CMP_FLAGS2_T_L4_CS_CALC (0x1 << 3) #define RX_TPA_START_CMP_FLAGS2_IP_TYPE (0x1 << 8) + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_VALID (0x1 << 9) + #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT (0x3 << 10) + #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT_SHIFT 10 + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL (0xffff << 16) + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_SHIFT 16 __le32 rx_tpa_start_cmp_metadata; __le32 rx_tpa_start_cmp_cfa_code_v2; #define RX_TPA_START_CMP_V2 (0x1 << 0) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK (0x7 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT 1 + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_NO_BUFFER (0x0 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_BAD_FORMAT (0x3 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_FLUSH (0x5 << 1) #define RX_TPA_START_CMP_CFA_CODE (0xffff << 16) #define RX_TPA_START_CMPL_CFA_CODE_SHIFT 16 __le32 rx_tpa_start_cmp_hdr_info; @@ -332,6 +361,11 @@ struct rx_tpa_start_cmp_ext { (!!((rx_tpa_start)->rx_tpa_start_cmp_flags2 & \ cpu_to_le32(RX_TPA_START_CMP_FLAGS2_IP_TYPE))) +#define TPA_START_ERROR_CODE(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) & \ + RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK) >> \ + RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT) + struct rx_tpa_end_cmp { __le32 rx_tpa_end_cmp_len_flags_type; #define RX_TPA_END_CMP_TYPE (0x3f << 0) @@ -361,6 +395,8 @@ struct rx_tpa_end_cmp { #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT 16 #define RX_TPA_END_CMP_AGG_ID (0x7f << 25) #define RX_TPA_END_CMP_AGG_ID_SHIFT 25 + #define RX_TPA_END_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_END_CMP_AGG_ID_SHIFT_P5 16 __le32 rx_tpa_end_cmp_tsdelta; #define RX_TPA_END_GRO_TS (0x1 << 31) @@ -370,6 +406,18 @@ struct rx_tpa_end_cmp { ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ RX_TPA_END_CMP_AGG_ID) >> RX_TPA_END_CMP_AGG_ID_SHIFT) +#define TPA_END_AGG_ID_P5(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_AGG_ID_P5) >> RX_TPA_END_CMP_AGG_ID_SHIFT_P5) + +#define TPA_END_PAYLOAD_OFF(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_PAYLOAD_OFFSET) >> RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT) + +#define TPA_END_AGG_BUFS(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_AGG_BUFS) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT) + #define TPA_END_TPA_SEGS(rx_tpa_end) \ ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ RX_TPA_END_CMP_TPA_SEGS) >> RX_TPA_END_CMP_TPA_SEGS_SHIFT) @@ -389,6 +437,10 @@ struct rx_tpa_end_cmp { struct rx_tpa_end_cmp_ext { __le32 rx_tpa_end_cmp_dup_acks; #define RX_TPA_END_CMP_TPA_DUP_ACKS (0xf << 0) + #define RX_TPA_END_CMP_PAYLOAD_OFFSET_P5 (0xff << 16) + #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT_P5 16 + #define RX_TPA_END_CMP_AGG_BUFS_P5 (0xff << 24) + #define RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5 24 __le32 rx_tpa_end_cmp_seg_len; #define RX_TPA_END_CMP_TPA_SEG_LEN (0xffff << 0) @@ -396,7 +448,13 @@ struct rx_tpa_end_cmp_ext { __le32 rx_tpa_end_cmp_errors_v2; #define RX_TPA_END_CMP_V2 (0x1 << 0) #define RX_TPA_END_CMP_ERRORS (0x3 << 1) + #define RX_TPA_END_CMP_ERRORS_P5 (0x7 << 1) #define RX_TPA_END_CMPL_ERRORS_SHIFT 1 + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_NO_BUFFER (0x0 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_NOT_ON_CHIP (0x2 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_BAD_FORMAT (0x3 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_RSV_ERROR (0x4 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_FLUSH (0x5 << 1) u32 rx_tpa_end_cmp_start_opaque; }; @@ -405,6 +463,15 @@ struct rx_tpa_end_cmp_ext { ((rx_tpa_end_ext)->rx_tpa_end_cmp_errors_v2 & \ cpu_to_le32(RX_TPA_END_CMP_ERRORS)) +#define TPA_END_PAYLOAD_OFF_P5(rx_tpa_end_ext) \ + ((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) & \ + RX_TPA_END_CMP_PAYLOAD_OFFSET_P5) >> \ + RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT_P5) + +#define TPA_END_AGG_BUFS_P5(rx_tpa_end_ext) \ + ((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) & \ + RX_TPA_END_CMP_AGG_BUFS_P5) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5) + struct nqe_cn { __le16 type; #define NQ_CN_TYPE_MASK 0x3fUL @@ -487,6 +554,9 @@ struct nqe_cn { #define BNXT_DEFAULT_TX_RING_SIZE 511 #define MAX_TPA 64 +#define MAX_TPA_P5 256 +#define MAX_TPA_P5_MASK (MAX_TPA_P5 - 1) +#define MAX_TPA_SEGS_P5 0x3f #if (BNXT_PAGE_SHIFT == 16) #define MAX_RX_PAGES 1 @@ -768,6 +838,15 @@ struct bnxt_tpa_info { ((hdr_info) & 0x1ff) u16 cfa_code; /* cfa_code in TPA start compl */ + u8 agg_count; + struct rx_agg_cmp *agg_arr; +}; + +#define BNXT_AGG_IDX_BMAP_SIZE (MAX_TPA_P5 / BITS_PER_LONG) + +struct bnxt_tpa_idx_map { + u16 agg_id_tbl[1024]; + unsigned long agg_idx_bmap[BNXT_AGG_IDX_BMAP_SIZE]; }; struct bnxt_rx_ring_info { @@ -797,6 +876,7 @@ struct bnxt_rx_ring_info { dma_addr_t rx_agg_desc_mapping[MAX_RX_AGG_PAGES]; struct bnxt_tpa_info *rx_tpa; + struct bnxt_tpa_idx_map *rx_tpa_idx_map; struct bnxt_ring_struct rx_ring_struct; struct bnxt_ring_struct rx_agg_ring_struct; @@ -1282,7 +1362,9 @@ struct bnxt { #define CHIP_NUM_5745X 0xd730 -#define CHIP_NUM_57500 0x1750 +#define CHIP_NUM_57508 0x1750 +#define CHIP_NUM_57504 0x1751 +#define CHIP_NUM_57502 0x1752 #define CHIP_NUM_58802 0xd802 #define CHIP_NUM_58804 0xd804 @@ -1379,12 +1461,14 @@ struct bnxt { #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0) #define BNXT_RX_PAGE_MODE(bp) ((bp)->flags & BNXT_FLAG_RX_PAGE_MODE) #define BNXT_SUPPORTS_TPA(bp) (!BNXT_CHIP_TYPE_NITRO_A0(bp) && \ - !(bp->flags & BNXT_FLAG_CHIP_P5) && \ - !is_kdump_kernel()) + (!((bp)->flags & BNXT_FLAG_CHIP_P5) || \ + (bp)->max_tpa_v2) && !is_kdump_kernel()) /* Chip class phase 5 */ #define BNXT_CHIP_P5(bp) \ - ((bp)->chip_num == CHIP_NUM_57500) + ((bp)->chip_num == CHIP_NUM_57508 || \ + (bp)->chip_num == CHIP_NUM_57504 || \ + (bp)->chip_num == CHIP_NUM_57502) /* Chip class phase 4.x */ #define BNXT_CHIP_P4(bp) \ @@ -1414,6 +1498,8 @@ struct bnxt { u16, void *, u8 *, dma_addr_t, unsigned int); + u16 max_tpa_v2; + u16 max_tpa; u32 rx_buf_size; u32 rx_buf_use_size; /* useable size */ u16 rx_offset; @@ -1525,6 +1611,7 @@ struct bnxt { int hw_port_stats_size; u16 fw_rx_stats_ext_size; u16 fw_tx_stats_ext_size; + u16 hw_ring_stats_size; u8 pri2cos[8]; u8 pri2cos_valid; @@ -1637,7 +1724,6 @@ struct bnxt { u8 switch_id[8]; struct bnxt_tc_info *tc_info; struct dentry *debugfs_pdev; - struct dentry *debugfs_dim; struct device *hwmon_dev; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c index 61393f351a77..156c2404854f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c @@ -61,45 +61,30 @@ static const struct file_operations debugfs_dim_fops = { .read = debugfs_dim_read, }; -static struct dentry *debugfs_dim_ring_init(struct dim *dim, int ring_idx, - struct dentry *dd) +static void debugfs_dim_ring_init(struct dim *dim, int ring_idx, + struct dentry *dd) { static char qname[16]; snprintf(qname, 10, "%d", ring_idx); - return debugfs_create_file(qname, 0600, dd, - dim, &debugfs_dim_fops); + debugfs_create_file(qname, 0600, dd, dim, &debugfs_dim_fops); } void bnxt_debug_dev_init(struct bnxt *bp) { const char *pname = pci_name(bp->pdev); - struct dentry *pdevf; + struct dentry *dir; int i; bp->debugfs_pdev = debugfs_create_dir(pname, bnxt_debug_mnt); - if (bp->debugfs_pdev) { - pdevf = debugfs_create_dir("dim", bp->debugfs_pdev); - if (!pdevf) { - pr_err("failed to create debugfs entry %s/dim\n", - pname); - return; - } - bp->debugfs_dim = pdevf; - /* create files for each rx ring */ - for (i = 0; i < bp->cp_nr_rings; i++) { - struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + dir = debugfs_create_dir("dim", bp->debugfs_pdev); - if (cpr && bp->bnapi[i]->rx_ring) { - pdevf = debugfs_dim_ring_init(&cpr->dim, i, - bp->debugfs_dim); - if (!pdevf) - pr_err("failed to create debugfs entry %s/dim/%d\n", - pname, i); - } - } - } else { - pr_err("failed to create debugfs entry %s\n", pname); + /* create files for each rx ring */ + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + + if (cpr && bp->bnapi[i]->rx_ring) + debugfs_dim_ring_init(&cpr->dim, i, dir); } } @@ -114,8 +99,6 @@ void bnxt_debug_dev_exit(struct bnxt *bp) void bnxt_debug_init(void) { bnxt_debug_mnt = debugfs_create_dir("bnxt_en", NULL); - if (!bnxt_debug_mnt) - pr_err("failed to init bnxt_en debugfs\n"); } void bnxt_debug_exit(void) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 8445a0cce849..b624174c8594 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -137,7 +137,44 @@ reset_coalesce: return rc; } -#define BNXT_NUM_STATS 22 +static const char * const bnxt_ring_stats_str[] = { + "rx_ucast_packets", + "rx_mcast_packets", + "rx_bcast_packets", + "rx_discards", + "rx_drops", + "rx_ucast_bytes", + "rx_mcast_bytes", + "rx_bcast_bytes", + "tx_ucast_packets", + "tx_mcast_packets", + "tx_bcast_packets", + "tx_discards", + "tx_drops", + "tx_ucast_bytes", + "tx_mcast_bytes", + "tx_bcast_bytes", +}; + +static const char * const bnxt_ring_tpa_stats_str[] = { + "tpa_packets", + "tpa_bytes", + "tpa_events", + "tpa_aborts", +}; + +static const char * const bnxt_ring_tpa2_stats_str[] = { + "rx_tpa_eligible_pkt", + "rx_tpa_eligible_bytes", + "rx_tpa_pkt", + "rx_tpa_bytes", + "rx_tpa_errors", +}; + +static const char * const bnxt_ring_sw_stats_str[] = { + "rx_l4_csum_errors", + "missed_irqs", +}; #define BNXT_RX_STATS_ENTRY(counter) \ { BNXT_RX_STATS_OFFSET(counter), __stringify(counter) } @@ -207,6 +244,20 @@ reset_coalesce: BNXT_TX_STATS_EXT_COS_ENTRY(6), \ BNXT_TX_STATS_EXT_COS_ENTRY(7) \ +#define BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(n) \ + BNXT_RX_STATS_EXT_ENTRY(rx_discard_bytes_cos##n), \ + BNXT_RX_STATS_EXT_ENTRY(rx_discard_packets_cos##n) + +#define BNXT_RX_STATS_EXT_DISCARD_COS_ENTRIES \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(0), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(1), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(2), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(3), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(4), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(5), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(6), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(7) + #define BNXT_RX_STATS_PRI_ENTRY(counter, n) \ { BNXT_RX_STATS_EXT_OFFSET(counter##_cos0), \ __stringify(counter##_pri##n) } @@ -352,6 +403,7 @@ static const struct { BNXT_RX_STATS_EXT_ENTRY(rx_buffer_passed_threshold), BNXT_RX_STATS_EXT_ENTRY(rx_pcs_symbol_err), BNXT_RX_STATS_EXT_ENTRY(rx_corrected_bits), + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRIES, }; static const struct { @@ -417,9 +469,29 @@ static const struct { ARRAY_SIZE(bnxt_tx_pkts_pri_arr)) #define BNXT_NUM_PCIE_STATS ARRAY_SIZE(bnxt_pcie_stats_arr) +static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp) +{ + if (BNXT_SUPPORTS_TPA(bp)) { + if (bp->max_tpa_v2) + return ARRAY_SIZE(bnxt_ring_tpa2_stats_str); + return ARRAY_SIZE(bnxt_ring_tpa_stats_str); + } + return 0; +} + +static int bnxt_get_num_ring_stats(struct bnxt *bp) +{ + int num_stats; + + num_stats = ARRAY_SIZE(bnxt_ring_stats_str) + + ARRAY_SIZE(bnxt_ring_sw_stats_str) + + bnxt_get_num_tpa_ring_stats(bp); + return num_stats * bp->cp_nr_rings; +} + static int bnxt_get_num_stats(struct bnxt *bp) { - int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings; + int num_stats = bnxt_get_num_ring_stats(bp); num_stats += BNXT_NUM_SW_FUNC_STATS; @@ -460,10 +532,11 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, { u32 i, j = 0; struct bnxt *bp = netdev_priv(dev); - u32 stat_fields = sizeof(struct ctx_hw_stats) / 8; + u32 stat_fields = ARRAY_SIZE(bnxt_ring_stats_str) + + bnxt_get_num_tpa_ring_stats(bp); if (!bp->bnapi) { - j += BNXT_NUM_STATS * bp->cp_nr_rings + BNXT_NUM_SW_FUNC_STATS; + j += bnxt_get_num_ring_stats(bp) + BNXT_NUM_SW_FUNC_STATS; goto skip_ring_stats; } @@ -551,56 +624,39 @@ skip_ring_stats: static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { struct bnxt *bp = netdev_priv(dev); - u32 i; + static const char * const *str; + u32 i, j, num_str; switch (stringset) { - /* The number of strings must match BNXT_NUM_STATS defined above. */ case ETH_SS_STATS: for (i = 0; i < bp->cp_nr_rings; i++) { - sprintf(buf, "[%d]: rx_ucast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_mcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_bcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_discards", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_drops", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_ucast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_mcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_bcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_ucast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_mcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_bcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_discards", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_drops", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_ucast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_mcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_bcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_events", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_aborts", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_l4_csum_errors", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: missed_irqs", i); - buf += ETH_GSTRING_LEN; + num_str = ARRAY_SIZE(bnxt_ring_stats_str); + for (j = 0; j < num_str; j++) { + sprintf(buf, "[%d]: %s", i, + bnxt_ring_stats_str[j]); + buf += ETH_GSTRING_LEN; + } + if (!BNXT_SUPPORTS_TPA(bp)) + goto skip_tpa_stats; + + if (bp->max_tpa_v2) { + num_str = ARRAY_SIZE(bnxt_ring_tpa2_stats_str); + str = bnxt_ring_tpa2_stats_str; + } else { + num_str = ARRAY_SIZE(bnxt_ring_tpa_stats_str); + str = bnxt_ring_tpa_stats_str; + } + for (j = 0; j < num_str; j++) { + sprintf(buf, "[%d]: %s", i, str[j]); + buf += ETH_GSTRING_LEN; + } +skip_tpa_stats: + num_str = ARRAY_SIZE(bnxt_ring_sw_stats_str); + for (j = 0; j < num_str; j++) { + sprintf(buf, "[%d]: %s", i, + bnxt_ring_sw_stats_str[j]); + buf += ETH_GSTRING_LEN; + } } for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++) { strcpy(buf, bnxt_sw_func_stats[i].string); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 12bbb2a207d0..2cdef753a1bc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -1,7 +1,8 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation - * Copyright (c) 2016-2019 Broadcom Limited + * Copyright (c) 2014-2018 Broadcom Limited + * Copyright (c) 2018-2019 Broadcom Inc. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -39,15 +40,15 @@ struct hwrm_resp_hdr { #define TLV_TYPE_ROCE_SP_COMMAND 0x3UL #define TLV_TYPE_QUERY_ROCE_CC_GEN1 0x4UL #define TLV_TYPE_MODIFY_ROCE_CC_GEN1 0x5UL -#define TLV_TYPE_ENGINE_CKV_DEVICE_SERIAL_NUMBER 0x8001UL -#define TLV_TYPE_ENGINE_CKV_NONCE 0x8002UL +#define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL #define TLV_TYPE_ENGINE_CKV_IV 0x8003UL #define TLV_TYPE_ENGINE_CKV_AUTH_TAG 0x8004UL #define TLV_TYPE_ENGINE_CKV_CIPHERTEXT 0x8005UL #define TLV_TYPE_ENGINE_CKV_ALGORITHMS 0x8006UL -#define TLV_TYPE_ENGINE_CKV_ECC_PUBLIC_KEY 0x8007UL +#define TLV_TYPE_ENGINE_CKV_HOST_ECC_PUBLIC_KEY 0x8007UL #define TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE 0x8008UL -#define TLV_TYPE_LAST TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE +#define TLV_TYPE_ENGINE_CKV_SRT_ECC_PUBLIC_KEY 0x8009UL +#define TLV_TYPE_LAST TLV_TYPE_ENGINE_CKV_SRT_ECC_PUBLIC_KEY /* tlv (size:64b/8B) */ @@ -267,7 +268,6 @@ struct cmd_nums { #define HWRM_CFA_EEM_OP 0x123UL #define HWRM_CFA_ADV_FLOW_MGNT_QCAPS 0x124UL #define HWRM_CFA_TFLIB 0x125UL - #define HWRM_ENGINE_CKV_HELLO 0x12dUL #define HWRM_ENGINE_CKV_STATUS 0x12eUL #define HWRM_ENGINE_CKV_CKEK_ADD 0x12fUL #define HWRM_ENGINE_CKV_CKEK_DELETE 0x130UL @@ -313,6 +313,7 @@ struct cmd_nums { #define HWRM_FUNC_BACKING_STORE_QCFG 0x194UL #define HWRM_FUNC_VF_BW_CFG 0x195UL #define HWRM_FUNC_VF_BW_QCFG 0x196UL + #define HWRM_FUNC_HOST_PF_IDS_QUERY 0x197UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -410,8 +411,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 0 -#define HWRM_VERSION_RSVD 69 -#define HWRM_VERSION_STR "1.10.0.69" +#define HWRM_VERSION_RSVD 89 +#define HWRM_VERSION_STR "1.10.0.89" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -624,6 +625,8 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE 0x3aUL #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE 0x3bUL #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE 0x3cUL + #define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_DEFAULT_VNIC_CHANGE 0x3dUL + #define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_LINK_STATUS_CHANGE 0x3eUL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -1122,6 +1125,7 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_FLAGS_MULTI_HOST 0x20UL #define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF 0x40UL #define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED 0x80UL + #define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS 0x100UL u8 mac_address[6]; __le16 pci_id; __le16 alloc_rsscos_ctx; @@ -1241,6 +1245,7 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC 0x400000UL #define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST 0x800000UL #define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE 0x1000000UL + #define FUNC_CFG_REQ_FLAGS_PREBOOT_LEGACY_L2_RINGS 0x2000000UL __le32 enables; #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL @@ -2916,7 +2921,7 @@ struct tx_port_stats_ext { __le64 pfc_pri7_tx_transitions; }; -/* rx_port_stats_ext (size:2624b/328B) */ +/* rx_port_stats_ext (size:3648b/456B) */ struct rx_port_stats_ext { __le64 link_down_events; __le64 continuous_pause_events; @@ -2959,6 +2964,22 @@ struct rx_port_stats_ext { __le64 rx_buffer_passed_threshold; __le64 rx_pcs_symbol_err; __le64 rx_corrected_bits; + __le64 rx_discard_bytes_cos0; + __le64 rx_discard_bytes_cos1; + __le64 rx_discard_bytes_cos2; + __le64 rx_discard_bytes_cos3; + __le64 rx_discard_bytes_cos4; + __le64 rx_discard_bytes_cos5; + __le64 rx_discard_bytes_cos6; + __le64 rx_discard_bytes_cos7; + __le64 rx_discard_packets_cos0; + __le64 rx_discard_packets_cos1; + __le64 rx_discard_packets_cos2; + __le64 rx_discard_packets_cos3; + __le64 rx_discard_packets_cos4; + __le64 rx_discard_packets_cos5; + __le64 rx_discard_packets_cos6; + __le64 rx_discard_packets_cos7; }; /* hwrm_port_qstats_ext_input (size:320b/40B) */ @@ -6115,6 +6136,21 @@ struct hwrm_cfa_flow_alloc_output { u8 valid; }; +/* hwrm_cfa_flow_alloc_cmd_err (size:64b/8B) */ +struct hwrm_cfa_flow_alloc_cmd_err { + u8 code; + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_UNKNOWN 0x0UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_L2_CONTEXT_TCAM 0x1UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_ACTION_RECORD 0x2UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_COUNTER 0x3UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_WILD_CARD_TCAM 0x4UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_HASH_COLLISION 0x5UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_KEY_EXISTS 0x6UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB 0x7UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_LAST CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB + u8 unused_0[7]; +}; + /* hwrm_cfa_flow_free_input (size:256b/32B) */ struct hwrm_cfa_flow_free_input { __le16 req_type; @@ -6305,7 +6341,7 @@ struct hwrm_cfa_eem_qcaps_input { __le32 unused_0; }; -/* hwrm_cfa_eem_qcaps_output (size:256b/32B) */ +/* hwrm_cfa_eem_qcaps_output (size:320b/40B) */ struct hwrm_cfa_eem_qcaps_output { __le16 error_code; __le16 req_type; @@ -6322,15 +6358,17 @@ struct hwrm_cfa_eem_qcaps_output { #define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE 0x2UL #define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE 0x4UL #define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE 0x8UL + #define CFA_EEM_QCAPS_RESP_SUPPORTED_FID_TABLE 0x10UL __le32 max_entries_supported; __le16 key_entry_size; __le16 record_entry_size; __le16 efc_entry_size; - u8 unused_1; + __le16 fid_entry_size; + u8 unused_1[7]; u8 valid; }; -/* hwrm_cfa_eem_cfg_input (size:320b/40B) */ +/* hwrm_cfa_eem_cfg_input (size:384b/48B) */ struct hwrm_cfa_eem_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -6350,6 +6388,9 @@ struct hwrm_cfa_eem_cfg_input { __le16 key1_ctx_id; __le16 record_ctx_id; __le16 efc_ctx_id; + __le16 fid_ctx_id; + __le16 unused_2; + __le32 unused_3; }; /* hwrm_cfa_eem_cfg_output (size:128b/16B) */ @@ -6375,7 +6416,7 @@ struct hwrm_cfa_eem_qcfg_input { __le32 unused_0; }; -/* hwrm_cfa_eem_qcfg_output (size:192b/24B) */ +/* hwrm_cfa_eem_qcfg_output (size:256b/32B) */ struct hwrm_cfa_eem_qcfg_output { __le16 error_code; __le16 req_type; @@ -6386,7 +6427,12 @@ struct hwrm_cfa_eem_qcfg_output { #define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX 0x2UL #define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD 0x4UL __le32 num_entries; - u8 unused_0[7]; + __le16 key0_ctx_id; + __le16 key1_ctx_id; + __le16 record_ctx_id; + __le16 efc_ctx_id; + __le16 fid_ctx_id; + u8 unused_2[5]; u8 valid; }; @@ -6567,6 +6613,31 @@ struct ctx_hw_stats { __le64 tpa_aborts; }; +/* ctx_hw_stats_ext (size:1344b/168B) */ +struct ctx_hw_stats_ext { + __le64 rx_ucast_pkts; + __le64 rx_mcast_pkts; + __le64 rx_bcast_pkts; + __le64 rx_discard_pkts; + __le64 rx_drop_pkts; + __le64 rx_ucast_bytes; + __le64 rx_mcast_bytes; + __le64 rx_bcast_bytes; + __le64 tx_ucast_pkts; + __le64 tx_mcast_pkts; + __le64 tx_bcast_pkts; + __le64 tx_discard_pkts; + __le64 tx_drop_pkts; + __le64 tx_ucast_bytes; + __le64 tx_mcast_bytes; + __le64 tx_bcast_bytes; + __le64 rx_tpa_eligible_pkt; + __le64 rx_tpa_eligible_bytes; + __le64 rx_tpa_pkt; + __le64 rx_tpa_bytes; + __le64 rx_tpa_errors; +}; + /* hwrm_stat_ctx_alloc_input (size:256b/32B) */ struct hwrm_stat_ctx_alloc_input { __le16 req_type; @@ -6578,7 +6649,8 @@ struct hwrm_stat_ctx_alloc_input { __le32 update_period_ms; u8 stat_ctx_flags; #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE 0x1UL - u8 unused_0[3]; + u8 unused_0; + __le16 stats_dma_length; }; /* hwrm_stat_ctx_alloc_output (size:128b/16B) */ @@ -7204,7 +7276,9 @@ struct coredump_segment_record { u8 version_hi; u8 version_low; u8 seg_flags; - u8 unused_0[7]; + u8 compress_flags; + #define SFLAG_COMPRESSED_ZLIB 0x1UL + u8 unused_0[6]; }; /* hwrm_dbg_coredump_list_input (size:256b/32B) */ @@ -7729,6 +7803,9 @@ struct hwrm_nvm_set_variable_input { #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256 (0x2UL << 1) #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH (0x3UL << 1) #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH + #define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_MASK 0x70UL + #define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_SFT 4 + #define NVM_SET_VARIABLE_REQ_FLAGS_FACTORY_DEFAULT 0x80UL u8 unused_0; }; diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 57dc3cbff36e..155599dcee76 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4096,12 +4096,16 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev) { struct cnic_local *cp = dev->cnic_priv; u32 port_id; + int i; cp->csk_tbl = kvcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock), GFP_KERNEL); if (!cp->csk_tbl) return -ENOMEM; + for (i = 0; i < MAX_CM_SK_TBL_SZ; i++) + atomic_set(&cp->csk_tbl[i].ref_count, 0); + port_id = prandom_u32(); port_id %= CNIC_LOCAL_PORT_RANGE; if (cnic_init_id_tbl(&cp->csk_port_tbl, CNIC_LOCAL_PORT_RANGE, @@ -5480,6 +5484,7 @@ static struct cnic_dev *cnic_alloc_dev(struct net_device *dev, cdev->unregister_device = cnic_unregister_device; cdev->iscsi_nl_msg_recv = cnic_iscsi_nl_msg_recv; cdev->get_fc_npiv_tbl = cnic_get_fc_npiv_tbl; + atomic_set(&cdev->ref_count, 0); cp = cdev->cnic_priv; cp->dev = cdev; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 4c404d2213f9..77f3511b97de 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18041,8 +18041,7 @@ static void tg3_remove_one(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int tg3_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct tg3 *tp = netdev_priv(dev); int err = 0; @@ -18098,8 +18097,7 @@ unlock: static int tg3_resume(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct tg3 *tp = netdev_priv(dev); int err = 0; diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 7767ae6fa1fd..e338272931d1 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -3032,7 +3032,7 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) head_unmap->nvecs++; for (i = 0, vect_id = 0; i < vectors - 1; i++) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 size = skb_frag_size(frag); if (unlikely(size == 0)) { diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index 99f49d059414..f96a42af1014 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -1104,7 +1104,7 @@ static netdev_tx_t xgmac_xmit(struct sk_buff *skb, struct net_device *dev) for (i = 0; i < nfrags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - len = frag->size; + len = skb_frag_size(frag); paddr = skb_frag_dma_map(priv->device, frag, 0, len, DMA_TO_DEVICE); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index eab805579f96..7f3b2e3b0868 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1492,11 +1492,11 @@ static void free_netsgbuf(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -1535,11 +1535,11 @@ static void free_netsgbuf_with_resp(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -2424,7 +2424,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) } else { int i, frags; - struct skb_frag_struct *frag; + skb_frag_t *frag; struct octnic_gather *g; spin_lock(&lio->glist_lock[q_idx]); @@ -2462,11 +2462,9 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[i - 1]; g->sg[(i >> 2)].ptr[(i & 3)] = - dma_map_page(&oct->pci_dev->dev, - frag->page.p, - frag->page_offset, - frag->size, - DMA_TO_DEVICE); + skb_frag_dma_map(&oct->pci_dev->dev, + frag, 0, skb_frag_size(frag), + DMA_TO_DEVICE); if (dma_mapping_error(&oct->pci_dev->dev, g->sg[i >> 2].ptr[i & 3])) { @@ -2478,7 +2476,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[j - 1]; dma_unmap_page(&oct->pci_dev->dev, g->sg[j >> 2].ptr[j & 3], - frag->size, + skb_frag_size(frag), DMA_TO_DEVICE); } dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n", @@ -2486,7 +2484,8 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_BUSY; } - add_sg_size(&g->sg[(i >> 2)], frag->size, (i & 3)); + add_sg_size(&g->sg[(i >> 2)], skb_frag_size(frag), + (i & 3)); i++; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index db0b90555acb..370d76822ee0 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -837,11 +837,11 @@ static void free_netsgbuf(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -881,11 +881,11 @@ static void free_netsgbuf_with_resp(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -1497,7 +1497,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) ndata.reqtype = REQTYPE_NORESP_NET; } else { - struct skb_frag_struct *frag; + skb_frag_t *frag; struct octnic_gather *g; int i, frags; @@ -1535,11 +1535,9 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[i - 1]; g->sg[(i >> 2)].ptr[(i & 3)] = - dma_map_page(&oct->pci_dev->dev, - frag->page.p, - frag->page_offset, - frag->size, - DMA_TO_DEVICE); + skb_frag_dma_map(&oct->pci_dev->dev, + frag, 0, skb_frag_size(frag), + DMA_TO_DEVICE); if (dma_mapping_error(&oct->pci_dev->dev, g->sg[i >> 2].ptr[i & 3])) { dma_unmap_single(&oct->pci_dev->dev, @@ -1550,7 +1548,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[j - 1]; dma_unmap_page(&oct->pci_dev->dev, g->sg[j >> 2].ptr[j & 3], - frag->size, + skb_frag_size(frag), DMA_TO_DEVICE); } dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n", @@ -1558,7 +1556,8 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_BUSY; } - add_sg_size(&g->sg[(i >> 2)], frag->size, (i & 3)); + add_sg_size(&g->sg[(i >> 2)], skb_frag_size(frag), + (i & 3)); i++; } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c index 021d99cd1665..614d07be7181 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c @@ -260,9 +260,7 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, dev_info(&oct->pci_dev->dev, "got a request for FLR from VF that owns DPI ring %u\n", mbox->q_no); - pcie_capability_set_word( - oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no], - PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR); + pcie_flr(oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no]); break; case OCTEON_PF_CHANGED_VF_MACADDR: diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 192bc92da881..4ab57d33a87e 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -1588,15 +1588,13 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq, goto doorbell; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - const struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; qentry = nicvf_get_nxt_sqentry(sq, qentry); size = skb_frag_size(frag); dma_addr = dma_map_page_attrs(&nic->pdev->dev, skb_frag_page(frag), - frag->page_offset, size, + skb_frag_off(frag), size, DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); if (dma_mapping_error(&nic->pdev->dev, dma_addr)) { diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index 89db739b7819..6dabbf1502c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -2132,7 +2132,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, struct port_info *pi = netdev_priv(qs->netdev); struct sk_buff *skb = NULL; struct cpl_rx_pkt *cpl; - struct skb_frag_struct *rx_frag; + skb_frag_t *rx_frag; int nr_frags; int offset = 0; @@ -2182,7 +2182,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, rx_frag += nr_frags; __skb_frag_set_page(rx_frag, sd->pg_chunk.page); - rx_frag->page_offset = sd->pg_chunk.offset + offset; + skb_frag_off_set(rx_frag, sd->pg_chunk.offset + offset); skb_frag_size_set(rx_frag, len); skb->len += len; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index d692251ee252..ae6a47dd7dc9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3531,7 +3531,6 @@ int t4_setup_debugfs(struct adapter *adap) { int i; u32 size = 0; - struct dentry *de; static struct t4_debugfs_entry t4_debugfs_files[] = { { "cim_la", &cim_la_fops, 0400, 0 }, @@ -3642,8 +3641,8 @@ int t4_setup_debugfs(struct adapter *adap) } } - de = debugfs_create_file_size("flash", 0400, adap->debugfs_root, adap, - &flash_debugfs_fops, adap->params.sf_size); + debugfs_create_file_size("flash", 0400, adap->debugfs_root, adap, + &flash_debugfs_fops, adap->params.sf_size); debugfs_create_bool("use_backdoor", 0600, adap->debugfs_root, &adap->use_bd); debugfs_create_bool("trace_rss", 0600, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 4311ad9c84b2..71854a19cebe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6269,10 +6269,7 @@ static int __init cxgb4_init_module(void) { int ret; - /* Debugfs support is optional, just warn if this fails */ cxgb4_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (!cxgb4_debugfs_root) - pr_warn("could not create debugfs entry, continuing\n"); ret = pci_register_driver(&cxgb4_driver); if (ret < 0) diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c index eaf1fb74689c..01c65d13fc0e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.c +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c @@ -57,7 +57,7 @@ struct smt_data *t4_init_smt(void) s->smtab[i].state = SMT_STATE_UNUSED; memset(&s->smtab[i].src_mac, 0, ETH_ALEN); spin_lock_init(&s->smtab[i].lock); - atomic_set(&s->smtab[i].refcnt, 0); + s->smtab[i].refcnt = 0; } return s; } @@ -68,7 +68,7 @@ static struct smt_entry *find_or_alloc_smte(struct smt_data *s, u8 *smac) struct smt_entry *e, *end; for (e = &s->smtab[0], end = &s->smtab[s->smt_size]; e != end; ++e) { - if (atomic_read(&e->refcnt) == 0) { + if (e->refcnt == 0) { if (!first_free) first_free = e; } else { @@ -97,11 +97,9 @@ found_reuse: static void t4_smte_free(struct smt_entry *e) { - spin_lock_bh(&e->lock); - if (atomic_read(&e->refcnt) == 0) { /* hasn't been recycled */ + if (e->refcnt == 0) { /* hasn't been recycled */ e->state = SMT_STATE_UNUSED; } - spin_unlock_bh(&e->lock); } /** @@ -111,8 +109,10 @@ static void t4_smte_free(struct smt_entry *e) */ void cxgb4_smt_release(struct smt_entry *e) { - if (atomic_dec_and_test(&e->refcnt)) + spin_lock_bh(&e->lock); + if ((--e->refcnt) == 0) t4_smte_free(e); + spin_unlock_bh(&e->lock); } EXPORT_SYMBOL(cxgb4_smt_release); @@ -215,14 +215,14 @@ static struct smt_entry *t4_smt_alloc_switching(struct adapter *adap, u16 pfvf, e = find_or_alloc_smte(s, smac); if (e) { spin_lock(&e->lock); - if (!atomic_read(&e->refcnt)) { - atomic_set(&e->refcnt, 1); + if (!e->refcnt) { + e->refcnt = 1; e->state = SMT_STATE_SWITCHING; e->pfvf = pfvf; memcpy(e->src_mac, smac, ETH_ALEN); write_smt_entry(adap, e); } else { - atomic_inc(&e->refcnt); + ++e->refcnt; } spin_unlock(&e->lock); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.h b/drivers/net/ethernet/chelsio/cxgb4/smt.h index d6c2cc271398..1268d6e93a47 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.h +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.h @@ -59,7 +59,7 @@ struct smt_entry { u16 idx; u16 pfvf; u8 src_mac[ETH_ALEN]; - atomic_t refcnt; + int refcnt; spinlock_t lock; /* protect smt entry add,removal */ }; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 6d4cf3d0b2f0..f6fc0875d5b0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2478,11 +2478,10 @@ static int setup_debugfs(struct adapter *adapter) * Debugfs support is best effort. */ for (i = 0; i < ARRAY_SIZE(debugfs_files); i++) - (void)debugfs_create_file(debugfs_files[i].name, - debugfs_files[i].mode, - adapter->debugfs_root, - (void *)adapter, - debugfs_files[i].fops); + debugfs_create_file(debugfs_files[i].name, + debugfs_files[i].mode, + adapter->debugfs_root, (void *)adapter, + debugfs_files[i].fops); return 0; } @@ -3257,11 +3256,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, adapter->debugfs_root = debugfs_create_dir(pci_name(pdev), cxgb4vf_debugfs_root); - if (IS_ERR_OR_NULL(adapter->debugfs_root)) - dev_warn(&pdev->dev, "could not create debugfs" - " directory"); - else - setup_debugfs(adapter); + setup_debugfs(adapter); } /* @@ -3486,13 +3481,11 @@ static int __init cxgb4vf_module_init(void) return -EINVAL; } - /* Debugfs support is optional, just warn if this fails */ + /* Debugfs support is optional, debugfs will warn if this fails */ cxgb4vf_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) - pr_warn("could not create debugfs entry, continuing\n"); ret = pci_register_driver(&cxgb4vf_driver); - if (ret < 0 && !IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) + if (ret < 0) debugfs_remove(cxgb4vf_debugfs_root); return ret; } diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 9003eb6716cd..e736ce2c58ca 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1182,9 +1182,8 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, buflen = skb_headlen(skb); } else { skb_frag = skb_si->frags + frag; - buffer = page_address(skb_frag_page(skb_frag)) + - skb_frag->page_offset; - buflen = skb_frag->size; + buffer = skb_frag_address(skb_frag); + buflen = skb_frag_size(skb_frag); } if (frag == last_frag) { @@ -2423,10 +2422,8 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) /* Interrupt */ irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(dev, "no IRQ\n"); + if (irq <= 0) return irq ? irq : -ENODEV; - } port->irq = irq; /* Clock the port */ diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 386bdc1378d1..cce90b5925d9 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1500,8 +1500,6 @@ dm9000_probe(struct platform_device *pdev) ndev->irq = platform_get_irq(pdev, 0); if (ndev->irq < 0) { - dev_err(db->dev, "interrupt resource unavailable: %d\n", - ndev->irq); ret = ndev->irq; goto out; } diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index f287b5da5546..cf3e6f2892ff 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -192,7 +192,6 @@ struct be_eq_obj { } ____cacheline_aligned_in_smp; struct be_aic_obj { /* Adaptive interrupt coalescing (AIC) info */ - bool enable; u32 min_eqd; /* in usecs */ u32 max_eqd; /* in usecs */ u32 prev_eqd; /* in usecs */ @@ -589,6 +588,7 @@ struct be_adapter { struct be_drv_stats drv_stats; struct be_aic_obj aic_obj[MAX_EVT_QS]; + bool aic_enabled; u8 vlan_prio_bmap; /* Available Priority BitMap */ u16 recommended_prio_bits;/* Recommended Priority bits in vlan tag */ struct be_dma_mem rx_filter; /* Cmd DMA mem for rx-filter */ diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 492f8769ac12..5bb5abf99588 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -329,8 +329,8 @@ static int be_get_coalesce(struct net_device *netdev, et->tx_coalesce_usecs_high = aic->max_eqd; et->tx_coalesce_usecs_low = aic->min_eqd; - et->use_adaptive_rx_coalesce = aic->enable; - et->use_adaptive_tx_coalesce = aic->enable; + et->use_adaptive_rx_coalesce = adapter->aic_enabled; + et->use_adaptive_tx_coalesce = adapter->aic_enabled; return 0; } @@ -346,8 +346,9 @@ static int be_set_coalesce(struct net_device *netdev, struct be_eq_obj *eqo; int i; + adapter->aic_enabled = et->use_adaptive_rx_coalesce; + for_all_evt_queues(adapter, eqo, i) { - aic->enable = et->use_adaptive_rx_coalesce; aic->max_eqd = min(et->rx_coalesce_usecs_high, BE_MAX_EQD); aic->min_eqd = min(et->rx_coalesce_usecs_low, aic->max_eqd); aic->et_eqd = min(et->rx_coalesce_usecs, aic->max_eqd); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 4d8e40ac66d2..39eb7d525043 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1014,7 +1014,7 @@ static u32 be_xmit_enqueue(struct be_adapter *adapter, struct be_tx_obj *txo, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = skb_frag_size(frag); busaddr = skb_frag_dma_map(dev, frag, 0, len, DMA_TO_DEVICE); @@ -2147,7 +2147,7 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) int i; aic = &adapter->aic_obj[eqo->idx]; - if (!aic->enable) { + if (!adapter->aic_enabled) { if (aic->jiffies) aic->jiffies = 0; eqd = aic->et_eqd; @@ -2204,7 +2204,7 @@ static u32 be_get_eq_delay_mult_enc(struct be_eq_obj *eqo) int eqd; u32 mult_enc; - if (!aic->enable) + if (!adapter->aic_enabled) return 0; if (jiffies_to_msecs(now - aic->jiffies) < 1) @@ -2346,8 +2346,8 @@ static void skb_fill_rx_data(struct be_rx_obj *rxo, struct sk_buff *skb, memcpy(skb->data, start, hdr_len); skb_shinfo(skb)->nr_frags = 1; skb_frag_set_page(skb, 0, page_info->page); - skb_shinfo(skb)->frags[0].page_offset = - page_info->page_offset + hdr_len; + skb_frag_off_set(&skb_shinfo(skb)->frags[0], + page_info->page_offset + hdr_len); skb_frag_size_set(&skb_shinfo(skb)->frags[0], curr_frag_len - hdr_len); skb->data_len = curr_frag_len - hdr_len; @@ -2372,8 +2372,8 @@ static void skb_fill_rx_data(struct be_rx_obj *rxo, struct sk_buff *skb, /* Fresh page */ j++; skb_frag_set_page(skb, j, page_info->page); - skb_shinfo(skb)->frags[j].page_offset = - page_info->page_offset; + skb_frag_off_set(&skb_shinfo(skb)->frags[j], + page_info->page_offset); skb_frag_size_set(&skb_shinfo(skb)->frags[j], 0); skb_shinfo(skb)->nr_frags++; } else { @@ -2454,8 +2454,8 @@ static void be_rx_compl_process_gro(struct be_rx_obj *rxo, /* First frag or Fresh page */ j++; skb_frag_set_page(skb, j, page_info->page); - skb_shinfo(skb)->frags[j].page_offset = - page_info->page_offset; + skb_frag_off_set(&skb_shinfo(skb)->frags[j], + page_info->page_offset); skb_frag_size_set(&skb_shinfo(skb)->frags[j], 0); } else { put_page(page_info->page); @@ -2959,6 +2959,8 @@ static int be_evt_queues_create(struct be_adapter *adapter) max(adapter->cfg_num_rx_irqs, adapter->cfg_num_tx_irqs)); + adapter->aic_enabled = true; + for_all_evt_queues(adapter, eqo, i) { int numa_node = dev_to_node(&adapter->pdev->dev); @@ -2966,7 +2968,6 @@ static int be_evt_queues_create(struct be_adapter *adapter) eqo->adapter = adapter; eqo->idx = i; aic->max_eqd = BE_MAX_EQD; - aic->enable = true; eq = &eqo->q; rc = be_queue_alloc(adapter, eq, EVNT_Q_LEN, diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig index a9b105803fb7..73e4f2648e49 100644 --- a/drivers/net/ethernet/faraday/Kconfig +++ b/drivers/net/ethernet/faraday/Kconfig @@ -32,6 +32,7 @@ config FTGMAC100 depends on ARM || NDS32 || COMPILE_TEST depends on !64BIT || BROKEN select PHYLIB + select MDIO_ASPEED if MACH_ASPEED_G6 ---help--- This driver supports the FTGMAC100 Gigabit Ethernet controller from Faraday. It is used on Faraday A369, Andes AG102 and some diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 030fed65393e..9b7af94a40bb 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_mdio.h> #include <linux/phy.h> #include <linux/platform_device.h> #include <linux/property.h> @@ -774,7 +775,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb, for (i = 0; i < nfrags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - len = frag->size; + len = skb_frag_size(frag); /* Map it */ map = skb_frag_dma_map(priv->dev, frag, 0, len, @@ -1619,8 +1620,13 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) if (!priv->mii_bus) return -EIO; - if (priv->is_aspeed) { - /* This driver supports the old MDIO interface */ + if (of_device_is_compatible(np, "aspeed,ast2400-mac") || + of_device_is_compatible(np, "aspeed,ast2500-mac")) { + /* The AST2600 has a separate MDIO controller */ + + /* For the AST2400 and AST2500 this driver only supports the + * old MDIO interface + */ reg = ioread32(priv->base + FTGMAC100_OFFSET_REVR); reg &= ~FTGMAC100_REVR_NEW_MDIO_INTERFACE; iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR); @@ -1797,7 +1803,8 @@ static int ftgmac100_probe(struct platform_device *pdev) np = pdev->dev.of_node; if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac") || - of_device_is_compatible(np, "aspeed,ast2500-mac"))) { + of_device_is_compatible(np, "aspeed,ast2500-mac") || + of_device_is_compatible(np, "aspeed,ast2600-mac"))) { priv->rxdes0_edorr_mask = BIT(30); priv->txdes0_edotr_mask = BIT(30); priv->is_aspeed = true; @@ -1817,7 +1824,29 @@ static int ftgmac100_probe(struct platform_device *pdev) priv->ndev = ncsi_register_dev(netdev, ftgmac100_ncsi_handler); if (!priv->ndev) goto err_ncsi_dev; - } else { + } else if (np && of_get_property(np, "phy-handle", NULL)) { + struct phy_device *phy; + + 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; + } + + /* Indicate that we support PAUSE frames (see comment in + * Documentation/networking/phy.txt) + */ + phy_support_asym_pause(phy); + + /* Display what we found */ + phy_attached_info(phy); + } else if (np && !of_get_child_by_name(np, "mdio")) { + /* Support legacy ASPEED devicetree descriptions that decribe a + * MAC with an embedded MDIO controller but have no "mdio" + * child node. Automatically scan the MDIO bus for available + * PHYs. + */ priv->use_ncsi = false; err = ftgmac100_setup_mdio(netdev); if (err) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index f38c3fa7d705..b4b82b9c5cd6 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -485,7 +485,7 @@ static struct dpaa_bp *dpaa_bpid2pool(int bpid) static bool dpaa_bpid2pool_use(int bpid) { if (dpaa_bpid2pool(bpid)) { - atomic_inc(&dpaa_bp_array[bpid]->refs); + refcount_inc(&dpaa_bp_array[bpid]->refs); return true; } @@ -496,7 +496,7 @@ static bool dpaa_bpid2pool_use(int bpid) static void dpaa_bpid2pool_map(int bpid, struct dpaa_bp *dpaa_bp) { dpaa_bp_array[bpid] = dpaa_bp; - atomic_set(&dpaa_bp->refs, 1); + refcount_set(&dpaa_bp->refs, 1); } static int dpaa_bp_alloc_pool(struct dpaa_bp *dpaa_bp) @@ -584,7 +584,7 @@ static void dpaa_bp_free(struct dpaa_bp *dpaa_bp) if (!bp) return; - if (!atomic_dec_and_test(&bp->refs)) + if (!refcount_dec_and_test(&bp->refs)) return; if (bp->free_buf_cb) @@ -1958,7 +1958,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, /* populate the rest of SGT entries */ for (i = 0; i < nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; - frag_len = frag->size; + frag_len = skb_frag_size(frag); WARN_ON(!skb_frag_page(frag)); addr = skb_frag_dma_map(dev, frag, 0, frag_len, dma_dir); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h index af320f83c742..f7e59e8db075 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h @@ -32,6 +32,7 @@ #define __DPAA_H #include <linux/netdevice.h> +#include <linux/refcount.h> #include <soc/fsl/qman.h> #include <soc/fsl/bman.h> @@ -99,7 +100,7 @@ struct dpaa_bp { int (*seed_cb)(struct dpaa_bp *); /* bpool can be emptied before freeing by this cb */ void (*free_buf_cb)(const struct dpaa_bp *, struct bm_buffer *); - atomic_t refs; + refcount_t refs; }; struct dpaa_rx_errors { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c index a027f4a9d0cc..a9afe46b837f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c @@ -164,70 +164,30 @@ static const struct file_operations dpaa2_dbg_ch_ops = { void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) { - if (!dpaa2_dbg_root) - return; + struct dentry *dir; /* Create a directory for the interface */ - priv->dbg.dir = debugfs_create_dir(priv->net_dev->name, - dpaa2_dbg_root); - if (!priv->dbg.dir) { - netdev_err(priv->net_dev, "debugfs_create_dir() failed\n"); - return; - } + dir = debugfs_create_dir(priv->net_dev->name, dpaa2_dbg_root); + priv->dbg.dir = dir; /* per-cpu stats file */ - priv->dbg.cpu_stats = debugfs_create_file("cpu_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_cpu_ops); - if (!priv->dbg.cpu_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_cpu_stats; - } + debugfs_create_file("cpu_stats", 0444, dir, priv, &dpaa2_dbg_cpu_ops); /* per-fq stats file */ - priv->dbg.fq_stats = debugfs_create_file("fq_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_fq_ops); - if (!priv->dbg.fq_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_fq_stats; - } + debugfs_create_file("fq_stats", 0444, dir, priv, &dpaa2_dbg_fq_ops); /* per-fq stats file */ - priv->dbg.ch_stats = debugfs_create_file("ch_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_ch_ops); - if (!priv->dbg.fq_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_ch_stats; - } - - return; - -err_ch_stats: - debugfs_remove(priv->dbg.fq_stats); -err_fq_stats: - debugfs_remove(priv->dbg.cpu_stats); -err_cpu_stats: - debugfs_remove(priv->dbg.dir); + debugfs_create_file("ch_stats", 0444, dir, priv, &dpaa2_dbg_ch_ops); } void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv) { - debugfs_remove(priv->dbg.fq_stats); - debugfs_remove(priv->dbg.ch_stats); - debugfs_remove(priv->dbg.cpu_stats); - debugfs_remove(priv->dbg.dir); + debugfs_remove_recursive(priv->dbg.dir); } void dpaa2_eth_dbg_init(void) { dpaa2_dbg_root = debugfs_create_dir(DPAA2_ETH_DBG_ROOT, NULL); - if (!dpaa2_dbg_root) { - pr_err("DPAA2-ETH: debugfs create failed\n"); - return; - } - pr_debug("DPAA2-ETH: debugfs created\n"); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h index 4f63de997a26..15598b28f03b 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h @@ -11,9 +11,6 @@ struct dpaa2_eth_priv; struct dpaa2_debugfs { struct dentry *dir; - struct dentry *fq_stats; - struct dentry *ch_stats; - struct dentry *cpu_stats; }; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 04a59db03f2b..c219587bd334 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -20,6 +20,15 @@ config FSL_ENETC_VF If compiled as module (M), the module name is fsl-enetc-vf. +config FSL_ENETC_MDIO + tristate "ENETC MDIO driver" + depends on PCI && (ARCH_LAYERSCAPE || COMPILE_TEST) + help + This driver supports NXP ENETC Central MDIO controller as a PCIe + physical function (PF) device. + + If compiled as module (M), the module name is fsl-enetc-mdio. + config FSL_ENETC_PTP_CLOCK tristate "ENETC PTP clock driver" depends on PTP_1588_CLOCK_QORIQ && (FSL_ENETC || FSL_ENETC_VF) diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile index 7139e414dccf..d200c27c3bf6 100644 --- a/drivers/net/ethernet/freescale/enetc/Makefile +++ b/drivers/net/ethernet/freescale/enetc/Makefile @@ -1,19 +1,16 @@ # SPDX-License-Identifier: GPL-2.0 + +common-objs := enetc.o enetc_cbdr.o enetc_ethtool.o + obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o -fsl-enetc-$(CONFIG_FSL_ENETC) += enetc.o enetc_cbdr.o enetc_ethtool.o \ - enetc_mdio.o +fsl-enetc-y := enetc_pf.o enetc_mdio.o $(common-objs) fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o -fsl-enetc-objs := enetc_pf.o $(fsl-enetc-y) obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o +fsl-enetc-vf-y := enetc_vf.o $(common-objs) -ifeq ($(CONFIG_FSL_ENETC)$(CONFIG_FSL_ENETC_VF), yy) -fsl-enetc-vf-objs := enetc_vf.o -else -fsl-enetc-vf-$(CONFIG_FSL_ENETC_VF) += enetc.o enetc_cbdr.o \ - enetc_ethtool.o -fsl-enetc-vf-objs := enetc_vf.o $(fsl-enetc-vf-y) -endif +obj-$(CONFIG_FSL_ENETC_MDIO) += fsl-enetc-mdio.o +fsl-enetc-mdio-y := enetc_pci_mdio.o enetc_mdio.o obj-$(CONFIG_FSL_ENETC_PTP_CLOCK) += fsl-enetc-ptp.o -fsl-enetc-ptp-$(CONFIG_FSL_ENETC_PTP_CLOCK) += enetc_ptp.o +fsl-enetc-ptp-y := enetc_ptp.o diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 223709443ea4..b6ff89307409 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -110,7 +110,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb, int active_offloads) { struct enetc_tx_swbd *tx_swbd; - struct skb_frag_struct *frag; + skb_frag_t *frag; int len = skb_headlen(skb); union enetc_tx_bd temp_bd; union enetc_tx_bd *txbd; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c index 77b9cd10ba2b..149883c8f0b8 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c @@ -6,18 +6,20 @@ #include <linux/iopoll.h> #include <linux/of.h> -#include "enetc_pf.h" +#include "enetc_mdio.h" -struct enetc_mdio_regs { - u32 mdio_cfg; /* MDIO configuration and status */ - u32 mdio_ctl; /* MDIO control */ - u32 mdio_data; /* MDIO data */ - u32 mdio_addr; /* MDIO address */ -}; +#define ENETC_MDIO_REG_OFFSET 0x1c00 +#define ENETC_MDIO_CFG 0x0 /* MDIO configuration and status */ +#define ENETC_MDIO_CTL 0x4 /* MDIO control */ +#define ENETC_MDIO_DATA 0x8 /* MDIO data */ +#define ENETC_MDIO_ADDR 0xc /* MDIO address */ -#define bus_to_enetc_regs(bus) (struct enetc_mdio_regs __iomem *)((bus)->priv) +#define enetc_mdio_rd(hw, off) \ + enetc_port_rd(hw, ENETC_##off + ENETC_MDIO_REG_OFFSET) +#define enetc_mdio_wr(hw, off, val) \ + enetc_port_wr(hw, ENETC_##off + ENETC_MDIO_REG_OFFSET, val) +#define enetc_mdio_rd_reg(off) enetc_mdio_rd(hw, off) -#define ENETC_MDIO_REG_OFFSET 0x1c00 #define ENETC_MDC_DIV 258 #define MDIO_CFG_CLKDIV(x) ((((x) >> 1) & 0xff) << 8) @@ -33,18 +35,18 @@ struct enetc_mdio_regs { #define MDIO_DATA(x) ((x) & 0xffff) #define TIMEOUT 1000 -static int enetc_mdio_wait_complete(struct enetc_mdio_regs __iomem *regs) +static int enetc_mdio_wait_complete(struct enetc_hw *hw) { u32 val; - return readx_poll_timeout(enetc_rd_reg, ®s->mdio_cfg, val, + return readx_poll_timeout(enetc_mdio_rd_reg, MDIO_CFG, val, !(val & MDIO_CFG_BSY), 10, 10 * TIMEOUT); } -static int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, - u16 value) +int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) { - struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus); + struct enetc_mdio_priv *mdio_priv = bus->priv; + struct enetc_hw *hw = mdio_priv->hw; u32 mdio_ctl, mdio_cfg; u16 dev_addr; int ret; @@ -59,38 +61,39 @@ static int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, mdio_cfg &= ~MDIO_CFG_ENC45; } - enetc_wr_reg(®s->mdio_cfg, mdio_cfg); + enetc_mdio_wr(hw, MDIO_CFG, mdio_cfg); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; /* set port and dev addr */ mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); - enetc_wr_reg(®s->mdio_ctl, mdio_ctl); + enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl); /* set the register address */ if (regnum & MII_ADDR_C45) { - enetc_wr_reg(®s->mdio_addr, regnum & 0xffff); + enetc_mdio_wr(hw, MDIO_ADDR, regnum & 0xffff); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; } /* write the value */ - enetc_wr_reg(®s->mdio_data, MDIO_DATA(value)); + enetc_mdio_wr(hw, MDIO_DATA, MDIO_DATA(value)); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; return 0; } -static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) { - struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus); + struct enetc_mdio_priv *mdio_priv = bus->priv; + struct enetc_hw *hw = mdio_priv->hw; u32 mdio_ctl, mdio_cfg; u16 dev_addr, value; int ret; @@ -104,41 +107,41 @@ static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) mdio_cfg &= ~MDIO_CFG_ENC45; } - enetc_wr_reg(®s->mdio_cfg, mdio_cfg); + enetc_mdio_wr(hw, MDIO_CFG, mdio_cfg); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; /* set port and device addr */ mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); - enetc_wr_reg(®s->mdio_ctl, mdio_ctl); + enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl); /* set the register address */ if (regnum & MII_ADDR_C45) { - enetc_wr_reg(®s->mdio_addr, regnum & 0xffff); + enetc_mdio_wr(hw, MDIO_ADDR, regnum & 0xffff); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; } /* initiate the read */ - enetc_wr_reg(®s->mdio_ctl, mdio_ctl | MDIO_CTL_READ); + enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl | MDIO_CTL_READ); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; /* return all Fs if nothing was there */ - if (enetc_rd_reg(®s->mdio_cfg) & MDIO_CFG_RD_ER) { + if (enetc_mdio_rd(hw, MDIO_CFG) & MDIO_CFG_RD_ER) { dev_dbg(&bus->dev, "Error while reading PHY%d reg at %d.%hhu\n", phy_id, dev_addr, regnum); return 0xffff; } - value = enetc_rd_reg(®s->mdio_data) & 0xffff; + value = enetc_mdio_rd(hw, MDIO_DATA) & 0xffff; return value; } @@ -146,12 +149,12 @@ static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) int enetc_mdio_probe(struct enetc_pf *pf) { struct device *dev = &pf->si->pdev->dev; - struct enetc_mdio_regs __iomem *regs; + struct enetc_mdio_priv *mdio_priv; struct device_node *np; struct mii_bus *bus; - int ret; + int err; - bus = mdiobus_alloc_size(sizeof(regs)); + bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv)); if (!bus) return -ENOMEM; @@ -159,41 +162,31 @@ int enetc_mdio_probe(struct enetc_pf *pf) bus->read = enetc_mdio_read; bus->write = enetc_mdio_write; bus->parent = dev; + mdio_priv = bus->priv; + mdio_priv->hw = &pf->si->hw; snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); - /* store the enetc mdio base address for this bus */ - regs = pf->si->hw.port + ENETC_MDIO_REG_OFFSET; - bus->priv = regs; - np = of_get_child_by_name(dev->of_node, "mdio"); if (!np) { dev_err(dev, "MDIO node missing\n"); - ret = -EINVAL; - goto err_registration; + return -EINVAL; } - ret = of_mdiobus_register(bus, np); - if (ret) { + err = of_mdiobus_register(bus, np); + if (err) { of_node_put(np); dev_err(dev, "cannot register MDIO bus\n"); - goto err_registration; + return err; } of_node_put(np); pf->mdio = bus; return 0; - -err_registration: - mdiobus_free(bus); - - return ret; } void enetc_mdio_remove(struct enetc_pf *pf) { - if (pf->mdio) { + if (pf->mdio) mdiobus_unregister(pf->mdio); - mdiobus_free(pf->mdio); - } } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.h b/drivers/net/ethernet/freescale/enetc/enetc_mdio.h new file mode 100644 index 000000000000..60c9a3889824 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2019 NXP */ + +#include <linux/phy.h> +#include "enetc_pf.h" + +struct enetc_mdio_priv { + struct enetc_hw *hw; +}; + +int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value); +int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c new file mode 100644 index 000000000000..fbd41ce01f06 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2019 NXP */ +#include <linux/of_mdio.h> +#include "enetc_mdio.h" + +#define ENETC_MDIO_DEV_ID 0xee01 +#define ENETC_MDIO_DEV_NAME "FSL PCIe IE Central MDIO" +#define ENETC_MDIO_BUS_NAME ENETC_MDIO_DEV_NAME " Bus" +#define ENETC_MDIO_DRV_NAME ENETC_MDIO_DEV_NAME " driver" + +static int enetc_pci_mdio_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct enetc_mdio_priv *mdio_priv; + struct device *dev = &pdev->dev; + struct enetc_hw *hw; + struct mii_bus *bus; + int err; + + hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL); + if (!hw) + return -ENOMEM; + + bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv)); + if (!bus) + return -ENOMEM; + + bus->name = ENETC_MDIO_BUS_NAME; + bus->read = enetc_mdio_read; + bus->write = enetc_mdio_write; + bus->parent = dev; + mdio_priv = bus->priv; + mdio_priv->hw = hw; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); + + pcie_flr(pdev); + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(dev, "device enable failed\n"); + return err; + } + + err = pci_request_region(pdev, 0, KBUILD_MODNAME); + if (err) { + dev_err(dev, "pci_request_region failed\n"); + goto err_pci_mem_reg; + } + + hw->port = pci_iomap(pdev, 0, 0); + if (!hw->port) { + err = -ENXIO; + dev_err(dev, "iomap failed\n"); + goto err_ioremap; + } + + err = of_mdiobus_register(bus, dev->of_node); + if (err) + goto err_mdiobus_reg; + + pci_set_drvdata(pdev, bus); + + return 0; + +err_mdiobus_reg: + iounmap(mdio_priv->hw->port); +err_ioremap: + pci_release_mem_regions(pdev); +err_pci_mem_reg: + pci_disable_device(pdev); + + return err; +} + +static void enetc_pci_mdio_remove(struct pci_dev *pdev) +{ + struct mii_bus *bus = pci_get_drvdata(pdev); + struct enetc_mdio_priv *mdio_priv; + + mdiobus_unregister(bus); + mdio_priv = bus->priv; + iounmap(mdio_priv->hw->port); + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} + +static const struct pci_device_id enetc_pci_mdio_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_MDIO_DEV_ID) }, + { 0, } /* End of table. */ +}; +MODULE_DEVICE_TABLE(pci, enetc_pci_mdio_id_table); + +static struct pci_driver enetc_pci_mdio_driver = { + .name = KBUILD_MODNAME, + .id_table = enetc_pci_mdio_id_table, + .probe = enetc_pci_mdio_probe, + .remove = enetc_pci_mdio_remove, +}; +module_pci_driver(enetc_pci_mdio_driver); + +MODULE_DESCRIPTION(ENETC_MDIO_DRV_NAME); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 258b3cb38a6f..7d6513ff8507 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -750,6 +750,7 @@ static int enetc_of_get_phy(struct enetc_ndev_priv *priv) { struct enetc_pf *pf = enetc_si_priv(priv->si); struct device_node *np = priv->dev->of_node; + struct device_node *mdio_np; int err; if (!np) { @@ -773,7 +774,9 @@ static int enetc_of_get_phy(struct enetc_ndev_priv *priv) priv->phy_node = of_node_get(np); } - if (!of_phy_is_fixed_link(np)) { + mdio_np = of_get_child_by_name(np, "mdio"); + if (mdio_np) { + of_node_put(mdio_np); err = enetc_mdio_probe(pf); if (err) { of_node_put(priv->phy_node); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index e5610a4da539..c01d3ec3e9af 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -365,7 +365,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); - frag_len = skb_shinfo(skb)->frags[frag].size; + frag_len = skb_frag_size(&skb_shinfo(skb)->frags[frag]); /* Handle the last BD specially */ if (frag == nr_frags - 1) { @@ -387,7 +387,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, ebdp->cbd_esc = cpu_to_fec32(estatus); } - bufaddr = page_address(this_frag->page.p) + this_frag->page_offset; + bufaddr = skb_frag_address(this_frag); index = fec_enet_get_bd_index(bdp, &txq->bd); if (((unsigned long) bufaddr) & fep->tx_align || diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 5fad73b2e123..3981c06f082f 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -501,7 +501,7 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) nr_frags = skb_shinfo(skb)->nr_frags; frag = skb_shinfo(skb)->frags; for (i = 0; i < nr_frags; i++, frag++) { - if (!IS_ALIGNED(frag->page_offset, 4)) { + if (!IS_ALIGNED(skb_frag_off(frag), 4)) { is_aligned = 0; break; } diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 689f18e3100f..90ab7ade44c4 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -877,7 +877,6 @@ static int hisi_femac_drv_probe(struct platform_device *pdev) ndev->irq = platform_get_irq(pdev, 0); if (ndev->irq <= 0) { - dev_err(dev, "No irq resource\n"); ret = -ENODEV; goto out_disconnect_phy; } diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index 349970557c52..95a6b0926170 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -719,7 +719,7 @@ static int hix5hd2_fill_sg_desc(struct hix5hd2_priv *priv, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - int len = frag->size; + int len = skb_frag_size(frag); addr = skb_frag_dma_map(priv->dev, frag, 0, len, DMA_TO_DEVICE); ret = dma_mapping_error(priv->dev, addr); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 2235dd55fab2..a48396dd4ebb 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -245,7 +245,7 @@ static int hns_nic_maybe_stop_tso( int frag_num; struct sk_buff *skb = *out_skb; struct sk_buff *new_skb = NULL; - struct skb_frag_struct *frag; + skb_frag_t *frag; size = skb_headlen(skb); buf_num = (size + BD_MAX_SEND_SIZE - 1) / BD_MAX_SEND_SIZE; @@ -309,7 +309,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, struct hnae_ring *ring = ring_data->ring; struct device *dev = ring_to_dev(ring); struct netdev_queue *dev_queue; - struct skb_frag_struct *frag; + skb_frag_t *frag; int buf_num; int seg_num; dma_addr_t dma; @@ -1182,6 +1182,8 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h) if (unlikely(ret)) return -ENODEV; + phy_attached_info(phy_dev); + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 75329ab775a6..f8a87f8ca983 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -47,6 +47,8 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */ HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */ + HCLGE_MBX_PUSH_LINK_STATUS, /* (M7 -> PF) get port link status */ + HCLGE_MBX_NCSI_ERROR, /* (M7 -> PF) receive a NCSI error */ }; /* below are per-VF mac-vlan subcodes */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 908d4f45c06a..528f6243cdc6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -46,7 +46,7 @@ void hnae3_set_client_init_flag(struct hnae3_client *client, EXPORT_SYMBOL(hnae3_set_client_init_flag); static int hnae3_get_client_init_flag(struct hnae3_client *client, - struct hnae3_ae_dev *ae_dev) + struct hnae3_ae_dev *ae_dev) { int inited = 0; @@ -104,7 +104,6 @@ int hnae3_register_client(struct hnae3_client *client) { struct hnae3_client *client_tmp; struct hnae3_ae_dev *ae_dev; - int ret = 0; if (!client) return -ENODEV; @@ -123,7 +122,7 @@ int hnae3_register_client(struct hnae3_client *client) /* if the client could not be initialized on current port, for * any error reasons, move on to next available port */ - ret = hnae3_init_client_instance(client, ae_dev); + int ret = hnae3_init_client_instance(client, ae_dev); if (ret) dev_err(&ae_dev->pdev->dev, "match and instantiation failed for port, ret = %d\n", @@ -164,7 +163,7 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) const struct pci_device_id *id; struct hnae3_ae_dev *ae_dev; struct hnae3_client *client; - int ret = 0; + int ret; if (!ae_algo) return; @@ -258,7 +257,7 @@ int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) const struct pci_device_id *id; struct hnae3_ae_algo *ae_algo; struct hnae3_client *client; - int ret = 0; + int ret; if (!ae_dev) return -ENODEV; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 48c7b70fc2c4..3e21533a2bf5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -58,10 +58,10 @@ BIT(HNAE3_DEV_SUPPORT_ROCE_B)) #define hnae3_dev_roce_supported(hdev) \ - hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) + hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) #define hnae3_dev_dcb_supported(hdev) \ - hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) + hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) #define hnae3_dev_fd_supported(hdev) \ hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B) @@ -85,13 +85,18 @@ struct hnae3_queue { void __iomem *io_base; struct hnae3_ae_algo *ae_algo; struct hnae3_handle *handle; - int tqp_index; /* index in a handle */ - u32 buf_size; /* size for hnae_desc->addr, preset by AE */ - u16 tx_desc_num;/* total number of tx desc */ - u16 rx_desc_num;/* total number of rx desc */ + int tqp_index; /* index in a handle */ + u32 buf_size; /* size for hnae_desc->addr, preset by AE */ + u16 tx_desc_num; /* total number of tx desc */ + u16 rx_desc_num; /* total number of rx desc */ }; -/*hnae3 loop mode*/ +struct hns3_mac_stats { + u64 tx_pause_cnt; + u64 rx_pause_cnt; +}; + +/* hnae3 loop mode */ enum hnae3_loop { HNAE3_LOOP_APP, HNAE3_LOOP_SERIAL_SERDES, @@ -179,6 +184,15 @@ struct hnae3_vector_info { #define HNAE3_RING_GL_RX 0 #define HNAE3_RING_GL_TX 1 +#define HNAE3_FW_VERSION_BYTE3_SHIFT 24 +#define HNAE3_FW_VERSION_BYTE3_MASK GENMASK(31, 24) +#define HNAE3_FW_VERSION_BYTE2_SHIFT 16 +#define HNAE3_FW_VERSION_BYTE2_MASK GENMASK(23, 16) +#define HNAE3_FW_VERSION_BYTE1_SHIFT 8 +#define HNAE3_FW_VERSION_BYTE1_MASK GENMASK(15, 8) +#define HNAE3_FW_VERSION_BYTE0_SHIFT 0 +#define HNAE3_FW_VERSION_BYTE0_MASK GENMASK(7, 0) + struct hnae3_ring_chain_node { struct hnae3_ring_chain_node *next; u32 tqp_index; @@ -289,6 +303,8 @@ struct hnae3_ae_dev { * Remove multicast address from mac table * update_stats() * Update Old network device statistics + * get_mac_stats() + * get mac pause statistics including tx_cnt and rx_cnt * get_ethtool_stats() * Get ethtool network device statistics * get_strings() @@ -417,8 +433,8 @@ struct hnae3_ae_ops { void (*update_stats)(struct hnae3_handle *handle, struct net_device_stats *net_stats); void (*get_stats)(struct hnae3_handle *handle, u64 *data); - void (*get_mac_pause_stats)(struct hnae3_handle *handle, u64 *tx_cnt, - u64 *rx_cnt); + void (*get_mac_stats)(struct hnae3_handle *handle, + struct hns3_mac_stats *mac_stats); void (*get_strings)(struct hnae3_handle *handle, u32 stringset, u8 *data); int (*get_sset_count)(struct hnae3_handle *handle, int stringset); @@ -605,7 +621,7 @@ struct hnae3_handle { struct pci_dev *pdev; void *priv; struct hnae3_ae_algo *ae_algo; /* the class who provides this handle */ - u64 flags; /* Indicate the capabilities for this handle*/ + u64 flags; /* Indicate the capabilities for this handle */ union { struct net_device *netdev; /* first member */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index a4b937286f55..7070d25ddb5b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -8,6 +8,7 @@ #include "hns3_enet.h" #define HNS3_DBG_READ_LEN 256 +#define HNS3_DBG_WRITE_LEN 1024 static struct dentry *hns3_dbgfs_root; @@ -322,6 +323,9 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer, test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) return 0; + if (count > HNS3_DBG_WRITE_LEN) + return -ENOSPC; + cmd_buf = kzalloc(count + 1, GFP_KERNEL); if (!cmd_buf) return count; @@ -372,20 +376,11 @@ static const struct file_operations hns3_dbg_cmd_fops = { void hns3_dbg_init(struct hnae3_handle *handle) { const char *name = pci_name(handle->pdev); - struct dentry *pfile; handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root); - if (!handle->hnae3_dbgfs) - return; - pfile = debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, - &hns3_dbg_cmd_fops); - if (!pfile) { - debugfs_remove_recursive(handle->hnae3_dbgfs); - handle->hnae3_dbgfs = NULL; - dev_warn(&handle->pdev->dev, "create file for %s fail\n", - name); - } + debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, + &hns3_dbg_cmd_fops); } void hns3_dbg_uninit(struct hnae3_handle *handle) @@ -397,10 +392,6 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) void hns3_dbg_register_debugfs(const char *debugfs_dir_name) { hns3_dbgfs_root = debugfs_create_dir(debugfs_dir_name, NULL); - if (!hns3_dbgfs_root) { - pr_warn("Register debugfs for %s fail\n", debugfs_dir_name); - return; - } } void hns3_dbg_unregister_debugfs(void) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 310afa708831..a11d514f7a25 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -28,6 +28,12 @@ #define hns3_set_field(origin, shift, val) ((origin) |= ((val) << (shift))) #define hns3_tx_bd_count(S) DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE) +#define hns3_rl_err(fmt, ...) \ + do { \ + if (net_ratelimit()) \ + netdev_err(fmt, ##__VA_ARGS__); \ + } while (0) + static void hns3_clear_all_ring(struct hnae3_handle *h, bool force); static void hns3_remove_hw_addr(struct net_device *netdev); @@ -45,6 +51,9 @@ MODULE_PARM_DESC(debug, " Network interface message level setting"); #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \ NETIF_MSG_IFDOWN | NETIF_MSG_IFUP) +#define HNS3_INNER_VLAN_TAG 1 +#define HNS3_OUTER_VLAN_TAG 2 + /* hns3_pci_tbl - PCI Device ID Table * * Last entry must be all 0s @@ -220,9 +229,9 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector, /* initialize the configuration for interrupt coalescing. * 1. GL (Interrupt Gap Limiter) * 2. RL (Interrupt Rate Limiter) + * + * Default: enable interrupt coalescing self-adaptive and GL */ - - /* 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; @@ -459,6 +468,9 @@ static int hns3_nic_net_open(struct net_device *netdev) h->ae_algo->ops->set_timer_task(priv->ae_handle, true); hns3_config_xps(priv); + + netif_dbg(h, drv, netdev, "net open\n"); + return 0; } @@ -519,6 +531,8 @@ static int hns3_nic_net_stop(struct net_device *netdev) if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state)) return 0; + netif_dbg(h, drv, netdev, "net stop\n"); + if (h->ae_algo->ops->set_timer_task) h->ae_algo->ops->set_timer_task(priv->ae_handle, false); @@ -956,16 +970,16 @@ static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end) hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1U); } -static int hns3_fill_desc_vtags(struct sk_buff *skb, - struct hns3_enet_ring *tx_ring, - u32 *inner_vlan_flag, - u32 *out_vlan_flag, - u16 *inner_vtag, - u16 *out_vtag) +static int hns3_handle_vtags(struct hns3_enet_ring *tx_ring, + struct sk_buff *skb) { -#define HNS3_TX_VLAN_PRIO_SHIFT 13 - struct hnae3_handle *handle = tx_ring->tqp->handle; + struct vlan_ethhdr *vhdr; + int rc; + + if (!(skb->protocol == htons(ETH_P_8021Q) || + skb_vlan_tag_present(skb))) + return 0; /* Since HW limitation, if port based insert VLAN enabled, only one VLAN * header is allowed in skb, otherwise it will cause RAS error. @@ -976,8 +990,7 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb, return -EINVAL; if (skb->protocol == htons(ETH_P_8021Q) && - !(tx_ring->tqp->handle->kinfo.netdev->features & - NETIF_F_HW_VLAN_CTAG_TX)) { + !(handle->kinfo.netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) { /* When HW VLAN acceleration is turned off, and the stack * sets the protocol to 802.1q, the driver just need to * set the protocol to the encapsulated ethertype. @@ -987,45 +1000,107 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb, } if (skb_vlan_tag_present(skb)) { - u16 vlan_tag; - - vlan_tag = skb_vlan_tag_get(skb); - vlan_tag |= (skb->priority & 0x7) << HNS3_TX_VLAN_PRIO_SHIFT; - /* Based on hw strategy, use out_vtag in two layer tag case, * and use inner_vtag in one tag case. */ - if (skb->protocol == htons(ETH_P_8021Q)) { - if (handle->port_base_vlan_state == - HNAE3_PORT_BASE_VLAN_DISABLE){ - hns3_set_field(*out_vlan_flag, - HNS3_TXD_OVLAN_B, 1); - *out_vtag = vlan_tag; - } else { - hns3_set_field(*inner_vlan_flag, - HNS3_TXD_VLAN_B, 1); - *inner_vtag = vlan_tag; - } - } else { - hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1); - *inner_vtag = vlan_tag; - } - } else if (skb->protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *vhdr; - int rc; + if (skb->protocol == htons(ETH_P_8021Q) && + handle->port_base_vlan_state == + HNAE3_PORT_BASE_VLAN_DISABLE) + rc = HNS3_OUTER_VLAN_TAG; + else + rc = HNS3_INNER_VLAN_TAG; - rc = skb_cow_head(skb, 0); - if (unlikely(rc < 0)) - return rc; - vhdr = (struct vlan_ethhdr *)skb->data; - vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority & 0x7) - << HNS3_TX_VLAN_PRIO_SHIFT); + skb->protocol = vlan_get_protocol(skb); + return rc; } + rc = skb_cow_head(skb, 0); + if (unlikely(rc < 0)) + return rc; + + vhdr = (struct vlan_ethhdr *)skb->data; + vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority << VLAN_PRIO_SHIFT) + & VLAN_PRIO_MASK); + skb->protocol = vlan_get_protocol(skb); return 0; } +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 type_cs_vlan_tso = 0; + u32 paylen = skb->len; + u16 inner_vtag = 0; + u16 out_vtag = 0; + u16 mss = 0; + int ret; + + ret = hns3_handle_vtags(ring, skb); + if (unlikely(ret < 0)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_vlan_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } else if (ret == HNS3_INNER_VLAN_TAG) { + inner_vtag = skb_vlan_tag_get(skb); + inner_vtag |= (skb->priority << VLAN_PRIO_SHIFT) & + VLAN_PRIO_MASK; + hns3_set_field(type_cs_vlan_tso, HNS3_TXD_VLAN_B, 1); + } else if (ret == HNS3_OUTER_VLAN_TAG) { + out_vtag = skb_vlan_tag_get(skb); + out_vtag |= (skb->priority << VLAN_PRIO_SHIFT) & + VLAN_PRIO_MASK; + hns3_set_field(ol_type_vlan_len_msec, HNS3_TXD_OVLAN_B, + 1); + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + u8 ol4_proto, il4_proto; + + skb_reset_mac_len(skb); + + ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_l4_proto_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + + ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto, + &type_cs_vlan_tso, + &ol_type_vlan_len_msec); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_l2l3l4_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + + ret = hns3_set_tso(skb, &paylen, &mss, + &type_cs_vlan_tso); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_tso_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + } + + /* 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.vlan_tag = cpu_to_le16(inner_vtag); + desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag); + + return 0; +} + static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, unsigned int size, int frag_end, enum hns_desc_type type) @@ -1033,65 +1108,29 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; struct hns3_desc *desc = &ring->desc[ring->next_to_use]; struct device *dev = ring_to_dev(ring); - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int frag_buf_num; int k, sizeoflast; dma_addr_t dma; if (type == DESC_TYPE_SKB) { struct sk_buff *skb = (struct sk_buff *)priv; - u32 ol_type_vlan_len_msec = 0; - u32 type_cs_vlan_tso = 0; - u32 paylen = skb->len; - u16 inner_vtag = 0; - u16 out_vtag = 0; - u16 mss = 0; int ret; - ret = hns3_fill_desc_vtags(skb, ring, &type_cs_vlan_tso, - &ol_type_vlan_len_msec, - &inner_vtag, &out_vtag); + ret = hns3_fill_skb_desc(ring, skb, desc); if (unlikely(ret)) return ret; - if (skb->ip_summed == CHECKSUM_PARTIAL) { - u8 ol4_proto, il4_proto; - - skb_reset_mac_len(skb); - - ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); - if (unlikely(ret)) - return ret; - - ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto, - &type_cs_vlan_tso, - &ol_type_vlan_len_msec); - if (unlikely(ret)) - return ret; - - ret = hns3_set_tso(skb, &paylen, &mss, - &type_cs_vlan_tso); - if (unlikely(ret)) - return ret; - } - - /* 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.vlan_tag = cpu_to_le16(inner_vtag); - desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag); - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); } else { - frag = (struct skb_frag_struct *)priv; + frag = (skb_frag_t *)priv; dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); } if (unlikely(dma_mapping_error(dev, dma))) { + u64_stats_update_begin(&ring->syncp); ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); return -ENOMEM; } @@ -1147,28 +1186,20 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, return 0; } -static int hns3_nic_bd_num(struct sk_buff *skb) +static unsigned int hns3_nic_bd_num(struct sk_buff *skb) { - int size = skb_headlen(skb); - int i, bd_num; + unsigned int bd_num; + int i; /* if the total len is within the max bd limit */ if (likely(skb->len <= HNS3_MAX_BD_SIZE)) return skb_shinfo(skb)->nr_frags + 1; - bd_num = hns3_tx_bd_count(size); + bd_num = hns3_tx_bd_count(skb_headlen(skb)); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; - int frag_bd_num; - - size = skb_frag_size(frag); - frag_bd_num = hns3_tx_bd_count(size); - - if (unlikely(frag_bd_num > HNS3_MAX_BD_PER_FRAG)) - return -ENOMEM; - - bd_num += frag_bd_num; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + bd_num += hns3_tx_bd_count(skb_frag_size(frag)); } return bd_num; @@ -1189,7 +1220,7 @@ static unsigned int hns3_gso_hdr_len(struct sk_buff *skb) */ static bool hns3_skb_need_linearized(struct sk_buff *skb) { - int bd_limit = HNS3_MAX_BD_PER_FRAG - 1; + int bd_limit = HNS3_MAX_BD_NUM_NORMAL - 1; unsigned int tot_len = 0; int i; @@ -1219,21 +1250,16 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring, struct sk_buff **out_skb) { struct sk_buff *skb = *out_skb; - int bd_num; + unsigned int bd_num; bd_num = hns3_nic_bd_num(skb); - if (bd_num < 0) - return bd_num; - - if (unlikely(bd_num > HNS3_MAX_BD_PER_FRAG)) { + if (unlikely(bd_num > HNS3_MAX_BD_NUM_NORMAL)) { struct sk_buff *new_skb; - if (skb_is_gso(skb) && !hns3_skb_need_linearized(skb)) + if (skb_is_gso(skb) && bd_num <= HNS3_MAX_BD_NUM_TSO && + !hns3_skb_need_linearized(skb)) goto out; - bd_num = hns3_tx_bd_count(skb->len); - if (unlikely(ring_space(ring) < bd_num)) - return -EBUSY; /* manual split the send packet */ new_skb = skb_copy(skb, GFP_ATOMIC); if (!new_skb) @@ -1241,6 +1267,11 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring, dev_kfree_skb_any(skb); *out_skb = new_skb; + bd_num = hns3_nic_bd_num(new_skb); + if ((skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_TSO) || + (!skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_NORMAL)) + return -ENOMEM; + u64_stats_update_begin(&ring->syncp); ring->stats.tx_copy++; u64_stats_update_end(&ring->syncp); @@ -1290,7 +1321,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) &tx_ring_data(priv, skb->queue_mapping); struct hns3_enet_ring *ring = ring_data->ring; struct netdev_queue *dev_queue; - struct skb_frag_struct *frag; + skb_frag_t *frag; int next_to_use_head; int buf_num; int seg_num; @@ -1314,9 +1345,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) u64_stats_update_end(&ring->syncp); } - if (net_ratelimit()) - netdev_err(netdev, "xmit error: %d!\n", buf_num); - + hns3_rl_err(netdev, "xmit error: %d!\n", buf_num); goto out_err_tx_ok; } @@ -1482,7 +1511,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev, tx_bytes += ring->stats.tx_bytes; tx_pkts += ring->stats.tx_pkts; tx_drop += ring->stats.sw_err_cnt; + tx_drop += ring->stats.tx_vlan_err; + tx_drop += ring->stats.tx_l4_proto_err; + tx_drop += ring->stats.tx_l2l3l4_err; + tx_drop += ring->stats.tx_tso_err; tx_errors += ring->stats.sw_err_cnt; + tx_errors += ring->stats.tx_vlan_err; + tx_errors += ring->stats.tx_l4_proto_err; + tx_errors += ring->stats.tx_l2l3l4_err; + tx_errors += ring->stats.tx_tso_err; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); /* fetch the rx stats */ @@ -1550,6 +1587,8 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data) h = hns3_get_handle(netdev); kinfo = &h->kinfo; + netif_dbg(h, drv, netdev, "setup tc: num_tc=%u\n", tc); + return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ? kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP; } @@ -1593,6 +1632,10 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; + netif_dbg(h, drv, netdev, + "set vf vlan: vf=%d, vlan=%u, qos=%u, vlan_proto=%u\n", + vf, vlan, qos, vlan_proto); + if (h->ae_algo->ops->set_vf_vlan_filter) ret = h->ae_algo->ops->set_vf_vlan_filter(h, vf, vlan, qos, vlan_proto); @@ -1611,6 +1654,9 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu) if (!h->ae_algo->ops->set_mtu) return -EOPNOTSUPP; + netif_dbg(h, drv, netdev, + "change mtu from %u to %d\n", netdev->mtu, new_mtu); + ret = h->ae_algo->ops->set_mtu(h, new_mtu); if (ret) netdev_err(netdev, "failed to change MTU in hardware %d\n", @@ -1680,15 +1726,12 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev) /* When mac received many pause frames continuous, it's unable to send * packets, which may cause tx timeout */ - if (h->ae_algo->ops->update_stats && - h->ae_algo->ops->get_mac_pause_stats) { - u64 tx_pause_cnt, rx_pause_cnt; + if (h->ae_algo->ops->get_mac_stats) { + struct hns3_mac_stats mac_stats; - h->ae_algo->ops->update_stats(h, &ndev->stats); - h->ae_algo->ops->get_mac_pause_stats(h, &tx_pause_cnt, - &rx_pause_cnt); + h->ae_algo->ops->get_mac_stats(h, &mac_stats); netdev_info(ndev, "tx_pause_cnt: %llu, rx_pause_cnt: %llu\n", - tx_pause_cnt, rx_pause_cnt); + mac_stats.tx_pause_cnt, mac_stats.rx_pause_cnt); } hw_head = readl_relaxed(tx_ring->tqp->io_base + @@ -1963,7 +2006,7 @@ static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev) ops = ae_dev->ops; /* request the reset */ - if (ops->reset_event) { + if (ops->reset_event && ops->get_reset_level) { if (ae_dev->hw_err_reset_req) { reset_type = ops->get_reset_level(ae_dev, &ae_dev->hw_err_reset_req); @@ -2067,7 +2110,7 @@ static void hns3_set_default_feature(struct net_device *netdev) static int hns3_alloc_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) { - unsigned int order = hnae3_page_order(ring); + unsigned int order = hns3_page_order(ring); struct page *p; p = dev_alloc_pages(order); @@ -2078,7 +2121,7 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring, cb->page_offset = 0; cb->reuse_flag = 0; cb->buf = page_address(p); - cb->length = hnae3_page_size(ring); + cb->length = hns3_page_size(ring); cb->type = DESC_TYPE_PAGE; return 0; @@ -2357,8 +2400,9 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, ring->stats.sw_err_cnt++; u64_stats_update_end(&ring->syncp); - netdev_err(ring->tqp->handle->kinfo.netdev, - "hnae reserve buffer map failed.\n"); + hns3_rl_err(ring->tqp_vector->napi.dev, + "alloc rx buffer failed: %d\n", + ret); break; } hns3_replace_buffer(ring, ring->next_to_use, &res_cbs); @@ -2381,7 +2425,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, { struct hns3_desc *desc = &ring->desc[ring->next_to_clean]; int size = le16_to_cpu(desc->rx.size); - u32 truesize = hnae3_buf_size(ring); + u32 truesize = hns3_buf_size(ring); skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, size - pull_len, truesize); @@ -2396,7 +2440,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, /* Move offset up to the next cache line */ desc_cb->page_offset += truesize; - if (desc_cb->page_offset + truesize <= hnae3_page_size(ring)) { + if (desc_cb->page_offset + truesize <= hns3_page_size(ring)) { desc_cb->reuse_flag = 1; /* Bump ref count on page before it is given */ get_page(desc_cb->priv); @@ -2443,9 +2487,9 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info) th->check = ~tcp_v6_check(skb->len - depth, &iph->saddr, &iph->daddr, 0); } else { - netdev_err(skb->dev, - "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n", - be16_to_cpu(type), depth); + hns3_rl_err(skb->dev, + "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n", + be16_to_cpu(type), depth); return -EFAULT; } @@ -2587,7 +2631,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length, ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE); skb = ring->skb; if (unlikely(!skb)) { - netdev_err(netdev, "alloc rx skb fail\n"); + hns3_rl_err(netdev, "alloc rx skb fail\n"); u64_stats_update_begin(&ring->syncp); ring->stats.sw_err_cnt++; @@ -2662,8 +2706,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc, new_skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE); if (unlikely(!new_skb)) { - netdev_err(ring->tqp->handle->kinfo.netdev, - "alloc rx skb frag fail\n"); + hns3_rl_err(ring->tqp_vector->napi.dev, + "alloc rx fraglist skb fail\n"); return -ENXIO; } ring->frag_num = 0; @@ -2678,7 +2722,7 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc, } if (ring->tail_skb) { - head_skb->truesize += hnae3_buf_size(ring); + head_skb->truesize += hns3_buf_size(ring); head_skb->data_len += le16_to_cpu(desc->rx.size); head_skb->len += le16_to_cpu(desc->rx.size); skb = ring->tail_skb; @@ -2895,24 +2939,22 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *)) { #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16 - int recv_pkts, recv_bds, clean_count, err; int unused_count = hns3_desc_unused(ring); struct sk_buff *skb = ring->skb; - int num; + int recv_pkts = 0; + int recv_bds = 0; + int err, num; num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG); rmb(); /* Make sure num taken effect before the other data is touched */ - recv_pkts = 0, recv_bds = 0, clean_count = 0; num -= unused_count; unused_count -= ring->pending_buf; while (recv_pkts < budget && recv_bds < num) { /* Reuse or realloc buffers */ - if (clean_count + unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { - hns3_nic_alloc_rx_buffers(ring, - clean_count + unused_count); - clean_count = 0; + if (unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { + hns3_nic_alloc_rx_buffers(ring, unused_count); unused_count = hns3_desc_unused(ring) - ring->pending_buf; } @@ -2926,7 +2968,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, goto out; } else if (unlikely(err)) { /* Do jump the err */ recv_bds += ring->pending_buf; - clean_count += ring->pending_buf; + unused_count += ring->pending_buf; ring->skb = NULL; ring->pending_buf = 0; continue; @@ -2934,7 +2976,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, rx_fn(ring, skb); recv_bds += ring->pending_buf; - clean_count += ring->pending_buf; + unused_count += ring->pending_buf; ring->skb = NULL; ring->pending_buf = 0; @@ -2943,8 +2985,8 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, out: /* Make all data has been write before submit */ - if (clean_count + unused_count > 0) - hns3_nic_alloc_rx_buffers(ring, clean_count + unused_count); + if (unused_count > 0) + hns3_nic_alloc_rx_buffers(ring, unused_count); return recv_pkts; } @@ -3574,7 +3616,7 @@ out: return ret; } -static void hns3_fini_ring(struct hns3_enet_ring *ring) +void hns3_fini_ring(struct hns3_enet_ring *ring) { hns3_free_desc(ring); devm_kfree(ring_to_dev(ring), ring->desc_cb); @@ -4165,8 +4207,8 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h) static void hns3_store_coal(struct hns3_nic_priv *priv) { /* ethtool only support setting and querying one coal - * configuation for now, so save the vector 0' coal - * configuation here in order to restore it. + * configuration for now, so save the vector 0' coal + * configuration here in order to restore it. */ memcpy(&priv->tx_coal, &priv->tqp_vector[0].tx_group.coal, sizeof(struct hns3_enet_coalesce)); @@ -4378,6 +4420,9 @@ int hns3_set_channels(struct net_device *netdev, u16 org_tqp_num; int ret; + if (hns3_nic_resetting(netdev)) + return -EBUSY; + if (ch->rx_count || ch->tx_count) return -EINVAL; @@ -4392,6 +4437,10 @@ int hns3_set_channels(struct net_device *netdev, if (kinfo->rss_size == new_tqp_num) return 0; + netif_dbg(h, drv, netdev, + "set channels: tqp_num=%u, rxfh=%d\n", + new_tqp_num, rxfh_configured); + ret = hns3_reset_notify(h, HNAE3_DOWN_CLIENT); if (ret) return ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 848b866761df..e37e64e70d8d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -75,7 +75,7 @@ enum hns3_nic_state { #define HNS3_TX_TIMEOUT (5 * HZ) #define HNS3_RING_NAME_LEN 16 #define HNS3_BUFFER_SIZE_2048 2048 -#define HNS3_RING_MAX_PENDING 32768 +#define HNS3_RING_MAX_PENDING 32760 #define HNS3_RING_MIN_PENDING 24 #define HNS3_RING_BD_MULTIPLE 8 /* max frame size of mac */ @@ -195,7 +195,8 @@ enum hns3_nic_state { #define HNS3_VECTOR_INITED 1 #define HNS3_MAX_BD_SIZE 65535 -#define HNS3_MAX_BD_PER_FRAG 8 +#define HNS3_MAX_BD_NUM_NORMAL 8 +#define HNS3_MAX_BD_NUM_TSO 63 #define HNS3_MAX_BD_PER_PKT MAX_SKB_FRAGS #define HNS3_VECTOR_GL0_OFFSET 0x100 @@ -301,7 +302,7 @@ struct hns3_desc_cb { dma_addr_t dma; /* dma address of this desc */ void *buf; /* cpu addr for a desc */ - /* priv data for the desc, e.g. skb when use with ip stack*/ + /* priv data for the desc, e.g. skb when use with ip stack */ void *priv; u32 page_offset; u32 length; /* length of the buffer */ @@ -324,11 +325,11 @@ enum hns3_pkt_l3type { HNS3_L3_TYPE_MAC_PAUSE, HNS3_L3_TYPE_PFC_PAUSE,/* 0x9*/ - /* reserved for 0xA~0xB*/ + /* reserved for 0xA~0xB */ HNS3_L3_TYPE_CNM = 0xc, - /* reserved for 0xD~0xE*/ + /* reserved for 0xD~0xE */ HNS3_L3_TYPE_PARSE_FAIL = 0xf /* must be last */ }; @@ -353,7 +354,7 @@ enum hns3_pkt_ol3type { HNS3_OL3_TYPE_IPV4_OPT = 4, HNS3_OL3_TYPE_IPV6_EXT, - /* reserved for 0x6~0xE*/ + /* reserved for 0x6~0xE */ HNS3_OL3_TYPE_PARSE_FAIL = 0xf /* must be last */ }; @@ -377,6 +378,10 @@ struct ring_stats { u64 restart_queue; u64 tx_busy; u64 tx_copy; + u64 tx_vlan_err; + u64 tx_l4_proto_err; + u64 tx_l2l3l4_err; + u64 tx_tso_err; }; struct { u64 rx_pkts; @@ -608,9 +613,18 @@ static inline bool hns3_nic_resetting(struct net_device *netdev) #define tx_ring_data(priv, idx) ((priv)->ring_data[idx]) -#define hnae3_buf_size(_ring) ((_ring)->buf_size) -#define hnae3_page_order(_ring) (get_order(hnae3_buf_size(_ring))) -#define hnae3_page_size(_ring) (PAGE_SIZE << (u32)hnae3_page_order(_ring)) +#define hns3_buf_size(_ring) ((_ring)->buf_size) + +static inline unsigned int hns3_page_order(struct hns3_enet_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->buf_size > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define hns3_page_size(_ring) (PAGE_SIZE << hns3_page_order(_ring)) /* iterator for handling rings in ring group */ #define hns3_for_each_ring(pos, head) \ @@ -633,6 +647,7 @@ void hns3_clean_tx_ring(struct hns3_enet_ring *ring); int hns3_init_all_ring(struct hns3_nic_priv *priv); int hns3_uninit_all_ring(struct hns3_nic_priv *priv); int hns3_nic_reset_all_ring(struct hnae3_handle *h); +void hns3_fini_ring(struct hns3_enet_ring *ring); netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev); bool hns3_is_phys_func(struct pci_dev *pdev); int hns3_clean_rx_ring( diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 5bff98a9b0dc..0332d6fb4c0d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -30,6 +30,10 @@ static const struct hns3_stats hns3_txq_stats[] = { HNS3_TQP_STAT("wake", restart_queue), HNS3_TQP_STAT("busy", tx_busy), HNS3_TQP_STAT("copy", tx_copy), + HNS3_TQP_STAT("vlan_err", tx_vlan_err), + HNS3_TQP_STAT("l4_proto_err", tx_l4_proto_err), + HNS3_TQP_STAT("l2l3l4_err", tx_l2l3l4_err), + HNS3_TQP_STAT("tso_err", tx_tso_err), }; #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats) @@ -311,6 +315,8 @@ static void hns3_self_test(struct net_device *ndev, if (eth_test->flags != ETH_TEST_FL_OFFLINE) return; + netif_dbg(h, drv, ndev, "self test start"); + st_param[HNAE3_LOOP_APP][0] = HNAE3_LOOP_APP; st_param[HNAE3_LOOP_APP][1] = h->flags & HNAE3_SUPPORT_APP_LOOPBACK; @@ -374,6 +380,8 @@ static void hns3_self_test(struct net_device *ndev, if (if_running) ndev->netdev_ops->ndo_open(ndev); + + netif_dbg(h, drv, ndev, "self test end\n"); } static int hns3_get_sset_count(struct net_device *netdev, int stringset) @@ -527,6 +535,7 @@ static void hns3_get_drvinfo(struct net_device *netdev, { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = priv->ae_handle; + u32 fw_version; if (!h->ae_algo->ops->get_fw_version) { netdev_err(netdev, "could not get fw version!\n"); @@ -545,8 +554,18 @@ static void hns3_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->bus_info)); drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "0x%08x", - priv->ae_handle->ae_algo->ops->get_fw_version(h)); + fw_version = priv->ae_handle->ae_algo->ops->get_fw_version(h); + + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%lu.%lu.%lu.%lu", + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE3_MASK, + HNAE3_FW_VERSION_BYTE3_SHIFT), + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE2_MASK, + HNAE3_FW_VERSION_BYTE2_SHIFT), + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE1_MASK, + HNAE3_FW_VERSION_BYTE1_SHIFT), + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE0_MASK, + HNAE3_FW_VERSION_BYTE0_SHIFT)); } static u32 hns3_get_link(struct net_device *netdev) @@ -593,6 +612,10 @@ static int hns3_set_pauseparam(struct net_device *netdev, { struct hnae3_handle *h = hns3_get_handle(netdev); + netif_dbg(h, drv, netdev, + "set pauseparam: autoneg=%u, rx:%u, tx:%u\n", + param->autoneg, param->rx_pause, param->tx_pause); + if (h->ae_algo->ops->set_pauseparam) return h->ae_algo->ops->set_pauseparam(h, param->autoneg, param->rx_pause, @@ -612,7 +635,7 @@ static void hns3_get_ksettings(struct hnae3_handle *h, &cmd->base.speed, &cmd->base.duplex); - /* 2.get link mode*/ + /* 2.get link mode */ if (ops->get_link_mode) ops->get_link_mode(h, cmd->link_modes.supported, @@ -681,7 +704,7 @@ static int hns3_get_link_ksettings(struct net_device *netdev, return 0; } -static int hns3_check_ksettings_param(struct net_device *netdev, +static int hns3_check_ksettings_param(const struct net_device *netdev, const struct ethtool_link_ksettings *cmd) { struct hnae3_handle *handle = hns3_get_handle(netdev); @@ -726,12 +749,17 @@ static int hns3_set_link_ksettings(struct net_device *netdev, { struct hnae3_handle *handle = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops = handle->ae_algo->ops; - int ret = 0; + int ret; /* Chip don't support this mode. */ if (cmd->base.speed == SPEED_1000 && cmd->base.duplex == DUPLEX_HALF) return -EINVAL; + netif_dbg(handle, drv, netdev, + "set link(%s): autoneg=%u, speed=%u, duplex=%u\n", + netdev->phydev ? "phy" : "mac", + cmd->base.autoneg, cmd->base.speed, cmd->base.duplex); + /* Only support ksettings_set for netdev with phy attached for now */ if (netdev->phydev) return phy_ethtool_ksettings_set(netdev->phydev, cmd); @@ -843,8 +871,8 @@ static int hns3_get_rxnfc(struct net_device *netdev, } } -static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, - u32 tx_desc_num, u32 rx_desc_num) +static void hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, + u32 tx_desc_num, u32 rx_desc_num) { struct hnae3_handle *h = priv->ae_handle; int i; @@ -857,21 +885,29 @@ static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, priv->ring_data[i + h->kinfo.num_tqps].ring->desc_num = rx_desc_num; } - - return hns3_init_all_ring(priv); } -static int hns3_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *param) +static struct hns3_enet_ring *hns3_backup_ringparam(struct hns3_nic_priv *priv) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; - bool if_running = netif_running(ndev); - u32 old_tx_desc_num, new_tx_desc_num; - u32 old_rx_desc_num, new_rx_desc_num; - int queue_num = h->kinfo.num_tqps; - int ret; + struct hnae3_handle *handle = priv->ae_handle; + struct hns3_enet_ring *tmp_rings; + int i; + + tmp_rings = kcalloc(handle->kinfo.num_tqps * 2, + sizeof(struct hns3_enet_ring), GFP_KERNEL); + if (!tmp_rings) + return NULL; + + for (i = 0; i < handle->kinfo.num_tqps * 2; i++) + memcpy(&tmp_rings[i], priv->ring_data[i].ring, + sizeof(struct hns3_enet_ring)); + + return tmp_rings; +} +static int hns3_check_ringparam(struct net_device *ndev, + struct ethtool_ringparam *param) +{ if (hns3_nic_resetting(ndev)) return -EBUSY; @@ -887,6 +923,25 @@ static int hns3_set_ringparam(struct net_device *ndev, return -EINVAL; } + return 0; +} + +static int hns3_set_ringparam(struct net_device *ndev, + struct ethtool_ringparam *param) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + struct hns3_enet_ring *tmp_rings; + bool if_running = netif_running(ndev); + u32 old_tx_desc_num, new_tx_desc_num; + u32 old_rx_desc_num, new_rx_desc_num; + u16 queue_num = h->kinfo.num_tqps; + int ret, i; + + ret = hns3_check_ringparam(ndev, param); + if (ret) + return ret; + /* Hardware requires that its descriptors must be multiple of eight */ new_tx_desc_num = ALIGN(param->tx_pending, HNS3_RING_BD_MULTIPLE); new_rx_desc_num = ALIGN(param->rx_pending, HNS3_RING_BD_MULTIPLE); @@ -896,6 +951,13 @@ static int hns3_set_ringparam(struct net_device *ndev, old_rx_desc_num == new_rx_desc_num) return 0; + tmp_rings = hns3_backup_ringparam(priv); + if (!tmp_rings) { + netdev_err(ndev, + "backup ring param failed by allocating memory fail\n"); + return -ENOMEM; + } + netdev_info(ndev, "Changing Tx/Rx ring depth from %d/%d to %d/%d\n", old_tx_desc_num, old_rx_desc_num, @@ -904,22 +966,24 @@ static int hns3_set_ringparam(struct net_device *ndev, if (if_running) ndev->netdev_ops->ndo_stop(ndev); - ret = hns3_uninit_all_ring(priv); - if (ret) - return ret; - - ret = hns3_change_all_ring_bd_num(priv, new_tx_desc_num, - new_rx_desc_num); + hns3_change_all_ring_bd_num(priv, new_tx_desc_num, new_rx_desc_num); + ret = hns3_init_all_ring(priv); if (ret) { - ret = hns3_change_all_ring_bd_num(priv, old_tx_desc_num, - old_rx_desc_num); - if (ret) { - netdev_err(ndev, - "Revert to old bd num fail, ret=%d.\n", ret); - return ret; - } + netdev_err(ndev, "Change bd num fail, revert to old value(%d)\n", + ret); + + hns3_change_all_ring_bd_num(priv, old_tx_desc_num, + old_rx_desc_num); + for (i = 0; i < h->kinfo.num_tqps * 2; i++) + memcpy(priv->ring_data[i].ring, &tmp_rings[i], + sizeof(struct hns3_enet_ring)); + } else { + for (i = 0; i < h->kinfo.num_tqps * 2; i++) + hns3_fini_ring(&tmp_rings[i]); } + kfree(tmp_rings); + if (if_running) ret = ndev->netdev_ops->ndo_open(ndev); @@ -973,6 +1037,9 @@ static int hns3_nway_reset(struct net_device *netdev) return -EINVAL; } + netif_dbg(handle, drv, netdev, + "nway reset (using %s)\n", phy ? "phy" : "mac"); + if (phy) return genphy_restart_aneg(phy); @@ -1297,6 +1364,9 @@ static int hns3_set_fecparam(struct net_device *netdev, if (!ops->set_fec) return -EOPNOTSUPP; fec_mode = eth_to_loc_fec(fec->fec); + + netif_dbg(handle, drv, netdev, "set fecparam: mode=%u\n", fec_mode); + return ops->set_fec(handle, fec_mode); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 22f6acd45d9a..ecf58cfd253d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -103,14 +103,17 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring) dma_addr_t dma = ring->desc_dma_addr; struct hclge_dev *hdev = ring->dev; struct hclge_hw *hw = &hdev->hw; + u32 reg_val; if (ring->ring_type == HCLGE_TYPE_CSQ) { hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG, lower_32_bits(dma)); hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG, upper_32_bits(dma)); - hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, - ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S); + reg_val = hclge_read_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG); + reg_val &= HCLGE_NIC_SW_RST_RDY; + reg_val |= ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S; + hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, reg_val); hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0); hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0); } else { @@ -383,6 +386,23 @@ err_csq: return ret; } +static int hclge_firmware_compat_config(struct hclge_dev *hdev) +{ + struct hclge_firmware_compat_cmd *req; + struct hclge_desc desc; + u32 compat = 0; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_M7_COMPAT_CFG, false); + + req = (struct hclge_firmware_compat_cmd *)desc.data; + + hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1); + hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1); + req->compat = cpu_to_le32(compat); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + int hclge_cmd_init(struct hclge_dev *hdev) { u32 version; @@ -419,7 +439,24 @@ int hclge_cmd_init(struct hclge_dev *hdev) } hdev->fw_version = version; - dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version); + dev_info(&hdev->pdev->dev, "The firmware version is %lu.%lu.%lu.%lu\n", + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE3_MASK, + HNAE3_FW_VERSION_BYTE3_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE2_MASK, + HNAE3_FW_VERSION_BYTE2_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE1_MASK, + HNAE3_FW_VERSION_BYTE1_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE0_MASK, + HNAE3_FW_VERSION_BYTE0_SHIFT)); + + /* ask the firmware to enable some features, driver can work without + * it. + */ + ret = hclge_firmware_compat_config(hdev); + if (ret) + dev_warn(&hdev->pdev->dev, + "Firmware compatible features not enabled(%d).\n", + ret); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 96840d8f3e24..29979be9e33a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -86,6 +86,8 @@ enum hclge_opcode_type { HCLGE_OPC_QUERY_PF_RSRC = 0x0023, HCLGE_OPC_QUERY_VF_RSRC = 0x0024, HCLGE_OPC_GET_CFG_PARAM = 0x0025, + HCLGE_OPC_PF_RST_DONE = 0x0026, + HCLGE_OPC_QUERY_VF_RST_RDY = 0x0027, HCLGE_OPC_STATS_64_BIT = 0x0030, HCLGE_OPC_STATS_32_BIT = 0x0031, @@ -257,6 +259,7 @@ enum hclge_opcode_type { /* M7 stats command */ HCLGE_OPC_M7_STATS_BD = 0x7012, HCLGE_OPC_M7_STATS_INFO = 0x7013, + HCLGE_OPC_M7_COMPAT_CFG = 0x701A, /* SFP command */ HCLGE_OPC_GET_SFP_INFO = 0x7104, @@ -586,6 +589,12 @@ struct hclge_config_mac_mode_cmd { u8 rsv[20]; }; +struct hclge_pf_rst_sync_cmd { +#define HCLGE_PF_RST_ALL_VF_RDY_B 0 + u8 all_vf_ready; + u8 rsv[23]; +}; + #define HCLGE_CFG_SPEED_S 0 #define HCLGE_CFG_SPEED_M GENMASK(5, 0) @@ -827,7 +836,7 @@ struct hclge_mac_ethertype_idx_rd_cmd { u8 flags; u8 resp_code; __le16 vlan_tag; - u8 mac_add[6]; + u8 mac_addr[6]; __le16 index; __le16 ethter_type; __le16 egress_port; @@ -877,6 +886,13 @@ struct hclge_reset_cmd { u8 rsv[22]; }; +#define HCLGE_PF_RESET_DONE_BIT BIT(0) + +struct hclge_pf_rst_done_cmd { + u8 pf_rst_done; + u8 rsv[23]; +}; + #define HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B BIT(0) #define HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B BIT(2) #define HCLGE_CMD_SERDES_DONE_B BIT(0) @@ -906,8 +922,11 @@ struct hclge_serdes_lb_cmd { #define HCLGE_NIC_CRQ_DEPTH_REG 0x27020 #define HCLGE_NIC_CRQ_TAIL_REG 0x27024 #define HCLGE_NIC_CRQ_HEAD_REG 0x27028 -#define HCLGE_NIC_CMQ_EN_B 16 -#define HCLGE_NIC_CMQ_ENABLE BIT(HCLGE_NIC_CMQ_EN_B) + +/* this bit indicates that the driver is ready for hardware reset */ +#define HCLGE_NIC_SW_RST_RDY_B 16 +#define HCLGE_NIC_SW_RST_RDY BIT(HCLGE_NIC_SW_RST_RDY_B) + #define HCLGE_NIC_CMQ_DESC_NUM 1024 #define HCLGE_NIC_CMQ_DESC_NUM_S 3 @@ -1009,6 +1028,13 @@ struct hclge_query_ppu_pf_other_int_dfx_cmd { u8 rsv[4]; }; +#define HCLGE_LINK_EVENT_REPORT_EN_B 0 +#define HCLGE_NCSI_ERROR_REPORT_EN_B 1 +struct hclge_firmware_compat_cmd { + __le32 compat; + u8 rsv[20]; +}; + int hclge_cmd_init(struct hclge_dev *hdev); static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index bac4ce13f6ae..814e0f076e32 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -201,6 +201,7 @@ static int hclge_client_setup_tc(struct hclge_dev *hdev) static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) { struct hclge_vport *vport = hclge_get_vport(h); + struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; bool map_changed = false; u8 num_tc = 0; @@ -215,6 +216,8 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) return ret; if (map_changed) { + netif_dbg(h, drv, netdev, "set ets\n"); + ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT); if (ret) return ret; @@ -300,6 +303,7 @@ static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) { struct hclge_vport *vport = hclge_get_vport(h); + struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; u8 i, j, pfc_map, *prio_tc; @@ -325,6 +329,10 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) hdev->tm_info.hw_pfc_map = pfc_map; hdev->tm_info.pfc_en = pfc->pfc_en; + netif_dbg(h, drv, netdev, + "set pfc: pfc_en=%u, pfc_map=%u, num_tc=%u\n", + pfc->pfc_en, pfc_map, hdev->tm_info.num_tc); + hclge_tm_pfc_info_update(hdev); return hclge_pause_setup_hw(hdev, false); @@ -345,8 +353,11 @@ static u8 hclge_getdcbx(struct hnae3_handle *h) static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode) { struct hclge_vport *vport = hclge_get_vport(h); + struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; + netif_dbg(h, drv, netdev, "set dcbx: mode=%u\n", mode); + /* No support for LLD_MANAGED modes or CEE */ if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || (mode & DCB_CAP_DCBX_VER_CEE) || diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index ab625c757a95..025184a0c839 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -14,16 +14,8 @@ static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset) struct hclge_desc desc[4]; int ret; - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true); - desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true); - desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true); - desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true); - - ret = hclge_cmd_send(&hdev->hw, desc, 4); - if (ret != HCLGE_CMD_EXEC_SUCCESS) { + ret = hclge_query_bd_num_cmd_send(hdev, desc); + if (ret) { dev_err(&hdev->pdev->dev, "get dfx bdnum fail, status is %d.\n", ret); return ret; @@ -325,6 +317,12 @@ static void hclge_dbg_dump_tc(struct hclge_dev *hdev) struct hclge_desc desc; int i, ret; + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports tc\n"); + return; + } + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -409,6 +407,12 @@ static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev) dev_info(&hdev->pdev->dev, "QS_SCH qs_id: %u\n", desc.data[0]); + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports tm mapping\n"); + return; + } + cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING; hclge_cmd_setup_basic_desc(&desc, cmd, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -590,6 +594,12 @@ static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, dev_info(&hdev->pdev->dev, "%04d | %04d | %02d | %02d\n", queue_id, qset_id, pri_id, tc_id); + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports tm mapping\n"); + return; + } + 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++) { @@ -715,6 +725,34 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) dev_info(&hdev->pdev->dev, "rx_share_buf: 0x%x\n", rx_buf_cmd->shared_buf); + cmd = HCLGE_OPC_RX_COM_WL_ALLOC; + hclge_cmd_setup_basic_desc(desc, cmd, true); + ret = hclge_cmd_send(&hdev->hw, desc, 1); + if (ret) + goto err_qos_cmd_send; + + rx_com_wl = (struct hclge_rx_com_wl *)desc[0].data; + dev_info(&hdev->pdev->dev, "\n"); + dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n", + rx_com_wl->com_wl.high, rx_com_wl->com_wl.low); + + cmd = HCLGE_OPC_RX_GBL_PKT_CNT; + hclge_cmd_setup_basic_desc(desc, cmd, true); + ret = hclge_cmd_send(&hdev->hw, desc, 1); + if (ret) + goto err_qos_cmd_send; + + rx_packet_cnt = (struct hclge_rx_com_wl *)desc[0].data; + dev_info(&hdev->pdev->dev, + "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n", + rx_packet_cnt->com_wl.high, rx_packet_cnt->com_wl.low); + dev_info(&hdev->pdev->dev, "\n"); + + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports rx priv wl\n"); + return; + } cmd = HCLGE_OPC_RX_PRIV_WL_ALLOC; hclge_cmd_setup_basic_desc(&desc[0], cmd, true); desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); @@ -723,7 +761,6 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) if (ret) goto err_qos_cmd_send; - dev_info(&hdev->pdev->dev, "\n"); rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[0].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) dev_info(&hdev->pdev->dev, @@ -758,29 +795,6 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i + 4, rx_com_thrd->com_thrd[i].high, rx_com_thrd->com_thrd[i].low); - - cmd = HCLGE_OPC_RX_COM_WL_ALLOC; - hclge_cmd_setup_basic_desc(desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, desc, 1); - if (ret) - goto err_qos_cmd_send; - - rx_com_wl = (struct hclge_rx_com_wl *)desc[0].data; - dev_info(&hdev->pdev->dev, "\n"); - dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n", - rx_com_wl->com_wl.high, rx_com_wl->com_wl.low); - - cmd = HCLGE_OPC_RX_GBL_PKT_CNT; - hclge_cmd_setup_basic_desc(desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, desc, 1); - if (ret) - goto err_qos_cmd_send; - - rx_packet_cnt = (struct hclge_rx_com_wl *)desc[0].data; - dev_info(&hdev->pdev->dev, - "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n", - rx_packet_cnt->com_wl.high, rx_packet_cnt->com_wl.low); - return; err_qos_cmd_send: @@ -825,9 +839,9 @@ static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev) memset(printf_buf, 0, HCLGE_DBG_BUF_LEN); snprintf(printf_buf, HCLGE_DBG_BUF_LEN, "%02u |%02x:%02x:%02x:%02x:%02x:%02x|", - req0->index, req0->mac_add[0], req0->mac_add[1], - req0->mac_add[2], req0->mac_add[3], req0->mac_add[4], - req0->mac_add[5]); + req0->index, req0->mac_addr[0], req0->mac_addr[1], + req0->mac_addr[2], req0->mac_addr[3], + req0->mac_addr[4], req0->mac_addr[5]); snprintf(printf_buf + strlen(printf_buf), HCLGE_DBG_BUF_LEN - strlen(printf_buf), @@ -883,14 +897,17 @@ static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage, dev_info(&hdev->pdev->dev, " read result tcam key %s(%u):\n", sel_x ? "x" : "y", loc); + /* tcam_data0 ~ tcam_data1 */ req = (u32 *)req1->tcam_data; for (i = 0; i < 2; i++) dev_info(&hdev->pdev->dev, "%08x\n", *req++); + /* tcam_data2 ~ tcam_data7 */ req = (u32 *)req2->tcam_data; for (i = 0; i < 6; i++) dev_info(&hdev->pdev->dev, "%08x\n", *req++); + /* tcam_data8 ~ tcam_data12 */ req = (u32 *)req3->tcam_data; for (i = 0; i < 5; i++) dev_info(&hdev->pdev->dev, "%08x\n", *req++); @@ -981,6 +998,33 @@ void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) kfree(desc_src); } +#define HCLGE_CMD_NCL_CONFIG_BD_NUM 5 + +static void hclge_ncl_config_data_print(struct hclge_dev *hdev, + struct hclge_desc *desc, int *offset, + int *length) +{ +#define HCLGE_CMD_DATA_NUM 6 + + int i; + int j; + + for (i = 0; i < HCLGE_CMD_NCL_CONFIG_BD_NUM; i++) { + for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) { + if (i == 0 && j == 0) + continue; + + dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n", + *offset, + le32_to_cpu(desc[i].data[j])); + *offset += sizeof(u32); + *length -= sizeof(u32); + if (*length <= 0) + return; + } + } +} + /* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file * @hdev: pointer to struct hclge_dev * @cmd_buf: string that contains offset and length @@ -990,17 +1034,13 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, { #define HCLGE_MAX_NCL_CONFIG_OFFSET 4096 #define HCLGE_MAX_NCL_CONFIG_LENGTH (20 + 24 * 4) -#define HCLGE_CMD_DATA_NUM 6 - struct hclge_desc desc[5]; - u32 byte_offset; - int bd_num = 5; + struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM]; + int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM; int offset; int length; int data0; int ret; - int i; - int j; ret = sscanf(cmd_buf, "%x %x", &offset, &length); if (ret != 2 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET || @@ -1026,22 +1066,7 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, if (ret) return; - byte_offset = offset; - for (i = 0; i < bd_num; i++) { - for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) { - if (i == 0 && j == 0) - continue; - - dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n", - byte_offset, - le32_to_cpu(desc[i].data[j])); - byte_offset += sizeof(u32); - length -= sizeof(u32); - if (length <= 0) - return; - } - } - offset += HCLGE_MAX_NCL_CONFIG_LENGTH; + hclge_ncl_config_data_print(hdev, desc, &offset, &length); } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 0a7243825e7b..2425b3f53ad8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -637,8 +637,8 @@ static void hclge_log_error(struct device *dev, char *reg, { while (err->msg) { if (err->int_msk & err_sts) { - dev_warn(dev, "%s %s found [error status=0x%x]\n", - reg, err->msg, err_sts); + dev_err(dev, "%s %s found [error status=0x%x]\n", + reg, err->msg, err_sts); if (err->reset_level && err->reset_level != HNAE3_NONE_RESET) set_bit(err->reset_level, reset_requests); @@ -652,16 +652,11 @@ static void hclge_log_error(struct device *dev, char *reg, * @desc: descriptor for describing the command * @cmd: command opcode * @flag: flag for extended command structure - * @w_num: offset for setting the read interrupt type. - * @int_type: select which type of the interrupt for which the error - * info will be read(RAS-CE/RAS-NFE/RAS-FE etc). * * This function query the error info from hw register/s using command */ static int hclge_cmd_query_error(struct hclge_dev *hdev, - struct hclge_desc *desc, u32 cmd, - u16 flag, u8 w_num, - enum hclge_err_int_type int_type) + struct hclge_desc *desc, u32 cmd, u16 flag) { struct device *dev = &hdev->pdev->dev; int desc_num = 1; @@ -673,8 +668,6 @@ static int hclge_cmd_query_error(struct hclge_dev *hdev, hclge_cmd_setup_basic_desc(&desc[1], cmd, true); desc_num = 2; } - if (w_num) - desc[0].data[w_num] = cpu_to_le32(int_type); ret = hclge_cmd_send(&hdev->hw, &desc[0], desc_num); if (ret) @@ -872,8 +865,7 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en) } /* configure TM QCN hw errors */ - ret = hclge_cmd_query_error(hdev, &desc, HCLGE_TM_QCN_MEM_INT_CFG, - 0, 0, 0); + ret = hclge_cmd_query_error(hdev, &desc, HCLGE_TM_QCN_MEM_INT_CFG, 0); if (ret) { dev_err(dev, "fail(%d) to read TM QCN CFG status\n", ret); return ret; @@ -1171,8 +1163,8 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev, status = le32_to_cpu(*(desc_data + 3)) & BIT(0); if (status) { - dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n", - status); + dev_err(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n", + status); set_bit(HNAE3_GLOBAL_RESET, &ae_dev->hw_err_reset_req); } @@ -1208,8 +1200,8 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev, desc_data = (__le32 *)&desc[5]; status = le32_to_cpu(*(desc_data + 1)); if (status) { - dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST1 %s found\n", - "rpu_rx_pkt_ecc_mbit_err"); + dev_err(dev, + "PPU_MPF_ABNORMAL_INT_ST1 rpu_rx_pkt_ecc_mbit_err found\n"); set_bit(HNAE3_GLOBAL_RESET, &ae_dev->hw_err_reset_req); } @@ -1387,17 +1379,17 @@ static int hclge_log_rocee_axi_error(struct hclge_dev *hdev) return ret; } - dev_info(dev, "AXI1: %08X %08X %08X %08X %08X %08X\n", - le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), - le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), - le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); - dev_info(dev, "AXI2: %08X %08X %08X %08X %08X %08X\n", - le32_to_cpu(desc[1].data[0]), le32_to_cpu(desc[1].data[1]), - le32_to_cpu(desc[1].data[2]), le32_to_cpu(desc[1].data[3]), - le32_to_cpu(desc[1].data[4]), le32_to_cpu(desc[1].data[5])); - dev_info(dev, "AXI3: %08X %08X %08X %08X\n", - le32_to_cpu(desc[2].data[0]), le32_to_cpu(desc[2].data[1]), - le32_to_cpu(desc[2].data[2]), le32_to_cpu(desc[2].data[3])); + dev_err(dev, "AXI1: %08X %08X %08X %08X %08X %08X\n", + le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), + le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), + le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); + dev_err(dev, "AXI2: %08X %08X %08X %08X %08X %08X\n", + le32_to_cpu(desc[1].data[0]), le32_to_cpu(desc[1].data[1]), + le32_to_cpu(desc[1].data[2]), le32_to_cpu(desc[1].data[3]), + le32_to_cpu(desc[1].data[4]), le32_to_cpu(desc[1].data[5])); + dev_err(dev, "AXI3: %08X %08X %08X %08X\n", + le32_to_cpu(desc[2].data[0]), le32_to_cpu(desc[2].data[1]), + le32_to_cpu(desc[2].data[2]), le32_to_cpu(desc[2].data[3])); return 0; } @@ -1410,18 +1402,18 @@ static int hclge_log_rocee_ecc_error(struct hclge_dev *hdev) ret = hclge_cmd_query_error(hdev, &desc[0], HCLGE_QUERY_ROCEE_ECC_RAS_INFO_CMD, - HCLGE_CMD_FLAG_NEXT, 0, 0); + HCLGE_CMD_FLAG_NEXT); if (ret) { dev_err(dev, "failed(%d) to query ROCEE ECC error sts\n", ret); return ret; } - dev_info(dev, "ECC1: %08X %08X %08X %08X %08X %08X\n", - le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), - le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), - le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); - dev_info(dev, "ECC2: %08X %08X %08X\n", le32_to_cpu(desc[1].data[0]), - le32_to_cpu(desc[1].data[1]), le32_to_cpu(desc[1].data[2])); + dev_err(dev, "ECC1: %08X %08X %08X %08X %08X %08X\n", + le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), + le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), + le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); + dev_err(dev, "ECC2: %08X %08X %08X\n", le32_to_cpu(desc[1].data[0]), + le32_to_cpu(desc[1].data[1]), le32_to_cpu(desc[1].data[2])); return 0; } @@ -1434,7 +1426,7 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev) /* read overflow error status */ ret = hclge_cmd_query_error(hdev, &desc[0], HCLGE_ROCEE_PF_RAS_INT_CMD, - 0, 0, 0); + 0); if (ret) { dev_err(dev, "failed(%d) to query ROCEE OVF error sts\n", ret); return ret; @@ -1450,9 +1442,9 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev) le32_to_cpu(desc[0].data[0]); while (err->msg) { if (err->int_msk == err_sts) { - dev_warn(dev, "%s [error status=0x%x] found\n", - err->msg, - le32_to_cpu(desc[0].data[0])); + dev_err(dev, "%s [error status=0x%x] found\n", + err->msg, + le32_to_cpu(desc[0].data[0])); break; } err++; @@ -1460,13 +1452,13 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev) } if (le32_to_cpu(desc[0].data[1]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) { - dev_warn(dev, "ROCEE TSP OVF [error status=0x%x] found\n", - le32_to_cpu(desc[0].data[1])); + dev_err(dev, "ROCEE TSP OVF [error status=0x%x] found\n", + le32_to_cpu(desc[0].data[1])); } if (le32_to_cpu(desc[0].data[2]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) { - dev_warn(dev, "ROCEE SCC OVF [error status=0x%x] found\n", - le32_to_cpu(desc[0].data[2])); + dev_err(dev, "ROCEE SCC OVF [error status=0x%x] found\n", + le32_to_cpu(desc[0].data[2])); } return 0; @@ -1483,8 +1475,7 @@ hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev) /* read RAS error interrupt status */ ret = hclge_cmd_query_error(hdev, &desc[0], - HCLGE_QUERY_CLEAR_ROCEE_RAS_INT, - 0, 0, 0); + HCLGE_QUERY_CLEAR_ROCEE_RAS_INT, 0); if (ret) { dev_err(dev, "failed(%d) to query ROCEE RAS INT SRC\n", ret); /* reset everything for now */ @@ -1495,10 +1486,10 @@ hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev) if (status & HCLGE_ROCEE_AXI_ERR_INT_MASK) { if (status & HCLGE_ROCEE_RERR_INT_MASK) - dev_warn(dev, "ROCEE RAS AXI rresp error\n"); + dev_err(dev, "ROCEE RAS AXI rresp error\n"); if (status & HCLGE_ROCEE_BERR_INT_MASK) - dev_warn(dev, "ROCEE RAS AXI bresp error\n"); + dev_err(dev, "ROCEE RAS AXI bresp error\n"); reset_type = HNAE3_FUNC_RESET; @@ -1508,7 +1499,7 @@ hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev) } if (status & HCLGE_ROCEE_ECC_INT_MASK) { - dev_warn(dev, "ROCEE RAS 2bit ECC error\n"); + dev_err(dev, "ROCEE RAS 2bit ECC error\n"); reset_type = HNAE3_GLOBAL_RESET; ret = hclge_log_rocee_ecc_error(hdev); @@ -1566,8 +1557,8 @@ int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en) static void hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev) { - enum hnae3_reset_type reset_type = HNAE3_NONE_RESET; struct hclge_dev *hdev = ae_dev->priv; + enum hnae3_reset_type reset_type; if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || hdev->pdev->revision < 0x21) @@ -1649,16 +1640,16 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev) /* Handling Non-fatal HNS RAS errors */ if (status & HCLGE_RAS_REG_NFE_MASK) { - dev_warn(dev, - "HNS Non-Fatal RAS error(status=0x%x) identified\n", - status); + dev_err(dev, + "HNS Non-Fatal RAS error(status=0x%x) identified\n", + status); hclge_handle_all_ras_errors(hdev); } /* Handling Non-fatal Rocee RAS errors */ if (hdev->pdev->revision >= 0x21 && status & HCLGE_RAS_REG_ROCEE_ERR_MASK) { - dev_warn(dev, "ROCEE Non-Fatal RAS error identified\n"); + dev_err(dev, "ROCEE Non-Fatal RAS error identified\n"); hclge_handle_rocee_ras_error(ae_dev); } @@ -1737,8 +1728,8 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev, return; } - dev_warn(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vf_id(%d), queue_id(%d)\n", - vf_id, q_id); + dev_err(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vf_id(%u), queue_id(%u)\n", + vf_id, q_id); if (vf_id) { if (vf_id >= hdev->num_alloc_vport) { @@ -1755,8 +1746,8 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev, ret = hclge_inform_reset_assert_to_vf(&hdev->vport[vf_id]); if (ret) - dev_warn(dev, "inform reset to vf(%d) failed %d!\n", - hdev->vport->vport_id, ret); + dev_err(dev, "inform reset to vf(%u) failed %d!\n", + hdev->vport->vport_id, ret); } else { set_bit(HNAE3_FUNC_RESET, reset_requests); } @@ -1802,8 +1793,8 @@ static int hclge_handle_mpf_msix_error(struct hclge_dev *hdev, status = le32_to_cpu(*(desc_data + 2)) & HCLGE_PPU_MPF_INT_ST2_MSIX_MASK; if (status) - dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST2 rx_q_search_miss found [dfx status=0x%x\n]", - status); + dev_err(dev, "PPU_MPF_ABNORMAL_INT_ST2 rx_q_search_miss found [dfx status=0x%x\n]", + status); /* clear all main PF MSIx errors */ ret = hclge_clear_hw_msix_error(hdev, desc, true, mpf_bd_num); @@ -1997,7 +1988,7 @@ void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev) /* Handle Non-fatal HNS RAS errors */ if (status & HCLGE_RAS_REG_NFE_MASK) { - dev_warn(dev, "HNS hw error(RAS) identified during init\n"); + dev_err(dev, "HNS hw error(RAS) identified during init\n"); hclge_handle_all_ras_errors(hdev); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 3fde5471e1c0..9d64c4304e5e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -35,6 +35,23 @@ #define BUF_RESERVE_PERCENT 90 #define HCLGE_RESET_MAX_FAIL_CNT 5 +#define HCLGE_RESET_SYNC_TIME 100 +#define HCLGE_PF_RESET_SYNC_TIME 20 +#define HCLGE_PF_RESET_SYNC_CNT 1500 + +/* Get DFX BD number offset */ +#define HCLGE_DFX_BIOS_BD_OFFSET 1 +#define HCLGE_DFX_SSU_0_BD_OFFSET 2 +#define HCLGE_DFX_SSU_1_BD_OFFSET 3 +#define HCLGE_DFX_IGU_BD_OFFSET 4 +#define HCLGE_DFX_RPU_0_BD_OFFSET 5 +#define HCLGE_DFX_RPU_1_BD_OFFSET 6 +#define HCLGE_DFX_NCSI_BD_OFFSET 7 +#define HCLGE_DFX_RTC_BD_OFFSET 8 +#define HCLGE_DFX_PPP_BD_OFFSET 9 +#define HCLGE_DFX_RCB_BD_OFFSET 10 +#define HCLGE_DFX_TQP_BD_OFFSET 11 +#define HCLGE_DFX_SSU_2_BD_OFFSET 12 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps); static int hclge_init_vlan_config(struct hclge_dev *hdev); @@ -317,6 +334,36 @@ static const u8 hclge_hash_key[] = { 0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA }; +static const u32 hclge_dfx_bd_offset_list[] = { + HCLGE_DFX_BIOS_BD_OFFSET, + HCLGE_DFX_SSU_0_BD_OFFSET, + HCLGE_DFX_SSU_1_BD_OFFSET, + HCLGE_DFX_IGU_BD_OFFSET, + HCLGE_DFX_RPU_0_BD_OFFSET, + HCLGE_DFX_RPU_1_BD_OFFSET, + HCLGE_DFX_NCSI_BD_OFFSET, + HCLGE_DFX_RTC_BD_OFFSET, + HCLGE_DFX_PPP_BD_OFFSET, + HCLGE_DFX_RCB_BD_OFFSET, + HCLGE_DFX_TQP_BD_OFFSET, + HCLGE_DFX_SSU_2_BD_OFFSET +}; + +static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = { + HCLGE_OPC_DFX_BIOS_COMMON_REG, + HCLGE_OPC_DFX_SSU_REG_0, + HCLGE_OPC_DFX_SSU_REG_1, + HCLGE_OPC_DFX_IGU_EGU_REG, + HCLGE_OPC_DFX_RPU_REG_0, + HCLGE_OPC_DFX_RPU_REG_1, + HCLGE_OPC_DFX_NCSI_REG, + HCLGE_OPC_DFX_RTC_REG, + HCLGE_OPC_DFX_PPP_REG, + HCLGE_OPC_DFX_RCB_REG, + HCLGE_OPC_DFX_TQP_REG, + HCLGE_OPC_DFX_SSU_REG_2 +}; + static int hclge_mac_update_stats_defective(struct hclge_dev *hdev) { #define HCLGE_MAC_CMD_NUM 21 @@ -364,9 +411,13 @@ static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num) u16 i, k, n; int ret; - desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL); + /* This may be called inside atomic sections, + * so GFP_ATOMIC is more suitalbe here + */ + desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_ATOMIC); if (!desc) return -ENOMEM; + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true); ret = hclge_cmd_send(&hdev->hw, desc, desc_num); if (ret) { @@ -702,14 +753,16 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data) p = hclge_tqps_get_stats(handle, p); } -static void hclge_get_mac_pause_stat(struct hnae3_handle *handle, u64 *tx_cnt, - u64 *rx_cnt) +static void hclge_get_mac_stat(struct hnae3_handle *handle, + struct hns3_mac_stats *mac_stats) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - *tx_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num; - *rx_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num; + hclge_update_stats(handle, NULL); + + mac_stats->tx_pause_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num; + mac_stats->rx_pause_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num; } static int hclge_parse_func_status(struct hclge_dev *hdev, @@ -1075,6 +1128,7 @@ static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability) else if (media_type == HNAE3_MEDIA_TYPE_BACKPLANE) hclge_parse_backplane_link_mode(hdev, speed_ability); } + static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) { struct hclge_cfg_param_cmd *req; @@ -1270,6 +1324,12 @@ static int hclge_configure(struct hclge_dev *hdev) hclge_init_kdump_kernel_config(hdev); + /* Set the init affinity based on pci func number */ + i = cpumask_weight(cpumask_of_node(dev_to_node(&hdev->pdev->dev))); + i = i ? PCI_FUNC(hdev->pdev->devfn) % i : 0; + cpumask_set_cpu(cpumask_local_spread(i, dev_to_node(&hdev->pdev->dev)), + &hdev->affinity_mask); + return ret; } @@ -2499,22 +2559,29 @@ static void hclge_mbx_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state) && !test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state)) - schedule_work(&hdev->mbx_service_task); + queue_work_on(cpumask_first(&hdev->affinity_mask), system_wq, + &hdev->mbx_service_task); } static void hclge_reset_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state)) - schedule_work(&hdev->rst_service_task); + queue_work_on(cpumask_first(&hdev->affinity_mask), system_wq, + &hdev->rst_service_task); } -static void hclge_task_schedule(struct hclge_dev *hdev) +void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time) { if (!test_bit(HCLGE_STATE_DOWN, &hdev->state) && !test_bit(HCLGE_STATE_REMOVING, &hdev->state) && - !test_and_set_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)) - (void)schedule_work(&hdev->service_task); + !test_and_set_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)) { + hdev->hw_stats.stats_timer++; + hdev->fd_arfs_expire_timer++; + mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), + system_wq, &hdev->service_task, + delay_time); + } } static int hclge_get_mac_link_status(struct hclge_dev *hdev) @@ -2729,25 +2796,6 @@ static int hclge_get_status(struct hnae3_handle *handle) return hdev->hw.mac.link; } -static void hclge_service_timer(struct timer_list *t) -{ - struct hclge_dev *hdev = from_timer(hdev, t, service_timer); - - mod_timer(&hdev->service_timer, jiffies + HZ); - hdev->hw_stats.stats_timer++; - hdev->fd_arfs_expire_timer++; - hclge_task_schedule(hdev); -} - -static void hclge_service_complete(struct hclge_dev *hdev) -{ - WARN_ON(!test_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)); - - /* Flush memory before next watchdog */ - smp_mb__before_atomic(); - clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); -} - static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) { u32 rst_src_reg, cmdq_src_reg, msix_src_reg; @@ -2763,9 +2811,9 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) * defer the processing of the mailbox events. Since, we would have not * cleared RX CMDQ event this time we would receive again another * interrupt from H/W just for the mailbox. + * + * check for vector0 reset event sources */ - - /* check for vector0 reset event sources */ if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) { dev_info(&hdev->pdev->dev, "IMP reset interrupt\n"); set_bit(HNAE3_IMP_RESET, &hdev->reset_pending); @@ -2882,10 +2930,15 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) break; } - /* clear the source of interrupt if it is not cause by reset */ + hclge_clear_event_cause(hdev, event_cause, clearval); + + /* Enable interrupt if it is not cause by reset. And when + * clearval equal to 0, it means interrupt status may be + * cleared by hardware before driver reads status register. + * For this case, vector0 interrupt also should be enabled. + */ if (!clearval || event_cause == HCLGE_VECTOR0_EVENT_MBX) { - hclge_clear_event_cause(hdev, event_cause, clearval); hclge_enable_vector(&hdev->misc_vector, true); } @@ -2918,6 +2971,36 @@ static void hclge_get_misc_vector(struct hclge_dev *hdev) hdev->num_msi_used += 1; } +static void hclge_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct hclge_dev *hdev = container_of(notify, struct hclge_dev, + affinity_notify); + + cpumask_copy(&hdev->affinity_mask, mask); +} + +static void hclge_irq_affinity_release(struct kref *ref) +{ +} + +static void hclge_misc_affinity_setup(struct hclge_dev *hdev) +{ + irq_set_affinity_hint(hdev->misc_vector.vector_irq, + &hdev->affinity_mask); + + hdev->affinity_notify.notify = hclge_irq_affinity_notify; + hdev->affinity_notify.release = hclge_irq_affinity_release; + irq_set_affinity_notifier(hdev->misc_vector.vector_irq, + &hdev->affinity_notify); +} + +static void hclge_misc_affinity_teardown(struct hclge_dev *hdev) +{ + irq_set_affinity_notifier(hdev->misc_vector.vector_irq, NULL); + irq_set_affinity_hint(hdev->misc_vector.vector_irq, NULL); +} + static int hclge_misc_irq_init(struct hclge_dev *hdev) { int ret; @@ -3105,6 +3188,39 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) return 0; } +static int hclge_func_reset_sync_vf(struct hclge_dev *hdev) +{ + struct hclge_pf_rst_sync_cmd *req; + struct hclge_desc desc; + int cnt = 0; + int ret; + + req = (struct hclge_pf_rst_sync_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_VF_RST_RDY, true); + + do { + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + /* for compatible with old firmware, wait + * 100 ms for VF to stop IO + */ + if (ret == -EOPNOTSUPP) { + msleep(HCLGE_RESET_SYNC_TIME); + return 0; + } else if (ret) { + dev_err(&hdev->pdev->dev, "sync with VF fail %d!\n", + ret); + return ret; + } else if (req->all_vf_ready) { + return 0; + } + msleep(HCLGE_PF_RESET_SYNC_TIME); + hclge_cmd_reuse_desc(&desc, true); + } while (cnt++ < HCLGE_PF_RESET_SYNC_CNT); + + dev_err(&hdev->pdev->dev, "sync with VF timeout!\n"); + return -ETIME; +} + int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id) { struct hclge_desc desc; @@ -3229,7 +3345,13 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev) if (!clearval) return; - hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, clearval); + /* For revision 0x20, the reset interrupt source + * can only be cleared after hardware reset done + */ + if (hdev->pdev->revision == 0x20) + hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, + clearval); + hclge_enable_vector(&hdev->misc_vector, true); } @@ -3250,19 +3372,33 @@ static int hclge_reset_prepare_down(struct hclge_dev *hdev) return ret; } -static int hclge_reset_prepare_wait(struct hclge_dev *hdev) +static void hclge_reset_handshake(struct hclge_dev *hdev, bool enable) { -#define HCLGE_RESET_SYNC_TIME 100 + u32 reg_val; + reg_val = hclge_read_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG); + if (enable) + reg_val |= HCLGE_NIC_SW_RST_RDY; + else + reg_val &= ~HCLGE_NIC_SW_RST_RDY; + + hclge_write_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG, reg_val); +} + +static int hclge_reset_prepare_wait(struct hclge_dev *hdev) +{ u32 reg_val; int ret = 0; switch (hdev->reset_type) { case HNAE3_FUNC_RESET: - /* There is no mechanism for PF to know if VF has stopped IO - * for now, just wait 100 ms for VF to stop IO + /* to confirm whether all running VF is ready + * before request PF reset */ - msleep(HCLGE_RESET_SYNC_TIME); + ret = hclge_func_reset_sync_vf(hdev); + if (ret) + return ret; + ret = hclge_func_reset_cmd(hdev, 0); if (ret) { dev_err(&hdev->pdev->dev, @@ -3279,10 +3415,13 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev) hdev->rst_stats.pf_rst_cnt++; break; case HNAE3_FLR_RESET: - /* There is no mechanism for PF to know if VF has stopped IO - * for now, just wait 100 ms for VF to stop IO + /* to confirm whether all running VF is ready + * before request PF reset */ - msleep(HCLGE_RESET_SYNC_TIME); + ret = hclge_func_reset_sync_vf(hdev); + if (ret) + return ret; + set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); set_bit(HNAE3_FLR_DOWN, &hdev->flr_state); hdev->rst_stats.flr_rst_cnt++; @@ -3298,14 +3437,13 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev) /* inform hardware that preparatory work is done */ msleep(HCLGE_RESET_SYNC_TIME); - hclge_write_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG, - HCLGE_NIC_CMQ_ENABLE); + hclge_reset_handshake(hdev, true); dev_info(&hdev->pdev->dev, "prepare wait ok\n"); return ret; } -static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout) +static bool hclge_reset_err_handle(struct hclge_dev *hdev) { #define MAX_RESET_FAIL_CNT 5 @@ -3322,27 +3460,34 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout) return false; } else if (hdev->reset_fail_cnt < MAX_RESET_FAIL_CNT) { hdev->reset_fail_cnt++; - if (is_timeout) { - set_bit(hdev->reset_type, &hdev->reset_pending); - dev_info(&hdev->pdev->dev, - "re-schedule to wait for hw reset done\n"); - return true; - } - - dev_info(&hdev->pdev->dev, "Upgrade reset level\n"); - hclge_clear_reset_cause(hdev); - set_bit(HNAE3_GLOBAL_RESET, &hdev->default_reset_request); - mod_timer(&hdev->reset_timer, - jiffies + HCLGE_RESET_INTERVAL); - - return false; + set_bit(hdev->reset_type, &hdev->reset_pending); + dev_info(&hdev->pdev->dev, + "re-schedule reset task(%d)\n", + hdev->reset_fail_cnt); + return true; } hclge_clear_reset_cause(hdev); + + /* recover the handshake status when reset fail */ + hclge_reset_handshake(hdev, true); + dev_err(&hdev->pdev->dev, "Reset fail!\n"); return false; } +static int hclge_set_rst_done(struct hclge_dev *hdev) +{ + struct hclge_pf_rst_done_cmd *req; + struct hclge_desc desc; + + req = (struct hclge_pf_rst_done_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PF_RST_DONE, false); + req->pf_rst_done |= HCLGE_PF_RESET_DONE_BIT; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + static int hclge_reset_prepare_up(struct hclge_dev *hdev) { int ret = 0; @@ -3353,10 +3498,18 @@ static int hclge_reset_prepare_up(struct hclge_dev *hdev) case HNAE3_FLR_RESET: ret = hclge_set_all_vf_rst(hdev, false); break; + case HNAE3_GLOBAL_RESET: + /* fall through */ + case HNAE3_IMP_RESET: + ret = hclge_set_rst_done(hdev); + break; default: break; } + /* clear up the handshake status after re-initialize done */ + hclge_reset_handshake(hdev, false); + return ret; } @@ -3382,7 +3535,6 @@ static int hclge_reset_stack(struct hclge_dev *hdev) static void hclge_reset(struct hclge_dev *hdev) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); - bool is_timeout = false; int ret; /* Initialize ae_dev reset status as well, in case enet layer wants to @@ -3410,10 +3562,8 @@ static void hclge_reset(struct hclge_dev *hdev) if (ret) goto err_reset; - if (hclge_reset_wait(hdev)) { - is_timeout = true; + if (hclge_reset_wait(hdev)) goto err_reset; - } hdev->rst_stats.hw_reset_done_cnt++; @@ -3458,14 +3608,22 @@ static void hclge_reset(struct hclge_dev *hdev) hdev->reset_fail_cnt = 0; hdev->rst_stats.reset_done_cnt++; ae_dev->reset_type = HNAE3_NONE_RESET; - del_timer(&hdev->reset_timer); + + /* if default_reset_request has a higher level reset request, + * it should be handled as soon as possible. since some errors + * need this kind of reset to fix. + */ + hdev->reset_level = hclge_get_reset_level(ae_dev, + &hdev->default_reset_request); + if (hdev->reset_level != HNAE3_NONE_RESET) + set_bit(hdev->reset_level, &hdev->reset_request); return; err_reset_lock: rtnl_unlock(); err_reset: - if (hclge_reset_err_handle(hdev, is_timeout)) + if (hclge_reset_err_handle(hdev)) hclge_reset_task_schedule(hdev); } @@ -3493,9 +3651,10 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) handle = &hdev->vport[0].nic; if (time_before(jiffies, (hdev->last_reset_time + - HCLGE_RESET_INTERVAL))) + HCLGE_RESET_INTERVAL))) { + mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL); return; - else if (hdev->default_reset_request) + } else if (hdev->default_reset_request) hdev->reset_level = hclge_get_reset_level(ae_dev, &hdev->default_reset_request); @@ -3525,6 +3684,12 @@ static void hclge_reset_timer(struct timer_list *t) { struct hclge_dev *hdev = from_timer(hdev, t, reset_timer); + /* if default_reset_request has no value, it means that this reset + * request has already be handled, so just return here + */ + if (!hdev->default_reset_request) + return; + dev_info(&hdev->pdev->dev, "triggering reset in reset timer\n"); hclge_reset_event(hdev->pdev, NULL); @@ -3606,7 +3771,9 @@ static void hclge_update_vport_alive(struct hclge_dev *hdev) static void hclge_service_task(struct work_struct *work) { struct hclge_dev *hdev = - container_of(work, struct hclge_dev, service_task); + container_of(work, struct hclge_dev, service_task.work); + + clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); if (hdev->hw_stats.stats_timer >= HCLGE_STATS_TIMER_INTERVAL) { hclge_update_stats_for_all(hdev); @@ -3621,7 +3788,8 @@ static void hclge_service_task(struct work_struct *work) hclge_rfs_filter_expire(hdev); hdev->fd_arfs_expire_timer = 0; } - hclge_service_complete(hdev); + + hclge_task_schedule(hdev, round_jiffies_relative(HZ)); } struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle) @@ -4197,8 +4365,8 @@ int hclge_bind_ring_with_vector(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hnae3_ring_chain_node *node; struct hclge_desc desc; - struct hclge_ctrl_vector_chain_cmd *req - = (struct hclge_ctrl_vector_chain_cmd *)desc.data; + struct hclge_ctrl_vector_chain_cmd *req = + (struct hclge_ctrl_vector_chain_cmd *)desc.data; enum hclge_cmd_status status; enum hclge_opcode_type op; u16 tqp_type_and_id; @@ -5808,7 +5976,7 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, return -ENOSPC; } - rule = kzalloc(sizeof(*rule), GFP_KERNEL); + rule = kzalloc(sizeof(*rule), GFP_ATOMIC); if (!rule) { spin_unlock_bh(&hdev->fd_rule_lock); @@ -6160,10 +6328,13 @@ static void hclge_set_timer_task(struct hnae3_handle *handle, bool enable) struct hclge_dev *hdev = vport->back; if (enable) { - mod_timer(&hdev->service_timer, jiffies + HZ); + hclge_task_schedule(hdev, round_jiffies_relative(HZ)); } else { - del_timer_sync(&hdev->service_timer); - cancel_work_sync(&hdev->service_task); + /* Set the DOWN flag here to disable the service to be + * scheduled again + */ + set_bit(HCLGE_STATE_DOWN, &hdev->state); + cancel_delayed_work_sync(&hdev->service_task); clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); } } @@ -6202,12 +6373,15 @@ static void hclge_ae_stop(struct hnae3_handle *handle) if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && hdev->reset_type != HNAE3_FUNC_RESET) { hclge_mac_stop_phy(hdev); + hclge_update_link_status(hdev); return; } for (i = 0; i < handle->kinfo.num_tqps; i++) hclge_reset_tqp(handle, i); + hclge_config_mac_tnl_int(hdev, false); + /* Mac disable */ hclge_cfg_mac_mode(hdev, false); @@ -6249,7 +6423,6 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport, enum hclge_mac_vlan_tbl_opcode op) { struct hclge_dev *hdev = vport->back; - int return_status = -EIO; if (cmdq_resp) { dev_err(&hdev->pdev->dev, @@ -6260,52 +6433,53 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport, if (op == HCLGE_MAC_VLAN_ADD) { if ((!resp_code) || (resp_code == 1)) { - return_status = 0; + return 0; } else if (resp_code == HCLGE_ADD_UC_OVERFLOW) { - return_status = -ENOSPC; dev_err(&hdev->pdev->dev, "add mac addr failed for uc_overflow.\n"); + return -ENOSPC; } else if (resp_code == HCLGE_ADD_MC_OVERFLOW) { - return_status = -ENOSPC; dev_err(&hdev->pdev->dev, "add mac addr failed for mc_overflow.\n"); - } else { - dev_err(&hdev->pdev->dev, - "add mac addr failed for undefined, code=%d.\n", - resp_code); + return -ENOSPC; } + + dev_err(&hdev->pdev->dev, + "add mac addr failed for undefined, code=%u.\n", + resp_code); + return -EIO; } else if (op == HCLGE_MAC_VLAN_REMOVE) { if (!resp_code) { - return_status = 0; + return 0; } else if (resp_code == 1) { - return_status = -ENOENT; dev_dbg(&hdev->pdev->dev, "remove mac addr failed for miss.\n"); - } else { - dev_err(&hdev->pdev->dev, - "remove mac addr failed for undefined, code=%d.\n", - resp_code); + return -ENOENT; } + + dev_err(&hdev->pdev->dev, + "remove mac addr failed for undefined, code=%u.\n", + resp_code); + return -EIO; } else if (op == HCLGE_MAC_VLAN_LKUP) { if (!resp_code) { - return_status = 0; + return 0; } else if (resp_code == 1) { - return_status = -ENOENT; dev_dbg(&hdev->pdev->dev, "lookup mac addr failed for miss.\n"); - } else { - dev_err(&hdev->pdev->dev, - "lookup mac addr failed for undefined, code=%d.\n", - resp_code); + return -ENOENT; } - } else { - return_status = -EINVAL; + dev_err(&hdev->pdev->dev, - "unknown opcode for get_mac_vlan_cmd_status,opcode=%d.\n", - op); + "lookup mac addr failed for undefined, code=%u.\n", + resp_code); + return -EIO; } - return return_status; + dev_err(&hdev->pdev->dev, + "unknown opcode for get_mac_vlan_cmd_status, opcode=%d.\n", op); + + return -EINVAL; } static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr) @@ -7829,7 +8003,7 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, return -EBUSY; } - /* When port base vlan enabled, we use port base vlan as the vlan + /* when port base vlan enabled, we use port base vlan as the vlan * filter entry. In this case, we don't update vlan filter table * when user add new vlan or remove exist vlan, just update the vport * vlan list. The vlan id in vlan list will be writen in vlan filter @@ -7848,7 +8022,7 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, hclge_add_vport_vlan_table(vport, vlan_id, writen_to_tbl); } else if (is_kill) { - /* When remove hw vlan filter failed, record the vlan id, + /* when remove hw vlan filter failed, record the vlan id, * and try to remove it from hw later, to be consistence * with stack */ @@ -8122,28 +8296,15 @@ static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) { int ret; - if (rx_en && tx_en) - hdev->fc_mode_last_time = HCLGE_FC_FULL; - else if (rx_en && !tx_en) - hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE; - else if (!rx_en && tx_en) - hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE; - else - hdev->fc_mode_last_time = HCLGE_FC_NONE; - if (hdev->tm_info.fc_mode == HCLGE_FC_PFC) return 0; ret = hclge_mac_pause_en_cfg(hdev, tx_en, rx_en); - if (ret) { - dev_err(&hdev->pdev->dev, "configure pauseparam error, ret = %d.\n", - ret); - return ret; - } - - hdev->tm_info.fc_mode = hdev->fc_mode_last_time; + if (ret) + dev_err(&hdev->pdev->dev, + "configure pauseparam error, ret = %d.\n", ret); - return 0; + return ret; } int hclge_cfg_flowctrl(struct hclge_dev *hdev) @@ -8208,6 +8369,21 @@ static void hclge_get_pauseparam(struct hnae3_handle *handle, u32 *auto_neg, } } +static void hclge_record_user_pauseparam(struct hclge_dev *hdev, + u32 rx_en, u32 tx_en) +{ + if (rx_en && tx_en) + hdev->fc_mode_last_time = HCLGE_FC_FULL; + else if (rx_en && !tx_en) + hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE; + else if (!rx_en && tx_en) + hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE; + else + hdev->fc_mode_last_time = HCLGE_FC_NONE; + + hdev->tm_info.fc_mode = hdev->fc_mode_last_time; +} + static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, u32 rx_en, u32 tx_en) { @@ -8233,6 +8409,8 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, hclge_set_flowctrl_adv(hdev, rx_en, tx_en); + hclge_record_user_pauseparam(hdev, rx_en, tx_en); + if (!auto_neg) return hclge_cfg_pauseparam(hdev, rx_en, tx_en); @@ -8481,7 +8659,7 @@ static int hclge_init_client_instance(struct hnae3_client *client, } } - return ret; + return 0; clear_nic: hdev->nic_client = NULL; @@ -8602,12 +8780,10 @@ static void hclge_state_uninit(struct hclge_dev *hdev) set_bit(HCLGE_STATE_DOWN, &hdev->state); set_bit(HCLGE_STATE_REMOVING, &hdev->state); - if (hdev->service_timer.function) - del_timer_sync(&hdev->service_timer); if (hdev->reset_timer.function) del_timer_sync(&hdev->reset_timer); - if (hdev->service_task.func) - cancel_work_sync(&hdev->service_task); + if (hdev->service_task.work.func) + cancel_delayed_work_sync(&hdev->service_task); if (hdev->rst_service_task.func) cancel_work_sync(&hdev->rst_service_task); if (hdev->mbx_service_task.func) @@ -8812,12 +8988,16 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_dcb_ops_set(hdev); - timer_setup(&hdev->service_timer, hclge_service_timer, 0); timer_setup(&hdev->reset_timer, hclge_reset_timer, 0); - INIT_WORK(&hdev->service_task, hclge_service_task); + INIT_DELAYED_WORK(&hdev->service_task, hclge_service_task); INIT_WORK(&hdev->rst_service_task, hclge_reset_service_task); INIT_WORK(&hdev->mbx_service_task, hclge_mailbox_service_task); + /* Setup affinity after service timer setup because add_timer_on + * is called in affinity notify. + */ + hclge_misc_affinity_setup(hdev); + hclge_clear_all_event_cause(hdev); hclge_clear_resetting_state(hdev); @@ -8842,7 +9022,9 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_state_init(hdev); hdev->last_reset_time = jiffies; - pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME); + dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n", + HCLGE_DRIVER_NAME); + return 0; err_mdiobus_unreg: @@ -8979,6 +9161,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) struct hclge_dev *hdev = ae_dev->priv; struct hclge_mac *mac = &hdev->hw.mac; + hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev); if (mac->phydev) @@ -9238,106 +9421,314 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num, } #define MAX_SEPARATE_NUM 4 -#define SEPARATOR_VALUE 0xFFFFFFFF +#define SEPARATOR_VALUE 0xFDFCFBFA #define REG_NUM_PER_LINE 4 #define REG_LEN_PER_LINE (REG_NUM_PER_LINE * sizeof(u32)) +#define REG_SEPARATOR_LINE 1 +#define REG_NUM_REMAIN_MASK 3 +#define BD_LIST_MAX_NUM 30 -static int hclge_get_regs_len(struct hnae3_handle *handle) +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc) { - int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u32 regs_num_32_bit, regs_num_64_bit; + /*prepare 4 commands to query DFX BD number*/ + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true); + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true); + desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true); + desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true); + + return hclge_cmd_send(&hdev->hw, desc, 4); +} + +static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev, + int *bd_num_list, + u32 type_num) +{ +#define HCLGE_DFX_REG_BD_NUM 4 + + u32 entries_per_desc, desc_index, index, offset, i; + struct hclge_desc desc[HCLGE_DFX_REG_BD_NUM]; int ret; - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + ret = hclge_query_bd_num_cmd_send(hdev, desc); if (ret) { dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return -EOPNOTSUPP; + "Get dfx bd num fail, status is %d.\n", ret); + return ret; } - cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1; - common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1; - ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1; - tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1; + entries_per_desc = ARRAY_SIZE(desc[0].data); + for (i = 0; i < type_num; i++) { + offset = hclge_dfx_bd_offset_list[i]; + index = offset % entries_per_desc; + desc_index = offset / entries_per_desc; + bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]); + } - return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps + - tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE + - regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64); + return ret; } -static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, - void *data) +static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc_src, int bd_num, + enum hclge_opcode_type cmd) { - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u32 regs_num_32_bit, regs_num_64_bit; - int i, j, reg_um, separator_num; + struct hclge_desc *desc = desc_src; + int i, ret; + + hclge_cmd_setup_basic_desc(desc, cmd, true); + for (i = 0; i < bd_num - 1; i++) { + desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + desc++; + hclge_cmd_setup_basic_desc(desc, cmd, true); + } + + desc = desc_src; + ret = hclge_cmd_send(&hdev->hw, desc, bd_num); + if (ret) + dev_err(&hdev->pdev->dev, + "Query dfx reg cmd(0x%x) send fail, status is %d.\n", + cmd, ret); + + return ret; +} + +static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num, + void *data) +{ + int entries_per_desc, reg_num, separator_num, desc_index, index, i; + struct hclge_desc *desc = desc_src; u32 *reg = data; + + entries_per_desc = ARRAY_SIZE(desc->data); + reg_num = entries_per_desc * bd_num; + separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) { + index = i % entries_per_desc; + desc_index = i / entries_per_desc; + *reg++ = le32_to_cpu(desc[desc_index].data[index]); + } + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; + + return reg_num + separator_num; +} + +static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + int data_len_per_desc, data_len, bd_num, i; + int bd_num_list[BD_LIST_MAX_NUM]; int ret; - *version = hdev->fw_version; + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg bd num fail, status is %d.\n", ret); + return ret; + } - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data); + *len = 0; + for (i = 0; i < dfx_reg_type_num; i++) { + bd_num = bd_num_list[i]; + data_len = data_len_per_desc * bd_num; + *len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE; + } + + return ret; +} + +static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + int bd_num, bd_num_max, buf_len, i; + int bd_num_list[BD_LIST_MAX_NUM]; + struct hclge_desc *desc_src; + u32 *reg = data; + int ret; + + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); if (ret) { dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return; + "Get dfx reg bd num fail, status is %d.\n", ret); + return ret; + } + + bd_num_max = bd_num_list[0]; + for (i = 1; i < dfx_reg_type_num; i++) + bd_num_max = max_t(int, bd_num_max, bd_num_list[i]); + + buf_len = sizeof(*desc_src) * bd_num_max; + desc_src = kzalloc(buf_len, GFP_KERNEL); + if (!desc_src) { + dev_err(&hdev->pdev->dev, "%s kzalloc failed\n", __func__); + return -ENOMEM; + } + + for (i = 0; i < dfx_reg_type_num; i++) { + bd_num = bd_num_list[i]; + ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num, + hclge_dfx_reg_opcode_list[i]); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg fail, status is %d.\n", ret); + break; + } + + reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg); } + kfree(desc_src); + return ret; +} + +static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, + struct hnae3_knic_private_info *kinfo) +{ +#define HCLGE_RING_REG_OFFSET 0x200 +#define HCLGE_RING_INT_REG_OFFSET 0x4 + + int i, j, reg_num, separator_num; + int data_num_sum; + u32 *reg = data; + /* fetching per-PF registers valus from PF PCIe register space */ - reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) + reg_num = ARRAY_SIZE(cmdq_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; + data_num_sum = reg_num + separator_num; - reg_um = sizeof(common_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) + reg_num = ARRAY_SIZE(common_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; + data_num_sum += reg_num + separator_num; - reg_um = sizeof(ring_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; + reg_num = ARRAY_SIZE(ring_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); for (j = 0; j < kinfo->num_tqps; j++) { - for (i = 0; i < reg_um; i++) + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, ring_reg_addr_list[i] + - 0x200 * j); + HCLGE_RING_REG_OFFSET * j); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; } + data_num_sum += (reg_num + separator_num) * kinfo->num_tqps; - reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; + reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); for (j = 0; j < hdev->num_msi_used - 1; j++) { - for (i = 0; i < reg_um; i++) + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, tqp_intr_reg_addr_list[i] + - 4 * j); + HCLGE_RING_INT_REG_OFFSET * j); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; } + data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1); + + return data_num_sum; +} + +static int hclge_get_regs_len(struct hnae3_handle *handle) +{ + int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int regs_num_32_bit, regs_num_64_bit, dfx_regs_len; + int regs_lines_32_bit, regs_lines_64_bit; + int ret; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return ret; + } + + ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg len failed, ret = %d.\n", ret); + return ret; + } + + cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + + return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps + + tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit + + regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len; +} + +static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, + void *data) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 regs_num_32_bit, regs_num_64_bit; + int i, reg_num, separator_num, ret; + u32 *reg = data; + + *version = hdev->fw_version; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return; + } + + reg += hclge_fetch_pf_reg(hdev, reg, kinfo); - /* fetching PF common registers values from firmware */ ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg); if (ret) { dev_err(&hdev->pdev->dev, "Get 32 bit register failed, ret = %d.\n", ret); return; } + reg_num = regs_num_32_bit; + reg += reg_num; + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; - reg += regs_num_32_bit; ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "Get 64 bit register failed, ret = %d.\n", ret); + return; + } + reg_num = regs_num_64_bit * 2; + reg += reg_num; + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; + + ret = hclge_get_dfx_reg(hdev, reg); + if (ret) + dev_err(&hdev->pdev->dev, + "Get dfx register failed, ret = %d.\n", ret); } static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status) @@ -9452,7 +9843,7 @@ static const struct hnae3_ae_ops hclge_ops = { .set_mtu = hclge_set_mtu, .reset_queue = hclge_reset_tqp, .get_stats = hclge_get_stats, - .get_mac_pause_stats = hclge_get_mac_pause_stat, + .get_mac_stats = hclge_get_mac_stat, .update_stats = hclge_update_stats, .get_strings = hclge_get_strings, .get_sset_count = hclge_get_sset_count, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 6a12285f4c76..7c28933e6f3d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -302,6 +302,13 @@ enum hclge_fc_mode { HCLGE_FC_DEFAULT }; +enum hclge_link_fail_code { + HCLGE_LF_NORMAL, + HCLGE_LF_REF_CLOCK_LOST, + HCLGE_LF_XSFP_TX_DISABLE, + HCLGE_LF_XSFP_ABSENT, +}; + #define HCLGE_PG_NUM 4 #define HCLGE_SCH_MODE_SP 0 #define HCLGE_SCH_MODE_DWRR 1 @@ -806,9 +813,8 @@ struct hclge_dev { u16 adminq_work_limit; /* Num of admin receive queue desc to process */ unsigned long service_timer_period; unsigned long service_timer_previous; - struct timer_list service_timer; struct timer_list reset_timer; - struct work_struct service_task; + struct delayed_work service_task; struct work_struct rst_service_task; struct work_struct mbx_service_task; @@ -864,6 +870,10 @@ struct hclge_dev { DECLARE_KFIFO(mac_tnl_log, struct hclge_mac_tnl_stats, HCLGE_MAC_TNL_LOG_SIZE); + + /* affinity mask and notify for misc interrupt */ + cpumask_t affinity_mask; + struct irq_affinity_notify affinity_notify; }; /* VPort level vlan tag configuration for TX direction */ @@ -990,7 +1000,6 @@ int hclge_buffer_alloc(struct hclge_dev *hdev); int hclge_rss_init_hw(struct hclge_dev *hdev); void hclge_rss_indir_init_cfg(struct hclge_dev *hdev); -int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport); void hclge_mbx_handler(struct hclge_dev *hdev); int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id); void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id); @@ -1018,4 +1027,7 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, u16 state, u16 vlan_tag, u16 qos, u16 vlan_proto); +void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time); +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 690b9990215c..f5da28a60d00 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -479,7 +479,7 @@ static void hclge_mbx_reset_vf_queue(struct hclge_vport *vport, hclge_reset_vf_queue(vport, queue_id); - /* send response msg to VF after queue reset complete*/ + /* send response msg to VF after queue reset complete */ hclge_gen_resp_to_vf(vport, mbx_req, 0, NULL, 0); } @@ -545,6 +545,36 @@ static int hclge_get_rss_key(struct hclge_vport *vport, HCLGE_RSS_MBX_RESP_LEN); } +static void hclge_link_fail_parse(struct hclge_dev *hdev, u8 link_fail_code) +{ + switch (link_fail_code) { + case HCLGE_LF_REF_CLOCK_LOST: + dev_warn(&hdev->pdev->dev, "Reference clock lost!\n"); + break; + case HCLGE_LF_XSFP_TX_DISABLE: + dev_warn(&hdev->pdev->dev, "SFP tx is disabled!\n"); + break; + case HCLGE_LF_XSFP_ABSENT: + dev_warn(&hdev->pdev->dev, "SFP is absent!\n"); + break; + default: + break; + } +} + +static void hclge_handle_link_change_event(struct hclge_dev *hdev, + struct hclge_mbx_vf_to_pf_cmd *req) +{ +#define LINK_STATUS_OFFSET 1 +#define LINK_FAIL_CODE_OFFSET 2 + + clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); + hclge_task_schedule(hdev, 0); + + if (!req->msg[LINK_STATUS_OFFSET]) + hclge_link_fail_parse(hdev, req->msg[LINK_FAIL_CODE_OFFSET]); +} + static bool hclge_cmd_crq_empty(struct hclge_hw *hw) { u32 tail = hclge_read_dev(hw, HCLGE_NIC_CRQ_TAIL_REG); @@ -552,6 +582,15 @@ static bool hclge_cmd_crq_empty(struct hclge_hw *hw) return tail == hw->cmq.crq.next_to_use; } +static void hclge_handle_ncsi_error(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = hdev->ae_dev; + + ae_dev->ops->set_default_reset_request(ae_dev, HNAE3_GLOBAL_RESET); + dev_warn(&hdev->pdev->dev, "requesting reset due to NCSI error\n"); + ae_dev->ops->reset_event(hdev->pdev, NULL); +} + void hclge_mbx_handler(struct hclge_dev *hdev) { struct hclge_cmq_ring *crq = &hdev->hw.cmq.crq; @@ -707,6 +746,12 @@ void hclge_mbx_handler(struct hclge_dev *hdev) "PF fail(%d) to media type for VF\n", ret); break; + case HCLGE_MBX_PUSH_LINK_STATUS: + hclge_handle_link_change_event(hdev, req); + break; + case HCLGE_MBX_NCSI_ERROR: + hclge_handle_ncsi_error(hdev); + break; default: dev_err(&hdev->pdev->dev, "un-supported mailbox message, code = %d\n", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index abb1b438564e..dc4dfd4602ab 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -231,6 +231,8 @@ int hclge_mac_connect_phy(struct hnae3_handle *handle) linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->advertising); + phy_attached_info(phydev); + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 3f41fa2bc414..e829101d576c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -404,8 +404,8 @@ static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev) { struct hclge_port_shapping_cmd *shap_cfg_cmd; struct hclge_desc desc; - u32 shapping_para = 0; u8 ir_u, ir_b, ir_s; + u32 shapping_para; int ret; ret = hclge_shaper_para_calc(hdev->hw.mac.speed, @@ -650,12 +650,8 @@ static void hclge_pfc_info_init(struct hclge_dev *hdev) } } -static int hclge_tm_schd_info_init(struct hclge_dev *hdev) +static void hclge_tm_schd_info_init(struct hclge_dev *hdev) { - if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) && - (hdev->tm_info.num_pg != 1)) - return -EINVAL; - hclge_tm_pg_info_init(hdev); hclge_tm_tc_info_init(hdev); @@ -663,8 +659,6 @@ static int hclge_tm_schd_info_init(struct hclge_dev *hdev) hclge_tm_vport_info_update(hdev); hclge_pfc_info_init(hdev); - - return 0; } static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev) @@ -1428,15 +1422,15 @@ int hclge_tm_init_hw(struct hclge_dev *hdev, bool init) int hclge_tm_schd_init(struct hclge_dev *hdev) { - int ret; - /* fc_mode is HCLGE_FC_FULL on reset */ hdev->tm_info.fc_mode = HCLGE_FC_FULL; hdev->fc_mode_last_time = hdev->tm_info.fc_mode; - ret = hclge_tm_schd_info_init(hdev); - if (ret) - return ret; + if (hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE && + hdev->tm_info.num_pg != 1) + return -EINVAL; + + hclge_tm_schd_info_init(hdev); return hclge_tm_init_hw(hdev, true); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index 652b796044e3..4c2c9458648f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -43,7 +43,7 @@ static int hclgevf_cmd_csq_clean(struct hclgevf_hw *hw) { struct hclgevf_dev *hdev = container_of(hw, struct hclgevf_dev, hw); struct hclgevf_cmq_ring *csq = &hw->cmq.csq; - int clean = 0; + int clean; u32 head; head = hclgevf_read_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG); @@ -97,7 +97,9 @@ static void hclgevf_cmd_config_regs(struct hclgevf_cmq_ring *ring) reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1); hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val); - reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S); + reg_val = hclgevf_read_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG); + reg_val &= HCLGEVF_NIC_SW_RST_RDY; + reg_val |= (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S); hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val); hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0); @@ -405,7 +407,15 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev) } hdev->fw_version = version; - dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version); + dev_info(&hdev->pdev->dev, "The firmware version is %lu.%lu.%lu.%lu\n", + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE3_MASK, + HNAE3_FW_VERSION_BYTE3_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE2_MASK, + HNAE3_FW_VERSION_BYTE2_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE1_MASK, + HNAE3_FW_VERSION_BYTE1_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE0_MASK, + HNAE3_FW_VERSION_BYTE0_SHIFT)); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h index 127a434a56f3..f830eef02e5c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h @@ -244,8 +244,11 @@ struct hclgevf_cfg_tx_queue_pointer_cmd { #define HCLGEVF_NIC_CRQ_DEPTH_REG 0x27020 #define HCLGEVF_NIC_CRQ_TAIL_REG 0x27024 #define HCLGEVF_NIC_CRQ_HEAD_REG 0x27028 -#define HCLGEVF_NIC_CMQ_EN_B 16 -#define HCLGEVF_NIC_CMQ_ENABLE BIT(HCLGEVF_NIC_CMQ_EN_B) + +/* this bit indicates that the driver is ready for hardware reset */ +#define HCLGEVF_NIC_SW_RST_RDY_B 16 +#define HCLGEVF_NIC_SW_RST_RDY BIT(HCLGEVF_NIC_SW_RST_RDY_B) + #define HCLGEVF_NIC_CMQ_DESC_NUM 1024 #define HCLGEVF_NIC_CMQ_DESC_NUM_S 3 #define HCLGEVF_NIC_CMDQ_INT_SRC_REG 0x27100 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a13a0e101c3b..594cae8c7410 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1269,7 +1269,7 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, HCLGE_MBX_VLAN_FILTER, msg_data, HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0); - /* When remove hw vlan filter failed, record the vlan id, + /* when remove hw vlan filter failed, record the vlan id, * and try to remove it from hw later, to be consistence * with stack. */ @@ -1396,19 +1396,22 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) u32 val; int ret; - /* wait to check the hardware reset completion status */ - val = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); - dev_info(&hdev->pdev->dev, "checking vf resetting status: %x\n", val); - if (hdev->reset_type == HNAE3_FLR_RESET) return hclgevf_flr_poll_timeout(hdev, HCLGEVF_RESET_WAIT_US, HCLGEVF_RESET_WAIT_CNT); - - ret = readl_poll_timeout(hdev->hw.io_base + HCLGEVF_RST_ING, val, - !(val & HCLGEVF_RST_ING_BITS), - HCLGEVF_RESET_WAIT_US, - HCLGEVF_RESET_WAIT_TIMEOUT_US); + else if (hdev->reset_type == HNAE3_VF_RESET) + ret = readl_poll_timeout(hdev->hw.io_base + + HCLGEVF_VF_RST_ING, val, + !(val & HCLGEVF_VF_RST_ING_BIT), + HCLGEVF_RESET_WAIT_US, + HCLGEVF_RESET_WAIT_TIMEOUT_US); + else + ret = readl_poll_timeout(hdev->hw.io_base + + HCLGEVF_RST_ING, val, + !(val & HCLGEVF_RST_ING_BITS), + HCLGEVF_RESET_WAIT_US, + HCLGEVF_RESET_WAIT_TIMEOUT_US); /* hardware completion status should be available by this time */ if (ret) { @@ -1426,6 +1429,20 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) return 0; } +static void hclgevf_reset_handshake(struct hclgevf_dev *hdev, bool enable) +{ + u32 reg_val; + + reg_val = hclgevf_read_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG); + if (enable) + reg_val |= HCLGEVF_NIC_SW_RST_RDY; + else + reg_val &= ~HCLGEVF_NIC_SW_RST_RDY; + + hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG, + reg_val); +} + static int hclgevf_reset_stack(struct hclgevf_dev *hdev) { int ret; @@ -1448,7 +1465,14 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev) if (ret) return ret; - return hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT); + ret = hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT); + if (ret) + return ret; + + /* clear handshake status with IMP */ + hclgevf_reset_handshake(hdev, false); + + return 0; } static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) @@ -1474,8 +1498,7 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state); /* inform hardware that preparatory work is done */ msleep(HCLGEVF_RESET_SYNC_TIME); - hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG, - HCLGEVF_NIC_CMQ_ENABLE); + hclgevf_reset_handshake(hdev, true); dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done, ret:%d\n", hdev->reset_type, ret); @@ -1484,6 +1507,8 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) { + /* recover handshake status with IMP when reset fail */ + hclgevf_reset_handshake(hdev, true); hdev->rst_stats.rst_fail_cnt++; dev_err(&hdev->pdev->dev, "failed to reset VF(%d)\n", hdev->rst_stats.rst_fail_cnt); @@ -1494,9 +1519,6 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) if (hclgevf_is_reset_pending(hdev)) { set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); hclgevf_reset_task_schedule(hdev); - } else { - hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG, - HCLGEVF_NIC_CMQ_ENABLE); } } @@ -1539,7 +1561,7 @@ static int hclgevf_reset(struct hclgevf_dev *hdev) rtnl_lock(); - /* now, re-initialize the nic client and ae device*/ + /* now, re-initialize the nic client and ae device */ ret = hclgevf_reset_stack(hdev); if (ret) { dev_err(&hdev->pdev->dev, "failed to reset VF stack\n"); @@ -1762,9 +1784,8 @@ static void hclgevf_reset_service_task(struct work_struct *work) * 1b and 2. cases but we will not get any intimation about 1a * from PF as cmdq would be in unreliable state i.e. mailbox * communication between PF and VF would be broken. - */ - - /* if we are never geting into pending state it means either: + * + * if we are never geting into pending state it means either: * 1. PF is not receiving our request which could be due to IMP * reset * 2. PF is screwed @@ -1867,29 +1888,45 @@ static void hclgevf_clear_event_cause(struct hclgevf_dev *hdev, u32 regclr) static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, u32 *clearval) { - u32 cmdq_src_reg, rst_ing_reg; + u32 val, cmdq_stat_reg, rst_ing_reg; /* fetch the events from their corresponding regs */ - cmdq_src_reg = hclgevf_read_dev(&hdev->hw, - HCLGEVF_VECTOR0_CMDQ_SRC_REG); + cmdq_stat_reg = hclgevf_read_dev(&hdev->hw, + HCLGEVF_VECTOR0_CMDQ_STAT_REG); - if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_src_reg) { + if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_stat_reg) { rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); dev_info(&hdev->pdev->dev, "receive reset interrupt 0x%x!\n", rst_ing_reg); set_bit(HNAE3_VF_RESET, &hdev->reset_pending); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state); - cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B); - *clearval = cmdq_src_reg; + *clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B); hdev->rst_stats.vf_rst_cnt++; + /* set up VF hardware reset status, its PF will clear + * this status when PF has initialized done. + */ + val = hclgevf_read_dev(&hdev->hw, HCLGEVF_VF_RST_ING); + hclgevf_write_dev(&hdev->hw, HCLGEVF_VF_RST_ING, + val | HCLGEVF_VF_RST_ING_BIT); return HCLGEVF_VECTOR0_EVENT_RST; } /* check for vector0 mailbox(=CMDQ RX) event source */ - if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) { - cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B); - *clearval = cmdq_src_reg; + if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_stat_reg) { + /* for revision 0x21, clearing interrupt is writing bit 0 + * to the clear register, writing bit 1 means to keep the + * old value. + * for revision 0x20, the clear register is a read & write + * register, so we should just write 0 to the bit we are + * handling, and keep other bits as cmdq_stat_reg. + */ + if (hdev->pdev->revision >= 0x21) + *clearval = ~(1U << HCLGEVF_VECTOR0_RX_CMDQ_INT_B); + else + *clearval = cmdq_stat_reg & + ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B); + return HCLGEVF_VECTOR0_EVENT_MBX; } @@ -2265,7 +2302,7 @@ static void hclgevf_uninit_msi(struct hclgevf_dev *hdev) static int hclgevf_misc_irq_init(struct hclgevf_dev *hdev) { - int ret = 0; + int ret; hclgevf_get_misc_vector(hdev); @@ -2695,7 +2732,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) } hdev->last_reset_time = jiffies; - pr_info("finished initializing %s driver\n", HCLGEVF_DRIVER_NAME); + dev_info(&hdev->pdev->dev, "finished initializing %s driver\n", + HCLGEVF_DRIVER_NAME); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 5a9e30998a8f..bdde3afc286b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -87,6 +87,8 @@ /* Vector0 interrupt CMDQ event source register(RW) */ #define HCLGEVF_VECTOR0_CMDQ_SRC_REG 0x27100 +/* Vector0 interrupt CMDQ event status register(RO) */ +#define HCLGEVF_VECTOR0_CMDQ_STAT_REG 0x27104 /* CMDQ register bits for RX event(=MBX event) */ #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B 1 /* RST register bits for RESET event */ @@ -103,6 +105,9 @@ (HCLGEVF_FUN_RST_ING_BIT | HCLGEVF_GLOBAL_RST_ING_BIT | \ HCLGEVF_CORE_RST_ING_BIT | HCLGEVF_IMP_RST_ING_BIT) +#define HCLGEVF_VF_RST_ING 0x07008 +#define HCLGEVF_VF_RST_ING_BIT BIT(16) + #define HCLGEVF_RSS_IND_TBL_SIZE 512 #define HCLGEVF_RSS_SET_BITMAP_MSK 0xffff #define HCLGEVF_RSS_KEY_SIZE 40 @@ -120,7 +125,7 @@ #define HCLGEVF_S_IP_BIT BIT(3) #define HCLGEVF_V_TAG_BIT BIT(4) -#define HCLGEVF_STATS_TIMER_INTERVAL (36) +#define HCLGEVF_STATS_TIMER_INTERVAL 36U enum hclgevf_evt_cause { HCLGEVF_VECTOR0_EVENT_RST, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 9c78251f9c39..0e13d1c7e474 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -136,7 +136,7 @@ static int tx_map_skb(struct hinic_dev *nic_dev, struct sk_buff *skb, struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma_addr; int i, j; diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 395dde444483..9e43c9ace9c2 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -1549,7 +1549,7 @@ emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev) ctrl); /* skb fragments */ for (i = 0; i < nr_frags; ++i) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = skb_frag_size(frag); if (unlikely(dev->tx_cnt + mal_tx_chunks(len) >= NUM_TX_BUFF)) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index cebd20f3128d..07efa2b40003 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1485,7 +1485,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) memcpy(dst + cur, page_address(skb_frag_page(frag)) + - frag->page_offset, skb_frag_size(frag)); + skb_frag_off(frag), skb_frag_size(frag)); cur += skb_frag_size(frag); } } else { diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index f703fa58458e..6b6ba1c38235 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2889,9 +2889,8 @@ static int e1000_tx_map(struct e1000_adapter *adapter, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; - frag = &skb_shinfo(skb)->frags[f]; len = skb_frag_size(frag); offset = 0; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 395b05701480..a1fab77b2096 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1429,6 +1429,16 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) else phy_reg |= 0xFA; e1e_wphy_locked(hw, I217_PLL_CLOCK_GATE_REG, phy_reg); + + if (speed == SPEED_1000) { + hw->phy.ops.read_reg_locked(hw, HV_PM_CTRL, + &phy_reg); + + phy_reg |= HV_PM_CTRL_K1_CLK_REQ; + + hw->phy.ops.write_reg_locked(hw, HV_PM_CTRL, + phy_reg); + } } hw->phy.ops.release(hw); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index eb09c755fa17..1502895eb45d 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -210,7 +210,7 @@ /* PHY Power Management Control */ #define HV_PM_CTRL PHY_REG(770, 17) -#define HV_PM_CTRL_PLL_STOP_IN_K1_GIGA 0x100 +#define HV_PM_CTRL_K1_CLK_REQ 0x200 #define HV_PM_CTRL_K1_ENABLE 0x4000 #define I217_PLL_CLOCK_GATE_REG PHY_REG(772, 28) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e4baa13b3cda..8a3f035c3a5f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5579,9 +5579,8 @@ static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; - frag = &skb_shinfo(skb)->frags[f]; len = skb_frag_size(frag); offset = 0; @@ -6297,7 +6296,7 @@ fl_out: static int e1000e_pm_freeze(struct device *dev) { - struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); + struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); @@ -6630,7 +6629,7 @@ static int __e1000_resume(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int e1000e_pm_thaw(struct device *dev) { - struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); + struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); e1000e_set_interrupt_capability(adapter); @@ -6679,8 +6678,7 @@ static int e1000e_pm_resume(struct device *dev) static int e1000e_pm_runtime_idle(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); u16 eee_lp; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 7d42582ed48d..b14441944b4b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_H_ #define _FM10K_H_ @@ -177,14 +177,10 @@ static inline struct netdev_queue *txring_txq(const struct fm10k_ring *ring) #define MIN_Q_VECTORS 1 enum fm10k_non_q_vectors { FM10K_MBX_VECTOR, -#define NON_Q_VECTORS_VF NON_Q_VECTORS_PF - NON_Q_VECTORS_PF + NON_Q_VECTORS }; -#define NON_Q_VECTORS(hw) (((hw)->mac.type == fm10k_mac_pf) ? \ - NON_Q_VECTORS_PF : \ - NON_Q_VECTORS_VF) -#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS(hw)) +#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS) struct fm10k_q_vector { struct fm10k_intfc *interface; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c index 20768ac7f17e..c45315472245 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" @@ -36,7 +36,7 @@ static int fm10k_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets) static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) { u8 num_tc = 0; - int i, err; + int i; /* verify type and determine num_tcs needed */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { @@ -57,7 +57,7 @@ static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) /* update TC hardware mapping if necessary */ if (num_tc != netdev_get_num_tc(dev)) { - err = fm10k_setup_tc(dev, num_tc); + int err = fm10k_setup_tc(dev, num_tc); if (err) return err; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index dca104121c05..1d27b2fb23af 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -160,8 +160,6 @@ void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) snprintf(name, sizeof(name), "q_vector.%03d", q_vector->v_idx); q_vector->dbg_q_vector = debugfs_create_dir(name, interface->dbg_intfc); - if (!q_vector->dbg_q_vector) - return; /* Generate a file for each rx ring in the q_vector */ for (i = 0; i < q_vector->tx.count; i++) { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 4895dd83dd08..c681d2d28107 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/vmalloc.h> @@ -222,7 +222,6 @@ static void __fm10k_add_ethtool_stats(u64 **data, void *pointer, const unsigned int size) { unsigned int i; - char *p; if (!pointer) { /* memory is not zero allocated so we have to clear it */ @@ -232,7 +231,7 @@ static void __fm10k_add_ethtool_stats(u64 **data, void *pointer, } for (i = 0; i < size; i++) { - p = (char *)pointer + stats[i].stat_offset; + char *p = (char *)pointer + stats[i].stat_offset; switch (stats[i].sizeof_stat) { case sizeof(u64): @@ -651,7 +650,6 @@ static int fm10k_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_q_vector *qv; u16 tx_itr, rx_itr; int i; @@ -677,7 +675,8 @@ static int fm10k_set_coalesce(struct net_device *dev, /* update q_vectors */ for (i = 0; i < interface->num_q_vectors; i++) { - qv = interface->q_vector[i]; + struct fm10k_q_vector *qv = interface->q_vector[i]; + qv->tx.itr = tx_itr; qv->rx.itr = rx_itr; } @@ -1115,13 +1114,12 @@ static void fm10k_get_channels(struct net_device *dev, struct ethtool_channels *ch) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_hw *hw = &interface->hw; /* report maximum channels */ ch->max_combined = fm10k_max_channels(dev); /* report info for other vector */ - ch->max_other = NON_Q_VECTORS(hw); + ch->max_other = NON_Q_VECTORS; ch->other_count = ch->max_other; /* record RSS queues */ @@ -1133,14 +1131,13 @@ static int fm10k_set_channels(struct net_device *dev, { struct fm10k_intfc *interface = netdev_priv(dev); unsigned int count = ch->combined_count; - struct fm10k_hw *hw = &interface->hw; /* verify they are not requesting separate vectors */ if (!count || ch->rx_count || ch->tx_count) return -EINVAL; /* verify other_count has not changed */ - if (ch->other_count != NON_Q_VECTORS(hw)) + if (ch->other_count != NON_Q_VECTORS) return -EINVAL; /* verify the number of channels does not exceed hardware limits */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 8de77155f2e7..afe1fafd2447 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" #include "fm10k_vf.h" @@ -426,7 +426,7 @@ static s32 fm10k_iov_alloc_data(struct pci_dev *pdev, int num_vfs) struct fm10k_iov_data *iov_data = interface->iov_data; struct fm10k_hw *hw = &interface->hw; size_t size; - int i, err; + int i; /* return error if iov_data is already populated */ if (iov_data) @@ -452,6 +452,7 @@ static s32 fm10k_iov_alloc_data(struct pci_dev *pdev, int num_vfs) /* loop through vf_info structures initializing each entry */ for (i = 0; i < num_vfs; i++) { struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; + int err; /* Record VF VSI value */ vf_info->vsi = i + 1; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 90270b4a1682..e0a2be534b20 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -17,7 +17,7 @@ const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; static const char fm10k_driver_string[] = DRV_SUMMARY; static const char fm10k_copyright[] = - "Copyright(c) 2013 - 2018 Intel Corporation."; + "Copyright(c) 2013 - 2019 Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); @@ -315,7 +315,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, /* prefetch first cache line of first page */ prefetch(page_addr); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES)); #endif /* allocate a skb to store the frags */ @@ -946,7 +946,7 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring, struct sk_buff *skb = first->skb; struct fm10k_tx_buffer *tx_buffer; struct fm10k_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned char *data; dma_addr_t dma; unsigned int data_len, size; @@ -1074,7 +1074,8 @@ netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (fm10k_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; @@ -1823,7 +1824,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) v_budget = min_t(u16, v_budget, num_online_cpus()); /* account for vectors not related to queues */ - v_budget += NON_Q_VECTORS(hw); + v_budget += NON_Q_VECTORS; /* At the same time, hardware can only support a maximum of * hw.mac->max_msix_vectors vectors. With features @@ -1855,7 +1856,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) } /* record the number of queues available for q_vectors */ - interface->num_q_vectors = v_budget - NON_Q_VECTORS(hw); + interface->num_q_vectors = v_budget - NON_Q_VECTORS; return 0; } @@ -1869,7 +1870,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) { struct net_device *dev = interface->netdev; - int pc, offset, rss_i, i, q_idx; + int pc, offset, rss_i, i; u16 pc_stride = interface->ring_feature[RING_F_QOS].mask + 1; u8 num_pcs = netdev_get_num_tc(dev); @@ -1879,7 +1880,8 @@ static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) rss_i = interface->ring_feature[RING_F_RSS].indices; for (pc = 0, offset = 0; pc < num_pcs; pc++, offset += rss_i) { - q_idx = pc; + int q_idx = pc; + for (i = 0; i < rss_i; i++) { interface->tx_ring[offset + i]->reg_idx = q_idx; interface->tx_ring[offset + i]->qos_pc = pc; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 21021fe4f1c3..75e51f91036c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_common.h" @@ -297,13 +297,14 @@ static u16 fm10k_mbx_validate_msg_size(struct fm10k_mbx_info *mbx, u16 len) { struct fm10k_mbx_fifo *fifo = &mbx->rx; u16 total_len = 0, msg_len; - u32 *msg; /* length should include previous amounts pushed */ len += mbx->pushed; /* offset in message is based off of current message size */ do { + u32 *msg; + msg = fifo->buffer + fm10k_fifo_tail_offset(fifo, total_len); msg_len = FM10K_TLV_DWORD_LEN(*msg); total_len += msg_len; @@ -1920,7 +1921,6 @@ static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw, /* reduce length by 1 to convert to a mask */ u16 mbmem_len = mbx->mbmem_len - 1; u16 tail_len, len = 0; - u32 *msg; /* push head behind tail */ if (mbx->tail < head) @@ -1930,6 +1930,8 @@ static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw, /* determine msg aligned offset for end of buffer */ do { + u32 *msg; + msg = fifo->buffer + fm10k_fifo_head_offset(fifo, len); tail_len = len; len += FM10K_TLV_DWORD_LEN(*msg); @@ -2132,7 +2134,8 @@ fifo_err: * DWORDs, not bytes. Any invalid values will cause the mailbox to return * error. **/ -s32 fm10k_sm_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, +s32 fm10k_sm_mbx_init(struct fm10k_hw __always_unused *hw, + struct fm10k_mbx_info *mbx, const struct fm10k_msg_data *msg_data) { mbx->mbx_reg = FM10K_GMBX; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 538a8467f434..d3e85480f46d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" #include <linux/vmalloc.h> @@ -54,7 +54,7 @@ err: **/ static int fm10k_setup_all_tx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_tx_queues; i++) { err = fm10k_setup_tx_resources(interface->tx_ring[i]); @@ -121,7 +121,7 @@ err: **/ static int fm10k_setup_all_rx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_rx_queues; i++) { err = fm10k_setup_rx_resources(interface->rx_ring[i]); @@ -169,7 +169,6 @@ void fm10k_unmap_and_free_tx_resource(struct fm10k_ring *ring, **/ static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring) { - struct fm10k_tx_buffer *tx_buffer; unsigned long size; u16 i; @@ -179,7 +178,8 @@ static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring) /* Free all the Tx ring sk_buffs */ for (i = 0; i < tx_ring->count; i++) { - tx_buffer = &tx_ring->tx_buffer[i]; + struct fm10k_tx_buffer *tx_buffer = &tx_ring->tx_buffer[i]; + fm10k_unmap_and_free_tx_resource(tx_ring, tx_buffer); } @@ -871,7 +871,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -891,7 +891,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -1444,11 +1444,11 @@ static int __fm10k_setup_tc(struct net_device *dev, enum tc_setup_type type, static void fm10k_assign_l2_accel(struct fm10k_intfc *interface, struct fm10k_l2_accel *l2_accel) { - struct fm10k_ring *ring; int i; for (i = 0; i < interface->num_rx_queues; i++) { - ring = interface->rx_ring[i]; + struct fm10k_ring *ring = interface->rx_ring[i]; + rcu_assign_pointer(ring->l2_accel, l2_accel); } @@ -1463,7 +1463,7 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, struct fm10k_l2_accel *old_l2_accel = NULL; struct fm10k_dglort_cfg dglort = { 0 }; struct fm10k_hw *hw = &interface->hw; - int size = 0, i; + int size, i; u16 vid, glort; /* The hardware supported by fm10k only filters on the destination MAC diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index e49fb51d3613..bb236fa44048 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/module.h> #include <linux/interrupt.h> @@ -344,7 +344,6 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) struct net_device *netdev = interface->netdev; u32 __iomem *hw_addr; u32 value; - int err; /* do nothing if netdev is still present or hw_addr is set */ if (netif_device_present(netdev) || interface->hw.hw_addr) @@ -362,6 +361,8 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) hw_addr = READ_ONCE(interface->uc_addr); value = readl(hw_addr); if (~value) { + int err; + /* Make sure the reset was initiated because we detached, * otherwise we might race with a different reset flow. */ @@ -697,8 +698,6 @@ static void fm10k_watchdog_subtask(struct fm10k_intfc *interface) */ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) { - int i; - /* If we're down or resetting, just bail */ if (test_bit(__FM10K_DOWN, interface->state) || test_bit(__FM10K_RESETTING, interface->state)) @@ -710,6 +709,8 @@ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) interface->next_tx_hang_check = jiffies + (2 * HZ); if (netif_carrier_ok(interface->netdev)) { + int i; + /* Force detection of hung controller */ for (i = 0; i < interface->num_tx_queues; i++) set_check_for_tx_hang(interface->tx_ring[i]); @@ -897,7 +898,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - txint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + txint = ring->q_vector->v_idx + NON_Q_VECTORS; txint |= FM10K_INT_MAP_TIMER0; } @@ -1036,7 +1037,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - rxint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + rxint = ring->q_vector->v_idx + NON_Q_VECTORS; rxint |= FM10K_INT_MAP_TIMER1; } @@ -1719,10 +1720,9 @@ int fm10k_mbx_request_irq(struct fm10k_intfc *interface) void fm10k_qv_free_irq(struct fm10k_intfc *interface) { int vector = interface->num_q_vectors; - struct fm10k_hw *hw = &interface->hw; struct msix_entry *entry; - entry = &interface->msix_entries[NON_Q_VECTORS(hw) + vector]; + entry = &interface->msix_entries[NON_Q_VECTORS + vector]; while (vector) { struct fm10k_q_vector *q_vector; @@ -1759,7 +1759,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) unsigned int ri = 0, ti = 0; int vector, err; - entry = &interface->msix_entries[NON_Q_VECTORS(hw)]; + entry = &interface->msix_entries[NON_Q_VECTORS]; for (vector = 0; vector < interface->num_q_vectors; vector++) { struct fm10k_q_vector *q_vector = interface->q_vector[vector]; @@ -2339,7 +2339,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) /* Restart the MAC/VLAN request queue in-case of outstanding events */ fm10k_macvlan_schedule(interface); - return err; + return 0; } /** @@ -2352,7 +2352,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) **/ static int __maybe_unused fm10k_resume(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); + struct fm10k_intfc *interface = dev_get_drvdata(dev); struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; int err; @@ -2379,7 +2379,7 @@ static int __maybe_unused fm10k_resume(struct device *dev) **/ static int __maybe_unused fm10k_suspend(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); + struct fm10k_intfc *interface = dev_get_drvdata(dev); struct net_device *netdev = interface->netdev; netif_device_detach(netdev); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index cb4d02629b86..be07bfdb0bb4 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_pf.h" #include "fm10k_vf.h" @@ -1152,7 +1152,7 @@ static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw, * assumption is that in this case it is acceptable to just directly * hand off the message from the VF to the underlying shared code. **/ -s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, +s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 __always_unused **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; @@ -1352,7 +1352,6 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; - u32 *result; s32 err = 0; u32 msg[2]; u8 mode = 0; @@ -1362,7 +1361,7 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, return FM10K_ERR_PARAM; if (!!results[FM10K_LPORT_STATE_MSG_XCAST_MODE]) { - result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE]; + u32 *result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE]; /* XCAST mode update requested */ err = fm10k_tlv_attr_get_u8(result, &mode); @@ -1566,7 +1565,7 @@ static s32 fm10k_get_fault_pf(struct fm10k_hw *hw, int type, /* read remaining fields */ fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_HI); fault->address <<= 32; - fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); + fault->address |= fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); fault->specinfo = fm10k_read_reg(hw, type + FM10K_FAULT_SPECINFO); /* clear valid bit to allow for next error */ @@ -1642,7 +1641,7 @@ const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[] = { * switch API. **/ s32 fm10k_msg_lport_map_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, mask; u32 dglort_map; @@ -1685,7 +1684,7 @@ const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[] = { * This handler configures the default VLAN for the PF **/ static s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, pvid; u32 pvid_update; @@ -1746,7 +1745,7 @@ const struct fm10k_tlv_attr fm10k_err_msg_attr[] = { * messages that the PF has sent. **/ s32 fm10k_msg_err_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { struct fm10k_swapi_error err_msg; s32 err; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c index 2a7a40bf2b1c..21eff0895a7a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_tlv.h" @@ -472,7 +472,7 @@ static s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results, const struct fm10k_tlv_attr *tlv_attr) { u32 i, attr_id, offset = 0; - s32 err = 0; + s32 err; u16 len; /* verify pointers are not NULL */ @@ -587,8 +587,9 @@ s32 fm10k_tlv_msg_parse(struct fm10k_hw *hw, u32 *msg, * a minimum it just indicates that the message requested was * unimplemented. **/ -s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) +s32 fm10k_tlv_msg_error(struct fm10k_hw __always_unused *hw, + u32 __always_unused **results, + struct fm10k_mbx_info __always_unused *mbx) { return FM10K_NOT_IMPLEMENTED; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 9fb9fca375e3..15ac1c7885bc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_TYPE_H_ #define _FM10K_TYPE_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index a8519c1f0406..dc8ccd378ec9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_vf.h" @@ -198,7 +198,7 @@ static s32 fm10k_update_vlan_vf(struct fm10k_hw *hw, u32 vid, u8 vsi, bool set) * This function should determine the MAC address for the VF **/ s32 fm10k_msg_mac_vlan_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u8 perm_addr[ETH_ALEN]; u16 vid; @@ -267,8 +267,10 @@ static s32 fm10k_read_mac_addr_vf(struct fm10k_hw *hw) * This function is used to add or remove unicast MAC addresses for * the VF. **/ -static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, - const u8 *mac, u16 vid, bool add, u8 flags) +static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + const u8 *mac, u16 vid, bool add, + u8 __always_unused flags) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[7]; @@ -309,7 +311,8 @@ static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, * This function is used to add or remove multicast MAC addresses for * the VF. **/ -static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, u16 glort, +static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, const u8 *mac, u16 vid, bool add) { struct fm10k_mbx_info *mbx = &hw->mbx; @@ -373,7 +376,7 @@ const struct fm10k_tlv_attr fm10k_lport_state_msg_attr[] = { * are ready to bring up the interface. **/ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { hw->mac.dglort_map = !results[FM10K_LPORT_STATE_MSG_READY] ? FM10K_DGLORTMAP_NONE : FM10K_DGLORTMAP_ZERO; @@ -392,8 +395,9 @@ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, * enabled we can add filters, if it is disabled all filters for this * logical port are flushed. **/ -static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, - u16 count, bool enable) +static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + u16 __always_unused count, bool enable) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[2]; @@ -420,7 +424,8 @@ static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, * so that it can enable either multicast, multicast promiscuous, or * promiscuous mode of operation. **/ -static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, u16 glort, u8 mode) +static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, + u16 __always_unused glort, u8 mode) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[3]; @@ -475,7 +480,7 @@ static void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw, * that information to then populate a DGLORTMAP/DEC entry and the queues * to which it has been assigned. **/ -static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw *hw, +static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw __always_unused *hw, struct fm10k_dglort_cfg *dglort) { /* verify the dglort pointer */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 84bd06901014..3e535d3263b3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1021,6 +1021,7 @@ i40e_find_vsi_by_type(struct i40e_pf *pf, u16 type) return NULL; } void i40e_update_stats(struct i40e_vsi *vsi); +void i40e_update_veb_stats(struct i40e_veb *veb); void i40e_update_eth_stats(struct i40e_vsi *vsi); struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi); int i40e_fetch_switch_configuration(struct i40e_pf *pf, diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 55d20acfcf70..41232898d8ae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1732,29 +1732,15 @@ static const struct file_operations i40e_dbg_netdev_ops_fops = { **/ void i40e_dbg_pf_init(struct i40e_pf *pf) { - struct dentry *pfile; const char *name = pci_name(pf->pdev); - const struct device *dev = &pf->pdev->dev; pf->i40e_dbg_pf = debugfs_create_dir(name, i40e_dbg_root); - if (!pf->i40e_dbg_pf) - return; - - pfile = debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf, - &i40e_dbg_command_fops); - if (!pfile) - goto create_failed; - pfile = debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf, - &i40e_dbg_netdev_ops_fops); - if (!pfile) - goto create_failed; + debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf, + &i40e_dbg_command_fops); - return; - -create_failed: - dev_info(dev, "debugfs dir/file for %s failed\n", name); - debugfs_remove_recursive(pf->i40e_dbg_pf); + debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf, + &i40e_dbg_netdev_ops_fops); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 527eb52c5401..01e4615b1b4b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -711,6 +711,35 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, } /** + * i40e_get_settings_link_up_fec - Get the FEC mode encoding from mask + * @req_fec_info: mask request FEC info + * @ks: ethtool ksettings to fill in + **/ +static void i40e_get_settings_link_up_fec(u8 req_fec_info, + struct ethtool_link_ksettings *ks) +{ + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); + + if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + } else if (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + } else { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_NONE); + if (I40E_AQ_SET_FEC_AUTO & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_RS); + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + } + } +} + +/** * i40e_get_settings_link_up - Get the Link settings for when link is up * @hw: hw structure * @ks: ethtool ksettings to fill in @@ -769,13 +798,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseSR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseSR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); ethtool_link_ksettings_add_link_mode(ks, supported, 10000baseSR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -892,9 +915,6 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 40000baseKR4_Full); ethtool_link_ksettings_add_link_mode(ks, supported, 25000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); ethtool_link_ksettings_add_link_mode(ks, supported, 20000baseKR2_Full); ethtool_link_ksettings_add_link_mode(ks, supported, @@ -908,10 +928,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 40000baseKR4_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); ethtool_link_ksettings_add_link_mode(ks, advertising, 20000baseKR2_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -929,13 +946,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseCR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); + break; case I40E_PHY_TYPE_25GBASE_AOC: case I40E_PHY_TYPE_25GBASE_ACC: @@ -945,13 +957,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseCR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); + ethtool_link_ksettings_add_link_mode(ks, supported, 10000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -2250,7 +2257,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - struct i40e_veb *veb = pf->veb[pf->lan_veb]; + struct i40e_veb *veb = NULL; unsigned int i; bool veb_stats; u64 *p = data; @@ -2273,8 +2280,14 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, goto check_data_pointer; veb_stats = ((pf->lan_veb != I40E_NO_VEB) && + (pf->lan_veb < I40E_MAX_VEB) && (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)); + if (veb_stats) { + veb = pf->veb[pf->lan_veb]; + i40e_update_veb_stats(veb); + } + /* If veb stats aren't enabled, pass NULL instead of the veb so that * we initialize stats to zero and update the data pointer * intelligently @@ -2329,7 +2342,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) } if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1) - return; + goto check_data_pointer; i40e_add_stat_strings(&data, i40e_gstrings_veb_stats); @@ -2341,6 +2354,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i); +check_data_pointer: WARN_ONCE(data - p != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN, "stat strings count mismatch!"); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 9ebbe3da61bb..6d456e579314 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -677,7 +677,7 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi) * i40e_update_veb_stats - Update Switch component statistics * @veb: the VEB being updated **/ -static void i40e_update_veb_stats(struct i40e_veb *veb) +void i40e_update_veb_stats(struct i40e_veb *veb) { struct i40e_pf *pf = veb->pf; struct i40e_hw *hw = &pf->hw; @@ -2530,6 +2530,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vsi_name, i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); + } else { + dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n", + vsi->netdev->name, + cur_multipromisc ? "entering" : "leaving"); } } @@ -8486,6 +8490,11 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) dev_dbg(&pf->pdev->dev, "PFR requested\n"); i40e_handle_reset_warning(pf, lock_acquired); + dev_info(&pf->pdev->dev, + pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? + "FW LLDP is disabled\n" : + "FW LLDP is enabled\n"); + } else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) { int v; @@ -15605,8 +15614,7 @@ static void i40e_shutdown(struct pci_dev *pdev) **/ static int __maybe_unused i40e_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct i40e_pf *pf = pci_get_drvdata(pdev); + struct i40e_pf *pf = dev_get_drvdata(dev); struct i40e_hw *hw = &pf->hw; /* If we're already suspended, then there is nothing to do */ @@ -15656,8 +15664,7 @@ static int __maybe_unused i40e_suspend(struct device *dev) **/ static int __maybe_unused i40e_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct i40e_pf *pf = pci_get_drvdata(pdev); + struct i40e_pf *pf = dev_get_drvdata(dev); int err; /* If we're not suspended, then there is nothing to do */ @@ -15674,7 +15681,7 @@ static int __maybe_unused i40e_resume(struct device *dev) */ err = i40e_restore_interrupt_scheme(pf); if (err) { - dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n", + dev_err(dev, "Cannot restore interrupt scheme: %d\n", err); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 2a2fe3ec7926..e3f29dc8b290 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3262,7 +3262,7 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) **/ bool __i40e_chk_linearize(struct sk_buff *skb) { - const struct skb_frag_struct *frag, *stale; + const skb_frag_t *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ @@ -3306,7 +3306,7 @@ bool __i40e_chk_linearize(struct sk_buff *skb) * descriptor associated with the fragment. */ if (stale_size > I40E_MAX_DATA_PER_TXD) { - int align_pad = -(stale->page_offset) & + int align_pad = -(skb_frag_off(stale)) & (I40E_MAX_READ_REQ_SIZE - 1); sum -= align_pad; @@ -3349,7 +3349,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); - struct skb_frag_struct *frag; + skb_frag_t *frag; struct i40e_tx_buffer *tx_bi; struct i40e_tx_desc *tx_desc; u16 i = tx_ring->next_to_use; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 100e92d2982f..36d37f31a287 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -521,7 +521,7 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring) **/ static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; int count = 0, size = skb_headlen(skb); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 02b09a8ad54c..4601f9e4e998 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -55,7 +55,12 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; - if (vf->link_forced) { + + /* Always report link is down if the VF queues aren't enabled */ + if (!vf->queues_enabled) { + pfe.event_data.link_event.link_status = false; + pfe.event_data.link_event.link_speed = 0; + } 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); @@ -65,6 +70,7 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event_data.link_event.link_speed = i40e_virtchnl_link_speed(ls->link_speed); } + i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, sizeof(pfe), NULL); } @@ -2037,30 +2043,33 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) alluni = true; aq_ret = i40e_config_vf_promiscuous_mode(vf, info->vsi_id, allmulti, alluni); - if (!aq_ret) { - if (allmulti) { + if (aq_ret) + goto err_out; + + if (allmulti) { + if (!test_and_set_bit(I40E_VF_STATE_MC_PROMISC, + &vf->vf_states)) dev_info(&pf->pdev->dev, "VF %d successfully set multicast promiscuous mode\n", vf->vf_id); - set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - } else { - dev_info(&pf->pdev->dev, - "VF %d successfully unset multicast promiscuous mode\n", - vf->vf_id); - clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - } - if (alluni) { + } else if (test_and_clear_bit(I40E_VF_STATE_MC_PROMISC, + &vf->vf_states)) + dev_info(&pf->pdev->dev, + "VF %d successfully unset multicast promiscuous mode\n", + vf->vf_id); + + if (alluni) { + if (!test_and_set_bit(I40E_VF_STATE_UC_PROMISC, + &vf->vf_states)) dev_info(&pf->pdev->dev, "VF %d successfully set unicast promiscuous mode\n", vf->vf_id); - set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); - } else { - dev_info(&pf->pdev->dev, - "VF %d successfully unset unicast promiscuous mode\n", - vf->vf_id); - clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); - } - } + } else if (test_and_clear_bit(I40E_VF_STATE_UC_PROMISC, + &vf->vf_states)) + dev_info(&pf->pdev->dev, + "VF %d successfully unset unicast promiscuous mode\n", + vf->vf_id); + err_out: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, @@ -2153,7 +2162,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) * VF does not know about these additional VSIs and all * it cares is about its own queues. PF configures these queues * to its appropriate VSIs based on TC mapping - **/ + */ if (vf->adq_enabled) { if (idx >= ARRAY_SIZE(vf->ch)) { aq_ret = I40E_ERR_NO_AVAILABLE_VSI; @@ -2364,6 +2373,8 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) } } + vf->queues_enabled = true; + error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, @@ -2385,6 +2396,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; + /* Immediately mark queues as disabled */ + vf->queues_enabled = false; + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index f65cc0c16550..7164b9bb294f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -99,6 +99,7 @@ struct i40e_vf { unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ bool link_forced; bool link_up; /* only valid if VF link is forced */ + bool queues_enabled; /* true if the VF queues are enabled */ bool spoofchk; u16 num_mac; u16 num_vlan; diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 0cca1b589b56..7a30d5d5ef53 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -2161,7 +2161,7 @@ static void iavf_create_tx_ctx(struct iavf_ring *tx_ring, **/ bool __iavf_chk_linearize(struct sk_buff *skb) { - const struct skb_frag_struct *frag, *stale; + const skb_frag_t *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ @@ -2205,7 +2205,7 @@ bool __iavf_chk_linearize(struct sk_buff *skb) * descriptor associated with the fragment. */ if (stale_size > IAVF_MAX_DATA_PER_TXD) { - int align_pad = -(stale->page_offset) & + int align_pad = -(skb_frag_off(stale)) & (IAVF_MAX_READ_REQ_SIZE - 1); sum -= align_pad; @@ -2269,7 +2269,7 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); - struct skb_frag_struct *frag; + skb_frag_t *frag; struct iavf_tx_buffer *tx_bi; struct iavf_tx_desc *tx_desc; u16 i = tx_ring->next_to_use; diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 71e7d090f8db..dd3348f9da9d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -462,7 +462,7 @@ bool __iavf_chk_linearize(struct sk_buff *skb); **/ static inline int iavf_xmit_descriptor_count(struct sk_buff *skb) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; int count = 0, size = skb_headlen(skb); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 9ee6b55553c0..794d97460fc7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -329,7 +329,6 @@ struct ice_q_vector { } ____cacheline_internodealigned_in_smp; enum ice_pf_flags { - ICE_FLAG_MSIX_ENA, ICE_FLAG_FLTR_SYNC, ICE_FLAG_RSS_ENA, ICE_FLAG_SRIOV_ENA, @@ -337,6 +336,7 @@ enum ice_pf_flags { ICE_FLAG_DCB_CAPABLE, ICE_FLAG_DCB_ENA, ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, + ICE_FLAG_NO_MEDIA, ICE_FLAG_ENABLE_FW_LLDP, ICE_FLAG_ETHTOOL_CTXT, /* set when ethtool holds RTNL lock */ ICE_PF_FLAGS_NBITS /* must be last */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2e0731c1e1a3..5f9dc76699d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -740,7 +740,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw) ice_get_itr_intrl_gran(hw); - status = ice_init_all_ctrlq(hw); + status = ice_create_all_ctrlq(hw); if (status) goto err_unroll_cqinit; @@ -855,7 +855,7 @@ err_unroll_sched: err_unroll_alloc: devm_kfree(ice_hw_to_dev(hw), hw->port_info); err_unroll_cqinit: - ice_shutdown_all_ctrlq(hw); + ice_destroy_all_ctrlq(hw); return status; } @@ -881,7 +881,7 @@ void ice_deinit_hw(struct ice_hw *hw) /* Attempt to disable FW logging before shutting down control queues */ ice_cfg_fw_log(hw, false); - ice_shutdown_all_ctrlq(hw); + ice_destroy_all_ctrlq(hw); /* Clear VSI contexts if not already cleared */ ice_clear_all_vsi_ctx(hw); @@ -1078,6 +1078,7 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { ICE_CTX_STORE(ice_rlan_ctx, tphdata_ena, 1, 195), ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena, 1, 196), ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh, 3, 198), + ICE_CTX_STORE(ice_rlan_ctx, prefena, 1, 201), { 0 } }; @@ -1088,7 +1089,8 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { * @rxq_index: the index of the Rx queue * * Converts rxq context from sparse to dense structure and then writes - * it to HW register space + * it to HW register space and enables the hardware to prefetch descriptors + * instead of only fetching them on demand */ enum ice_status ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, @@ -1096,6 +1098,11 @@ ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, { u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 }; + if (!rlan_ctx) + return ICE_ERR_BAD_PTR; + + rlan_ctx->prefena = 1; + ice_set_ctx((u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info); return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index); } @@ -3240,40 +3247,44 @@ void ice_replay_post(struct ice_hw *hw) /** * ice_stat_update40 - read 40 bit stat from the chip and update stat values * @hw: ptr to the hardware info - * @hireg: high 32 bit HW register to read from - * @loreg: low 32 bit HW register to read from + * @reg: offset of 64 bit HW register to read from * @prev_stat_loaded: bool to specify if previous stats are loaded * @prev_stat: ptr to previous loaded stat value * @cur_stat: ptr to current stat value */ void -ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, - bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat) +ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat) { - u64 new_data; - - new_data = rd32(hw, loreg); - new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32; + u64 new_data = rd64(hw, reg) & (BIT_ULL(40) - 1); /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. + * when the driver starts. Thus, save the value from the first read + * without adding to the statistic value so that we report stats which + * count up from zero. */ - if (!prev_stat_loaded) + if (!prev_stat_loaded) { *prev_stat = new_data; + return; + } + + /* Calculate the difference between the new and old values, and then + * add it to the software stat value. + */ if (new_data >= *prev_stat) - *cur_stat = new_data - *prev_stat; + *cur_stat += new_data - *prev_stat; else /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat; - *cur_stat &= 0xFFFFFFFFFFULL; + *cur_stat += (new_data + BIT_ULL(40)) - *prev_stat; + + /* Update the previously stored value to prepare for next read */ + *prev_stat = new_data; } /** * ice_stat_update32 - read 32 bit stat from the chip and update stat values * @hw: ptr to the hardware info - * @reg: HW register to read from + * @reg: offset of HW register to read from * @prev_stat_loaded: bool to specify if previous stats are loaded * @prev_stat: ptr to previous loaded stat value * @cur_stat: ptr to current stat value @@ -3287,17 +3298,26 @@ ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, new_data = rd32(hw, reg); /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. + * when the driver starts. Thus, save the value from the first read + * without adding to the statistic value so that we report stats which + * count up from zero. */ - if (!prev_stat_loaded) + if (!prev_stat_loaded) { *prev_stat = new_data; + return; + } + + /* Calculate the difference between the new and old values, and then + * add it to the software stat value. + */ if (new_data >= *prev_stat) - *cur_stat = new_data - *prev_stat; + *cur_stat += new_data - *prev_stat; else /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat; + *cur_stat += (new_data + BIT_ULL(32)) - *prev_stat; + + /* Update the previously stored value to prepare for next read */ + *prev_stat = new_data; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index d1f8353fe6bb..e376d1eadba4 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -17,8 +17,10 @@ enum ice_status ice_init_hw(struct ice_hw *hw); void ice_deinit_hw(struct ice_hw *hw); enum ice_status ice_check_reset(struct ice_hw *hw); enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req); +enum ice_status ice_create_all_ctrlq(struct ice_hw *hw); enum ice_status ice_init_all_ctrlq(struct ice_hw *hw); void ice_shutdown_all_ctrlq(struct ice_hw *hw); +void ice_destroy_all_ctrlq(struct ice_hw *hw); enum ice_status ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_rq_event_info *e, u16 *pending); @@ -123,8 +125,8 @@ enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); void ice_replay_post(struct ice_hw *hw); void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); void -ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, - bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); +ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat); void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index e91ac4df0242..2353166c654e 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -310,7 +310,7 @@ ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) * @cq: pointer to the specific Control queue * * This is the main initialization routine for the Control Send Queue - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_sq_entries * - cq->sq_buf_size @@ -369,7 +369,7 @@ init_ctrlq_exit: * @cq: pointer to the specific Control queue * * The main initialization routine for the Admin Receive (Event) Queue. - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_rq_entries * - cq->rq_buf_size @@ -569,14 +569,8 @@ static enum ice_status ice_init_check_adminq(struct ice_hw *hw) return 0; init_ctrlq_free_rq: - if (cq->rq.count) { - ice_shutdown_rq(hw, cq); - mutex_destroy(&cq->rq_lock); - } - if (cq->sq.count) { - ice_shutdown_sq(hw, cq); - mutex_destroy(&cq->sq_lock); - } + ice_shutdown_rq(hw, cq); + ice_shutdown_sq(hw, cq); return status; } @@ -585,12 +579,14 @@ init_ctrlq_free_rq: * @hw: pointer to the hardware structure * @q_type: specific Control queue type * - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_sq_entries * - cq->num_rq_entries * - cq->rq_buf_size * - cq->sq_buf_size + * + * NOTE: this function does not initialize the controlq locks */ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) { @@ -616,8 +612,6 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) !cq->rq_buf_size || !cq->sq_buf_size) { return ICE_ERR_CFG; } - mutex_init(&cq->sq_lock); - mutex_init(&cq->rq_lock); /* setup SQ command write back timeout */ cq->sq_cmd_timeout = ICE_CTL_Q_SQ_CMD_TIMEOUT; @@ -625,7 +619,7 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) /* allocate the ATQ */ ret_code = ice_init_sq(hw, cq); if (ret_code) - goto init_ctrlq_destroy_locks; + return ret_code; /* allocate the ARQ */ ret_code = ice_init_rq(hw, cq); @@ -637,9 +631,6 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) init_ctrlq_free_sq: ice_shutdown_sq(hw, cq); -init_ctrlq_destroy_locks: - mutex_destroy(&cq->sq_lock); - mutex_destroy(&cq->rq_lock); return ret_code; } @@ -647,12 +638,14 @@ init_ctrlq_destroy_locks: * ice_init_all_ctrlq - main initialization routine for all control queues * @hw: pointer to the hardware structure * - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver MUST* set the following fields * in the cq->structure for all control queues: * - cq->num_sq_entries * - cq->num_rq_entries * - cq->rq_buf_size * - cq->sq_buf_size + * + * NOTE: this function does not initialize the controlq locks. */ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) { @@ -672,9 +665,47 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) } /** + * ice_init_ctrlq_locks - Initialize locks for a control queue + * @cq: pointer to the control queue + * + * Initializes the send and receive queue locks for a given control queue. + */ +static void ice_init_ctrlq_locks(struct ice_ctl_q_info *cq) +{ + mutex_init(&cq->sq_lock); + mutex_init(&cq->rq_lock); +} + +/** + * ice_create_all_ctrlq - main initialization routine for all control queues + * @hw: pointer to the hardware structure + * + * Prior to calling this function, the driver *MUST* set the following fields + * in the cq->structure for all control queues: + * - cq->num_sq_entries + * - cq->num_rq_entries + * - cq->rq_buf_size + * - cq->sq_buf_size + * + * This function creates all the control queue locks and then calls + * ice_init_all_ctrlq. It should be called once during driver load. If the + * driver needs to re-initialize control queues at run time it should call + * ice_init_all_ctrlq instead. + */ +enum ice_status ice_create_all_ctrlq(struct ice_hw *hw) +{ + ice_init_ctrlq_locks(&hw->adminq); + ice_init_ctrlq_locks(&hw->mailboxq); + + return ice_init_all_ctrlq(hw); +} + +/** * ice_shutdown_ctrlq - shutdown routine for any control queue * @hw: pointer to the hardware structure * @q_type: specific Control queue type + * + * NOTE: this function does not destroy the control queue locks. */ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) { @@ -693,19 +724,17 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) return; } - if (cq->sq.count) { - ice_shutdown_sq(hw, cq); - mutex_destroy(&cq->sq_lock); - } - if (cq->rq.count) { - ice_shutdown_rq(hw, cq); - mutex_destroy(&cq->rq_lock); - } + ice_shutdown_sq(hw, cq); + ice_shutdown_rq(hw, cq); } /** * ice_shutdown_all_ctrlq - shutdown routine for all control queues * @hw: pointer to the hardware structure + * + * NOTE: this function does not destroy the control queue locks. The driver + * may call this at runtime to shutdown and later restart control queues, such + * as in response to a reset event. */ void ice_shutdown_all_ctrlq(struct ice_hw *hw) { @@ -716,6 +745,37 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw) } /** + * ice_destroy_ctrlq_locks - Destroy locks for a control queue + * @cq: pointer to the control queue + * + * Destroys the send and receive queue locks for a given control queue. + */ +static void +ice_destroy_ctrlq_locks(struct ice_ctl_q_info *cq) +{ + mutex_destroy(&cq->sq_lock); + mutex_destroy(&cq->rq_lock); +} + +/** + * ice_destroy_all_ctrlq - exit routine for all control queues + * @hw: pointer to the hardware structure + * + * This function shuts down all the control queues and then destroys the + * control queue locks. It should be called once during driver unload. The + * driver should call ice_shutdown_all_ctrlq if it needs to shut down and + * reinitialize control queues, such as in response to a reset event. + */ +void ice_destroy_all_ctrlq(struct ice_hw *hw) +{ + /* shut down all the control queues first */ + ice_shutdown_all_ctrlq(hw); + + ice_destroy_ctrlq_locks(&hw->adminq); + ice_destroy_ctrlq_locks(&hw->mailboxq); +} + +/** * ice_clean_sq - cleans Admin send queue (ATQ) * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 52083a63dee6..d3ba535bd65a 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1716,6 +1716,7 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_port_info *pi = np->vsi->port_info; struct ethtool_link_ksettings cap_ksettings; struct ice_link_status *link_info; struct ice_vsi *vsi = np->vsi; @@ -2040,6 +2041,33 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, break; } ks->base.duplex = DUPLEX_FULL; + + if (link_info->an_info & ICE_AQ_AN_COMPLETED) + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, + Autoneg); + + /* Set flow control negotiated Rx/Tx pause */ + switch (pi->fc.current_mode) { + case ICE_FC_FULL: + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, Pause); + break; + case ICE_FC_TX_PAUSE: + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, Pause); + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, + Asym_Pause); + break; + case ICE_FC_RX_PAUSE: + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, + Asym_Pause); + break; + case ICE_FC_PFC: + /* fall through */ + default: + ethtool_link_ksettings_del_link_mode(ks, lp_advertising, Pause); + ethtool_link_ksettings_del_link_mode(ks, lp_advertising, + Asym_Pause); + break; + } } /** @@ -2078,9 +2106,12 @@ ice_get_link_ksettings(struct net_device *netdev, struct ice_aqc_get_phy_caps_data *caps; struct ice_link_status *hw_link_info; struct ice_vsi *vsi = np->vsi; + enum ice_status status; + int err = 0; ethtool_link_ksettings_zero_link_mode(ks, supported); ethtool_link_ksettings_zero_link_mode(ks, advertising); + ethtool_link_ksettings_zero_link_mode(ks, lp_advertising); hw_link_info = &vsi->port_info->phy.link_info; /* set speed and duplex */ @@ -2125,48 +2156,36 @@ ice_get_link_ksettings(struct net_device *netdev, /* flow control is symmetric and always supported */ ethtool_link_ksettings_add_link_mode(ks, supported, Pause); - switch (vsi->port_info->fc.req_mode) { - case ICE_FC_FULL: + caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL); + if (!caps) + return -ENOMEM; + + status = ice_aq_get_phy_caps(vsi->port_info, false, + ICE_AQC_REPORT_SW_CFG, caps, NULL); + if (status) { + err = -EIO; + goto done; + } + + /* Set the advertised flow control based on the PHY capability */ + if ((caps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE) && + (caps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE)) { ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); - break; - case ICE_FC_TX_PAUSE: ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); - break; - case ICE_FC_RX_PAUSE: + } else if (caps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + Asym_Pause); + } else if (caps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE) { ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); - break; - case ICE_FC_PFC: - default: + } else { ethtool_link_ksettings_del_link_mode(ks, advertising, Pause); ethtool_link_ksettings_del_link_mode(ks, advertising, Asym_Pause); - break; } - caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL); - if (!caps) - goto done; - - if (ice_aq_get_phy_caps(vsi->port_info, false, ICE_AQC_REPORT_TOPO_CAP, - caps, NULL)) - netdev_info(netdev, "Get phy capability failed.\n"); - - /* Set supported FEC modes based on PHY capability */ - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - - if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN || - caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN) - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN) - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - - if (ice_aq_get_phy_caps(vsi->port_info, false, ICE_AQC_REPORT_SW_CFG, - caps, NULL)) - netdev_info(netdev, "Get phy capability failed.\n"); - /* Set advertised FEC modes based on PHY capability */ ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); @@ -2178,9 +2197,25 @@ ice_get_link_ksettings(struct net_device *netdev, caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ) ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + status = ice_aq_get_phy_caps(vsi->port_info, false, + ICE_AQC_REPORT_TOPO_CAP, caps, NULL); + if (status) { + err = -EIO; + goto done; + } + + /* Set supported FEC modes based on PHY capability */ + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); + + if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN || + caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN) + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); + if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN) + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + done: devm_kfree(&vsi->back->pdev->dev, caps); - return 0; + return err; } /** @@ -2763,6 +2798,11 @@ static int ice_nway_reset(struct net_device *netdev) * ice_get_pauseparam - Get Flow Control status * @netdev: network interface device structure * @pause: ethernet pause (flow control) parameters + * + * Get requested flow control status from PHY capability. + * If autoneg is true, then ethtool will send the ETHTOOL_GSET ioctl which + * is handled by ice_get_link_ksettings. ice_get_link_ksettings will report + * the negotiated Rx/Tx pause via lp_advertising. */ static void ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 6c5ce05742b1..87652d722a30 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -281,14 +281,10 @@ #define GL_PWR_MODE_CTL 0x000B820C #define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) -#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) #define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) -#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) #define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) #define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) -#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) #define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) -#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) #define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) #define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) #define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) @@ -296,38 +292,22 @@ #define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) #define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) #define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) -#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) #define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) -#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) #define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) #define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) -#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) #define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) -#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) #define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) -#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) #define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) -#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) #define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) -#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) #define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) -#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) #define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) -#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) #define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) -#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) #define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) -#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) #define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) -#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) #define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) -#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) #define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) -#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) #define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) -#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) #define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) -#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) #define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) #define GLPRT_PXOFFRXC(_i, _j) (0x00380500 + ((_i) * 8 + (_j) * 64)) #define GLPRT_PXOFFTXC(_i, _j) (0x00380F40 + ((_i) * 8 + (_j) * 64)) @@ -340,32 +320,23 @@ #define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) #define GLPRT_RXON2OFFCNT(_i, _j) (0x00380700 + ((_i) * 8 + (_j) * 64)) #define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) -#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) #define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) -#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) #define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) -#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) #define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) -#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) #define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) -#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) #define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) -#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) #define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) -#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) #define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) -#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) #define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) #define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) #define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) -#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) #define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) -#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) #define PF_VT_PFALLOC_HIF 0x0009DD80 #define VSIQF_HKEY_MAX_INDEX 12 #define VSIQF_HLUT_MAX_INDEX 15 #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) +#define PRTRPB_RDPC 0x000AC260 #endif /* _ICE_HW_AUTOGEN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 510a8c900e61..57ea6811fe2c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -290,6 +290,7 @@ struct ice_rlan_ctx { u8 tphdata_ena; u8 tphhead_ena; u16 lrxqthresh; /* bigger than needed, see above for reason */ + u8 prefena; /* NOTE: normally must be set to 1 at init */ }; struct ice_ctx_ele { diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index a19f5920733b..6e34c40e7840 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1129,12 +1129,7 @@ static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) return -EEXIST; } - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - num_q_vectors = vsi->num_q_vectors; - } else { - err = -EINVAL; - goto err_out; - } + num_q_vectors = vsi->num_q_vectors; for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { err = ice_vsi_alloc_q_vector(vsi, v_idx); @@ -1180,9 +1175,6 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) return -EEXIST; } - if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - return -ENOENT; - num_q_vectors = vsi->num_q_vectors; /* reserve slots from OS requested IRQs */ vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors, @@ -1477,40 +1469,32 @@ void ice_update_eth_stats(struct ice_vsi *vsi) prev_es = &vsi->eth_stats_prev; cur_es = &vsi->eth_stats; - ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_bytes, - &cur_es->rx_bytes); + ice_stat_update40(hw, GLV_GORCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_bytes, &cur_es->rx_bytes); - ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_unicast, - &cur_es->rx_unicast); + ice_stat_update40(hw, GLV_UPRCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_unicast, &cur_es->rx_unicast); - ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_multicast, - &cur_es->rx_multicast); + ice_stat_update40(hw, GLV_MPRCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_multicast, &cur_es->rx_multicast); - ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_broadcast, - &cur_es->rx_broadcast); + ice_stat_update40(hw, GLV_BPRCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_broadcast, &cur_es->rx_broadcast); ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded, &prev_es->rx_discards, &cur_es->rx_discards); - ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_bytes, - &cur_es->tx_bytes); + ice_stat_update40(hw, GLV_GOTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_bytes, &cur_es->tx_bytes); - ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_unicast, - &cur_es->tx_unicast); + ice_stat_update40(hw, GLV_UPTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_unicast, &cur_es->tx_unicast); - ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_multicast, - &cur_es->tx_multicast); + ice_stat_update40(hw, GLV_MPTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_multicast, &cur_es->tx_multicast); - ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_broadcast, - &cur_es->tx_broadcast); + ice_stat_update40(hw, GLV_BPTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_broadcast, &cur_es->tx_broadcast); ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded, &prev_es->tx_errors, &cur_es->tx_errors); @@ -2156,6 +2140,9 @@ ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, if (status == ICE_ERR_RESET_ONGOING) { dev_dbg(&pf->pdev->dev, "Reset in progress. LAN Tx queues already disabled\n"); + } else if (status == ICE_ERR_DOES_NOT_EXIST) { + dev_dbg(&pf->pdev->dev, + "LAN Tx queues does not exist, nothing to disabled\n"); } else if (status) { dev_err(&pf->pdev->dev, "Failed to disable LAN Tx queues, error: %d\n", @@ -2519,7 +2506,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, /* configure VSI nodes based on number of queues and TC's */ for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = pf->num_lan_tx; + max_txqs[i] = vsi->alloc_txq; status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); @@ -2610,39 +2597,36 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; int base = vsi->base_vector; + int i; - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - int i; - - if (!vsi->q_vectors || !vsi->irqs_ready) - return; + if (!vsi->q_vectors || !vsi->irqs_ready) + return; - ice_vsi_release_msix(vsi); - if (vsi->type == ICE_VSI_VF) - return; + ice_vsi_release_msix(vsi); + if (vsi->type == ICE_VSI_VF) + return; - vsi->irqs_ready = false; - ice_for_each_q_vector(vsi, i) { - u16 vector = i + base; - int irq_num; + vsi->irqs_ready = false; + ice_for_each_q_vector(vsi, i) { + u16 vector = i + base; + int irq_num; - irq_num = pf->msix_entries[vector].vector; + irq_num = pf->msix_entries[vector].vector; - /* free only the irqs that were actually requested */ - if (!vsi->q_vectors[i] || - !(vsi->q_vectors[i]->num_ring_tx || - vsi->q_vectors[i]->num_ring_rx)) - continue; + /* free only the irqs that were actually requested */ + if (!vsi->q_vectors[i] || + !(vsi->q_vectors[i]->num_ring_tx || + vsi->q_vectors[i]->num_ring_rx)) + continue; - /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + /* clear the affinity notifier in the IRQ descriptor */ + irq_set_affinity_notifier(irq_num, NULL); - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(irq_num, NULL); - synchronize_irq(irq_num); - devm_free_irq(&pf->pdev->dev, irq_num, - vsi->q_vectors[i]); - } + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(irq_num, NULL); + synchronize_irq(irq_num); + devm_free_irq(&pf->pdev->dev, irq_num, + vsi->q_vectors[i]); } } @@ -2821,15 +2805,13 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi) } /* disable each interrupt */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - ice_for_each_q_vector(vsi, i) - wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); + ice_for_each_q_vector(vsi, i) + wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); - ice_flush(hw); + ice_flush(hw); - ice_for_each_q_vector(vsi, i) - synchronize_irq(pf->msix_entries[i + base].vector); - } + ice_for_each_q_vector(vsi, i) + synchronize_irq(pf->msix_entries[i + base].vector); } /** @@ -2986,6 +2968,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) if (ret) goto err_rings; + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto err_vectors; + ret = ice_vsi_set_q_vectors_reg_idx(vsi); if (ret) goto err_vectors; @@ -3007,10 +2993,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) if (ret) goto err_rings; - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_vectors; - ret = ice_vsi_set_q_vectors_reg_idx(vsi); if (ret) goto err_vectors; @@ -3028,7 +3010,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) /* configure VSI nodes based on number of queues and TC's */ for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = pf->num_lan_tx; + max_txqs[i] = vsi->alloc_txq; status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); @@ -3145,7 +3127,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) if (ena_tc & BIT(i)) num_tc++; /* populate max_txqs per TC */ - max_txqs[i] = pf->num_lan_tx; + max_txqs[i] = vsi->alloc_txq; } vsi->tc_cfg.ena_tc = ena_tc; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 63db08d9bafa..c26e6a102dac 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -9,7 +9,7 @@ #include "ice_lib.h" #include "ice_dcb_lib.h" -#define DRV_VERSION "0.7.4-k" +#define DRV_VERSION "0.7.5-k" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" const char ice_drv_ver[] = DRV_VERSION; static const char ice_driver_string[] = DRV_SUMMARY; @@ -488,6 +488,7 @@ static void ice_prepare_for_reset(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; + u8 i; /* already prepared for reset */ if (test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) @@ -497,6 +498,10 @@ ice_prepare_for_reset(struct ice_pf *pf) if (ice_check_sq_alive(hw, &hw->mailboxq)) ice_vc_notify_reset(pf); + /* Disable VFs until reset is completed */ + for (i = 0; i < pf->num_alloc_vfs; i++) + clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states); + /* disable the VSIs and their queues that are not already DOWN */ ice_pf_dis_all_vsi(pf, false); @@ -810,6 +815,20 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (!vsi || !vsi->port_info) return -EINVAL; + /* turn off PHY if media was removed */ + if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) && + !(pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) { + set_bit(ICE_FLAG_NO_MEDIA, pf->flags); + + result = ice_aq_set_link_restart_an(pi, false, NULL); + if (result) { + dev_dbg(&pf->pdev->dev, + "Failed to set link down, VSI %d error %d\n", + vsi->vsi_num, result); + return result; + } + } + ice_vsi_link_event(vsi, link_up); ice_print_link_msg(vsi, link_up); @@ -1315,6 +1334,124 @@ static void ice_handle_mdd_event(struct ice_pf *pf) } /** + * ice_force_phys_link_state - Force the physical link state + * @vsi: VSI to force the physical link state to up/down + * @link_up: true/false indicates to set the physical link to up/down + * + * Force the physical link state by getting the current PHY capabilities from + * hardware and setting the PHY config based on the determined capabilities. If + * link changes a link event will be triggered because both the Enable Automatic + * Link Update and LESM Enable bits are set when setting the PHY capabilities. + * + * Returns 0 on success, negative on failure + */ +static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) +{ + struct ice_aqc_get_phy_caps_data *pcaps; + struct ice_aqc_set_phy_cfg_data *cfg; + struct ice_port_info *pi; + struct device *dev; + int retcode; + + if (!vsi || !vsi->port_info || !vsi->back) + return -EINVAL; + if (vsi->type != ICE_VSI_PF) + return 0; + + dev = &vsi->back->pdev->dev; + + pi = vsi->port_info; + + pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL); + if (!pcaps) + return -ENOMEM; + + retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, + NULL); + if (retcode) { + dev_err(dev, + "Failed to get phy capabilities, VSI %d error %d\n", + vsi->vsi_num, retcode); + retcode = -EIO; + goto out; + } + + /* No change in link */ + if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) && + link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP)) + goto out; + + cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL); + if (!cfg) { + retcode = -ENOMEM; + goto out; + } + + cfg->phy_type_low = pcaps->phy_type_low; + cfg->phy_type_high = pcaps->phy_type_high; + cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + cfg->low_power_ctrl = pcaps->low_power_ctrl; + cfg->eee_cap = pcaps->eee_cap; + cfg->eeer_value = pcaps->eeer_value; + cfg->link_fec_opt = pcaps->link_fec_options; + if (link_up) + cfg->caps |= ICE_AQ_PHY_ENA_LINK; + else + cfg->caps &= ~ICE_AQ_PHY_ENA_LINK; + + retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL); + if (retcode) { + dev_err(dev, "Failed to set phy config, VSI %d error %d\n", + vsi->vsi_num, retcode); + retcode = -EIO; + } + + devm_kfree(dev, cfg); +out: + devm_kfree(dev, pcaps); + return retcode; +} + +/** + * ice_check_media_subtask - Check for media; bring link up if detected. + * @pf: pointer to PF struct + */ +static void ice_check_media_subtask(struct ice_pf *pf) +{ + struct ice_port_info *pi; + struct ice_vsi *vsi; + int err; + + vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF); + if (!vsi) + return; + + /* No need to check for media if it's already present or the interface + * is down + */ + if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) || + test_bit(__ICE_DOWN, vsi->state)) + return; + + /* Refresh link info and check if media is present */ + pi = vsi->port_info; + err = ice_update_link_info(pi); + if (err) + return; + + if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { + err = ice_force_phys_link_state(vsi, true); + if (err) + return; + clear_bit(ICE_FLAG_NO_MEDIA, pf->flags); + + /* A Link Status Event will be generated; the event handler + * will complete bringing the interface up + */ + } +} + +/** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct */ @@ -1336,6 +1473,7 @@ static void ice_service_task(struct work_struct *work) return; } + ice_check_media_subtask(pf); ice_check_for_hang_subtask(pf); ice_sync_fltr_subtask(pf); ice_handle_mdd_event(pf); @@ -1409,15 +1547,11 @@ static void ice_irq_affinity_release(struct kref __always_unused *ref) {} */ static int ice_vsi_ena_irq(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - int i; + struct ice_hw *hw = &vsi->back->hw; + int i; - ice_for_each_q_vector(vsi, i) - ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]); - } + ice_for_each_q_vector(vsi, i) + ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]); ice_flush(hw); return 0; @@ -1665,7 +1799,7 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) wr32(hw, PFINT_OICR_ENA, 0); ice_flush(hw); - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) { + if (pf->msix_entries) { synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); devm_free_irq(&pf->pdev->dev, pf->msix_entries[pf->oicr_idx].vector, pf); @@ -2091,7 +2225,6 @@ static void ice_deinit_pf(struct ice_pf *pf) static void ice_init_pf(struct ice_pf *pf) { bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS); - set_bit(ICE_FLAG_MSIX_ENA, pf->flags); #ifdef CONFIG_PCI_IOV if (pf->hw.func_caps.common_cap.sr_iov_1_1) { struct ice_hw *hw = &pf->hw; @@ -2191,7 +2324,6 @@ msix_err: exit_err: pf->num_lan_msix = 0; - clear_bit(ICE_FLAG_MSIX_ENA, pf->flags); return err; } @@ -2204,7 +2336,6 @@ static void ice_dis_msix(struct ice_pf *pf) pci_disable_msix(pf->pdev); devm_kfree(&pf->pdev->dev, pf->msix_entries); pf->msix_entries = NULL; - clear_bit(ICE_FLAG_MSIX_ENA, pf->flags); } /** @@ -2213,8 +2344,7 @@ static void ice_dis_msix(struct ice_pf *pf) */ static void ice_clear_interrupt_scheme(struct ice_pf *pf) { - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_dis_msix(pf); + ice_dis_msix(pf); if (pf->irq_tracker) { devm_kfree(&pf->pdev->dev, pf->irq_tracker); @@ -2230,10 +2360,7 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) { int vectors; - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - vectors = ice_ena_msix_range(pf); - else - return -ENODEV; + vectors = ice_ena_msix_range(pf); if (vectors < 0) return vectors; @@ -2390,12 +2517,10 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) * the misc functionality and queue processing is combined in * the same vector and that gets setup at open. */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - err = ice_req_irq_msix_misc(pf); - if (err) { - dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_init_interrupt_unroll; - } + err = ice_req_irq_msix_misc(pf); + if (err) { + dev_err(dev, "setup of misc vector failed: %d\n", err); + goto err_init_interrupt_unroll; } /* create switch struct for the switch element created by FW on boot */ @@ -3008,10 +3133,7 @@ static int ice_up_complete(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; int err; - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_vsi_cfg_msix(vsi); - else - return -ENOTSUPP; + ice_vsi_cfg_msix(vsi); /* Enable only Rx rings, Tx rings were enabled by the FW when the * Tx queue group list was configured and the context bits were @@ -3159,6 +3281,8 @@ static void ice_update_vsi_stats(struct ice_vsi *vsi) cur_ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes; cur_ns->rx_length_errors = pf->stats.rx_len_errors; + /* record drops from the port level */ + cur_ns->rx_missed_errors = pf->stats.eth.rx_discards; } } @@ -3176,96 +3300,86 @@ static void ice_update_pf_stats(struct ice_pf *pf) cur_ps = &pf->stats; pf_id = hw->pf_id; - ice_stat_update40(hw, GLPRT_GORCH(pf_id), GLPRT_GORCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_bytes, + ice_stat_update40(hw, GLPRT_GORCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.rx_bytes, &cur_ps->eth.rx_bytes); - ice_stat_update40(hw, GLPRT_UPRCH(pf_id), GLPRT_UPRCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_unicast, + ice_stat_update40(hw, GLPRT_UPRCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.rx_unicast, &cur_ps->eth.rx_unicast); - ice_stat_update40(hw, GLPRT_MPRCH(pf_id), GLPRT_MPRCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_multicast, + ice_stat_update40(hw, GLPRT_MPRCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.rx_multicast, &cur_ps->eth.rx_multicast); - ice_stat_update40(hw, GLPRT_BPRCH(pf_id), GLPRT_BPRCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_broadcast, + ice_stat_update40(hw, GLPRT_BPRCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.rx_broadcast, &cur_ps->eth.rx_broadcast); - ice_stat_update40(hw, GLPRT_GOTCH(pf_id), GLPRT_GOTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_bytes, + ice_stat_update32(hw, PRTRPB_RDPC, pf->stat_prev_loaded, + &prev_ps->eth.rx_discards, + &cur_ps->eth.rx_discards); + + ice_stat_update40(hw, GLPRT_GOTCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.tx_bytes, &cur_ps->eth.tx_bytes); - ice_stat_update40(hw, GLPRT_UPTCH(pf_id), GLPRT_UPTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_unicast, + ice_stat_update40(hw, GLPRT_UPTCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.tx_unicast, &cur_ps->eth.tx_unicast); - ice_stat_update40(hw, GLPRT_MPTCH(pf_id), GLPRT_MPTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_multicast, + ice_stat_update40(hw, GLPRT_MPTCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.tx_multicast, &cur_ps->eth.tx_multicast); - ice_stat_update40(hw, GLPRT_BPTCH(pf_id), GLPRT_BPTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_broadcast, + ice_stat_update40(hw, GLPRT_BPTCL(pf_id), pf->stat_prev_loaded, + &prev_ps->eth.tx_broadcast, &cur_ps->eth.tx_broadcast); ice_stat_update32(hw, GLPRT_TDOLD(pf_id), pf->stat_prev_loaded, &prev_ps->tx_dropped_link_down, &cur_ps->tx_dropped_link_down); - ice_stat_update40(hw, GLPRT_PRC64H(pf_id), GLPRT_PRC64L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_64, - &cur_ps->rx_size_64); + ice_stat_update40(hw, GLPRT_PRC64L(pf_id), pf->stat_prev_loaded, + &prev_ps->rx_size_64, &cur_ps->rx_size_64); - ice_stat_update40(hw, GLPRT_PRC127H(pf_id), GLPRT_PRC127L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_127, - &cur_ps->rx_size_127); + ice_stat_update40(hw, GLPRT_PRC127L(pf_id), pf->stat_prev_loaded, + &prev_ps->rx_size_127, &cur_ps->rx_size_127); - ice_stat_update40(hw, GLPRT_PRC255H(pf_id), GLPRT_PRC255L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_255, - &cur_ps->rx_size_255); + ice_stat_update40(hw, GLPRT_PRC255L(pf_id), pf->stat_prev_loaded, + &prev_ps->rx_size_255, &cur_ps->rx_size_255); - ice_stat_update40(hw, GLPRT_PRC511H(pf_id), GLPRT_PRC511L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_511, - &cur_ps->rx_size_511); + ice_stat_update40(hw, GLPRT_PRC511L(pf_id), pf->stat_prev_loaded, + &prev_ps->rx_size_511, &cur_ps->rx_size_511); - ice_stat_update40(hw, GLPRT_PRC1023H(pf_id), - GLPRT_PRC1023L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PRC1023L(pf_id), pf->stat_prev_loaded, &prev_ps->rx_size_1023, &cur_ps->rx_size_1023); - ice_stat_update40(hw, GLPRT_PRC1522H(pf_id), - GLPRT_PRC1522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PRC1522L(pf_id), pf->stat_prev_loaded, &prev_ps->rx_size_1522, &cur_ps->rx_size_1522); - ice_stat_update40(hw, GLPRT_PRC9522H(pf_id), - GLPRT_PRC9522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PRC9522L(pf_id), pf->stat_prev_loaded, &prev_ps->rx_size_big, &cur_ps->rx_size_big); - ice_stat_update40(hw, GLPRT_PTC64H(pf_id), GLPRT_PTC64L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_64, - &cur_ps->tx_size_64); + ice_stat_update40(hw, GLPRT_PTC64L(pf_id), pf->stat_prev_loaded, + &prev_ps->tx_size_64, &cur_ps->tx_size_64); - ice_stat_update40(hw, GLPRT_PTC127H(pf_id), GLPRT_PTC127L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_127, - &cur_ps->tx_size_127); + ice_stat_update40(hw, GLPRT_PTC127L(pf_id), pf->stat_prev_loaded, + &prev_ps->tx_size_127, &cur_ps->tx_size_127); - ice_stat_update40(hw, GLPRT_PTC255H(pf_id), GLPRT_PTC255L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_255, - &cur_ps->tx_size_255); + ice_stat_update40(hw, GLPRT_PTC255L(pf_id), pf->stat_prev_loaded, + &prev_ps->tx_size_255, &cur_ps->tx_size_255); - ice_stat_update40(hw, GLPRT_PTC511H(pf_id), GLPRT_PTC511L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_511, - &cur_ps->tx_size_511); + ice_stat_update40(hw, GLPRT_PTC511L(pf_id), pf->stat_prev_loaded, + &prev_ps->tx_size_511, &cur_ps->tx_size_511); - ice_stat_update40(hw, GLPRT_PTC1023H(pf_id), - GLPRT_PTC1023L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PTC1023L(pf_id), pf->stat_prev_loaded, &prev_ps->tx_size_1023, &cur_ps->tx_size_1023); - ice_stat_update40(hw, GLPRT_PTC1522H(pf_id), - GLPRT_PTC1522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PTC1522L(pf_id), pf->stat_prev_loaded, &prev_ps->tx_size_1522, &cur_ps->tx_size_1522); - ice_stat_update40(hw, GLPRT_PTC9522H(pf_id), - GLPRT_PTC9522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PTC9522L(pf_id), pf->stat_prev_loaded, &prev_ps->tx_size_big, &cur_ps->tx_size_big); ice_stat_update32(hw, GLPRT_LXONRXC(pf_id), pf->stat_prev_loaded, @@ -3372,85 +3486,6 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) } /** - * ice_force_phys_link_state - Force the physical link state - * @vsi: VSI to force the physical link state to up/down - * @link_up: true/false indicates to set the physical link to up/down - * - * Force the physical link state by getting the current PHY capabilities from - * hardware and setting the PHY config based on the determined capabilities. If - * link changes a link event will be triggered because both the Enable Automatic - * Link Update and LESM Enable bits are set when setting the PHY capabilities. - * - * Returns 0 on success, negative on failure - */ -static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) -{ - struct ice_aqc_get_phy_caps_data *pcaps; - struct ice_aqc_set_phy_cfg_data *cfg; - struct ice_port_info *pi; - struct device *dev; - int retcode; - - if (!vsi || !vsi->port_info || !vsi->back) - return -EINVAL; - if (vsi->type != ICE_VSI_PF) - return 0; - - dev = &vsi->back->pdev->dev; - - pi = vsi->port_info; - - pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL); - if (!pcaps) - return -ENOMEM; - - retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, - NULL); - if (retcode) { - dev_err(dev, - "Failed to get phy capabilities, VSI %d error %d\n", - vsi->vsi_num, retcode); - retcode = -EIO; - goto out; - } - - /* No change in link */ - if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) && - link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP)) - goto out; - - cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL); - if (!cfg) { - retcode = -ENOMEM; - goto out; - } - - cfg->phy_type_low = pcaps->phy_type_low; - cfg->phy_type_high = pcaps->phy_type_high; - cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; - cfg->low_power_ctrl = pcaps->low_power_ctrl; - cfg->eee_cap = pcaps->eee_cap; - cfg->eeer_value = pcaps->eeer_value; - cfg->link_fec_opt = pcaps->link_fec_options; - if (link_up) - cfg->caps |= ICE_AQ_PHY_ENA_LINK; - else - cfg->caps &= ~ICE_AQ_PHY_ENA_LINK; - - retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL); - if (retcode) { - dev_err(dev, "Failed to set phy config, VSI %d error %d\n", - vsi->vsi_num, retcode); - retcode = -EIO; - } - - devm_kfree(dev, cfg); -out: - devm_kfree(dev, pcaps); - return retcode; -} - -/** * ice_down - Shutdown the connection * @vsi: The VSI being stopped */ @@ -3559,24 +3594,6 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) } /** - * ice_vsi_req_irq - Request IRQ from the OS - * @vsi: The VSI IRQ is being requested for - * @basename: name for the vector - * - * Return 0 on success and a negative value on error - */ -static int ice_vsi_req_irq(struct ice_vsi *vsi, char *basename) -{ - struct ice_pf *pf = vsi->back; - int err = -EINVAL; - - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - err = ice_vsi_req_irq_msix(vsi, basename); - - return err; -} - -/** * ice_vsi_open - Called when a network interface is made active * @vsi: the VSI to open * @@ -3605,7 +3622,7 @@ static int ice_vsi_open(struct ice_vsi *vsi) snprintf(int_name, sizeof(int_name) - 1, "%s-%s", dev_driver_string(&pf->pdev->dev), vsi->netdev->name); - err = ice_vsi_req_irq(vsi, int_name); + err = ice_vsi_req_irq_msix(vsi, int_name); if (err) goto err_setup_rx; @@ -3842,12 +3859,10 @@ static void ice_rebuild(struct ice_pf *pf) } /* start misc vector */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - err = ice_req_irq_msix_misc(pf); - if (err) { - dev_err(dev, "misc vector setup failed: %d\n", err); - goto err_vsi_rebuild; - } + err = ice_req_irq_msix_misc(pf); + if (err) { + dev_err(dev, "misc vector setup failed: %d\n", err); + goto err_vsi_rebuild; } /* restart the VSIs that were rebuilt and running before the reset */ @@ -4244,9 +4259,7 @@ static void ice_tx_timeout(struct net_device *netdev) head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) & QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S; /* Read interrupt register */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - val = rd32(hw, - GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); + val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n", vsi->vsi_num, hung_queue, tx_ring->next_to_clean, @@ -4295,6 +4308,7 @@ int ice_open(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + struct ice_port_info *pi; int err; if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) { @@ -4304,13 +4318,33 @@ int ice_open(struct net_device *netdev) netif_carrier_off(netdev); - err = ice_force_phys_link_state(vsi, true); + pi = vsi->port_info; + err = ice_update_link_info(pi); if (err) { - netdev_err(netdev, - "Failed to set physical link up, error %d\n", err); + netdev_err(netdev, "Failed to get link info, error %d\n", + err); return err; } + /* Set PHY if there is media, otherwise, turn off PHY */ + if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { + err = ice_force_phys_link_state(vsi, true); + if (err) { + netdev_err(netdev, + "Failed to set physical link up, error %d\n", + err); + return err; + } + } else { + err = ice_aq_set_link_restart_an(pi, false, NULL); + if (err) { + netdev_err(netdev, "Failed to set PHY state, VSI %d error %d\n", + vsi->vsi_num, err); + return err; + } + set_bit(ICE_FLAG_NO_MEDIA, vsi->back->flags); + } + err = ice_vsi_open(vsi); if (err) netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n", diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 3c83230434b6..9234fd203929 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -377,18 +377,28 @@ err: */ static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val) { + u16 prev_ntu = rx_ring->next_to_use; + rx_ring->next_to_use = val; /* update next to alloc since we have filled the ring */ rx_ring->next_to_alloc = val; - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). + /* QRX_TAIL will be updated with any tail value, but hardware ignores + * the lower 3 bits. This makes it so we only bump tail on meaningful + * boundaries. Also, this allows us to bump tail on intervals of 8 up to + * the budget depending on the current traffic load. */ - wmb(); - writel(val, rx_ring->tail); + val &= ~0x7; + if (prev_ntu != val) { + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(val, rx_ring->tail); + } } /** @@ -445,7 +455,13 @@ ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi) * @rx_ring: ring to place buffers on * @cleaned_count: number of buffers to replace * - * Returns false if all allocations were successful, true if any fail + * Returns false if all allocations were successful, true if any fail. Returning + * true signals to the caller that we didn't replace cleaned_count buffers and + * there is more work to do. + * + * First, try to clean "cleaned_count" Rx buffers. Then refill the cleaned Rx + * buffers. Then bump tail at most one time. Grouping like this lets us avoid + * multiple tail writes per call. */ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) { @@ -462,8 +478,9 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) bi = &rx_ring->rx_buf[ntu]; do { + /* if we fail here, we have work remaining */ if (!ice_alloc_mapped_page(rx_ring, bi)) - goto no_bufs; + break; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, @@ -494,16 +511,7 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) if (rx_ring->next_to_use != ntu) ice_release_rx_desc(rx_ring, ntu); - return false; - -no_bufs: - if (rx_ring->next_to_use != ntu) - ice_release_rx_desc(rx_ring, ntu); - - /* make sure to come back via polling to try again after - * allocation failure - */ - return true; + return !!cleaned_count; } /** @@ -990,7 +998,7 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_pkts = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); - bool failure = false; + bool failure; /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { @@ -1002,13 +1010,6 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) u16 vlan_tag = 0; u8 rx_ptype; - /* return some buffers to hardware, one at a time is too slow */ - if (cleaned_count >= ICE_RX_BUF_WRITE) { - failure = failure || - ice_alloc_rx_bufs(rx_ring, cleaned_count); - cleaned_count = 0; - } - /* get the Rx desc from Rx ring based on 'next_to_clean' */ rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); @@ -1085,6 +1086,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) total_rx_pkts++; } + /* return up to cleaned_count buffers to hardware */ + failure = ice_alloc_rx_bufs(rx_ring, cleaned_count); + /* update queue and vector specific stats */ u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.pkts += total_rx_pkts; @@ -1409,7 +1413,6 @@ int ice_napi_poll(struct napi_struct *napi, int budget) struct ice_q_vector *q_vector = container_of(napi, struct ice_q_vector, napi); struct ice_vsi *vsi = q_vector->vsi; - struct ice_pf *pf = vsi->back; bool clean_complete = true; int budget_per_ring = 0; struct ice_ring *ring; @@ -1450,8 +1453,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * poll us due to busy-polling */ if (likely(napi_complete_done(napi, work_done))) - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_update_ena_itr(vsi, q_vector); + ice_update_ena_itr(vsi, q_vector); return min_t(int, work_done, budget - 1); } @@ -1521,7 +1523,7 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, { u64 td_offset, td_tag, td_cmd; u16 i = tx_ring->next_to_use; - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int data_len, size; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; @@ -1923,7 +1925,7 @@ static unsigned int ice_txd_use_count(unsigned int size) */ static unsigned int ice_xmit_desc_count(struct sk_buff *skb) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; unsigned int count = 0, size = skb_headlen(skb); @@ -1954,7 +1956,7 @@ static unsigned int ice_xmit_desc_count(struct sk_buff *skb) */ static bool __ice_chk_linearize(struct sk_buff *skb) { - const struct skb_frag_struct *frag, *stale; + const skb_frag_t *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 5d24b539648f..ce01cbe70ea4 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -297,13 +297,6 @@ void ice_free_vfs(struct ice_pf *pf) if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { /* disable VF qp mappings */ ice_dis_vf_mappings(&pf->vf[i]); - - /* Set this state so that assigned VF vectors can be - * reclaimed by PF for reuse in ice_vsi_release(). No - * need to clear this bit since pf->vf array is being - * freed anyways after this for loop - */ - set_bit(ICE_VF_STATE_CFG_INTR, pf->vf[i].vf_states); ice_free_vf_res(&pf->vf[i]); } } @@ -551,7 +544,6 @@ static int ice_alloc_vsi_res(struct ice_vf *vf) * expect vector assignment to be changed unless there is a request for * more vectors. */ - clear_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states); ice_alloc_vsi_res_exit: ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); return status; @@ -567,11 +559,6 @@ static int ice_alloc_vf_res(struct ice_vf *vf) int tx_rx_queue_left; int status; - /* setup VF VSI and necessary resources */ - status = ice_alloc_vsi_res(vf); - if (status) - goto ice_alloc_vf_res_exit; - /* Update number of VF queues, in case VF had requested for queue * changes */ @@ -581,6 +568,11 @@ static int ice_alloc_vf_res(struct ice_vf *vf) vf->num_req_qs != vf->num_vf_qs) vf->num_vf_qs = vf->num_req_qs; + /* setup VF VSI and necessary resources */ + status = ice_alloc_vsi_res(vf); + if (status) + goto ice_alloc_vf_res_exit; + if (vf->trusted) set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); else @@ -1283,9 +1275,6 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs) /* assign default capabilities */ set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps); vfs[i].spoofchk = true; - - /* Set this state so that PF driver does VF vector assignment */ - set_bit(ICE_VF_STATE_CFG_INTR, vfs[i].vf_states); } pf->num_alloc_vfs = num_alloc_vfs; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index c3ca522c245a..ada69120ff38 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -30,11 +30,6 @@ enum ice_vf_states { ICE_VF_STATE_DIS, ICE_VF_STATE_MC_PROMISC, ICE_VF_STATE_UC_PROMISC, - /* state to indicate if PF needs to do vector assignment for VF. - * This needs to be set during first time VF initialization or later - * when VF asks for more Vectors through virtchnl OP. - */ - ICE_VF_STATE_CFG_INTR, ICE_VF_STATES_NBITS }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b4df3e319467..b63e77528a91 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5918,7 +5918,7 @@ static int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb = first->skb; struct igb_tx_buffer *tx_buffer; union e1000_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma; unsigned int data_len, size; u32 tx_flags = first->tx_flags; @@ -6074,7 +6074,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (igb_maybe_stop_tx(tx_ring, count + 3)) { /* this is a hard error */ @@ -8879,8 +8880,7 @@ static int __maybe_unused igb_resume(struct device *dev) static int __maybe_unused igb_runtime_idle(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct igb_adapter *adapter = netdev_priv(netdev); if (!igb_has_link(adapter)) diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 34cd30d7162f..0f2b68f4bb0f 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2174,7 +2174,7 @@ static inline int igbvf_tx_map_adv(struct igbvf_adapter *adapter, goto dma_error; for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; count++; i++; diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 59258d791106..db289bcce21d 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -40,7 +40,7 @@ static s32 igc_reset_hw_base(struct igc_hw *hw) ctrl = rd32(IGC_CTRL); hw_dbg("Issuing a global reset to MAC\n"); - wr32(IGC_CTRL, ctrl | IGC_CTRL_RST); + wr32(IGC_CTRL, ctrl | IGC_CTRL_DEV_RST); ret_val = igc_get_auto_rd_done(hw); if (ret_val) { @@ -209,6 +209,9 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) switch (hw->device_id) { case IGC_DEV_ID_I225_LM: case IGC_DEV_ID_I225_V: + case IGC_DEV_ID_I225_I: + case IGC_DEV_ID_I220_V: + case IGC_DEV_ID_I225_K: mac->type = igc_i225; break; default: diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index fc0ccfe38a20..11b99acf4abe 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -54,7 +54,7 @@ #define IGC_ERR_SWFW_SYNC 13 /* Device Control */ -#define IGC_CTRL_RST 0x04000000 /* Global reset */ +#define IGC_CTRL_DEV_RST 0x20000000 /* Device reset */ #define IGC_CTRL_PHY_RST 0x80000000 /* PHY Reset */ #define IGC_CTRL_SLU 0x00000040 /* Set link up (Force Link) */ diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index 1039a224ac80..abb2d72911ff 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -18,6 +18,9 @@ #define IGC_DEV_ID_I225_LM 0x15F2 #define IGC_DEV_ID_I225_V 0x15F3 +#define IGC_DEV_ID_I225_I 0x15F8 +#define IGC_DEV_ID_I220_V 0x15F7 +#define IGC_DEV_ID_I225_K 0x3100 #define IGC_FUNC_0 0 @@ -151,16 +154,10 @@ struct igc_phy_info { u16 autoneg_advertised; u16 autoneg_mask; - u16 cable_length; - u16 max_cable_length; - u16 min_cable_length; - u16 pair_length[4]; u8 mdix; - bool disable_polarity_correction; bool is_mdix; - bool polarity_correction; bool reset_disable; bool speed_downgraded; bool autoneg_wait_to_complete; @@ -190,12 +187,7 @@ struct igc_fc_info { }; struct igc_dev_spec_base { - bool global_device_reset; - bool eee_disable; bool clear_semaphore_once; - bool module_plugged; - u8 media_port; - bool mas_capable; }; struct igc_hw { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index aa9323e55406..e5114bebd30b 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -36,6 +36,9 @@ static const struct igc_info *igc_info_tbl[] = { static const struct pci_device_id igc_pci_tbl[] = { { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_LM), board_base }, { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_V), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_I), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I220_V), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K), board_base }, /* required last entry */ {0, } }; @@ -861,7 +864,7 @@ static int igc_tx_map(struct igc_ring *tx_ring, struct igc_tx_buffer *tx_buffer; union igc_adv_tx_desc *tx_desc; u32 tx_flags = first->tx_flags; - struct skb_frag_struct *frag; + skb_frag_t *frag; u16 i = tx_ring->next_to_use; unsigned int data_len, size; dma_addr_t dma; @@ -1015,7 +1018,8 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (igc_maybe_stop_tx(tx_ring, count + 3)) { /* this is a hard error */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index e5ac2d3fd816..0940a0da16f2 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -1331,9 +1331,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[f]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; len = skb_frag_size(frag); offset = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c index 50dfb02fa34c..171cdc552961 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -190,22 +190,12 @@ static const struct file_operations ixgbe_dbg_netdev_ops_fops = { void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) { const char *name = pci_name(adapter->pdev); - struct dentry *pfile; + adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); - if (adapter->ixgbe_dbg_adapter) { - pfile = debugfs_create_file("reg_ops", 0600, - adapter->ixgbe_dbg_adapter, adapter, - &ixgbe_dbg_reg_ops_fops); - if (!pfile) - e_dev_err("debugfs reg_ops for %s failed\n", name); - pfile = debugfs_create_file("netdev_ops", 0600, - adapter->ixgbe_dbg_adapter, adapter, - &ixgbe_dbg_netdev_ops_fops); - if (!pfile) - e_dev_err("debugfs netdev_ops for %s failed\n", name); - } else { - e_dev_err("debugfs entry for %s failed\n", name); - } + debugfs_create_file("reg_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_reg_ops_fops); + debugfs_create_file("netdev_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_netdev_ops_fops); } /** @@ -224,8 +214,6 @@ void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) void ixgbe_dbg_init(void) { ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL); - if (ixgbe_dbg_root == NULL) - pr_err("init of debugfs failed\n"); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 7882148abb43..17b7ae9f46ec 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1785,7 +1785,7 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, struct sk_buff *skb) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned char *va; unsigned int pull_len; @@ -1807,7 +1807,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, /* update all of the pointers */ skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; + skb_frag_off_add(frag, pull_len); skb->data_len -= pull_len; skb->tail += pull_len; } @@ -1840,11 +1840,11 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, skb_headlen(skb), DMA_FROM_DEVICE); } else { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; dma_sync_single_range_for_cpu(rx_ring->dev, IXGBE_CB(skb)->dma, - frag->page_offset, + skb_frag_off(frag), skb_frag_size(frag), DMA_FROM_DEVICE); } @@ -8183,7 +8183,7 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, struct sk_buff *skb = first->skb; struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma; unsigned int data_len, size; u32 tx_flags = first->tx_flags; @@ -8602,7 +8602,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index d2b41f9f87f8..8c011d4ce7a9 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3949,7 +3949,7 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, struct sk_buff *skb = first->skb; struct ixgbevf_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma; unsigned int data_len, size; u32 tx_flags = first->tx_flags; @@ -4134,8 +4134,11 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ #if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD - for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; + + count += TXD_USE_COUNT(skb_frag_size(frag)); + } #else count += skb_shinfo(skb)->nr_frags; #endif diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 0b668357db4d..6d52cf5ce20e 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -2030,23 +2030,22 @@ jme_map_tx_skb(struct jme_adapter *jme, struct sk_buff *skb, int idx) bool hidma = jme->dev->features & NETIF_F_HIGHDMA; int i, nr_frags = skb_shinfo(skb)->nr_frags; int mask = jme->tx_ring_mask; - const struct skb_frag_struct *frag; u32 len; int ret = 0; for (i = 0 ; i < nr_frags ; ++i) { - frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + ctxdesc = txdesc + ((idx + i + 2) & (mask)); ctxbi = txbi + ((idx + i + 2) & (mask)); ret = jme_fill_tx_map(jme->pdev, ctxdesc, ctxbi, - skb_frag_page(frag), - frag->page_offset, skb_frag_size(frag), hidma); + skb_frag_page(frag), skb_frag_off(frag), + skb_frag_size(frag), hidma); if (ret) { jme_drop_tx_map(jme, idx, i); goto out; } - } len = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len; @@ -3193,8 +3192,7 @@ jme_shutdown(struct pci_dev *pdev) static int jme_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct jme_adapter *jme = netdev_priv(netdev); if (!netif_running(netdev)) @@ -3236,8 +3234,7 @@ jme_suspend(struct device *dev) static int jme_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct jme_adapter *jme = netdev_priv(netdev); if (!netif_running(netdev)) diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index cda641ef89af..900affbdcc0e 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -458,17 +458,11 @@ static int xrx200_probe(struct platform_device *pdev) } priv->chan_rx.dma.irq = platform_get_irq_byname(pdev, "rx"); - if (priv->chan_rx.dma.irq < 0) { - dev_err(dev, "failed to get RX IRQ, %i\n", - priv->chan_rx.dma.irq); + if (priv->chan_rx.dma.irq < 0) return -ENOENT; - } priv->chan_tx.dma.irq = platform_get_irq_byname(pdev, "tx"); - if (priv->chan_tx.dma.irq < 0) { - dev_err(dev, "failed to get TX IRQ, %i\n", - priv->chan_tx.dma.irq); + if (priv->chan_tx.dma.irq < 0) return -ENOENT; - } /* get the clock */ priv->clk = devm_clk_get(dev, NULL); diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 88ea5ac83c93..82ea55ae5053 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -659,7 +659,7 @@ static inline unsigned int has_tiny_unaligned_frags(struct sk_buff *skb) for (frag = 0; frag < skb_shinfo(skb)->nr_frags; frag++) { const skb_frag_t *fragp = &skb_shinfo(skb)->frags[frag]; - if (skb_frag_size(fragp) <= 8 && fragp->page_offset & 7) + if (skb_frag_size(fragp) <= 8 && skb_frag_off(fragp) & 7) return 1; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 895bfed26a8a..e49820675c8c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2350,10 +2350,10 @@ static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb, for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - void *addr = page_address(frag->page.p) + frag->page_offset; + void *addr = skb_frag_address(frag); tx_desc = mvneta_txq_next_desc_get(txq); - tx_desc->data_size = frag->size; + tx_desc->data_size = skb_frag_size(frag); tx_desc->buf_phys_addr = dma_map_single(pp->dev->dev.parent, addr, @@ -4469,7 +4469,6 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) /* Device initialization routine */ static int mvneta_probe(struct platform_device *pdev) { - struct resource *res; struct device_node *dn = pdev->dev.of_node; struct device_node *bm_node; struct mvneta_port *pp; @@ -4553,8 +4552,7 @@ static int mvneta_probe(struct platform_device *pdev) if (!IS_ERR(pp->clk_bus)) clk_prepare_enable(pp->clk_bus); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pp->base = devm_ioremap_resource(&pdev->dev, res); + pp->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pp->base)) { err = PTR_ERR(pp->base); goto err_clk; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 4d9564ba68f6..ee3bab508ee8 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -829,9 +829,8 @@ struct mvpp2_pcpu_stats { /* Per-CPU port control */ struct mvpp2_port_pcpu { struct hrtimer tx_done_timer; + struct net_device *dev; bool timer_scheduled; - /* Tasklet for egress finalization */ - struct tasklet_struct tx_done_tasklet; }; struct mvpp2_queue_vector { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c index 274fb07362cb..4a3baa7e0142 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -452,8 +452,6 @@ static int mvpp2_dbgfs_flow_port_init(struct dentry *parent, struct dentry *port_dir; port_dir = debugfs_create_dir(port->dev->name, parent); - if (IS_ERR(port_dir)) - return PTR_ERR(port_dir); port_entry = &port->priv->dbgfs_entries->port_flow_entries[port->id]; @@ -480,8 +478,6 @@ static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent, sprintf(flow_entry_name, "%02d", flow); flow_entry_dir = debugfs_create_dir(flow_entry_name, parent); - if (!flow_entry_dir) - return -ENOMEM; entry = &priv->dbgfs_entries->flow_entries[flow]; @@ -514,8 +510,6 @@ static int mvpp2_dbgfs_flow_init(struct dentry *parent, struct mvpp2 *priv) int i, ret; flow_dir = debugfs_create_dir("flows", parent); - if (!flow_dir) - return -ENOMEM; for (i = 0; i < MVPP2_N_PRS_FLOWS; i++) { ret = mvpp2_dbgfs_flow_entry_init(flow_dir, priv, i); @@ -539,8 +533,6 @@ static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent, sprintf(prs_entry_name, "%03d", tid); prs_entry_dir = debugfs_create_dir(prs_entry_name, parent); - if (!prs_entry_dir) - return -ENOMEM; entry = &priv->dbgfs_entries->prs_entries[tid]; @@ -578,8 +570,6 @@ static int mvpp2_dbgfs_prs_init(struct dentry *parent, struct mvpp2 *priv) int i, ret; prs_dir = debugfs_create_dir("parser", parent); - if (!prs_dir) - return -ENOMEM; for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) { ret = mvpp2_dbgfs_prs_entry_init(prs_dir, priv, i); @@ -688,8 +678,6 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent, struct dentry *port_dir; port_dir = debugfs_create_dir(port->dev->name, parent); - if (IS_ERR(port_dir)) - return PTR_ERR(port_dir); debugfs_create_file("parser_entries", 0444, port_dir, port, &mvpp2_dbgfs_port_parser_fops); @@ -716,15 +704,10 @@ void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) int ret, i; mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); - if (!mvpp2_root) { + if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL); - if (IS_ERR(mvpp2_root)) - return; - } mvpp2_dir = debugfs_create_dir(name, mvpp2_root); - if (IS_ERR(mvpp2_dir)) - return; priv->dbgfs_dir = mvpp2_dir; priv->dbgfs_entries = kzalloc(sizeof(*priv->dbgfs_entries), GFP_KERNEL); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ccdd47f3b8fb..12e799e99803 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -2651,31 +2651,21 @@ handled: return IRQ_HANDLED; } -static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu) -{ - ktime_t interval; - - if (!port_pcpu->timer_scheduled) { - port_pcpu->timer_scheduled = true; - interval = MVPP2_TXDONE_HRTIMER_PERIOD_NS; - hrtimer_start(&port_pcpu->tx_done_timer, interval, - HRTIMER_MODE_REL_PINNED); - } -} - -static void mvpp2_tx_proc_cb(unsigned long data) +static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) { - struct net_device *dev = (struct net_device *)data; - struct mvpp2_port *port = netdev_priv(dev); + struct net_device *dev; + struct mvpp2_port *port; struct mvpp2_port_pcpu *port_pcpu; unsigned int tx_todo, cause; - port_pcpu = per_cpu_ptr(port->pcpu, - mvpp2_cpu_to_thread(port->priv, smp_processor_id())); + port_pcpu = container_of(timer, struct mvpp2_port_pcpu, tx_done_timer); + dev = port_pcpu->dev; if (!netif_running(dev)) - return; + return HRTIMER_NORESTART; + port_pcpu->timer_scheduled = false; + port = netdev_priv(dev); /* Process all the Tx queues */ cause = (1 << port->ntxqs) - 1; @@ -2683,18 +2673,13 @@ static void mvpp2_tx_proc_cb(unsigned long data) mvpp2_cpu_to_thread(port->priv, smp_processor_id())); /* Set the timer in case not all the packets were processed */ - if (tx_todo) - mvpp2_timer_set(port_pcpu); -} - -static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) -{ - struct mvpp2_port_pcpu *port_pcpu = container_of(timer, - struct mvpp2_port_pcpu, - tx_done_timer); - - tasklet_schedule(&port_pcpu->tx_done_tasklet); + if (tx_todo && !port_pcpu->timer_scheduled) { + port_pcpu->timer_scheduled = true; + hrtimer_forward_now(&port_pcpu->tx_done_timer, + MVPP2_TXDONE_HRTIMER_PERIOD_NS); + return HRTIMER_RESTART; + } return HRTIMER_NORESTART; } @@ -2923,14 +2908,15 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - void *addr = page_address(frag->page.p) + frag->page_offset; + void *addr = skb_frag_address(frag); tx_desc = mvpp2_txq_next_desc_get(aggr_txq); mvpp2_txdesc_txq_set(port, tx_desc, txq->id); - mvpp2_txdesc_size_set(port, tx_desc, frag->size); + mvpp2_txdesc_size_set(port, tx_desc, skb_frag_size(frag)); buf_dma_addr = dma_map_single(port->dev->dev.parent, addr, - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), + DMA_TO_DEVICE); if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) { mvpp2_txq_desc_put(txq); goto cleanup; @@ -3181,7 +3167,12 @@ out: txq_pcpu->count > 0) { struct mvpp2_port_pcpu *port_pcpu = per_cpu_ptr(port->pcpu, thread); - mvpp2_timer_set(port_pcpu); + if (!port_pcpu->timer_scheduled) { + port_pcpu->timer_scheduled = true; + hrtimer_start(&port_pcpu->tx_done_timer, + MVPP2_TXDONE_HRTIMER_PERIOD_NS, + HRTIMER_MODE_REL_PINNED_SOFT); + } } if (test_bit(thread, &port->priv->lock_map)) @@ -3618,7 +3609,6 @@ static int mvpp2_stop(struct net_device *dev) hrtimer_cancel(&port_pcpu->tx_done_timer); port_pcpu->timer_scheduled = false; - tasklet_kill(&port_pcpu->tx_done_tasklet); } } mvpp2_cleanup_rxqs(port); @@ -5010,7 +5000,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, struct device_node *port_node = to_of_node(port_fwnode); netdev_features_t features; struct net_device *dev; - struct resource *res; struct phylink *phylink; char *mac_from = ""; unsigned int ntxqs, nrxqs, thread; @@ -5114,8 +5103,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->comphy = comphy; if (priv->hw_version == MVPP21) { - res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id); - port->base = devm_ioremap_resource(&pdev->dev, res); + port->base = devm_platform_ioremap_resource(pdev, 2 + id); if (IS_ERR(port->base)) { err = PTR_ERR(port->base); goto err_free_irq; @@ -5184,13 +5172,10 @@ static int mvpp2_port_probe(struct platform_device *pdev, port_pcpu = per_cpu_ptr(port->pcpu, thread); hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_REL_PINNED_SOFT); port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb; port_pcpu->timer_scheduled = false; - - tasklet_init(&port_pcpu->tx_done_tasklet, - mvpp2_tx_proc_cb, - (unsigned long)dev); + port_pcpu->dev = dev; } } @@ -5544,14 +5529,12 @@ static int mvpp2_probe(struct platform_device *pdev) if (priv->hw_version == MVPP21) queue_mode = MVPP2_QDIST_SINGLE_MODE; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(&pdev->dev, res); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); if (priv->hw_version == MVPP21) { - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - priv->lms_base = devm_ioremap_resource(&pdev->dev, res); + priv->lms_base = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(priv->lms_base)) return PTR_ERR(priv->lms_base); } else { diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 9ac854c2b371..0a2ec387a482 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3731,7 +3731,6 @@ static int skge_device_event(struct notifier_block *unused, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct skge_port *skge; - struct dentry *d; if (dev->netdev_ops->ndo_open != &skge_up || !skge_debug) goto done; @@ -3739,33 +3738,20 @@ static int skge_device_event(struct notifier_block *unused, skge = netdev_priv(dev); switch (event) { case NETDEV_CHANGENAME: - if (skge->debugfs) { - d = debugfs_rename(skge_debug, skge->debugfs, - skge_debug, dev->name); - if (d) - skge->debugfs = d; - else { - netdev_info(dev, "rename failed\n"); - debugfs_remove(skge->debugfs); - } - } + if (skge->debugfs) + skge->debugfs = debugfs_rename(skge_debug, + skge->debugfs, + skge_debug, dev->name); break; case NETDEV_GOING_DOWN: - if (skge->debugfs) { - debugfs_remove(skge->debugfs); - skge->debugfs = NULL; - } + debugfs_remove(skge->debugfs); + skge->debugfs = NULL; break; case NETDEV_UP: - d = debugfs_create_file(dev->name, 0444, - skge_debug, dev, - &skge_debug_fops); - if (!d || IS_ERR(d)) - netdev_info(dev, "debugfs create failed\n"); - else - skge->debugfs = d; + skge->debugfs = debugfs_create_file(dev->name, 0444, skge_debug, + dev, &skge_debug_fops); break; } @@ -3780,15 +3766,8 @@ static struct notifier_block skge_notifier = { static __init void skge_debug_init(void) { - struct dentry *ent; + skge_debug = debugfs_create_dir("skge", NULL); - ent = debugfs_create_dir("skge", NULL); - if (!ent || IS_ERR(ent)) { - pr_info("debugfs create directory failed\n"); - return; - } - - skge_debug = ent; register_netdevice_notifier(&skge_notifier); } @@ -4078,8 +4057,7 @@ static void skge_remove(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int skge_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct skge_hw *hw = pci_get_drvdata(pdev); + struct skge_hw *hw = dev_get_drvdata(dev); int i; if (!hw) @@ -4103,8 +4081,7 @@ static int skge_suspend(struct device *dev) static int skge_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct skge_hw *hw = pci_get_drvdata(pdev); + struct skge_hw *hw = dev_get_drvdata(dev); int i, err; if (!hw) diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index a01c75ede871..c2e00bb587cd 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5167,8 +5167,7 @@ static void sky2_remove(struct pci_dev *pdev) static int sky2_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct sky2_hw *hw = pci_get_drvdata(pdev); + struct sky2_hw *hw = dev_get_drvdata(dev); int i; if (!hw) diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index 1f7fff81f24d..b76cf2e1c9dc 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config NET_VENDOR_MEDIATEK bool "MediaTek ethernet driver" - depends on ARCH_MEDIATEK || SOC_MT7621 + depends on ARCH_MEDIATEK || SOC_MT7621 || SOC_MT7620 ---help--- If you have a Mediatek SoC with ethernet, say Y. diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c index 7f05880cf9ef..28960e4c4e43 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_path.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c @@ -315,6 +315,10 @@ int mtk_setup_hw_path(struct mtk_eth *eth, int mac_id, int phymode) { int err; + /* No mux'ing for MT7628/88 */ + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) + return 0; + switch (phymode) { case PHY_INTERFACE_MODE_TRGMII: case PHY_INTERFACE_MODE_RGMII_TXID: diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index c39d7f4ab1d4..8ddbb8dcf032 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -323,11 +323,14 @@ static int mtk_phy_connect(struct net_device *dev) goto err_phy; } - /* put the gmac into the right mode */ - regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); - val &= ~SYSCFG0_GE_MODE(SYSCFG0_GE_MASK, mac->id); - val |= SYSCFG0_GE_MODE(mac->ge_mode, mac->id); - regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val); + /* No MT7628/88 support for now */ + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + /* put the gmac into the right mode */ + regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); + val &= ~SYSCFG0_GE_MODE(SYSCFG0_GE_MASK, mac->id); + val |= SYSCFG0_GE_MODE(mac->ge_mode, mac->id); + regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val); + } /* couple phydev to net_device */ if (mtk_phy_connect_node(eth, mac, np)) @@ -395,8 +398,8 @@ static inline void mtk_tx_irq_disable(struct mtk_eth *eth, u32 mask) u32 val; spin_lock_irqsave(ð->tx_irq_lock, flags); - val = mtk_r32(eth, MTK_QDMA_INT_MASK); - mtk_w32(eth, val & ~mask, MTK_QDMA_INT_MASK); + val = mtk_r32(eth, eth->tx_int_mask_reg); + mtk_w32(eth, val & ~mask, eth->tx_int_mask_reg); spin_unlock_irqrestore(ð->tx_irq_lock, flags); } @@ -406,8 +409,8 @@ static inline void mtk_tx_irq_enable(struct mtk_eth *eth, u32 mask) u32 val; spin_lock_irqsave(ð->tx_irq_lock, flags); - val = mtk_r32(eth, MTK_QDMA_INT_MASK); - mtk_w32(eth, val | mask, MTK_QDMA_INT_MASK); + val = mtk_r32(eth, eth->tx_int_mask_reg); + mtk_w32(eth, val | mask, eth->tx_int_mask_reg); spin_unlock_irqrestore(ð->tx_irq_lock, flags); } @@ -437,6 +440,7 @@ static int mtk_set_mac_address(struct net_device *dev, void *p) { int ret = eth_mac_addr(dev, p); struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; const char *macaddr = dev->dev_addr; if (ret) @@ -446,11 +450,19 @@ static int mtk_set_mac_address(struct net_device *dev, void *p) return -EBUSY; spin_lock_bh(&mac->hw->page_lock); - mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], - MTK_GDMA_MAC_ADRH(mac->id)); - mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | - (macaddr[4] << 8) | macaddr[5], - MTK_GDMA_MAC_ADRL(mac->id)); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], + MT7628_SDM_MAC_ADRH); + mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | + (macaddr[4] << 8) | macaddr[5], + MT7628_SDM_MAC_ADRL); + } else { + mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], + MTK_GDMA_MAC_ADRH(mac->id)); + mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | + (macaddr[4] << 8) | macaddr[5], + MTK_GDMA_MAC_ADRL(mac->id)); + } spin_unlock_bh(&mac->hw->page_lock); return 0; @@ -626,19 +638,47 @@ static inline struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring, return &ring->buf[idx]; } +static struct mtk_tx_dma *qdma_to_pdma(struct mtk_tx_ring *ring, + struct mtk_tx_dma *dma) +{ + return ring->dma_pdma - ring->dma + dma; +} + +static int txd_to_idx(struct mtk_tx_ring *ring, struct mtk_tx_dma *dma) +{ + return ((void *)dma - (void *)ring->dma) / sizeof(*dma); +} + static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf) { - if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { - dma_unmap_single(eth->dev, - dma_unmap_addr(tx_buf, dma_addr0), - dma_unmap_len(tx_buf, dma_len0), - DMA_TO_DEVICE); - } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { - dma_unmap_page(eth->dev, - dma_unmap_addr(tx_buf, dma_addr0), - dma_unmap_len(tx_buf, dma_len0), - DMA_TO_DEVICE); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { + dma_unmap_single(eth->dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { + dma_unmap_page(eth->dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } + } else { + if (dma_unmap_len(tx_buf, dma_len0)) { + dma_unmap_page(eth->dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } + + if (dma_unmap_len(tx_buf, dma_len1)) { + dma_unmap_page(eth->dev, + dma_unmap_addr(tx_buf, dma_addr1), + dma_unmap_len(tx_buf, dma_len1), + DMA_TO_DEVICE); + } } + tx_buf->flags = 0; if (tx_buf->skb && (tx_buf->skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC)) @@ -646,19 +686,45 @@ static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf) tx_buf->skb = NULL; } +static void setup_tx_buf(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf, + struct mtk_tx_dma *txd, dma_addr_t mapped_addr, + size_t size, int idx) +{ + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len0, size); + } else { + if (idx & 1) { + txd->txd3 = mapped_addr; + txd->txd2 |= TX_DMA_PLEN1(size); + dma_unmap_addr_set(tx_buf, dma_addr1, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len1, size); + } else { + tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; + txd->txd1 = mapped_addr; + txd->txd2 = TX_DMA_PLEN0(size); + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len0, size); + } + } +} + static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, int tx_num, struct mtk_tx_ring *ring, bool gso) { struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; struct mtk_tx_dma *itxd, *txd; + struct mtk_tx_dma *itxd_pdma, *txd_pdma; struct mtk_tx_buf *itx_buf, *tx_buf; dma_addr_t mapped_addr; unsigned int nr_frags; int i, n_desc = 1; u32 txd4 = 0, fport; + int k = 0; itxd = ring->next_free; + itxd_pdma = qdma_to_pdma(ring, itxd); if (itxd == ring->last_free) return -ENOMEM; @@ -689,26 +755,37 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, itx_buf->flags |= MTK_TX_FLAGS_SINGLE0; itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : MTK_TX_FLAGS_FPORT1; - dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb)); + setup_tx_buf(eth, itx_buf, itxd_pdma, mapped_addr, skb_headlen(skb), + k++); /* TX SG offload */ txd = itxd; + txd_pdma = qdma_to_pdma(ring, txd); nr_frags = skb_shinfo(skb)->nr_frags; + for (i = 0; i < nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; unsigned int offset = 0; int frag_size = skb_frag_size(frag); while (frag_size) { bool last_frag = false; unsigned int frag_map_size; + bool new_desc = true; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA) || + (i & 0x1)) { + txd = mtk_qdma_phys_to_virt(ring, txd->txd2); + txd_pdma = qdma_to_pdma(ring, txd); + if (txd == ring->last_free) + goto err_dma; + + n_desc++; + } else { + new_desc = false; + } - txd = mtk_qdma_phys_to_virt(ring, txd->txd2); - if (txd == ring->last_free) - goto err_dma; - n_desc++; frag_map_size = min(frag_size, MTK_TX_DMA_BUF_LEN); mapped_addr = skb_frag_dma_map(eth->dev, frag, offset, frag_map_size, @@ -727,14 +804,16 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, WRITE_ONCE(txd->txd4, fport); tx_buf = mtk_desc_to_tx_buf(ring, txd); - memset(tx_buf, 0, sizeof(*tx_buf)); + if (new_desc) + memset(tx_buf, 0, sizeof(*tx_buf)); tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf->flags |= MTK_TX_FLAGS_PAGE0; tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : MTK_TX_FLAGS_FPORT1; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, frag_map_size); + setup_tx_buf(eth, tx_buf, txd_pdma, mapped_addr, + frag_map_size, k++); + frag_size -= frag_map_size; offset += frag_map_size; } @@ -746,6 +825,12 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, WRITE_ONCE(itxd->txd4, txd4); WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) | (!nr_frags * TX_DMA_LS0))); + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (k & 0x1) + txd_pdma->txd2 |= TX_DMA_LS0; + else + txd_pdma->txd2 |= TX_DMA_LS1; + } netdev_sent_queue(dev, skb->len); skb_tx_timestamp(skb); @@ -758,9 +843,15 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, */ wmb(); - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || - !netdev_xmit_more()) - mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || + !netdev_xmit_more()) + mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); + } else { + int next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd), + ring->dma_size); + mtk_w32(eth, next_idx, MT7628_TX_CTX_IDX0); + } return 0; @@ -772,7 +863,11 @@ err_dma: mtk_tx_unmap(eth, tx_buf); itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + itxd_pdma->txd2 = TX_DMA_DESP2_DEF; + itxd = mtk_qdma_phys_to_virt(ring, itxd->txd2); + itxd_pdma = qdma_to_pdma(ring, itxd); } while (itxd != txd); return -ENOMEM; @@ -781,13 +876,14 @@ err_dma: static inline int mtk_cal_txd_req(struct sk_buff *skb) { int i, nfrags; - struct skb_frag_struct *frag; + skb_frag_t *frag; nfrags = 1; if (skb_is_gso(skb)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; - nfrags += DIV_ROUND_UP(frag->size, MTK_TX_DMA_BUF_LEN); + nfrags += DIV_ROUND_UP(skb_frag_size(frag), + MTK_TX_DMA_BUF_LEN); } } else { nfrags += skb_shinfo(skb)->nr_frags; @@ -902,7 +998,7 @@ static struct mtk_rx_ring *mtk_get_rx_ring(struct mtk_eth *eth) for (i = 0; i < MTK_MAX_RX_RING_NUM; i++) { ring = ð->rx_ring[i]; - idx = NEXT_RX_DESP_IDX(ring->calc_idx, ring->dma_size); + idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); if (ring->dma[idx].rxd2 & RX_DMA_DONE) { ring->calc_idx_update = true; return ring; @@ -945,13 +1041,13 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, struct net_device *netdev; unsigned int pktlen; dma_addr_t dma_addr; - int mac = 0; + int mac; ring = mtk_get_rx_ring(eth); if (unlikely(!ring)) goto rx_done; - idx = NEXT_RX_DESP_IDX(ring->calc_idx, ring->dma_size); + idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); rxd = &ring->dma[idx]; data = ring->data[idx]; @@ -960,9 +1056,13 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, break; /* find out which mac the packet come from. values start at 1 */ - mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) & - RX_DMA_FPORT_MASK; - mac--; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + mac = 0; + } else { + mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) & + RX_DMA_FPORT_MASK; + mac--; + } if (unlikely(mac < 0 || mac >= MTK_MAC_COUNT || !eth->netdev[mac])) @@ -980,7 +1080,8 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, goto release_desc; } dma_addr = dma_map_single(eth->dev, - new_data + NET_SKB_PAD, + new_data + NET_SKB_PAD + + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dev, dma_addr))) { @@ -1003,7 +1104,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, pktlen = RX_DMA_GET_PLEN0(trxd.rxd2); skb->dev = netdev; skb_put(skb, pktlen); - if (trxd.rxd4 & RX_DMA_L4_VALID) + if (trxd.rxd4 & eth->rx_dma_l4_valid) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb_checksum_none_assert(skb); @@ -1020,7 +1121,10 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, rxd->rxd1 = (unsigned int)dma_addr; release_desc: - rxd->rxd2 = RX_DMA_PLEN0(ring->buf_size); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) + rxd->rxd2 = RX_DMA_LSO; + else + rxd->rxd2 = RX_DMA_PLEN0(ring->buf_size); ring->calc_idx = idx; @@ -1039,19 +1143,14 @@ rx_done: return done; } -static int mtk_poll_tx(struct mtk_eth *eth, int budget) +static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget, + unsigned int *done, unsigned int *bytes) { struct mtk_tx_ring *ring = ð->tx_ring; struct mtk_tx_dma *desc; struct sk_buff *skb; struct mtk_tx_buf *tx_buf; - unsigned int done[MTK_MAX_DEVS]; - unsigned int bytes[MTK_MAX_DEVS]; u32 cpu, dma; - int total = 0, i; - - memset(done, 0, sizeof(done)); - memset(bytes, 0, sizeof(bytes)); cpu = mtk_r32(eth, MTK_QTX_CRX_PTR); dma = mtk_r32(eth, MTK_QTX_DRX_PTR); @@ -1089,6 +1188,62 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) mtk_w32(eth, cpu, MTK_QTX_CRX_PTR); + return budget; +} + +static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget, + unsigned int *done, unsigned int *bytes) +{ + struct mtk_tx_ring *ring = ð->tx_ring; + struct mtk_tx_dma *desc; + struct sk_buff *skb; + struct mtk_tx_buf *tx_buf; + u32 cpu, dma; + + cpu = ring->cpu_idx; + dma = mtk_r32(eth, MT7628_TX_DTX_IDX0); + + while ((cpu != dma) && budget) { + tx_buf = &ring->buf[cpu]; + skb = tx_buf->skb; + if (!skb) + break; + + if (skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC) { + bytes[0] += skb->len; + done[0]++; + budget--; + } + + mtk_tx_unmap(eth, tx_buf); + + desc = &ring->dma[cpu]; + ring->last_free = desc; + atomic_inc(&ring->free_count); + + cpu = NEXT_DESP_IDX(cpu, ring->dma_size); + } + + ring->cpu_idx = cpu; + + return budget; +} + +static int mtk_poll_tx(struct mtk_eth *eth, int budget) +{ + struct mtk_tx_ring *ring = ð->tx_ring; + unsigned int done[MTK_MAX_DEVS]; + unsigned int bytes[MTK_MAX_DEVS]; + int total = 0, i; + + memset(done, 0, sizeof(done)); + memset(bytes, 0, sizeof(bytes)); + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + budget = mtk_poll_tx_qdma(eth, budget, done, bytes); + else + budget = mtk_poll_tx_pdma(eth, budget, done, bytes); + for (i = 0; i < MTK_MAC_COUNT; i++) { if (!eth->netdev[i] || !done[i]) continue; @@ -1120,13 +1275,14 @@ static int mtk_napi_tx(struct napi_struct *napi, int budget) u32 status, mask; int tx_done = 0; - mtk_handle_status_irq(eth); - mtk_w32(eth, MTK_TX_DONE_INT, MTK_QMTK_INT_STATUS); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_handle_status_irq(eth); + mtk_w32(eth, MTK_TX_DONE_INT, eth->tx_int_status_reg); tx_done = mtk_poll_tx(eth, budget); if (unlikely(netif_msg_intr(eth))) { - status = mtk_r32(eth, MTK_QMTK_INT_STATUS); - mask = mtk_r32(eth, MTK_QDMA_INT_MASK); + status = mtk_r32(eth, eth->tx_int_status_reg); + mask = mtk_r32(eth, eth->tx_int_mask_reg); dev_info(eth->dev, "done tx %d, intr 0x%08x/0x%x\n", tx_done, status, mask); @@ -1135,7 +1291,7 @@ static int mtk_napi_tx(struct napi_struct *napi, int budget) if (tx_done == budget) return budget; - status = mtk_r32(eth, MTK_QMTK_INT_STATUS); + status = mtk_r32(eth, eth->tx_int_status_reg); if (status & MTK_TX_DONE_INT) return budget; @@ -1202,6 +1358,24 @@ static int mtk_tx_alloc(struct mtk_eth *eth) ring->dma[i].txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; } + /* On MT7688 (PDMA only) this driver uses the ring->dma structs + * only as the framework. The real HW descriptors are the PDMA + * descriptors in ring->dma_pdma. + */ + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + ring->dma_pdma = dma_alloc_coherent(eth->dev, MTK_DMA_SIZE * sz, + &ring->phys_pdma, + GFP_ATOMIC); + if (!ring->dma_pdma) + goto no_tx_mem; + + for (i = 0; i < MTK_DMA_SIZE; i++) { + ring->dma_pdma[i].txd2 = TX_DMA_DESP2_DEF; + ring->dma_pdma[i].txd4 = 0; + } + } + + ring->dma_size = MTK_DMA_SIZE; atomic_set(&ring->free_count, MTK_DMA_SIZE - 2); ring->next_free = &ring->dma[0]; ring->last_free = &ring->dma[MTK_DMA_SIZE - 1]; @@ -1212,15 +1386,23 @@ static int mtk_tx_alloc(struct mtk_eth *eth) */ wmb(); - mtk_w32(eth, ring->phys, MTK_QTX_CTX_PTR); - mtk_w32(eth, ring->phys, MTK_QTX_DTX_PTR); - mtk_w32(eth, - ring->phys + ((MTK_DMA_SIZE - 1) * sz), - MTK_QTX_CRX_PTR); - mtk_w32(eth, - ring->phys + ((MTK_DMA_SIZE - 1) * sz), - MTK_QTX_DRX_PTR); - mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0)); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + mtk_w32(eth, ring->phys, MTK_QTX_CTX_PTR); + mtk_w32(eth, ring->phys, MTK_QTX_DTX_PTR); + mtk_w32(eth, + ring->phys + ((MTK_DMA_SIZE - 1) * sz), + MTK_QTX_CRX_PTR); + mtk_w32(eth, + ring->phys + ((MTK_DMA_SIZE - 1) * sz), + MTK_QTX_DRX_PTR); + mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, + MTK_QTX_CFG(0)); + } else { + mtk_w32(eth, ring->phys_pdma, MT7628_TX_BASE_PTR0); + mtk_w32(eth, MTK_DMA_SIZE, MT7628_TX_MAX_CNT0); + mtk_w32(eth, 0, MT7628_TX_CTX_IDX0); + mtk_w32(eth, MT7628_PST_DTX_IDX0, MTK_PDMA_RST_IDX); + } return 0; @@ -1247,6 +1429,14 @@ static void mtk_tx_clean(struct mtk_eth *eth) ring->phys); ring->dma = NULL; } + + if (ring->dma_pdma) { + dma_free_coherent(eth->dev, + MTK_DMA_SIZE * sizeof(*ring->dma_pdma), + ring->dma_pdma, + ring->phys_pdma); + ring->dma_pdma = NULL; + } } static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) @@ -1294,14 +1484,17 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) for (i = 0; i < rx_dma_size; i++) { dma_addr_t dma_addr = dma_map_single(eth->dev, - ring->data[i] + NET_SKB_PAD, + ring->data[i] + NET_SKB_PAD + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dev, dma_addr))) return -ENOMEM; ring->dma[i].rxd1 = (unsigned int)dma_addr; - ring->dma[i].rxd2 = RX_DMA_PLEN0(ring->buf_size); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) + ring->dma[i].rxd2 = RX_DMA_LSO; + else + ring->dma[i].rxd2 = RX_DMA_PLEN0(ring->buf_size); } ring->dma_size = rx_dma_size; ring->calc_idx_update = false; @@ -1617,9 +1810,16 @@ static int mtk_dma_busy_wait(struct mtk_eth *eth) unsigned long t_start = jiffies; while (1) { - if (!(mtk_r32(eth, MTK_QDMA_GLO_CFG) & - (MTK_RX_DMA_BUSY | MTK_TX_DMA_BUSY))) - return 0; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (!(mtk_r32(eth, MTK_QDMA_GLO_CFG) & + (MTK_RX_DMA_BUSY | MTK_TX_DMA_BUSY))) + return 0; + } else { + if (!(mtk_r32(eth, MTK_PDMA_GLO_CFG) & + (MTK_RX_DMA_BUSY | MTK_TX_DMA_BUSY))) + return 0; + } + if (time_after(jiffies, t_start + MTK_DMA_BUSY_TIMEOUT)) break; } @@ -1636,20 +1836,24 @@ static int mtk_dma_init(struct mtk_eth *eth) if (mtk_dma_busy_wait(eth)) return -EBUSY; - /* QDMA needs scratch memory for internal reordering of the - * descriptors - */ - err = mtk_init_fq_dma(eth); - if (err) - return err; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + /* QDMA needs scratch memory for internal reordering of the + * descriptors + */ + err = mtk_init_fq_dma(eth); + if (err) + return err; + } err = mtk_tx_alloc(eth); if (err) return err; - err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_QDMA); - if (err) - return err; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_QDMA); + if (err) + return err; + } err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_NORMAL); if (err) @@ -1666,10 +1870,14 @@ static int mtk_dma_init(struct mtk_eth *eth) return err; } - /* Enable random early drop and set drop threshold automatically */ - mtk_w32(eth, FC_THRES_DROP_MODE | FC_THRES_DROP_EN | FC_THRES_MIN, - MTK_QDMA_FC_THRES); - mtk_w32(eth, 0x0, MTK_QDMA_HRED2); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + /* Enable random early drop and set drop threshold + * automatically + */ + mtk_w32(eth, FC_THRES_DROP_MODE | FC_THRES_DROP_EN | + FC_THRES_MIN, MTK_QDMA_FC_THRES); + mtk_w32(eth, 0x0, MTK_QDMA_HRED2); + } return 0; } @@ -1740,13 +1948,15 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth) static irqreturn_t mtk_handle_irq(int irq, void *_eth) { struct mtk_eth *eth = _eth; + u32 status; + status = mtk_r32(eth, MTK_PDMA_INT_STATUS); if (mtk_r32(eth, MTK_PDMA_INT_MASK) & MTK_RX_DONE_INT) { if (mtk_r32(eth, MTK_PDMA_INT_STATUS) & MTK_RX_DONE_INT) mtk_handle_irq_rx(irq, _eth); } - if (mtk_r32(eth, MTK_QDMA_INT_MASK) & MTK_TX_DONE_INT) { - if (mtk_r32(eth, MTK_QMTK_INT_STATUS) & MTK_TX_DONE_INT) + if (mtk_r32(eth, eth->tx_int_mask_reg) & MTK_TX_DONE_INT) { + if (mtk_r32(eth, eth->tx_int_status_reg) & MTK_TX_DONE_INT) mtk_handle_irq_tx(irq, _eth); } @@ -1778,17 +1988,23 @@ static int mtk_start_dma(struct mtk_eth *eth) return err; } - mtk_w32(eth, - MTK_TX_WB_DDONE | MTK_TX_DMA_EN | - MTK_DMA_SIZE_16DWORDS | MTK_NDP_CO_PRO | - MTK_RX_DMA_EN | MTK_RX_2B_OFFSET | - MTK_RX_BT_32DWORDS, - MTK_QDMA_GLO_CFG); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + mtk_w32(eth, + MTK_TX_WB_DDONE | MTK_TX_DMA_EN | + MTK_DMA_SIZE_16DWORDS | MTK_NDP_CO_PRO | + MTK_RX_DMA_EN | MTK_RX_2B_OFFSET | + MTK_RX_BT_32DWORDS, + MTK_QDMA_GLO_CFG); - mtk_w32(eth, - MTK_RX_DMA_EN | rx_2b_offset | - MTK_RX_BT_32DWORDS | MTK_MULTI_EN, - MTK_PDMA_GLO_CFG); + mtk_w32(eth, + MTK_RX_DMA_EN | rx_2b_offset | + MTK_RX_BT_32DWORDS | MTK_MULTI_EN, + MTK_PDMA_GLO_CFG); + } else { + mtk_w32(eth, MTK_TX_WB_DDONE | MTK_TX_DMA_EN | MTK_RX_DMA_EN | + MTK_MULTI_EN | MTK_PDMA_SIZE_8DWORDS, + MTK_PDMA_GLO_CFG); + } return 0; } @@ -1816,7 +2032,6 @@ static int mtk_open(struct net_device *dev) phy_start(dev->phydev); netif_start_queue(dev); - return 0; } @@ -1860,7 +2075,8 @@ static int mtk_stop(struct net_device *dev) napi_disable(ð->tx_napi); napi_disable(ð->rx_napi); - mtk_stop_dma(eth, MTK_QDMA_GLO_CFG); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_stop_dma(eth, MTK_QDMA_GLO_CFG); mtk_stop_dma(eth, MTK_PDMA_GLO_CFG); mtk_dma_free(eth); @@ -1922,6 +2138,24 @@ static int mtk_hw_init(struct mtk_eth *eth) if (ret) goto err_disable_pm; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + ret = device_reset(eth->dev); + if (ret) { + dev_err(eth->dev, "MAC reset failed!\n"); + goto err_disable_pm; + } + + /* enable interrupt delay for RX */ + mtk_w32(eth, MTK_PDMA_DELAY_RX_DELAY, MTK_PDMA_DELAY_INT); + + /* disable delay and normal interrupt */ + mtk_tx_irq_disable(eth, ~0); + mtk_rx_irq_disable(eth, ~0); + + return 0; + } + + /* Non-MT7628 handling... */ ethsys_reset(eth, RSTCTRL_FE); ethsys_reset(eth, RSTCTRL_PPE); @@ -2425,13 +2659,13 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) eth->netdev[id]->netdev_ops = &mtk_netdev_ops; eth->netdev[id]->base_addr = (unsigned long)eth->base; - eth->netdev[id]->hw_features = MTK_HW_FEATURES; + eth->netdev[id]->hw_features = eth->soc->hw_features; if (eth->hwlro) eth->netdev[id]->hw_features |= NETIF_F_LRO; - eth->netdev[id]->vlan_features = MTK_HW_FEATURES & + eth->netdev[id]->vlan_features = eth->soc->hw_features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); - eth->netdev[id]->features |= MTK_HW_FEATURES; + eth->netdev[id]->features |= eth->soc->hw_features; eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops; eth->netdev[id]->irq = eth->irq[0]; @@ -2446,7 +2680,6 @@ free_netdev: static int mtk_probe(struct platform_device *pdev) { - struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct device_node *mac_np; struct mtk_eth *eth; int err; @@ -2459,19 +2692,36 @@ static int mtk_probe(struct platform_device *pdev) eth->soc = of_device_get_match_data(&pdev->dev); eth->dev = &pdev->dev; - eth->base = devm_ioremap_resource(&pdev->dev, res); + eth->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(eth->base)) return PTR_ERR(eth->base); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + eth->tx_int_mask_reg = MTK_QDMA_INT_MASK; + eth->tx_int_status_reg = MTK_QDMA_INT_STATUS; + } else { + eth->tx_int_mask_reg = MTK_PDMA_INT_MASK; + eth->tx_int_status_reg = MTK_PDMA_INT_STATUS; + } + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + eth->rx_dma_l4_valid = RX_DMA_L4_VALID_PDMA; + eth->ip_align = NET_IP_ALIGN; + } else { + eth->rx_dma_l4_valid = RX_DMA_L4_VALID; + } + spin_lock_init(ð->page_lock); spin_lock_init(ð->tx_irq_lock); spin_lock_init(ð->rx_irq_lock); - eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, - "mediatek,ethsys"); - if (IS_ERR(eth->ethsys)) { - dev_err(&pdev->dev, "no ethsys regmap found\n"); - return PTR_ERR(eth->ethsys); + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "mediatek,ethsys"); + if (IS_ERR(eth->ethsys)) { + dev_err(&pdev->dev, "no ethsys regmap found\n"); + return PTR_ERR(eth->ethsys); + } } if (MTK_HAS_CAPS(eth->soc->caps, MTK_INFRA)) { @@ -2572,9 +2822,12 @@ static int mtk_probe(struct platform_device *pdev) if (err) goto err_free_dev; - err = mtk_mdio_init(eth); - if (err) - goto err_free_dev; + /* No MT7628/88 support yet */ + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + err = mtk_mdio_init(eth); + if (err) + goto err_free_dev; + } for (i = 0; i < MTK_MAX_DEVS; i++) { if (!eth->netdev[i]) @@ -2637,12 +2890,14 @@ static int mtk_remove(struct platform_device *pdev) static const struct mtk_soc_data mt2701_data = { .caps = MT7623_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, }; static const struct mtk_soc_data mt7621_data = { .caps = MT7621_CAPS, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7621_CLKS_BITMAP, .required_pctl = false, }; @@ -2650,12 +2905,14 @@ static const struct mtk_soc_data mt7621_data = { static const struct mtk_soc_data mt7622_data = { .ana_rgc3 = 0x2028, .caps = MT7622_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7622_CLKS_BITMAP, .required_pctl = false, }; static const struct mtk_soc_data mt7623_data = { .caps = MT7623_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, }; @@ -2663,16 +2920,25 @@ static const struct mtk_soc_data mt7623_data = { static const struct mtk_soc_data mt7629_data = { .ana_rgc3 = 0x128, .caps = MT7629_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7629_CLKS_BITMAP, .required_pctl = false, }; +static const struct mtk_soc_data rt5350_data = { + .caps = MT7628_CAPS, + .hw_features = MTK_HW_FEATURES_MT7628, + .required_clks = MT7628_CLKS_BITMAP, + .required_pctl = false, +}; + const struct of_device_id of_mtk_match[] = { { .compatible = "mediatek,mt2701-eth", .data = &mt2701_data}, { .compatible = "mediatek,mt7621-eth", .data = &mt7621_data}, { .compatible = "mediatek,mt7622-eth", .data = &mt7622_data}, { .compatible = "mediatek,mt7623-eth", .data = &mt7623_data}, { .compatible = "mediatek,mt7629-eth", .data = &mt7629_data}, + { .compatible = "ralink,rt5350-eth", .data = &rt5350_data}, {}, }; MODULE_DEVICE_TABLE(of, of_mtk_match); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index bab94f763e2c..cc1466ae0926 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -39,7 +39,8 @@ NETIF_F_SG | NETIF_F_TSO | \ NETIF_F_TSO6 | \ NETIF_F_IPV6_CSUM) -#define NEXT_RX_DESP_IDX(X, Y) (((X) + 1) & ((Y) - 1)) +#define MTK_HW_FEATURES_MT7628 (NETIF_F_SG | NETIF_F_RXCSUM) +#define NEXT_DESP_IDX(X, Y) (((X) + 1) & ((Y) - 1)) #define MTK_MAX_RX_RING_NUM 4 #define MTK_HW_LRO_DMA_SIZE 8 @@ -118,6 +119,7 @@ /* PDMA Global Configuration Register */ #define MTK_PDMA_GLO_CFG 0xa04 #define MTK_MULTI_EN BIT(10) +#define MTK_PDMA_SIZE_8DWORDS (1 << 4) /* PDMA Reset Index Register */ #define MTK_PDMA_RST_IDX 0xa08 @@ -212,7 +214,7 @@ #define FC_THRES_MIN 0x4444 /* QDMA Interrupt Status Register */ -#define MTK_QMTK_INT_STATUS 0x1A18 +#define MTK_QDMA_INT_STATUS 0x1A18 #define MTK_RX_DONE_DLY BIT(30) #define MTK_RX_DONE_INT3 BIT(19) #define MTK_RX_DONE_INT2 BIT(18) @@ -276,11 +278,18 @@ #define TX_DMA_OWNER_CPU BIT(31) #define TX_DMA_LS0 BIT(30) #define TX_DMA_PLEN0(_x) (((_x) & MTK_TX_DMA_BUF_LEN) << 16) +#define TX_DMA_PLEN1(_x) ((_x) & MTK_TX_DMA_BUF_LEN) #define TX_DMA_SWC BIT(14) #define TX_DMA_SDL(_x) (((_x) & 0x3fff) << 16) +/* PDMA on MT7628 */ +#define TX_DMA_DONE BIT(31) +#define TX_DMA_LS1 BIT(14) +#define TX_DMA_DESP2_DEF (TX_DMA_LS0 | TX_DMA_DONE) + /* QDMA descriptor rxd2 */ #define RX_DMA_DONE BIT(31) +#define RX_DMA_LSO BIT(30) #define RX_DMA_PLEN0(_x) (((_x) & 0x3fff) << 16) #define RX_DMA_GET_PLEN0(_x) (((_x) >> 16) & 0x3fff) @@ -289,6 +298,7 @@ /* QDMA descriptor rxd4 */ #define RX_DMA_L4_VALID BIT(24) +#define RX_DMA_L4_VALID_PDMA BIT(30) /* when PDMA is used */ #define RX_DMA_FPORT_SHIFT 19 #define RX_DMA_FPORT_MASK 0x7 @@ -412,6 +422,19 @@ #define CO_QPHY_SEL BIT(0) #define GEPHY_MAC_SEL BIT(1) +/* MT7628/88 specific stuff */ +#define MT7628_PDMA_OFFSET 0x0800 +#define MT7628_SDM_OFFSET 0x0c00 + +#define MT7628_TX_BASE_PTR0 (MT7628_PDMA_OFFSET + 0x00) +#define MT7628_TX_MAX_CNT0 (MT7628_PDMA_OFFSET + 0x04) +#define MT7628_TX_CTX_IDX0 (MT7628_PDMA_OFFSET + 0x08) +#define MT7628_TX_DTX_IDX0 (MT7628_PDMA_OFFSET + 0x0c) +#define MT7628_PST_DTX_IDX0 BIT(0) + +#define MT7628_SDM_MAC_ADRL (MT7628_SDM_OFFSET + 0x0c) +#define MT7628_SDM_MAC_ADRH (MT7628_SDM_OFFSET + 0x10) + struct mtk_rx_dma { unsigned int rxd1; unsigned int rxd2; @@ -509,6 +532,7 @@ enum mtk_clks_map { BIT(MTK_CLK_SGMII_CK) | \ BIT(MTK_CLK_ETH2PLL)) #define MT7621_CLKS_BITMAP (0) +#define MT7628_CLKS_BITMAP (0) #define MT7629_CLKS_BITMAP (BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) | \ BIT(MTK_CLK_GP0) | BIT(MTK_CLK_GP1) | \ BIT(MTK_CLK_GP2) | BIT(MTK_CLK_FE) | \ @@ -563,6 +587,10 @@ struct mtk_tx_ring { struct mtk_tx_dma *last_free; u16 thresh; atomic_t free_count; + int dma_size; + struct mtk_tx_dma *dma_pdma; /* For MT7628/88 PDMA handling */ + dma_addr_t phys_pdma; + int cpu_idx; }; /* PDMA rx ring mode */ @@ -604,6 +632,8 @@ enum mkt_eth_capabilities { MTK_HWLRO_BIT, MTK_SHARED_INT_BIT, MTK_TRGMII_MT7621_CLK_BIT, + MTK_QDMA_BIT, + MTK_SOC_MT7628_BIT, /* MUX BITS*/ MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT, @@ -634,6 +664,8 @@ enum mkt_eth_capabilities { #define MTK_HWLRO BIT(MTK_HWLRO_BIT) #define MTK_SHARED_INT BIT(MTK_SHARED_INT_BIT) #define MTK_TRGMII_MT7621_CLK BIT(MTK_TRGMII_MT7621_CLK_BIT) +#define MTK_QDMA BIT(MTK_QDMA_BIT) +#define MTK_SOC_MT7628 BIT(MTK_SOC_MT7628_BIT) #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW \ BIT(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT) @@ -687,26 +719,31 @@ enum mkt_eth_capabilities { #define MTK_HAS_CAPS(caps, _x) (((caps) & (_x)) == (_x)) #define MT7621_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | \ - MTK_GMAC2_RGMII | MTK_SHARED_INT | MTK_TRGMII_MT7621_CLK) + MTK_GMAC2_RGMII | MTK_SHARED_INT | \ + MTK_TRGMII_MT7621_CLK | MTK_QDMA) #define MT7622_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_SGMII | MTK_GMAC2_RGMII | \ MTK_GMAC2_SGMII | MTK_GDM1_ESW | \ MTK_MUX_GDM1_TO_GMAC1_ESW | \ - MTK_MUX_GMAC1_GMAC2_TO_SGMII_RGMII) + MTK_MUX_GMAC1_GMAC2_TO_SGMII_RGMII | MTK_QDMA) + +#define MT7623_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | MTK_GMAC2_RGMII | \ + MTK_QDMA) -#define MT7623_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | MTK_GMAC2_RGMII) +#define MT7628_CAPS (MTK_SHARED_INT | MTK_SOC_MT7628) #define MT7629_CAPS (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | MTK_GMAC2_GEPHY | \ MTK_GDM1_ESW | MTK_MUX_GDM1_TO_GMAC1_ESW | \ MTK_MUX_GMAC2_GMAC0_TO_GEPHY | \ MTK_MUX_U3_GMAC2_TO_QPHY | \ - MTK_MUX_GMAC12_TO_GEPHY_SGMII) + MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA) /* struct mtk_eth_data - This is the structure holding all differences * among various plaforms * @ana_rgc3: The offset for register ANA_RGC3 related to * sgmiisys syscon * @caps Flags shown the extra capability for the SoC + * @hw_features Flags shown HW features * @required_clks Flags shown the bitmap for required clocks on * the target SoC * @required_pctl A bool value to show whether the SoC requires @@ -717,6 +754,7 @@ struct mtk_soc_data { u32 caps; u32 required_clks; bool required_pctl; + netdev_features_t hw_features; }; /* currently no SoC has more than 2 macs */ @@ -810,6 +848,11 @@ struct mtk_eth { unsigned long state; const struct mtk_soc_data *soc; + + u32 tx_int_mask_reg; + u32 tx_int_status_reg; + u32 rx_dma_l4_valid; + int ip_align; }; /* struct mtk_mac - the structure that holds the info about the MACs of the diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c index 88316c743820..eaf08f7ad128 100644 --- a/drivers/net/ethernet/mellanox/mlx4/crdump.c +++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c @@ -99,8 +99,7 @@ static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev, readl(cr_space + offset); err = devlink_region_snapshot_create(crdump->region_crspace, - cr_res_size, crspace_data, - id, &kvfree); + crspace_data, id, &kvfree); if (err) { kvfree(crspace_data); mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", @@ -139,9 +138,7 @@ static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev, readl(health_buf_start + offset); err = devlink_region_snapshot_create(crdump->region_fw_health, - HEALTH_BUFFER_SIZE, - health_data, - id, &kvfree); + health_data, id, &kvfree); if (err) { kvfree(health_data); mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index c1438ae52a11..40ec5acf79c0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2645,14 +2645,6 @@ out: en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret); return; } - - /* set offloads */ - priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_RXCSUM | - NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; } static void mlx4_en_del_vxlan_offloads(struct work_struct *work) @@ -2660,14 +2652,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work) int ret; struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, vxlan_del_task); - /* unset offloads */ - priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_RXCSUM | - NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL); - ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 0); if (ret) @@ -3415,6 +3399,23 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, if (mdev->LSO_support) dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; + if (mdev->dev->caps.tunnel_offload_mode == + MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; + dev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + } + dev->vlan_features = dev->hw_features; dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_RXHASH; @@ -3483,16 +3484,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->rss_hash_fn = ETH_RSS_HASH_TOP; } - if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { - dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; - dev->features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; - dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; - } - /* MTU range: 68 - hw-specific max */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = priv->max_mtu; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 36a92b19e613..4d5ca302c067 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -772,9 +772,7 @@ static bool mlx4_en_build_dma_wqe(struct mlx4_en_priv *priv, /* Map fragments if any */ for (i_frag = shinfo->nr_frags - 1; i_frag >= 0; i_frag--) { - const struct skb_frag_struct *frag; - - frag = &shinfo->frags[i_frag]; + const skb_frag_t *frag = &shinfo->frags[i_frag]; byte_count = skb_frag_size(frag); dma = skb_frag_dma_map(ddev, frag, 0, byte_count, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 1f6e16d5ea6b..07c204bd3fc4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2292,23 +2292,31 @@ static int mlx4_init_fw(struct mlx4_dev *dev) static int mlx4_init_hca(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_init_hca_param *init_hca = NULL; + struct mlx4_dev_cap *dev_cap = NULL; struct mlx4_adapter adapter; - struct mlx4_dev_cap dev_cap; struct mlx4_profile profile; - struct mlx4_init_hca_param init_hca; u64 icm_size; struct mlx4_config_dev_params params; int err; if (!mlx4_is_slave(dev)) { - err = mlx4_dev_cap(dev, &dev_cap); + dev_cap = kzalloc(sizeof(*dev_cap), GFP_KERNEL); + init_hca = kzalloc(sizeof(*init_hca), GFP_KERNEL); + + if (!dev_cap || !init_hca) { + err = -ENOMEM; + goto out_free; + } + + err = mlx4_dev_cap(dev, dev_cap); if (err) { mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n"); - return err; + goto out_free; } - choose_steering_mode(dev, &dev_cap); - choose_tunnel_offload_mode(dev, &dev_cap); + choose_steering_mode(dev, dev_cap); + choose_tunnel_offload_mode(dev, dev_cap); if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC && mlx4_is_master(dev)) @@ -2331,48 +2339,48 @@ static int mlx4_init_hca(struct mlx4_dev *dev) MLX4_STEERING_MODE_DEVICE_MANAGED) profile.num_mcg = MLX4_FS_NUM_MCG; - icm_size = mlx4_make_profile(dev, &profile, &dev_cap, - &init_hca); + icm_size = mlx4_make_profile(dev, &profile, dev_cap, + init_hca); if ((long long) icm_size < 0) { err = icm_size; - return err; + goto out_free; } dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; if (enable_4k_uar || !dev->persist->num_vfs) { - init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + + init_hca->log_uar_sz = ilog2(dev->caps.num_uars) + PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT; - init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; + init_hca->uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; } else { - init_hca.log_uar_sz = ilog2(dev->caps.num_uars); - init_hca.uar_page_sz = PAGE_SHIFT - 12; + init_hca->log_uar_sz = ilog2(dev->caps.num_uars); + init_hca->uar_page_sz = PAGE_SHIFT - 12; } - init_hca.mw_enabled = 0; + init_hca->mw_enabled = 0; if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) - init_hca.mw_enabled = INIT_HCA_TPT_MW_ENABLE; + init_hca->mw_enabled = INIT_HCA_TPT_MW_ENABLE; - err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size); + err = mlx4_init_icm(dev, dev_cap, init_hca, icm_size); if (err) - return err; + goto out_free; - err = mlx4_INIT_HCA(dev, &init_hca); + err = mlx4_INIT_HCA(dev, init_hca); if (err) { mlx4_err(dev, "INIT_HCA command failed, aborting\n"); goto err_free_icm; } - if (dev_cap.flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) { - err = mlx4_query_func(dev, &dev_cap); + if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) { + err = mlx4_query_func(dev, dev_cap); if (err < 0) { mlx4_err(dev, "QUERY_FUNC command failed, aborting.\n"); goto err_close; } else if (err & MLX4_QUERY_FUNC_NUM_SYS_EQS) { - dev->caps.num_eqs = dev_cap.max_eqs; - dev->caps.reserved_eqs = dev_cap.reserved_eqs; - dev->caps.reserved_uars = dev_cap.reserved_uars; + dev->caps.num_eqs = dev_cap->max_eqs; + dev->caps.reserved_eqs = dev_cap->reserved_eqs; + dev->caps.reserved_uars = dev_cap->reserved_uars; } } @@ -2381,14 +2389,13 @@ static int mlx4_init_hca(struct mlx4_dev *dev) * read HCA frequency by QUERY_HCA command */ if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) { - memset(&init_hca, 0, sizeof(init_hca)); - err = mlx4_QUERY_HCA(dev, &init_hca); + err = mlx4_QUERY_HCA(dev, init_hca); if (err) { mlx4_err(dev, "QUERY_HCA command failed, disable timestamp\n"); dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; } else { dev->caps.hca_core_clock = - init_hca.hca_core_clock; + init_hca->hca_core_clock; } /* In case we got HCA frequency 0 - disable timestamping @@ -2464,7 +2471,8 @@ static int mlx4_init_hca(struct mlx4_dev *dev) priv->eq_table.inta_pin = adapter.inta_pin; memcpy(dev->board_id, adapter.board_id, sizeof(dev->board_id)); - return 0; + err = 0; + goto out_free; unmap_bf: unmap_internal_clock(dev); @@ -2483,6 +2491,10 @@ err_free_icm: if (!mlx4_is_slave(dev)) mlx4_free_icms(dev); +out_free: + kfree(dev_cap); + kfree(init_hca); + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 8cdd7e66f8df..973f90888b1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1368,49 +1368,19 @@ static void clean_debug_files(struct mlx5_core_dev *dev) debugfs_remove_recursive(dbg->dbg_root); } -static int create_debugfs_files(struct mlx5_core_dev *dev) +static void create_debugfs_files(struct mlx5_core_dev *dev) { struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - int err = -ENOMEM; - - if (!mlx5_debugfs_root) - return 0; dbg->dbg_root = debugfs_create_dir("cmd", dev->priv.dbg_root); - if (!dbg->dbg_root) - return err; - - dbg->dbg_in = debugfs_create_file("in", 0400, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_in) - goto err_dbg; - dbg->dbg_out = debugfs_create_file("out", 0200, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_out) - goto err_dbg; - - dbg->dbg_outlen = debugfs_create_file("out_len", 0600, dbg->dbg_root, - dev, &olfops); - if (!dbg->dbg_outlen) - goto err_dbg; - - dbg->dbg_status = debugfs_create_u8("status", 0600, dbg->dbg_root, - &dbg->status); - if (!dbg->dbg_status) - goto err_dbg; - - dbg->dbg_run = debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); - if (!dbg->dbg_run) - goto err_dbg; + debugfs_create_file("in", 0400, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out", 0200, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out_len", 0600, dbg->dbg_root, dev, &olfops); + debugfs_create_u8("status", 0600, dbg->dbg_root, &dbg->status); + debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); mlx5_cmdif_debugfs_init(dev); - - return 0; - -err_dbg: - clean_debug_files(dev); - return err; } static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) @@ -2007,17 +1977,10 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) goto err_cache; } - err = create_debugfs_files(dev); - if (err) { - err = -ENOMEM; - goto err_wq; - } + create_debugfs_files(dev); return 0; -err_wq: - destroy_workqueue(cmd->wq); - err_cache: destroy_msg_cache(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index a11e22d0b0cc..04854e5fbcd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -92,8 +92,6 @@ EXPORT_SYMBOL(mlx5_debugfs_root); void mlx5_register_debugfs(void) { mlx5_debugfs_root = debugfs_create_dir("mlx5", NULL); - if (IS_ERR_OR_NULL(mlx5_debugfs_root)) - mlx5_debugfs_root = NULL; } void mlx5_unregister_debugfs(void) @@ -101,45 +99,25 @@ void mlx5_unregister_debugfs(void) debugfs_remove(mlx5_debugfs_root); } -int mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - atomic_set(&dev->num_qps, 0); dev->priv.qp_debugfs = debugfs_create_dir("QPs", dev->priv.dbg_root); - if (!dev->priv.qp_debugfs) - return -ENOMEM; - - return 0; } void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.qp_debugfs); } -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.eq_debugfs = debugfs_create_dir("EQs", dev->priv.dbg_root); - if (!dev->priv.eq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.eq_debugfs); } @@ -183,85 +161,41 @@ static const struct file_operations stats_fops = { .write = average_write, }; -int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) { struct mlx5_cmd_stats *stats; struct dentry **cmd; const char *namep; - int err; int i; - if (!mlx5_debugfs_root) - return 0; - cmd = &dev->priv.cmdif_debugfs; *cmd = debugfs_create_dir("commands", dev->priv.dbg_root); - if (!*cmd) - return -ENOMEM; for (i = 0; i < ARRAY_SIZE(dev->cmd.stats); i++) { stats = &dev->cmd.stats[i]; namep = mlx5_command_str(i); if (strcmp(namep, "unknown command opcode")) { stats->root = debugfs_create_dir(namep, *cmd); - if (!stats->root) { - mlx5_core_warn(dev, "failed adding command %d\n", - i); - err = -ENOMEM; - goto out; - } - - stats->avg = debugfs_create_file("average", 0400, - stats->root, stats, - &stats_fops); - if (!stats->avg) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } - - stats->count = debugfs_create_u64("n", 0400, - stats->root, - &stats->n); - if (!stats->count) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } + + debugfs_create_file("average", 0400, stats->root, stats, + &stats_fops); + debugfs_create_u64("n", 0400, stats->root, &stats->n); } } - - return 0; -out: - debugfs_remove_recursive(dev->priv.cmdif_debugfs); - return err; } void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cmdif_debugfs); } -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.cq_debugfs = debugfs_create_dir("CQs", dev->priv.dbg_root); - if (!dev->priv.cq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cq_debugfs); } @@ -484,7 +418,6 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, { struct mlx5_rsc_debug *d; char resn[32]; - int err; int i; d = kzalloc(struct_size(d, fields, nfile), GFP_KERNEL); @@ -496,30 +429,15 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, d->type = type; sprintf(resn, "0x%x", rsn); d->root = debugfs_create_dir(resn, root); - if (!d->root) { - err = -ENOMEM; - goto out_free; - } for (i = 0; i < nfile; i++) { d->fields[i].i = i; - d->fields[i].dent = debugfs_create_file(field[i], 0400, - d->root, &d->fields[i], - &fops); - if (!d->fields[i].dent) { - err = -ENOMEM; - goto out_rem; - } + debugfs_create_file(field[i], 0400, d->root, &d->fields[i], + &fops); } *dbg = d; return 0; -out_rem: - debugfs_remove_recursive(d->root); - -out_free: - kfree(d); - return err; } static void rem_res_tree(struct mlx5_rsc_debug *d) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 65bec19a438f..8cf548c7ad9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -356,6 +356,7 @@ enum { MLX5E_SQ_STATE_IPSEC, MLX5E_SQ_STATE_AM, MLX5E_SQ_STATE_TLS, + MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, }; struct mlx5e_sq_wqe_info { @@ -480,8 +481,6 @@ struct mlx5e_xdp_mpwqe { struct mlx5e_tx_wqe *wqe; u8 ds_count; u8 pkt_count; - u8 max_ds_count; - u8 complete; u8 inline_on; }; @@ -1135,7 +1134,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, u16 num_channels); -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev); void mlx5e_rx_dim_work(struct work_struct *work); void mlx5e_tx_dim_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index be5961ff24cc..ca2161b42c7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -10,11 +10,14 @@ enum { }; struct mlx5e_tc_table { + /* protects flow table */ + struct mutex t_lock; struct mlx5_flow_table *t; struct rhashtable ht; - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; + struct mutex hairpin_tbl_lock; /* protects hairpin_tbl */ DECLARE_HASHTABLE(hairpin_tbl, 8); struct notifier_block netdevice_nb; @@ -132,12 +135,17 @@ struct mlx5e_ethtool_steering { void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); -int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd); -int mlx5e_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *info, u32 *rule_locs); +int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd); +int mlx5e_ethtool_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, u32 *rule_locs); #else static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) { } static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { } +static inline int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ return -EOPNOTSUPP; } +static inline int mlx5e_ethtool_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, u32 *rule_locs) +{ return -EOPNOTSUPP; } #endif /* CONFIG_MLX5_EN_RXNFC */ #ifdef CONFIG_MLX5_EN_ARFS diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h index e78e92753d73..ed7a3881d2c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h @@ -4,7 +4,6 @@ #ifndef __MLX5E_EN_REPORTER_H #define __MLX5E_EN_REPORTER_H -#include <linux/mlx5/driver.h> #include "en.h" int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index c7f86453c638..817c6ea7e349 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2019 Mellanox Technologies. */ -#include <net/devlink.h> #include "reporter.h" #include "lib/eq.h" @@ -116,7 +115,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter, char *err_str, struct mlx5e_tx_err_ctx *err_ctx) { - if (IS_ERR_OR_NULL(tx_reporter)) { + if (!tx_reporter) { netdev_err(err_ctx->sq->channel->netdev, err_str); return err_ctx->recover(err_ctx->sq); } @@ -288,23 +287,27 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *mdev = priv->mdev; struct devlink *devlink = priv_to_devlink(mdev); - priv->tx_reporter = + reporter = devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, MLX5_REPORTER_TX_GRACEFUL_PERIOD, true, priv); - if (IS_ERR(priv->tx_reporter)) + if (IS_ERR(reporter)) { netdev_warn(priv->netdev, "Failed to create tx reporter, err = %ld\n", - PTR_ERR(priv->tx_reporter)); - return IS_ERR_OR_NULL(priv->tx_reporter); + PTR_ERR(reporter)); + return PTR_ERR(reporter); + } + priv->tx_reporter = reporter; + return 0; } void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) { - if (IS_ERR_OR_NULL(priv->tx_reporter)) + if (!priv->tx_reporter) return; devlink_health_reporter_destroy(priv->tx_reporter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index a6a52806be45..4c4620db3d31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -31,29 +31,36 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, real_dev = is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : dev; uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); - uplink_upper = netdev_master_upper_dev_get(uplink_dev); + + rcu_read_lock(); + uplink_upper = netdev_master_upper_dev_get_rcu(uplink_dev); + /* mlx5_lag_is_sriov() is a blocking function which can't be called + * while holding rcu read lock. Take the net_device for correctness + * sake. + */ + if (uplink_upper) + dev_hold(uplink_upper); + rcu_read_unlock(); + dst_is_lag_dev = (uplink_upper && netif_is_lag_master(uplink_upper) && real_dev == uplink_upper && mlx5_lag_is_sriov(priv->mdev)); + if (uplink_upper) + dev_put(uplink_upper); /* if the egress device isn't on the same HW e-switch or * it's a LAG device, use the uplink */ + *route_dev = dev; if (!netdev_port_same_parent_id(priv->netdev, real_dev) || - dst_is_lag_dev) { - *route_dev = dev; + dst_is_lag_dev || is_vlan_dev(*route_dev)) *out_dev = uplink_dev; - } else { - *route_dev = dev; - if (is_vlan_dev(*route_dev)) - *out_dev = uplink_dev; - else if (mlx5e_eswitch_rep(dev) && - mlx5e_is_valid_eswitch_fwd_dev(priv, dev)) - *out_dev = *route_dev; - else - return -EOPNOTSUPP; - } + else if (mlx5e_eswitch_rep(dev) && + mlx5e_is_valid_eswitch_fwd_dev(priv, dev)) + *out_dev = *route_dev; + else + return -EOPNOTSUPP; if (!(mlx5e_eswitch_rep(*out_dev) && mlx5e_is_uplink_rep(netdev_priv(*out_dev)))) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index ddfe19adb3d9..87be96747902 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -6,7 +6,7 @@ #include "en.h" -#define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS +#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1) #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ MLX5E_SQ_NOPS_ROOM) @@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map, mlx5_write64((__be32 *)ctrl, uar_map); } -static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe) +static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg) { - return !!wqe->ctrl.tisn; + return cseg && !!cseg->tisn; +} + +static inline u8 +mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg, + struct sk_buff *skb) +{ + u8 mode; + + if (mlx5e_transport_inline_tx_wqe(cseg)) + return MLX5_INLINE_MODE_TCP_UDP; + + mode = sq->min_inline_mode; + + if (skb_vlan_tag_present(skb) && + test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state)) + mode = max_t(u8, MLX5_INLINE_MODE_L2, mode); + + return mode; } static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index b0b982cf69bb..1ed5c33e022f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -179,33 +179,19 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; struct mlx5_wq_cyc *wq = &sq->wq; - u8 wqebbs; - u16 pi; - - mlx5e_xdpsq_fetch_wqe(sq, &session->wqe); - - prefetchw(session->wqe->data); - session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; - session->pkt_count = 0; - session->complete = 0; + u16 pi, contig_wqebbs; pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); -/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS - * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. - * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a - * full-session WQE be cache-aligned. - */ -#if L1_CACHE_BYTES < 128 -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) -#else -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) -#endif + if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS)) + mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs); - wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi), - MLX5E_XDP_MPW_MAX_WQEBBS); + session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi); - session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs; + prefetchw(session->wqe->data); + session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; + session->pkt_count = 0; mlx5e_xdp_update_inline_state(sq); @@ -244,7 +230,7 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq) { if (unlikely(!sq->mpwqe.wqe)) { if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - MLX5_SEND_WQE_MAX_WQEBBS))) { + MLX5E_XDPSQ_STOP_ROOM))) { /* SQ is full, ring doorbell */ mlx5e_xmit_xdp_doorbell(sq); sq->stats->full++; @@ -285,8 +271,8 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats); - if (unlikely(session->complete || - session->ds_count == session->max_ds_count)) + if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) || + session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS)) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index b90923932668..36ac1e3816b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -40,6 +40,26 @@ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) +#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM) + +#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) +#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \ + DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS) + +/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS + * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. + * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a + * full-session WQE be cache-aligned. + */ +#if L1_CACHE_BYTES < 128 +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) +#else +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) +#endif + +#define MLX5E_XDP_MPW_MAX_NUM_DS \ + (MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS) + struct mlx5e_xsk_param; int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, @@ -114,6 +134,30 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq) session->inline_on = 1; } +static inline bool +mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session) +{ + return session->inline_on && + session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS; +} + +static inline void +mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq, + u16 pi, u16 nnops) +{ + struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi]; + + edge_wi = wi + nnops; + /* fill sq frag edge with nops to avoid wqe wrapping two pages */ + for (; wi < edge_wi; wi++) { + wi->num_wqebbs = 1; + wi->num_pkts = 0; + mlx5e_post_nop(wq, sq->sqn, &sq->pc); + } + + sq->stats->nops += nnops; +} + static inline void mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, @@ -126,20 +170,12 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, session->pkt_count++; -#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) - if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) { struct mlx5_wqe_inline_seg *inline_dseg = (struct mlx5_wqe_inline_seg *)dseg; u16 ds_len = sizeof(*inline_dseg) + dma_len; u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS); - if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) { - /* Not enough space for inline wqe, send with memory pointer */ - session->complete = true; - goto no_inline; - } - inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG); memcpy(inline_dseg->data, xdptxd->data, dma_len); @@ -148,21 +184,23 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, return; } -no_inline: dseg->addr = cpu_to_be64(xdptxd->dma_addr); dseg->byte_count = cpu_to_be32(dma_len); dseg->lkey = sq->mkey_be; session->ds_count++; } -static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, - struct mlx5e_tx_wqe **wqe) +static inline struct mlx5e_tx_wqe * +mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi) { struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + struct mlx5e_tx_wqe *wqe; + + *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + wqe = mlx5_wq_cyc_get_wqe(wq, *pi); + memset(wqe, 0, sizeof(*wqe)); - *wqe = mlx5_wq_cyc_get_wqe(wq, pi); - memset(*wqe, 0, sizeof(**wqe)); + return wqe; } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 7f78c004d12f..2c4d1f415968 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -60,24 +60,28 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, struct mlx5e_channel *c) { - struct mlx5e_channel_param cparam = {}; + struct mlx5e_channel_param *cparam; struct dim_cq_moder icocq_moder = {}; int err; if (!mlx5e_validate_xsk_param(params, xsk, priv->mdev)) return -EINVAL; - mlx5e_build_xsk_cparam(priv, params, xsk, &cparam); + cparam = kvzalloc(sizeof(*cparam), GFP_KERNEL); + if (!cparam) + return -ENOMEM; - err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam.rx_cq, &c->xskrq.cq); + mlx5e_build_xsk_cparam(priv, params, xsk, cparam); + + err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->xskrq.cq); if (unlikely(err)) - return err; + goto err_free_cparam; - err = mlx5e_open_rq(c, params, &cparam.rq, xsk, umem, &c->xskrq); + err = mlx5e_open_rq(c, params, &cparam->rq, xsk, umem, &c->xskrq); if (unlikely(err)) goto err_close_rx_cq; - err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam.tx_cq, &c->xsksq.cq); + err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->xsksq.cq); if (unlikely(err)) goto err_close_rq; @@ -87,21 +91,23 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, * is disabled and then reenabled, but the SQ continues receiving CQEs * from the old UMEM. */ - err = mlx5e_open_xdpsq(c, params, &cparam.xdp_sq, umem, &c->xsksq, true); + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, umem, &c->xsksq, true); if (unlikely(err)) goto err_close_tx_cq; - err = mlx5e_open_cq(c, icocq_moder, &cparam.icosq_cq, &c->xskicosq.cq); + err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->xskicosq.cq); if (unlikely(err)) goto err_close_sq; /* Create a dedicated SQ for posting NOPs whenever we need an IRQ to be * triggered and NAPI to be called on the correct CPU. */ - err = mlx5e_open_icosq(c, params, &cparam.icosq, &c->xskicosq); + err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->xskicosq); if (unlikely(err)) goto err_close_icocq; + kvfree(cparam); + spin_lock_init(&c->xskicosq_lock); set_bit(MLX5E_CHANNEL_STATE_XSK, c->state); @@ -123,6 +129,9 @@ err_close_rq: err_close_rx_cq: mlx5e_close_cq(&c->xskrq.cq); +err_free_cparam: + kvfree(cparam); + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1539cf3de5dc..f7890e0ce96c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -180,15 +180,3 @@ out: return err; } - -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev) -{ - u8 min_inline_mode; - - mlx5_query_min_inline(mdev, &min_inline_mode); - if (min_inline_mode == MLX5_INLINE_MODE_NONE && - !MLX5_CAP_ETH(mdev, wqe_vlan_insert)) - min_inline_mode = MLX5_INLINE_MODE_L2; - - return min_inline_mode; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 8dd31b5c740c..01f2918063af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv) static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv, struct mlx5e_params *params) { - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev); + mlx5_query_min_inline(priv->mdev, ¶ms->tx_min_inline_mode); if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP && params->tx_min_inline_mode == MLX5_INLINE_MODE_L2) params->tx_min_inline_mode = MLX5_INLINE_MODE_IP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 20e628c907e5..7347d673f448 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1958,21 +1958,27 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev) return priv->channels.params.pflags; } -#ifndef CONFIG_MLX5_EN_RXNFC -/* When CONFIG_MLX5_EN_RXNFC=n we only support ETHTOOL_GRXRINGS - * otherwise this function will be defined from en_fs_ethtool.c - */ static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = netdev_priv(dev); - if (info->cmd != ETHTOOL_GRXRINGS) - return -EOPNOTSUPP; - /* ring_count is needed by ethtool -x */ - info->data = priv->channels.params.num_channels; - return 0; + /* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part + * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc, + * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc + * is compiled out via CONFIG_MLX5_EN_RXNFC=n. + */ + if (info->cmd == ETHTOOL_GRXRINGS) { + info->data = priv->channels.params.num_channels; + return 0; + } + + return mlx5e_ethtool_get_rxnfc(dev, info, rule_locs); +} + +static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + return mlx5e_ethtool_set_rxnfc(dev, cmd); } -#endif const struct ethtool_ops mlx5e_ethtool_ops = { .get_drvinfo = mlx5e_get_drvinfo, @@ -1993,9 +1999,7 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_rxfh = mlx5e_get_rxfh, .set_rxfh = mlx5e_set_rxfh, .get_rxnfc = mlx5e_get_rxnfc, -#ifdef CONFIG_MLX5_EN_RXNFC .set_rxnfc = mlx5e_set_rxnfc, -#endif .get_tunable = mlx5e_get_tunable, .set_tunable = mlx5e_set_tunable, .get_pauseparam = mlx5e_get_pauseparam, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 94304abc49e9..eed7101e8bb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -888,10 +888,10 @@ static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv, return 0; } -int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) { - int err = 0; struct mlx5e_priv *priv = netdev_priv(dev); + int err = 0; switch (cmd->cmd) { case ETHTOOL_SRXCLSRLINS: @@ -911,16 +911,13 @@ int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return err; } -int mlx5e_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *info, u32 *rule_locs) +int mlx5e_ethtool_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = priv->channels.params.num_channels; - break; case ETHTOOL_GRXCLSRLCNT: info->rule_cnt = priv->fs.ethtool.tot_num_rules; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9d5f6e56188f..0c8e847a9eee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1130,6 +1130,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; sq->stop_room = MLX5E_SQ_STOP_ROOM; INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); + if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert)) + set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) { @@ -2321,7 +2323,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, goto err_close_channels; } - if (!IS_ERR_OR_NULL(priv->tx_reporter)) + if (priv->tx_reporter) devlink_health_reporter_state_update(priv->tx_reporter, DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); @@ -3422,7 +3424,7 @@ out: #ifdef CONFIG_MLX5_ESWITCH static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv, struct flow_cls_offload *cls_flower, - int flags) + unsigned long flags) { switch (cls_flower->command) { case FLOW_CLS_REPLACE: @@ -3442,12 +3444,12 @@ static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv, static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(NIC_OFFLOAD); struct mlx5e_priv *priv = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: - return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS | - MLX5E_TC_NIC_OFFLOAD); + return mlx5e_setup_tc_cls_flower(priv, type_data, flags); default: return -EOPNOTSUPP; } @@ -3640,7 +3642,7 @@ static int set_feature_tc_num_filters(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); - if (!enable && mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD)) { + if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) { netdev_err(netdev, "Active offloaded tc filters, can't turn hw_tc_offload off\n"); return -EINVAL; @@ -3781,9 +3783,10 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_warn(netdev, "Dropping C-tag vlan stripping offload due to S-tag vlan\n"); } if (!MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ)) { - features &= ~NETIF_F_LRO; - if (params->lro_en) + if (features & NETIF_F_LRO) { netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n"); + features &= ~NETIF_F_LRO; + } } if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { @@ -3950,7 +3953,8 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: /* Disable CQE compression */ - netdev_warn(priv->netdev, "Disabling cqe compression"); + if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS)) + netdev_warn(priv->netdev, "Disabling RX cqe compression\n"); err = mlx5e_modify_rx_cqe_compression_locked(priv, false); if (err) { netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); @@ -4768,7 +4772,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); /* TX inline */ - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev); + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); /* RSS */ mlx5e_build_rss_params(rss_params, params->num_channels); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index d0684fdb69e1..7ce5cb6e527e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -389,24 +389,17 @@ static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = { .set_pauseparam = mlx5e_uplink_rep_set_pauseparam, }; -static int mlx5e_rep_get_port_parent_id(struct net_device *dev, - struct netdev_phys_item_id *ppid) +static void mlx5e_rep_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { - struct mlx5_eswitch *esw; struct mlx5e_priv *priv; u64 parent_id; priv = netdev_priv(dev); - esw = priv->mdev->priv.eswitch; - - if (esw->mode == MLX5_ESWITCH_NONE) - return -EOPNOTSUPP; parent_id = mlx5_query_nic_system_image_guid(priv->mdev); ppid->id_len = sizeof(parent_id); memcpy(ppid->id, &parent_id, sizeof(parent_id)); - - return 0; } static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, @@ -613,12 +606,17 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) neigh_connected = (nud_state & NUD_VALID) && !dead; list_for_each_entry(e, &nhe->encap_list, encap_list) { + if (!mlx5e_encap_take(e)) + continue; + encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); priv = netdev_priv(e->out_dev); if (encap_connected != neigh_connected || !ether_addr_equal(e->h_dest, ha)) mlx5e_rep_update_flows(priv, e, neigh_connected, ha); + + mlx5e_encap_put(priv, e); } mlx5e_rep_neigh_entry_release(nhe); rtnl_unlock(); @@ -659,8 +657,8 @@ mlx5e_rep_indr_offload(struct net_device *netdev, struct flow_cls_offload *flower, struct mlx5e_rep_indr_block_priv *indr_priv) { + unsigned long flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD); struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev); - int flags = MLX5E_TC_EGRESS | MLX5E_TC_ESW_OFFLOAD; int err = 0; switch (flower->command) { @@ -722,10 +720,6 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, if (indr_priv) return -EEXIST; - if (flow_block_cb_is_busy(mlx5e_rep_indr_setup_block_cb, - indr_priv, &mlx5e_block_cb_list)) - return -EBUSY; - indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL); if (!indr_priv) return -ENOMEM; @@ -785,9 +779,9 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, { int err; - err = __tc_indr_block_cb_register(netdev, rpriv, - mlx5e_rep_indr_setup_tc_cb, - rpriv); + err = __flow_indr_block_cb_register(netdev, rpriv, + mlx5e_rep_indr_setup_tc_cb, + rpriv); if (err) { struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); @@ -800,8 +794,8 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv, struct net_device *netdev) { - __tc_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb, - rpriv); + __flow_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb, + rpriv); } static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb, @@ -1160,15 +1154,34 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, } } +static +int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + switch (ma->command) { + case TC_CLSMATCHALL_REPLACE: + return mlx5e_tc_configure_matchall(priv, ma); + case TC_CLSMATCHALL_DESTROY: + return mlx5e_tc_delete_matchall(priv, ma); + case TC_CLSMATCHALL_STATS: + mlx5e_tc_stats_matchall(priv, ma); + return 0; + default: + return -EOPNOTSUPP; + } +} + static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD); struct mlx5e_priv *priv = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: - return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS | - MLX5E_TC_ESW_OFFLOAD); + return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags); + case TC_SETUP_CLSMATCHALL: + return mlx5e_rep_setup_tc_cls_matchall(priv, type_data); default: return -EOPNOTSUPP; } @@ -1564,6 +1577,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { uplink_priv = &rpriv->uplink_priv; + mutex_init(&uplink_priv->unready_flows_lock); INIT_LIST_HEAD(&uplink_priv->unready_flows); /* init shared tc flow table */ @@ -1608,6 +1622,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) /* delete shared tc flow table */ mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht); + mutex_destroy(&rpriv->uplink_priv.unready_flows_lock); } } @@ -1731,37 +1746,46 @@ is_devlink_port_supported(const struct mlx5_core_dev *dev, mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport); } +static unsigned int +vport_to_devlink_port_index(const struct mlx5_core_dev *dev, u16 vport_num) +{ + return (MLX5_CAP_GEN(dev, vhca_id) << 16) | vport_num; +} + static int register_devlink_port(struct mlx5_core_dev *dev, struct mlx5e_rep_priv *rpriv) { struct devlink *devlink = priv_to_devlink(dev); struct mlx5_eswitch_rep *rep = rpriv->rep; struct netdev_phys_item_id ppid = {}; - int ret; + unsigned int dl_port_index = 0; if (!is_devlink_port_supported(dev, rpriv)) return 0; - ret = mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); - if (ret) - return ret; + mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); - if (rep->vport == MLX5_VPORT_UPLINK) + if (rep->vport == MLX5_VPORT_UPLINK) { devlink_port_attrs_set(&rpriv->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, PCI_FUNC(dev->pdev->devfn), false, 0, &ppid.id[0], ppid.id_len); - else if (rep->vport == MLX5_VPORT_PF) + dl_port_index = vport_to_devlink_port_index(dev, rep->vport); + } else if (rep->vport == MLX5_VPORT_PF) { devlink_port_attrs_pci_pf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, dev->pdev->devfn); - else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) + dl_port_index = rep->vport; + } else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, + rpriv->rep->vport)) { devlink_port_attrs_pci_vf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, dev->pdev->devfn, rep->vport - 1); + dl_port_index = vport_to_devlink_port_index(dev, rep->vport); + } - return devlink_port_register(devlink, &rpriv->dl_port, rep->vport); + return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index); } static void unregister_devlink_port(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index c56e6ee4350c..8ac96727cad8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -75,6 +75,8 @@ struct mlx5_rep_uplink_priv { struct mlx5_tun_entropy tun_entropy; + /* protects unready_flows */ + struct mutex unready_flows_lock; struct list_head unready_flows; struct work_struct reoffload_flows_work; }; @@ -86,6 +88,7 @@ struct mlx5e_rep_priv { struct mlx5_flow_handle *vport_rx_rule; struct list_head vport_sqs_list; struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */ + struct rtnl_link_stats64 prev_vf_vport_stats; struct devlink_port dl_port; }; @@ -161,6 +164,9 @@ struct mlx5e_encap_entry { u8 flags; char *encap_header; int encap_size; + refcount_t refcnt; + struct completion res_ready; + int compl_result; }; struct mlx5e_rep_sq { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index ac6e586d403d..60570b442fff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -859,13 +859,24 @@ tail_padding_csum(struct sk_buff *skb, int offset, } static void -mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto, - struct mlx5e_rq_stats *stats) +mlx5e_skb_csum_fixup(struct sk_buff *skb, int network_depth, __be16 proto, + struct mlx5e_rq_stats *stats) { struct ipv6hdr *ip6; struct iphdr *ip4; int pkt_len; + /* Fixup vlan headers, if any */ + if (network_depth > ETH_HLEN) + /* CQE csum is calculated from the IP header and does + * not cover VLAN headers (if present). This will add + * the checksum manually. + */ + skb->csum = csum_partial(skb->data + ETH_HLEN, + network_depth - ETH_HLEN, + skb->csum); + + /* Fixup tail padding, if any */ switch (proto) { case htons(ETH_P_IP): ip4 = (struct iphdr *)(skb->data + network_depth); @@ -931,16 +942,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; /* CQE csum covers all received bytes */ /* csum might need some fixups ...*/ - if (network_depth > ETH_HLEN) - /* CQE csum is calculated from the IP header and does - * not cover VLAN headers (if present). This will add - * the checksum manually. - */ - skb->csum = csum_partial(skb->data + ETH_HLEN, - network_depth - ETH_HLEN, - skb->csum); - - mlx5e_skb_padding_csum(skb, network_depth, proto, stats); + mlx5e_skb_csum_fixup(skb, network_depth, proto, stats); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 57f9f346d213..94a32c76c182 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -74,6 +74,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, @@ -90,6 +91,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) }, @@ -200,6 +202,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_xdp_tx_xmit += xdpsq_stats->xmit; s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe; s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw; + s->rx_xdp_tx_nops += xdpsq_stats->nops; s->rx_xdp_tx_full += xdpsq_stats->full; s->rx_xdp_tx_err += xdpsq_stats->err; s->rx_xdp_tx_cqe += xdpsq_stats->cqes; @@ -227,6 +230,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_xdp_xmit += xdpsq_red_stats->xmit; s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; s->tx_xdp_inlnw += xdpsq_red_stats->inlnw; + s->tx_xdp_nops += xdpsq_red_stats->nops; s->tx_xdp_full += xdpsq_red_stats->full; s->tx_xdp_err += xdpsq_red_stats->err; s->tx_xdp_cqes += xdpsq_red_stats->cqes; @@ -1331,6 +1335,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = { { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, @@ -1340,6 +1345,7 @@ static const struct counter_desc xdpsq_stats_desc[] = { { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 76ac111e14d0..bf645d42c833 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -81,6 +81,7 @@ struct mlx5e_sw_stats { u64 rx_xdp_tx_xmit; u64 rx_xdp_tx_mpwqe; u64 rx_xdp_tx_inlnw; + u64 rx_xdp_tx_nops; u64 rx_xdp_tx_full; u64 rx_xdp_tx_err; u64 rx_xdp_tx_cqe; @@ -97,6 +98,7 @@ struct mlx5e_sw_stats { u64 tx_xdp_xmit; u64 tx_xdp_mpwqe; u64 tx_xdp_inlnw; + u64 tx_xdp_nops; u64 tx_xdp_full; u64 tx_xdp_err; u64 tx_xdp_cqes; @@ -288,6 +290,7 @@ struct mlx5e_xdpsq_stats { u64 xmit; u64 mpwqe; u64 inlnw; + u64 nops; u64 full; u64 err; /* dirtied @completion */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 00b2d4a86159..c57f7533a6d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -38,6 +38,8 @@ #include <linux/mlx5/fs.h> #include <linux/mlx5/device.h> #include <linux/rhashtable.h> +#include <linux/refcount.h> +#include <linux/completion.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_vlan.h> #include <net/tc_act/tc_tunnel_key.h> @@ -65,19 +67,20 @@ struct mlx5_nic_flow_attr { struct mlx5_fc *counter; }; -#define MLX5E_TC_FLOW_BASE (MLX5E_TC_LAST_EXPORTED_BIT + 1) +#define MLX5E_TC_FLOW_BASE (MLX5E_TC_FLAG_LAST_EXPORTED_BIT + 1) enum { - MLX5E_TC_FLOW_INGRESS = MLX5E_TC_INGRESS, - MLX5E_TC_FLOW_EGRESS = MLX5E_TC_EGRESS, - MLX5E_TC_FLOW_ESWITCH = MLX5E_TC_ESW_OFFLOAD, - MLX5E_TC_FLOW_NIC = MLX5E_TC_NIC_OFFLOAD, - MLX5E_TC_FLOW_OFFLOADED = BIT(MLX5E_TC_FLOW_BASE), - MLX5E_TC_FLOW_HAIRPIN = BIT(MLX5E_TC_FLOW_BASE + 1), - MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 2), - MLX5E_TC_FLOW_SLOW = BIT(MLX5E_TC_FLOW_BASE + 3), - MLX5E_TC_FLOW_DUP = BIT(MLX5E_TC_FLOW_BASE + 4), - MLX5E_TC_FLOW_NOT_READY = BIT(MLX5E_TC_FLOW_BASE + 5), + MLX5E_TC_FLOW_FLAG_INGRESS = MLX5E_TC_FLAG_INGRESS_BIT, + MLX5E_TC_FLOW_FLAG_EGRESS = MLX5E_TC_FLAG_EGRESS_BIT, + MLX5E_TC_FLOW_FLAG_ESWITCH = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, + MLX5E_TC_FLOW_FLAG_NIC = MLX5E_TC_FLAG_NIC_OFFLOAD_BIT, + MLX5E_TC_FLOW_FLAG_OFFLOADED = MLX5E_TC_FLOW_BASE, + MLX5E_TC_FLOW_FLAG_HAIRPIN = MLX5E_TC_FLOW_BASE + 1, + MLX5E_TC_FLOW_FLAG_HAIRPIN_RSS = MLX5E_TC_FLOW_BASE + 2, + MLX5E_TC_FLOW_FLAG_SLOW = MLX5E_TC_FLOW_BASE + 3, + MLX5E_TC_FLOW_FLAG_DUP = MLX5E_TC_FLOW_BASE + 4, + MLX5E_TC_FLOW_FLAG_NOT_READY = MLX5E_TC_FLOW_BASE + 5, + MLX5E_TC_FLOW_FLAG_DELETED = MLX5E_TC_FLOW_BASE + 6, }; #define MLX5E_TC_MAX_SPLITS 1 @@ -100,6 +103,7 @@ enum { * container_of(helper item, containing struct type, helper field[index]) */ struct encap_flow_item { + struct mlx5e_encap_entry *e; /* attached encap instance */ struct list_head list; int index; }; @@ -108,7 +112,7 @@ struct mlx5e_tc_flow { struct rhash_head node; struct mlx5e_priv *priv; u64 cookie; - u16 flags; + unsigned long flags; struct mlx5_flow_handle *rule[MLX5E_TC_MAX_SPLITS + 1]; /* Flow can be associated with multiple encap IDs. * The number of encaps is bounded by the number of supported @@ -116,10 +120,14 @@ struct mlx5e_tc_flow { */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5e_tc_flow *peer_flow; + struct mlx5e_mod_hdr_entry *mh; /* attached mod header instance */ struct list_head mod_hdr; /* flows sharing the same mod hdr ID */ + struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ struct list_head peer; /* flows with peer flow */ struct list_head unready; /* flows not ready to be offloaded (e.g due to missing route) */ + refcount_t refcnt; + struct rcu_head rcu_head; union { struct mlx5_esw_flow_attr esw_attr[0]; struct mlx5_nic_flow_attr nic_attr[0]; @@ -157,12 +165,20 @@ struct mlx5e_hairpin_entry { /* a node of a hash table which keeps all the hairpin entries */ struct hlist_node hairpin_hlist; + /* protects flows list */ + spinlock_t flows_lock; /* flows sharing the same hairpin */ struct list_head flows; + /* hpe's that were not fully initialized when dead peer update event + * function traversed them. + */ + struct list_head dead_peer_wait_list; u16 peer_vhca_id; u8 prio; struct mlx5e_hairpin *hp; + refcount_t refcnt; + struct completion res_ready; }; struct mod_hdr_key { @@ -174,16 +190,93 @@ struct mlx5e_mod_hdr_entry { /* a node of a hash table which keeps all the mod_hdr entries */ struct hlist_node mod_hdr_hlist; + /* protects flows list */ + spinlock_t flows_lock; /* flows sharing the same mod_hdr entry */ struct list_head flows; struct mod_hdr_key key; u32 mod_hdr_id; + + refcount_t refcnt; + struct completion res_ready; + int compl_result; }; #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) +static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow); + +static struct mlx5e_tc_flow *mlx5e_flow_get(struct mlx5e_tc_flow *flow) +{ + if (!flow || !refcount_inc_not_zero(&flow->refcnt)) + return ERR_PTR(-EINVAL); + return flow; +} + +static void mlx5e_flow_put(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow) +{ + if (refcount_dec_and_test(&flow->refcnt)) { + mlx5e_tc_del_flow(priv, flow); + kfree_rcu(flow, rcu_head); + } +} + +static void __flow_flag_set(struct mlx5e_tc_flow *flow, unsigned long flag) +{ + /* Complete all memory stores before setting bit. */ + smp_mb__before_atomic(); + set_bit(flag, &flow->flags); +} + +#define flow_flag_set(flow, flag) __flow_flag_set(flow, MLX5E_TC_FLOW_FLAG_##flag) + +static bool __flow_flag_test_and_set(struct mlx5e_tc_flow *flow, + unsigned long flag) +{ + /* test_and_set_bit() provides all necessary barriers */ + return test_and_set_bit(flag, &flow->flags); +} + +#define flow_flag_test_and_set(flow, flag) \ + __flow_flag_test_and_set(flow, \ + MLX5E_TC_FLOW_FLAG_##flag) + +static void __flow_flag_clear(struct mlx5e_tc_flow *flow, unsigned long flag) +{ + /* Complete all memory stores before clearing bit. */ + smp_mb__before_atomic(); + clear_bit(flag, &flow->flags); +} + +#define flow_flag_clear(flow, flag) __flow_flag_clear(flow, \ + MLX5E_TC_FLOW_FLAG_##flag) + +static bool __flow_flag_test(struct mlx5e_tc_flow *flow, unsigned long flag) +{ + bool ret = test_bit(flag, &flow->flags); + + /* Read fields of flow structure only after checking flags. */ + smp_mb__after_atomic(); + return ret; +} + +#define flow_flag_test(flow, flag) __flow_flag_test(flow, \ + MLX5E_TC_FLOW_FLAG_##flag) + +static bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow) +{ + return flow_flag_test(flow, ESWITCH); +} + +static bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow) +{ + return flow_flag_test(flow, OFFLOADED); +} + static inline u32 hash_mod_hdr_info(struct mod_hdr_key *key) { return jhash(key->actions, @@ -199,15 +292,62 @@ static inline int cmp_mod_hdr_info(struct mod_hdr_key *a, return memcmp(a->actions, b->actions, a->num_actions * MLX5_MH_ACT_SZ); } +static struct mod_hdr_tbl * +get_mod_hdr_table(struct mlx5e_priv *priv, int namespace) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + return namespace == MLX5_FLOW_NAMESPACE_FDB ? &esw->offloads.mod_hdr : + &priv->fs.tc.mod_hdr; +} + +static struct mlx5e_mod_hdr_entry * +mlx5e_mod_hdr_get(struct mod_hdr_tbl *tbl, struct mod_hdr_key *key, u32 hash_key) +{ + struct mlx5e_mod_hdr_entry *mh, *found = NULL; + + hash_for_each_possible(tbl->hlist, mh, mod_hdr_hlist, hash_key) { + if (!cmp_mod_hdr_info(&mh->key, key)) { + refcount_inc(&mh->refcnt); + found = mh; + break; + } + } + + return found; +} + +static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, + struct mlx5e_mod_hdr_entry *mh, + int namespace) +{ + struct mod_hdr_tbl *tbl = get_mod_hdr_table(priv, namespace); + + if (!refcount_dec_and_mutex_lock(&mh->refcnt, &tbl->lock)) + return; + hash_del(&mh->mod_hdr_hlist); + mutex_unlock(&tbl->lock); + + WARN_ON(!list_empty(&mh->flows)); + if (mh->compl_result > 0) + mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); + + kfree(mh); +} + +static int get_flow_name_space(struct mlx5e_tc_flow *flow) +{ + return mlx5e_is_eswitch_flow(flow) ? + MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; +} static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5e_tc_flow_parse_attr *parse_attr) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int num_actions, actions_size, namespace, err; struct mlx5e_mod_hdr_entry *mh; + struct mod_hdr_tbl *tbl; struct mod_hdr_key key; - bool found = false; u32 hash_key; num_actions = parse_attr->num_mod_hdr_actions; @@ -218,80 +358,82 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_key = hash_mod_hdr_info(&key); - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { - namespace = MLX5_FLOW_NAMESPACE_FDB; - hash_for_each_possible(esw->offloads.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } else { - namespace = MLX5_FLOW_NAMESPACE_KERNEL; - hash_for_each_possible(priv->fs.tc.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } + namespace = get_flow_name_space(flow); + tbl = get_mod_hdr_table(priv, namespace); + + mutex_lock(&tbl->lock); + mh = mlx5e_mod_hdr_get(tbl, &key, hash_key); + if (mh) { + mutex_unlock(&tbl->lock); + wait_for_completion(&mh->res_ready); - if (found) + if (mh->compl_result < 0) { + err = -EREMOTEIO; + goto attach_header_err; + } goto attach_flow; + } mh = kzalloc(sizeof(*mh) + actions_size, GFP_KERNEL); - if (!mh) + if (!mh) { + mutex_unlock(&tbl->lock); return -ENOMEM; + } mh->key.actions = (void *)mh + sizeof(*mh); memcpy(mh->key.actions, key.actions, actions_size); mh->key.num_actions = num_actions; + spin_lock_init(&mh->flows_lock); INIT_LIST_HEAD(&mh->flows); + refcount_set(&mh->refcnt, 1); + init_completion(&mh->res_ready); + + hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); + mutex_unlock(&tbl->lock); err = mlx5_modify_header_alloc(priv->mdev, namespace, mh->key.num_actions, mh->key.actions, &mh->mod_hdr_id); - if (err) - goto out_err; - - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) - hash_add(esw->offloads.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); - else - hash_add(priv->fs.tc.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); + if (err) { + mh->compl_result = err; + goto alloc_header_err; + } + mh->compl_result = 1; + complete_all(&mh->res_ready); attach_flow: + flow->mh = mh; + spin_lock(&mh->flows_lock); list_add(&flow->mod_hdr, &mh->flows); - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + spin_unlock(&mh->flows_lock); + if (mlx5e_is_eswitch_flow(flow)) flow->esw_attr->mod_hdr_id = mh->mod_hdr_id; else flow->nic_attr->mod_hdr_id = mh->mod_hdr_id; return 0; -out_err: - kfree(mh); +alloc_header_err: + complete_all(&mh->res_ready); +attach_header_err: + mlx5e_mod_hdr_put(priv, mh, namespace); return err; } static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - struct list_head *next = flow->mod_hdr.next; + /* flow wasn't fully initialized */ + if (!flow->mh) + return; + spin_lock(&flow->mh->flows_lock); list_del(&flow->mod_hdr); + spin_unlock(&flow->mh->flows_lock); - if (list_empty(next)) { - struct mlx5e_mod_hdr_entry *mh; - - mh = list_entry(next, struct mlx5e_mod_hdr_entry, flows); - - mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); - hash_del(&mh->mod_hdr_hlist); - kfree(mh); - } + mlx5e_mod_hdr_put(priv, flow->mh, get_flow_name_space(flow)); + flow->mh = NULL; } static @@ -555,13 +697,35 @@ static struct mlx5e_hairpin_entry *mlx5e_hairpin_get(struct mlx5e_priv *priv, hash_for_each_possible(priv->fs.tc.hairpin_tbl, hpe, hairpin_hlist, hash_key) { - if (hpe->peer_vhca_id == peer_vhca_id && hpe->prio == prio) + if (hpe->peer_vhca_id == peer_vhca_id && hpe->prio == prio) { + refcount_inc(&hpe->refcnt); return hpe; + } } return NULL; } +static void mlx5e_hairpin_put(struct mlx5e_priv *priv, + struct mlx5e_hairpin_entry *hpe) +{ + /* no more hairpin flows for us, release the hairpin pair */ + if (!refcount_dec_and_mutex_lock(&hpe->refcnt, &priv->fs.tc.hairpin_tbl_lock)) + return; + hash_del(&hpe->hairpin_hlist); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + + if (!IS_ERR_OR_NULL(hpe->hp)) { + netdev_dbg(priv->netdev, "del hairpin: peer %s\n", + dev_name(hpe->hp->pair->peer_mdev->device)); + + mlx5e_hairpin_destroy(hpe->hp); + } + + WARN_ON(!list_empty(&hpe->flows)); + kfree(hpe); +} + #define UNKNOWN_MATCH_PRIO 8 static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, @@ -627,17 +791,37 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, extack); if (err) return err; + + mutex_lock(&priv->fs.tc.hairpin_tbl_lock); hpe = mlx5e_hairpin_get(priv, peer_id, match_prio); - if (hpe) + if (hpe) { + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + wait_for_completion(&hpe->res_ready); + + if (IS_ERR(hpe->hp)) { + err = -EREMOTEIO; + goto out_err; + } goto attach_flow; + } hpe = kzalloc(sizeof(*hpe), GFP_KERNEL); - if (!hpe) + if (!hpe) { + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); return -ENOMEM; + } + spin_lock_init(&hpe->flows_lock); INIT_LIST_HEAD(&hpe->flows); + INIT_LIST_HEAD(&hpe->dead_peer_wait_list); hpe->peer_vhca_id = peer_id; hpe->prio = match_prio; + refcount_set(&hpe->refcnt, 1); + init_completion(&hpe->res_ready); + + hash_add(priv->fs.tc.hairpin_tbl, &hpe->hairpin_hlist, + hash_hairpin_info(peer_id, match_prio)); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); params.log_data_size = 15; params.log_data_size = min_t(u8, params.log_data_size, @@ -659,9 +843,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, params.num_channels = link_speed64; hp = mlx5e_hairpin_create(priv, ¶ms, peer_ifindex); + hpe->hp = hp; + complete_all(&hpe->res_ready); if (IS_ERR(hp)) { err = PTR_ERR(hp); - goto create_hairpin_err; + goto out_err; } netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n", @@ -669,46 +855,39 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, dev_name(hp->pair->peer_mdev->device), hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets); - hpe->hp = hp; - hash_add(priv->fs.tc.hairpin_tbl, &hpe->hairpin_hlist, - hash_hairpin_info(peer_id, match_prio)); - attach_flow: if (hpe->hp->num_channels > 1) { - flow->flags |= MLX5E_TC_FLOW_HAIRPIN_RSS; + flow_flag_set(flow, HAIRPIN_RSS); flow->nic_attr->hairpin_ft = hpe->hp->ttc.ft.t; } else { flow->nic_attr->hairpin_tirn = hpe->hp->tirn; } + + flow->hpe = hpe; + spin_lock(&hpe->flows_lock); list_add(&flow->hairpin, &hpe->flows); + spin_unlock(&hpe->flows_lock); return 0; -create_hairpin_err: - kfree(hpe); +out_err: + mlx5e_hairpin_put(priv, hpe); return err; } static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - struct list_head *next = flow->hairpin.next; + /* flow wasn't fully initialized */ + if (!flow->hpe) + return; + spin_lock(&flow->hpe->flows_lock); list_del(&flow->hairpin); + spin_unlock(&flow->hpe->flows_lock); - /* no more hairpin flows for us, release the hairpin pair */ - if (list_empty(next)) { - struct mlx5e_hairpin_entry *hpe; - - hpe = list_entry(next, struct mlx5e_hairpin_entry, flows); - - netdev_dbg(priv->netdev, "del hairpin: peer %s\n", - dev_name(hpe->hp->pair->peer_mdev->device)); - - mlx5e_hairpin_destroy(hpe->hp); - hash_del(&hpe->hairpin_hlist); - kfree(hpe); - } + mlx5e_hairpin_put(priv, flow->hpe); + flow->hpe = NULL; } static int @@ -727,18 +906,17 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_fc *counter = NULL; - bool table_created = false; int err, dest_ix = 0; flow_context->flags |= FLOW_CONTEXT_HAS_TAG; flow_context->flow_tag = attr->flow_tag; - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) { + if (flow_flag_test(flow, HAIRPIN)) { err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack); - if (err) { - goto err_add_hairpin_flow; - } - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN_RSS) { + if (err) + return err; + + if (flow_flag_test(flow, HAIRPIN_RSS)) { dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[dest_ix].ft = attr->hairpin_ft; } else { @@ -754,10 +932,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { counter = mlx5_fc_create(dev, true); - if (IS_ERR(counter)) { - err = PTR_ERR(counter); - goto err_fc_create; - } + if (IS_ERR(counter)) + return PTR_ERR(counter); + dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[dest_ix].counter_id = mlx5_fc_id(counter); dest_ix++; @@ -769,9 +946,10 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, flow_act.modify_id = attr->mod_hdr_id; kfree(parse_attr->mod_hdr_actions); if (err) - goto err_create_mod_hdr_id; + return err; } + mutex_lock(&priv->fs.tc.t_lock); if (IS_ERR_OR_NULL(priv->fs.tc.t)) { int tc_grp_size, tc_tbl_size; u32 max_flow_counter; @@ -791,15 +969,13 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, MLX5E_TC_TABLE_NUM_GROUPS, MLX5E_TC_FT_LEVEL, 0); if (IS_ERR(priv->fs.tc.t)) { + mutex_unlock(&priv->fs.tc.t_lock); NL_SET_ERR_MSG_MOD(extack, "Failed to create tc offload table\n"); netdev_err(priv->netdev, "Failed to create tc offload table\n"); - err = PTR_ERR(priv->fs.tc.t); - goto err_create_ft; + return PTR_ERR(priv->fs.tc.t); } - - table_created = true; } if (attr->match_level != MLX5_MATCH_NONE) @@ -807,29 +983,12 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, flow->rule[0] = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec, &flow_act, dest, dest_ix); + mutex_unlock(&priv->fs.tc.t_lock); - if (IS_ERR(flow->rule[0])) { - err = PTR_ERR(flow->rule[0]); - goto err_add_rule; - } + if (IS_ERR(flow->rule[0])) + return PTR_ERR(flow->rule[0]); return 0; - -err_add_rule: - if (table_created) { - mlx5_destroy_flow_table(priv->fs.tc.t); - priv->fs.tc.t = NULL; - } -err_create_ft: - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - mlx5e_detach_mod_hdr(priv, flow); -err_create_mod_hdr_id: - mlx5_fc_destroy(dev, counter); -err_fc_create: - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) - mlx5e_hairpin_flow_del(priv, flow); -err_add_hairpin_flow: - return err; } static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, @@ -839,18 +998,21 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, struct mlx5_fc *counter = NULL; counter = attr->counter; - mlx5_del_flow_rules(flow->rule[0]); + if (!IS_ERR_OR_NULL(flow->rule[0])) + mlx5_del_flow_rules(flow->rule[0]); mlx5_fc_destroy(priv->mdev, counter); - if (!mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD) && priv->fs.tc.t) { + mutex_lock(&priv->fs.tc.t_lock); + if (!mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD)) && priv->fs.tc.t) { mlx5_destroy_flow_table(priv->fs.tc.t); priv->fs.tc.t = NULL; } + mutex_unlock(&priv->fs.tc.t_lock); if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) + if (flow_flag_test(flow, HAIRPIN)) mlx5e_hairpin_flow_del(priv, flow); } @@ -885,7 +1047,6 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, } } - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; return rule; } @@ -894,7 +1055,7 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_esw_flow_attr *attr) { - flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED; + flow_flag_clear(flow, OFFLOADED); if (attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); @@ -917,7 +1078,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); if (!IS_ERR(rule)) - flow->flags |= MLX5E_TC_FLOW_SLOW; + flow_flag_set(flow, SLOW); return rule; } @@ -932,7 +1093,26 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, slow_attr->split_count = 0; slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN; mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); - flow->flags &= ~MLX5E_TC_FLOW_SLOW; + flow_flag_clear(flow, SLOW); +} + +/* Caller must obtain uplink_priv->unready_flows_lock mutex before calling this + * function. + */ +static void unready_flow_add(struct mlx5e_tc_flow *flow, + struct list_head *unready_flows) +{ + flow_flag_set(flow, NOT_READY); + list_add_tail(&flow->unready, unready_flows); +} + +/* Caller must obtain uplink_priv->unready_flows_lock mutex before calling this + * function. + */ +static void unready_flow_del(struct mlx5e_tc_flow *flow) +{ + list_del(&flow->unready); + flow_flag_clear(flow, NOT_READY); } static void add_unready_flow(struct mlx5e_tc_flow *flow) @@ -945,14 +1125,24 @@ static void add_unready_flow(struct mlx5e_tc_flow *flow) rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); uplink_priv = &rpriv->uplink_priv; - flow->flags |= MLX5E_TC_FLOW_NOT_READY; - list_add_tail(&flow->unready, &uplink_priv->unready_flows); + mutex_lock(&uplink_priv->unready_flows_lock); + unready_flow_add(flow, &uplink_priv->unready_flows); + mutex_unlock(&uplink_priv->unready_flows_lock); } static void remove_unready_flow(struct mlx5e_tc_flow *flow) { - list_del(&flow->unready); - flow->flags &= ~MLX5E_TC_FLOW_NOT_READY; + struct mlx5_rep_uplink_priv *uplink_priv; + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + + esw = flow->priv->mdev->priv.eswitch; + rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + uplink_priv = &rpriv->uplink_priv; + + mutex_lock(&uplink_priv->unready_flows_lock); + unready_flow_del(flow); + mutex_unlock(&uplink_priv->unready_flows_lock); } static int @@ -980,14 +1170,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (attr->chain > max_chain) { NL_SET_ERR_MSG(extack, "Requested chain is out of supported range"); - err = -EOPNOTSUPP; - goto err_max_prio_chain; + return -EOPNOTSUPP; } if (attr->prio > max_prio) { NL_SET_ERR_MSG(extack, "Requested priority is out of supported range"); - err = -EOPNOTSUPP; - goto err_max_prio_chain; + return -EOPNOTSUPP; } for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { @@ -1002,7 +1190,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, err = mlx5e_attach_encap(priv, flow, out_dev, out_index, extack, &encap_dev, &encap_valid); if (err) - goto err_attach_encap; + return err; out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; @@ -1012,21 +1200,19 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) - goto err_add_vlan; + return err; if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); kfree(parse_attr->mod_hdr_actions); if (err) - goto err_mod_hdr; + return err; } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { counter = mlx5_fc_create(attr->counter_dev, true); - if (IS_ERR(counter)) { - err = PTR_ERR(counter); - goto err_create_counter; - } + if (IS_ERR(counter)) + return PTR_ERR(counter); attr->counter = counter; } @@ -1044,27 +1230,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); } - if (IS_ERR(flow->rule[0])) { - err = PTR_ERR(flow->rule[0]); - goto err_add_rule; - } + if (IS_ERR(flow->rule[0])) + return PTR_ERR(flow->rule[0]); + else + flow_flag_set(flow, OFFLOADED); return 0; - -err_add_rule: - mlx5_fc_destroy(attr->counter_dev, counter); -err_create_counter: - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - mlx5e_detach_mod_hdr(priv, flow); -err_mod_hdr: - mlx5_eswitch_del_vlan_action(esw, attr); -err_add_vlan: - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) - if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) - mlx5e_detach_encap(priv, flow, out_index); -err_attach_encap: -err_max_prio_chain: - return err; } static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow) @@ -1088,14 +1259,14 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr slow_attr; int out_index; - if (flow->flags & MLX5E_TC_FLOW_NOT_READY) { + if (flow_flag_test(flow, NOT_READY)) { remove_unready_flow(flow); kvfree(attr->parse_attr); return; } - if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { - if (flow->flags & MLX5E_TC_FLOW_SLOW) + if (mlx5e_is_offloaded_flow(flow)) { + if (flow_flag_test(flow, SLOW)) mlx5e_tc_unoffload_from_slow_path(esw, flow, &slow_attr); else mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); @@ -1123,9 +1294,9 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr slow_attr, *esw_attr; + struct encap_flow_item *efi, *tmp; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; - struct encap_flow_item *efi; struct mlx5e_tc_flow *flow; int err; @@ -1142,11 +1313,14 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(priv); - list_for_each_entry(efi, &e->flows, list) { + list_for_each_entry_safe(efi, tmp, &e->flows, list) { bool all_flow_encaps_valid = true; int i; flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); + if (IS_ERR(mlx5e_flow_get(flow))) + continue; + esw_attr = flow->esw_attr; spec = &esw_attr->parse_attr->spec; @@ -1166,19 +1340,23 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, } /* Do not offload flows with unresolved neighbors */ if (!all_flow_encaps_valid) - continue; + goto loop_cont; /* update from slow path rule to encap rule */ rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, esw_attr); if (IS_ERR(rule)) { err = PTR_ERR(rule); mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n", err); - continue; + goto loop_cont; } mlx5e_tc_unoffload_from_slow_path(esw, flow, &slow_attr); - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; /* was unset when slow path rule removed */ flow->rule[0] = rule; + /* was unset when slow path rule removed */ + flow_flag_set(flow, OFFLOADED); + +loop_cont: + mlx5e_flow_put(priv, flow); } } @@ -1187,14 +1365,17 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr slow_attr; + struct encap_flow_item *efi, *tmp; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; - struct encap_flow_item *efi; struct mlx5e_tc_flow *flow; int err; - list_for_each_entry(efi, &e->flows, list) { + list_for_each_entry_safe(efi, tmp, &e->flows, list) { flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); + if (IS_ERR(mlx5e_flow_get(flow))) + continue; + spec = &flow->esw_attr->parse_attr->spec; /* update from encap rule to slow path rule */ @@ -1206,12 +1387,16 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, err = PTR_ERR(rule); mlx5_core_warn(priv->mdev, "Failed to update slow path (encap) flow, %d\n", err); - continue; + goto loop_cont; } mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->esw_attr); - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; /* was unset when fast path rule removed */ flow->rule[0] = rule; + /* was unset when fast path rule removed */ + flow_flag_set(flow, OFFLOADED); + +loop_cont: + mlx5e_flow_put(priv, flow); } /* we know that the encap is valid */ @@ -1221,7 +1406,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) { - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (mlx5e_is_eswitch_flow(flow)) return flow->esw_attr->counter; else return flow->nic_attr->counter; @@ -1248,21 +1433,32 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) return; list_for_each_entry(e, &nhe->encap_list, encap_list) { - struct encap_flow_item *efi; - if (!(e->flags & MLX5_ENCAP_ENTRY_VALID)) + struct encap_flow_item *efi, *tmp; + + if (!(e->flags & MLX5_ENCAP_ENTRY_VALID) || + !mlx5e_encap_take(e)) continue; - list_for_each_entry(efi, &e->flows, list) { + + list_for_each_entry_safe(efi, tmp, &e->flows, list) { flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); - if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { + if (IS_ERR(mlx5e_flow_get(flow))) + continue; + + if (mlx5e_is_offloaded_flow(flow)) { counter = mlx5e_tc_get_counter(flow); lastuse = mlx5_fc_query_lastuse(counter); if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { + mlx5e_flow_put(netdev_priv(e->out_dev), flow); neigh_used = true; break; } } + + mlx5e_flow_put(netdev_priv(e->out_dev), flow); } + + mlx5e_encap_put(netdev_priv(e->out_dev), e); if (neigh_used) break; } @@ -1282,40 +1478,66 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) } } -static void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index) +static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) { - struct list_head *next = flow->encaps[out_index].list.next; + WARN_ON(!list_empty(&e->flows)); + mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); - list_del(&flow->encaps[out_index].list); - if (list_empty(next)) { - struct mlx5e_encap_entry *e; + if (e->flags & MLX5_ENCAP_ENTRY_VALID) + mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); - e = list_entry(next, struct mlx5e_encap_entry, flows); - mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); + kfree(e->encap_header); + kfree(e); +} - if (e->flags & MLX5_ENCAP_ENTRY_VALID) - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); +void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - hash_del_rcu(&e->encap_hlist); - kfree(e->encap_header); - kfree(e); + if (!refcount_dec_and_mutex_lock(&e->refcnt, &esw->offloads.encap_tbl_lock)) + return; + hash_del_rcu(&e->encap_hlist); + mutex_unlock(&esw->offloads.encap_tbl_lock); + + mlx5e_encap_dealloc(priv, e); +} + +static void mlx5e_detach_encap(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, int out_index) +{ + struct mlx5e_encap_entry *e = flow->encaps[out_index].e; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + /* flow wasn't fully initialized */ + if (!e) + return; + + mutex_lock(&esw->offloads.encap_tbl_lock); + list_del(&flow->encaps[out_index].list); + flow->encaps[out_index].e = NULL; + if (!refcount_dec_and_test(&e->refcnt)) { + mutex_unlock(&esw->offloads.encap_tbl_lock); + return; } + hash_del_rcu(&e->encap_hlist); + mutex_unlock(&esw->offloads.encap_tbl_lock); + + mlx5e_encap_dealloc(priv, e); } static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; - if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) || - !(flow->flags & MLX5E_TC_FLOW_DUP)) + if (!flow_flag_test(flow, ESWITCH) || + !flow_flag_test(flow, DUP)) return; mutex_lock(&esw->offloads.peer_mutex); list_del(&flow->peer); mutex_unlock(&esw->offloads.peer_mutex); - flow->flags &= ~MLX5E_TC_FLOW_DUP; + flow_flag_clear(flow, DUP); mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow); kvfree(flow->peer_flow); @@ -1339,7 +1561,7 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { + if (mlx5e_is_eswitch_flow(flow)) { mlx5e_tc_del_fdb_peer_flow(flow); mlx5e_tc_del_fdb_flow(priv, flow); } else { @@ -1840,6 +2062,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep; + bool is_eswitch_flow; int err; inner_match_level = MLX5_MATCH_NONE; @@ -1850,7 +2073,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv, non_tunnel_match_level = (inner_match_level == MLX5_MATCH_NONE) ? outer_match_level : inner_match_level; - if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { + is_eswitch_flow = mlx5e_is_eswitch_flow(flow); + if (!err && is_eswitch_flow) { rep = rpriv->rep; if (rep->vport != MLX5_VPORT_UPLINK && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && @@ -1864,7 +2088,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, } } - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { + if (is_eswitch_flow) { flow->esw_attr->inner_match_level = inner_match_level; flow->esw_attr->outer_match_level = outer_match_level; } else { @@ -2385,14 +2609,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv, { u32 actions; - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (mlx5e_is_eswitch_flow(flow)) actions = flow->esw_attr->action; else actions = flow->nic_attr->action; - if (flow->flags & MLX5E_TC_FLOW_EGRESS && + if (flow_flag_test(flow, EGRESS) && !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) || - (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP))) + (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) || + (actions & MLX5_FLOW_CONTEXT_ACTION_DROP))) return false; if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) @@ -2542,7 +2767,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, if (priv->netdev->netdev_ops == peer_dev->netdev_ops && same_hw_devs(priv, netdev_priv(peer_dev))) { parse_attr->mirred_ifindex[0] = peer_dev->ifindex; - flow->flags |= MLX5E_TC_FLOW_HAIRPIN; + flow_flag_set(flow, HAIRPIN); action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; } else { @@ -2629,6 +2854,31 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv, +bool mlx5e_encap_take(struct mlx5e_encap_entry *e) +{ + return refcount_inc_not_zero(&e->refcnt); +} + +static struct mlx5e_encap_entry * +mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key, + uintptr_t hash_key) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_encap_entry *e; + struct encap_key e_key; + + hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, + encap_hlist, hash_key) { + e_key.ip_tun_key = &e->tun_info->key; + e_key.tc_tunnel = e->tunnel; + if (!cmp_encap_info(&e_key, key) && + mlx5e_encap_take(e)) + return e; + } + + return NULL; +} + static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct net_device *mirred_dev, @@ -2641,11 +2891,10 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; const struct ip_tunnel_info *tun_info; - struct encap_key key, e_key; + struct encap_key key; struct mlx5e_encap_entry *e; unsigned short family; uintptr_t hash_key; - bool found = false; int err = 0; parse_attr = attr->parse_attr; @@ -2660,42 +2909,59 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, hash_key = hash_encap_info(&key); - hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, - encap_hlist, hash_key) { - e_key.ip_tun_key = &e->tun_info->key; - e_key.tc_tunnel = e->tunnel; - if (!cmp_encap_info(&e_key, &key)) { - found = true; - break; - } - } + mutex_lock(&esw->offloads.encap_tbl_lock); + e = mlx5e_encap_get(priv, &key, hash_key); /* must verify if encap is valid or not */ - if (found) + if (e) { + mutex_unlock(&esw->offloads.encap_tbl_lock); + wait_for_completion(&e->res_ready); + + /* Protect against concurrent neigh update. */ + mutex_lock(&esw->offloads.encap_tbl_lock); + if (e->compl_result) { + err = -EREMOTEIO; + goto out_err; + } goto attach_flow; + } e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) - return -ENOMEM; + if (!e) { + err = -ENOMEM; + goto out_err; + } + + refcount_set(&e->refcnt, 1); + init_completion(&e->res_ready); e->tun_info = tun_info; err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack); - if (err) + if (err) { + kfree(e); + e = NULL; goto out_err; + } INIT_LIST_HEAD(&e->flows); + hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); + mutex_unlock(&esw->offloads.encap_tbl_lock); if (family == AF_INET) err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); else if (family == AF_INET6) err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); - if (err) + /* Protect against concurrent neigh update. */ + mutex_lock(&esw->offloads.encap_tbl_lock); + complete_all(&e->res_ready); + if (err) { + e->compl_result = err; goto out_err; - - hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); + } attach_flow: + flow->encaps[out_index].e = e; list_add(&flow->encaps[out_index].list, &e->flows); flow->encaps[out_index].index = out_index; *encap_dev = e->out_dev; @@ -2706,11 +2972,14 @@ attach_flow: } else { *encap_valid = false; } + mutex_unlock(&esw->offloads.encap_tbl_lock); return err; out_err: - kfree(e); + mutex_unlock(&esw->offloads.encap_tbl_lock); + if (e) + mlx5e_encap_put(priv, e); return err; } @@ -2890,12 +3159,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (netdev_port_same_parent_id(priv->netdev, out_dev)) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); - struct net_device *uplink_upper = netdev_master_upper_dev_get(uplink_dev); + struct net_device *uplink_upper; + rcu_read_lock(); + uplink_upper = + netdev_master_upper_dev_get_rcu(uplink_dev); if (uplink_upper && netif_is_lag_master(uplink_upper) && uplink_upper == out_dev) out_dev = uplink_dev; + rcu_read_unlock(); if (is_vlan_dev(out_dev)) { err = add_vlan_push_action(priv, attr, @@ -3066,19 +3339,19 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return 0; } -static void get_flags(int flags, u16 *flow_flags) +static void get_flags(int flags, unsigned long *flow_flags) { - u16 __flow_flags = 0; + unsigned long __flow_flags = 0; - if (flags & MLX5E_TC_INGRESS) - __flow_flags |= MLX5E_TC_FLOW_INGRESS; - if (flags & MLX5E_TC_EGRESS) - __flow_flags |= MLX5E_TC_FLOW_EGRESS; + if (flags & MLX5_TC_FLAG(INGRESS)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_INGRESS); + if (flags & MLX5_TC_FLAG(EGRESS)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_EGRESS); - if (flags & MLX5E_TC_ESW_OFFLOAD) - __flow_flags |= MLX5E_TC_FLOW_ESWITCH; - if (flags & MLX5E_TC_NIC_OFFLOAD) - __flow_flags |= MLX5E_TC_FLOW_NIC; + if (flags & MLX5_TC_FLAG(ESW_OFFLOAD)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_ESWITCH); + if (flags & MLX5_TC_FLAG(NIC_OFFLOAD)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_NIC); *flow_flags = __flow_flags; } @@ -3090,12 +3363,13 @@ static const struct rhashtable_params tc_ht_params = { .automatic_shrinking = true, }; -static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags) +static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, + unsigned long flags) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *uplink_rpriv; - if (flags & MLX5E_TC_ESW_OFFLOAD) { + if (flags & MLX5_TC_FLAG(ESW_OFFLOAD)) { uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); return &uplink_rpriv->uplink_priv.tc_ht; } else /* NIC offload */ @@ -3106,7 +3380,7 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) { struct mlx5_esw_flow_attr *attr = flow->esw_attr; bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK && - flow->flags & MLX5E_TC_FLOW_INGRESS; + flow_flag_test(flow, INGRESS); bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); bool esw_paired = mlx5_devcom_is_paired(attr->in_mdev->priv.devcom, @@ -3125,13 +3399,13 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) static int mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, - struct flow_cls_offload *f, u16 flow_flags, + struct flow_cls_offload *f, unsigned long flow_flags, struct mlx5e_tc_flow_parse_attr **__parse_attr, struct mlx5e_tc_flow **__flow) { struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_tc_flow *flow; - int err; + int out_index, err; flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL); parse_attr = kvzalloc(sizeof(*parse_attr), GFP_KERNEL); @@ -3143,6 +3417,11 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, flow->cookie = f->cookie; flow->flags = flow_flags; flow->priv = priv; + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) + INIT_LIST_HEAD(&flow->encaps[out_index].list); + INIT_LIST_HEAD(&flow->mod_hdr); + INIT_LIST_HEAD(&flow->hairpin); + refcount_set(&flow->refcnt, 1); *__flow = flow; *__parse_attr = parse_attr; @@ -3182,7 +3461,7 @@ mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr, static struct mlx5e_tc_flow * __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - u16 flow_flags, + unsigned long flow_flags, struct net_device *filter_dev, struct mlx5_eswitch_rep *in_rep, struct mlx5_core_dev *in_mdev) @@ -3193,7 +3472,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; int attr_size, err; - flow_flags |= MLX5E_TC_FLOW_ESWITCH; + flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_ESWITCH); attr_size = sizeof(struct mlx5_esw_flow_attr); err = mlx5e_alloc_flow(priv, attr_size, f, flow_flags, &parse_attr, &flow); @@ -3225,15 +3504,14 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, return flow; err_free: - kfree(flow); - kvfree(parse_attr); + mlx5e_flow_put(priv, flow); out: return ERR_PTR(err); } static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, struct mlx5e_tc_flow *flow, - u16 flow_flags) + unsigned long flow_flags) { struct mlx5e_priv *priv = flow->priv, *peer_priv; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw; @@ -3271,7 +3549,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, } flow->peer_flow = peer_flow; - flow->flags |= MLX5E_TC_FLOW_DUP; + flow_flag_set(flow, DUP); mutex_lock(&esw->offloads.peer_mutex); list_add_tail(&flow->peer, &esw->offloads.peer_flows); mutex_unlock(&esw->offloads.peer_mutex); @@ -3284,7 +3562,7 @@ out: static int mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - u16 flow_flags, + unsigned long flow_flags, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { @@ -3318,7 +3596,7 @@ out: static int mlx5e_add_nic_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - u16 flow_flags, + unsigned long flow_flags, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { @@ -3332,7 +3610,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, if (!tc_cls_can_offload_and_chain0(priv->netdev, &f->common)) return -EOPNOTSUPP; - flow_flags |= MLX5E_TC_FLOW_NIC; + flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_NIC); attr_size = sizeof(struct mlx5_nic_flow_attr); err = mlx5e_alloc_flow(priv, attr_size, f, flow_flags, &parse_attr, &flow); @@ -3353,14 +3631,14 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, if (err) goto err_free; - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; + flow_flag_set(flow, OFFLOADED); kvfree(parse_attr); *__flow = flow; return 0; err_free: - kfree(flow); + mlx5e_flow_put(priv, flow); kvfree(parse_attr); out: return err; @@ -3369,12 +3647,12 @@ out: static int mlx5e_tc_add_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - int flags, + unsigned long flags, struct net_device *filter_dev, struct mlx5e_tc_flow **flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - u16 flow_flags; + unsigned long flow_flags; int err; get_flags(flags, &flow_flags); @@ -3393,14 +3671,16 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv, } int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags) + struct flow_cls_offload *f, unsigned long flags) { struct netlink_ext_ack *extack = f->common.extack; struct rhashtable *tc_ht = get_tc_ht(priv, flags); struct mlx5e_tc_flow *flow; int err = 0; - flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); + rcu_read_lock(); + flow = rhashtable_lookup(tc_ht, &f->cookie, tc_ht_params); + rcu_read_unlock(); if (flow) { NL_SET_ERR_MSG_MOD(extack, "flow cookie already exists, ignoring"); @@ -3415,51 +3695,62 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, if (err) goto out; - err = rhashtable_insert_fast(tc_ht, &flow->node, tc_ht_params); + err = rhashtable_lookup_insert_fast(tc_ht, &flow->node, tc_ht_params); if (err) goto err_free; return 0; err_free: - mlx5e_tc_del_flow(priv, flow); - kfree(flow); + mlx5e_flow_put(priv, flow); out: return err; } -#define DIRECTION_MASK (MLX5E_TC_INGRESS | MLX5E_TC_EGRESS) -#define FLOW_DIRECTION_MASK (MLX5E_TC_FLOW_INGRESS | MLX5E_TC_FLOW_EGRESS) - static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags) { - if ((flow->flags & FLOW_DIRECTION_MASK) == (flags & DIRECTION_MASK)) - return true; + bool dir_ingress = !!(flags & MLX5_TC_FLAG(INGRESS)); + bool dir_egress = !!(flags & MLX5_TC_FLAG(EGRESS)); - return false; + return flow_flag_test(flow, INGRESS) == dir_ingress && + flow_flag_test(flow, EGRESS) == dir_egress; } int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags) + struct flow_cls_offload *f, unsigned long flags) { struct rhashtable *tc_ht = get_tc_ht(priv, flags); struct mlx5e_tc_flow *flow; + int err; + rcu_read_lock(); flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); - if (!flow || !same_flow_direction(flow, flags)) - return -EINVAL; + if (!flow || !same_flow_direction(flow, flags)) { + err = -EINVAL; + goto errout; + } + /* Only delete the flow if it doesn't have MLX5E_TC_FLOW_DELETED flag + * set. + */ + if (flow_flag_test_and_set(flow, DELETED)) { + err = -EINVAL; + goto errout; + } rhashtable_remove_fast(tc_ht, &flow->node, tc_ht_params); + rcu_read_unlock(); - mlx5e_tc_del_flow(priv, flow); - - kfree(flow); + mlx5e_flow_put(priv, flow); return 0; + +errout: + rcu_read_unlock(); + return err; } int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags) + struct flow_cls_offload *f, unsigned long flags) { struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct rhashtable *tc_ht = get_tc_ht(priv, flags); @@ -3469,15 +3760,24 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, u64 lastuse = 0; u64 packets = 0; u64 bytes = 0; + int err = 0; - flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); - if (!flow || !same_flow_direction(flow, flags)) - return -EINVAL; + rcu_read_lock(); + flow = mlx5e_flow_get(rhashtable_lookup(tc_ht, &f->cookie, + tc_ht_params)); + rcu_read_unlock(); + if (IS_ERR(flow)) + return PTR_ERR(flow); - if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { + if (!same_flow_direction(flow, flags)) { + err = -EINVAL; + goto errout; + } + + if (mlx5e_is_offloaded_flow(flow)) { counter = mlx5e_tc_get_counter(flow); if (!counter) - return 0; + goto errout; mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); } @@ -3489,8 +3789,8 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, if (!peer_esw) goto out; - if ((flow->flags & MLX5E_TC_FLOW_DUP) && - (flow->peer_flow->flags & MLX5E_TC_FLOW_OFFLOADED)) { + if (flow_flag_test(flow, DUP) && + flow_flag_test(flow->peer_flow, OFFLOADED)) { u64 bytes2; u64 packets2; u64 lastuse2; @@ -3509,15 +3809,117 @@ no_peer_counter: mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); out: flow_stats_update(&f->stats, bytes, packets, lastuse); +errout: + mlx5e_flow_put(priv, flow); + return err; +} + +static int apply_police_params(struct mlx5e_priv *priv, u32 rate, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch *esw; + u16 vport_num; + u32 rate_mbps; + int err; + + esw = priv->mdev->priv.eswitch; + /* rate is given in bytes/sec. + * First convert to bits/sec and then round to the nearest mbit/secs. + * mbit means million bits. + * Moreover, if rate is non zero we choose to configure to a minimum of + * 1 mbit/sec. + */ + rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0; + vport_num = rpriv->rep->vport; + + err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); + if (err) + NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); + + return err; +} + +static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + const struct flow_action_entry *act; + int err; + int i; + + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall called with no action"); + return -EINVAL; + } + + if (!flow_offload_has_one_action(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall policing support only a single action"); + return -EOPNOTSUPP; + } + + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_POLICE: + err = apply_police_params(priv, act->police.rate_bytes_ps, extack); + if (err) + return err; + + rpriv->prev_vf_vport_stats = priv->stats.vf_vport; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall"); + return -EOPNOTSUPP; + } + } return 0; } +int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct netlink_ext_ack *extack = ma->common.extack; + int prio = TC_H_MAJ(ma->common.prio) >> 16; + + if (prio != 1) { + NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported"); + return -EINVAL; + } + + return scan_tc_matchall_fdb_actions(priv, &ma->rule->action, extack); +} + +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct netlink_ext_ack *extack = ma->common.extack; + + return apply_police_params(priv, 0, extack); +} + +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct rtnl_link_stats64 cur_stats; + u64 dbytes; + u64 dpkts; + + cur_stats = priv->stats.vf_vport; + dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets; + dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; + rpriv->prev_vf_vport_stats = cur_stats; + flow_stats_update(&ma->stats, dpkts, dbytes, jiffies); +} + static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { struct mlx5_core_dev *peer_mdev = peer_priv->mdev; - struct mlx5e_hairpin_entry *hpe; + struct mlx5e_hairpin_entry *hpe, *tmp; + LIST_HEAD(init_wait_list); u16 peer_vhca_id; int bkt; @@ -3526,9 +3928,18 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, peer_vhca_id = MLX5_CAP_GEN(peer_mdev, vhca_id); - hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) { - if (hpe->peer_vhca_id == peer_vhca_id) + mutex_lock(&priv->fs.tc.hairpin_tbl_lock); + hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) + if (refcount_inc_not_zero(&hpe->refcnt)) + list_add(&hpe->dead_peer_wait_list, &init_wait_list); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + + list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { + wait_for_completion(&hpe->res_ready); + if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) hpe->hp->pair->peer_gone = true; + + mlx5e_hairpin_put(priv, hpe); } } @@ -3564,7 +3975,10 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) struct mlx5e_tc_table *tc = &priv->fs.tc; int err; - hash_init(tc->mod_hdr_tbl); + mutex_init(&tc->t_lock); + mutex_init(&tc->mod_hdr.lock); + hash_init(tc->mod_hdr.hlist); + mutex_init(&tc->hairpin_tbl_lock); hash_init(tc->hairpin_tbl); err = rhashtable_init(&tc->ht, &tc_ht_params); @@ -3596,12 +4010,16 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) if (tc->netdevice_nb.notifier_call) unregister_netdevice_notifier(&tc->netdevice_nb); + mutex_destroy(&tc->mod_hdr.lock); + mutex_destroy(&tc->hairpin_tbl_lock); + rhashtable_destroy(&tc->ht); if (!IS_ERR_OR_NULL(tc->t)) { mlx5_destroy_flow_table(tc->t); tc->t = NULL; } + mutex_destroy(&tc->t_lock); } int mlx5e_tc_esw_init(struct rhashtable *tc_ht) @@ -3614,7 +4032,7 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL); } -int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags) +int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) { struct rhashtable *tc_ht = get_tc_ht(priv, flags); @@ -3636,10 +4054,10 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work) reoffload_flows_work); struct mlx5e_tc_flow *flow, *tmp; - rtnl_lock(); + mutex_lock(&rpriv->unready_flows_lock); list_for_each_entry_safe(flow, tmp, &rpriv->unready_flows, unready) { if (!mlx5e_tc_add_fdb_flow(flow->priv, flow, NULL)) - remove_unready_flow(flow); + unready_flow_del(flow); } - rtnl_unlock(); + mutex_unlock(&rpriv->unready_flows_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 3ab39275ca7d..ea2072e2fe84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -40,13 +40,15 @@ #ifdef CONFIG_MLX5_ESWITCH enum { - MLX5E_TC_INGRESS = BIT(0), - MLX5E_TC_EGRESS = BIT(1), - MLX5E_TC_NIC_OFFLOAD = BIT(2), - MLX5E_TC_ESW_OFFLOAD = BIT(3), - MLX5E_TC_LAST_EXPORTED_BIT = 3, + MLX5E_TC_FLAG_INGRESS_BIT, + MLX5E_TC_FLAG_EGRESS_BIT, + MLX5E_TC_FLAG_NIC_OFFLOAD_BIT, + MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, + MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, }; +#define MLX5_TC_FLAG(flag) BIT(MLX5E_TC_FLAG_##flag##_BIT) + int mlx5e_tc_nic_init(struct mlx5e_priv *priv); void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv); @@ -54,23 +56,32 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht); void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht); int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags); + struct flow_cls_offload *f, unsigned long flags); int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags); + struct flow_cls_offload *f, unsigned long flags); int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags); + struct flow_cls_offload *f, unsigned long flags); + +int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma); struct mlx5e_encap_entry; void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); +bool mlx5e_encap_take(struct mlx5e_encap_entry *e); +void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); struct mlx5e_neigh_hash_entry; void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); -int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags); +int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags); void mlx5e_tc_reoffload_flows_work(struct work_struct *work); @@ -80,7 +91,11 @@ bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv, #else /* CONFIG_MLX5_ESWITCH */ static inline int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; } static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {} -static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags) { return 0; } +static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv, + unsigned long flags) +{ + return 0; +} #endif #endif /* __MLX5_EN_TC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 600e92cb629a..d3a67a9b4eba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -210,7 +210,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int fsz = skb_frag_size(frag); dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz, @@ -292,8 +292,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { - u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ? - MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode; + u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb); opcode = MLX5_OPCODE_SEND; mss = 0; @@ -608,9 +607,11 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { + u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb); + opcode = MLX5_OPCODE_SEND; mss = 0; - ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + ihs = mlx5e_calc_min_inline(mode, skb); num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); stats->packets++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 41f25ea2e8d9..09d4c64b6e73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -215,11 +215,7 @@ static int mlx5_eq_async_int(struct notifier_block *nb, */ dma_rmb(); - if (likely(eqe->type < MLX5_EVENT_TYPE_MAX)) - atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); - else - mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type); - + atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe); ++eq->cons_index; @@ -415,7 +411,7 @@ void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) int mlx5_eq_table_init(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table; - int i, err; + int i; eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL); if (!eq_table) @@ -423,9 +419,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) dev->priv.eq_table = eq_table; - err = mlx5_eq_debugfs_init(dev); - if (err) - goto kvfree_eq_table; + mlx5_eq_debugfs_init(dev); mutex_init(&eq_table->lock); for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++) @@ -433,11 +427,6 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) eq_table->irq_table = dev->priv.irq_table; return 0; - -kvfree_eq_table: - kvfree(eq_table); - dev->priv.eq_table = NULL; - return err; } void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev) @@ -945,9 +934,6 @@ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_register); @@ -956,9 +942,6 @@ int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_unregister); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1f3891fde2eb..f0692407f617 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -58,20 +58,9 @@ struct vport_addr { bool mc_promisc; }; -enum { - UC_ADDR_CHANGE = BIT(0), - MC_ADDR_CHANGE = BIT(1), - PROMISC_CHANGE = BIT(3), -}; - static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw); static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw); -/* Vport context events */ -#define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \ - MC_ADDR_CHANGE | \ - PROMISC_CHANGE) - struct mlx5_vport *__must_check mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num) { @@ -108,13 +97,13 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, MLX5_SET(nic_vport_context, nic_vport_ctx, arm_change_event, 1); - if (events_mask & UC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_UC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_uc_address_change, 1); - if (events_mask & MC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_MC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_mc_address_change, 1); - if (events_mask & PROMISC_CHANGE) + if (events_mask & MLX5_VPORT_PROMISC_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_promisc_change, 1); @@ -463,6 +452,22 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw) return err; } +#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \ + MLX5_VPORT_MC_ADDR_CHANGE | \ + MLX5_VPORT_PROMISC_CHANGE) + +static int esw_legacy_enable(struct mlx5_eswitch *esw) +{ + int ret; + + ret = esw_create_legacy_table(esw); + if (ret) + return ret; + + mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); + return 0; +} + static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) { esw_cleanup_vepa_rules(esw); @@ -470,6 +475,19 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) esw_destroy_legacy_vepa_table(esw); } +static void esw_legacy_disable(struct mlx5_eswitch *esw) +{ + struct esw_mc_addr *mc_promisc; + + mlx5_eswitch_disable_pf_vf_vports(esw); + + mc_promisc = &esw->mc_promisc; + if (mc_promisc->uplink_rule) + mlx5_del_flow_rules(mc_promisc->uplink_rule); + + esw_destroy_legacy_table(esw); +} + /* E-Switch vport UC/MC lists management */ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, struct vport_addr *vaddr); @@ -901,21 +919,21 @@ static void esw_vport_change_handle_locked(struct mlx5_vport *vport) esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n", vport->vport, mac); - if (vport->enabled_events & UC_ADDR_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_UC_ADDR_CHANGE) { esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); } - if (vport->enabled_events & MC_ADDR_CHANGE) + if (vport->enabled_events & MLX5_VPORT_MC_ADDR_CHANGE) esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); - if (vport->enabled_events & PROMISC_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_PROMISC_CHANGE) { esw_update_vport_rx_mode(esw, vport); if (!IS_ERR_OR_NULL(vport->allmulti_rule)) esw_update_vport_mc_promisc(esw, vport); } - if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE)) + if (vport->enabled_events & (MLX5_VPORT_PROMISC_CHANGE | MLX5_VPORT_MC_ADDR_CHANGE)) esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport); @@ -1393,18 +1411,49 @@ out: return err; } +static bool element_type_supported(struct mlx5_eswitch *esw, int type) +{ + struct mlx5_core_dev *dev = esw->dev = esw->dev; + + switch (type) { + case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_TASR; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT_TC; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; + } + return false; +} + /* Vport QoS management */ -static int esw_create_tsar(struct mlx5_eswitch *esw) +static void esw_create_tsar(struct mlx5_eswitch *esw) { u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; struct mlx5_core_dev *dev = esw->dev; + __be32 *attr; int err; if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) - return 0; + return; + + if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + return; if (esw->qos.enabled) - return -EEXIST; + return; + + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); err = mlx5_create_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, @@ -1412,11 +1461,10 @@ static int esw_create_tsar(struct mlx5_eswitch *esw) &esw->qos.root_tsar_id); if (err) { esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err); - return err; + return; } esw->qos.enabled = true; - return 0; } static void esw_destroy_tsar(struct mlx5_eswitch *esw) @@ -1537,6 +1585,22 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw, return 0; } +int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, + u32 rate_mbps) +{ + u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); + + return mlx5_modify_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + ctx, + vport->qos.esw_tsar_ix, + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW); +} + static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN]) { ((u8 *)node_guid)[7] = mac[0]; @@ -1619,7 +1683,7 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) } static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, - int enable_events) + enum mlx5_eswitch_vport_event enabled_events) { u16 vport_num = vport->vport; @@ -1641,7 +1705,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num); /* Sync with current vport context */ - vport->enabled_events = enable_events; + vport->enabled_events = enabled_events; vport->enabled = true; /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well @@ -1770,11 +1834,46 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw) /* Public E-Switch API */ #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev)) -int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +/* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs + * whichever are present on the eswitch. + */ +void +mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, + enum mlx5_eswitch_vport_event enabled_events) { struct mlx5_vport *vport; + int i; + + /* Enable PF vport */ + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_enable_vport(esw, vport, enabled_events); + + /* Enable ECPF vports */ + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_enable_vport(esw, vport, enabled_events); + } + + /* Enable VF vports */ + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + esw_enable_vport(esw, vport, enabled_events); +} + +/* mlx5_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs + * whichever are previously enabled on the eswitch. + */ +void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + int i; + + mlx5_esw_for_all_vports_reverse(esw, i, vport) + esw_disable_vport(esw, vport); +} + +int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +{ int err; - int i, enabled_events; if (!ESW_ALLOWED(esw) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { @@ -1788,44 +1887,23 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support)) esw_warn(esw->dev, "engress ACL is not supported by FW\n"); + esw_create_tsar(esw); + esw->mode = mode; mlx5_lag_update(esw->dev); if (mode == MLX5_ESWITCH_LEGACY) { - err = esw_create_legacy_table(esw); - if (err) - goto abort; + err = esw_legacy_enable(esw); } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw); + err = esw_offloads_enable(esw); } if (err) goto abort; - err = esw_create_tsar(esw); - if (err) - esw_warn(esw->dev, "Failed to create eswitch TSAR"); - - enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS : - UC_ADDR_CHANGE; - - /* Enable PF vport */ - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_enable_vport(esw, vport, enabled_events); - - /* Enable ECPF vports */ - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - esw_enable_vport(esw, vport, enabled_events); - } - - /* Enable VF vports */ - mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) - esw_enable_vport(esw, vport, enabled_events); - mlx5_eswitch_event_handlers_register(esw); esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n", @@ -1847,10 +1925,7 @@ abort: void mlx5_eswitch_disable(struct mlx5_eswitch *esw) { - struct esw_mc_addr *mc_promisc; - struct mlx5_vport *vport; int old_mode; - int i; if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE) return; @@ -1859,21 +1934,14 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", esw->esw_funcs.num_vfs, esw->enabled_vports); - mc_promisc = &esw->mc_promisc; mlx5_eswitch_event_handlers_unregister(esw); - mlx5_esw_for_all_vports(esw, i, vport) - esw_disable_vport(esw, vport); - - if (mc_promisc && mc_promisc->uplink_rule) - mlx5_del_flow_rules(mc_promisc->uplink_rule); - - esw_destroy_tsar(esw); - if (esw->mode == MLX5_ESWITCH_LEGACY) - esw_destroy_legacy_table(esw); + esw_legacy_disable(esw); else if (esw->mode == MLX5_ESWITCH_OFFLOADS) - esw_offloads_cleanup(esw); + esw_offloads_disable(esw); + + esw_destroy_tsar(esw); old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; @@ -1931,8 +1999,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) if (err) goto abort; + mutex_init(&esw->offloads.encap_tbl_lock); hash_init(esw->offloads.encap_tbl); - hash_init(esw->offloads.mod_hdr_tbl); + mutex_init(&esw->offloads.mod_hdr.lock); + hash_init(esw->offloads.mod_hdr.hlist); + atomic64_set(&esw->offloads.num_flows, 0); mutex_init(&esw->state_lock); mlx5_esw_for_all_vports(esw, i, vport) { @@ -1968,6 +2039,8 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); esw_offloads_cleanup_reps(esw); + mutex_destroy(&esw->offloads.mod_hdr.lock); + mutex_destroy(&esw->offloads.encap_tbl_lock); kfree(esw->vports); kfree(esw); } @@ -2085,23 +2158,19 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, if (vlan > 4095 || qos > 7) return -EINVAL; - mutex_lock(&esw->state_lock); - err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags); if (err) - goto unlock; + return err; evport->info.vlan = vlan; evport->info.qos = qos; if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) { err = esw_vport_ingress_config(esw, evport); if (err) - goto unlock; + return err; err = esw_vport_egress_config(esw, evport); } -unlock: - mutex_unlock(&esw->state_lock); return err; } @@ -2109,11 +2178,16 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u16 vport, u16 vlan, u8 qos) { u8 set_flags = 0; + int err; if (vlan || qos) set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT; - return __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags); + mutex_lock(&esw->state_lock); + err = __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags); + mutex_unlock(&esw->state_lock); + + return err; } int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 04685dbb280c..aba9e7a6ad3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -35,6 +35,7 @@ #include <linux/if_ether.h> #include <linux/if_link.h> +#include <linux/atomic.h> #include <net/devlink.h> #include <linux/mlx5/device.h> #include <linux/mlx5/eswitch.h> @@ -101,6 +102,13 @@ struct mlx5_vport_info { bool trusted; }; +/* Vport context events */ +enum mlx5_eswitch_vport_event { + MLX5_VPORT_UC_ADDR_CHANGE = BIT(0), + MLX5_VPORT_MC_ADDR_CHANGE = BIT(1), + MLX5_VPORT_PROMISC_CHANGE = BIT(3), +}; + struct mlx5_vport { struct mlx5_core_dev *dev; int vport; @@ -122,7 +130,7 @@ struct mlx5_vport { } qos; bool enabled; - u16 enabled_events; + enum mlx5_eswitch_vport_event enabled_events; }; enum offloads_fdb_flags { @@ -173,13 +181,14 @@ struct mlx5_esw_offload { struct mlx5_eswitch_rep *vport_reps; struct list_head peer_flows; struct mutex peer_mutex; + struct mutex encap_tbl_lock; /* protects encap_tbl */ DECLARE_HASHTABLE(encap_tbl, 8); - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; DECLARE_HASHTABLE(termtbl_tbl, 8); struct mutex termtbl_mutex; /* protects termtbl hash */ const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES]; u8 inline_mode; - u64 num_flows; + atomic64_t num_flows; enum devlink_eswitch_encap_mode encap; }; @@ -207,8 +216,11 @@ enum { struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; + /* legacy data structures */ struct mlx5_eswitch_fdb fdb_table; struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE]; + struct esw_mc_addr mc_promisc; + /* end of legacy */ struct workqueue_struct *work_queue; struct mlx5_vport *vports; u32 flags; @@ -218,7 +230,6 @@ struct mlx5_eswitch { * and async SRIOV admin state changes */ struct mutex state_lock; - struct esw_mc_addr mc_promisc; struct { bool enabled; @@ -233,8 +244,8 @@ struct mlx5_eswitch { struct mlx5_esw_functions esw_funcs; }; -void esw_offloads_cleanup(struct mlx5_eswitch *esw); -int esw_offloads_init(struct mlx5_eswitch *esw); +void esw_offloads_disable(struct mlx5_eswitch *esw); +int esw_offloads_enable(struct mlx5_eswitch *esw); void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw); int esw_offloads_init_reps(struct mlx5_eswitch *esw); void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, @@ -251,6 +262,8 @@ void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, struct mlx5_vport *vport); void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, + u32 rate_mbps); /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); @@ -513,6 +526,11 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); (vport) = &(esw)->vports[i], \ (i) < (esw)->total_vports; (i)++) +#define mlx5_esw_for_all_vports_reverse(esw, i, vport) \ + for ((i) = (esw)->total_vports - 1; \ + (vport) = &(esw)->vports[i], \ + (i) >= MLX5_VPORT_PF; (i)--) + #define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) \ for ((i) = MLX5_VPORT_FIRST_VF; \ (vport) = &(esw)->vports[(i)], \ @@ -574,6 +592,11 @@ bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num); void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs); int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data); +void +mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, + enum mlx5_eswitch_vport_event enabled_events); +void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw); + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0323fd078271..7d3582ee66b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -229,7 +229,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (IS_ERR(rule)) goto err_add_rule; else - esw->offloads.num_flows++; + atomic64_inc(&esw->offloads.num_flows); return rule; @@ -294,7 +294,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, if (IS_ERR(rule)) goto add_err; - esw->offloads.num_flows++; + atomic64_inc(&esw->offloads.num_flows); return rule; add_err: @@ -322,7 +322,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw, mlx5_eswitch_termtbl_put(esw, attr->dests[i].termtbl); } - esw->offloads.num_flows--; + atomic64_dec(&esw->offloads.num_flows); if (fwd_rule) { esw_put_prio_table(esw, attr->chain, attr->prio, 1); @@ -438,9 +438,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, fwd = !!((attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && !attr->dest_chain); + mutex_lock(&esw->state_lock); + err = esw_add_vlan_action_check(attr, push, pop, fwd); if (err) - return err; + goto unlock; attr->vlan_handled = false; @@ -453,11 +455,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, attr->vlan_handled = true; } - return 0; + goto unlock; } if (!push && !pop) - return 0; + goto unlock; if (!(offloads->vlan_push_pop_refcount)) { /* it's the 1st vlan rule, apply global vlan pop policy */ @@ -482,6 +484,8 @@ skip_set_push: out: if (!err) attr->vlan_handled = true; +unlock: + mutex_unlock(&esw->state_lock); return err; } @@ -504,6 +508,8 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); fwd = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); + mutex_lock(&esw->state_lock); + vport = esw_vlan_action_get_vport(attr, push, pop); if (!push && !pop && fwd) { @@ -511,7 +517,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) vport->vlan_refcount--; - return 0; + goto out; } if (push) { @@ -529,12 +535,13 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, skip_unset_push: offloads->vlan_push_pop_refcount--; if (offloads->vlan_push_pop_refcount) - return 0; + goto out; /* no more vlan rules, stop global vlan pop policy */ err = esw_set_global_vlan_pop(esw, 0); out: + mutex_unlock(&esw->state_lock); return err; } @@ -583,38 +590,15 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule) mlx5_del_flow_rules(rule); } -static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw) +static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable) { u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; u8 fdb_to_vport_reg_c_id; int err; - err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, - out, sizeof(out)); - if (err) - return err; - - fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, - esw_vport_context.fdb_to_vport_reg_c_id); - - fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; - MLX5_SET(modify_esw_vport_context_in, in, - esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); - - MLX5_SET(modify_esw_vport_context_in, in, - field_select.fdb_to_vport_reg_c_id, 1); - - return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport, - in, sizeof(in)); -} - -static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) -{ - u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; - u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; - u8 fdb_to_vport_reg_c_id; - int err; + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) + return 0; err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, out, sizeof(out)); @@ -624,7 +608,10 @@ static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, esw_vport_context.fdb_to_vport_reg_c_id); - fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; + if (enable) + fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; + else + fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; MLX5_SET(modify_esw_vport_context_in, in, esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); @@ -1402,10 +1389,9 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw) int esw_offloads_init_reps(struct mlx5_eswitch *esw) { int total_vports = esw->total_vports; - struct mlx5_core_dev *dev = esw->dev; struct mlx5_eswitch_rep *rep; - u8 hw_id[ETH_ALEN], rep_type; int vport_index; + u8 rep_type; esw->offloads.vport_reps = kcalloc(total_vports, sizeof(struct mlx5_eswitch_rep), @@ -1413,12 +1399,9 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) if (!esw->offloads.vport_reps) return -ENOMEM; - mlx5_query_mac_address(dev, hw_id); - mlx5_esw_for_all_reps(esw, vport_index, rep) { rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index); rep->vport_index = vport_index; - ether_addr_copy(rep->hw_id, hw_id); for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) atomic_set(&rep->rep_data[rep_type].state, @@ -2120,7 +2103,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type return NOTIFY_OK; } -int esw_offloads_init(struct mlx5_eswitch *esw) +int esw_offloads_enable(struct mlx5_eswitch *esw) { int err; @@ -2134,11 +2117,11 @@ int esw_offloads_init(struct mlx5_eswitch *esw) if (err) return err; - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { - err = mlx5_eswitch_enable_passing_vport_metadata(esw); - if (err) - goto err_vport_metadata; - } + err = esw_set_passing_vport_metadata(esw, true); + if (err) + goto err_vport_metadata; + + mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE); err = esw_offloads_load_all_reps(esw); if (err) @@ -2152,8 +2135,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw) return 0; err_reps: - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); err_vport_metadata: esw_offloads_steering_cleanup(esw); return err; @@ -2178,13 +2161,13 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, return err; } -void esw_offloads_cleanup(struct mlx5_eswitch *esw) +void esw_offloads_disable(struct mlx5_eswitch *esw) { mlx5_rdma_disable_roce(esw->dev); esw_offloads_devcom_cleanup(esw); esw_offloads_unload_all_reps(esw); - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); esw_offloads_steering_cleanup(esw); esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } @@ -2345,7 +2328,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, break; } - if (esw->offloads.num_flows > 0) { + if (atomic64_read(&esw->offloads.num_flows) > 0) { NL_SET_ERR_MSG_MOD(extack, "Can't set inline mode when flows are configured"); return -EOPNOTSUPP; @@ -2455,7 +2438,7 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, if (esw->offloads.encap == encap) return 0; - if (esw->offloads.num_flows > 0) { + if (atomic64_read(&esw->offloads.num_flows) > 0) { NL_SET_ERR_MSG_MOD(extack, "Can't set encapsulation when flows are configured"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7ac1249eadc3..b84a225bbe86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -566,7 +566,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id) { u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)] = {0}; u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0}; @@ -574,6 +576,7 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) MLX5_SET(alloc_flow_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_FLOW_COUNTER); + MLX5_SET(alloc_flow_counter_in, in, flow_counter_bulk, alloc_bitmask); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (!err) @@ -581,6 +584,11 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) return err; } +int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +{ + return mlx5_cmd_fc_bulk_alloc(dev, 0, id); +} + int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id) { u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)] = {0}; @@ -615,67 +623,24 @@ int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, return 0; } -struct mlx5_cmd_fc_bulk { - u32 id; - int num; - int outlen; - u32 out[0]; -}; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num) -{ - struct mlx5_cmd_fc_bulk *b; - int outlen = - MLX5_ST_SZ_BYTES(query_flow_counter_out) + - MLX5_ST_SZ_BYTES(traffic_counter) * num; - - b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL); - if (!b) - return NULL; - - b->id = id; - b->num = num; - b->outlen = outlen; - - return b; -} - -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len) { - kfree(b); + return MLX5_ST_SZ_BYTES(query_flow_counter_out) + + MLX5_ST_SZ_BYTES(traffic_counter) * bulk_len; } -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out) { + int outlen = mlx5_cmd_fc_get_bulk_query_out_len(bulk_len); u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0}; MLX5_SET(query_flow_counter_in, in, opcode, MLX5_CMD_OP_QUERY_FLOW_COUNTER); MLX5_SET(query_flow_counter_in, in, op_mod, 0); - MLX5_SET(query_flow_counter_in, in, flow_counter_id, b->id); - MLX5_SET(query_flow_counter_in, in, num_of_counters, b->num); - return mlx5_cmd_exec(dev, in, sizeof(in), b->out, b->outlen); -} - -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes) -{ - int index = id - b->id; - void *stats; - - if (index < 0 || index >= b->num) { - mlx5_core_warn(dev, "Flow counter id (0x%x) out of range (0x%x..0x%x). Counter ignored.\n", - id, b->id, b->id + b->num - 1); - return; - } - - stats = MLX5_ADDR_OF(query_flow_counter_out, b->out, - flow_statistics[index]); - *packets = MLX5_GET64(traffic_counter, stats, packets); - *bytes = MLX5_GET64(traffic_counter, stats, octets); + MLX5_SET(query_flow_counter_in, in, flow_counter_id, base_id); + MLX5_SET(query_flow_counter_in, in, num_of_counters, bulk_len); + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index e340f9af2f5a..bc4606306009 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -78,20 +78,16 @@ struct mlx5_flow_cmds { }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes); -struct mlx5_cmd_fc_bulk; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num); -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b); -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b); -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes); +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len); +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out); const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 1834d9f3aa1c..1804cf3c3814 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,6 +40,8 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) +#define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) +#define MLX5_FC_POOL_USED_BUFF_RATIO 10 struct mlx5_fc_cache { u64 packets; @@ -58,12 +60,18 @@ struct mlx5_fc { u64 lastpackets; u64 lastbytes; + struct mlx5_fc_bulk *bulk; u32 id; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev); +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool); +static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool); +static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc); + /* locking scheme: * * It is the responsibility of the user to prevent concurrent calls or bad @@ -75,7 +83,7 @@ struct mlx5_fc { * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * mlx5_fc_stats_work(). addlist is a lockless single linked list * that doesn't require any additional synchronization when adding single * node. * - spawn thread to do the actual destroy @@ -136,81 +144,87 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev, spin_unlock(&fc_stats->counters_idr_lock); } -/* The function returns the last counter that was queried so the caller - * function can continue calling it till all counters are queried. - */ -static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, - struct mlx5_fc *first, - u32 last_id) +static int get_max_bulk_query_len(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - struct mlx5_fc *counter = NULL; - struct mlx5_cmd_fc_bulk *b; - bool more = false; - u32 afirst_id; - int num; - int err; + return min_t(int, MLX5_SW_MAX_COUNTERS_BULK, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +} - int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK, - (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +static void update_counter_cache(int index, u32 *bulk_raw_data, + struct mlx5_fc_cache *cache) +{ + void *stats = MLX5_ADDR_OF(query_flow_counter_out, bulk_raw_data, + flow_statistics[index]); + u64 packets = MLX5_GET64(traffic_counter, stats, packets); + u64 bytes = MLX5_GET64(traffic_counter, stats, octets); - /* first id must be aligned to 4 when using bulk query */ - afirst_id = first->id & ~0x3; + if (cache->packets == packets) + return; - /* number of counters to query inc. the last counter */ - num = ALIGN(last_id - afirst_id + 1, 4); - if (num > max_bulk) { - num = max_bulk; - last_id = afirst_id + num - 1; - } + cache->packets = packets; + cache->bytes = bytes; + cache->lastuse = jiffies; +} - b = mlx5_cmd_fc_bulk_alloc(dev, afirst_id, num); - if (!b) { - mlx5_core_err(dev, "Error allocating resources for bulk query\n"); - return NULL; - } +static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, + struct mlx5_fc *first, + u32 last_id) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + bool query_more_counters = (first->id <= last_id); + int max_bulk_len = get_max_bulk_query_len(dev); + u32 *data = fc_stats->bulk_query_out; + struct mlx5_fc *counter = first; + u32 bulk_base_id; + int bulk_len; + int err; - err = mlx5_cmd_fc_bulk_query(dev, b); - if (err) { - mlx5_core_err(dev, "Error doing bulk query: %d\n", err); - goto out; - } + while (query_more_counters) { + /* first id must be aligned to 4 when using bulk query */ + bulk_base_id = counter->id & ~0x3; - counter = first; - list_for_each_entry_from(counter, &fc_stats->counters, list) { - struct mlx5_fc_cache *c = &counter->cache; - u64 packets; - u64 bytes; + /* number of counters to query inc. the last counter */ + bulk_len = min_t(int, max_bulk_len, + ALIGN(last_id - bulk_base_id + 1, 4)); - if (counter->id > last_id) { - more = true; - break; + err = mlx5_cmd_fc_bulk_query(dev, bulk_base_id, bulk_len, + data); + if (err) { + mlx5_core_err(dev, "Error doing bulk query: %d\n", err); + return; } + query_more_counters = false; - mlx5_cmd_fc_bulk_get(dev, b, - counter->id, &packets, &bytes); + list_for_each_entry_from(counter, &fc_stats->counters, list) { + int counter_index = counter->id - bulk_base_id; + struct mlx5_fc_cache *cache = &counter->cache; - if (c->packets == packets) - continue; + if (counter->id >= bulk_base_id + bulk_len) { + query_more_counters = true; + break; + } - c->packets = packets; - c->bytes = bytes; - c->lastuse = jiffies; + update_counter_cache(counter_index, data, cache); + } } - -out: - mlx5_cmd_fc_bulk_free(b); - - return more ? counter : NULL; } -static void mlx5_free_fc(struct mlx5_core_dev *dev, - struct mlx5_fc *counter) +static void mlx5_fc_free(struct mlx5_core_dev *dev, struct mlx5_fc *counter) { mlx5_cmd_fc_free(dev, counter->id); kfree(counter); } +static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + + if (counter->bulk) + mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter); + else + mlx5_fc_free(dev, counter); +} + static void mlx5_fc_stats_work(struct work_struct *work) { struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, @@ -234,7 +248,7 @@ static void mlx5_fc_stats_work(struct work_struct *work) llist_for_each_entry_safe(counter, tmp, dellist, dellist) { mlx5_fc_stats_remove(dev, counter); - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } if (time_before(now, fc_stats->next_query) || @@ -244,32 +258,62 @@ static void mlx5_fc_stats_work(struct work_struct *work) counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, list); - while (counter) - counter = mlx5_fc_stats_query(dev, counter, last->id); + if (counter) + mlx5_fc_stats_query_counter_range(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } -struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +static struct mlx5_fc *mlx5_fc_single_alloc(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; struct mlx5_fc *counter; int err; counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); - if (err) - goto err_out; + if (err) { + kfree(counter); + return ERR_PTR(err); + } + + return counter; +} + +static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter; + + if (aging && MLX5_CAP_GEN(dev, flow_counter_bulk_alloc) != 0) { + counter = mlx5_fc_pool_acquire_counter(&fc_stats->fc_pool); + if (!IS_ERR(counter)) + return counter; + } + + return mlx5_fc_single_alloc(dev); +} + +struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging); + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int err; + + if (IS_ERR(counter)) + return counter; + + INIT_LIST_HEAD(&counter->list); + counter->aging = aging; if (aging) { u32 id = counter->id; counter->cache.lastuse = jiffies; - counter->aging = true; + counter->lastbytes = counter->cache.bytes; + counter->lastpackets = counter->cache.packets; idr_preload(GFP_KERNEL); spin_lock(&fc_stats->counters_idr_lock); @@ -290,10 +334,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) return counter; err_out_alloc: - mlx5_cmd_fc_free(dev, counter->id); -err_out: - kfree(counter); - + mlx5_fc_release(dev, counter); return ERR_PTR(err); } EXPORT_SYMBOL(mlx5_fc_create); @@ -317,13 +358,15 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; } - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int max_bulk_len; + int max_out_len; spin_lock_init(&fc_stats->counters_idr_lock); idr_init(&fc_stats->counters_idr); @@ -331,14 +374,25 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); + max_bulk_len = get_max_bulk_query_len(dev); + max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len); + fc_stats->bulk_query_out = kzalloc(max_out_len, GFP_KERNEL); + if (!fc_stats->bulk_query_out) + return -ENOMEM; + fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) - return -ENOMEM; + goto err_wq_create; fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD; INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work); + mlx5_fc_pool_init(&fc_stats->fc_pool, dev); return 0; + +err_wq_create: + kfree(fc_stats->bulk_query_out); + return -ENOMEM; } void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) @@ -348,18 +402,21 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) struct mlx5_fc *counter; struct mlx5_fc *tmp; + mlx5_fc_pool_cleanup(&fc_stats->fc_pool); cancel_delayed_work_sync(&dev->priv.fc_stats.work); destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; + kfree(fc_stats->bulk_query_out); + idr_destroy(&fc_stats->counters_idr); tmplist = llist_del_all(&fc_stats->addlist); llist_for_each_entry_safe(counter, tmp, tmplist, addlist) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, @@ -406,3 +463,243 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, fc_stats->sampling_interval = min_t(unsigned long, interval, fc_stats->sampling_interval); } + +/* Flow counter bluks */ + +struct mlx5_fc_bulk { + struct list_head pool_list; + u32 base_id; + int bulk_len; + unsigned long *bitmask; + struct mlx5_fc fcs[0]; +}; + +static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, + u32 id) +{ + counter->bulk = bulk; + counter->id = id; +} + +static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk) +{ + return bitmap_weight(bulk->bitmask, bulk->bulk_len); +} + +static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) +{ + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask; + struct mlx5_fc_bulk *bulk; + int err = -ENOMEM; + int bulk_len; + u32 base_id; + int i; + + alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc); + bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1; + + bulk = kzalloc(sizeof(*bulk) + bulk_len * sizeof(struct mlx5_fc), + GFP_KERNEL); + if (!bulk) + goto err_alloc_bulk; + + bulk->bitmask = kcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long), + GFP_KERNEL); + if (!bulk->bitmask) + goto err_alloc_bitmask; + + err = mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id); + if (err) + goto err_mlx5_cmd_bulk_alloc; + + bulk->base_id = base_id; + bulk->bulk_len = bulk_len; + for (i = 0; i < bulk_len; i++) { + mlx5_fc_init(&bulk->fcs[i], bulk, base_id + i); + set_bit(i, bulk->bitmask); + } + + return bulk; + +err_mlx5_cmd_bulk_alloc: + kfree(bulk->bitmask); +err_alloc_bitmask: + kfree(bulk); +err_alloc_bulk: + return ERR_PTR(err); +} + +static int +mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk) +{ + if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all counters were released\n"); + return -EBUSY; + } + + mlx5_cmd_fc_free(dev, bulk->base_id); + kfree(bulk->bitmask); + kfree(bulk); + + return 0; +} + +static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk) +{ + int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len); + + if (free_fc_index >= bulk->bulk_len) + return ERR_PTR(-ENOSPC); + + clear_bit(free_fc_index, bulk->bitmask); + return &bulk->fcs[free_fc_index]; +} + +static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) +{ + int fc_index = fc->id - bulk->base_id; + + if (test_bit(fc_index, bulk->bitmask)) + return -EINVAL; + + set_bit(fc_index, bulk->bitmask); + return 0; +} + +/* Flow counters pool API */ + +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev) +{ + fc_pool->dev = dev; + mutex_init(&fc_pool->pool_lock); + INIT_LIST_HEAD(&fc_pool->fully_used); + INIT_LIST_HEAD(&fc_pool->partially_used); + INIT_LIST_HEAD(&fc_pool->unused); + fc_pool->available_fcs = 0; + fc_pool->used_fcs = 0; + fc_pool->threshold = 0; +} + +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk; + struct mlx5_fc_bulk *tmp; + + list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); +} + +static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool) +{ + fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD, + fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO); +} + +static struct mlx5_fc_bulk * +mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *new_bulk; + + new_bulk = mlx5_fc_bulk_create(dev); + if (!IS_ERR(new_bulk)) + fc_pool->available_fcs += new_bulk->bulk_len; + mlx5_fc_pool_update_threshold(fc_pool); + return new_bulk; +} + +static void +mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + + fc_pool->available_fcs -= bulk->bulk_len; + mlx5_fc_bulk_destroy(dev, bulk); + mlx5_fc_pool_update_threshold(fc_pool); +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_from_list(struct list_head *src_list, + struct list_head *next_list, + bool move_non_full_bulk) +{ + struct mlx5_fc_bulk *bulk; + struct mlx5_fc *fc; + + if (list_empty(src_list)) + return ERR_PTR(-ENODATA); + + bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list); + fc = mlx5_fc_bulk_acquire_fc(bulk); + if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0) + list_move(&bulk->pool_list, next_list); + return fc; +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_fc_bulk *new_bulk; + struct mlx5_fc *fc; + + mutex_lock(&fc_pool->pool_lock); + + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used, + &fc_pool->fully_used, false); + if (IS_ERR(fc)) + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused, + &fc_pool->partially_used, + true); + if (IS_ERR(fc)) { + new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool); + if (IS_ERR(new_bulk)) { + fc = ERR_CAST(new_bulk); + goto out; + } + fc = mlx5_fc_bulk_acquire_fc(new_bulk); + list_add(&new_bulk->pool_list, &fc_pool->partially_used); + } + fc_pool->available_fcs--; + fc_pool->used_fcs++; + +out: + mutex_unlock(&fc_pool->pool_lock); + return fc; +} + +static void +mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk = fc->bulk; + int bulk_free_fcs_amount; + + mutex_lock(&fc_pool->pool_lock); + + if (mlx5_fc_bulk_release_fc(bulk, fc)) { + mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n"); + goto unlock; + } + + fc_pool->available_fcs++; + fc_pool->used_fcs--; + + bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk); + if (bulk_free_fcs_amount == 1) + list_move_tail(&bulk->pool_list, &fc_pool->partially_used); + if (bulk_free_fcs_amount == bulk->bulk_len) { + list_del(&bulk->pool_list); + if (fc_pool->available_fcs > fc_pool->threshold) + mlx5_fc_pool_free_bulk(fc_pool, bulk); + else + list_add(&bulk->pool_list, &fc_pool->unused); + } + +unlock: + mutex_unlock(&fc_pool->pool_lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 3dfab91ae5f2..4be4d2d36218 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -87,7 +87,7 @@ void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev); int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); /* This function should only be called after mlx5_cmd_force_teardown_hca */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index b9d4f4e19ff9..148b55c3db7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/refcount.h> #include <linux/mlx5/driver.h> #include <net/vxlan.h> #include "mlx5_core.h" @@ -48,7 +49,7 @@ struct mlx5_vxlan { struct mlx5_vxlan_port { struct hlist_node hlist; - atomic_t refcount; + refcount_t refcount; u16 udp_port; }; @@ -113,7 +114,7 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) vxlanp = mlx5_vxlan_lookup_port(vxlan, port); if (vxlanp) { - atomic_inc(&vxlanp->refcount); + refcount_inc(&vxlanp->refcount); return 0; } @@ -137,7 +138,7 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) } vxlanp->udp_port = port; - atomic_set(&vxlanp->refcount, 1); + refcount_set(&vxlanp->refcount, 1); spin_lock_bh(&vxlan->lock); hash_add(vxlan->htable, &vxlanp->hlist, port); @@ -170,7 +171,7 @@ int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) goto out_unlock; } - if (atomic_dec_and_test(&vxlanp->refcount)) { + if (refcount_dec_and_test(&vxlanp->refcount)) { hash_del(&vxlanp->hlist); remove = true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b15b27a497fc..0b70b1d6338d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -826,11 +826,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eq_cleanup; } - err = mlx5_cq_debugfs_init(dev); - if (err) { - mlx5_core_err(dev, "failed to initialize cq debugfs\n"); - goto err_events_cleanup; - } + mlx5_cq_debugfs_init(dev); mlx5_init_qp_table(dev); @@ -891,7 +887,6 @@ err_tables_cleanup: mlx5_cleanup_mkey_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cq_debugfs_cleanup(dev); -err_events_cleanup: mlx5_events_cleanup(dev); err_eq_cleanup: mlx5_eq_table_cleanup(dev); @@ -1217,8 +1212,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) { int err = 0; - if (cleanup) + if (cleanup) { + mlx5_unregister_device(dev); mlx5_drain_health_wq(dev); + } mutex_lock(&dev->intf_state_mutex); if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { @@ -1369,7 +1366,6 @@ static void remove_one(struct pci_dev *pdev) mlx5_crdump_disable(dev); mlx5_devlink_unregister(devlink); - mlx5_unregister_device(dev); if (mlx5_unload_one(dev, true)) { mlx5_core_err(dev, "mlx5_unload_one failed\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 471bbc48bc1f..87b75b2207c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -146,7 +146,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); void mlx5_cmd_flush(struct mlx5_core_dev *dev); -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index c912d82ca64b..30f7848a6f88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -122,12 +122,13 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline_mode) { switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) { + case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: + if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode)) + break; + /* fall through */ case MLX5_CAP_INLINE_MODE_L2: *min_inline_mode = MLX5_INLINE_MODE_L2; break; - case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: - mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode); - break; case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: *min_inline_mode = MLX5_INLINE_MODE_NONE; break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 06c80343d9ed..f458fd1ce9f8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -71,7 +71,7 @@ config MLXSW_SWITCHX2 module will be called mlxsw_switchx2. config MLXSW_SPECTRUM - tristate "Mellanox Technologies Spectrum support" + tristate "Mellanox Technologies Spectrum family support" depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV && VLAN_8021Q depends on PSAMPLE || PSAMPLE=n depends on BRIDGE || BRIDGE=n @@ -87,8 +87,8 @@ config MLXSW_SPECTRUM select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m ---help--- - This driver supports Mellanox Technologies Spectrum Ethernet - Switch ASICs. + This driver supports Mellanox Technologies + Spectrum/Spectrum-2/Spectrum-3 Ethernet Switch ASICs. To compile this driver as a module, choose M here: the module will be called mlxsw_spectrum. diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index 946339e13eb9..5b1323645a5d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -9,6 +9,7 @@ #define PCI_DEVICE_ID_MELLANOX_SWITCHX2 0xc738 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM 0xcb84 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM2 0xcf6c +#define PCI_DEVICE_ID_MELLANOX_SPECTRUM3 0xcf70 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB 0xcb20 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB2 0xcf08 diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index eda9c23e87b2..389861ece418 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -65,6 +65,7 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum"; static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2"; +static const char mlxsw_sp3_driver_name[] = "mlxsw_spectrum3"; static const char mlxsw_sp_driver_version[] = "1.0"; static const unsigned char mlxsw_sp1_mac_mask[ETH_ALEN] = { @@ -1625,7 +1626,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, } flow_block_cb_incref(block_cb); err = mlxsw_sp_acl_block_bind(mlxsw_sp, acl_block, - mlxsw_sp_port, ingress); + mlxsw_sp_port, ingress, f->extack); if (err) goto err_block_bind; @@ -5026,6 +5027,26 @@ static int mlxsw_sp1_resources_kvd_register(struct mlxsw_core *mlxsw_core) return 0; } +static int mlxsw_sp2_resources_kvd_register(struct mlxsw_core *mlxsw_core) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_core); + struct devlink_resource_size_params kvd_size_params; + u32 kvd_size; + + if (!MLXSW_CORE_RES_VALID(mlxsw_core, KVD_SIZE)) + return -EIO; + + kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); + devlink_resource_size_params_init(&kvd_size_params, kvd_size, kvd_size, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + + return devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD, + kvd_size, MLXSW_SP_RESOURCE_KVD, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &kvd_size_params); +} + static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core) { return mlxsw_sp1_resources_kvd_register(mlxsw_core); @@ -5033,7 +5054,7 @@ static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core) static int mlxsw_sp2_resources_register(struct mlxsw_core *mlxsw_core) { - return 0; + return mlxsw_sp2_resources_kvd_register(mlxsw_core); } static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core, @@ -5270,6 +5291,35 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .res_query_enabled = true, }; +static struct mlxsw_driver mlxsw_sp3_driver = { + .kind = mlxsw_sp3_driver_name, + .priv_size = sizeof(struct mlxsw_sp), + .init = mlxsw_sp2_init, + .fini = mlxsw_sp_fini, + .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set, + .port_split = mlxsw_sp_port_split, + .port_unsplit = mlxsw_sp_port_unsplit, + .sb_pool_get = mlxsw_sp_sb_pool_get, + .sb_pool_set = mlxsw_sp_sb_pool_set, + .sb_port_pool_get = mlxsw_sp_sb_port_pool_get, + .sb_port_pool_set = mlxsw_sp_sb_port_pool_set, + .sb_tc_pool_bind_get = mlxsw_sp_sb_tc_pool_bind_get, + .sb_tc_pool_bind_set = mlxsw_sp_sb_tc_pool_bind_set, + .sb_occ_snapshot = mlxsw_sp_sb_occ_snapshot, + .sb_occ_max_clear = mlxsw_sp_sb_occ_max_clear, + .sb_occ_port_pool_get = mlxsw_sp_sb_occ_port_pool_get, + .sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get, + .flash_update = mlxsw_sp_flash_update, + .txhdr_construct = mlxsw_sp_txhdr_construct, + .resources_register = mlxsw_sp2_resources_register, + .params_register = mlxsw_sp2_params_register, + .params_unregister = mlxsw_sp2_params_unregister, + .ptp_transmitted = mlxsw_sp_ptp_transmitted, + .txhdr_len = MLXSW_TXHDR_LEN, + .profile = &mlxsw_sp2_config_profile, + .res_query_enabled = true, +}; + bool mlxsw_sp_port_dev_check(const struct net_device *dev) { return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; @@ -6304,6 +6354,16 @@ static struct pci_driver mlxsw_sp2_pci_driver = { .id_table = mlxsw_sp2_pci_id_table, }; +static const struct pci_device_id mlxsw_sp3_pci_id_table[] = { + {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM3), 0}, + {0, }, +}; + +static struct pci_driver mlxsw_sp3_pci_driver = { + .name = mlxsw_sp3_driver_name, + .id_table = mlxsw_sp3_pci_id_table, +}; + static int __init mlxsw_sp_module_init(void) { int err; @@ -6319,6 +6379,10 @@ static int __init mlxsw_sp_module_init(void) if (err) goto err_sp2_core_driver_register; + err = mlxsw_core_driver_register(&mlxsw_sp3_driver); + if (err) + goto err_sp3_core_driver_register; + err = mlxsw_pci_driver_register(&mlxsw_sp1_pci_driver); if (err) goto err_sp1_pci_driver_register; @@ -6327,11 +6391,19 @@ static int __init mlxsw_sp_module_init(void) if (err) goto err_sp2_pci_driver_register; + err = mlxsw_pci_driver_register(&mlxsw_sp3_pci_driver); + if (err) + goto err_sp3_pci_driver_register; + return 0; +err_sp3_pci_driver_register: + mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver); err_sp2_pci_driver_register: mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver); err_sp1_pci_driver_register: + mlxsw_core_driver_unregister(&mlxsw_sp3_driver); +err_sp3_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp2_driver); err_sp2_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp1_driver); @@ -6343,8 +6415,10 @@ err_sp1_core_driver_register: static void __exit mlxsw_sp_module_exit(void) { + mlxsw_pci_driver_unregister(&mlxsw_sp3_pci_driver); mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver); mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver); + mlxsw_core_driver_unregister(&mlxsw_sp3_driver); mlxsw_core_driver_unregister(&mlxsw_sp2_driver); mlxsw_core_driver_unregister(&mlxsw_sp1_driver); unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); @@ -6359,4 +6433,5 @@ MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Spectrum driver"); MODULE_DEVICE_TABLE(pci, mlxsw_sp1_pci_id_table); MODULE_DEVICE_TABLE(pci, mlxsw_sp2_pci_id_table); +MODULE_DEVICE_TABLE(pci, mlxsw_sp3_pci_id_table); MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 6664119fb0c8..db17ba35ec84 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -623,7 +623,8 @@ struct mlxsw_sp_acl_rule_info { unsigned int priority; struct mlxsw_afk_element_values values; struct mlxsw_afa_block *act_block; - u8 action_created:1; + u8 action_created:1, + egress_bind_blocker:1; unsigned int counter_index; }; @@ -642,6 +643,7 @@ struct mlxsw_sp_acl_block { struct mlxsw_sp *mlxsw_sp; unsigned int rule_count; unsigned int disable_count; + unsigned int egress_blocker_rule_count; struct net *net; }; @@ -657,7 +659,8 @@ void mlxsw_sp_acl_block_destroy(struct mlxsw_sp_acl_block *block); int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, - bool ingress); + bool ingress, + struct netlink_ext_ack *extack); int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 84a87d059333..150b3a144b83 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -239,7 +239,8 @@ mlxsw_sp_acl_block_lookup(struct mlxsw_sp_acl_block *block, int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, - bool ingress) + bool ingress, + struct netlink_ext_ack *extack) { struct mlxsw_sp_acl_block_binding *binding; int err; @@ -247,6 +248,11 @@ int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(mlxsw_sp_acl_block_lookup(block, mlxsw_sp_port, ingress))) return -EEXIST; + if (!ingress && block->egress_blocker_rule_count) { + NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to egress because it contains unsupported rules"); + return -EOPNOTSUPP; + } + binding = kzalloc(sizeof(*binding), GFP_KERNEL); if (!binding) return -ENOMEM; @@ -672,6 +678,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + struct mlxsw_sp_acl_block *block = ruleset->ht_key.block; int err; err = ops->rule_add(mlxsw_sp, ruleset->priv, rule->priv, rule->rulei); @@ -689,14 +696,14 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, * one, to be directly bound to device. The rest of the * rulesets are bound by "Goto action set". */ - err = mlxsw_sp_acl_ruleset_block_bind(mlxsw_sp, ruleset, - ruleset->ht_key.block); + err = mlxsw_sp_acl_ruleset_block_bind(mlxsw_sp, ruleset, block); if (err) goto err_ruleset_block_bind; } list_add_tail(&rule->list, &mlxsw_sp->acl->rules); - ruleset->ht_key.block->rule_count++; + block->rule_count++; + block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker; return 0; err_ruleset_block_bind: @@ -712,7 +719,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + struct mlxsw_sp_acl_block *block = ruleset->ht_key.block; + block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker; ruleset->ht_key.block->rule_count--; list_del(&rule->list); if (!ruleset->ht_key.chain_index && diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 202e9a246019..0ad1a24abfc6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -78,6 +78,16 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid; u16 fid_index; + if (mlxsw_sp_acl_block_is_egress_bound(block)) { + NL_SET_ERR_MSG_MOD(extack, "Redirect action is not supported on egress"); + return -EOPNOTSUPP; + } + + /* Forbid block with this rulei to be bound + * to egress in future. + */ + rulei->egress_bind_blocker = 1; + fid = mlxsw_sp_acl_dummy_fid(mlxsw_sp); fid_index = mlxsw_sp_fid_index(fid); err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei, @@ -257,6 +267,12 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp, flow_rule_match_tcp(rule, &match); + if (match.mask->flags & htons(0x0E00)) { + NL_SET_ERR_MSG_MOD(f->common.extack, "TCP flags match not supported on reserved bits"); + dev_err(mlxsw_sp->bus_info->dev, "TCP flags match not supported on reserved bits\n"); + return -EINVAL; + } + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_TCP_FLAGS, ntohs(match.key->flags), ntohs(match.mask->flags)); @@ -390,6 +406,12 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress"); return -EOPNOTSUPP; } + + /* Forbid block with this rulei to be bound + * to egress in future. + */ + rulei->egress_bind_blocker = 1; + if (match.mask->vlan_id != 0) mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VID, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index e618be7ce6c6..a330b369e899 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2943,7 +2943,7 @@ static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) val = nh_grp->count; for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; - val ^= nh->ifindex; + val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed); } return jhash(&val, sizeof(val), seed); default: @@ -2961,7 +2961,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed) list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { dev = mlxsw_sp_rt6->rt->fib6_nh->fib_nh_dev; - val ^= dev->ifindex; + val ^= jhash(&dev->ifindex, sizeof(dev->ifindex), seed); } return jhash(&val, sizeof(val), seed); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 13e6bf13ac4d..15a8be6bad27 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1434,7 +1434,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx, } static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx, - const struct skb_frag_struct *fragment, + const skb_frag_t *fragment, unsigned int frame_length) { /* called only from within lan743x_tx_xmit_frame @@ -1607,9 +1607,8 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, goto finish; for (j = 0; j < nr_frags; j++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &(skb_shinfo(skb)->frags[j]); - frag = &(skb_shinfo(skb)->frags[j]); if (lan743x_tx_frame_add_fragment(tx, frag, frame_length)) { /* upon error no need to call * lan743x_tx_frame_end diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 6932e615d4b0..4d1bce4389c7 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/phy.h> +#include <linux/ptp_clock_kernel.h> #include <linux/skbuff.h> #include <linux/iopoll.h> #include <net/arp.h> @@ -538,7 +539,7 @@ static int ocelot_port_stop(struct net_device *dev) */ static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info) { - ifh[0] = IFH_INJ_BYPASS; + ifh[0] = IFH_INJ_BYPASS | ((0x1ff & info->rew_op) << 21); ifh[1] = (0xf00 & info->port) >> 8; ifh[2] = (0xff & info->port) << 24; ifh[3] = (info->tag_type << 16) | info->vid; @@ -548,6 +549,7 @@ static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info) static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) { + struct skb_shared_info *shinfo = skb_shinfo(skb); struct ocelot_port *port = netdev_priv(dev); struct ocelot *ocelot = port->ocelot; u32 val, ifh[IFH_LEN]; @@ -566,6 +568,14 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) info.port = BIT(port->chip_port); info.tag_type = IFH_TAG_TYPE_C; info.vid = skb_vlan_tag_get(skb); + + /* Check if timestamping is needed */ + if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP) { + info.rew_op = port->ptp_cmd; + if (port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + info.rew_op |= (port->ts_id % 4) << 3; + } + ocelot_gen_ifh(ifh, &info); for (i = 0; i < IFH_LEN; i++) @@ -596,11 +606,58 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - dev_kfree_skb_any(skb); + if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP && + port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { + struct ocelot_skb *oskb = + kzalloc(sizeof(struct ocelot_skb), GFP_ATOMIC); + + if (unlikely(!oskb)) + goto out; + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + oskb->skb = skb; + oskb->id = port->ts_id % 4; + port->ts_id++; + + list_add_tail(&oskb->head, &port->skbs); + + return NETDEV_TX_OK; + } + +out: + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } +void ocelot_get_hwtimestamp(struct ocelot *ocelot, struct timespec64 *ts) +{ + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + /* Read current PTP time to get seconds */ + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE); + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + ts->tv_sec = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + + /* Read packet HW timestamp from FIFO */ + val = ocelot_read(ocelot, SYS_PTP_TXSTAMP); + ts->tv_nsec = SYS_PTP_TXSTAMP_PTP_TXSTAMP(val); + + /* Sec has incremented since the ts was registered */ + if ((ts->tv_sec & 0x1) != !!(val & SYS_PTP_TXSTAMP_PTP_TXSTAMP_SEC)) + ts->tv_sec--; + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); +} +EXPORT_SYMBOL(ocelot_get_hwtimestamp); + static int ocelot_mc_unsync(struct net_device *dev, const unsigned char *addr) { struct ocelot_port *port = netdev_priv(dev); @@ -917,6 +974,97 @@ static int ocelot_get_port_parent_id(struct net_device *dev, return 0; } +static int ocelot_hwstamp_get(struct ocelot_port *port, struct ifreq *ifr) +{ + struct ocelot *ocelot = port->ocelot; + + return copy_to_user(ifr->ifr_data, &ocelot->hwtstamp_config, + sizeof(ocelot->hwtstamp_config)) ? -EFAULT : 0; +} + +static int ocelot_hwstamp_set(struct ocelot_port *port, struct ifreq *ifr) +{ + struct ocelot *ocelot = port->ocelot; + struct hwtstamp_config cfg; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + /* reserved for future extensions */ + if (cfg.flags) + return -EINVAL; + + /* Tx type sanity check */ + switch (cfg.tx_type) { + case HWTSTAMP_TX_ON: + port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; + break; + case HWTSTAMP_TX_ONESTEP_SYNC: + /* IFH_REW_OP_ONE_STEP_PTP updates the correctional field, we + * need to update the origin time. + */ + port->ptp_cmd = IFH_REW_OP_ORIGIN_PTP; + break; + case HWTSTAMP_TX_OFF: + port->ptp_cmd = 0; + break; + default: + return -ERANGE; + } + + mutex_lock(&ocelot->ptp_lock); + + switch (cfg.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + 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: + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + default: + mutex_unlock(&ocelot->ptp_lock); + return -ERANGE; + } + + /* Commit back the result & save it */ + memcpy(&ocelot->hwtstamp_config, &cfg, sizeof(cfg)); + mutex_unlock(&ocelot->ptp_lock); + + return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; +} + +static int ocelot_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct ocelot_port *port = netdev_priv(dev); + struct ocelot *ocelot = port->ocelot; + + /* The function is only used for PTP operations for now */ + if (!ocelot->ptp) + return -EOPNOTSUPP; + + switch (cmd) { + case SIOCSHWTSTAMP: + return ocelot_hwstamp_set(port, ifr); + case SIOCGHWTSTAMP: + return ocelot_hwstamp_get(port, ifr); + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_open = ocelot_port_open, .ndo_stop = ocelot_port_stop, @@ -933,6 +1081,7 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_set_features = ocelot_set_features, .ndo_get_port_parent_id = ocelot_get_port_parent_id, .ndo_setup_tc = ocelot_setup_tc, + .ndo_do_ioctl = ocelot_ioctl, }; static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data) @@ -1014,12 +1163,37 @@ static int ocelot_get_sset_count(struct net_device *dev, int sset) return ocelot->num_stats; } +static int ocelot_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct ocelot_port *ocelot_port = netdev_priv(dev); + struct ocelot *ocelot = ocelot_port->ocelot; + + if (!ocelot->ptp) + return ethtool_op_get_ts_info(dev, info); + + info->phc_index = ocelot->ptp_clock ? + ptp_clock_index(ocelot->ptp_clock) : -1; + info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | + BIT(HWTSTAMP_TX_ONESTEP_SYNC); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + static const struct ethtool_ops ocelot_ethtool_ops = { .get_strings = ocelot_get_strings, .get_ethtool_stats = ocelot_get_ethtool_stats, .get_sset_count = ocelot_get_sset_count, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, + .get_ts_info = ocelot_get_ts_info, }; static int ocelot_port_attr_stp_state_set(struct ocelot_port *ocelot_port, @@ -1629,6 +1803,196 @@ struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = { }; EXPORT_SYMBOL(ocelot_switchdev_blocking_nb); +int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + time64_t s; + u32 val; + s64 ns; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE); + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + s = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN) & 0xffff; + s <<= 32; + s += ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + ns = ocelot_read_rix(ocelot, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + + /* Deal with negative values */ + if (ns >= 0x3ffffff0 && ns <= 0x3fffffff) { + s--; + ns &= 0xf; + ns += 999999984; + } + + set_normalized_timespec64(ts, s, ns); + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_gettime64); + +static int ocelot_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + ocelot_write_rix(ocelot, lower_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_LSB, + TOD_ACC_PIN); + ocelot_write_rix(ocelot, upper_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_MSB, + TOD_ACC_PIN); + ocelot_write_rix(ocelot, ts->tv_nsec, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_LOAD); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; +} + +static int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) { + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN); + ocelot_write_rix(ocelot, delta, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_DELTA); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + } else { + /* Fall back using ocelot_ptp_settime64 which is not exact. */ + struct timespec64 ts; + u64 now; + + ocelot_ptp_gettime64(ptp, &ts); + + now = ktime_to_ns(timespec64_to_ktime(ts)); + ts = ns_to_timespec64(now + delta); + + ocelot_ptp_settime64(ptp, &ts); + } + return 0; +} + +static int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + u32 unit = 0, direction = 0; + unsigned long flags; + u64 adj = 0; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + if (!scaled_ppm) + goto disable_adj; + + if (scaled_ppm < 0) { + direction = PTP_CFG_CLK_ADJ_CFG_DIR; + scaled_ppm = -scaled_ppm; + } + + adj = PSEC_PER_SEC << 16; + do_div(adj, scaled_ppm); + do_div(adj, 1000); + + /* If the adjustment value is too large, use ns instead */ + if (adj >= (1L << 30)) { + unit = PTP_CFG_CLK_ADJ_FREQ_NS; + do_div(adj, 1000); + } + + /* Still too big */ + if (adj >= (1L << 30)) + goto disable_adj; + + ocelot_write(ocelot, unit | adj, PTP_CLK_CFG_ADJ_FREQ); + ocelot_write(ocelot, PTP_CFG_CLK_ADJ_CFG_ENA | direction, + PTP_CLK_CFG_ADJ_CFG); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; + +disable_adj: + ocelot_write(ocelot, 0, PTP_CLK_CFG_ADJ_CFG); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; +} + +static struct ptp_clock_info ocelot_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "ocelot ptp", + .max_adj = 0x7fffffff, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .n_pins = 0, + .pps = 0, + .gettime64 = ocelot_ptp_gettime64, + .settime64 = ocelot_ptp_settime64, + .adjtime = ocelot_ptp_adjtime, + .adjfine = ocelot_ptp_adjfine, +}; + +static int ocelot_init_timestamp(struct ocelot *ocelot) +{ + ocelot->ptp_info = ocelot_ptp_clock_info; + ocelot->ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev); + if (IS_ERR(ocelot->ptp_clock)) + return PTR_ERR(ocelot->ptp_clock); + /* Check if PHC support is missing at the configuration level */ + if (!ocelot->ptp_clock) + return 0; + + ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG); + ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW); + ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH); + + ocelot_write(ocelot, PTP_CFG_MISC_PTP_EN, PTP_CFG_MISC); + + /* There is no device reconfiguration, PTP Rx stamping is always + * enabled. + */ + ocelot->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + + return 0; +} + int ocelot_probe_port(struct ocelot *ocelot, u8 port, void __iomem *regs, struct phy_device *phy) @@ -1661,6 +2025,8 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port, ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid, ENTRYTYPE_LOCKED); + INIT_LIST_HEAD(&ocelot_port->skbs); + err = register_netdev(dev); if (err) { dev_err(ocelot->dev, "register_netdev failed\n"); @@ -1684,7 +2050,7 @@ EXPORT_SYMBOL(ocelot_probe_port); int ocelot_init(struct ocelot *ocelot) { u32 port; - int i, cpu = ocelot->num_phys_ports; + int i, ret, cpu = ocelot->num_phys_ports; char queue_name[32]; ocelot->lags = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports, @@ -1699,6 +2065,8 @@ int ocelot_init(struct ocelot *ocelot) return -ENOMEM; mutex_init(&ocelot->stats_lock); + mutex_init(&ocelot->ptp_lock); + spin_lock_init(&ocelot->ptp_clock_lock); snprintf(queue_name, sizeof(queue_name), "%s-stats", dev_name(ocelot->dev)); ocelot->stats_queue = create_singlethread_workqueue(queue_name); @@ -1812,16 +2180,43 @@ int ocelot_init(struct ocelot *ocelot) INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work); queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); + + if (ocelot->ptp) { + ret = ocelot_init_timestamp(ocelot); + if (ret) { + dev_err(ocelot->dev, + "Timestamp initialization failed\n"); + return ret; + } + } + return 0; } EXPORT_SYMBOL(ocelot_init); void ocelot_deinit(struct ocelot *ocelot) { + struct list_head *pos, *tmp; + struct ocelot_port *port; + struct ocelot_skb *entry; + int i; + cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); ocelot_ace_deinit(); + + for (i = 0; i < ocelot->num_phys_ports; i++) { + port = ocelot->ports[i]; + + list_for_each_safe(pos, tmp, &port->skbs) { + entry = list_entry(pos, struct ocelot_skb, head); + + list_del(pos); + dev_kfree_skb_any(entry->skb); + kfree(entry); + } + } } EXPORT_SYMBOL(ocelot_deinit); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index f7eeb4806897..e40773c01a44 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -11,9 +11,11 @@ #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> +#include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/ptp_clock_kernel.h> #include <linux/regmap.h> #include "ocelot_ana.h" @@ -23,6 +25,7 @@ #include "ocelot_sys.h" #include "ocelot_qs.h" #include "ocelot_tc.h" +#include "ocelot_ptp.h" #define PGID_AGGR 64 #define PGID_SRC 80 @@ -38,14 +41,17 @@ #define OCELOT_STATS_CHECK_DELAY (2 * HZ) +#define OCELOT_PTP_QUEUE_SZ 128 + #define IFH_LEN 4 struct frame_info { u32 len; u16 port; u16 vid; - u8 cpuq; u8 tag_type; + u16 rew_op; + u32 timestamp; /* rew_val */ }; #define IFH_INJ_BYPASS BIT(31) @@ -54,6 +60,12 @@ struct frame_info { #define IFH_TAG_TYPE_C 0 #define IFH_TAG_TYPE_S 1 +#define IFH_REW_OP_NOOP 0x0 +#define IFH_REW_OP_DSCP 0x1 +#define IFH_REW_OP_ONE_STEP_PTP 0x2 +#define IFH_REW_OP_TWO_STEP_PTP 0x3 +#define IFH_REW_OP_ORIGIN_PTP 0x5 + #define OCELOT_SPEED_2500 0 #define OCELOT_SPEED_1000 1 #define OCELOT_SPEED_100 2 @@ -71,6 +83,7 @@ enum ocelot_target { SYS, S2, HSIO, + PTP, TARGET_MAX, }; @@ -343,6 +356,13 @@ enum ocelot_reg { S2_CACHE_ACTION_DAT, S2_CACHE_CNT_DAT, S2_CACHE_TG_DAT, + PTP_PIN_CFG = PTP << TARGET_OFFSET, + PTP_PIN_TOD_SEC_MSB, + PTP_PIN_TOD_SEC_LSB, + PTP_PIN_TOD_NSEC, + PTP_CFG_MISC, + PTP_CLK_CFG_ADJ_CFG, + PTP_CLK_CFG_ADJ_FREQ, }; enum ocelot_regfield { @@ -393,6 +413,13 @@ enum ocelot_regfield { REGFIELD_MAX }; +enum ocelot_clk_pins { + ALT_PPS_PIN = 1, + EXT_CLK_PIN, + ALT_LDST_PIN, + TOD_ACC_PIN +}; + struct ocelot_multicast { struct list_head list; unsigned char addr[ETH_ALEN]; @@ -442,6 +469,13 @@ struct ocelot { u64 *stats; struct delayed_work stats_work; struct workqueue_struct *stats_queue; + + u8 ptp:1; + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_info; + struct hwtstamp_config hwtstamp_config; + struct mutex ptp_lock; /* Protects the PTP interface state */ + spinlock_t ptp_clock_lock; /* Protects the PTP clock */ }; struct ocelot_port { @@ -465,6 +499,16 @@ struct ocelot_port { struct phy *serdes; struct ocelot_port_tc tc; + + u8 ptp_cmd; + struct list_head skbs; + u8 ts_id; +}; + +struct ocelot_skb { + struct list_head head; + struct sk_buff *skb; + u8 id; }; u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset); @@ -509,4 +553,7 @@ extern struct notifier_block ocelot_netdevice_nb; extern struct notifier_block ocelot_switchdev_nb; extern struct notifier_block ocelot_switchdev_blocking_nb; +int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); +void ocelot_get_hwtimestamp(struct ocelot *ocelot, struct timespec64 *ts); + #endif diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 2451d4a96490..b063eb78fa0c 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -16,24 +16,27 @@ #include "ocelot.h" -static int ocelot_parse_ifh(u32 *ifh, struct frame_info *info) +#define IFH_EXTRACT_BITFIELD64(x, o, w) (((x) >> (o)) & GENMASK_ULL((w) - 1, 0)) + +static int ocelot_parse_ifh(u32 *_ifh, struct frame_info *info) { - int i; u8 llen, wlen; + u64 ifh[2]; + + ifh[0] = be64_to_cpu(((__force __be64 *)_ifh)[0]); + ifh[1] = be64_to_cpu(((__force __be64 *)_ifh)[1]); - /* The IFH is in network order, switch to CPU order */ - for (i = 0; i < IFH_LEN; i++) - ifh[i] = ntohl((__force __be32)ifh[i]); + wlen = IFH_EXTRACT_BITFIELD64(ifh[0], 7, 8); + llen = IFH_EXTRACT_BITFIELD64(ifh[0], 15, 6); - wlen = (ifh[1] >> 7) & 0xff; - llen = (ifh[1] >> 15) & 0x3f; info->len = OCELOT_BUFFER_CELL_SZ * wlen + llen - 80; - info->port = (ifh[2] & GENMASK(14, 11)) >> 11; + info->timestamp = IFH_EXTRACT_BITFIELD64(ifh[0], 21, 32); + + info->port = IFH_EXTRACT_BITFIELD64(ifh[1], 43, 4); - info->cpuq = (ifh[3] & GENMASK(27, 20)) >> 20; - info->tag_type = (ifh[3] & BIT(16)) >> 16; - info->vid = ifh[3] & GENMASK(11, 0); + info->tag_type = IFH_EXTRACT_BITFIELD64(ifh[1], 16, 1); + info->vid = IFH_EXTRACT_BITFIELD64(ifh[1], 0, 12); return 0; } @@ -91,13 +94,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) return IRQ_NONE; do { - struct sk_buff *skb; + struct skb_shared_hwtstamps *shhwtstamps; + u64 tod_in_ns, full_ts_in_ns; + struct frame_info info = {}; struct net_device *dev; - u32 *buf; + u32 ifh[4], val, *buf; + struct timespec64 ts; int sz, len, buf_len; - u32 ifh[4]; - u32 val; - struct frame_info info; + struct sk_buff *skb; for (i = 0; i < IFH_LEN; i++) { err = ocelot_rx_frame_word(ocelot, grp, true, &ifh[i]); @@ -144,6 +148,22 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) break; } + if (ocelot->ptp) { + ocelot_ptp_gettime64(&ocelot->ptp_info, &ts); + + tod_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec); + if ((tod_in_ns & 0xffffffff) < info.timestamp) + full_ts_in_ns = (((tod_in_ns >> 32) - 1) << 32) | + info.timestamp; + else + full_ts_in_ns = (tod_in_ns & GENMASK_ULL(63, 32)) | + info.timestamp; + + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamps->hwtstamp = full_ts_in_ns; + } + /* Everything we see on an interface that is in the HW bridge * has already been forwarded. */ @@ -163,6 +183,66 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) return IRQ_HANDLED; } +static irqreturn_t ocelot_ptp_rdy_irq_handler(int irq, void *arg) +{ + int budget = OCELOT_PTP_QUEUE_SZ; + struct ocelot *ocelot = arg; + + while (budget--) { + struct skb_shared_hwtstamps shhwtstamps; + struct list_head *pos, *tmp; + struct sk_buff *skb = NULL; + struct ocelot_skb *entry; + struct ocelot_port *port; + struct timespec64 ts; + u32 val, id, txport; + + val = ocelot_read(ocelot, SYS_PTP_STATUS); + + /* Check if a timestamp can be retrieved */ + if (!(val & SYS_PTP_STATUS_PTP_MESS_VLD)) + break; + + WARN_ON(val & SYS_PTP_STATUS_PTP_OVFL); + + /* Retrieve the ts ID and Tx port */ + id = SYS_PTP_STATUS_PTP_MESS_ID_X(val); + txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val); + + /* Retrieve its associated skb */ + port = ocelot->ports[txport]; + + list_for_each_safe(pos, tmp, &port->skbs) { + entry = list_entry(pos, struct ocelot_skb, head); + if (entry->id != id) + continue; + + skb = entry->skb; + + list_del(pos); + kfree(entry); + } + + /* Next ts */ + ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); + + if (unlikely(!skb)) + continue; + + /* Get the h/w timestamp */ + ocelot_get_hwtimestamp(ocelot, &ts); + + /* Set the timestamp into the skb */ + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); + skb_tstamp_tx(skb, &shhwtstamps); + + dev_kfree_skb_any(skb); + } + + return IRQ_HANDLED; +} + static const struct of_device_id mscc_ocelot_match[] = { { .compatible = "mscc,vsc7514-switch" }, { } @@ -171,17 +251,18 @@ MODULE_DEVICE_TABLE(of, mscc_ocelot_match); static int mscc_ocelot_probe(struct platform_device *pdev) { - int err, irq; - unsigned int i; struct device_node *np = pdev->dev.of_node; struct device_node *ports, *portnp; + int err, irq_xtr, irq_ptp_rdy; struct ocelot *ocelot; struct regmap *hsio; + unsigned int i; u32 val; struct { enum ocelot_target id; char *name; + u8 optional:1; } res[] = { { SYS, "sys" }, { REW, "rew" }, @@ -189,6 +270,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) { ANA, "ana" }, { QS, "qs" }, { S2, "s2" }, + { PTP, "ptp", 1 }, }; if (!np && !pdev->dev.platform_data) @@ -205,8 +287,14 @@ static int mscc_ocelot_probe(struct platform_device *pdev) struct regmap *target; target = ocelot_io_platform_init(ocelot, pdev, res[i].name); - if (IS_ERR(target)) + if (IS_ERR(target)) { + if (res[i].optional) { + ocelot->targets[res[i].id] = NULL; + continue; + } + return PTR_ERR(target); + } ocelot->targets[res[i].id] = target; } @@ -223,16 +311,29 @@ static int mscc_ocelot_probe(struct platform_device *pdev) if (err) return err; - irq = platform_get_irq_byname(pdev, "xtr"); - if (irq < 0) + irq_xtr = platform_get_irq_byname(pdev, "xtr"); + if (irq_xtr < 0) return -ENODEV; - err = devm_request_threaded_irq(&pdev->dev, irq, NULL, + err = devm_request_threaded_irq(&pdev->dev, irq_xtr, NULL, ocelot_xtr_irq_handler, IRQF_ONESHOT, "frame extraction", ocelot); if (err) return err; + irq_ptp_rdy = platform_get_irq_byname(pdev, "ptp_rdy"); + if (irq_ptp_rdy > 0 && ocelot->targets[PTP]) { + err = devm_request_threaded_irq(&pdev->dev, irq_ptp_rdy, NULL, + ocelot_ptp_rdy_irq_handler, + IRQF_ONESHOT, "ptp ready", + ocelot); + if (err) + return err; + + /* Both the PTP interrupt and the PTP bank are available */ + ocelot->ptp = 1; + } + regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], 1); regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1); diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.h b/drivers/net/ethernet/mscc/ocelot_ptp.h new file mode 100644 index 000000000000..9ede14a12573 --- /dev/null +++ b/drivers/net/ethernet/mscc/ocelot_ptp.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Microsemi Ocelot Switch driver + * + * License: Dual MIT/GPL + * Copyright (c) 2017 Microsemi Corporation + */ + +#ifndef _MSCC_OCELOT_PTP_H_ +#define _MSCC_OCELOT_PTP_H_ + +#define PTP_PIN_CFG_RSZ 0x20 +#define PTP_PIN_TOD_SEC_MSB_RSZ PTP_PIN_CFG_RSZ +#define PTP_PIN_TOD_SEC_LSB_RSZ PTP_PIN_CFG_RSZ +#define PTP_PIN_TOD_NSEC_RSZ PTP_PIN_CFG_RSZ + +#define PTP_PIN_CFG_DOM BIT(0) +#define PTP_PIN_CFG_SYNC BIT(2) +#define PTP_PIN_CFG_ACTION(x) ((x) << 3) +#define PTP_PIN_CFG_ACTION_MASK PTP_PIN_CFG_ACTION(0x7) + +enum { + PTP_PIN_ACTION_IDLE = 0, + PTP_PIN_ACTION_LOAD, + PTP_PIN_ACTION_SAVE, + PTP_PIN_ACTION_CLOCK, + PTP_PIN_ACTION_DELTA, + PTP_PIN_ACTION_NOSYNC, + PTP_PIN_ACTION_SYNC, +}; + +#define PTP_CFG_MISC_PTP_EN BIT(2) + +#define PSEC_PER_SEC 1000000000000LL + +#define PTP_CFG_CLK_ADJ_CFG_ENA BIT(0) +#define PTP_CFG_CLK_ADJ_CFG_DIR BIT(1) + +#define PTP_CFG_CLK_ADJ_FREQ_NS BIT(30) + +#endif diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index 6c387f994ec5..e59977d20400 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -234,6 +234,16 @@ static const u32 ocelot_s2_regmap[] = { REG(S2_CACHE_TG_DAT, 0x000388), }; +static const u32 ocelot_ptp_regmap[] = { + REG(PTP_PIN_CFG, 0x000000), + REG(PTP_PIN_TOD_SEC_MSB, 0x000004), + REG(PTP_PIN_TOD_SEC_LSB, 0x000008), + REG(PTP_PIN_TOD_NSEC, 0x00000c), + REG(PTP_CFG_MISC, 0x0000a0), + REG(PTP_CLK_CFG_ADJ_CFG, 0x0000a4), + REG(PTP_CLK_CFG_ADJ_FREQ, 0x0000a8), +}; + static const u32 *ocelot_regmap[] = { [ANA] = ocelot_ana_regmap, [QS] = ocelot_qs_regmap, @@ -241,6 +251,7 @@ static const u32 *ocelot_regmap[] = { [REW] = ocelot_rew_regmap, [SYS] = ocelot_sys_regmap, [S2] = ocelot_s2_regmap, + [PTP] = ocelot_ptp_regmap, }; static const struct reg_field ocelot_regfields[] = { diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 337b0cbfd153..c979f38a2e0c 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1286,7 +1286,7 @@ myri10ge_vlan_rx(struct net_device *dev, void *addr, struct sk_buff *skb) { u8 *va; struct vlan_ethhdr *veh; - struct skb_frag_struct *frag; + skb_frag_t *frag; __wsum vsum; va = addr; @@ -1306,8 +1306,8 @@ myri10ge_vlan_rx(struct net_device *dev, void *addr, struct sk_buff *skb) skb->len -= VLAN_HLEN; skb->data_len -= VLAN_HLEN; frag = skb_shinfo(skb)->frags; - frag->page_offset += VLAN_HLEN; - skb_frag_size_set(frag, skb_frag_size(frag) - VLAN_HLEN); + skb_frag_off_add(frag, VLAN_HLEN); + skb_frag_size_sub(frag, VLAN_HLEN); } } @@ -1318,7 +1318,7 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) { struct myri10ge_priv *mgp = ss->mgp; struct sk_buff *skb; - struct skb_frag_struct *rx_frags; + skb_frag_t *rx_frags; struct myri10ge_rx_buf *rx; int i, idx, remainder, bytes; struct pci_dev *pdev = mgp->pdev; @@ -1351,7 +1351,7 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) return 0; } rx_frags = skb_shinfo(skb)->frags; - /* Fill skb_frag_struct(s) with data from our receive */ + /* Fill skb_frag_t(s) with data from our receive */ for (i = 0, remainder = len; remainder > 0; i++) { myri10ge_unmap_rx_page(pdev, &rx->info[idx], bytes); skb_fill_page_desc(skb, i, rx->info[idx].page, @@ -1364,8 +1364,8 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) } /* remove padding */ - rx_frags[0].page_offset += MXGEFW_PAD; - rx_frags[0].size -= MXGEFW_PAD; + skb_frag_off_add(&rx_frags[0], MXGEFW_PAD); + skb_frag_size_sub(&rx_frags[0], MXGEFW_PAD); len -= MXGEFW_PAD; skb->len = len; @@ -2628,7 +2628,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb, struct myri10ge_slice_state *ss; struct mcp_kreq_ether_send *req; struct myri10ge_tx_buf *tx; - struct skb_frag_struct *frag; + skb_frag_t *frag; struct netdev_queue *netdev_queue; dma_addr_t bus; u32 low; @@ -3037,7 +3037,6 @@ static int myri10ge_set_mac_address(struct net_device *dev, void *addr) static int myri10ge_change_mtu(struct net_device *dev, int new_mtu) { struct myri10ge_priv *mgp = netdev_priv(dev); - int error = 0; netdev_info(dev, "changing mtu from %d to %d\n", dev->mtu, new_mtu); if (mgp->running) { @@ -3049,7 +3048,7 @@ static int myri10ge_change_mtu(struct net_device *dev, int new_mtu) } else dev->mtu = new_mtu; - return error; + return 0; } /* diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 5a54fe848de4..1b019fdfcd97 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -2,10 +2,12 @@ /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ #include <linux/bitfield.h> +#include <linux/mpls.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_csum.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_mpls.h> #include <net/tc_act/tc_pedit.h> #include <net/tc_act/tc_vlan.h> #include <net/tc_act/tc_tunnel_key.h> @@ -25,6 +27,80 @@ NFP_FL_TUNNEL_KEY | \ NFP_FL_TUNNEL_GENEVE_OPT) +static int +nfp_fl_push_mpls(struct nfp_fl_push_mpls *push_mpls, + const struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + size_t act_size = sizeof(struct nfp_fl_push_mpls); + u32 mpls_lse = 0; + + push_mpls->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_MPLS; + push_mpls->head.len_lw = act_size >> NFP_FL_LW_SIZ; + + /* BOS is optional in the TC action but required for offload. */ + if (act->mpls_push.bos != ACT_MPLS_BOS_NOT_SET) { + mpls_lse |= act->mpls_push.bos << MPLS_LS_S_SHIFT; + } else { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: BOS field must explicitly be set for MPLS push"); + return -EOPNOTSUPP; + } + + /* Leave MPLS TC as a default value of 0 if not explicitly set. */ + if (act->mpls_push.tc != ACT_MPLS_TC_NOT_SET) + mpls_lse |= act->mpls_push.tc << MPLS_LS_TC_SHIFT; + + /* Proto, label and TTL are enforced and verified for MPLS push. */ + mpls_lse |= act->mpls_push.label << MPLS_LS_LABEL_SHIFT; + mpls_lse |= act->mpls_push.ttl << MPLS_LS_TTL_SHIFT; + push_mpls->ethtype = act->mpls_push.proto; + push_mpls->lse = cpu_to_be32(mpls_lse); + + return 0; +} + +static void +nfp_fl_pop_mpls(struct nfp_fl_pop_mpls *pop_mpls, + const struct flow_action_entry *act) +{ + size_t act_size = sizeof(struct nfp_fl_pop_mpls); + + pop_mpls->head.jump_id = NFP_FL_ACTION_OPCODE_POP_MPLS; + pop_mpls->head.len_lw = act_size >> NFP_FL_LW_SIZ; + pop_mpls->ethtype = act->mpls_pop.proto; +} + +static void +nfp_fl_set_mpls(struct nfp_fl_set_mpls *set_mpls, + const struct flow_action_entry *act) +{ + size_t act_size = sizeof(struct nfp_fl_set_mpls); + u32 mpls_lse = 0, mpls_mask = 0; + + set_mpls->head.jump_id = NFP_FL_ACTION_OPCODE_SET_MPLS; + set_mpls->head.len_lw = act_size >> NFP_FL_LW_SIZ; + + if (act->mpls_mangle.label != ACT_MPLS_LABEL_NOT_SET) { + mpls_lse |= act->mpls_mangle.label << MPLS_LS_LABEL_SHIFT; + mpls_mask |= MPLS_LS_LABEL_MASK; + } + if (act->mpls_mangle.tc != ACT_MPLS_TC_NOT_SET) { + mpls_lse |= act->mpls_mangle.tc << MPLS_LS_TC_SHIFT; + mpls_mask |= MPLS_LS_TC_MASK; + } + if (act->mpls_mangle.bos != ACT_MPLS_BOS_NOT_SET) { + mpls_lse |= act->mpls_mangle.bos << MPLS_LS_S_SHIFT; + mpls_mask |= MPLS_LS_S_MASK; + } + if (act->mpls_mangle.ttl) { + mpls_lse |= act->mpls_mangle.ttl << MPLS_LS_TTL_SHIFT; + mpls_mask |= MPLS_LS_TTL_MASK; + } + + set_mpls->lse = cpu_to_be32(mpls_lse); + set_mpls->lse_mask = cpu_to_be32(mpls_mask); +} + static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan) { size_t act_size = sizeof(struct nfp_fl_pop_vlan); @@ -97,7 +173,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, struct nfp_fl_payload *nfp_flow, bool last, struct net_device *in_dev, enum nfp_flower_tun_type tun_type, int *tun_out_cnt, - struct netlink_ext_ack *extack) + bool pkt_host, struct netlink_ext_ack *extack) { size_t act_size = sizeof(struct nfp_fl_output); struct nfp_flower_priv *priv = app->priv; @@ -142,6 +218,20 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, return gid; } output->port = cpu_to_be32(NFP_FL_LAG_OUT | gid); + } else if (nfp_flower_internal_port_can_offload(app, out_dev)) { + if (!(priv->flower_ext_feats & NFP_FL_FEATS_PRE_TUN_RULES)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules not supported in loaded firmware"); + return -EOPNOTSUPP; + } + + if (nfp_flow->pre_tun_rule.dev || !pkt_host) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules require single egress dev and ptype HOST action"); + return -EOPNOTSUPP; + } + + nfp_flow->pre_tun_rule.dev = out_dev; + + return 0; } else { /* Set action output parameters. */ output->flags = cpu_to_be16(tmp_flags); @@ -809,7 +899,7 @@ nfp_flower_output_action(struct nfp_app *app, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, bool last, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, - int *out_cnt, u32 *csum_updated, + int *out_cnt, u32 *csum_updated, bool pkt_host, struct netlink_ext_ack *extack) { struct nfp_flower_priv *priv = app->priv; @@ -831,7 +921,7 @@ nfp_flower_output_action(struct nfp_app *app, output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len]; err = nfp_fl_output(app, output, act, nfp_fl, last, netdev, *tun_type, - tun_out_cnt, extack); + tun_out_cnt, pkt_host, extack); if (err) return err; @@ -863,30 +953,37 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, struct net_device *netdev, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, int *out_cnt, u32 *csum_updated, - struct nfp_flower_pedit_acts *set_act, + struct nfp_flower_pedit_acts *set_act, bool *pkt_host, struct netlink_ext_ack *extack, int act_idx) { struct nfp_fl_set_ipv4_tun *set_tun; struct nfp_fl_pre_tunnel *pre_tun; struct nfp_fl_push_vlan *psh_v; + struct nfp_fl_push_mpls *psh_m; struct nfp_fl_pop_vlan *pop_v; + struct nfp_fl_pop_mpls *pop_m; + struct nfp_fl_set_mpls *set_m; int err; switch (act->id) { case FLOW_ACTION_DROP: nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_DROP); break; + case FLOW_ACTION_REDIRECT_INGRESS: case FLOW_ACTION_REDIRECT: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, true, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; + case FLOW_ACTION_MIRRED_INGRESS: case FLOW_ACTION_MIRRED: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, false, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; @@ -975,6 +1072,54 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, */ *csum_updated &= ~act->csum_flags; break; + case FLOW_ACTION_MPLS_PUSH: + if (*a_len + + sizeof(struct nfp_fl_push_mpls) > NFP_FL_MAX_A_SIZ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at push MPLS"); + return -EOPNOTSUPP; + } + + psh_m = (struct nfp_fl_push_mpls *)&nfp_fl->action_data[*a_len]; + nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); + + err = nfp_fl_push_mpls(psh_m, act, extack); + if (err) + return err; + *a_len += sizeof(struct nfp_fl_push_mpls); + break; + case FLOW_ACTION_MPLS_POP: + if (*a_len + + sizeof(struct nfp_fl_pop_mpls) > NFP_FL_MAX_A_SIZ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at pop MPLS"); + return -EOPNOTSUPP; + } + + pop_m = (struct nfp_fl_pop_mpls *)&nfp_fl->action_data[*a_len]; + nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); + + nfp_fl_pop_mpls(pop_m, act); + *a_len += sizeof(struct nfp_fl_pop_mpls); + break; + case FLOW_ACTION_MPLS_MANGLE: + if (*a_len + + sizeof(struct nfp_fl_set_mpls) > NFP_FL_MAX_A_SIZ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at set MPLS"); + return -EOPNOTSUPP; + } + + set_m = (struct nfp_fl_set_mpls *)&nfp_fl->action_data[*a_len]; + nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); + + nfp_fl_set_mpls(set_m, act); + *a_len += sizeof(struct nfp_fl_set_mpls); + break; + case FLOW_ACTION_PTYPE: + /* TC ptype skbedit sets PACKET_HOST for ingress redirect. */ + if (act->ptype != PACKET_HOST) + return -EOPNOTSUPP; + + *pkt_host = true; + break; default: /* Currently we do not handle any other actions. */ NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported action in action list"); @@ -1030,6 +1175,7 @@ int nfp_flower_compile_action(struct nfp_app *app, struct nfp_flower_pedit_acts set_act; enum nfp_flower_tun_type tun_type; struct flow_action_entry *act; + bool pkt_host = false; u32 csum_updated = 0; memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); @@ -1046,7 +1192,7 @@ int nfp_flower_compile_action(struct nfp_app *app, err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len, netdev, &tun_type, &tun_out_cnt, &out_cnt, &csum_updated, - &set_act, extack, i); + &set_act, &pkt_host, extack, i); if (err) return err; act_cnt++; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 0f1706ae5bfc..7eb2ec8969c3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -68,8 +68,11 @@ #define NFP_FL_ACTION_OPCODE_OUTPUT 0 #define NFP_FL_ACTION_OPCODE_PUSH_VLAN 1 #define NFP_FL_ACTION_OPCODE_POP_VLAN 2 +#define NFP_FL_ACTION_OPCODE_PUSH_MPLS 3 +#define NFP_FL_ACTION_OPCODE_POP_MPLS 4 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL 6 #define NFP_FL_ACTION_OPCODE_SET_ETHERNET 7 +#define NFP_FL_ACTION_OPCODE_SET_MPLS 8 #define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS 9 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS 10 #define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC 11 @@ -217,7 +220,8 @@ struct nfp_fl_set_ipv4_tun { __be16 tun_flags; u8 ttl; u8 tos; - __be32 extra; + __be16 outer_vlan_tpid; + __be16 outer_vlan_tci; u8 tun_len; u8 res2; __be16 tun_proto; @@ -232,6 +236,24 @@ struct nfp_fl_push_geneve { u8 opt_data[]; }; +struct nfp_fl_push_mpls { + struct nfp_fl_act_head head; + __be16 ethtype; + __be32 lse; +}; + +struct nfp_fl_pop_mpls { + struct nfp_fl_act_head head; + __be16 ethtype; +}; + +struct nfp_fl_set_mpls { + struct nfp_fl_act_head head; + __be16 reserved; + __be32 lse_mask; + __be32 lse; +}; + /* Metadata with L2 (1W/4B) * ---------------------------------------------------------------- * 3 2 1 @@ -462,6 +484,7 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_QOS_MOD = 18, NFP_FLOWER_CMSG_TYPE_QOS_DEL = 19, NFP_FLOWER_CMSG_TYPE_QOS_STATS = 20, + NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE = 21, NFP_FLOWER_CMSG_TYPE_MAX = 32, }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index eb846133943b..7a20447cca19 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -781,6 +781,7 @@ static int nfp_flower_init(struct nfp_app *app) INIT_LIST_HEAD(&app_priv->indr_block_cb_priv); INIT_LIST_HEAD(&app_priv->non_repr_priv); + app_priv->pre_tun_rule_cnt = 0; return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index af9441d5787f..31d94592a7c0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -42,6 +42,7 @@ struct nfp_app; #define NFP_FL_FEATS_VLAN_PCP BIT(3) #define NFP_FL_FEATS_VF_RLIM BIT(4) #define NFP_FL_FEATS_FLOW_MOD BIT(5) +#define NFP_FL_FEATS_PRE_TUN_RULES BIT(6) #define NFP_FL_FEATS_FLOW_MERGE BIT(30) #define NFP_FL_FEATS_LAG BIT(31) @@ -162,6 +163,7 @@ struct nfp_fl_internal_ports { * @qos_stats_work: Workqueue for qos stats processing * @qos_rate_limiters: Current active qos rate limiters * @qos_stats_lock: Lock on qos stats updates + * @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded */ struct nfp_flower_priv { struct nfp_app *app; @@ -193,6 +195,7 @@ struct nfp_flower_priv { struct delayed_work qos_stats_work; unsigned int qos_rate_limiters; spinlock_t qos_stats_lock; /* Protect the qos stats */ + int pre_tun_rule_cnt; }; /** @@ -218,6 +221,7 @@ struct nfp_fl_qos { * @block_shared: Flag indicating if offload applies to shared blocks * @mac_list: List entry of reprs that share the same offloaded MAC * @qos_table: Stored info on filters implementing qos + * @on_bridge: Indicates if the repr is attached to a bridge */ struct nfp_flower_repr_priv { struct nfp_repr *nfp_repr; @@ -227,6 +231,7 @@ struct nfp_flower_repr_priv { bool block_shared; struct list_head mac_list; struct nfp_fl_qos qos_table; + bool on_bridge; }; /** @@ -280,6 +285,11 @@ struct nfp_fl_payload { char *action_data; struct list_head linked_flows; bool in_hw; + struct { + struct net_device *dev; + __be16 vlan_tci; + __be16 port_idx; + } pre_tun_rule; }; struct nfp_fl_payload_link { @@ -333,6 +343,11 @@ static inline bool nfp_flower_is_merge_flow(struct nfp_fl_payload *flow_pay) return flow_pay->tc_flower_cookie == (unsigned long)flow_pay; } +static inline bool nfp_flower_is_supported_bridge(struct net_device *netdev) +{ + return netif_is_ovs_master(netdev); +} + int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, unsigned int host_ctx_split); void nfp_flower_metadata_cleanup(struct nfp_app *app); @@ -415,4 +430,8 @@ void nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev); u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app, struct net_device *netdev); +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index e209f150c5f2..3a4f4f042ae7 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -61,6 +61,11 @@ NFP_FLOWER_LAYER_IPV4 | \ NFP_FLOWER_LAYER_IPV6) +#define NFP_FLOWER_PRE_TUN_RULE_FIELDS \ + (NFP_FLOWER_LAYER_PORT | \ + NFP_FLOWER_LAYER_MAC | \ + NFP_FLOWER_LAYER_IPV4) + struct nfp_flower_merge_check { union { struct { @@ -489,6 +494,7 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) flow_pay->meta.flags = 0; INIT_LIST_HEAD(&flow_pay->linked_flows); flow_pay->in_hw = false; + flow_pay->pre_tun_rule.dev = NULL; return flow_pay; @@ -732,28 +738,62 @@ nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len, return act_off; } -static int nfp_fl_verify_post_tun_acts(char *acts, int len) +static int +nfp_fl_verify_post_tun_acts(char *acts, int len, struct nfp_fl_push_vlan **vlan) { struct nfp_fl_act_head *a; unsigned int act_off = 0; while (act_off < len) { a = (struct nfp_fl_act_head *)&acts[act_off]; - if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) + + if (a->jump_id == NFP_FL_ACTION_OPCODE_PUSH_VLAN && !act_off) + *vlan = (struct nfp_fl_push_vlan *)a; + else if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) return -EOPNOTSUPP; act_off += a->len_lw << NFP_FL_LW_SIZ; } + /* Ensure any VLAN push also has an egress action. */ + if (*vlan && act_off <= sizeof(struct nfp_fl_push_vlan)) + return -EOPNOTSUPP; + return 0; } static int +nfp_fl_push_vlan_after_tun(char *acts, int len, struct nfp_fl_push_vlan *vlan) +{ + struct nfp_fl_set_ipv4_tun *tun; + struct nfp_fl_act_head *a; + unsigned int act_off = 0; + + while (act_off < len) { + a = (struct nfp_fl_act_head *)&acts[act_off]; + + if (a->jump_id == NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL) { + tun = (struct nfp_fl_set_ipv4_tun *)a; + tun->outer_vlan_tpid = vlan->vlan_tpid; + tun->outer_vlan_tci = vlan->vlan_tci; + + return 0; + } + + act_off += a->len_lw << NFP_FL_LW_SIZ; + } + + /* Return error if no tunnel action is found. */ + return -EOPNOTSUPP; +} + +static int nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, struct nfp_fl_payload *sub_flow2, struct nfp_fl_payload *merge_flow) { unsigned int sub1_act_len, sub2_act_len, pre_off1, pre_off2; + struct nfp_fl_push_vlan *post_tun_push_vlan = NULL; bool tunnel_act = false; char *merge_act; int err; @@ -790,18 +830,36 @@ nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, sub2_act_len -= pre_off2; /* FW does a tunnel push when egressing, therefore, if sub_flow 1 pushes - * a tunnel, sub_flow 2 can only have output actions for a valid merge. + * a tunnel, there are restrictions on what sub_flow 2 actions lead to a + * valid merge. */ if (tunnel_act) { char *post_tun_acts = &sub_flow2->action_data[pre_off2]; - err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len); + err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len, + &post_tun_push_vlan); if (err) return err; + + if (post_tun_push_vlan) { + pre_off2 += sizeof(*post_tun_push_vlan); + sub2_act_len -= sizeof(*post_tun_push_vlan); + } } /* Copy remaining actions from sub_flows 1 and 2. */ memcpy(merge_act, sub_flow1->action_data + pre_off1, sub1_act_len); + + if (post_tun_push_vlan) { + /* Update tunnel action in merge to include VLAN push. */ + err = nfp_fl_push_vlan_after_tun(merge_act, sub1_act_len, + post_tun_push_vlan); + if (err) + return err; + + merge_flow->meta.act_len -= sizeof(*post_tun_push_vlan); + } + merge_act += sub1_act_len; memcpy(merge_act, sub_flow2->action_data + pre_off2, sub2_act_len); @@ -945,6 +1003,106 @@ err_destroy_merge_flow: } /** + * nfp_flower_validate_pre_tun_rule() + * @app: Pointer to the APP handle + * @flow: Pointer to NFP flow representation of rule + * @extack: Netlink extended ACK report + * + * Verifies the flow as a pre-tunnel rule. + * + * Return: negative value on error, 0 if verified. + */ +static int +nfp_flower_validate_pre_tun_rule(struct nfp_app *app, + struct nfp_fl_payload *flow, + struct netlink_ext_ack *extack) +{ + struct nfp_flower_meta_tci *meta_tci; + struct nfp_flower_mac_mpls *mac; + struct nfp_fl_act_head *act; + u8 *mask = flow->mask_data; + bool vlan = false; + int act_offset; + u8 key_layer; + + meta_tci = (struct nfp_flower_meta_tci *)flow->unmasked_data; + if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { + u16 vlan_tci = be16_to_cpu(meta_tci->tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } + + key_layer = meta_tci->nfp_flow_key_layer; + if (key_layer & ~NFP_FLOWER_PRE_TUN_RULE_FIELDS) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: too many match fields"); + return -EOPNOTSUPP; + } + + if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MAC fields match required"); + return -EOPNOTSUPP; + } + + /* Skip fields known to exist. */ + mask += sizeof(struct nfp_flower_meta_tci); + mask += sizeof(struct nfp_flower_in_port); + + /* Ensure destination MAC address is fully matched. */ + mac = (struct nfp_flower_mac_mpls *)mask; + if (!is_broadcast_ether_addr(&mac->mac_dst[0])) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC field must not be masked"); + return -EOPNOTSUPP; + } + + if (key_layer & NFP_FLOWER_LAYER_IPV4) { + int ip_flags = offsetof(struct nfp_flower_ipv4, ip_ext.flags); + int ip_proto = offsetof(struct nfp_flower_ipv4, ip_ext.proto); + int i; + + mask += sizeof(struct nfp_flower_mac_mpls); + + /* Ensure proto and flags are the only IP layer fields. */ + for (i = 0; i < sizeof(struct nfp_flower_ipv4); i++) + if (mask[i] && i != ip_flags && i != ip_proto) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: only flags and proto can be matched in ip header"); + return -EOPNOTSUPP; + } + } + + /* Action must be a single egress or pop_vlan and egress. */ + act_offset = 0; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + if (vlan) { + if (act->jump_id != NFP_FL_ACTION_OPCODE_POP_VLAN) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on VLAN must have VLAN pop as first action"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + } + + if (act->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: non egress action detected where egress was expected"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + + /* Ensure there are no more actions after egress. */ + if (act_offset != flow->meta.act_len) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: egress is not the last action"); + return -EOPNOTSUPP; + } + + return 0; +} + +/** * nfp_flower_add_offload() - Adds a new flow to hardware. * @app: Pointer to the APP handle * @netdev: netdev structure. @@ -994,6 +1152,12 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_destroy_flow; + if (flow_pay->pre_tun_rule.dev) { + err = nfp_flower_validate_pre_tun_rule(app, flow_pay, extack); + if (err) + goto err_destroy_flow; + } + err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev, extack); if (err) goto err_destroy_flow; @@ -1006,8 +1170,11 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, goto err_release_metadata; } - err = nfp_flower_xmit_flow(app, flow_pay, - NFP_FLOWER_CMSG_TYPE_FLOW_ADD); + if (flow_pay->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_flow(app, flow_pay); + else + err = nfp_flower_xmit_flow(app, flow_pay, + NFP_FLOWER_CMSG_TYPE_FLOW_ADD); if (err) goto err_remove_rhash; @@ -1149,8 +1316,11 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, goto err_free_merge_flow; } - err = nfp_flower_xmit_flow(app, nfp_flow, - NFP_FLOWER_CMSG_TYPE_FLOW_DEL); + if (nfp_flow->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_del_flow(app, nfp_flow); + else + err = nfp_flower_xmit_flow(app, nfp_flow, + NFP_FLOWER_CMSG_TYPE_FLOW_DEL); /* Fall through on error. */ err_free_merge_flow: @@ -1479,16 +1649,17 @@ int nfp_flower_reg_indir_block_handler(struct nfp_app *app, return NOTIFY_OK; if (event == NETDEV_REGISTER) { - err = __tc_indr_block_cb_register(netdev, app, - nfp_flower_indr_setup_tc_cb, - app); + err = __flow_indr_block_cb_register(netdev, app, + nfp_flower_indr_setup_tc_cb, + app); if (err) nfp_flower_cmsg_warn(app, "Indirect block reg failed - %s\n", netdev->name); } else if (event == NETDEV_UNREGISTER) { - __tc_indr_block_cb_unregister(netdev, - nfp_flower_indr_setup_tc_cb, app); + __flow_indr_block_cb_unregister(netdev, + nfp_flower_indr_setup_tc_cb, + app); } return NOTIFY_OK; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index a7a80f4b722a..def8c198b016 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -15,6 +15,24 @@ #define NFP_FL_MAX_ROUTES 32 +#define NFP_TUN_PRE_TUN_RULE_LIMIT 32 +#define NFP_TUN_PRE_TUN_RULE_DEL 0x1 +#define NFP_TUN_PRE_TUN_IDX_BIT 0x8 + +/** + * struct nfp_tun_pre_run_rule - rule matched before decap + * @flags: options for the rule offset + * @port_idx: index of destination MAC address for the rule + * @vlan_tci: VLAN info associated with MAC + * @host_ctx_id: stats context of rule to update + */ +struct nfp_tun_pre_tun_rule { + __be32 flags; + __be16 port_idx; + __be16 vlan_tci; + __be32 host_ctx_id; +}; + /** * struct nfp_tun_active_tuns - periodic message of active tunnels * @seq: sequence number of the message @@ -124,11 +142,12 @@ enum nfp_flower_mac_offload_cmd { /** * struct nfp_tun_offloaded_mac - hashtable entry for an offloaded MAC - * @ht_node: Hashtable entry - * @addr: Offloaded MAC address - * @index: Offloaded index for given MAC address - * @ref_count: Number of devs using this MAC address - * @repr_list: List of reprs sharing this MAC address + * @ht_node: Hashtable entry + * @addr: Offloaded MAC address + * @index: Offloaded index for given MAC address + * @ref_count: Number of devs using this MAC address + * @repr_list: List of reprs sharing this MAC address + * @bridge_count: Number of bridge/internal devs with MAC */ struct nfp_tun_offloaded_mac { struct rhash_head ht_node; @@ -136,6 +155,7 @@ struct nfp_tun_offloaded_mac { u16 index; int ref_count; struct list_head repr_list; + int bridge_count; }; static const struct rhashtable_params offloaded_macs_params = { @@ -556,6 +576,8 @@ nfp_tunnel_offloaded_macs_inc_ref_and_link(struct nfp_tun_offloaded_mac *entry, list_del(&repr_priv->mac_list); list_add_tail(&repr_priv->mac_list, &entry->repr_list); + } else if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count++; } entry->ref_count++; @@ -572,20 +594,35 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { - nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod); - return 0; + if (entry->bridge_count || + !nfp_flower_is_supported_bridge(netdev)) { + nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, + netdev, mod); + return 0; + } + + /* MAC is global but matches need to go to pre_tun table. */ + nfp_mac_idx = entry->index | NFP_TUN_PRE_TUN_IDX_BIT; } - /* Assign a global index if non-repr or MAC address is now shared. */ - if (entry || !port) { - ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, - NFP_MAX_MAC_INDEX, GFP_KERNEL); - if (ida_idx < 0) - return ida_idx; + if (!nfp_mac_idx) { + /* Assign a global index if non-repr or MAC is now shared. */ + if (entry || !port) { + ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, + NFP_MAX_MAC_INDEX, GFP_KERNEL); + if (ida_idx < 0) + return ida_idx; - nfp_mac_idx = nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); - } else { - nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port); + nfp_mac_idx = + nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); + + if (nfp_flower_is_supported_bridge(netdev)) + nfp_mac_idx |= NFP_TUN_PRE_TUN_IDX_BIT; + + } else { + nfp_mac_idx = + nfp_tunnel_get_mac_idx_from_phy_port_id(port); + } } if (!entry) { @@ -654,6 +691,25 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, list_del(&repr_priv->mac_list); } + if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count--; + + if (!entry->bridge_count && entry->ref_count) { + u16 nfp_mac_idx; + + nfp_mac_idx = entry->index & ~NFP_TUN_PRE_TUN_IDX_BIT; + if (__nfp_tunnel_offload_mac(app, mac, nfp_mac_idx, + false)) { + nfp_flower_cmsg_warn(app, "MAC offload index revert failed on %s.\n", + netdev_name(netdev)); + return 0; + } + + entry->index = nfp_mac_idx; + return 0; + } + } + /* If MAC is now used by 1 repr set the offloaded MAC index to port. */ if (entry->ref_count == 1 && list_is_singular(&entry->repr_list)) { u16 nfp_mac_idx; @@ -713,6 +769,9 @@ nfp_tunnel_offload_mac(struct nfp_app *app, struct net_device *netdev, return 0; repr_priv = repr->app_priv; + if (repr_priv->on_bridge) + return 0; + mac_offloaded = &repr_priv->mac_offloaded; off_mac = &repr_priv->offloaded_mac_addr[0]; port = nfp_repr_get_port_id(netdev); @@ -828,10 +887,119 @@ int nfp_tunnel_mac_event_handler(struct nfp_app *app, if (err) nfp_flower_cmsg_warn(app, "Failed to offload MAC change on %s.\n", netdev_name(netdev)); + } else if (event == NETDEV_CHANGEUPPER) { + /* If a repr is attached to a bridge then tunnel packets + * entering the physical port are directed through the bridge + * datapath and cannot be directly detunneled. Therefore, + * associated offloaded MACs and indexes should not be used + * by fw for detunneling. + */ + struct netdev_notifier_changeupper_info *info = ptr; + struct net_device *upper = info->upper_dev; + struct nfp_flower_repr_priv *repr_priv; + struct nfp_repr *repr; + + if (!nfp_netdev_is_nfp_repr(netdev) || + !nfp_flower_is_supported_bridge(upper)) + return NOTIFY_OK; + + repr = netdev_priv(netdev); + if (repr->app != app) + return NOTIFY_OK; + + repr_priv = repr->app_priv; + + if (info->linking) { + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_DEL)) + nfp_flower_cmsg_warn(app, "Failed to delete offloaded MAC on %s.\n", + netdev_name(netdev)); + repr_priv->on_bridge = true; + } else { + repr_priv->on_bridge = false; + + if (!(netdev->flags & IFF_UP)) + return NOTIFY_OK; + + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_ADD)) + nfp_flower_cmsg_warn(app, "Failed to offload MAC on %s.\n", + netdev_name(netdev)); + } } return NOTIFY_OK; } +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_offloaded_mac *mac_entry; + struct nfp_tun_pre_tun_rule payload; + struct net_device *internal_dev; + int err; + + if (app_priv->pre_tun_rule_cnt == NFP_TUN_PRE_TUN_RULE_LIMIT) + return -ENOSPC; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + internal_dev = flow->pre_tun_rule.dev; + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.host_ctx_id = flow->meta.host_ctx_id; + + /* Lookup MAC index for the pre-tunnel rule egress device. + * Note that because the device is always an internal port, it will + * have a constant global index so does not need to be tracked. + */ + mac_entry = nfp_tunnel_lookup_offloaded_macs(app, + internal_dev->dev_addr); + if (!mac_entry) + return -ENOENT; + + payload.port_idx = cpu_to_be16(mac_entry->index); + + /* Copy mac id and vlan to flow - dev may not exist at delete time. */ + flow->pre_tun_rule.vlan_tci = payload.vlan_tci; + flow->pre_tun_rule.port_idx = payload.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt++; + + return 0; +} + +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_pre_tun_rule payload; + u32 tmp_flags = 0; + int err; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + tmp_flags |= NFP_TUN_PRE_TUN_RULE_DEL; + payload.flags = cpu_to_be32(tmp_flags); + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.port_idx = flow->pre_tun_rule.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt--; + + return 0; +} + int nfp_tunnel_config_start(struct nfp_app *app) { struct nfp_flower_priv *priv = app->priv; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 9903805717da..6f97b554f7da 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -975,7 +975,7 @@ static int nfp_net_prep_tx_meta(struct sk_buff *skb, u64 tls_handle) static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - const struct skb_frag_struct *frag; + const skb_frag_t *frag; int f, nr_frags, wr_idx, md_bytes; struct nfp_net_tx_ring *tx_ring; struct nfp_net_r_vector *r_vec; @@ -1155,7 +1155,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget) todo = D_IDX(tx_ring, qcp_rd_p - tx_ring->qcp_rd_p); while (todo--) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; struct nfp_net_tx_buf *tx_buf; struct sk_buff *skb; int fidx, nr_frags; @@ -1270,7 +1270,7 @@ static bool nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) static void nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; struct netdev_queue *nd_q; while (!tx_ring->is_xdp && tx_ring->rd_p != tx_ring->wr_p) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c index ab7f2498e1c4..553c708694e8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c @@ -159,19 +159,13 @@ void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir) else strcpy(name, "ctrl-vnic"); nn->debugfs_dir = debugfs_create_dir(name, ddir); - if (IS_ERR_OR_NULL(nn->debugfs_dir)) - return; /* Create queue debugging sub-tree */ queues = debugfs_create_dir("queue", nn->debugfs_dir); - if (IS_ERR_OR_NULL(queues)) - return; rx = debugfs_create_dir("rx", queues); tx = debugfs_create_dir("tx", queues); xdp = debugfs_create_dir("xdp", queues); - if (IS_ERR_OR_NULL(rx) || IS_ERR_OR_NULL(tx) || IS_ERR_OR_NULL(xdp)) - return; for (i = 0; i < min(nn->max_rx_rings, nn->max_r_vecs); i++) { sprintf(name, "%d", i); @@ -190,16 +184,7 @@ void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir) struct dentry *nfp_net_debugfs_device_add(struct pci_dev *pdev) { - struct dentry *dev_dir; - - if (IS_ERR_OR_NULL(nfp_dir)) - return NULL; - - dev_dir = debugfs_create_dir(pci_name(pdev), nfp_dir); - if (IS_ERR_OR_NULL(dev_dir)) - return NULL; - - return dev_dir; + return debugfs_create_dir(pci_name(pdev), nfp_dir); } void nfp_net_debugfs_dir_clean(struct dentry **dir) diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index 3d73970b3a2e..219b0b863c89 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -993,14 +993,12 @@ static int w90p910_ether_probe(struct platform_device *pdev) ether->txirq = platform_get_irq(pdev, 0); if (ether->txirq < 0) { - dev_err(&pdev->dev, "failed to get ether tx irq\n"); error = -ENXIO; goto failed_free_io; } ether->rxirq = platform_get_irq(pdev, 1); if (ether->rxirq < 0) { - dev_err(&pdev->dev, "failed to get ether rx irq\n"); error = -ENXIO; goto failed_free_io; } diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index b327b29f5d57..ecca794c55e2 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -6126,8 +6126,7 @@ static void nv_remove(struct pci_dev *pci_dev) #ifdef CONFIG_PM_SLEEP static int nv_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); int i; diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index a391cf6ee4b2..55a29ec76680 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -66,15 +66,6 @@ config QLCNIC_HWMON This data is available via the hwmon sysfs interface. -config QLGE - tristate "QLogic QLGE 10Gb Ethernet Driver Support" - depends on PCI - ---help--- - This driver supports QLogic ISP8XXX 10Gb Ethernet cards. - - To compile this driver as a module, choose M here: the module - will be called qlge. - config NETXEN_NIC tristate "NetXen Multi port (1/10) Gigabit Ethernet NIC" depends on PCI diff --git a/drivers/net/ethernet/qlogic/Makefile b/drivers/net/ethernet/qlogic/Makefile index 6cd2e333a5fc..1ae4a0743bd5 100644 --- a/drivers/net/ethernet/qlogic/Makefile +++ b/drivers/net/ethernet/qlogic/Makefile @@ -5,7 +5,6 @@ obj-$(CONFIG_QLA3XXX) += qla3xxx.o obj-$(CONFIG_QLCNIC) += qlcnic/ -obj-$(CONFIG_QLGE) += qlge/ obj-$(CONFIG_NETXEN_NIC) += netxen/ obj-$(CONFIG_QED) += qed/ obj-$(CONFIG_QEDE)+= qede/ diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 58e2eaf77014..c692a41e4548 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1980,7 +1980,7 @@ netxen_map_tx_skb(struct pci_dev *pdev, struct sk_buff *skb, struct netxen_cmd_buffer *pbuf) { struct netxen_skb_frag *nf; - struct skb_frag_struct *frag; + skb_frag_t *frag; int i, nr_frags; dma_addr_t map; @@ -2043,7 +2043,7 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) struct pci_dev *pdev; int i, k; int delta = 0; - struct skb_frag_struct *frag; + skb_frag_t *frag; u32 producer; int frag_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index e054f6c69e3a..557a12ef9815 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12580,6 +12580,8 @@ struct public_drv_mb { #define DRV_MSG_CODE_BW_UPDATE_ACK 0x32000000 #define DRV_MSG_CODE_NIG_DRAIN 0x30000000 #define DRV_MSG_CODE_S_TAG_UPDATE_ACK 0x3b000000 +#define DRV_MSG_CODE_GET_NVM_CFG_OPTION 0x003e0000 +#define DRV_MSG_CODE_SET_NVM_CFG_OPTION 0x003f0000 #define DRV_MSG_CODE_INITIATE_PF_FLR 0x02010000 #define DRV_MSG_CODE_VF_DISABLED_DONE 0xc0000000 #define DRV_MSG_CODE_CFG_VF_MSIX 0xc0010000 @@ -12748,6 +12750,21 @@ struct public_drv_mb { #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE 0x00000002 #define DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK 0x00010000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ID_SHIFT 0 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ID_MASK 0x0000FFFF +#define DRV_MB_PARAM_NVM_CFG_OPTION_ALL_SHIFT 16 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ALL_MASK 0x00010000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_INIT_SHIFT 17 +#define DRV_MB_PARAM_NVM_CFG_OPTION_INIT_MASK 0x00020000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_COMMIT_SHIFT 18 +#define DRV_MB_PARAM_NVM_CFG_OPTION_COMMIT_MASK 0x00040000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_FREE_SHIFT 19 +#define DRV_MB_PARAM_NVM_CFG_OPTION_FREE_MASK 0x00080000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL_SHIFT 20 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL_MASK 0x00100000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID_SHIFT 24 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID_MASK 0x0f000000 + u32 fw_mb_header; #define FW_MSG_CODE_MASK 0xffff0000 #define FW_MSG_CODE_UNSUPPORTED 0x00000000 diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 9f36e7948222..1a5fc2ae351c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1631,10 +1631,9 @@ static void __qed_get_vport_pstats_addrlen(struct qed_hwfn *p_hwfn, } } -static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack void +__qed_get_vport_pstats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct eth_pstorm_per_queue_stat pstats; u32 pstats_addr = 0, pstats_len = 0; @@ -1661,10 +1660,9 @@ static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn, HILO_64_REGPAIR(pstats.error_drop_pkts); } -static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack void +__qed_get_vport_tstats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct tstorm_per_port_stat tstats; u32 tstats_addr, tstats_len; @@ -1709,10 +1707,9 @@ static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn, } } -static void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack +void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct eth_ustorm_per_queue_stat ustats; u32 ustats_addr = 0, ustats_len = 0; @@ -1751,10 +1748,9 @@ static void __qed_get_vport_mstats_addrlen(struct qed_hwfn *p_hwfn, } } -static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack void +__qed_get_vport_mstats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct eth_mstorm_per_queue_stat mstats; u32 mstats_addr = 0, mstats_len = 0; @@ -1780,9 +1776,9 @@ static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn, HILO_64_REGPAIR(mstats.tpa_coalesced_bytes); } -static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats) +static noinline_for_stack void +__qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats) { struct qed_eth_stats_common *p_common = &p_stats->common; struct port_stats port_stats; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 829dd60ab937..0a7645937412 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -67,6 +67,8 @@ #define QED_ROCE_QPS (8192) #define QED_ROCE_DPIS (8) #define QED_RDMA_SRQS QED_ROCE_QPS +#define QED_NVM_CFG_SET_FLAGS 0xE +#define QED_NVM_CFG_SET_PF_FLAGS 0x1E static char version[] = "QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n"; @@ -1688,6 +1690,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, switch (media_type) { case MEDIA_DA_TWINAX: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; /* For DAC media multiple speed capabilities are supported*/ @@ -1707,6 +1710,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, *if_capability |= QED_LM_100000baseCR4_Full_BIT; break; case MEDIA_BASE_T: + *if_capability |= QED_LM_TP_BIT; if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_EXT_PHY) { if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { @@ -1718,6 +1722,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, } } if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_MODULE) { + *if_capability |= QED_LM_FIBRE_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_1000BASET) *if_capability |= QED_LM_1000baseT_Full_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_BASET) @@ -1728,6 +1733,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, case MEDIA_SFPP_10G_FIBER: case MEDIA_XFP_FIBER: case MEDIA_MODULE_FIBER: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { if ((tcvr_type == ETH_TRANSCEIVER_TYPE_1G_LX) || @@ -1770,6 +1776,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, break; case MEDIA_KR: + *if_capability |= QED_LM_Backplane_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; if (capability & @@ -1821,7 +1828,6 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->link_up = true; /* TODO - at the moment assume supported and advertised speed equal */ - if_link->supported_caps = QED_LM_FIBRE_BIT; if (link_caps.default_speed_autoneg) if_link->supported_caps |= QED_LM_Autoneg_BIT; if (params.pause.autoneg || @@ -2227,6 +2233,69 @@ static int qed_nvm_flash_image_validate(struct qed_dev *cdev, return 0; } +/* Binary file format - + * /----------------------------------------------------------------------\ + * 0B | 0x5 [command index] | + * 4B | Entity ID | Reserved | Number of config attributes | + * 8B | Config ID | Length | Value | + * | | + * \----------------------------------------------------------------------/ + * There can be several cfg_id-Length-Value sets as specified by 'Number of...'. + * Entity ID - A non zero entity value for which the config need to be updated. + * + * The API parses config attributes from the user provided buffer and flashes + * them to the respective NVM path using Management FW inerface. + */ +static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + u8 entity_id, len, buf[32]; + struct qed_ptt *ptt; + u16 cfg_id, count; + int rc = 0, i; + u32 flags; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + /* NVM CFG ID attribute header */ + *data += 4; + entity_id = **data; + *data += 2; + count = *((u16 *)*data); + *data += 2; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "Read config ids: entity id %02x num _attrs = %0d\n", + entity_id, count); + /* NVM CFG ID attributes */ + for (i = 0; i < count; i++) { + cfg_id = *((u16 *)*data); + *data += 2; + len = **data; + (*data)++; + memcpy(buf, *data, len); + *data += len; + + flags = entity_id ? QED_NVM_CFG_SET_PF_FLAGS : + QED_NVM_CFG_SET_FLAGS; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "cfg_id = %d len = %d\n", cfg_id, len); + rc = qed_mcp_nvm_set_cfg(hwfn, ptt, cfg_id, entity_id, flags, + buf, len); + if (rc) { + DP_ERR(cdev, "Error %d configuring %d\n", rc, cfg_id); + break; + } + } + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static int qed_nvm_flash(struct qed_dev *cdev, const char *name) { const struct firmware *image; @@ -2268,6 +2337,9 @@ static int qed_nvm_flash(struct qed_dev *cdev, const char *name) rc = qed_nvm_flash_image_access(cdev, &data, &check_resp); break; + case QED_NVM_FLASH_CMD_NVM_CFG_ID: + rc = qed_nvm_flash_cfg_write(cdev, &data); + break; default: DP_ERR(cdev, "Unknown command %08x\n", cmd_type); rc = -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 758702c1ce9c..89462c4a5022 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3750,3 +3750,35 @@ int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) return 0; } + +int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 len) +{ + u32 mb_param = 0, resp, param; + + QED_MFW_SET_FIELD(mb_param, DRV_MB_PARAM_NVM_CFG_OPTION_ID, option_id); + if (flags & QED_NVM_CFG_OPTION_ALL) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ALL, 1); + if (flags & QED_NVM_CFG_OPTION_INIT) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_INIT, 1); + if (flags & QED_NVM_CFG_OPTION_COMMIT) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_COMMIT, 1); + if (flags & QED_NVM_CFG_OPTION_FREE) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_FREE, 1); + if (flags & QED_NVM_CFG_OPTION_ENTITY_SEL) { + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL, 1); + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID, + entity_id); + } + + return qed_mcp_nvm_wr_cmd(p_hwfn, p_ptt, + DRV_MSG_CODE_SET_NVM_CFG_OPTION, + mb_param, &resp, ¶m, len, (u32 *)p_buf); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index e4f8fe4bd062..83649a82977b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -251,6 +251,12 @@ union qed_mfw_tlv_data { struct qed_mfw_tlv_iscsi iscsi; }; +#define QED_NVM_CFG_OPTION_ALL BIT(0) +#define QED_NVM_CFG_OPTION_INIT BIT(1) +#define QED_NVM_CFG_OPTION_COMMIT BIT(2) +#define QED_NVM_CFG_OPTION_FREE BIT(3) +#define QED_NVM_CFG_OPTION_ENTITY_SEL BIT(4) + /** * @brief - returns the link params of the hw function * @@ -1202,4 +1208,18 @@ int qed_mcp_get_engine_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); */ int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); +/** + * @brief Set NVM config attribute value. + * + * @param p_hwfn + * @param p_ptt + * @param option_id + * @param entity_id + * @param flags + * @param p_buf + * @param len + */ +int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 len); #endif diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index e85f9fef930c..abcee474909a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -424,12 +424,13 @@ struct qede_link_mode_mapping { }; static const struct qede_link_mode_mapping qed_lm_map[] = { + {QED_LM_FIBRE_BIT, ETHTOOL_LINK_MODE_FIBRE_BIT}, {QED_LM_Autoneg_BIT, ETHTOOL_LINK_MODE_Autoneg_BIT}, {QED_LM_Asym_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT}, {QED_LM_Pause_BIT, ETHTOOL_LINK_MODE_Pause_BIT}, {QED_LM_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT}, {QED_LM_10000baseT_Full_BIT, ETHTOOL_LINK_MODE_10000baseT_Full_BIT}, - {QED_LM_2500baseX_Full_BIT, ETHTOOL_LINK_MODE_2500baseX_Full_BIT}, + {QED_LM_TP_BIT, ETHTOOL_LINK_MODE_TP_BIT}, {QED_LM_Backplane_BIT, ETHTOOL_LINK_MODE_Backplane_BIT}, {QED_LM_1000baseKX_Full_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT}, {QED_LM_10000baseKX4_Full_BIT, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT}, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 14f26bf3b388..ac61f614de37 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -581,7 +581,7 @@ static int qlcnic_map_tx_skb(struct pci_dev *pdev, struct sk_buff *skb, struct qlcnic_cmd_buffer *pbuf) { struct qlcnic_skb_frag *nf; - struct skb_frag_struct *frag; + skb_frag_t *frag; int i, nr_frags; dma_addr_t map; diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 707665b62eb7..bebe38d74d66 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1385,15 +1385,13 @@ static void emac_tx_fill_tpd(struct emac_adapter *adpt, } for (i = 0; i < nr_frags; i++) { - struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; tpbuf = GET_TPD_BUFFER(tx_q, tx_q->tpd.produce_idx); - tpbuf->length = frag->size; - tpbuf->dma_addr = dma_map_page(adpt->netdev->dev.parent, - frag->page.p, frag->page_offset, - tpbuf->length, DMA_TO_DEVICE); + tpbuf->length = skb_frag_size(frag); + tpbuf->dma_addr = skb_frag_dma_map(adpt->netdev->dev.parent, + frag, 0, tpbuf->length, + DMA_TO_DEVICE); ret = dma_mapping_error(adpt->netdev->dev.parent, tpbuf->dma_addr); if (ret) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 59c2349b59df..c84ab052ef26 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -544,7 +544,6 @@ static int emac_probe_resources(struct platform_device *pdev, struct emac_adapter *adpt) { struct net_device *netdev = adpt->netdev; - struct resource *res; char maddr[ETH_ALEN]; int ret = 0; @@ -556,22 +555,17 @@ static int emac_probe_resources(struct platform_device *pdev, /* Core 0 interrupt */ ret = platform_get_irq(pdev, 0); - if (ret < 0) { - dev_err(&pdev->dev, - "error: missing core0 irq resource (error=%i)\n", ret); + if (ret < 0) return ret; - } adpt->irq.irq = ret; /* base register address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - adpt->base = devm_ioremap_resource(&pdev->dev, res); + adpt->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(adpt->base)) return PTR_ERR(adpt->base); /* CSR register address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - adpt->csr = devm_ioremap_resource(&pdev->dev, res); + adpt->csr = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(adpt->csr)) return PTR_ERR(adpt->csr); diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index bcb890b18a94..702aa217a27a 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -131,17 +131,10 @@ DEFINE_SHOW_ATTRIBUTE(qcaspi_info); void qcaspi_init_device_debugfs(struct qcaspi *qca) { - struct dentry *device_root; + qca->device_root = debugfs_create_dir(dev_name(&qca->net_dev->dev), + NULL); - device_root = debugfs_create_dir(dev_name(&qca->net_dev->dev), NULL); - qca->device_root = device_root; - - if (IS_ERR(device_root) || !device_root) { - pr_warn("failed to create debugfs directory for %s\n", - dev_name(&qca->net_dev->dev)); - return; - } - debugfs_create_file("info", S_IFREG | 0444, device_root, qca, + debugfs_create_file("info", S_IFREG | 0444, qca->device_root, qca, &qcaspi_info_fops); } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index e1dd6ea60d67..910944120a65 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -61,7 +61,7 @@ /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast). The RTL chips use a 64 element hash table based on the Ethernet CRC. */ -static const int multicast_filter_limit = 32; +#define MC_FILTER_LIMIT 32 #define TX_DMA_BURST 7 /* Maximum PCI burst, '7' is unlimited */ #define InterFrameGap 0x03 /* 3 means InterFrameGap = the shortest one */ @@ -271,7 +271,6 @@ enum rtl_registers { Config3 = 0x54, Config4 = 0x55, Config5 = 0x56, - MultiIntr = 0x5c, PHYAR = 0x60, PHYstatus = 0x6c, RxMaxSize = 0xda, @@ -539,11 +538,11 @@ enum rtl_tx_desc_bit_1 { TD1_GTSENV4 = (1 << 26), /* Giant Send for IPv4 */ TD1_GTSENV6 = (1 << 25), /* Giant Send for IPv6 */ #define GTTCPHO_SHIFT 18 -#define GTTCPHO_MAX 0x7fU +#define GTTCPHO_MAX 0x7f /* Second doubleword. */ #define TCPHO_SHIFT 18 -#define TCPHO_MAX 0x3ffU +#define TCPHO_MAX 0x3ff #define TD1_MSS_SHIFT 18 /* MSS position (11 bits) */ TD1_IPv6_CS = (1 << 28), /* Calculate IPv6 checksum */ TD1_IPv4_CS = (1 << 29), /* Calculate IPv4 checksum */ @@ -569,6 +568,11 @@ enum rtl_rx_desc_bit { #define RsvdMask 0x3fffc000 +#define RTL_GSO_MAX_SIZE_V1 32000 +#define RTL_GSO_MAX_SEGS_V1 24 +#define RTL_GSO_MAX_SIZE_V2 64000 +#define RTL_GSO_MAX_SEGS_V2 64 + struct TxDesc { __le32 opts1; __le32 opts2; @@ -638,7 +642,7 @@ struct rtl8169_private { struct RxDesc *RxDescArray; /* 256-aligned Rx descriptor ring */ dma_addr_t TxPhyAddr; dma_addr_t RxPhyAddr; - void *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */ + struct page *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */ struct ring_info tx_skb[NUM_TX_DESC]; /* Tx data buffers */ u16 cp_cmd; u16 irq_mask; @@ -729,6 +733,13 @@ static bool rtl_is_8168evl_up(struct rtl8169_private *tp) tp->mac_version != RTL_GIGA_MAC_VER_39; } +static bool rtl_supports_eee(struct rtl8169_private *tp) +{ + return tp->mac_version >= RTL_GIGA_MAC_VER_34 && + tp->mac_version != RTL_GIGA_MAC_VER_37 && + tp->mac_version != RTL_GIGA_MAC_VER_39; +} + struct rtl_cond { bool (*check)(struct rtl8169_private *); const char *msg; @@ -846,6 +857,14 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) return RTL_R32(tp, OCPDR); } +static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, + u16 set) +{ + u16 data = r8168_mac_ocp_read(tp, reg); + + r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); +} + #define OCP_STD_PHY_BASE 0xa400 static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value) @@ -1414,18 +1433,22 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) } switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_17: + case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: options = RTL_R8(tp, Config1) & ~PMEnable; if (wolopts) options |= PMEnable; RTL_W8(tp, Config1, options); break; - default: + case RTL_GIGA_MAC_VER_34: + case RTL_GIGA_MAC_VER_37: + case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_51: options = RTL_R8(tp, Config2) & ~PME_SIGNAL; if (wolopts) options |= PME_SIGNAL; RTL_W8(tp, Config2, options); break; + default: + break; } rtl_lock_config_regs(tp); @@ -1929,144 +1952,40 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) return 0; } -static int rtl_get_eee_supp(struct rtl8169_private *tp) -{ - struct phy_device *phydev = tp->phydev; - int ret; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - ret = phy_read_paged(phydev, 0x0a5c, 0x12); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - -static int rtl_get_eee_lpadv(struct rtl8169_private *tp) -{ - struct phy_device *phydev = tp->phydev; - int ret; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - ret = phy_read_paged(phydev, 0x0a5d, 0x11); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - -static int rtl_get_eee_adv(struct rtl8169_private *tp) -{ - struct phy_device *phydev = tp->phydev; - int ret; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - ret = phy_read_paged(phydev, 0x0a5d, 0x10); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - -static int rtl_set_eee_adv(struct rtl8169_private *tp, int val) -{ - struct phy_device *phydev = tp->phydev; - int ret = 0; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, val); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - phy_write_paged(phydev, 0x0a5d, 0x10, val); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - static int rtl8169_get_eee(struct net_device *dev, struct ethtool_eee *data) { struct rtl8169_private *tp = netdev_priv(dev); struct device *d = tp_to_dev(tp); int ret; + if (!rtl_supports_eee(tp)) + return -EOPNOTSUPP; + pm_runtime_get_noresume(d); if (!pm_runtime_active(d)) { ret = -EOPNOTSUPP; - goto out; + } else { + ret = phy_ethtool_get_eee(tp->phydev, data); } - /* Get Supported EEE */ - ret = rtl_get_eee_supp(tp); - if (ret < 0) - goto out; - data->supported = mmd_eee_cap_to_ethtool_sup_t(ret); - - /* Get advertisement EEE */ - ret = rtl_get_eee_adv(tp); - if (ret < 0) - goto out; - data->advertised = mmd_eee_adv_to_ethtool_adv_t(ret); - data->eee_enabled = !!data->advertised; - - /* Get LP advertisement EEE */ - ret = rtl_get_eee_lpadv(tp); - if (ret < 0) - goto out; - data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(ret); - data->eee_active = !!(data->advertised & data->lp_advertised); -out: pm_runtime_put_noidle(d); - return ret < 0 ? ret : 0; + + return ret; } static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data) { struct rtl8169_private *tp = netdev_priv(dev); struct device *d = tp_to_dev(tp); - int old_adv, adv = 0, cap, ret; + int ret; + + if (!rtl_supports_eee(tp)) + return -EOPNOTSUPP; pm_runtime_get_noresume(d); - if (!dev->phydev || !pm_runtime_active(d)) { + if (!pm_runtime_active(d)) { ret = -EOPNOTSUPP; goto out; } @@ -2077,38 +1996,10 @@ static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data) goto out; } - /* Get Supported EEE */ - ret = rtl_get_eee_supp(tp); - if (ret < 0) - goto out; - cap = ret; - - ret = rtl_get_eee_adv(tp); - if (ret < 0) - goto out; - old_adv = ret; - - if (data->eee_enabled) { - adv = !data->advertised ? cap : - ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap; - /* Mask prohibited EEE modes */ - adv &= ~dev->phydev->eee_broken_modes; - } - - if (old_adv != adv) { - ret = rtl_set_eee_adv(tp, adv); - if (ret < 0) - goto out; - - /* Restart autonegotiation so the new modes get sent to the - * link partner. - */ - ret = phy_restart_aneg(dev->phydev); - } - + ret = phy_ethtool_set_eee(tp->phydev, data); out: pm_runtime_put_noidle(d); - return ret < 0 ? ret : 0; + return ret; } static const struct ethtool_ops rtl8169_ethtool_ops = { @@ -2135,10 +2026,11 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { static void rtl_enable_eee(struct rtl8169_private *tp) { - int supported = rtl_get_eee_supp(tp); + struct phy_device *phydev = tp->phydev; + int supported = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE); if (supported > 0) - rtl_set_eee_adv(tp, supported); + phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, supported); } static void rtl8169_get_mac_version(struct rtl8169_private *tp) @@ -2324,6 +2216,16 @@ static void rtl8168g_config_eee_phy(struct rtl8169_private *tp) phy_modify_paged(tp->phydev, 0x0a43, 0x11, 0, BIT(4)); } +static void rtl8168h_config_eee_phy(struct rtl8169_private *tp) +{ + struct phy_device *phydev = tp->phydev; + + rtl8168g_config_eee_phy(tp); + + phy_modify_paged(phydev, 0xa4a, 0x11, 0x0000, 0x0200); + phy_modify_paged(phydev, 0xa42, 0x14, 0x0000, 0x0080); +} + static void rtl8169s_hw_phy_config(struct rtl8169_private *tp) { static const struct phy_reg phy_reg_init[] = { @@ -3391,7 +3293,7 @@ static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp) phy_modify_paged(tp->phydev, 0x0a44, 0x11, BIT(7), 0); rtl8168g_disable_aldps(tp); - rtl8168g_config_eee_phy(tp); + rtl8168h_config_eee_phy(tp); rtl_enable_eee(tp); } @@ -4146,54 +4048,46 @@ static void rtl8169_set_magic_reg(struct rtl8169_private *tp, unsigned mac_versi static void rtl_set_rx_mode(struct net_device *dev) { + u32 rx_mode = AcceptBroadcast | AcceptMyPhys | AcceptMulticast; + /* Multicast hash filter */ + u32 mc_filter[2] = { 0xffffffff, 0xffffffff }; struct rtl8169_private *tp = netdev_priv(dev); - u32 mc_filter[2]; /* Multicast hash filter */ - int rx_mode; - u32 tmp = 0; + u32 tmp; if (dev->flags & IFF_PROMISC) { /* Unconditionally log net taps. */ netif_notice(tp, link, dev, "Promiscuous mode enabled\n"); - rx_mode = - AcceptBroadcast | AcceptMulticast | AcceptMyPhys | - AcceptAllPhys; - mc_filter[1] = mc_filter[0] = 0xffffffff; - } else if ((netdev_mc_count(dev) > multicast_filter_limit) || - (dev->flags & IFF_ALLMULTI)) { - /* Too many to filter perfectly -- accept all multicasts. */ - rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; - mc_filter[1] = mc_filter[0] = 0xffffffff; + rx_mode |= AcceptAllPhys; + } else if (netdev_mc_count(dev) > MC_FILTER_LIMIT || + dev->flags & IFF_ALLMULTI || + tp->mac_version == RTL_GIGA_MAC_VER_35) { + /* accept all multicasts */ + } else if (netdev_mc_empty(dev)) { + rx_mode &= ~AcceptMulticast; } else { struct netdev_hw_addr *ha; - rx_mode = AcceptBroadcast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0; netdev_for_each_mc_addr(ha, dev) { - int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; - mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); - rx_mode |= AcceptMulticast; + u32 bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; + mc_filter[bit_nr >> 5] |= BIT(bit_nr & 31); + } + + if (tp->mac_version > RTL_GIGA_MAC_VER_06) { + tmp = mc_filter[0]; + mc_filter[0] = swab32(mc_filter[1]); + mc_filter[1] = swab32(tmp); } } if (dev->features & NETIF_F_RXALL) rx_mode |= (AcceptErr | AcceptRunt); - tmp = (RTL_R32(tp, RxConfig) & ~RX_CONFIG_ACCEPT_MASK) | rx_mode; - - if (tp->mac_version > RTL_GIGA_MAC_VER_06) { - u32 data = mc_filter[0]; - - mc_filter[0] = swab32(mc_filter[1]); - mc_filter[1] = swab32(data); - } - - if (tp->mac_version == RTL_GIGA_MAC_VER_35) - mc_filter[1] = mc_filter[0] = 0xffffffff; - RTL_W32(tp, MAR0 + 4, mc_filter[1]); RTL_W32(tp, MAR0 + 0, mc_filter[0]); - RTL_W32(tp, RxConfig, tmp); + tmp = RTL_R32(tp, RxConfig); + RTL_W32(tp, RxConfig, (tmp & ~RX_CONFIG_ACCEPT_MASK) | rx_mode); } DECLARE_RTL_COND(rtl_csiar_cond) @@ -4407,7 +4301,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168c_2[] = { { 0x01, 0, 0x0001 }, - { 0x03, 0x0400, 0x0220 } + { 0x03, 0x0400, 0x0020 } }; rtl_set_def_aspm_entry_latency(tp); @@ -4454,7 +4348,8 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) static const struct ephy_info e_info_8168d_4[] = { { 0x0b, 0x0000, 0x0048 }, { 0x19, 0x0020, 0x0050 }, - { 0x0c, 0x0100, 0x0020 } + { 0x0c, 0x0100, 0x0020 }, + { 0x10, 0x0004, 0x0000 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4504,7 +4399,9 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168e_2[] = { { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4566,7 +4463,9 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) { 0x06, 0x00c0, 0x0020 }, { 0x08, 0x0001, 0x0002 }, { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4581,8 +4480,9 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) static const struct ephy_info e_info_8168f_1[] = { { 0x06, 0x00c0, 0x0020 }, { 0x0f, 0xffff, 0x5200 }, - { 0x1e, 0x0000, 0x4000 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4621,8 +4521,8 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_1[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x37d0, 0x0820 }, + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, { 0x1e, 0x0000, 0x0001 }, { 0x19, 0x8000, 0x0000 } }; @@ -4638,10 +4538,15 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x19, 0xffff, 0xfc00 }, - { 0x1e, 0xffff, 0x20eb } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, + { 0x19, 0xffff, 0x7c00 }, + { 0x1e, 0xffff, 0x20eb }, + { 0x0d, 0xffff, 0x1666 }, + { 0x00, 0xffff, 0x10a3 }, + { 0x06, 0xffff, 0xf050 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x4000, 0x0000 }, }; rtl_hw_start_8168g(tp); @@ -4655,11 +4560,16 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) static void rtl_hw_start_8411_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8411_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x0f, 0xffff, 0x5200 }, - { 0x19, 0x0020, 0x0000 }, - { 0x1e, 0x0000, 0x2000 } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x37d0, 0x0820 }, + { 0x1e, 0x0000, 0x0001 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x00, 0x0000, 0x0080 }, + { 0x06, 0x0000, 0x0010 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x0000, 0x4000 }, }; rtl_hw_start_8168g(tp); @@ -4809,16 +4719,15 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp) static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) { - int rg_saw_cnt; - u32 data; static const struct ephy_info e_info_8168h_1[] = { { 0x1e, 0x0800, 0x0001 }, { 0x1d, 0x0000, 0x0800 }, { 0x05, 0xffff, 0x2089 }, { 0x06, 0xffff, 0x5881 }, - { 0x04, 0xffff, 0x154a }, + { 0x04, 0xffff, 0x854a }, { 0x01, 0xffff, 0x068b } }; + int rg_saw_cnt; /* disable aspm and clock request before access ephy */ rtl_hw_aspm_clkreq_enable(tp, false); @@ -4863,31 +4772,13 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) sw_cnt_1ms_ini = 16000000/rg_saw_cnt; sw_cnt_1ms_ini &= 0x0fff; - data = r8168_mac_ocp_read(tp, 0xd412); - data &= ~0x0fff; - data |= sw_cnt_1ms_ini; - r8168_mac_ocp_write(tp, 0xd412, data); + r8168_mac_ocp_modify(tp, 0xd412, 0x0fff, sw_cnt_1ms_ini); } - data = r8168_mac_ocp_read(tp, 0xe056); - data &= ~0xf0; - data |= 0x70; - r8168_mac_ocp_write(tp, 0xe056, data); - - data = r8168_mac_ocp_read(tp, 0xe052); - data &= ~0x6000; - data |= 0x8008; - r8168_mac_ocp_write(tp, 0xe052, data); - - data = r8168_mac_ocp_read(tp, 0xe0d6); - data &= ~0x01ff; - data |= 0x017f; - r8168_mac_ocp_write(tp, 0xe0d6, data); - - data = r8168_mac_ocp_read(tp, 0xd420); - data &= ~0x0fff; - data |= 0x047f; - r8168_mac_ocp_write(tp, 0xd420, data); + r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0070); + r8168_mac_ocp_modify(tp, 0xe052, 0x6000, 0x8008); + r8168_mac_ocp_modify(tp, 0xe0d6, 0x01ff, 0x017f); + r8168_mac_ocp_modify(tp, 0xd420, 0x0fff, 0x047f); r8168_mac_ocp_write(tp, 0xe63e, 0x0001); r8168_mac_ocp_write(tp, 0xe63e, 0x0000); @@ -4969,12 +4860,11 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) { - u32 data; static const struct ephy_info e_info_8168ep_3[] = { - { 0x00, 0xffff, 0x10a3 }, - { 0x19, 0xffff, 0x7c00 }, - { 0x1e, 0xffff, 0x20eb }, - { 0x0d, 0xffff, 0x1666 } + { 0x00, 0x0000, 0x0080 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, }; /* disable aspm and clock request before access ephy */ @@ -4986,18 +4876,9 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); - data = r8168_mac_ocp_read(tp, 0xd3e2); - data &= 0xf000; - data |= 0x0271; - r8168_mac_ocp_write(tp, 0xd3e2, data); - - data = r8168_mac_ocp_read(tp, 0xd3e4); - data &= 0xff00; - r8168_mac_ocp_write(tp, 0xd3e4, data); - - data = r8168_mac_ocp_read(tp, 0xe860); - data |= 0x0080; - r8168_mac_ocp_write(tp, 0xe860, data); + r8168_mac_ocp_modify(tp, 0xd3e2, 0x0fff, 0x0271); + r8168_mac_ocp_modify(tp, 0xd3e4, 0x00ff, 0x0000); + r8168_mac_ocp_modify(tp, 0xe860, 0x0000, 0x0080); rtl_hw_aspm_clkreq_enable(tp, true); } @@ -5240,10 +5121,7 @@ static void rtl_hw_start(struct rtl8169_private *tp) RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_init_rxcfg(tp); rtl_set_tx_config_registers(tp); - rtl_set_rx_mode(tp->dev); - /* no early-rx interrupts */ - RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); rtl_irq_enable(tp); } @@ -5268,17 +5146,6 @@ static inline void rtl8169_make_unusable_by_asic(struct RxDesc *desc) desc->opts1 &= ~cpu_to_le32(DescOwn | RsvdMask); } -static void rtl8169_free_rx_databuff(struct rtl8169_private *tp, - void **data_buff, struct RxDesc *desc) -{ - dma_unmap_single(tp_to_dev(tp), le64_to_cpu(desc->addr), - R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); - - kfree(*data_buff); - *data_buff = NULL; - rtl8169_make_unusable_by_asic(desc); -} - static inline void rtl8169_mark_to_asic(struct RxDesc *desc) { u32 eor = le32_to_cpu(desc->opts1) & RingEnd; @@ -5289,49 +5156,43 @@ static inline void rtl8169_mark_to_asic(struct RxDesc *desc) desc->opts1 = cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE); } -static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp, - struct RxDesc *desc) +static struct page *rtl8169_alloc_rx_data(struct rtl8169_private *tp, + struct RxDesc *desc) { - void *data; - dma_addr_t mapping; struct device *d = tp_to_dev(tp); int node = dev_to_node(d); + dma_addr_t mapping; + struct page *data; - data = kmalloc_node(R8169_RX_BUF_SIZE, GFP_KERNEL, node); + data = alloc_pages_node(node, GFP_KERNEL, get_order(R8169_RX_BUF_SIZE)); if (!data) return NULL; - /* Memory should be properly aligned, but better check. */ - if (!IS_ALIGNED((unsigned long)data, 8)) { - netdev_err_once(tp->dev, "RX buffer not 8-byte-aligned\n"); - goto err_out; - } - - mapping = dma_map_single(d, data, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); + mapping = dma_map_page(d, data, 0, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(d, mapping))) { if (net_ratelimit()) netif_err(tp, drv, tp->dev, "Failed to map RX DMA!\n"); - goto err_out; + __free_pages(data, get_order(R8169_RX_BUF_SIZE)); + return NULL; } desc->addr = cpu_to_le64(mapping); rtl8169_mark_to_asic(desc); - return data; -err_out: - kfree(data); - return NULL; + return data; } static void rtl8169_rx_clear(struct rtl8169_private *tp) { unsigned int i; - for (i = 0; i < NUM_RX_DESC; i++) { - if (tp->Rx_databuff[i]) { - rtl8169_free_rx_databuff(tp, tp->Rx_databuff + i, - tp->RxDescArray + i); - } + for (i = 0; i < NUM_RX_DESC && tp->Rx_databuff[i]; i++) { + dma_unmap_page(tp_to_dev(tp), + le64_to_cpu(tp->RxDescArray[i].addr), + R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); + __free_pages(tp->Rx_databuff[i], get_order(R8169_RX_BUF_SIZE)); + tp->Rx_databuff[i] = NULL; + rtl8169_make_unusable_by_asic(tp->RxDescArray + i); } } @@ -5345,7 +5206,7 @@ static int rtl8169_rx_fill(struct rtl8169_private *tp) unsigned int i; for (i = 0; i < NUM_RX_DESC; i++) { - void *data; + struct page *data; data = rtl8169_alloc_rx_data(tp, tp->RxDescArray + i); if (!data) { @@ -5507,44 +5368,6 @@ static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp, struct sk_buff *skb) return skb->len < ETH_ZLEN && tp->mac_version == RTL_GIGA_MAC_VER_34; } -static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, - struct net_device *dev); -/* r8169_csum_workaround() - * The hw limites the value the transport offset. When the offset is out of the - * range, calculate the checksum by sw. - */ -static void r8169_csum_workaround(struct rtl8169_private *tp, - struct sk_buff *skb) -{ - if (skb_is_gso(skb)) { - netdev_features_t features = tp->dev->features; - struct sk_buff *segs, *nskb; - - features &= ~(NETIF_F_SG | NETIF_F_IPV6_CSUM | NETIF_F_TSO6); - segs = skb_gso_segment(skb, features); - if (IS_ERR(segs) || !segs) - goto drop; - - do { - nskb = segs; - segs = segs->next; - nskb->next = NULL; - rtl8169_start_xmit(nskb, tp->dev); - } while (segs); - - dev_consume_skb_any(skb); - } else if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (skb_checksum_help(skb) < 0) - goto drop; - - rtl8169_start_xmit(skb, tp->dev); - } else { -drop: - tp->dev->stats.tx_dropped++; - dev_kfree_skb_any(skb); - } -} - /* msdn_giant_send_check() * According to the document of microsoft, the TCP Pseudo Header excludes the * packet length for IPv6 TCP large packets. @@ -5594,13 +5417,6 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, u32 mss = skb_shinfo(skb)->gso_size; if (mss) { - if (transport_offset > GTTCPHO_MAX) { - netif_warn(tp, tx_err, tp->dev, - "Invalid transport offset 0x%x for TSO\n", - transport_offset); - return false; - } - switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): opts[0] |= TD1_GTSENV4; @@ -5623,16 +5439,6 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, } else if (skb->ip_summed == CHECKSUM_PARTIAL) { u8 ip_protocol; - if (unlikely(rtl_test_hw_pad_bug(tp, skb))) - return !(skb_checksum_help(skb) || eth_skb_pad(skb)); - - if (transport_offset > TCPHO_MAX) { - netif_warn(tp, tx_err, tp->dev, - "Invalid transport offset 0x%x\n", - transport_offset); - return false; - } - switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): opts[1] |= TD1_IPv4_CS; @@ -5695,6 +5501,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct device *d = tp_to_dev(tp); dma_addr_t mapping; u32 opts[2], len; + bool stop_queue; + bool door_bell; int frags; if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { @@ -5709,10 +5517,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, opts[0] = DescOwn; if (rtl_chip_supports_csum_v2(tp)) { - if (!rtl8169_tso_csum_v2(tp, skb, opts)) { - r8169_csum_workaround(tp, skb); - return NETDEV_TX_OK; - } + if (!rtl8169_tso_csum_v2(tp, skb, opts)) + goto err_dma_0; } else { rtl8169_tso_csum_v1(skb, opts); } @@ -5740,13 +5546,13 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd->opts2 = cpu_to_le32(opts[1]); - netdev_sent_queue(dev, skb->len); - skb_tx_timestamp(skb); /* Force memory writes to complete before releasing descriptor */ dma_wmb(); + door_bell = __netdev_sent_queue(dev, skb->len, netdev_xmit_more()); + txd->opts1 = rtl8169_get_txd_opts1(opts[0], len, entry); /* Force all memory writes to complete before notifying device */ @@ -5754,14 +5560,20 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - RTL_W8(tp, TxPoll, NPQ); - - if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) { + stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS); + 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) + RTL_W8(tp, TxPoll, NPQ); + + 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). @@ -5789,6 +5601,39 @@ err_stop_0: return NETDEV_TX_BUSY; } +static netdev_features_t rtl8169_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + int transport_offset = skb_transport_offset(skb); + struct rtl8169_private *tp = netdev_priv(dev); + + if (skb_is_gso(skb)) { + if (transport_offset > GTTCPHO_MAX && + rtl_chip_supports_csum_v2(tp)) + features &= ~NETIF_F_ALL_TSO; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (skb->len < ETH_ZLEN) { + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_11: + case RTL_GIGA_MAC_VER_12: + case RTL_GIGA_MAC_VER_17: + case RTL_GIGA_MAC_VER_34: + features &= ~NETIF_F_CSUM_MASK; + break; + default: + break; + } + } + + if (transport_offset > TCPHO_MAX && + rtl_chip_supports_csum_v2(tp)) + features &= ~NETIF_F_CSUM_MASK; + } + + return vlan_features_check(skb, features); +} + static void rtl8169_pcierr_interrupt(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); @@ -5908,23 +5753,6 @@ static inline void rtl8169_rx_csum(struct sk_buff *skb, u32 opts1) skb_checksum_none_assert(skb); } -static struct sk_buff *rtl8169_try_rx_copy(void *data, - struct rtl8169_private *tp, - int pkt_size, - dma_addr_t addr) -{ - struct sk_buff *skb; - struct device *d = tp_to_dev(tp); - - dma_sync_single_for_cpu(d, addr, pkt_size, DMA_FROM_DEVICE); - prefetch(data); - skb = napi_alloc_skb(&tp->napi, pkt_size); - if (skb) - skb_copy_to_linear_data(skb, data, pkt_size); - - return skb; -} - static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget) { unsigned int cur_rx, rx_left; @@ -5934,6 +5762,7 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget for (rx_left = min(budget, NUM_RX_DESC); rx_left > 0; rx_left--, cur_rx++) { unsigned int entry = cur_rx % NUM_RX_DESC; + const void *rx_buf = page_address(tp->Rx_databuff[entry]); struct RxDesc *desc = tp->RxDescArray + entry; u32 status; @@ -5960,17 +5789,13 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget goto process_pkt; } } else { + unsigned int pkt_size; struct sk_buff *skb; - dma_addr_t addr; - int pkt_size; process_pkt: - addr = le64_to_cpu(desc->addr); + pkt_size = status & GENMASK(13, 0); if (likely(!(dev->features & NETIF_F_RXFCS))) - pkt_size = (status & 0x00003fff) - 4; - else - pkt_size = status & 0x00003fff; - + pkt_size -= ETH_FCS_LEN; /* * The driver does not support incoming fragmented * frames. They are seen as a symptom of over-mtu @@ -5982,15 +5807,22 @@ process_pkt: goto release_descriptor; } - skb = rtl8169_try_rx_copy(tp->Rx_databuff[entry], - tp, pkt_size, addr); - if (!skb) { + dma_sync_single_for_cpu(tp_to_dev(tp), + le64_to_cpu(desc->addr), + pkt_size, DMA_FROM_DEVICE); + + skb = napi_alloc_skb(&tp->napi, pkt_size); + if (unlikely(!skb)) { dev->stats.rx_dropped++; goto release_descriptor; } + prefetch(rx_buf); + skb_copy_to_linear_data(skb, rx_buf, pkt_size); + skb->tail += pkt_size; + skb->len = pkt_size; + rtl8169_rx_csum(skb, status); - skb_put(skb, pkt_size); skb->protocol = eth_type_trans(skb, dev); rtl8169_rx_vlan_tag(desc, skb); @@ -6331,7 +6163,7 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->multicast = dev->stats.multicast; /* - * Fetch additonal counter values missing in stats collected by driver + * Fetch additional counter values missing in stats collected by driver * from tally counters. */ if (pm_runtime_active(&pdev->dev)) @@ -6555,6 +6387,7 @@ static const struct net_device_ops rtl_netdev_ops = { .ndo_stop = rtl8169_close, .ndo_get_stats64 = rtl8169_get_stats64, .ndo_start_xmit = rtl8169_start_xmit, + .ndo_features_check = rtl8169_features_check, .ndo_tx_timeout = rtl8169_tx_timeout, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = rtl8169_change_mtu, @@ -6691,8 +6524,6 @@ static int r8169_mdio_register(struct rtl8169_private *tp) static void rtl_hw_init_8168g(struct rtl8169_private *tp) { - u32 data; - tp->ocp_base = OCP_STD_PHY_BASE; RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); @@ -6707,16 +6538,12 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp) msleep(1); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); - data = r8168_mac_ocp_read(tp, 0xe8de); - data &= ~(1 << 14); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0); if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42)) return; - data = r8168_mac_ocp_read(tp, 0xe8de); - data |= (1 << 15); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, 0, BIT(15)); rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42); } @@ -6916,11 +6743,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netif_napi_add(dev, &tp->napi, rtl8169_poll, NAPI_POLL_WEIGHT); - /* don't enable SG, IP_CSUM and TSO by default - it might not work - * properly for all devices */ - dev->features |= NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; - + dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | + NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; @@ -6938,8 +6763,22 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Disallow toggling */ dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX; - if (rtl_chip_supports_csum_v2(tp)) + if (rtl_chip_supports_csum_v2(tp)) { dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + dev->features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + dev->gso_max_size = RTL_GSO_MAX_SIZE_V2; + dev->gso_max_segs = RTL_GSO_MAX_SEGS_V2; + } else { + dev->gso_max_size = RTL_GSO_MAX_SIZE_V1; + dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1; + } + + /* RTL8168e-vl has a HW issue with TSO */ + if (tp->mac_version == RTL_GIGA_MAC_VER_34) { + dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + } dev->hw_features |= NETIF_F_RXALL; dev->hw_features |= NETIF_F_RXFCS; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 16d6952c312a..0ec13f520e90 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -508,7 +508,7 @@ static ssize_t efx_ef10_show_link_control_flag(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", ((efx->mcdi->fn_flags) & @@ -520,7 +520,7 @@ static ssize_t efx_ef10_show_primary_flag(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", ((efx->mcdi->fn_flags) & diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index ab58b837df47..2fef7402233e 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2517,7 +2517,7 @@ static struct notifier_block efx_netdev_notifier = { static ssize_t show_phy_type(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", efx->phy_type); } static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); @@ -2526,7 +2526,7 @@ static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled); @@ -2534,7 +2534,7 @@ static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr, static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); bool enable = count > 0 && *buf != '0'; @@ -3654,7 +3654,7 @@ static int efx_pci_sriov_configure(struct pci_dev *dev, int num_vfs) static int efx_pm_freeze(struct device *dev) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); rtnl_lock(); @@ -3675,7 +3675,7 @@ static int efx_pm_freeze(struct device *dev) static int efx_pm_thaw(struct device *dev) { int rc; - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); rtnl_lock(); diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 9b15c39ac670..eecc348b1c32 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2256,7 +2256,7 @@ static struct notifier_block ef4_netdev_notifier = { static ssize_t show_phy_type(struct device *dev, struct device_attribute *attr, char *buf) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", efx->phy_type); } static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); @@ -2999,7 +2999,7 @@ static int ef4_pci_probe(struct pci_dev *pci_dev, static int ef4_pm_freeze(struct device *dev) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); rtnl_lock(); @@ -3020,7 +3020,7 @@ static int ef4_pm_freeze(struct device *dev) static int ef4_pm_thaw(struct device *dev) { int rc; - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); rtnl_lock(); diff --git a/drivers/net/ethernet/sfc/falcon/falcon_boards.c b/drivers/net/ethernet/sfc/falcon/falcon_boards.c index 839189dab98e..605f486fa675 100644 --- a/drivers/net/ethernet/sfc/falcon/falcon_boards.c +++ b/drivers/net/ethernet/sfc/falcon/falcon_boards.c @@ -357,7 +357,7 @@ fail_on: static ssize_t show_phy_flash_cfg(struct device *dev, struct device_attribute *attr, char *buf) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", !!(efx->phy_mode & PHY_MODE_SPECIAL)); } @@ -365,7 +365,7 @@ static ssize_t set_phy_flash_cfg(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); enum ef4_phy_mode old_mode, new_mode; int err; @@ -454,13 +454,13 @@ static int sfe4001_init(struct ef4_nic *efx) #if IS_ENABLED(CONFIG_SENSORS_LM90) board->hwmon_client = - i2c_new_device(&board->i2c_adap, &sfe4001_hwmon_info); + i2c_new_client_device(&board->i2c_adap, &sfe4001_hwmon_info); #else board->hwmon_client = - i2c_new_dummy(&board->i2c_adap, sfe4001_hwmon_info.addr); + i2c_new_dummy_device(&board->i2c_adap, sfe4001_hwmon_info.addr); #endif - if (!board->hwmon_client) - return -EIO; + if (IS_ERR(board->hwmon_client)) + return PTR_ERR(board->hwmon_client); /* Raise board/PHY high limit from 85 to 90 degrees Celsius */ rc = i2c_smbus_write_byte_data(board->hwmon_client, @@ -468,9 +468,9 @@ static int sfe4001_init(struct ef4_nic *efx) if (rc) goto fail_hwmon; - board->ioexp_client = i2c_new_dummy(&board->i2c_adap, PCA9539); - if (!board->ioexp_client) { - rc = -EIO; + board->ioexp_client = i2c_new_dummy_device(&board->i2c_adap, PCA9539); + if (IS_ERR(board->ioexp_client)) { + rc = PTR_ERR(board->ioexp_client); goto fail_hwmon; } diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c index fd850d3d8ec0..05ea3523890a 100644 --- a/drivers/net/ethernet/sfc/falcon/rx.c +++ b/drivers/net/ethernet/sfc/falcon/rx.c @@ -424,7 +424,6 @@ ef4_rx_packet_gro(struct ef4_channel *channel, struct ef4_rx_buffer *rx_buf, unsigned int n_frags, u8 *eh) { struct napi_struct *napi = &channel->napi_str; - gro_result_t gro_result; struct ef4_nic *efx = channel->efx; struct sk_buff *skb; @@ -460,9 +459,7 @@ ef4_rx_packet_gro(struct ef4_channel *channel, struct ef4_rx_buffer *rx_buf, skb_record_rx_queue(skb, channel->rx_queue.core_index); - gro_result = napi_gro_frags(napi); - if (gro_result != GRO_DROP) - channel->irq_mod_score += 2; + napi_gro_frags(napi); } /* Allocate and construct an SKB around page fragments */ diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index d5db045535d3..85ec07f5a674 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -412,7 +412,6 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, unsigned int n_frags, u8 *eh) { struct napi_struct *napi = &channel->napi_str; - gro_result_t gro_result; struct efx_nic *efx = channel->efx; struct sk_buff *skb; @@ -449,9 +448,7 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, skb_record_rx_queue(skb, channel->rx_queue.core_index); - gro_result = napi_gro_frags(napi); - if (gro_result != GRO_DROP) - channel->irq_mod_score += 2; + napi_gro_frags(napi); } /* Allocate and construct an SKB around page fragments */ diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 31ec56091a5d..65e81ec1b314 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -274,7 +274,7 @@ static void efx_skb_copy_bits_to_pio(struct efx_nic *efx, struct sk_buff *skb, vaddr = kmap_atomic(skb_frag_page(f)); - efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + f->page_offset, + efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + skb_frag_off(f), skb_frag_size(f), copy_buf); kunmap_atomic(vaddr); } diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 6e07f5ebacfc..85eaccbbbac1 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -191,6 +191,8 @@ struct sis900_private { unsigned int tx_full; /* The Tx queue is full. */ u8 host_bridge_rev; u8 chipset_rev; + /* EEPROM data */ + int eeprom_size; }; MODULE_AUTHOR("Jim Huang <cmhuang@sis.com.tw>, Ollie Lho <ollie@sis.com.tw>"); @@ -475,6 +477,8 @@ static int sis900_probe(struct pci_dev *pci_dev, sis_priv->pci_dev = pci_dev; spin_lock_init(&sis_priv->lock); + sis_priv->eeprom_size = 24; + pci_set_drvdata(pci_dev, net_dev); ring_space = pci_alloc_consistent(pci_dev, TX_TOTAL_SIZE, &ring_dma); @@ -2122,6 +2126,68 @@ static void sis900_get_wol(struct net_device *net_dev, struct ethtool_wolinfo *w wol->supported = (WAKE_PHY | WAKE_MAGIC); } +static int sis900_get_eeprom_len(struct net_device *dev) +{ + struct sis900_private *sis_priv = netdev_priv(dev); + + return sis_priv->eeprom_size; +} + +static int sis900_read_eeprom(struct net_device *net_dev, u8 *buf) +{ + struct sis900_private *sis_priv = netdev_priv(net_dev); + void __iomem *ioaddr = sis_priv->ioaddr; + int wait, ret = -EAGAIN; + u16 signature; + u16 *ebuf = (u16 *)buf; + int i; + + if (sis_priv->chipset_rev == SIS96x_900_REV) { + sw32(mear, EEREQ); + for (wait = 0; wait < 2000; wait++) { + if (sr32(mear) & EEGNT) { + /* read 16 bits, and index by 16 bits */ + for (i = 0; i < sis_priv->eeprom_size / 2; i++) + ebuf[i] = (u16)read_eeprom(ioaddr, i); + ret = 0; + break; + } + udelay(1); + } + sw32(mear, EEDONE); + } else { + signature = (u16)read_eeprom(ioaddr, EEPROMSignature); + if (signature != 0xffff && signature != 0x0000) { + /* read 16 bits, and index by 16 bits */ + for (i = 0; i < sis_priv->eeprom_size / 2; i++) + ebuf[i] = (u16)read_eeprom(ioaddr, i); + ret = 0; + } + } + return ret; +} + +#define SIS900_EEPROM_MAGIC 0xBABE +static int sis900_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) +{ + struct sis900_private *sis_priv = netdev_priv(dev); + u8 *eebuf; + int res; + + eebuf = kmalloc(sis_priv->eeprom_size, GFP_KERNEL); + if (!eebuf) + return -ENOMEM; + + eeprom->magic = SIS900_EEPROM_MAGIC; + spin_lock_irq(&sis_priv->lock); + res = sis900_read_eeprom(dev, eebuf); + spin_unlock_irq(&sis_priv->lock); + if (!res) + memcpy(data, eebuf + eeprom->offset, eeprom->len); + kfree(eebuf); + return res; +} + static const struct ethtool_ops sis900_ethtool_ops = { .get_drvinfo = sis900_get_drvinfo, .get_msglevel = sis900_get_msglevel, @@ -2132,6 +2198,8 @@ static const struct ethtool_ops sis900_ethtool_ops = { .set_wol = sis900_set_wol, .get_link_ksettings = sis900_get_link_ksettings, .set_link_ksettings = sis900_set_link_ksettings, + .get_eeprom_len = sis900_get_eeprom_len, + .get_eeprom = sis900_get_eeprom, }; /** diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 51a7b48db4bc..87ab0b5da91e 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1573,10 +1573,8 @@ static int ave_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "IRQ not found\n"); + if (irq < 0) return irq; - } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); base = devm_ioremap_resource(dev, res); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index ed872eed1cab..49aa56ca09cc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -75,6 +75,7 @@ struct stmmac_extra_stats { unsigned long rx_missed_cntr; unsigned long rx_overflow_cntr; unsigned long rx_vlan; + unsigned long rx_split_hdr_pkt_n; /* Tx/Rx IRQ error info */ unsigned long tx_undeflow_irq; unsigned long tx_process_stopped_irq; @@ -354,6 +355,11 @@ struct dma_features { unsigned int frpbs; unsigned int frpes; unsigned int addr64; + unsigned int rssen; + unsigned int vlhash; + unsigned int sphen; + unsigned int vlins; + unsigned int dvlan; }; /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ @@ -381,6 +387,16 @@ struct dma_features { #define JUMBO_LEN 9000 +/* Receive Side Scaling */ +#define STMMAC_RSS_HASH_KEY_SIZE 40 +#define STMMAC_RSS_MAX_TABLE_SIZE 256 + +/* VLAN */ +#define STMMAC_VLAN_NONE 0x0 +#define STMMAC_VLAN_REMOVE 0x1 +#define STMMAC_VLAN_INSERT 0x2 +#define STMMAC_VLAN_REPLACE 0x3 + extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 3a14cdd01f5f..f2197b066ed1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -333,6 +333,9 @@ static void *tegra_eqos_probe(struct platform_device *pdev, usleep_range(2000, 4000); gpiod_set_value(eqos->reset, 0); + /* MDIO bus was already reset just above */ + data->mdio_bus_data->needs_reset = false; + eqos->rst = devm_reset_control_get(&pdev->dev, "eqos"); if (IS_ERR(eqos->rst)) { err = PTR_ERR(eqos->rst); @@ -428,13 +431,8 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) * resource initialization is done in the glue logic. */ stmmac_res.irq = platform_get_irq(pdev, 0); - if (stmmac_res.irq < 0) { - if (stmmac_res.irq != -EPROBE_DEFER) - dev_err(&pdev->dev, - "IRQ configuration information not found\n"); - + if (stmmac_res.irq < 0) return stmmac_res.irq; - } stmmac_res.wol_irq = stmmac_res.irq; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 3174b701aa90..7357b8bdc128 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -32,6 +32,9 @@ #define XGMAC_CONFIG_ARPEN BIT(31) #define XGMAC_CONFIG_GPSL GENMASK(29, 16) #define XGMAC_CONFIG_GPSL_SHIFT 16 +#define XGMAC_CONFIG_HDSMS GENMASK(14, 12) +#define XGMAC_CONFIG_HDSMS_SHIFT 12 +#define XGMAC_CONFIG_HDSMS_256 (0x2 << XGMAC_CONFIG_HDSMS_SHIFT) #define XGMAC_CONFIG_S2KP BIT(11) #define XGMAC_CONFIG_LM BIT(10) #define XGMAC_CONFIG_IPC BIT(9) @@ -44,6 +47,7 @@ #define XGMAC_CORE_INIT_RX 0 #define XGMAC_PACKET_FILTER 0x00000008 #define XGMAC_FILTER_RA BIT(31) +#define XGMAC_FILTER_VTFE BIT(16) #define XGMAC_FILTER_HPF BIT(10) #define XGMAC_FILTER_PCF BIT(7) #define XGMAC_FILTER_PM BIT(4) @@ -51,6 +55,19 @@ #define XGMAC_FILTER_PR BIT(0) #define XGMAC_HASH_TABLE(x) (0x00000010 + (x) * 4) #define XGMAC_MAX_HASH_TABLE 8 +#define XGMAC_VLAN_TAG 0x00000050 +#define XGMAC_VLAN_EDVLP BIT(26) +#define XGMAC_VLAN_VTHM BIT(25) +#define XGMAC_VLAN_DOVLTC BIT(20) +#define XGMAC_VLAN_ESVL BIT(18) +#define XGMAC_VLAN_ETV BIT(16) +#define XGMAC_VLAN_VID GENMASK(15, 0) +#define XGMAC_VLAN_HASH_TABLE 0x00000058 +#define XGMAC_VLAN_INCL 0x00000060 +#define XGMAC_VLAN_VLTI BIT(20) +#define XGMAC_VLAN_CSVL BIT(19) +#define XGMAC_VLAN_VLC GENMASK(17, 16) +#define XGMAC_VLAN_VLC_SHIFT 16 #define XGMAC_RXQ_CTRL0 0x000000a0 #define XGMAC_RXQEN(x) GENMASK((x) * 2 + 1, (x) * 2) #define XGMAC_RXQEN_SHIFT(x) ((x) * 2) @@ -59,6 +76,7 @@ #define XGMAC_PSRQ(x) GENMASK((x) * 8 + 7, (x) * 8) #define XGMAC_PSRQ_SHIFT(x) ((x) * 8) #define XGMAC_INT_STATUS 0x000000b0 +#define XGMAC_LPIIS BIT(5) #define XGMAC_PMTIS BIT(4) #define XGMAC_INT_EN 0x000000b4 #define XGMAC_TSIE BIT(12) @@ -76,19 +94,34 @@ #define XGMAC_RWKPKTEN BIT(2) #define XGMAC_MGKPKTEN BIT(1) #define XGMAC_PWRDWN BIT(0) +#define XGMAC_LPI_CTRL 0x000000d0 +#define XGMAC_TXCGE BIT(21) +#define XGMAC_LPITXA BIT(19) +#define XGMAC_PLS BIT(17) +#define XGMAC_LPITXEN BIT(16) +#define XGMAC_RLPIEX BIT(3) +#define XGMAC_RLPIEN BIT(2) +#define XGMAC_TLPIEX BIT(1) +#define XGMAC_TLPIEN BIT(0) +#define XGMAC_LPI_TIMER_CTRL 0x000000d4 #define XGMAC_HW_FEATURE0 0x0000011c #define XGMAC_HWFEAT_SAVLANINS BIT(27) #define XGMAC_HWFEAT_RXCOESEL BIT(16) #define XGMAC_HWFEAT_TXCOESEL BIT(14) +#define XGMAC_HWFEAT_EEESEL BIT(13) #define XGMAC_HWFEAT_TSSEL BIT(12) #define XGMAC_HWFEAT_AVSEL BIT(11) #define XGMAC_HWFEAT_RAVSEL BIT(10) #define XGMAC_HWFEAT_ARPOFFSEL BIT(9) +#define XGMAC_HWFEAT_MMCSEL BIT(8) #define XGMAC_HWFEAT_MGKSEL BIT(7) #define XGMAC_HWFEAT_RWKSEL BIT(6) +#define XGMAC_HWFEAT_VLHASH BIT(4) #define XGMAC_HWFEAT_GMIISEL BIT(1) #define XGMAC_HW_FEATURE1 0x00000120 +#define XGMAC_HWFEAT_RSSEN BIT(20) #define XGMAC_HWFEAT_TSOEN BIT(18) +#define XGMAC_HWFEAT_SPHEN BIT(17) #define XGMAC_HWFEAT_ADDR64 GENMASK(15, 14) #define XGMAC_HWFEAT_TXFIFOSIZE GENMASK(10, 6) #define XGMAC_HWFEAT_RXFIFOSIZE GENMASK(4, 0) @@ -98,6 +131,16 @@ #define XGMAC_HWFEAT_RXCHCNT GENMASK(15, 12) #define XGMAC_HWFEAT_TXQCNT GENMASK(9, 6) #define XGMAC_HWFEAT_RXQCNT GENMASK(3, 0) +#define XGMAC_HW_FEATURE3 0x00000128 +#define XGMAC_HWFEAT_ASP GENMASK(15, 14) +#define XGMAC_HWFEAT_DVLAN BIT(13) +#define XGMAC_HWFEAT_FRPES GENMASK(12, 11) +#define XGMAC_HWFEAT_FRPPB GENMASK(10, 9) +#define XGMAC_HWFEAT_FRPSEL BIT(3) +#define XGMAC_MAC_DPP_FSM_INT_STATUS 0x00000150 +#define XGMAC_MAC_FSM_CONTROL 0x00000158 +#define XGMAC_PRTYEN BIT(1) +#define XGMAC_TMOUTEN BIT(0) #define XGMAC_MDIO_ADDR 0x00000200 #define XGMAC_MDIO_DATA 0x00000204 #define XGMAC_MDIO_C22P 0x00000220 @@ -108,14 +151,45 @@ #define XGMAC_DCS_SHIFT 16 #define XGMAC_ADDRx_LOW(x) (0x00000304 + (x) * 0x8) #define XGMAC_ARP_ADDR 0x00000c10 +#define XGMAC_RSS_CTRL 0x00000c80 +#define XGMAC_UDP4TE BIT(3) +#define XGMAC_TCP4TE BIT(2) +#define XGMAC_IP2TE BIT(1) +#define XGMAC_RSSE BIT(0) +#define XGMAC_RSS_ADDR 0x00000c88 +#define XGMAC_RSSIA_SHIFT 8 +#define XGMAC_ADDRT BIT(2) +#define XGMAC_CT BIT(1) +#define XGMAC_OB BIT(0) +#define XGMAC_RSS_DATA 0x00000c8c #define XGMAC_TIMESTAMP_STATUS 0x00000d20 #define XGMAC_TXTSC BIT(15) #define XGMAC_TXTIMESTAMP_NSEC 0x00000d30 #define XGMAC_TXTSSTSLO GENMASK(30, 0) #define XGMAC_TXTIMESTAMP_SEC 0x00000d34 +#define XGMAC_PPS_CONTROL 0x00000d70 +#define XGMAC_PPS_MAXIDX(x) ((((x) + 1) * 8) - 1) +#define XGMAC_PPS_MINIDX(x) ((x) * 8) +#define XGMAC_PPSx_MASK(x) \ + GENMASK(XGMAC_PPS_MAXIDX(x), XGMAC_PPS_MINIDX(x)) +#define XGMAC_TRGTMODSELx(x, val) \ + GENMASK(XGMAC_PPS_MAXIDX(x) - 1, XGMAC_PPS_MAXIDX(x) - 2) & \ + ((val) << (XGMAC_PPS_MAXIDX(x) - 2)) +#define XGMAC_PPSCMDx(x, val) \ + GENMASK(XGMAC_PPS_MINIDX(x) + 3, XGMAC_PPS_MINIDX(x)) & \ + ((val) << XGMAC_PPS_MINIDX(x)) +#define XGMAC_PPSCMD_START 0x2 +#define XGMAC_PPSCMD_STOP 0x5 +#define XGMAC_PPSEN0 BIT(4) +#define XGMAC_PPSx_TARGET_TIME_SEC(x) (0x00000d80 + (x) * 0x10) +#define XGMAC_PPSx_TARGET_TIME_NSEC(x) (0x00000d84 + (x) * 0x10) +#define XGMAC_TRGTBUSY0 BIT(31) +#define XGMAC_PPSx_INTERVAL(x) (0x00000d88 + (x) * 0x10) +#define XGMAC_PPSx_WIDTH(x) (0x00000d8c + (x) * 0x10) /* MTL Registers */ #define XGMAC_MTL_OPMODE 0x00001000 +#define XGMAC_FRPE BIT(15) #define XGMAC_ETSALG GENMASK(6, 5) #define XGMAC_WRR (0x0 << 5) #define XGMAC_WFQ (0x1 << 5) @@ -124,8 +198,32 @@ #define XGMAC_MTL_INT_STATUS 0x00001020 #define XGMAC_MTL_RXQ_DMA_MAP0 0x00001030 #define XGMAC_MTL_RXQ_DMA_MAP1 0x00001034 -#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 3, (x) * 8) +#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 7, (x) * 8) #define XGMAC_QxMDMACH_SHIFT(x) ((x) * 8) +#define XGMAC_QDDMACH BIT(7) +#define XGMAC_TC_PRTY_MAP0 0x00001040 +#define XGMAC_TC_PRTY_MAP1 0x00001044 +#define XGMAC_PSTC(x) GENMASK((x) * 8 + 7, (x) * 8) +#define XGMAC_PSTC_SHIFT(x) ((x) * 8) +#define XGMAC_MTL_RXP_CONTROL_STATUS 0x000010a0 +#define XGMAC_RXPI BIT(31) +#define XGMAC_NPE GENMASK(23, 16) +#define XGMAC_NVE GENMASK(7, 0) +#define XGMAC_MTL_RXP_IACC_CTRL_ST 0x000010b0 +#define XGMAC_STARTBUSY BIT(31) +#define XGMAC_WRRDN BIT(16) +#define XGMAC_ADDR GENMASK(9, 0) +#define XGMAC_MTL_RXP_IACC_DATA 0x000010b4 +#define XGMAC_MTL_ECC_CONTROL 0x000010c0 +#define XGMAC_MTL_SAFETY_INT_STATUS 0x000010c4 +#define XGMAC_MEUIS BIT(1) +#define XGMAC_MECIS BIT(0) +#define XGMAC_MTL_ECC_INT_ENABLE 0x000010c8 +#define XGMAC_RPCEIE BIT(12) +#define XGMAC_ECEIE BIT(8) +#define XGMAC_RXCEIE BIT(4) +#define XGMAC_TXCEIE BIT(0) +#define XGMAC_MTL_ECC_INT_STATUS 0x000010cc #define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x))) #define XGMAC_TQS GENMASK(25, 16) #define XGMAC_TQS_SHIFT 16 @@ -164,6 +262,7 @@ #define XGMAC_RXOVFIS BIT(16) #define XGMAC_ABPSIS BIT(1) #define XGMAC_TXUNFIS BIT(0) +#define XGMAC_MAC_REGSIZE (XGMAC_MTL_QINT_STATUS(15) / 4) /* DMA Registers */ #define XGMAC_DMA_MODE 0x00003000 @@ -190,7 +289,18 @@ #define XGMAC_TDPS GENMASK(29, 0) #define XGMAC_RX_EDMA_CTRL 0x00003044 #define XGMAC_RDPS GENMASK(29, 0) +#define XGMAC_DMA_SAFETY_INT_STATUS 0x00003064 +#define XGMAC_MCSIS BIT(31) +#define XGMAC_MSUIS BIT(29) +#define XGMAC_MSCIS BIT(28) +#define XGMAC_DEUIS BIT(1) +#define XGMAC_DECIS BIT(0) +#define XGMAC_DMA_ECC_INT_ENABLE 0x00003068 +#define XGMAC_DCEIE BIT(1) +#define XGMAC_TCEIE BIT(0) +#define XGMAC_DMA_ECC_INT_STATUS 0x0000306c #define XGMAC_DMA_CH_CONTROL(x) (0x00003100 + (0x80 * (x))) +#define XGMAC_SPH BIT(24) #define XGMAC_PBLx8 BIT(16) #define XGMAC_DMA_CH_TX_CONTROL(x) (0x00003104 + (0x80 * (x))) #define XGMAC_TxPBL GENMASK(21, 16) @@ -230,12 +340,17 @@ #define XGMAC_TBU BIT(2) #define XGMAC_TPS BIT(1) #define XGMAC_TI BIT(0) +#define XGMAC_REGSIZE ((0x0000317c + (0x80 * 15)) / 4) /* Descriptors */ +#define XGMAC_TDES2_IVT GENMASK(31, 16) +#define XGMAC_TDES2_IVT_SHIFT 16 #define XGMAC_TDES2_IOC BIT(31) #define XGMAC_TDES2_TTSE BIT(30) #define XGMAC_TDES2_B2L GENMASK(29, 16) #define XGMAC_TDES2_B2L_SHIFT 16 +#define XGMAC_TDES2_VTIR GENMASK(15, 14) +#define XGMAC_TDES2_VTIR_SHIFT 14 #define XGMAC_TDES2_B1L GENMASK(13, 0) #define XGMAC_TDES3_OWN BIT(31) #define XGMAC_TDES3_CTXT BIT(30) @@ -244,18 +359,33 @@ #define XGMAC_TDES3_CPC GENMASK(27, 26) #define XGMAC_TDES3_CPC_SHIFT 26 #define XGMAC_TDES3_TCMSSV BIT(26) +#define XGMAC_TDES3_SAIC GENMASK(25, 23) +#define XGMAC_TDES3_SAIC_SHIFT 23 #define XGMAC_TDES3_THL GENMASK(22, 19) #define XGMAC_TDES3_THL_SHIFT 19 +#define XGMAC_TDES3_IVTIR GENMASK(19, 18) +#define XGMAC_TDES3_IVTIR_SHIFT 18 #define XGMAC_TDES3_TSE BIT(18) +#define XGMAC_TDES3_IVLTV BIT(17) #define XGMAC_TDES3_CIC GENMASK(17, 16) #define XGMAC_TDES3_CIC_SHIFT 16 #define XGMAC_TDES3_TPL GENMASK(17, 0) +#define XGMAC_TDES3_VLTV BIT(16) +#define XGMAC_TDES3_VT GENMASK(15, 0) #define XGMAC_TDES3_FL GENMASK(14, 0) +#define XGMAC_RDES2_HL GENMASK(9, 0) #define XGMAC_RDES3_OWN BIT(31) #define XGMAC_RDES3_CTXT BIT(30) #define XGMAC_RDES3_IOC BIT(30) #define XGMAC_RDES3_LD BIT(28) #define XGMAC_RDES3_CDA BIT(27) +#define XGMAC_RDES3_RSV BIT(26) +#define XGMAC_RDES3_L34T GENMASK(23, 20) +#define XGMAC_RDES3_L34T_SHIFT 20 +#define XGMAC_L34T_IP4TCP 0x1 +#define XGMAC_L34T_IP4UDP 0x2 +#define XGMAC_L34T_IP6TCP 0x9 +#define XGMAC_L34T_IP6UDP 0xA #define XGMAC_RDES3_ES BIT(15) #define XGMAC_RDES3_PL GENMASK(13, 0) #define XGMAC_RDES3_TSD BIT(6) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 85c68b7ee8c6..e534a3aaf4a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -6,7 +6,9 @@ #include <linux/bitrev.h> #include <linux/crc32.h> +#include <linux/iopoll.h> #include "stmmac.h" +#include "stmmac_ptp.h" #include "dwxgmac2.h" static void dwxgmac2_core_init(struct mac_device_info *hw, @@ -118,6 +120,23 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, writel(value, ioaddr + reg); } +static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, + u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value, reg; + + reg = (queue < 4) ? XGMAC_TC_PRTY_MAP0 : XGMAC_TC_PRTY_MAP1; + if (queue >= 4) + queue -= 4; + + value = readl(ioaddr + reg); + value &= ~XGMAC_PSTC(queue); + value |= (prio << XGMAC_PSTC_SHIFT(queue)) & XGMAC_PSTC(queue); + + writel(value, ioaddr + reg); +} + static void dwxgmac2_prog_mtl_rx_algorithms(struct mac_device_info *hw, u32 rx_alg) { @@ -144,7 +163,9 @@ static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw, u32 tx_alg) { void __iomem *ioaddr = hw->pcsr; + bool ets = true; u32 value; + int i; value = readl(ioaddr + XGMAC_MTL_OPMODE); value &= ~XGMAC_ETSALG; @@ -160,10 +181,28 @@ static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw, value |= XGMAC_DWRR; break; default: + ets = false; break; } writel(value, ioaddr + XGMAC_MTL_OPMODE); + + /* Set ETS if desired */ + for (i = 0; i < MTL_MAX_TX_QUEUES; i++) { + value = readl(ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(i)); + value &= ~XGMAC_TSA; + if (ets) + value |= XGMAC_ETS; + writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(i)); + } +} + +static void dwxgmac2_set_mtl_tx_queue_weight(struct mac_device_info *hw, + u32 weight, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + + writel(weight, ioaddr + XGMAC_MTL_TCx_QUANTUM_WEIGHT(queue)); } static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue, @@ -200,11 +239,21 @@ static void dwxgmac2_config_cbs(struct mac_device_info *hw, writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); } +static void dwxgmac2_dump_regs(struct mac_device_info *hw, u32 *reg_space) +{ + void __iomem *ioaddr = hw->pcsr; + int i; + + for (i = 0; i < XGMAC_MAC_REGSIZE; i++) + reg_space[i] = readl(ioaddr + i * 4); +} + static int dwxgmac2_host_irq_status(struct mac_device_info *hw, struct stmmac_extra_stats *x) { void __iomem *ioaddr = hw->pcsr; u32 stat, en; + int ret = 0; en = readl(ioaddr + XGMAC_INT_EN); stat = readl(ioaddr + XGMAC_INT_STATUS); @@ -216,7 +265,24 @@ static int dwxgmac2_host_irq_status(struct mac_device_info *hw, readl(ioaddr + XGMAC_PMT); } - return 0; + if (stat & XGMAC_LPIIS) { + u32 lpi = readl(ioaddr + XGMAC_LPI_CTRL); + + if (lpi & XGMAC_TLPIEN) { + ret |= CORE_IRQ_TX_PATH_IN_LPI_MODE; + x->irq_tx_path_in_lpi_mode_n++; + } + if (lpi & XGMAC_TLPIEX) { + ret |= CORE_IRQ_TX_PATH_EXIT_LPI_MODE; + x->irq_tx_path_exit_lpi_mode_n++; + } + if (lpi & XGMAC_RLPIEN) + x->irq_rx_path_in_lpi_mode_n++; + if (lpi & XGMAC_RLPIEX) + x->irq_rx_path_exit_lpi_mode_n++; + } + + return ret; } static int dwxgmac2_host_mtl_irq_status(struct mac_device_info *hw, u32 chan) @@ -309,6 +375,53 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, addr[5] = (hi_addr >> 8) & 0xff; } +static void dwxgmac2_set_eee_mode(struct mac_device_info *hw, + bool en_tx_lpi_clockgating) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_LPI_CTRL); + + value |= XGMAC_LPITXEN | XGMAC_LPITXA; + if (en_tx_lpi_clockgating) + value |= XGMAC_TXCGE; + + writel(value, ioaddr + XGMAC_LPI_CTRL); +} + +static void dwxgmac2_reset_eee_mode(struct mac_device_info *hw) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_LPI_CTRL); + value &= ~(XGMAC_LPITXEN | XGMAC_LPITXA | XGMAC_TXCGE); + writel(value, ioaddr + XGMAC_LPI_CTRL); +} + +static void dwxgmac2_set_eee_pls(struct mac_device_info *hw, int link) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_LPI_CTRL); + if (link) + value |= XGMAC_PLS; + else + value &= ~XGMAC_PLS; + writel(value, ioaddr + XGMAC_LPI_CTRL); +} + +static void dwxgmac2_set_eee_timer(struct mac_device_info *hw, int ls, int tw) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = (tw & 0xffff) | ((ls & 0x3ff) << 16); + writel(value, ioaddr + XGMAC_LPI_TIMER_CTRL); +} + static void dwxgmac2_set_mchash(void __iomem *ioaddr, u32 *mcfilterbits, int mcbitslog2) { @@ -402,36 +515,694 @@ static void dwxgmac2_set_mac_loopback(void __iomem *ioaddr, bool enable) writel(value, ioaddr + XGMAC_RX_CONFIG); } +static int dwxgmac2_rss_write_reg(void __iomem *ioaddr, bool is_key, int idx, + u32 val) +{ + u32 ctrl = 0; + + writel(val, ioaddr + XGMAC_RSS_DATA); + ctrl |= idx << XGMAC_RSSIA_SHIFT; + ctrl |= is_key ? XGMAC_ADDRT : 0x0; + ctrl |= XGMAC_OB; + writel(ctrl, ioaddr + XGMAC_RSS_ADDR); + + return readl_poll_timeout(ioaddr + XGMAC_RSS_ADDR, ctrl, + !(ctrl & XGMAC_OB), 100, 10000); +} + +static int dwxgmac2_rss_configure(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq) +{ + void __iomem *ioaddr = hw->pcsr; + u32 *key = (u32 *)cfg->key; + int i, ret; + u32 value; + + value = readl(ioaddr + XGMAC_RSS_CTRL); + if (!cfg->enable) { + value &= ~XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; + } + + for (i = 0; i < (sizeof(cfg->key) / sizeof(u32)); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, true, i, *key++); + if (ret) + return ret; + } + + for (i = 0; i < ARRAY_SIZE(cfg->table); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, false, i, cfg->table[i]); + if (ret) + return ret; + } + + for (i = 0; i < num_rxq; i++) + dwxgmac2_map_mtl_to_dma(hw, i, XGMAC_QDDMACH); + + value |= XGMAC_UDP4TE | XGMAC_TCP4TE | XGMAC_IP2TE | XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; +} + +static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash, + bool is_double) +{ + void __iomem *ioaddr = hw->pcsr; + + writel(hash, ioaddr + XGMAC_VLAN_HASH_TABLE); + + if (hash) { + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + + value |= XGMAC_FILTER_VTFE; + + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + value |= XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV; + if (is_double) { + value |= XGMAC_VLAN_EDVLP; + value |= XGMAC_VLAN_ESVL; + value |= XGMAC_VLAN_DOVLTC; + } + + writel(value, ioaddr + XGMAC_VLAN_TAG); + } else { + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + + value &= ~XGMAC_FILTER_VTFE; + + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + value = readl(ioaddr + XGMAC_VLAN_TAG); + + value &= ~(XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV); + value &= ~(XGMAC_VLAN_EDVLP | XGMAC_VLAN_ESVL); + value &= ~XGMAC_VLAN_DOVLTC; + value &= ~XGMAC_VLAN_VID; + + writel(value, ioaddr + XGMAC_VLAN_TAG); + } +} + +struct dwxgmac3_error_desc { + bool valid; + const char *desc; + const char *detailed_desc; +}; + +#define STAT_OFF(field) offsetof(struct stmmac_safety_stats, field) + +static void dwxgmac3_log_error(struct net_device *ndev, u32 value, bool corr, + const char *module_name, + const struct dwxgmac3_error_desc *desc, + unsigned long field_offset, + struct stmmac_safety_stats *stats) +{ + unsigned long loc, mask; + u8 *bptr = (u8 *)stats; + unsigned long *ptr; + + ptr = (unsigned long *)(bptr + field_offset); + + mask = value; + for_each_set_bit(loc, &mask, 32) { + netdev_err(ndev, "Found %s error in %s: '%s: %s'\n", corr ? + "correctable" : "uncorrectable", module_name, + desc[loc].desc, desc[loc].detailed_desc); + + /* Update counters */ + ptr[loc]++; + } +} + +static const struct dwxgmac3_error_desc dwxgmac3_mac_errors[32]= { + { true, "ATPES", "Application Transmit Interface Parity Check Error" }, + { true, "DPES", "Descriptor Cache Data Path Parity Check Error" }, + { true, "TPES", "TSO Data Path Parity Check Error" }, + { true, "TSOPES", "TSO Header Data Path Parity Check Error" }, + { true, "MTPES", "MTL Data Path Parity Check Error" }, + { true, "MTSPES", "MTL TX Status Data Path Parity Check Error" }, + { true, "MTBUPES", "MAC TBU Data Path Parity Check Error" }, + { true, "MTFCPES", "MAC TFC Data Path Parity Check Error" }, + { true, "ARPES", "Application Receive Interface Data Path Parity Check Error" }, + { true, "MRWCPES", "MTL RWC Data Path Parity Check Error" }, + { true, "MRRCPES", "MTL RCC Data Path Parity Check Error" }, + { true, "CWPES", "CSR Write Data Path Parity Check Error" }, + { true, "ASRPES", "AXI Slave Read Data Path Parity Check Error" }, + { true, "TTES", "TX FSM Timeout Error" }, + { true, "RTES", "RX FSM Timeout Error" }, + { true, "CTES", "CSR FSM Timeout Error" }, + { true, "ATES", "APP FSM Timeout Error" }, + { true, "PTES", "PTP FSM Timeout Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { true, "MSTTES", "Master Read/Write Timeout Error" }, + { true, "SLVTES", "Slave Read/Write Timeout Error" }, + { true, "ATITES", "Application Timeout on ATI Interface Error" }, + { true, "ARITES", "Application Timeout on ARI Interface Error" }, + { true, "FSMPES", "FSM State Parity Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { true, "CPI", "Control Register Parity Check Error" }, +}; + +static void dwxgmac3_handle_mac_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_MAC_DPP_FSM_INT_STATUS); + writel(value, ioaddr + XGMAC_MAC_DPP_FSM_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "MAC", + dwxgmac3_mac_errors, STAT_OFF(mac_errors), stats); +} + +static const struct dwxgmac3_error_desc dwxgmac3_mtl_errors[32]= { + { true, "TXCES", "MTL TX Memory Error" }, + { true, "TXAMS", "MTL TX Memory Address Mismatch Error" }, + { true, "TXUES", "MTL TX Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 3 */ + { true, "RXCES", "MTL RX Memory Error" }, + { true, "RXAMS", "MTL RX Memory Address Mismatch Error" }, + { true, "RXUES", "MTL RX Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 7 */ + { true, "ECES", "MTL EST Memory Error" }, + { true, "EAMS", "MTL EST Memory Address Mismatch Error" }, + { true, "EUES", "MTL EST Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 11 */ + { true, "RPCES", "MTL RX Parser Memory Error" }, + { true, "RPAMS", "MTL RX Parser Memory Address Mismatch Error" }, + { true, "RPUES", "MTL RX Parser Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 15 */ + { false, "UNKNOWN", "Unknown Error" }, /* 16 */ + { false, "UNKNOWN", "Unknown Error" }, /* 17 */ + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { false, "UNKNOWN", "Unknown Error" }, /* 21 */ + { false, "UNKNOWN", "Unknown Error" }, /* 22 */ + { false, "UNKNOWN", "Unknown Error" }, /* 23 */ + { false, "UNKNOWN", "Unknown Error" }, /* 24 */ + { false, "UNKNOWN", "Unknown Error" }, /* 25 */ + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { false, "UNKNOWN", "Unknown Error" }, /* 31 */ +}; + +static void dwxgmac3_handle_mtl_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_MTL_ECC_INT_STATUS); + writel(value, ioaddr + XGMAC_MTL_ECC_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "MTL", + dwxgmac3_mtl_errors, STAT_OFF(mtl_errors), stats); +} + +static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { + { true, "TCES", "DMA TSO Memory Error" }, + { true, "TAMS", "DMA TSO Memory Address Mismatch Error" }, + { true, "TUES", "DMA TSO Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 3 */ + { true, "DCES", "DMA DCACHE Memory Error" }, + { true, "DAMS", "DMA DCACHE Address Mismatch Error" }, + { true, "DUES", "DMA DCACHE Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 7 */ + { false, "UNKNOWN", "Unknown Error" }, /* 8 */ + { false, "UNKNOWN", "Unknown Error" }, /* 9 */ + { false, "UNKNOWN", "Unknown Error" }, /* 10 */ + { false, "UNKNOWN", "Unknown Error" }, /* 11 */ + { false, "UNKNOWN", "Unknown Error" }, /* 12 */ + { false, "UNKNOWN", "Unknown Error" }, /* 13 */ + { false, "UNKNOWN", "Unknown Error" }, /* 14 */ + { false, "UNKNOWN", "Unknown Error" }, /* 15 */ + { false, "UNKNOWN", "Unknown Error" }, /* 16 */ + { false, "UNKNOWN", "Unknown Error" }, /* 17 */ + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { false, "UNKNOWN", "Unknown Error" }, /* 21 */ + { false, "UNKNOWN", "Unknown Error" }, /* 22 */ + { false, "UNKNOWN", "Unknown Error" }, /* 23 */ + { false, "UNKNOWN", "Unknown Error" }, /* 24 */ + { false, "UNKNOWN", "Unknown Error" }, /* 25 */ + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { false, "UNKNOWN", "Unknown Error" }, /* 31 */ +}; + +static void dwxgmac3_handle_dma_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_DMA_ECC_INT_STATUS); + writel(value, ioaddr + XGMAC_DMA_ECC_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "DMA", + dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); +} + +static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp) +{ + u32 value; + + if (!asp) + return -EINVAL; + + /* 1. Enable Safety Features */ + writel(0x0, ioaddr + XGMAC_MTL_ECC_CONTROL); + + /* 2. Enable MTL Safety Interrupts */ + value = readl(ioaddr + XGMAC_MTL_ECC_INT_ENABLE); + value |= XGMAC_RPCEIE; /* RX Parser Memory Correctable Error */ + value |= XGMAC_ECEIE; /* EST Memory Correctable Error */ + value |= XGMAC_RXCEIE; /* RX Memory Correctable Error */ + value |= XGMAC_TXCEIE; /* TX Memory Correctable Error */ + writel(value, ioaddr + XGMAC_MTL_ECC_INT_ENABLE); + + /* 3. Enable DMA Safety Interrupts */ + value = readl(ioaddr + XGMAC_DMA_ECC_INT_ENABLE); + value |= XGMAC_DCEIE; /* Descriptor Cache Memory Correctable Error */ + value |= XGMAC_TCEIE; /* TSO Memory Correctable Error */ + writel(value, ioaddr + XGMAC_DMA_ECC_INT_ENABLE); + + /* Only ECC Protection for External Memory feature is selected */ + if (asp <= 0x1) + return 0; + + /* 4. Enable Parity and Timeout for FSM */ + value = readl(ioaddr + XGMAC_MAC_FSM_CONTROL); + value |= XGMAC_PRTYEN; /* FSM Parity Feature */ + value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */ + writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL); + + return 0; +} + +static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev, + void __iomem *ioaddr, + unsigned int asp, + struct stmmac_safety_stats *stats) +{ + bool err, corr; + u32 mtl, dma; + int ret = 0; + + if (!asp) + return -EINVAL; + + mtl = readl(ioaddr + XGMAC_MTL_SAFETY_INT_STATUS); + dma = readl(ioaddr + XGMAC_DMA_SAFETY_INT_STATUS); + + err = (mtl & XGMAC_MCSIS) || (dma & XGMAC_MCSIS); + corr = false; + if (err) { + dwxgmac3_handle_mac_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + err = (mtl & (XGMAC_MEUIS | XGMAC_MECIS)) || + (dma & (XGMAC_MSUIS | XGMAC_MSCIS)); + corr = (mtl & XGMAC_MECIS) || (dma & XGMAC_MSCIS); + if (err) { + dwxgmac3_handle_mtl_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + err = dma & (XGMAC_DEUIS | XGMAC_DECIS); + corr = dma & XGMAC_DECIS; + if (err) { + dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + return ret; +} + +static const struct dwxgmac3_error { + const struct dwxgmac3_error_desc *desc; +} dwxgmac3_all_errors[] = { + { dwxgmac3_mac_errors }, + { dwxgmac3_mtl_errors }, + { dwxgmac3_dma_errors }, +}; + +static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats, + int index, unsigned long *count, + const char **desc) +{ + int module = index / 32, offset = index % 32; + unsigned long *ptr = (unsigned long *)stats; + + if (module >= ARRAY_SIZE(dwxgmac3_all_errors)) + return -EINVAL; + if (!dwxgmac3_all_errors[module].desc[offset].valid) + return -EINVAL; + if (count) + *count = *(ptr + index); + if (desc) + *desc = dwxgmac3_all_errors[module].desc[offset].desc; + return 0; +} + +static int dwxgmac3_rxp_disable(void __iomem *ioaddr) +{ + u32 val = readl(ioaddr + XGMAC_MTL_OPMODE); + + val &= ~XGMAC_FRPE; + writel(val, ioaddr + XGMAC_MTL_OPMODE); + + return 0; +} + +static void dwxgmac3_rxp_enable(void __iomem *ioaddr) +{ + u32 val; + + val = readl(ioaddr + XGMAC_MTL_OPMODE); + val |= XGMAC_FRPE; + writel(val, ioaddr + XGMAC_MTL_OPMODE); +} + +static int dwxgmac3_rxp_update_single_entry(void __iomem *ioaddr, + struct stmmac_tc_entry *entry, + int pos) +{ + int ret, i; + + for (i = 0; i < (sizeof(entry->val) / sizeof(u32)); i++) { + int real_pos = pos * (sizeof(entry->val) / sizeof(u32)) + i; + u32 val; + + /* Wait for ready */ + ret = readl_poll_timeout(ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST, + val, !(val & XGMAC_STARTBUSY), 1, 10000); + if (ret) + return ret; + + /* Write data */ + val = *((u32 *)&entry->val + i); + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_DATA); + + /* Write pos */ + val = real_pos & XGMAC_ADDR; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Write OP */ + val |= XGMAC_WRRDN; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Start Write */ + val |= XGMAC_STARTBUSY; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Wait for done */ + ret = readl_poll_timeout(ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST, + val, !(val & XGMAC_STARTBUSY), 1, 10000); + if (ret) + return ret; + } + + return 0; +} + +static struct stmmac_tc_entry * +dwxgmac3_rxp_get_next_entry(struct stmmac_tc_entry *entries, + unsigned int count, u32 curr_prio) +{ + struct stmmac_tc_entry *entry; + u32 min_prio = ~0x0; + int i, min_prio_idx; + bool found = false; + + for (i = count - 1; i >= 0; i--) { + entry = &entries[i]; + + /* Do not update unused entries */ + if (!entry->in_use) + continue; + /* Do not update already updated entries (i.e. fragments) */ + if (entry->in_hw) + continue; + /* Let last entry be updated last */ + if (entry->is_last) + continue; + /* Do not return fragments */ + if (entry->is_frag) + continue; + /* Check if we already checked this prio */ + if (entry->prio < curr_prio) + continue; + /* Check if this is the minimum prio */ + if (entry->prio < min_prio) { + min_prio = entry->prio; + min_prio_idx = i; + found = true; + } + } + + if (found) + return &entries[min_prio_idx]; + return NULL; +} + +static int dwxgmac3_rxp_config(void __iomem *ioaddr, + struct stmmac_tc_entry *entries, + unsigned int count) +{ + struct stmmac_tc_entry *entry, *frag; + int i, ret, nve = 0; + u32 curr_prio = 0; + u32 old_val, val; + + /* Force disable RX */ + old_val = readl(ioaddr + XGMAC_RX_CONFIG); + val = old_val & ~XGMAC_CONFIG_RE; + writel(val, ioaddr + XGMAC_RX_CONFIG); + + /* Disable RX Parser */ + ret = dwxgmac3_rxp_disable(ioaddr); + if (ret) + goto re_enable; + + /* Set all entries as NOT in HW */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + entry->in_hw = false; + } + + /* Update entries by reverse order */ + while (1) { + entry = dwxgmac3_rxp_get_next_entry(entries, count, curr_prio); + if (!entry) + break; + + curr_prio = entry->prio; + frag = entry->frag_ptr; + + /* Set special fragment requirements */ + if (frag) { + entry->val.af = 0; + entry->val.rf = 0; + entry->val.nc = 1; + entry->val.ok_index = nve + 2; + } + + ret = dwxgmac3_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + entry->in_hw = true; + + if (frag && !frag->in_hw) { + ret = dwxgmac3_rxp_update_single_entry(ioaddr, frag, nve); + if (ret) + goto re_enable; + frag->table_pos = nve++; + frag->in_hw = true; + } + } + + if (!nve) + goto re_enable; + + /* Update all pass entry */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + if (!entry->is_last) + continue; + + ret = dwxgmac3_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + } + + /* Assume n. of parsable entries == n. of valid entries */ + val = (nve << 16) & XGMAC_NPE; + val |= nve & XGMAC_NVE; + writel(val, ioaddr + XGMAC_MTL_RXP_CONTROL_STATUS); + + /* Enable RX Parser */ + dwxgmac3_rxp_enable(ioaddr); + +re_enable: + /* Re-enable RX */ + writel(old_val, ioaddr + XGMAC_RX_CONFIG); + return ret; +} + +static int dwxgmac2_get_mac_tx_timestamp(struct mac_device_info *hw, u64 *ts) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + if (readl_poll_timeout_atomic(ioaddr + XGMAC_TIMESTAMP_STATUS, + value, value & XGMAC_TXTSC, 100, 10000)) + return -EBUSY; + + *ts = readl(ioaddr + XGMAC_TXTIMESTAMP_NSEC) & XGMAC_TXTSSTSLO; + *ts += readl(ioaddr + XGMAC_TXTIMESTAMP_SEC) * 1000000000ULL; + return 0; +} + +static int dwxgmac2_flex_pps_config(void __iomem *ioaddr, int index, + struct stmmac_pps_cfg *cfg, bool enable, + u32 sub_second_inc, u32 systime_flags) +{ + u32 tnsec = readl(ioaddr + XGMAC_PPSx_TARGET_TIME_NSEC(index)); + u32 val = readl(ioaddr + XGMAC_PPS_CONTROL); + u64 period; + + if (!cfg->available) + return -EINVAL; + if (tnsec & XGMAC_TRGTBUSY0) + return -EBUSY; + if (!sub_second_inc || !systime_flags) + return -EINVAL; + + val &= ~XGMAC_PPSx_MASK(index); + + if (!enable) { + val |= XGMAC_PPSCMDx(index, XGMAC_PPSCMD_STOP); + writel(val, ioaddr + XGMAC_PPS_CONTROL); + return 0; + } + + val |= XGMAC_PPSCMDx(index, XGMAC_PPSCMD_START); + val |= XGMAC_TRGTMODSELx(index, XGMAC_PPSCMD_START); + val |= XGMAC_PPSEN0; + + writel(cfg->start.tv_sec, ioaddr + XGMAC_PPSx_TARGET_TIME_SEC(index)); + + if (!(systime_flags & PTP_TCR_TSCTRLSSR)) + cfg->start.tv_nsec = (cfg->start.tv_nsec * 1000) / 465; + writel(cfg->start.tv_nsec, ioaddr + XGMAC_PPSx_TARGET_TIME_NSEC(index)); + + period = cfg->period.tv_sec * 1000000000; + period += cfg->period.tv_nsec; + + do_div(period, sub_second_inc); + + if (period <= 1) + return -EINVAL; + + writel(period - 1, ioaddr + XGMAC_PPSx_INTERVAL(index)); + + period >>= 1; + if (period <= 1) + return -EINVAL; + + writel(period - 1, ioaddr + XGMAC_PPSx_WIDTH(index)); + + /* Finally, activate it */ + writel(val, ioaddr + XGMAC_PPS_CONTROL); + return 0; +} + +static void dwxgmac2_sarc_configure(void __iomem *ioaddr, int val) +{ + u32 value = readl(ioaddr + XGMAC_TX_CONFIG); + + value &= ~XGMAC_CONFIG_SARC; + value |= val << XGMAC_CONFIG_SARC_SHIFT; + + writel(value, ioaddr + XGMAC_TX_CONFIG); +} + +static void dwxgmac2_enable_vlan(struct mac_device_info *hw, u32 type) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_VLAN_INCL); + value |= XGMAC_VLAN_VLTI; + value |= XGMAC_VLAN_CSVL; /* Only use SVLAN */ + value &= ~XGMAC_VLAN_VLC; + value |= (type << XGMAC_VLAN_VLC_SHIFT) & XGMAC_VLAN_VLC; + writel(value, ioaddr + XGMAC_VLAN_INCL); +} + const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxgmac2_rx_queue_enable, .rx_queue_prio = dwxgmac2_rx_queue_prio, - .tx_queue_prio = NULL, + .tx_queue_prio = dwxgmac2_tx_queue_prio, .rx_queue_routing = NULL, .prog_mtl_rx_algorithms = dwxgmac2_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms, - .set_mtl_tx_queue_weight = NULL, + .set_mtl_tx_queue_weight = dwxgmac2_set_mtl_tx_queue_weight, .map_mtl_to_dma = dwxgmac2_map_mtl_to_dma, .config_cbs = dwxgmac2_config_cbs, - .dump_regs = NULL, + .dump_regs = dwxgmac2_dump_regs, .host_irq_status = dwxgmac2_host_irq_status, .host_mtl_irq_status = dwxgmac2_host_mtl_irq_status, .flow_ctrl = dwxgmac2_flow_ctrl, .pmt = dwxgmac2_pmt, .set_umac_addr = dwxgmac2_set_umac_addr, .get_umac_addr = dwxgmac2_get_umac_addr, - .set_eee_mode = NULL, - .reset_eee_mode = NULL, - .set_eee_timer = NULL, - .set_eee_pls = NULL, + .set_eee_mode = dwxgmac2_set_eee_mode, + .reset_eee_mode = dwxgmac2_reset_eee_mode, + .set_eee_timer = dwxgmac2_set_eee_timer, + .set_eee_pls = dwxgmac2_set_eee_pls, .pcs_ctrl_ane = NULL, .pcs_rane = NULL, .pcs_get_adv_lp = NULL, .debug = NULL, .set_filter = dwxgmac2_set_filter, + .safety_feat_config = dwxgmac3_safety_feat_config, + .safety_feat_irq_status = dwxgmac3_safety_feat_irq_status, + .safety_feat_dump = dwxgmac3_safety_feat_dump, .set_mac_loopback = dwxgmac2_set_mac_loopback, + .rss_configure = dwxgmac2_rss_configure, + .update_vlan_hash = dwxgmac2_update_vlan_hash, + .rxp_config = dwxgmac3_rxp_config, + .get_mac_tx_timestamp = dwxgmac2_get_mac_tx_timestamp, + .flex_pps_config = dwxgmac2_flex_pps_config, + .sarc_configure = dwxgmac2_sarc_configure, + .enable_vlan = dwxgmac2_enable_vlan, }; int dwxgmac2_setup(struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c index c4c45402b8f8..ae48154f933c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c @@ -26,16 +26,17 @@ static int dwxgmac2_get_rx_status(void *data, struct stmmac_extra_stats *x, struct dma_desc *p) { unsigned int rdes3 = le32_to_cpu(p->des3); - int ret = good_frame; if (unlikely(rdes3 & XGMAC_RDES3_OWN)) return dma_own; + if (unlikely(rdes3 & XGMAC_RDES3_CTXT)) + return discard_frame; if (likely(!(rdes3 & XGMAC_RDES3_LD))) + return rx_not_ls; + if (unlikely((rdes3 & XGMAC_RDES3_ES) && (rdes3 & XGMAC_RDES3_LD))) return discard_frame; - if (unlikely(rdes3 & XGMAC_RDES3_ES)) - ret = discard_frame; - return ret; + return good_frame; } static int dwxgmac2_get_tx_len(struct dma_desc *p) @@ -55,7 +56,7 @@ static void dwxgmac2_set_tx_owner(struct dma_desc *p) static void dwxgmac2_set_rx_owner(struct dma_desc *p, int disable_rx_ic) { - p->des3 = cpu_to_le32(XGMAC_RDES3_OWN); + p->des3 |= cpu_to_le32(XGMAC_RDES3_OWN); if (!disable_rx_ic) p->des3 |= cpu_to_le32(XGMAC_RDES3_IOC); @@ -98,11 +99,17 @@ static int dwxgmac2_rx_check_timestamp(void *desc) unsigned int rdes3 = le32_to_cpu(p->des3); bool desc_valid, ts_valid; + dma_rmb(); + desc_valid = !(rdes3 & XGMAC_RDES3_OWN) && (rdes3 & XGMAC_RDES3_CTXT); ts_valid = !(rdes3 & XGMAC_RDES3_TSD) && (rdes3 & XGMAC_RDES3_TSA); - if (likely(desc_valid && ts_valid)) + if (likely(desc_valid && ts_valid)) { + if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + return -EINVAL; return 0; + } + return -EINVAL; } @@ -113,13 +120,10 @@ static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc, unsigned int rdes3 = le32_to_cpu(p->des3); int ret = -EBUSY; - if (likely(rdes3 & XGMAC_RDES3_CDA)) { + if (likely(rdes3 & XGMAC_RDES3_CDA)) ret = dwxgmac2_rx_check_timestamp(next_desc); - if (ret) - return ret; - } - return ret; + return !ret; } static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic, @@ -144,7 +148,7 @@ static void dwxgmac2_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, p->des2 |= cpu_to_le32(len & XGMAC_TDES2_B1L); - tdes3 = tot_pkt_len & XGMAC_TDES3_FL; + tdes3 |= tot_pkt_len & XGMAC_TDES3_FL; if (is_fs) tdes3 |= XGMAC_TDES3_FD; else @@ -254,6 +258,86 @@ static void dwxgmac2_clear(struct dma_desc *p) p->des3 = 0; } +static int dwxgmac2_get_rx_hash(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type) +{ + unsigned int rdes3 = le32_to_cpu(p->des3); + u32 ptype; + + if (rdes3 & XGMAC_RDES3_RSV) { + ptype = (rdes3 & XGMAC_RDES3_L34T) >> XGMAC_RDES3_L34T_SHIFT; + + switch (ptype) { + case XGMAC_L34T_IP4TCP: + case XGMAC_L34T_IP4UDP: + case XGMAC_L34T_IP6TCP: + case XGMAC_L34T_IP6UDP: + *type = PKT_HASH_TYPE_L4; + break; + default: + *type = PKT_HASH_TYPE_L3; + break; + } + + *hash = le32_to_cpu(p->des1); + return 0; + } + + return -EINVAL; +} + +static int dwxgmac2_get_rx_header_len(struct dma_desc *p, unsigned int *len) +{ + *len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL; + return 0; +} + +static void dwxgmac2_set_sec_addr(struct dma_desc *p, dma_addr_t addr) +{ + p->des2 = cpu_to_le32(lower_32_bits(addr)); + p->des3 = cpu_to_le32(upper_32_bits(addr)); +} + +static void dwxgmac2_set_sarc(struct dma_desc *p, u32 sarc_type) +{ + sarc_type <<= XGMAC_TDES3_SAIC_SHIFT; + + p->des3 |= cpu_to_le32(sarc_type & XGMAC_TDES3_SAIC); +} + +static void dwxgmac2_set_vlan_tag(struct dma_desc *p, u16 tag, u16 inner_tag, + u32 inner_type) +{ + p->des0 = 0; + p->des1 = 0; + p->des2 = 0; + p->des3 = 0; + + /* Inner VLAN */ + if (inner_type) { + u32 des = inner_tag << XGMAC_TDES2_IVT_SHIFT; + + des &= XGMAC_TDES2_IVT; + p->des2 = cpu_to_le32(des); + + des = inner_type << XGMAC_TDES3_IVTIR_SHIFT; + des &= XGMAC_TDES3_IVTIR; + p->des3 = cpu_to_le32(des | XGMAC_TDES3_IVLTV); + } + + /* Outer VLAN */ + p->des3 |= cpu_to_le32(tag & XGMAC_TDES3_VT); + p->des3 |= cpu_to_le32(XGMAC_TDES3_VLTV); + + p->des3 |= cpu_to_le32(XGMAC_TDES3_CTXT); +} + +static void dwxgmac2_set_vlan(struct dma_desc *p, u32 type) +{ + type <<= XGMAC_TDES2_VTIR_SHIFT; + p->des2 |= cpu_to_le32(type & XGMAC_TDES2_VTIR); +} + const struct stmmac_desc_ops dwxgmac210_desc_ops = { .tx_status = dwxgmac2_get_tx_status, .rx_status = dwxgmac2_get_rx_status, @@ -277,4 +361,10 @@ const struct stmmac_desc_ops dwxgmac210_desc_ops = { .get_addr = dwxgmac2_get_addr, .set_addr = dwxgmac2_set_addr, .clear = dwxgmac2_clear, + .get_rx_hash = dwxgmac2_get_rx_hash, + .get_rx_header_len = dwxgmac2_get_rx_header_len, + .set_sec_addr = dwxgmac2_set_sec_addr, + .set_sarc = dwxgmac2_set_sarc, + .set_vlan_tag = dwxgmac2_set_vlan_tag, + .set_vlan = dwxgmac2_set_vlan, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index a4f236e3593e..64956465c030 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -128,6 +128,14 @@ static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) writel(XGMAC_RDPS, ioaddr + XGMAC_RX_EDMA_CTRL); } +static void dwxgmac2_dma_dump_regs(void __iomem *ioaddr, u32 *reg_space) +{ + int i; + + for (i = (XGMAC_DMA_MODE / 4); i < XGMAC_REGSIZE; i++) + reg_space[i] = readl(ioaddr + i * 4); +} + static void dwxgmac2_dma_rx_mode(void __iomem *ioaddr, int mode, u32 channel, int fifosz, u8 qmode) { @@ -351,18 +359,24 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, /* MAC HW feature 0 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0); + dma_cap->vlins = (hw_cap & XGMAC_HWFEAT_SAVLANINS) >> 27; dma_cap->rx_coe = (hw_cap & XGMAC_HWFEAT_RXCOESEL) >> 16; dma_cap->tx_coe = (hw_cap & XGMAC_HWFEAT_TXCOESEL) >> 14; + dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13; dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12; dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11; dma_cap->av &= (hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10; + dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8; dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7; dma_cap->pmt_remote_wake_up = (hw_cap & XGMAC_HWFEAT_RWKSEL) >> 6; + dma_cap->vlhash = (hw_cap & XGMAC_HWFEAT_VLHASH) >> 4; dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1; /* MAC HW feature 1 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1); + dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20; dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18; + dma_cap->sphen = (hw_cap & XGMAC_HWFEAT_SPHEN) >> 17; dma_cap->addr64 = (hw_cap & XGMAC_HWFEAT_ADDR64) >> 14; switch (dma_cap->addr64) { @@ -396,6 +410,14 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, ((hw_cap & XGMAC_HWFEAT_TXQCNT) >> 6) + 1; dma_cap->number_rx_queues = ((hw_cap & XGMAC_HWFEAT_RXQCNT) >> 0) + 1; + + /* MAC HW feature 3 */ + hw_cap = readl(ioaddr + XGMAC_HW_FEATURE3); + dma_cap->asp = (hw_cap & XGMAC_HWFEAT_ASP) >> 14; + dma_cap->dvlan = (hw_cap & XGMAC_HWFEAT_DVLAN) >> 13; + dma_cap->frpes = (hw_cap & XGMAC_HWFEAT_FRPES) >> 11; + dma_cap->frpbs = (hw_cap & XGMAC_HWFEAT_FRPPB) >> 9; + dma_cap->frpsel = (hw_cap & XGMAC_HWFEAT_FRPSEL) >> 3; } static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 nchan) @@ -462,6 +484,22 @@ static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan)); } +static void dwxgmac2_enable_sph(void __iomem *ioaddr, bool en, u32 chan) +{ + u32 value = readl(ioaddr + XGMAC_RX_CONFIG); + + value &= ~XGMAC_CONFIG_HDSMS; + value |= XGMAC_CONFIG_HDSMS_256; /* Segment max 256 bytes */ + writel(value, ioaddr + XGMAC_RX_CONFIG); + + value = readl(ioaddr + XGMAC_DMA_CH_CONTROL(chan)); + if (en) + value |= XGMAC_SPH; + else + value &= ~XGMAC_SPH; + writel(value, ioaddr + XGMAC_DMA_CH_CONTROL(chan)); +} + const struct stmmac_dma_ops dwxgmac210_dma_ops = { .reset = dwxgmac2_dma_reset, .init = dwxgmac2_dma_init, @@ -469,7 +507,7 @@ const struct stmmac_dma_ops dwxgmac210_dma_ops = { .init_rx_chan = dwxgmac2_dma_init_rx_chan, .init_tx_chan = dwxgmac2_dma_init_tx_chan, .axi = dwxgmac2_dma_axi, - .dump_regs = NULL, + .dump_regs = dwxgmac2_dma_dump_regs, .dma_rx_mode = dwxgmac2_dma_rx_mode, .dma_tx_mode = dwxgmac2_dma_tx_mode, .enable_dma_irq = dwxgmac2_enable_dma_irq, @@ -488,4 +526,5 @@ const struct stmmac_dma_ops dwxgmac210_dma_ops = { .enable_tso = dwxgmac2_enable_tso, .qmode = dwxgmac2_qmode, .set_bfsize = dwxgmac2_set_bfsize, + .enable_sph = dwxgmac2_enable_sph, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 6c61b753b55e..3af2e5015245 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -201,7 +201,7 @@ static const struct stmmac_hwif_entry { .min_id = DWXGMAC_CORE_2_10, .regs = { .ptp_off = PTP_XGMAC_OFFSET, - .mmc_off = 0, + .mmc_off = MMC_XGMAC_OFFSET, }, .desc = &dwxgmac210_desc_ops, .dma = &dwxgmac210_dma_ops, @@ -209,7 +209,7 @@ static const struct stmmac_hwif_entry { .hwtimestamp = &stmmac_ptp, .mode = NULL, .tc = &dwmac510_tc_ops, - .mmc = NULL, + .mmc = &dwxgmac_mmc_ops, .setup = dwxgmac2_setup, .quirks = NULL, }, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 278c0dbec9d9..9435b312495d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -86,6 +86,15 @@ struct stmmac_desc_ops { void (*set_addr)(struct dma_desc *p, dma_addr_t addr); /* clear descriptor */ void (*clear)(struct dma_desc *p); + /* RSS */ + int (*get_rx_hash)(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type); + int (*get_rx_header_len)(struct dma_desc *p, unsigned int *len); + void (*set_sec_addr)(struct dma_desc *p, dma_addr_t addr); + void (*set_sarc)(struct dma_desc *p, u32 sarc_type); + void (*set_vlan_tag)(struct dma_desc *p, u16 tag, u16 inner_tag, + u32 inner_type); + void (*set_vlan)(struct dma_desc *p, u32 type); }; #define stmmac_init_rx_desc(__priv, __args...) \ @@ -136,6 +145,18 @@ struct stmmac_desc_ops { stmmac_do_void_callback(__priv, desc, set_addr, __args) #define stmmac_clear_desc(__priv, __args...) \ stmmac_do_void_callback(__priv, desc, clear, __args) +#define stmmac_get_rx_hash(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_hash, __args) +#define stmmac_get_rx_header_len(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_header_len, __args) +#define stmmac_set_desc_sec_addr(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_sec_addr, __args) +#define stmmac_set_desc_sarc(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_sarc, __args) +#define stmmac_set_desc_vlan_tag(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_vlan_tag, __args) +#define stmmac_set_desc_vlan(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_vlan, __args) struct stmmac_dma_cfg; struct dma_features; @@ -186,6 +207,7 @@ struct stmmac_dma_ops { void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); void (*qmode)(void __iomem *ioaddr, u32 channel, u8 qmode); void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan); + void (*enable_sph)(void __iomem *ioaddr, bool en, u32 chan); }; #define stmmac_reset(__priv, __args...) \ @@ -242,6 +264,8 @@ struct stmmac_dma_ops { stmmac_do_void_callback(__priv, dma, qmode, __args) #define stmmac_set_dma_bfsize(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, set_bfsize, __args) +#define stmmac_enable_sph(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, enable_sph, __args) struct mac_device_info; struct net_device; @@ -249,6 +273,7 @@ struct rgmii_adv; struct stmmac_safety_stats; struct stmmac_tc_entry; struct stmmac_pps_cfg; +struct stmmac_rss; /* Helpers to program the MAC core */ struct stmmac_ops { @@ -327,6 +352,17 @@ struct stmmac_ops { u32 sub_second_inc, u32 systime_flags); /* Loopback for selftests */ void (*set_mac_loopback)(void __iomem *ioaddr, bool enable); + /* RSS */ + int (*rss_configure)(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq); + /* VLAN */ + void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash, + bool is_double); + void (*enable_vlan)(struct mac_device_info *hw, u32 type); + /* TX Timestamp */ + int (*get_mac_tx_timestamp)(struct mac_device_info *hw, u64 *ts); + /* Source Address Insertion / Replacement */ + void (*sarc_configure)(void __iomem *ioaddr, int val); }; #define stmmac_core_init(__priv, __args...) \ @@ -397,6 +433,16 @@ struct stmmac_ops { stmmac_do_callback(__priv, mac, flex_pps_config, __args) #define stmmac_set_mac_loopback(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, set_mac_loopback, __args) +#define stmmac_rss_configure(__priv, __args...) \ + stmmac_do_callback(__priv, mac, rss_configure, __args) +#define stmmac_update_vlan_hash(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, update_vlan_hash, __args) +#define stmmac_enable_vlan(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, enable_vlan, __args) +#define stmmac_get_mac_tx_timestamp(__priv, __args...) \ + stmmac_do_callback(__priv, mac, get_mac_tx_timestamp, __args) +#define stmmac_sarc_configure(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, sarc_configure, __args) /* PTP and HW Timer helpers */ struct stmmac_hwtimestamp { @@ -503,6 +549,7 @@ extern const struct stmmac_ops dwxgmac210_ops; extern const struct stmmac_dma_ops dwxgmac210_dma_ops; extern const struct stmmac_desc_ops dwxgmac210_desc_ops; extern const struct stmmac_mmc_ops dwmac_mmc_ops; +extern const struct stmmac_mmc_ops dwxgmac_mmc_ops; #define GMAC_VERSION 0x00000020 /* GMAC CORE Version */ #define GMAC4_VERSION 0x00000110 /* GMAC4+ CORE Version */ diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h index 3587ceb9faf5..a0c05925883e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc.h +++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h @@ -24,6 +24,7 @@ #define MMC_GMAC4_OFFSET 0x700 #define MMC_GMAC3_X_OFFSET 0x100 +#define MMC_XGMAC_OFFSET 0x800 struct stmmac_counters { unsigned int mmc_tx_octetcount_gb; @@ -116,6 +117,14 @@ struct stmmac_counters { unsigned int mmc_rx_tcp_err_octets; unsigned int mmc_rx_icmp_gd_octets; unsigned int mmc_rx_icmp_err_octets; + + /* FPE */ + unsigned int mmc_tx_fpe_fragment_cntr; + unsigned int mmc_tx_hold_req_cntr; + unsigned int mmc_rx_packet_assembly_err_cntr; + unsigned int mmc_rx_packet_smd_err_cntr; + unsigned int mmc_rx_packet_assembly_ok_cntr; + unsigned int mmc_rx_fpe_fragment_cntr; }; #endif /* __MMC_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index a471db6d7b11..a223584f5f9a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -119,6 +119,64 @@ #define MMC_RX_ICMP_GD_OCTETS 0x180 #define MMC_RX_ICMP_ERR_OCTETS 0x184 +/* XGMAC MMC Registers */ +#define MMC_XGMAC_TX_OCTET_GB 0x14 +#define MMC_XGMAC_TX_PKT_GB 0x1c +#define MMC_XGMAC_TX_BROAD_PKT_G 0x24 +#define MMC_XGMAC_TX_MULTI_PKT_G 0x2c +#define MMC_XGMAC_TX_64OCT_GB 0x34 +#define MMC_XGMAC_TX_65OCT_GB 0x3c +#define MMC_XGMAC_TX_128OCT_GB 0x44 +#define MMC_XGMAC_TX_256OCT_GB 0x4c +#define MMC_XGMAC_TX_512OCT_GB 0x54 +#define MMC_XGMAC_TX_1024OCT_GB 0x5c +#define MMC_XGMAC_TX_UNI_PKT_GB 0x64 +#define MMC_XGMAC_TX_MULTI_PKT_GB 0x6c +#define MMC_XGMAC_TX_BROAD_PKT_GB 0x74 +#define MMC_XGMAC_TX_UNDER 0x7c +#define MMC_XGMAC_TX_OCTET_G 0x84 +#define MMC_XGMAC_TX_PKT_G 0x8c +#define MMC_XGMAC_TX_PAUSE 0x94 +#define MMC_XGMAC_TX_VLAN_PKT_G 0x9c +#define MMC_XGMAC_TX_LPI_USEC 0xa4 +#define MMC_XGMAC_TX_LPI_TRAN 0xa8 + +#define MMC_XGMAC_RX_PKT_GB 0x100 +#define MMC_XGMAC_RX_OCTET_GB 0x108 +#define MMC_XGMAC_RX_OCTET_G 0x110 +#define MMC_XGMAC_RX_BROAD_PKT_G 0x118 +#define MMC_XGMAC_RX_MULTI_PKT_G 0x120 +#define MMC_XGMAC_RX_CRC_ERR 0x128 +#define MMC_XGMAC_RX_RUNT_ERR 0x130 +#define MMC_XGMAC_RX_JABBER_ERR 0x134 +#define MMC_XGMAC_RX_UNDER 0x138 +#define MMC_XGMAC_RX_OVER 0x13c +#define MMC_XGMAC_RX_64OCT_GB 0x140 +#define MMC_XGMAC_RX_65OCT_GB 0x148 +#define MMC_XGMAC_RX_128OCT_GB 0x150 +#define MMC_XGMAC_RX_256OCT_GB 0x158 +#define MMC_XGMAC_RX_512OCT_GB 0x160 +#define MMC_XGMAC_RX_1024OCT_GB 0x168 +#define MMC_XGMAC_RX_UNI_PKT_G 0x170 +#define MMC_XGMAC_RX_LENGTH_ERR 0x178 +#define MMC_XGMAC_RX_RANGE 0x180 +#define MMC_XGMAC_RX_PAUSE 0x188 +#define MMC_XGMAC_RX_FIFOOVER_PKT 0x190 +#define MMC_XGMAC_RX_VLAN_PKT_GB 0x198 +#define MMC_XGMAC_RX_WATCHDOG_ERR 0x1a0 +#define MMC_XGMAC_RX_LPI_USEC 0x1a4 +#define MMC_XGMAC_RX_LPI_TRAN 0x1a8 +#define MMC_XGMAC_RX_DISCARD_PKT_GB 0x1ac +#define MMC_XGMAC_RX_DISCARD_OCT_GB 0x1b4 +#define MMC_XGMAC_RX_ALIGN_ERR_PKT 0x1bc + +#define MMC_XGMAC_TX_FPE_FRAG 0x208 +#define MMC_XGMAC_TX_HOLD_REQ 0x20c +#define MMC_XGMAC_RX_PKT_ASSEMBLY_ERR 0x228 +#define MMC_XGMAC_RX_PKT_SMD_ERR 0x22c +#define MMC_XGMAC_RX_PKT_ASSEMBLY_OK 0x230 +#define MMC_XGMAC_RX_FPE_FRAG 0x234 + static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) { u32 value = readl(mmcaddr + MMC_CNTRL); @@ -263,3 +321,137 @@ const struct stmmac_mmc_ops dwmac_mmc_ops = { .intr_all_mask = dwmac_mmc_intr_all_mask, .read = dwmac_mmc_read, }; + +static void dwxgmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) +{ + u32 value = readl(mmcaddr + MMC_CNTRL); + + value |= (mode & 0x3F); + + writel(value, mmcaddr + MMC_CNTRL); +} + +static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr) +{ + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_RX_INTR_MASK); + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_TX_INTR_MASK); +} + +static void dwxgmac_read_mmc_reg(void __iomem *addr, u32 reg, u32 *dest) +{ + u64 tmp = 0; + + tmp += readl(addr + reg); + tmp += ((u64 )readl(addr + reg + 0x4)) << 32; + if (tmp > GENMASK(31, 0)) + *dest = ~0x0; + else + *dest = *dest + tmp; +} + +/* This reads the MAC core counters (if actaully supported). + * by default the MMC core is programmed to reset each + * counter after a read. So all the field of the mmc struct + * have to be incremented. + */ +static void dwxgmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc) +{ + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_OCTET_GB, + &mmc->mmc_tx_octetcount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PKT_GB, + &mmc->mmc_tx_framecount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_BROAD_PKT_G, + &mmc->mmc_tx_broadcastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_MULTI_PKT_G, + &mmc->mmc_tx_multicastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_64OCT_GB, + &mmc->mmc_tx_64_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_65OCT_GB, + &mmc->mmc_tx_65_to_127_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_128OCT_GB, + &mmc->mmc_tx_128_to_255_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_256OCT_GB, + &mmc->mmc_tx_256_to_511_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_512OCT_GB, + &mmc->mmc_tx_512_to_1023_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_1024OCT_GB, + &mmc->mmc_tx_1024_to_max_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_UNI_PKT_GB, + &mmc->mmc_tx_unicast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_MULTI_PKT_GB, + &mmc->mmc_tx_multicast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_BROAD_PKT_GB, + &mmc->mmc_tx_broadcast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_UNDER, + &mmc->mmc_tx_underflow_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_OCTET_G, + &mmc->mmc_tx_octetcount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PKT_G, + &mmc->mmc_tx_framecount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PAUSE, + &mmc->mmc_tx_pause_frame); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_VLAN_PKT_G, + &mmc->mmc_tx_vlan_frame_g); + + /* MMC RX counter registers */ + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_PKT_GB, + &mmc->mmc_rx_framecount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_OCTET_GB, + &mmc->mmc_rx_octetcount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_OCTET_G, + &mmc->mmc_rx_octetcount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_BROAD_PKT_G, + &mmc->mmc_rx_broadcastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_MULTI_PKT_G, + &mmc->mmc_rx_multicastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_CRC_ERR, + &mmc->mmc_rx_crc_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_CRC_ERR, + &mmc->mmc_rx_crc_error); + mmc->mmc_rx_run_error += readl(mmcaddr + MMC_XGMAC_RX_RUNT_ERR); + mmc->mmc_rx_jabber_error += readl(mmcaddr + MMC_XGMAC_RX_JABBER_ERR); + mmc->mmc_rx_undersize_g += readl(mmcaddr + MMC_XGMAC_RX_UNDER); + mmc->mmc_rx_oversize_g += readl(mmcaddr + MMC_XGMAC_RX_OVER); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_64OCT_GB, + &mmc->mmc_rx_64_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_65OCT_GB, + &mmc->mmc_rx_65_to_127_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_128OCT_GB, + &mmc->mmc_rx_128_to_255_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_256OCT_GB, + &mmc->mmc_rx_256_to_511_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_512OCT_GB, + &mmc->mmc_rx_512_to_1023_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_1024OCT_GB, + &mmc->mmc_rx_1024_to_max_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_UNI_PKT_G, + &mmc->mmc_rx_unicast_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_LENGTH_ERR, + &mmc->mmc_rx_length_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_RANGE, + &mmc->mmc_rx_autofrangetype); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_PAUSE, + &mmc->mmc_rx_pause_frames); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_FIFOOVER_PKT, + &mmc->mmc_rx_fifo_overflow); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_VLAN_PKT_GB, + &mmc->mmc_rx_vlan_frames_gb); + mmc->mmc_rx_watchdog_error += readl(mmcaddr + MMC_XGMAC_RX_WATCHDOG_ERR); + + mmc->mmc_tx_fpe_fragment_cntr += readl(mmcaddr + MMC_XGMAC_TX_FPE_FRAG); + mmc->mmc_tx_hold_req_cntr += readl(mmcaddr + MMC_XGMAC_TX_HOLD_REQ); + mmc->mmc_rx_packet_assembly_err_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_ERR); + mmc->mmc_rx_packet_smd_err_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_SMD_ERR); + mmc->mmc_rx_packet_assembly_ok_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_OK); + mmc->mmc_rx_fpe_fragment_cntr += + readl(mmcaddr + MMC_XGMAC_RX_FPE_FRAG); +} + +const struct stmmac_mmc_ops dwxgmac_mmc_ops = { + .ctrl = dwxgmac_mmc_ctrl, + .intr_all_mask = dwxgmac_mmc_intr_all_mask, + .read = dwxgmac_mmc_read, +}; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 5cd966c154f3..dcb2e29a5717 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -13,6 +13,7 @@ #define DRV_MODULE_VERSION "Jan_2016" #include <linux/clk.h> +#include <linux/if_vlan.h> #include <linux/stmmac.h> #include <linux/phylink.h> #include <linux/pci.h> @@ -57,7 +58,9 @@ struct stmmac_tx_queue { struct stmmac_rx_buffer { struct page *page; + struct page *sec_page; dma_addr_t addr; + dma_addr_t sec_addr; }; struct stmmac_rx_queue { @@ -73,6 +76,12 @@ struct stmmac_rx_queue { u32 rx_zeroc_thresh; dma_addr_t dma_rx_phy; u32 rx_tail_addr; + unsigned int state_saved; + struct { + struct sk_buff *skb; + unsigned int len; + unsigned int error; + } state; }; struct stmmac_channel { @@ -113,6 +122,12 @@ struct stmmac_pps_cfg { struct timespec64 period; }; +struct stmmac_rss { + int enable; + u8 key[STMMAC_RSS_HASH_KEY_SIZE]; + u32 table[STMMAC_RSS_MAX_TABLE_SIZE]; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ u32 tx_coal_frames; @@ -123,6 +138,8 @@ struct stmmac_priv { int hwts_tx_en; bool tx_path_in_lpi_mode; bool tso; + int sph; + u32 sarc_type; unsigned int dma_buf_sz; unsigned int rx_copybreak; @@ -185,11 +202,10 @@ struct stmmac_priv { spinlock_t ptp_lock; void __iomem *mmcaddr; void __iomem *ptpaddr; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; #ifdef CONFIG_DEBUG_FS struct dentry *dbgfs_dir; - struct dentry *dbgfs_rings_status; - struct dentry *dbgfs_dma_cap; #endif unsigned long state; @@ -203,6 +219,9 @@ struct stmmac_priv { /* Pulse Per Second output */ struct stmmac_pps_cfg pps[STMMAC_PPS_MAX]; + + /* Receive Side Scaling */ + struct stmmac_rss rss; }; enum stmmac_state { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 6efb66820d4c..1c450105e5a6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -18,10 +18,12 @@ #include "stmmac.h" #include "dwmac_dma.h" +#include "dwxgmac2.h" #define REG_SPACE_SIZE 0x1060 #define MAC100_ETHTOOL_NAME "st_mac100" #define GMAC_ETHTOOL_NAME "st_gmac" +#define XGMAC_ETHTOOL_NAME "st_xgmac" #define ETHTOOL_DMA_OFFSET 55 @@ -65,6 +67,7 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = { STMMAC_STAT(rx_missed_cntr), STMMAC_STAT(rx_overflow_cntr), STMMAC_STAT(rx_vlan), + STMMAC_STAT(rx_split_hdr_pkt_n), /* Tx/Rx IRQ error info */ STMMAC_STAT(tx_undeflow_irq), STMMAC_STAT(tx_process_stopped_irq), @@ -243,6 +246,12 @@ static const struct stmmac_stats stmmac_mmc[] = { STMMAC_MMC_STAT(mmc_rx_tcp_err_octets), STMMAC_MMC_STAT(mmc_rx_icmp_gd_octets), STMMAC_MMC_STAT(mmc_rx_icmp_err_octets), + STMMAC_MMC_STAT(mmc_tx_fpe_fragment_cntr), + STMMAC_MMC_STAT(mmc_tx_hold_req_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_assembly_err_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_smd_err_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_assembly_ok_cntr), + STMMAC_MMC_STAT(mmc_rx_fpe_fragment_cntr), }; #define STMMAC_MMC_STATS_LEN ARRAY_SIZE(stmmac_mmc) @@ -253,6 +262,8 @@ static void stmmac_ethtool_getdrvinfo(struct net_device *dev, if (priv->plat->has_gmac || priv->plat->has_gmac4) strlcpy(info->driver, GMAC_ETHTOOL_NAME, sizeof(info->driver)); + else if (priv->plat->has_xgmac) + strlcpy(info->driver, XGMAC_ETHTOOL_NAME, sizeof(info->driver)); else strlcpy(info->driver, MAC100_ETHTOOL_NAME, sizeof(info->driver)); @@ -398,23 +409,28 @@ static int stmmac_check_if_running(struct net_device *dev) static int stmmac_ethtool_get_regs_len(struct net_device *dev) { + struct stmmac_priv *priv = netdev_priv(dev); + + if (priv->plat->has_xgmac) + return XGMAC_REGSIZE * 4; return REG_SPACE_SIZE; } static void stmmac_ethtool_gregs(struct net_device *dev, struct ethtool_regs *regs, void *space) { - u32 *reg_space = (u32 *) space; - struct stmmac_priv *priv = netdev_priv(dev); - - memset(reg_space, 0x0, REG_SPACE_SIZE); + u32 *reg_space = (u32 *) space; stmmac_dump_mac_regs(priv, priv->hw, reg_space); stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); - /* Copy DMA registers to where ethtool expects them */ - memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], - NUM_DWMAC1000_DMA_REGS * 4); + + if (!priv->plat->has_xgmac) { + /* Copy DMA registers to where ethtool expects them */ + memcpy(®_space[ETHTOOL_DMA_OFFSET], + ®_space[DMA_BUS_MODE / 4], + NUM_DWMAC1000_DMA_REGS * 4); + } } static int stmmac_nway_reset(struct net_device *dev) @@ -758,6 +774,76 @@ static int stmmac_set_coalesce(struct net_device *dev, return 0; } +static int stmmac_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *rxnfc, u32 *rule_locs) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + switch (rxnfc->cmd) { + case ETHTOOL_GRXRINGS: + rxnfc->data = priv->plat->rx_queues_to_use; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static u32 stmmac_get_rxfh_key_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return sizeof(priv->rss.key); +} + +static u32 stmmac_get_rxfh_indir_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return ARRAY_SIZE(priv->rss.table); +} + +static int stmmac_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + indir[i] = priv->rss.table[i]; + } + + if (key) + memcpy(key, priv->rss.key, sizeof(priv->rss.key)); + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + return 0; +} + +static int stmmac_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = indir[i]; + } + + if (key) + memcpy(priv->rss.key, key, sizeof(priv->rss.key)); + + return stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + static int stmmac_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { @@ -849,6 +935,11 @@ static const struct ethtool_ops stmmac_ethtool_ops = { .get_eee = stmmac_ethtool_op_get_eee, .set_eee = stmmac_ethtool_op_set_eee, .get_sset_count = stmmac_get_sset_count, + .get_rxnfc = stmmac_get_rxnfc, + .get_rxfh_key_size = stmmac_get_rxfh_key_size, + .get_rxfh_indir_size = stmmac_get_rxfh_indir_size, + .get_rxfh = stmmac_get_rxfh, + .set_rxfh = stmmac_set_rxfh, .get_ts_info = stmmac_get_ts_info, .get_coalesce = stmmac_get_coalesce, .set_coalesce = stmmac_set_coalesce, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index fd54c7c87485..bd1078433448 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -105,7 +105,7 @@ MODULE_PARM_DESC(chain_mode, "To use chain instead of ring mode"); static irqreturn_t stmmac_interrupt(int irq, void *dev_id); #ifdef CONFIG_DEBUG_FS -static int stmmac_init_fs(struct net_device *dev); +static void stmmac_init_fs(struct net_device *dev); static void stmmac_exit_fs(struct net_device *dev); #endif @@ -432,6 +432,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, struct sk_buff *skb) { struct skb_shared_hwtstamps shhwtstamp; + bool found = false; u64 ns = 0; if (!priv->hwts_tx_en) @@ -443,9 +444,13 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, /* check tx tstamp status */ if (stmmac_get_tx_timestamp_status(priv, p)) { - /* get the valid tstamp */ stmmac_get_timestamp(priv, p, priv->adv_ts, &ns); + found = true; + } else if (!stmmac_get_mac_tx_timestamp(priv, priv->hw, &ns)) { + found = true; + } + if (found) { memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp.hwtstamp = ns_to_ktime(ns); @@ -453,8 +458,6 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, /* pass tstamp to stack */ skb_tstamp_tx(skb, &shhwtstamp); } - - return; } /* stmmac_get_rx_hwtstamp - get HW RX timestamps @@ -1198,6 +1201,17 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, if (!buf->page) return -ENOMEM; + if (priv->sph) { + buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + if (!buf->sec_page) + return -ENOMEM; + + buf->sec_addr = page_pool_get_dma_addr(buf->sec_page); + stmmac_set_desc_sec_addr(priv, p, buf->sec_addr); + } else { + buf->sec_page = NULL; + } + buf->addr = page_pool_get_dma_addr(buf->page); stmmac_set_desc_addr(priv, p, buf->addr); if (priv->dma_buf_sz == BUF_SIZE_16KiB) @@ -1220,6 +1234,10 @@ static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i) if (buf->page) page_pool_put_page(rx_q->page_pool, buf->page, false); buf->page = NULL; + + if (buf->sec_page) + page_pool_put_page(rx_q->page_pool, buf->sec_page, false); + buf->sec_page = NULL; } /** @@ -2417,6 +2435,22 @@ static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) } } +static void stmmac_mac_config_rss(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.rssen || !priv->plat->rss_en) { + priv->rss.enable = false; + return; + } + + if (priv->dev->features & NETIF_F_RXHASH) + priv->rss.enable = true; + else + priv->rss.enable = false; + + stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -2461,6 +2495,10 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) /* Set RX routing */ if (rx_queues_count > 1) stmmac_mac_config_rx_queues_routing(priv); + + /* Receive Side Scaling */ + if (rx_queues_count > 1) + stmmac_mac_config_rss(priv); } static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) @@ -2573,6 +2611,16 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_enable_tso(priv, priv->ioaddr, 1, chan); } + /* Enable Split Header */ + if (priv->sph && priv->hw->rx_csum) { + for (chan = 0; chan < rx_cnt; chan++) + stmmac_enable_sph(priv, priv->ioaddr, 1, chan); + } + + /* VLAN Tag Insertion */ + if (priv->dma_cap.vlins) + stmmac_enable_vlan(priv, priv->hw, STMMAC_VLAN_INSERT); + /* Start the ball rolling... */ stmmac_start_all_dma(priv); @@ -2750,6 +2798,33 @@ static int stmmac_release(struct net_device *dev) return 0; } +static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, + struct stmmac_tx_queue *tx_q) +{ + u16 tag = 0x0, inner_tag = 0x0; + u32 inner_type = 0x0; + struct dma_desc *p; + + if (!priv->dma_cap.vlins) + return false; + if (!skb_vlan_tag_present(skb)) + return false; + if (skb->vlan_proto == htons(ETH_P_8021AD)) { + inner_tag = skb_vlan_tag_get(skb); + inner_type = STMMAC_VLAN_INSERT; + } + + tag = skb_vlan_tag_get(skb); + + p = tx_q->dma_tx + tx_q->cur_tx; + if (stmmac_set_desc_vlan_tag(priv, p, tag, inner_tag, inner_type)) + return false; + + stmmac_set_tx_owner(priv, p); + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + return true; +} + /** * stmmac_tso_allocator - close entry point of the driver * @priv: driver private structure @@ -2829,12 +2904,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); int nfrags = skb_shinfo(skb)->nr_frags; u32 queue = skb_get_queue_mapping(skb); - unsigned int first_entry; struct stmmac_tx_queue *tx_q; + unsigned int first_entry; int tmp_pay_len = 0; u32 pay_len, mss; u8 proto_hdr_len; dma_addr_t des; + bool has_vlan; int i; tx_q = &priv->tx_queue[queue]; @@ -2876,12 +2952,18 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb->data_len); } + /* Check if VLAN can be inserted by HW */ + has_vlan = stmmac_vlan_insert(priv, skb, tx_q); + first_entry = tx_q->cur_tx; WARN_ON(tx_q->tx_skbuff[first_entry]); desc = tx_q->dma_tx + first_entry; first = desc; + if (has_vlan) + stmmac_set_desc_vlan(priv, first, STMMAC_VLAN_INSERT); + /* first descriptor: fill Headers on Buf1 */ des = dma_map_single(priv->device, skb->data, skb_headlen(skb), DMA_TO_DEVICE); @@ -2960,6 +3042,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_set_ic_bit++; } + if (priv->sarc_type) + stmmac_set_desc_sarc(priv, first, priv->sarc_type); + skb_tx_timestamp(skb); if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && @@ -3038,6 +3123,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int first_entry; unsigned int enh_desc; dma_addr_t des; + bool has_vlan; int entry; tx_q = &priv->tx_queue[queue]; @@ -3063,6 +3149,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } + /* Check if VLAN can be inserted by HW */ + has_vlan = stmmac_vlan_insert(priv, skb, tx_q); + entry = tx_q->cur_tx; first_entry = entry; WARN_ON(tx_q->tx_skbuff[first_entry]); @@ -3076,6 +3165,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) first = desc; + if (has_vlan) + stmmac_set_desc_vlan(priv, first, STMMAC_VLAN_INSERT); + enh_desc = priv->plat->enh_desc; /* To program the descriptors according to the size of the frame */ if (enh_desc) @@ -3173,6 +3265,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_set_ic_bit++; } + if (priv->sarc_type) + stmmac_set_desc_sarc(priv, first, priv->sarc_type); + skb_tx_timestamp(skb); /* Ready to fill the first descriptor and set the OWN bit w/o any @@ -3292,6 +3387,17 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) break; } + if (priv->sph && !buf->sec_page) { + buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + if (!buf->sec_page) + break; + + buf->sec_addr = page_pool_get_dma_addr(buf->sec_page); + + dma_sync_single_for_device(priv->device, buf->sec_addr, + len, DMA_FROM_DEVICE); + } + buf->addr = page_pool_get_dma_addr(buf->page); /* Sync whole allocation to device. This will invalidate old @@ -3301,6 +3407,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) DMA_FROM_DEVICE); stmmac_set_desc_addr(priv, p, buf->addr); + stmmac_set_desc_sec_addr(priv, p, buf->sec_addr); stmmac_refill_desc3(priv, rx_q, p); rx_q->rx_count_frames++; @@ -3330,9 +3437,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct stmmac_channel *ch = &priv->channel[queue]; + unsigned int count = 0, error = 0, len = 0; + int status = 0, coe = priv->hw->rx_csum; unsigned int next_entry = rx_q->cur_rx; - int coe = priv->hw->rx_csum; - unsigned int count = 0; + struct sk_buff *skb = NULL; if (netif_msg_rx_status(priv)) { void *rx_head; @@ -3346,10 +3454,30 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true); } while (count < limit) { + unsigned int hlen = 0, prev_len = 0; + enum pkt_hash_types hash_type; struct stmmac_rx_buffer *buf; struct dma_desc *np, *p; - int entry, status; + unsigned int sec_len; + int entry; + u32 hash; + + if (!count && rx_q->state_saved) { + skb = rx_q->state.skb; + error = rx_q->state.error; + len = rx_q->state.len; + } else { + rx_q->state_saved = false; + skb = NULL; + error = 0; + len = 0; + } + if (count >= limit) + break; + +read_again: + sec_len = 0; entry = next_entry; buf = &rx_q->buf_pool[entry]; @@ -3376,6 +3504,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) np = rx_q->dma_rx + next_entry; prefetch(np); + prefetch(page_address(buf->page)); if (priv->extend_desc) stmmac_rx_extended_status(priv, &priv->dev->stats, @@ -3384,26 +3513,24 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) page_pool_recycle_direct(rx_q->page_pool, buf->page); priv->dev->stats.rx_errors++; buf->page = NULL; - } else { - struct sk_buff *skb; - int frame_len; - unsigned int des; + error = 1; + } - stmmac_get_desc_addr(priv, p, &des); - frame_len = stmmac_get_rx_frame_len(priv, p, coe); + if (unlikely(error && (status & rx_not_ls))) + goto read_again; + if (unlikely(error)) { + if (skb) + dev_kfree_skb(skb); + continue; + } - /* If frame length is greater than skb buffer size - * (preallocated during init) then the packet is - * ignored - */ - if (frame_len > priv->dma_buf_sz) { - if (net_ratelimit()) - netdev_err(priv->dev, - "len %d larger than size (%d)\n", - frame_len, priv->dma_buf_sz); - priv->dev->stats.rx_length_errors++; - continue; - } + /* Buffer is good. Go on. */ + + if (likely(status & rx_not_ls)) { + len += priv->dma_buf_sz; + } else { + prev_len = len; + len = stmmac_get_rx_frame_len(priv, p, coe); /* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3 * Type frames (LLC/LLC-SNAP) @@ -3414,53 +3541,97 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) */ if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) || unlikely(status != llc_snap)) - frame_len -= ETH_FCS_LEN; + len -= ETH_FCS_LEN; + } + + if (!skb) { + int ret = stmmac_get_rx_header_len(priv, p, &hlen); - if (netif_msg_rx_status(priv)) { - netdev_dbg(priv->dev, "\tdesc: %p [entry %d] buff=0x%x\n", - p, entry, des); - netdev_dbg(priv->dev, "frame size %d, COE: %d\n", - frame_len, status); + if (priv->sph && !ret && (hlen > 0)) { + sec_len = len; + if (!(status & rx_not_ls)) + sec_len = sec_len - hlen; + len = hlen; + + prefetch(page_address(buf->sec_page)); + priv->xstats.rx_split_hdr_pkt_n++; } - skb = netdev_alloc_skb_ip_align(priv->dev, frame_len); - if (unlikely(!skb)) { + skb = napi_alloc_skb(&ch->rx_napi, len); + if (!skb) { priv->dev->stats.rx_dropped++; continue; } - dma_sync_single_for_cpu(priv->device, buf->addr, - frame_len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(priv->device, buf->addr, len, + DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, page_address(buf->page), - frame_len); - skb_put(skb, frame_len); - - if (netif_msg_pktdata(priv)) { - netdev_dbg(priv->dev, "frame received (%dbytes)", - frame_len); - print_pkt(skb->data, frame_len); - } + len); + skb_put(skb, len); - stmmac_get_rx_hwtstamp(priv, p, np, skb); + /* Data payload copied into SKB, page ready for recycle */ + page_pool_recycle_direct(rx_q->page_pool, buf->page); + buf->page = NULL; + } else { + unsigned int buf_len = len - prev_len; - stmmac_rx_vlan(priv->dev, skb); + if (likely(status & rx_not_ls)) + buf_len = priv->dma_buf_sz; - skb->protocol = eth_type_trans(skb, priv->dev); + dma_sync_single_for_cpu(priv->device, buf->addr, + buf_len, DMA_FROM_DEVICE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + buf->page, 0, buf_len, + priv->dma_buf_sz); - if (unlikely(!coe)) - skb_checksum_none_assert(skb); - else - skb->ip_summed = CHECKSUM_UNNECESSARY; + /* Data payload appended into SKB */ + page_pool_release_page(rx_q->page_pool, buf->page); + buf->page = NULL; + } - napi_gro_receive(&ch->rx_napi, skb); + if (sec_len > 0) { + dma_sync_single_for_cpu(priv->device, buf->sec_addr, + sec_len, DMA_FROM_DEVICE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + buf->sec_page, 0, sec_len, + priv->dma_buf_sz); - /* Data payload copied into SKB, page ready for recycle */ - page_pool_recycle_direct(rx_q->page_pool, buf->page); - buf->page = NULL; + len += sec_len; - priv->dev->stats.rx_packets++; - priv->dev->stats.rx_bytes += frame_len; + /* Data payload appended into SKB */ + page_pool_release_page(rx_q->page_pool, buf->sec_page); + buf->sec_page = NULL; } + + if (likely(status & rx_not_ls)) + goto read_again; + + /* Got entire packet into SKB. Finish it. */ + + stmmac_get_rx_hwtstamp(priv, p, np, skb); + stmmac_rx_vlan(priv->dev, skb); + skb->protocol = eth_type_trans(skb, priv->dev); + + if (unlikely(!coe)) + skb_checksum_none_assert(skb); + else + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (!stmmac_get_rx_hash(priv, p, &hash, &hash_type)) + skb_set_hash(skb, hash, hash_type); + + skb_record_rx_queue(skb, queue); + napi_gro_receive(&ch->rx_napi, skb); + + priv->dev->stats.rx_packets++; + priv->dev->stats.rx_bytes += len; + } + + if (status & rx_not_ls) { + rx_q->state_saved = true; + rx_q->state.skb = skb; + rx_q->state.error = error; + rx_q->state.len = len; } stmmac_rx_refill(priv, queue); @@ -3606,6 +3777,8 @@ static int stmmac_set_features(struct net_device *netdev, netdev_features_t features) { struct stmmac_priv *priv = netdev_priv(netdev); + bool sph_en; + u32 chan; /* Keep the COE Type in case of csum is supporting */ if (features & NETIF_F_RXCSUM) @@ -3617,6 +3790,10 @@ static int stmmac_set_features(struct net_device *netdev, */ stmmac_rx_ipc(priv, priv->hw); + sph_en = (priv->hw->rx_csum > 0) && priv->sph; + for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++) + stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan); + return 0; } @@ -3962,54 +4139,102 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) } DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap); -static int stmmac_init_fs(struct net_device *dev) +static void stmmac_init_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); /* Create per netdev entries */ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir); - if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) { - netdev_err(priv->dev, "ERROR failed to create debugfs directory\n"); + /* Entry to report DMA RX/TX rings */ + debugfs_create_file("descriptors_status", 0444, priv->dbgfs_dir, dev, + &stmmac_rings_status_fops); - return -ENOMEM; + /* Entry to report the DMA HW features */ + debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev, + &stmmac_dma_cap_fops); +} + +static void stmmac_exit_fs(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + debugfs_remove_recursive(priv->dbgfs_dir); +} +#endif /* CONFIG_DEBUG_FS */ + +static u32 stmmac_vid_crc32_le(__le16 vid_le) +{ + unsigned char *data = (unsigned char *)&vid_le; + unsigned char data_byte = 0; + u32 crc = ~0x0; + u32 temp = 0; + int i, bits; + + bits = get_bitmask_order(VLAN_VID_MASK); + for (i = 0; i < bits; i++) { + if ((i % 8) == 0) + data_byte = data[i / 8]; + + temp = ((crc & 1) ^ data_byte) & 1; + crc >>= 1; + data_byte >>= 1; + + if (temp) + crc ^= 0xedb88320; } - /* Entry to report DMA RX/TX rings */ - priv->dbgfs_rings_status = - debugfs_create_file("descriptors_status", 0444, - priv->dbgfs_dir, dev, - &stmmac_rings_status_fops); + return crc; +} - if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) { - netdev_err(priv->dev, "ERROR creating stmmac ring debugfs file\n"); - debugfs_remove_recursive(priv->dbgfs_dir); +static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) +{ + u32 crc, hash = 0; + u16 vid; - return -ENOMEM; + for_each_set_bit(vid, priv->active_vlans, VLAN_N_VID) { + __le16 vid_le = cpu_to_le16(vid); + crc = bitrev32(~stmmac_vid_crc32_le(vid_le)) >> 28; + hash |= (1 << crc); } - /* Entry to report the DMA HW features */ - priv->dbgfs_dma_cap = debugfs_create_file("dma_cap", 0444, - priv->dbgfs_dir, - dev, &stmmac_dma_cap_fops); + return stmmac_update_vlan_hash(priv, priv->hw, hash, is_double); +} + +static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) +{ + struct stmmac_priv *priv = netdev_priv(ndev); + bool is_double = false; + int ret; - if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) { - netdev_err(priv->dev, "ERROR creating stmmac MMC debugfs file\n"); - debugfs_remove_recursive(priv->dbgfs_dir); + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + if (be16_to_cpu(proto) == ETH_P_8021AD) + is_double = true; - return -ENOMEM; + set_bit(vid, priv->active_vlans); + ret = stmmac_vlan_update(priv, is_double); + if (ret) { + clear_bit(vid, priv->active_vlans); + return ret; } - return 0; + return ret; } -static void stmmac_exit_fs(struct net_device *dev) +static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { - struct stmmac_priv *priv = netdev_priv(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + bool is_double = false; - debugfs_remove_recursive(priv->dbgfs_dir); + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + if (be16_to_cpu(proto) == ETH_P_8021AD) + is_double = true; + + clear_bit(vid, priv->active_vlans); + return stmmac_vlan_update(priv, is_double); } -#endif /* CONFIG_DEBUG_FS */ static const struct net_device_ops stmmac_netdev_ops = { .ndo_open = stmmac_open, @@ -4027,6 +4252,8 @@ static const struct net_device_ops stmmac_netdev_ops = { .ndo_poll_controller = stmmac_poll_controller, #endif .ndo_set_mac_address = stmmac_set_mac_address, + .ndo_vlan_rx_add_vid = stmmac_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = stmmac_vlan_rx_kill_vid, }; static void stmmac_reset_subtask(struct stmmac_priv *priv) @@ -4175,8 +4402,8 @@ int stmmac_dvr_probe(struct device *device, { struct net_device *ndev = NULL; struct stmmac_priv *priv; - u32 queue, maxq; - int ret = 0; + u32 queue, rxq, maxq; + int i, ret = 0; ndev = devm_alloc_etherdev_mqs(device, sizeof(struct stmmac_priv), MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES); @@ -4259,6 +4486,12 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "TSO feature enabled\n"); } + if (priv->dma_cap.sphen) { + ndev->hw_features |= NETIF_F_GRO; + priv->sph = true; + dev_info(priv->device, "SPH feature enabled\n"); + } + if (priv->dma_cap.addr64) { ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(priv->dma_cap.addr64)); @@ -4281,9 +4514,27 @@ int stmmac_dvr_probe(struct device *device, #ifdef STMMAC_VLAN_TAG_USED /* Both mac100 and gmac support receive VLAN tag detection */ ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; + if (priv->dma_cap.vlhash) { + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->features |= NETIF_F_HW_VLAN_STAG_FILTER; + } + if (priv->dma_cap.vlins) { + ndev->features |= NETIF_F_HW_VLAN_CTAG_TX; + if (priv->dma_cap.dvlan) + ndev->features |= NETIF_F_HW_VLAN_STAG_TX; + } #endif priv->msg_enable = netif_msg_init(debug, default_msg_level); + /* Initialize RSS */ + rxq = priv->plat->rx_queues_to_use; + netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key)); + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = ethtool_rxfh_indir_default(i, rxq); + + if (priv->dma_cap.rssen && priv->plat->rss_en) + ndev->features |= NETIF_F_RXHASH; + /* MTU range: 46 - hw-specific max */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00)) @@ -4368,10 +4619,7 @@ int stmmac_dvr_probe(struct device *device, } #ifdef CONFIG_DEBUG_FS - ret = stmmac_init_fs(ndev); - if (ret < 0) - netdev_warn(priv->dev, "%s: failed debugFS registration\n", - __func__); + stmmac_init_fs(ndev); #endif return ret; @@ -4617,16 +4865,8 @@ static int __init stmmac_init(void) { #ifdef CONFIG_DEBUG_FS /* Create debugfs main directory if it doesn't exist yet */ - if (!stmmac_fs_dir) { + if (!stmmac_fs_dir) stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); - - if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) { - pr_err("ERROR %s, debugfs create directory failed\n", - STMMAC_RESOURCE_NAME); - - return -ENOMEM; - } - } #endif return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 4304c1abc5d1..40c42637ad75 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -348,7 +348,9 @@ int stmmac_mdio_register(struct net_device *ndev) max_addr = PHY_MAX_ADDR; } - new_bus->reset = &stmmac_mdio_reset; + if (mdio_bus_data->needs_reset) + new_bus->reset = &stmmac_mdio_reset; + snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x", new_bus->name, priv->plat->bus_id); new_bus->priv = ndev; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 86f9c07a38cf..d5d08e11c353 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -63,6 +63,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat) plat->has_gmac = 1; plat->force_sf_dma_mode = 1; + plat->mdio_bus_data->needs_reset = true; plat->mdio_bus_data->phy_mask = 0; /* Set default value for multicast hash bins */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 154daf4d1072..eaf8f08f2e91 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -342,10 +342,16 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, mdio = true; } - if (mdio) + if (mdio) { plat->mdio_bus_data = devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data), GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + + plat->mdio_bus_data->needs_reset = true; + } + return 0; } @@ -522,13 +528,15 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) } /* clock setup */ - plat->stmmac_clk = devm_clk_get(&pdev->dev, - STMMAC_RESOURCE_NAME); - if (IS_ERR(plat->stmmac_clk)) { - dev_warn(&pdev->dev, "Cannot get CSR clock\n"); - plat->stmmac_clk = NULL; + if (!of_device_is_compatible(np, "snps,dwc-qos-ethernet-4.10")) { + plat->stmmac_clk = devm_clk_get(&pdev->dev, + STMMAC_RESOURCE_NAME); + if (IS_ERR(plat->stmmac_clk)) { + dev_warn(&pdev->dev, "Cannot get CSR clock\n"); + plat->stmmac_clk = NULL; + } + clk_prepare_enable(plat->stmmac_clk); } - clk_prepare_enable(plat->stmmac_clk); plat->pclk = devm_clk_get(&pdev->dev, "pclk"); if (IS_ERR(plat->pclk)) { @@ -609,13 +617,8 @@ int stmmac_get_platform_resources(struct platform_device *pdev, * probe if needed before we went too far with resource allocation. */ stmmac_res->irq = platform_get_irq_byname(pdev, "macirq"); - if (stmmac_res->irq < 0) { - if (stmmac_res->irq != -EPROBE_DEFER) { - dev_err(&pdev->dev, - "MAC IRQ configuration information not found\n"); - } + if (stmmac_res->irq < 0) return stmmac_res->irq; - } /* On some platforms e.g. SPEAr the wake up irq differs from the mac irq * The external wake up irq can be passed through the platform code diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index a97b1ea76438..ecc8602c6799 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -11,8 +11,10 @@ #include <linux/ip.h> #include <linux/phy.h> #include <linux/udp.h> +#include <net/pkt_cls.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/tc_act/tc_gact.h> #include "stmmac.h" struct stmmachdr { @@ -43,6 +45,7 @@ struct stmmac_packet_attrs { int size; int remove_sa; u8 id; + int sarc; }; static u8 stmmac_test_next_id; @@ -228,8 +231,11 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb, if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst)) goto out; } - if (tpriv->packet->src) { - if (!ether_addr_equal(ehdr->h_source, orig_ndev->dev_addr)) + if (tpriv->packet->sarc) { + if (!ether_addr_equal(ehdr->h_source, ehdr->h_dest)) + goto out; + } else if (tpriv->packet->src) { + if (!ether_addr_equal(ehdr->h_source, tpriv->packet->src)) goto out; } @@ -290,7 +296,9 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv, tpriv->pt.dev = priv->dev; tpriv->pt.af_packet_priv = tpriv; tpriv->packet = attr; - dev_add_pack(&tpriv->pt); + + if (!attr->dont_wait) + dev_add_pack(&tpriv->pt); skb = stmmac_test_get_udp_skb(priv, attr); if (!skb) { @@ -313,7 +321,8 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv, ret = !tpriv->ok; cleanup: - dev_remove_pack(&tpriv->pt); + if (!attr->dont_wait) + dev_remove_pack(&tpriv->pt); kfree(tpriv); return ret; } @@ -700,6 +709,465 @@ cleanup: return ret; } +static int stmmac_test_rss(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + + if (!priv->dma_cap.rssen || !priv->rss.enable) + return -EOPNOTSUPP; + + attr.dst = priv->dev->dev_addr; + attr.exp_hash = true; + attr.sport = 0x321; + attr.dport = 0x123; + + return __stmmac_test_loopback(priv, &attr); +} + +static int stmmac_test_vlan_validate(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt, + struct net_device *orig_ndev) +{ + struct stmmac_test_priv *tpriv = pt->af_packet_priv; + struct stmmachdr *shdr; + struct ethhdr *ehdr; + struct udphdr *uhdr; + struct iphdr *ihdr; + u16 proto; + + proto = tpriv->double_vlan ? ETH_P_8021AD : ETH_P_8021Q; + + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + goto out; + + if (skb_linearize(skb)) + goto out; + if (skb_headlen(skb) < (STMMAC_TEST_PKT_SIZE - ETH_HLEN)) + goto out; + if (tpriv->vlan_id) { + if (skb->vlan_proto != htons(proto)) + goto out; + if (skb->vlan_tci != tpriv->vlan_id) + goto out; + } + + ehdr = (struct ethhdr *)skb_mac_header(skb); + if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst)) + goto out; + + ihdr = ip_hdr(skb); + if (tpriv->double_vlan) + ihdr = (struct iphdr *)(skb_network_header(skb) + 4); + if (ihdr->protocol != IPPROTO_UDP) + goto out; + + uhdr = (struct udphdr *)((u8 *)ihdr + 4 * ihdr->ihl); + if (uhdr->dest != htons(tpriv->packet->dport)) + goto out; + + shdr = (struct stmmachdr *)((u8 *)uhdr + sizeof(*uhdr)); + if (shdr->magic != cpu_to_be64(STMMAC_TEST_PKT_MAGIC)) + goto out; + + tpriv->ok = true; + complete(&tpriv->comp); + +out: + kfree_skb(skb); + return 0; +} + +static int stmmac_test_vlanfilt(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0, i; + + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + tpriv->ok = false; + init_completion(&tpriv->comp); + + tpriv->pt.type = htons(ETH_P_IP); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + + /* + * As we use HASH filtering, false positives may appear. This is a + * specially chosen ID so that adjacent IDs (+4) have different + * HASH values. + */ + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id); + if (ret) + goto cleanup; + + for (i = 0; i < 4; i++) { + attr.vlan = 1; + attr.vlan_id_out = tpriv->vlan_id + i; + attr.dst = priv->dev->dev_addr; + attr.sport = 9; + attr.dport = 9; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = !tpriv->ok; + if (ret && !i) { + goto vlan_del; + } else if (!ret && i) { + ret = -1; + goto vlan_del; + } else { + ret = 0; + } + + tpriv->ok = false; + } + +vlan_del: + vlan_vid_del(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +static int stmmac_test_dvlanfilt(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0, i; + + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + tpriv->ok = false; + tpriv->double_vlan = true; + init_completion(&tpriv->comp); + + tpriv->pt.type = htons(ETH_P_8021Q); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + + /* + * As we use HASH filtering, false positives may appear. This is a + * specially chosen ID so that adjacent IDs (+4) have different + * HASH values. + */ + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id); + if (ret) + goto cleanup; + + for (i = 0; i < 4; i++) { + attr.vlan = 2; + attr.vlan_id_out = tpriv->vlan_id + i; + attr.dst = priv->dev->dev_addr; + attr.sport = 9; + attr.dport = 9; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = !tpriv->ok; + if (ret && !i) { + goto vlan_del; + } else if (!ret && i) { + ret = -1; + goto vlan_del; + } else { + ret = 0; + } + + tpriv->ok = false; + } + +vlan_del: + vlan_vid_del(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +#ifdef CONFIG_NET_CLS_ACT +static int stmmac_test_rxp(struct stmmac_priv *priv) +{ + unsigned char addr[ETH_ALEN] = {0xde, 0xad, 0xbe, 0xef, 0x00, 0x00}; + struct tc_cls_u32_offload cls_u32 = { }; + struct stmmac_packet_attrs attr = { }; + struct tc_action **actions, *act; + struct tc_u32_sel *sel; + struct tcf_exts *exts; + int ret, i, nk = 1; + + if (!tc_can_offload(priv->dev)) + return -EOPNOTSUPP; + if (!priv->dma_cap.frpsel) + return -EOPNOTSUPP; + + sel = kzalloc(sizeof(*sel) + nk * sizeof(struct tc_u32_key), GFP_KERNEL); + if (!sel) + return -ENOMEM; + + exts = kzalloc(sizeof(*exts), GFP_KERNEL); + if (!exts) { + ret = -ENOMEM; + goto cleanup_sel; + } + + actions = kzalloc(nk * sizeof(*actions), GFP_KERNEL); + if (!actions) { + ret = -ENOMEM; + goto cleanup_exts; + } + + act = kzalloc(nk * sizeof(*act), GFP_KERNEL); + if (!act) { + ret = -ENOMEM; + goto cleanup_actions; + } + + cls_u32.command = TC_CLSU32_NEW_KNODE; + cls_u32.common.chain_index = 0; + cls_u32.common.protocol = htons(ETH_P_ALL); + cls_u32.knode.exts = exts; + cls_u32.knode.sel = sel; + cls_u32.knode.handle = 0x123; + + exts->nr_actions = nk; + exts->actions = actions; + for (i = 0; i < nk; i++) { + struct tcf_gact *gact = to_gact(&act[i]); + + actions[i] = &act[i]; + gact->tcf_action = TC_ACT_SHOT; + } + + sel->nkeys = nk; + sel->offshift = 0; + sel->keys[0].off = 6; + sel->keys[0].val = htonl(0xdeadbeef); + sel->keys[0].mask = ~0x0; + + ret = stmmac_tc_setup_cls_u32(priv, priv, &cls_u32); + if (ret) + goto cleanup_act; + + attr.dst = priv->dev->dev_addr; + attr.src = addr; + + ret = __stmmac_test_loopback(priv, &attr); + ret = !ret; /* Shall NOT receive packet */ + + cls_u32.command = TC_CLSU32_DELETE_KNODE; + stmmac_tc_setup_cls_u32(priv, priv, &cls_u32); + +cleanup_act: + kfree(act); +cleanup_actions: + kfree(actions); +cleanup_exts: + kfree(exts); +cleanup_sel: + kfree(sel); + return ret; +} +#else +static int stmmac_test_rxp(struct stmmac_priv *priv) +{ + return -EOPNOTSUPP; +} +#endif + +static int stmmac_test_desc_sai(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + attr.remove_sa = true; + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + priv->sarc_type = 0x1; + + ret = __stmmac_test_loopback(priv, &attr); + + priv->sarc_type = 0x0; + return ret; +} + +static int stmmac_test_desc_sar(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + priv->sarc_type = 0x2; + + ret = __stmmac_test_loopback(priv, &attr); + + priv->sarc_type = 0x0; + return ret; +} + +static int stmmac_test_reg_sai(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + attr.remove_sa = true; + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + if (stmmac_sarc_configure(priv, priv->ioaddr, 0x2)) + return -EOPNOTSUPP; + + ret = __stmmac_test_loopback(priv, &attr); + + stmmac_sarc_configure(priv, priv->ioaddr, 0x0); + return ret; +} + +static int stmmac_test_reg_sar(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + if (stmmac_sarc_configure(priv, priv->ioaddr, 0x3)) + return -EOPNOTSUPP; + + ret = __stmmac_test_loopback(priv, &attr); + + stmmac_sarc_configure(priv, priv->ioaddr, 0x0); + return ret; +} + +static int stmmac_test_vlanoff_common(struct stmmac_priv *priv, bool svlan) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0; + u16 proto; + + if (!priv->dma_cap.vlins) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + proto = svlan ? ETH_P_8021AD : ETH_P_8021Q; + + tpriv->ok = false; + tpriv->double_vlan = svlan; + init_completion(&tpriv->comp); + + tpriv->pt.type = svlan ? htons(ETH_P_8021Q) : htons(ETH_P_IP); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(proto), tpriv->vlan_id); + if (ret) + goto cleanup; + + attr.dst = priv->dev->dev_addr; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + __vlan_hwaccel_put_tag(skb, htons(proto), tpriv->vlan_id); + skb->protocol = htons(proto); + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = tpriv->ok ? 0 : -ETIMEDOUT; + +vlan_del: + vlan_vid_del(priv->dev, htons(proto), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +static int stmmac_test_vlanoff(struct stmmac_priv *priv) +{ + return stmmac_test_vlanoff_common(priv, false); +} + +static int stmmac_test_svlanoff(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.dvlan) + return -EOPNOTSUPP; + return stmmac_test_vlanoff_common(priv, true); +} + #define STMMAC_LOOPBACK_NONE 0 #define STMMAC_LOOPBACK_MAC 1 #define STMMAC_LOOPBACK_PHY 2 @@ -745,6 +1213,46 @@ static const struct stmmac_test { .name = "Flow Control ", .lb = STMMAC_LOOPBACK_PHY, .fn = stmmac_test_flowctrl, + }, { + .name = "RSS ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_rss, + }, { + .name = "VLAN Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_vlanfilt, + }, { + .name = "Double VLAN Filtering", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_dvlanfilt, + }, { + .name = "Flexible RX Parser ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_rxp, + }, { + .name = "SA Insertion (desc) ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_desc_sai, + }, { + .name = "SA Replacement (desc)", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_desc_sar, + }, { + .name = "SA Insertion (reg) ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_reg_sai, + }, { + .name = "SA Replacement (reg)", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_reg_sar, + }, { + .name = "VLAN TX Insertion ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_vlanoff, + }, { + .name = "SVLAN TX Insertion ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_svlanoff, }, }; diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 6fc05c106afc..c91876f8c536 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -2034,7 +2034,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, __skb_frag_set_page(frag, page->buffer); __skb_frag_ref(frag); - frag->page_offset = off; + skb_frag_off_set(frag, off); skb_frag_size_set(frag, hlen - swivel); /* any more data? */ @@ -2058,7 +2058,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, __skb_frag_set_page(frag, page->buffer); __skb_frag_ref(frag); - frag->page_offset = 0; + skb_frag_off_set(frag, 0); skb_frag_size_set(frag, hlen); RX_USED_ADD(page, hlen + cp->crc_size); } @@ -2816,7 +2816,7 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring, mapping = skb_frag_dma_map(&cp->pdev->dev, fragp, 0, len, DMA_TO_DEVICE); - tabort = cas_calc_tabort(cp, fragp->page_offset, len); + tabort = cas_calc_tabort(cp, skb_frag_off(fragp), len); if (unlikely(tabort)) { void *addr; @@ -2827,7 +2827,7 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring, addr = cas_page_map(skb_frag_page(fragp)); memcpy(tx_tiny_buf(cp, ring, entry), - addr + fragp->page_offset + len - tabort, + addr + skb_frag_off(fragp) + len - tabort, tabort); cas_page_unmap(addr); mapping = tx_tiny_map(cp, ring, entry, tentry); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 0bc5863bffeb..f5fd1f3c07cc 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6695,7 +6695,7 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, len = skb_frag_size(frag); mapping = np->ops->map_page(np->device, skb_frag_page(frag), - frag->page_offset, len, + skb_frag_off(frag), len, DMA_TO_DEVICE); rp->tx_buffs[prod].skb = NULL; diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index baa3088b475c..646e67236b65 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1088,7 +1088,7 @@ static inline int vnet_skb_map(struct ldc_channel *lp, struct sk_buff *skb, vaddr = kmap_atomic(skb_frag_page(f)); blen = skb_frag_size(f); blen += 8 - (blen & 7); - err = ldc_map_single(lp, vaddr + f->page_offset, + err = ldc_map_single(lp, vaddr + skb_frag_off(f), blen, cookies + nc, ncookies - nc, map_perm); kunmap_atomic(vaddr); @@ -1124,7 +1124,7 @@ static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *f = &skb_shinfo(skb)->frags[i]; - docopy |= f->page_offset & 7; + docopy |= skb_frag_off(f) & 7; } if (((unsigned long)skb->data & 7) != VNET_PACKET_SKIP || skb_tailroom(skb) < pad || diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c index 031cf9c3435a..8c4195a9a2cc 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c @@ -503,7 +503,7 @@ static int xlgmac_map_tx_skb(struct xlgmac_channel *channel, struct xlgmac_desc_data *desc_data; unsigned int offset, datalen, len; struct xlgmac_pkt_info *pkt_info; - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int tso, vlan; dma_addr_t skb_dma; unsigned int i; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c index 1f8e9601592a..a1f5a1e61040 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c @@ -116,7 +116,7 @@ static void xlgmac_prep_tx_pkt(struct xlgmac_pdata *pdata, struct sk_buff *skb, struct xlgmac_pkt_info *pkt_info) { - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int context_desc; unsigned int len; unsigned int i; diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 5d6960fe3309..0f8a924fc60c 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1501,7 +1501,7 @@ bdx_tx_map_skb(struct bdx_priv *priv, struct sk_buff *skb, bdx_tx_db_inc_wptr(db); for (i = 0; i < nr_frags; i++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; frag = &skb_shinfo(skb)->frags[i]; db->wptr->len = skb_frag_size(frag); diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 642843945031..1b2702f74455 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1116,7 +1116,7 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct page *page = skb_frag_page(frag); - u32 page_offset = frag->page_offset; + u32 page_offset = skb_frag_off(frag); u32 buf_len = skb_frag_size(frag); dma_addr_t desc_dma; u32 desc_dma_32; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 442018ccd65e..c5bfa19ddb93 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -25,6 +25,7 @@ #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/jiffies.h> +#include <linux/refcount.h> #include <net/ax25.h> @@ -70,7 +71,7 @@ struct mkiss { #define CRC_MODE_FLEX_TEST 3 #define CRC_MODE_SMACK_TEST 4 - atomic_t refcnt; + refcount_t refcnt; struct completion dead; }; @@ -668,7 +669,7 @@ static struct mkiss *mkiss_get(struct tty_struct *tty) read_lock(&disc_data_lock); ax = tty->disc_data; if (ax) - atomic_inc(&ax->refcnt); + refcount_inc(&ax->refcnt); read_unlock(&disc_data_lock); return ax; @@ -676,7 +677,7 @@ static struct mkiss *mkiss_get(struct tty_struct *tty) static void mkiss_put(struct mkiss *ax) { - if (atomic_dec_and_test(&ax->refcnt)) + if (refcount_dec_and_test(&ax->refcnt)) complete(&ax->dead); } @@ -704,7 +705,7 @@ static int mkiss_open(struct tty_struct *tty) ax->dev = dev; spin_lock_init(&ax->buflock); - atomic_set(&ax->refcnt, 1); + refcount_set(&ax->refcnt, 1); init_completion(&ax->dead); ax->tty = tty; @@ -784,7 +785,7 @@ static void mkiss_close(struct tty_struct *tty) * We have now ensured that nobody can start using ap from now on, but * we have to wait for all existing users to finish. */ - if (!atomic_dec_and_test(&ax->refcnt)) + if (!refcount_dec_and_test(&ax->refcnt)) wait_for_completion(&ax->dead); /* * Halt the transmit queue so that a new transmit cannot scribble diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index e8fce6d715ef..0a6cd2f1111f 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -435,7 +435,7 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, skb_frag_t *frag = skb_shinfo(skb)->frags + i; slots_used += fill_pg_buf(skb_frag_page(frag), - frag->page_offset, + skb_frag_off(frag), skb_frag_size(frag), &pb[slots_used]); } return slots_used; @@ -449,7 +449,7 @@ static int count_skb_frag_slots(struct sk_buff *skb) for (i = 0; i < frags; i++) { skb_frag_t *frag = skb_shinfo(skb)->frags + i; unsigned long size = skb_frag_size(frag); - unsigned long offset = frag->page_offset; + unsigned long offset = skb_frag_off(frag); /* Skip unused frames from start of page */ offset &= ~PAGE_MASK; diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index c9392d70e639..5a37514e4234 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -1158,23 +1158,16 @@ static int adf7242_stats_show(struct seq_file *file, void *offset) return 0; } -static int adf7242_debugfs_init(struct adf7242_local *lp) +static void adf7242_debugfs_init(struct adf7242_local *lp) { char debugfs_dir_name[DNAME_INLINE_LEN + 1] = "adf7242-"; - struct dentry *stats; strncat(debugfs_dir_name, dev_name(&lp->spi->dev), DNAME_INLINE_LEN); lp->debugfs_root = debugfs_create_dir(debugfs_dir_name, NULL); - if (IS_ERR_OR_NULL(lp->debugfs_root)) - return PTR_ERR_OR_ZERO(lp->debugfs_root); - stats = debugfs_create_devm_seqfile(&lp->spi->dev, "status", - lp->debugfs_root, - adf7242_stats_show); - return PTR_ERR_OR_ZERO(stats); - - return 0; + debugfs_create_devm_seqfile(&lp->spi->dev, "status", lp->debugfs_root, + adf7242_stats_show); } static const s32 adf7242_powers[] = { diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 595cf7e2a651..7d67f41387f5 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -1626,24 +1626,16 @@ static int at86rf230_stats_show(struct seq_file *file, void *offset) } DEFINE_SHOW_ATTRIBUTE(at86rf230_stats); -static int at86rf230_debugfs_init(struct at86rf230_local *lp) +static void at86rf230_debugfs_init(struct at86rf230_local *lp) { char debugfs_dir_name[DNAME_INLINE_LEN + 1] = "at86rf230-"; - struct dentry *stats; strncat(debugfs_dir_name, dev_name(&lp->spi->dev), DNAME_INLINE_LEN); at86rf230_debugfs_root = debugfs_create_dir(debugfs_dir_name, NULL); - if (!at86rf230_debugfs_root) - return -ENOMEM; - - stats = debugfs_create_file("trac_stats", 0444, - at86rf230_debugfs_root, lp, - &at86rf230_stats_fops); - if (!stats) - return -ENOMEM; - return 0; + debugfs_create_file("trac_stats", 0444, at86rf230_debugfs_root, lp, + &at86rf230_stats_fops); } static void at86rf230_debugfs_remove(void) @@ -1651,7 +1643,7 @@ static void at86rf230_debugfs_remove(void) debugfs_remove_recursive(at86rf230_debugfs_root); } #else -static int at86rf230_debugfs_init(struct at86rf230_local *lp) { return 0; } +static void at86rf230_debugfs_init(struct at86rf230_local *lp) { } static void at86rf230_debugfs_remove(void) { } #endif @@ -1751,9 +1743,7 @@ static int at86rf230_probe(struct spi_device *spi) /* going into sleep by default */ at86rf230_sleep(lp); - rc = at86rf230_debugfs_init(lp); - if (rc) - goto free_dev; + at86rf230_debugfs_init(lp); rc = ieee802154_register_hw(lp->hw); if (rc) diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index b188fce3f641..11402dc347db 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -3019,14 +3019,7 @@ static int ca8210_test_interface_init(struct ca8210_priv *priv) priv, &test_int_fops ); - if (IS_ERR(test->ca8210_dfs_spi_int)) { - dev_err( - &priv->spi->dev, - "Error %ld when creating debugfs node\n", - PTR_ERR(test->ca8210_dfs_spi_int) - ); - return PTR_ERR(test->ca8210_dfs_spi_int); - } + debugfs_create_symlink("ca8210", NULL, node_name); init_waitqueue_head(&test->readq); return kfifo_alloc( diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 1c96bed5a7c4..887bbba4631e 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -126,6 +126,7 @@ static int ipvlan_init(struct net_device *dev) (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED; + dev->hw_enc_features |= dev->features; dev->gso_max_size = phy_dev->gso_max_size; dev->gso_max_segs = phy_dev->gso_max_segs; dev->hard_header_len = phy_dev->hard_header_len; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index bcc40a236624..c5b026150bf5 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -17,16 +17,60 @@ #include <linux/debugfs.h> #include <linux/device.h> +#include <linux/etherdevice.h> +#include <linux/inet.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rtnetlink.h> +#include <linux/workqueue.h> #include <net/devlink.h> +#include <net/ip.h> +#include <uapi/linux/devlink.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/udp.h> #include "netdevsim.h" static struct dentry *nsim_dev_ddir; +#define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32) + +static ssize_t nsim_dev_take_snapshot_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + void *dummy_data; + int err; + u32 id; + + dummy_data = kmalloc(NSIM_DEV_DUMMY_REGION_SIZE, GFP_KERNEL); + if (!dummy_data) + return -ENOMEM; + + get_random_bytes(dummy_data, NSIM_DEV_DUMMY_REGION_SIZE); + + id = devlink_region_shapshot_id_get(priv_to_devlink(nsim_dev)); + err = devlink_region_snapshot_create(nsim_dev->dummy_region, + dummy_data, id, kfree); + if (err) { + pr_err("Failed to create region snapshot\n"); + kfree(dummy_data); + return err; + } + + return count; +} + +static const struct file_operations nsim_dev_take_snapshot_fops = { + .open = simple_open, + .write = nsim_dev_take_snapshot_write, + .llseek = generic_file_llseek, +}; + static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) { char dev_ddir_name[16]; @@ -40,6 +84,12 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) return PTR_ERR_OR_ZERO(nsim_dev->ports_ddir) ?: -EINVAL; debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir, &nsim_dev->fw_update_status); + debugfs_create_u32("max_macs", 0600, nsim_dev->ddir, + &nsim_dev->max_macs); + debugfs_create_bool("test1", 0600, nsim_dev->ddir, + &nsim_dev->test1); + debugfs_create_file("take_snapshot", 0200, nsim_dev->ddir, nsim_dev, + &nsim_dev_take_snapshot_fops); return 0; } @@ -193,6 +243,283 @@ out: return err; } +enum nsim_devlink_param_id { + NSIM_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + NSIM_DEVLINK_PARAM_ID_TEST1, +}; + +static const struct devlink_param nsim_devlink_params[] = { + DEVLINK_PARAM_GENERIC(MAX_MACS, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL), + DEVLINK_PARAM_DRIVER(NSIM_DEVLINK_PARAM_ID_TEST1, + "test1", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL), +}; + +static void nsim_devlink_set_params_init_values(struct nsim_dev *nsim_dev, + struct devlink *devlink) +{ + union devlink_param_value value; + + value.vu32 = nsim_dev->max_macs; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + value); + value.vbool = nsim_dev->test1; + devlink_param_driverinit_value_set(devlink, + NSIM_DEVLINK_PARAM_ID_TEST1, + value); +} + +static void nsim_devlink_param_load_driverinit_values(struct devlink *devlink) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + union devlink_param_value saved_value; + int err; + + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + &saved_value); + if (!err) + nsim_dev->max_macs = saved_value.vu32; + err = devlink_param_driverinit_value_get(devlink, + NSIM_DEVLINK_PARAM_ID_TEST1, + &saved_value); + if (!err) + nsim_dev->test1 = saved_value.vbool; +} + +#define NSIM_DEV_DUMMY_REGION_SNAPSHOT_MAX 16 + +static int nsim_dev_dummy_region_init(struct nsim_dev *nsim_dev, + struct devlink *devlink) +{ + nsim_dev->dummy_region = + devlink_region_create(devlink, "dummy", + NSIM_DEV_DUMMY_REGION_SNAPSHOT_MAX, + NSIM_DEV_DUMMY_REGION_SIZE); + return PTR_ERR_OR_ZERO(nsim_dev->dummy_region); +} + +static void nsim_dev_dummy_region_exit(struct nsim_dev *nsim_dev) +{ + devlink_region_destroy(nsim_dev->dummy_region); +} + +struct nsim_trap_item { + void *trap_ctx; + enum devlink_trap_action action; +}; + +struct nsim_trap_data { + struct delayed_work trap_report_dw; + struct nsim_trap_item *trap_items_arr; + struct nsim_dev *nsim_dev; + spinlock_t trap_lock; /* Protects trap_items_arr */ +}; + +/* All driver-specific traps must be documented in + * Documentation/networking/devlink-trap-netdevsim.rst + */ +enum { + NSIM_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX, + NSIM_TRAP_ID_FID_MISS, +}; + +#define NSIM_TRAP_NAME_FID_MISS "fid_miss" + +#define NSIM_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT + +#define NSIM_TRAP_DROP(_id, _group_id) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + NSIM_TRAP_METADATA) +#define NSIM_TRAP_EXCEPTION(_id, _group_id) \ + DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + NSIM_TRAP_METADATA) +#define NSIM_TRAP_DRIVER_EXCEPTION(_id, _group_id) \ + DEVLINK_TRAP_DRIVER(EXCEPTION, TRAP, NSIM_TRAP_ID_##_id, \ + NSIM_TRAP_NAME_##_id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + NSIM_TRAP_METADATA) + +static const struct devlink_trap nsim_traps_arr[] = { + NSIM_TRAP_DROP(SMAC_MC, L2_DROPS), + NSIM_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS), + NSIM_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS), + NSIM_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS), + NSIM_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS), + NSIM_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS), + NSIM_TRAP_DRIVER_EXCEPTION(FID_MISS, L2_DROPS), + NSIM_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS), + NSIM_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS), + NSIM_TRAP_DROP(TAIL_DROP, BUFFER_DROPS), +}; + +#define NSIM_TRAP_L4_DATA_LEN 100 + +static struct sk_buff *nsim_dev_trap_skb_build(void) +{ + int tot_len, data_len = NSIM_TRAP_L4_DATA_LEN; + struct sk_buff *skb; + struct udphdr *udph; + struct ethhdr *eth; + struct iphdr *iph; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); + if (!skb) + return NULL; + tot_len = sizeof(struct iphdr) + sizeof(struct udphdr) + data_len; + + eth = skb_put(skb, sizeof(struct ethhdr)); + eth_random_addr(eth->h_dest); + eth_random_addr(eth->h_source); + eth->h_proto = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IP); + + iph = skb_put(skb, sizeof(struct iphdr)); + iph->protocol = IPPROTO_UDP; + iph->saddr = in_aton("192.0.2.1"); + iph->daddr = in_aton("198.51.100.1"); + iph->version = 0x4; + iph->frag_off = 0; + iph->ihl = 0x5; + iph->tot_len = htons(tot_len); + iph->ttl = 100; + ip_send_check(iph); + + udph = skb_put_zero(skb, sizeof(struct udphdr) + data_len); + get_random_bytes(&udph->source, sizeof(u16)); + get_random_bytes(&udph->dest, sizeof(u16)); + udph->len = htons(sizeof(struct udphdr) + data_len); + + return skb; +} + +static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port) +{ + struct nsim_dev *nsim_dev = nsim_dev_port->ns->nsim_dev; + struct devlink *devlink = priv_to_devlink(nsim_dev); + struct nsim_trap_data *nsim_trap_data; + int i; + + nsim_trap_data = nsim_dev->trap_data; + + spin_lock(&nsim_trap_data->trap_lock); + for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) { + struct nsim_trap_item *nsim_trap_item; + struct sk_buff *skb; + + nsim_trap_item = &nsim_trap_data->trap_items_arr[i]; + if (nsim_trap_item->action == DEVLINK_TRAP_ACTION_DROP) + continue; + + skb = nsim_dev_trap_skb_build(); + if (!skb) + continue; + skb->dev = nsim_dev_port->ns->netdev; + + /* Trapped packets are usually passed to devlink in softIRQ, + * but in this case they are generated in a workqueue. Disable + * softIRQs to prevent lockdep from complaining about + * "incosistent lock state". + */ + local_bh_disable(); + devlink_trap_report(devlink, skb, nsim_trap_item->trap_ctx, + &nsim_dev_port->devlink_port); + local_bh_enable(); + consume_skb(skb); + } + spin_unlock(&nsim_trap_data->trap_lock); +} + +#define NSIM_TRAP_REPORT_INTERVAL_MS 100 + +static void nsim_dev_trap_report_work(struct work_struct *work) +{ + struct nsim_trap_data *nsim_trap_data; + struct nsim_dev_port *nsim_dev_port; + struct nsim_dev *nsim_dev; + + nsim_trap_data = container_of(work, struct nsim_trap_data, + trap_report_dw.work); + nsim_dev = nsim_trap_data->nsim_dev; + + /* For each running port and enabled packet trap, generate a UDP + * packet with a random 5-tuple and report it. + */ + mutex_lock(&nsim_dev->port_list_lock); + list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) { + if (!netif_running(nsim_dev_port->ns->netdev)) + continue; + + nsim_dev_trap_report(nsim_dev_port); + } + mutex_unlock(&nsim_dev->port_list_lock); + + schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, + msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); +} + +static int nsim_dev_traps_init(struct devlink *devlink) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + struct nsim_trap_data *nsim_trap_data; + int err; + + nsim_trap_data = kzalloc(sizeof(*nsim_trap_data), GFP_KERNEL); + if (!nsim_trap_data) + return -ENOMEM; + + nsim_trap_data->trap_items_arr = kcalloc(ARRAY_SIZE(nsim_traps_arr), + sizeof(struct nsim_trap_item), + GFP_KERNEL); + if (!nsim_trap_data->trap_items_arr) { + err = -ENOMEM; + goto err_trap_data_free; + } + + /* The lock is used to protect the action state of the registered + * traps. The value is written by user and read in delayed work when + * iterating over all the traps. + */ + spin_lock_init(&nsim_trap_data->trap_lock); + nsim_trap_data->nsim_dev = nsim_dev; + nsim_dev->trap_data = nsim_trap_data; + + err = devlink_traps_register(devlink, nsim_traps_arr, + ARRAY_SIZE(nsim_traps_arr), NULL); + if (err) + goto err_trap_items_free; + + INIT_DELAYED_WORK(&nsim_dev->trap_data->trap_report_dw, + nsim_dev_trap_report_work); + schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, + msecs_to_jiffies(NSIM_TRAP_REPORT_INTERVAL_MS)); + + return 0; + +err_trap_items_free: + kfree(nsim_trap_data->trap_items_arr); +err_trap_data_free: + kfree(nsim_trap_data); + return err; +} + +static void nsim_dev_traps_exit(struct devlink *devlink) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + cancel_delayed_work_sync(&nsim_dev->trap_data->trap_report_dw); + devlink_traps_unregister(devlink, nsim_traps_arr, + ARRAY_SIZE(nsim_traps_arr)); + kfree(nsim_dev->trap_data->trap_items_arr); + kfree(nsim_dev->trap_data); +} + static int nsim_dev_reload(struct devlink *devlink, struct netlink_ext_ack *extack) { @@ -214,6 +541,7 @@ static int nsim_dev_reload(struct devlink *devlink, return err; } } + nsim_devlink_param_load_driverinit_values(devlink); return 0; } @@ -258,11 +586,66 @@ static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name, return 0; } +static struct nsim_trap_item * +nsim_dev_trap_item_lookup(struct nsim_dev *nsim_dev, u16 trap_id) +{ + struct nsim_trap_data *nsim_trap_data = nsim_dev->trap_data; + int i; + + for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) { + if (nsim_traps_arr[i].id == trap_id) + return &nsim_trap_data->trap_items_arr[i]; + } + + return NULL; +} + +static int nsim_dev_devlink_trap_init(struct devlink *devlink, + const struct devlink_trap *trap, + void *trap_ctx) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + struct nsim_trap_item *nsim_trap_item; + + nsim_trap_item = nsim_dev_trap_item_lookup(nsim_dev, trap->id); + if (WARN_ON(!nsim_trap_item)) + return -ENOENT; + + nsim_trap_item->trap_ctx = trap_ctx; + nsim_trap_item->action = trap->init_action; + + return 0; +} + +static int +nsim_dev_devlink_trap_action_set(struct devlink *devlink, + const struct devlink_trap *trap, + enum devlink_trap_action action) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + struct nsim_trap_item *nsim_trap_item; + + nsim_trap_item = nsim_dev_trap_item_lookup(nsim_dev, trap->id); + if (WARN_ON(!nsim_trap_item)) + return -ENOENT; + + spin_lock(&nsim_dev->trap_data->trap_lock); + nsim_trap_item->action = action; + spin_unlock(&nsim_dev->trap_data->trap_lock); + + return 0; +} + static const struct devlink_ops nsim_dev_devlink_ops = { .reload = nsim_dev_reload, .flash_update = nsim_dev_flash_update, + .trap_init = nsim_dev_devlink_trap_init, + .trap_action_set = nsim_dev_devlink_trap_action_set, }; +#define NSIM_DEV_MAX_MACS_DEFAULT 32 +#define NSIM_DEV_TEST1_DEFAULT true + static struct nsim_dev * nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) { @@ -280,6 +663,8 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) INIT_LIST_HEAD(&nsim_dev->port_list); mutex_init(&nsim_dev->port_list_lock); nsim_dev->fw_update_status = true; + nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; + nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; err = nsim_dev_resources_register(devlink); if (err) @@ -289,18 +674,40 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) if (err) goto err_resources_unregister; - err = nsim_dev_debugfs_init(nsim_dev); + err = devlink_params_register(devlink, nsim_devlink_params, + ARRAY_SIZE(nsim_devlink_params)); if (err) goto err_dl_unregister; + nsim_devlink_set_params_init_values(nsim_dev, devlink); + + err = nsim_dev_dummy_region_init(nsim_dev, devlink); + if (err) + goto err_params_unregister; + + err = nsim_dev_traps_init(devlink); + if (err) + goto err_dummy_region_exit; + + err = nsim_dev_debugfs_init(nsim_dev); + if (err) + goto err_traps_exit; err = nsim_bpf_dev_init(nsim_dev); if (err) goto err_debugfs_exit; + devlink_params_publish(devlink); return nsim_dev; err_debugfs_exit: nsim_dev_debugfs_exit(nsim_dev); +err_traps_exit: + nsim_dev_traps_exit(devlink); +err_dummy_region_exit: + nsim_dev_dummy_region_exit(nsim_dev); +err_params_unregister: + devlink_params_unregister(devlink, nsim_devlink_params, + ARRAY_SIZE(nsim_devlink_params)); err_dl_unregister: devlink_unregister(devlink); err_resources_unregister: @@ -316,6 +723,10 @@ static void nsim_dev_destroy(struct nsim_dev *nsim_dev) nsim_bpf_dev_exit(nsim_dev); nsim_dev_debugfs_exit(nsim_dev); + nsim_dev_traps_exit(devlink); + nsim_dev_dummy_region_exit(nsim_dev); + devlink_params_unregister(devlink, nsim_devlink_params, + ARRAY_SIZE(nsim_devlink_params)); devlink_unregister(devlink); devlink_resources_unregister(devlink, NULL); mutex_destroy(&nsim_dev->port_list_lock); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 9404637d34b7..66bf13765ad0 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -145,6 +145,7 @@ struct nsim_dev_port { struct nsim_dev { struct nsim_bus_dev *nsim_bus_dev; struct nsim_fib_data *fib_data; + struct nsim_trap_data *trap_data; struct dentry *ddir; struct dentry *ports_ddir; struct bpf_offload_dev *bpf_dev; @@ -158,6 +159,9 @@ struct nsim_dev { struct list_head port_list; struct mutex port_list_lock; /* protects port list */ bool fw_update_status; + u32 max_macs; + bool test1; + struct devlink_region *dummy_region; }; int nsim_dev_init(void); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 20f14c5fbb7e..03be30cde552 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -21,6 +21,19 @@ config MDIO_BUS if MDIO_BUS +config MDIO_ASPEED + tristate "ASPEED MDIO bus controller" + depends on ARCH_ASPEED || COMPILE_TEST + depends on OF_MDIO && HAS_IOMEM + help + This module provides a driver for the independent MDIO bus + controllers found in the ASPEED AST2600 SoC. This is a driver for the + third revision of the ASPEED MDIO register interface - the first two + revisions are the "old" and "new" interfaces found in the AST2400 and + AST2500, embedded in the MAC. For legacy reasons, FTGMAC100 driver + continues to drive the embedded MDIO controller for the AST2400 and + AST2500 SoCs, so say N if AST2600 support is not required. + config MDIO_BCM_IPROC tristate "Broadcom iProc MDIO bus controller" depends on ARCH_BCM_IPROC || COMPILE_TEST @@ -159,8 +172,8 @@ config MDIO_MSCC_MIIM config MDIO_OCTEON tristate "Octeon and some ThunderX SOCs MDIO buses" - depends on 64BIT - depends on HAS_IOMEM && OF_MDIO + depends on (64BIT && OF_MDIO) || COMPILE_TEST + depends on HAS_IOMEM select MDIO_CAVIUM help This module provides a driver for the Octeon and ThunderX MDIO @@ -244,6 +257,15 @@ config SFP depends on HWMON || HWMON=n select MDIO_I2C +config ADIN_PHY + tristate "Analog Devices Industrial Ethernet PHYs" + help + Adds support for the Analog Devices Industrial Ethernet PHYs. + Currently supports the: + - ADIN1200 - Robust,Industrial, Low Power 10/100 Ethernet PHY + - ADIN1300 - Robust,Industrial, Low Latency 10/100/1000 Gigabit + Ethernet PHY + config AMD_PHY tristate "AMD PHYs" ---help--- diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 839acb292c38..a03437e091f3 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -22,6 +22,7 @@ libphy-$(CONFIG_LED_TRIGGER_PHY) += phy_led_triggers.o obj-$(CONFIG_PHYLINK) += phylink.o obj-$(CONFIG_PHYLIB) += libphy.o +obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o obj-$(CONFIG_MDIO_BCM_UNIMAC) += mdio-bcm-unimac.o obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o @@ -46,6 +47,7 @@ obj-$(CONFIG_SFP) += sfp.o sfp-obj-$(CONFIG_SFP) += sfp-bus.o obj-y += $(sfp-obj-y) $(sfp-obj-m) +obj-$(CONFIG_ADIN_PHY) += adin.o obj-$(CONFIG_AMD_PHY) += amd.o aquantia-objs += aquantia_main.o ifdef CONFIG_HWMON diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c new file mode 100644 index 000000000000..4dec83df048d --- /dev/null +++ b/drivers/net/phy/adin.c @@ -0,0 +1,720 @@ +// SPDX-License-Identifier: GPL-2.0+ +/** + * Driver for Analog Devices Industrial Ethernet PHYs + * + * Copyright 2019 Analog Devices Inc. + */ +#include <linux/kernel.h> +#include <linux/bitfield.h> +#include <linux/delay.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mii.h> +#include <linux/phy.h> +#include <linux/property.h> + +#define PHY_ID_ADIN1200 0x0283bc20 +#define PHY_ID_ADIN1300 0x0283bc30 + +#define ADIN1300_MII_EXT_REG_PTR 0x0010 +#define ADIN1300_MII_EXT_REG_DATA 0x0011 + +#define ADIN1300_PHY_CTRL1 0x0012 +#define ADIN1300_AUTO_MDI_EN BIT(10) +#define ADIN1300_MAN_MDIX_EN BIT(9) + +#define ADIN1300_RX_ERR_CNT 0x0014 + +#define ADIN1300_PHY_CTRL2 0x0016 +#define ADIN1300_DOWNSPEED_AN_100_EN BIT(11) +#define ADIN1300_DOWNSPEED_AN_10_EN BIT(10) +#define ADIN1300_GROUP_MDIO_EN BIT(6) +#define ADIN1300_DOWNSPEEDS_EN \ + (ADIN1300_DOWNSPEED_AN_100_EN | ADIN1300_DOWNSPEED_AN_10_EN) + +#define ADIN1300_PHY_CTRL3 0x0017 +#define ADIN1300_LINKING_EN BIT(13) +#define ADIN1300_DOWNSPEED_RETRIES_MSK GENMASK(12, 10) + +#define ADIN1300_INT_MASK_REG 0x0018 +#define ADIN1300_INT_MDIO_SYNC_EN BIT(9) +#define ADIN1300_INT_ANEG_STAT_CHNG_EN BIT(8) +#define ADIN1300_INT_ANEG_PAGE_RX_EN BIT(6) +#define ADIN1300_INT_IDLE_ERR_CNT_EN BIT(5) +#define ADIN1300_INT_MAC_FIFO_OU_EN BIT(4) +#define ADIN1300_INT_RX_STAT_CHNG_EN BIT(3) +#define ADIN1300_INT_LINK_STAT_CHNG_EN BIT(2) +#define ADIN1300_INT_SPEED_CHNG_EN BIT(1) +#define ADIN1300_INT_HW_IRQ_EN BIT(0) +#define ADIN1300_INT_MASK_EN \ + (ADIN1300_INT_LINK_STAT_CHNG_EN | ADIN1300_INT_HW_IRQ_EN) +#define ADIN1300_INT_STATUS_REG 0x0019 + +#define ADIN1300_PHY_STATUS1 0x001a +#define ADIN1300_PAIR_01_SWAP BIT(11) + +/* EEE register addresses, accessible via Clause 22 access using + * ADIN1300_MII_EXT_REG_PTR & ADIN1300_MII_EXT_REG_DATA. + * The bit-fields are the same as specified by IEEE for EEE. + */ +#define ADIN1300_EEE_CAP_REG 0x8000 +#define ADIN1300_EEE_ADV_REG 0x8001 +#define ADIN1300_EEE_LPABLE_REG 0x8002 +#define ADIN1300_CLOCK_STOP_REG 0x9400 +#define ADIN1300_LPI_WAKE_ERR_CNT_REG 0xa000 + +#define ADIN1300_GE_SOFT_RESET_REG 0xff0c +#define ADIN1300_GE_SOFT_RESET BIT(0) + +#define ADIN1300_GE_RGMII_CFG_REG 0xff23 +#define ADIN1300_GE_RGMII_RX_MSK GENMASK(8, 6) +#define ADIN1300_GE_RGMII_RX_SEL(x) \ + FIELD_PREP(ADIN1300_GE_RGMII_RX_MSK, x) +#define ADIN1300_GE_RGMII_GTX_MSK GENMASK(5, 3) +#define ADIN1300_GE_RGMII_GTX_SEL(x) \ + FIELD_PREP(ADIN1300_GE_RGMII_GTX_MSK, x) +#define ADIN1300_GE_RGMII_RXID_EN BIT(2) +#define ADIN1300_GE_RGMII_TXID_EN BIT(1) +#define ADIN1300_GE_RGMII_EN BIT(0) + +/* RGMII internal delay settings for rx and tx for ADIN1300 */ +#define ADIN1300_RGMII_1_60_NS 0x0001 +#define ADIN1300_RGMII_1_80_NS 0x0002 +#define ADIN1300_RGMII_2_00_NS 0x0000 +#define ADIN1300_RGMII_2_20_NS 0x0006 +#define ADIN1300_RGMII_2_40_NS 0x0007 + +#define ADIN1300_GE_RMII_CFG_REG 0xff24 +#define ADIN1300_GE_RMII_FIFO_DEPTH_MSK GENMASK(6, 4) +#define ADIN1300_GE_RMII_FIFO_DEPTH_SEL(x) \ + FIELD_PREP(ADIN1300_GE_RMII_FIFO_DEPTH_MSK, x) +#define ADIN1300_GE_RMII_EN BIT(0) + +/* RMII fifo depth values */ +#define ADIN1300_RMII_4_BITS 0x0000 +#define ADIN1300_RMII_8_BITS 0x0001 +#define ADIN1300_RMII_12_BITS 0x0002 +#define ADIN1300_RMII_16_BITS 0x0003 +#define ADIN1300_RMII_20_BITS 0x0004 +#define ADIN1300_RMII_24_BITS 0x0005 + +/** + * struct adin_cfg_reg_map - map a config value to aregister value + * @cfg value in device configuration + * @reg value in the register + */ +struct adin_cfg_reg_map { + int cfg; + int reg; +}; + +static const struct adin_cfg_reg_map adin_rgmii_delays[] = { + { 1600, ADIN1300_RGMII_1_60_NS }, + { 1800, ADIN1300_RGMII_1_80_NS }, + { 2000, ADIN1300_RGMII_2_00_NS }, + { 2200, ADIN1300_RGMII_2_20_NS }, + { 2400, ADIN1300_RGMII_2_40_NS }, + { }, +}; + +static const struct adin_cfg_reg_map adin_rmii_fifo_depths[] = { + { 4, ADIN1300_RMII_4_BITS }, + { 8, ADIN1300_RMII_8_BITS }, + { 12, ADIN1300_RMII_12_BITS }, + { 16, ADIN1300_RMII_16_BITS }, + { 20, ADIN1300_RMII_20_BITS }, + { 24, ADIN1300_RMII_24_BITS }, + { }, +}; + +/** + * struct adin_clause45_mmd_map - map to convert Clause 45 regs to Clause 22 + * @devad device address used in Clause 45 access + * @cl45_regnum register address defined by Clause 45 + * @adin_regnum equivalent register address accessible via Clause 22 + */ +struct adin_clause45_mmd_map { + int devad; + u16 cl45_regnum; + u16 adin_regnum; +}; + +static struct adin_clause45_mmd_map adin_clause45_mmd_map[] = { + { MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE, ADIN1300_EEE_CAP_REG }, + { MDIO_MMD_AN, MDIO_AN_EEE_LPABLE, ADIN1300_EEE_LPABLE_REG }, + { MDIO_MMD_AN, MDIO_AN_EEE_ADV, ADIN1300_EEE_ADV_REG }, + { MDIO_MMD_PCS, MDIO_CTRL1, ADIN1300_CLOCK_STOP_REG }, + { MDIO_MMD_PCS, MDIO_PCS_EEE_WK_ERR, ADIN1300_LPI_WAKE_ERR_CNT_REG }, +}; + +struct adin_hw_stat { + const char *string; + u16 reg1; + u16 reg2; +}; + +static struct adin_hw_stat adin_hw_stats[] = { + { "total_frames_checked_count", 0x940A, 0x940B }, /* hi + lo */ + { "length_error_frames_count", 0x940C }, + { "alignment_error_frames_count", 0x940D }, + { "symbol_error_count", 0x940E }, + { "oversized_frames_count", 0x940F }, + { "undersized_frames_count", 0x9410 }, + { "odd_nibble_frames_count", 0x9411 }, + { "odd_preamble_packet_count", 0x9412 }, + { "dribble_bits_frames_count", 0x9413 }, + { "false_carrier_events_count", 0x9414 }, +}; + +/** + * struct adin_priv - ADIN PHY driver private data + * stats statistic counters for the PHY + */ +struct adin_priv { + u64 stats[ARRAY_SIZE(adin_hw_stats)]; +}; + +static int adin_lookup_reg_value(const struct adin_cfg_reg_map *tbl, int cfg) +{ + size_t i; + + for (i = 0; tbl[i].cfg; i++) { + if (tbl[i].cfg == cfg) + return tbl[i].reg; + } + + return -EINVAL; +} + +static u32 adin_get_reg_value(struct phy_device *phydev, + const char *prop_name, + const struct adin_cfg_reg_map *tbl, + u32 dflt) +{ + struct device *dev = &phydev->mdio.dev; + u32 val; + int rc; + + if (device_property_read_u32(dev, prop_name, &val)) + return dflt; + + rc = adin_lookup_reg_value(tbl, val); + if (rc < 0) { + phydev_warn(phydev, + "Unsupported value %u for %s using default (%u)\n", + val, prop_name, dflt); + return dflt; + } + + return rc; +} + +static int adin_config_rgmii_mode(struct phy_device *phydev) +{ + u32 val; + int reg; + + if (!phy_interface_is_rgmii(phydev)) + return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_GE_RGMII_CFG_REG, + ADIN1300_GE_RGMII_EN); + + reg = phy_read_mmd(phydev, MDIO_MMD_VEND1, ADIN1300_GE_RGMII_CFG_REG); + if (reg < 0) + return reg; + + reg |= ADIN1300_GE_RGMII_EN; + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) { + reg |= ADIN1300_GE_RGMII_RXID_EN; + + val = adin_get_reg_value(phydev, "adi,rx-internal-delay-ps", + adin_rgmii_delays, + ADIN1300_RGMII_2_00_NS); + reg &= ~ADIN1300_GE_RGMII_RX_MSK; + reg |= ADIN1300_GE_RGMII_RX_SEL(val); + } else { + reg &= ~ADIN1300_GE_RGMII_RXID_EN; + } + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) { + reg |= ADIN1300_GE_RGMII_TXID_EN; + + val = adin_get_reg_value(phydev, "adi,tx-internal-delay-ps", + adin_rgmii_delays, + ADIN1300_RGMII_2_00_NS); + reg &= ~ADIN1300_GE_RGMII_GTX_MSK; + reg |= ADIN1300_GE_RGMII_GTX_SEL(val); + } else { + reg &= ~ADIN1300_GE_RGMII_TXID_EN; + } + + return phy_write_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_GE_RGMII_CFG_REG, reg); +} + +static int adin_config_rmii_mode(struct phy_device *phydev) +{ + u32 val; + int reg; + + if (phydev->interface != PHY_INTERFACE_MODE_RMII) + return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_GE_RMII_CFG_REG, + ADIN1300_GE_RMII_EN); + + reg = phy_read_mmd(phydev, MDIO_MMD_VEND1, ADIN1300_GE_RMII_CFG_REG); + if (reg < 0) + return reg; + + reg |= ADIN1300_GE_RMII_EN; + + val = adin_get_reg_value(phydev, "adi,fifo-depth-bits", + adin_rmii_fifo_depths, + ADIN1300_RMII_8_BITS); + + reg &= ~ADIN1300_GE_RMII_FIFO_DEPTH_MSK; + reg |= ADIN1300_GE_RMII_FIFO_DEPTH_SEL(val); + + return phy_write_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_GE_RMII_CFG_REG, reg); +} + +static int adin_get_downshift(struct phy_device *phydev, u8 *data) +{ + int val, cnt, enable; + + val = phy_read(phydev, ADIN1300_PHY_CTRL2); + if (val < 0) + return val; + + cnt = phy_read(phydev, ADIN1300_PHY_CTRL3); + if (cnt < 0) + return cnt; + + enable = FIELD_GET(ADIN1300_DOWNSPEEDS_EN, val); + cnt = FIELD_GET(ADIN1300_DOWNSPEED_RETRIES_MSK, cnt); + + *data = (enable && cnt) ? cnt : DOWNSHIFT_DEV_DISABLE; + + return 0; +} + +static int adin_set_downshift(struct phy_device *phydev, u8 cnt) +{ + u16 val; + int rc; + + if (cnt == DOWNSHIFT_DEV_DISABLE) + return phy_clear_bits(phydev, ADIN1300_PHY_CTRL2, + ADIN1300_DOWNSPEEDS_EN); + + if (cnt > 7) + 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, + val); + if (rc < 0) + return rc; + + return phy_set_bits(phydev, ADIN1300_PHY_CTRL2, + ADIN1300_DOWNSPEEDS_EN); +} + +static int adin_get_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return adin_get_downshift(phydev, data); + default: + return -EOPNOTSUPP; + } +} + +static int adin_set_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, const void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return adin_set_downshift(phydev, *(const u8 *)data); + default: + return -EOPNOTSUPP; + } +} + +static int adin_config_init(struct phy_device *phydev) +{ + int rc; + + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + + rc = adin_config_rgmii_mode(phydev); + if (rc < 0) + return rc; + + rc = adin_config_rmii_mode(phydev); + if (rc < 0) + return rc; + + rc = adin_set_downshift(phydev, 4); + if (rc < 0) + return rc; + + phydev_dbg(phydev, "PHY is using mode '%s'\n", + phy_modes(phydev->interface)); + + return 0; +} + +static int adin_phy_ack_intr(struct phy_device *phydev) +{ + /* Clear pending interrupts */ + int rc = phy_read(phydev, ADIN1300_INT_STATUS_REG); + + return rc < 0 ? rc : 0; +} + +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); + + return phy_clear_bits(phydev, ADIN1300_INT_MASK_REG, + ADIN1300_INT_MASK_EN); +} + +static int adin_cl45_to_adin_reg(struct phy_device *phydev, int devad, + u16 cl45_regnum) +{ + struct adin_clause45_mmd_map *m; + int i; + + if (devad == MDIO_MMD_VEND1) + return cl45_regnum; + + for (i = 0; i < ARRAY_SIZE(adin_clause45_mmd_map); i++) { + m = &adin_clause45_mmd_map[i]; + if (m->devad == devad && m->cl45_regnum == cl45_regnum) + return m->adin_regnum; + } + + phydev_err(phydev, + "No translation available for devad: %d reg: %04x\n", + devad, cl45_regnum); + + return -EINVAL; +} + +static int adin_read_mmd(struct phy_device *phydev, int devad, u16 regnum) +{ + struct mii_bus *bus = phydev->mdio.bus; + int phy_addr = phydev->mdio.addr; + int adin_regnum; + int err; + + adin_regnum = adin_cl45_to_adin_reg(phydev, devad, regnum); + if (adin_regnum < 0) + return adin_regnum; + + err = __mdiobus_write(bus, phy_addr, ADIN1300_MII_EXT_REG_PTR, + adin_regnum); + if (err) + return err; + + return __mdiobus_read(bus, phy_addr, ADIN1300_MII_EXT_REG_DATA); +} + +static int adin_write_mmd(struct phy_device *phydev, int devad, u16 regnum, + u16 val) +{ + struct mii_bus *bus = phydev->mdio.bus; + int phy_addr = phydev->mdio.addr; + int adin_regnum; + int err; + + adin_regnum = adin_cl45_to_adin_reg(phydev, devad, regnum); + if (adin_regnum < 0) + return adin_regnum; + + err = __mdiobus_write(bus, phy_addr, ADIN1300_MII_EXT_REG_PTR, + adin_regnum); + if (err) + return err; + + return __mdiobus_write(bus, phy_addr, ADIN1300_MII_EXT_REG_DATA, val); +} + +static int adin_config_mdix(struct phy_device *phydev) +{ + bool auto_en, mdix_en; + int reg; + + mdix_en = false; + auto_en = false; + switch (phydev->mdix_ctrl) { + case ETH_TP_MDI: + break; + case ETH_TP_MDI_X: + mdix_en = true; + break; + case ETH_TP_MDI_AUTO: + auto_en = true; + break; + default: + return -EINVAL; + } + + reg = phy_read(phydev, ADIN1300_PHY_CTRL1); + if (reg < 0) + return reg; + + if (mdix_en) + reg |= ADIN1300_MAN_MDIX_EN; + else + reg &= ~ADIN1300_MAN_MDIX_EN; + + if (auto_en) + reg |= ADIN1300_AUTO_MDI_EN; + else + reg &= ~ADIN1300_AUTO_MDI_EN; + + return phy_write(phydev, ADIN1300_PHY_CTRL1, reg); +} + +static int adin_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = adin_config_mdix(phydev); + if (ret) + return ret; + + return genphy_config_aneg(phydev); +} + +static int adin_mdix_update(struct phy_device *phydev) +{ + bool auto_en, mdix_en; + bool swapped; + int reg; + + reg = phy_read(phydev, ADIN1300_PHY_CTRL1); + if (reg < 0) + return reg; + + auto_en = !!(reg & ADIN1300_AUTO_MDI_EN); + mdix_en = !!(reg & ADIN1300_MAN_MDIX_EN); + + /* If MDI/MDIX is forced, just read it from the control reg */ + if (!auto_en) { + if (mdix_en) + phydev->mdix = ETH_TP_MDI_X; + else + phydev->mdix = ETH_TP_MDI; + return 0; + } + + /** + * Otherwise, we need to deduce it from the PHY status2 reg. + * When Auto-MDI is enabled, the ADIN1300_MAN_MDIX_EN bit implies + * a preference for MDIX when it is set. + */ + reg = phy_read(phydev, ADIN1300_PHY_STATUS1); + if (reg < 0) + return reg; + + swapped = !!(reg & ADIN1300_PAIR_01_SWAP); + + if (mdix_en != swapped) + phydev->mdix = ETH_TP_MDI_X; + else + phydev->mdix = ETH_TP_MDI; + + return 0; +} + +static int adin_read_status(struct phy_device *phydev) +{ + int ret; + + ret = adin_mdix_update(phydev); + if (ret < 0) + return ret; + + return genphy_read_status(phydev); +} + +static int adin_soft_reset(struct phy_device *phydev) +{ + int rc; + + /* The reset bit is self-clearing, set it and wait */ + rc = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_GE_SOFT_RESET_REG, + ADIN1300_GE_SOFT_RESET); + if (rc < 0) + return rc; + + msleep(10); + + /* If we get a read error something may be wrong */ + rc = phy_read_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_GE_SOFT_RESET_REG); + + return rc < 0 ? rc : 0; +} + +static int adin_get_sset_count(struct phy_device *phydev) +{ + return ARRAY_SIZE(adin_hw_stats); +} + +static void adin_get_strings(struct phy_device *phydev, u8 *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(adin_hw_stats); i++) { + strlcpy(&data[i * ETH_GSTRING_LEN], + adin_hw_stats[i].string, ETH_GSTRING_LEN); + } +} + +static int adin_read_mmd_stat_regs(struct phy_device *phydev, + struct adin_hw_stat *stat, + u32 *val) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, stat->reg1); + if (ret < 0) + return ret; + + *val = (ret & 0xffff); + + if (stat->reg2 == 0) + return 0; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, stat->reg2); + if (ret < 0) + return ret; + + *val <<= 16; + *val |= (ret & 0xffff); + + return 0; +} + +static u64 adin_get_stat(struct phy_device *phydev, int i) +{ + struct adin_hw_stat *stat = &adin_hw_stats[i]; + struct adin_priv *priv = phydev->priv; + u32 val; + int ret; + + if (stat->reg1 > 0x1f) { + ret = adin_read_mmd_stat_regs(phydev, stat, &val); + if (ret < 0) + return (u64)(~0); + } else { + ret = phy_read(phydev, stat->reg1); + if (ret < 0) + return (u64)(~0); + val = (ret & 0xffff); + } + + priv->stats[i] += val; + + return priv->stats[i]; +} + +static void adin_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + int i, rc; + + /* latch copies of all the frame-checker counters */ + rc = phy_read(phydev, ADIN1300_RX_ERR_CNT); + if (rc < 0) + return; + + for (i = 0; i < ARRAY_SIZE(adin_hw_stats); i++) + data[i] = adin_get_stat(phydev, i); +} + +static int adin_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct adin_priv *priv; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return 0; +} + +static struct phy_driver adin_driver[] = { + { + PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200), + .name = "ADIN1200", + .probe = adin_probe, + .config_init = adin_config_init, + .soft_reset = adin_soft_reset, + .config_aneg = adin_config_aneg, + .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, + .get_sset_count = adin_get_sset_count, + .get_strings = adin_get_strings, + .get_stats = adin_get_stats, + .resume = genphy_resume, + .suspend = genphy_suspend, + .read_mmd = adin_read_mmd, + .write_mmd = adin_write_mmd, + }, + { + PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300), + .name = "ADIN1300", + .probe = adin_probe, + .config_init = adin_config_init, + .soft_reset = adin_soft_reset, + .config_aneg = adin_config_aneg, + .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, + .get_sset_count = adin_get_sset_count, + .get_strings = adin_get_strings, + .get_stats = adin_get_stats, + .resume = genphy_resume, + .suspend = genphy_suspend, + .read_mmd = adin_read_mmd, + .write_mmd = adin_write_mmd, + }, +}; + +module_phy_driver(adin_driver); + +static struct mdio_device_id __maybe_unused adin_tbl[] = { + { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200) }, + { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300) }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, adin_tbl); +MODULE_DESCRIPTION("Analog Devices Industrial Ethernet PHY driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 6ad8b1c63c34..2aa7b2e60046 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -249,10 +249,6 @@ static int at803x_config_init(struct phy_device *phydev) { int ret; - ret = genphy_config_init(phydev); - if (ret < 0) - return ret; - /* The RX and TX delay default is: * after HW reset: RX delay enabled and TX delay disabled * after SW reset: RX delay enabled, while TX delay retains the diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 7ed4760fb155..8a4b1d167ce2 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -254,13 +254,8 @@ static int dp83822_config_intr(struct phy_device *phydev) static int dp83822_config_init(struct phy_device *phydev) { - int err; int value; - err = genphy_config_init(phydev); - if (err < 0) - return err; - value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN; return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c index 6f9bc7d91f17..54c7c1b44e4d 100644 --- a/drivers/net/phy/dp83848.c +++ b/drivers/net/phy/dp83848.c @@ -68,13 +68,8 @@ static int dp83848_config_intr(struct phy_device *phydev) static int dp83848_config_init(struct phy_device *phydev) { - int err; int val; - err = genphy_config_init(phydev); - if (err < 0) - return err; - /* DP83620 always reports Auto Negotiation Ability on BMSR. Instead, * we check initial value of BMCR Auto negotiation enable bit */ @@ -113,13 +108,13 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl); static struct phy_driver dp83848_driver[] = { DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY", - genphy_config_init), + NULL), DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY", - genphy_config_init), + NULL), DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY", dp83848_config_init), DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY", - genphy_config_init), + NULL), }; module_phy_driver(dp83848_driver); diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index ac27da16824d..06f08832ebcd 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -277,10 +277,6 @@ static int dp83811_config_init(struct phy_device *phydev) { int value, err; - err = genphy_config_init(phydev); - if (err < 0) - return err; - value = phy_read(phydev, MII_DP83811_SGMII_CTRL); if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { err = phy_write(phydev, MII_DP83811_SGMII_CTRL, diff --git a/drivers/net/phy/mdio-aspeed.c b/drivers/net/phy/mdio-aspeed.c new file mode 100644 index 000000000000..cad820568f75 --- /dev/null +++ b/drivers/net/phy/mdio-aspeed.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright (C) 2019 IBM Corp. */ + +#include <linux/bitfield.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/mdio.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/phy.h> +#include <linux/platform_device.h> + +#define DRV_NAME "mdio-aspeed" + +#define ASPEED_MDIO_CTRL 0x0 +#define ASPEED_MDIO_CTRL_FIRE BIT(31) +#define ASPEED_MDIO_CTRL_ST BIT(28) +#define ASPEED_MDIO_CTRL_ST_C45 0 +#define ASPEED_MDIO_CTRL_ST_C22 1 +#define ASPEED_MDIO_CTRL_OP GENMASK(27, 26) +#define MDIO_C22_OP_WRITE 0b01 +#define MDIO_C22_OP_READ 0b10 +#define ASPEED_MDIO_CTRL_PHYAD GENMASK(25, 21) +#define ASPEED_MDIO_CTRL_REGAD GENMASK(20, 16) +#define ASPEED_MDIO_CTRL_MIIWDATA GENMASK(15, 0) + +#define ASPEED_MDIO_DATA 0x4 +#define ASPEED_MDIO_DATA_MDC_THRES GENMASK(31, 24) +#define ASPEED_MDIO_DATA_MDIO_EDGE BIT(23) +#define ASPEED_MDIO_DATA_MDIO_LATCH GENMASK(22, 20) +#define ASPEED_MDIO_DATA_IDLE BIT(16) +#define ASPEED_MDIO_DATA_MIIRDATA GENMASK(15, 0) + +#define ASPEED_MDIO_INTERVAL_US 100 +#define ASPEED_MDIO_TIMEOUT_US (ASPEED_MDIO_INTERVAL_US * 10) + +struct aspeed_mdio { + void __iomem *base; +}; + +static int aspeed_mdio_read(struct mii_bus *bus, int addr, int regnum) +{ + struct aspeed_mdio *ctx = bus->priv; + u32 ctrl; + u32 data; + int rc; + + dev_dbg(&bus->dev, "%s: addr: %d, regnum: %d\n", __func__, addr, + regnum); + + /* Just clause 22 for the moment */ + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + + ctrl = ASPEED_MDIO_CTRL_FIRE + | FIELD_PREP(ASPEED_MDIO_CTRL_ST, ASPEED_MDIO_CTRL_ST_C22) + | FIELD_PREP(ASPEED_MDIO_CTRL_OP, MDIO_C22_OP_READ) + | FIELD_PREP(ASPEED_MDIO_CTRL_PHYAD, addr) + | FIELD_PREP(ASPEED_MDIO_CTRL_REGAD, regnum); + + iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL); + + rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_DATA, data, + data & ASPEED_MDIO_DATA_IDLE, + ASPEED_MDIO_INTERVAL_US, + ASPEED_MDIO_TIMEOUT_US); + if (rc < 0) + return rc; + + return FIELD_GET(ASPEED_MDIO_DATA_MIIRDATA, data); +} + +static int aspeed_mdio_write(struct mii_bus *bus, int addr, int regnum, u16 val) +{ + struct aspeed_mdio *ctx = bus->priv; + u32 ctrl; + + dev_dbg(&bus->dev, "%s: addr: %d, regnum: %d, val: 0x%x\n", + __func__, addr, regnum, val); + + /* Just clause 22 for the moment */ + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + + ctrl = ASPEED_MDIO_CTRL_FIRE + | FIELD_PREP(ASPEED_MDIO_CTRL_ST, ASPEED_MDIO_CTRL_ST_C22) + | FIELD_PREP(ASPEED_MDIO_CTRL_OP, MDIO_C22_OP_WRITE) + | FIELD_PREP(ASPEED_MDIO_CTRL_PHYAD, addr) + | FIELD_PREP(ASPEED_MDIO_CTRL_REGAD, regnum) + | FIELD_PREP(ASPEED_MDIO_CTRL_MIIWDATA, val); + + iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL); + + return readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl, + !(ctrl & ASPEED_MDIO_CTRL_FIRE), + ASPEED_MDIO_INTERVAL_US, + ASPEED_MDIO_TIMEOUT_US); +} + +static int aspeed_mdio_probe(struct platform_device *pdev) +{ + struct aspeed_mdio *ctx; + struct mii_bus *bus; + int rc; + + bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*ctx)); + if (!bus) + return -ENOMEM; + + ctx = bus->priv; + ctx->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(ctx->base)) + return PTR_ERR(ctx->base); + + bus->name = DRV_NAME; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s%d", pdev->name, pdev->id); + bus->parent = &pdev->dev; + bus->read = aspeed_mdio_read; + bus->write = aspeed_mdio_write; + + rc = of_mdiobus_register(bus, pdev->dev.of_node); + if (rc) { + dev_err(&pdev->dev, "Cannot register MDIO bus!\n"); + return rc; + } + + platform_set_drvdata(pdev, bus); + + return 0; +} + +static int aspeed_mdio_remove(struct platform_device *pdev) +{ + mdiobus_unregister(platform_get_drvdata(pdev)); + + return 0; +} + +static const struct of_device_id aspeed_mdio_of_match[] = { + { .compatible = "aspeed,ast2600-mdio", }, + { }, +}; + +static struct platform_driver aspeed_mdio_driver = { + .driver = { + .name = DRV_NAME, + .of_match_table = aspeed_mdio_of_match, + }, + .probe = aspeed_mdio_probe, + .remove = aspeed_mdio_remove, +}; + +module_platform_driver(aspeed_mdio_driver); + +MODULE_AUTHOR("Andrew Jeffery <andrew@aj.id.au>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/mdio-cavium.h b/drivers/net/phy/mdio-cavium.h index ed5f9bb5448d..b7f89ad27465 100644 --- a/drivers/net/phy/mdio-cavium.h +++ b/drivers/net/phy/mdio-cavium.h @@ -108,6 +108,8 @@ static inline u64 oct_mdio_readq(u64 addr) return cvmx_read_csr(addr); } #else +#include <linux/io-64-nonatomic-lo-hi.h> + #define oct_mdio_writeq(val, addr) writeq(val, (void *)addr) #define oct_mdio_readq(addr) readq((void *)addr) #endif diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c index 717cc2a056e8..34990eaa3298 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/phy/mdio-xgene.c @@ -328,7 +328,6 @@ static int xgene_mdio_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct mii_bus *mdio_bus; const struct of_device_id *of_id; - struct resource *res; struct xgene_mdio_pdata *pdata; void __iomem *csr_base; int mdio_id = 0, ret = 0; @@ -355,8 +354,7 @@ static int xgene_mdio_probe(struct platform_device *pdev) pdata->mdio_id = mdio_id; pdata->dev = dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - csr_base = devm_ioremap_resource(dev, res); + csr_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(csr_base)) return PTR_ERR(csr_base); pdata->mac_csr_addr = csr_base; diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index fa80d6dce8ee..e8f2ca625837 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -136,7 +136,7 @@ static int meson_gxl_config_init(struct phy_device *phydev) if (ret) return ret; - return genphy_config_init(phydev); + return 0; } /* This function is provided to cope with the possible failures of this phy diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index eb1b3287fe08..a644e8e5071c 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -305,7 +305,6 @@ static int lan88xx_config_init(struct phy_device *phydev) { int val; - genphy_config_init(phydev); /*Zerodetect delay enable */ val = phy_read_mmd(phydev, MDIO_MMD_PCS, PHY_ARDENNES_MMD_DEV_3_PHY_CFG); diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index 3d09b471632c..001def4509c2 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -48,7 +48,6 @@ static struct phy_driver microchip_t1_phy_driver[] = { .features = PHY_BASIC_T1_FEATURES, - .config_init = genphy_config_init, .config_aneg = genphy_config_aneg, .ack_interrupt = lan87xx_phy_ack_interrupt, diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 645d354ffb48..7ada1fd9ca71 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -1725,7 +1725,7 @@ static int vsc8584_config_init(struct phy_device *phydev) return ret; } - return genphy_config_init(phydev); + return 0; err: mutex_unlock(&phydev->mdio.bus->mdio_lock); @@ -1767,7 +1767,7 @@ static int vsc85xx_config_init(struct phy_device *phydev) return rc; } - return genphy_config_init(phydev); + return 0; } static int vsc8584_did_interrupt(struct phy_device *phydev) diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 16667fbac8bf..369903d9b6ec 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -207,14 +207,14 @@ size_t phy_speeds(unsigned int *speeds, size_t size, return count; } -static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +static int __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) { const struct phy_setting *p; int i; for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) { if (p->speed > max_speed) - linkmode_clear_bit(p->bit, phydev->supported); + linkmode_clear_bit(p->bit, addr); else break; } @@ -222,6 +222,11 @@ static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) return 0; } +static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +{ + return __set_linkmode_max_speed(max_speed, phydev->supported); +} + int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) { int err; @@ -310,6 +315,34 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode); +static int phy_resolve_min_speed(struct phy_device *phydev, bool fdx_only) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(common); + int i = ARRAY_SIZE(settings); + + linkmode_and(common, phydev->lp_advertising, phydev->advertising); + + while (--i >= 0) { + if (test_bit(settings[i].bit, common)) { + if (fdx_only && settings[i].duplex != DUPLEX_FULL) + continue; + return settings[i].speed; + } + } + + return SPEED_UNKNOWN; +} + +int phy_speed_down_core(struct phy_device *phydev) +{ + int min_common_speed = phy_resolve_min_speed(phydev, true); + + if (min_common_speed == SPEED_UNKNOWN) + return -EINVAL; + + return __set_linkmode_max_speed(min_common_speed, phydev->advertising); +} + static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, u16 regnum) { @@ -783,24 +816,43 @@ int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val) EXPORT_SYMBOL(phy_write_paged); /** - * phy_modify_paged() - Convenience function for modifying a paged register + * phy_modify_paged_changed() - Function for modifying a paged register * @phydev: a pointer to a &struct phy_device * @page: the page for the phy * @regnum: register number * @mask: bit mask of bits to clear * @set: bit mask of bits to set * - * Same rules as for phy_read() and phy_write(). + * Returns negative errno, 0 if there was no change, and 1 in case of change */ -int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, - u16 mask, u16 set) +int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set) { int ret = 0, oldpage; oldpage = phy_select_page(phydev, page); if (oldpage >= 0) - ret = __phy_modify(phydev, regnum, mask, set); + ret = __phy_modify_changed(phydev, regnum, mask, set); return phy_restore_page(phydev, oldpage, ret); } +EXPORT_SYMBOL(phy_modify_paged_changed); + +/** + * phy_modify_paged() - Convenience function for modifying a paged register + * @phydev: a pointer to a &struct phy_device + * @page: the page for the phy + * @regnum: register number + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + * + * Same rules as for phy_read() and phy_write(). + */ +int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set) +{ + int ret = phy_modify_paged_changed(phydev, page, regnum, mask, set); + + return ret < 0 ? ret : 0; +} EXPORT_SYMBOL(phy_modify_paged); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index ef7aa738e0dc..f3adea9ef400 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -608,38 +608,21 @@ static int phy_poll_aneg_done(struct phy_device *phydev) */ int phy_speed_down(struct phy_device *phydev, bool sync) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv); + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_tmp); int ret; if (phydev->autoneg != AUTONEG_ENABLE) return 0; - linkmode_copy(adv_old, phydev->advertising); - linkmode_copy(adv, phydev->lp_advertising); - linkmode_and(adv, adv, phydev->supported); - - if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, adv) || - linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, adv)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->advertising); - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - adv) || - linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - adv)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->advertising); - } + linkmode_copy(adv_tmp, phydev->advertising); + + ret = phy_speed_down_core(phydev); + if (ret) + return ret; - if (linkmode_equal(phydev->advertising, adv_old)) + linkmode_copy(phydev->adv_old, adv_tmp); + + if (linkmode_equal(phydev->advertising, adv_tmp)) return 0; ret = phy_config_aneg(phydev); @@ -658,30 +641,19 @@ EXPORT_SYMBOL_GPL(phy_speed_down); */ int phy_speed_up(struct phy_device *phydev) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(all_speeds) = { 0, }; - __ETHTOOL_DECLARE_LINK_MODE_MASK(not_speeds); - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - __ETHTOOL_DECLARE_LINK_MODE_MASK(speeds); - - linkmode_copy(adv_old, phydev->advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_tmp); if (phydev->autoneg != AUTONEG_ENABLE) return 0; - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, all_speeds); + if (linkmode_empty(phydev->adv_old)) + return 0; - linkmode_andnot(not_speeds, adv_old, all_speeds); - linkmode_copy(supported, phydev->supported); - linkmode_and(speeds, supported, all_speeds); - linkmode_or(phydev->advertising, not_speeds, speeds); + linkmode_copy(adv_tmp, phydev->advertising); + linkmode_copy(phydev->advertising, phydev->adv_old); + linkmode_zero(phydev->adv_old); - if (linkmode_equal(phydev->advertising, adv_old)) + if (linkmode_equal(phydev->advertising, adv_tmp)) return 0; return phy_config_aneg(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 27ebc2c6c2d0..d347ddcac45b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1564,24 +1564,20 @@ EXPORT_SYMBOL(phy_reset_after_clk_enable); */ static int genphy_config_advert(struct phy_device *phydev) { - u32 advertise; - int bmsr, adv; - int err, changed = 0; + int err, bmsr, changed = 0; + u32 adv; /* Only allow advertising what this PHY supports */ linkmode_and(phydev->advertising, phydev->advertising, phydev->supported); - if (!ethtool_convert_link_mode_to_legacy_u32(&advertise, - phydev->advertising)) - phydev_warn(phydev, "PHY advertising (%*pb) more modes than genphy supports, some modes not advertised.\n", - __ETHTOOL_LINK_MODE_MASK_NBITS, - phydev->advertising); + + adv = linkmode_adv_to_mii_adv_t(phydev->advertising); /* Setup standard advertisement */ err = phy_modify_changed(phydev, MII_ADVERTISE, ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, - ethtool_adv_to_mii_adv_t(advertise)); + adv); if (err < 0) return err; if (err > 0) @@ -1598,13 +1594,7 @@ static int genphy_config_advert(struct phy_device *phydev) if (!(bmsr & BMSR_ESTATEN)) return changed; - /* Configure gigabit if it's supported */ - adv = 0; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->supported) || - linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->supported)) - adv = ethtool_adv_to_mii_ctrl1000_t(advertise); + adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); err = phy_modify_changed(phydev, MII_CTRL1000, ADVERTISE_1000FULL | ADVERTISE_1000HALF, @@ -1681,18 +1671,20 @@ int genphy_restart_aneg(struct phy_device *phydev) EXPORT_SYMBOL(genphy_restart_aneg); /** - * genphy_config_aneg - restart auto-negotiation or write BMCR + * __genphy_config_aneg - restart auto-negotiation or write BMCR * @phydev: target phy_device struct + * @changed: whether autoneg is requested * * Description: If auto-negotiation is enabled, we configure the * advertising, and then restart auto-negotiation. If it is not * enabled, then we write the BMCR. */ -int genphy_config_aneg(struct phy_device *phydev) +int __genphy_config_aneg(struct phy_device *phydev, bool changed) { - int err, changed; + int err; - changed = genphy_config_eee_advert(phydev); + if (genphy_config_eee_advert(phydev)) + changed = true; if (AUTONEG_ENABLE != phydev->autoneg) return genphy_setup_forced(phydev); @@ -1700,10 +1692,10 @@ int genphy_config_aneg(struct phy_device *phydev) err = genphy_config_advert(phydev); if (err < 0) /* error */ return err; + else if (err) + changed = true; - changed |= err; - - if (changed == 0) { + if (!changed) { /* Advertisement hasn't changed, but maybe aneg was never on to * begin with? Or maybe phy was isolated? */ @@ -1713,18 +1705,15 @@ int genphy_config_aneg(struct phy_device *phydev) return ctl; if (!(ctl & BMCR_ANENABLE) || (ctl & BMCR_ISOLATE)) - changed = 1; /* do restart aneg */ + changed = true; /* do restart aneg */ } /* Only restart aneg if we are advertising something different * than we were before. */ - if (changed > 0) - return genphy_restart_aneg(phydev); - - return 0; + return changed ? genphy_restart_aneg(phydev) : 0; } -EXPORT_SYMBOL(genphy_config_aneg); +EXPORT_SYMBOL(__genphy_config_aneg); /** * genphy_aneg_done - return auto-negotiation status @@ -1805,7 +1794,7 @@ EXPORT_SYMBOL(genphy_update_link); */ int genphy_read_status(struct phy_device *phydev) { - int adv, lpa, lpagb, err, old_link = phydev->link; + int lpa, lpagb, err, old_link = phydev->link; /* Update the link, but return if there was an error */ err = genphy_update_link(phydev); @@ -1821,19 +1810,18 @@ int genphy_read_status(struct phy_device *phydev) phydev->pause = 0; phydev->asym_pause = 0; - linkmode_zero(phydev->lp_advertising); - if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { if (phydev->is_gigabit_capable) { lpagb = phy_read(phydev, MII_STAT1000); if (lpagb < 0) return lpagb; - adv = phy_read(phydev, MII_CTRL1000); - if (adv < 0) - return adv; - if (lpagb & LPA_1000MSFAIL) { + int adv = phy_read(phydev, MII_CTRL1000); + + if (adv < 0) + return adv; + if (adv & CTL1000_ENABLE_MASTER) phydev_err(phydev, "Master/Slave resolution failed, maybe conflicting manual settings?\n"); else @@ -1907,57 +1895,6 @@ int genphy_soft_reset(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_soft_reset); -int genphy_config_init(struct phy_device *phydev) -{ - int val; - __ETHTOOL_DECLARE_LINK_MODE_MASK(features) = { 0, }; - - linkmode_set_bit_array(phy_basic_ports_array, - ARRAY_SIZE(phy_basic_ports_array), - features); - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, features); - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, features); - - /* Do we support autonegotiation? */ - val = phy_read(phydev, MII_BMSR); - if (val < 0) - return val; - - if (val & BMSR_ANEGCAPABLE) - linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, features); - - if (val & BMSR_100FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, features); - if (val & BMSR_100HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, features); - if (val & BMSR_10FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, features); - if (val & BMSR_10HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, features); - - if (val & BMSR_ESTATEN) { - val = phy_read(phydev, MII_ESTATUS); - if (val < 0) - return val; - - if (val & ESTATUS_1000_TFULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - features); - if (val & ESTATUS_1000_THALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - features); - if (val & ESTATUS_1000_XFULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, - features); - } - - linkmode_and(phydev->supported, phydev->supported, features); - linkmode_and(phydev->advertising, phydev->advertising, features); - - return 0; -} -EXPORT_SYMBOL(genphy_config_init); - /** * genphy_read_abilities - read PHY abilities from Clause 22 registers * @phydev: target phy_device struct diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index a669945eb829..fa662099fb85 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -39,6 +39,16 @@ #define RTL8366RB_POWER_SAVE 0x15 #define RTL8366RB_POWER_SAVE_ON BIT(12) +#define RTL_SUPPORTS_5000FULL BIT(14) +#define RTL_SUPPORTS_2500FULL BIT(13) +#define RTL_SUPPORTS_10000FULL BIT(0) +#define RTL_ADV_2500FULL BIT(7) +#define RTL_LPADV_10000FULL BIT(11) +#define RTL_LPADV_5000FULL BIT(6) +#define RTL_LPADV_2500FULL BIT(5) + +#define RTL_GENERIC_PHYID 0x001cc800 + MODULE_DESCRIPTION("Realtek PHY driver"); MODULE_AUTHOR("Johnson Leung"); MODULE_LICENSE("GPL"); @@ -256,6 +266,125 @@ static int rtl8366rb_config_init(struct phy_device *phydev) return ret; } +static int rtlgen_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) +{ + int ret; + + if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE) { + rtl821x_write_page(phydev, 0xa5c); + ret = __phy_read(phydev, 0x12); + rtl821x_write_page(phydev, 0); + } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) { + rtl821x_write_page(phydev, 0xa5d); + ret = __phy_read(phydev, 0x10); + rtl821x_write_page(phydev, 0); + } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE) { + rtl821x_write_page(phydev, 0xa5d); + ret = __phy_read(phydev, 0x11); + rtl821x_write_page(phydev, 0); + } else { + ret = -EOPNOTSUPP; + } + + return ret; +} + +static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, + u16 val) +{ + int ret; + + if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) { + rtl821x_write_page(phydev, 0xa5d); + ret = __phy_write(phydev, 0x10, val); + rtl821x_write_page(phydev, 0); + } else { + ret = -EOPNOTSUPP; + } + + return ret; +} + +static int rtl8125_get_features(struct phy_device *phydev) +{ + int val; + + val = phy_read_paged(phydev, 0xa61, 0x13); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->supported, val & RTL_SUPPORTS_2500FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + phydev->supported, val & RTL_SUPPORTS_5000FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + phydev->supported, val & RTL_SUPPORTS_10000FULL); + + return genphy_read_abilities(phydev); +} + +static int rtl8125_config_aneg(struct phy_device *phydev) +{ + int ret = 0; + + if (phydev->autoneg == AUTONEG_ENABLE) { + u16 adv2500 = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->advertising)) + adv2500 = RTL_ADV_2500FULL; + + ret = phy_modify_paged_changed(phydev, 0xa5d, 0x12, + RTL_ADV_2500FULL, adv2500); + if (ret < 0) + return ret; + } + + return __genphy_config_aneg(phydev, ret); +} + +static int rtl8125_read_status(struct phy_device *phydev) +{ + if (phydev->autoneg == AUTONEG_ENABLE) { + int lpadv = phy_read_paged(phydev, 0xa5d, 0x13); + + if (lpadv < 0) + return lpadv; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + phydev->lp_advertising, lpadv & RTL_LPADV_10000FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + phydev->lp_advertising, lpadv & RTL_LPADV_5000FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->lp_advertising, lpadv & RTL_LPADV_2500FULL); + } + + return genphy_read_status(phydev); +} + +static bool rtlgen_supports_2_5gbps(struct phy_device *phydev) +{ + int val; + + phy_write(phydev, RTL821x_PAGE_SELECT, 0xa61); + val = phy_read(phydev, 0x13); + phy_write(phydev, RTL821x_PAGE_SELECT, 0); + + return val >= 0 && val & RTL_SUPPORTS_2500FULL; +} + +static int rtlgen_match_phy_device(struct phy_device *phydev) +{ + return phydev->phy_id == RTL_GENERIC_PHYID && + !rtlgen_supports_2_5gbps(phydev); +} + +static int rtl8125_match_phy_device(struct phy_device *phydev) +{ + return phydev->phy_id == RTL_GENERIC_PHYID && + rtlgen_supports_2_5gbps(phydev); +} + static struct phy_driver realtek_drvs[] = { { PHY_ID_MATCH_EXACT(0x00008201), @@ -326,12 +455,26 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { - PHY_ID_MATCH_EXACT(0x001cc800), - .name = "Generic Realtek PHY", + .name = "Generic FE-GE Realtek PHY", + .match_phy_device = rtlgen_match_phy_device, + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, + .read_mmd = rtlgen_read_mmd, + .write_mmd = rtlgen_write_mmd, + }, { + .name = "RTL8125 2.5Gbps internal", + .match_phy_device = rtl8125_match_phy_device, + .get_features = rtl8125_get_features, + .config_aneg = rtl8125_config_aneg, + .read_status = rtl8125_read_status, .suspend = genphy_suspend, .resume = genphy_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, + .read_mmd = rtlgen_read_mmd, + .write_mmd = rtlgen_write_mmd, }, { PHY_ID_MATCH_EXACT(0x001cc961), .name = "RTL8366RB Gigabit Ethernet", diff --git a/drivers/net/phy/swphy.c b/drivers/net/phy/swphy.c index dad22481d9c1..53c214a22b95 100644 --- a/drivers/net/phy/swphy.c +++ b/drivers/net/phy/swphy.c @@ -22,6 +22,7 @@ struct swmii_regs { u16 bmsr; u16 lpa; u16 lpagb; + u16 estat; }; enum { @@ -48,6 +49,7 @@ static const struct swmii_regs speed[] = { [SWMII_SPEED_1000] = { .bmsr = BMSR_ESTATEN, .lpagb = LPA_1000FULL | LPA_1000HALF, + .estat = ESTATUS_1000_TFULL | ESTATUS_1000_THALF, }, }; @@ -56,11 +58,13 @@ static const struct swmii_regs duplex[] = { .bmsr = BMSR_ESTATEN | BMSR_100HALF, .lpa = LPA_10HALF | LPA_100HALF, .lpagb = LPA_1000HALF, + .estat = ESTATUS_1000_THALF, }, [SWMII_DUPLEX_FULL] = { .bmsr = BMSR_ESTATEN | BMSR_100FULL, .lpa = LPA_10FULL | LPA_100FULL, .lpagb = LPA_1000FULL, + .estat = ESTATUS_1000_TFULL, }, }; @@ -112,6 +116,7 @@ int swphy_read_reg(int reg, const struct fixed_phy_status *state) { int speed_index, duplex_index; u16 bmsr = BMSR_ANEGCAPABLE; + u16 estat = 0; u16 lpagb = 0; u16 lpa = 0; @@ -125,6 +130,7 @@ int swphy_read_reg(int reg, const struct fixed_phy_status *state) duplex_index = state->duplex ? SWMII_DUPLEX_FULL : SWMII_DUPLEX_HALF; bmsr |= speed[speed_index].bmsr & duplex[duplex_index].bmsr; + estat |= speed[speed_index].estat & duplex[duplex_index].estat; if (state->link) { bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE; @@ -151,6 +157,8 @@ int swphy_read_reg(int reg, const struct fixed_phy_status *state) return lpa; case MII_STAT1000: return lpagb; + case MII_ESTATUS: + return estat; /* * We do not support emulating Clause 45 over Clause 22 register diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 43691b1acfd9..bb680352708a 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -197,7 +197,7 @@ static int vsc738x_config_init(struct phy_device *phydev) vsc73xx_config_init(phydev); - return genphy_config_init(phydev); + return 0; } static int vsc739x_config_init(struct phy_device *phydev) @@ -229,7 +229,7 @@ static int vsc739x_config_init(struct phy_device *phydev) vsc73xx_config_init(phydev); - return genphy_config_init(phydev); + return 0; } static int vsc73xx_config_aneg(struct phy_device *phydev) @@ -267,7 +267,7 @@ static int vsc8601_config_init(struct phy_device *phydev) if (ret < 0) return ret; - return genphy_config_init(phydev); + return 0; } static int vsc824x_ack_interrupt(struct phy_device *phydev) diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index ea90db3c7705..58a69f830d29 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -91,8 +91,8 @@ static unsigned short pull16(unsigned char **cpp); struct slcompress * slhc_init(int rslots, int tslots) { - register short i; - register struct cstate *ts; + short i; + struct cstate *ts; struct slcompress *comp; if (rslots < 0 || rslots > 255 || tslots < 0 || tslots > 255) @@ -206,7 +206,7 @@ pull16(unsigned char **cpp) static long decode(unsigned char **cpp) { - register int x; + int x; x = *(*cpp)++; if(x == 0){ @@ -227,14 +227,14 @@ int slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, unsigned char *ocp, unsigned char **cpp, int compress_cid) { - register struct cstate *ocs = &(comp->tstate[comp->xmit_oldest]); - register struct cstate *lcs = ocs; - register struct cstate *cs = lcs->next; - register unsigned long deltaS, deltaA; - register short changes = 0; + struct cstate *ocs = &(comp->tstate[comp->xmit_oldest]); + struct cstate *lcs = ocs; + struct cstate *cs = lcs->next; + unsigned long deltaS, deltaA; + short changes = 0; int hlen; unsigned char new_seq[16]; - register unsigned char *cp = new_seq; + unsigned char *cp = new_seq; struct iphdr *ip; struct tcphdr *th, *oth; __sum16 csum; @@ -486,11 +486,11 @@ uncompressed: int slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) { - register int changes; + int changes; long x; - register struct tcphdr *thp; - register struct iphdr *ip; - register struct cstate *cs; + struct tcphdr *thp; + struct iphdr *ip; + struct cstate *cs; int len, hdrlen; unsigned char *cp = icp; @@ -543,7 +543,7 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) switch(changes & SPECIALS_MASK){ case SPECIAL_I: /* Echoed terminal traffic */ { - register short i; + short i; i = ntohs(ip->tot_len) - hdrlen; thp->ack_seq = htonl( ntohl(thp->ack_seq) + i); thp->seq = htonl( ntohl(thp->seq) + i); @@ -637,7 +637,7 @@ bad: int slhc_remember(struct slcompress *comp, unsigned char *icp, int isize) { - register struct cstate *cs; + struct cstate *cs; unsigned ihl; unsigned char index; diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index fcf31335a8b6..dacb4f680fd4 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -1005,7 +1005,7 @@ static void *tbnet_kmap_frag(struct sk_buff *skb, unsigned int frag_num, const skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_num]; *len = skb_frag_size(frag); - return kmap_atomic(skb_frag_page(frag)) + frag->page_offset; + return kmap_atomic(skb_frag_page(frag)) + skb_frag_off(frag); } static netdev_tx_t tbnet_start_xmit(struct sk_buff *skb, diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index b39ee714fb01..e39f41efda3e 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -221,6 +221,7 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, int tailroom = skb_tailroom(skb); u32 packet_len; u32 padbytes = 0xffff0000; + void *ptr; padlen = ((skb->len + 4) & (dev->maxpacket - 1)) ? 0 : 4; @@ -256,13 +257,11 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, } packet_len = ((skb->len ^ 0x0000ffff) << 16) + skb->len; - skb_push(skb, 4); - cpu_to_le32s(&packet_len); - skb_copy_to_linear_data(skb, &packet_len, sizeof(packet_len)); + ptr = skb_push(skb, 4); + put_unaligned_le32(packet_len, ptr); if (padlen) { - cpu_to_le32s(&padbytes); - memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes)); + put_unaligned_le32(padbytes, skb_tail_pointer(skb)); skb_put(skb, sizeof(padbytes)); } diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 0bc457ba8574..daa54486ab09 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1366,8 +1366,7 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) return 0; skb_trim(skb, skb->len - 4); - memcpy(&rx_hdr, skb_tail_pointer(skb), 4); - le32_to_cpus(&rx_hdr); + rx_hdr = get_unaligned_le32(skb_tail_pointer(skb)); pkt_cnt = (u16)rx_hdr; hdr_off = (u16)(rx_hdr >> 16); @@ -1422,6 +1421,7 @@ ax88179_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) int frame_size = dev->maxpacket; int mss = skb_shinfo(skb)->gso_size; int headroom; + void *ptr; tx_hdr1 = skb->len; tx_hdr2 = mss; @@ -1436,13 +1436,9 @@ ax88179_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) return NULL; } - skb_push(skb, 4); - cpu_to_le32s(&tx_hdr2); - skb_copy_to_linear_data(skb, &tx_hdr2, 4); - - skb_push(skb, 4); - cpu_to_le32s(&tx_hdr1); - skb_copy_to_linear_data(skb, &tx_hdr1, 4); + ptr = skb_push(skb, 8); + put_unaligned_le32(tx_hdr1, ptr); + put_unaligned_le32(tx_hdr2, ptr + 4); return skb; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index f033fee225a1..58f5a219fb65 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1258,8 +1258,7 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb) return; } - memcpy(&intdata, urb->transfer_buffer, 4); - le32_to_cpus(&intdata); + intdata = get_unaligned_le32(urb->transfer_buffer); if (intdata & INT_ENP_PHY_INT) { netif_dbg(dev, link, dev->net, "PHY INTR: 0x%08x\n", intdata); @@ -2730,6 +2729,7 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev, struct sk_buff *skb, gfp_t flags) { u32 tx_cmd_a, tx_cmd_b; + void *ptr; if (skb_cow_head(skb, TX_OVERHEAD)) { dev_kfree_skb_any(skb); @@ -2758,13 +2758,9 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev, tx_cmd_b |= skb_vlan_tag_get(skb) & TX_CMD_B_VTAG_MASK_; } - skb_push(skb, 4); - cpu_to_le32s(&tx_cmd_b); - memcpy(skb->data, &tx_cmd_b, 4); - - skb_push(skb, 4); - cpu_to_le32s(&tx_cmd_a); - memcpy(skb->data, &tx_cmd_a, 4); + ptr = skb_push(skb, 8); + put_unaligned_le32(tx_cmd_a, ptr); + put_unaligned_le32(tx_cmd_b, ptr + 4); return skb; } @@ -3105,16 +3101,13 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb) struct sk_buff *skb2; unsigned char *packet; - memcpy(&rx_cmd_a, skb->data, sizeof(rx_cmd_a)); - le32_to_cpus(&rx_cmd_a); + rx_cmd_a = get_unaligned_le32(skb->data); skb_pull(skb, sizeof(rx_cmd_a)); - memcpy(&rx_cmd_b, skb->data, sizeof(rx_cmd_b)); - le32_to_cpus(&rx_cmd_b); + rx_cmd_b = get_unaligned_le32(skb->data); skb_pull(skb, sizeof(rx_cmd_b)); - memcpy(&rx_cmd_c, skb->data, sizeof(rx_cmd_c)); - le16_to_cpus(&rx_cmd_c); + rx_cmd_c = get_unaligned_le16(skb->data); skb_pull(skb, sizeof(rx_cmd_c)); packet = skb->data; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0cc03a9ff545..40d18e866269 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -22,10 +22,11 @@ #include <linux/mdio.h> #include <linux/usb/cdc.h> #include <linux/suspend.h> +#include <linux/atomic.h> #include <linux/acpi.h> /* Information for net-next */ -#define NETNEXT_VERSION "09" +#define NETNEXT_VERSION "10" /* Information for net */ #define NET_VERSION "10" @@ -583,6 +584,9 @@ enum rtl_register_content { #define TX_ALIGN 4 #define RX_ALIGN 8 +#define RTL8152_RX_MAX_PENDING 4096 +#define RTL8152_RXFG_HEADSZ 256 + #define INTR_LINK 0x0004 #define RTL8152_REQT_READ 0xc0 @@ -694,11 +698,11 @@ struct tx_desc { struct r8152; struct rx_agg { - struct list_head list; + struct list_head list, info_list; struct urb *urb; struct r8152 *context; + struct page *page; void *buffer; - void *head; }; struct tx_agg { @@ -719,7 +723,7 @@ struct r8152 { struct net_device *netdev; struct urb *intr_urb; struct tx_agg tx_info[RTL8152_MAX_TX]; - struct rx_agg rx_info[RTL8152_MAX_RX]; + struct list_head rx_info, rx_used; struct list_head rx_done, tx_free; struct sk_buff_head tx_queue, rx_queue; spinlock_t rx_lock, tx_lock; @@ -744,11 +748,17 @@ struct r8152 { void (*autosuspend_en)(struct r8152 *tp, bool enable); } rtl_ops; + atomic_t rx_count; + int intr_interval; u32 saved_wolopts; u32 msg_enable; u32 tx_qlen; u32 coalesce; + u32 rx_buf_sz; + u32 rx_copybreak; + u32 rx_pending; + u16 ocp_base; u16 speed; u8 *intr_buff; @@ -1467,18 +1477,72 @@ static inline void *tx_agg_align(void *data) return (void *)ALIGN((uintptr_t)data, TX_ALIGN); } +static void free_rx_agg(struct r8152 *tp, struct rx_agg *agg) +{ + list_del(&agg->info_list); + + usb_free_urb(agg->urb); + put_page(agg->page); + kfree(agg); + + atomic_dec(&tp->rx_count); +} + +static struct rx_agg *alloc_rx_agg(struct r8152 *tp, gfp_t mflags) +{ + struct net_device *netdev = tp->netdev; + int node = netdev->dev.parent ? dev_to_node(netdev->dev.parent) : -1; + unsigned int order = get_order(tp->rx_buf_sz); + struct rx_agg *rx_agg; + unsigned long flags; + + rx_agg = kmalloc_node(sizeof(*rx_agg), mflags, node); + if (!rx_agg) + return NULL; + + rx_agg->page = alloc_pages(mflags | __GFP_COMP, order); + if (!rx_agg->page) + goto free_rx; + + rx_agg->buffer = page_address(rx_agg->page); + + rx_agg->urb = usb_alloc_urb(0, mflags); + if (!rx_agg->urb) + goto free_buf; + + rx_agg->context = tp; + + INIT_LIST_HEAD(&rx_agg->list); + INIT_LIST_HEAD(&rx_agg->info_list); + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&rx_agg->info_list, &tp->rx_info); + spin_unlock_irqrestore(&tp->rx_lock, flags); + + atomic_inc(&tp->rx_count); + + return rx_agg; + +free_buf: + __free_pages(rx_agg->page, order); +free_rx: + kfree(rx_agg); + return NULL; +} + static void free_all_mem(struct r8152 *tp) { + struct rx_agg *agg, *agg_next; + unsigned long flags; int i; - for (i = 0; i < RTL8152_MAX_RX; i++) { - usb_free_urb(tp->rx_info[i].urb); - tp->rx_info[i].urb = NULL; + spin_lock_irqsave(&tp->rx_lock, flags); - kfree(tp->rx_info[i].buffer); - tp->rx_info[i].buffer = NULL; - tp->rx_info[i].head = NULL; - } + list_for_each_entry_safe(agg, agg_next, &tp->rx_info, info_list) + free_rx_agg(tp, agg); + + spin_unlock_irqrestore(&tp->rx_lock, flags); + + WARN_ON(atomic_read(&tp->rx_count)); for (i = 0; i < RTL8152_MAX_TX; i++) { usb_free_urb(tp->tx_info[i].urb); @@ -1502,46 +1566,28 @@ static int alloc_all_mem(struct r8152 *tp) struct usb_interface *intf = tp->intf; struct usb_host_interface *alt = intf->cur_altsetting; struct usb_host_endpoint *ep_intr = alt->endpoint + 2; - struct urb *urb; int node, i; - u8 *buf; node = netdev->dev.parent ? dev_to_node(netdev->dev.parent) : -1; spin_lock_init(&tp->rx_lock); spin_lock_init(&tp->tx_lock); + INIT_LIST_HEAD(&tp->rx_info); INIT_LIST_HEAD(&tp->tx_free); INIT_LIST_HEAD(&tp->rx_done); skb_queue_head_init(&tp->tx_queue); skb_queue_head_init(&tp->rx_queue); + atomic_set(&tp->rx_count, 0); for (i = 0; i < RTL8152_MAX_RX; i++) { - buf = kmalloc_node(agg_buf_sz, GFP_KERNEL, node); - if (!buf) - goto err1; - - if (buf != rx_agg_align(buf)) { - kfree(buf); - buf = kmalloc_node(agg_buf_sz + RX_ALIGN, GFP_KERNEL, - node); - if (!buf) - goto err1; - } - - urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) { - kfree(buf); + if (!alloc_rx_agg(tp, GFP_KERNEL)) goto err1; - } - - INIT_LIST_HEAD(&tp->rx_info[i].list); - tp->rx_info[i].context = tp; - tp->rx_info[i].urb = urb; - tp->rx_info[i].buffer = buf; - tp->rx_info[i].head = rx_agg_align(buf); } for (i = 0; i < RTL8152_MAX_TX; i++) { + struct urb *urb; + u8 *buf; + buf = kmalloc_node(agg_buf_sz, GFP_KERNEL, node); if (!buf) goto err1; @@ -1907,6 +1953,46 @@ return_result: return checksum; } +static inline bool rx_count_exceed(struct r8152 *tp) +{ + return atomic_read(&tp->rx_count) > RTL8152_MAX_RX; +} + +static inline int agg_offset(struct rx_agg *agg, void *addr) +{ + return (int)(addr - agg->buffer); +} + +static struct rx_agg *rtl_get_free_rx(struct r8152 *tp, gfp_t mflags) +{ + struct rx_agg *agg, *agg_next, *agg_free = NULL; + unsigned long flags; + + spin_lock_irqsave(&tp->rx_lock, flags); + + list_for_each_entry_safe(agg, agg_next, &tp->rx_used, list) { + if (page_count(agg->page) == 1) { + if (!agg_free) { + list_del_init(&agg->list); + agg_free = agg; + continue; + } + if (rx_count_exceed(tp)) { + list_del_init(&agg->list); + free_rx_agg(tp, agg); + } + break; + } + } + + spin_unlock_irqrestore(&tp->rx_lock, flags); + + if (!agg_free && atomic_read(&tp->rx_count) < tp->rx_pending) + agg_free = alloc_rx_agg(tp, mflags); + + return agg_free; +} + static int rx_bottom(struct r8152 *tp, int budget) { unsigned long flags; @@ -1942,7 +2028,7 @@ static int rx_bottom(struct r8152 *tp, int budget) list_for_each_safe(cursor, next, &rx_queue) { struct rx_desc *rx_desc; - struct rx_agg *agg; + struct rx_agg *agg, *agg_free; int len_used = 0; struct urb *urb; u8 *rx_data; @@ -1954,14 +2040,16 @@ static int rx_bottom(struct r8152 *tp, int budget) if (urb->actual_length < ETH_ZLEN) goto submit; - rx_desc = agg->head; - rx_data = agg->head; + agg_free = rtl_get_free_rx(tp, GFP_ATOMIC); + + rx_desc = agg->buffer; + rx_data = agg->buffer; len_used += sizeof(struct rx_desc); while (urb->actual_length > len_used) { struct net_device *netdev = tp->netdev; struct net_device_stats *stats = &netdev->stats; - unsigned int pkt_len; + unsigned int pkt_len, rx_frag_head_sz; struct sk_buff *skb; /* limite the skb numbers for rx_queue */ @@ -1979,22 +2067,37 @@ static int rx_bottom(struct r8152 *tp, int budget) pkt_len -= ETH_FCS_LEN; rx_data += sizeof(struct rx_desc); - skb = napi_alloc_skb(napi, pkt_len); + if (!agg_free || tp->rx_copybreak > pkt_len) + rx_frag_head_sz = pkt_len; + else + rx_frag_head_sz = tp->rx_copybreak; + + skb = napi_alloc_skb(napi, rx_frag_head_sz); if (!skb) { stats->rx_dropped++; goto find_next_rx; } skb->ip_summed = r8152_rx_csum(tp, rx_desc); - memcpy(skb->data, rx_data, pkt_len); - skb_put(skb, pkt_len); + memcpy(skb->data, rx_data, rx_frag_head_sz); + skb_put(skb, rx_frag_head_sz); + pkt_len -= rx_frag_head_sz; + rx_data += rx_frag_head_sz; + if (pkt_len) { + skb_add_rx_frag(skb, 0, agg->page, + agg_offset(agg, rx_data), + pkt_len, + SKB_DATA_ALIGN(pkt_len)); + get_page(agg->page); + } + skb->protocol = eth_type_trans(skb, netdev); rtl_rx_vlan_tag(rx_desc, skb); if (work_done < budget) { napi_gro_receive(napi, skb); work_done++; stats->rx_packets++; - stats->rx_bytes += pkt_len; + stats->rx_bytes += skb->len; } else { __skb_queue_tail(&tp->rx_queue, skb); } @@ -2002,10 +2105,24 @@ static int rx_bottom(struct r8152 *tp, int budget) find_next_rx: rx_data = rx_agg_align(rx_data + pkt_len + ETH_FCS_LEN); rx_desc = (struct rx_desc *)rx_data; - len_used = (int)(rx_data - (u8 *)agg->head); + len_used = agg_offset(agg, rx_data); len_used += sizeof(struct rx_desc); } + WARN_ON(!agg_free && page_count(agg->page) > 1); + + if (agg_free) { + spin_lock_irqsave(&tp->rx_lock, flags); + if (page_count(agg->page) == 1) { + list_add(&agg_free->list, &tp->rx_used); + } else { + list_add_tail(&agg->list, &tp->rx_used); + agg = agg_free; + urb = agg->urb; + } + spin_unlock_irqrestore(&tp->rx_lock, flags); + } + submit: if (!ret) { ret = r8152_submit_rx(tp, agg, GFP_ATOMIC); @@ -2113,7 +2230,7 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags) return 0; usb_fill_bulk_urb(agg->urb, tp->udev, usb_rcvbulkpipe(tp->udev, 1), - agg->head, agg_buf_sz, + agg->buffer, tp->rx_buf_sz, (usb_complete_t)read_bulk_callback, agg); ret = usb_submit_urb(agg->urb, mem_flags); @@ -2330,44 +2447,80 @@ static void rxdy_gated_en(struct r8152 *tp, bool enable) static int rtl_start_rx(struct r8152 *tp) { - int i, ret = 0; + struct rx_agg *agg, *agg_next; + struct list_head tmp_list; + unsigned long flags; + int ret = 0, i = 0; - INIT_LIST_HEAD(&tp->rx_done); - for (i = 0; i < RTL8152_MAX_RX; i++) { - INIT_LIST_HEAD(&tp->rx_info[i].list); - ret = r8152_submit_rx(tp, &tp->rx_info[i], GFP_KERNEL); - if (ret) - break; - } + INIT_LIST_HEAD(&tmp_list); - if (ret && ++i < RTL8152_MAX_RX) { - struct list_head rx_queue; - unsigned long flags; + spin_lock_irqsave(&tp->rx_lock, flags); - INIT_LIST_HEAD(&rx_queue); + INIT_LIST_HEAD(&tp->rx_done); + INIT_LIST_HEAD(&tp->rx_used); - do { - struct rx_agg *agg = &tp->rx_info[i++]; - struct urb *urb = agg->urb; + list_splice_init(&tp->rx_info, &tmp_list); - urb->actual_length = 0; - list_add_tail(&agg->list, &rx_queue); - } while (i < RTL8152_MAX_RX); + spin_unlock_irqrestore(&tp->rx_lock, flags); - spin_lock_irqsave(&tp->rx_lock, flags); - list_splice_tail(&rx_queue, &tp->rx_done); - spin_unlock_irqrestore(&tp->rx_lock, flags); + list_for_each_entry_safe(agg, agg_next, &tmp_list, info_list) { + INIT_LIST_HEAD(&agg->list); + + /* Only RTL8152_MAX_RX rx_agg need to be submitted. */ + if (++i > RTL8152_MAX_RX) { + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&agg->list, &tp->rx_used); + spin_unlock_irqrestore(&tp->rx_lock, flags); + } else if (unlikely(ret < 0)) { + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&agg->list, &tp->rx_done); + spin_unlock_irqrestore(&tp->rx_lock, flags); + } else { + ret = r8152_submit_rx(tp, agg, GFP_KERNEL); + } } + spin_lock_irqsave(&tp->rx_lock, flags); + WARN_ON(!list_empty(&tp->rx_info)); + list_splice(&tmp_list, &tp->rx_info); + spin_unlock_irqrestore(&tp->rx_lock, flags); + return ret; } static int rtl_stop_rx(struct r8152 *tp) { - int i; + struct rx_agg *agg, *agg_next; + struct list_head tmp_list; + unsigned long flags; + + INIT_LIST_HEAD(&tmp_list); + + /* The usb_kill_urb() couldn't be used in atomic. + * Therefore, move the list of rx_info to a tmp one. + * Then, list_for_each_entry_safe could be used without + * spin lock. + */ + + spin_lock_irqsave(&tp->rx_lock, flags); + list_splice_init(&tp->rx_info, &tmp_list); + spin_unlock_irqrestore(&tp->rx_lock, flags); + + list_for_each_entry_safe(agg, agg_next, &tmp_list, info_list) { + /* At least RTL8152_MAX_RX rx_agg have the page_count being + * equal to 1, so the other ones could be freed safely. + */ + if (page_count(agg->page) > 1) + free_rx_agg(tp, agg); + else + usb_kill_urb(agg->urb); + } - for (i = 0; i < RTL8152_MAX_RX; i++) - usb_kill_urb(tp->rx_info[i].urb); + /* Move back the list of temp to the rx_info */ + spin_lock_irqsave(&tp->rx_lock, flags); + WARN_ON(!list_empty(&tp->rx_info)); + list_splice(&tmp_list, &tp->rx_info); + spin_unlock_irqrestore(&tp->rx_lock, flags); while (!skb_queue_empty(&tp->rx_queue)) dev_kfree_skb(__skb_dequeue(&tp->rx_queue)); @@ -2447,7 +2600,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp) static void r8153_set_rx_early_size(struct r8152 *tp) { - u32 ocp_data = agg_buf_sz - rx_reserved_size(tp->netdev->mtu); + u32 ocp_data = tp->rx_buf_sz - rx_reserved_size(tp->netdev->mtu); switch (tp->version) { case RTL_VER_03: @@ -4954,6 +5107,77 @@ static int rtl8152_set_coalesce(struct net_device *netdev, return ret; } +static int rtl8152_get_tunable(struct net_device *netdev, + const struct ethtool_tunable *tunable, void *d) +{ + struct r8152 *tp = netdev_priv(netdev); + + switch (tunable->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)d = tp->rx_copybreak; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int rtl8152_set_tunable(struct net_device *netdev, + const struct ethtool_tunable *tunable, + const void *d) +{ + struct r8152 *tp = netdev_priv(netdev); + u32 val; + + switch (tunable->id) { + case ETHTOOL_RX_COPYBREAK: + val = *(u32 *)d; + if (val < ETH_ZLEN) { + netif_err(tp, rx_err, netdev, + "Invalid rx copy break value\n"); + return -EINVAL; + } + + if (tp->rx_copybreak != val) { + napi_disable(&tp->napi); + tp->rx_copybreak = val; + napi_enable(&tp->napi); + } + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static void rtl8152_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct r8152 *tp = netdev_priv(netdev); + + ring->rx_max_pending = RTL8152_RX_MAX_PENDING; + ring->rx_pending = tp->rx_pending; +} + +static int rtl8152_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct r8152 *tp = netdev_priv(netdev); + + if (ring->rx_pending < (RTL8152_MAX_RX * 2)) + return -EINVAL; + + if (tp->rx_pending != ring->rx_pending) { + napi_disable(&tp->napi); + tp->rx_pending = ring->rx_pending; + napi_enable(&tp->napi); + } + + return 0; +} + static const struct ethtool_ops ops = { .get_drvinfo = rtl8152_get_drvinfo, .get_link = ethtool_op_get_link, @@ -4971,6 +5195,10 @@ static const struct ethtool_ops ops = { .set_eee = rtl_ethtool_set_eee, .get_link_ksettings = rtl8152_get_link_ksettings, .set_link_ksettings = rtl8152_set_link_ksettings, + .get_tunable = rtl8152_get_tunable, + .set_tunable = rtl8152_set_tunable, + .get_ringparam = rtl8152_get_ringparam, + .set_ringparam = rtl8152_set_ringparam, }; static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) @@ -5115,6 +5343,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8152_in_nway; ops->hw_phy_cfg = r8152b_hw_phy_cfg; ops->autosuspend_en = rtl_runtime_suspend_enable; + tp->rx_buf_sz = 16 * 1024; break; case RTL_VER_03: @@ -5132,6 +5361,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8153_in_nway; ops->hw_phy_cfg = r8153_hw_phy_cfg; ops->autosuspend_en = rtl8153_runtime_enable; + tp->rx_buf_sz = 32 * 1024; break; case RTL_VER_08: @@ -5147,6 +5377,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8153_in_nway; ops->hw_phy_cfg = r8153b_hw_phy_cfg; ops->autosuspend_en = rtl8153b_runtime_enable; + tp->rx_buf_sz = 32 * 1024; break; default: @@ -5321,6 +5552,9 @@ static int rtl8152_probe(struct usb_interface *intf, tp->speed = tp->mii.supports_gmii ? SPEED_1000 : SPEED_100; tp->duplex = DUPLEX_FULL; + tp->rx_copybreak = RTL8152_RXFG_HEADSZ; + tp->rx_pending = 10 * RTL8152_MAX_RX; + intf->needs_remote_wakeup = 1; tp->rtl_ops.init(tp); diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 1417a22962a1..9556d431885f 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -661,8 +661,7 @@ static void smsc75xx_status(struct usbnet *dev, struct urb *urb) return; } - memcpy(&intdata, urb->transfer_buffer, 4); - le32_to_cpus(&intdata); + intdata = get_unaligned_le32(urb->transfer_buffer); netif_dbg(dev, link, dev->net, "intdata: 0x%08X\n", intdata); @@ -2181,12 +2180,10 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) struct sk_buff *ax_skb; unsigned char *packet; - memcpy(&rx_cmd_a, skb->data, sizeof(rx_cmd_a)); - le32_to_cpus(&rx_cmd_a); + rx_cmd_a = get_unaligned_le32(skb->data); skb_pull(skb, 4); - memcpy(&rx_cmd_b, skb->data, sizeof(rx_cmd_b)); - le32_to_cpus(&rx_cmd_b); + rx_cmd_b = get_unaligned_le32(skb->data); skb_pull(skb, 4 + RXW_PADDING); packet = skb->data; @@ -2258,6 +2255,7 @@ static struct sk_buff *smsc75xx_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) { u32 tx_cmd_a, tx_cmd_b; + void *ptr; if (skb_cow_head(skb, SMSC75XX_TX_OVERHEAD)) { dev_kfree_skb_any(skb); @@ -2278,13 +2276,9 @@ static struct sk_buff *smsc75xx_tx_fixup(struct usbnet *dev, tx_cmd_b = 0; } - skb_push(skb, 4); - cpu_to_le32s(&tx_cmd_b); - memcpy(skb->data, &tx_cmd_b, 4); - - skb_push(skb, 4); - cpu_to_le32s(&tx_cmd_a); - memcpy(skb->data, &tx_cmd_a, 4); + ptr = skb_push(skb, 8); + put_unaligned_le32(tx_cmd_a, ptr); + put_unaligned_le32(tx_cmd_b, ptr + 4); return skb; } diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 35f39f23d881..c5d4a0060124 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -115,6 +115,7 @@ static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb, u32 padbytes = 0xffff0000; u32 packet_len; int padlen; + void *ptr; padlen = ((skb->len + 4) % (dev->maxpacket - 1)) ? 0 : 4; @@ -133,14 +134,12 @@ static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb, return NULL; } - skb_push(skb, 4); + ptr = skb_push(skb, 4); packet_len = (((skb->len - 4) ^ 0x0000ffff) << 16) + (skb->len - 4); - cpu_to_le32s(&packet_len); - skb_copy_to_linear_data(skb, &packet_len, sizeof(packet_len)); + put_unaligned_le32(packet_len, ptr); if (padlen) { - cpu_to_le32s(&padbytes); - memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes)); + put_unaligned_le32(padbytes, skb_tail_pointer(skb)); skb_put(skb, sizeof(padbytes)); } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 72514c46b478..58952a79b05f 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1324,11 +1324,11 @@ static int build_dma_sg(const struct sk_buff *skb, struct urb *urb) total_len += skb_headlen(skb); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - struct skb_frag_struct *f = &skb_shinfo(skb)->frags[i]; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; total_len += skb_frag_size(f); - sg_set_page(&urb->sg[i + s], f->page.p, f->size, - f->page_offset); + sg_set_page(&urb->sg[i + s], skb_frag_page(f), skb_frag_size(f), + skb_frag_off(f)); } urb->transfer_buffer_length = total_len; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 2a1918f25e47..216acf37ca7c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -657,13 +657,12 @@ static void vmxnet3_append_frag(struct sk_buff *skb, struct Vmxnet3_RxCompDesc *rcd, struct vmxnet3_rx_buf_info *rbi) { - struct skb_frag_struct *frag = skb_shinfo(skb)->frags + - skb_shinfo(skb)->nr_frags; + skb_frag_t *frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags; BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); __skb_frag_set_page(frag, rbi->page); - frag->page_offset = 0; + skb_frag_off_set(frag, 0); skb_frag_size_set(frag, rcd->len); skb->data_len += rcd->len; skb->truesize += PAGE_SIZE; @@ -755,7 +754,7 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 buf_size; buf_offset = 0; @@ -956,7 +955,7 @@ static int txd_estimate(const struct sk_buff *skb) int i; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; count += VMXNET3_TXD_NEEDED(skb_frag_size(frag)); } diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c index 6544ac9df047..73f5892ce6c1 100644 --- a/drivers/net/wimax/i2400m/debugfs.c +++ b/drivers/net/wimax/i2400m/debugfs.c @@ -30,15 +30,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_netdev_queue_stopped, debugfs_netdev_queue_stopped_get, NULL, "%llu\n"); - -static -struct dentry *debugfs_create_netdev_queue_stopped( - const char *name, struct dentry *parent, struct i2400m *i2400m) -{ - return debugfs_create_file(name, 0400, parent, i2400m, - &fops_netdev_queue_stopped); -} - /* * We don't allow partial reads of this file, as then the reader would * get weirdly confused data as it is updated. @@ -167,15 +158,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_i2400m_suspend, NULL, debugfs_i2400m_suspend_set, "%llu\n"); -static -struct dentry *debugfs_create_i2400m_suspend( - const char *name, struct dentry *parent, struct i2400m *i2400m) -{ - return debugfs_create_file(name, 0200, parent, i2400m, - &fops_i2400m_suspend); -} - - /* * Reset the device * @@ -205,73 +187,25 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_i2400m_reset, NULL, debugfs_i2400m_reset_set, "%llu\n"); -static -struct dentry *debugfs_create_i2400m_reset( - const char *name, struct dentry *parent, struct i2400m *i2400m) +void i2400m_debugfs_add(struct i2400m *i2400m) { - return debugfs_create_file(name, 0200, parent, i2400m, - &fops_i2400m_reset); -} - - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - -int i2400m_debugfs_add(struct i2400m *i2400m) -{ - int result; - struct device *dev = i2400m_dev(i2400m); struct dentry *dentry = i2400m->wimax_dev.debugfs_dentry; - struct dentry *fd; dentry = debugfs_create_dir("i2400m", dentry); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - goto error; - } i2400m->debugfs_dentry = dentry; - __debugfs_register("dl_", control, dentry); - __debugfs_register("dl_", driver, dentry); - __debugfs_register("dl_", debugfs, dentry); - __debugfs_register("dl_", fw, dentry); - __debugfs_register("dl_", netdev, dentry); - __debugfs_register("dl_", rfkill, dentry); - __debugfs_register("dl_", rx, dentry); - __debugfs_register("dl_", tx, dentry); - - fd = debugfs_create_size_t("tx_in", 0400, dentry, - &i2400m->tx_in); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_in: %d\n", result); - goto error; - } - fd = debugfs_create_size_t("tx_out", 0400, dentry, - &i2400m->tx_out); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_out: %d\n", result); - goto error; - } + 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); - fd = debugfs_create_u32("state", 0600, dentry, - &i2400m->state); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "state: %d\n", result); - goto error; - } + 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 @@ -295,60 +229,22 @@ int i2400m_debugfs_add(struct i2400m *i2400m) * It is not really very atomic, but it is also not too * critical. */ - fd = debugfs_create_u8("trace_msg_from_user", 0600, dentry, - &i2400m->trace_msg_from_user); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "trace_msg_from_user: %d\n", result); - goto error; - } + debugfs_create_u8("trace_msg_from_user", 0600, dentry, + &i2400m->trace_msg_from_user); - fd = debugfs_create_netdev_queue_stopped("netdev_queue_stopped", - dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "netdev_queue_stopped: %d\n", result); - goto error; - } + debugfs_create_file("netdev_queue_stopped", 0400, dentry, i2400m, + &fops_netdev_queue_stopped); - fd = debugfs_create_file("rx_stats", 0600, dentry, i2400m, - &i2400m_rx_stats_fops); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_stats: %d\n", result); - goto error; - } + debugfs_create_file("rx_stats", 0600, dentry, i2400m, + &i2400m_rx_stats_fops); - fd = debugfs_create_file("tx_stats", 0600, dentry, i2400m, - &i2400m_tx_stats_fops); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_stats: %d\n", result); - goto error; - } + debugfs_create_file("tx_stats", 0600, dentry, i2400m, + &i2400m_tx_stats_fops); - fd = debugfs_create_i2400m_suspend("suspend", dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry suspend: %d\n", - result); - goto error; - } + debugfs_create_file("suspend", 0200, dentry, i2400m, + &fops_i2400m_suspend); - fd = debugfs_create_i2400m_reset("reset", dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry reset: %d\n", result); - goto error; - } - - result = 0; -error: - return result; + debugfs_create_file("reset", 0200, dentry, i2400m, &fops_i2400m_reset); } void i2400m_debugfs_rm(struct i2400m *i2400m) diff --git a/drivers/net/wimax/i2400m/driver.c b/drivers/net/wimax/i2400m/driver.c index 0a29222a1bf9..f66c0f8f6f4a 100644 --- a/drivers/net/wimax/i2400m/driver.c +++ b/drivers/net/wimax/i2400m/driver.c @@ -905,11 +905,7 @@ int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags) goto error_sysfs_setup; } - result = i2400m_debugfs_add(i2400m); - if (result < 0) { - dev_err(dev, "cannot setup i2400m's debugfs: %d\n", result); - goto error_debugfs_setup; - } + i2400m_debugfs_add(i2400m); result = i2400m_dev_start(i2400m, bm_flags); if (result < 0) @@ -919,7 +915,6 @@ int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags) error_dev_start: i2400m_debugfs_rm(i2400m); -error_debugfs_setup: sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj, &i2400m_dev_attr_group); error_sysfs_setup: diff --git a/drivers/net/wimax/i2400m/i2400m.h b/drivers/net/wimax/i2400m/i2400m.h index 5a34e72bab9a..a3733a6d14f5 100644 --- a/drivers/net/wimax/i2400m/i2400m.h +++ b/drivers/net/wimax/i2400m/i2400m.h @@ -812,13 +812,10 @@ enum i2400m_pt; int i2400m_tx(struct i2400m *, const void *, size_t, enum i2400m_pt); #ifdef CONFIG_DEBUG_FS -int i2400m_debugfs_add(struct i2400m *); +void i2400m_debugfs_add(struct i2400m *); void i2400m_debugfs_rm(struct i2400m *); #else -static inline int i2400m_debugfs_add(struct i2400m *i2400m) -{ - return 0; -} +static inline void i2400m_debugfs_add(struct i2400m *i2400m) {} static inline void i2400m_debugfs_rm(struct i2400m *i2400m) {} #endif diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index 2075e7b1fff6..6953f904232f 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -366,61 +366,25 @@ struct d_level D_LEVEL[] = { }; size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL); - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - static -int i2400mu_debugfs_add(struct i2400mu *i2400mu) +void i2400mu_debugfs_add(struct i2400mu *i2400mu) { - int result; - struct device *dev = &i2400mu->usb_iface->dev; struct dentry *dentry = i2400mu->i2400m.wimax_dev.debugfs_dentry; - struct dentry *fd; dentry = debugfs_create_dir("i2400m-usb", dentry); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - goto error; - } i2400mu->debugfs_dentry = dentry; - __debugfs_register("dl_", usb, dentry); - __debugfs_register("dl_", fw, dentry); - __debugfs_register("dl_", notif, dentry); - __debugfs_register("dl_", rx, dentry); - __debugfs_register("dl_", tx, dentry); - /* Don't touch these if you don't know what you are doing */ - fd = debugfs_create_u8("rx_size_auto_shrink", 0600, dentry, - &i2400mu->rx_size_auto_shrink); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_size_auto_shrink: %d\n", result); - goto error; - } + 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); - fd = debugfs_create_size_t("rx_size", 0600, dentry, - &i2400mu->rx_size); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_size: %d\n", result); - goto error; - } - - return 0; + /* 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); -error: - debugfs_remove_recursive(i2400mu->debugfs_dentry); - return result; + debugfs_create_size_t("rx_size", 0600, dentry, &i2400mu->rx_size); } @@ -534,15 +498,9 @@ int i2400mu_probe(struct usb_interface *iface, dev_err(dev, "cannot setup device: %d\n", result); goto error_setup; } - result = i2400mu_debugfs_add(i2400mu); - if (result < 0) { - dev_err(dev, "Can't register i2400mu's debugfs: %d\n", result); - goto error_debugfs_add; - } + i2400mu_debugfs_add(i2400mu); return 0; -error_debugfs_add: - i2400m_release(i2400m); error_setup: usb_set_intfdata(iface, NULL); usb_put_dev(i2400mu->usb_dev); diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 0606416dc971..12dad659bf68 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -6970,7 +6970,8 @@ exit: return ret; } -static int ath10k_cancel_remain_on_channel(struct ieee80211_hw *hw) +static int ath10k_cancel_remain_on_channel(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { struct ath10k *ar = hw->priv; diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index f23cb2f3d296..34121fbf32e3 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -2392,7 +2392,8 @@ out: return ret; } -static int ath9k_cancel_remain_on_channel(struct ieee80211_hw *hw) +static int ath9k_cancel_remain_on_channel(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c index 74834131cf7c..fd3b2b3d1b5c 100644 --- a/drivers/net/wireless/ath/wil6210/debugfs.c +++ b/drivers/net/wireless/ath/wil6210/debugfs.c @@ -1052,8 +1052,7 @@ static void wil_seq_print_skb(struct seq_file *s, struct sk_buff *skb) if (nr_frags) { seq_printf(s, " nr_frags = %d\n", nr_frags); for (i = 0; i < nr_frags; i++) { - const struct skb_frag_struct *frag = - &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = skb_frag_size(frag); p = skb_frag_address_safe(frag); diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c index eae00aafaa88..8b01ef8269da 100644 --- a/drivers/net/wireless/ath/wil6210/txrx.c +++ b/drivers/net/wireless/ath/wil6210/txrx.c @@ -1657,7 +1657,7 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif, len); } else { frag = &skb_shinfo(skb)->frags[f]; - len = frag->size; + len = skb_frag_size(frag); wil_dbg_txrx(wil, "TSO: frag[%d]: len %u\n", f, len); } @@ -1678,8 +1678,8 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif, if (!headlen) { pa = skb_frag_dma_map(dev, frag, - frag->size - len, lenmss, - DMA_TO_DEVICE); + skb_frag_size(frag) - len, + lenmss, DMA_TO_DEVICE); vring->ctx[i].mapped_as = wil_mapped_as_page; } else { pa = dma_map_single(dev, @@ -1900,8 +1900,7 @@ static int __wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif, /* middle segments */ for (; f < nr_frags; f++) { - const struct skb_frag_struct *frag = - &skb_shinfo(skb)->frags[f]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; int len = skb_frag_size(frag); *_d = *d; diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c index dc040cd4ab06..71b7ad4b6454 100644 --- a/drivers/net/wireless/ath/wil6210/txrx_edma.c +++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c @@ -1471,7 +1471,7 @@ static int __wil_tx_ring_tso_edma(struct wil6210_priv *wil, /* Rest of the descriptors are from the SKB fragments */ for (f = 0; f < nr_frags; f++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; - int len = frag->size; + int len = skb_frag_size(frag); wil_dbg_txrx(wil, "TSO: frag[%d]: len %u, descs_used %d\n", f, len, descs_used); diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c index b1e5d64ca60d..74229fcb63a9 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.c @@ -3256,28 +3256,16 @@ static void rs_add_debugfs(void *priv, void *priv_sta, struct dentry *dir) { struct iwl_lq_sta *lq_sta = priv_sta; - lq_sta->rs_sta_dbgfs_scale_table_file = - debugfs_create_file("rate_scale_table", 0600, dir, - lq_sta, &rs_sta_dbgfs_scale_table_ops); - lq_sta->rs_sta_dbgfs_stats_table_file = - debugfs_create_file("rate_stats_table", 0400, dir, - lq_sta, &rs_sta_dbgfs_stats_table_ops); - lq_sta->rs_sta_dbgfs_rate_scale_data_file = - debugfs_create_file("rate_scale_data", 0400, dir, - lq_sta, &rs_sta_dbgfs_rate_scale_data_ops); - lq_sta->rs_sta_dbgfs_tx_agg_tid_en_file = - debugfs_create_u8("tx_agg_tid_enable", 0600, dir, - &lq_sta->tx_agg_tid_en); -} + debugfs_create_file("rate_scale_table", 0600, dir, lq_sta, + &rs_sta_dbgfs_scale_table_ops); + debugfs_create_file("rate_stats_table", 0400, dir, lq_sta, + &rs_sta_dbgfs_stats_table_ops); + debugfs_create_file("rate_scale_data", 0400, dir, lq_sta, + &rs_sta_dbgfs_rate_scale_data_ops); + debugfs_create_u8("tx_agg_tid_enable", 0600, dir, + &lq_sta->tx_agg_tid_en); -static void rs_remove_debugfs(void *priv, void *priv_sta) -{ - struct iwl_lq_sta *lq_sta = priv_sta; - debugfs_remove(lq_sta->rs_sta_dbgfs_scale_table_file); - debugfs_remove(lq_sta->rs_sta_dbgfs_stats_table_file); - debugfs_remove(lq_sta->rs_sta_dbgfs_rate_scale_data_file); - debugfs_remove(lq_sta->rs_sta_dbgfs_tx_agg_tid_en_file); } #endif @@ -3303,7 +3291,6 @@ static const struct rate_control_ops rs_ops = { .free_sta = rs_free_sta, #ifdef CONFIG_MAC80211_DEBUGFS .add_sta_debugfs = rs_add_debugfs, - .remove_sta_debugfs = rs_remove_debugfs, #endif }; diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/rs.h b/drivers/net/wireless/intel/iwlwifi/dvm/rs.h index b7a1854cd202..68a840d739e8 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/dvm/rs.h @@ -356,10 +356,6 @@ struct iwl_lq_sta { struct iwl_traffic_load load[IWL_MAX_TID_COUNT]; u8 tx_agg_tid_en; #ifdef CONFIG_MAC80211_DEBUGFS - struct dentry *rs_sta_dbgfs_scale_table_file; - struct dentry *rs_sta_dbgfs_stats_table_file; - struct dentry *rs_sta_dbgfs_rate_scale_data_file; - struct dentry *rs_sta_dbgfs_tx_agg_tid_en_file; u32 dbg_fixed_rate; #endif struct iwl_priv *drv; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 1c904b5226aa..b74bd58f3f45 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -4035,7 +4035,8 @@ out_unlock: return ret; } -static int iwl_mvm_cancel_roc(struct ieee80211_hw *hw) +static int iwl_mvm_cancel_roc(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index d3f04acfbacb..e4415e58fa78 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -4127,10 +4127,6 @@ static void rs_drv_add_sta_debugfs(void *mvm, void *priv_sta, MVM_DEBUGFS_ADD_FILE_RS(ss_force, dir, 0600); } - -void rs_remove_sta_debugfs(void *mvm, void *mvm_sta) -{ -} #endif /* @@ -4158,7 +4154,6 @@ static const struct rate_control_ops rs_mvm_ops_drv = { .rate_update = rs_drv_rate_update, #ifdef CONFIG_MAC80211_DEBUGFS .add_sta_debugfs = rs_drv_add_sta_debugfs, - .remove_sta_debugfs = rs_remove_sta_debugfs, #endif .capa = RATE_CTRL_CAPA_VHT_EXT_NSS_BW, }; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 772e54f0696f..f86c2891310a 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2216,7 +2216,8 @@ static int mac80211_hwsim_roc(struct ieee80211_hw *hw, return 0; } -static int mac80211_hwsim_croc(struct ieee80211_hw *hw) +static int mac80211_hwsim_croc(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { struct mac80211_hwsim_data *hwsim = hw->priv; @@ -2594,7 +2595,7 @@ static const struct ieee80211_sband_iftype_data he_capa_5ghz = { }, }; -static void mac80211_hswim_he_capab(struct ieee80211_supported_band *sband) +static void mac80211_hwsim_he_capab(struct ieee80211_supported_band *sband) { if (sband->band == NL80211_BAND_2GHZ) sband->iftype_data = @@ -2805,12 +2806,6 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, ieee80211_hw_set(hw, SIGNAL_DBM); ieee80211_hw_set(hw, SUPPORTS_PS); ieee80211_hw_set(hw, TDLS_WIDER_BW); - - /* We only have SW crypto and only implement the A-MPDU API - * (but don't really build A-MPDUs) so can have extended key - * support - */ - ieee80211_hw_set(hw, EXT_KEY_ID_NATIVE); if (rctbl) ieee80211_hw_set(hw, SUPPORTS_RC_TABLE); ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); @@ -2897,7 +2892,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, sband->ht_cap.mcs.rx_mask[1] = 0xff; sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; - mac80211_hswim_he_capab(sband); + mac80211_hwsim_he_capab(sband); hw->wiphy->bands[band] = sband; } @@ -3233,6 +3228,7 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, { struct mac80211_hwsim_data *data2; struct ieee80211_rx_status rx_status; + struct ieee80211_hdr *hdr; const u8 *dst; int frame_data_len; void *frame_data; @@ -3299,6 +3295,12 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, rx_status.rate_idx = nla_get_u32(info->attrs[HWSIM_ATTR_RX_RATE]); rx_status.signal = nla_get_u32(info->attrs[HWSIM_ATTR_SIGNAL]); + hdr = (void *)skb->data; + + if (ieee80211_is_beacon(hdr->frame_control) || + ieee80211_is_probe_resp(hdr->frame_control)) + rx_status.boottime_ns = ktime_get_boottime_ns(); + memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status)); data2->rx_pkts++; data2->rx_bytes += skb->len; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c index b920be1f5718..c6c1ce69bcbc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c @@ -17,10 +17,8 @@ mt76_wmac_probe(struct platform_device *pdev) int ret; irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(&pdev->dev, "Failed to get device IRQ\n"); + if (irq < 0) return irq; - } mem_base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(mem_base)) { diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index 49df3bb08d41..ce5e92d82efc 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -1818,7 +1818,8 @@ out: return status; } -static int rsi_mac80211_cancel_roc(struct ieee80211_hw *hw) +static int rsi_mac80211_cancel_roc(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index b74dc8bc9755..547ad538d8b6 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -5749,7 +5749,8 @@ static void wlcore_roc_complete_work(struct work_struct *work) ieee80211_remain_on_channel_expired(wl->hw); } -static int wlcore_op_cancel_remain_on_channel(struct ieee80211_hw *hw) +static int wlcore_op_cancel_remain_on_channel(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { struct wl1271 *wl = hw->priv; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index c9262ffeefe4..0020b2e8c279 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -136,12 +136,12 @@ static inline struct xenvif_queue *ubuf_to_queue(const struct ubuf_info *ubuf) static u16 frag_get_pending_idx(skb_frag_t *frag) { - return (u16)frag->page_offset; + return (u16)skb_frag_off(frag); } static void frag_set_pending_idx(skb_frag_t *frag, u16 pending_idx) { - frag->page_offset = pending_idx; + skb_frag_off_set(frag, pending_idx); } static inline pending_ring_idx_t pending_index(unsigned i) @@ -1057,7 +1057,7 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s int j; skb->truesize += skb->data_len; for (j = 0; j < i; j++) - put_page(frags[j].page.p); + put_page(skb_frag_page(&frags[j])); return -ENOMEM; } @@ -1069,8 +1069,8 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s BUG(); offset += len; - frags[i].page.p = page; - frags[i].page_offset = 0; + __skb_frag_set_page(&frags[i], page); + skb_frag_off_set(&frags[i], 0); skb_frag_size_set(&frags[i], len); } @@ -1655,9 +1655,6 @@ static int __init netback_init(void) #ifdef CONFIG_DEBUG_FS xen_netback_dbg_root = debugfs_create_dir("xen-netback", NULL); - if (IS_ERR_OR_NULL(xen_netback_dbg_root)) - pr_warn("Init of debugfs returned %ld!\n", - PTR_ERR(xen_netback_dbg_root)); #endif /* CONFIG_DEBUG_FS */ return 0; diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 41034264bd34..f533b7372d59 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -170,50 +170,26 @@ DEFINE_SHOW_ATTRIBUTE(xenvif_ctrl); static void xenvif_debugfs_addif(struct xenvif *vif) { - struct dentry *pfile; int i; - if (IS_ERR_OR_NULL(xen_netback_dbg_root)) - return; - vif->xenvif_dbg_root = debugfs_create_dir(vif->dev->name, xen_netback_dbg_root); - if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) { - for (i = 0; i < vif->num_queues; ++i) { - char filename[sizeof("io_ring_q") + 4]; - - snprintf(filename, sizeof(filename), "io_ring_q%d", i); - pfile = debugfs_create_file(filename, - 0600, - vif->xenvif_dbg_root, - &vif->queues[i], - &xenvif_dbg_io_ring_ops_fops); - if (IS_ERR_OR_NULL(pfile)) - pr_warn("Creation of io_ring file returned %ld!\n", - PTR_ERR(pfile)); - } + for (i = 0; i < vif->num_queues; ++i) { + char filename[sizeof("io_ring_q") + 4]; - if (vif->ctrl_irq) { - pfile = debugfs_create_file("ctrl", - 0400, - vif->xenvif_dbg_root, - vif, - &xenvif_ctrl_fops); - if (IS_ERR_OR_NULL(pfile)) - pr_warn("Creation of ctrl file returned %ld!\n", - PTR_ERR(pfile)); - } - } else - netdev_warn(vif->dev, - "Creation of vif debugfs dir returned %ld!\n", - PTR_ERR(vif->xenvif_dbg_root)); + snprintf(filename, sizeof(filename), "io_ring_q%d", i); + debugfs_create_file(filename, 0600, vif->xenvif_dbg_root, + &vif->queues[i], + &xenvif_dbg_io_ring_ops_fops); + } + + if (vif->ctrl_irq) + debugfs_create_file("ctrl", 0400, vif->xenvif_dbg_root, vif, + &xenvif_ctrl_fops); } static void xenvif_debugfs_delif(struct xenvif *vif) { - if (IS_ERR_OR_NULL(xen_netback_dbg_root)) - return; - debugfs_remove_recursive(vif->xenvif_dbg_root); vif->xenvif_dbg_root = NULL; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 8d33970a2950..b930d5f95222 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -531,7 +531,7 @@ static int xennet_count_skb_slots(struct sk_buff *skb) for (i = 0; i < frags; i++) { skb_frag_t *frag = skb_shinfo(skb)->frags + i; unsigned long size = skb_frag_size(frag); - unsigned long offset = frag->page_offset; + unsigned long offset = skb_frag_off(frag); /* Skip unused frames from start of page */ offset &= ~PAGE_MASK; @@ -674,8 +674,8 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev /* Requests for all the frags. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - tx = xennet_make_txreqs(queue, tx, skb, - skb_frag_page(frag), frag->page_offset, + tx = xennet_make_txreqs(queue, tx, skb, skb_frag_page(frag), + skb_frag_off(frag), skb_frag_size(frag)); } @@ -1040,7 +1040,7 @@ err: if (NETFRONT_SKB_CB(skb)->pull_to > RX_COPY_THRESHOLD) NETFRONT_SKB_CB(skb)->pull_to = RX_COPY_THRESHOLD; - skb_shinfo(skb)->frags[0].page_offset = rx->offset; + skb_frag_off_set(&skb_shinfo(skb)->frags[0], rx->offset); skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status); skb->data_len = rx->status; skb->len += rx->status; diff --git a/drivers/nfc/nxp-nci/Kconfig b/drivers/nfc/nxp-nci/Kconfig index 12df2c8cc51d..e1f71deab6fc 100644 --- a/drivers/nfc/nxp-nci/Kconfig +++ b/drivers/nfc/nxp-nci/Kconfig @@ -2,10 +2,9 @@ config NFC_NXP_NCI tristate "NXP-NCI NFC driver" depends on NFC_NCI - default n ---help--- - Generic core driver for NXP NCI chips such as the NPC100 - or PN7150 families. + Generic core driver for NXP NCI chips such as the NPC100 (PN547), + NPC300 (PN548) or PN7150 families. This is a driver based on the NCI NFC kernel layers and will thus not work with NXP libnfc library. @@ -23,4 +22,4 @@ config NFC_NXP_NCI_I2C To compile this driver as a module, choose m here. The module will be called nxp_nci_i2c. - Say Y if unsure. + Say N if unsure. diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index 8dafc696719f..a0ce95a287c5 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -11,10 +11,8 @@ */ #include <linux/delay.h> -#include <linux/gpio.h> #include <linux/module.h> #include <linux/nfc.h> -#include <linux/platform_data/nxp-nci.h> #include <net/nfc/nci_core.h> diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 4aeb3861b409..307bd2afbe05 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -12,8 +12,6 @@ * Copyright (C) 2012 Intel Corporation. All rights reserved. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include <linux/acpi.h> #include <linux/delay.h> #include <linux/i2c.h> @@ -21,9 +19,6 @@ #include <linux/module.h> #include <linux/nfc.h> #include <linux/gpio/consumer.h> -#include <linux/of_gpio.h> -#include <linux/of_irq.h> -#include <linux/platform_data/nxp-nci.h> #include <asm/unaligned.h> #include <net/nfc/nfc.h> @@ -38,8 +33,8 @@ struct nxp_nci_i2c_phy { struct i2c_client *i2c_dev; struct nci_dev *ndev; - unsigned int gpio_en; - unsigned int gpio_fw; + struct gpio_desc *gpiod_en; + struct gpio_desc *gpiod_fw; int hard_fault; /* * < 0 if hardware error occurred (e.g. i2c err) @@ -52,8 +47,8 @@ static int nxp_nci_i2c_set_mode(void *phy_id, { struct nxp_nci_i2c_phy *phy = (struct nxp_nci_i2c_phy *) phy_id; - gpio_set_value(phy->gpio_fw, (mode == NXP_NCI_MODE_FW) ? 1 : 0); - gpio_set_value(phy->gpio_en, (mode != NXP_NCI_MODE_COLD) ? 1 : 0); + gpiod_set_value(phy->gpiod_fw, (mode == NXP_NCI_MODE_FW) ? 1 : 0); + gpiod_set_value(phy->gpiod_en, (mode != NXP_NCI_MODE_COLD) ? 1 : 0); usleep_range(10000, 15000); if (mode == NXP_NCI_MODE_COLD) @@ -250,116 +245,55 @@ exit_irq_none: return IRQ_NONE; } -static int nxp_nci_i2c_parse_devtree(struct i2c_client *client) -{ - struct nxp_nci_i2c_phy *phy = i2c_get_clientdata(client); - struct device_node *pp; - int r; - - pp = client->dev.of_node; - if (!pp) - return -ENODEV; - - r = of_get_named_gpio(pp, "enable-gpios", 0); - if (r == -EPROBE_DEFER) - r = of_get_named_gpio(pp, "enable-gpios", 0); - if (r < 0) { - nfc_err(&client->dev, "Failed to get EN gpio, error: %d\n", r); - return r; - } - phy->gpio_en = r; - - r = of_get_named_gpio(pp, "firmware-gpios", 0); - if (r == -EPROBE_DEFER) - r = of_get_named_gpio(pp, "firmware-gpios", 0); - if (r < 0) { - nfc_err(&client->dev, "Failed to get FW gpio, error: %d\n", r); - return r; - } - phy->gpio_fw = r; - - return 0; -} - -static int nxp_nci_i2c_acpi_config(struct nxp_nci_i2c_phy *phy) -{ - struct i2c_client *client = phy->i2c_dev; - struct gpio_desc *gpiod_en, *gpiod_fw; +static const struct acpi_gpio_params firmware_gpios = { 1, 0, false }; +static const struct acpi_gpio_params enable_gpios = { 2, 0, false }; - gpiod_en = devm_gpiod_get_index(&client->dev, NULL, 2, GPIOD_OUT_LOW); - gpiod_fw = devm_gpiod_get_index(&client->dev, NULL, 1, GPIOD_OUT_LOW); - - if (IS_ERR(gpiod_en) || IS_ERR(gpiod_fw)) { - nfc_err(&client->dev, "No GPIOs\n"); - return -EINVAL; - } - - phy->gpio_en = desc_to_gpio(gpiod_en); - phy->gpio_fw = desc_to_gpio(gpiod_fw); - - return 0; -} +static const struct acpi_gpio_mapping acpi_nxp_nci_gpios[] = { + { "enable-gpios", &enable_gpios, 1 }, + { "firmware-gpios", &firmware_gpios, 1 }, + { } +}; static int nxp_nci_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) { + struct device *dev = &client->dev; struct nxp_nci_i2c_phy *phy; - struct nxp_nci_nfc_platform_data *pdata; int r; if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { nfc_err(&client->dev, "Need I2C_FUNC_I2C\n"); - r = -ENODEV; - goto probe_exit; + return -ENODEV; } phy = devm_kzalloc(&client->dev, sizeof(struct nxp_nci_i2c_phy), GFP_KERNEL); - if (!phy) { - r = -ENOMEM; - goto probe_exit; - } + if (!phy) + return -ENOMEM; phy->i2c_dev = client; i2c_set_clientdata(client, phy); - pdata = client->dev.platform_data; - - if (!pdata && client->dev.of_node) { - r = nxp_nci_i2c_parse_devtree(client); - if (r < 0) { - nfc_err(&client->dev, "Failed to get DT data\n"); - goto probe_exit; - } - } else if (pdata) { - phy->gpio_en = pdata->gpio_en; - phy->gpio_fw = pdata->gpio_fw; - } else if (ACPI_HANDLE(&client->dev)) { - r = nxp_nci_i2c_acpi_config(phy); - if (r < 0) - goto probe_exit; - goto nci_probe; - } else { - nfc_err(&client->dev, "No platform data\n"); - r = -EINVAL; - goto probe_exit; - } + r = devm_acpi_dev_add_driver_gpios(dev, acpi_nxp_nci_gpios); + if (r) + return r; - r = devm_gpio_request_one(&phy->i2c_dev->dev, phy->gpio_en, - GPIOF_OUT_INIT_LOW, "nxp_nci_en"); - if (r < 0) - goto probe_exit; + phy->gpiod_en = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW); + if (IS_ERR(phy->gpiod_en)) { + nfc_err(dev, "Failed to get EN gpio\n"); + return PTR_ERR(phy->gpiod_en); + } - r = devm_gpio_request_one(&phy->i2c_dev->dev, phy->gpio_fw, - GPIOF_OUT_INIT_LOW, "nxp_nci_fw"); - if (r < 0) - goto probe_exit; + phy->gpiod_fw = devm_gpiod_get(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); + } -nci_probe: r = nxp_nci_probe(phy, &client->dev, &i2c_phy_ops, NXP_NCI_I2C_MAX_PAYLOAD, &phy->ndev); if (r < 0) - goto probe_exit; + return r; r = request_threaded_irq(client->irq, NULL, nxp_nci_i2c_irq_thread_fn, @@ -368,7 +302,6 @@ nci_probe: if (r < 0) nfc_err(&client->dev, "Unable to register IRQ handler\n"); -probe_exit: return r; } @@ -390,14 +323,15 @@ MODULE_DEVICE_TABLE(i2c, nxp_nci_i2c_id_table); static const struct of_device_id of_nxp_nci_i2c_match[] = { { .compatible = "nxp,nxp-nci-i2c", }, - {}, + {} }; MODULE_DEVICE_TABLE(of, of_nxp_nci_i2c_match); #ifdef CONFIG_ACPI -static struct acpi_device_id acpi_id[] = { +static const struct acpi_device_id acpi_id[] = { + { "NXP1001" }, { "NXP7471" }, - { }, + { } }; MODULE_DEVICE_TABLE(acpi, acpi_id); #endif @@ -406,7 +340,7 @@ static struct i2c_driver nxp_nci_i2c_driver = { .driver = { .name = NXP_NCI_I2C_DRIVER_NAME, .acpi_match_table = ACPI_PTR(acpi_id), - .of_match_table = of_match_ptr(of_nxp_nci_i2c_match), + .of_match_table = of_nxp_nci_i2c_match, }, .probe = nxp_nci_i2c_probe, .id_table = nxp_nci_i2c_id_table, diff --git a/drivers/nfc/nxp-nci/nxp-nci.h b/drivers/nfc/nxp-nci/nxp-nci.h index 6fe7c45544bf..ae3fb2735a4e 100644 --- a/drivers/nfc/nxp-nci/nxp-nci.h +++ b/drivers/nfc/nxp-nci/nxp-nci.h @@ -14,7 +14,6 @@ #include <linux/completion.h> #include <linux/firmware.h> #include <linux/nfc.h> -#include <linux/platform_data/nxp-nci.h> #include <net/nfc/nci_core.h> diff --git a/drivers/ptp/ptp_dte.c b/drivers/ptp/ptp_dte.c index 5b6393e3ea27..0dcfdc806f57 100644 --- a/drivers/ptp/ptp_dte.c +++ b/drivers/ptp/ptp_dte.c @@ -248,11 +248,8 @@ static int ptp_dte_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ptp_dte->regs = devm_ioremap_resource(dev, res); - if (IS_ERR(ptp_dte->regs)) { - dev_err(dev, - "%s: io remap failed\n", __func__); + if (IS_ERR(ptp_dte->regs)) return PTR_ERR(ptp_dte->regs); - } spin_lock_init(&ptp_dte->lock); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 9c3310c4d61d..0803070246aa 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -3535,7 +3535,7 @@ static int qeth_get_elements_for_frags(struct sk_buff *skb) int cnt, elements = 0; for (cnt = 0; cnt < skb_shinfo(skb)->nr_frags; cnt++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[cnt]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[cnt]; elements += qeth_get_elements_for_range( (addr_t)skb_frag_address(frag), diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 7796799bf04a..9ff9429395eb 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -346,7 +346,7 @@ static int bnx2fc_xmit(struct fc_lport *lport, struct fc_frame *fp) return -ENOMEM; } frag = &skb_shinfo(skb)->frags[skb_shinfo(skb)->nr_frags - 1]; - cp = kmap_atomic(skb_frag_page(frag)) + frag->page_offset; + cp = kmap_atomic(skb_frag_page(frag)) + skb_frag_off(frag); } else { cp = skb_put(skb, tlen); } diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 00dd47bcbb1e..587d4bbb7d22 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1522,8 +1522,7 @@ static int fcoe_xmit(struct fc_lport *lport, struct fc_frame *fp) return -ENOMEM; } frag = &skb_shinfo(skb)->frags[skb_shinfo(skb)->nr_frags - 1]; - cp = kmap_atomic(skb_frag_page(frag)) - + frag->page_offset; + cp = kmap_atomic(skb_frag_page(frag)) + skb_frag_off(frag); } else { cp = skb_put(skb, tlen); } diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c index ba4603d76284..a20ddc301c89 100644 --- a/drivers/scsi/fcoe/fcoe_transport.c +++ b/drivers/scsi/fcoe/fcoe_transport.c @@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(fcoe_get_wwn); u32 fcoe_fc_crc(struct fc_frame *fp) { struct sk_buff *skb = fp_skb(fp); - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned char *data; unsigned long off, len, clen; u32 crc; @@ -318,7 +318,7 @@ u32 fcoe_fc_crc(struct fc_frame *fp) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; - off = frag->page_offset; + off = skb_frag_off(frag); len = skb_frag_size(frag); while (len > 0) { clen = min(len, PAGE_SIZE - (off & ~PAGE_MASK)); diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index a42babde036d..42542720962f 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -1077,7 +1077,7 @@ static int qedf_xmit(struct fc_lport *lport, struct fc_frame *fp) return -ENOMEM; } frag = &skb_shinfo(skb)->frags[skb_shinfo(skb)->nr_frags - 1]; - cp = kmap_atomic(skb_frag_page(frag)) + frag->page_offset; + cp = kmap_atomic(skb_frag_page(frag)) + skb_frag_off(frag); } else { cp = skb_put(skb, tlen); } diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index 7c96a01eef6c..0b8a614be11e 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -120,4 +120,6 @@ source "drivers/staging/kpc2000/Kconfig" source "drivers/staging/isdn/Kconfig" +source "drivers/staging/qlge/Kconfig" + endif # STAGING diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index fcaac9693b83..741152511a10 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -50,3 +50,4 @@ obj-$(CONFIG_EROFS_FS) += erofs/ obj-$(CONFIG_FIELDBUS_DEV) += fieldbus/ obj-$(CONFIG_KPC2000) += kpc2000/ obj-$(CONFIG_ISDN_CAPI) += isdn/ +obj-$(CONFIG_QLGE) += qlge/ diff --git a/drivers/staging/octeon/Kconfig b/drivers/staging/octeon/Kconfig index 1e3012b9991c..5319909eb2f6 100644 --- a/drivers/staging/octeon/Kconfig +++ b/drivers/staging/octeon/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 config OCTEON_ETHERNET tristate "Cavium Networks Octeon Ethernet support" - depends on CAVIUM_OCTEON_SOC && NETDEVICES + depends on CAVIUM_OCTEON_SOC || COMPILE_TEST + depends on NETDEVICES select PHYLIB select MDIO_OCTEON help diff --git a/drivers/staging/octeon/ethernet-defines.h b/drivers/staging/octeon/ethernet-defines.h index 1e114422993a..ef9e767b0e2e 100644 --- a/drivers/staging/octeon/ethernet-defines.h +++ b/drivers/staging/octeon/ethernet-defines.h @@ -21,8 +21,6 @@ #ifndef __ETHERNET_DEFINES_H__ #define __ETHERNET_DEFINES_H__ -#include <asm/octeon/cvmx-config.h> - #ifdef CONFIG_NETFILTER #define REUSE_SKBUFFS_WITHOUT_FREE 0 #else diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index 2aee64fdaec5..ffac0c4b3f5c 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -13,15 +13,11 @@ #include <generated/utsrelease.h> #include <net/dst.h> -#include <asm/octeon/octeon.h> - -#include "ethernet-defines.h" #include "octeon-ethernet.h" +#include "ethernet-defines.h" #include "ethernet-mdio.h" #include "ethernet-util.h" -#include <asm/octeon/cvmx-gmxx-defs.h> - static void cvm_oct_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { diff --git a/drivers/staging/octeon/ethernet-mem.c b/drivers/staging/octeon/ethernet-mem.c index 0d26c4a93ec1..532594957ebc 100644 --- a/drivers/staging/octeon/ethernet-mem.c +++ b/drivers/staging/octeon/ethernet-mem.c @@ -9,13 +9,10 @@ #include <linux/netdevice.h> #include <linux/slab.h> -#include <asm/octeon/octeon.h> - +#include "octeon-ethernet.h" #include "ethernet-mem.h" #include "ethernet-defines.h" -#include <asm/octeon/cvmx-fpa.h> - /** * cvm_oct_fill_hw_skbuff - fill the supplied hardware pool with skbuffs * @pool: Pool to allocate an skbuff for diff --git a/drivers/staging/octeon/ethernet-rgmii.c b/drivers/staging/octeon/ethernet-rgmii.c index c15376d33891..d91fd5ce9e68 100644 --- a/drivers/staging/octeon/ethernet-rgmii.c +++ b/drivers/staging/octeon/ethernet-rgmii.c @@ -12,19 +12,11 @@ #include <linux/ratelimit.h> #include <net/dst.h> -#include <asm/octeon/octeon.h> - -#include "ethernet-defines.h" #include "octeon-ethernet.h" +#include "ethernet-defines.h" #include "ethernet-util.h" #include "ethernet-mdio.h" -#include <asm/octeon/cvmx-helper.h> - -#include <asm/octeon/cvmx-ipd-defs.h> -#include <asm/octeon/cvmx-npi-defs.h> -#include <asm/octeon/cvmx-gmxx-defs.h> - static DEFINE_SPINLOCK(global_register_lock); static void cvm_oct_set_hw_preamble(struct octeon_ethernet *priv, bool enable) diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c index 5e271245273c..0e65955c746b 100644 --- a/drivers/staging/octeon/ethernet-rx.c +++ b/drivers/staging/octeon/ethernet-rx.c @@ -23,23 +23,12 @@ #include <net/xfrm.h> #endif /* CONFIG_XFRM */ -#include <asm/octeon/octeon.h> - +#include "octeon-ethernet.h" #include "ethernet-defines.h" #include "ethernet-mem.h" #include "ethernet-rx.h" -#include "octeon-ethernet.h" #include "ethernet-util.h" -#include <asm/octeon/cvmx-helper.h> -#include <asm/octeon/cvmx-wqe.h> -#include <asm/octeon/cvmx-fau.h> -#include <asm/octeon/cvmx-pow.h> -#include <asm/octeon/cvmx-pip.h> -#include <asm/octeon/cvmx-scratch.h> - -#include <asm/octeon/cvmx-gmxx-defs.h> - static atomic_t oct_rx_ready = ATOMIC_INIT(0); static struct oct_rx_group { diff --git a/drivers/staging/octeon/ethernet-rx.h b/drivers/staging/octeon/ethernet-rx.h index 096553d8fc99..ff6482fa20d6 100644 --- a/drivers/staging/octeon/ethernet-rx.h +++ b/drivers/staging/octeon/ethernet-rx.h @@ -5,8 +5,6 @@ * Copyright (c) 2003-2007 Cavium Networks */ -#include <asm/octeon/cvmx-fau.h> - void cvm_oct_poll_controller(struct net_device *dev); void cvm_oct_rx_initialize(void); void cvm_oct_rx_shutdown(void); diff --git a/drivers/staging/octeon/ethernet-sgmii.c b/drivers/staging/octeon/ethernet-sgmii.c index a4a8f094e2b4..d7fbd9159302 100644 --- a/drivers/staging/octeon/ethernet-sgmii.c +++ b/drivers/staging/octeon/ethernet-sgmii.c @@ -11,17 +11,11 @@ #include <linux/ratelimit.h> #include <net/dst.h> -#include <asm/octeon/octeon.h> - -#include "ethernet-defines.h" #include "octeon-ethernet.h" +#include "ethernet-defines.h" #include "ethernet-util.h" #include "ethernet-mdio.h" -#include <asm/octeon/cvmx-helper.h> - -#include <asm/octeon/cvmx-gmxx-defs.h> - int cvm_oct_sgmii_open(struct net_device *dev) { return cvm_oct_common_open(dev, cvm_oct_link_poll); diff --git a/drivers/staging/octeon/ethernet-spi.c b/drivers/staging/octeon/ethernet-spi.c index 01efdf2a2c20..c582403e6a1f 100644 --- a/drivers/staging/octeon/ethernet-spi.c +++ b/drivers/staging/octeon/ethernet-spi.c @@ -10,18 +10,10 @@ #include <linux/interrupt.h> #include <net/dst.h> -#include <asm/octeon/octeon.h> - -#include "ethernet-defines.h" #include "octeon-ethernet.h" +#include "ethernet-defines.h" #include "ethernet-util.h" -#include <asm/octeon/cvmx-spi.h> - -#include <asm/octeon/cvmx-npi-defs.h> -#include <asm/octeon/cvmx-spxx-defs.h> -#include <asm/octeon/cvmx-stxx-defs.h> - static int number_spi_ports; static int need_retrain[2] = { 0, 0 }; diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c index 20f513fbaa85..c64728fc21f2 100644 --- a/drivers/staging/octeon/ethernet-tx.c +++ b/drivers/staging/octeon/ethernet-tx.c @@ -22,21 +22,11 @@ #include <linux/atomic.h> #include <net/sch_generic.h> -#include <asm/octeon/octeon.h> - -#include "ethernet-defines.h" #include "octeon-ethernet.h" +#include "ethernet-defines.h" #include "ethernet-tx.h" #include "ethernet-util.h" -#include <asm/octeon/cvmx-wqe.h> -#include <asm/octeon/cvmx-fau.h> -#include <asm/octeon/cvmx-pip.h> -#include <asm/octeon/cvmx-pko.h> -#include <asm/octeon/cvmx-helper.h> - -#include <asm/octeon/cvmx-gmxx-defs.h> - #define CVM_OCT_SKB_CB(skb) ((u64 *)((skb)->cb)) /* @@ -280,12 +270,11 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev) hw_buffer.s.size = skb_headlen(skb); CVM_OCT_SKB_CB(skb)[0] = hw_buffer.u64; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - struct skb_frag_struct *fs = skb_shinfo(skb)->frags + i; + skb_frag_t *fs = skb_shinfo(skb)->frags + i; hw_buffer.s.addr = - XKPHYS_TO_PHYS((u64)(page_address(fs->page.p) + - fs->page_offset)); - hw_buffer.s.size = fs->size; + XKPHYS_TO_PHYS((u64)skb_frag_address(fs)); + hw_buffer.s.size = skb_frag_size(fs); CVM_OCT_SKB_CB(skb)[i + 1] = hw_buffer.u64; } hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)CVM_OCT_SKB_CB(skb)); diff --git a/drivers/staging/octeon/ethernet-util.h b/drivers/staging/octeon/ethernet-util.h index 31a82873e15c..2af83a12ca78 100644 --- a/drivers/staging/octeon/ethernet-util.h +++ b/drivers/staging/octeon/ethernet-util.h @@ -5,10 +5,6 @@ * Copyright (c) 2003-2007 Cavium Networks */ -#include <asm/octeon/cvmx-pip.h> -#include <asm/octeon/cvmx-helper.h> -#include <asm/octeon/cvmx-helper-util.h> - /** * cvm_oct_get_buffer_ptr - convert packet data address to pointer * @packet_ptr: Packet data hardware address diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index 8847a11c212f..8889494adf1f 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -19,24 +19,14 @@ #include <net/dst.h> -#include <asm/octeon/octeon.h> - -#include "ethernet-defines.h" #include "octeon-ethernet.h" +#include "ethernet-defines.h" #include "ethernet-mem.h" #include "ethernet-rx.h" #include "ethernet-tx.h" #include "ethernet-mdio.h" #include "ethernet-util.h" -#include <asm/octeon/cvmx-pip.h> -#include <asm/octeon/cvmx-pko.h> -#include <asm/octeon/cvmx-fau.h> -#include <asm/octeon/cvmx-ipd.h> -#include <asm/octeon/cvmx-helper.h> -#include <asm/octeon/cvmx-asxx-defs.h> -#include <asm/octeon/cvmx-gmxx-defs.h> - #define OCTEON_MAX_MTU 65392 static int num_packet_buffers = 1024; diff --git a/drivers/staging/octeon/octeon-ethernet.h b/drivers/staging/octeon/octeon-ethernet.h index be570d33685a..a8a864b40913 100644 --- a/drivers/staging/octeon/octeon-ethernet.h +++ b/drivers/staging/octeon/octeon-ethernet.h @@ -13,7 +13,34 @@ #include <linux/of.h> #include <linux/phy.h> -#include <asm/octeon/cvmx-helper-board.h> + +#ifdef CONFIG_MIPS + +#include <asm/octeon/octeon.h> + +#include <asm/octeon/cvmx-asxx-defs.h> +#include <asm/octeon/cvmx-config.h> +#include <asm/octeon/cvmx-fau.h> +#include <asm/octeon/cvmx-gmxx-defs.h> +#include <asm/octeon/cvmx-helper.h> +#include <asm/octeon/cvmx-helper-util.h> +#include <asm/octeon/cvmx-ipd.h> +#include <asm/octeon/cvmx-ipd-defs.h> +#include <asm/octeon/cvmx-npi-defs.h> +#include <asm/octeon/cvmx-pip.h> +#include <asm/octeon/cvmx-pko.h> +#include <asm/octeon/cvmx-pow.h> +#include <asm/octeon/cvmx-scratch.h> +#include <asm/octeon/cvmx-spi.h> +#include <asm/octeon/cvmx-spxx-defs.h> +#include <asm/octeon/cvmx-stxx-defs.h> +#include <asm/octeon/cvmx-wqe.h> + +#else + +#include "octeon-stubs.h" + +#endif /** * This is the definition of the Ethernet driver's private diff --git a/drivers/staging/octeon/octeon-stubs.h b/drivers/staging/octeon/octeon-stubs.h new file mode 100644 index 000000000000..a4ac3bfb62a8 --- /dev/null +++ b/drivers/staging/octeon/octeon-stubs.h @@ -0,0 +1,1429 @@ +#define CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE 512 +#define XKPHYS_TO_PHYS(p) (p) + +#define OCTEON_IRQ_WORKQ0 0 +#define OCTEON_IRQ_RML 0 +#define OCTEON_IRQ_TIMER1 0 +#define OCTEON_IS_MODEL(x) 0 +#define octeon_has_feature(x) 0 +#define octeon_get_clock_rate() 0 + +#define CVMX_SYNCIOBDMA do { } while(0) + +#define CVMX_HELPER_INPUT_TAG_TYPE 0 +#define CVMX_HELPER_FIRST_MBUFF_SKIP 7 +#define CVMX_FAU_REG_END (2048) +#define CVMX_FPA_OUTPUT_BUFFER_POOL (2) +#define CVMX_FPA_OUTPUT_BUFFER_POOL_SIZE 16 +#define CVMX_FPA_PACKET_POOL (0) +#define CVMX_FPA_PACKET_POOL_SIZE 16 +#define CVMX_FPA_WQE_POOL (1) +#define CVMX_FPA_WQE_POOL_SIZE 16 +#define CVMX_GMXX_RXX_ADR_CAM_EN(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_ADR_CTL(a, b) ((a)+(b)) +#define CVMX_GMXX_PRTX_CFG(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_FRM_MAX(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_JABBER(a, b) ((a)+(b)) +#define CVMX_IPD_CTL_STATUS 0 +#define CVMX_PIP_FRM_LEN_CHKX(a) (a) +#define CVMX_PIP_NUM_INPUT_PORTS 1 +#define CVMX_SCR_SCRATCH 0 +#define CVMX_PKO_QUEUES_PER_PORT_INTERFACE0 2 +#define CVMX_PKO_QUEUES_PER_PORT_INTERFACE1 2 +#define CVMX_IPD_SUB_PORT_FCS 0 +#define CVMX_SSO_WQ_IQ_DIS 0 +#define CVMX_SSO_WQ_INT 0 +#define CVMX_POW_WQ_INT 0 +#define CVMX_SSO_WQ_INT_PC 0 +#define CVMX_NPI_RSL_INT_BLOCKS 0 +#define CVMX_POW_WQ_INT_PC 0 + +typedef union { + uint64_t u64; + struct { + uint64_t bufs:8; + uint64_t ip_offset:8; + uint64_t vlan_valid:1; + uint64_t vlan_stacked:1; + uint64_t unassigned:1; + uint64_t vlan_cfi:1; + uint64_t vlan_id:12; + uint64_t pr:4; + uint64_t unassigned2:8; + uint64_t dec_ipcomp:1; + uint64_t tcp_or_udp:1; + uint64_t dec_ipsec:1; + uint64_t is_v6:1; + uint64_t software:1; + uint64_t L4_error:1; + uint64_t is_frag:1; + uint64_t IP_exc:1; + uint64_t is_bcast:1; + uint64_t is_mcast:1; + uint64_t not_IP:1; + uint64_t rcv_error:1; + uint64_t err_code:8; + } s; + struct { + uint64_t bufs:8; + uint64_t ip_offset:8; + uint64_t vlan_valid:1; + uint64_t vlan_stacked:1; + uint64_t unassigned:1; + uint64_t vlan_cfi:1; + uint64_t vlan_id:12; + uint64_t port:12; + uint64_t dec_ipcomp:1; + uint64_t tcp_or_udp:1; + uint64_t dec_ipsec:1; + uint64_t is_v6:1; + uint64_t software:1; + uint64_t L4_error:1; + uint64_t is_frag:1; + uint64_t IP_exc:1; + uint64_t is_bcast:1; + uint64_t is_mcast:1; + uint64_t not_IP:1; + uint64_t rcv_error:1; + uint64_t err_code:8; + } s_cn68xx; + + struct { + uint64_t unused1:16; + uint64_t vlan:16; + uint64_t unused2:32; + } svlan; + struct { + uint64_t bufs:8; + uint64_t unused:8; + uint64_t vlan_valid:1; + uint64_t vlan_stacked:1; + uint64_t unassigned:1; + uint64_t vlan_cfi:1; + uint64_t vlan_id:12; + uint64_t pr:4; + uint64_t unassigned2:12; + uint64_t software:1; + uint64_t unassigned3:1; + uint64_t is_rarp:1; + uint64_t is_arp:1; + uint64_t is_bcast:1; + uint64_t is_mcast:1; + uint64_t not_IP:1; + uint64_t rcv_error:1; + uint64_t err_code:8; + } snoip; + +} cvmx_pip_wqe_word2; + +union cvmx_pip_wqe_word0 { + struct { + uint64_t next_ptr:40; + uint8_t unused; + uint16_t hw_chksum; + } cn38xx; + struct { + uint64_t pknd:6; /* 0..5 */ + uint64_t unused2:2; /* 6..7 */ + uint64_t bpid:6; /* 8..13 */ + uint64_t unused1:18; /* 14..31 */ + uint64_t l2ptr:8; /* 32..39 */ + uint64_t l3ptr:8; /* 40..47 */ + uint64_t unused0:8; /* 48..55 */ + uint64_t l4ptr:8; /* 56..63 */ + } cn68xx; +}; + +union cvmx_wqe_word0 { + uint64_t u64; + union cvmx_pip_wqe_word0 pip; +}; + +union cvmx_wqe_word1 { + uint64_t u64; + struct { + uint64_t tag:32; + uint64_t tag_type:2; + uint64_t varies:14; + uint64_t len:16; + }; + struct { + uint64_t tag:32; + uint64_t tag_type:2; + uint64_t zero_2:3; + uint64_t grp:6; + uint64_t zero_1:1; + uint64_t qos:3; + uint64_t zero_0:1; + uint64_t len:16; + } cn68xx; + struct { + uint64_t tag:32; + uint64_t tag_type:2; + uint64_t zero_2:1; + uint64_t grp:4; + uint64_t qos:3; + uint64_t ipprt:6; + uint64_t len:16; + } cn38xx; +}; + +union cvmx_buf_ptr { + void *ptr; + uint64_t u64; + struct { + uint64_t i:1; + uint64_t back:4; + uint64_t pool:3; + uint64_t size:16; + uint64_t addr:40; + } s; +}; + +typedef struct { + union cvmx_wqe_word0 word0; + union cvmx_wqe_word1 word1; + cvmx_pip_wqe_word2 word2; + union cvmx_buf_ptr packet_ptr; + uint8_t packet_data[96]; +} cvmx_wqe_t; + +typedef union { + uint64_t u64; + struct { + uint64_t reserved_20_63:44; + uint64_t link_up:1; /**< Is the physical link up? */ + uint64_t full_duplex:1; /**< 1 if the link is full duplex */ + uint64_t speed:18; /**< Speed of the link in Mbps */ + } s; +} cvmx_helper_link_info_t; + +typedef enum { + CVMX_FAU_REG_32_START = 0, +} cvmx_fau_reg_32_t; + +typedef enum { + CVMX_FAU_OP_SIZE_8 = 0, + CVMX_FAU_OP_SIZE_16 = 1, + CVMX_FAU_OP_SIZE_32 = 2, + CVMX_FAU_OP_SIZE_64 = 3 +} cvmx_fau_op_size_t; + +typedef enum { + CVMX_SPI_MODE_UNKNOWN = 0, + CVMX_SPI_MODE_TX_HALFPLEX = 1, + CVMX_SPI_MODE_RX_HALFPLEX = 2, + CVMX_SPI_MODE_DUPLEX = 3 +} cvmx_spi_mode_t; + +typedef enum { + CVMX_HELPER_INTERFACE_MODE_DISABLED, + CVMX_HELPER_INTERFACE_MODE_RGMII, + CVMX_HELPER_INTERFACE_MODE_GMII, + CVMX_HELPER_INTERFACE_MODE_SPI, + CVMX_HELPER_INTERFACE_MODE_PCIE, + CVMX_HELPER_INTERFACE_MODE_XAUI, + CVMX_HELPER_INTERFACE_MODE_SGMII, + CVMX_HELPER_INTERFACE_MODE_PICMG, + CVMX_HELPER_INTERFACE_MODE_NPI, + CVMX_HELPER_INTERFACE_MODE_LOOP, +} cvmx_helper_interface_mode_t; + +typedef enum { + CVMX_POW_WAIT = 1, + CVMX_POW_NO_WAIT = 0, +} cvmx_pow_wait_t; + +typedef enum { + CVMX_PKO_LOCK_NONE = 0, + CVMX_PKO_LOCK_ATOMIC_TAG = 1, + CVMX_PKO_LOCK_CMD_QUEUE = 2, +} cvmx_pko_lock_t; + +typedef enum { + CVMX_PKO_SUCCESS, + CVMX_PKO_INVALID_PORT, + CVMX_PKO_INVALID_QUEUE, + CVMX_PKO_INVALID_PRIORITY, + CVMX_PKO_NO_MEMORY, + CVMX_PKO_PORT_ALREADY_SETUP, + CVMX_PKO_CMD_QUEUE_INIT_ERROR +} cvmx_pko_status_t; + +enum cvmx_pow_tag_type { + CVMX_POW_TAG_TYPE_ORDERED = 0L, + CVMX_POW_TAG_TYPE_ATOMIC = 1L, + CVMX_POW_TAG_TYPE_NULL = 2L, + CVMX_POW_TAG_TYPE_NULL_NULL = 3L +}; + +union cvmx_ipd_ctl_status { + uint64_t u64; + struct cvmx_ipd_ctl_status_s { + uint64_t reserved_18_63:46; + uint64_t use_sop:1; + uint64_t rst_done:1; + uint64_t clken:1; + uint64_t no_wptr:1; + uint64_t pq_apkt:1; + uint64_t pq_nabuf:1; + uint64_t ipd_full:1; + uint64_t pkt_off:1; + uint64_t len_m8:1; + uint64_t reset:1; + uint64_t addpkt:1; + uint64_t naddbuf:1; + uint64_t pkt_lend:1; + uint64_t wqe_lend:1; + uint64_t pbp_en:1; + uint64_t opc_mode:2; + uint64_t ipd_en:1; + } s; + struct cvmx_ipd_ctl_status_cn30xx { + uint64_t reserved_10_63:54; + uint64_t len_m8:1; + uint64_t reset:1; + uint64_t addpkt:1; + uint64_t naddbuf:1; + uint64_t pkt_lend:1; + uint64_t wqe_lend:1; + uint64_t pbp_en:1; + uint64_t opc_mode:2; + uint64_t ipd_en:1; + } cn30xx; + struct cvmx_ipd_ctl_status_cn38xxp2 { + uint64_t reserved_9_63:55; + uint64_t reset:1; + uint64_t addpkt:1; + uint64_t naddbuf:1; + uint64_t pkt_lend:1; + uint64_t wqe_lend:1; + uint64_t pbp_en:1; + uint64_t opc_mode:2; + uint64_t ipd_en:1; + } cn38xxp2; + struct cvmx_ipd_ctl_status_cn50xx { + uint64_t reserved_15_63:49; + uint64_t no_wptr:1; + uint64_t pq_apkt:1; + uint64_t pq_nabuf:1; + uint64_t ipd_full:1; + uint64_t pkt_off:1; + uint64_t len_m8:1; + uint64_t reset:1; + uint64_t addpkt:1; + uint64_t naddbuf:1; + uint64_t pkt_lend:1; + uint64_t wqe_lend:1; + uint64_t pbp_en:1; + uint64_t opc_mode:2; + uint64_t ipd_en:1; + } cn50xx; + struct cvmx_ipd_ctl_status_cn58xx { + uint64_t reserved_12_63:52; + uint64_t ipd_full:1; + uint64_t pkt_off:1; + uint64_t len_m8:1; + uint64_t reset:1; + uint64_t addpkt:1; + uint64_t naddbuf:1; + uint64_t pkt_lend:1; + uint64_t wqe_lend:1; + uint64_t pbp_en:1; + uint64_t opc_mode:2; + uint64_t ipd_en:1; + } cn58xx; + struct cvmx_ipd_ctl_status_cn63xxp1 { + uint64_t reserved_16_63:48; + uint64_t clken:1; + uint64_t no_wptr:1; + uint64_t pq_apkt:1; + uint64_t pq_nabuf:1; + uint64_t ipd_full:1; + uint64_t pkt_off:1; + uint64_t len_m8:1; + uint64_t reset:1; + uint64_t addpkt:1; + uint64_t naddbuf:1; + uint64_t pkt_lend:1; + uint64_t wqe_lend:1; + uint64_t pbp_en:1; + uint64_t opc_mode:2; + uint64_t ipd_en:1; + } cn63xxp1; +}; + +union cvmx_ipd_sub_port_fcs { + uint64_t u64; + struct cvmx_ipd_sub_port_fcs_s { + uint64_t port_bit:32; + uint64_t reserved_32_35:4; + uint64_t port_bit2:4; + uint64_t reserved_40_63:24; + } s; + struct cvmx_ipd_sub_port_fcs_cn30xx { + uint64_t port_bit:3; + uint64_t reserved_3_63:61; + } cn30xx; + struct cvmx_ipd_sub_port_fcs_cn38xx { + uint64_t port_bit:32; + uint64_t reserved_32_63:32; + } cn38xx; +}; + +union cvmx_ipd_sub_port_qos_cnt { + uint64_t u64; + struct cvmx_ipd_sub_port_qos_cnt_s { + uint64_t cnt:32; + uint64_t port_qos:9; + uint64_t reserved_41_63:23; + } s; +}; +typedef struct { + uint32_t dropped_octets; + uint32_t dropped_packets; + uint32_t pci_raw_packets; + uint32_t octets; + uint32_t packets; + uint32_t multicast_packets; + uint32_t broadcast_packets; + uint32_t len_64_packets; + uint32_t len_65_127_packets; + uint32_t len_128_255_packets; + uint32_t len_256_511_packets; + uint32_t len_512_1023_packets; + uint32_t len_1024_1518_packets; + uint32_t len_1519_max_packets; + uint32_t fcs_align_err_packets; + uint32_t runt_packets; + uint32_t runt_crc_packets; + uint32_t oversize_packets; + uint32_t oversize_crc_packets; + uint32_t inb_packets; + uint64_t inb_octets; + uint16_t inb_errors; +} cvmx_pip_port_status_t; + +typedef struct { + uint32_t packets; + uint64_t octets; + uint64_t doorbell; +} cvmx_pko_port_status_t; + +union cvmx_pip_frm_len_chkx { + uint64_t u64; + struct cvmx_pip_frm_len_chkx_s { + uint64_t reserved_32_63:32; + uint64_t maxlen:16; + uint64_t minlen:16; + } s; +}; + +union cvmx_gmxx_rxx_frm_ctl { + uint64_t u64; + struct cvmx_gmxx_rxx_frm_ctl_s { + uint64_t pre_chk:1; + uint64_t pre_strp:1; + uint64_t ctl_drp:1; + uint64_t ctl_bck:1; + uint64_t ctl_mcst:1; + uint64_t ctl_smac:1; + uint64_t pre_free:1; + uint64_t vlan_len:1; + uint64_t pad_len:1; + uint64_t pre_align:1; + uint64_t null_dis:1; + uint64_t reserved_11_11:1; + uint64_t ptp_mode:1; + uint64_t reserved_13_63:51; + } s; + struct cvmx_gmxx_rxx_frm_ctl_cn30xx { + uint64_t pre_chk:1; + uint64_t pre_strp:1; + uint64_t ctl_drp:1; + uint64_t ctl_bck:1; + uint64_t ctl_mcst:1; + uint64_t ctl_smac:1; + uint64_t pre_free:1; + uint64_t vlan_len:1; + uint64_t pad_len:1; + uint64_t reserved_9_63:55; + } cn30xx; + struct cvmx_gmxx_rxx_frm_ctl_cn31xx { + uint64_t pre_chk:1; + uint64_t pre_strp:1; + uint64_t ctl_drp:1; + uint64_t ctl_bck:1; + uint64_t ctl_mcst:1; + uint64_t ctl_smac:1; + uint64_t pre_free:1; + uint64_t vlan_len:1; + uint64_t reserved_8_63:56; + } cn31xx; + struct cvmx_gmxx_rxx_frm_ctl_cn50xx { + uint64_t pre_chk:1; + uint64_t pre_strp:1; + uint64_t ctl_drp:1; + uint64_t ctl_bck:1; + uint64_t ctl_mcst:1; + uint64_t ctl_smac:1; + uint64_t pre_free:1; + uint64_t reserved_7_8:2; + uint64_t pre_align:1; + uint64_t null_dis:1; + uint64_t reserved_11_63:53; + } cn50xx; + struct cvmx_gmxx_rxx_frm_ctl_cn56xxp1 { + uint64_t pre_chk:1; + uint64_t pre_strp:1; + uint64_t ctl_drp:1; + uint64_t ctl_bck:1; + uint64_t ctl_mcst:1; + uint64_t ctl_smac:1; + uint64_t pre_free:1; + uint64_t reserved_7_8:2; + uint64_t pre_align:1; + uint64_t reserved_10_63:54; + } cn56xxp1; + struct cvmx_gmxx_rxx_frm_ctl_cn58xx { + uint64_t pre_chk:1; + uint64_t pre_strp:1; + uint64_t ctl_drp:1; + uint64_t ctl_bck:1; + uint64_t ctl_mcst:1; + uint64_t ctl_smac:1; + uint64_t pre_free:1; + uint64_t vlan_len:1; + uint64_t pad_len:1; + uint64_t pre_align:1; + uint64_t null_dis:1; + uint64_t reserved_11_63:53; + } cn58xx; + struct cvmx_gmxx_rxx_frm_ctl_cn61xx { + uint64_t pre_chk:1; + uint64_t pre_strp:1; + uint64_t ctl_drp:1; + uint64_t ctl_bck:1; + uint64_t ctl_mcst:1; + uint64_t ctl_smac:1; + uint64_t pre_free:1; + uint64_t reserved_7_8:2; + uint64_t pre_align:1; + uint64_t null_dis:1; + uint64_t reserved_11_11:1; + uint64_t ptp_mode:1; + uint64_t reserved_13_63:51; + } cn61xx; +}; + +union cvmx_gmxx_rxx_int_reg { + uint64_t u64; + struct cvmx_gmxx_rxx_int_reg_s { + uint64_t minerr:1; + uint64_t carext:1; + uint64_t maxerr:1; + uint64_t jabber:1; + uint64_t fcserr:1; + uint64_t alnerr:1; + uint64_t lenerr:1; + uint64_t rcverr:1; + uint64_t skperr:1; + uint64_t niberr:1; + uint64_t ovrerr:1; + uint64_t pcterr:1; + uint64_t rsverr:1; + uint64_t falerr:1; + uint64_t coldet:1; + uint64_t ifgerr:1; + uint64_t phy_link:1; + uint64_t phy_spd:1; + uint64_t phy_dupx:1; + uint64_t pause_drp:1; + uint64_t loc_fault:1; + uint64_t rem_fault:1; + uint64_t bad_seq:1; + uint64_t bad_term:1; + uint64_t unsop:1; + uint64_t uneop:1; + uint64_t undat:1; + uint64_t hg2fld:1; + uint64_t hg2cc:1; + uint64_t reserved_29_63:35; + } s; + struct cvmx_gmxx_rxx_int_reg_cn30xx { + uint64_t minerr:1; + uint64_t carext:1; + uint64_t maxerr:1; + uint64_t jabber:1; + uint64_t fcserr:1; + uint64_t alnerr:1; + uint64_t lenerr:1; + uint64_t rcverr:1; + uint64_t skperr:1; + uint64_t niberr:1; + uint64_t ovrerr:1; + uint64_t pcterr:1; + uint64_t rsverr:1; + uint64_t falerr:1; + uint64_t coldet:1; + uint64_t ifgerr:1; + uint64_t phy_link:1; + uint64_t phy_spd:1; + uint64_t phy_dupx:1; + uint64_t reserved_19_63:45; + } cn30xx; + struct cvmx_gmxx_rxx_int_reg_cn50xx { + uint64_t reserved_0_0:1; + uint64_t carext:1; + uint64_t reserved_2_2:1; + uint64_t jabber:1; + uint64_t fcserr:1; + uint64_t alnerr:1; + uint64_t reserved_6_6:1; + uint64_t rcverr:1; + uint64_t skperr:1; + uint64_t niberr:1; + uint64_t ovrerr:1; + uint64_t pcterr:1; + uint64_t rsverr:1; + uint64_t falerr:1; + uint64_t coldet:1; + uint64_t ifgerr:1; + uint64_t phy_link:1; + uint64_t phy_spd:1; + uint64_t phy_dupx:1; + uint64_t pause_drp:1; + uint64_t reserved_20_63:44; + } cn50xx; + struct cvmx_gmxx_rxx_int_reg_cn52xx { + uint64_t reserved_0_0:1; + uint64_t carext:1; + uint64_t reserved_2_2:1; + uint64_t jabber:1; + uint64_t fcserr:1; + uint64_t reserved_5_6:2; + uint64_t rcverr:1; + uint64_t skperr:1; + uint64_t reserved_9_9:1; + uint64_t ovrerr:1; + uint64_t pcterr:1; + uint64_t rsverr:1; + uint64_t falerr:1; + uint64_t coldet:1; + uint64_t ifgerr:1; + uint64_t reserved_16_18:3; + uint64_t pause_drp:1; + uint64_t loc_fault:1; + uint64_t rem_fault:1; + uint64_t bad_seq:1; + uint64_t bad_term:1; + uint64_t unsop:1; + uint64_t uneop:1; + uint64_t undat:1; + uint64_t hg2fld:1; + uint64_t hg2cc:1; + uint64_t reserved_29_63:35; + } cn52xx; + struct cvmx_gmxx_rxx_int_reg_cn56xxp1 { + uint64_t reserved_0_0:1; + uint64_t carext:1; + uint64_t reserved_2_2:1; + uint64_t jabber:1; + uint64_t fcserr:1; + uint64_t reserved_5_6:2; + uint64_t rcverr:1; + uint64_t skperr:1; + uint64_t reserved_9_9:1; + uint64_t ovrerr:1; + uint64_t pcterr:1; + uint64_t rsverr:1; + uint64_t falerr:1; + uint64_t coldet:1; + uint64_t ifgerr:1; + uint64_t reserved_16_18:3; + uint64_t pause_drp:1; + uint64_t loc_fault:1; + uint64_t rem_fault:1; + uint64_t bad_seq:1; + uint64_t bad_term:1; + uint64_t unsop:1; + uint64_t uneop:1; + uint64_t undat:1; + uint64_t reserved_27_63:37; + } cn56xxp1; + struct cvmx_gmxx_rxx_int_reg_cn58xx { + uint64_t minerr:1; + uint64_t carext:1; + uint64_t maxerr:1; + uint64_t jabber:1; + uint64_t fcserr:1; + uint64_t alnerr:1; + uint64_t lenerr:1; + uint64_t rcverr:1; + uint64_t skperr:1; + uint64_t niberr:1; + uint64_t ovrerr:1; + uint64_t pcterr:1; + uint64_t rsverr:1; + uint64_t falerr:1; + uint64_t coldet:1; + uint64_t ifgerr:1; + uint64_t phy_link:1; + uint64_t phy_spd:1; + uint64_t phy_dupx:1; + uint64_t pause_drp:1; + uint64_t reserved_20_63:44; + } cn58xx; + struct cvmx_gmxx_rxx_int_reg_cn61xx { + uint64_t minerr:1; + uint64_t carext:1; + uint64_t reserved_2_2:1; + uint64_t jabber:1; + uint64_t fcserr:1; + uint64_t reserved_5_6:2; + uint64_t rcverr:1; + uint64_t skperr:1; + uint64_t reserved_9_9:1; + uint64_t ovrerr:1; + uint64_t pcterr:1; + uint64_t rsverr:1; + uint64_t falerr:1; + uint64_t coldet:1; + uint64_t ifgerr:1; + uint64_t reserved_16_18:3; + uint64_t pause_drp:1; + uint64_t loc_fault:1; + uint64_t rem_fault:1; + uint64_t bad_seq:1; + uint64_t bad_term:1; + uint64_t unsop:1; + uint64_t uneop:1; + uint64_t undat:1; + uint64_t hg2fld:1; + uint64_t hg2cc:1; + uint64_t reserved_29_63:35; + } cn61xx; +}; + +union cvmx_gmxx_prtx_cfg { + uint64_t u64; + struct cvmx_gmxx_prtx_cfg_s { + uint64_t reserved_22_63:42; + uint64_t pknd:6; + uint64_t reserved_14_15:2; + uint64_t tx_idle:1; + uint64_t rx_idle:1; + uint64_t reserved_9_11:3; + uint64_t speed_msb:1; + uint64_t reserved_4_7:4; + uint64_t slottime:1; + uint64_t duplex:1; + uint64_t speed:1; + uint64_t en:1; + } s; + struct cvmx_gmxx_prtx_cfg_cn30xx { + uint64_t reserved_4_63:60; + uint64_t slottime:1; + uint64_t duplex:1; + uint64_t speed:1; + uint64_t en:1; + } cn30xx; + struct cvmx_gmxx_prtx_cfg_cn52xx { + uint64_t reserved_14_63:50; + uint64_t tx_idle:1; + uint64_t rx_idle:1; + uint64_t reserved_9_11:3; + uint64_t speed_msb:1; + uint64_t reserved_4_7:4; + uint64_t slottime:1; + uint64_t duplex:1; + uint64_t speed:1; + uint64_t en:1; + } cn52xx; +}; + +union cvmx_gmxx_rxx_adr_ctl { + uint64_t u64; + struct cvmx_gmxx_rxx_adr_ctl_s { + uint64_t reserved_4_63:60; + uint64_t cam_mode:1; + uint64_t mcst:2; + uint64_t bcst:1; + } s; +}; + +union cvmx_pip_prt_tagx { + uint64_t u64; + struct cvmx_pip_prt_tagx_s { + uint64_t reserved_54_63:10; + uint64_t portadd_en:1; + uint64_t inc_hwchk:1; + uint64_t reserved_50_51:2; + uint64_t grptagbase_msb:2; + uint64_t reserved_46_47:2; + uint64_t grptagmask_msb:2; + uint64_t reserved_42_43:2; + uint64_t grp_msb:2; + uint64_t grptagbase:4; + uint64_t grptagmask:4; + uint64_t grptag:1; + uint64_t grptag_mskip:1; + uint64_t tag_mode:2; + uint64_t inc_vs:2; + uint64_t inc_vlan:1; + uint64_t inc_prt_flag:1; + uint64_t ip6_dprt_flag:1; + uint64_t ip4_dprt_flag:1; + uint64_t ip6_sprt_flag:1; + uint64_t ip4_sprt_flag:1; + uint64_t ip6_nxth_flag:1; + uint64_t ip4_pctl_flag:1; + uint64_t ip6_dst_flag:1; + uint64_t ip4_dst_flag:1; + uint64_t ip6_src_flag:1; + uint64_t ip4_src_flag:1; + uint64_t tcp6_tag_type:2; + uint64_t tcp4_tag_type:2; + uint64_t ip6_tag_type:2; + uint64_t ip4_tag_type:2; + uint64_t non_tag_type:2; + uint64_t grp:4; + } s; + struct cvmx_pip_prt_tagx_cn30xx { + uint64_t reserved_40_63:24; + uint64_t grptagbase:4; + uint64_t grptagmask:4; + uint64_t grptag:1; + uint64_t reserved_30_30:1; + uint64_t tag_mode:2; + uint64_t inc_vs:2; + uint64_t inc_vlan:1; + uint64_t inc_prt_flag:1; + uint64_t ip6_dprt_flag:1; + uint64_t ip4_dprt_flag:1; + uint64_t ip6_sprt_flag:1; + uint64_t ip4_sprt_flag:1; + uint64_t ip6_nxth_flag:1; + uint64_t ip4_pctl_flag:1; + uint64_t ip6_dst_flag:1; + uint64_t ip4_dst_flag:1; + uint64_t ip6_src_flag:1; + uint64_t ip4_src_flag:1; + uint64_t tcp6_tag_type:2; + uint64_t tcp4_tag_type:2; + uint64_t ip6_tag_type:2; + uint64_t ip4_tag_type:2; + uint64_t non_tag_type:2; + uint64_t grp:4; + } cn30xx; + struct cvmx_pip_prt_tagx_cn50xx { + uint64_t reserved_40_63:24; + uint64_t grptagbase:4; + uint64_t grptagmask:4; + uint64_t grptag:1; + uint64_t grptag_mskip:1; + uint64_t tag_mode:2; + uint64_t inc_vs:2; + uint64_t inc_vlan:1; + uint64_t inc_prt_flag:1; + uint64_t ip6_dprt_flag:1; + uint64_t ip4_dprt_flag:1; + uint64_t ip6_sprt_flag:1; + uint64_t ip4_sprt_flag:1; + uint64_t ip6_nxth_flag:1; + uint64_t ip4_pctl_flag:1; + uint64_t ip6_dst_flag:1; + uint64_t ip4_dst_flag:1; + uint64_t ip6_src_flag:1; + uint64_t ip4_src_flag:1; + uint64_t tcp6_tag_type:2; + uint64_t tcp4_tag_type:2; + uint64_t ip6_tag_type:2; + uint64_t ip4_tag_type:2; + uint64_t non_tag_type:2; + uint64_t grp:4; + } cn50xx; +}; + +union cvmx_spxx_int_reg { + uint64_t u64; + struct cvmx_spxx_int_reg_s { + uint64_t reserved_32_63:32; + uint64_t spf:1; + uint64_t reserved_12_30:19; + uint64_t calerr:1; + uint64_t syncerr:1; + uint64_t diperr:1; + uint64_t tpaovr:1; + uint64_t rsverr:1; + uint64_t drwnng:1; + uint64_t clserr:1; + uint64_t spiovr:1; + uint64_t reserved_2_3:2; + uint64_t abnorm:1; + uint64_t prtnxa:1; + } s; +}; + +union cvmx_spxx_int_msk { + uint64_t u64; + struct cvmx_spxx_int_msk_s { + uint64_t reserved_12_63:52; + uint64_t calerr:1; + uint64_t syncerr:1; + uint64_t diperr:1; + uint64_t tpaovr:1; + uint64_t rsverr:1; + uint64_t drwnng:1; + uint64_t clserr:1; + uint64_t spiovr:1; + uint64_t reserved_2_3:2; + uint64_t abnorm:1; + uint64_t prtnxa:1; + } s; +}; + +union cvmx_pow_wq_int { + uint64_t u64; + struct cvmx_pow_wq_int_s { + uint64_t wq_int:16; + uint64_t iq_dis:16; + uint64_t reserved_32_63:32; + } s; +}; + +union cvmx_sso_wq_int_thrx { + uint64_t u64; + struct { + uint64_t iq_thr:12; + uint64_t reserved_12_13:2; + uint64_t ds_thr:12; + uint64_t reserved_26_27:2; + uint64_t tc_thr:4; + uint64_t tc_en:1; + uint64_t reserved_33_63:31; + } s; +}; + +union cvmx_stxx_int_reg { + uint64_t u64; + struct cvmx_stxx_int_reg_s { + uint64_t reserved_9_63:55; + uint64_t syncerr:1; + uint64_t frmerr:1; + uint64_t unxfrm:1; + uint64_t nosync:1; + uint64_t diperr:1; + uint64_t datovr:1; + uint64_t ovrbst:1; + uint64_t calpar1:1; + uint64_t calpar0:1; + } s; +}; + +union cvmx_stxx_int_msk { + uint64_t u64; + struct cvmx_stxx_int_msk_s { + uint64_t reserved_8_63:56; + uint64_t frmerr:1; + uint64_t unxfrm:1; + uint64_t nosync:1; + uint64_t diperr:1; + uint64_t datovr:1; + uint64_t ovrbst:1; + uint64_t calpar1:1; + uint64_t calpar0:1; + } s; +}; + +union cvmx_pow_wq_int_pc { + uint64_t u64; + struct cvmx_pow_wq_int_pc_s { + uint64_t reserved_0_7:8; + uint64_t pc_thr:20; + uint64_t reserved_28_31:4; + uint64_t pc:28; + uint64_t reserved_60_63:4; + } s; +}; + +union cvmx_pow_wq_int_thrx { + uint64_t u64; + struct cvmx_pow_wq_int_thrx_s { + uint64_t reserved_29_63:35; + uint64_t tc_en:1; + uint64_t tc_thr:4; + uint64_t reserved_23_23:1; + uint64_t ds_thr:11; + uint64_t reserved_11_11:1; + uint64_t iq_thr:11; + } s; + struct cvmx_pow_wq_int_thrx_cn30xx { + uint64_t reserved_29_63:35; + uint64_t tc_en:1; + uint64_t tc_thr:4; + uint64_t reserved_18_23:6; + uint64_t ds_thr:6; + uint64_t reserved_6_11:6; + uint64_t iq_thr:6; + } cn30xx; + struct cvmx_pow_wq_int_thrx_cn31xx { + uint64_t reserved_29_63:35; + uint64_t tc_en:1; + uint64_t tc_thr:4; + uint64_t reserved_20_23:4; + uint64_t ds_thr:8; + uint64_t reserved_8_11:4; + uint64_t iq_thr:8; + } cn31xx; + struct cvmx_pow_wq_int_thrx_cn52xx { + uint64_t reserved_29_63:35; + uint64_t tc_en:1; + uint64_t tc_thr:4; + uint64_t reserved_21_23:3; + uint64_t ds_thr:9; + uint64_t reserved_9_11:3; + uint64_t iq_thr:9; + } cn52xx; + struct cvmx_pow_wq_int_thrx_cn63xx { + uint64_t reserved_29_63:35; + uint64_t tc_en:1; + uint64_t tc_thr:4; + uint64_t reserved_22_23:2; + uint64_t ds_thr:10; + uint64_t reserved_10_11:2; + uint64_t iq_thr:10; + } cn63xx; +}; + +union cvmx_npi_rsl_int_blocks { + uint64_t u64; + struct cvmx_npi_rsl_int_blocks_s { + uint64_t reserved_32_63:32; + uint64_t rint_31:1; + uint64_t iob:1; + uint64_t reserved_28_29:2; + uint64_t rint_27:1; + uint64_t rint_26:1; + uint64_t rint_25:1; + uint64_t rint_24:1; + uint64_t asx1:1; + uint64_t asx0:1; + uint64_t rint_21:1; + uint64_t pip:1; + uint64_t spx1:1; + uint64_t spx0:1; + uint64_t lmc:1; + uint64_t l2c:1; + uint64_t rint_15:1; + uint64_t reserved_13_14:2; + uint64_t pow:1; + uint64_t tim:1; + uint64_t pko:1; + uint64_t ipd:1; + uint64_t rint_8:1; + uint64_t zip:1; + uint64_t dfa:1; + uint64_t fpa:1; + uint64_t key:1; + uint64_t npi:1; + uint64_t gmx1:1; + uint64_t gmx0:1; + uint64_t mio:1; + } s; + struct cvmx_npi_rsl_int_blocks_cn30xx { + uint64_t reserved_32_63:32; + uint64_t rint_31:1; + uint64_t iob:1; + uint64_t rint_29:1; + uint64_t rint_28:1; + uint64_t rint_27:1; + uint64_t rint_26:1; + uint64_t rint_25:1; + uint64_t rint_24:1; + uint64_t asx1:1; + uint64_t asx0:1; + uint64_t rint_21:1; + uint64_t pip:1; + uint64_t spx1:1; + uint64_t spx0:1; + uint64_t lmc:1; + uint64_t l2c:1; + uint64_t rint_15:1; + uint64_t rint_14:1; + uint64_t usb:1; + uint64_t pow:1; + uint64_t tim:1; + uint64_t pko:1; + uint64_t ipd:1; + uint64_t rint_8:1; + uint64_t zip:1; + uint64_t dfa:1; + uint64_t fpa:1; + uint64_t key:1; + uint64_t npi:1; + uint64_t gmx1:1; + uint64_t gmx0:1; + uint64_t mio:1; + } cn30xx; + struct cvmx_npi_rsl_int_blocks_cn38xx { + uint64_t reserved_32_63:32; + uint64_t rint_31:1; + uint64_t iob:1; + uint64_t rint_29:1; + uint64_t rint_28:1; + uint64_t rint_27:1; + uint64_t rint_26:1; + uint64_t rint_25:1; + uint64_t rint_24:1; + uint64_t asx1:1; + uint64_t asx0:1; + uint64_t rint_21:1; + uint64_t pip:1; + uint64_t spx1:1; + uint64_t spx0:1; + uint64_t lmc:1; + uint64_t l2c:1; + uint64_t rint_15:1; + uint64_t rint_14:1; + uint64_t rint_13:1; + uint64_t pow:1; + uint64_t tim:1; + uint64_t pko:1; + uint64_t ipd:1; + uint64_t rint_8:1; + uint64_t zip:1; + uint64_t dfa:1; + uint64_t fpa:1; + uint64_t key:1; + uint64_t npi:1; + uint64_t gmx1:1; + uint64_t gmx0:1; + uint64_t mio:1; + } cn38xx; + struct cvmx_npi_rsl_int_blocks_cn50xx { + uint64_t reserved_31_63:33; + uint64_t iob:1; + uint64_t lmc1:1; + uint64_t agl:1; + uint64_t reserved_24_27:4; + uint64_t asx1:1; + uint64_t asx0:1; + uint64_t reserved_21_21:1; + uint64_t pip:1; + uint64_t spx1:1; + uint64_t spx0:1; + uint64_t lmc:1; + uint64_t l2c:1; + uint64_t reserved_15_15:1; + uint64_t rad:1; + uint64_t usb:1; + uint64_t pow:1; + uint64_t tim:1; + uint64_t pko:1; + uint64_t ipd:1; + uint64_t reserved_8_8:1; + uint64_t zip:1; + uint64_t dfa:1; + uint64_t fpa:1; + uint64_t key:1; + uint64_t npi:1; + uint64_t gmx1:1; + uint64_t gmx0:1; + uint64_t mio:1; + } cn50xx; +}; + +typedef union { + uint64_t u64; + struct { + uint64_t total_bytes:16; + uint64_t segs:6; + uint64_t dontfree:1; + uint64_t ignore_i:1; + uint64_t ipoffp1:7; + uint64_t gather:1; + uint64_t rsp:1; + uint64_t wqp:1; + uint64_t n2:1; + uint64_t le:1; + uint64_t reg0:11; + uint64_t subone0:1; + uint64_t reg1:11; + uint64_t subone1:1; + uint64_t size0:2; + uint64_t size1:2; + } s; +} cvmx_pko_command_word0_t; + +union cvmx_ciu_timx { + uint64_t u64; + struct cvmx_ciu_timx_s { + uint64_t reserved_37_63:27; + uint64_t one_shot:1; + uint64_t len:36; + } s; +}; + +union cvmx_gmxx_rxx_rx_inbnd { + uint64_t u64; + struct cvmx_gmxx_rxx_rx_inbnd_s { + uint64_t status:1; + uint64_t speed:2; + uint64_t duplex:1; + uint64_t reserved_4_63:60; + } s; +}; + +static inline int32_t cvmx_fau_fetch_and_add32(cvmx_fau_reg_32_t reg, + int32_t value) +{ + return value; +} + +static inline void cvmx_fau_atomic_add32(cvmx_fau_reg_32_t reg, int32_t value) +{ } + +static inline void cvmx_fau_atomic_write32(cvmx_fau_reg_32_t reg, int32_t value) +{ } + +static inline uint64_t cvmx_scratch_read64(uint64_t address) +{ + return 0; +} + +static inline void cvmx_scratch_write64(uint64_t address, uint64_t value) +{ } + +static inline int cvmx_wqe_get_grp(cvmx_wqe_t *work) +{ + return 0; +} + +static inline void *cvmx_phys_to_ptr(uint64_t physical_address) +{ + return (void *)(physical_address); +} + +static inline uint64_t cvmx_ptr_to_phys(void *ptr) +{ + return (unsigned long)ptr; +} + +static inline int cvmx_helper_get_interface_num(int ipd_port) +{ + return ipd_port; +} + +static inline int cvmx_helper_get_interface_index_num(int ipd_port) +{ + return ipd_port; +} + +static inline void cvmx_fpa_enable(void) +{ } + +static inline uint64_t cvmx_read_csr(uint64_t csr_addr) +{ + return 0; +} + +static inline void cvmx_write_csr(uint64_t csr_addr, uint64_t val) +{ } + +static inline int cvmx_helper_setup_red(int pass_thresh, int drop_thresh) +{ + return 0; +} + +static inline void *cvmx_fpa_alloc(uint64_t pool) +{ + return NULL; +} + +static inline void cvmx_fpa_free(void *ptr, uint64_t pool, + uint64_t num_cache_lines) +{ } + +static inline int octeon_is_simulation(void) +{ + return 1; +} + +static inline void cvmx_pip_get_port_status(uint64_t port_num, uint64_t clear, + cvmx_pip_port_status_t *status) +{ } + +static inline void cvmx_pko_get_port_status(uint64_t port_num, uint64_t clear, + cvmx_pko_port_status_t *status) +{ } + +static inline cvmx_helper_interface_mode_t cvmx_helper_interface_get_mode(int + interface) +{ + return 0; +} + +static inline cvmx_helper_link_info_t cvmx_helper_link_get(int ipd_port) +{ + cvmx_helper_link_info_t ret = { .u64 = 0 }; + + return ret; +} + +static inline int cvmx_helper_link_set(int ipd_port, + cvmx_helper_link_info_t link_info) +{ + return 0; +} + +static inline int cvmx_helper_initialize_packet_io_global(void) +{ + return 0; +} + +static inline int cvmx_helper_get_number_of_interfaces(void) +{ + return 2; +} + +static inline int cvmx_helper_ports_on_interface(int interface) +{ + return 1; +} + +static inline int cvmx_helper_get_ipd_port(int interface, int port) +{ + return 0; +} + +static inline int cvmx_helper_ipd_and_packet_input_enable(void) +{ + return 0; +} + +static inline void cvmx_ipd_disable(void) +{ } + +static inline void cvmx_ipd_free_ptr(void) +{ } + +static inline void cvmx_pko_disable(void) +{ } + +static inline void cvmx_pko_shutdown(void) +{ } + +static inline int cvmx_pko_get_base_queue_per_core(int port, int core) +{ + return port; +} + +static inline int cvmx_pko_get_base_queue(int port) +{ + return port; +} + +static inline int cvmx_pko_get_num_queues(int port) +{ + return port; +} + +static inline unsigned int cvmx_get_core_num(void) +{ + return 0; +} + +static inline void cvmx_pow_work_request_async_nocheck(int scr_addr, + cvmx_pow_wait_t wait) +{ } + +static inline void cvmx_pow_work_request_async(int scr_addr, + cvmx_pow_wait_t wait) +{ } + +static inline cvmx_wqe_t *cvmx_pow_work_response_async(int scr_addr) +{ + cvmx_wqe_t *wqe = (void *)(unsigned long)scr_addr; + + return wqe; +} + +static inline cvmx_wqe_t *cvmx_pow_work_request_sync(cvmx_pow_wait_t wait) +{ + return (void *)(unsigned long)wait; +} + +static inline int cvmx_spi_restart_interface(int interface, + cvmx_spi_mode_t mode, int timeout) +{ + return 0; +} + +static inline void cvmx_fau_async_fetch_and_add32(uint64_t scraddr, + cvmx_fau_reg_32_t reg, + int32_t value) +{ } + +static inline union cvmx_gmxx_rxx_rx_inbnd cvmx_spi4000_check_speed( + int interface, + int port) +{ + union cvmx_gmxx_rxx_rx_inbnd r; + r.u64 = 0; + return r; +} + +static inline void cvmx_pko_send_packet_prepare(uint64_t port, uint64_t queue, + cvmx_pko_lock_t use_locking) +{ } + +static inline cvmx_pko_status_t cvmx_pko_send_packet_finish(uint64_t port, + uint64_t queue, cvmx_pko_command_word0_t pko_command, + union cvmx_buf_ptr packet, cvmx_pko_lock_t use_locking) +{ + cvmx_pko_status_t ret = 0; + + return ret; +} + +static inline void cvmx_wqe_set_port(cvmx_wqe_t *work, int port) +{ } + +static inline void cvmx_wqe_set_qos(cvmx_wqe_t *work, int qos) +{ } + +static inline int cvmx_wqe_get_qos(cvmx_wqe_t *work) +{ + return 0; +} + +static inline void cvmx_wqe_set_grp(cvmx_wqe_t *work, int grp) +{ } + +static inline void cvmx_pow_work_submit(cvmx_wqe_t *wqp, uint32_t tag, + enum cvmx_pow_tag_type tag_type, + uint64_t qos, uint64_t grp) +{ } + +#define CVMX_ASXX_RX_CLK_SETX(a, b) ((a)+(b)) +#define CVMX_ASXX_TX_CLK_SETX(a, b) ((a)+(b)) +#define CVMX_CIU_TIMX(a) (a) +#define CVMX_GMXX_RXX_ADR_CAM0(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_ADR_CAM1(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_ADR_CAM2(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_ADR_CAM3(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_ADR_CAM4(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_ADR_CAM5(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_FRM_CTL(a, b) ((a)+(b)) +#define CVMX_GMXX_RXX_INT_REG(a, b) ((a)+(b)) +#define CVMX_GMXX_SMACX(a, b) ((a)+(b)) +#define CVMX_PIP_PRT_TAGX(a) (a) +#define CVMX_POW_PP_GRP_MSKX(a) (a) +#define CVMX_POW_WQ_INT_THRX(a) (a) +#define CVMX_SPXX_INT_MSK(a) (a) +#define CVMX_SPXX_INT_REG(a) (a) +#define CVMX_SSO_PPX_GRP_MSK(a) (a) +#define CVMX_SSO_WQ_INT_THRX(a) (a) +#define CVMX_STXX_INT_MSK(a) (a) +#define CVMX_STXX_INT_REG(a) (a) diff --git a/drivers/staging/qlge/Kconfig b/drivers/staging/qlge/Kconfig new file mode 100644 index 000000000000..a3cb25a3ab80 --- /dev/null +++ b/drivers/staging/qlge/Kconfig @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +config QLGE + tristate "QLogic QLGE 10Gb Ethernet Driver Support" + depends on ETHERNET && PCI + help + This driver supports QLogic ISP8XXX 10Gb Ethernet cards. + + To compile this driver as a module, choose M here. The module will be + called qlge. diff --git a/drivers/net/ethernet/qlogic/qlge/Makefile b/drivers/staging/qlge/Makefile index 1dc2568e820c..1dc2568e820c 100644 --- a/drivers/net/ethernet/qlogic/qlge/Makefile +++ b/drivers/staging/qlge/Makefile diff --git a/drivers/staging/qlge/TODO b/drivers/staging/qlge/TODO new file mode 100644 index 000000000000..51c509084e80 --- /dev/null +++ b/drivers/staging/qlge/TODO @@ -0,0 +1,46 @@ +* reception stalls permanently (until admin intervention) if the rx buffer + queues become empty because of allocation failures (ex. under memory + pressure) +* commit 7c734359d350 ("qlge: Size RX buffers based on MTU.", v2.6.33-rc1) + introduced dead code in the receive routines, which should be rewritten + anyways by the admission of the author himself, see the comment above + ql_build_rx_skb(). That function is now used exclusively to handle packets + that underwent header splitting but it still contains code to handle non + split cases. +* truesize accounting is incorrect (ex: a 9000B frame has skb->truesize 10280 + while containing two frags of order-1 allocations, ie. >16K) +* while in that area, using two 8k buffers to store one 9k frame is a poor + choice of buffer size. +* in the "chain of large buffers" case, the driver uses an skb allocated with + head room but only puts data in the frags. +* rename "rx" queues to "completion" queues. Calling tx completion queues "rx + queues" is confusing. +* struct rx_ring is used for rx and tx completions, with some members relevant + to one case only +* there is an inordinate amount of disparate debugging code, most of which is + of questionable value. In particular, qlge_dbg.c has hundreds of lines of + code bitrotting away in ifdef land (doesn't compile since commit + 18c49b91777c ("qlge: do vlan cleanup", v3.1-rc1), 8 years ago). +* triggering an ethtool regdump will hexdump a 176k struct to dmesg depending + on some module parameters. +* the flow control implementation in firmware is buggy (sends a flood of pause + frames, resets the link, device and driver buffer queues become + desynchronized), disable it by default +* some structures are initialized redundantly (ex. memset 0 after + alloc_etherdev()) +* the driver has a habit of using runtime checks where compile time checks are + possible (ex. ql_free_rx_buffers(), ql_alloc_rx_buffers()) +* reorder struct members to avoid holes if it doesn't impact performance +* in terms of namespace, the driver uses either qlge_, ql_ (used by + other qlogic drivers, with clashes, ex: ql_sem_spinlock) or nothing (with + clashes, ex: struct ob_mac_iocb_req). Rename everything to use the "qlge_" + prefix. +* avoid legacy/deprecated apis (ex. replace pci_dma_*, replace pci_enable_msi, + use pci_iomap) +* some "while" loops could be rewritten with simple "for", ex. + ql_wait_reg_rdy(), ql_start_rx_ring()) +* remove duplicate and useless comments +* fix weird line wrapping (all over, ex. the ql_set_routing_reg() calls in + qlge_set_multicast_list()). +* fix weird indentation (all over, ex. the for loops in qlge_get_stats()) +* fix checkpatch issues diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/staging/qlge/qlge.h index ad7c5eb8a3b6..ad7c5eb8a3b6 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/staging/qlge/qlge.h diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/staging/qlge/qlge_dbg.c index 31389ab8bdf7..31389ab8bdf7 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c +++ b/drivers/staging/qlge/qlge_dbg.c diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/staging/qlge/qlge_ethtool.c index a6886cc5654c..a6886cc5654c 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c +++ b/drivers/staging/qlge/qlge_ethtool.c diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/staging/qlge/qlge_main.c index 6cae33072496..6cae33072496 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/staging/qlge/qlge_main.c diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c b/drivers/staging/qlge/qlge_mpi.c index 957c72985a06..957c72985a06 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c +++ b/drivers/staging/qlge/qlge_mpi.c diff --git a/drivers/staging/unisys/visornic/visornic_main.c b/drivers/staging/unisys/visornic/visornic_main.c index 40dd573e73c3..1d1440d43002 100644 --- a/drivers/staging/unisys/visornic/visornic_main.c +++ b/drivers/staging/unisys/visornic/visornic_main.c @@ -284,9 +284,9 @@ static int visor_copy_fragsinfo_from_skb(struct sk_buff *skb, for (frag = 0; frag < numfrags; frag++) { count = add_physinfo_entries(page_to_pfn( skb_frag_page(&skb_shinfo(skb)->frags[frag])), - skb_shinfo(skb)->frags[frag].page_offset, - skb_shinfo(skb)->frags[frag].size, count, - frags_max, frags); + skb_frag_off(&skb_shinfo(skb)->frags[frag]), + skb_frag_size(&skb_shinfo(skb)->frags[frag]), + count, frags_max, frags); /* add_physinfo_entries only returns * zero if the frags array is out of room * That should never happen because we diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index 24309d937d8c..fcdc4211e3c2 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -899,9 +899,9 @@ cxgbit_handle_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr, skb_frag_t *dfrag = &ssi->frags[pdu_cb->dfrag_idx]; sg_init_table(&ccmd->sg, 1); - sg_set_page(&ccmd->sg, dfrag->page.p, skb_frag_size(dfrag), - dfrag->page_offset); - get_page(dfrag->page.p); + sg_set_page(&ccmd->sg, skb_frag_page(dfrag), + skb_frag_size(dfrag), skb_frag_off(dfrag)); + get_page(skb_frag_page(dfrag)); cmd->se_cmd.t_data_sg = &ccmd->sg; cmd->se_cmd.t_data_nents = 1; @@ -1403,7 +1403,8 @@ static void cxgbit_lro_skb_dump(struct sk_buff *skb) pdu_cb->ddigest, pdu_cb->frags); for (i = 0; i < ssi->nr_frags; i++) pr_info("skb 0x%p, frag %d, off %u, sz %u.\n", - skb, i, ssi->frags[i].page_offset, ssi->frags[i].size); + skb, i, skb_frag_off(&ssi->frags[i]), + skb_frag_size(&ssi->frags[i])); } static void cxgbit_lro_hskb_reset(struct cxgbit_sock *csk) @@ -1447,7 +1448,7 @@ cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx) hpdu_cb->frags++; hpdu_cb->hfrag_idx = hfrag_idx; - len = hssi->frags[hfrag_idx].size; + len = skb_frag_size(&hssi->frags[hfrag_idx]); hskb->len += len; hskb->data_len += len; hskb->truesize += len; @@ -1467,7 +1468,7 @@ cxgbit_lro_skb_merge(struct cxgbit_sock *csk, struct sk_buff *skb, u8 pdu_idx) get_page(skb_frag_page(&hssi->frags[dfrag_idx])); - len += hssi->frags[dfrag_idx].size; + len += skb_frag_size(&hssi->frags[dfrag_idx]); hssi->nr_frags++; hpdu_cb->frags++; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 6a50e1d0529c..9f57736fe15e 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -102,7 +102,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, struct iov_iter iov_iter; unsigned out, in; size_t nbytes; - size_t len; + size_t iov_len, payload_len; int head; spin_lock_bh(&vsock->send_pkt_list_lock); @@ -147,8 +147,24 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - len = iov_length(&vq->iov[out], in); - iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len); + iov_len = iov_length(&vq->iov[out], in); + if (iov_len < sizeof(pkt->hdr)) { + virtio_transport_free_pkt(pkt); + vq_err(vq, "Buffer len [%zu] too small\n", iov_len); + break; + } + + iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len); + payload_len = pkt->len - pkt->off; + + /* If the packet is greater than the space available in the + * buffer, we split it using multiple buffers. + */ + if (payload_len > iov_len - sizeof(pkt->hdr)) + payload_len = iov_len - sizeof(pkt->hdr); + + /* Set the correct length in the header */ + pkt->hdr.len = cpu_to_le32(payload_len); nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter); if (nbytes != sizeof(pkt->hdr)) { @@ -157,33 +173,47 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter); - if (nbytes != pkt->len) { + nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len, + &iov_iter); + if (nbytes != payload_len) { virtio_transport_free_pkt(pkt); vq_err(vq, "Faulted on copying pkt buf\n"); break; } - vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len); + vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); added = true; - if (pkt->reply) { - int val; - - val = atomic_dec_return(&vsock->queued_replies); - - /* Do we have resources to resume tx processing? */ - if (val + 1 == tx_vq->num) - restart_tx = true; - } - /* Deliver to monitoring devices all correctly transmitted * packets. */ virtio_transport_deliver_tap_pkt(pkt); - total_len += pkt->len; - virtio_transport_free_pkt(pkt); + pkt->off += payload_len; + total_len += payload_len; + + /* If we didn't send all the payload we can requeue the packet + * to send it with the next available buffer. + */ + if (pkt->off < pkt->len) { + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + } else { + if (pkt->reply) { + int val; + + val = atomic_dec_return(&vsock->queued_replies); + + /* Do we have resources to resume tx + * processing? + */ + if (val + 1 == tx_vq->num) + restart_tx = true; + } + + virtio_transport_free_pkt(pkt); + } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) vhost_signal(&vsock->dev, vq); @@ -329,6 +359,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } + pkt->buf_len = pkt->len; + nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter); if (nbytes != pkt->len) { vq_err(vq, "Expected %u byte payload, got %zu bytes\n", diff --git a/include/Kbuild b/include/Kbuild index c38f0d46b267..af498acb7cd2 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -386,31 +386,6 @@ header-test- += linux/mvebu-pmsu.h header-test- += linux/mxm-wmi.h header-test- += linux/n_r3964.h header-test- += linux/ndctl.h -header-test- += linux/netfilter/ipset/ip_set.h -header-test- += linux/netfilter/ipset/ip_set_bitmap.h -header-test- += linux/netfilter/ipset/ip_set_comment.h -header-test- += linux/netfilter/ipset/ip_set_counter.h -header-test- += linux/netfilter/ipset/ip_set_getport.h -header-test- += linux/netfilter/ipset/ip_set_hash.h -header-test- += linux/netfilter/ipset/ip_set_list.h -header-test- += linux/netfilter/ipset/ip_set_skbinfo.h -header-test- += linux/netfilter/ipset/ip_set_timeout.h -header-test- += linux/netfilter/nf_conntrack_amanda.h -header-test- += linux/netfilter/nf_conntrack_ftp.h -header-test- += linux/netfilter/nf_conntrack_h323.h -header-test- += linux/netfilter/nf_conntrack_h323_asn1.h -header-test- += linux/netfilter/nf_conntrack_irc.h -header-test- += linux/netfilter/nf_conntrack_pptp.h -header-test- += linux/netfilter/nf_conntrack_proto_gre.h -header-test- += linux/netfilter/nf_conntrack_sip.h -header-test- += linux/netfilter/nf_conntrack_snmp.h -header-test- += linux/netfilter/nf_conntrack_tftp.h -header-test- += linux/netfilter/x_tables.h -header-test- += linux/netfilter_arp/arp_tables.h -header-test- += linux/netfilter_bridge/ebtables.h -header-test- += linux/netfilter_ipv4/ip4_tables.h -header-test- += linux/netfilter_ipv4/ip_tables.h -header-test- += linux/netfilter_ipv6/ip6_tables.h header-test- += linux/nfs.h header-test- += linux/nfs_fs_i.h header-test- += linux/nfs_fs_sb.h @@ -874,43 +849,6 @@ header-test- += net/mpls_iptunnel.h header-test- += net/mrp.h header-test- += net/ncsi.h header-test- += net/netevent.h -header-test- += net/netfilter/br_netfilter.h -header-test- += net/netfilter/ipv4/nf_dup_ipv4.h -header-test- += net/netfilter/ipv6/nf_defrag_ipv6.h -header-test- += net/netfilter/ipv6/nf_dup_ipv6.h -header-test- += net/netfilter/nf_conntrack.h -header-test- += net/netfilter/nf_conntrack_acct.h -header-test- += net/netfilter/nf_conntrack_bridge.h -header-test- += net/netfilter/nf_conntrack_core.h -header-test- += net/netfilter/nf_conntrack_count.h -header-test- += net/netfilter/nf_conntrack_ecache.h -header-test- += net/netfilter/nf_conntrack_expect.h -header-test- += net/netfilter/nf_conntrack_extend.h -header-test- += net/netfilter/nf_conntrack_helper.h -header-test- += net/netfilter/nf_conntrack_l4proto.h -header-test- += net/netfilter/nf_conntrack_labels.h -header-test- += net/netfilter/nf_conntrack_seqadj.h -header-test- += net/netfilter/nf_conntrack_synproxy.h -header-test- += net/netfilter/nf_conntrack_timeout.h -header-test- += net/netfilter/nf_conntrack_timestamp.h -header-test- += net/netfilter/nf_conntrack_tuple.h -header-test- += net/netfilter/nf_dup_netdev.h -header-test- += net/netfilter/nf_flow_table.h -header-test- += net/netfilter/nf_nat.h -header-test- += net/netfilter/nf_nat_helper.h -header-test- += net/netfilter/nf_nat_masquerade.h -header-test- += net/netfilter/nf_nat_redirect.h -header-test- += net/netfilter/nf_queue.h -header-test- += net/netfilter/nf_reject.h -header-test- += net/netfilter/nf_synproxy.h -header-test-$(CONFIG_NF_TABLES) += net/netfilter/nf_tables.h -header-test-$(CONFIG_NF_TABLES) += net/netfilter/nf_tables_core.h -header-test-$(CONFIG_NF_TABLES) += net/netfilter/nf_tables_ipv4.h -header-test- += net/netfilter/nf_tables_ipv6.h -header-test-$(CONFIG_NF_TABLES) += net/netfilter/nf_tables_offload.h -header-test- += net/netfilter/nft_fib.h -header-test- += net/netfilter/nft_meta.h -header-test- += net/netfilter/nft_reject.h header-test- += net/netns/can.h header-test- += net/netns/generic.h header-test- += net/netns/ieee802154_6lowpan.h @@ -1140,18 +1078,6 @@ header-test- += uapi/linux/kvm_para.h header-test- += uapi/linux/lightnvm.h header-test- += uapi/linux/mic_common.h header-test- += uapi/linux/mman.h -header-test- += uapi/linux/netfilter/ipset/ip_set_bitmap.h -header-test- += uapi/linux/netfilter/ipset/ip_set_hash.h -header-test- += uapi/linux/netfilter/ipset/ip_set_list.h -header-test- += uapi/linux/netfilter/nf_synproxy.h -header-test- += uapi/linux/netfilter/xt_policy.h -header-test- += uapi/linux/netfilter/xt_set.h -header-test- += uapi/linux/netfilter_arp/arp_tables.h -header-test- += uapi/linux/netfilter_arp/arpt_mangle.h -header-test- += uapi/linux/netfilter_ipv4/ip_tables.h -header-test- += uapi/linux/netfilter_ipv4/ipt_LOG.h -header-test- += uapi/linux/netfilter_ipv6/ip6_tables.h -header-test- += uapi/linux/netfilter_ipv6/ip6t_LOG.h header-test- += uapi/linux/nilfs2_ondisk.h header-test- += uapi/linux/patchkey.h header-test- += uapi/linux/ptrace.h diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 18f4cc2c6acd..f9a506147c8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -713,7 +713,7 @@ struct xdp_buff; struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_insert_ctx(struct bpf_map *map, u32 index); +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -721,7 +721,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); -void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); void __cpu_map_flush(struct bpf_map *map); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -801,8 +800,10 @@ static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, return NULL; } -static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) +static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map, + u32 key) { + return NULL; } static inline void __dev_map_flush(struct bpf_map *map) @@ -834,10 +835,6 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) return NULL; } -static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) -{ -} - static inline void __cpu_map_flush(struct bpf_map *map) { } diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index eec5aeeeaf92..36a9c2325176 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -62,6 +62,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 6099bc18bd0c..708c10d3417a 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/core.h * @@ -57,6 +57,5 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); -extern int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); #endif /* !_CAN_CORE_H */ diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index b3379a97245c..a954def26c0d 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/skb.h * diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8511fadc0935..7d3f2ced92d1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -881,6 +881,14 @@ struct ieee80211_tpc_report_ie { u8 link_margin; } __packed; +#define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) +#define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 +#define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) + +struct ieee80211_addba_ext_ie { + u8 data; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -973,6 +981,8 @@ struct ieee80211_mgmt { __le16 capab; __le16 timeout; __le16 start_seq_num; + /* followed by BA Extension */ + u8 variable[0]; } __packed addba_req; struct{ u8 action_code; @@ -1626,6 +1636,18 @@ struct ieee80211_he_operation { } __packed; /** + * struct ieee80211_he_spr - HE spatial reuse element + * + * This structure is the "HE spatial reuse element" element as + * described in P802.11ax_D4.0 section 9.4.2.241 + */ +struct ieee80211_he_spr { + u8 he_sr_control; + /* Optional 0 to 19 bytes: depends on @he_sr_control */ + u8 optional[0]; +} __packed; + +/** * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field * * This structure is the "MU AC Parameter Record" fields as @@ -2033,8 +2055,8 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the the byte * after the ext ID byte. It is assumed that he_oper_ie has at least - * sizeof(struct ieee80211_he_operation) bytes, checked already in - * ieee802_11_parse_elems_crc() + * sizeof(struct ieee80211_he_operation) bytes, the caller must have + * validated this. * @return the actual size of the IE data (not including header), or 0 on error */ static inline u8 @@ -2063,6 +2085,42 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) return oper_len; } +/* HE Spatial Reuse defines */ +#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT 0x4 +#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT 0x8 + +/* + * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size + * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the the byte + * after the ext ID byte. It is assumed that he_spr_ie has at least + * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated + * this + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_spr_size(const u8 *he_spr_ie) +{ + struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; + u8 spr_len = sizeof(struct ieee80211_he_spr); + u32 he_spr_params; + + /* Make sure the input is not NULL */ + if (!he_spr_ie) + return 0; + + /* Calc required length */ + he_spr_params = le32_to_cpu(he_spr->he_sr_control); + if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) + spr_len++; + if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) + spr_len += 18; + + /* Add the first byte (extension ID) to the total length */ + spr_len++; + + return spr_len; +} + /* Authentication algorithms */ #define WLAN_AUTH_OPEN 0 #define WLAN_AUTH_SHARED_KEY 1 @@ -2485,6 +2543,7 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_HE_OPERATION = 36, WLAN_EID_EXT_UORA = 37, WLAN_EID_EXT_HE_MU_EDCA = 38, + WLAN_EID_EXT_HE_SPR = 39, WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55, WLAN_EID_EXT_NON_INHERITANCE = 56, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0e6da1840c7d..df23f17eed64 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -189,7 +189,6 @@ enum mlx5_coredev_type { }; struct mlx5_field_desc { - struct dentry *dent; int i; }; @@ -242,11 +241,6 @@ struct mlx5_cmd_msg { struct mlx5_cmd_debug { struct dentry *dbg_root; - struct dentry *dbg_in; - struct dentry *dbg_out; - struct dentry *dbg_outlen; - struct dentry *dbg_status; - struct dentry *dbg_run; void *in_msg; void *out_msg; u8 status; @@ -271,8 +265,6 @@ struct mlx5_cmd_stats { u64 sum; u64 n; struct dentry *root; - struct dentry *avg; - struct dentry *count; /* protect command average calculations */ spinlock_t lock; }; @@ -477,6 +469,17 @@ struct mlx5_core_sriov { u16 max_vfs; }; +struct mlx5_fc_pool { + struct mlx5_core_dev *dev; + struct mutex pool_lock; /* protects pool lists */ + struct list_head fully_used; + struct list_head partially_used; + struct list_head unused; + int available_fcs; + int used_fcs; + int threshold; +}; + struct mlx5_fc_stats { spinlock_t counters_idr_lock; /* protects counters_idr */ struct idr counters_idr; @@ -488,6 +491,8 @@ struct mlx5_fc_stats { struct delayed_work work; unsigned long next_query; unsigned long sampling_interval; /* jiffies */ + u32 *bulk_query_out; + struct mlx5_fc_pool fc_pool; }; struct mlx5_events; @@ -959,7 +964,7 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); -int mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, @@ -971,7 +976,7 @@ int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); -int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 46b5ba029802..38a70d16d8d5 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -44,7 +44,6 @@ struct mlx5_eswitch_rep_data { struct mlx5_eswitch_rep { struct mlx5_eswitch_rep_data rep_data[NUM_REP_TYPES]; u16 vport; - u8 hw_id[ETH_ALEN]; u16 vlan; /* Only IB rep is using vport_index */ u16 vport_index; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index f049af3f3cd8..1cb1045ce313 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -126,6 +126,11 @@ struct mlx5_flow_destination { }; }; +struct mod_hdr_tbl { + struct mutex lock; /* protects hlist */ + DECLARE_HASHTABLE(hlist, 8); +}; + struct mlx5_flow_namespace * mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, int n); struct mlx5_flow_namespace * diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b8b570c30b5e..a66ed0abe40e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1040,6 +1040,21 @@ enum { MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, }; +#define MLX5_FC_BULK_SIZE_FACTOR 128 + +enum mlx5_fc_bulk_alloc_bitmask { + MLX5_FC_BULK_128 = (1 << 0), + MLX5_FC_BULK_256 = (1 << 1), + MLX5_FC_BULK_512 = (1 << 2), + MLX5_FC_BULK_1024 = (1 << 3), + MLX5_FC_BULK_2048 = (1 << 4), + MLX5_FC_BULK_4096 = (1 << 5), + MLX5_FC_BULK_8192 = (1 << 6), + MLX5_FC_BULK_16384 = (1 << 7), +}; + +#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1244,7 +1259,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2e0[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_at_300[0x18]; + u8 reserved_at_300[0x10]; + u8 flow_counter_bulk_alloc[0x8]; u8 log_max_mcg[0x8]; u8 reserved_at_320[0x3]; @@ -2766,7 +2782,7 @@ struct mlx5_ifc_traffic_counter_bits { struct mlx5_ifc_tisc_bits { u8 strict_lag_tx_port_affinity[0x1]; u8 tls_en[0x1]; - u8 reserved_at_1[0x2]; + u8 reserved_at_2[0x2]; u8 lag_tx_port_affinity[0x04]; u8 reserved_at_8[0x4]; @@ -2941,6 +2957,13 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, }; +enum { + ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0, + ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, + ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, +}; + struct mlx5_ifc_scheduling_context_bits { u8 element_type[0x8]; u8 reserved_at_8[0x18]; @@ -7817,7 +7840,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x38]; + u8 flow_counter_bulk[0x8]; }; struct mlx5_ifc_add_vxlan_udp_dport_out_bits { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88292953aa6f..55ac223553f8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -332,6 +332,8 @@ struct napi_struct { struct net_device *dev; struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; + struct list_head rx_list; /* Pending GRO_NORMAL skbs */ + int rx_count; /* length of rx_list */ struct hrtimer timer; struct list_head dev_list; struct hlist_node napi_hash_node; @@ -4239,6 +4241,7 @@ extern int dev_weight_rx_bias; extern int dev_weight_tx_bias; extern int dev_rx_weight; extern int dev_tx_weight; +extern int gro_normal_batch; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 12ad9b1853b4..9bc255a8461b 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -452,10 +452,240 @@ bitmap_bytes(u32 a, u32 b) return 4 * ((((b - a + 8) / 8) + 3) / 4); } -#include <linux/netfilter/ipset/ip_set_timeout.h> -#include <linux/netfilter/ipset/ip_set_comment.h> -#include <linux/netfilter/ipset/ip_set_counter.h> -#include <linux/netfilter/ipset/ip_set_skbinfo.h> +/* How often should the gc be run by default */ +#define IPSET_GC_TIME (3 * 60) + +/* Timeout period depending on the timeout value of the given set */ +#define IPSET_GC_PERIOD(timeout) \ + ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) + +/* Entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT 0 + +/* Set is defined with timeout support: timeout value may be 0 */ +#define IPSET_NO_TIMEOUT UINT_MAX + +/* Max timeout value, see msecs_to_jiffies() in jiffies.h */ +#define IPSET_MAX_TIMEOUT (UINT_MAX >> 1)/MSEC_PER_SEC + +#define ip_set_adt_opt_timeout(opt, set) \ +((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout) + +static inline unsigned int +ip_set_timeout_uget(struct nlattr *tb) +{ + unsigned int timeout = ip_set_get_h32(tb); + + /* Normalize to fit into jiffies */ + if (timeout > IPSET_MAX_TIMEOUT) + timeout = IPSET_MAX_TIMEOUT; + + return timeout; +} + +static inline bool +ip_set_timeout_expired(const unsigned long *t) +{ + return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); +} + +static inline void +ip_set_timeout_set(unsigned long *timeout, u32 value) +{ + unsigned long t; + + if (!value) { + *timeout = IPSET_ELEM_PERMANENT; + return; + } + + t = msecs_to_jiffies(value * MSEC_PER_SEC) + jiffies; + if (t == IPSET_ELEM_PERMANENT) + /* Bingo! :-) */ + t--; + *timeout = t; +} + +static inline u32 +ip_set_timeout_get(const unsigned long *timeout) +{ + u32 t; + + if (*timeout == IPSET_ELEM_PERMANENT) + return 0; + + t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; + /* Zero value in userspace means no timeout */ + return t == 0 ? 1 : t; +} + +static inline char* +ip_set_comment_uget(struct nlattr *tb) +{ + return nla_data(tb); +} + +/* Called from uadd only, protected by the set spinlock. + * The kadt functions don't use the comment extensions in any way. + */ +static inline void +ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, + const struct ip_set_ext *ext) +{ + struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); + size_t len = ext->comment ? strlen(ext->comment) : 0; + + if (unlikely(c)) { + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); + } + if (!len) + return; + if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) + len = IPSET_MAX_COMMENT_SIZE; + c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); + if (unlikely(!c)) + return; + strlcpy(c->str, ext->comment, len + 1); + set->ext_size += sizeof(*c) + strlen(c->str) + 1; + rcu_assign_pointer(comment->c, c); +} + +/* Used only when dumping a set, protected by rcu_read_lock() */ +static inline int +ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) +{ + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); + + if (!c) + return 0; + return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); +} + +/* Called from uadd/udel, flush or the garbage collectors protected + * by the set spinlock. + * Called when the set is destroyed and when there can't be any user + * of the set data anymore. + */ +static inline void +ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) +{ + struct ip_set_comment_rcu *c; + + c = rcu_dereference_protected(comment->c, 1); + if (unlikely(!c)) + return; + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); +} + +static inline void +ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) +{ + atomic64_add((long long)bytes, &(counter)->bytes); +} + +static inline void +ip_set_add_packets(u64 packets, struct ip_set_counter *counter) +{ + atomic64_add((long long)packets, &(counter)->packets); +} + +static inline u64 +ip_set_get_bytes(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->bytes); +} + +static inline u64 +ip_set_get_packets(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->packets); +} + +static inline bool +ip_set_match_counter(u64 counter, u64 match, u8 op) +{ + switch (op) { + case IPSET_COUNTER_NONE: + return true; + case IPSET_COUNTER_EQ: + return counter == match; + case IPSET_COUNTER_NE: + return counter != match; + case IPSET_COUNTER_LT: + return counter < match; + case IPSET_COUNTER_GT: + return counter > match; + } + return false; +} + +static inline void +ip_set_update_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext, u32 flags) +{ + if (ext->packets != ULLONG_MAX && + !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { + ip_set_add_bytes(ext->bytes, counter); + ip_set_add_packets(ext->packets, counter); + } +} + +static inline bool +ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) +{ + return nla_put_net64(skb, IPSET_ATTR_BYTES, + cpu_to_be64(ip_set_get_bytes(counter)), + IPSET_ATTR_PAD) || + nla_put_net64(skb, IPSET_ATTR_PACKETS, + cpu_to_be64(ip_set_get_packets(counter)), + IPSET_ATTR_PAD); +} + +static inline void +ip_set_init_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext) +{ + if (ext->bytes != ULLONG_MAX) + atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); + if (ext->packets != ULLONG_MAX) + atomic64_set(&(counter)->packets, (long long)(ext->packets)); +} + +static inline void +ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) +{ + mext->skbinfo = *skbinfo; +} + +static inline bool +ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) +{ + /* Send nonzero parameters only */ + return ((skbinfo->skbmark || skbinfo->skbmarkmask) && + nla_put_net64(skb, IPSET_ATTR_SKBMARK, + cpu_to_be64((u64)skbinfo->skbmark << 32 | + skbinfo->skbmarkmask), + IPSET_ATTR_PAD)) || + (skbinfo->skbprio && + nla_put_net32(skb, IPSET_ATTR_SKBPRIO, + cpu_to_be32(skbinfo->skbprio))) || + (skbinfo->skbqueue && + nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, + cpu_to_be16(skbinfo->skbqueue))); +} + +static inline void +ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, + const struct ip_set_ext *ext) +{ + *skbinfo = ext->skbinfo; +} #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, \ diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h deleted file mode 100644 index 0b894d81bbf2..000000000000 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ /dev/null @@ -1,73 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_COMMENT_H -#define _IP_SET_COMMENT_H - -/* Copyright (C) 2013 Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa> - */ - -#ifdef __KERNEL__ - -static inline char* -ip_set_comment_uget(struct nlattr *tb) -{ - return nla_data(tb); -} - -/* Called from uadd only, protected by the set spinlock. - * The kadt functions don't use the comment extensions in any way. - */ -static inline void -ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, - const struct ip_set_ext *ext) -{ - struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); - size_t len = ext->comment ? strlen(ext->comment) : 0; - - if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); - } - if (!len) - return; - if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) - len = IPSET_MAX_COMMENT_SIZE; - c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); - if (unlikely(!c)) - return; - strlcpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; - rcu_assign_pointer(comment->c, c); -} - -/* Used only when dumping a set, protected by rcu_read_lock() */ -static inline int -ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c = rcu_dereference(comment->c); - - if (!c) - return 0; - return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); -} - -/* Called from uadd/udel, flush or the garbage collectors protected - * by the set spinlock. - * Called when the set is destroyed and when there can't be any user - * of the set data anymore. - */ -static inline void -ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c; - - c = rcu_dereference_protected(comment->c, 1); - if (unlikely(!c)) - return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); -} - -#endif -#endif diff --git a/include/linux/netfilter/ipset/ip_set_counter.h b/include/linux/netfilter/ipset/ip_set_counter.h deleted file mode 100644 index 3400958c07be..000000000000 --- a/include/linux/netfilter/ipset/ip_set_counter.h +++ /dev/null @@ -1,84 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_COUNTER_H -#define _IP_SET_COUNTER_H - -/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@netfilter.org> */ - -#ifdef __KERNEL__ - -static inline void -ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) -{ - atomic64_add((long long)bytes, &(counter)->bytes); -} - -static inline void -ip_set_add_packets(u64 packets, struct ip_set_counter *counter) -{ - atomic64_add((long long)packets, &(counter)->packets); -} - -static inline u64 -ip_set_get_bytes(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->bytes); -} - -static inline u64 -ip_set_get_packets(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->packets); -} - -static inline bool -ip_set_match_counter(u64 counter, u64 match, u8 op) -{ - switch (op) { - case IPSET_COUNTER_NONE: - return true; - case IPSET_COUNTER_EQ: - return counter == match; - case IPSET_COUNTER_NE: - return counter != match; - case IPSET_COUNTER_LT: - return counter < match; - case IPSET_COUNTER_GT: - return counter > match; - } - return false; -} - -static inline void -ip_set_update_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext, u32 flags) -{ - if (ext->packets != ULLONG_MAX && - !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { - ip_set_add_bytes(ext->bytes, counter); - ip_set_add_packets(ext->packets, counter); - } -} - -static inline bool -ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) -{ - return nla_put_net64(skb, IPSET_ATTR_BYTES, - cpu_to_be64(ip_set_get_bytes(counter)), - IPSET_ATTR_PAD) || - nla_put_net64(skb, IPSET_ATTR_PACKETS, - cpu_to_be64(ip_set_get_packets(counter)), - IPSET_ATTR_PAD); -} - -static inline void -ip_set_init_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext) -{ - if (ext->bytes != ULLONG_MAX) - atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); - if (ext->packets != ULLONG_MAX) - atomic64_set(&(counter)->packets, (long long)(ext->packets)); -} - -#endif /* __KERNEL__ */ -#endif /* _IP_SET_COUNTER_H */ diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h index ac6a11d38a19..a906df06948b 100644 --- a/include/linux/netfilter/ipset/ip_set_getport.h +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -2,6 +2,10 @@ #ifndef _IP_SET_GETPORT_H #define _IP_SET_GETPORT_H +#include <linux/skbuff.h> +#include <linux/types.h> +#include <uapi/linux/in.h> + extern bool ip_set_get_ip4_port(const struct sk_buff *skb, bool src, __be16 *port, u8 *proto); diff --git a/include/linux/netfilter/ipset/ip_set_skbinfo.h b/include/linux/netfilter/ipset/ip_set_skbinfo.h deleted file mode 100644 index 3a2df02dbd55..000000000000 --- a/include/linux/netfilter/ipset/ip_set_skbinfo.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_SKBINFO_H -#define _IP_SET_SKBINFO_H - -/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@netfilter.org> */ - -#ifdef __KERNEL__ - -static inline void -ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) -{ - mext->skbinfo = *skbinfo; -} - -static inline bool -ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) -{ - /* Send nonzero parameters only */ - return ((skbinfo->skbmark || skbinfo->skbmarkmask) && - nla_put_net64(skb, IPSET_ATTR_SKBMARK, - cpu_to_be64((u64)skbinfo->skbmark << 32 | - skbinfo->skbmarkmask), - IPSET_ATTR_PAD)) || - (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, - cpu_to_be32(skbinfo->skbprio))) || - (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, - cpu_to_be16(skbinfo->skbqueue))); -} - -static inline void -ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext) -{ - *skbinfo = ext->skbinfo; -} - -#endif /* __KERNEL__ */ -#endif /* _IP_SET_SKBINFO_H */ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h deleted file mode 100644 index 2be60e379ecf..000000000000 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ /dev/null @@ -1,77 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _IP_SET_TIMEOUT_H -#define _IP_SET_TIMEOUT_H - -/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ - -#ifdef __KERNEL__ - -/* How often should the gc be run by default */ -#define IPSET_GC_TIME (3 * 60) - -/* Timeout period depending on the timeout value of the given set */ -#define IPSET_GC_PERIOD(timeout) \ - ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) - -/* Entry is set with no timeout value */ -#define IPSET_ELEM_PERMANENT 0 - -/* Set is defined with timeout support: timeout value may be 0 */ -#define IPSET_NO_TIMEOUT UINT_MAX - -/* Max timeout value, see msecs_to_jiffies() in jiffies.h */ -#define IPSET_MAX_TIMEOUT (UINT_MAX >> 1)/MSEC_PER_SEC - -#define ip_set_adt_opt_timeout(opt, set) \ -((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout) - -static inline unsigned int -ip_set_timeout_uget(struct nlattr *tb) -{ - unsigned int timeout = ip_set_get_h32(tb); - - /* Normalize to fit into jiffies */ - if (timeout > IPSET_MAX_TIMEOUT) - timeout = IPSET_MAX_TIMEOUT; - - return timeout; -} - -static inline bool -ip_set_timeout_expired(const unsigned long *t) -{ - return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t); -} - -static inline void -ip_set_timeout_set(unsigned long *timeout, u32 value) -{ - unsigned long t; - - if (!value) { - *timeout = IPSET_ELEM_PERMANENT; - return; - } - - t = msecs_to_jiffies(value * MSEC_PER_SEC) + jiffies; - if (t == IPSET_ELEM_PERMANENT) - /* Bingo! :-) */ - t--; - *timeout = t; -} - -static inline u32 -ip_set_timeout_get(const unsigned long *timeout) -{ - u32 t; - - if (*timeout == IPSET_ELEM_PERMANENT) - return 0; - - t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; - /* Zero value in userspace means no timeout */ - return t == 0 ? 1 : t; -} - -#endif /* __KERNEL__ */ -#endif /* _IP_SET_TIMEOUT_H */ diff --git a/include/linux/netfilter/nf_conntrack_amanda.h b/include/linux/netfilter/nf_conntrack_amanda.h index 34345e543ba2..6f0ac896fcc9 100644 --- a/include/linux/netfilter/nf_conntrack_amanda.h +++ b/include/linux/netfilter/nf_conntrack_amanda.h @@ -3,6 +3,10 @@ #define _NF_CONNTRACK_AMANDA_H /* AMANDA tracking. */ +#include <linux/netfilter.h> +#include <linux/skbuff.h> +#include <net/netfilter/nf_conntrack_expect.h> + extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, unsigned int protoff, diff --git a/include/linux/netfilter/nf_conntrack_dccp.h b/include/linux/netfilter/nf_conntrack_dccp.h index ace0f952d50f..c509ed76e714 100644 --- a/include/linux/netfilter/nf_conntrack_dccp.h +++ b/include/linux/netfilter/nf_conntrack_dccp.h @@ -25,7 +25,6 @@ enum ct_dccp_roles { }; #define CT_DCCP_ROLE_MAX (__CT_DCCP_ROLE_MAX - 1) -#ifdef __KERNEL__ #include <linux/netfilter/nf_conntrack_tuple_common.h> struct nf_ct_dccp { @@ -36,6 +35,4 @@ struct nf_ct_dccp { u_int64_t handshake_seq; }; -#endif /* __KERNEL__ */ - #endif /* _NF_CONNTRACK_DCCP_H */ diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index 73a296dfd019..0e38302820b9 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -2,8 +2,12 @@ #ifndef _NF_CONNTRACK_FTP_H #define _NF_CONNTRACK_FTP_H +#include <linux/netfilter.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <net/netfilter/nf_conntrack_expect.h> #include <uapi/linux/netfilter/nf_conntrack_ftp.h> - +#include <uapi/linux/netfilter/nf_conntrack_tuple_common.h> #define FTP_PORT 21 @@ -20,8 +24,6 @@ struct nf_ct_ftp_master { u_int16_t flags[IP_CT_DIR_MAX]; }; -struct nf_conntrack_expect; - /* For NAT to hook in when we find a packet which describes what other * connection we should expect. */ extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index f76ed373a2a5..4561ec0fcea4 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -2,9 +2,12 @@ #ifndef _NF_CONNTRACK_H323_H #define _NF_CONNTRACK_H323_H -#ifdef __KERNEL__ - +#include <linux/netfilter.h> +#include <linux/skbuff.h> +#include <linux/types.h> #include <linux/netfilter/nf_conntrack_h323_asn1.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <uapi/linux/netfilter/nf_conntrack_tuple_common.h> #define RAS_PORT 1719 #define Q931_PORT 1720 @@ -28,8 +31,6 @@ struct nf_ct_h323_master { }; }; -struct nf_conn; - int get_h225_addr(struct nf_conn *ct, unsigned char *data, TransportAddress *taddr, union nf_inet_addr *addr, __be16 *port); @@ -94,5 +95,3 @@ extern int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, struct nf_conntrack_expect *exp); #endif - -#endif diff --git a/include/linux/netfilter/nf_conntrack_h323_asn1.h b/include/linux/netfilter/nf_conntrack_h323_asn1.h index 19df78341fb3..bd6797f823b2 100644 --- a/include/linux/netfilter/nf_conntrack_h323_asn1.h +++ b/include/linux/netfilter/nf_conntrack_h323_asn1.h @@ -37,6 +37,8 @@ /***************************************************************************** * H.323 Types ****************************************************************************/ + +#include <linux/types.h> #include <linux/netfilter/nf_conntrack_h323_types.h> typedef struct { diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h index 00c2b74206e1..d02255f721e1 100644 --- a/include/linux/netfilter/nf_conntrack_irc.h +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -2,7 +2,9 @@ #ifndef _NF_CONNTRACK_IRC_H #define _NF_CONNTRACK_IRC_H -#ifdef __KERNEL__ +#include <linux/netfilter.h> +#include <linux/skbuff.h> +#include <net/netfilter/nf_conntrack_expect.h> #define IRC_PORT 6667 @@ -13,5 +15,4 @@ extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, unsigned int matchlen, struct nf_conntrack_expect *exp); -#endif /* __KERNEL__ */ #endif /* _NF_CONNTRACK_IRC_H */ diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index 833a5b2255ea..fcc409de31a4 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -3,7 +3,12 @@ #ifndef _NF_CONNTRACK_PPTP_H #define _NF_CONNTRACK_PPTP_H +#include <linux/netfilter.h> +#include <linux/skbuff.h> +#include <linux/types.h> #include <linux/netfilter/nf_conntrack_common.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <uapi/linux/netfilter/nf_conntrack_tuple_common.h> extern const char *const pptp_msg_name[]; @@ -45,8 +50,6 @@ struct nf_nat_pptp { __be16 pac_call_id; /* NAT'ed PAC call id */ }; -#ifdef __KERNEL__ - #define PPTP_CONTROL_PORT 1723 #define PPTP_PACKET_CONTROL 1 @@ -297,10 +300,6 @@ union pptp_ctrl_union { struct PptpSetLinkInfo setlink; }; -/* crap needed for nf_conntrack_compat.h */ -struct nf_conn; -struct nf_conntrack_expect; - extern int (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, @@ -323,5 +322,4 @@ extern void (*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, struct nf_conntrack_expect *exp); -#endif /* __KERNEL__ */ #endif /* _NF_CONNTRACK_PPTP_H */ diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 25f9a770fb84..f33aa6021364 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -10,7 +10,6 @@ struct nf_ct_gre { unsigned int timeout; }; -#ifdef __KERNEL__ #include <net/netfilter/nf_conntrack_tuple.h> struct nf_conn; @@ -32,5 +31,4 @@ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple); -#endif /* __KERNEL__ */ #endif /* _CONNTRACK_PROTO_GRE_H */ diff --git a/include/linux/netfilter/nf_conntrack_sane.h b/include/linux/netfilter/nf_conntrack_sane.h index 7d2de44edce3..46c7acd1b4a7 100644 --- a/include/linux/netfilter/nf_conntrack_sane.h +++ b/include/linux/netfilter/nf_conntrack_sane.h @@ -3,8 +3,6 @@ #define _NF_CONNTRACK_SANE_H /* SANE tracking. */ -#ifdef __KERNEL__ - #define SANE_PORT 6566 enum sane_state { @@ -17,6 +15,4 @@ struct nf_ct_sane_master { enum sane_state state; }; -#endif /* __KERNEL__ */ - #endif /* _NF_CONNTRACK_SANE_H */ diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index c7fc38807a33..c620521c42bc 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -1,11 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NF_CONNTRACK_SIP_H__ #define __NF_CONNTRACK_SIP_H__ -#ifdef __KERNEL__ - -#include <net/netfilter/nf_conntrack_expect.h> +#include <linux/skbuff.h> #include <linux/types.h> +#include <net/netfilter/nf_conntrack_expect.h> #define SIP_PORT 5060 #define SIP_TIMEOUT 3600 @@ -196,5 +195,4 @@ int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr, enum sdp_header_types term, unsigned int *matchoff, unsigned int *matchlen); -#endif /* __KERNEL__ */ #endif /* __NF_CONNTRACK_SIP_H__ */ diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h index 818088c47475..87e4f33eb55f 100644 --- a/include/linux/netfilter/nf_conntrack_snmp.h +++ b/include/linux/netfilter/nf_conntrack_snmp.h @@ -2,6 +2,9 @@ #ifndef _NF_CONNTRACK_SNMP_H #define _NF_CONNTRACK_SNMP_H +#include <linux/netfilter.h> +#include <linux/skbuff.h> + extern int (*nf_nat_snmp_hook)(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, diff --git a/include/linux/netfilter/nf_conntrack_tftp.h b/include/linux/netfilter/nf_conntrack_tftp.h index 5769e12dd0a2..dc4c1b9beac0 100644 --- a/include/linux/netfilter/nf_conntrack_tftp.h +++ b/include/linux/netfilter/nf_conntrack_tftp.h @@ -4,6 +4,11 @@ #define TFTP_PORT 69 +#include <linux/netfilter.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <net/netfilter/nf_conntrack_expect.h> + struct tftphdr { __be16 opcode; }; diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 1f852ef7b098..ae62bf1c6824 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -35,12 +35,15 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; +#if IS_ENABLED(CONFIG_NETFILTER) const struct nf_hook_state *state; +#endif int fragoff; unsigned int thoff; bool hotdrop; }; +#if IS_ENABLED(CONFIG_NETFILTER) static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; @@ -75,6 +78,7 @@ static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } +#endif /** * struct xt_mtchk_param - parameters for match extensions' @@ -446,7 +450,9 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) return cnt; } +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); +#endif #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index e98028f00e47..1b7b35bb9c27 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -49,6 +49,7 @@ struct arpt_error { } extern void *arpt_alloc_initial_table(const struct xt_table *); +#if IS_ENABLED(CONFIG_NETFILTER) int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); @@ -57,6 +58,7 @@ void arpt_unregister_table(struct net *net, struct xt_table *table, extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); +#endif #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index c6935be7c6ca..b5b2d371f0ef 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -105,6 +105,7 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) +#if IS_ENABLED(CONFIG_NETFILTER) extern int ebt_register_table(struct net *net, const struct ebt_table *table, const struct nf_hook_ops *ops, @@ -114,6 +115,7 @@ extern void ebt_unregister_table(struct net *net, struct ebt_table *table, extern unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct ebt_table *table); +#endif /* True if the hook mask denotes that the rule is in a base chain, * used in the check() functions */ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index d026e63a5aa4..f40a65481df4 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -25,11 +25,13 @@ extern void ipt_init(void) __init; +#if IS_ENABLED(CONFIG_NETFILTER) int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); +#endif /* Standard entry. */ struct ipt_standard { @@ -65,9 +67,11 @@ struct ipt_error { } extern void *ipt_alloc_initial_table(const struct xt_table *); +#if IS_ENABLED(CONFIG_NETFILTER) extern unsigned int ipt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); +#endif #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 99cbfd3add40..53b7309613bf 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -26,6 +26,7 @@ extern void ip6t_init(void) __init; extern void *ip6t_alloc_initial_table(const struct xt_table *); +#if IS_ENABLED(CONFIG_NETFILTER) int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); @@ -34,6 +35,7 @@ void ip6t_unregister_table(struct net *net, struct xt_table *table, extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); +#endif /* Check for an extension */ static inline int diff --git a/include/linux/phy.h b/include/linux/phy.h index 462b90b73f93..d26779f1fb6b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -403,6 +403,8 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + /* used with phy_speed_down */ + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; @@ -665,6 +667,7 @@ size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); +int phy_speed_down_core(struct phy_device *phydev); /** * phy_is_started - Convenience function to check whether PHY is started @@ -984,6 +987,8 @@ int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); +int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); @@ -1064,12 +1069,11 @@ void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ -int genphy_config_init(struct phy_device *phydev); int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_eee_advert(struct phy_device *phydev); -int genphy_config_aneg(struct phy_device *phydev); +int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); @@ -1077,6 +1081,12 @@ int genphy_suspend(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); + +static inline int genphy_config_aneg(struct phy_device *phydev) +{ + return __genphy_config_aneg(phydev, false); +} + static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; diff --git a/include/linux/platform_data/nxp-nci.h b/include/linux/platform_data/nxp-nci.h deleted file mode 100644 index 97827ad468e2..000000000000 --- a/include/linux/platform_data/nxp-nci.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Generic platform data for the NXP NCI NFC chips. - * - * Copyright (C) 2014 NXP Semiconductors All rights reserved. - * - * Authors: Clément Perrochaud <clement.perrochaud@nxp.com> - */ - -#ifndef _NXP_NCI_H_ -#define _NXP_NCI_H_ - -struct nxp_nci_nfc_platform_data { - unsigned int gpio_en; - unsigned int gpio_fw; - unsigned int irq; -}; - -#endif /* _NXP_NCI_H_ */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index eef02e64b422..e366399874f3 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -689,7 +689,7 @@ enum qed_link_mode_bits { QED_LM_40000baseLR4_Full_BIT = BIT(9), QED_LM_50000baseKR2_Full_BIT = BIT(10), QED_LM_100000baseKR4_Full_BIT = BIT(11), - QED_LM_2500baseX_Full_BIT = BIT(12), + QED_LM_TP_BIT = BIT(12), QED_LM_Backplane_BIT = BIT(13), QED_LM_1000baseKX_Full_BIT = BIT(14), QED_LM_10000baseKX4_Full_BIT = BIT(15), @@ -804,6 +804,7 @@ enum qed_nvm_flash_cmd { QED_NVM_FLASH_CMD_FILE_DATA = 0x2, QED_NVM_FLASH_CMD_FILE_START = 0x3, QED_NVM_FLASH_CMD_NVM_CHANGE = 0x4, + QED_NVM_FLASH_CMD_NVM_CFG_ID = 0x5, QED_NVM_FLASH_CMD_NVM_MAX, }; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ba5583522d24..77c6dc88e95d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -14,6 +14,7 @@ #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> +#include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> @@ -308,58 +309,45 @@ extern int sysctl_max_skb_frags; */ #define GSO_BY_FRAGS 0xFFFF -typedef struct skb_frag_struct skb_frag_t; - -struct skb_frag_struct { - struct { - struct page *p; - } page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; - __u32 size; -#else - __u16 page_offset; - __u16 size; -#endif -}; +typedef struct bio_vec skb_frag_t; /** - * skb_frag_size - Returns the size of a skb fragment + * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { - return frag->size; + return frag->bv_len; } /** - * skb_frag_size_set - Sets the size of a skb fragment + * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { - frag->size = size; + frag->bv_len = size; } /** - * skb_frag_size_add - Incrementes the size of a skb fragment by %delta + * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { - frag->size += delta; + frag->bv_len += delta; } /** - * skb_frag_size_sub - Decrements the size of a skb fragment by %delta + * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { - frag->size -= delta; + frag->bv_len -= delta; } /** @@ -379,7 +367,7 @@ static inline bool skb_frag_must_loop(struct page *p) * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on - * @f_off: offset from start of f->page.p + * @f_off: offset from start of f->bv_page * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, @@ -1283,7 +1271,7 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen); + __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, @@ -2097,8 +2085,8 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ - frag->page.p = page; - frag->page_offset = off; + frag->bv_page = page; + frag->bv_offset = off; skb_frag_size_set(frag, size); page = compound_head(page); @@ -2878,6 +2866,46 @@ static inline void skb_propagate_pfmemalloc(struct page *page, } /** + * skb_frag_off() - Returns the offset of a skb fragment + * @frag: the paged fragment + */ +static inline unsigned int skb_frag_off(const skb_frag_t *frag) +{ + return frag->bv_offset; +} + +/** + * skb_frag_off_add() - Increments the offset of a skb fragment by @delta + * @frag: skb fragment + * @delta: value to add + */ +static inline void skb_frag_off_add(skb_frag_t *frag, int delta) +{ + frag->bv_offset += delta; +} + +/** + * skb_frag_off_set() - Sets the offset of a skb fragment + * @frag: skb fragment + * @offset: offset of fragment + */ +static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) +{ + frag->bv_offset = offset; +} + +/** + * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment + * @fragto: skb fragment where offset is set + * @fragfrom: skb fragment offset is copied from + */ +static inline void skb_frag_off_copy(skb_frag_t *fragto, + const skb_frag_t *fragfrom) +{ + fragto->bv_offset = fragfrom->bv_offset; +} + +/** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * @@ -2885,7 +2913,7 @@ static inline void skb_propagate_pfmemalloc(struct page *page, */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { - return frag->page.p; + return frag->bv_page; } /** @@ -2943,7 +2971,7 @@ static inline void skb_frag_unref(struct sk_buff *skb, int f) */ static inline void *skb_frag_address(const skb_frag_t *frag) { - return page_address(skb_frag_page(frag)) + frag->page_offset; + return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** @@ -2959,7 +2987,18 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) if (unlikely(!ptr)) return NULL; - return ptr + frag->page_offset; + return ptr + skb_frag_off(frag); +} + +/** + * skb_frag_page_copy() - sets the page in a fragment from another fragment + * @fragto: skb fragment where page is set + * @fragfrom: skb fragment page is copied from + */ +static inline void skb_frag_page_copy(skb_frag_t *fragto, + const skb_frag_t *fragfrom) +{ + fragto->bv_page = fragfrom->bv_page; } /** @@ -2971,7 +3010,7 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag) */ static inline void __skb_frag_set_page(skb_frag_t *frag, struct page *page) { - frag->page.p = page; + frag->bv_page = page; } /** @@ -3007,7 +3046,7 @@ static inline dma_addr_t skb_frag_dma_map(struct device *dev, enum dma_data_direction dir) { return dma_map_page(dev, skb_frag_page(frag), - frag->page_offset + offset, size, dir); + skb_frag_off(frag) + offset, size, dir); } static inline struct sk_buff *pskb_copy(struct sk_buff *skb, @@ -3174,10 +3213,10 @@ static inline bool skb_can_coalesce(struct sk_buff *skb, int i, if (skb_zcopy(skb)) return false; if (i) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return page == skb_frag_page(frag) && - off == frag->page_offset + skb_frag_size(frag); + off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7d06241582dd..5cc6b6faf359 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -81,6 +81,7 @@ struct stmmac_mdio_bus_data { unsigned int phy_mask; int *irqs; int probed_phy_irq; + bool needs_reset; }; struct stmmac_dma_cfg { @@ -172,6 +173,7 @@ struct plat_stmmacenet_data { int has_gmac4; bool has_sun8i; bool tso_en; + int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; int has_xgmac; diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index e223e2632edd..4c7781f4b29b 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -35,13 +35,14 @@ struct virtio_vsock_sock { /* Protected by tx_lock */ u32 tx_cnt; - u32 buf_alloc; u32 peer_fwd_cnt; u32 peer_buf_alloc; /* Protected by rx_lock */ u32 fwd_cnt; + u32 last_fwd_cnt; u32 rx_bytes; + u32 buf_alloc; struct list_head rx_queue; }; @@ -52,6 +53,7 @@ struct virtio_vsock_pkt { /* socket refcnt not held, only use for cancellation */ struct vsock_sock *vsk; void *buf; + u32 buf_len; u32 len; u32 off; bool reply; diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index 7cb63e4ec0ae..4dd2c1cea6a9 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -98,9 +98,7 @@ * To manipulate from user space the levels, create a debugfs dentry * and then register each submodule with: * - * result = d_level_register_debugfs("PREFIX_", submodule_X, parent); - * if (result < 0) - * goto error; + * 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 @@ -408,25 +406,13 @@ do { \ * @submodule: name of submodule (not a string, just the name) * @dentry: debugfs parent dentry * - * Returns: 0 if ok, < 0 errno on error. - * * For removing, just use debugfs_remove_recursive() on the parent. */ #define d_level_register_debugfs(prefix, name, parent) \ ({ \ - int rc; \ - struct dentry *fd; \ - struct dentry *verify_parent_type = parent; \ - fd = debugfs_create_u8( \ - prefix #name, 0600, verify_parent_type, \ + debugfs_create_u8( \ + prefix #name, 0600, parent, \ &(D_LEVEL[__D_SUBMODULE_ ## name].level)); \ - rc = PTR_ERR(fd); \ - if (IS_ERR(fd) && rc != -ENODEV) \ - printk(KERN_ERR "%s: Can't create debugfs entry %s: " \ - "%d\n", __func__, prefix #name, rc); \ - else \ - rc = 0; \ - rc; \ }) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 26e2ad2c7027..8140c4837122 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -247,6 +247,19 @@ struct ieee80211_rate { }; /** + * struct ieee80211_he_obss_pd - AP settings for spatial reuse + * + * @enable: is the feature enabled. + * @min_offset: minimal tx power offset an associated station shall use + * @max_offset: maximum tx power offset an associated station shall use + */ +struct ieee80211_he_obss_pd { + bool enable; + u8 min_offset; + u8 max_offset; +}; + +/** * struct ieee80211_sta_ht_cap - STA's HT capabilities * * This structure describes most essential parameters needed @@ -896,6 +909,7 @@ enum cfg80211_ap_settings_flags { * @vht_required: stations must support VHT * @twt_responder: Enable Target Wait Time * @flags: flags, as defined in enum cfg80211_ap_settings_flags + * @he_obss_pd: OBSS Packet Detection settings */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -923,6 +937,7 @@ struct cfg80211_ap_settings { bool ht_required, vht_required; bool twt_responder; u32 flags; + struct ieee80211_he_obss_pd he_obss_pd; }; /** diff --git a/include/net/devlink.h b/include/net/devlink.h index bc36f942a7d5..7f43c48f54cd 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -14,6 +14,7 @@ #include <linux/netdevice.h> #include <linux/spinlock.h> #include <linux/workqueue.h> +#include <linux/refcount.h> #include <net/net_namespace.h> #include <uapi/linux/devlink.h> @@ -31,6 +32,8 @@ struct devlink { struct list_head reporter_list; struct mutex reporters_lock; /* protects reporter_list */ struct devlink_dpipe_headers *dpipe_headers; + struct list_head trap_list; + struct list_head trap_group_list; const struct devlink_ops *ops; struct device *dev; possible_net_t _net; @@ -497,6 +500,135 @@ struct devlink_health_reporter_ops { struct devlink_fmsg *fmsg); }; +/** + * struct devlink_trap_group - Immutable packet trap group attributes. + * @name: Trap group name. + * @id: Trap group identifier. + * @generic: Whether the trap group is generic or not. + * + * Describes immutable attributes of packet trap groups that drivers register + * with devlink. + */ +struct devlink_trap_group { + const char *name; + u16 id; + bool generic; +}; + +#define DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT BIT(0) + +/** + * struct devlink_trap - Immutable packet trap attributes. + * @type: Trap type. + * @init_action: Initial trap action. + * @generic: Whether the trap is generic or not. + * @id: Trap identifier. + * @name: Trap name. + * @group: Immutable packet trap group attributes. + * @metadata_cap: Metadata types that can be provided by the trap. + * + * Describes immutable attributes of packet traps that drivers register with + * devlink. + */ +struct devlink_trap { + enum devlink_trap_type type; + enum devlink_trap_action init_action; + bool generic; + u16 id; + const char *name; + struct devlink_trap_group group; + u32 metadata_cap; +}; + +/* All traps must be documented in + * Documentation/networking/devlink-trap.rst + */ +enum devlink_trap_generic_id { + DEVLINK_TRAP_GENERIC_ID_SMAC_MC, + DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH, + DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER, + DEVLINK_TRAP_GENERIC_ID_INGRESS_STP_FILTER, + DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST, + DEVLINK_TRAP_GENERIC_ID_PORT_LOOPBACK_FILTER, + DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE, + DEVLINK_TRAP_GENERIC_ID_TTL_ERROR, + DEVLINK_TRAP_GENERIC_ID_TAIL_DROP, + + /* Add new generic trap IDs above */ + __DEVLINK_TRAP_GENERIC_ID_MAX, + DEVLINK_TRAP_GENERIC_ID_MAX = __DEVLINK_TRAP_GENERIC_ID_MAX - 1, +}; + +/* All trap groups must be documented in + * Documentation/networking/devlink-trap.rst + */ +enum devlink_trap_group_generic_id { + DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS, + + /* Add new generic trap group IDs above */ + __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, + DEVLINK_TRAP_GROUP_GENERIC_ID_MAX = + __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX - 1, +}; + +#define DEVLINK_TRAP_GENERIC_NAME_SMAC_MC \ + "source_mac_is_multicast" +#define DEVLINK_TRAP_GENERIC_NAME_VLAN_TAG_MISMATCH \ + "vlan_tag_mismatch" +#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_VLAN_FILTER \ + "ingress_vlan_filter" +#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_STP_FILTER \ + "ingress_spanning_tree_filter" +#define DEVLINK_TRAP_GENERIC_NAME_EMPTY_TX_LIST \ + "port_list_is_empty" +#define DEVLINK_TRAP_GENERIC_NAME_PORT_LOOPBACK_FILTER \ + "port_loopback_filter" +#define DEVLINK_TRAP_GENERIC_NAME_BLACKHOLE_ROUTE \ + "blackhole_route" +#define DEVLINK_TRAP_GENERIC_NAME_TTL_ERROR \ + "ttl_value_is_too_small" +#define DEVLINK_TRAP_GENERIC_NAME_TAIL_DROP \ + "tail_drop" + +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ + "l2_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L3_DROPS \ + "l3_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BUFFER_DROPS \ + "buffer_drops" + +#define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \ + { \ + .type = DEVLINK_TRAP_TYPE_##_type, \ + .init_action = DEVLINK_TRAP_ACTION_##_init_action, \ + .generic = true, \ + .id = DEVLINK_TRAP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \ + .group = _group, \ + .metadata_cap = _metadata_cap, \ + } + +#define DEVLINK_TRAP_DRIVER(_type, _init_action, _id, _name, _group, \ + _metadata_cap) \ + { \ + .type = DEVLINK_TRAP_TYPE_##_type, \ + .init_action = DEVLINK_TRAP_ACTION_##_init_action, \ + .generic = false, \ + .id = _id, \ + .name = _name, \ + .group = _group, \ + .metadata_cap = _metadata_cap, \ + } + +#define DEVLINK_TRAP_GROUP_GENERIC(_id) \ + { \ + .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \ + .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \ + .generic = true, \ + } + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -558,6 +690,38 @@ struct devlink_ops { int (*flash_update)(struct devlink *devlink, const char *file_name, const char *component, struct netlink_ext_ack *extack); + /** + * @trap_init: Trap initialization function. + * + * Should be used by device drivers to initialize the trap in the + * underlying device. Drivers should also store the provided trap + * context, so that they could efficiently pass it to + * devlink_trap_report() when the trap is triggered. + */ + int (*trap_init)(struct devlink *devlink, + const struct devlink_trap *trap, void *trap_ctx); + /** + * @trap_fini: Trap de-initialization function. + * + * Should be used by device drivers to de-initialize the trap in the + * underlying device. + */ + void (*trap_fini)(struct devlink *devlink, + const struct devlink_trap *trap, void *trap_ctx); + /** + * @trap_action_set: Trap action set function. + */ + int (*trap_action_set)(struct devlink *devlink, + const struct devlink_trap *trap, + enum devlink_trap_action action); + /** + * @trap_group_init: Trap group initialization function. + * + * Should be used by device drivers to initialize the trap group in the + * underlying device. + */ + int (*trap_group_init)(struct devlink *devlink, + const struct devlink_trap_group *group); }; static inline void *devlink_priv(struct devlink *devlink) @@ -702,7 +866,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink, u64 region_size); void devlink_region_destroy(struct devlink_region *region); u32 devlink_region_shapshot_id_get(struct devlink *devlink); -int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, +int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); int devlink_info_serial_number_put(struct devlink_info_req *req, @@ -774,6 +938,17 @@ void devlink_flash_update_status_notify(struct devlink *devlink, unsigned long done, unsigned long total); +int devlink_traps_register(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count, void *priv); +void devlink_traps_unregister(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count); +void devlink_trap_report(struct devlink *devlink, + struct sk_buff *skb, void *trap_ctx, + struct devlink_port *in_devlink_port); +void *devlink_trap_ctx_priv(void *trap_ctx); + #if IS_ENABLED(CONFIG_NET_DEVLINK) void devlink_compat_running_version(struct net_device *dev, diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h new file mode 100644 index 000000000000..2ab668461463 --- /dev/null +++ b/include/net/drop_monitor.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _NET_DROP_MONITOR_H_ +#define _NET_DROP_MONITOR_H_ + +#include <linux/ktime.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> + +/** + * struct net_dm_hw_metadata - Hardware-supplied packet metadata. + * @trap_group_name: Hardware trap group name. + * @trap_name: Hardware trap name. + * @input_dev: Input netdevice. + */ +struct net_dm_hw_metadata { + const char *trap_group_name; + const char *trap_name; + struct net_device *input_dev; +}; + +#if IS_ENABLED(CONFIG_NET_DROP_MONITOR) +void net_dm_hw_report(struct sk_buff *skb, + const struct net_dm_hw_metadata *hw_metadata); +#else +static inline void +net_dm_hw_report(struct sk_buff *skb, + const struct net_dm_hw_metadata *hw_metadata) +{ +} +#endif + +#endif /* _NET_DROP_MONITOR_H_ */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 1e8650fa8acc..147b757ef8ea 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -41,6 +41,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 +#define DSA_TAG_PROTO_KSZ8795_VALUE 14 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -57,6 +58,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, + DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, }; struct packet_type; diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index b16d21636d69..e8069b6c474c 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -4,6 +4,7 @@ #include <linux/kernel.h> #include <linux/list.h> #include <net/flow_dissector.h> +#include <linux/rhashtable.h> struct flow_match { struct flow_dissector *dissector; @@ -117,6 +118,8 @@ enum flow_action_id { FLOW_ACTION_GOTO, FLOW_ACTION_REDIRECT, FLOW_ACTION_MIRRED, + FLOW_ACTION_REDIRECT_INGRESS, + FLOW_ACTION_MIRRED_INGRESS, FLOW_ACTION_VLAN_PUSH, FLOW_ACTION_VLAN_POP, FLOW_ACTION_VLAN_MANGLE, @@ -126,11 +129,15 @@ enum flow_action_id { FLOW_ACTION_ADD, FLOW_ACTION_CSUM, FLOW_ACTION_MARK, + FLOW_ACTION_PTYPE, FLOW_ACTION_WAKE, FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, FLOW_ACTION_POLICE, FLOW_ACTION_CT, + FLOW_ACTION_MPLS_PUSH, + FLOW_ACTION_MPLS_POP, + FLOW_ACTION_MPLS_MANGLE, }; /* This is mirroring enum pedit_header_type definition for easy mapping between @@ -165,6 +172,7 @@ struct flow_action_entry { const struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ u32 csum_flags; /* FLOW_ACTION_CSUM */ u32 mark; /* FLOW_ACTION_MARK */ + u16 ptype; /* FLOW_ACTION_PTYPE */ struct { /* FLOW_ACTION_QUEUE */ u32 ctx; u32 index; @@ -184,6 +192,22 @@ struct flow_action_entry { int action; u16 zone; } ct; + struct { /* FLOW_ACTION_MPLS_PUSH */ + u32 label; + __be16 proto; + u8 tc; + u8 bos; + u8 ttl; + } mpls_push; + struct { /* FLOW_ACTION_MPLS_POP */ + __be16 proto; + } mpls_pop; + struct { /* FLOW_ACTION_MPLS_MANGLE */ + u32 label; + u8 tc; + u8 bos; + u8 ttl; + } mpls_mangle; }; }; @@ -347,4 +371,40 @@ static inline void flow_block_init(struct flow_block *flow_block) INIT_LIST_HEAD(&flow_block->cb_list); } +typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, + enum tc_setup_type type, void *type_data); + +typedef void flow_indr_block_ing_cmd_t(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command); + +struct flow_indr_block_ing_entry { + flow_indr_block_ing_cmd_t *cb; + struct list_head list; +}; + +void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry); + +void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry); + +int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident); + +void __flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident); + +int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, void *cb_ident); + +void flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident); + +void flow_indr_block_call(struct net_device *dev, + struct flow_block_offload *bo, + enum flow_block_command command); + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d26da013f7c0..6781d4637557 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -315,6 +315,7 @@ struct ieee80211_vif_chanctx_switch { * @BSS_CHANGED_FTM_RESPONDER: fime timing reasurement request responder * functionality changed for this BSS (AP mode). * @BSS_CHANGED_TWT: TWT status changed + * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. * */ enum ieee80211_bss_change { @@ -346,6 +347,7 @@ enum ieee80211_bss_change { BSS_CHANGED_MCAST_RATE = 1<<25, BSS_CHANGED_FTM_RESPONDER = 1<<26, BSS_CHANGED_TWT = 1<<27, + BSS_CHANGED_HE_OBSS_PD = 1<<28, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -600,6 +602,8 @@ struct ieee80211_ftm_responder_params { * 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_operation: HE operation information of the AP we are connected to + * @he_obss_pd: OBSS Packet Detection parameters. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -661,6 +665,8 @@ struct ieee80211_bss_conf { u8 bssid_indicator; bool ema_ap; u8 profile_periodicity; + struct ieee80211_he_operation he_operation; + struct ieee80211_he_obss_pd he_obss_pd; }; /** @@ -1058,11 +1064,13 @@ struct ieee80211_tx_info { * @sta: Station that the packet was transmitted for * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) + * @rate: The TX rate that was used when sending the packet */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; + struct rate_info *rate; }; /** @@ -1702,6 +1710,9 @@ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); * a TKIP key if it only requires MIC space. Do not set together with * @IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key. * @IEEE80211_KEY_FLAG_NO_AUTO_TX: Key needs explicit Tx activation. + * @IEEE80211_KEY_FLAG_GENERATE_MMIE: This flag should be set by the driver + * for a AES_CMAC key to indicate that it requires sequence number + * generation only */ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_GENERATE_IV_MGMT = BIT(0), @@ -1714,6 +1725,7 @@ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_RESERVE_TAILROOM = BIT(7), IEEE80211_KEY_FLAG_PUT_MIC_SPACE = BIT(8), IEEE80211_KEY_FLAG_NO_AUTO_TX = BIT(9), + IEEE80211_KEY_FLAG_GENERATE_MMIE = BIT(10), }; /** @@ -2268,11 +2280,9 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID: Hardware supports multi BSSID * only for HE APs. Applies if @IEEE80211_HW_SUPPORTS_MULTI_BSSID is set. * - * @IEEE80211_HW_EXT_KEY_ID_NATIVE: Driver and hardware are supporting Extended - * Key ID and can handle two unicast keys per station for Rx and Tx. - * - * @IEEE80211_HW_NO_AMPDU_KEYBORDER_SUPPORT: The card/driver can't handle - * active Tx A-MPDU sessions with Extended Key IDs during rekey. + * @IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT: The card and driver is only + * aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx + * A-MPDU sessions active while rekeying with Extended Key ID. * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ @@ -2325,8 +2335,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN, IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, - IEEE80211_HW_EXT_KEY_ID_NATIVE, - IEEE80211_HW_NO_AMPDU_KEYBORDER_SUPPORT, + IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -3914,7 +3923,8 @@ struct ieee80211_ops { struct ieee80211_channel *chan, int duration, enum ieee80211_roc_type type); - int (*cancel_remain_on_channel)(struct ieee80211_hw *hw); + int (*cancel_remain_on_channel)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx); void (*get_ringparam)(struct ieee80211_hw *hw, u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max); @@ -5945,7 +5955,6 @@ struct rate_control_ops { void (*add_sta_debugfs)(void *priv, void *priv_sta, struct dentry *dir); - void (*remove_sta_debugfs)(void *priv, void *priv_sta); u32 (*get_expected_throughput)(void *priv_sta); }; @@ -6234,11 +6243,37 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); * but for the duration of the frame handling. * However, also note that while in the wake_tx_queue() method, * rcu_read_lock() is already held. + * + * softirqs must also be disabled when this function is called. + * In process context, use ieee80211_tx_dequeue_ni() instead. */ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** + * ieee80211_tx_dequeue_ni - dequeue a packet from a software tx queue + * (in process context) + * + * Like ieee80211_tx_dequeue() but can be called in process context + * (internally disables bottom halves). + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface, or from + * ieee80211_next_txq() + */ +static inline struct sk_buff *ieee80211_tx_dequeue_ni(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = ieee80211_tx_dequeue(hw, txq); + local_bh_enable(); + + return skb; +} + +/** * ieee80211_next_txq - get next tx queue to pull packets from * * @hw: pointer as obtained from ieee80211_alloc_hw() diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 366150053043..b2f715ca0567 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -40,6 +40,7 @@ enum { ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ ND_OPT_6CO = 34, /* RFC6775 */ + ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */ __ND_OPT_MAX }; diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 302fcd3aade2..2a613c84d49f 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -2,16 +2,22 @@ #ifndef _BR_NETFILTER_H_ #define _BR_NETFILTER_H_ +#include <linux/netfilter.h> + #include "../../../net/bridge/br_private.h" static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) { +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info *b = skb_ext_add(skb, SKB_EXT_BRIDGE_NF); if (b) memset(b, 0, sizeof(*b)); return b; +#else + return NULL; +#endif } void nf_bridge_update_protocol(struct sk_buff *skb); @@ -36,15 +42,20 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) { +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct net_bridge_port *port; port = br_port_get_rcu(dev); return port ? &port->br->fake_rtable : NULL; +#else + return NULL; +#endif } struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net); +#if IS_ENABLED(CONFIG_NETFILTER) #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct net *net, struct sk_buff *skb); unsigned int br_nf_pre_routing_ipv6(void *priv, @@ -63,5 +74,6 @@ br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, return NF_ACCEPT; } #endif +#endif #endif /* _BR_NETFILTER_H_ */ diff --git a/include/net/netfilter/ipv4/nf_dup_ipv4.h b/include/net/netfilter/ipv4/nf_dup_ipv4.h index c962e0be3549..a2bc16cdbcd3 100644 --- a/include/net/netfilter/ipv4/nf_dup_ipv4.h +++ b/include/net/netfilter/ipv4/nf_dup_ipv4.h @@ -2,6 +2,9 @@ #ifndef _NF_DUP_IPV4_H_ #define _NF_DUP_IPV4_H_ +#include <linux/skbuff.h> +#include <uapi/linux/in.h> + void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in_addr *gw, int oif); diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 9d7e28736da9..6d31cd041143 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -2,7 +2,9 @@ #ifndef _NF_DEFRAG_IPV6_H #define _NF_DEFRAG_IPV6_H -struct net; +#include <linux/skbuff.h> +#include <linux/types.h> + int nf_defrag_ipv6_enable(struct net *); int nf_ct_frag6_init(void); diff --git a/include/net/netfilter/ipv6/nf_dup_ipv6.h b/include/net/netfilter/ipv6/nf_dup_ipv6.h index caf0c2dd8ee7..f6312bb04a13 100644 --- a/include/net/netfilter/ipv6/nf_dup_ipv6.h +++ b/include/net/netfilter/ipv6/nf_dup_ipv6.h @@ -2,6 +2,8 @@ #ifndef _NF_DUP_IPV6_H_ #define _NF_DUP_IPV6_H_ +#include <linux/skbuff.h> + void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index c86657d99630..2cc304efe7f9 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -59,6 +59,7 @@ struct nf_conntrack_net { #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> struct nf_conn { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Usage count in here is 1 for hash table, 1 per skb, * plus 1 for any connection(s) we are `master' for * @@ -68,6 +69,7 @@ struct nf_conn { * beware nf_ct_get() is different and don't inc refcnt. */ struct nf_conntrack ct_general; +#endif spinlock_t lock; /* jiffies32 when this ct is considered dead */ @@ -148,6 +150,8 @@ void nf_conntrack_alter_reply(struct nf_conn *ct, int nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack); +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) @@ -167,6 +171,8 @@ static inline void nf_ct_put(struct nf_conn *ct) nf_conntrack_put(&ct->ct_general); } +#endif + /* Protocol module loading */ int nf_ct_l3proto_try_module_get(unsigned short l3proto); void nf_ct_l3proto_module_put(unsigned short l3proto); @@ -318,12 +324,16 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl); u32 nf_ct_get_id(const struct nf_conn *ct); +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + static inline void nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) { skb->_nfct = (unsigned long)ct | info; } +#endif + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h index 1fee733c18a7..ad9f2172dee1 100644 --- a/include/net/netfilter/nf_conntrack_acct.h +++ b/include/net/netfilter/nf_conntrack_acct.h @@ -29,6 +29,7 @@ struct nf_conn_acct *nf_conn_acct_find(const struct nf_conn *ct) static inline struct nf_conn_acct *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp) { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) struct net *net = nf_ct_net(ct); struct nf_conn_acct *acct; @@ -41,22 +42,34 @@ struct nf_conn_acct *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp) return acct; +#else + return NULL; +#endif }; /* Check if connection tracking accounting is enabled */ static inline bool nf_ct_acct_enabled(struct net *net) { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) return net->ct.sysctl_acct != 0; +#else + return false; +#endif } /* Enable/disable connection tracking accounting */ static inline void nf_ct_set_acct(struct net *net, bool enable) { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) net->ct.sysctl_acct = enable; +#endif } +#if IS_ENABLED(CONFIG_NF_CONNTRACK) void nf_conntrack_acct_pernet_init(struct net *net); int nf_conntrack_acct_init(void); void nf_conntrack_acct_fini(void); +#endif /* IS_ENABLED(CONFIG_NF_CONNTRACK) */ + #endif /* _NF_CONNTRACK_ACCT_H */ diff --git a/include/net/netfilter/nf_conntrack_bridge.h b/include/net/netfilter/nf_conntrack_bridge.h index 9a5514d5bc51..34c28f248b18 100644 --- a/include/net/netfilter/nf_conntrack_bridge.h +++ b/include/net/netfilter/nf_conntrack_bridge.h @@ -1,8 +1,14 @@ #ifndef NF_CONNTRACK_BRIDGE_ #define NF_CONNTRACK_BRIDGE_ +#include <linux/module.h> +#include <linux/types.h> +#include <uapi/linux/if_ether.h> + struct nf_ct_bridge_info { +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *ops; +#endif unsigned int ops_size; struct module *me; }; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index de10faf2ce91..71a2d9cb64ea 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -20,7 +20,10 @@ /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use of connection tracking. */ + +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state); +#endif int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index f32fc8289473..9645b47fa7e4 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -2,6 +2,9 @@ #define _NF_CONNTRACK_COUNT_H #include <linux/list.h> +#include <linux/spinlock.h> +#include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_zones.h> struct nf_conncount_data; diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index a49edfdf47e8..c200b95d27ae 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -75,6 +75,7 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); +#if IS_ENABLED(CONFIG_NETFILTER) int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state, @@ -131,6 +132,7 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); +#endif void nf_conntrack_generic_init_net(struct net *net); void nf_conntrack_tcp_init_net(struct net *net); @@ -176,6 +178,7 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const char *fmt, ...) { } #endif /* CONFIG_SYSCTL */ +#if IS_ENABLED(CONFIG_NF_CONNTRACK) static inline struct nf_generic_net *nf_generic_pernet(struct net *net) { return &net->ct.nf_ct_proto.generic; @@ -200,6 +203,7 @@ static inline struct nf_icmp_net *nf_icmpv6_pernet(struct net *net) { return &net->ct.nf_ct_proto.icmpv6; } +#endif #ifdef CONFIG_NF_CT_PROTO_DCCP static inline struct nf_dccp_net *nf_dccp_pernet(struct net *net) diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index 44513b93bd55..2f0171d24997 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -67,7 +67,7 @@ static inline struct synproxy_net *synproxy_pernet(struct net *net) struct synproxy_options { u8 options; u8 wscale; - u16 mss; + u16 mss_option; u16 mss_encode; u32 tsval; u32 tsecr; diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h index 0ed617bf0a3d..2b8aeba649aa 100644 --- a/include/net/netfilter/nf_conntrack_timestamp.h +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -40,12 +40,18 @@ struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) static inline bool nf_ct_tstamp_enabled(struct net *net) { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) return net->ct.sysctl_tstamp != 0; +#else + return false; +#endif } static inline void nf_ct_set_tstamp(struct net *net, bool enable) { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) net->ct.sysctl_tstamp = enable; +#endif } #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index bf0444e111a6..480c87b44a96 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -121,6 +121,7 @@ struct nf_conntrack_tuple_hash { struct nf_conntrack_tuple tuple; }; +#if IS_ENABLED(CONFIG_NETFILTER) static inline bool __nf_ct_tuple_src_equal(const struct nf_conntrack_tuple *t1, const struct nf_conntrack_tuple *t2) { @@ -183,5 +184,6 @@ nf_ct_tuple_mask_cmp(const struct nf_conntrack_tuple *t, return nf_ct_tuple_src_mask_cmp(t, tuple, mask) && __nf_ct_tuple_dst_equal(t, tuple); } +#endif #endif /* _NF_CONNTRACK_TUPLE_H */ diff --git a/include/net/netfilter/nf_dup_netdev.h b/include/net/netfilter/nf_dup_netdev.h index 2a6f6dcad3d9..181672672160 100644 --- a/include/net/netfilter/nf_dup_netdev.h +++ b/include/net/netfilter/nf_dup_netdev.h @@ -2,6 +2,8 @@ #ifndef _NF_DUP_NETDEV_H_ #define _NF_DUP_NETDEV_H_ +#include <net/netfilter/nf_tables.h> + void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif); void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif); diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d8c187936bec..609df33b1209 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/rhashtable-types.h> #include <linux/rcupdate.h> +#include <linux/netfilter.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/dst.h> @@ -16,7 +17,9 @@ struct nf_flowtable_type { int family; int (*init)(struct nf_flowtable *ft); void (*free)(struct nf_flowtable *ft); +#if IS_ENABLED(CONFIG_NETFILTER) nf_hookfn *hook; +#endif struct module *owner; }; @@ -114,10 +117,12 @@ struct flow_ports { __be16 source, dest; }; +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +#endif #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 423cda2c6542..eec208fb9c23 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -69,10 +69,12 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum, #endif } +#if IS_ENABLED(CONFIG_NETFILTER) int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, const struct nf_hook_ops *nat_ops, unsigned int ops_count); void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, unsigned int ops_count); +#endif unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb); @@ -92,6 +94,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen); +#if IS_ENABLED(CONFIG_NETFILTER) int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops); @@ -104,6 +107,7 @@ void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops); unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +#endif int nf_xfrm_me_harder(struct net *n, struct sk_buff *s, unsigned int family); diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 97d7033e93a4..efae84646353 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -3,9 +3,9 @@ #define _NF_NAT_HELPER_H /* NAT protocol helper routines. */ +#include <linux/skbuff.h> #include <net/netfilter/nf_conntrack.h> - -struct sk_buff; +#include <net/netfilter/nf_conntrack_expect.h> /* These return true or false. */ bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct, diff --git a/include/net/netfilter/nf_nat_redirect.h b/include/net/netfilter/nf_nat_redirect.h index c129aacc8ae8..2418653a66db 100644 --- a/include/net/netfilter/nf_nat_redirect.h +++ b/include/net/netfilter/nf_nat_redirect.h @@ -2,6 +2,9 @@ #ifndef _NF_NAT_REDIRECT_H_ #define _NF_NAT_REDIRECT_H_ +#include <linux/skbuff.h> +#include <uapi/linux/netfilter/nf_nat.h> + unsigned int nf_nat_redirect_ipv4(struct sk_buff *skb, const struct nf_nat_ipv4_multi_range_compat *mr, diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 3cb6dcf53a4e..80edb46a1bbc 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -5,6 +5,8 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/jhash.h> +#include <linux/netfilter.h> +#include <linux/skbuff.h> /* Each queued (to userspace) skbuff has one of these. */ struct nf_queue_entry { @@ -13,7 +15,9 @@ struct nf_queue_entry { unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_state state; +#endif u16 size; /* sizeof(entry) + saved route keys */ /* extra space to store route keys */ @@ -119,6 +123,9 @@ nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, return queue; } +#if IS_ENABLED(CONFIG_NETFILTER) int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, unsigned int index, unsigned int verdict); +#endif + #endif /* _NF_QUEUE_H */ diff --git a/include/net/netfilter/nf_reject.h b/include/net/netfilter/nf_reject.h index 221f877f29d1..9051c3a0c8e7 100644 --- a/include/net/netfilter/nf_reject.h +++ b/include/net/netfilter/nf_reject.h @@ -2,6 +2,9 @@ #ifndef _NF_REJECT_H #define _NF_REJECT_H +#include <linux/types.h> +#include <uapi/linux/in.h> + static inline bool nf_reject_verify_csum(__u8 proto) { /* Skip protocols that don't use 16-bit one's complement checksum diff --git a/include/net/netfilter/nf_synproxy.h b/include/net/netfilter/nf_synproxy.h index 87d73fb5279d..dc420b47e3aa 100644 --- a/include/net/netfilter/nf_synproxy.h +++ b/include/net/netfilter/nf_synproxy.h @@ -20,8 +20,10 @@ bool synproxy_recv_client_ack(struct net *net, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); +#endif int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net); @@ -35,8 +37,10 @@ bool synproxy_recv_client_ack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); +#if IS_ENABLED(CONFIG_NETFILTER) unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); +#endif int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net); #else diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 475d6f28ca67..e73d16f8b870 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -25,6 +25,7 @@ struct nft_pktinfo { struct xt_action_param xt; }; +#if IS_ENABLED(CONFIG_NETFILTER) static inline struct net *nft_net(const struct nft_pktinfo *pkt) { return pkt->xt.state->net; @@ -57,6 +58,7 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, pkt->skb = skb; pkt->xt.state = state; } +#endif static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, struct sk_buff *skb) @@ -926,9 +928,11 @@ struct nft_chain_type { int family; struct module *owner; unsigned int hook_mask; +#if IS_ENABLED(CONFIG_NETFILTER) nf_hookfn *hooks[NF_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); +#endif }; int nft_chain_validate_dependency(const struct nft_chain *chain, @@ -954,7 +958,9 @@ struct nft_stats { * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops ops; +#endif const struct nft_chain_type *type; u8 policy; u8 flags; @@ -1151,7 +1157,9 @@ struct nft_flowtable { use:30; u64 handle; /* runtime data below here */ +#if IS_ENABLED(CONFIG_NETFILTER) struct nf_hook_ops *ops ____cacheline_aligned; +#endif struct nf_flowtable data; }; @@ -1206,6 +1214,8 @@ void nft_trace_notify(struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_OBJ(type) \ MODULE_ALIAS("nft-obj-" __stringify(type)) +#if IS_ENABLED(CONFIG_NF_TABLES) + /* * The gencursor defines two generations, the currently active and the * next one. Objects contain a bitmask of 2 bits specifying the generations @@ -1279,6 +1289,8 @@ static inline void nft_set_elem_change_active(const struct net *net, ext->genmask ^= nft_genmask_next(net); } +#endif /* IS_ENABLED(CONFIG_NF_TABLES) */ + /* * We use a free bit in the genmask field to indicate the element * is busy, meaning it is currently being processed either by diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index dabe6fdb553a..d0f1c537b017 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -4,6 +4,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/ipv6.h> +#include <net/netfilter/nf_tables.h> static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, struct sk_buff *skb) diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index c8b9dec376f5..db104665a9e4 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -9,6 +9,7 @@ struct nft_offload_reg { u32 len; u32 base_offset; u32 offset; + struct nft_data data; struct nft_data mask; }; @@ -63,6 +64,10 @@ struct nft_rule; struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule); void nft_flow_rule_destroy(struct nft_flow_rule *flow); int nft_flow_rule_offload_commit(struct net *net); +void nft_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command); #define NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ (__reg)->base_offset = \ diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index e4c4d8eaca8c..628b6fa579cd 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -2,6 +2,8 @@ #ifndef _NFT_FIB_H_ #define _NFT_FIB_H_ +#include <net/netfilter/nf_tables.h> + struct nft_fib { enum nft_registers dreg:8; u8 result; diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 5c69e9b09388..07e2fd507963 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -2,6 +2,8 @@ #ifndef _NFT_META_H_ #define _NFT_META_H_ +#include <net/netfilter/nf_tables.h> + struct nft_meta { enum nft_meta_keys key:8; union { diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h index de80c50761f0..56b123a42220 100644 --- a/include/net/netfilter/nft_reject.h +++ b/include/net/netfilter/nft_reject.h @@ -2,6 +2,11 @@ #ifndef _NFT_REJECT_H_ #define _NFT_REJECT_H_ +#include <linux/types.h> +#include <net/netlink.h> +#include <net/netfilter/nf_tables.h> +#include <uapi/linux/netfilter/nf_tables.h> + struct nft_reject { enum nft_reject_types type:8; u8 icmp_code; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index bc24a8ec1ce5..c0c0791b1912 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -116,6 +116,7 @@ struct netns_ipv4 { int sysctl_tcp_l3mdev_accept; #endif int sysctl_tcp_mtu_probing; + int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; int sysctl_tcp_min_snd_mss; int sysctl_tcp_probe_threshold; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 98be18ef1ed3..64999ffcb486 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -70,15 +70,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident); -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident); -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident); -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident); - int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); @@ -137,32 +128,6 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, { } -static inline -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - return 0; -} - -static inline -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - return 0; -} - -static inline -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ -} - -static inline -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ -} - static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6b6b01234dd9..d9f359af0b93 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -23,9 +23,6 @@ struct tcf_walker; struct module; struct bpf_flow_keys; -typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, - enum tc_setup_type type, void *type_data); - struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index c757585a05b0..1cace4c69e44 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -32,6 +32,24 @@ static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) return false; } +static inline bool is_tcf_mirred_ingress_redirect(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_INGRESS_REDIR; +#endif + return false; +} + +static inline bool is_tcf_mirred_ingress_mirror(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_INGRESS_MIRROR; +#endif + return false; +} + static inline struct net_device *tcf_mirred_dev(const struct tc_action *a) { return rtnl_dereference(to_mirred(a)->tcfm_dev); diff --git a/include/net/tc_act/tc_mpls.h b/include/net/tc_act/tc_mpls.h index 4bc3d9250ef0..721de4f5733a 100644 --- a/include/net/tc_act/tc_mpls.h +++ b/include/net/tc_act/tc_mpls.h @@ -27,4 +27,79 @@ struct tcf_mpls { }; #define to_mpls(a) ((struct tcf_mpls *)a) +static inline bool is_tcf_mpls(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_MPLS) + return true; +#endif + return false; +} + +static inline u32 tcf_mpls_action(const struct tc_action *a) +{ + u32 tcfm_action; + + rcu_read_lock(); + tcfm_action = rcu_dereference(to_mpls(a)->mpls_p)->tcfm_action; + rcu_read_unlock(); + + return tcfm_action; +} + +static inline __be16 tcf_mpls_proto(const struct tc_action *a) +{ + __be16 tcfm_proto; + + rcu_read_lock(); + tcfm_proto = rcu_dereference(to_mpls(a)->mpls_p)->tcfm_proto; + rcu_read_unlock(); + + return tcfm_proto; +} + +static inline u32 tcf_mpls_label(const struct tc_action *a) +{ + u32 tcfm_label; + + rcu_read_lock(); + tcfm_label = rcu_dereference(to_mpls(a)->mpls_p)->tcfm_label; + rcu_read_unlock(); + + return tcfm_label; +} + +static inline u8 tcf_mpls_tc(const struct tc_action *a) +{ + u8 tcfm_tc; + + rcu_read_lock(); + tcfm_tc = rcu_dereference(to_mpls(a)->mpls_p)->tcfm_tc; + rcu_read_unlock(); + + return tcfm_tc; +} + +static inline u8 tcf_mpls_bos(const struct tc_action *a) +{ + u8 tcfm_bos; + + rcu_read_lock(); + tcfm_bos = rcu_dereference(to_mpls(a)->mpls_p)->tcfm_bos; + rcu_read_unlock(); + + return tcfm_bos; +} + +static inline u8 tcf_mpls_ttl(const struct tc_action *a) +{ + u8 tcfm_ttl; + + rcu_read_lock(); + tcfm_ttl = rcu_dereference(to_mpls(a)->mpls_p)->tcfm_ttl; + rcu_read_unlock(); + + return tcfm_ttl; +} + #endif /* __NET_TC_MPLS_H */ diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 4c04e2985508..b22a1f641f02 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -54,4 +54,31 @@ static inline u32 tcf_skbedit_mark(const struct tc_action *a) return mark; } +/* Return true iff action is ptype */ +static inline bool is_tcf_skbedit_ptype(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + u32 flags; + + if (a->ops && a->ops->id == TCA_ID_SKBEDIT) { + rcu_read_lock(); + flags = rcu_dereference(to_skbedit(a)->params)->flags; + rcu_read_unlock(); + return flags == SKBEDIT_F_PTYPE; + } +#endif + return false; +} + +static inline u32 tcf_skbedit_ptype(const struct tc_action *a) +{ + u16 ptype; + + rcu_read_lock(); + ptype = rcu_dereference(to_skbedit(a)->params)->ptype; + rcu_read_unlock(); + + return ptype; +} + #endif /* __NET_TC_SKBEDIT_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 81e8ade1e6e4..77fe87f7a992 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -64,7 +64,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U -/* The least MTU to use for probing */ +/* The initial MTU to use for probing */ #define TCP_BASE_MSS 1024 /* probing interval, default to 10 minutes as per RFC4821 */ @@ -415,6 +415,16 @@ void tcp_parse_options(const struct net *net, const struct sk_buff *skb, const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* + * BPF SKB-less helpers + */ +u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, + struct tcphdr *th, u32 *cookie); +u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, + struct tcphdr *th, u32 *cookie); +u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, + const struct tcp_request_sock_ops *af_ops, + struct sock *sk, struct tcphdr *th); +/* * TCP v4 functions exported for the inet6 API */ diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 68899fdc985b..8c8420230a10 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -175,7 +175,8 @@ struct _bpf_dtab_netdev { #endif /* __DEVMAP_OBJ_TYPE */ #define devmap_ifindex(fwd, map) \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((map->map_type == BPF_MAP_TYPE_DEVMAP || \ + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \ ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a5aa7d3ac6a1..0e66371bea13 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -134,6 +134,7 @@ enum bpf_map_type { BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, }; /* Note that tracing related programs such as @@ -2713,6 +2714,33 @@ union bpf_attr { * **-EPERM** if no permission to send the *sig*. * * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2824,7 +2852,8 @@ union bpf_attr { FN(strtoul), \ FN(sk_storage_get), \ FN(sk_storage_delete), \ - FN(send_signal), + FN(send_signal), \ + FN(tcp_gen_syncookie), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3507,6 +3536,10 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + struct bpf_flow_keys { __u16 nhoff; __u16 thoff; @@ -3528,6 +3561,8 @@ struct bpf_flow_keys { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; }; + __u32 flags; + __be32 flow_label; }; struct bpf_func_info { diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h index 7bee7a0b9800..3aea5388c8e4 100644 --- a/include/uapi/linux/can/gw.h +++ b/include/uapi/linux/can/gw.h @@ -80,6 +80,10 @@ enum { CGW_DELETED, /* number of deleted CAN frames (see max_hops param) */ CGW_LIM_HOPS, /* limit the number of hops of this specific rule */ CGW_MOD_UID, /* user defined identifier for modification updates */ + CGW_FDMOD_AND, /* CAN FD frame modification binary AND */ + CGW_FDMOD_OR, /* CAN FD frame modification binary OR */ + CGW_FDMOD_XOR, /* CAN FD frame modification binary XOR */ + CGW_FDMOD_SET, /* CAN FD frame modification set alternate values */ __CGW_MAX }; @@ -88,15 +92,18 @@ enum { #define CGW_FLAGS_CAN_ECHO 0x01 #define CGW_FLAGS_CAN_SRC_TSTAMP 0x02 #define CGW_FLAGS_CAN_IIF_TX_OK 0x04 +#define CGW_FLAGS_CAN_FD 0x08 #define CGW_MOD_FUNCS 4 /* AND OR XOR SET */ /* CAN frame elements that are affected by curr. 3 CAN frame modifications */ #define CGW_MOD_ID 0x01 -#define CGW_MOD_DLC 0x02 +#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_DATA 0x04 +#define CGW_MOD_FLAGS 0x08 /* CAN FD flags */ -#define CGW_FRAME_MODS 3 /* ID DLC DATA */ +#define CGW_FRAME_MODS 4 /* ID DLC/LEN DATA FLAGS */ #define MAX_MODFUNCTIONS (CGW_MOD_FUNCS * CGW_FRAME_MODS) @@ -105,7 +112,13 @@ struct cgw_frame_mod { __u8 modtype; } __attribute__((packed)); +struct cgw_fdframe_mod { + struct canfd_frame cf; + __u8 modtype; +} __attribute__((packed)); + #define CGW_MODATTR_LEN sizeof(struct cgw_frame_mod) +#define CGW_FDMODATTR_LEN sizeof(struct cgw_fdframe_mod) struct cgw_csum_xor { __s8 from_idx; diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 9f56fad4785b..1bc70d3a4d39 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -40,15 +40,15 @@ struct can_bittiming { }; /* - * CAN harware-dependent bit-timing constant + * CAN hardware-dependent bit-timing constant * * Used for calculating and checking bit-timing parameters */ struct can_bittiming_const { char name[16]; /* Name of the CAN controller hardware */ - __u32 tseg1_min; /* Time segement 1 = prop_seg + phase_seg1 */ + __u32 tseg1_min; /* Time segment 1 = prop_seg + phase_seg1 */ __u32 tseg1_max; - __u32 tseg2_min; /* Time segement 2 = phase_seg2 */ + __u32 tseg2_min; /* Time segment 2 = phase_seg2 */ __u32 tseg2_max; __u32 sjw_max; /* Synchronisation jump width */ __u32 brp_min; /* Bit-rate prescaler */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ffc993256527..546e75dd74ac 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -107,6 +107,16 @@ enum devlink_command { DEVLINK_CMD_FLASH_UPDATE_END, /* notification only */ DEVLINK_CMD_FLASH_UPDATE_STATUS, /* notification only */ + DEVLINK_CMD_TRAP_GET, /* can dump */ + DEVLINK_CMD_TRAP_SET, + DEVLINK_CMD_TRAP_NEW, + DEVLINK_CMD_TRAP_DEL, + + DEVLINK_CMD_TRAP_GROUP_GET, /* can dump */ + DEVLINK_CMD_TRAP_GROUP_SET, + DEVLINK_CMD_TRAP_GROUP_NEW, + DEVLINK_CMD_TRAP_GROUP_DEL, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -194,6 +204,47 @@ enum devlink_param_fw_load_policy_value { DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH, }; +enum { + DEVLINK_ATTR_STATS_RX_PACKETS, /* u64 */ + DEVLINK_ATTR_STATS_RX_BYTES, /* u64 */ + + __DEVLINK_ATTR_STATS_MAX, + DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1 +}; + +/** + * enum devlink_trap_action - Packet trap action. + * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not + * sent to the CPU. + * @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU. + */ +enum devlink_trap_action { + DEVLINK_TRAP_ACTION_DROP, + DEVLINK_TRAP_ACTION_TRAP, +}; + +/** + * enum devlink_trap_type - Packet trap type. + * @DEVLINK_TRAP_TYPE_DROP: Trap reason is a drop. Trapped packets are only + * processed by devlink and not injected to the + * kernel's Rx path. + * @DEVLINK_TRAP_TYPE_EXCEPTION: Trap reason is an exception. Packet was not + * forwarded as intended due to an exception + * (e.g., missing neighbour entry) and trapped to + * control plane for resolution. Trapped packets + * are processed by devlink and injected to + * the kernel's Rx path. + */ +enum devlink_trap_type { + DEVLINK_TRAP_TYPE_DROP, + DEVLINK_TRAP_TYPE_EXCEPTION, +}; + +enum { + /* Trap can report input port as metadata */ + DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT, +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -348,6 +399,17 @@ enum devlink_attr { DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u16 */ DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u16 */ + DEVLINK_ATTR_STATS, /* nested */ + + DEVLINK_ATTR_TRAP_NAME, /* string */ + /* enum devlink_trap_action */ + DEVLINK_ATTR_TRAP_ACTION, /* u8 */ + /* enum devlink_trap_type */ + DEVLINK_ATTR_TRAP_TYPE, /* u8 */ + DEVLINK_ATTR_TRAP_GENERIC, /* flag */ + DEVLINK_ATTR_TRAP_METADATA, /* nested */ + DEVLINK_ATTR_TRAP_GROUP_NAME, /* string */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 773e476a8e54..1b3c2b643a02 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -237,6 +237,7 @@ struct br_mdb_entry { #define MDB_PERMANENT 1 __u8 state; #define MDB_FLAGS_OFFLOAD (1 << 0) +#define MDB_FLAGS_FAST_LEAVE (1 << 1) __u8 flags; __u16 vid; struct { diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 5edbd0a675fd..75a35dccb675 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -53,6 +53,11 @@ enum { NET_DM_CMD_CONFIG, NET_DM_CMD_START, NET_DM_CMD_STOP, + NET_DM_CMD_PACKET_ALERT, + NET_DM_CMD_CONFIG_GET, + NET_DM_CMD_CONFIG_NEW, + NET_DM_CMD_STATS_GET, + NET_DM_CMD_STATS_NEW, _NET_DM_CMD_MAX, }; @@ -62,4 +67,65 @@ enum { * Our group identifiers */ #define NET_DM_GRP_ALERT 1 + +enum net_dm_attr { + NET_DM_ATTR_UNSPEC, + + NET_DM_ATTR_ALERT_MODE, /* u8 */ + NET_DM_ATTR_PC, /* u64 */ + NET_DM_ATTR_SYMBOL, /* string */ + NET_DM_ATTR_IN_PORT, /* nested */ + NET_DM_ATTR_TIMESTAMP, /* struct timespec */ + NET_DM_ATTR_PROTO, /* u16 */ + NET_DM_ATTR_PAYLOAD, /* binary */ + NET_DM_ATTR_PAD, + NET_DM_ATTR_TRUNC_LEN, /* u32 */ + NET_DM_ATTR_ORIG_LEN, /* u32 */ + NET_DM_ATTR_QUEUE_LEN, /* u32 */ + NET_DM_ATTR_STATS, /* nested */ + NET_DM_ATTR_HW_STATS, /* nested */ + NET_DM_ATTR_ORIGIN, /* u16 */ + NET_DM_ATTR_HW_TRAP_GROUP_NAME, /* string */ + NET_DM_ATTR_HW_TRAP_NAME, /* string */ + NET_DM_ATTR_HW_ENTRIES, /* nested */ + NET_DM_ATTR_HW_ENTRY, /* nested */ + NET_DM_ATTR_HW_TRAP_COUNT, /* u32 */ + NET_DM_ATTR_SW_DROPS, /* flag */ + NET_DM_ATTR_HW_DROPS, /* flag */ + + __NET_DM_ATTR_MAX, + NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1 +}; + +/** + * enum net_dm_alert_mode - Alert mode. + * @NET_DM_ALERT_MODE_SUMMARY: A summary of recent drops is sent to user space. + * @NET_DM_ALERT_MODE_PACKET: Each dropped packet is sent to user space along + * with metadata. + */ +enum net_dm_alert_mode { + NET_DM_ALERT_MODE_SUMMARY, + NET_DM_ALERT_MODE_PACKET, +}; + +enum { + NET_DM_ATTR_PORT_NETDEV_IFINDEX, /* u32 */ + NET_DM_ATTR_PORT_NETDEV_NAME, /* string */ + + __NET_DM_ATTR_PORT_MAX, + NET_DM_ATTR_PORT_MAX = __NET_DM_ATTR_PORT_MAX - 1 +}; + +enum { + NET_DM_ATTR_STATS_DROPPED, /* u64 */ + + __NET_DM_ATTR_STATS_MAX, + NET_DM_ATTR_STATS_MAX = __NET_DM_ATTR_STATS_MAX - 1 +}; + +enum net_dm_origin { + NET_DM_ORIGIN_SW, + NET_DM_ORIGIN_HW, +}; + #endif diff --git a/include/uapi/linux/netfilter/xt_policy.h b/include/uapi/linux/netfilter/xt_policy.h index 323bfa3074c5..4cf2ce2a8a44 100644 --- a/include/uapi/linux/netfilter/xt_policy.h +++ b/include/uapi/linux/netfilter/xt_policy.h @@ -2,6 +2,7 @@ #ifndef _XT_POLICY_H #define _XT_POLICY_H +#include <linux/netfilter.h> #include <linux/types.h> #include <linux/in.h> #include <linux/in6.h> diff --git a/include/uapi/linux/netfilter_ipv4/ipt_LOG.h b/include/uapi/linux/netfilter_ipv4/ipt_LOG.h index 6dec14ba851b..b7cf2c669f40 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_LOG.h @@ -2,8 +2,6 @@ #ifndef _IPT_LOG_H #define _IPT_LOG_H -#warning "Please update iptables, this file will be removed soon!" - /* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IPT_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IPT_LOG_TCPOPT 0x02 /* Log TCP options */ diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h b/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h index 7553a434e4da..23e91a9c2583 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h @@ -2,8 +2,6 @@ #ifndef _IP6T_LOG_H #define _IP6T_LOG_H -#warning "Please update iptables, this file will be removed soon!" - /* make sure not to change this without changing netfilter.h:NF_LOG_* (!) */ #define IP6T_LOG_TCPSEQ 0x01 /* Log TCP sequence numbers */ #define IP6T_LOG_TCPOPT 0x02 /* Log TCP options */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index beb9a9d0c00a..822851d369ab 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -657,7 +657,9 @@ * is used during CSA period. * @NL80211_CMD_FRAME_WAIT_CANCEL: When an off-channel TX was requested, this * command may be used with the corresponding cookie to cancel the wait - * time if it is known that it is no longer necessary. + * time if it is known that it is no longer necessary. This command is + * also sent as an event whenever the driver has completed the off-channel + * wait time. * @NL80211_CMD_ACTION: Alias for @NL80211_CMD_FRAME for backward compatibility. * @NL80211_CMD_FRAME_TX_STATUS: Report TX status of a management frame * transmitted with %NL80211_CMD_FRAME. %NL80211_ATTR_COOKIE identifies @@ -2356,6 +2358,9 @@ enum nl80211_commands { * * @NL80211_ATTR_TWT_RESPONDER: Enable target wait time responder support. * + * @NL80211_ATTR_HE_OBSS_PD: nested attribute for OBSS Packet Detection + * functionality. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2813,6 +2818,8 @@ enum nl80211_attrs { NL80211_ATTR_TWT_RESPONDER, + NL80211_ATTR_HE_OBSS_PD, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -6488,4 +6495,26 @@ enum nl80211_peer_measurement_ftm_resp { NL80211_PMSR_FTM_RESP_ATTR_MAX = NUM_NL80211_PMSR_FTM_RESP_ATTR - 1 }; +/** + * enum nl80211_obss_pd_attributes - OBSS packet detection attributes + * @__NL80211_HE_OBSS_PD_ATTR_INVALID: Invalid + * + * @NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET: the OBSS PD minimum tx power offset. + * @NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET: the OBSS PD maximum tx power offset. + * + * @__NL80211_HE_OBSS_PD_ATTR_LAST: Internal + * @NL80211_HE_OBSS_PD_ATTR_MAX: highest OBSS PD attribute. + */ +enum nl80211_obss_pd_attributes { + __NL80211_HE_OBSS_PD_ATTR_INVALID, + + NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET, + NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET, + + /* keep last */ + __NL80211_HE_OBSS_PD_ATTR_LAST, + NL80211_HE_OBSS_PD_ATTR_MAX = __NL80211_HE_OBSS_PD_ATTR_LAST - 1, +}; + + #endif /* __LINUX_NL80211_H */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 29d781061cd5..e1d9adb212f9 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -22,3 +22,6 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o endif +ifeq ($(CONFIG_SYSFS),y) +obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o +endif diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 0a00eaca6fae..6a6a154cfa7b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -964,7 +964,6 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; - ctx->optlen = max_optlen; return 0; } @@ -984,7 +983,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, .level = *level, .optname = *optname, }; - int ret; + int ret, max_optlen; /* Opportunistic check to see whether we have any BPF program * attached to the hook so we don't waste time allocating @@ -994,10 +993,18 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) return 0; - ret = sockopt_alloc_buf(&ctx, *optlen); + /* Allocate a bit more than the initial user buffer for + * BPF program. The canonical use case is overriding + * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic). + */ + max_optlen = max_t(int, 16, *optlen); + + ret = sockopt_alloc_buf(&ctx, max_optlen); if (ret) return ret; + ctx.optlen = *optlen; + if (copy_from_user(ctx.optval, optval, *optlen) != 0) { ret = -EFAULT; goto out; @@ -1016,7 +1023,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ ret = 1; - } else if (ctx.optlen > *optlen || ctx.optlen < -1) { + } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ ret = -EFAULT; } else { @@ -1063,6 +1070,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, if (ret) return ret; + ctx.optlen = max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d83cf8ccc872..9af048a932b5 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -37,6 +37,12 @@ * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. + * + * The devmap_hash type is a map type which interprets keys as ifindexes and + * indexes these using a hashmap. This allows maps that use ifindex as key to be + * densely packed instead of having holes in the lookup array for unused + * ifindexes. The setup and packet enqueue/send code is shared between the two + * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> @@ -59,10 +65,11 @@ struct xdp_bulk_queue { struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ + struct hlist_node index_hlist; struct bpf_dtab *dtab; - unsigned int bit; struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; + unsigned int idx; /* keep track of map index for tracepoint */ }; struct bpf_dtab { @@ -70,33 +77,45 @@ struct bpf_dtab { struct bpf_dtab_netdev **netdev_map; struct list_head __percpu *flush_list; struct list_head list; + + /* these are only used for DEVMAP_HASH type maps */ + struct hlist_head *dev_index_head; + spinlock_t index_lock; + unsigned int items; + u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +static struct hlist_head *dev_map_create_hash(unsigned int entries) +{ + int i; + struct hlist_head *hash; + + hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + if (hash != NULL) + for (i = 0; i < entries; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; +} + +static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { - struct bpf_dtab *dtab; int err, cpu; u64 cost; - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); + return -EINVAL; /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; - dtab = kzalloc(sizeof(*dtab), GFP_USER); - if (!dtab) - return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&dtab->map, attr); @@ -104,12 +123,18 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); cost += sizeof(struct list_head) * num_possible_cpus(); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + + if (!dtab->n_buckets) /* Overflow check */ + return -EINVAL; + cost += sizeof(struct hlist_head) * dtab->n_buckets; + } + /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) - goto free_dtab; - - err = -ENOMEM; + return -EINVAL; dtab->flush_list = alloc_percpu(struct list_head); if (!dtab->flush_list) @@ -124,19 +149,48 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (!dtab->netdev_map) goto free_percpu; - spin_lock(&dev_map_lock); - list_add_tail_rcu(&dtab->list, &dev_map_list); - spin_unlock(&dev_map_lock); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + if (!dtab->dev_index_head) + goto free_map_area; - return &dtab->map; + spin_lock_init(&dtab->index_lock); + } + return 0; + +free_map_area: + bpf_map_area_free(dtab->netdev_map); free_percpu: free_percpu(dtab->flush_list); free_charge: bpf_map_charge_finish(&dtab->map.memory); -free_dtab: - kfree(dtab); - return ERR_PTR(err); + return -ENOMEM; +} + +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + int err; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + dtab = kzalloc(sizeof(*dtab), GFP_USER); + if (!dtab) + return ERR_PTR(-ENOMEM); + + err = dev_map_init_map(dtab, attr); + if (err) { + kfree(dtab); + return ERR_PTR(err); + } + + spin_lock(&dev_map_lock); + list_add_tail_rcu(&dtab->list, &dev_map_list); + spin_unlock(&dev_map_lock); + + return &dtab->map; } static void dev_map_free(struct bpf_map *map) @@ -188,6 +242,7 @@ static void dev_map_free(struct bpf_map *map) free_percpu(dtab->flush_list); bpf_map_area_free(dtab->netdev_map); + kfree(dtab->dev_index_head); kfree(dtab); } @@ -208,6 +263,70 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, + int idx) +{ + return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; +} + +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct hlist_head *head = dev_map_index_hash(dtab, key); + struct bpf_dtab_netdev *dev; + + hlist_for_each_entry_rcu(dev, head, index_hlist) + if (dev->idx == key) + return dev; + + return NULL; +} + +static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 idx, *next = next_key; + struct bpf_dtab_netdev *dev, *next_dev; + struct hlist_head *head; + int i = 0; + + if (!key) + goto find_first; + + idx = *(u32 *)key; + + dev = __dev_map_hash_lookup_elem(map, idx); + if (!dev) + goto find_first; + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), + struct bpf_dtab_netdev, index_hlist); + + if (next_dev) { + *next = next_dev->idx; + return 0; + } + + i = idx & (dtab->n_buckets - 1); + i++; + + find_first: + for (; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_dtab_netdev, + index_hlist); + if (next_dev) { + *next = next_dev->idx; + return 0; + } + } + + return -ENOENT; +} + static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, bool in_napi_ctx) { @@ -235,7 +354,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, out: bq->count = 0; - trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, + trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx, sent, drops, bq->dev_rx, dev, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); @@ -363,6 +482,15 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key) return dev ? &dev->ifindex : NULL; } +static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, + *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; + + return dev ? &dev->ifindex : NULL; +} + static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { if (dev->dev->netdev_ops->ndo_xdp_xmit) { @@ -412,17 +540,74 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct net *net = current->nsproxy->net_ns; + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + unsigned long flags; + int ret = -ENOENT; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, k); + if (old_dev) { + dtab->items--; + hlist_del_init_rcu(&old_dev->index_hlist); + call_rcu(&old_dev->rcu, __dev_map_entry_free); + ret = 0; + } + spin_unlock_irqrestore(&dtab->index_lock, flags); + + return ret; +} + +static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, + struct bpf_dtab *dtab, + u32 ifindex, + unsigned int idx) +{ gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; + struct bpf_dtab_netdev *dev; + struct xdp_bulk_queue *bq; + int cpu; + + dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), + sizeof(void *), gfp); + if (!dev->bulkq) { + kfree(dev); + return ERR_PTR(-ENOMEM); + } + + for_each_possible_cpu(cpu) { + bq = per_cpu_ptr(dev->bulkq, cpu); + bq->obj = dev; + } + + dev->dev = dev_get_by_index(net, ifindex); + if (!dev->dev) { + free_percpu(dev->bulkq); + kfree(dev); + return ERR_PTR(-EINVAL); + } + + dev->idx = idx; + dev->dtab = dtab; + + return dev; +} + +static int __dev_map_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; u32 ifindex = *(u32 *)value; - struct xdp_bulk_queue *bq; u32 i = *(u32 *)key; - int cpu; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -434,31 +619,9 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); - if (!dev) - return -ENOMEM; - - dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), - sizeof(void *), gfp); - if (!dev->bulkq) { - kfree(dev); - return -ENOMEM; - } - - for_each_possible_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq->obj = dev; - } - - dev->dev = dev_get_by_index(net, ifindex); - if (!dev->dev) { - free_percpu(dev->bulkq); - kfree(dev); - return -EINVAL; - } - - dev->bit = i; - dev->dtab = dtab; + dev = __dev_map_alloc_node(net, dtab, ifindex, i); + if (IS_ERR(dev)) + return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed @@ -472,6 +635,63 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, return 0; } +static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + +static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev, *old_dev; + u32 ifindex = *(u32 *)value; + u32 idx = *(u32 *)key; + unsigned long flags; + + if (unlikely(map_flags > BPF_EXIST || !ifindex)) + return -EINVAL; + + old_dev = __dev_map_hash_lookup_elem(map, idx); + if (old_dev && (map_flags & BPF_NOEXIST)) + return -EEXIST; + + dev = __dev_map_alloc_node(net, dtab, ifindex, idx); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + spin_lock_irqsave(&dtab->index_lock, flags); + + if (old_dev) { + hlist_del_rcu(&old_dev->index_hlist); + } else { + if (dtab->items >= dtab->map.max_entries) { + spin_unlock_irqrestore(&dtab->index_lock, flags); + call_rcu(&dev->rcu, __dev_map_entry_free); + return -E2BIG; + } + dtab->items++; + } + + hlist_add_head_rcu(&dev->index_hlist, + dev_map_index_hash(dtab, idx)); + spin_unlock_irqrestore(&dtab->index_lock, flags); + + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; +} + +static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_hash_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + const struct bpf_map_ops dev_map_ops = { .map_alloc = dev_map_alloc, .map_free = dev_map_free, @@ -482,6 +702,16 @@ const struct bpf_map_ops dev_map_ops = { .map_check_btf = map_check_no_btf, }; +const struct bpf_map_ops dev_map_hash_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_hash_get_next_key, + .map_lookup_elem = dev_map_hash_lookup_elem, + .map_update_elem = dev_map_hash_update_elem, + .map_delete_elem = dev_map_hash_delete_elem, + .map_check_btf = map_check_no_btf, +}; + static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c new file mode 100644 index 000000000000..4659349fc795 --- /dev/null +++ b/kernel/bpf/sysfs_btf.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide kernel BTF information for introspection and use by eBPF tools. + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/kobject.h> +#include <linux/init.h> +#include <linux/sysfs.h> + +/* See scripts/link-vmlinux.sh, gen_btf() func for details */ +extern char __weak _binary__btf_vmlinux_bin_start[]; +extern char __weak _binary__btf_vmlinux_bin_end[]; + +static ssize_t +btf_vmlinux_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t len) +{ + memcpy(buf, _binary__btf_vmlinux_bin_start + off, len); + return len; +} + +static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = { + .attr = { .name = "vmlinux", .mode = 0444, }, + .read = btf_vmlinux_read, +}; + +static struct kobject *btf_kobj; + +static int __init btf_vmlinux_init(void) +{ + int err; + + if (!_binary__btf_vmlinux_bin_start) + return 0; + + btf_kobj = kobject_create_and_add("btf", kernel_kobj); + if (IS_ERR(btf_kobj)) { + err = PTR_ERR(btf_kobj); + btf_kobj = NULL; + return err; + } + + bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end - + _binary__btf_vmlinux_bin_start; + + return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); +} + +subsys_initcall(btf_vmlinux_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c84d83f86141..10c0ff93f52b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3457,6 +3457,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; @@ -3539,6 +3540,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; diff --git a/net/Kconfig b/net/Kconfig index 57f51a279ad6..3101bfcbdd7a 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -430,6 +430,7 @@ config NET_SOCK_MSG config NET_DEVLINK bool default n + imply NET_DROP_MONITOR config PAGE_POOL bool diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index a8cb6b2e20c1..4072e9d394d6 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -953,8 +953,8 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, if (copy > len) copy = len; vaddr = kmap_atomic(skb_frag_page(frag)); - sum = atalk_sum_partial(vaddr + frag->page_offset + - offset - start, copy, sum); + sum = atalk_sum_partial(vaddr + skb_frag_off(frag) + + offset - start, copy, sum); kunmap_atomic(vaddr); if (!(len -= copy)) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 22672cb3e25d..64054edc2e3c 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -79,6 +79,7 @@ static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface) static void batadv_v_iface_disable(struct batadv_hard_iface *hard_iface) { + batadv_v_ogm_iface_disable(hard_iface); batadv_v_elp_iface_disable(hard_iface); } @@ -1081,6 +1082,12 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface) */ atomic_set(&hard_iface->bat_v.throughput_override, 0); atomic_set(&hard_iface->bat_v.elp_interval, 500); + + hard_iface->bat_v.aggr_len = 0; + skb_queue_head_init(&hard_iface->bat_v.aggr_list); + spin_lock_init(&hard_iface->bat_v.aggr_list_lock); + INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq, + batadv_v_ogm_aggr_work); } /** diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index fad95ef64e01..319249f0f85f 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -17,12 +17,14 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> @@ -77,6 +79,20 @@ struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, } /** + * batadv_v_ogm_start_queue_timer() - restart the OGM aggregation timer + * @hard_iface: the interface to use to send the OGM + */ +static void batadv_v_ogm_start_queue_timer(struct batadv_hard_iface *hard_iface) +{ + unsigned int msecs = BATADV_MAX_AGGREGATION_MS * 1000; + + /* msecs * [0.9, 1.1] */ + msecs += prandom_u32() % (msecs / 5) - (msecs / 10); + queue_delayed_work(batadv_event_workqueue, &hard_iface->bat_v.aggr_wq, + msecs_to_jiffies(msecs / 1000)); +} + +/** * batadv_v_ogm_start_timer() - restart the OGM sending timer * @bat_priv: the bat priv with all the soft interface information */ @@ -116,6 +132,130 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, } /** + * batadv_v_ogm_len() - OGMv2 packet length + * @skb: the OGM to check + * + * Return: Length of the given OGMv2 packet, including tvlv length, excluding + * ethernet header length. + */ +static unsigned int batadv_v_ogm_len(struct sk_buff *skb) +{ + struct batadv_ogm2_packet *ogm_packet; + + ogm_packet = (struct batadv_ogm2_packet *)skb->data; + return BATADV_OGM2_HLEN + ntohs(ogm_packet->tvlv_len); +} + +/** + * batadv_v_ogm_queue_left() - check if given OGM still fits aggregation queue + * @skb: the OGM to check + * @hard_iface: the interface to use to send the OGM + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + * + * Return: True, if the given OGMv2 packet still fits, false otherwise. + */ +static bool batadv_v_ogm_queue_left(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface) +{ + unsigned int max = min_t(unsigned int, hard_iface->net_dev->mtu, + BATADV_MAX_AGGREGATION_BYTES); + unsigned int ogm_len = batadv_v_ogm_len(skb); + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + return hard_iface->bat_v.aggr_len + ogm_len <= max; +} + +/** + * batadv_v_ogm_aggr_list_free - free all elements in an aggregation queue + * @hard_iface: the interface holding the aggregation queue + * + * Empties the OGMv2 aggregation queue and frees all the skbs it contained. + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + */ +static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) +{ + struct sk_buff *skb; + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) + kfree_skb(skb); + + hard_iface->bat_v.aggr_len = 0; +} + +/** + * batadv_v_ogm_aggr_send() - flush & send aggregation queue + * @hard_iface: the interface with the aggregation queue to flush + * + * Aggregates all OGMv2 packets currently in the aggregation queue into a + * single OGMv2 packet and transmits this aggregate. + * + * The aggregation queue is empty after this call. + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + */ +static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) +{ + unsigned int aggr_len = hard_iface->bat_v.aggr_len; + struct sk_buff *skb_aggr; + unsigned int ogm_len; + struct sk_buff *skb; + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + if (!aggr_len) + return; + + skb_aggr = dev_alloc_skb(aggr_len + ETH_HLEN + NET_IP_ALIGN); + if (!skb_aggr) { + batadv_v_ogm_aggr_list_free(hard_iface); + return; + } + + skb_reserve(skb_aggr, ETH_HLEN + NET_IP_ALIGN); + skb_reset_network_header(skb_aggr); + + while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) { + hard_iface->bat_v.aggr_len -= batadv_v_ogm_len(skb); + + ogm_len = batadv_v_ogm_len(skb); + skb_put_data(skb_aggr, skb->data, ogm_len); + + consume_skb(skb); + } + + batadv_v_ogm_send_to_if(skb_aggr, hard_iface); +} + +/** + * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface + * @skb: the OGM to queue + * @hard_iface: the interface to queue the OGM on + */ +static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface) +{ + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + + if (!atomic_read(&bat_priv->aggregated_ogms)) { + batadv_v_ogm_send_to_if(skb, hard_iface); + return; + } + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + if (!batadv_v_ogm_queue_left(skb, hard_iface)) + batadv_v_ogm_aggr_send(hard_iface); + + hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); + skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); +} + +/** * batadv_v_ogm_send() - periodic worker broadcasting the own OGM * @work: work queue item */ @@ -210,7 +350,7 @@ static void batadv_v_ogm_send(struct work_struct *work) break; } - batadv_v_ogm_send_to_if(skb_tmp, hard_iface); + batadv_v_ogm_queue_on_if(skb_tmp, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); @@ -224,6 +364,27 @@ out: } /** + * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface + * @work: work queue item + * + * Emits aggregated OGM message in regular intervals. + */ +void batadv_v_ogm_aggr_work(struct work_struct *work) +{ + struct batadv_hard_iface_bat_v *batv; + struct batadv_hard_iface *hard_iface; + + batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work); + hard_iface = container_of(batv, struct batadv_hard_iface, bat_v); + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + batadv_v_ogm_aggr_send(hard_iface); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); + + batadv_v_ogm_start_queue_timer(hard_iface); +} + +/** * batadv_v_ogm_iface_enable() - prepare an interface for B.A.T.M.A.N. V * @hard_iface: the interface to prepare * @@ -235,12 +396,26 @@ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + batadv_v_ogm_start_queue_timer(hard_iface); batadv_v_ogm_start_timer(bat_priv); return 0; } /** + * batadv_v_ogm_iface_disable() - release OGM interface private resources + * @hard_iface: interface for which the resources have to be released + */ +void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface) +{ + cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq); + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + batadv_v_ogm_aggr_list_free(hard_iface); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); +} + +/** * batadv_v_ogm_primary_iface_set() - set a new primary interface * @primary_iface: the new primary interface */ @@ -382,7 +557,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, if_outgoing->net_dev->name, ntohl(ogm_forward->throughput), ogm_forward->ttl, if_incoming->net_dev->name); - batadv_v_ogm_send_to_if(skb, if_outgoing); + batadv_v_ogm_queue_on_if(skb, if_outgoing); out: if (orig_ifinfo) diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index 2a50df7fc2bf..bf16d040461d 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -11,10 +11,13 @@ #include <linux/skbuff.h> #include <linux/types.h> +#include <linux/workqueue.h> int batadv_v_ogm_init(struct batadv_priv *bat_priv); void batadv_v_ogm_free(struct batadv_priv *bat_priv); +void batadv_v_ogm_aggr_work(struct work_struct *work); int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface); +void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface); struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr); void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 3d4c04d87ff3..6967f2e4c3f4 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2019.3" +#define BATADV_SOURCE_VERSION "2019.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c7a2e77ca1da..a1146cb10919 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -943,10 +943,10 @@ static const struct net_device_ops batadv_netdev_ops = { static void batadv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); - strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); - strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); - strlcpy(info->bus_info, "batman", sizeof(info->bus_info)); + strscpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); + strscpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); + strscpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strscpy(info->bus_info, "batman", sizeof(info->bus_info)); } /* Inspired by drivers/net/ethernet/dlink/sundance.c:1702 diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 1efcb97039cd..e5bbc28ed12c 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1070,7 +1070,7 @@ static ssize_t batadv_store_mesh_iface(struct kobject *kobj, dev_hold(net_dev); INIT_WORK(&store_work->work, batadv_store_mesh_iface_work); store_work->net_dev = net_dev; - strlcpy(store_work->soft_iface_name, buff, + strscpy(store_work->soft_iface_name, buff, sizeof(store_work->soft_iface_name)); queue_work(batadv_event_workqueue, &store_work->work); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 6ae139d74e0f..be7c02aa91e2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -117,6 +117,18 @@ struct batadv_hard_iface_bat_v { /** @elp_wq: workqueue used to schedule ELP transmissions */ struct delayed_work elp_wq; + /** @aggr_wq: workqueue used to transmit queued OGM packets */ + struct delayed_work aggr_wq; + + /** @aggr_list: queue for to be aggregated OGM packets */ + struct sk_buff_head aggr_list; + + /** @aggr_len: size of the OGM aggregate (excluding ethernet header) */ + unsigned int aggr_len; + + /** @aggr_list_lock: protects aggr_list */ + spinlock_t aggr_list_lock; + /** * @throughput_override: throughput override to disable link * auto-detection diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 80e6f3a6864d..1153bbcdff72 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -377,6 +377,22 @@ out: return ret; } +static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) +{ + /* make sure the fields we don't use are zeroed */ + if (!range_is_zero(ctx, 0, offsetof(struct bpf_flow_keys, flags))) + return -EINVAL; + + /* flags is allowed */ + + if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) + + FIELD_SIZEOF(struct bpf_flow_keys, flags), + sizeof(struct bpf_flow_keys))) + return -EINVAL; + + return 0; +} + int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) @@ -384,9 +400,11 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, u32 size = kattr->test.data_size_in; struct bpf_flow_dissector ctx = {}; u32 repeat = kattr->test.repeat; + struct bpf_flow_keys *user_ctx; struct bpf_flow_keys flow_keys; u64 time_start, time_spent = 0; const struct ethhdr *eth; + unsigned int flags = 0; u32 retval, duration; void *data; int ret; @@ -395,9 +413,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; - if (kattr->test.ctx_in || kattr->test.ctx_out) - return -EINVAL; - if (size < ETH_HLEN) return -EINVAL; @@ -410,6 +425,18 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (!repeat) repeat = 1; + user_ctx = bpf_ctx_init(kattr, sizeof(struct bpf_flow_keys)); + if (IS_ERR(user_ctx)) { + kfree(data); + return PTR_ERR(user_ctx); + } + if (user_ctx) { + ret = verify_user_bpf_flow_keys(user_ctx); + if (ret) + goto out; + flags = user_ctx->flags; + } + ctx.flow_keys = &flow_keys; ctx.data = data; ctx.data_end = (__u8 *)data + size; @@ -419,7 +446,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, - size); + size, flags); if (signal_pending(current)) { preempt_enable(); @@ -450,8 +477,12 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), retval, duration); + if (!ret) + ret = bpf_ctx_finish(kattr, uattr, user_ctx, + sizeof(struct bpf_flow_keys)); out: + kfree(user_ctx); kfree(data); return ret; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index bf6acd34234d..44594635a972 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -60,6 +60,8 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) e->flags = 0; if (flags & MDB_PG_FLAGS_OFFLOAD) e->flags |= MDB_FLAGS_OFFLOAD; + if (flags & MDB_PG_FLAGS_FAST_LEAVE) + e->flags |= MDB_FLAGS_FAST_LEAVE; } static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) @@ -75,6 +77,53 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) #endif } +static int __mdb_fill_info(struct sk_buff *skb, + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *p) +{ + struct timer_list *mtimer; + struct nlattr *nest_ent; + struct br_mdb_entry e; + u8 flags = 0; + int ifindex; + + memset(&e, 0, sizeof(e)); + if (p) { + ifindex = p->port->dev->ifindex; + mtimer = &p->timer; + flags = p->flags; + } else { + ifindex = mp->br->dev->ifindex; + mtimer = &mp->timer; + } + + __mdb_entry_fill_flags(&e, flags); + e.ifindex = ifindex; + e.vid = mp->addr.vid; + if (mp->addr.proto == htons(ETH_P_IP)) + e.addr.u.ip4 = mp->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + if (mp->addr.proto == htons(ETH_P_IPV6)) + e.addr.u.ip6 = mp->addr.u.ip6; +#endif + e.addr.proto = mp->addr.proto; + nest_ent = nla_nest_start_noflag(skb, + MDBA_MDB_ENTRY_INFO); + if (!nest_ent) + return -EMSGSIZE; + + if (nla_put_nohdr(skb, sizeof(e), &e) || + nla_put_u32(skb, + MDBA_MDB_EATTR_TIMER, + br_timer_value(mtimer))) { + nla_nest_cancel(skb, nest_ent); + return -EMSGSIZE; + } + nla_nest_end(skb, nest_ent); + + return 0; +} + static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { @@ -93,7 +142,6 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; - struct net_bridge_port *port; if (idx < s_idx) goto skip; @@ -104,43 +152,24 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, break; } + if (mp->host_joined) { + err = __mdb_fill_info(skb, mp, NULL); + if (err) { + nla_nest_cancel(skb, nest2); + break; + } + } + for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; pp = &p->next) { - struct nlattr *nest_ent; - struct br_mdb_entry e; - - port = p->port; - if (!port) + if (!p->port) continue; - memset(&e, 0, sizeof(e)); - e.ifindex = port->dev->ifindex; - e.vid = p->addr.vid; - __mdb_entry_fill_flags(&e, p->flags); - if (p->addr.proto == htons(ETH_P_IP)) - e.addr.u.ip4 = p->addr.u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - if (p->addr.proto == htons(ETH_P_IPV6)) - e.addr.u.ip6 = p->addr.u.ip6; -#endif - e.addr.proto = p->addr.proto; - nest_ent = nla_nest_start_noflag(skb, - MDBA_MDB_ENTRY_INFO); - if (!nest_ent) { - nla_nest_cancel(skb, nest2); - err = -EMSGSIZE; - goto out; - } - if (nla_put_nohdr(skb, sizeof(e), &e) || - nla_put_u32(skb, - MDBA_MDB_EATTR_TIMER, - br_timer_value(&p->timer))) { - nla_nest_cancel(skb, nest_ent); + err = __mdb_fill_info(skb, mp, p); + if (err) { nla_nest_cancel(skb, nest2); - err = -EMSGSIZE; goto out; } - nla_nest_end(skb, nest_ent); } nla_nest_end(skb, nest2); skip: @@ -587,6 +616,19 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, return err; } + /* host join */ + if (!port) { + /* don't allow any flags for host-joined groups */ + if (state) + return -EINVAL; + if (mp->host_joined) + return -EEXIST; + + br_multicast_host_join(mp, false); + + return 0; + } + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { @@ -611,19 +653,21 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, { struct br_ip ip; struct net_device *dev; - struct net_bridge_port *p; + struct net_bridge_port *p = NULL; int ret; if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED)) return -EINVAL; - dev = __dev_get_by_index(net, entry->ifindex); - if (!dev) - return -ENODEV; + if (entry->ifindex != br->dev->ifindex) { + dev = __dev_get_by_index(net, entry->ifindex); + if (!dev) + return -ENODEV; - p = br_port_get_rtnl(dev); - if (!p || p->br != br || p->state == BR_STATE_DISABLED) - return -EINVAL; + p = br_port_get_rtnl(dev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + } __mdb_entry_to_br_ip(entry, &ip); @@ -638,9 +682,9 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct net_bridge_vlan_group *vg; + struct net_bridge_port *p = NULL; struct net_device *dev, *pdev; struct br_mdb_entry *entry; - struct net_bridge_port *p; struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -651,18 +695,22 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, br = netdev_priv(dev); + if (entry->ifindex != br->dev->ifindex) { + pdev = __dev_get_by_index(net, entry->ifindex); + if (!pdev) + return -ENODEV; + + p = br_port_get_rtnl(pdev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + vg = nbp_vlan_group(p); + } else { + vg = br_vlan_group(br); + } + /* If vlan filtering is enabled and VLAN is not specified * install mdb entry on all vlans configured on the port. */ - pdev = __dev_get_by_index(net, entry->ifindex); - if (!pdev) - return -ENODEV; - - p = br_port_get_rtnl(pdev); - if (!p || p->br != br || p->state == BR_STATE_DISABLED) - return -EINVAL; - - vg = nbp_vlan_group(p); if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; @@ -698,6 +746,15 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (!mp) goto unlock; + /* host leave */ + if (entry->ifindex == mp->br->dev->ifindex && mp->host_joined) { + br_multicast_host_leave(mp, false); + err = 0; + if (!mp->ports && netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + goto unlock; + } + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { @@ -730,9 +787,9 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct net_bridge_vlan_group *vg; + struct net_bridge_port *p = NULL; struct net_device *dev, *pdev; struct br_mdb_entry *entry; - struct net_bridge_port *p; struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -743,18 +800,22 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, br = netdev_priv(dev); + if (entry->ifindex != br->dev->ifindex) { + pdev = __dev_get_by_index(net, entry->ifindex); + if (!pdev) + return -ENODEV; + + p = br_port_get_rtnl(pdev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + vg = nbp_vlan_group(p); + } else { + vg = br_vlan_group(br); + } + /* If vlan filtering is enabled and VLAN is not specified * delete mdb entry on all vlans configured on the port. */ - pdev = __dev_get_by_index(net, entry->ifindex); - if (!pdev) - return -ENODEV; - - p = br_port_get_rtnl(pdev); - if (!p || p->br != br || p->state == BR_STATE_DISABLED) - return -EINVAL; - - vg = nbp_vlan_group(p); if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f8cac3702712..ad12fe3fca8c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -148,8 +148,7 @@ static void br_multicast_group_expired(struct timer_list *t) if (!netif_running(br->dev) || timer_pending(&mp->timer)) goto out; - mp->host_joined = false; - br_mdb_notify(br->dev, NULL, &mp->addr, RTM_DELMDB, 0); + br_multicast_host_leave(mp, true); if (mp->ports) goto out; @@ -512,6 +511,27 @@ static bool br_port_group_equal(struct net_bridge_port_group *p, return ether_addr_equal(src, p->eth_addr); } +void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify) +{ + if (!mp->host_joined) { + mp->host_joined = true; + if (notify) + br_mdb_notify(mp->br->dev, NULL, &mp->addr, + RTM_NEWMDB, 0); + } + mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval); +} + +void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify) +{ + if (!mp->host_joined) + return; + + mp->host_joined = false; + if (notify) + br_mdb_notify(mp->br->dev, NULL, &mp->addr, RTM_DELMDB, 0); +} + static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, @@ -534,11 +554,7 @@ static int br_multicast_add_group(struct net_bridge *br, goto err; if (!port) { - if (!mp->host_joined) { - mp->host_joined = true; - br_mdb_notify(br->dev, NULL, &mp->addr, RTM_NEWMDB, 0); - } - mod_timer(&mp->timer, now + br->multicast_membership_interval); + br_multicast_host_join(mp, true); goto out; } @@ -1396,7 +1412,7 @@ br_multicast_leave_group(struct net_bridge *br, del_timer(&p->timer); kfree_rcu(p, rcu); br_mdb_notify(br->dev, port, group, RTM_DELMDB, - p->flags); + p->flags | MDB_PG_FLAGS_FAST_LEAVE); if (!mp->ports && !mp->host_joined && netif_running(br->dev)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 646504db0220..ce2ab14ee605 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -199,6 +199,7 @@ struct net_bridge_fdb_entry { #define MDB_PG_FLAGS_PERMANENT BIT(0) #define MDB_PG_FLAGS_OFFLOAD BIT(1) +#define MDB_PG_FLAGS_FAST_LEAVE BIT(2) struct net_bridge_port_group { struct net_bridge_port *port; @@ -701,6 +702,8 @@ void br_multicast_get_stats(const struct net_bridge *br, struct br_mcast_stats *dest); void br_mdb_init(void); void br_mdb_uninit(void); +void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify); +void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify); #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) diff --git a/net/can/Kconfig b/net/can/Kconfig index 0f9fe846ddef..d4319aa3e1b1 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -8,11 +8,12 @@ menuconfig CAN tristate "CAN bus subsystem support" ---help--- Controller Area Network (CAN) is a slow (up to 1Mbit/s) serial - communications protocol which was developed by Bosch in - 1991, mainly for automotive, but now widely used in marine - (NMEA2000), industrial, and medical applications. - More information on the CAN network protocol family PF_CAN - is contained in <Documentation/networking/can.rst>. + communications protocol. Development of the CAN bus started in + 1983 at Robert Bosch GmbH, and the protocol was officially + released in 1986. The CAN bus was originally mainly for automotive, + but is now widely used in marine (NMEA2000), industrial, and medical + applications. More information on the CAN network protocol family + PF_CAN is contained in <Documentation/networking/can.rst>. If you want CAN support you should say Y here and also to the specific driver for your controller(s) below. diff --git a/net/can/af_can.c b/net/can/af_can.c index 80281ef2ccbd..9a9a51847c7c 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -1,5 +1,5 @@ -/* - * af_can.c - Protocol family CAN core module +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +/* af_can.c - Protocol family CAN core module * (used by different CAN protocol modules) * * Copyright (c) 2002-2017 Volkswagen Group Electronic Research @@ -83,18 +83,7 @@ static DEFINE_MUTEX(proto_tab_lock); static atomic_t skbcounter = ATOMIC_INIT(0); -/* - * af_can socket functions - */ - -int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - default: - return -ENOIOCTLCMD; - } -} -EXPORT_SYMBOL(can_ioctl); +/* af_can socket functions */ static void can_sock_destruct(struct sock *sk) { @@ -140,14 +129,13 @@ static int can_create(struct net *net, struct socket *sock, int protocol, err = request_module("can-proto-%d", protocol); - /* - * In case of error we only print a message but don't + /* In case of error we only print a message but don't * return the error code immediately. Below we will * return -EPROTONOSUPPORT */ if (err) - printk_ratelimited(KERN_ERR "can: request_module " - "(can-proto-%d) failed.\n", protocol); + pr_err_ratelimited("can: request_module (can-proto-%d) failed.\n", + protocol); cp = can_get_proto(protocol); } @@ -188,9 +176,7 @@ static int can_create(struct net *net, struct socket *sock, int protocol, return err; } -/* - * af_can tx path - */ +/* af_can tx path */ /** * can_send - transmit a CAN frame (optional with local loopback) @@ -223,11 +209,11 @@ int can_send(struct sk_buff *skb, int loop) skb->protocol = htons(ETH_P_CANFD); if (unlikely(cfd->len > CANFD_MAX_DLEN)) goto inval_skb; - } else + } else { goto inval_skb; + } - /* - * Make sure the CAN frame can pass the selected CAN netdevice. + /* Make sure the CAN frame can pass the selected CAN netdevice. * As structs can_frame and canfd_frame are similar, we can provide * CAN FD frames to legacy CAN drivers as long as the length is <= 8 */ @@ -258,8 +244,7 @@ int can_send(struct sk_buff *skb, int loop) /* indication for the CAN driver: do loopback */ skb->pkt_type = PACKET_LOOPBACK; - /* - * The reference to the originating sock may be required + /* The reference to the originating sock may be required * by the receiving socket to check whether the frame is * its own. Example: can_raw sockopt CAN_RAW_RECV_OWN_MSGS * Therefore we have to ensure that skb->sk remains the @@ -268,8 +253,7 @@ int can_send(struct sk_buff *skb, int loop) */ if (!(skb->dev->flags & IFF_ECHO)) { - /* - * If the interface is not capable to do loopback + /* If the interface is not capable to do loopback * itself, we do it here. */ newskb = skb_clone(skb, GFP_ATOMIC); @@ -312,12 +296,10 @@ inval_skb: } EXPORT_SYMBOL(can_send); -/* - * af_can rx path - */ +/* af_can rx path */ static struct can_dev_rcv_lists *find_dev_rcv_lists(struct net *net, - struct net_device *dev) + struct net_device *dev) { if (!dev) return net->can.can_rx_alldev_list; @@ -409,7 +391,6 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, /* extra filterlists for the subscription of a single non-RTR can_id */ if (((*mask & CAN_EFF_RTR_FLAGS) == CAN_EFF_RTR_FLAGS) && !(*can_id & CAN_RTR_FLAG)) { - if (*can_id & CAN_EFF_FLAG) { if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) return &d->rx_eff[effhash(*can_id)]; @@ -506,9 +487,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, } EXPORT_SYMBOL(can_rx_register); -/* - * can_rx_delete_receiver - rcu callback for single receiver entry removal - */ +/* can_rx_delete_receiver - rcu callback for single receiver entry removal */ static void can_rx_delete_receiver(struct rcu_head *rp) { struct receiver *r = container_of(rp, struct receiver, rcu); @@ -549,16 +528,14 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, d = find_dev_rcv_lists(net, dev); if (!d) { - pr_err("BUG: receive list not found for " - "dev %s, id %03X, mask %03X\n", + pr_err("BUG: receive list not found for dev %s, id %03X, mask %03X\n", DNAME(dev), can_id, mask); goto out; } rl = find_rcv_list(&can_id, &mask, d); - /* - * Search the receiver list for the item to delete. This should + /* Search the receiver list for the item to delete. This should * exist, since no receiver may be unregistered that hasn't * been registered before. */ @@ -569,14 +546,13 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, break; } - /* - * Check for bugs in CAN protocol implementations using af_can.c: + /* Check for bugs in CAN protocol implementations using af_can.c: * 'r' will be NULL if no matching list item was found for removal. */ if (!r) { - WARN(1, "BUG: receive list entry not found for dev %s, " - "id %03X, mask %03X\n", DNAME(dev), can_id, mask); + WARN(1, "BUG: receive list entry not found for dev %s, id %03X, mask %03X\n", + DNAME(dev), can_id, mask); goto out; } @@ -729,7 +705,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, } static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) + struct packet_type *pt, struct net_device *orig_dev) { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; @@ -745,9 +721,7 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, return NET_RX_SUCCESS; } -/* - * af_can protocol functions - */ +/* af_can protocol functions */ /** * can_proto_register - register CAN transport protocol @@ -778,8 +752,9 @@ int can_proto_register(const struct can_proto *cp) if (rcu_access_pointer(proto_tab[proto])) { pr_err("can: protocol %d already registered\n", proto); err = -EBUSY; - } else + } else { RCU_INIT_POINTER(proto_tab[proto], cp); + } mutex_unlock(&proto_tab_lock); @@ -809,9 +784,7 @@ void can_proto_unregister(const struct can_proto *cp) } EXPORT_SYMBOL(can_proto_unregister); -/* - * af_can notifier to create/remove CAN netdevice specific structs - */ +/* af_can notifier to create/remove CAN netdevice specific structs */ static int can_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { @@ -822,7 +795,6 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, return NOTIFY_DONE; switch (msg) { - case NETDEV_REGISTER: /* create new dev_rcv_lists for this device */ @@ -839,15 +811,16 @@ static int can_notifier(struct notifier_block *nb, unsigned long msg, d = dev->ml_priv; if (d) { - if (d->entries) + if (d->entries) { d->remove_on_zero_entries = 1; - else { + } else { kfree(d); dev->ml_priv = NULL; } - } else - pr_err("can: notifier: receive list not found for dev " - "%s\n", dev->name); + } else { + pr_err("can: notifier: receive list not found for dev %s\n", + dev->name); + } spin_unlock(&dev_net(dev)->can.can_rcvlists_lock); @@ -861,13 +834,13 @@ static int can_pernet_init(struct net *net) { spin_lock_init(&net->can.can_rcvlists_lock); net->can.can_rx_alldev_list = - kzalloc(sizeof(struct can_dev_rcv_lists), GFP_KERNEL); + kzalloc(sizeof(*net->can.can_rx_alldev_list), GFP_KERNEL); if (!net->can.can_rx_alldev_list) goto out; - net->can.can_stats = kzalloc(sizeof(struct s_stats), GFP_KERNEL); + net->can.can_stats = kzalloc(sizeof(*net->can.can_stats), GFP_KERNEL); if (!net->can.can_stats) goto out_free_alldev_list; - net->can.can_pstats = kzalloc(sizeof(struct s_pstats), GFP_KERNEL); + net->can.can_pstats = kzalloc(sizeof(*net->can.can_pstats), GFP_KERNEL); if (!net->can.can_pstats) goto out_free_can_stats; @@ -921,9 +894,7 @@ static void can_pernet_exit(struct net *net) kfree(net->can.can_pstats); } -/* - * af_can module init/exit functions - */ +/* af_can module init/exit functions */ static struct packet_type can_packet __read_mostly = { .type = cpu_to_be16(ETH_P_CAN), diff --git a/net/can/af_can.h b/net/can/af_can.h index 9cb3719632bd..9cdb79083623 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -1,5 +1,5 @@ -/* - * Copyright (c) 2002-2007 Volkswagen Group Electronic Research +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -53,7 +53,7 @@ struct receiver { canid_t can_id; canid_t mask; unsigned long matches; - void (*func)(struct sk_buff *, void *); + void (*func)(struct sk_buff *skb, void *data); void *data; char *ident; struct sock *sk; diff --git a/net/can/bcm.c b/net/can/bcm.c index a34ee52f19ea..28fd1a1c8487 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * @@ -105,7 +106,6 @@ struct bcm_op { unsigned long frames_abs, frames_filtered; struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; - struct tasklet_struct tsklet, thrtsklet; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; int rx_ifindex; int cfsiz; @@ -370,25 +370,34 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, } } -static void bcm_tx_start_timer(struct bcm_op *op) +static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt) { + ktime_t ival; + if (op->kt_ival1 && op->count) - hrtimer_start(&op->timer, - ktime_add(ktime_get(), op->kt_ival1), - HRTIMER_MODE_ABS); + ival = op->kt_ival1; else if (op->kt_ival2) - hrtimer_start(&op->timer, - ktime_add(ktime_get(), op->kt_ival2), - HRTIMER_MODE_ABS); + ival = op->kt_ival2; + else + return false; + + hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival)); + return true; } -static void bcm_tx_timeout_tsklet(unsigned long data) +static void bcm_tx_start_timer(struct bcm_op *op) { - struct bcm_op *op = (struct bcm_op *)data; + if (bcm_tx_set_expiry(op, &op->timer)) + hrtimer_start_expires(&op->timer, HRTIMER_MODE_ABS_SOFT); +} + +/* bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */ +static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) +{ + struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { - op->count--; if (!op->count && (op->flags & TX_COUNTEVT)) { @@ -405,22 +414,12 @@ static void bcm_tx_timeout_tsklet(unsigned long data) } bcm_can_tx(op); - } else if (op->kt_ival2) + } else if (op->kt_ival2) { bcm_can_tx(op); + } - bcm_tx_start_timer(op); -} - -/* - * bcm_tx_timeout_handler - performs cyclic CAN frame transmissions - */ -static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) -{ - struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); - - tasklet_schedule(&op->tsklet); - - return HRTIMER_NORESTART; + return bcm_tx_set_expiry(op, &op->timer) ? + HRTIMER_RESTART : HRTIMER_NORESTART; } /* @@ -486,7 +485,7 @@ static void bcm_rx_update_and_send(struct bcm_op *op, /* do not send the saved data - only start throttle timer */ hrtimer_start(&op->thrtimer, ktime_add(op->kt_lastmsg, op->kt_ival2), - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_SOFT); return; } @@ -545,14 +544,21 @@ static void bcm_rx_starttimer(struct bcm_op *op) return; if (op->kt_ival1) - hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL); + hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } -static void bcm_rx_timeout_tsklet(unsigned long data) +/* bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out */ +static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) { - struct bcm_op *op = (struct bcm_op *)data; + struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; + /* if user wants to be informed, when cyclic CAN-Messages come back */ + if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { + /* clear received CAN frames to indicate 'nothing received' */ + memset(op->last_frames, 0, op->nframes * op->cfsiz); + } + /* create notification to user */ msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; @@ -563,25 +569,6 @@ static void bcm_rx_timeout_tsklet(unsigned long data) msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); -} - -/* - * bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out - */ -static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) -{ - struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); - - /* schedule before NET_RX_SOFTIRQ */ - tasklet_hi_schedule(&op->tsklet); - - /* no restart of the timer is done here! */ - - /* if user wants to be informed, when cyclic CAN-Messages come back */ - if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { - /* clear received CAN frames to indicate 'nothing received' */ - memset(op->last_frames, 0, op->nframes * op->cfsiz); - } return HRTIMER_NORESTART; } @@ -589,14 +576,12 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) /* * bcm_rx_do_flush - helper for bcm_rx_thr_flush */ -static inline int bcm_rx_do_flush(struct bcm_op *op, int update, - unsigned int index) +static inline int bcm_rx_do_flush(struct bcm_op *op, unsigned int index) { struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; if ((op->last_frames) && (lcf->flags & RX_THR)) { - if (update) - bcm_rx_changed(op, lcf); + bcm_rx_changed(op, lcf); return 1; } return 0; @@ -604,11 +589,8 @@ static inline int bcm_rx_do_flush(struct bcm_op *op, int update, /* * bcm_rx_thr_flush - Check for throttled data and send it to the userspace - * - * update == 0 : just check if throttled data is available (any irq context) - * update == 1 : check and send throttled data to userspace (soft_irq context) */ -static int bcm_rx_thr_flush(struct bcm_op *op, int update) +static int bcm_rx_thr_flush(struct bcm_op *op) { int updated = 0; @@ -617,24 +599,16 @@ static int bcm_rx_thr_flush(struct bcm_op *op, int update) /* for MUX filter we start at index 1 */ for (i = 1; i < op->nframes; i++) - updated += bcm_rx_do_flush(op, update, i); + updated += bcm_rx_do_flush(op, i); } else { /* for RX_FILTER_ID and simple filter */ - updated += bcm_rx_do_flush(op, update, 0); + updated += bcm_rx_do_flush(op, 0); } return updated; } -static void bcm_rx_thr_tsklet(unsigned long data) -{ - struct bcm_op *op = (struct bcm_op *)data; - - /* push the changed data to the userspace */ - bcm_rx_thr_flush(op, 1); -} - /* * bcm_rx_thr_handler - the time for blocked content updates is over now: * Check for throttled data and send it to the userspace @@ -643,9 +617,7 @@ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer); - tasklet_schedule(&op->thrtsklet); - - if (bcm_rx_thr_flush(op, 0)) { + if (bcm_rx_thr_flush(op)) { hrtimer_forward(hrtimer, ktime_get(), op->kt_ival2); return HRTIMER_RESTART; } else { @@ -741,23 +713,8 @@ static struct bcm_op *bcm_find_op(struct list_head *ops, static void bcm_remove_op(struct bcm_op *op) { - if (op->tsklet.func) { - while (test_bit(TASKLET_STATE_SCHED, &op->tsklet.state) || - test_bit(TASKLET_STATE_RUN, &op->tsklet.state) || - hrtimer_active(&op->timer)) { - hrtimer_cancel(&op->timer); - tasklet_kill(&op->tsklet); - } - } - - if (op->thrtsklet.func) { - while (test_bit(TASKLET_STATE_SCHED, &op->thrtsklet.state) || - test_bit(TASKLET_STATE_RUN, &op->thrtsklet.state) || - hrtimer_active(&op->thrtimer)) { - hrtimer_cancel(&op->thrtimer); - tasklet_kill(&op->thrtsklet); - } - } + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); @@ -990,15 +947,13 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ - hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_tx_timeout_handler; - /* initialize tasklet for tx countevent notification */ - tasklet_init(&op->tsklet, bcm_tx_timeout_tsklet, - (unsigned long) op); - /* currently unused in tx_ops */ - hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); /* add this bcm_op to the list of the tx_ops */ list_add(&op->list, &bo->tx_ops); @@ -1167,20 +1122,14 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->rx_ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ - hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_rx_timeout_handler; - /* initialize tasklet for rx timeout notification */ - tasklet_init(&op->tsklet, bcm_rx_timeout_tsklet, - (unsigned long) op); - - hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); op->thrtimer.function = bcm_rx_thr_handler; - /* initialize tasklet for rx throttle handling */ - tasklet_init(&op->thrtsklet, bcm_rx_thr_tsklet, - (unsigned long) op); - /* add this bcm_op to the list of the rx_ops */ list_add(&op->list, &bo->rx_ops); @@ -1226,12 +1175,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, */ op->kt_lastmsg = 0; hrtimer_cancel(&op->thrtimer); - bcm_rx_thr_flush(op, 1); + bcm_rx_thr_flush(op); } if ((op->flags & STARTTIMER) && op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, - HRTIMER_MODE_REL); + HRTIMER_MODE_REL_SOFT); } /* now we can register for can_ids, if we added a new bcm_op */ @@ -1679,6 +1628,13 @@ static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, return size; } +static int bcm_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + /* no ioctls for socket layer -> hand it down to NIC layer */ + return -ENOIOCTLCMD; +} + static const struct proto_ops bcm_ops = { .family = PF_CAN, .release = bcm_release, @@ -1688,7 +1644,7 @@ static const struct proto_ops bcm_ops = { .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = bcm_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, diff --git a/net/can/gw.c b/net/can/gw.c index 72711053ebe6..65d60c93af29 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1,7 +1,7 @@ -/* - * gw.c - CAN frame Gateway/Router/Bridge with netlink interface +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* gw.c - CAN frame Gateway/Router/Bridge with netlink interface * - * Copyright (c) 2017 Volkswagen Group Electronic Research + * Copyright (c) 2019 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -59,7 +59,7 @@ #include <net/net_namespace.h> #include <net/sock.h> -#define CAN_GW_VERSION "20170425" +#define CAN_GW_VERSION "20190810" #define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); @@ -85,10 +85,10 @@ static struct kmem_cache *cgw_cache __read_mostly; /* structure that contains the (on-the-fly) CAN frame modifications */ struct cf_mod { struct { - struct can_frame and; - struct can_frame or; - struct can_frame xor; - struct can_frame set; + struct canfd_frame and; + struct canfd_frame or; + struct canfd_frame xor; + struct canfd_frame set; } modframe; struct { u8 and; @@ -96,7 +96,7 @@ struct cf_mod { u8 xor; u8 set; } modtype; - void (*modfunc[MAX_MODFUNCTIONS])(struct can_frame *cf, + void (*modfunc[MAX_MODFUNCTIONS])(struct canfd_frame *cf, struct cf_mod *mod); /* CAN frame checksum calculation after CAN frame modifications */ @@ -105,15 +105,15 @@ struct cf_mod { struct cgw_csum_crc8 crc8; } csum; struct { - void (*xor)(struct can_frame *cf, struct cgw_csum_xor *xor); - void (*crc8)(struct can_frame *cf, struct cgw_csum_crc8 *crc8); + void (*xor)(struct canfd_frame *cf, + struct cgw_csum_xor *xor); + void (*crc8)(struct canfd_frame *cf, + struct cgw_csum_crc8 *crc8); } csumfunc; u32 uid; }; - -/* - * So far we just support CAN -> CAN routing and frame modifications. +/* So far we just support CAN -> CAN routing and frame modifications. * * The internal can_can_gw structure contains data and attributes for * a CAN -> CAN gateway job. @@ -151,39 +151,88 @@ struct cgw_job { /* modification functions that are invoked in the hot path in can_can_gw_rcv */ -#define MODFUNC(func, op) static void func(struct can_frame *cf, \ +#define MODFUNC(func, op) static void func(struct canfd_frame *cf, \ struct cf_mod *mod) { op ; } MODFUNC(mod_and_id, cf->can_id &= mod->modframe.and.can_id) -MODFUNC(mod_and_dlc, cf->can_dlc &= mod->modframe.and.can_dlc) +MODFUNC(mod_and_len, cf->len &= mod->modframe.and.len) +MODFUNC(mod_and_flags, cf->flags &= mod->modframe.and.flags) MODFUNC(mod_and_data, *(u64 *)cf->data &= *(u64 *)mod->modframe.and.data) MODFUNC(mod_or_id, cf->can_id |= mod->modframe.or.can_id) -MODFUNC(mod_or_dlc, cf->can_dlc |= mod->modframe.or.can_dlc) +MODFUNC(mod_or_len, cf->len |= mod->modframe.or.len) +MODFUNC(mod_or_flags, cf->flags |= mod->modframe.or.flags) MODFUNC(mod_or_data, *(u64 *)cf->data |= *(u64 *)mod->modframe.or.data) MODFUNC(mod_xor_id, cf->can_id ^= mod->modframe.xor.can_id) -MODFUNC(mod_xor_dlc, cf->can_dlc ^= mod->modframe.xor.can_dlc) +MODFUNC(mod_xor_len, cf->len ^= mod->modframe.xor.len) +MODFUNC(mod_xor_flags, cf->flags ^= mod->modframe.xor.flags) MODFUNC(mod_xor_data, *(u64 *)cf->data ^= *(u64 *)mod->modframe.xor.data) MODFUNC(mod_set_id, cf->can_id = mod->modframe.set.can_id) -MODFUNC(mod_set_dlc, cf->can_dlc = mod->modframe.set.can_dlc) +MODFUNC(mod_set_len, cf->len = mod->modframe.set.len) +MODFUNC(mod_set_flags, cf->flags = mod->modframe.set.flags) MODFUNC(mod_set_data, *(u64 *)cf->data = *(u64 *)mod->modframe.set.data) -static inline void canframecpy(struct can_frame *dst, struct can_frame *src) +static void mod_and_fddata(struct canfd_frame *cf, struct cf_mod *mod) +{ + int i; + + for (i = 0; i < CANFD_MAX_DLEN; i += 8) + *(u64 *)(cf->data + i) &= *(u64 *)(mod->modframe.and.data + i); +} + +static void mod_or_fddata(struct canfd_frame *cf, struct cf_mod *mod) +{ + int i; + + for (i = 0; i < CANFD_MAX_DLEN; i += 8) + *(u64 *)(cf->data + i) |= *(u64 *)(mod->modframe.or.data + i); +} + +static void mod_xor_fddata(struct canfd_frame *cf, struct cf_mod *mod) +{ + int i; + + for (i = 0; i < CANFD_MAX_DLEN; i += 8) + *(u64 *)(cf->data + i) ^= *(u64 *)(mod->modframe.xor.data + i); +} + +static void mod_set_fddata(struct canfd_frame *cf, struct cf_mod *mod) +{ + memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN); +} + +static void canframecpy(struct canfd_frame *dst, struct can_frame *src) { - /* - * Copy the struct members separately to ensure that no uninitialized + /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 3 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; - dst->can_dlc = src->can_dlc; + dst->len = src->can_dlc; *(u64 *)dst->data = *(u64 *)src->data; } -static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re) +static void canfdframecpy(struct canfd_frame *dst, struct canfd_frame *src) { - /* - * absolute dlc values 0 .. 7 => 0 .. 7, e.g. data [0] + /* Copy the struct members separately to ensure that no uninitialized + * data are copied in the 2 bytes hole of the struct. This is needed + * to make easy compares of the data in the struct cf_mod. + */ + + dst->can_id = src->can_id; + dst->flags = src->flags; + dst->len = src->len; + memcpy(dst->data, src->data, CANFD_MAX_DLEN); +} + +static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re, struct rtcanmsg *r) +{ + s8 dlen = CAN_MAX_DLEN; + + if (r->flags & CGW_FLAGS_CAN_FD) + dlen = CANFD_MAX_DLEN; + + /* absolute dlc values 0 .. 7 => 0 .. 7, e.g. data [0] * relative to received dlc -1 .. -8 : * e.g. for received dlc = 8 * -1 => index = 7 (data[7]) @@ -191,27 +240,27 @@ static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re) * -8 => index = 0 (data[0]) */ - if (fr > -9 && fr < 8 && - to > -9 && to < 8 && - re > -9 && re < 8) + if (fr >= -dlen && fr < dlen && + to >= -dlen && to < dlen && + re >= -dlen && re < dlen) return 0; else return -EINVAL; } -static inline int calc_idx(int idx, int rx_dlc) +static inline int calc_idx(int idx, int rx_len) { if (idx < 0) - return rx_dlc + idx; + return rx_len + idx; else return idx; } -static void cgw_csum_xor_rel(struct can_frame *cf, struct cgw_csum_xor *xor) +static void cgw_csum_xor_rel(struct canfd_frame *cf, struct cgw_csum_xor *xor) { - int from = calc_idx(xor->from_idx, cf->can_dlc); - int to = calc_idx(xor->to_idx, cf->can_dlc); - int res = calc_idx(xor->result_idx, cf->can_dlc); + int from = calc_idx(xor->from_idx, cf->len); + int to = calc_idx(xor->to_idx, cf->len); + int res = calc_idx(xor->result_idx, cf->len); u8 val = xor->init_xor_val; int i; @@ -229,7 +278,7 @@ static void cgw_csum_xor_rel(struct can_frame *cf, struct cgw_csum_xor *xor) cf->data[res] = val; } -static void cgw_csum_xor_pos(struct can_frame *cf, struct cgw_csum_xor *xor) +static void cgw_csum_xor_pos(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; @@ -240,7 +289,7 @@ static void cgw_csum_xor_pos(struct can_frame *cf, struct cgw_csum_xor *xor) cf->data[xor->result_idx] = val; } -static void cgw_csum_xor_neg(struct can_frame *cf, struct cgw_csum_xor *xor) +static void cgw_csum_xor_neg(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; @@ -251,11 +300,12 @@ static void cgw_csum_xor_neg(struct can_frame *cf, struct cgw_csum_xor *xor) cf->data[xor->result_idx] = val; } -static void cgw_csum_crc8_rel(struct can_frame *cf, struct cgw_csum_crc8 *crc8) +static void cgw_csum_crc8_rel(struct canfd_frame *cf, + struct cgw_csum_crc8 *crc8) { - int from = calc_idx(crc8->from_idx, cf->can_dlc); - int to = calc_idx(crc8->to_idx, cf->can_dlc); - int res = calc_idx(crc8->result_idx, cf->can_dlc); + int from = calc_idx(crc8->from_idx, cf->len); + int to = calc_idx(crc8->to_idx, cf->len); + int res = calc_idx(crc8->result_idx, cf->len); u8 crc = crc8->init_crc_val; int i; @@ -264,96 +314,102 @@ static void cgw_csum_crc8_rel(struct can_frame *cf, struct cgw_csum_crc8 *crc8) if (from <= to) { for (i = crc8->from_idx; i <= crc8->to_idx; i++) - crc = crc8->crctab[crc^cf->data[i]]; + crc = crc8->crctab[crc ^ cf->data[i]]; } else { for (i = crc8->from_idx; i >= crc8->to_idx; i--) - crc = crc8->crctab[crc^cf->data[i]]; + crc = crc8->crctab[crc ^ cf->data[i]]; } switch (crc8->profile) { - case CGW_CRC8PRF_1U8: - crc = crc8->crctab[crc^crc8->profile_data[0]]; + crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: - crc = crc8->crctab[crc^crc8->profile_data[cf->data[1] & 0xF]]; + crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: - crc = crc8->crctab[crc^(cf->can_id & 0xFF)^ + crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; - } - cf->data[crc8->result_idx] = crc^crc8->final_xor_val; + cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } -static void cgw_csum_crc8_pos(struct can_frame *cf, struct cgw_csum_crc8 *crc8) +static void cgw_csum_crc8_pos(struct canfd_frame *cf, + struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i <= crc8->to_idx; i++) - crc = crc8->crctab[crc^cf->data[i]]; + crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { - case CGW_CRC8PRF_1U8: - crc = crc8->crctab[crc^crc8->profile_data[0]]; + crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: - crc = crc8->crctab[crc^crc8->profile_data[cf->data[1] & 0xF]]; + crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: - crc = crc8->crctab[crc^(cf->can_id & 0xFF)^ + crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } - cf->data[crc8->result_idx] = crc^crc8->final_xor_val; + cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } -static void cgw_csum_crc8_neg(struct can_frame *cf, struct cgw_csum_crc8 *crc8) +static void cgw_csum_crc8_neg(struct canfd_frame *cf, + struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i >= crc8->to_idx; i--) - crc = crc8->crctab[crc^cf->data[i]]; + crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { - case CGW_CRC8PRF_1U8: - crc = crc8->crctab[crc^crc8->profile_data[0]]; + crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: - crc = crc8->crctab[crc^crc8->profile_data[cf->data[1] & 0xF]]; + crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: - crc = crc8->crctab[crc^(cf->can_id & 0xFF)^ + crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } - cf->data[crc8->result_idx] = crc^crc8->final_xor_val; + cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } /* the receive & process & send function */ static void can_can_gw_rcv(struct sk_buff *skb, void *data) { struct cgw_job *gwj = (struct cgw_job *)data; - struct can_frame *cf; + struct canfd_frame *cf; struct sk_buff *nskb; int modidx = 0; - /* - * Do not handle CAN frames routed more than 'max_hops' times. + /* process strictly Classic CAN or CAN FD frames */ + if (gwj->flags & CGW_FLAGS_CAN_FD) { + if (skb->len != CANFD_MTU) + return; + } else { + if (skb->len != CAN_MTU) + return; + } + + /* Do not handle CAN frames routed more than 'max_hops' times. * In general we should never catch this delimiter which is intended * to cover a misconfiguration protection (e.g. circular CAN routes). * @@ -384,8 +440,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) can_skb_prv(skb)->ifindex == gwj->dst.dev->ifindex) return; - /* - * clone the given skb, which has not been done in can_rcv() + /* clone the given skb, which has not been done in can_rcv() * * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. @@ -410,7 +465,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) nskb->dev = gwj->dst.dev; /* pointer to modifiable CAN frame */ - cf = (struct can_frame *)nskb->data; + cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) @@ -419,26 +474,22 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) /* Has the CAN frame been modified? */ if (modidx) { /* get available space for the processed CAN frame type */ - int max_len = nskb->len - offsetof(struct can_frame, data); + int max_len = nskb->len - offsetof(struct canfd_frame, data); /* dlc may have changed, make sure it fits to the CAN frame */ - if (cf->can_dlc > max_len) - goto out_delete; - - /* check for checksum updates in classic CAN length only */ - if (gwj->mod.csumfunc.crc8) { - if (cf->can_dlc > 8) - goto out_delete; - - (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + if (cf->len > max_len) { + /* delete frame due to misconfiguration */ + gwj->deleted_frames++; + kfree_skb(nskb); + return; } - if (gwj->mod.csumfunc.xor) { - if (cf->can_dlc > 8) - goto out_delete; + /* check for checksum updates */ + if (gwj->mod.csumfunc.crc8) + (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); - } } /* clear the skb timestamp if not configured the other way */ @@ -450,14 +501,6 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) gwj->dropped_frames++; else gwj->handled_frames++; - - return; - - out_delete: - /* delete frame due to misconfiguration */ - gwj->deleted_frames++; - kfree_skb(nskb); - return; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) @@ -483,14 +526,12 @@ static int cgw_notifier(struct notifier_block *nb, return NOTIFY_DONE; if (msg == NETDEV_UNREGISTER) { - struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { - if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); @@ -505,7 +546,6 @@ static int cgw_notifier(struct notifier_block *nb, static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, u32 pid, u32 seq, int flags) { - struct cgw_frame_mod mb; struct rtcanmsg *rtcan; struct nlmsghdr *nlh; @@ -542,32 +582,66 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } - if (gwj->mod.modtype.and) { - memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.and; - if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) - goto cancel; - } + if (gwj->flags & CGW_FLAGS_CAN_FD) { + struct cgw_fdframe_mod mb; - if (gwj->mod.modtype.or) { - memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.or; - if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) - goto cancel; - } + if (gwj->mod.modtype.and) { + memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.and; + if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) + goto cancel; + } - if (gwj->mod.modtype.xor) { - memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.xor; - if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) - goto cancel; - } + if (gwj->mod.modtype.or) { + memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.or; + if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) + goto cancel; + } - if (gwj->mod.modtype.set) { - memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.set; - if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) - goto cancel; + if (gwj->mod.modtype.xor) { + memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.xor; + if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) + goto cancel; + } + + if (gwj->mod.modtype.set) { + memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.set; + if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) + goto cancel; + } + } else { + struct cgw_frame_mod mb; + + if (gwj->mod.modtype.and) { + memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.and; + if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) + goto cancel; + } + + if (gwj->mod.modtype.or) { + memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.or; + if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) + goto cancel; + } + + if (gwj->mod.modtype.xor) { + memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.xor; + if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) + goto cancel; + } + + if (gwj->mod.modtype.set) { + memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); + mb.modtype = gwj->mod.modtype.set; + if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) + goto cancel; + } } if (gwj->mod.uid) { @@ -588,7 +662,6 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, } if (gwj->gwtype == CGW_TYPE_CAN_CAN) { - if (gwj->ccgw.filter.can_id || gwj->ccgw.filter.can_mask) { if (nla_put(skb, CGW_FILTER, sizeof(struct can_filter), &gwj->ccgw.filter) < 0) @@ -623,8 +696,9 @@ static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) goto cont; - if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) + if (cgw_put_job(skb, gwj, RTM_NEWROUTE, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) break; cont: idx++; @@ -636,7 +710,7 @@ cont: return skb->len; } -static const struct nla_policy cgw_policy[CGW_MAX+1] = { +static const struct nla_policy cgw_policy[CGW_MAX + 1] = { [CGW_MOD_AND] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_OR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_XOR] = { .len = sizeof(struct cgw_frame_mod) }, @@ -648,14 +722,18 @@ static const struct nla_policy cgw_policy[CGW_MAX+1] = { [CGW_FILTER] = { .len = sizeof(struct can_filter) }, [CGW_LIM_HOPS] = { .type = NLA_U8 }, [CGW_MOD_UID] = { .type = NLA_U32 }, + [CGW_FDMOD_AND] = { .len = sizeof(struct cgw_fdframe_mod) }, + [CGW_FDMOD_OR] = { .len = sizeof(struct cgw_fdframe_mod) }, + [CGW_FDMOD_XOR] = { .len = sizeof(struct cgw_fdframe_mod) }, + [CGW_FDMOD_SET] = { .len = sizeof(struct cgw_fdframe_mod) }, }; /* check for common and gwtype specific attributes */ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, u8 gwtype, void *gwtypeattr, u8 *limhops) { - struct nlattr *tb[CGW_MAX+1]; - struct cgw_frame_mod mb; + struct nlattr *tb[CGW_MAX + 1]; + struct rtcanmsg *r = nlmsg_data(nlh); int modidx = 0; int err = 0; @@ -675,87 +753,166 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, } /* check for AND/OR/XOR/SET modifications */ + if (r->flags & CGW_FLAGS_CAN_FD) { + struct cgw_fdframe_mod mb; - if (tb[CGW_MOD_AND]) { - nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); + if (tb[CGW_FDMOD_AND]) { + nla_memcpy(&mb, tb[CGW_FDMOD_AND], CGW_FDMODATTR_LEN); - canframecpy(&mod->modframe.and, &mb.cf); - mod->modtype.and = mb.modtype; + canfdframecpy(&mod->modframe.and, &mb.cf); + mod->modtype.and = mb.modtype; - if (mb.modtype & CGW_MOD_ID) - mod->modfunc[modidx++] = mod_and_id; + if (mb.modtype & CGW_MOD_ID) + mod->modfunc[modidx++] = mod_and_id; - if (mb.modtype & CGW_MOD_DLC) - mod->modfunc[modidx++] = mod_and_dlc; + if (mb.modtype & CGW_MOD_LEN) + mod->modfunc[modidx++] = mod_and_len; - if (mb.modtype & CGW_MOD_DATA) - mod->modfunc[modidx++] = mod_and_data; - } + if (mb.modtype & CGW_MOD_FLAGS) + mod->modfunc[modidx++] = mod_and_flags; + + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_and_fddata; + } - if (tb[CGW_MOD_OR]) { - nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); + if (tb[CGW_FDMOD_OR]) { + nla_memcpy(&mb, tb[CGW_FDMOD_OR], CGW_FDMODATTR_LEN); - canframecpy(&mod->modframe.or, &mb.cf); - mod->modtype.or = mb.modtype; + canfdframecpy(&mod->modframe.or, &mb.cf); + mod->modtype.or = mb.modtype; - if (mb.modtype & CGW_MOD_ID) - mod->modfunc[modidx++] = mod_or_id; + if (mb.modtype & CGW_MOD_ID) + mod->modfunc[modidx++] = mod_or_id; - if (mb.modtype & CGW_MOD_DLC) - mod->modfunc[modidx++] = mod_or_dlc; + if (mb.modtype & CGW_MOD_LEN) + mod->modfunc[modidx++] = mod_or_len; - if (mb.modtype & CGW_MOD_DATA) - mod->modfunc[modidx++] = mod_or_data; - } + if (mb.modtype & CGW_MOD_FLAGS) + mod->modfunc[modidx++] = mod_or_flags; - if (tb[CGW_MOD_XOR]) { - nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_or_fddata; + } - canframecpy(&mod->modframe.xor, &mb.cf); - mod->modtype.xor = mb.modtype; + if (tb[CGW_FDMOD_XOR]) { + nla_memcpy(&mb, tb[CGW_FDMOD_XOR], CGW_FDMODATTR_LEN); - if (mb.modtype & CGW_MOD_ID) - mod->modfunc[modidx++] = mod_xor_id; + canfdframecpy(&mod->modframe.xor, &mb.cf); + mod->modtype.xor = mb.modtype; - if (mb.modtype & CGW_MOD_DLC) - mod->modfunc[modidx++] = mod_xor_dlc; + if (mb.modtype & CGW_MOD_ID) + mod->modfunc[modidx++] = mod_xor_id; - if (mb.modtype & CGW_MOD_DATA) - mod->modfunc[modidx++] = mod_xor_data; - } + if (mb.modtype & CGW_MOD_LEN) + mod->modfunc[modidx++] = mod_xor_len; - if (tb[CGW_MOD_SET]) { - nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); + if (mb.modtype & CGW_MOD_FLAGS) + mod->modfunc[modidx++] = mod_xor_flags; + + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_xor_fddata; + } - canframecpy(&mod->modframe.set, &mb.cf); - mod->modtype.set = mb.modtype; + if (tb[CGW_FDMOD_SET]) { + nla_memcpy(&mb, tb[CGW_FDMOD_SET], CGW_FDMODATTR_LEN); + + canfdframecpy(&mod->modframe.set, &mb.cf); + mod->modtype.set = mb.modtype; + + 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_FLAGS) + mod->modfunc[modidx++] = mod_set_flags; + + if (mb.modtype & CGW_MOD_DATA) + mod->modfunc[modidx++] = mod_set_fddata; + } + } else { + struct cgw_frame_mod mb; - if (mb.modtype & CGW_MOD_ID) - mod->modfunc[modidx++] = mod_set_id; + if (tb[CGW_MOD_AND]) { + nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); - if (mb.modtype & CGW_MOD_DLC) - mod->modfunc[modidx++] = mod_set_dlc; + canframecpy(&mod->modframe.and, &mb.cf); + mod->modtype.and = mb.modtype; - if (mb.modtype & CGW_MOD_DATA) - mod->modfunc[modidx++] = mod_set_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_DATA) + mod->modfunc[modidx++] = mod_and_data; + } + + if (tb[CGW_MOD_OR]) { + nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); + + canframecpy(&mod->modframe.or, &mb.cf); + mod->modtype.or = mb.modtype; + + 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_DATA) + mod->modfunc[modidx++] = mod_or_data; + } + + if (tb[CGW_MOD_XOR]) { + nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); + + canframecpy(&mod->modframe.xor, &mb.cf); + mod->modtype.xor = mb.modtype; + + 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_DATA) + mod->modfunc[modidx++] = mod_xor_data; + } + + if (tb[CGW_MOD_SET]) { + nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); + + canframecpy(&mod->modframe.set, &mb.cf); + mod->modtype.set = mb.modtype; + + 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_DATA) + mod->modfunc[modidx++] = mod_set_data; + } } /* check for checksum operations after CAN frame modifications */ if (modidx) { - if (tb[CGW_CS_CRC8]) { struct cgw_csum_crc8 *c = nla_data(tb[CGW_CS_CRC8]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, - c->result_idx); + c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.crc8, tb[CGW_CS_CRC8], CGW_CS_CRC8_LEN); - /* - * select dedicated processing function to reduce + /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || @@ -771,15 +928,14 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, struct cgw_csum_xor *c = nla_data(tb[CGW_CS_XOR]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, - c->result_idx); + c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.xor, tb[CGW_CS_XOR], CGW_CS_XOR_LEN); - /* - * select dedicated processing function to reduce + /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || @@ -791,16 +947,14 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, mod->csumfunc.xor = cgw_csum_xor_neg; } - if (tb[CGW_MOD_UID]) { + if (tb[CGW_MOD_UID]) nla_memcpy(&mod->uid, tb[CGW_MOD_UID], sizeof(u32)); - } } if (gwtype == CGW_TYPE_CAN_CAN) { - /* check CGW_TYPE_CAN_CAN specific attributes */ - struct can_can_gw *ccgw = (struct can_can_gw *)gwtypeattr; + memset(ccgw, 0, sizeof(*ccgw)); /* check for can_filter in attributes */ @@ -861,12 +1015,10 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, return err; if (mod.uid) { - ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { - if (gwj->mod.uid != mod.uid) continue; @@ -987,7 +1139,6 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { - if (gwj->flags != r->flags) continue; diff --git a/net/can/proc.c b/net/can/proc.c index 70fea17bb04c..edb822c31902 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * proc.c - procfs support for Protocol family CAN core module * diff --git a/net/can/raw.c b/net/can/raw.c index afcbff063a67..fdbc36140e9b 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -1,5 +1,5 @@ -/* - * raw.c - Raw sockets for protocol family CAN +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* raw.c - Raw sockets for protocol family CAN * * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. @@ -64,8 +64,7 @@ MODULE_ALIAS("can-proto-1"); #define MASK_ALL 0 -/* - * A raw socket has a list of can_filters attached to it, each receiving +/* A raw socket has a list of can_filters attached to it, each receiving * the CAN frames matching that filter. If the filter list is empty, * no CAN frames will be received by the socket. The default after * opening the socket, is to have one filter which receives all frames. @@ -96,8 +95,7 @@ struct raw_sock { struct uniqframe __percpu *uniq; }; -/* - * Return pointer to store the extra msg flags for raw_recvmsg(). +/* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. */ @@ -156,8 +154,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!skb) return; - /* - * Put the datagram to the queue so that raw_recvmsg() can + /* Put the datagram to the queue so that raw_recvmsg() can * get it from there. We need to pass the interface index to * raw_recvmsg(). We pass a whole struct sockaddr_can in skb->cb * containing the interface index. @@ -283,7 +280,6 @@ static int raw_notifier(struct notifier_block *nb, return NOTIFY_DONE; switch (msg) { - case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ @@ -369,8 +365,9 @@ static int raw_release(struct socket *sock) raw_disable_allfilters(dev_net(dev), dev, sk); dev_put(dev); } - } else + } else { raw_disable_allfilters(sock_net(sk), NULL, sk); + } } if (ro->count > 1) @@ -450,8 +447,9 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) dev, sk); dev_put(dev); } - } else + } else { raw_disable_allfilters(sock_net(sk), NULL, sk); + } } ro->ifindex = ifindex; ro->bound = 1; @@ -502,7 +500,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EINVAL; switch (optname) { - case CAN_RAW_FILTER: if (optlen % sizeof(struct can_filter) != 0) return -EINVAL; @@ -665,17 +662,18 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; switch (optname) { - case CAN_RAW_FILTER: lock_sock(sk); if (ro->count > 0) { int fsize = ro->count * sizeof(struct can_filter); + if (len > fsize) len = fsize; if (copy_to_user(optval, ro->filter, len)) err = -EFAULT; - } else + } else { len = 0; + } release_sock(sk); if (!err) @@ -742,8 +740,9 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return -EINVAL; ifindex = addr->can_ifindex; - } else + } else { ifindex = ro->ifindex; + } dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) @@ -836,6 +835,13 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, return size; } +static int raw_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + /* no ioctls for socket layer -> hand it down to NIC layer */ + return -ENOIOCTLCMD; +} + static const struct proto_ops raw_ops = { .family = PF_CAN, .release = raw_release, @@ -845,7 +851,7 @@ static const struct proto_ops raw_ops = { .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, - .ioctl = can_ioctl, /* use can_ioctl() from af_can.c */ + .ioctl = raw_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, @@ -879,7 +885,7 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) - printk(KERN_ERR "can: registration of raw protocol failed\n"); + pr_err("can: registration of raw protocol failed\n"); return err; } diff --git a/net/core/datagram.c b/net/core/datagram.c index 45a162ef5e02..4cc8dc5db2b7 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -442,8 +442,8 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - n = cb(vaddr + frag->page_offset + - offset - start, copy, data, to); + n = cb(vaddr + skb_frag_off(frag) + offset - start, + copy, data, to); kunmap(page); offset += n; if (n != copy) @@ -573,7 +573,7 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, if (copy > len) copy = len; copied = copy_page_from_iter(skb_frag_page(frag), - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, from); if (copied != copy) goto fault; diff --git a/net/core/dev.c b/net/core/dev.c index 0891f499c1bb..49589ed2018d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3963,6 +3963,8 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; +/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ +int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -5486,7 +5488,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) skb->data_len -= grow; skb->tail += grow; - pinfo->frags[0].page_offset += grow; + skb_frag_off_add(&pinfo->frags[0], grow); skb_frag_size_sub(&pinfo->frags[0], grow); if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { @@ -5747,6 +5749,26 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@ -5756,8 +5778,8 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, case GRO_HELD: __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL && netif_receive_skb_internal(skb)) - ret = GRO_DROP; + if (ret == GRO_NORMAL) + gro_normal_one(napi, skb); break; case GRO_DROP: @@ -6034,6 +6056,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; + gro_normal_list(n); + if (n->gro_bitmask) { unsigned long timeout = 0; @@ -6119,10 +6143,19 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, BUSY_POLL_BUDGET); + /* We can't gro_normal_list() here, because napi->poll() might have + * rearmed the napi (napi_complete_done()) in which case it could + * already be running on another CPU. + */ trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) + if (rc == BUSY_POLL_BUDGET) { + /* As the whole budget was spent, we still own the napi so can + * safely handle the rx_list. + */ + gro_normal_list(napi); __napi_schedule(napi); + } local_bh_enable(); } @@ -6167,6 +6200,7 @@ restart: } work = napi_poll(napi, BUSY_POLL_BUDGET); trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), @@ -6272,6 +6306,8 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, @@ -6368,6 +6404,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } + gro_normal_list(n); + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. diff --git a/net/core/devlink.c b/net/core/devlink.c index 4f40aeace902..650f36379203 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -18,6 +18,8 @@ #include <linux/spinlock.h> #include <linux/refcount.h> #include <linux/workqueue.h> +#include <linux/u64_stats_sync.h> +#include <linux/timekeeping.h> #include <rdma/ib_verbs.h> #include <net/netlink.h> #include <net/genetlink.h> @@ -25,6 +27,7 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/devlink.h> +#include <net/drop_monitor.h> #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> @@ -342,7 +345,6 @@ struct devlink_snapshot { struct list_head list; struct devlink_region *region; devlink_snapshot_data_dest_t *data_destructor; - u64 data_len; u8 *data; u32 id; }; @@ -371,14 +373,6 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -static void devlink_region_snapshot_del(struct devlink_snapshot *snapshot) -{ - snapshot->region->cur_snapshots--; - list_del(&snapshot->list); - (*snapshot->data_destructor)(snapshot->data); - kfree(snapshot); -} - #define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) #define DEVLINK_NL_FLAG_NEED_PORT BIT(1) #define DEVLINK_NL_FLAG_NEED_SB BIT(2) @@ -560,7 +554,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; - spin_lock(&devlink_port->type_lock); + spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && @@ -585,7 +579,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, ibdev->name)) goto nla_put_failure_type_locked; } - spin_unlock(&devlink_port->type_lock); + spin_unlock_bh(&devlink_port->type_lock); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; @@ -593,7 +587,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, return 0; nla_put_failure_type_locked: - spin_unlock(&devlink_port->type_lock); + spin_unlock_bh(&devlink_port->type_lock); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -3596,6 +3590,16 @@ out_free_msg: nlmsg_free(msg); } +static void devlink_region_snapshot_del(struct devlink_region *region, + struct devlink_snapshot *snapshot) +{ + devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); + region->cur_snapshots--; + list_del(&snapshot->list); + (*snapshot->data_destructor)(snapshot->data); + kfree(snapshot); +} + static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -3691,8 +3695,7 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, if (!snapshot) return -EINVAL; - devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); - devlink_region_snapshot_del(snapshot); + devlink_region_snapshot_del(region, snapshot); return 0; } @@ -3748,8 +3751,8 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, if (!snapshot) return -EINVAL; - if (end_offset > snapshot->data_len || dump) - end_offset = snapshot->data_len; + if (end_offset > region->size || dump) + end_offset = region->size; while (curr_offset < end_offset) { u32 data_size; @@ -5154,6 +5157,571 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, return 0; } +struct devlink_stats { + u64 rx_bytes; + u64 rx_packets; + struct u64_stats_sync syncp; +}; + +/** + * struct devlink_trap_group_item - Packet trap group attributes. + * @group: Immutable packet trap group attributes. + * @refcount: Number of trap items using the group. + * @list: trap_group_list member. + * @stats: Trap group statistics. + * + * Describes packet trap group attributes. Created by devlink during trap + * registration. + */ +struct devlink_trap_group_item { + const struct devlink_trap_group *group; + refcount_t refcount; + struct list_head list; + struct devlink_stats __percpu *stats; +}; + +/** + * struct devlink_trap_item - Packet trap attributes. + * @trap: Immutable packet trap attributes. + * @group_item: Associated group item. + * @list: trap_list member. + * @action: Trap action. + * @stats: Trap statistics. + * @priv: Driver private information. + * + * Describes both mutable and immutable packet trap attributes. Created by + * devlink during trap registration and used for all trap related operations. + */ +struct devlink_trap_item { + const struct devlink_trap *trap; + struct devlink_trap_group_item *group_item; + struct list_head list; + enum devlink_trap_action action; + struct devlink_stats __percpu *stats; + void *priv; +}; + +static struct devlink_trap_item * +devlink_trap_item_lookup(struct devlink *devlink, const char *name) +{ + struct devlink_trap_item *trap_item; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (!strcmp(trap_item->trap->name, name)) + return trap_item; + } + + return NULL; +} + +static struct devlink_trap_item * +devlink_trap_item_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + struct nlattr *attr; + + if (!info->attrs[DEVLINK_ATTR_TRAP_NAME]) + return NULL; + attr = info->attrs[DEVLINK_ATTR_TRAP_NAME]; + + return devlink_trap_item_lookup(devlink, nla_data(attr)); +} + +static int +devlink_trap_action_get_from_info(struct genl_info *info, + enum devlink_trap_action *p_trap_action) +{ + u8 val; + + val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]); + switch (val) { + case DEVLINK_TRAP_ACTION_DROP: /* fall-through */ + case DEVLINK_TRAP_ACTION_TRAP: + *p_trap_action = val; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int devlink_trap_metadata_put(struct sk_buff *msg, + const struct devlink_trap *trap) +{ + struct nlattr *attr; + + attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA); + if (!attr) + return -EMSGSIZE; + + if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, + struct devlink_stats *stats) +{ + int i; + + memset(stats, 0, sizeof(*stats)); + for_each_possible_cpu(i) { + struct devlink_stats *cpu_stats; + u64 rx_packets, rx_bytes; + unsigned int start; + + cpu_stats = per_cpu_ptr(trap_stats, i); + do { + start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + rx_packets = cpu_stats->rx_packets; + rx_bytes = cpu_stats->rx_bytes; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; + } +} + +static int devlink_trap_stats_put(struct sk_buff *msg, + struct devlink_stats __percpu *trap_stats) +{ + struct devlink_stats stats; + struct nlattr *attr; + + devlink_trap_stats_read(trap_stats, &stats); + + attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, + stats.rx_packets, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, + stats.rx_bytes, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd, u32 portid, u32 seq, + int flags) +{ + struct devlink_trap_group_item *group_item = trap_item->group_item; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, + group_item->group->name)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name)) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type)) + goto nla_put_failure; + + if (trap_item->trap->generic && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action)) + goto nla_put_failure; + + err = devlink_trap_metadata_put(msg, trap_item->trap); + if (err) + goto nla_put_failure; + + err = devlink_trap_stats_put(msg, trap_item->stats); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_trap_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_item *trap_item; + struct sk_buff *msg; + int err; + + if (list_empty(&devlink->trap_list)) + return -EOPNOTSUPP; + + trap_item = devlink_trap_item_get_from_info(devlink, info); + if (!trap_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_trap_fill(msg, devlink, trap_item, + DEVLINK_CMD_TRAP_NEW, info->snd_portid, + info->snd_seq, 0); + if (err) + goto err_trap_fill; + + return genlmsg_reply(msg, info); + +err_trap_fill: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_trap_item *trap_item; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_trap_fill(msg, devlink, trap_item, + DEVLINK_CMD_TRAP_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int __devlink_trap_action_set(struct devlink *devlink, + struct devlink_trap_item *trap_item, + enum devlink_trap_action trap_action, + struct netlink_ext_ack *extack) +{ + int err; + + if (trap_item->action != trap_action && + trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Cannot change action of non-drop traps. Skipping"); + return 0; + } + + err = devlink->ops->trap_action_set(devlink, trap_item->trap, + trap_action); + if (err) + return err; + + trap_item->action = trap_action; + + return 0; +} + +static int devlink_trap_action_set(struct devlink *devlink, + struct devlink_trap_item *trap_item, + struct genl_info *info) +{ + enum devlink_trap_action trap_action; + int err; + + if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) + return 0; + + err = devlink_trap_action_get_from_info(info, &trap_action); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); + return -EINVAL; + } + + return __devlink_trap_action_set(devlink, trap_item, trap_action, + info->extack); +} + +static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_item *trap_item; + int err; + + if (list_empty(&devlink->trap_list)) + return -EOPNOTSUPP; + + trap_item = devlink_trap_item_get_from_info(devlink, info); + if (!trap_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); + return -ENOENT; + } + + err = devlink_trap_action_set(devlink, trap_item, info); + if (err) + return err; + + return 0; +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_lookup(struct devlink *devlink, const char *name) +{ + struct devlink_trap_group_item *group_item; + + list_for_each_entry(group_item, &devlink->trap_group_list, list) { + if (!strcmp(group_item->group->name, name)) + return group_item; + } + + return NULL; +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *name; + + if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]) + return NULL; + name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]); + + return devlink_trap_group_item_lookup(devlink, name); +} + +static int +devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd, u32 portid, u32 seq, + int flags) +{ + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, + group_item->group->name)) + goto nla_put_failure; + + if (group_item->group->generic && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) + goto nla_put_failure; + + err = devlink_trap_stats_put(msg, group_item->stats); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_trap_group_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_group_item *group_item; + struct sk_buff *msg; + int err; + + if (list_empty(&devlink->trap_group_list)) + return -EOPNOTSUPP; + + group_item = devlink_trap_group_item_get_from_info(devlink, info); + if (!group_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_trap_group_fill(msg, devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) + goto err_trap_group_fill; + + return genlmsg_reply(msg, info); + +err_trap_group_fill: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + enum devlink_command cmd = DEVLINK_CMD_TRAP_GROUP_NEW; + struct devlink_trap_group_item *group_item; + u32 portid = NETLINK_CB(cb->skb).portid; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(group_item, &devlink->trap_group_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_trap_group_fill(msg, devlink, + group_item, cmd, + portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int +__devlink_trap_group_action_set(struct devlink *devlink, + struct devlink_trap_group_item *group_item, + enum devlink_trap_action trap_action, + struct netlink_ext_ack *extack) +{ + const char *group_name = group_item->group->name; + struct devlink_trap_item *trap_item; + int err; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (strcmp(trap_item->trap->group.name, group_name)) + continue; + err = __devlink_trap_action_set(devlink, trap_item, + trap_action, extack); + if (err) + return err; + } + + return 0; +} + +static int +devlink_trap_group_action_set(struct devlink *devlink, + struct devlink_trap_group_item *group_item, + struct genl_info *info) +{ + enum devlink_trap_action trap_action; + int err; + + if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) + return 0; + + err = devlink_trap_action_get_from_info(info, &trap_action); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); + return -EINVAL; + } + + err = __devlink_trap_group_action_set(devlink, group_item, trap_action, + info->extack); + if (err) + return err; + + return 0; +} + +static int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_group_item *group_item; + int err; + + if (list_empty(&devlink->trap_group_list)) + return -EOPNOTSUPP; + + group_item = devlink_trap_group_item_get_from_info(devlink, info); + if (!group_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); + return -ENOENT; + } + + err = devlink_trap_group_action_set(devlink, group_item, info); + if (err) + return err; + + return 0; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -5184,6 +5752,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -5483,6 +6054,32 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_TRAP_GET, + .doit = devlink_nl_cmd_trap_get_doit, + .dumpit = devlink_nl_cmd_trap_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_TRAP_SET, + .doit = devlink_nl_cmd_trap_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_GET, + .doit = devlink_nl_cmd_trap_group_get_doit, + .dumpit = devlink_nl_cmd_trap_group_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_SET, + .doit = devlink_nl_cmd_trap_group_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -5528,6 +6125,8 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->param_list); INIT_LIST_HEAD(&devlink->region_list); INIT_LIST_HEAD(&devlink->reporter_list); + INIT_LIST_HEAD(&devlink->trap_list); + INIT_LIST_HEAD(&devlink->trap_group_list); mutex_init(&devlink->lock); mutex_init(&devlink->reporters_lock); return devlink; @@ -5574,6 +6173,8 @@ void devlink_free(struct devlink *devlink) { mutex_destroy(&devlink->reporters_lock); mutex_destroy(&devlink->lock); + WARN_ON(!list_empty(&devlink->trap_group_list)); + WARN_ON(!list_empty(&devlink->trap_list)); WARN_ON(!list_empty(&devlink->reporter_list)); WARN_ON(!list_empty(&devlink->region_list)); WARN_ON(!list_empty(&devlink->param_list)); @@ -5678,10 +6279,10 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, if (WARN_ON(!devlink_port->registered)) return; devlink_port_type_warn_cancel(devlink_port); - spin_lock(&devlink_port->type_lock); + spin_lock_bh(&devlink_port->type_lock); devlink_port->type = type; devlink_port->type_dev = type_dev; - spin_unlock(&devlink_port->type_lock); + spin_unlock_bh(&devlink_port->type_lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } @@ -6744,7 +7345,7 @@ void devlink_region_destroy(struct devlink_region *region) /* Free all snapshots of region */ list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) - devlink_region_snapshot_del(snapshot); + devlink_region_snapshot_del(region, snapshot); list_del(®ion->list); @@ -6784,12 +7385,11 @@ EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); * The @snapshot_id should be obtained using the getter function. * * @region: devlink region of the snapshot - * @data_len: size of snapshot data * @data: snapshot data * @snapshot_id: snapshot id to be created * @data_destructor: pointer to destructor function to free data */ -int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, +int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor) { @@ -6819,7 +7419,6 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, snapshot->id = snapshot_id; snapshot->region = region; snapshot->data = data; - snapshot->data_len = data_len; snapshot->data_destructor = data_destructor; list_add_tail(&snapshot->list, ®ion->snapshot_list); @@ -6836,6 +7435,475 @@ unlock: } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); +#define DEVLINK_TRAP(_id, _type) \ + { \ + .type = DEVLINK_TRAP_TYPE_##_type, \ + .id = DEVLINK_TRAP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \ + } + +static const struct devlink_trap devlink_trap_generic[] = { + DEVLINK_TRAP(SMAC_MC, DROP), + DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP), + DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP), + DEVLINK_TRAP(INGRESS_STP_FILTER, DROP), + DEVLINK_TRAP(EMPTY_TX_LIST, DROP), + DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP), + DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), + DEVLINK_TRAP(TTL_ERROR, EXCEPTION), + DEVLINK_TRAP(TAIL_DROP, DROP), +}; + +#define DEVLINK_TRAP_GROUP(_id) \ + { \ + .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \ + } + +static const struct devlink_trap_group devlink_trap_group_generic[] = { + DEVLINK_TRAP_GROUP(L2_DROPS), + DEVLINK_TRAP_GROUP(L3_DROPS), + DEVLINK_TRAP_GROUP(BUFFER_DROPS), +}; + +static int devlink_trap_generic_verify(const struct devlink_trap *trap) +{ + if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX) + return -EINVAL; + + if (strcmp(trap->name, devlink_trap_generic[trap->id].name)) + return -EINVAL; + + if (trap->type != devlink_trap_generic[trap->id].type) + return -EINVAL; + + return 0; +} + +static int devlink_trap_driver_verify(const struct devlink_trap *trap) +{ + int i; + + if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) { + if (!strcmp(trap->name, devlink_trap_generic[i].name)) + return -EEXIST; + } + + return 0; +} + +static int devlink_trap_verify(const struct devlink_trap *trap) +{ + if (!trap || !trap->name || !trap->group.name) + return -EINVAL; + + if (trap->generic) + return devlink_trap_generic_verify(trap); + else + return devlink_trap_driver_verify(trap); +} + +static int +devlink_trap_group_generic_verify(const struct devlink_trap_group *group) +{ + if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) + return -EINVAL; + + if (strcmp(group->name, devlink_trap_group_generic[group->id].name)) + return -EINVAL; + + return 0; +} + +static int +devlink_trap_group_driver_verify(const struct devlink_trap_group *group) +{ + int i; + + if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) { + if (!strcmp(group->name, devlink_trap_group_generic[i].name)) + return -EEXIST; + } + + return 0; +} + +static int devlink_trap_group_verify(const struct devlink_trap_group *group) +{ + if (group->generic) + return devlink_trap_group_generic_verify(group); + else + return devlink_trap_group_driver_verify(group); +} + +static void +devlink_trap_group_notify(struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW && + cmd != DEVLINK_CMD_TRAP_GROUP_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0, + 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_create(struct devlink *devlink, + const struct devlink_trap_group *group) +{ + struct devlink_trap_group_item *group_item; + int err; + + err = devlink_trap_group_verify(group); + if (err) + return ERR_PTR(err); + + group_item = kzalloc(sizeof(*group_item), GFP_KERNEL); + if (!group_item) + return ERR_PTR(-ENOMEM); + + group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); + if (!group_item->stats) { + err = -ENOMEM; + goto err_stats_alloc; + } + + group_item->group = group; + refcount_set(&group_item->refcount, 1); + + if (devlink->ops->trap_group_init) { + err = devlink->ops->trap_group_init(devlink, group); + if (err) + goto err_group_init; + } + + list_add_tail(&group_item->list, &devlink->trap_group_list); + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW); + + return group_item; + +err_group_init: + free_percpu(group_item->stats); +err_stats_alloc: + kfree(group_item); + return ERR_PTR(err); +} + +static void +devlink_trap_group_item_destroy(struct devlink *devlink, + struct devlink_trap_group_item *group_item) +{ + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_DEL); + list_del(&group_item->list); + free_percpu(group_item->stats); + kfree(group_item); +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_get(struct devlink *devlink, + const struct devlink_trap_group *group) +{ + struct devlink_trap_group_item *group_item; + + group_item = devlink_trap_group_item_lookup(devlink, group->name); + if (group_item) { + refcount_inc(&group_item->refcount); + return group_item; + } + + return devlink_trap_group_item_create(devlink, group); +} + +static void +devlink_trap_group_item_put(struct devlink *devlink, + struct devlink_trap_group_item *group_item) +{ + if (!refcount_dec_and_test(&group_item->refcount)) + return; + + devlink_trap_group_item_destroy(devlink, group_item); +} + +static int +devlink_trap_item_group_link(struct devlink *devlink, + struct devlink_trap_item *trap_item) +{ + struct devlink_trap_group_item *group_item; + + group_item = devlink_trap_group_item_get(devlink, + &trap_item->trap->group); + if (IS_ERR(group_item)) + return PTR_ERR(group_item); + + trap_item->group_item = group_item; + + return 0; +} + +static void +devlink_trap_item_group_unlink(struct devlink *devlink, + struct devlink_trap_item *trap_item) +{ + devlink_trap_group_item_put(devlink, trap_item->group_item); +} + +static void devlink_trap_notify(struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW && + cmd != DEVLINK_CMD_TRAP_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int +devlink_trap_register(struct devlink *devlink, + const struct devlink_trap *trap, void *priv) +{ + struct devlink_trap_item *trap_item; + int err; + + if (devlink_trap_item_lookup(devlink, trap->name)) + return -EEXIST; + + trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL); + if (!trap_item) + return -ENOMEM; + + trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); + if (!trap_item->stats) { + err = -ENOMEM; + goto err_stats_alloc; + } + + trap_item->trap = trap; + trap_item->action = trap->init_action; + trap_item->priv = priv; + + err = devlink_trap_item_group_link(devlink, trap_item); + if (err) + goto err_group_link; + + err = devlink->ops->trap_init(devlink, trap, trap_item); + if (err) + goto err_trap_init; + + list_add_tail(&trap_item->list, &devlink->trap_list); + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); + + return 0; + +err_trap_init: + devlink_trap_item_group_unlink(devlink, trap_item); +err_group_link: + free_percpu(trap_item->stats); +err_stats_alloc: + kfree(trap_item); + return err; +} + +static void devlink_trap_unregister(struct devlink *devlink, + const struct devlink_trap *trap) +{ + struct devlink_trap_item *trap_item; + + trap_item = devlink_trap_item_lookup(devlink, trap->name); + if (WARN_ON_ONCE(!trap_item)) + return; + + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); + list_del(&trap_item->list); + if (devlink->ops->trap_fini) + devlink->ops->trap_fini(devlink, trap, trap_item); + devlink_trap_item_group_unlink(devlink, trap_item); + free_percpu(trap_item->stats); + kfree(trap_item); +} + +static void devlink_trap_disable(struct devlink *devlink, + const struct devlink_trap *trap) +{ + struct devlink_trap_item *trap_item; + + trap_item = devlink_trap_item_lookup(devlink, trap->name); + if (WARN_ON_ONCE(!trap_item)) + return; + + devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP); + trap_item->action = DEVLINK_TRAP_ACTION_DROP; +} + +/** + * devlink_traps_register - Register packet traps with devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + * @priv: Driver private information. + * + * Return: Non-zero value on failure. + */ +int devlink_traps_register(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count, void *priv) +{ + int i, err; + + if (!devlink->ops->trap_init || !devlink->ops->trap_action_set) + return -EINVAL; + + mutex_lock(&devlink->lock); + for (i = 0; i < traps_count; i++) { + const struct devlink_trap *trap = &traps[i]; + + err = devlink_trap_verify(trap); + if (err) + goto err_trap_verify; + + err = devlink_trap_register(devlink, trap, priv); + if (err) + goto err_trap_register; + } + mutex_unlock(&devlink->lock); + + return 0; + +err_trap_register: +err_trap_verify: + for (i--; i >= 0; i--) + devlink_trap_unregister(devlink, &traps[i]); + mutex_unlock(&devlink->lock); + return err; +} +EXPORT_SYMBOL_GPL(devlink_traps_register); + +/** + * devlink_traps_unregister - Unregister packet traps from devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + */ +void devlink_traps_unregister(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count) +{ + int i; + + mutex_lock(&devlink->lock); + /* Make sure we do not have any packets in-flight while unregistering + * traps by disabling all of them and waiting for a grace period. + */ + for (i = traps_count - 1; i >= 0; i--) + devlink_trap_disable(devlink, &traps[i]); + synchronize_rcu(); + for (i = traps_count - 1; i >= 0; i--) + devlink_trap_unregister(devlink, &traps[i]); + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_traps_unregister); + +static void +devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, + size_t skb_len) +{ + struct devlink_stats *stats; + + stats = this_cpu_ptr(trap_stats); + u64_stats_update_begin(&stats->syncp); + stats->rx_bytes += skb_len; + stats->rx_packets++; + u64_stats_update_end(&stats->syncp); +} + +static void +devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, + const struct devlink_trap_item *trap_item, + struct devlink_port *in_devlink_port) +{ + struct devlink_trap_group_item *group_item = trap_item->group_item; + + hw_metadata->trap_group_name = group_item->group->name; + hw_metadata->trap_name = trap_item->trap->name; + + spin_lock(&in_devlink_port->type_lock); + if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) + hw_metadata->input_dev = in_devlink_port->type_dev; + spin_unlock(&in_devlink_port->type_lock); +} + +/** + * devlink_trap_report - Report trapped packet to drop monitor. + * @devlink: devlink. + * @skb: Trapped packet. + * @trap_ctx: Trap context. + * @in_devlink_port: Input devlink port. + */ +void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, + void *trap_ctx, struct devlink_port *in_devlink_port) +{ + struct devlink_trap_item *trap_item = trap_ctx; + struct net_dm_hw_metadata hw_metadata = {}; + + devlink_trap_stats_update(trap_item->stats, skb->len); + devlink_trap_stats_update(trap_item->group_item->stats, skb->len); + + devlink_trap_report_metadata_fill(&hw_metadata, trap_item, + in_devlink_port); + net_dm_hw_report(skb, &hw_metadata); +} +EXPORT_SYMBOL_GPL(devlink_trap_report); + +/** + * devlink_trap_ctx_priv - Trap context to driver private information. + * @trap_ctx: Trap context. + * + * Return: Driver private information passed during registration. + */ +void *devlink_trap_ctx_priv(void *trap_ctx) +{ + struct devlink_trap_item *trap_item = trap_ctx; + + return trap_item->priv; +} +EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv); + static void __devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len) { @@ -6941,11 +8009,10 @@ int devlink_compat_switch_id_get(struct net_device *dev, { struct devlink_port *devlink_port; - /* RTNL mutex is held here which ensures that devlink_port - * instance cannot disappear in the middle. No need to take + /* Caller must hold RTNL mutex or reference to dev, which ensures that + * devlink_port instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ - ASSERT_RTNL(); devlink_port = netdev_to_devlink_port(dev); if (!devlink_port || !devlink_port->attrs.switch_port) return -EOPNOTSUPP; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 4ea4347f5062..bfc024024aa3 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -26,6 +26,7 @@ #include <linux/bitops.h> #include <linux/slab.h> #include <linux/module.h> +#include <net/drop_monitor.h> #include <net/genetlink.h> #include <net/netevent.h> @@ -43,13 +44,44 @@ * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_MUTEX(trace_state_mutex); +static bool monitor_hw; + +/* net_dm_mutex + * + * An overall lock guarding every operation coming from userspace. + * It also guards the global 'hw_stats_list' list. + */ +static DEFINE_MUTEX(net_dm_mutex); + +struct net_dm_stats { + u64 dropped; + struct u64_stats_sync syncp; +}; + +#define NET_DM_MAX_HW_TRAP_NAME_LEN 40 + +struct net_dm_hw_entry { + char trap_name[NET_DM_MAX_HW_TRAP_NAME_LEN]; + u32 count; +}; + +struct net_dm_hw_entries { + u32 num_entries; + struct net_dm_hw_entry entries[0]; +}; struct per_cpu_dm_data { - spinlock_t lock; - struct sk_buff *skb; + spinlock_t lock; /* Protects 'skb', 'hw_entries' and + * 'send_timer' + */ + union { + struct sk_buff *skb; + struct net_dm_hw_entries *hw_entries; + }; + struct sk_buff_head drop_queue; struct work_struct dm_alert_work; struct timer_list send_timer; + struct net_dm_stats stats; }; struct dm_hw_stat_delta { @@ -63,12 +95,37 @@ struct dm_hw_stat_delta { static struct genl_family net_drop_monitor_family; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); +static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_hw_cpu_data); static int dm_hit_limit = 64; static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); +static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY; +static u32 net_dm_trunc_len; +static u32 net_dm_queue_len = 1000; + +struct net_dm_alert_ops { + void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, + void *location); + void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, + int work, int budget); + void (*work_item_func)(struct work_struct *work); + void (*hw_work_item_func)(struct work_struct *work); + void (*hw_probe)(struct sk_buff *skb, + const struct net_dm_hw_metadata *hw_metadata); +}; + +struct net_dm_skb_cb { + union { + struct net_dm_hw_metadata *hw_metadata; + void *pc; + }; +}; + +#define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) + static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; @@ -235,48 +292,840 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, rcu_read_unlock(); } -static int set_all_monitor_traces(int state) +static struct net_dm_hw_entries * +net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data) { - int rc = 0; - struct dm_hw_stat_delta *new_stat = NULL; - struct dm_hw_stat_delta *temp; + struct net_dm_hw_entries *hw_entries; + unsigned long flags; + + hw_entries = kzalloc(struct_size(hw_entries, entries, dm_hit_limit), + GFP_KERNEL); + if (!hw_entries) { + /* If the memory allocation failed, we try to perform another + * allocation in 1/10 second. Otherwise, the probe function + * will constantly bail out. + */ + mod_timer(&hw_data->send_timer, jiffies + HZ / 10); + } - mutex_lock(&trace_state_mutex); + spin_lock_irqsave(&hw_data->lock, flags); + swap(hw_data->hw_entries, hw_entries); + spin_unlock_irqrestore(&hw_data->lock, flags); - if (state == trace_state) { - rc = -EAGAIN; - goto out_unlock; + return hw_entries; +} + +static int net_dm_hw_entry_put(struct sk_buff *msg, + const struct net_dm_hw_entry *hw_entry) +{ + struct nlattr *attr; + + attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRY); + if (!attr) + return -EMSGSIZE; + + if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_entry->trap_name)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_HW_TRAP_COUNT, hw_entry->count)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int net_dm_hw_entries_put(struct sk_buff *msg, + const struct net_dm_hw_entries *hw_entries) +{ + struct nlattr *attr; + int i; + + attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRIES); + if (!attr) + return -EMSGSIZE; + + for (i = 0; i < hw_entries->num_entries; i++) { + int rc; + + rc = net_dm_hw_entry_put(msg, &hw_entries->entries[i]); + if (rc) + goto nla_put_failure; } - switch (state) { - case TRACE_ON: - if (!try_module_get(THIS_MODULE)) { - rc = -ENODEV; - break; + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int +net_dm_hw_summary_report_fill(struct sk_buff *msg, + const struct net_dm_hw_entries *hw_entries) +{ + struct net_dm_alert_msg anc_hdr = { 0 }; + void *hdr; + int rc; + + hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, + NET_DM_CMD_ALERT); + if (!hdr) + return -EMSGSIZE; + + /* We need to put the ancillary header in order not to break user + * space. + */ + if (nla_put(msg, NLA_UNSPEC, sizeof(anc_hdr), &anc_hdr)) + goto nla_put_failure; + + rc = net_dm_hw_entries_put(msg, hw_entries); + if (rc) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void net_dm_hw_summary_work(struct work_struct *work) +{ + struct net_dm_hw_entries *hw_entries; + struct per_cpu_dm_data *hw_data; + struct sk_buff *msg; + int rc; + + hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); + + hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); + if (!hw_entries) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + goto out; + + rc = net_dm_hw_summary_report_fill(msg, hw_entries); + if (rc) { + nlmsg_free(msg); + goto out; + } + + genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); + +out: + kfree(hw_entries); +} + +static void +net_dm_hw_summary_probe(struct sk_buff *skb, + const struct net_dm_hw_metadata *hw_metadata) +{ + struct net_dm_hw_entries *hw_entries; + struct net_dm_hw_entry *hw_entry; + struct per_cpu_dm_data *hw_data; + unsigned long flags; + int i; + + hw_data = this_cpu_ptr(&dm_hw_cpu_data); + spin_lock_irqsave(&hw_data->lock, flags); + hw_entries = hw_data->hw_entries; + + if (!hw_entries) + goto out; + + for (i = 0; i < hw_entries->num_entries; i++) { + hw_entry = &hw_entries->entries[i]; + if (!strncmp(hw_entry->trap_name, hw_metadata->trap_name, + NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) { + hw_entry->count++; + goto out; } + } + if (WARN_ON_ONCE(hw_entries->num_entries == dm_hit_limit)) + goto out; - rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL); - rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL); - break; + hw_entry = &hw_entries->entries[hw_entries->num_entries]; + strlcpy(hw_entry->trap_name, hw_metadata->trap_name, + NET_DM_MAX_HW_TRAP_NAME_LEN - 1); + hw_entry->count = 1; + hw_entries->num_entries++; - case TRACE_OFF: - rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL); - rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL); + if (!timer_pending(&hw_data->send_timer)) { + hw_data->send_timer.expires = jiffies + dm_delay * HZ; + add_timer(&hw_data->send_timer); + } - tracepoint_synchronize_unregister(); +out: + spin_unlock_irqrestore(&hw_data->lock, flags); +} - /* - * Clean the device list +static const struct net_dm_alert_ops net_dm_alert_summary_ops = { + .kfree_skb_probe = trace_kfree_skb_hit, + .napi_poll_probe = trace_napi_poll_hit, + .work_item_func = send_dm_alert, + .hw_work_item_func = net_dm_hw_summary_work, + .hw_probe = net_dm_hw_summary_probe, +}; + +static void net_dm_packet_trace_kfree_skb_hit(void *ignore, + struct sk_buff *skb, + void *location) +{ + ktime_t tstamp = ktime_get_real(); + struct per_cpu_dm_data *data; + struct sk_buff *nskb; + unsigned long flags; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return; + + NET_DM_SKB_CB(nskb)->pc = location; + /* Override the timestamp because we care about the time when the + * packet was dropped. + */ + nskb->tstamp = tstamp; + + data = this_cpu_ptr(&dm_cpu_data); + + spin_lock_irqsave(&data->drop_queue.lock, flags); + if (skb_queue_len(&data->drop_queue) < net_dm_queue_len) + __skb_queue_tail(&data->drop_queue, nskb); + else + goto unlock_free; + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + + schedule_work(&data->dm_alert_work); + + return; + +unlock_free: + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + u64_stats_update_begin(&data->stats.syncp); + data->stats.dropped++; + u64_stats_update_end(&data->stats.syncp); + consume_skb(nskb); +} + +static void net_dm_packet_trace_napi_poll_hit(void *ignore, + struct napi_struct *napi, + int work, int budget) +{ +} + +static size_t net_dm_in_port_size(void) +{ + /* NET_DM_ATTR_IN_PORT nest */ + return nla_total_size(0) + + /* NET_DM_ATTR_PORT_NETDEV_IFINDEX */ + nla_total_size(sizeof(u32)) + + /* NET_DM_ATTR_PORT_NETDEV_NAME */ + nla_total_size(IFNAMSIZ + 1); +} + +#define NET_DM_MAX_SYMBOL_LEN 40 + +static size_t net_dm_packet_report_size(size_t payload_len) +{ + size_t size; + + size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); + + return NLMSG_ALIGN(size) + + /* NET_DM_ATTR_ORIGIN */ + nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_PC */ + nla_total_size(sizeof(u64)) + + /* NET_DM_ATTR_SYMBOL */ + nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + + /* NET_DM_ATTR_IN_PORT */ + net_dm_in_port_size() + + /* NET_DM_ATTR_TIMESTAMP */ + nla_total_size(sizeof(struct timespec)) + + /* NET_DM_ATTR_ORIG_LEN */ + nla_total_size(sizeof(u32)) + + /* NET_DM_ATTR_PROTO */ + nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_PAYLOAD */ + nla_total_size(payload_len); +} + +static int net_dm_packet_report_in_port_put(struct sk_buff *msg, int ifindex, + const char *name) +{ + struct nlattr *attr; + + attr = nla_nest_start(msg, NET_DM_ATTR_IN_PORT); + if (!attr) + return -EMSGSIZE; + + if (ifindex && + nla_put_u32(msg, NET_DM_ATTR_PORT_NETDEV_IFINDEX, ifindex)) + goto nla_put_failure; + + if (name && nla_put_string(msg, NET_DM_ATTR_PORT_NETDEV_NAME, name)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, + size_t payload_len) +{ + u64 pc = (u64)(uintptr_t) NET_DM_SKB_CB(skb)->pc; + char buf[NET_DM_MAX_SYMBOL_LEN]; + struct nlattr *attr; + struct timespec ts; + void *hdr; + int rc; + + hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, + NET_DM_CMD_PACKET_ALERT); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_SW)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, pc, NET_DM_ATTR_PAD)) + goto nla_put_failure; + + snprintf(buf, sizeof(buf), "%pS", NET_DM_SKB_CB(skb)->pc); + if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) + goto nla_put_failure; + + rc = net_dm_packet_report_in_port_put(msg, skb->skb_iif, NULL); + if (rc) + goto nla_put_failure; + + if (ktime_to_timespec_cond(skb->tstamp, &ts) && + nla_put(msg, NET_DM_ATTR_TIMESTAMP, sizeof(ts), &ts)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) + goto nla_put_failure; + + if (!payload_len) + goto out; + + if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) + goto nla_put_failure; + + attr = skb_put(msg, nla_total_size(payload_len)); + attr->nla_type = NET_DM_ATTR_PAYLOAD; + attr->nla_len = nla_attr_size(payload_len); + if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +#define NET_DM_MAX_PACKET_SIZE (0xffff - NLA_HDRLEN - NLA_ALIGNTO) + +static void net_dm_packet_report(struct sk_buff *skb) +{ + struct sk_buff *msg; + size_t payload_len; + int rc; + + /* Make sure we start copying the packet from the MAC header */ + if (skb->data > skb_mac_header(skb)) + skb_push(skb, skb->data - skb_mac_header(skb)); + else + skb_pull(skb, skb_mac_header(skb) - skb->data); + + /* Ensure packet fits inside a single netlink attribute */ + payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); + if (net_dm_trunc_len) + payload_len = min_t(size_t, net_dm_trunc_len, payload_len); + + msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); + if (!msg) + goto out; + + rc = net_dm_packet_report_fill(msg, skb, payload_len); + if (rc) { + nlmsg_free(msg); + goto out; + } + + genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); + +out: + consume_skb(skb); +} + +static void net_dm_packet_work(struct work_struct *work) +{ + struct per_cpu_dm_data *data; + struct sk_buff_head list; + struct sk_buff *skb; + unsigned long flags; + + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); + + __skb_queue_head_init(&list); + + spin_lock_irqsave(&data->drop_queue.lock, flags); + skb_queue_splice_tail_init(&data->drop_queue, &list); + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + + while ((skb = __skb_dequeue(&list))) + net_dm_packet_report(skb); +} + +static size_t +net_dm_hw_packet_report_size(size_t payload_len, + const struct net_dm_hw_metadata *hw_metadata) +{ + size_t size; + + size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); + + return NLMSG_ALIGN(size) + + /* NET_DM_ATTR_ORIGIN */ + nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_HW_TRAP_GROUP_NAME */ + nla_total_size(strlen(hw_metadata->trap_group_name) + 1) + + /* NET_DM_ATTR_HW_TRAP_NAME */ + nla_total_size(strlen(hw_metadata->trap_name) + 1) + + /* NET_DM_ATTR_IN_PORT */ + net_dm_in_port_size() + + /* NET_DM_ATTR_TIMESTAMP */ + nla_total_size(sizeof(struct timespec)) + + /* NET_DM_ATTR_ORIG_LEN */ + nla_total_size(sizeof(u32)) + + /* NET_DM_ATTR_PROTO */ + nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_PAYLOAD */ + nla_total_size(payload_len); +} + +static int net_dm_hw_packet_report_fill(struct sk_buff *msg, + struct sk_buff *skb, size_t payload_len) +{ + struct net_dm_hw_metadata *hw_metadata; + struct nlattr *attr; + struct timespec ts; + void *hdr; + + hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; + + hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, + NET_DM_CMD_PACKET_ALERT); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_HW)) + goto nla_put_failure; + + if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_GROUP_NAME, + hw_metadata->trap_group_name)) + goto nla_put_failure; + + if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, + hw_metadata->trap_name)) + goto nla_put_failure; + + if (hw_metadata->input_dev) { + struct net_device *dev = hw_metadata->input_dev; + int rc; + + rc = net_dm_packet_report_in_port_put(msg, dev->ifindex, + dev->name); + if (rc) + goto nla_put_failure; + } + + if (ktime_to_timespec_cond(skb->tstamp, &ts) && + nla_put(msg, NET_DM_ATTR_TIMESTAMP, sizeof(ts), &ts)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) + goto nla_put_failure; + + if (!payload_len) + goto out; + + if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) + goto nla_put_failure; + + attr = skb_put(msg, nla_total_size(payload_len)); + attr->nla_type = NET_DM_ATTR_PAYLOAD; + attr->nla_len = nla_attr_size(payload_len); + if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static struct net_dm_hw_metadata * +net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) +{ + struct net_dm_hw_metadata *n_hw_metadata; + const char *trap_group_name; + const char *trap_name; + + n_hw_metadata = kmalloc(sizeof(*hw_metadata), GFP_ATOMIC); + if (!n_hw_metadata) + return NULL; + + trap_group_name = kmemdup(hw_metadata->trap_group_name, + strlen(hw_metadata->trap_group_name) + 1, + GFP_ATOMIC | __GFP_ZERO); + if (!trap_group_name) + goto free_hw_metadata; + n_hw_metadata->trap_group_name = trap_group_name; + + trap_name = kmemdup(hw_metadata->trap_name, + strlen(hw_metadata->trap_name) + 1, + GFP_ATOMIC | __GFP_ZERO); + if (!trap_name) + goto free_trap_group; + n_hw_metadata->trap_name = trap_name; + + n_hw_metadata->input_dev = hw_metadata->input_dev; + if (n_hw_metadata->input_dev) + dev_hold(n_hw_metadata->input_dev); + + return n_hw_metadata; + +free_trap_group: + kfree(trap_group_name); +free_hw_metadata: + kfree(n_hw_metadata); + return NULL; +} + +static void +net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) +{ + if (hw_metadata->input_dev) + dev_put(hw_metadata->input_dev); + kfree(hw_metadata->trap_name); + kfree(hw_metadata->trap_group_name); + kfree(hw_metadata); +} + +static void net_dm_hw_packet_report(struct sk_buff *skb) +{ + struct net_dm_hw_metadata *hw_metadata; + struct sk_buff *msg; + size_t payload_len; + int rc; + + if (skb->data > skb_mac_header(skb)) + skb_push(skb, skb->data - skb_mac_header(skb)); + else + skb_pull(skb, skb_mac_header(skb) - skb->data); + + payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); + if (net_dm_trunc_len) + payload_len = min_t(size_t, net_dm_trunc_len, payload_len); + + hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; + msg = nlmsg_new(net_dm_hw_packet_report_size(payload_len, hw_metadata), + GFP_KERNEL); + if (!msg) + goto out; + + rc = net_dm_hw_packet_report_fill(msg, skb, payload_len); + if (rc) { + nlmsg_free(msg); + goto out; + } + + genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); + +out: + net_dm_hw_metadata_free(NET_DM_SKB_CB(skb)->hw_metadata); + consume_skb(skb); +} + +static void net_dm_hw_packet_work(struct work_struct *work) +{ + struct per_cpu_dm_data *hw_data; + struct sk_buff_head list; + struct sk_buff *skb; + unsigned long flags; + + hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); + + __skb_queue_head_init(&list); + + spin_lock_irqsave(&hw_data->drop_queue.lock, flags); + skb_queue_splice_tail_init(&hw_data->drop_queue, &list); + spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); + + while ((skb = __skb_dequeue(&list))) + net_dm_hw_packet_report(skb); +} + +static void +net_dm_hw_packet_probe(struct sk_buff *skb, + const struct net_dm_hw_metadata *hw_metadata) +{ + struct net_dm_hw_metadata *n_hw_metadata; + ktime_t tstamp = ktime_get_real(); + struct per_cpu_dm_data *hw_data; + struct sk_buff *nskb; + unsigned long flags; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return; + + n_hw_metadata = net_dm_hw_metadata_clone(hw_metadata); + if (!n_hw_metadata) + goto free; + + NET_DM_SKB_CB(nskb)->hw_metadata = n_hw_metadata; + nskb->tstamp = tstamp; + + hw_data = this_cpu_ptr(&dm_hw_cpu_data); + + spin_lock_irqsave(&hw_data->drop_queue.lock, flags); + if (skb_queue_len(&hw_data->drop_queue) < net_dm_queue_len) + __skb_queue_tail(&hw_data->drop_queue, nskb); + else + goto unlock_free; + spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); + + schedule_work(&hw_data->dm_alert_work); + + return; + +unlock_free: + spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); + u64_stats_update_begin(&hw_data->stats.syncp); + hw_data->stats.dropped++; + u64_stats_update_end(&hw_data->stats.syncp); + net_dm_hw_metadata_free(n_hw_metadata); +free: + consume_skb(nskb); +} + +static const struct net_dm_alert_ops net_dm_alert_packet_ops = { + .kfree_skb_probe = net_dm_packet_trace_kfree_skb_hit, + .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, + .work_item_func = net_dm_packet_work, + .hw_work_item_func = net_dm_hw_packet_work, + .hw_probe = net_dm_hw_packet_probe, +}; + +static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { + [NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops, + [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, +}; + +void net_dm_hw_report(struct sk_buff *skb, + const struct net_dm_hw_metadata *hw_metadata) +{ + rcu_read_lock(); + + if (!monitor_hw) + goto out; + + net_dm_alert_ops_arr[net_dm_alert_mode]->hw_probe(skb, hw_metadata); + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(net_dm_hw_report); + +static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) +{ + const struct net_dm_alert_ops *ops; + int cpu; + + if (monitor_hw) { + NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled"); + return -EAGAIN; + } + + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + + if (!try_module_get(THIS_MODULE)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); + return -ENODEV; + } + + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); + struct net_dm_hw_entries *hw_entries; + + INIT_WORK(&hw_data->dm_alert_work, ops->hw_work_item_func); + timer_setup(&hw_data->send_timer, sched_send_work, 0); + hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); + kfree(hw_entries); + } + + monitor_hw = true; + + return 0; +} + +static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) +{ + int cpu; + + if (!monitor_hw) + NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled"); + + monitor_hw = false; + + /* After this call returns we are guaranteed that no CPU is processing + * any hardware drops. + */ + synchronize_rcu(); + + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&hw_data->send_timer); + cancel_work_sync(&hw_data->dm_alert_work); + while ((skb = __skb_dequeue(&hw_data->drop_queue))) { + struct net_dm_hw_metadata *hw_metadata; + + hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; + net_dm_hw_metadata_free(hw_metadata); + consume_skb(skb); + } + } + + module_put(THIS_MODULE); +} + +static int net_dm_trace_on_set(struct netlink_ext_ack *extack) +{ + const struct net_dm_alert_ops *ops; + int cpu, rc; + + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + + if (!try_module_get(THIS_MODULE)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); + return -ENODEV; + } + + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + INIT_WORK(&data->dm_alert_work, ops->work_item_func); + timer_setup(&data->send_timer, sched_send_work, 0); + /* Allocate a new per-CPU skb for the summary alert message and + * free the old one which might contain stale data from + * previous tracing. */ - list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { - if (new_stat->dev == NULL) { - list_del_rcu(&new_stat->list); - kfree_rcu(new_stat, rcu); - } + skb = reset_per_cpu_data(data); + consume_skb(skb); + } + + rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint"); + goto err_module_put; + } + + rc = register_trace_napi_poll(ops->napi_poll_probe, NULL); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint"); + goto err_unregister_trace; + } + + return 0; + +err_unregister_trace: + unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); +err_module_put: + module_put(THIS_MODULE); + return rc; +} + +static void net_dm_trace_off_set(void) +{ + struct dm_hw_stat_delta *new_stat, *temp; + const struct net_dm_alert_ops *ops; + int cpu; + + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + + unregister_trace_napi_poll(ops->napi_poll_probe, NULL); + unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); + + tracepoint_synchronize_unregister(); + + /* Make sure we do not send notifications to user space after request + * to stop tracing returns. + */ + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + while ((skb = __skb_dequeue(&data->drop_queue))) + consume_skb(skb); + } + + list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { + if (new_stat->dev == NULL) { + list_del_rcu(&new_stat->list); + kfree_rcu(new_stat, rcu); } + } + + module_put(THIS_MODULE); +} + +static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) +{ + int rc = 0; - module_put(THIS_MODULE); + if (state == trace_state) { + NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); + return -EAGAIN; + } + switch (state) { + case TRACE_ON: + rc = net_dm_trace_on_set(extack); + break; + case TRACE_OFF: + net_dm_trace_off_set(); break; default: rc = 1; @@ -288,30 +1137,331 @@ static int set_all_monitor_traces(int state) else rc = -EINPROGRESS; -out_unlock: - mutex_unlock(&trace_state_mutex); - return rc; } +static bool net_dm_is_monitoring(void) +{ + return trace_state == TRACE_ON || monitor_hw; +} + +static int net_dm_alert_mode_get_from_info(struct genl_info *info, + enum net_dm_alert_mode *p_alert_mode) +{ + u8 val; + + val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); + + switch (val) { + case NET_DM_ALERT_MODE_SUMMARY: /* fall-through */ + case NET_DM_ALERT_MODE_PACKET: + *p_alert_mode = val; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int net_dm_alert_mode_set(struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + enum net_dm_alert_mode alert_mode; + int rc; + + if (!info->attrs[NET_DM_ATTR_ALERT_MODE]) + return 0; + + rc = net_dm_alert_mode_get_from_info(info, &alert_mode); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Invalid alert mode"); + return -EINVAL; + } + + net_dm_alert_mode = alert_mode; + + return 0; +} + +static void net_dm_trunc_len_set(struct genl_info *info) +{ + if (!info->attrs[NET_DM_ATTR_TRUNC_LEN]) + return; + + net_dm_trunc_len = nla_get_u32(info->attrs[NET_DM_ATTR_TRUNC_LEN]); +} + +static void net_dm_queue_len_set(struct genl_info *info) +{ + if (!info->attrs[NET_DM_ATTR_QUEUE_LEN]) + return; + + net_dm_queue_len = nla_get_u32(info->attrs[NET_DM_ATTR_QUEUE_LEN]); +} static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { - return -ENOTSUPP; + struct netlink_ext_ack *extack = info->extack; + int rc; + + if (net_dm_is_monitoring()) { + NL_SET_ERR_MSG_MOD(extack, "Cannot configure drop monitor during monitoring"); + return -EBUSY; + } + + rc = net_dm_alert_mode_set(info); + if (rc) + return rc; + + net_dm_trunc_len_set(info); + + net_dm_queue_len_set(info); + + return 0; +} + +static int net_dm_monitor_start(bool set_sw, bool set_hw, + struct netlink_ext_ack *extack) +{ + bool sw_set = false; + int rc; + + if (set_sw) { + rc = set_all_monitor_traces(TRACE_ON, extack); + if (rc) + return rc; + sw_set = true; + } + + if (set_hw) { + rc = net_dm_hw_monitor_start(extack); + if (rc) + goto err_monitor_hw; + } + + return 0; + +err_monitor_hw: + if (sw_set) + set_all_monitor_traces(TRACE_OFF, extack); + return rc; +} + +static void net_dm_monitor_stop(bool set_sw, bool set_hw, + struct netlink_ext_ack *extack) +{ + if (set_hw) + net_dm_hw_monitor_stop(extack); + if (set_sw) + set_all_monitor_traces(TRACE_OFF, extack); } static int net_dm_cmd_trace(struct sk_buff *skb, struct genl_info *info) { + bool set_sw = !!info->attrs[NET_DM_ATTR_SW_DROPS]; + bool set_hw = !!info->attrs[NET_DM_ATTR_HW_DROPS]; + struct netlink_ext_ack *extack = info->extack; + + /* To maintain backward compatibility, we start / stop monitoring of + * software drops if no flag is specified. + */ + if (!set_sw && !set_hw) + set_sw = true; + switch (info->genlhdr->cmd) { case NET_DM_CMD_START: - return set_all_monitor_traces(TRACE_ON); + return net_dm_monitor_start(set_sw, set_hw, extack); case NET_DM_CMD_STOP: - return set_all_monitor_traces(TRACE_OFF); + net_dm_monitor_stop(set_sw, set_hw, extack); + return 0; + } + + return -EOPNOTSUPP; +} + +static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info) +{ + void *hdr; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &net_drop_monitor_family, 0, NET_DM_CMD_CONFIG_NEW); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u8(msg, NET_DM_ATTR_ALERT_MODE, net_dm_alert_mode)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_TRUNC_LEN, net_dm_trunc_len)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_QUEUE_LEN, net_dm_queue_len)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int net_dm_cmd_config_get(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + int rc; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rc = net_dm_config_fill(msg, info); + if (rc) + goto free_msg; + + return genlmsg_reply(msg, info); + +free_msg: + nlmsg_free(msg); + return rc; +} + +static void net_dm_stats_read(struct net_dm_stats *stats) +{ + int cpu; + + memset(stats, 0, sizeof(*stats)); + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct net_dm_stats *cpu_stats = &data->stats; + unsigned int start; + u64 dropped; + + do { + start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + dropped = cpu_stats->dropped; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + + stats->dropped += dropped; } +} + +static int net_dm_stats_put(struct sk_buff *msg) +{ + struct net_dm_stats stats; + struct nlattr *attr; + + net_dm_stats_read(&stats); + + attr = nla_nest_start(msg, NET_DM_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, + stats.dropped, NET_DM_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static void net_dm_hw_stats_read(struct net_dm_stats *stats) +{ + int cpu; + + memset(stats, 0, sizeof(*stats)); + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); + struct net_dm_stats *cpu_stats = &hw_data->stats; + unsigned int start; + u64 dropped; + + do { + start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + dropped = cpu_stats->dropped; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + + stats->dropped += dropped; + } +} + +static int net_dm_hw_stats_put(struct sk_buff *msg) +{ + struct net_dm_stats stats; + struct nlattr *attr; + + net_dm_hw_stats_read(&stats); + + attr = nla_nest_start(msg, NET_DM_ATTR_HW_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, + stats.dropped, NET_DM_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int net_dm_stats_fill(struct sk_buff *msg, struct genl_info *info) +{ + void *hdr; + int rc; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &net_drop_monitor_family, 0, NET_DM_CMD_STATS_NEW); + if (!hdr) + return -EMSGSIZE; + + rc = net_dm_stats_put(msg); + if (rc) + goto nla_put_failure; + + rc = net_dm_hw_stats_put(msg); + if (rc) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; - return -ENOTSUPP; +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int net_dm_cmd_stats_get(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + int rc; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rc = net_dm_stats_fill(msg, info); + if (rc) + goto free_msg; + + return genlmsg_reply(msg, info); + +free_msg: + nlmsg_free(msg); + return rc; } static int dropmon_net_event(struct notifier_block *ev_block, @@ -330,12 +1480,12 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; case NETDEV_UNREGISTER: - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; @@ -346,18 +1496,28 @@ static int dropmon_net_event(struct notifier_block *ev_block, } } } - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; } out: return NOTIFY_DONE; } +static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { + [NET_DM_ATTR_UNSPEC] = { .strict_start_type = NET_DM_ATTR_UNSPEC + 1 }, + [NET_DM_ATTR_ALERT_MODE] = { .type = NLA_U8 }, + [NET_DM_ATTR_TRUNC_LEN] = { .type = NLA_U32 }, + [NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 }, + [NET_DM_ATTR_SW_DROPS] = {. type = NLA_FLAG }, + [NET_DM_ATTR_HW_DROPS] = {. type = NLA_FLAG }, +}; + static const struct genl_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_config, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_START, @@ -369,12 +1529,38 @@ static const struct genl_ops dropmon_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, }, + { + .cmd = NET_DM_CMD_CONFIG_GET, + .doit = net_dm_cmd_config_get, + }, + { + .cmd = NET_DM_CMD_STATS_GET, + .doit = net_dm_cmd_stats_get, + }, }; +static int net_dm_nl_pre_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_lock(&net_dm_mutex); + + return 0; +} + +static void net_dm_nl_post_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_unlock(&net_dm_mutex); +} + static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, + .maxattr = NET_DM_ATTR_MAX, + .policy = net_dm_nl_policy, + .pre_doit = net_dm_nl_pre_doit, + .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .ops = dropmon_ops, .n_ops = ARRAY_SIZE(dropmon_ops), @@ -386,9 +1572,57 @@ static struct notifier_block dropmon_net_notifier = { .notifier_call = dropmon_net_event }; -static int __init init_net_drop_monitor(void) +static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data) +{ + spin_lock_init(&data->lock); + skb_queue_head_init(&data->drop_queue); + u64_stats_init(&data->stats.syncp); +} + +static void __net_dm_cpu_data_fini(struct per_cpu_dm_data *data) +{ + WARN_ON(!skb_queue_empty(&data->drop_queue)); +} + +static void net_dm_cpu_data_init(int cpu) +{ + struct per_cpu_dm_data *data; + + data = &per_cpu(dm_cpu_data, cpu); + __net_dm_cpu_data_init(data); +} + +static void net_dm_cpu_data_fini(int cpu) { struct per_cpu_dm_data *data; + + data = &per_cpu(dm_cpu_data, cpu); + /* At this point, we should have exclusive access + * to this struct and can free the skb inside it. + */ + consume_skb(data->skb); + __net_dm_cpu_data_fini(data); +} + +static void net_dm_hw_cpu_data_init(int cpu) +{ + struct per_cpu_dm_data *hw_data; + + hw_data = &per_cpu(dm_hw_cpu_data, cpu); + __net_dm_cpu_data_init(hw_data); +} + +static void net_dm_hw_cpu_data_fini(int cpu) +{ + struct per_cpu_dm_data *hw_data; + + hw_data = &per_cpu(dm_hw_cpu_data, cpu); + kfree(hw_data->hw_entries); + __net_dm_cpu_data_fini(hw_data); +} + +static int __init init_net_drop_monitor(void) +{ int cpu, rc; pr_info("Initializing network drop monitor service\n"); @@ -414,14 +1648,10 @@ static int __init init_net_drop_monitor(void) rc = 0; for_each_possible_cpu(cpu) { - data = &per_cpu(dm_cpu_data, cpu); - INIT_WORK(&data->dm_alert_work, send_dm_alert); - timer_setup(&data->send_timer, sched_send_work, 0); - spin_lock_init(&data->lock); - reset_per_cpu_data(data); + net_dm_cpu_data_init(cpu); + net_dm_hw_cpu_data_init(cpu); } - goto out; out_unreg: @@ -432,7 +1662,6 @@ out: static void exit_net_drop_monitor(void) { - struct per_cpu_dm_data *data; int cpu; BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); @@ -440,19 +1669,11 @@ static void exit_net_drop_monitor(void) /* * Because of the module_get/put we do in the trace state change path * we are guarnateed not to have any current users when we get here - * all we need to do is make sure that we don't have any running timers - * or pending schedule calls */ for_each_possible_cpu(cpu) { - data = &per_cpu(dm_cpu_data, cpu); - del_timer_sync(&data->send_timer); - cancel_work_sync(&data->dm_alert_work); - /* - * At this point, we should have exclusive access - * to this struct and can free the skb inside it - */ - kfree_skb(data->skb); + net_dm_hw_cpu_data_fini(cpu); + net_dm_cpu_data_fini(cpu); } BUG_ON(genl_unregister_family(&net_drop_monitor_family)); diff --git a/net/core/filter.c b/net/core/filter.c index 7878f918b8c0..0c1059cdad3d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3517,7 +3517,8 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, int err; switch (map->map_type) { - case BPF_MAP_TYPE_DEVMAP: { + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: { struct bpf_dtab_netdev *dst = fwd; err = dev_map_enqueue(dst, xdp, dev_rx); @@ -3554,6 +3555,7 @@ void xdp_do_flush_map(void) if (map) { switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: __dev_map_flush(map); break; case BPF_MAP_TYPE_CPUMAP: @@ -3574,6 +3576,8 @@ static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: return __dev_map_lookup_elem(map, index); + case BPF_MAP_TYPE_DEVMAP_HASH: + return __dev_map_hash_lookup_elem(map, index); case BPF_MAP_TYPE_CPUMAP: return __cpu_map_lookup_elem(map, index); case BPF_MAP_TYPE_XSKMAP: @@ -3655,7 +3659,8 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + if (map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { struct bpf_dtab_netdev *dst = fwd; err = dev_map_generic_redirect(dst, skb, xdp_prog); @@ -5850,6 +5855,75 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, + struct tcphdr *, th, u32, th_len) +{ +#ifdef CONFIG_SYN_COOKIES + u32 cookie; + u16 mss; + + if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + return -EINVAL; + + if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) + return -EINVAL; + + if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + return -ENOENT; + + if (!th->syn || th->ack || th->fin || th->rst) + return -EINVAL; + + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && sk->sk_ipv6only) + return -EINVAL; + + mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); + break; + +#if IS_BUILTIN(CONFIG_IPV6) + case 6: + if (unlikely(iph_len < sizeof(struct ipv6hdr))) + return -EINVAL; + + if (sk->sk_family != AF_INET6) + return -EINVAL; + + mss = tcp_v6_get_syncookie(sk, iph, th, &cookie); + break; +#endif /* CONFIG_IPV6 */ + + default: + return -EPROTONOSUPPORT; + } + if (mss <= 0) + return -ENOENT; + + return cookie | ((u64)mss << 32); +#else + return -EOPNOTSUPP; +#endif /* CONFIG_SYN_COOKIES */ +} + +static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { + .func = bpf_tcp_gen_syncookie, + .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -5999,6 +6073,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; default: return bpf_base_func_proto(func_id); } @@ -6019,6 +6095,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; @@ -6135,6 +6213,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; + case BPF_FUNC_tcp_gen_syncookie: + return &bpf_tcp_gen_syncookie_proto; #endif default: return bpf_base_func_proto(func_id); @@ -6174,6 +6254,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; + case BPF_FUNC_tcp_gen_syncookie: + return &bpf_tcp_gen_syncookie_proto; #endif default: return bpf_base_func_proto(func_id); @@ -6267,6 +6349,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3e6fedb57bc1..9741b593ea53 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -737,6 +737,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, @@ -781,10 +782,18 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } + + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL)) { + key_tags = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL, + target_container); + key_tags->flow_label = ntohl(flow_keys->flow_label); + } } bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen) + __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; @@ -795,6 +804,14 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != + (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != + (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != + (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); + flow_keys->flags = flags; + preempt_disable(); result = BPF_PROG_RUN(prog, ctx); preempt_enable(); @@ -914,7 +931,7 @@ bool __skb_flow_dissect(const struct net *net, } ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, - hlen); + hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d63b970784dc..64c3d4d72b9c 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -2,6 +2,8 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <net/flow_offload.h> +#include <linux/rtnetlink.h> +#include <linux/mutex.h> struct flow_rule *flow_rule_alloc(unsigned int num_actions) { @@ -280,3 +282,241 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, } } EXPORT_SYMBOL(flow_block_cb_setup_simple); + +static LIST_HEAD(block_ing_cb_list); + +static struct rhashtable indr_setup_block_ht; + +struct flow_indr_block_cb { + struct list_head list; + void *cb_priv; + flow_indr_block_bind_cb_t *cb; + void *cb_ident; +}; + +struct flow_indr_block_dev { + struct rhash_head ht_node; + struct net_device *dev; + unsigned int refcnt; + struct list_head cb_list; +}; + +static const struct rhashtable_params flow_indr_setup_block_ht_params = { + .key_offset = offsetof(struct flow_indr_block_dev, dev), + .head_offset = offsetof(struct flow_indr_block_dev, ht_node), + .key_len = sizeof(struct net_device *), +}; + +static struct flow_indr_block_dev * +flow_indr_block_dev_lookup(struct net_device *dev) +{ + return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, + flow_indr_setup_block_ht_params); +} + +static struct flow_indr_block_dev * +flow_indr_block_dev_get(struct net_device *dev) +{ + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (indr_dev) + goto inc_ref; + + indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); + if (!indr_dev) + return NULL; + + INIT_LIST_HEAD(&indr_dev->cb_list); + indr_dev->dev = dev; + if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, + flow_indr_setup_block_ht_params)) { + kfree(indr_dev); + return NULL; + } + +inc_ref: + indr_dev->refcnt++; + return indr_dev; +} + +static void flow_indr_block_dev_put(struct flow_indr_block_dev *indr_dev) +{ + if (--indr_dev->refcnt) + return; + + rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, + flow_indr_setup_block_ht_params); + kfree(indr_dev); +} + +static struct flow_indr_block_cb * +flow_indr_block_cb_lookup(struct flow_indr_block_dev *indr_dev, + flow_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + if (indr_block_cb->cb == cb && + indr_block_cb->cb_ident == cb_ident) + return indr_block_cb; + return NULL; +} + +static struct flow_indr_block_cb * +flow_indr_block_cb_add(struct flow_indr_block_dev *indr_dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + + indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (indr_block_cb) + return ERR_PTR(-EEXIST); + + indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); + if (!indr_block_cb) + return ERR_PTR(-ENOMEM); + + indr_block_cb->cb_priv = cb_priv; + indr_block_cb->cb = cb; + indr_block_cb->cb_ident = cb_ident; + list_add(&indr_block_cb->list, &indr_dev->cb_list); + + return indr_block_cb; +} + +static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb) +{ + list_del(&indr_block_cb->list); + kfree(indr_block_cb); +} + +static void flow_block_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) +{ + struct flow_indr_block_ing_entry *entry; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &block_ing_cb_list, list) { + entry->cb(dev, cb, cb_priv, command); + } + rcu_read_unlock(); +} + +int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + int err; + + indr_dev = flow_indr_block_dev_get(dev); + if (!indr_dev) + return -ENOMEM; + + indr_block_cb = flow_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); + err = PTR_ERR_OR_ZERO(indr_block_cb); + if (err) + goto err_dev_put; + + flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_BIND); + + return 0; + +err_dev_put: + flow_indr_block_dev_put(indr_dev); + return err; +} +EXPORT_SYMBOL_GPL(__flow_indr_block_cb_register); + +int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + int err; + + rtnl_lock(); + err = __flow_indr_block_cb_register(dev, cb_priv, cb, cb_ident); + rtnl_unlock(); + + return err; +} +EXPORT_SYMBOL_GPL(flow_indr_block_cb_register); + +void __flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (!indr_block_cb) + return; + + flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_UNBIND); + + flow_indr_block_cb_del(indr_block_cb); + flow_indr_block_dev_put(indr_dev); +} +EXPORT_SYMBOL_GPL(__flow_indr_block_cb_unregister); + +void flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + rtnl_lock(); + __flow_indr_block_cb_unregister(dev, cb, cb_ident); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(flow_indr_block_cb_unregister); + +void flow_indr_block_call(struct net_device *dev, + struct flow_block_offload *bo, + enum flow_block_command command) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, + bo); +} +EXPORT_SYMBOL_GPL(flow_indr_block_call); + +static DEFINE_MUTEX(flow_indr_block_ing_cb_lock); +void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry) +{ + mutex_lock(&flow_indr_block_ing_cb_lock); + list_add_tail_rcu(&entry->list, &block_ing_cb_list); + mutex_unlock(&flow_indr_block_ing_cb_lock); +} +EXPORT_SYMBOL_GPL(flow_indr_add_block_ing_cb); + +void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry) +{ + mutex_lock(&flow_indr_block_ing_cb_lock); + list_del_rcu(&entry->list); + mutex_unlock(&flow_indr_block_ing_cb_lock); +} +EXPORT_SYMBOL_GPL(flow_indr_del_block_ing_cb); + +static int __init init_flow_indr_rhashtable(void) +{ + return rhashtable_init(&indr_setup_block_ht, + &flow_indr_setup_block_ht_params); +} +subsys_initcall(init_flow_indr_rhashtable); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f79e61c570ea..5480edff0c86 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3033,7 +3033,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); struct neigh_hash_table *nht = state->nht; struct neighbour *n = NULL; - int bucket = state->bucket; + int bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 3272dc7a8c81..5bc65587f1c4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -61,7 +61,7 @@ static int page_pool_init(struct page_pool *pool, struct page_pool *page_pool_create(const struct page_pool_params *params) { struct page_pool *pool; - int err = 0; + int err; pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, params->nid); if (!pool) @@ -82,12 +82,9 @@ EXPORT_SYMBOL(page_pool_create); static struct page *__page_pool_get_cached(struct page_pool *pool) { struct ptr_ring *r = &pool->ring; + bool refill = false; struct page *page; - /* Quicker fallback, avoid locks when ring is empty */ - if (__ptr_ring_empty(r)) - return NULL; - /* Test for safe-context, caller should provide this guarantee */ if (likely(in_serving_softirq())) { if (likely(pool->alloc.count)) { @@ -95,27 +92,23 @@ static struct page *__page_pool_get_cached(struct page_pool *pool) page = pool->alloc.cache[--pool->alloc.count]; return page; } - /* Slower-path: Alloc array empty, time to refill - * - * Open-coded bulk ptr_ring consumer. - * - * Discussion: the ring consumer lock is not really - * needed due to the softirq/NAPI protection, but - * later need the ability to reclaim pages on the - * ring. Thus, keeping the locks. - */ - spin_lock(&r->consumer_lock); - while ((page = __ptr_ring_consume(r))) { - if (pool->alloc.count == PP_ALLOC_CACHE_REFILL) - break; - pool->alloc.cache[pool->alloc.count++] = page; - } - spin_unlock(&r->consumer_lock); - return page; + refill = true; } - /* Slow-path: Get page from locked ring queue */ - page = ptr_ring_consume(&pool->ring); + /* Quicker fallback, avoid locks when ring is empty */ + if (__ptr_ring_empty(r)) + return NULL; + + /* Slow-path: Get page from locked ring queue, + * refill alloc array if requested. + */ + spin_lock(&r->consumer_lock); + page = __ptr_ring_consume(r); + if (refill) + pool->alloc.count = __ptr_ring_consume_batched(r, + pool->alloc.cache, + PP_ALLOC_CACHE_REFILL); + spin_unlock(&r->consumer_lock); return page; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index bb9915291644..c5dbdc87342a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2652,7 +2652,7 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } get_page(pkt_dev->page); skb_frag_set_page(skb, i, pkt_dev->page); - skb_shinfo(skb)->frags[i].page_offset = 0; + skb_frag_off_set(&skb_shinfo(skb)->frags[i], 0); /*last fragment, fill rest of data*/ if (i == (frags - 1)) skb_frag_size_set(&skb_shinfo(skb)->frags[i], diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0338820ee0ec..ea8e8d332d85 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -785,7 +785,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) struct page *p; u8 *vaddr; - skb_frag_foreach_page(frag, frag->page_offset, + skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { seg_len = min_t(int, p_len, len); @@ -1375,7 +1375,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) struct page *p; u8 *vaddr; - skb_frag_foreach_page(f, f->page_offset, skb_frag_size(f), + skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), p, p_off, p_len, copied) { u32 copy, done = 0; vaddr = kmap_atomic(p); @@ -2144,10 +2144,12 @@ pull_pages: skb_frag_unref(skb, i); eat -= size; } else { - skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; + + *frag = skb_shinfo(skb)->frags[i]; if (eat) { - skb_shinfo(skb)->frags[k].page_offset += eat; - skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat); + skb_frag_off_add(frag, eat); + skb_frag_size_sub(frag, eat); if (!i) goto end; eat = 0; @@ -2219,7 +2221,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) copy = len; skb_frag_foreach_page(f, - f->page_offset + offset - start, + skb_frag_off(f) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(to + copied, vaddr + p_off, p_len); @@ -2395,7 +2397,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(skb_frag_page(f), - f->page_offset, skb_frag_size(f), + skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) return true; } @@ -2485,20 +2487,20 @@ do_frag_list: for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; - if (offset < frag->size) + if (offset < skb_frag_size(frag)) break; - offset -= frag->size; + offset -= skb_frag_size(frag); } for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx]; - slen = min_t(size_t, len, frag->size - offset); + slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { - ret = kernel_sendpage_locked(sk, frag->page.p, - frag->page_offset + offset, + ret = kernel_sendpage_locked(sk, skb_frag_page(frag), + skb_frag_off(frag) + offset, slen, MSG_DONTWAIT); if (ret <= 0) goto error; @@ -2580,7 +2582,7 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) copy = len; skb_frag_foreach_page(frag, - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); memcpy(vaddr + p_off, from + copied, p_len); @@ -2660,7 +2662,7 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, copy = len; skb_frag_foreach_page(frag, - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = INDIRECT_CALL_1(ops->update, @@ -2759,7 +2761,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, copy = len; skb_frag_foreach_page(frag, - frag->page_offset + offset - start, + skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, @@ -2975,11 +2977,15 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { + int size; + if (!len) break; skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; - skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); - len -= skb_shinfo(to)->frags[j].size; + size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]), + len); + skb_frag_size_set(&skb_shinfo(to)->frags[j], size); + len -= size; skb_frag_ref(to, j); j++; } @@ -3230,7 +3236,7 @@ static inline void skb_split_no_header(struct sk_buff *skb, * 2. Split is accurately. We make this. */ skb_frag_ref(skb, i); - skb_shinfo(skb1)->frags[0].page_offset += len - pos; + skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; @@ -3293,7 +3299,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) { int from, to, merge, todo; - struct skb_frag_struct *fragfrom, *fragto; + skb_frag_t *fragfrom, *fragto; BUG_ON(shiftlen > skb->len); @@ -3312,7 +3318,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) */ if (!to || !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), - fragfrom->page_offset)) { + skb_frag_off(fragfrom))) { merge = -1; } else { merge = to - 1; @@ -3329,7 +3335,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) skb_frag_size_add(fragto, shiftlen); skb_frag_size_sub(fragfrom, shiftlen); - fragfrom->page_offset += shiftlen; + skb_frag_off_add(fragfrom, shiftlen); goto onlymerged; } @@ -3360,11 +3366,11 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) } else { __skb_frag_ref(fragfrom); - fragto->page = fragfrom->page; - fragto->page_offset = fragfrom->page_offset; + skb_frag_page_copy(fragto, fragfrom); + skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); - fragfrom->page_offset += todo; + skb_frag_off_add(fragfrom, todo); skb_frag_size_sub(fragfrom, todo); todo = 0; @@ -3489,7 +3495,7 @@ next_skb: if (!st->frag_data) st->frag_data = kmap_atomic(skb_frag_page(frag)); - *data = (u8 *) st->frag_data + frag->page_offset + + *data = (u8 *) st->frag_data + skb_frag_off(frag) + (abs_offset - st->stepped_offset); return block_limit - abs_offset; @@ -3625,10 +3631,10 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) struct page *page; page = virt_to_head_page(frag_skb->head); - head_frag.page.p = page; - head_frag.page_offset = frag_skb->data - - (unsigned char *)page_address(page); - head_frag.size = skb_headlen(frag_skb); + __skb_frag_set_page(&head_frag, page); + skb_frag_off_set(&head_frag, frag_skb->data - + (unsigned char *)page_address(page)); + skb_frag_size_set(&head_frag, skb_headlen(frag_skb)); return head_frag; } @@ -3871,7 +3877,7 @@ normal: size = skb_frag_size(nskb_frag); if (pos < offset) { - nskb_frag->page_offset += offset - pos; + skb_frag_off_add(nskb_frag, offset - pos); skb_frag_size_sub(nskb_frag, offset - pos); } @@ -3992,7 +3998,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) *--frag = *--frag2; } while (--i); - frag->page_offset += offset; + skb_frag_off_add(frag, offset); skb_frag_size_sub(frag, offset); /* all fragments truesize : remove (head size + sk_buff) */ @@ -4021,8 +4027,8 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; - frag->page.p = page; - frag->page_offset = first_offset; + __skb_frag_set_page(frag, page); + skb_frag_off_set(frag, first_offset); skb_frag_size_set(frag, first_size); memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); @@ -4038,7 +4044,7 @@ merge: if (offset > headlen) { unsigned int eat = offset - headlen; - skbinfo->frags[0].page_offset += eat; + skb_frag_off_add(&skbinfo->frags[0], eat); skb_frag_size_sub(&skbinfo->frags[0], eat); skb->data_len -= eat; skb->len -= eat; @@ -4163,7 +4169,7 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len, if (copy > len) copy = len; sg_set_page(&sg[elt], skb_frag_page(frag), copy, - frag->page_offset+offset-start); + skb_frag_off(frag) + offset - start); elt++; if (!(len -= copy)) return elt; @@ -5834,7 +5840,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, * where splitting is expensive. * 2. Split is accurately. We make this. */ - shinfo->frags[0].page_offset += off - pos; + skb_frag_off_add(&shinfo->frags[0], off - pos); skb_frag_size_sub(&shinfo->frags[0], off - pos); } skb_frag_ref(skb, i); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8da5b3a54dac..eb29e5adc84d 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -567,6 +567,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_do_static_key, }, + { + .procname = "gro_normal_batch", + .data = &gro_normal_batch, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, { } }; diff --git a/net/core/tso.c b/net/core/tso.c index 43f4eba61933..d4d5c077ad72 100644 --- a/net/core/tso.c +++ b/net/core/tso.c @@ -55,8 +55,8 @@ void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size) skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; /* Move to next segment */ - tso->size = frag->size; - tso->data = page_address(frag->page.p) + frag->page_offset; + tso->size = skb_frag_size(frag); + tso->data = skb_frag_address(frag); tso->next_frag_idx++; } } @@ -79,8 +79,8 @@ void tso_start(struct sk_buff *skb, struct tso_t *tso) skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; /* Move to next segment */ - tso->size = frag->size; - tso->data = page_address(frag->page.p) + frag->page_offset; + tso->size = skb_frag_size(frag); + tso->data = skb_frag_address(frag); tso->next_frag_idx++; } } diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 6e942dda1bcd..2f69d4b53d46 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -84,13 +84,6 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 9893 family of switches. -config NET_DSA_TAG_KSZ9477 - tristate "Tag driver for Microchip 9477 family of switches" - select NET_DSA_TAG_KSZ_COMMON - help - Say Y if you want to enable support for tagging frames for the - Microchip 9477 family of switches. - config NET_DSA_TAG_QCA tristate "Tag driver for Qualcomm Atheros QCA8K switches" help diff --git a/net/dsa/master.c b/net/dsa/master.c index 4b52f8bac5e1..a8e52c9967f4 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -8,6 +8,70 @@ #include "dsa_priv.h" +static int dsa_master_get_regs_len(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int ret = 0; + int len; + + if (ops->get_regs_len) { + len = ops->get_regs_len(dev); + if (len < 0) + return len; + ret += len; + } + + ret += sizeof(struct ethtool_drvinfo); + ret += sizeof(struct ethtool_regs); + + if (ds->ops->get_regs_len) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return len; + ret += len; + } + + return ret; +} + +static void dsa_master_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + struct ethtool_drvinfo *cpu_info; + struct ethtool_regs *cpu_regs; + int port = cpu_dp->index; + int len; + + if (ops->get_regs_len && ops->get_regs) { + len = ops->get_regs_len(dev); + if (len < 0) + return; + regs->len = len; + ops->get_regs(dev, regs, data); + data += regs->len; + } + + cpu_info = (struct ethtool_drvinfo *)data; + strlcpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver)); + data += sizeof(*cpu_info); + cpu_regs = (struct ethtool_regs *)data; + data += sizeof(*cpu_regs); + + if (ds->ops->get_regs_len && ds->ops->get_regs) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return; + cpu_regs->len = len; + ds->ops->get_regs(ds, port, cpu_regs, data); + } +} + static void dsa_master_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) @@ -147,6 +211,8 @@ static int dsa_master_ethtool_setup(struct net_device *dev) if (cpu_dp->orig_ethtool_ops) memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); + ops->get_regs_len = dsa_master_get_regs_len; + ops->get_regs = dsa_master_get_regs; ops->get_sset_count = dsa_master_get_sset_count; ops->get_ethtool_stats = dsa_master_get_ethtool_stats; ops->get_strings = dsa_master_get_strings; diff --git a/net/dsa/port.c b/net/dsa/port.c index f071acf2842b..f75301456430 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -538,10 +538,6 @@ static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) return PTR_ERR(phydev); if (enable) { - err = genphy_config_init(phydev); - if (err < 0) - goto err_put_dev; - err = genphy_resume(phydev); if (err < 0) goto err_put_dev; @@ -589,7 +585,6 @@ static int dsa_port_fixed_link_register_of(struct dsa_port *dp) mode = PHY_INTERFACE_MODE_NA; phydev->interface = mode; - genphy_config_init(phydev); genphy_read_status(phydev); if (ds->ops->adjust_link) diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index b4872b87d4a6..73605bcbb385 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -70,6 +70,67 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, } /* + * For Ingress (Host -> KSZ8795), 1 byte is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5) + * + * For Egress (KSZ8795 -> Host), 1 byte is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : zero-based value represents port + * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + */ + +#define KSZ8795_INGRESS_TAG_LEN 1 + +#define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) +#define KSZ8795_TAIL_TAG_LOOKUP BIT(7) + +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, KSZ8795_INGRESS_TAG_LEN); + if (!nskb) + return NULL; + + /* Tag encoding */ + tag = skb_put(nskb, KSZ8795_INGRESS_TAG_LEN); + addr = skb_mac_header(nskb); + + *tag = 1 << dp->index; + if (is_link_local_ether_addr(addr)) + *tag |= KSZ8795_TAIL_TAG_OVERRIDE; + + return nskb; +} + +static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + + return ksz_common_rcv(skb, dev, tag[0] & 7, KSZ_EGRESS_TAG_LEN); +} + +static const struct dsa_device_ops ksz8795_netdev_ops = { + .name = "ksz8795", + .proto = DSA_TAG_PROTO_KSZ8795, + .xmit = ksz8795_xmit, + .rcv = ksz8795_rcv, + .overhead = KSZ8795_INGRESS_TAG_LEN, +}; + +DSA_TAG_DRIVER(ksz8795_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795); + +/* * For Ingress (Host -> KSZ9477), 2 bytes are added before FCS. * --------------------------------------------------------------------------- * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) @@ -183,6 +244,7 @@ DSA_TAG_DRIVER(ksz9893_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893); static struct dsa_tag_driver *dsa_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(ksz8795_netdev_ops), &DSA_TAG_DRIVER_NAME(ksz9477_netdev_ops), &DSA_TAG_DRIVER_NAME(ksz9893_netdev_ops), }; diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 0e70f3f65f6f..748dc3ce58d3 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -36,8 +36,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; - opts.mss_encode = opts.mss; - opts.mss = info->mss; + opts.mss_encode = opts.mss_option; + opts.mss_option = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0b980e841927..59ded25acd04 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -820,6 +820,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &tcp_min_snd_mss_max, }, { + .procname = "tcp_mtu_probe_floor", + .data = &init_net.ipv4.sysctl_tcp_mtu_probe_floor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_min_snd_mss_min, + .extra2 = &tcp_min_snd_mss_max, + }, + { .procname = "tcp_probe_threshold", .data = &init_net.ipv4.sysctl_tcp_probe_threshold, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77b485d60b9d..051ef10374f6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1165,7 +1165,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; - bool process_backlog = false; + int process_backlog = 0; bool zc = false; long timeo; @@ -1257,9 +1257,10 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - if (process_backlog && sk_flush_backlog(sk)) { - process_backlog = false; - goto restart; + if (unlikely(process_backlog >= 16)) { + process_backlog = 0; + if (sk_flush_backlog(sk)) + goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, @@ -1267,7 +1268,7 @@ new_segment: if (!skb) goto wait_for_memory; - process_backlog = true; + process_backlog++; skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); @@ -1779,19 +1780,21 @@ static int tcp_zerocopy_receive(struct sock *sk, break; frags = skb_shinfo(skb)->frags; while (offset) { - if (frags->size > offset) + if (skb_frag_size(frags) > offset) goto out; - offset -= frags->size; + offset -= skb_frag_size(frags); frags++; } } - if (frags->size != PAGE_SIZE || frags->page_offset) { + if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { int remaining = zc->recv_skip_hint; + int size = skb_frag_size(frags); - while (remaining && (frags->size != PAGE_SIZE || - frags->page_offset)) { - remaining -= frags->size; + while (remaining && (size != PAGE_SIZE || + skb_frag_off(frags))) { + remaining -= size; frags++; + size = skb_frag_size(frags); } zc->recv_skip_hint -= remaining; break; @@ -3784,8 +3787,8 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, return 1; for (i = 0; i < shi->nr_frags; ++i) { - const struct skb_frag_struct *f = &shi->frags[i]; - unsigned int offset = f->page_offset; + const skb_frag_t *f = &shi->frags[i]; + unsigned int offset = skb_frag_off(f); struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); sg_set_page(&sg, page, skb_frag_size(f), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c21e8a22fb3b..706cbb3b2986 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3782,6 +3782,49 @@ static void smc_parse_options(const struct tcphdr *th, #endif } +/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped + * value on success. + */ +static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss) +{ + const unsigned char *ptr = (const unsigned char *)(th + 1); + int length = (th->doff * 4) - sizeof(struct tcphdr); + u16 mss = 0; + + while (length > 0) { + int opcode = *ptr++; + int opsize; + + switch (opcode) { + case TCPOPT_EOL: + return mss; + case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ + length--; + continue; + default: + if (length < 2) + return mss; + opsize = *ptr++; + if (opsize < 2) /* "silly options" */ + return mss; + if (opsize > length) + return mss; /* fail on partial options */ + if (opcode == TCPOPT_MSS && opsize == TCPOLEN_MSS) { + u16 in_mss = get_unaligned_be16(ptr); + + if (in_mss) { + if (user_mss && user_mss < in_mss) + in_mss = user_mss; + mss = in_mss; + } + } + ptr += opsize - 2; + length -= opsize; + } + } + return mss; +} + /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when * the fast version below fails. @@ -6422,9 +6465,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(const struct sock *sk, - const struct sk_buff *skb, - const char *proto) +static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; @@ -6444,7 +6485,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); + proto, sk->sk_num, msg); return want_cookie; } @@ -6466,6 +6507,36 @@ static void tcp_reqsk_record_syn(const struct sock *sk, } } +/* If a SYN cookie is required and supported, returns a clamped MSS value to be + * used for SYN cookie generation. + */ +u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, + const struct tcp_request_sock_ops *af_ops, + struct sock *sk, struct tcphdr *th) +{ + struct tcp_sock *tp = tcp_sk(sk); + u16 mss; + + if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 && + !inet_csk_reqsk_queue_is_full(sk)) + return 0; + + if (!tcp_syn_flood_action(sk, rsk_ops->slab_name)) + return 0; + + if (sk_acceptq_is_full(sk)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + return 0; + } + + mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss); + if (!mss) + mss = af_ops->mss_clamp; + + return mss; +} +EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss); + int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) @@ -6487,7 +6558,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, */ if ((net->ipv4.sysctl_tcp_syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name); + want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); if (!want_cookie) goto drop; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d57641cb3477..fd394ad179a0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1515,6 +1515,21 @@ static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) return sk; } +u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, + struct tcphdr *th, u32 *cookie) +{ + u16 mss = 0; +#ifdef CONFIG_SYN_COOKIES + mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, th); + if (mss) { + *cookie = __cookie_v4_init_sequence(iph, th, &mss); + tcp_synq_overflow(sk); + } +#endif + return mss; +} + /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * @@ -2637,6 +2652,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; + net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 979520e46e33..5c46bc4c7e8d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1403,7 +1403,7 @@ static int __pskb_trim_head(struct sk_buff *skb, int len) } else { shinfo->frags[k] = shinfo->frags[i]; if (eat) { - shinfo->frags[k].page_offset += eat; + skb_frag_off_add(&shinfo->frags[k], eat); skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c801cd37cc2a..dbd9d2d0ee63 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -154,7 +154,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len); + mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index b358f1a4dd08..da46c4284676 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -197,10 +197,8 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, struct ipv6hdr _ip6, *ip6; ip6 = skb_header_pointer(skb, *offset, sizeof(_ip6), &_ip6); - if (!ip6 || (ip6->version != 6)) { - printk(KERN_ERR "IPv6 header not found\n"); + if (!ip6 || (ip6->version != 6)) return -EBADMSG; - } start = *offset + sizeof(struct ipv6hdr); nexthdr = ip6->nexthdr; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 083cc1c94cd3..53caf59c591e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -196,6 +196,7 @@ static inline int ndisc_is_useropt(const struct net_device *dev, { return opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || + opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || ndisc_ops_is_useropt(dev, opt->nd_opt_type); } diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 5cdb4a69d277..fd1f52a21bf1 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -36,8 +36,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; - opts.mss_encode = opts.mss; - opts.mss = info->mss; + opts.mss_encode = opts.mss_option; + opts.mss_option = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fd059e08785a..7a5d331cdefa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2725,10 +2725,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); - if (!res.f6i) { - rcu_read_unlock(); - return; - } + if (!res.f6i) + goto out_unlock; + res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; @@ -2744,10 +2743,8 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ - if (!arg.match) { - rcu_read_unlock(); - return; - } + if (!arg.match) + goto out_unlock; res.nh = arg.match; } else { @@ -2760,6 +2757,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } +out_unlock: rcu_read_unlock(); } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5da069e91cac..87f44d3250ee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1063,6 +1063,21 @@ static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) return sk; } +u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, + struct tcphdr *th, u32 *cookie) +{ + u16 mss = 0; +#ifdef CONFIG_SYN_COOKIES + mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, th); + if (mss) { + *cookie = __cookie_v6_init_sequence(iph, th, &mss); + tcp_synq_overflow(sk); + } +#endif + return mss; +} + static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 5dbc0c48f8cb..4ff75c3a8d6e 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -635,15 +635,15 @@ do_frag_list: frag_offset = 0; do_frag: frag = &skb_shinfo(skb)->frags[fragidx]; - if (WARN_ON(!frag->size)) { + if (WARN_ON(!skb_frag_size(frag))) { ret = -EINVAL; goto out; } ret = kernel_sendpage(psock->sk->sk_socket, - frag->page.p, - frag->page_offset + frag_offset, - frag->size - frag_offset, + skb_frag_page(frag), + skb_frag_off(frag) + frag_offset, + skb_frag_size(frag) - frag_offset, MSG_DONTWAIT); if (ret <= 0) { if (ret == -EAGAIN) { @@ -678,7 +678,7 @@ do_frag: sent += ret; frag_offset += ret; KCM_STATS_ADD(psock->stats.tx_bytes, ret); - if (frag_offset < frag->size) { + if (frag_offset < skb_frag_size(frag)) { /* Not finished with this frag */ goto do_frag; } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 01b0dad24500..4d1c335e06e5 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -178,17 +178,54 @@ static void sta_rx_agg_reorder_timer_expired(struct timer_list *t) rcu_read_unlock(); } -static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *da, u16 tid, +static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + const struct ieee80211_addba_ext_ie *req) +{ + struct ieee80211_supported_band *sband; + struct ieee80211_addba_ext_ie *resp; + const struct ieee80211_sta_he_cap *he_cap; + u8 frag_level, cap_frag_level; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return; + he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type); + if (!he_cap) + return; + + pos = skb_put_zero(skb, 2 + sizeof(struct ieee80211_addba_ext_ie)); + *pos++ = WLAN_EID_ADDBA_EXT; + *pos++ = sizeof(struct ieee80211_addba_ext_ie); + resp = (struct ieee80211_addba_ext_ie *)pos; + resp->data = req->data & IEEE80211_ADDBA_EXT_NO_FRAG; + + frag_level = u32_get_bits(req->data, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); + cap_frag_level = u32_get_bits(he_cap->he_cap_elem.mac_cap_info[0], + IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK); + if (frag_level > cap_frag_level) + frag_level = cap_frag_level; + resp->data |= u8_encode_bits(frag_level, + IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); +} + +static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid, u8 dialog_token, u16 status, u16 policy, - u16 buf_size, u16 timeout) + u16 buf_size, u16 timeout, + const struct ieee80211_addba_ext_ie *addbaext) { + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; bool amsdu = ieee80211_hw_check(&local->hw, SUPPORTS_AMSDU_IN_AMPDU); u16 capab; - skb = dev_alloc_skb(sizeof(*mgmt) + local->hw.extra_tx_headroom); + skb = dev_alloc_skb(sizeof(*mgmt) + + 2 + sizeof(struct ieee80211_addba_ext_ie) + + local->hw.extra_tx_headroom); if (!skb) return; @@ -222,13 +259,17 @@ static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *d mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout); mgmt->u.action.u.addba_resp.status = cpu_to_le16(status); + if (sta->sta.he_cap.has_he && addbaext) + ieee80211_add_addbaext(sdata, skb, addbaext); + ieee80211_tx_skb(sdata, skb); } void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq) + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { struct ieee80211_local *local = sta->sdata->local; struct tid_ampdu_rx *tid_agg_rx; @@ -410,21 +451,22 @@ end: } if (tx) - ieee80211_send_addba_resp(sta->sdata, sta->sta.addr, tid, + ieee80211_send_addba_resp(sta, sta->sta.addr, tid, dialog_token, status, 1, buf_size, - timeout); + timeout, addbaext); } static void __ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, u16 buf_size, bool tx, - bool auto_seq) + bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext) { mutex_lock(&sta->ampdu_mlme.mtx); ___ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, tx, auto_seq); + buf_size, tx, auto_seq, addbaext); mutex_unlock(&sta->ampdu_mlme.mtx); } @@ -434,7 +476,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, size_t len) { u16 capab, tid, timeout, ba_policy, buf_size, start_seq_num; + struct ieee802_11_elems elems = { 0 }; u8 dialog_token; + int ies_len; /* extract session parameters from addba request frame */ dialog_token = mgmt->u.action.u.addba_req.dialog_token; @@ -447,9 +491,19 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; + ies_len = len - offsetof(struct ieee80211_mgmt, + u.action.u.addba_req.variable); + if (ies_len) { + ieee802_11_parse_elems(mgmt->u.action.u.addba_req.variable, + ies_len, true, &elems, mgmt->bssid, NULL); + if (elems.parse_error) + return; + } + __ieee80211_start_rx_ba_session(sta, dialog_token, timeout, start_seq_num, ba_policy, tid, - buf_size, true, false); + buf_size, true, false, + elems.addba_ext_ie); } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4d458067d80d..ed56b0c6fe19 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -980,7 +980,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_SSID | BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | - BSS_CHANGED_TWT; + BSS_CHANGED_TWT | + BSS_CHANGED_HE_OBSS_PD; int err; int prev_beacon_int; @@ -1051,6 +1052,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.enable_beacon = true; sdata->vif.bss_conf.allow_p2p_go_ps = sdata->vif.p2p; sdata->vif.bss_conf.twt_responder = params->twt_responder; + memcpy(&sdata->vif.bss_conf.he_obss_pd, ¶ms->he_obss_pd, + sizeof(struct ieee80211_he_obss_pd)); sdata->vif.bss_conf.ssid_len = params->ssid_len; if (params->ssid_len) @@ -1543,7 +1546,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (ether_addr_equal(mac, sdata->vif.addr)) return -EINVAL; - if (is_multicast_ether_addr(mac)) + if (!is_valid_ether_addr(mac)) return -EINVAL; sta = sta_info_alloc(sdata, mac, GFP_KERNEL); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 2e7f75938c51..568b3b276931 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -271,8 +271,7 @@ static const char *hw_flag_names[] = { FLAG(TX_STATUS_NO_AMPDU_LEN), FLAG(SUPPORTS_MULTI_BSSID), FLAG(SUPPORTS_ONLY_HE_MULTI_BSSID), - FLAG(EXT_KEY_ID_NATIVE), - FLAG(NO_AMPDU_KEYBORDER_SUPPORT), + FLAG(AMPDU_KEYBORDER_SUPPORT), #undef FLAG }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index c2d8b5451a5e..2c9b3eb8b652 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -692,14 +692,16 @@ static inline int drv_remain_on_channel(struct ieee80211_local *local, return ret; } -static inline int drv_cancel_remain_on_channel(struct ieee80211_local *local) +static inline int +drv_cancel_remain_on_channel(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { int ret; might_sleep(); - trace_drv_cancel_remain_on_channel(local); - ret = local->ops->cancel_remain_on_channel(&local->hw); + trace_drv_cancel_remain_on_channel(local, sdata); + ret = local->ops->cancel_remain_on_channel(&local->hw, &sdata->vif); trace_drv_return_int(local, ret); return ret; diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 219650591c79..a02abfc424aa 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -50,3 +50,42 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, he_cap->has_he = true; } + +void +ieee80211_he_op_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_operation *he_op_ie_elem) +{ + struct ieee80211_he_operation *he_operation = + &vif->bss_conf.he_operation; + + if (!he_op_ie_elem) { + memset(he_operation, 0, sizeof(*he_operation)); + return; + } + + vif->bss_conf.he_operation = *he_op_ie_elem; +} + +void +ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_spr *he_spr_ie_elem) +{ + struct ieee80211_he_obss_pd *he_obss_pd = + &vif->bss_conf.he_obss_pd; + const u8 *data = he_spr_ie_elem->optional; + + memset(he_obss_pd, 0, sizeof(*he_obss_pd)); + + if (!he_spr_ie_elem) + return; + + if (he_spr_ie_elem->he_sr_control & + IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) + data++; + if (he_spr_ie_elem->he_sr_control & + IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) { + he_obss_pd->max_offset = *data++; + he_obss_pd->min_offset = *data++; + he_obss_pd->enable = true; + } +} diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d5a500b2a448..a2e4d6b8fd98 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -359,7 +359,7 @@ void ieee80211_ba_session_work(struct work_struct *work) sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, IEEE80211_MAX_AMPDU_BUF_HT, - false, true); + false, true, NULL); if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, sta->ampdu_mlme.tid_rx_manage_offl)) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 004e2e3adb88..791ce58d0f09 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1480,6 +1480,7 @@ struct ieee802_11_elems { const struct ieee80211_meshconf_ie *mesh_config; const u8 *he_cap; const struct ieee80211_he_operation *he_operation; + const struct ieee80211_he_spr *he_spr; const struct ieee80211_mu_edca_param_set *mu_edca_param_set; const u8 *uora_element; const u8 *mesh_id; @@ -1506,6 +1507,7 @@ struct ieee802_11_elems { u8 max_bssid_indicator; u8 dtim_count; u8 dtim_period; + const struct ieee80211_addba_ext_ie *addba_ext_ie; /* length of them, respectively */ u8 ext_capab_len; @@ -1767,7 +1769,8 @@ ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags); void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_supported_band *sband, - int retry_count, int shift, bool send_to_cooked); + int retry_count, int shift, bool send_to_cooked, + struct ieee80211_tx_status *status); void ieee80211_check_fast_xmit(struct sta_info *sta); void ieee80211_check_fast_xmit_all(struct ieee80211_local *local); @@ -1804,7 +1807,8 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, void ___ieee80211_start_rx_ba_session(struct sta_info *sta, u8 dialog_token, u16 timeout, u16 start_seq_num, u16 ba_policy, u16 tid, - u16 buf_size, bool tx, bool auto_seq); + u16 buf_size, bool tx, bool auto_seq, + const struct ieee80211_addba_ext_ie *addbaext); void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, enum ieee80211_agg_stop_reason reason); void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, @@ -1869,6 +1873,13 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const u8 *he_cap_ie, u8 he_cap_len, struct sta_info *sta); +void +ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_spr *he_spr_ie_elem); + +void +ieee80211_he_op_ie_to_bss_conf(struct ieee80211_vif *vif, + const struct ieee80211_he_operation *he_op_ie_elem); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, @@ -2133,9 +2144,11 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef); +u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype); u8 *ieee80211_ie_build_he_cap(u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end); +u8 *ieee80211_ie_build_he_oper(u8 *pos); int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index dd60f6428049..7dfee848abac 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -270,7 +270,7 @@ int ieee80211_set_tx_key(struct ieee80211_key *key) sta->ptk_idx = key->conf.keyidx; - if (ieee80211_hw_check(&local->hw, NO_AMPDU_KEYBORDER_SUPPORT)) + if (!ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) clear_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_check_fast_xmit(sta); @@ -290,15 +290,15 @@ static void ieee80211_pairwise_rekey(struct ieee80211_key *old, /* Extended Key ID key install, initial one or rekey */ if (sta->ptk_idx != INVALID_PTK_KEYIDX && - ieee80211_hw_check(&local->hw, - NO_AMPDU_KEYBORDER_SUPPORT)) { + !ieee80211_hw_check(&local->hw, AMPDU_KEYBORDER_SUPPORT)) { /* Aggregation Sessions with Extended Key ID must not * mix MPDUs with different keyIDs within one A-MPDU. - * Tear down any running Tx aggregation and all new - * Rx/Tx aggregation request during rekey if the driver - * asks us to do so. (Blocking Tx only would be - * sufficient but WLAN_STA_BLOCK_BA gets the job done - * for the few ms we need it.) + * Tear down running Tx aggregation sessions and block + * new Rx/Tx aggregation requests during rekey to + * ensure there are no A-MPDUs when the driver is not + * supporting A-MPDU key borders. (Blocking Tx only + * would be sufficient but WLAN_STA_BLOCK_BA gets the + * job done for the few ms we need it.) */ set_sta_flag(sta, WLAN_STA_BLOCK_BA); mutex_lock(&sta->ampdu_mlme.mtx); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4c2702f128f3..29b9d57df1a3 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1048,21 +1048,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } } - /* Enable Extended Key IDs when driver allowed it, or when it - * supports neither HW crypto nor A-MPDUs + /* Mac80211 and therefore all drivers using SW crypto only + * are able to handle PTK rekeys and Extended Key ID. */ - if ((!local->ops->set_key && - !ieee80211_hw_check(hw, AMPDU_AGGREGATION)) || - ieee80211_hw_check(&local->hw, EXT_KEY_ID_NATIVE)) - wiphy_ext_feature_set(local->hw.wiphy, - NL80211_EXT_FEATURE_EXT_KEY_ID); - - /* Mac80211 and therefore all cards only using SW crypto are able to - * handle PTK rekeys correctly - */ - if (!local->ops->set_key) + if (!local->ops->set_key) { wiphy_ext_feature_set(local->hw.wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0); + wiphy_ext_feature_set(local->hw.wiphy, + NL80211_EXT_FEATURE_EXT_KEY_ID); + } /* * Calculate scan IE length -- we need this to alloc diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 2e7fa743c892..d09b3c789314 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -532,6 +532,61 @@ int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, return 0; } +int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, u8 ie_len) +{ + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_supported_band *sband; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return -EINVAL; + + he_cap = ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); + + if (!he_cap || + 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 0; + + if (skb_tailroom(skb) < ie_len) + return -ENOMEM; + + pos = skb_put(skb, ie_len); + ieee80211_ie_build_he_cap(pos, he_cap, pos + ie_len); + + return 0; +} + +int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_supported_band *sband; + u8 *pos; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return -EINVAL; + + he_cap = ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); + if (!he_cap || + 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 0; + + if (skb_tailroom(skb) < 2 + 1 + sizeof(struct ieee80211_he_operation)) + return -ENOMEM; + + pos = skb_put(skb, 2 + 1 + sizeof(struct ieee80211_he_operation)); + ieee80211_ie_build_he_oper(pos); + + return 0; +} + static void ieee80211_mesh_path_timer(struct timer_list *t) { struct ieee80211_sub_if_data *sdata = @@ -677,6 +732,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) struct ieee80211_chanctx_conf *chanctx_conf; struct mesh_csa_settings *csa; enum nl80211_band band; + u8 ie_len_he_cap; u8 *pos; struct ieee80211_sub_if_data *sdata; int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon); @@ -687,6 +743,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) band = chanctx_conf->def.chan->band; rcu_read_unlock(); + ie_len_he_cap = ieee80211_ie_len_he_cap(sdata, + NL80211_IFTYPE_MESH_POINT); head_len = hdr_len + 2 + /* NULL SSID */ /* Channel Switch Announcement */ @@ -706,6 +764,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) 2 + sizeof(__le16) + /* awake window */ 2 + sizeof(struct ieee80211_vht_cap) + 2 + sizeof(struct ieee80211_vht_operation) + + ie_len_he_cap + + 2 + 1 + sizeof(struct ieee80211_he_operation) + ifmsh->ie_len; bcn = kzalloc(sizeof(*bcn) + head_len + tail_len, GFP_KERNEL); @@ -823,6 +883,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) mesh_add_awake_window_ie(sdata, skb) || mesh_add_vht_cap_ie(sdata, skb) || mesh_add_vht_oper_ie(sdata, skb) || + mesh_add_he_cap_ie(sdata, skb, ie_len_he_cap) || + mesh_add_he_oper_ie(sdata, skb) || mesh_add_vendor_ies(sdata, skb)) goto out_free; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 94d57cce70da..953f720754e8 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -218,6 +218,10 @@ int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); +int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, u8 ie_len); +int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index dd3aefd052a9..737c5f4dbf52 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -218,9 +218,12 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, bool include_plid = false; u16 peering_proto = 0; u8 *pos, ie_len = 4; + u8 ie_len_he_cap; int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.self_prot); int err = -ENOMEM; + ie_len_he_cap = ieee80211_ie_len_he_cap(sdata, + NL80211_IFTYPE_MESH_POINT); skb = dev_alloc_skb(local->tx_headroom + hdr_len + 2 + /* capability info */ @@ -233,6 +236,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, 2 + sizeof(struct ieee80211_ht_operation) + 2 + sizeof(struct ieee80211_vht_cap) + 2 + sizeof(struct ieee80211_vht_operation) + + ie_len_he_cap + + 2 + 1 + sizeof(struct ieee80211_he_operation) + 2 + 8 + /* peering IE */ sdata->u.mesh.ie_len); if (!skb) @@ -321,7 +326,9 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, if (mesh_add_ht_cap_ie(sdata, skb) || mesh_add_ht_oper_ie(sdata, skb) || mesh_add_vht_cap_ie(sdata, skb) || - mesh_add_vht_oper_ie(sdata, skb)) + mesh_add_vht_oper_ie(sdata, skb) || + mesh_add_he_cap_ie(sdata, skb, ie_len_he_cap) || + mesh_add_he_oper_ie(sdata, skb)) goto free; } @@ -433,6 +440,9 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, elems->vht_cap_elem, sta); + ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, elems->he_cap, + elems->he_cap_len, sta); + if (bw != sta->sta.bandwidth) changed |= IEEE80211_RC_BW_CHANGED; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 4c888dc9bd81..641876982ab9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2522,7 +2522,10 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) if (ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) { ifmgd->nullfunc_failed = false; - ieee80211_send_nullfunc(sdata->local, sdata, false); + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) + ifmgd->probe_send_count--; + else + ieee80211_send_nullfunc(sdata->local, sdata, false); } else { int ssid_len; @@ -3391,6 +3394,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (elems.uora_element) bss_conf->uora_ocw_range = elems.uora_element[0]; + ieee80211_he_op_ie_to_bss_conf(&sdata->vif, elems.he_operation); + ieee80211_he_spr_ie_to_bss_conf(&sdata->vif, elems.he_spr); /* TODO: OPEN: what happens if BSS color disable is set? */ } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 60ef8972b254..c710504ccf1a 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -8,6 +8,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2019 Intel Corporation */ #include <linux/export.h> #include <net/mac80211.h> @@ -732,7 +733,7 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local, } if (local->ops->remain_on_channel) { - ret = drv_cancel_remain_on_channel(local); + ret = drv_cancel_remain_on_channel(local, roc->sdata); if (WARN_ON_ONCE(ret)) { mutex_unlock(&local->mtx); return ret; @@ -991,7 +992,7 @@ void ieee80211_roc_purge(struct ieee80211_local *local, if (roc->started) { if (local->ops->remain_on_channel) { /* can race, so ignore return value */ - drv_cancel_remain_on_channel(local); + drv_cancel_remain_on_channel(local, sdata); ieee80211_roc_notify_destroy(roc); } else { roc->abort = true; diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 5d5348bc41ec..5397c6dad056 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -60,15 +60,6 @@ static inline void rate_control_add_sta_debugfs(struct sta_info *sta) #endif } -static inline void rate_control_remove_sta_debugfs(struct sta_info *sta) -{ -#ifdef CONFIG_MAC80211_DEBUGFS - struct rate_control_ref *ref = sta->rate_ctrl; - if (ref && ref->ops->remove_sta_debugfs) - ref->ops->remove_sta_debugfs(ref->priv, sta->rate_ctrl_priv); -#endif -} - void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata); /* Get a reference to the rate control algorithm. If `name' is NULL, get the diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 95eb8220e2e4..fb6614f57cbc 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1065,7 +1065,6 @@ static void __sta_info_destroy_part2(struct sta_info *sta) cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); kfree(sinfo); - rate_control_remove_sta_debugfs(sta); ieee80211_sta_debugfs_remove(sta); cleanup_single_sta(sta); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index a88e3bf17e9d..f03aa8924d23 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -254,7 +254,8 @@ static void ieee80211_set_bar_pending(struct sta_info *sta, u8 tid, u16 ssn) tid_tx->bar_pending = true; } -static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info) +static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info, + struct ieee80211_tx_status *status) { int len = sizeof(struct ieee80211_radiotap_header); @@ -272,7 +273,14 @@ static int ieee80211_tx_radiotap_len(struct ieee80211_tx_info *info) /* IEEE80211_RADIOTAP_MCS * IEEE80211_RADIOTAP_VHT */ - if (info->status.rates[0].idx >= 0) { + if (status && status->rate) { + if (status->rate->flags & RATE_INFO_FLAGS_MCS) + len += 3; + else if (status->rate->flags & RATE_INFO_FLAGS_VHT_MCS) + len = ALIGN(len, 2) + 12; + else if (status->rate->flags & RATE_INFO_FLAGS_HE_MCS) + len = ALIGN(len, 2) + 12; + } else if (info->status.rates[0].idx >= 0) { if (info->status.rates[0].flags & IEEE80211_TX_RC_MCS) len += 3; else if (info->status.rates[0].flags & IEEE80211_TX_RC_VHT_MCS) @@ -286,12 +294,14 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, struct ieee80211_supported_band *sband, struct sk_buff *skb, int retry_count, - int rtap_len, int shift) + int rtap_len, int shift, + struct ieee80211_tx_status *status) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_radiotap_header *rthdr; unsigned char *pos; + u16 legacy_rate = 0; u16 txflags; rthdr = skb_push(skb, rtap_len); @@ -310,14 +320,22 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, */ /* IEEE80211_RADIOTAP_RATE */ - if (info->status.rates[0].idx >= 0 && - !(info->status.rates[0].flags & (IEEE80211_TX_RC_MCS | - IEEE80211_TX_RC_VHT_MCS))) { - u16 rate; + if (status && status->rate && !(status->rate->flags & + (RATE_INFO_FLAGS_MCS | + RATE_INFO_FLAGS_60G | + RATE_INFO_FLAGS_VHT_MCS | + RATE_INFO_FLAGS_HE_MCS))) + legacy_rate = status->rate->legacy; + else if (info->status.rates[0].idx >= 0 && + !(info->status.rates[0].flags & (IEEE80211_TX_RC_MCS | + IEEE80211_TX_RC_VHT_MCS))) + legacy_rate = + sband->bitrates[info->status.rates[0].idx].bitrate; + + if (legacy_rate) { rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_RATE); - rate = sband->bitrates[info->status.rates[0].idx].bitrate; - *pos = DIV_ROUND_UP(rate, 5 * (1 << shift)); + *pos = DIV_ROUND_UP(legacy_rate, 5 * (1 << shift)); /* padding for tx flags */ pos += 2; } @@ -341,7 +359,139 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, *pos = retry_count; pos++; - if (info->status.rates[0].idx < 0) + if (status && status->rate && + (status->rate->flags & RATE_INFO_FLAGS_MCS)) { + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS); + pos[0] = IEEE80211_RADIOTAP_MCS_HAVE_MCS | + IEEE80211_RADIOTAP_MCS_HAVE_GI | + IEEE80211_RADIOTAP_MCS_HAVE_BW; + if (status->rate->flags & RATE_INFO_FLAGS_SHORT_GI) + pos[1] |= IEEE80211_RADIOTAP_MCS_SGI; + if (status->rate->bw == RATE_INFO_BW_40) + pos[1] |= IEEE80211_RADIOTAP_MCS_BW_40; + pos[2] = status->rate->mcs; + pos += 3; + } else if (status && status->rate && + (status->rate->flags & RATE_INFO_FLAGS_VHT_MCS)) { + u16 known = local->hw.radiotap_vht_details & + (IEEE80211_RADIOTAP_VHT_KNOWN_GI | + IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH); + + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT); + + /* required alignment from rthdr */ + pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); + + /* u16 known - IEEE80211_RADIOTAP_VHT_KNOWN_* */ + put_unaligned_le16(known, pos); + pos += 2; + + /* u8 flags - IEEE80211_RADIOTAP_VHT_FLAG_* */ + if (status->rate->flags & RATE_INFO_FLAGS_SHORT_GI) + *pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; + pos++; + + /* u8 bandwidth */ + switch (status->rate->bw) { + case RATE_INFO_BW_160: + *pos = 11; + break; + case RATE_INFO_BW_80: + *pos = 2; + break; + case RATE_INFO_BW_40: + *pos = 1; + break; + default: + *pos = 0; + break; + } + + /* u8 mcs_nss[4] */ + *pos = (status->rate->mcs << 4) | status->rate->nss; + pos += 4; + + /* u8 coding */ + pos++; + /* u8 group_id */ + pos++; + /* u16 partial_aid */ + pos += 2; + } else if (status && status->rate && + (status->rate->flags & RATE_INFO_FLAGS_HE_MCS)) { + struct ieee80211_radiotap_he *he; + + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE); + + /* required alignment from rthdr */ + pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); + he = (struct ieee80211_radiotap_he *)pos; + + he->data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_SU | + IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN); + + he->data2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN); + +#define HE_PREP(f, val) le16_encode_bits(val, IEEE80211_RADIOTAP_HE_##f) + + he->data6 |= HE_PREP(DATA6_NSTS, status->rate->nss); + +#define CHECK_GI(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_GI_##s != \ + (int)NL80211_RATE_INFO_HE_GI_##s) + + CHECK_GI(0_8); + CHECK_GI(1_6); + CHECK_GI(3_2); + + he->data3 |= HE_PREP(DATA3_DATA_MCS, status->rate->mcs); + he->data3 |= HE_PREP(DATA3_DATA_DCM, status->rate->he_dcm); + + he->data5 |= HE_PREP(DATA5_GI, status->rate->he_gi); + + switch (status->rate->bw) { + case RATE_INFO_BW_20: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ); + break; + case RATE_INFO_BW_40: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ); + break; + case RATE_INFO_BW_80: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ); + break; + case RATE_INFO_BW_160: + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ); + break; + case RATE_INFO_BW_HE_RU: +#define CHECK_RU_ALLOC(s) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_##s##T != \ + NL80211_RATE_INFO_HE_RU_ALLOC_##s + 4) + + CHECK_RU_ALLOC(26); + CHECK_RU_ALLOC(52); + CHECK_RU_ALLOC(106); + CHECK_RU_ALLOC(242); + CHECK_RU_ALLOC(484); + CHECK_RU_ALLOC(996); + CHECK_RU_ALLOC(2x996); + + he->data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC, + status->rate->he_ru_alloc + 4); + break; + default: + WARN_ONCE(1, "Invalid SU BW %d\n", status->rate->bw); + } + + pos += sizeof(struct ieee80211_radiotap_he); + } + + if ((status && status->rate) || info->status.rates[0].idx < 0) return; /* IEEE80211_RADIOTAP_MCS @@ -645,7 +795,8 @@ static int ieee80211_tx_get_rates(struct ieee80211_hw *hw, void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_supported_band *sband, - int retry_count, int shift, bool send_to_cooked) + int retry_count, int shift, bool send_to_cooked, + struct ieee80211_tx_status *status) { struct sk_buff *skb2; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -654,14 +805,14 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, int rtap_len; /* send frame to monitor interfaces now */ - rtap_len = ieee80211_tx_radiotap_len(info); + rtap_len = ieee80211_tx_radiotap_len(info, status); if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) { pr_err("ieee80211_tx_status: headroom too small\n"); dev_kfree_skb(skb); return; } ieee80211_add_tx_radiotap_header(local, sband, skb, retry_count, - rtap_len, shift); + rtap_len, shift, status); /* XXX: is this sufficient for BPF? */ skb_reset_mac_header(skb); @@ -901,7 +1052,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, } /* send to monitor interfaces */ - ieee80211_tx_monitor(local, skb, sband, retry_count, shift, send_to_cooked); + ieee80211_tx_monitor(local, skb, sband, retry_count, shift, + send_to_cooked, status); } void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 3bb4459b52c7..4768322dc202 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -1242,9 +1242,10 @@ TRACE_EVENT(drv_remain_on_channel, ) ); -DEFINE_EVENT(local_only_evt, drv_cancel_remain_on_channel, - TP_PROTO(struct ieee80211_local *local), - TP_ARGS(local) +DEFINE_EVENT(local_sdata_evt, drv_cancel_remain_on_channel, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + TP_ARGS(local, sdata) ); TRACE_EVENT(drv_set_ringparam, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f13eb2f61ccf..235c6377a203 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3546,6 +3546,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, ieee80211_tx_result r; struct ieee80211_vif *vif = txq->vif; + WARN_ON_ONCE(softirq_count() == 0); + begin: spin_lock_bh(&fq->lock); @@ -4647,7 +4649,8 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, if (!sband) return bcn; - ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false); + ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false, + NULL); return bcn; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index ad1e58184c4e..286c7ee35e63 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1200,6 +1200,13 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; + case WLAN_EID_ADDBA_EXT: + if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + elem_parse_failed = true; + break; + } + elems->addba_ext_ie = (void *)pos; + break; case WLAN_EID_TIMEOUT_INTERVAL: if (elen >= sizeof(struct ieee80211_timeout_interval_ie)) elems->timeout_int = (void *)pos; @@ -1233,6 +1240,10 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION && elen == 3) { elems->mbssid_config_ie = (void *)&pos[1]; + } else if (pos[0] == WLAN_EID_EXT_HE_SPR && + elen >= sizeof(*elems->he_spr) && + elen >= ieee80211_he_spr_size(&pos[1])) { + elems->he_spr = (void *)&pos[1]; } break; default: @@ -2702,6 +2713,27 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, return pos; } +u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) +{ + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_supported_band *sband; + u8 n; + + sband = ieee80211_get_sband(sdata); + if (!sband) + return 0; + + he_cap = ieee80211_get_he_iftype_cap(sband, iftype); + if (!he_cap) + return 0; + + n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem); + return 2 + 1 + + sizeof(he_cap->he_cap_elem) + n + + ieee80211_he_ppe_size(he_cap->ppe_thres[0], + he_cap->he_cap_elem.phy_cap_info); +} + u8 *ieee80211_ie_build_he_cap(u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end) @@ -2891,6 +2923,34 @@ u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, return pos + sizeof(struct ieee80211_vht_operation); } +u8 *ieee80211_ie_build_he_oper(u8 *pos) +{ + struct ieee80211_he_operation *he_oper; + u32 he_oper_params; + + *pos++ = WLAN_EID_EXTENSION; + *pos++ = 1 + sizeof(struct ieee80211_he_operation); + *pos++ = WLAN_EID_EXT_HE_OPERATION; + + he_oper_params = 0; + he_oper_params |= u32_encode_bits(1023, /* disabled */ + IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); + he_oper_params |= u32_encode_bits(1, + IEEE80211_HE_OPERATION_ER_SU_DISABLE); + he_oper_params |= u32_encode_bits(1, + IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED); + + he_oper = (struct ieee80211_he_operation *)pos; + he_oper->he_oper_params = cpu_to_le32(he_oper_params); + + /* don't require special HE peer rates */ + he_oper->he_mcs_nss_set = cpu_to_le16(0xffff); + + /* TODO add VHT operational and 6GHz operational subelement? */ + + return pos + sizeof(struct ieee80211_vht_operation); +} + bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, struct cfg80211_chan_def *chandef) { diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index ee72779729e5..91bf32af55e9 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -946,7 +946,8 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) info = IEEE80211_SKB_CB(skb); - if (info->control.hw_key) + if (info->control.hw_key && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIE)) return TX_CONTINUE; if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) @@ -962,6 +963,9 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) bip_ipn_set64(mmie->sequence_number, pn64); + if (info->control.hw_key) + return TX_CONTINUE; + bip_aad(skb, aad); /* diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 0feb77fa9edc..d098d87bc331 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -7,7 +7,7 @@ #include <linux/rcupdate.h> #include <linux/jhash.h> #include <linux/types.h> -#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set.h> #define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) #define ipset_dereference_protected(p, set) \ @@ -953,7 +953,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0])); #endif key = HKEY(d, h->initval, t->htable_bits); - n = rcu_dereference_bh(hbucket(t, key)); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) continue; for (i = 0; i < n->pos; i++) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 6f9ead6319e0..67ac50104e6f 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -288,7 +288,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (n && !(SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(n, set)))) - n = NULL; + n = NULL; e = kzalloc(set->dsize, GFP_ATOMIC); if (!e) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 46f06f92ab8f..8b80ab794a92 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -617,7 +617,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; - union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; + union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; /* create a new connection entry */ IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 060565e7d227..8b48e7ce1c2c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -262,7 +262,7 @@ static inline unsigned int ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { - register unsigned int porth = ntohs(port); + unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; __u32 ahash; @@ -493,7 +493,7 @@ static inline unsigned int ip_vs_rs_hashkey(int af, const union nf_inet_addr *addr, __be16 port) { - register unsigned int porth = ntohs(port); + unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 @@ -1737,12 +1737,18 @@ proc_do_defense_mode(struct ctl_table *table, int write, int val = *valp; int rc; - rc = proc_dointvec(table, write, buffer, lenp, ppos); + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(int), + .mode = table->mode, + }; + + rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write && (*valp != val)) { - if ((*valp < 0) || (*valp > 3)) { - /* Restore the correct value */ - *valp = val; + if (val < 0 || val > 3) { + rc = -EINVAL; } else { + *valp = val; update_defense_level(ipvs); } } @@ -1756,33 +1762,20 @@ proc_do_sync_threshold(struct ctl_table *table, int write, int *valp = table->data; int val[2]; int rc; + struct ctl_table tmp = { + .data = &val, + .maxlen = table->maxlen, + .mode = table->mode, + }; - /* backup the value first */ memcpy(val, valp, sizeof(val)); - - rc = proc_dointvec(table, write, buffer, lenp, ppos); - if (write && (valp[0] < 0 || valp[1] < 0 || - (valp[0] >= valp[1] && valp[1]))) { - /* Restore the correct value */ - memcpy(valp, val, sizeof(val)); - } - return rc; -} - -static int -proc_do_sync_mode(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - int *valp = table->data; - int val = *valp; - int rc; - - rc = proc_dointvec(table, write, buffer, lenp, ppos); - if (write && (*valp != val)) { - if ((*valp < 0) || (*valp > 1)) { - /* Restore the correct value */ - *valp = val; - } + rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); + if (write) { + if (val[0] < 0 || val[1] < 0 || + (val[0] >= val[1] && val[1])) + rc = -EINVAL; + else + memcpy(valp, val, sizeof(val)); } return rc; } @@ -1795,12 +1788,18 @@ proc_do_sync_ports(struct ctl_table *table, int write, int val = *valp; int rc; - rc = proc_dointvec(table, write, buffer, lenp, ppos); + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(int), + .mode = table->mode, + }; + + rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write && (*valp != val)) { - if (*valp < 1 || !is_power_of_2(*valp)) { - /* Restore the correct value */ + if (val < 1 || !is_power_of_2(val)) + rc = -EINVAL; + else *valp = val; - } } return rc; } @@ -1860,7 +1859,9 @@ static struct ctl_table vs_vars[] = { .procname = "sync_version", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_do_sync_mode, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "sync_ports", diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c8b5a504476c..77c323c36a88 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -160,7 +160,7 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) /* get weighted least-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) { - register struct ip_vs_dest_set_elem *e; + struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *least; int loh, doh; @@ -209,7 +209,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) /* get weighted most-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) { - register struct ip_vs_dest_set_elem *e; + struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *most; int moh, doh; diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c index 94d9d349ebb0..da0280cec506 100644 --- a/net/netfilter/ipvs/ip_vs_mh.c +++ b/net/netfilter/ipvs/ip_vs_mh.c @@ -174,8 +174,8 @@ static int ip_vs_mh_populate(struct ip_vs_mh_state *s, return 0; } - table = kcalloc(BITS_TO_LONGS(IP_VS_MH_TAB_SIZE), - sizeof(unsigned long), GFP_KERNEL); + table = kcalloc(BITS_TO_LONGS(IP_VS_MH_TAB_SIZE), + sizeof(unsigned long), GFP_KERNEL); if (!table) return -ENOMEM; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 000d961b97e4..32b028853a7c 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -710,7 +710,7 @@ static int __ip_vs_tcp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd sizeof(tcp_timeouts)); if (!pd->timeout_table) return -ENOMEM; - pd->tcp_state_table = tcp_states; + pd->tcp_state_table = tcp_states; return 0; } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 0ecb3e289ef2..c57d2348c505 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -162,7 +162,7 @@ static int try_rfc959(const char *data, size_t dlen, if (length == 0) return 0; - cmd->u3.ip = htonl((array[0] << 24) | (array[1] << 16) | + cmd->u3.ip = htonl((array[0] << 24) | (array[1] << 16) | (array[2] << 8) | array[3]); cmd->u.tcp.port = htons((array[4] << 8) | array[5]); return length; diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 74b8113f7aeb..d1c6b2a2e7bd 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -11,7 +11,7 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> -static spinlock_t nf_connlabels_lock; +static __read_mostly DEFINE_SPINLOCK(nf_connlabels_lock); static int replace_u32(u32 *address, u32 mask, u32 new) { @@ -89,7 +89,6 @@ int nf_conntrack_labels_init(void) { BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX); - spin_lock_init(&nf_connlabels_lock); return nf_ct_extend_register(&labels_extend); } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 85c1f8c213b0..1926fd56df56 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1227,7 +1227,7 @@ static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = { [CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_WSCALE_REPLY] = { .type = NLA_U8 }, [CTA_PROTOINFO_TCP_FLAGS_ORIGINAL] = { .len = sizeof(struct nf_ct_tcp_flags) }, - [CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) }, + [CTA_PROTOINFO_TCP_FLAGS_REPLY] = { .len = sizeof(struct nf_ct_tcp_flags) }, }; #define TCP_NLATTR_SIZE ( \ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index e0d392cb3075..d97f4ea47cf3 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -511,8 +511,6 @@ static void nf_conntrack_standalone_fini_proc(struct net *net) /* Log invalid packets of a given protocol */ static int log_invalid_proto_min __read_mostly; static int log_invalid_proto_max __read_mostly = 255; -static int zero; -static int one = 1; /* size the user *wants to set */ static unsigned int nf_conntrack_htable_size_user __read_mostly; @@ -629,8 +627,8 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_LOG_INVALID] = { .procname = "nf_conntrack_log_invalid", @@ -654,8 +652,8 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_HELPER] = { .procname = "nf_conntrack_helper", @@ -663,8 +661,8 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_NF_CONNTRACK_EVENTS [NF_SYSCTL_CT_EVENTS] = { @@ -673,8 +671,8 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP @@ -684,8 +682,8 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC] = { @@ -759,16 +757,16 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_LIBERAL] = { .procname = "nf_conntrack_tcp_be_liberal", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { .procname = "nf_conntrack_tcp_max_retrans", @@ -904,8 +902,8 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_NF_CT_PROTO_GRE diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 7ac733ebd060..0a59c14b5177 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -722,7 +722,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, return ret; } -const struct nf_hook_ops nf_nat_ipv4_ops[] = { +static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_in, @@ -961,7 +961,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, return ret; } -const struct nf_hook_ops nf_nat_ipv6_ops[] = { +static const struct nf_hook_ops nf_nat_ipv6_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_in, diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index c769462a839e..b0930d4aba22 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -56,7 +56,7 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, switch (opcode) { case TCPOPT_MSS: if (opsize == TCPOLEN_MSS) { - opts->mss = get_unaligned_be16(ptr); + opts->mss_option = get_unaligned_be16(ptr); opts->options |= NF_SYNPROXY_OPT_MSS; } break; @@ -115,7 +115,7 @@ synproxy_build_options(struct tcphdr *th, const struct synproxy_options *opts) if (options & NF_SYNPROXY_OPT_MSS) *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | - opts->mss); + opts->mss_option); if (options & NF_SYNPROXY_OPT_TIMESTAMP) { if (options & NF_SYNPROXY_OPT_SACK_PERM) @@ -642,7 +642,7 @@ synproxy_recv_client_ack(struct net *net, } this_cpu_inc(snet->stats->cookie_valid); - opts->mss = mss; + opts->mss_option = mss; opts->options |= NF_SYNPROXY_OPT_MSS; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) @@ -1060,7 +1060,7 @@ synproxy_recv_client_ack_ipv6(struct net *net, } this_cpu_inc(snet->stats->cookie_valid); - opts->mss = mss; + opts->mss_option = mss; opts->options |= NF_SYNPROXY_OPT_MSS; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d47469f824a1..6d00bef023c4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7602,6 +7602,11 @@ static struct pernet_operations nf_tables_net_ops = { .exit = nf_tables_exit_net, }; +static struct flow_indr_block_ing_entry block_ing_entry = { + .cb = nft_indr_block_get_and_ing_cmd, + .list = LIST_HEAD_INIT(block_ing_entry.list), +}; + static int __init nf_tables_module_init(void) { int err; @@ -7633,6 +7638,7 @@ static int __init nf_tables_module_init(void) goto err5; nft_chain_route_init(); + flow_indr_add_block_ing_cb(&block_ing_entry); return err; err5: rhltable_destroy(&nft_objname_ht); @@ -7649,6 +7655,7 @@ err1: static void __exit nf_tables_module_exit(void) { + flow_indr_del_block_ing_cb(&block_ing_entry); nfnetlink_subsys_unregister(&nf_tables_subsys); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index c0d18c1d77ac..3c2725ade61b 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -182,24 +182,110 @@ static int nft_flow_offload_unbind(struct flow_block_offload *bo, return 0; } +static int nft_block_setup(struct nft_base_chain *basechain, + struct flow_block_offload *bo, + enum flow_block_command cmd) +{ + int err; + + switch (cmd) { + case FLOW_BLOCK_BIND: + err = nft_flow_offload_bind(bo, basechain); + break; + case FLOW_BLOCK_UNBIND: + err = nft_flow_offload_unbind(bo, basechain); + break; + default: + WARN_ON_ONCE(1); + err = -EOPNOTSUPP; + } + + return err; +} + +static int nft_block_offload_cmd(struct nft_base_chain *chain, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + int err; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + if (err < 0) + return err; + + return nft_block_setup(chain, &bo, cmd); +} + +static void nft_indr_block_ing_cmd(struct net_device *dev, + struct nft_base_chain *chain, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + + if (!chain) + return; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); + + nft_block_setup(chain, &bo, cmd); +} + +static int nft_indr_block_offload_cmd(struct nft_base_chain *chain, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct flow_block_offload bo = {}; + struct netlink_ext_ack extack = {}; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + flow_indr_block_call(dev, &bo, cmd); + + if (list_empty(&bo.cb_list)) + return -EOPNOTSUPP; + + return nft_block_setup(chain, &bo, cmd); +} + #define FLOW_SETUP_BLOCK TC_SETUP_BLOCK static int nft_flow_offload_chain(struct nft_trans *trans, enum flow_block_command cmd) { struct nft_chain *chain = trans->ctx.chain; - struct netlink_ext_ack extack = {}; - struct flow_block_offload bo = {}; struct nft_base_chain *basechain; struct net_device *dev; - int err; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); dev = basechain->ops.dev; - if (!dev || !dev->netdev_ops->ndo_setup_tc) + if (!dev) return -EOPNOTSUPP; /* Only default policy to accept is supported for now. */ @@ -208,26 +294,10 @@ static int nft_flow_offload_chain(struct nft_trans *trans, nft_trans_chain_policy(trans) != NF_ACCEPT) return -EOPNOTSUPP; - bo.command = cmd; - bo.block = &basechain->flow_block; - bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; - bo.extack = &extack; - INIT_LIST_HEAD(&bo.cb_list); - - err = dev->netdev_ops->ndo_setup_tc(dev, FLOW_SETUP_BLOCK, &bo); - if (err < 0) - return err; - - switch (cmd) { - case FLOW_BLOCK_BIND: - err = nft_flow_offload_bind(&bo, basechain); - break; - case FLOW_BLOCK_UNBIND: - err = nft_flow_offload_unbind(&bo, basechain); - break; - } - - return err; + if (dev->netdev_ops->ndo_setup_tc) + return nft_block_offload_cmd(basechain, dev, cmd); + else + return nft_indr_block_offload_cmd(basechain, dev, cmd); } int nft_flow_rule_offload_commit(struct net *net) @@ -277,3 +347,33 @@ int nft_flow_rule_offload_commit(struct net *net) return err; } + +void nft_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) +{ + struct net *net = dev_net(dev); + const struct nft_table *table; + const struct nft_chain *chain; + + list_for_each_entry_rcu(table, &net->nft.tables, list) { + if (table->family != NFPROTO_NETDEV) + continue; + + list_for_each_entry_rcu(chain, &table->chains, list) { + if (nft_is_base_chain(chain)) { + struct nft_base_chain *basechain; + + basechain = nft_base_chain(chain); + if (!strncmp(basechain->dev_name, dev->name, + IFNAMSIZ)) { + nft_indr_block_ing_cmd(dev, basechain, + cb, cb_priv, + command); + return; + } + } + } + } +} diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 6dee4f9a944c..d69e1863e536 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -651,7 +651,7 @@ nfulnl_log_packet(struct net *net, /* FIXME: do we want to make the size calculation conditional based on * what is actually present? way more branches and checks, but more * memory efficient... */ - size = nlmsg_total_size(sizeof(struct nfgenmsg)) + size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfulnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ @@ -668,7 +668,7 @@ nfulnl_log_packet(struct net *net, + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { - size += nla_total_size(skb->dev->hard_header_len) + size += nla_total_size(skb->dev->hard_header_len) + nla_total_size(sizeof(u_int16_t)) /* hwtype */ + nla_total_size(sizeof(u_int16_t)); /* hwlen */ } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index b6a7ce622c72..feabdfb22920 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -394,7 +394,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, char *secdata = NULL; u32 seclen = 0; - size = nlmsg_total_size(sizeof(struct nfgenmsg)) + size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ @@ -453,7 +453,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, } if (queue->flags & NFQA_CFG_F_UID_GID) { - size += (nla_total_size(sizeof(u_int32_t)) /* uid */ + size += (nla_total_size(sizeof(u_int32_t)) /* uid */ + nla_total_size(sizeof(u_int32_t))); /* gid */ } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index b310b637b550..974300178fa9 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -13,6 +13,7 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_offload.h> struct nft_bitwise { enum nft_registers sreg:8; @@ -126,12 +127,30 @@ nla_put_failure: return -1; } +static struct nft_data zero; + +static int nft_bitwise_offload(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_expr *expr) +{ + const struct nft_bitwise *priv = nft_expr_priv(expr); + + if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) || + priv->sreg != priv->dreg) + return -EOPNOTSUPP; + + memcpy(&ctx->regs[priv->dreg].mask, &priv->mask, sizeof(priv->mask)); + + return 0; +} + static const struct nft_expr_ops nft_bitwise_ops = { .type = &nft_bitwise_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_bitwise)), .eval = nft_bitwise_eval, .init = nft_bitwise_init, .dump = nft_bitwise_dump, + .offload = nft_bitwise_offload, }; struct nft_expr_type nft_bitwise_type __read_mostly = { diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index ca2ae4b95a8d..c7f0ef73d939 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -125,17 +125,13 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, return 0; } -static int nft_immediate_offload(struct nft_offload_ctx *ctx, - struct nft_flow_rule *flow, - const struct nft_expr *expr) +static int nft_immediate_offload_verdict(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_immediate_expr *priv) { - const struct nft_immediate_expr *priv = nft_expr_priv(expr); struct flow_action_entry *entry; const struct nft_data *data; - if (priv->dreg != NFT_REG_VERDICT) - return -EOPNOTSUPP; - entry = &flow->rule->action.entries[ctx->num_actions++]; data = &priv->data; @@ -153,6 +149,20 @@ static int nft_immediate_offload(struct nft_offload_ctx *ctx, return 0; } +static int nft_immediate_offload(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_expr *expr) +{ + const struct nft_immediate_expr *priv = nft_expr_priv(expr); + + if (priv->dreg == NFT_REG_VERDICT) + return nft_immediate_offload_verdict(ctx, flow, priv); + + memcpy(&ctx->regs[priv->dreg].data, &priv->data, sizeof(priv->data)); + + return 0; +} + static const struct nft_expr_ops nft_imm_ops = { .type = &nft_imm_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)), diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index b5aeccdddb22..087a056e34d1 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -10,7 +10,7 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> struct nft_bitmap_elem { struct list_head head; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6e8d20c03e3d..c490451fcebf 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -16,7 +16,7 @@ #include <linux/rhashtable.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> /* We target a hash table size of 4, element hint is 75% of final size */ #define NFT_RHASH_ELEMENT_HINT 3 diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 419d58ef802b..57123259452f 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -13,7 +13,7 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> struct nft_rbtree { struct rb_root root; diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 928e661d1517..db4c23f5dfcb 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -31,8 +31,8 @@ static void nft_synproxy_tcp_options(struct synproxy_options *opts, opts->options |= NF_SYNPROXY_OPT_ECN; opts->options &= priv->info.options; - opts->mss_encode = opts->mss; - opts->mss = info->mss; + opts->mss_encode = opts->mss_option; + opts->mss_option = info->mss; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, opts); else diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 9cec9eae556a..f56d3ed93e56 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -283,7 +283,7 @@ static int __init idletimer_tg_init(void) idletimer_tg_kobj = &idletimer_tg_device->kobj; - err = xt_register_target(&idletimer_tg); + err = xt_register_target(&idletimer_tg); if (err < 0) { pr_debug("couldn't register xt target\n"); goto out_dev; diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index ecbfa291fb70..731bc2cafae4 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -14,7 +14,6 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/ipset/ip_set.h> -#include <linux/netfilter/ipset/ip_set_timeout.h> #include <uapi/linux/netfilter/xt_set.h> MODULE_LICENSE("GPL"); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index ea64c90b14e8..17e6ca62f1be 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -970,7 +970,8 @@ static int nfc_genl_dep_link_down(struct sk_buff *skb, struct genl_info *info) int rc; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + !info->attrs[NFC_ATTR_TARGET_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); @@ -1018,7 +1019,8 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg = NULL; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index d01410e52097..65122bbccd27 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -222,6 +222,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_stats_percpu *stats; u64 *stats_counter; u32 n_mask_hit; + int error; stats = this_cpu_ptr(dp->stats_percpu); @@ -229,7 +230,6 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) flow = ovs_flow_tbl_lookup_stats(&dp->table, key, &n_mask_hit); if (unlikely(!flow)) { struct dp_upcall_info upcall; - int error; memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; @@ -246,7 +246,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) ovs_flow_stats_update(flow, key->tp.flags, skb); sf_acts = rcu_dereference(flow->sf_acts); - ovs_execute_actions(dp, skb, sf_acts, key); + error = ovs_execute_actions(dp, skb, sf_acts, key); + if (unlikely(error)) + net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", + ovs_dp_name(dp), error); stats_counter = &stats->n_hit; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 2b969f99ef13..2977137c28eb 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -705,7 +705,7 @@ static int rds_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_SEQPACKET || protocol) return -ESOCKTNOSUPPORT; - sk = sk_alloc(net, AF_RDS, GFP_ATOMIC, &rds_proto, kern); + sk = sk_alloc(net, AF_RDS, GFP_KERNEL, &rds_proto, kern); if (!sk) return -ENOMEM; @@ -741,6 +741,10 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len, spin_lock_bh(&rds_sock_lock); list_for_each_entry(rs, &rds_sock_list, rs_item) { + /* This option only supports IPv4 sockets. */ + if (!ipv6_addr_v4mapped(&rs->rs_bound_addr)) + continue; + read_lock(&rs->rs_recv_lock); /* XXX too lazy to maintain counts.. */ @@ -762,21 +766,60 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len, lens->each = sizeof(struct rds_info_message); } +#if IS_ENABLED(CONFIG_IPV6) +static void rds6_sock_inc_info(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + struct rds_incoming *inc; + unsigned int total = 0; + struct rds_sock *rs; + + len /= sizeof(struct rds6_info_message); + + spin_lock_bh(&rds_sock_lock); + + list_for_each_entry(rs, &rds_sock_list, rs_item) { + read_lock(&rs->rs_recv_lock); + + list_for_each_entry(inc, &rs->rs_recv_queue, i_item) { + total++; + if (total <= len) + rds6_inc_info_copy(inc, iter, &inc->i_saddr, + &rs->rs_bound_addr, 1); + } + + read_unlock(&rs->rs_recv_lock); + } + + spin_unlock_bh(&rds_sock_lock); + + lens->nr = total; + lens->each = sizeof(struct rds6_info_message); +} +#endif + static void rds_sock_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds_info_socket sinfo; + unsigned int cnt = 0; struct rds_sock *rs; len /= sizeof(struct rds_info_socket); spin_lock_bh(&rds_sock_lock); - if (len < rds_sock_count) + if (len < rds_sock_count) { + cnt = rds_sock_count; goto out; + } list_for_each_entry(rs, &rds_sock_list, rs_item) { + /* This option only supports IPv4 sockets. */ + if (!ipv6_addr_v4mapped(&rs->rs_bound_addr)) + continue; sinfo.sndbuf = rds_sk_sndbuf(rs); sinfo.rcvbuf = rds_sk_rcvbuf(rs); sinfo.bound_addr = rs->rs_bound_addr_v4; @@ -786,15 +829,51 @@ static void rds_sock_info(struct socket *sock, unsigned int len, sinfo.inum = sock_i_ino(rds_rs_to_sk(rs)); rds_info_copy(iter, &sinfo, sizeof(sinfo)); + cnt++; } out: - lens->nr = rds_sock_count; + lens->nr = cnt; lens->each = sizeof(struct rds_info_socket); spin_unlock_bh(&rds_sock_lock); } +#if IS_ENABLED(CONFIG_IPV6) +static void rds6_sock_info(struct socket *sock, unsigned int len, + struct rds_info_iterator *iter, + struct rds_info_lengths *lens) +{ + struct rds6_info_socket sinfo6; + struct rds_sock *rs; + + len /= sizeof(struct rds6_info_socket); + + spin_lock_bh(&rds_sock_lock); + + if (len < rds_sock_count) + goto out; + + list_for_each_entry(rs, &rds_sock_list, rs_item) { + sinfo6.sndbuf = rds_sk_sndbuf(rs); + sinfo6.rcvbuf = rds_sk_rcvbuf(rs); + sinfo6.bound_addr = rs->rs_bound_addr; + sinfo6.connected_addr = rs->rs_conn_addr; + sinfo6.bound_port = rs->rs_bound_port; + sinfo6.connected_port = rs->rs_conn_port; + sinfo6.inum = sock_i_ino(rds_rs_to_sk(rs)); + + rds_info_copy(iter, &sinfo6, sizeof(sinfo6)); + } + + out: + lens->nr = rds_sock_count; + lens->each = sizeof(struct rds6_info_socket); + + spin_unlock_bh(&rds_sock_lock); +} +#endif + static void rds_exit(void) { sock_unregister(rds_family_ops.family); @@ -808,6 +887,10 @@ static void rds_exit(void) rds_bind_lock_destroy(); rds_info_deregister_func(RDS_INFO_SOCKETS, rds_sock_info); rds_info_deregister_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info); +#if IS_ENABLED(CONFIG_IPV6) + rds_info_deregister_func(RDS6_INFO_SOCKETS, rds6_sock_info); + rds_info_deregister_func(RDS6_INFO_RECV_MESSAGES, rds6_sock_inc_info); +#endif } module_exit(rds_exit); @@ -845,6 +928,10 @@ static int rds_init(void) rds_info_register_func(RDS_INFO_SOCKETS, rds_sock_info); rds_info_register_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info); +#if IS_ENABLED(CONFIG_IPV6) + rds_info_register_func(RDS6_INFO_SOCKETS, rds6_sock_info); + rds_info_register_func(RDS6_INFO_RECV_MESSAGES, rds6_sock_inc_info); +#endif goto out; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 3cae88cbdaa0..1a8a4a760b84 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -385,6 +385,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) unsigned int posted = 0; int ret = 0; bool can_wait = !!(gfp & __GFP_DIRECT_RECLAIM); + bool must_wake = false; u32 pos; /* the goal here is to just make sure that someone, somewhere @@ -405,6 +406,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) recv = &ic->i_recvs[pos]; ret = rds_ib_recv_refill_one(conn, recv, gfp); if (ret) { + must_wake = true; break; } @@ -423,6 +425,11 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) } posted++; + + if ((posted > 128 && need_resched()) || posted > 8192) { + must_wake = true; + break; + } } /* We're doing flow control - update the window. */ @@ -445,10 +452,13 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) * if we should requeue. */ if (rds_conn_up(conn) && - ((can_wait && rds_ib_ring_low(&ic->i_recv_ring)) || + (must_wake || + (can_wait && rds_ib_ring_low(&ic->i_recv_ring)) || rds_ib_ring_empty(&ic->i_recv_ring))) { queue_delayed_work(rds_wq, &conn->c_recv_w, 1); } + if (can_wait) + cond_resched(); } /* diff --git a/net/rds/rds.h b/net/rds/rds.h index f0066d168499..ad605fd61655 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -717,7 +717,7 @@ struct rds_statistics { uint64_t s_cong_send_blocked; uint64_t s_recv_bytes_added_to_socket; uint64_t s_recv_bytes_removed_from_socket; - + uint64_t s_send_stuck_rm; }; /* af_rds.c */ diff --git a/net/rds/send.c b/net/rds/send.c index 031b1e97a466..9ce552abf9e9 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -145,6 +145,7 @@ int rds_send_xmit(struct rds_conn_path *cp) LIST_HEAD(to_be_dropped); int batch_count; unsigned long send_gen = 0; + int same_rm = 0; restart: batch_count = 0; @@ -200,6 +201,17 @@ restart: rm = cp->cp_xmit_rm; + if (!rm) { + same_rm = 0; + } else { + same_rm++; + if (same_rm >= 4096) { + rds_stats_inc(s_send_stuck_rm); + ret = -EAGAIN; + break; + } + } + /* * If between sending messages, we can send a pending congestion * map update. diff --git a/net/rds/stats.c b/net/rds/stats.c index 73be187d389e..9e87da43c004 100644 --- a/net/rds/stats.c +++ b/net/rds/stats.c @@ -76,6 +76,9 @@ static const char *const rds_stat_names[] = { "cong_update_received", "cong_send_error", "cong_send_blocked", + "recv_bytes_added_to_sock", + "recv_bytes_freed_fromsock", + "send_stuck_rm", }; void rds_stats_info_copy(struct rds_info_iterator *iter, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 145335611af6..fa5b030acaa8 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -226,6 +226,9 @@ struct rxrpc_security { int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, unsigned int, unsigned int, rxrpc_seq_t, u16); + /* Free crypto request on a call */ + void (*free_call_crypto)(struct rxrpc_call *); + /* Locate the data in a received packet that has been verified. */ void (*locate_data)(struct rxrpc_call *, struct sk_buff *, unsigned int *, unsigned int *); @@ -558,6 +561,7 @@ struct rxrpc_call { unsigned long expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ + struct skcipher_request *cipher_req; /* Packet cipher request buffer */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 217b12be9e08..60cbc81dc461 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -476,8 +476,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn) + if (conn) { rxrpc_disconnect_call(call); + conn->security->free_call_crypto(call); + } for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { rxrpc_free_skb(call->rxtx_buffer[i], diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index a29d26c273b5..f6c59f5fae9d 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -33,6 +33,10 @@ static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, return 0; } +static void none_free_call_crypto(struct rxrpc_call *call) +{ +} + static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb, unsigned int *_offset, unsigned int *_len) { @@ -83,6 +87,7 @@ const struct rxrpc_security rxrpc_no_security = { .exit = none_exit, .init_connection_security = none_init_connection_security, .prime_packet_security = none_prime_packet_security, + .free_call_crypto = none_free_call_crypto, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, .locate_data = none_locate_data, diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index ae8cd8926456..dbb109da1835 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -43,6 +43,7 @@ struct rxkad_level2_hdr { * packets */ static struct crypto_sync_skcipher *rxkad_ci; +static struct skcipher_request *rxkad_ci_req; static DEFINE_MUTEX(rxkad_ci_mutex); /* @@ -99,8 +100,8 @@ error: */ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) { + struct skcipher_request *req; struct rxrpc_key_token *token; - SYNC_SKCIPHER_REQUEST_ON_STACK(req, conn->cipher); struct scatterlist sg; struct rxrpc_crypt iv; __be32 *tmpbuf; @@ -115,6 +116,12 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) if (!tmpbuf) return -ENOMEM; + req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS); + if (!req) { + kfree(tmpbuf); + return -ENOMEM; + } + token = conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); @@ -128,7 +135,7 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, tmpsize, iv.x); crypto_skcipher_encrypt(req); - skcipher_request_zero(req); + skcipher_request_free(req); memcpy(&conn->csum_iv, tmpbuf + 2, sizeof(conn->csum_iv)); kfree(tmpbuf); @@ -137,6 +144,35 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn) } /* + * Allocate and prepare the crypto request on a call. For any particular call, + * this is called serially for the packets, so no lock should be necessary. + */ +static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call) +{ + struct crypto_skcipher *tfm = &call->conn->cipher->base; + struct skcipher_request *cipher_req = call->cipher_req; + + if (!cipher_req) { + cipher_req = skcipher_request_alloc(tfm, GFP_NOFS); + if (!cipher_req) + return NULL; + call->cipher_req = cipher_req; + } + + return cipher_req; +} + +/* + * Clean up the crypto on a call. + */ +static void rxkad_free_call_crypto(struct rxrpc_call *call) +{ + if (call->cipher_req) + skcipher_request_free(call->cipher_req); + call->cipher_req = NULL; +} + +/* * partially encrypt a packet (level 1 security) */ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, @@ -246,7 +282,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, void *sechdr) { struct rxrpc_skb_priv *sp; - SYNC_SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); + struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; u32 x, y; @@ -265,6 +301,10 @@ static int rxkad_secure_packet(struct rxrpc_call *call, if (ret < 0) return ret; + req = rxkad_get_call_crypto(call); + if (!req) + return -ENOMEM; + /* continue encrypting from where we left off */ memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); @@ -502,7 +542,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, unsigned int offset, unsigned int len, rxrpc_seq_t seq, u16 expected_cksum) { - SYNC_SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher); + struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; bool aborted; @@ -515,6 +555,10 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, if (!call->conn->cipher) return 0; + req = rxkad_get_call_crypto(call); + if (!req) + return -ENOMEM; + /* continue encrypting from where we left off */ memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); @@ -747,14 +791,18 @@ static void rxkad_calc_response_checksum(struct rxkad_response *response) /* * encrypt the response packet */ -static void rxkad_encrypt_response(struct rxrpc_connection *conn, - struct rxkad_response *resp, - const struct rxkad_key *s2) +static int rxkad_encrypt_response(struct rxrpc_connection *conn, + struct rxkad_response *resp, + const struct rxkad_key *s2) { - SYNC_SKCIPHER_REQUEST_ON_STACK(req, conn->cipher); + struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg[1]; + req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS); + if (!req) + return -ENOMEM; + /* continue encrypting from where we left off */ memcpy(&iv, s2->session_key, sizeof(iv)); @@ -764,7 +812,8 @@ static void rxkad_encrypt_response(struct rxrpc_connection *conn, skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x); crypto_skcipher_encrypt(req); - skcipher_request_zero(req); + skcipher_request_free(req); + return 0; } /* @@ -839,8 +888,9 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, /* calculate the response checksum and then do the encryption */ rxkad_calc_response_checksum(resp); - rxkad_encrypt_response(conn, resp, token->kad); - ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); + ret = rxkad_encrypt_response(conn, resp, token->kad); + if (ret == 0) + ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); kfree(resp); return ret; @@ -1017,18 +1067,16 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn, struct rxkad_response *resp, const struct rxrpc_crypt *session_key) { - SYNC_SKCIPHER_REQUEST_ON_STACK(req, rxkad_ci); + struct skcipher_request *req = rxkad_ci_req; struct scatterlist sg[1]; struct rxrpc_crypt iv; _enter(",,%08x%08x", ntohl(session_key->n[0]), ntohl(session_key->n[1])); - ASSERT(rxkad_ci != NULL); - mutex_lock(&rxkad_ci_mutex); if (crypto_sync_skcipher_setkey(rxkad_ci, session_key->x, - sizeof(*session_key)) < 0) + sizeof(*session_key)) < 0) BUG(); memcpy(&iv, session_key, sizeof(iv)); @@ -1222,10 +1270,26 @@ static void rxkad_clear(struct rxrpc_connection *conn) */ static int rxkad_init(void) { + struct crypto_sync_skcipher *tfm; + struct skcipher_request *req; + /* pin the cipher we need so that the crypto layer doesn't invoke * keventd to go get it */ - rxkad_ci = crypto_alloc_sync_skcipher("pcbc(fcrypt)", 0, 0); - return PTR_ERR_OR_ZERO(rxkad_ci); + tfm = crypto_alloc_sync_skcipher("pcbc(fcrypt)", 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + req = skcipher_request_alloc(&tfm->base, GFP_KERNEL); + if (!req) + goto nomem_tfm; + + rxkad_ci_req = req; + rxkad_ci = tfm; + return 0; + +nomem_tfm: + crypto_free_sync_skcipher(tfm); + return -ENOMEM; } /* @@ -1233,8 +1297,8 @@ static int rxkad_init(void) */ static void rxkad_exit(void) { - if (rxkad_ci) - crypto_free_sync_skcipher(rxkad_ci); + crypto_free_sync_skcipher(rxkad_ci); + skcipher_request_free(rxkad_ci_req); } /* @@ -1249,6 +1313,7 @@ const struct rxrpc_security rxkad = { .prime_packet_security = rxkad_prime_packet_security, .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, + .free_call_crypto = rxkad_free_call_crypto, .locate_data = rxkad_locate_data, .issue_challenge = rxkad_issue_challenge, .respond_to_challenge = rxkad_respond_to_challenge, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index efd3cfb80a2a..e0d8b456e9f5 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -36,6 +36,8 @@ #include <net/tc_act/tc_sample.h> #include <net/tc_act/tc_skbedit.h> #include <net/tc_act/tc_ct.h> +#include <net/tc_act/tc_mpls.h> +#include <net/flow_offload.h> extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -544,235 +546,71 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) } } -static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) -{ - const struct Qdisc_class_ops *cops; - struct Qdisc *qdisc; - - if (!dev_ingress_queue(dev)) - return NULL; - - qdisc = dev_ingress_queue(dev)->qdisc_sleeping; - if (!qdisc) - return NULL; - - cops = qdisc->ops->cl_ops; - if (!cops) - return NULL; - - if (!cops->tcf_block) - return NULL; - - return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); -} - -static struct rhashtable indr_setup_block_ht; - -struct tc_indr_block_dev { - struct rhash_head ht_node; - struct net_device *dev; - unsigned int refcnt; - struct list_head cb_list; - struct tcf_block *block; -}; - -struct tc_indr_block_cb { - struct list_head list; - void *cb_priv; - tc_indr_block_bind_cb_t *cb; - void *cb_ident; -}; - -static const struct rhashtable_params tc_indr_setup_block_ht_params = { - .key_offset = offsetof(struct tc_indr_block_dev, dev), - .head_offset = offsetof(struct tc_indr_block_dev, ht_node), - .key_len = sizeof(struct net_device *), -}; - -static struct tc_indr_block_dev * -tc_indr_block_dev_lookup(struct net_device *dev) -{ - return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, - tc_indr_setup_block_ht_params); -} - -static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev) -{ - struct tc_indr_block_dev *indr_dev; - - indr_dev = tc_indr_block_dev_lookup(dev); - if (indr_dev) - goto inc_ref; - - indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); - if (!indr_dev) - return NULL; - - INIT_LIST_HEAD(&indr_dev->cb_list); - indr_dev->dev = dev; - indr_dev->block = tc_dev_ingress_block(dev); - if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params)) { - kfree(indr_dev); - return NULL; - } - -inc_ref: - indr_dev->refcnt++; - return indr_dev; -} - -static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev) -{ - if (--indr_dev->refcnt) - return; - - rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params); - kfree(indr_dev); -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - if (indr_block_cb->cb == cb && - indr_block_cb->cb_ident == cb_ident) - return indr_block_cb; - return NULL; -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (indr_block_cb) - return ERR_PTR(-EEXIST); - - indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); - if (!indr_block_cb) - return ERR_PTR(-ENOMEM); - - indr_block_cb->cb_priv = cb_priv; - indr_block_cb->cb = cb; - indr_block_cb->cb_ident = cb_ident; - list_add(&indr_block_cb->list, &indr_dev->cb_list); - - return indr_block_cb; -} - -static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb) -{ - list_del(&indr_block_cb->list); - kfree(indr_block_cb); -} - static int tcf_block_setup(struct tcf_block *block, struct flow_block_offload *bo); -static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, - struct tc_indr_block_cb *indr_block_cb, +static void tc_indr_block_ing_cmd(struct net_device *dev, + struct tcf_block *block, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, enum flow_block_command command) { struct flow_block_offload bo = { .command = command, .binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - .net = dev_net(indr_dev->dev), - .block_shared = tcf_block_non_null_shared(indr_dev->block), + .net = dev_net(dev), + .block_shared = tcf_block_non_null_shared(block), }; INIT_LIST_HEAD(&bo.cb_list); - if (!indr_dev->block) + if (!block) return; - bo.block = &indr_dev->block->flow_block; - - indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - tcf_block_setup(indr_dev->block, &bo); -} - -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - int err; - - indr_dev = tc_indr_block_dev_get(dev); - if (!indr_dev) - return -ENOMEM; - - indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); - err = PTR_ERR_OR_ZERO(indr_block_cb); - if (err) - goto err_dev_put; + bo.block = &block->flow_block; - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_BIND); - return 0; + cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); -err_dev_put: - tc_indr_block_dev_put(indr_dev); - return err; + tcf_block_setup(block, &bo); } -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register); -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) { - int err; - - rtnl_lock(); - err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident); - rtnl_unlock(); + const struct Qdisc_class_ops *cops; + struct Qdisc *qdisc; - return err; -} -EXPORT_SYMBOL_GPL(tc_indr_block_cb_register); + if (!dev_ingress_queue(dev)) + return NULL; -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; + qdisc = dev_ingress_queue(dev)->qdisc_sleeping; + if (!qdisc) + return NULL; - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; + cops = qdisc->ops->cl_ops; + if (!cops) + return NULL; - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (!indr_block_cb) - return; + if (!cops->tcf_block) + return NULL; - /* Send unbind message if required to free any block cbs. */ - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_UNBIND); - tc_indr_block_cb_del(indr_block_cb); - tc_indr_block_dev_put(indr_dev); + return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); } -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister); -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static void tc_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) { - rtnl_lock(); - __tc_indr_block_cb_unregister(dev, cb, cb_ident); - rtnl_unlock(); + struct tcf_block *block = tc_dev_ingress_block(dev); + + tc_indr_block_ing_cmd(dev, block, cb, cb_priv, command); } -EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister); -static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, +static void tc_indr_block_call(struct tcf_block *block, + struct net_device *dev, struct tcf_block_ext_info *ei, enum flow_block_command command, struct netlink_ext_ack *extack) { - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; struct flow_block_offload bo = { .command = command, .binder_type = ei->binder_type, @@ -783,16 +621,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, }; INIT_LIST_HEAD(&bo.cb_list); - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; - - indr_dev->block = command == FLOW_BLOCK_BIND ? block : NULL; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - + flow_indr_block_call(dev, &bo, command); tcf_block_setup(block, &bo); } @@ -3204,6 +3033,12 @@ int tc_setup_flow_action(struct flow_action *flow_action, } else if (is_tcf_mirred_egress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED; entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT_INGRESS; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED_INGRESS; + entry->dev = tcf_mirred_dev(act); } else if (is_tcf_vlan(act)) { switch (tcf_vlan_action(act)) { case TCA_VLAN_ACT_PUSH: @@ -3269,6 +3104,33 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); entry->ct.zone = tcf_ct_zone(act); + } else if (is_tcf_mpls(act)) { + switch (tcf_mpls_action(act)) { + case TCA_MPLS_ACT_PUSH: + entry->id = FLOW_ACTION_MPLS_PUSH; + entry->mpls_push.proto = tcf_mpls_proto(act); + entry->mpls_push.label = tcf_mpls_label(act); + entry->mpls_push.tc = tcf_mpls_tc(act); + entry->mpls_push.bos = tcf_mpls_bos(act); + entry->mpls_push.ttl = tcf_mpls_ttl(act); + break; + case TCA_MPLS_ACT_POP: + entry->id = FLOW_ACTION_MPLS_POP; + entry->mpls_pop.proto = tcf_mpls_proto(act); + break; + case TCA_MPLS_ACT_MODIFY: + entry->id = FLOW_ACTION_MPLS_MANGLE; + entry->mpls_mangle.label = tcf_mpls_label(act); + entry->mpls_mangle.tc = tcf_mpls_tc(act); + entry->mpls_mangle.bos = tcf_mpls_bos(act); + entry->mpls_mangle.ttl = tcf_mpls_ttl(act); + break; + default: + goto err_out; + } + } else if (is_tcf_skbedit_ptype(act)) { + entry->id = FLOW_ACTION_PTYPE; + entry->ptype = tcf_skbedit_ptype(act); } else { goto err_out; } @@ -3321,6 +3183,11 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; +static struct flow_indr_block_ing_entry block_ing_entry = { + .cb = tc_indr_block_get_and_ing_cmd, + .list = LIST_HEAD_INIT(block_ing_entry.list), +}; + static int __init tc_filter_init(void) { int err; @@ -3333,10 +3200,7 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - err = rhashtable_init(&indr_setup_block_ht, - &tc_indr_setup_block_ht_params); - if (err) - goto err_rhash_setup_block_ht; + flow_indr_add_block_ing_cb(&block_ing_entry); rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, RTNL_FLAG_DOIT_UNLOCKED); @@ -3351,8 +3215,6 @@ static int __init tc_filter_init(void) return 0; -err_rhash_setup_block_ht: - unregister_pernet_subsys(&tcf_net_ops); err_register_pernet_subsys: destroy_workqueue(tc_filter_wq); return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index d59fbcc745d1..c261c0a18868 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -45,7 +45,6 @@ struct fq_codel_flow { struct sk_buff *tail; struct list_head flowchain; int deficit; - u32 dropped; /* number of drops (or ECN marks) on this flow */ struct codel_vars cvars; }; /* please try to keep this structure <= 64 bytes */ @@ -173,7 +172,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, __qdisc_drop(skb, to_free); } while (++i < max_packets && len < threshold); - flow->dropped += i; + /* Tell codel to increase its signal strength also */ + flow->cvars.count += i; q->backlogs[idx] -= len; q->memory_usage -= mem; sch->qstats.drops += i; @@ -211,7 +211,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_add_tail(&flow->flowchain, &q->new_flows); q->new_flow_count++; flow->deficit = q->quantum; - flow->dropped = 0; } get_codel_cb(skb)->mem_usage = skb->truesize; q->memory_usage += get_codel_cb(skb)->mem_usage; @@ -286,7 +285,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct sk_buff *skb; struct fq_codel_flow *flow; struct list_head *head; - u32 prev_drop_count, prev_ecn_mark; begin: head = &q->new_flows; @@ -303,16 +301,10 @@ begin: goto begin; } - prev_drop_count = q->cstats.drop_count; - prev_ecn_mark = q->cstats.ecn_mark; - skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - flow->dropped += q->cstats.drop_count - prev_drop_count; - flow->dropped += q->cstats.ecn_mark - prev_ecn_mark; - if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &q->new_flows) && !list_empty(&q->old_flows)) @@ -658,7 +650,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch_tree_unlock(sch); } qs.backlog = q->backlogs[idx]; - qs.drops = flow->dropped; + qs.drops = 0; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index e25d414ae12f..540bde009ea5 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -677,10 +677,6 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, }; -static const struct nla_policy entry_list_policy[TCA_TAPRIO_SCHED_MAX + 1] = { - [TCA_TAPRIO_SCHED_ENTRY] = { .type = NLA_NESTED }, -}; - static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9d1f83b10c0a..12503e16fa96 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1044,158 +1044,161 @@ out: return err; } -/* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size) - * - * Common routine for handling connect() and sctp_connectx(). - * Connect will come in with just a single address. - */ -static int __sctp_connect(struct sock *sk, - struct sockaddr *kaddrs, - int addrs_size, int flags, - sctp_assoc_t *assoc_id) +static int sctp_connect_new_asoc(struct sctp_endpoint *ep, + const union sctp_addr *daddr, + const struct sctp_initmsg *init, + struct sctp_transport **tp) { + struct sctp_association *asoc; + struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); - struct sctp_sock *sp; - struct sctp_endpoint *ep; - struct sctp_association *asoc = NULL; - struct sctp_association *asoc2; - struct sctp_transport *transport; - union sctp_addr to; enum sctp_scope scope; - long timeo; - int err = 0; - int addrcnt = 0; - int walk_size = 0; - union sctp_addr *sa_addr = NULL; - void *addr_buf; - unsigned short port; + int err; - sp = sctp_sk(sk); - ep = sp->ep; + if (sctp_endpoint_is_peeled_off(ep, daddr)) + return -EADDRNOTAVAIL; - /* connect() cannot be done on a socket that is already in ESTABLISHED - * state - UDP-style peeled off socket or a TCP-style socket that - * is already connected. - * It cannot be done even on a TCP-style listening socket. - */ - if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || - (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) { - err = -EISCONN; - goto out_free; + if (!ep->base.bind_addr.port) { + if (sctp_autobind(sk)) + return -EAGAIN; + } else { + if (ep->base.bind_addr.port < inet_prot_sock(net) && + !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) + return -EACCES; } - /* Walk through the addrs buffer and count the number of addresses. */ - addr_buf = kaddrs; - while (walk_size < addrs_size) { - struct sctp_af *af; - - if (walk_size + sizeof(sa_family_t) > addrs_size) { - err = -EINVAL; - goto out_free; - } + scope = sctp_scope(daddr); + asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); + if (!asoc) + return -ENOMEM; - sa_addr = addr_buf; - af = sctp_get_af_specific(sa_addr->sa.sa_family); + err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); + if (err < 0) + goto free; - /* If the address family is not supported or if this address - * causes the address buffer to overflow return EINVAL. - */ - if (!af || (walk_size + af->sockaddr_len) > addrs_size) { - err = -EINVAL; - goto out_free; - } + *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); + if (!*tp) { + err = -ENOMEM; + goto free; + } - port = ntohs(sa_addr->v4.sin_port); + if (!init) + return 0; - /* Save current address so we can work with it */ - memcpy(&to, sa_addr, af->sockaddr_len); + if (init->sinit_num_ostreams) { + __u16 outcnt = init->sinit_num_ostreams; - err = sctp_verify_addr(sk, &to, af->sockaddr_len); + asoc->c.sinit_num_ostreams = outcnt; + /* outcnt has been changed, need to re-init stream */ + err = sctp_stream_init(&asoc->stream, outcnt, 0, GFP_KERNEL); if (err) - goto out_free; + goto free; + } - /* Make sure the destination port is correctly set - * in all addresses. - */ - if (asoc && asoc->peer.port && asoc->peer.port != port) { - err = -EINVAL; - goto out_free; - } + if (init->sinit_max_instreams) + asoc->c.sinit_max_instreams = init->sinit_max_instreams; - /* Check if there already is a matching association on the - * endpoint (other than the one created here). - */ - asoc2 = sctp_endpoint_lookup_assoc(ep, &to, &transport); - if (asoc2 && asoc2 != asoc) { - if (asoc2->state >= SCTP_STATE_ESTABLISHED) - err = -EISCONN; - else - err = -EALREADY; - goto out_free; - } + if (init->sinit_max_attempts) + asoc->max_init_attempts = init->sinit_max_attempts; - /* If we could not find a matching association on the endpoint, - * make sure that there is no peeled-off association matching - * the peer address even on another socket. - */ - if (sctp_endpoint_is_peeled_off(ep, &to)) { - err = -EADDRNOTAVAIL; - goto out_free; - } + if (init->sinit_max_init_timeo) + asoc->max_init_timeo = + msecs_to_jiffies(init->sinit_max_init_timeo); - if (!asoc) { - /* If a bind() or sctp_bindx() is not called prior to - * an sctp_connectx() call, the system picks an - * ephemeral port and will choose an address set - * equivalent to binding with a wildcard address. - */ - if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) { - err = -EAGAIN; - goto out_free; - } - } else { - /* - * If an unprivileged user inherits a 1-many - * style socket with open associations on a - * privileged port, it MAY be permitted to - * accept new associations, but it SHOULD NOT - * be permitted to open new associations. - */ - if (ep->base.bind_addr.port < - inet_prot_sock(net) && - !ns_capable(net->user_ns, - CAP_NET_BIND_SERVICE)) { - err = -EACCES; - goto out_free; - } - } + return 0; +free: + sctp_association_free(asoc); + return err; +} - scope = sctp_scope(&to); - asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); - if (!asoc) { - err = -ENOMEM; - goto out_free; - } +static int sctp_connect_add_peer(struct sctp_association *asoc, + union sctp_addr *daddr, int addr_len) +{ + struct sctp_endpoint *ep = asoc->ep; + struct sctp_association *old; + struct sctp_transport *t; + int err; - err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, - GFP_KERNEL); - if (err < 0) { - goto out_free; - } + err = sctp_verify_addr(ep->base.sk, daddr, addr_len); + if (err) + return err; - } + old = sctp_endpoint_lookup_assoc(ep, daddr, &t); + if (old && old != asoc) + return old->state >= SCTP_STATE_ESTABLISHED ? -EISCONN + : -EALREADY; - /* Prime the peer's transport structures. */ - transport = sctp_assoc_add_peer(asoc, &to, GFP_KERNEL, - SCTP_UNKNOWN); - if (!transport) { - err = -ENOMEM; + if (sctp_endpoint_is_peeled_off(ep, daddr)) + return -EADDRNOTAVAIL; + + t = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); + if (!t) + return -ENOMEM; + + return 0; +} + +/* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size) + * + * Common routine for handling connect() and sctp_connectx(). + * Connect will come in with just a single address. + */ +static int __sctp_connect(struct sock *sk, struct sockaddr *kaddrs, + int addrs_size, int flags, sctp_assoc_t *assoc_id) +{ + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_endpoint *ep = sp->ep; + struct sctp_transport *transport; + struct sctp_association *asoc; + void *addr_buf = kaddrs; + union sctp_addr *daddr; + struct sctp_af *af; + int walk_size, err; + long timeo; + + if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || + (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) + return -EISCONN; + + daddr = addr_buf; + af = sctp_get_af_specific(daddr->sa.sa_family); + if (!af || af->sockaddr_len > addrs_size) + return -EINVAL; + + err = sctp_verify_addr(sk, daddr, af->sockaddr_len); + if (err) + return err; + + asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); + if (asoc) + return asoc->state >= SCTP_STATE_ESTABLISHED ? -EISCONN + : -EALREADY; + + err = sctp_connect_new_asoc(ep, daddr, NULL, &transport); + if (err) + return err; + asoc = transport->asoc; + + addr_buf += af->sockaddr_len; + walk_size = af->sockaddr_len; + while (walk_size < addrs_size) { + err = -EINVAL; + if (walk_size + sizeof(sa_family_t) > addrs_size) goto out_free; - } - addrcnt++; - addr_buf += af->sockaddr_len; + daddr = addr_buf; + af = sctp_get_af_specific(daddr->sa.sa_family); + if (!af || af->sockaddr_len + walk_size > addrs_size) + goto out_free; + + if (asoc->peer.port != ntohs(daddr->v4.sin_port)) + goto out_free; + + err = sctp_connect_add_peer(asoc, daddr, af->sockaddr_len); + if (err) + goto out_free; + + addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } @@ -1208,40 +1211,25 @@ static int __sctp_connect(struct sock *sk, goto out_free; } - err = sctp_primitive_ASSOCIATE(net, asoc, NULL); - if (err < 0) { + err = sctp_primitive_ASSOCIATE(sock_net(sk), asoc, NULL); + if (err < 0) goto out_free; - } /* Initialize sk's dport and daddr for getpeername() */ inet_sk(sk)->inet_dport = htons(asoc->peer.port); - sp->pf->to_sk_daddr(sa_addr, sk); + sp->pf->to_sk_daddr(daddr, sk); sk->sk_err = 0; - timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); - if (assoc_id) *assoc_id = asoc->assoc_id; - err = sctp_wait_for_connect(asoc, &timeo); - /* Note: the asoc may be freed after the return of - * sctp_wait_for_connect. - */ - - /* Don't free association on exit. */ - asoc = NULL; + timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); + return sctp_wait_for_connect(asoc, &timeo); out_free: pr_debug("%s: took out_free path with asoc:%p kaddrs:%p err:%d\n", __func__, asoc, kaddrs, err); - - if (asoc) { - /* sctp_primitive_ASSOCIATE may have added this association - * To the hash table, try to unhash it, just in case, its a noop - * if it wasn't hashed so we're safe - */ - sctp_association_free(asoc); - } + sctp_association_free(asoc); return err; } @@ -1311,7 +1299,8 @@ static int __sctp_setsockopt_connectx(struct sock *sk, pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, addrs, addrs_size); - if (unlikely(addrs_size <= 0)) + /* make sure the 1st addr's sa_family is accessible later */ + if (unlikely(addrs_size < sizeof(sa_family_t))) return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); @@ -1659,9 +1648,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, struct sctp_transport **tp) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct net *net = sock_net(sk); struct sctp_association *asoc; - enum sctp_scope scope; struct cmsghdr *cmsg; __be32 flowinfo = 0; struct sctp_af *af; @@ -1676,20 +1663,6 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, sctp_sstate(sk, CLOSING))) return -EADDRNOTAVAIL; - if (sctp_endpoint_is_peeled_off(ep, daddr)) - return -EADDRNOTAVAIL; - - if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) - return -EAGAIN; - } else { - if (ep->base.bind_addr.port < inet_prot_sock(net) && - !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) - return -EACCES; - } - - scope = sctp_scope(daddr); - /* Label connection socket for first association 1-to-many * style for client sequence socket()->sendmsg(). This * needs to be done before sctp_assoc_add_peer() as that will @@ -1705,45 +1678,10 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, if (err < 0) return err; - asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); - if (!asoc) - return -ENOMEM; - - if (sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL) < 0) { - err = -ENOMEM; - goto free; - } - - if (cmsgs->init) { - struct sctp_initmsg *init = cmsgs->init; - - if (init->sinit_num_ostreams) { - __u16 outcnt = init->sinit_num_ostreams; - - asoc->c.sinit_num_ostreams = outcnt; - /* outcnt has been changed, need to re-init stream */ - err = sctp_stream_init(&asoc->stream, outcnt, 0, - GFP_KERNEL); - if (err) - goto free; - } - - if (init->sinit_max_instreams) - asoc->c.sinit_max_instreams = init->sinit_max_instreams; - - if (init->sinit_max_attempts) - asoc->max_init_attempts = init->sinit_max_attempts; - - if (init->sinit_max_init_timeo) - asoc->max_init_timeo = - msecs_to_jiffies(init->sinit_max_init_timeo); - } - - *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); - if (!*tp) { - err = -ENOMEM; - goto free; - } + err = sctp_connect_new_asoc(ep, daddr, cmsgs->init, tp); + if (err) + return err; + asoc = (*tp)->asoc; if (!cmsgs->addrs_msg) return 0; @@ -1753,8 +1691,6 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, /* sendv addr list parse */ for_each_cmsghdr(cmsg, cmsgs->addrs_msg) { - struct sctp_transport *transport; - struct sctp_association *old; union sctp_addr _daddr; int dlen; @@ -1788,30 +1724,10 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, daddr->v6.sin6_port = htons(asoc->peer.port); memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen); } - err = sctp_verify_addr(sk, daddr, sizeof(*daddr)); - if (err) - goto free; - - old = sctp_endpoint_lookup_assoc(ep, daddr, &transport); - if (old && old != asoc) { - if (old->state >= SCTP_STATE_ESTABLISHED) - err = -EISCONN; - else - err = -EALREADY; - goto free; - } - - if (sctp_endpoint_is_peeled_off(ep, daddr)) { - err = -EADDRNOTAVAIL; - goto free; - } - transport = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, - SCTP_UNKNOWN); - if (!transport) { - err = -ENOMEM; + err = sctp_connect_add_peer(asoc, daddr, sizeof(*daddr)); + if (err) goto free; - } } return 0; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index e2f8e369cd08..7235a6032671 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -43,8 +43,8 @@ static struct sctp_transport *sctp_transport_init(struct net *net, gfp_t gfp) { /* Copy in the address. */ - peer->ipaddr = *addr; peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); + memcpy(&peer->ipaddr, addr, peer->af_specific->sockaddr_len); memset(&peer->saddr, 0, sizeof(union sctp_addr)); peer->sack_generation = 0; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 1336f3cdad38..6ef1abdd525f 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -185,7 +185,7 @@ static void tipc_bcbase_xmit(struct net *net, struct sk_buff_head *xmitq) } /* We have to transmit across all bearers */ - skb_queue_head_init(&_xmitq); + __skb_queue_head_init(&_xmitq); for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { if (!bb->dests[bearer_id]) continue; @@ -256,7 +256,7 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, struct sk_buff_head xmitq; int rc = 0; - skb_queue_head_init(&xmitq); + __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (tipc_link_bc_peers(l)) rc = tipc_link_xmit(l, pkts, &xmitq); @@ -286,7 +286,7 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, u32 dnode, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); - skb_queue_head_init(&_pkts); + __skb_queue_head_init(&_pkts); list_for_each_entry_safe(dst, tmp, &dests->list, list) { dnode = dst->node; @@ -344,7 +344,7 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); - skb_queue_head_init(&tmpq); + __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) tipc_bcast_xmit(net, &tmpq, cong_link_cnt); @@ -378,7 +378,7 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, int rc = 0; skb_queue_head_init(&inputq); - skb_queue_head_init(&localq); + __skb_queue_head_init(&localq); /* Clone packets before they are consumed by next call */ if (dests->local && !tipc_msg_reassemble(pkts, &localq)) { @@ -406,8 +406,10 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, rc = tipc_bcast_xmit(net, pkts, cong_link_cnt); } - if (dests->local) + if (dests->local) { + tipc_loopback_trace(net, &localq); tipc_sk_mcast_rcv(net, &localq, &inputq); + } exit: /* This queue should normally be empty by now */ __skb_queue_purge(pkts); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a809c0ec8d15..0214aa1c4427 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -389,6 +389,11 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev_put(dev); return -EINVAL; } + if (dev == net->loopback_dev) { + dev_put(dev); + pr_info("Enabling <%s> not permitted\n", b->name); + return -EINVAL; + } /* Autoconfigure own node identity if needed */ if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) { @@ -674,6 +679,65 @@ void tipc_bearer_stop(struct net *net) } } +void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts) +{ + struct net_device *dev = net->loopback_dev; + struct sk_buff *skb, *_skb; + int exp; + + skb_queue_walk(pkts, _skb) { + skb = pskb_copy(_skb, GFP_ATOMIC); + if (!skb) + continue; + + exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); + if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) { + kfree_skb(skb); + continue; + } + + skb_reset_network_header(skb); + dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr, + dev->dev_addr, skb->len); + skb->dev = dev; + skb->pkt_type = PACKET_HOST; + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->protocol = eth_type_trans(skb, dev); + netif_rx_ni(skb); + } +} + +static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *od) +{ + consume_skb(skb); + return NET_RX_SUCCESS; +} + +int tipc_attach_loopback(struct net *net) +{ + struct net_device *dev = net->loopback_dev; + struct tipc_net *tn = tipc_net(net); + + if (!dev) + return -ENODEV; + + dev_hold(dev); + tn->loopback_pt.dev = dev; + tn->loopback_pt.type = htons(ETH_P_TIPC); + tn->loopback_pt.func = tipc_loopback_rcv_pkt; + dev_add_pack(&tn->loopback_pt); + return 0; +} + +void tipc_detach_loopback(struct net *net) +{ + struct tipc_net *tn = tipc_net(net); + + dev_remove_pack(&tn->loopback_pt); + dev_put(net->loopback_dev); +} + /* Caller should hold rtnl_lock to protect the bearer */ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, struct tipc_bearer *bearer, int nlflags) diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 7f4c569594a5..ea0f3c49cbed 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -232,6 +232,16 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct tipc_media_addr *dst); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); +int tipc_attach_loopback(struct net *net); +void tipc_detach_loopback(struct net *net); + +static inline void tipc_loopback_trace(struct net *net, + struct sk_buff_head *pkts) +{ + if (unlikely(dev_nit_active(net->loopback_dev))) + tipc_clone_to_loopback(net, pkts); +} /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) diff --git a/net/tipc/core.c b/net/tipc/core.c index c8370722f0bb..23cb379a93d6 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -82,6 +82,10 @@ static int __net_init tipc_init_net(struct net *net) if (err) goto out_bclink; + err = tipc_attach_loopback(net); + if (err) + goto out_bclink; + return 0; out_bclink: @@ -94,6 +98,7 @@ out_sk_rht: static void __net_exit tipc_exit_net(struct net *net) { + tipc_detach_loopback(net); tipc_net_stop(net); tipc_bcast_stop(net); tipc_nametbl_stop(net); diff --git a/net/tipc/core.h b/net/tipc/core.h index 7a68e1b6a066..60d829581068 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -125,6 +125,9 @@ struct tipc_net { /* Cluster capabilities */ u16 capabilities; + + /* Tracing of node internal messages */ + struct packet_type loopback_pt; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/group.c b/net/tipc/group.c index 5f98d38bcf08..89257e2a980d 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -199,7 +199,7 @@ void tipc_group_join(struct net *net, struct tipc_group *grp, int *sk_rcvbuf) struct tipc_member *m, *tmp; struct sk_buff_head xmitq; - skb_queue_head_init(&xmitq); + __skb_queue_head_init(&xmitq); rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, &xmitq); tipc_group_update_member(m, 0); @@ -435,7 +435,7 @@ bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, return true; if (state == MBR_PENDING && adv == ADV_IDLE) return true; - skb_queue_head_init(&xmitq); + __skb_queue_head_init(&xmitq); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq); tipc_node_distr_xmit(grp->net, &xmitq); return true; diff --git a/net/tipc/link.c b/net/tipc/link.c index c2c5c53cad22..6cc75ffd9e2c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -176,6 +176,7 @@ struct tipc_link { /* Fragmentation/reassembly */ struct sk_buff *reasm_buf; + struct sk_buff *reasm_tnlmsg; /* Broadcast */ u16 ackers; @@ -849,18 +850,31 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) */ static void link_prepare_wakeup(struct tipc_link *l) { + struct sk_buff_head *wakeupq = &l->wakeupq; + struct sk_buff_head *inputq = l->inputq; struct sk_buff *skb, *tmp; - int imp, i = 0; + struct sk_buff_head tmpq; + int avail[5] = {0,}; + int imp = 0; + + __skb_queue_head_init(&tmpq); + + for (; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) + avail[imp] = l->backlog[imp].limit - l->backlog[imp].len; - skb_queue_walk_safe(&l->wakeupq, skb, tmp) { + skb_queue_walk_safe(wakeupq, skb, tmp) { imp = TIPC_SKB_CB(skb)->chain_imp; - if (l->backlog[imp].len < l->backlog[imp].limit) { - skb_unlink(skb, &l->wakeupq); - skb_queue_tail(l->inputq, skb); - } else if (i++ > 10) { - break; - } + if (avail[imp] <= 0) + continue; + avail[imp]--; + __skb_unlink(skb, wakeupq); + __skb_queue_tail(&tmpq, skb); } + + spin_lock_bh(&inputq->lock); + skb_queue_splice_tail(&tmpq, inputq); + spin_unlock_bh(&inputq->lock); + } void tipc_link_reset(struct tipc_link *l) @@ -893,8 +907,10 @@ void tipc_link_reset(struct tipc_link *l) l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0; l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0; kfree_skb(l->reasm_buf); + kfree_skb(l->reasm_tnlmsg); kfree_skb(l->failover_reasm_skb); l->reasm_buf = NULL; + l->reasm_tnlmsg = NULL; l->failover_reasm_skb = NULL; l->rcv_unacked = 0; l->snd_nxt = 1; @@ -936,7 +952,10 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, int rc = 0; if (unlikely(msg_size(hdr) > mtu)) { - skb_queue_purge(list); + pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n", + skb_queue_len(list), msg_user(hdr), + msg_type(hdr), msg_size(hdr), mtu); + __skb_queue_purge(list); return -EMSGSIZE; } @@ -965,7 +984,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (likely(skb_queue_len(transmq) < maxwin)) { _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) { - skb_queue_purge(list); + __skb_queue_purge(list); return -ENOBUFS; } __skb_dequeue(list); @@ -1238,6 +1257,7 @@ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { struct sk_buff **reasm_skb = &l->failover_reasm_skb; + struct sk_buff **reasm_tnlmsg = &l->reasm_tnlmsg; struct sk_buff_head *fdefq = &l->failover_deferdq; struct tipc_msg *hdr = buf_msg(skb); struct sk_buff *iskb; @@ -1245,40 +1265,56 @@ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, int rc = 0; u16 seqno; - /* SYNCH_MSG */ - if (msg_type(hdr) == SYNCH_MSG) - goto drop; + if (msg_type(hdr) == SYNCH_MSG) { + kfree_skb(skb); + return 0; + } - /* FAILOVER_MSG */ - if (!tipc_msg_extract(skb, &iskb, &ipos)) { - pr_warn_ratelimited("Cannot extract FAILOVER_MSG, defq: %d\n", - skb_queue_len(fdefq)); - return rc; + /* Not a fragment? */ + if (likely(!msg_nof_fragms(hdr))) { + if (unlikely(!tipc_msg_extract(skb, &iskb, &ipos))) { + pr_warn_ratelimited("Unable to extract msg, defq: %d\n", + skb_queue_len(fdefq)); + return 0; + } + kfree_skb(skb); + } else { + /* Set fragment type for buf_append */ + if (msg_fragm_no(hdr) == 1) + msg_set_type(hdr, FIRST_FRAGMENT); + else if (msg_fragm_no(hdr) < msg_nof_fragms(hdr)) + msg_set_type(hdr, FRAGMENT); + else + msg_set_type(hdr, LAST_FRAGMENT); + + if (!tipc_buf_append(reasm_tnlmsg, &skb)) { + /* Successful but non-complete reassembly? */ + if (*reasm_tnlmsg || link_is_bc_rcvlink(l)) + return 0; + pr_warn_ratelimited("Unable to reassemble tunnel msg\n"); + return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); + } + iskb = skb; } do { seqno = buf_seqno(iskb); - if (unlikely(less(seqno, l->drop_point))) { kfree_skb(iskb); continue; } - if (unlikely(seqno != l->drop_point)) { __tipc_skb_queue_sorted(fdefq, seqno, iskb); continue; } l->drop_point++; - if (!tipc_data_input(l, iskb, inputq)) rc |= tipc_link_input(l, iskb, inputq, reasm_skb); if (unlikely(rc)) break; } while ((iskb = __tipc_skb_dequeue(fdefq, l->drop_point))); -drop: - kfree_skb(skb); return rc; } @@ -1644,7 +1680,7 @@ void tipc_link_create_dummy_tnl_msg(struct tipc_link *l, struct sk_buff *skb; u32 dnode = l->addr; - skb_queue_head_init(&tnlq); + __skb_queue_head_init(&tnlq); skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG, INT_H_SIZE, BASIC_H_SIZE, dnode, onode, 0, 0, 0); @@ -1675,14 +1711,18 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, struct sk_buff *skb, *tnlskb; struct tipc_msg *hdr, tnlhdr; struct sk_buff_head *queue = &l->transmq; - struct sk_buff_head tmpxq, tnlq; + struct sk_buff_head tmpxq, tnlq, frags; u16 pktlen, pktcnt, seqno = l->snd_nxt; + bool pktcnt_need_update = false; + u16 syncpt; + int rc; if (!tnl) return; - skb_queue_head_init(&tnlq); - skb_queue_head_init(&tmpxq); + __skb_queue_head_init(&tnlq); + __skb_queue_head_init(&tmpxq); + __skb_queue_head_init(&frags); /* At least one packet required for safe algorithm => add dummy */ skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, @@ -1692,10 +1732,35 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, pr_warn("%sunable to create tunnel packet\n", link_co_err); return; } - skb_queue_tail(&tnlq, skb); + __skb_queue_tail(&tnlq, skb); tipc_link_xmit(l, &tnlq, &tmpxq); __skb_queue_purge(&tmpxq); + /* Link Synching: + * From now on, send only one single ("dummy") SYNCH message + * to peer. The SYNCH message does not contain any data, just + * a header conveying the synch point to the peer. + */ + if (mtyp == SYNCH_MSG && (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { + tnlskb = tipc_msg_create(TUNNEL_PROTOCOL, SYNCH_MSG, + INT_H_SIZE, 0, l->addr, + tipc_own_addr(l->net), + 0, 0, 0); + if (!tnlskb) { + pr_warn("%sunable to create dummy SYNCH_MSG\n", + link_co_err); + return; + } + + hdr = buf_msg(tnlskb); + syncpt = l->snd_nxt + skb_queue_len(&l->backlogq) - 1; + msg_set_syncpt(hdr, syncpt); + msg_set_bearer_id(hdr, l->peer_bearer_id); + __skb_queue_tail(&tnlq, tnlskb); + tipc_link_xmit(tnl, &tnlq, xmitq); + return; + } + /* Initialize reusable tunnel packet header */ tipc_msg_init(tipc_own_addr(l->net), &tnlhdr, TUNNEL_PROTOCOL, mtyp, INT_H_SIZE, l->addr); @@ -1713,6 +1778,39 @@ tnl: if (queue == &l->backlogq) msg_set_seqno(hdr, seqno++); pktlen = msg_size(hdr); + + /* Tunnel link MTU is not large enough? This could be + * due to: + * 1) Link MTU has just changed or set differently; + * 2) Or FAILOVER on the top of a SYNCH message + * + * The 2nd case should not happen if peer supports + * TIPC_TUNNEL_ENHANCED + */ + if (pktlen > tnl->mtu - INT_H_SIZE) { + if (mtyp == FAILOVER_MSG && + (tnl->peer_caps & TIPC_TUNNEL_ENHANCED)) { + rc = tipc_msg_fragment(skb, &tnlhdr, tnl->mtu, + &frags); + if (rc) { + pr_warn("%sunable to frag msg: rc %d\n", + link_co_err, rc); + return; + } + pktcnt += skb_queue_len(&frags) - 1; + pktcnt_need_update = true; + skb_queue_splice_tail_init(&frags, &tnlq); + continue; + } + /* Unluckily, peer doesn't have TIPC_TUNNEL_ENHANCED + * => Just warn it and return! + */ + pr_warn_ratelimited("%stoo large msg <%d, %d>: %d!\n", + link_co_err, msg_user(hdr), + msg_type(hdr), msg_size(hdr)); + return; + } + msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE, GFP_ATOMIC); if (!tnlskb) { @@ -1728,6 +1826,12 @@ tnl: goto tnl; } + if (pktcnt_need_update) + skb_queue_walk(&tnlq, skb) { + hdr = buf_msg(skb); + msg_set_msgcnt(hdr, pktcnt); + } + tipc_link_xmit(tnl, &tnlq, xmitq); if (mtyp == FAILOVER_MSG) { diff --git a/net/tipc/msg.c b/net/tipc/msg.c index f48e5857210f..e6d49cdc61b4 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -244,6 +244,65 @@ bool tipc_msg_validate(struct sk_buff **_skb) } /** + * tipc_msg_fragment - build a fragment skb list for TIPC message + * + * @skb: TIPC message skb + * @hdr: internal msg header to be put on the top of the fragments + * @pktmax: max size of a fragment incl. the header + * @frags: returned fragment skb list + * + * Returns 0 if the fragmentation is successful, otherwise: -EINVAL + * or -ENOMEM + */ +int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, + int pktmax, struct sk_buff_head *frags) +{ + int pktno, nof_fragms, dsz, dmax, eat; + struct tipc_msg *_hdr; + struct sk_buff *_skb; + u8 *data; + + /* Non-linear buffer? */ + if (skb_linearize(skb)) + return -ENOMEM; + + data = (u8 *)skb->data; + dsz = msg_size(buf_msg(skb)); + dmax = pktmax - INT_H_SIZE; + if (dsz <= dmax || !dmax) + return -EINVAL; + + nof_fragms = dsz / dmax + 1; + for (pktno = 1; pktno <= nof_fragms; pktno++) { + if (pktno < nof_fragms) + eat = dmax; + else + eat = dsz % dmax; + /* Allocate a new fragment */ + _skb = tipc_buf_acquire(INT_H_SIZE + eat, GFP_ATOMIC); + if (!_skb) + goto error; + skb_orphan(_skb); + __skb_queue_tail(frags, _skb); + /* Copy header & data to the fragment */ + skb_copy_to_linear_data(_skb, hdr, INT_H_SIZE); + skb_copy_to_linear_data_offset(_skb, INT_H_SIZE, data, eat); + data += eat; + /* Update the fragment's header */ + _hdr = buf_msg(_skb); + msg_set_fragm_no(_hdr, pktno); + msg_set_nof_fragms(_hdr, nof_fragms); + msg_set_size(_hdr, INT_H_SIZE + eat); + } + return 0; + +error: + __skb_queue_purge(frags); + __skb_queue_head_init(frags); + return -ENOMEM; +} + +/** * tipc_msg_build - create buffer chain containing specified header and data * @mhdr: Message header, to be prepended to data * @m: User message diff --git a/net/tipc/msg.h b/net/tipc/msg.h index d7ebc9e955f6..0daa6f04ca81 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -723,12 +723,26 @@ static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n) msg_set_bits(m, 4, 16, 0xffff, n); } +static inline u32 msg_nof_fragms(struct tipc_msg *m) +{ + return msg_bits(m, 4, 0, 0xffff); +} + +static inline void msg_set_nof_fragms(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 4, 0, 0xffff, n); +} + +static inline u32 msg_fragm_no(struct tipc_msg *m) +{ + return msg_bits(m, 4, 16, 0xffff); +} + static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 16, 0xffff, n); } - static inline u16 msg_next_sent(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); @@ -879,6 +893,16 @@ static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n) msg_set_bits(m, 9, 16, 0xffff, n); } +static inline u16 msg_syncpt(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_syncpt(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + static inline u32 msg_conn_ack(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); @@ -1037,6 +1061,8 @@ bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu); bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, u32 mtu, u32 dnode); bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); +int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, + int pktmax, struct sk_buff_head *frags); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 44abc8e9c990..61219f0b9677 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -190,7 +190,7 @@ void tipc_named_node_up(struct net *net, u32 dnode) struct name_table *nt = tipc_name_table(net); struct sk_buff_head head; - skb_queue_head_init(&head); + __skb_queue_head_init(&head); read_lock_bh(&nt->cluster_scope_lock); named_distribute(net, &head, dnode, &nt->cluster_scope); diff --git a/net/tipc/node.c b/net/tipc/node.c index 3a5be1d7e572..c8f6177dd5a2 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1443,13 +1443,15 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, int rc; if (in_own_node(net, dnode)) { + tipc_loopback_trace(net, list); + spin_lock_init(&list->lock); tipc_sk_rcv(net, list); return 0; } n = tipc_node_find(net, dnode); if (unlikely(!n)) { - skb_queue_purge(list); + __skb_queue_purge(list); return -EHOSTUNREACH; } @@ -1458,7 +1460,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, if (unlikely(bearer_id == INVALID_BEARER_ID)) { tipc_node_read_unlock(n); tipc_node_put(n); - skb_queue_purge(list); + __skb_queue_purge(list); return -EHOSTUNREACH; } @@ -1490,7 +1492,7 @@ int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, { struct sk_buff_head head; - skb_queue_head_init(&head); + __skb_queue_head_init(&head); __skb_queue_tail(&head, skb); tipc_node_xmit(net, &head, dnode, selector); return 0; @@ -1649,7 +1651,6 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, int usr = msg_user(hdr); int mtyp = msg_type(hdr); u16 oseqno = msg_seqno(hdr); - u16 iseqno = msg_seqno(msg_inner_hdr(hdr)); u16 exp_pkts = msg_msgcnt(hdr); u16 rcv_nxt, syncpt, dlv_nxt, inputq_len; int state = n->state; @@ -1748,7 +1749,10 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, /* Initiate synch mode if applicable */ if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { - syncpt = iseqno + exp_pkts - 1; + if (n->capabilities & TIPC_TUNNEL_ENHANCED) + syncpt = msg_syncpt(hdr); + else + syncpt = msg_seqno(msg_inner_hdr(hdr)) + exp_pkts - 1; if (!tipc_link_is_up(l)) __tipc_node_link_up(n, bearer_id, xmitq); if (n->state == SELF_UP_PEER_UP) { diff --git a/net/tipc/node.h b/net/tipc/node.h index c0bf49ea3de4..291d0ecd4101 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -53,7 +53,8 @@ enum { TIPC_NODE_ID128 = (1 << 5), TIPC_LINK_PROTO_SEQNO = (1 << 6), TIPC_MCAST_RBCTL = (1 << 7), - TIPC_GAP_ACK_BLOCK = (1 << 8) + TIPC_GAP_ACK_BLOCK = (1 << 8), + TIPC_TUNNEL_ENHANCED = (1 << 9) }; #define TIPC_NODE_CAPABILITIES (TIPC_SYN_BIT | \ @@ -64,7 +65,8 @@ enum { TIPC_NODE_ID128 | \ TIPC_LINK_PROTO_SEQNO | \ TIPC_MCAST_RBCTL | \ - TIPC_GAP_ACK_BLOCK) + TIPC_GAP_ACK_BLOCK | \ + TIPC_TUNNEL_ENHANCED) #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 83ae41d7e554..3b9f8cc328f5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -809,7 +809,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, msg_set_nameupper(hdr, seq->upper); /* Build message as chain of buffers */ - skb_queue_head_init(&pkts); + __skb_queue_head_init(&pkts); rc = tipc_msg_build(hdr, msg, 0, dlen, mtu, &pkts); /* Send message if build was successful */ @@ -853,7 +853,7 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, msg_set_grp_bc_seqno(hdr, bc_snd_nxt); /* Build message as chain of buffers */ - skb_queue_head_init(&pkts); + __skb_queue_head_init(&pkts); mtu = tipc_node_get_mtu(net, dnode, tsk->portid); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); if (unlikely(rc != dlen)) @@ -1058,7 +1058,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, msg_set_grp_bc_ack_req(hdr, ack); /* Build message as chain of buffers */ - skb_queue_head_init(&pkts); + __skb_queue_head_init(&pkts); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); if (unlikely(rc != dlen)) return rc; @@ -1387,7 +1387,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(rc)) return rc; - skb_queue_head_init(&pkts); + __skb_queue_head_init(&pkts); mtu = tipc_node_get_mtu(net, dnode, tsk->portid); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); if (unlikely(rc != dlen)) @@ -1445,7 +1445,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) int send, sent = 0; int rc = 0; - skb_queue_head_init(&pkts); + __skb_queue_head_init(&pkts); if (unlikely(dlen > INT_MAX)) return -EMSGSIZE; @@ -1805,7 +1805,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, /* Send group flow control advertisement when applicable */ if (tsk->group && msg_in_group(hdr) && !grp_evt) { - skb_queue_head_init(&xmitq); + __skb_queue_head_init(&xmitq); tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen), msg_orignode(hdr), msg_origport(hdr), &xmitq); @@ -2674,7 +2674,7 @@ static void tipc_sk_timeout(struct timer_list *t) struct sk_buff_head list; int rc = 0; - skb_queue_head_init(&list); + __skb_queue_head_init(&list); bh_lock_sock(sk); /* Try again later if socket is busy */ diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index ca8ac96d22a9..3a12fc18239b 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -40,6 +40,7 @@ #include "socket.h" #include "addr.h" #include "msg.h" +#include "bearer.h" #include <net/sock.h> #include <linux/module.h> @@ -608,6 +609,7 @@ static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt) memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); skb_queue_head_init(&evtq); __skb_queue_tail(&evtq, skb); + tipc_loopback_trace(net, &evtq); tipc_sk_rcv(net, &evtq); } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 43922d86e510..a470df7ffcf9 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -243,14 +243,14 @@ static void tls_append_frag(struct tls_record_info *record, skb_frag_t *frag; frag = &record->frags[record->num_frags - 1]; - if (frag->page.p == pfrag->page && - frag->page_offset + frag->size == pfrag->offset) { - frag->size += size; + if (skb_frag_page(frag) == pfrag->page && + skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) { + skb_frag_size_add(frag, size); } else { ++frag; - frag->page.p = pfrag->page; - frag->page_offset = pfrag->offset; - frag->size = size; + __skb_frag_set_page(frag, pfrag->page); + skb_frag_off_set(frag, pfrag->offset); + skb_frag_size_set(frag, size); ++record->num_frags; get_page(pfrag->page); } @@ -301,8 +301,8 @@ static int tls_push_record(struct sock *sk, frag = &record->frags[i]; sg_unmark_end(&offload_ctx->sg_tx_data[i]); sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), - frag->size, frag->page_offset); - sk_mem_charge(sk, frag->size); + skb_frag_size(frag), skb_frag_off(frag)); + sk_mem_charge(sk, skb_frag_size(frag)); get_page(skb_frag_page(frag)); } sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]); @@ -324,7 +324,7 @@ static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, frag = &record->frags[0]; __skb_frag_set_page(frag, pfrag->page); - frag->page_offset = pfrag->offset; + skb_frag_off_set(frag, pfrag->offset); skb_frag_size_set(frag, prepend_size); get_page(pfrag->page); diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 9070d68a92a4..28895333701e 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -273,7 +273,7 @@ static int fill_sg_in(struct scatterlist *sg_in, __skb_frag_ref(frag); sg_set_page(sg_in + i, skb_frag_page(frag), - skb_frag_size(frag), frag->page_offset); + skb_frag_size(frag), skb_frag_off(frag)); remaining -= skb_frag_size(frag); diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 9d864ebeb7b3..261521d286d6 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -77,11 +77,11 @@ struct hvs_send_buf { VMBUS_PKT_TRAILER_SIZE) union hvs_service_id { - uuid_le srv_id; + guid_t srv_id; struct { unsigned int svm_port; - unsigned char b[sizeof(uuid_le) - sizeof(unsigned int)]; + unsigned char b[sizeof(guid_t) - sizeof(unsigned int)]; }; }; @@ -89,8 +89,8 @@ union hvs_service_id { struct hvsock { struct vsock_sock *vsk; - uuid_le vm_srv_id; - uuid_le host_srv_id; + guid_t vm_srv_id; + guid_t host_srv_id; struct vmbus_channel *chan; struct vmpacket_descriptor *recv_desc; @@ -159,21 +159,21 @@ struct hvsock { #define MIN_HOST_EPHEMERAL_PORT (MAX_HOST_LISTEN_PORT + 1) /* 00000000-facb-11e6-bd58-64006a7986d3 */ -static const uuid_le srv_id_template = - UUID_LE(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58, - 0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3); +static const guid_t srv_id_template = + GUID_INIT(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58, + 0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3); -static bool is_valid_srv_id(const uuid_le *id) +static bool is_valid_srv_id(const guid_t *id) { - return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(uuid_le) - 4); + return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(guid_t) - 4); } -static unsigned int get_port_by_srv_id(const uuid_le *svr_id) +static unsigned int get_port_by_srv_id(const guid_t *svr_id) { return *((unsigned int *)svr_id); } -static void hvs_addr_init(struct sockaddr_vm *addr, const uuid_le *svr_id) +static void hvs_addr_init(struct sockaddr_vm *addr, const guid_t *svr_id) { unsigned int port = get_port_by_srv_id(svr_id); @@ -321,7 +321,7 @@ static void hvs_close_connection(struct vmbus_channel *chan) static void hvs_open_connection(struct vmbus_channel *chan) { - uuid_le *if_instance, *if_type; + guid_t *if_instance, *if_type; unsigned char conn_from_host; struct sockaddr_vm addr; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 0815d1357861..082a30936690 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -307,6 +307,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) break; } + pkt->buf_len = buf_len; pkt->len = buf_len; sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6f1a8aff65c5..94cc0fa3e848 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,9 @@ /* How long to wait for graceful shutdown of a connection */ #define VSOCK_CLOSE_TIMEOUT (8 * HZ) +/* Threshold for detecting small packets to copy */ +#define GOOD_COPY_LEN 128 + static const struct virtio_transport *virtio_transport_get_ops(void) { const struct vsock_transport *t = vsock_core_get_transport(); @@ -64,6 +67,9 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, pkt->buf = kmalloc(len, GFP_KERNEL); if (!pkt->buf) goto out_pkt; + + pkt->buf_len = len; + err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; @@ -91,8 +97,17 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct virtio_vsock_pkt *pkt = opaque; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; + size_t payload_len; + void *payload_buf; + + /* A packet could be split to fit the RX buffer, so we can retrieve + * the payload length from the header and the buffer pointer taking + * care of the offset in the original packet. + */ + payload_len = le32_to_cpu(pkt->hdr.len); + payload_buf = pkt->buf + pkt->off; - skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len, + skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len, GFP_ATOMIC); if (!skb) return NULL; @@ -132,8 +147,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr)); - if (pkt->len) { - skb_put_data(skb, pkt->buf, pkt->len); + if (payload_len) { + skb_put_data(skb, payload_buf, payload_len); } return skb; @@ -166,8 +181,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, vvs = vsk->trans; /* we can send less than pkt_len bytes */ - if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE) - pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + if (pkt_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + pkt_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE; /* virtio_transport_get_credit might return less than pkt_len credit */ pkt_len = virtio_transport_get_credit(vvs, pkt_len); @@ -204,10 +219,11 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { - spin_lock_bh(&vvs->tx_lock); + spin_lock_bh(&vvs->rx_lock); + vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); - spin_unlock_bh(&vvs->tx_lock); + spin_unlock_bh(&vvs->rx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); @@ -255,6 +271,7 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_sock *vvs = vsk->trans; struct virtio_vsock_pkt *pkt; size_t bytes, total = 0; + u32 free_space; int err = -EFAULT; spin_lock_bh(&vvs->rx_lock); @@ -285,11 +302,19 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, virtio_transport_free_pkt(pkt); } } + + free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt); + spin_unlock_bh(&vvs->rx_lock); - /* Send a credit pkt to peer */ - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + /* We send a credit update only when the space available seen + * by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + */ + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { + virtio_transport_send_credit_update(vsk, + VIRTIO_VSOCK_TYPE_STREAM, + NULL); + } return total; @@ -841,24 +866,60 @@ destroy: return err; } +static void +virtio_transport_recv_enqueue(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + bool free_pkt = false; + + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + + virtio_transport_inc_rx_pkt(vvs, pkt); + + /* Try to copy small packets into the buffer of last packet queued, + * to avoid wasting memory queueing the entire buffer with a small + * payload. + */ + if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) { + struct virtio_vsock_pkt *last_pkt; + + last_pkt = list_last_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + /* If there is space in the last packet queued, we copy the + * new packet in its buffer. + */ + if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + memcpy(last_pkt->buf + last_pkt->len, pkt->buf, + pkt->len); + last_pkt->len += pkt->len; + free_pkt = true; + goto out; + } + } + + list_add_tail(&pkt->list, &vvs->rx_queue); + +out: + spin_unlock_bh(&vvs->rx_lock); + if (free_pkt) + virtio_transport_free_pkt(pkt); +} + static int virtio_transport_recv_connected(struct sock *sk, struct virtio_vsock_pkt *pkt) { struct vsock_sock *vsk = vsock_sk(sk); - struct virtio_vsock_sock *vvs = vsk->trans; int err = 0; switch (le16_to_cpu(pkt->hdr.op)) { case VIRTIO_VSOCK_OP_RW: - pkt->len = le32_to_cpu(pkt->hdr.len); - pkt->off = 0; - - spin_lock_bh(&vvs->rx_lock); - virtio_transport_inc_rx_pkt(vvs, pkt); - list_add_tail(&pkt->list, &vvs->rx_queue); - spin_unlock_bh(&vvs->rx_lock); - + virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c index 1af56df30276..3c54bb6b925a 100644 --- a/net/wimax/debugfs.c +++ b/net/wimax/debugfs.c @@ -13,49 +13,23 @@ #define D_SUBMODULE debugfs #include "debug-levels.h" - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - -int wimax_debugfs_add(struct wimax_dev *wimax_dev) +void wimax_debugfs_add(struct wimax_dev *wimax_dev) { - int result; struct net_device *net_dev = wimax_dev->net_dev; - struct device *dev = net_dev->dev.parent; struct dentry *dentry; char buf[128]; snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name); dentry = debugfs_create_dir(buf, NULL); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - else - dev_err(dev, "Can't create debugfs dentry: %d\n", - result); - goto out; - } wimax_dev->debugfs_dentry = dentry; - __debugfs_register("wimax_dl_", debugfs, dentry); - __debugfs_register("wimax_dl_", id_table, dentry); - __debugfs_register("wimax_dl_", op_msg, dentry); - __debugfs_register("wimax_dl_", op_reset, dentry); - __debugfs_register("wimax_dl_", op_rfkill, dentry); - __debugfs_register("wimax_dl_", op_state_get, dentry); - __debugfs_register("wimax_dl_", stack, dentry); - result = 0; -out: - return result; -error: - debugfs_remove_recursive(wimax_dev->debugfs_dentry); - return result; + 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) diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 1ba99d65feca..4b9b1c5e8f3a 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -481,12 +481,7 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) /* Set up user-space interaction */ mutex_lock(&wimax_dev->mutex); wimax_id_table_add(wimax_dev); - result = wimax_debugfs_add(wimax_dev); - if (result < 0) { - dev_err(dev, "cannot initialize debugfs: %d\n", - result); - goto error_debugfs_add; - } + wimax_debugfs_add(wimax_dev); __wimax_state_set(wimax_dev, WIMAX_ST_DOWN); mutex_unlock(&wimax_dev->mutex); @@ -498,10 +493,6 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev); return 0; -error_debugfs_add: - wimax_id_table_rm(wimax_dev); - mutex_unlock(&wimax_dev->mutex); - wimax_rfkill_rm(wimax_dev); error_rfkill_add: d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n", wimax_dev, net_dev, result); diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h index e819a09337ee..40751207296c 100644 --- a/net/wimax/wimax-internal.h +++ b/net/wimax/wimax-internal.h @@ -57,13 +57,10 @@ void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state) void __wimax_state_change(struct wimax_dev *, enum wimax_st); #ifdef CONFIG_DEBUG_FS -int wimax_debugfs_add(struct wimax_dev *); +void wimax_debugfs_add(struct wimax_dev *); void wimax_debugfs_rm(struct wimax_dev *); #else -static inline int wimax_debugfs_add(struct wimax_dev *wimax_dev) -{ - return 0; -} +static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {} static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {} #endif diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 67f8360dfcee..63cf7131f601 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -217,6 +217,8 @@ config LIB80211_CRYPT_WEP config LIB80211_CRYPT_CCMP tristate + select CRYPTO_AES + select CRYPTO_CCM config LIB80211_CRYPT_TKIP tristate diff --git a/net/wireless/core.c b/net/wireless/core.c index 32b3c719fdfc..a599469b8157 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -142,12 +142,10 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev, if (result) return result; - if (rdev->wiphy.debugfsdir && - !debugfs_rename(rdev->wiphy.debugfsdir->d_parent, - rdev->wiphy.debugfsdir, - rdev->wiphy.debugfsdir->d_parent, - newname)) - pr_err("failed to rename debugfs dir to %s!\n", newname); + if (rdev->wiphy.debugfsdir) + debugfs_rename(rdev->wiphy.debugfsdir->d_parent, + rdev->wiphy.debugfsdir, + rdev->wiphy.debugfsdir->d_parent, newname); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); @@ -899,11 +897,8 @@ int wiphy_register(struct wiphy *wiphy) cfg80211_rdev_list_generation++; /* add to debugfs */ - rdev->wiphy.debugfsdir = - debugfs_create_dir(wiphy_name(&rdev->wiphy), - ieee80211_debugfs_dir); - if (IS_ERR(rdev->wiphy.debugfsdir)) - rdev->wiphy.debugfsdir = NULL; + rdev->wiphy.debugfsdir = debugfs_create_dir(wiphy_name(&rdev->wiphy), + ieee80211_debugfs_dir); cfg80211_debugfs_rdev_add(rdev); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); diff --git a/net/wireless/core.h b/net/wireless/core.h index ee8388fe4a92..77556c58d9ac 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -306,6 +306,8 @@ void ieee80211_set_bitrate_flags(struct wiphy *wiphy); void cfg80211_bss_expire(struct cfg80211_registered_device *rdev); void cfg80211_bss_age(struct cfg80211_registered_device *rdev, unsigned long age_secs); +void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev, + struct ieee80211_channel *channel); /* IBSS */ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c index 7e8ff9d7dcfa..6a5f08f7491e 100644 --- a/net/wireless/lib80211_crypt_ccmp.c +++ b/net/wireless/lib80211_crypt_ccmp.c @@ -22,6 +22,7 @@ #include <linux/ieee80211.h> #include <linux/crypto.h> +#include <crypto/aead.h> #include <net/lib80211.h> @@ -48,20 +49,13 @@ struct lib80211_ccmp_data { int key_idx; - struct crypto_cipher *tfm; + struct crypto_aead *tfm; /* scratch buffers for virt_to_page() (crypto API) */ - u8 tx_b0[AES_BLOCK_LEN], tx_b[AES_BLOCK_LEN], - tx_e[AES_BLOCK_LEN], tx_s0[AES_BLOCK_LEN]; - u8 rx_b0[AES_BLOCK_LEN], rx_b[AES_BLOCK_LEN], rx_a[AES_BLOCK_LEN]; + u8 tx_aad[2 * AES_BLOCK_LEN]; + u8 rx_aad[2 * AES_BLOCK_LEN]; }; -static inline void lib80211_ccmp_aes_encrypt(struct crypto_cipher *tfm, - const u8 pt[16], u8 ct[16]) -{ - crypto_cipher_encrypt_one(tfm, ct, pt); -} - static void *lib80211_ccmp_init(int key_idx) { struct lib80211_ccmp_data *priv; @@ -71,7 +65,7 @@ static void *lib80211_ccmp_init(int key_idx) goto fail; priv->key_idx = key_idx; - priv->tfm = crypto_alloc_cipher("aes", 0, 0); + priv->tfm = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(priv->tfm)) { priv->tfm = NULL; goto fail; @@ -82,7 +76,7 @@ static void *lib80211_ccmp_init(int key_idx) fail: if (priv) { if (priv->tfm) - crypto_free_cipher(priv->tfm); + crypto_free_aead(priv->tfm); kfree(priv); } @@ -93,25 +87,16 @@ static void lib80211_ccmp_deinit(void *priv) { struct lib80211_ccmp_data *_priv = priv; if (_priv && _priv->tfm) - crypto_free_cipher(_priv->tfm); + crypto_free_aead(_priv->tfm); kfree(priv); } -static inline void xor_block(u8 * b, u8 * a, size_t len) -{ - int i; - for (i = 0; i < len; i++) - b[i] ^= a[i]; -} - -static void ccmp_init_blocks(struct crypto_cipher *tfm, - struct ieee80211_hdr *hdr, - u8 * pn, size_t dlen, u8 * b0, u8 * auth, u8 * s0) +static int ccmp_init_iv_and_aad(const struct ieee80211_hdr *hdr, + const u8 *pn, u8 *iv, u8 *aad) { u8 *pos, qc = 0; size_t aad_len; int a4_included, qc_included; - u8 aad[2 * AES_BLOCK_LEN]; a4_included = ieee80211_has_a4(hdr->frame_control); qc_included = ieee80211_is_data_qos(hdr->frame_control); @@ -127,17 +112,19 @@ static void ccmp_init_blocks(struct crypto_cipher *tfm, aad_len += 2; } - /* CCM Initial Block: - * Flag (Include authentication header, M=3 (8-octet MIC), - * L=1 (2-octet Dlen)) - * Nonce: 0x00 | A2 | PN - * Dlen */ - b0[0] = 0x59; - b0[1] = qc; - memcpy(b0 + 2, hdr->addr2, ETH_ALEN); - memcpy(b0 + 8, pn, CCMP_PN_LEN); - b0[14] = (dlen >> 8) & 0xff; - b0[15] = dlen & 0xff; + /* In CCM, the initial vectors (IV) used for CTR mode encryption and CBC + * mode authentication are not allowed to collide, yet both are derived + * from the same vector. We only set L := 1 here to indicate that the + * data size can be represented in (L+1) bytes. The CCM layer will take + * care of storing the data length in the top (L+1) bytes and setting + * and clearing the other bits as is required to derive the two IVs. + */ + iv[0] = 0x1; + + /* Nonce: QC | A2 | PN */ + iv[1] = qc; + memcpy(iv + 2, hdr->addr2, ETH_ALEN); + memcpy(iv + 8, pn, CCMP_PN_LEN); /* AAD: * FC with bits 4..6 and 11..13 masked to zero; 14 is always one @@ -147,31 +134,20 @@ static void ccmp_init_blocks(struct crypto_cipher *tfm, * QC (if present) */ pos = (u8 *) hdr; - aad[0] = 0; /* aad_len >> 8 */ - aad[1] = aad_len & 0xff; - aad[2] = pos[0] & 0x8f; - aad[3] = pos[1] & 0xc7; - memcpy(aad + 4, hdr->addr1, 3 * ETH_ALEN); + aad[0] = pos[0] & 0x8f; + aad[1] = pos[1] & 0xc7; + memcpy(aad + 2, hdr->addr1, 3 * ETH_ALEN); pos = (u8 *) & hdr->seq_ctrl; - aad[22] = pos[0] & 0x0f; - aad[23] = 0; /* all bits masked */ - memset(aad + 24, 0, 8); + aad[20] = pos[0] & 0x0f; + aad[21] = 0; /* all bits masked */ + memset(aad + 22, 0, 8); if (a4_included) - memcpy(aad + 24, hdr->addr4, ETH_ALEN); + memcpy(aad + 22, hdr->addr4, ETH_ALEN); if (qc_included) { - aad[a4_included ? 30 : 24] = qc; + aad[a4_included ? 28 : 22] = qc; /* rest of QC masked */ } - - /* Start with the first block and AAD */ - lib80211_ccmp_aes_encrypt(tfm, b0, auth); - xor_block(auth, aad, AES_BLOCK_LEN); - lib80211_ccmp_aes_encrypt(tfm, auth, auth); - xor_block(auth, &aad[AES_BLOCK_LEN], AES_BLOCK_LEN); - lib80211_ccmp_aes_encrypt(tfm, auth, auth); - b0[0] &= 0x07; - b0[14] = b0[15] = 0; - lib80211_ccmp_aes_encrypt(tfm, b0, s0); + return aad_len; } static int lib80211_ccmp_hdr(struct sk_buff *skb, int hdr_len, @@ -214,13 +190,13 @@ static int lib80211_ccmp_hdr(struct sk_buff *skb, int hdr_len, static int lib80211_ccmp_encrypt(struct sk_buff *skb, int hdr_len, void *priv) { struct lib80211_ccmp_data *key = priv; - int data_len, i, blocks, last, len; - u8 *pos, *mic; struct ieee80211_hdr *hdr; - u8 *b0 = key->tx_b0; - u8 *b = key->tx_b; - u8 *e = key->tx_e; - u8 *s0 = key->tx_s0; + struct aead_request *req; + struct scatterlist sg[2]; + u8 *aad = key->tx_aad; + u8 iv[AES_BLOCK_LEN]; + int len, data_len, aad_len; + int ret; if (skb_tailroom(skb) < CCMP_MIC_LEN || skb->len < hdr_len) return -1; @@ -230,31 +206,28 @@ static int lib80211_ccmp_encrypt(struct sk_buff *skb, int hdr_len, void *priv) if (len < 0) return -1; - pos = skb->data + hdr_len + CCMP_HDR_LEN; + req = aead_request_alloc(key->tfm, GFP_ATOMIC); + if (!req) + return -ENOMEM; + hdr = (struct ieee80211_hdr *)skb->data; - ccmp_init_blocks(key->tfm, hdr, key->tx_pn, data_len, b0, b, s0); - - blocks = DIV_ROUND_UP(data_len, AES_BLOCK_LEN); - last = data_len % AES_BLOCK_LEN; - - for (i = 1; i <= blocks; i++) { - len = (i == blocks && last) ? last : AES_BLOCK_LEN; - /* Authentication */ - xor_block(b, pos, len); - lib80211_ccmp_aes_encrypt(key->tfm, b, b); - /* Encryption, with counter */ - b0[14] = (i >> 8) & 0xff; - b0[15] = i & 0xff; - lib80211_ccmp_aes_encrypt(key->tfm, b0, e); - xor_block(pos, e, len); - pos += len; - } + aad_len = ccmp_init_iv_and_aad(hdr, key->tx_pn, iv, aad); - mic = skb_put(skb, CCMP_MIC_LEN); - for (i = 0; i < CCMP_MIC_LEN; i++) - mic[i] = b[i] ^ s0[i]; + skb_put(skb, CCMP_MIC_LEN); - return 0; + sg_init_table(sg, 2); + sg_set_buf(&sg[0], aad, aad_len); + sg_set_buf(&sg[1], skb->data + hdr_len + CCMP_HDR_LEN, + data_len + CCMP_MIC_LEN); + + aead_request_set_callback(req, 0, NULL, NULL); + aead_request_set_ad(req, aad_len); + aead_request_set_crypt(req, sg, sg, data_len, iv); + + ret = crypto_aead_encrypt(req); + aead_request_free(req); + + return ret; } /* @@ -283,13 +256,13 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) struct lib80211_ccmp_data *key = priv; u8 keyidx, *pos; struct ieee80211_hdr *hdr; - u8 *b0 = key->rx_b0; - u8 *b = key->rx_b; - u8 *a = key->rx_a; + struct aead_request *req; + struct scatterlist sg[2]; + u8 *aad = key->rx_aad; + u8 iv[AES_BLOCK_LEN]; u8 pn[6]; - int i, blocks, last, len; - size_t data_len = skb->len - hdr_len - CCMP_HDR_LEN - CCMP_MIC_LEN; - u8 *mic = skb->data + skb->len - CCMP_MIC_LEN; + int aad_len, ret; + size_t data_len = skb->len - hdr_len - CCMP_HDR_LEN; if (skb->len < hdr_len + CCMP_HDR_LEN + CCMP_MIC_LEN) { key->dot11RSNAStatsCCMPFormatErrors++; @@ -337,28 +310,26 @@ static int lib80211_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) return -4; } - ccmp_init_blocks(key->tfm, hdr, pn, data_len, b0, a, b); - xor_block(mic, b, CCMP_MIC_LEN); - - blocks = DIV_ROUND_UP(data_len, AES_BLOCK_LEN); - last = data_len % AES_BLOCK_LEN; - - for (i = 1; i <= blocks; i++) { - len = (i == blocks && last) ? last : AES_BLOCK_LEN; - /* Decrypt, with counter */ - b0[14] = (i >> 8) & 0xff; - b0[15] = i & 0xff; - lib80211_ccmp_aes_encrypt(key->tfm, b0, b); - xor_block(pos, b, len); - /* Authentication */ - xor_block(a, pos, len); - lib80211_ccmp_aes_encrypt(key->tfm, a, a); - pos += len; - } + req = aead_request_alloc(key->tfm, GFP_ATOMIC); + if (!req) + return -ENOMEM; - if (memcmp(mic, a, CCMP_MIC_LEN) != 0) { - net_dbg_ratelimited("CCMP: decrypt failed: STA=%pM\n", - hdr->addr2); + aad_len = ccmp_init_iv_and_aad(hdr, pn, iv, aad); + + sg_init_table(sg, 2); + sg_set_buf(&sg[0], aad, aad_len); + sg_set_buf(&sg[1], pos, data_len); + + aead_request_set_callback(req, 0, NULL, NULL); + aead_request_set_ad(req, aad_len); + aead_request_set_crypt(req, sg, sg, data_len, iv); + + ret = crypto_aead_decrypt(req); + aead_request_free(req); + + if (ret) { + net_dbg_ratelimited("CCMP: decrypt failed: STA=%pM (%d)\n", + hdr->addr2, ret); key->dot11RSNAStatsCCMPDecryptErrors++; return -5; } @@ -377,7 +348,7 @@ static int lib80211_ccmp_set_key(void *key, int len, u8 * seq, void *priv) { struct lib80211_ccmp_data *data = priv; int keyidx; - struct crypto_cipher *tfm = data->tfm; + struct crypto_aead *tfm = data->tfm; keyidx = data->key_idx; memset(data, 0, sizeof(*data)); @@ -394,7 +365,9 @@ static int lib80211_ccmp_set_key(void *key, int len, u8 * seq, void *priv) data->rx_pn[4] = seq[1]; data->rx_pn[5] = seq[0]; } - crypto_cipher_setkey(data->tfm, data->key, CCMP_TK_LEN); + if (crypto_aead_setauthsize(data->tfm, CCMP_MIC_LEN) || + crypto_aead_setkey(data->tfm, data->key, CCMP_TK_LEN)) + return -1; } else if (len == 0) data->key_set = 0; else diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fd05ae1437a9..92e06482563c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -281,7 +281,16 @@ nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = { NLA_POLICY_NESTED_ARRAY(nl80211_psmr_peer_attr_policy), }; +static const struct nla_policy +he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = { + [NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] = + NLA_POLICY_RANGE(NLA_U8, 1, 20), + [NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET] = + NLA_POLICY_RANGE(NLA_U8, 1, 20), +}; + const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { + [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, [NL80211_ATTR_WIPHY_NAME] = { .type = NLA_NUL_STRING, .len = 20-1 }, @@ -574,6 +583,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_SAE_PASSWORD] = { .type = NLA_BINARY, .len = SAE_PASSWORD_MAX_LEN }, [NL80211_ATTR_TWT_RESPONDER] = { .type = NLA_FLAG }, + [NL80211_ATTR_HE_OBSS_PD] = NLA_POLICY_NESTED(he_obss_pd_policy), }; /* policy for the key attributes */ @@ -749,17 +759,25 @@ int nl80211_prepare_wdev_dump(struct netlink_callback *cb, int err; if (!cb->args[0]) { + struct nlattr **attrbuf; + + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), + GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, - genl_family_attrbuf(&nl80211_fam), - nl80211_fam.maxattr, + attrbuf, nl80211_fam.maxattr, nl80211_policy, NULL); - if (err) + if (err) { + kfree(attrbuf); return err; + } - *wdev = __cfg80211_wdev_from_attrs( - sock_net(cb->skb->sk), - genl_family_attrbuf(&nl80211_fam)); + *wdev = __cfg80211_wdev_from_attrs(sock_net(cb->skb->sk), + attrbuf); + kfree(attrbuf); if (IS_ERR(*wdev)) return PTR_ERR(*wdev); *rdev = wiphy_to_rdev((*wdev)->wiphy); @@ -2172,6 +2190,30 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.vht_capa_mod_mask)) goto nla_put_failure; + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, + rdev->wiphy.perm_addr)) + goto nla_put_failure; + + if (!is_zero_ether_addr(rdev->wiphy.addr_mask) && + nla_put(msg, NL80211_ATTR_MAC_MASK, ETH_ALEN, + rdev->wiphy.addr_mask)) + goto nla_put_failure; + + if (rdev->wiphy.n_addresses > 1) { + void *attr; + + attr = nla_nest_start(msg, NL80211_ATTR_MAC_ADDRS); + if (!attr) + goto nla_put_failure; + + for (i = 0; i < rdev->wiphy.n_addresses; i++) + if (nla_put(msg, i + 1, ETH_ALEN, + rdev->wiphy.addresses[i].addr)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + } + state->split_start++; break; case 10: @@ -2366,14 +2408,21 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, struct netlink_callback *cb, struct nl80211_dump_wiphy_state *state) { - struct nlattr **tb = genl_family_attrbuf(&nl80211_fam); - int ret = nlmsg_parse_deprecated(cb->nlh, - GENL_HDRLEN + nl80211_fam.hdrsize, - tb, nl80211_fam.maxattr, - nl80211_policy, NULL); + struct nlattr **tb = kcalloc(NUM_NL80211_ATTR, sizeof(*tb), GFP_KERNEL); + int ret; + + if (!tb) + return -ENOMEM; + + ret = nlmsg_parse_deprecated(cb->nlh, + GENL_HDRLEN + nl80211_fam.hdrsize, + tb, nl80211_fam.maxattr, + nl80211_policy, NULL); /* ignore parse errors for backward compatibility */ - if (ret) - return 0; + if (ret) { + ret = 0; + goto out; + } state->split = tb[NL80211_ATTR_SPLIT_WIPHY_DUMP]; if (tb[NL80211_ATTR_WIPHY]) @@ -2386,8 +2435,10 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, int ifidx = nla_get_u32(tb[NL80211_ATTR_IFINDEX]); netdev = __dev_get_by_index(sock_net(skb->sk), ifidx); - if (!netdev) - return -ENODEV; + if (!netdev) { + ret = -ENODEV; + goto out; + } if (netdev->ieee80211_ptr) { rdev = wiphy_to_rdev( netdev->ieee80211_ptr->wiphy); @@ -2395,7 +2446,10 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb, } } - return 0; + ret = 0; +out: + kfree(tb); + return ret; } static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) @@ -4359,6 +4413,34 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, return 0; } +static int nl80211_parse_he_obss_pd(struct nlattr *attrs, + struct ieee80211_he_obss_pd *he_obss_pd) +{ + struct nlattr *tb[NL80211_HE_OBSS_PD_ATTR_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NL80211_HE_OBSS_PD_ATTR_MAX, attrs, + he_obss_pd_policy, NULL); + if (err) + return err; + + if (!tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] || + !tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) + return -EINVAL; + + he_obss_pd->min_offset = + nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); + he_obss_pd->max_offset = + nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); + + if (he_obss_pd->min_offset >= he_obss_pd->max_offset) + return -EINVAL; + + he_obss_pd->enable = true; + + return 0; +} + static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params, const u8 *rates) { @@ -4643,6 +4725,14 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.twt_responder = nla_get_flag(info->attrs[NL80211_ATTR_TWT_RESPONDER]); + if (info->attrs[NL80211_ATTR_HE_OBSS_PD]) { + err = nl80211_parse_he_obss_pd( + info->attrs[NL80211_ATTR_HE_OBSS_PD], + ¶ms.he_obss_pd); + if (err) + return err; + } + nl80211_calculate_ap_params(¶ms); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) @@ -8698,7 +8788,7 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) { - struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam); + struct nlattr **attrbuf; struct survey_info survey; struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; @@ -8706,6 +8796,10 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) int res; bool radio_stats; + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + rtnl_lock(); res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); if (res) @@ -8750,6 +8844,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) cb->args[2] = survey_idx; res = skb->len; out_err: + kfree(attrbuf); rtnl_unlock(); return res; } @@ -9609,6 +9704,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct cfg80211_registered_device *rdev; + struct nlattr **attrbuf = NULL; int err; long phy_idx; void *data = NULL; @@ -9629,7 +9725,12 @@ static int nl80211_testmode_dump(struct sk_buff *skb, goto out_err; } } else { - struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam); + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), + GFP_KERNEL); + if (!attrbuf) { + err = -ENOMEM; + goto out_err; + } err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, @@ -9696,6 +9797,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, /* see above */ cb->args[0] = phy_idx + 1; out_err: + kfree(attrbuf); rtnl_unlock(); return err; } @@ -12789,7 +12891,7 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, struct cfg80211_registered_device **rdev, struct wireless_dev **wdev) { - struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam); + struct nlattr **attrbuf; u32 vid, subcmd; unsigned int i; int vcmd_idx = -1; @@ -12820,24 +12922,32 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, return 0; } + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, attrbuf, nl80211_fam.maxattr, nl80211_policy, NULL); if (err) - return err; + goto out; if (!attrbuf[NL80211_ATTR_VENDOR_ID] || - !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) - return -EINVAL; + !attrbuf[NL80211_ATTR_VENDOR_SUBCMD]) { + err = -EINVAL; + goto out; + } *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), attrbuf); if (IS_ERR(*wdev)) *wdev = NULL; *rdev = __cfg80211_rdev_from_attrs(sock_net(skb->sk), attrbuf); - if (IS_ERR(*rdev)) - return PTR_ERR(*rdev); + if (IS_ERR(*rdev)) { + err = PTR_ERR(*rdev); + goto out; + } vid = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_ID]); subcmd = nla_get_u32(attrbuf[NL80211_ATTR_VENDOR_SUBCMD]); @@ -12850,15 +12960,19 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, if (vcmd->info.vendor_id != vid || vcmd->info.subcmd != subcmd) continue; - if (!vcmd->dumpit) - return -EOPNOTSUPP; + if (!vcmd->dumpit) { + err = -EOPNOTSUPP; + goto out; + } vcmd_idx = i; break; } - if (vcmd_idx < 0) - return -EOPNOTSUPP; + if (vcmd_idx < 0) { + err = -EOPNOTSUPP; + goto out; + } if (attrbuf[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(attrbuf[NL80211_ATTR_VENDOR_DATA]); @@ -12869,7 +12983,7 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, attrbuf[NL80211_ATTR_VENDOR_DATA], cb->extack); if (err) - return err; + goto out; } /* 0 is the first index - add 1 to parse only once */ @@ -12881,7 +12995,10 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, cb->args[4] = data_len; /* keep rtnl locked in successful case */ - return 0; + err = 0; +out: + kfree(attrbuf); + return err; } static int nl80211_vendor_cmd_dump(struct sk_buff *skb, @@ -14559,6 +14676,7 @@ static struct genl_family nl80211_fam __ro_after_init = { .n_ops = ARRAY_SIZE(nl80211_ops), .mcgrps = nl80211_mcgrps, .n_mcgrps = ARRAY_SIZE(nl80211_mcgrps), + .parallel_ops = true, }; /* notification functions */ @@ -16090,7 +16208,9 @@ void cfg80211_ch_switch_notify(struct net_device *dev, if (wdev->iftype == NL80211_IFTYPE_STATION && !WARN_ON(!wdev->current_bss)) - wdev->current_bss->pub.channel = chandef->chan; + cfg80211_update_assoc_bss_entry(wdev, chandef->chan); + + cfg80211_sched_dfs_chan_update(rdev); nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL, NL80211_CMD_CH_SWITCH_NOTIFY, 0); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d66e6d4b7555..d313c9befa23 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1091,6 +1091,93 @@ struct cfg80211_non_tx_bss { u8 bssid_index; }; +static bool +cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, + struct cfg80211_internal_bss *known, + struct cfg80211_internal_bss *new, + bool signal_valid) +{ + lockdep_assert_held(&rdev->bss_lock); + + /* Update IEs */ + if (rcu_access_pointer(new->pub.proberesp_ies)) { + const struct cfg80211_bss_ies *old; + + old = rcu_access_pointer(known->pub.proberesp_ies); + + rcu_assign_pointer(known->pub.proberesp_ies, + new->pub.proberesp_ies); + /* Override possible earlier Beacon frame IEs */ + rcu_assign_pointer(known->pub.ies, + new->pub.proberesp_ies); + if (old) + kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); + } else if (rcu_access_pointer(new->pub.beacon_ies)) { + const struct cfg80211_bss_ies *old; + struct cfg80211_internal_bss *bss; + + if (known->pub.hidden_beacon_bss && + !list_empty(&known->hidden_list)) { + const struct cfg80211_bss_ies *f; + + /* The known BSS struct is one of the probe + * response members of a group, but we're + * receiving a beacon (beacon_ies in the new + * bss is used). This can only mean that the + * AP changed its beacon from not having an + * SSID to showing it, which is confusing so + * drop this information. + */ + + f = rcu_access_pointer(new->pub.beacon_ies); + kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head); + return false; + } + + old = rcu_access_pointer(known->pub.beacon_ies); + + rcu_assign_pointer(known->pub.beacon_ies, new->pub.beacon_ies); + + /* Override IEs if they were from a beacon before */ + if (old == rcu_access_pointer(known->pub.ies)) + rcu_assign_pointer(known->pub.ies, new->pub.beacon_ies); + + /* Assign beacon IEs to all sub entries */ + list_for_each_entry(bss, &known->hidden_list, hidden_list) { + const struct cfg80211_bss_ies *ies; + + ies = rcu_access_pointer(bss->pub.beacon_ies); + WARN_ON(ies != old); + + rcu_assign_pointer(bss->pub.beacon_ies, + new->pub.beacon_ies); + } + + if (old) + kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); + } + + known->pub.beacon_interval = new->pub.beacon_interval; + + /* don't update the signal if beacon was heard on + * adjacent channel. + */ + if (signal_valid) + known->pub.signal = new->pub.signal; + known->pub.capability = new->pub.capability; + known->ts = new->ts; + known->ts_boottime = new->ts_boottime; + known->parent_tsf = new->parent_tsf; + known->pub.chains = new->pub.chains; + memcpy(known->pub.chain_signal, new->pub.chain_signal, + IEEE80211_MAX_CHAINS); + ether_addr_copy(known->parent_bssid, new->parent_bssid); + known->pub.max_bssid_indicator = new->pub.max_bssid_indicator; + known->pub.bssid_index = new->pub.bssid_index; + + return true; +} + /* Returned bss is reference counted and must be cleaned up appropriately. */ struct cfg80211_internal_bss * cfg80211_bss_update(struct cfg80211_registered_device *rdev, @@ -1114,88 +1201,8 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, found = rb_find_bss(rdev, tmp, BSS_CMP_REGULAR); if (found) { - /* Update IEs */ - if (rcu_access_pointer(tmp->pub.proberesp_ies)) { - const struct cfg80211_bss_ies *old; - - old = rcu_access_pointer(found->pub.proberesp_ies); - - rcu_assign_pointer(found->pub.proberesp_ies, - tmp->pub.proberesp_ies); - /* Override possible earlier Beacon frame IEs */ - rcu_assign_pointer(found->pub.ies, - tmp->pub.proberesp_ies); - if (old) - kfree_rcu((struct cfg80211_bss_ies *)old, - rcu_head); - } else if (rcu_access_pointer(tmp->pub.beacon_ies)) { - const struct cfg80211_bss_ies *old; - struct cfg80211_internal_bss *bss; - - if (found->pub.hidden_beacon_bss && - !list_empty(&found->hidden_list)) { - const struct cfg80211_bss_ies *f; - - /* - * The found BSS struct is one of the probe - * response members of a group, but we're - * receiving a beacon (beacon_ies in the tmp - * bss is used). This can only mean that the - * AP changed its beacon from not having an - * SSID to showing it, which is confusing so - * drop this information. - */ - - f = rcu_access_pointer(tmp->pub.beacon_ies); - kfree_rcu((struct cfg80211_bss_ies *)f, - rcu_head); - goto drop; - } - - old = rcu_access_pointer(found->pub.beacon_ies); - - rcu_assign_pointer(found->pub.beacon_ies, - tmp->pub.beacon_ies); - - /* Override IEs if they were from a beacon before */ - if (old == rcu_access_pointer(found->pub.ies)) - rcu_assign_pointer(found->pub.ies, - tmp->pub.beacon_ies); - - /* Assign beacon IEs to all sub entries */ - list_for_each_entry(bss, &found->hidden_list, - hidden_list) { - const struct cfg80211_bss_ies *ies; - - ies = rcu_access_pointer(bss->pub.beacon_ies); - WARN_ON(ies != old); - - rcu_assign_pointer(bss->pub.beacon_ies, - tmp->pub.beacon_ies); - } - - if (old) - kfree_rcu((struct cfg80211_bss_ies *)old, - rcu_head); - } - - found->pub.beacon_interval = tmp->pub.beacon_interval; - /* - * don't update the signal if beacon was heard on - * adjacent channel. - */ - if (signal_valid) - found->pub.signal = tmp->pub.signal; - found->pub.capability = tmp->pub.capability; - found->ts = tmp->ts; - found->ts_boottime = tmp->ts_boottime; - found->parent_tsf = tmp->parent_tsf; - found->pub.chains = tmp->pub.chains; - memcpy(found->pub.chain_signal, tmp->pub.chain_signal, - IEEE80211_MAX_CHAINS); - ether_addr_copy(found->parent_bssid, tmp->parent_bssid); - found->pub.max_bssid_indicator = tmp->pub.max_bssid_indicator; - found->pub.bssid_index = tmp->pub.bssid_index; + if (!cfg80211_update_known_bss(rdev, found, tmp, signal_valid)) + goto drop; } else { struct cfg80211_internal_bss *new; struct cfg80211_internal_bss *hidden; @@ -1368,6 +1375,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, struct cfg80211_internal_bss tmp = {}, *res; int bss_type; bool signal_valid; + unsigned long ts; if (WARN_ON(!wiphy)) return NULL; @@ -1390,8 +1398,11 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, tmp.ts_boottime = data->boottime_ns; if (non_tx_data) { tmp.pub.transmitted_bss = non_tx_data->tx_bss; + ts = bss_from_pub(non_tx_data->tx_bss)->ts; tmp.pub.bssid_index = non_tx_data->bssid_index; tmp.pub.max_bssid_indicator = non_tx_data->max_bssid_indicator; + } else { + ts = jiffies; } /* @@ -1425,8 +1436,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; - res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, - jiffies); + res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, ts); if (!res) return NULL; @@ -1440,7 +1450,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, regulatory_hint_found_beacon(wiphy, channel, gfp); } - if (non_tx_data && non_tx_data->tx_bss) { + if (non_tx_data) { /* this is a nontransmitting bss, we need to add it to * transmitting bss' list if it is not there */ @@ -1659,6 +1669,8 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, res = cfg80211_inform_single_bss_data(wiphy, data, ftype, bssid, tsf, capability, beacon_interval, ie, ielen, NULL, gfp); + if (!res) + return NULL; non_tx_data.tx_bss = res; cfg80211_parse_mbssid_data(wiphy, data, ftype, bssid, tsf, beacon_interval, ie, ielen, &non_tx_data, @@ -1776,7 +1788,6 @@ static struct cfg80211_bss * cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, struct cfg80211_inform_bss *data, struct ieee80211_mgmt *mgmt, size_t len, - struct cfg80211_non_tx_bss *non_tx_data, gfp_t gfp) { struct cfg80211_internal_bss tmp = {}, *res; @@ -1835,11 +1846,6 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, tmp.pub.chains = data->chains; memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS); ether_addr_copy(tmp.parent_bssid, data->parent_bssid); - if (non_tx_data) { - tmp.pub.transmitted_bss = non_tx_data->tx_bss; - tmp.pub.bssid_index = non_tx_data->bssid_index; - tmp.pub.max_bssid_indicator = non_tx_data->max_bssid_indicator; - } signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; @@ -1877,7 +1883,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct cfg80211_non_tx_bss non_tx_data; res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt, - len, NULL, gfp); + len, gfp); if (!res || !wiphy->support_mbssid || !cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) return res; @@ -1995,6 +2001,85 @@ void cfg80211_bss_iter(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_bss_iter); +void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev, + struct ieee80211_channel *chan) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct cfg80211_internal_bss *cbss = wdev->current_bss; + struct cfg80211_internal_bss *new = NULL; + struct cfg80211_internal_bss *bss; + struct cfg80211_bss *nontrans_bss; + struct cfg80211_bss *tmp; + + spin_lock_bh(&rdev->bss_lock); + + if (WARN_ON(cbss->pub.channel == chan)) + goto done; + + /* use transmitting bss */ + if (cbss->pub.transmitted_bss) + cbss = container_of(cbss->pub.transmitted_bss, + struct cfg80211_internal_bss, + pub); + + cbss->pub.channel = chan; + + list_for_each_entry(bss, &rdev->bss_list, list) { + if (!cfg80211_bss_type_match(bss->pub.capability, + bss->pub.channel->band, + wdev->conn_bss_type)) + continue; + + if (bss == cbss) + continue; + + if (!cmp_bss(&bss->pub, &cbss->pub, BSS_CMP_REGULAR)) { + new = bss; + break; + } + } + + if (new) { + /* to save time, update IEs for transmitting bss only */ + if (cfg80211_update_known_bss(rdev, cbss, new, false)) { + new->pub.proberesp_ies = NULL; + new->pub.beacon_ies = NULL; + } + + list_for_each_entry_safe(nontrans_bss, tmp, + &new->pub.nontrans_list, + nontrans_list) { + bss = container_of(nontrans_bss, + struct cfg80211_internal_bss, pub); + if (__cfg80211_unlink_bss(rdev, bss)) + rdev->bss_generation++; + } + + WARN_ON(atomic_read(&new->hold)); + if (!WARN_ON(!__cfg80211_unlink_bss(rdev, new))) + rdev->bss_generation++; + } + + rb_erase(&cbss->rbn, &rdev->bss_tree); + rb_insert_bss(rdev, cbss); + rdev->bss_generation++; + + list_for_each_entry_safe(nontrans_bss, tmp, + &cbss->pub.nontrans_list, + nontrans_list) { + bss = container_of(nontrans_bss, + struct cfg80211_internal_bss, pub); + bss->pub.channel = chan; + rb_erase(&bss->rbn, &rdev->bss_tree); + rb_insert_bss(rdev, bss); + rdev->bss_generation++; + } + +done: + spin_unlock_bh(&rdev->bss_lock); +} + #ifdef CONFIG_CFG80211_WEXT static struct cfg80211_registered_device * cfg80211_get_dev_from_ifindex(struct net *net, int ifindex) diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 83de74ca729a..a0607969f8c0 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -14,6 +14,7 @@ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/idr.h> +#include <linux/highmem.h> #include "xdp_umem.h" #include "xsk_queue.h" @@ -164,6 +165,14 @@ void xdp_umem_clear_dev(struct xdp_umem *umem) umem->zc = false; } +static void xdp_umem_unmap_pages(struct xdp_umem *umem) +{ + unsigned int i; + + for (i = 0; i < umem->npgs; i++) + kunmap(umem->pgs[i]); +} + static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unsigned int i; @@ -207,6 +216,7 @@ static void xdp_umem_release(struct xdp_umem *umem) xsk_reuseq_destroy(umem); + xdp_umem_unmap_pages(umem); xdp_umem_unpin_pages(umem); kfree(umem->pages); @@ -369,7 +379,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) } for (i = 0; i < umem->npgs; i++) - umem->pages[i].addr = page_address(umem->pgs[i]); + umem->pages[i].addr = kmap(umem->pgs[i]); return 0; diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 32c364d3bfb3..4d422447aadc 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -85,7 +85,7 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) if (dlen < len) len = dlen; - frag->page_offset = 0; + skb_frag_off_set(frag, 0); skb_frag_size_set(frag, len); memcpy(skb_frag_address(frag), scratch, len); diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index 2dd1d39b152a..8ee47699a870 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -18,9 +18,6 @@ #include <libbpf.h> #include "bpf_load.h" #include "perf-sys.h" -#include "trace_helpers.h" - -static int pmu_fd; static __u64 time_get_ns(void) { @@ -31,12 +28,12 @@ static __u64 time_get_ns(void) } static __u64 start_time; +static __u64 cnt; #define MAX_CNT 100000ll -static int print_bpf_output(void *data, int size) +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) { - static __u64 cnt; struct { __u64 pid; __u64 cookie; @@ -45,7 +42,7 @@ static int print_bpf_output(void *data, int size) if (e->cookie != 0x12345678) { printf("BUG pid %llx cookie %llx sized %d\n", e->pid, e->cookie, size); - return LIBBPF_PERF_EVENT_ERROR; + return; } cnt++; @@ -53,30 +50,14 @@ static int print_bpf_output(void *data, int size) if (cnt == MAX_CNT) { printf("recv %lld events per sec\n", MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); - return LIBBPF_PERF_EVENT_DONE; + return; } - - return LIBBPF_PERF_EVENT_CONT; -} - -static void test_bpf_perf_event(void) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - }; - int key = 0; - - pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); - - assert(pmu_fd >= 0); - assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0); - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); } int main(int argc, char **argv) { + struct perf_buffer_opts pb_opts = {}; + struct perf_buffer *pb; char filename[256]; FILE *f; int ret; @@ -88,16 +69,20 @@ int main(int argc, char **argv) return 1; } - test_bpf_perf_event(); - - if (perf_event_mmap(pmu_fd) < 0) + pb_opts.sample_cb = print_bpf_output; + pb = perf_buffer__new(map_fd[0], 8, &pb_opts); + ret = libbpf_get_error(pb); + if (ret) { + printf("failed to setup perf_buffer: %d\n", ret); return 1; + } f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r"); (void) f; start_time = time_get_ns(); - ret = perf_event_poller(pmu_fd, print_bpf_output); + while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) { + } kill(0, SIGINT); return ret; } diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c index a7e94e7ff87d..701a30f258b1 100644 --- a/samples/bpf/xdp_fwd_kern.c +++ b/samples/bpf/xdp_fwd_kern.c @@ -23,7 +23,8 @@ #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) -struct bpf_map_def SEC("maps") tx_port = { +/* For TX-traffic redirect requires net_device ifindex to be in this devmap */ +struct bpf_map_def SEC("maps") xdp_tx_ports = { .type = BPF_MAP_TYPE_DEVMAP, .key_size = sizeof(int), .value_size = sizeof(int), @@ -102,14 +103,34 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) fib_params.ifindex = ctx->ingress_ifindex; rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); - - /* verify egress index has xdp support - * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with - * cannot pass map_type 14 into func bpf_map_lookup_elem#1: - * NOTE: without verification that egress index supports XDP - * forwarding packets are dropped. + /* + * Some rc (return codes) from bpf_fib_lookup() are important, + * to understand how this XDP-prog interacts with network stack. + * + * BPF_FIB_LKUP_RET_NO_NEIGH: + * Even if route lookup was a success, then the MAC-addresses are also + * needed. This is obtained from arp/neighbour table, but if table is + * (still) empty then BPF_FIB_LKUP_RET_NO_NEIGH is returned. To avoid + * doing ARP lookup directly from XDP, then send packet to normal + * network stack via XDP_PASS and expect it will do ARP resolution. + * + * BPF_FIB_LKUP_RET_FWD_DISABLED: + * The bpf_fib_lookup respect sysctl net.ipv{4,6}.conf.all.forwarding + * setting, and will return BPF_FIB_LKUP_RET_FWD_DISABLED if not + * enabled this on ingress device. */ - if (rc == 0) { + if (rc == BPF_FIB_LKUP_RET_SUCCESS) { + /* Verify egress index has been configured as TX-port. + * (Note: User can still have inserted an egress ifindex that + * doesn't support XDP xmit, which will result in packet drops). + * + * Note: lookup in devmap supported since 0cdbb4b09a0. + * If not supported will fail with: + * cannot pass map_type 14 into func bpf_map_lookup_elem#1: + */ + if (!bpf_map_lookup_elem(&xdp_tx_ports, &fib_params.ifindex)) + return XDP_PASS; + if (h_proto == htons(ETH_P_IP)) ip_decrease_ttl(iph); else if (h_proto == htons(ETH_P_IPV6)) @@ -117,7 +138,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); memcpy(eth->h_source, fib_params.smac, ETH_ALEN); - return bpf_redirect_map(&tx_port, fib_params.ifindex, 0); + return bpf_redirect_map(&xdp_tx_ports, fib_params.ifindex, 0); } return XDP_PASS; diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c index 5b46ee12c696..97ff1dad7669 100644 --- a/samples/bpf/xdp_fwd_user.c +++ b/samples/bpf/xdp_fwd_user.c @@ -27,14 +27,20 @@ #include "libbpf.h" #include <bpf/bpf.h> - -static int do_attach(int idx, int fd, const char *name) +static int do_attach(int idx, int prog_fd, int map_fd, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, fd, 0); - if (err < 0) + err = bpf_set_link_xdp_fd(idx, prog_fd, 0); + if (err < 0) { printf("ERROR: failed to attach program to %s\n", name); + return err; + } + + /* Adding ifindex as a possible egress TX port */ + err = bpf_map_update_elem(map_fd, &idx, &idx, 0); + if (err) + printf("ERROR: failed using device %s as TX-port\n", name); return err; } @@ -47,6 +53,9 @@ static int do_detach(int idx, const char *name) if (err < 0) printf("ERROR: failed to detach program from %s\n", name); + /* TODO: Remember to cleanup map, when adding use of shared map + * bpf_map_delete_elem((map_fd, &idx); + */ return err; } @@ -67,10 +76,10 @@ int main(int argc, char **argv) }; const char *prog_name = "xdp_fwd"; struct bpf_program *prog; + int prog_fd, map_fd = -1; char filename[PATH_MAX]; struct bpf_object *obj; int opt, i, idx, err; - int prog_fd, map_fd; int attach = 1; int ret = 0; @@ -103,8 +112,14 @@ int main(int argc, char **argv) return 1; } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + err = bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd); + if (err) { + printf("Does kernel support devmap lookup?\n"); + /* If not, the error message will be: + * "cannot pass map_type 14 into func bpf_map_lookup_elem#1" + */ return 1; + } prog = bpf_object__find_program_by_title(obj, prog_name); prog_fd = bpf_program__fd(prog); @@ -113,16 +128,12 @@ int main(int argc, char **argv) return 1; } map_fd = bpf_map__fd(bpf_object__find_map_by_name(obj, - "tx_port")); + "xdp_tx_ports")); if (map_fd < 0) { printf("map not found: %s\n", strerror(map_fd)); return 1; } } - if (attach) { - for (i = 1; i < 64; ++i) - bpf_map_update_elem(map_fd, &i, &i, 0); - } for (i = optind; i < argc; ++i) { idx = if_nametoindex(argv[i]); @@ -138,7 +149,7 @@ int main(int argc, char **argv) if (err) ret = err; } else { - err = do_attach(idx, prog_fd, argv[i]); + err = do_attach(idx, prog_fd, map_fd, argv[i]); if (err) ret = err; } diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index dc66345a929a..3002714e3cd5 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -17,14 +17,13 @@ #include <linux/if_link.h> #include "perf-sys.h" -#include "trace_helpers.h" #define MAX_CPUS 128 -static int pmu_fds[MAX_CPUS], if_idx; -static struct perf_event_mmap_page *headers[MAX_CPUS]; +static int if_idx; static char *if_name; static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static __u32 prog_id; +static struct perf_buffer *pb = NULL; static int do_attach(int idx, int fd, const char *name) { @@ -73,7 +72,7 @@ static int do_detach(int idx, const char *name) #define SAMPLE_SIZE 64 -static int print_bpf_output(void *data, int size) +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) { struct { __u16 cookie; @@ -83,45 +82,20 @@ static int print_bpf_output(void *data, int size) int i; if (e->cookie != 0xdead) { - printf("BUG cookie %x sized %d\n", - e->cookie, size); - return LIBBPF_PERF_EVENT_ERROR; + printf("BUG cookie %x sized %d\n", e->cookie, size); + return; } printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len); for (i = 0; i < 14 && i < e->pkt_len; i++) printf("%02x ", e->pkt_data[i]); printf("\n"); - - return LIBBPF_PERF_EVENT_CONT; -} - -static void test_bpf_perf_event(int map_fd, int num) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - .wakeup_events = 1, /* get an fd notification for every event */ - }; - int i; - - for (i = 0; i < num; i++) { - int key = i; - - pmu_fds[i] = sys_perf_event_open(&attr, -1/*pid*/, i/*cpu*/, - -1/*group_fd*/, 0); - - assert(pmu_fds[i] >= 0); - assert(bpf_map_update_elem(map_fd, &key, - &pmu_fds[i], BPF_ANY) == 0); - ioctl(pmu_fds[i], PERF_EVENT_IOC_ENABLE, 0); - } } static void sig_handler(int signo) { do_detach(if_idx, if_name); + perf_buffer__free(pb); exit(0); } @@ -140,13 +114,13 @@ int main(int argc, char **argv) struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; + struct perf_buffer_opts pb_opts = {}; const char *optstr = "F"; int prog_fd, map_fd, opt; struct bpf_object *obj; struct bpf_map *map; char filename[256]; - int ret, err, i; - int numcpus; + int ret, err; while ((opt = getopt(argc, argv, optstr)) != -1) { switch (opt) { @@ -169,10 +143,6 @@ int main(int argc, char **argv) return 1; } - numcpus = get_nprocs(); - if (numcpus > MAX_CPUS) - numcpus = MAX_CPUS; - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; @@ -211,14 +181,17 @@ int main(int argc, char **argv) return 1; } - test_bpf_perf_event(map_fd, numcpus); + pb_opts.sample_cb = print_bpf_output; + pb = perf_buffer__new(map_fd, 8, &pb_opts); + err = libbpf_get_error(pb); + if (err) { + perror("perf_buffer setup failed"); + return 1; + } - for (i = 0; i < numcpus; i++) - if (perf_event_mmap_header(pmu_fds[i], &headers[i]) < 0) - return 1; + while ((ret = perf_buffer__poll(pb, 1000)) >= 0) { + } - ret = perf_event_poller_multi(pmu_fds, headers, numcpus, - print_bpf_output); kill(0, SIGINT); return ret; } diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 915775eb2921..c31193340108 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -56,8 +56,8 @@ modpost_link() } # Link of vmlinux -# ${1} - optional extra .o files -# ${2} - output file +# ${1} - output file +# ${@:2} - optional extra .o files vmlinux_link() { local lds="${objtree}/${KBUILD_LDS}" @@ -70,9 +70,9 @@ vmlinux_link() --start-group \ ${KBUILD_VMLINUX_LIBS} \ --end-group \ - ${1}" + ${@:2}" - ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \ + ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} -o ${1} \ -T ${lds} ${objects} else objects="-Wl,--whole-archive \ @@ -81,9 +81,9 @@ vmlinux_link() -Wl,--start-group \ ${KBUILD_VMLINUX_LIBS} \ -Wl,--end-group \ - ${1}" + ${@:2}" - ${CC} ${CFLAGS_vmlinux} -o ${2} \ + ${CC} ${CFLAGS_vmlinux} -o ${1} \ -Wl,-T,${lds} \ ${objects} \ -lutil -lrt -lpthread @@ -92,23 +92,34 @@ vmlinux_link() } # generate .BTF typeinfo from DWARF debuginfo +# ${1} - vmlinux image +# ${2} - file to dump raw BTF data into gen_btf() { - local pahole_ver; + local pahole_ver + local bin_arch if ! [ -x "$(command -v ${PAHOLE})" ]; then info "BTF" "${1}: pahole (${PAHOLE}) is not available" - return 0 + return 1 fi pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/') if [ "${pahole_ver}" -lt "113" ]; then info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13" - return 0 + return 1 fi - info "BTF" ${1} + info "BTF" ${2} + vmlinux_link ${1} LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1} + + # dump .BTF section into raw binary file to link with final vmlinux + bin_arch=$(${OBJDUMP} -f ${1} | grep architecture | \ + cut -d, -f1 | cut -d' ' -f2) + ${OBJCOPY} --dump-section .BTF=.btf.vmlinux.bin ${1} 2>/dev/null + ${OBJCOPY} -I binary -O ${CONFIG_OUTPUT_FORMAT} -B ${bin_arch} \ + --rename-section .data=.BTF .btf.vmlinux.bin ${2} } # Create ${2} .o file with all symbols from the ${1} object file @@ -153,6 +164,7 @@ sortextable() # Delete output files in case of error cleanup() { + rm -f .btf.* rm -f .tmp_System.map rm -f .tmp_kallsyms* rm -f .tmp_vmlinux* @@ -215,6 +227,13 @@ ${MAKE} -f "${srctree}/scripts/Makefile.modpost" MODPOST_VMLINUX=1 info MODINFO modules.builtin.modinfo ${OBJCOPY} -j .modinfo -O binary vmlinux.o modules.builtin.modinfo +btf_vmlinux_bin_o="" +if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then + if gen_btf .tmp_vmlinux.btf .btf.vmlinux.bin.o ; then + btf_vmlinux_bin_o=.btf.vmlinux.bin.o + fi +fi + kallsymso="" kallsyms_vmlinux="" if [ -n "${CONFIG_KALLSYMS}" ]; then @@ -246,11 +265,11 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then kallsyms_vmlinux=.tmp_vmlinux2 # step 1 - vmlinux_link "" .tmp_vmlinux1 + vmlinux_link .tmp_vmlinux1 ${btf_vmlinux_bin_o} kallsyms .tmp_vmlinux1 .tmp_kallsyms1.o # step 2 - vmlinux_link .tmp_kallsyms1.o .tmp_vmlinux2 + vmlinux_link .tmp_vmlinux2 .tmp_kallsyms1.o ${btf_vmlinux_bin_o} kallsyms .tmp_vmlinux2 .tmp_kallsyms2.o # step 3 @@ -261,18 +280,13 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then kallsymso=.tmp_kallsyms3.o kallsyms_vmlinux=.tmp_vmlinux3 - vmlinux_link .tmp_kallsyms2.o .tmp_vmlinux3 - + vmlinux_link .tmp_vmlinux3 .tmp_kallsyms2.o ${btf_vmlinux_bin_o} kallsyms .tmp_vmlinux3 .tmp_kallsyms3.o fi fi info LD vmlinux -vmlinux_link "${kallsymso}" vmlinux - -if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then - gen_btf vmlinux -fi +vmlinux_link vmlinux "${kallsymso}" "${btf_vmlinux_bin_o}" if [ -n "${CONFIG_BUILDTIME_EXTABLE_SORT}" ]; then info SORTEX vmlinux diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 585f270c2d25..06a28b07787d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -20,8 +20,8 @@ SYNOPSIS CGROUP COMMANDS =============== -| **bpftool** **cgroup { show | list }** *CGROUP* -| **bpftool** **cgroup tree** [*CGROUP_ROOT*] +| **bpftool** **cgroup { show | list }** *CGROUP* [**effective**] +| **bpftool** **cgroup tree** [*CGROUP_ROOT*] [**effective**] | **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] | **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* | **bpftool** **cgroup help** @@ -35,13 +35,17 @@ CGROUP COMMANDS DESCRIPTION =========== - **bpftool cgroup { show | list }** *CGROUP* + **bpftool cgroup { show | list }** *CGROUP* [**effective**] List all programs attached to the cgroup *CGROUP*. Output will start with program ID followed by attach type, attach flags and program name. - **bpftool cgroup tree** [*CGROUP_ROOT*] + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + + **bpftool cgroup tree** [*CGROUP_ROOT*] [**effective**] Iterate over all cgroups in *CGROUP_ROOT* and list all attached programs. If *CGROUP_ROOT* is not specified, bpftool uses cgroup v2 mountpoint. @@ -50,6 +54,10 @@ DESCRIPTION commands: it starts with absolute cgroup path, followed by program ID, attach type, attach flags and program name. + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + **bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] Attach program *PROG* to the cgroup *CGROUP* with attach type *ATTACH_TYPE* and optional *ATTACH_FLAGS*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 490b4501cb6e..61d1d270eb5e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -46,7 +46,7 @@ MAP COMMANDS | *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** | | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** -| | **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash** +| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** } diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index a7afea4dec47..4c9d1ffc3fc7 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -52,14 +52,14 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif -LIBS = -lelf $(LIBBPF) +LIBS = -lelf -lz $(LIBBPF) INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray -FEATURE_DISPLAY = libbfd disassembler-four-args +FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib +FEATURE_DISPLAY = libbfd disassembler-four-args zlib check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -111,6 +111,8 @@ OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< +$(OUTPUT)feature.o: | zdep + $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ $(LIBS) @@ -149,6 +151,9 @@ doc-uninstall: FORCE: -.PHONY: all FORCE clean install uninstall +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + +.PHONY: all FORCE clean install uninstall zdep .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index c8f42e1fcbc9..df16c5415444 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -489,8 +489,8 @@ _bpftool() perf_event_array percpu_hash percpu_array \ stack_trace cgroup_array lru_hash \ lru_percpu_hash lpm_trie array_of_maps \ - hash_of_maps devmap sockmap cpumap xskmap \ - sockhash cgroup_storage reuseport_sockarray \ + hash_of_maps devmap devmap_hash sockmap cpumap \ + xskmap sockhash cgroup_storage reuseport_sockarray \ percpu_cgroup_storage queue stack' -- \ "$cur" ) ) return 0 @@ -710,12 +710,15 @@ _bpftool() ;; cgroup) case $command in - show|list) - _filedir - return 0 - ;; - tree) - _filedir + show|list|tree) + case $cword in + 3) + _filedir + ;; + 4) + COMPREPLY=( $( compgen -W 'effective' -- "$cur" ) ) + ;; + esac return 0 ;; attach|detach) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index f3c05b08c68c..44352b5aca85 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -29,6 +29,8 @@ " recvmsg4 | recvmsg6 | sysctl |\n" \ " getsockopt | setsockopt }" +static unsigned int query_flags; + static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", [BPF_CGROUP_INET_EGRESS] = "egress", @@ -107,7 +109,8 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) __u32 prog_cnt = 0; int ret; - ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, NULL, + NULL, &prog_cnt); if (ret) return -1; @@ -125,8 +128,8 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int ret; prog_cnt = ARRAY_SIZE(prog_ids); - ret = bpf_prog_query(cgroup_fd, type, 0, &attach_flags, prog_ids, - &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags, + prog_ids, &prog_cnt); if (ret) return ret; @@ -158,20 +161,34 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + const char *path; int cgroup_fd; int ret = -1; - if (argc < 1) { - p_err("too few parameters for cgroup show"); - goto exit; - } else if (argc > 1) { - p_err("too many parameters for cgroup show"); - goto exit; + query_flags = 0; + + if (!REQ_ARGS(1)) + return -1; + path = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } } - cgroup_fd = open(argv[0], O_RDONLY); + cgroup_fd = open(path, O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[0]); + p_err("can't open cgroup %s", path); goto exit; } @@ -294,26 +311,37 @@ static char *find_cgroup_root(void) static int do_show_tree(int argc, char **argv) { - char *cgroup_root; + char *cgroup_root, *cgroup_alloced = NULL; int ret; - switch (argc) { - case 0: - cgroup_root = find_cgroup_root(); - if (!cgroup_root) { + query_flags = 0; + + if (!argc) { + cgroup_alloced = find_cgroup_root(); + if (!cgroup_alloced) { p_err("cgroup v2 isn't mounted"); return -1; } - break; - case 1: - cgroup_root = argv[0]; - break; - default: - p_err("too many parameters for cgroup tree"); - return -1; + cgroup_root = cgroup_alloced; + } else { + cgroup_root = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } + } } - if (json_output) jsonw_start_array(json_wtr); else @@ -338,8 +366,7 @@ static int do_show_tree(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - if (argc == 0) - free(cgroup_root); + free(cgroup_alloced); return ret; } @@ -459,8 +486,8 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } CGROUP\n" - " %s %s tree [CGROUP_ROOT]\n" + "Usage: %s %s { show | list } CGROUP [**effective**]\n" + " %s %s tree [CGROUP_ROOT] [**effective**]\n" " %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index d672d9086fff..03bdc5b3ac49 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -14,6 +14,7 @@ #include <bpf.h> #include <libbpf.h> +#include <zlib.h> #include "main.h" @@ -284,34 +285,32 @@ static void probe_jit_limit(void) } } -static char *get_kernel_config_option(FILE *fd, const char *option) +static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n, + char **value) { - size_t line_n = 0, optlen = strlen(option); - char *res, *strval, *line = NULL; - ssize_t n; + char *sep; - rewind(fd); - while ((n = getline(&line, &line_n, fd)) > 0) { - if (strncmp(line, option, optlen)) + while (gzgets(file, buf, n)) { + if (strncmp(buf, "CONFIG_", 7)) continue; - /* Check we have at least '=', value, and '\n' */ - if (strlen(line) < optlen + 3) - continue; - if (*(line + optlen) != '=') + + sep = strchr(buf, '='); + if (!sep) continue; /* Trim ending '\n' */ - line[strlen(line) - 1] = '\0'; + buf[strlen(buf) - 1] = '\0'; + + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) + continue; - /* Copy and return config option value */ - strval = line + optlen + 1; - res = strdup(strval); - free(line); - return res; + *value = sep + 1; + return true; } - free(line); - return NULL; + return false; } static void probe_kernel_image_config(void) @@ -386,59 +385,61 @@ static void probe_kernel_image_config(void) /* test_bpf module for BPF tests */ "CONFIG_TEST_BPF", }; - char *value, *buf = NULL; + char *values[ARRAY_SIZE(options)] = { }; struct utsname utsn; char path[PATH_MAX]; - size_t i, n; - ssize_t ret; - FILE *fd; + gzFile file = NULL; + char buf[4096]; + char *value; + size_t i; - if (uname(&utsn)) - goto no_config; + if (!uname(&utsn)) { + snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); - snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); + /* gzopen also accepts uncompressed files. */ + file = gzopen(path, "r"); + } - fd = fopen(path, "r"); - if (!fd && errno == ENOENT) { - /* Some distributions put the config file at /proc/config, give - * it a try. - * Sometimes it is also at /proc/config.gz but we do not try - * this one for now, it would require linking against libz. + if (!file) { + /* Some distributions build with CONFIG_IKCONFIG=y and put the + * config file at /proc/config.gz. */ - fd = fopen("/proc/config", "r"); + file = gzopen("/proc/config.gz", "r"); } - if (!fd) { + if (!file) { p_info("skipping kernel config, can't open file: %s", strerror(errno)); - goto no_config; + goto end_parse; } /* Sanity checks */ - ret = getline(&buf, &n, fd); - ret = getline(&buf, &n, fd); - if (!buf || !ret) { + if (!gzgets(file, buf, sizeof(buf)) || + !gzgets(file, buf, sizeof(buf))) { p_info("skipping kernel config, can't read from file: %s", strerror(errno)); - free(buf); - goto no_config; + goto end_parse; } if (strcmp(buf, "# Automatically generated file; DO NOT EDIT.\n")) { p_info("skipping kernel config, can't find correct file"); - free(buf); - goto no_config; + goto end_parse; } - free(buf); - for (i = 0; i < ARRAY_SIZE(options); i++) { - value = get_kernel_config_option(fd, options[i]); - print_kernel_option(options[i], value); - free(value); + while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) { + for (i = 0; i < ARRAY_SIZE(options); i++) { + if (values[i] || strcmp(buf, options[i])) + continue; + + values[i] = strdup(value); + } } - fclose(fd); - return; -no_config: - for (i = 0; i < ARRAY_SIZE(options); i++) - print_kernel_option(options[i], NULL); +end_parse: + if (file) + gzclose(file); + + for (i = 0; i < ARRAY_SIZE(options); i++) { + print_kernel_option(options[i], values[i]); + free(values[i]); + } } static bool probe_bpf_syscall(const char *define_prefix) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 5da5a7311f13..bfbbc6b4cb83 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -37,6 +37,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", [BPF_MAP_TYPE_XSKMAP] = "xskmap", @@ -1271,7 +1272,7 @@ static int do_help(int argc, char **argv) " TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n" " percpu_array | stack_trace | cgroup_array | lru_hash |\n" " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" - " devmap | sockmap | cpumap | xskmap | sockhash |\n" + " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n" " " HELP_SPEC_OPTIONS "\n" "", diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a5aa7d3ac6a1..0e66371bea13 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -134,6 +134,7 @@ enum bpf_map_type { BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, }; /* Note that tracing related programs such as @@ -2713,6 +2714,33 @@ union bpf_attr { * **-EPERM** if no permission to send the *sig*. * * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2824,7 +2852,8 @@ union bpf_attr { FN(strtoul), \ FN(sk_storage_get), \ FN(sk_storage_delete), \ - FN(send_signal), + FN(send_signal), \ + FN(tcp_gen_syncookie), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3507,6 +3536,10 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + struct bpf_flow_keys { __u16 nhoff; __u16 thoff; @@ -3528,6 +3561,8 @@ struct bpf_flow_keys { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; }; + __u32 flags; + __be32 flow_label; }; struct bpf_func_info { diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index d821107f55f9..1aa189a9112a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -20,13 +20,6 @@ #define BTF_MAX_NR_TYPES 0x7fffffff #define BTF_MAX_STR_OFFSET 0x7fffffff -#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ - ((k) == BTF_KIND_VOLATILE) || \ - ((k) == BTF_KIND_CONST) || \ - ((k) == BTF_KIND_RESTRICT)) - -#define IS_VAR(k) ((k) == BTF_KIND_VAR) - static struct btf_type btf_void; struct btf { @@ -43,47 +36,6 @@ struct btf { int fd; }; -struct btf_ext_info { - /* - * info points to the individual info section (e.g. func_info and - * line_info) from the .BTF.ext. It does not include the __u32 rec_size. - */ - void *info; - __u32 rec_size; - __u32 len; -}; - -struct btf_ext { - union { - struct btf_ext_header *hdr; - void *data; - }; - struct btf_ext_info func_info; - struct btf_ext_info line_info; - __u32 data_size; -}; - -struct btf_ext_info_sec { - __u32 sec_name_off; - __u32 num_info; - /* Followed by num_info * record_size number of bytes */ - __u8 data[0]; -}; - -/* The minimum bpf_func_info checked by the loader */ -struct bpf_func_info_min { - __u32 insn_off; - __u32 type_id; -}; - -/* The minimum bpf_line_info checked by the loader */ -struct bpf_line_info_min { - __u32 insn_off; - __u32 file_name_off; - __u32 line_off; - __u32 line_col; -}; - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -193,9 +145,9 @@ static int btf_parse_str_sec(struct btf *btf) static int btf_type_size(struct btf_type *t) { int base_size = sizeof(struct btf_type); - __u16 vlen = BTF_INFO_VLEN(t->info); + __u16 vlen = btf_vlen(t); - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_FWD: case BTF_KIND_CONST: case BTF_KIND_VOLATILE: @@ -220,7 +172,7 @@ static int btf_type_size(struct btf_type *t) case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); default: - pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info)); + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; } } @@ -264,7 +216,7 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) static bool btf_type_is_void(const struct btf_type *t) { - return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; + return t == &btf_void || btf_is_fwd(t); } static bool btf_type_is_void_or_null(const struct btf_type *t) @@ -285,7 +237,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: @@ -304,7 +256,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) type_id = t->type; break; case BTF_KIND_ARRAY: - array = (const struct btf_array *)(t + 1); + array = btf_array(t); if (nelems && array->nelems > UINT32_MAX / nelems) return -E2BIG; nelems *= array->nelems; @@ -335,8 +287,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); while (depth < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t) && - (IS_MODIFIER(BTF_INFO_KIND(t->info)) || - IS_VAR(BTF_INFO_KIND(t->info)))) { + (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) { type_id = t->type; t = btf__type_by_id(btf, type_id); depth++; @@ -555,11 +506,11 @@ static int compare_vsi_off(const void *_a, const void *_b) static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, struct btf_type *t) { - __u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info); + __u32 size = 0, off = 0, i, vars = btf_vlen(t); const char *name = btf__name_by_offset(btf, t->name_off); const struct btf_type *t_var; struct btf_var_secinfo *vsi; - struct btf_var *var; + const struct btf_var *var; int ret; if (!name) { @@ -575,12 +526,11 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, t->size = size; - for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1); - i < vars; i++, vsi++) { + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { t_var = btf__type_by_id(btf, vsi->type); - var = (struct btf_var *)(t_var + 1); + var = btf_var(t_var); - if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) { + if (!btf_is_var(t_var)) { pr_debug("Non-VAR type seen in section %s\n", name); return -EINVAL; } @@ -596,7 +546,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, ret = bpf_object__variable_offset(obj, name, &off); if (ret) { - pr_debug("No offset found in symbol table for VAR %s\n", name); + pr_debug("No offset found in symbol table for VAR %s\n", + name); return -ENOENT; } @@ -620,7 +571,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) * is section size and global variable offset. We use * the info from the ELF itself for this purpose. */ - if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) { + if (btf_is_datasec(t)) { err = btf_fixup_datasec(obj, btf, t); if (err) break; @@ -775,14 +726,13 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, return -EINVAL; } - if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || - BTF_INFO_VLEN(container_type->info) < 2) { + if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) { pr_warning("map:%s container_name:%s is an invalid container struct\n", map_name, container_name); return -EINVAL; } - key = (struct btf_member *)(container_type + 1); + key = btf_members(container_type); value = key + 1; key_size = btf__resolve_size(btf, key->type); @@ -832,6 +782,9 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, /* The start of the info sec (including the __u32 record_size). */ void *info; + if (ext_sec->len == 0) + return 0; + if (ext_sec->off & 0x03) { pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n", ext_sec->desc); @@ -935,11 +888,24 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext) return btf_ext_setup_info(btf_ext, ¶m); } +static int btf_ext_setup_offset_reloc(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->offset_reloc_off, + .len = btf_ext->hdr->offset_reloc_len, + .min_rec_size = sizeof(struct bpf_offset_reloc), + .ext_info = &btf_ext->offset_reloc_info, + .desc = "offset_reloc", + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) { const struct btf_ext_header *hdr = (struct btf_ext_header *)data; - if (data_size < offsetof(struct btf_ext_header, func_info_off) || + if (data_size < offsetofend(struct btf_ext_header, hdr_len) || data_size < hdr->hdr_len) { pr_debug("BTF.ext header not found"); return -EINVAL; @@ -997,6 +963,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, line_info_len)) + goto done; err = btf_ext_setup_func_info(btf_ext); if (err) goto done; @@ -1005,6 +974,13 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, offset_reloc_len)) + goto done; + err = btf_ext_setup_offset_reloc(btf_ext); + if (err) + goto done; + done: if (err) { btf_ext__free(btf_ext); @@ -1441,10 +1417,9 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, d->map[0] = 0; for (i = 1; i <= btf->nr_types; i++) { struct btf_type *t = d->btf->types[i]; - __u16 kind = BTF_INFO_KIND(t->info); /* VAR and DATASEC are never deduped and are self-canonical */ - if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC) + if (btf_is_var(t) || btf_is_datasec(t)) d->map[i] = i; else d->map[i] = BTF_UNPROCESSED_ID; @@ -1485,11 +1460,11 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) if (r) return r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *m = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1500,8 +1475,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_ENUM: { - struct btf_enum *m = (struct btf_enum *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_enum *m = btf_enum(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1512,8 +1487,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *m = btf_params(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1802,16 +1777,16 @@ static long btf_hash_enum(struct btf_type *t) /* Check structural equality of two ENUMs. */ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) { - struct btf_enum *m1, *m2; + const struct btf_enum *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_enum *)(t1 + 1); - m2 = (struct btf_enum *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_enum(t1); + m2 = btf_enum(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->val != m2->val) return false; @@ -1823,8 +1798,7 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) static inline bool btf_is_enum_fwd(struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM && - BTF_INFO_VLEN(t->info) == 0; + return btf_is_enum(t) && btf_vlen(t) == 0; } static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) @@ -1844,8 +1818,8 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_struct(struct btf_type *t) { - struct btf_member *member = (struct btf_member *)(t + 1); - __u32 vlen = BTF_INFO_VLEN(t->info); + const struct btf_member *member = btf_members(t); + __u32 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1865,16 +1839,16 @@ static long btf_hash_struct(struct btf_type *t) */ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) { - struct btf_member *m1, *m2; + const struct btf_member *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_member *)(t1 + 1); - m2 = (struct btf_member *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_members(t1); + m2 = btf_members(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->offset != m2->offset) return false; @@ -1891,7 +1865,7 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_array(struct btf_type *t) { - struct btf_array *info = (struct btf_array *)(t + 1); + const struct btf_array *info = btf_array(t); long h = btf_hash_common(t); h = hash_combine(h, info->type); @@ -1909,13 +1883,13 @@ static long btf_hash_array(struct btf_type *t) */ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; + const struct btf_array *info1, *info2; if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); + info1 = btf_array(t1); + info2 = btf_array(t2); return info1->type == info2->type && info1->index_type == info2->index_type && info1->nelems == info2->nelems; @@ -1928,14 +1902,10 @@ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) */ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; - if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); - return info1->nelems == info2->nelems; + return btf_array(t1)->nelems == btf_array(t2)->nelems; } /* @@ -1945,8 +1915,8 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_fnproto(struct btf_type *t) { - struct btf_param *member = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + const struct btf_param *member = btf_params(t); + __u16 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1967,16 +1937,16 @@ static long btf_hash_fnproto(struct btf_type *t) */ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->type != m2->type) return false; @@ -1993,7 +1963,7 @@ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) */ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; @@ -2001,9 +1971,9 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) if (t1->name_off != t2->name_off || t1->info != t2->info) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off) return false; @@ -2029,7 +1999,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) __u32 cand_id; long h; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -2142,13 +2112,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) { __u32 orig_type_id = type_id; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) type_id = d->map[type_id]; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; return orig_type_id; @@ -2157,7 +2127,7 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) static inline __u16 btf_fwd_kind(struct btf_type *t) { - return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT; + return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; } /* @@ -2278,8 +2248,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, cand_type = d->btf->types[cand_id]; canon_type = d->btf->types[canon_id]; - cand_kind = BTF_INFO_KIND(cand_type->info); - canon_kind = BTF_INFO_KIND(canon_type->info); + cand_kind = btf_kind(cand_type); + canon_kind = btf_kind(canon_type); if (cand_type->name_off != canon_type->name_off) return 0; @@ -2328,12 +2298,12 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); case BTF_KIND_ARRAY: { - struct btf_array *cand_arr, *canon_arr; + const struct btf_array *cand_arr, *canon_arr; if (!btf_compat_array(cand_type, canon_type)) return 0; - cand_arr = (struct btf_array *)(cand_type + 1); - canon_arr = (struct btf_array *)(canon_type + 1); + 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); if (eq <= 0) @@ -2343,14 +2313,14 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *cand_m, *canon_m; + const struct btf_member *cand_m, *canon_m; __u16 vlen; if (!btf_shallow_equal_struct(cand_type, canon_type)) return 0; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_m = (struct btf_member *)(cand_type + 1); - canon_m = (struct btf_member *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_m = btf_members(cand_type); + canon_m = btf_members(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type); if (eq <= 0) @@ -2363,7 +2333,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, } case BTF_KIND_FUNC_PROTO: { - struct btf_param *cand_p, *canon_p; + const struct btf_param *cand_p, *canon_p; __u16 vlen; if (!btf_compat_fnproto(cand_type, canon_type)) @@ -2371,9 +2341,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type); if (eq <= 0) return eq; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_p = (struct btf_param *)(cand_type + 1); - canon_p = (struct btf_param *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_p = btf_params(cand_type); + canon_p = btf_params(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type); if (eq <= 0) @@ -2428,8 +2398,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) targ_type_id = d->hypot_map[cand_type_id]; t_id = resolve_type_id(d, targ_type_id); c_id = resolve_type_id(d, cand_type_id); - t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info); - c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info); + t_kind = btf_kind(d->btf->types[t_id]); + c_kind = btf_kind(d->btf->types[c_id]); /* * Resolve FWD into STRUCT/UNION. * It's ok to resolve FWD into STRUCT/UNION that's not yet @@ -2498,7 +2468,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) return 0; t = d->btf->types[type_id]; - kind = BTF_INFO_KIND(t->info); + kind = btf_kind(t); if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) return 0; @@ -2593,7 +2563,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) t = d->btf->types[type_id]; d->map[type_id] = BTF_IN_PROGRESS_ID; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -2617,7 +2587,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) break; case BTF_KIND_ARRAY: { - struct btf_array *info = (struct btf_array *)(t + 1); + struct btf_array *info = btf_array(t); ref_type_id = btf_dedup_ref_type(d, info->type); if (ref_type_id < 0) @@ -2651,8 +2621,8 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) return ref_type_id; t->type = ref_type_id; - vlen = BTF_INFO_VLEN(t->info); - param = (struct btf_param *)(t + 1); + vlen = btf_vlen(t); + param = btf_params(t); for (i = 0; i < vlen; i++) { ref_type_id = btf_dedup_ref_type(d, param->type); if (ref_type_id < 0) @@ -2792,7 +2762,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) struct btf_type *t = d->btf->types[type_id]; int i, r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_ENUM: break; @@ -2812,7 +2782,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) break; case BTF_KIND_ARRAY: { - struct btf_array *arr_info = (struct btf_array *)(t + 1); + struct btf_array *arr_info = btf_array(t); r = btf_dedup_remap_type_id(d, arr_info->type); if (r < 0) @@ -2827,8 +2797,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *member = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *member = btf_members(t); + __u16 vlen = btf_vlen(t); for (i = 0; i < vlen; i++) { r = btf_dedup_remap_type_id(d, member->type); @@ -2841,8 +2811,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_FUNC_PROTO: { - struct btf_param *param = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *param = btf_params(t); + __u16 vlen = btf_vlen(t); r = btf_dedup_remap_type_id(d, t->type); if (r < 0) @@ -2860,8 +2830,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_DATASEC: { - struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_var_secinfo *var = btf_var_secinfos(t); + __u16 vlen = btf_vlen(t); for (i = 0; i < vlen; i++) { r = btf_dedup_remap_type_id(d, var->type); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 88a52ae56fc6..9cb44b4fbf60 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -5,6 +5,7 @@ #define __LIBBPF_BTF_H #include <stdarg.h> +#include <linux/btf.h> #include <linux/types.h> #ifdef __cplusplus @@ -57,6 +58,10 @@ struct btf_ext_header { __u32 func_info_len; __u32 line_info_off; __u32 line_info_len; + + /* optional part of .BTF.ext header */ + __u32 offset_reloc_off; + __u32 offset_reloc_len; }; LIBBPF_API void btf__free(struct btf *btf); @@ -120,6 +125,183 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); +/* + * A set of helpers for easier BTF types handling + */ +static inline __u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline __u16 btf_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline bool btf_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_struct(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_STRUCT; +} + +static inline bool btf_is_union(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_UNION; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_fwd(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FWD; +} + +static inline bool btf_is_typedef(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_is_volatile(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VOLATILE; +} + +static inline bool btf_is_const(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_CONST; +} + +static inline bool btf_is_restrict(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_mod(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_VOLATILE || + kind == BTF_KIND_CONST || + kind == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_func(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC; +} + +static inline bool btf_is_func_proto(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC_PROTO; +} + +static inline bool btf_is_var(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VAR; +} + +static inline bool btf_is_datasec(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_DATASEC; +} + +static inline __u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_bits(const struct btf_type *t) +{ + return BTF_INT_BITS(*(__u32 *)(t + 1)); +} + +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +/* Get bit offset of a member with specified index. */ +static inline __u32 btf_member_bit_offset(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; +} +/* + * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or + * BTF_KIND_UNION. If member is not a bitfield, zero is returned. + */ +static inline __u32 btf_member_bitfield_size(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; +} + +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + +static inline struct btf_var *btf_var(const struct btf_type *t) +{ + return (struct btf_var *)(t + 1); +} + +static inline struct btf_var_secinfo * +btf_var_secinfos(const struct btf_type *t) +{ + return (struct btf_var_secinfo *)(t + 1); +} + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 7065bb5b2752..715967762312 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -100,21 +100,6 @@ static bool str_equal_fn(const void *a, const void *b, void *ctx) return strcmp(a, b) == 0; } -static __u16 btf_kind_of(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info); -} - -static __u16 btf_vlen_of(const struct btf_type *t) -{ - return BTF_INFO_VLEN(t->info); -} - -static bool btf_kflag_of(const struct btf_type *t) -{ - return BTF_INFO_KFLAG(t->info); -} - static const char *btf_name_of(const struct btf_dump *d, __u32 name_off) { return btf__name_by_offset(d->btf, name_off); @@ -349,7 +334,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) */ struct btf_dump_type_aux_state *tstate = &d->type_states[id]; const struct btf_type *t; - __u16 kind, vlen; + __u16 vlen; int err, i; /* return true, letting typedefs know that it's ok to be emitted */ @@ -357,18 +342,16 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return 1; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); if (tstate->order_state == ORDERING) { /* type loop, but resolvable through fwd declaration */ - if ((kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION) && - through_ptr && t->name_off != 0) + if (btf_is_composite(t) && through_ptr && t->name_off != 0) return 0; pr_warning("unsatisfiable type cycle, id:[%u]\n", id); return -ELOOP; } - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_INT: tstate->order_state = ORDERED; return 0; @@ -378,14 +361,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERED; return err; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + case BTF_KIND_ARRAY: + return btf_dump_order_type(d, btf_array(t)->type, through_ptr); - return btf_dump_order_type(d, a->type, through_ptr); - } case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); + const struct btf_member *m = btf_members(t); /* * struct/union is part of strong link, only if it's embedded * (so no ptr in a path) or it's anonymous (so has to be @@ -396,7 +377,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERING; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, m++) { err = btf_dump_order_type(d, m->type, false); if (err < 0) @@ -447,7 +428,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return btf_dump_order_type(d, t->type, through_ptr); case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); + const struct btf_param *p = btf_params(t); bool is_strong; err = btf_dump_order_type(d, t->type, through_ptr); @@ -455,7 +436,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return err; is_strong = err > 0; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, p++) { err = btf_dump_order_type(d, p->type, through_ptr); if (err < 0) @@ -553,7 +534,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) return; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); + kind = btf_kind(t); if (top_level_def && t->name_off == 0) { pr_warning("unexpected nameless definition, id:[%u]\n", id); @@ -618,12 +599,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) case BTF_KIND_RESTRICT: btf_dump_emit_type(d, t->type, cont_id); break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - btf_dump_emit_type(d, a->type, cont_id); + case BTF_KIND_ARRAY: + btf_dump_emit_type(d, btf_array(t)->type, cont_id); break; - } case BTF_KIND_FWD: btf_dump_emit_fwd_def(d, id, t); btf_dump_printf(d, ";\n\n"); @@ -656,8 +634,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) * applicable */ if (top_level_def || t->name_off == 0) { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); int i, new_cont_id; new_cont_id = t->name_off == 0 ? cont_id : id; @@ -678,8 +656,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } break; case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_type(d, t->type, cont_id); @@ -696,7 +674,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) static int btf_align_of(const struct btf *btf, __u32 id) { const struct btf_type *t = btf__type_by_id(btf, id); - __u16 kind = btf_kind_of(t); + __u16 kind = btf_kind(t); switch (kind) { case BTF_KIND_INT: @@ -709,15 +687,12 @@ static int btf_align_of(const struct btf *btf, __u32 id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: return btf_align_of(btf, t->type); - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - return btf_align_of(btf, a->type); - } + case BTF_KIND_ARRAY: + return btf_align_of(btf, btf_array(t)->type); case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); int i, align = 1; for (i = 0; i < vlen; i++, m++) @@ -726,7 +701,7 @@ static int btf_align_of(const struct btf *btf, __u32 id) return align; } default: - pr_warning("unsupported BTF_KIND:%u\n", btf_kind_of(t)); + pr_warning("unsupported BTF_KIND:%u\n", btf_kind(t)); return 1; } } @@ -737,20 +712,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_member *m; int align, i, bit_sz; __u16 vlen; - bool kflag; align = btf_align_of(btf, id); /* size of a non-packed struct has to be a multiple of its alignment*/ if (t->size % align) return true; - m = (void *)(t + 1); - kflag = btf_kflag_of(t); - vlen = btf_vlen_of(t); + m = btf_members(t); + vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { align = btf_align_of(btf, m->type); - bit_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; + bit_sz = btf_member_bitfield_size(t, i); if (bit_sz == 0 && m->offset % (8 * align) != 0) return true; } @@ -807,7 +780,7 @@ static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t) { btf_dump_printf(d, "%s %s", - btf_kind_of(t) == BTF_KIND_STRUCT ? "struct" : "union", + btf_is_struct(t) ? "struct" : "union", btf_dump_type_name(d, id)); } @@ -816,12 +789,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, const struct btf_type *t, int lvl) { - const struct btf_member *m = (void *)(t + 1); - bool kflag = btf_kflag_of(t), is_struct; + const struct btf_member *m = btf_members(t); + bool is_struct = btf_is_struct(t); int align, i, packed, off = 0; - __u16 vlen = btf_vlen_of(t); + __u16 vlen = btf_vlen(t); - is_struct = btf_kind_of(t) == BTF_KIND_STRUCT; packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; align = packed ? 1 : btf_align_of(d->btf, id); @@ -835,8 +807,8 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, int m_off, m_sz; fname = btf_name_of(d, m->name_off); - m_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; - m_off = kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; + m_sz = btf_member_bitfield_size(t, i); + m_off = btf_member_bit_offset(t, i); align = packed ? 1 : btf_align_of(d->btf, m->type); btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); @@ -870,8 +842,8 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, const struct btf_type *t, int lvl) { - const struct btf_enum *v = (void *)(t+1); - __u16 vlen = btf_vlen_of(t); + const struct btf_enum *v = btf_enum(t); + __u16 vlen = btf_vlen(t); const char *name; size_t dup_cnt; int i; @@ -905,7 +877,7 @@ static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, { const char *name = btf_dump_type_name(d, id); - if (btf_kflag_of(t)) + if (btf_kflag(t)) btf_dump_printf(d, "union %s", name); else btf_dump_printf(d, "struct %s", name); @@ -987,7 +959,6 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, struct id_stack decl_stack; const struct btf_type *t; int err, stack_start; - __u16 kind; stack_start = d->decl_stack_cnt; for (;;) { @@ -1008,8 +979,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, break; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_PTR: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -1017,12 +987,9 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, case BTF_KIND_FUNC_PROTO: id = t->type; break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - id = a->type; + case BTF_KIND_ARRAY: + id = btf_array(t)->type; break; - } case BTF_KIND_INT: case BTF_KIND_ENUM: case BTF_KIND_FWD: @@ -1032,7 +999,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, goto done; default: pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n", - kind, id); + btf_kind(t), id); goto done; } } @@ -1070,7 +1037,7 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) id = decl_stack->ids[decl_stack->cnt - 1]; t = btf__type_by_id(d->btf, id); - switch (btf_kind_of(t)) { + switch (btf_kind(t)) { case BTF_KIND_VOLATILE: btf_dump_printf(d, "volatile "); break; @@ -1087,20 +1054,6 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) } } -static bool btf_is_mod_kind(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - - switch (btf_kind_of(t)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - return true; - default: - return false; - } -} - static void btf_dump_emit_name(const struct btf_dump *d, const char *name, bool last_was_ptr) { @@ -1139,7 +1092,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, } t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); + kind = btf_kind(t); switch (kind) { case BTF_KIND_INT: @@ -1185,7 +1138,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, btf_dump_printf(d, " restrict"); break; case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + const struct btf_array *a = btf_array(t); const struct btf_type *next_t; __u32 next_id; bool multidim; @@ -1201,7 +1154,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, */ while (decls->cnt) { next_id = decls->ids[decls->cnt - 1]; - if (btf_is_mod_kind(d->btf, next_id)) + next_t = btf__type_by_id(d->btf, next_id); + if (btf_is_mod(next_t)) decls->cnt--; else break; @@ -1214,7 +1168,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, } next_t = btf__type_by_id(d->btf, next_id); - multidim = btf_kind_of(next_t) == BTF_KIND_ARRAY; + multidim = btf_is_array(next_t); /* we need space if we have named non-pointer */ if (fname[0] && !last_was_ptr) btf_dump_printf(d, " "); @@ -1228,8 +1182,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, return; } case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_mods(d, decls); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2b57d7ea7836..e0276520171b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -39,6 +39,7 @@ #include <sys/stat.h> #include <sys/types.h> #include <sys/vfs.h> +#include <sys/utsname.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> @@ -48,6 +49,7 @@ #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" +#include "hashmap.h" #ifndef EM_BPF #define EM_BPF 247 @@ -75,9 +77,12 @@ static int __base_pr(enum libbpf_print_level level, const char *format, static libbpf_print_fn_t __libbpf_pr = __base_pr; -void libbpf_set_print(libbpf_print_fn_t fn) +libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) { + libbpf_print_fn_t old_print_fn = __libbpf_pr; + __libbpf_pr = fn; + return old_print_fn; } __printf(2, 3) @@ -1010,23 +1015,21 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return 0; } -static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, - __u32 id) +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) { const struct btf_type *t = btf__type_by_id(btf, id); - while (true) { - switch (BTF_INFO_KIND(t->info)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - case BTF_KIND_TYPEDEF: - t = btf__type_by_id(btf, t->type); - break; - default: - return t; - } + if (res_id) + *res_id = id; + + while (btf_is_mod(t) || btf_is_typedef(t)) { + if (res_id) + *res_id = t->type; + t = btf__type_by_id(btf, t->type); } + + return t; } /* @@ -1039,14 +1042,14 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, static bool get_map_field_int(const char *map_name, const struct btf *btf, const struct btf_type *def, const struct btf_member *m, __u32 *res) { - const struct btf_type *t = skip_mods_and_typedefs(btf, m->type); + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL); const char *name = btf__name_by_offset(btf, m->name_off); const struct btf_array *arr_info; const struct btf_type *arr_t; - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': attr '%s': expected PTR, got %u.\n", - map_name, name, BTF_INFO_KIND(t->info)); + map_name, name, btf_kind(t)); return false; } @@ -1056,12 +1059,12 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, map_name, name, t->type); return false; } - if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) { + if (!btf_is_array(arr_t)) { pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n", - map_name, name, BTF_INFO_KIND(arr_t->info)); + map_name, name, btf_kind(arr_t)); return false; } - arr_info = (const void *)(arr_t + 1); + arr_info = btf_array(arr_t); *res = arr_info->nelems; return true; } @@ -1079,11 +1082,11 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, struct bpf_map *map; int vlen, i; - vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx; + vi = btf_var_secinfos(sec) + var_idx; var = btf__type_by_id(obj->btf, vi->type); - var_extra = (const void *)(var + 1); + var_extra = btf_var(var); map_name = btf__name_by_offset(obj->btf, var->name_off); - vlen = BTF_INFO_VLEN(var->info); + vlen = btf_vlen(var); if (map_name == NULL || map_name[0] == '\0') { pr_warning("map #%d: empty name.\n", var_idx); @@ -1093,9 +1096,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_warning("map '%s' BTF data is corrupted.\n", map_name); return -EINVAL; } - if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) { + if (!btf_is_var(var)) { pr_warning("map '%s': unexpected var kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + map_name, btf_kind(var)); return -EINVAL; } if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && @@ -1105,10 +1108,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, return -EOPNOTSUPP; } - def = skip_mods_and_typedefs(obj->btf, var->type); - if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) { + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { pr_warning("map '%s': unexpected def kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + map_name, btf_kind(var)); return -EINVAL; } if (def->size > vi->size) { @@ -1131,8 +1134,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': at sec_idx %d, offset %zu.\n", map_name, map->sec_idx, map->sec_offset); - vlen = BTF_INFO_VLEN(def->info); - m = (const void *)(def + 1); + vlen = btf_vlen(def); + m = btf_members(def); for (i = 0; i < vlen; i++, m++) { const char *name = btf__name_by_offset(obj->btf, m->name_off); @@ -1182,9 +1185,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': key spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + map_name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -1225,9 +1228,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': value spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + map_name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -1288,7 +1291,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) nr_types = btf__get_nr_types(obj->btf); for (i = 1; i <= nr_types; i++) { t = btf__type_by_id(obj->btf, i); - if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) + if (!btf_is_datasec(t)) continue; name = btf__name_by_offset(obj->btf, t->name_off); if (strcmp(name, MAPS_ELF_SEC) == 0) { @@ -1302,7 +1305,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) return -ENOENT; } - vlen = BTF_INFO_VLEN(sec->info); + vlen = btf_vlen(sec); for (i = 0; i < vlen; i++) { err = bpf_object__init_user_btf_map(obj, sec, i, obj->efile.btf_maps_shndx, @@ -1363,16 +1366,14 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) struct btf *btf = obj->btf; struct btf_type *t; int i, j, vlen; - __u16 kind; if (!obj->btf || (has_func && has_datasec)) return; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - kind = BTF_INFO_KIND(t->info); - if (!has_datasec && kind == BTF_KIND_VAR) { + if (!has_datasec && btf_is_var(t)) { /* replace VAR with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* @@ -1381,11 +1382,11 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) * original variable took less than 4 bytes */ t->size = 1; - *(int *)(t+1) = BTF_INT_ENC(0, 0, 8); - } else if (!has_datasec && kind == BTF_KIND_DATASEC) { + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { /* replace DATASEC with STRUCT */ - struct btf_var_secinfo *v = (void *)(t + 1); - struct btf_member *m = (void *)(t + 1); + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); struct btf_type *vt; char *name; @@ -1396,7 +1397,7 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) name++; } - vlen = BTF_INFO_VLEN(t->info); + vlen = btf_vlen(t); t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); for (j = 0; j < vlen; j++, v++, m++) { /* order of field assignments is important */ @@ -1406,12 +1407,12 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) vt = (void *)btf__type_by_id(btf, v->type); m->name_off = vt->name_off; } - } else if (!has_func && kind == BTF_KIND_FUNC_PROTO) { + } else if (!has_func && btf_is_func_proto(t)) { /* replace FUNC_PROTO with ENUM */ - vlen = BTF_INFO_VLEN(t->info); + vlen = btf_vlen(t); t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); t->size = sizeof(__u32); /* kernel enforced */ - } else if (!has_func && kind == BTF_KIND_FUNC) { + } else if (!has_func && btf_is_func(t)) { /* replace FUNC with TYPEDEF */ t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); } @@ -1769,15 +1770,22 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, (long long) sym.st_value, sym.st_name, name); shdr_idx = sym.st_shndx; + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n", + insn_idx, shdr_idx); + + if (shdr_idx >= SHN_LORESERVE) { + pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n", + name, shdr_idx, insn_idx, + insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", prog->section_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { pr_warning("incorrect bpf_call opcode\n"); @@ -2288,6 +2296,894 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, return 0; } +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field byte offset represented by spec */ + __u32 offset; +}; + +static bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +/* + * Turn bpf_offset_reloc into a low- and high-level spec representation, + * validating correctness along the way, as well as calculating resulting + * field offset (in bytes), specified by accessor string. Low-level spec + * captures every single level of nestedness, including traversing anonymous + * struct/union members. High-level one only captures semantically meaningful + * "turning points": named fields and array indicies. + * E.g., for this case: + * + * struct sample { + * int __unimportant; + * struct { + * int __1; + * int __2; + * int a[7]; + * }; + * }; + * + * struct sample *s = ...; + * + * int x = &s->a[3]; // access string = '0:1:2:3' + * + * Low-level spec has 1:1 mapping with each element of access string (it's + * just a parsed access string representation): [0, 1, 2, 3]. + * + * High-level spec will capture only 3 points: + * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - field 'a' access (corresponds to '2' in low-level spec); + * - array element #3 access (corresponds to '3' in low-level spec). + * + */ +static int bpf_core_spec_parse(const struct btf *btf, + __u32 type_id, + const char *spec_str, + struct bpf_core_spec *spec) +{ + int access_idx, parsed_len, i; + const struct btf_type *t; + const char *name; + __u32 id; + __s64 sz; + + if (str_is_empty(spec_str) || *spec_str == ':') + return -EINVAL; + + memset(spec, 0, sizeof(*spec)); + spec->btf = btf; + + /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */ + while (*spec_str) { + if (*spec_str == ':') + ++spec_str; + if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1) + return -EINVAL; + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + spec_str += parsed_len; + spec->raw_spec[spec->raw_len++] = access_idx; + } + + if (spec->raw_len == 0) + return -EINVAL; + + /* first spec value is always reloc type array index */ + t = skip_mods_and_typedefs(btf, type_id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[0]; + spec->spec[0].type_id = id; + spec->spec[0].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->offset = access_idx * sz; + + for (i = 1; i < spec->raw_len; i++) { + t = skip_mods_and_typedefs(btf, id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[i]; + + if (btf_is_composite(t)) { + const struct btf_member *m; + __u32 offset; + + if (access_idx >= btf_vlen(t)) + return -EINVAL; + if (btf_member_bitfield_size(t, access_idx)) + return -EINVAL; + + offset = btf_member_bit_offset(t, access_idx); + if (offset % 8) + return -EINVAL; + spec->offset += offset / 8; + + m = btf_members(t) + access_idx; + if (m->name_off) { + name = btf__name_by_offset(btf, m->name_off); + if (str_is_empty(name)) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->spec[spec->len].name = name; + spec->len++; + } + + id = m->type; + } else if (btf_is_array(t)) { + const struct btf_array *a = btf_array(t); + + t = skip_mods_and_typedefs(btf, a->type, &id); + if (!t || access_idx >= a->nelems) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->offset += access_idx * sz; + } else { + pr_warning("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n", + type_id, spec_str, i, id, btf_kind(t)); + return -EINVAL; + } + } + + return 0; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +/* Given 'some_struct_name___with_flavor' return the length of a name prefix + * before last triple underscore. Struct name part after last triple + * underscore is ignored by BPF CO-RE relocation during relocation matching. + */ +static size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +/* dynamically sized list of type IDs */ +struct ids_vec { + __u32 *data; + int len; +}; + +static void bpf_core_free_cands(struct ids_vec *cand_ids) +{ + free(cand_ids->data); + free(cand_ids); +} + +static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, + __u32 local_type_id, + const struct btf *targ_btf) +{ + size_t local_essent_len, targ_essent_len; + const char *local_name, *targ_name; + const struct btf_type *t; + struct ids_vec *cand_ids; + __u32 *new_ids; + int i, err, n; + + t = btf__type_by_id(local_btf, local_type_id); + if (!t) + return ERR_PTR(-EINVAL); + + local_name = btf__name_by_offset(local_btf, t->name_off); + if (str_is_empty(local_name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_name); + + cand_ids = calloc(1, sizeof(*cand_ids)); + if (!cand_ids) + return ERR_PTR(-ENOMEM); + + n = btf__get_nr_types(targ_btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(targ_btf, i); + targ_name = btf__name_by_offset(targ_btf, t->name_off); + if (str_is_empty(targ_name)) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + + if (strncmp(local_name, targ_name, local_essent_len) == 0) { + pr_debug("[%d] %s: found candidate [%d] %s\n", + local_type_id, local_name, i, targ_name); + new_ids = realloc(cand_ids->data, cand_ids->len + 1); + if (!new_ids) { + err = -ENOMEM; + goto err_out; + } + cand_ids->data = new_ids; + cand_ids->data[cand_ids->len++] = i; + } + } + return cand_ids; +err_out: + bpf_core_free_cands(cand_ids); + return ERR_PTR(err); +} + +/* Check two types for compatibility, skipping const/volatile/restrict and + * typedefs, to ensure we are relocating offset to the compatible entities: + * - any two STRUCTs/UNIONs are compatible and can be mixed; + * - any two FWDs are compatible; + * - any two PTRs are always compatible; + * - for ENUMs, check sizes, names are ignored; + * - for INT, size and bitness should match, signedness is ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - everything else shouldn't be ever a target of relocation. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +static int bpf_core_fields_are_compat(const struct btf *local_btf, + __u32 local_id, + const struct btf *targ_btf, + __u32 targ_id) +{ + const struct btf_type *local_type, *targ_type; + +recur: + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_is_composite(local_type) && btf_is_composite(targ_type)) + return 1; + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_FWD: + case BTF_KIND_PTR: + return 1; + case BTF_KIND_ENUM: + return local_type->size == targ_type->size; + case BTF_KIND_INT: + return btf_int_offset(local_type) == 0 && + btf_int_offset(targ_type) == 0 && + local_type->size == targ_type->size && + btf_int_bits(local_type) == btf_int_bits(targ_type); + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + default: + pr_warning("unexpected kind %d relocated, local [%d], target [%d]\n", + btf_kind(local_type), local_id, targ_id); + return 0; + } +} + +/* + * Given single high-level named field accessor in local type, find + * corresponding high-level accessor for a target type. Along the way, + * maintain low-level spec for target as well. Also keep updating target + * offset. + * + * Searching is performed through recursive exhaustive enumeration of all + * fields of a struct/union. If there are any anonymous (embedded) + * structs/unions, they are recursively searched as well. If field with + * desired name is found, check compatibility between local and target types, + * before returning result. + * + * 1 is returned, if field is found. + * 0 is returned if no compatible field is found. + * <0 is returned on error. + */ +static int bpf_core_match_member(const struct btf *local_btf, + const struct bpf_core_accessor *local_acc, + const struct btf *targ_btf, + __u32 targ_id, + struct bpf_core_spec *spec, + __u32 *next_targ_id) +{ + const struct btf_type *local_type, *targ_type; + const struct btf_member *local_member, *m; + const char *local_name, *targ_name; + __u32 local_id; + int i, n, found; + + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!targ_type) + return -EINVAL; + if (!btf_is_composite(targ_type)) + return 0; + + local_id = local_acc->type_id; + local_type = btf__type_by_id(local_btf, local_id); + local_member = btf_members(local_type) + local_acc->idx; + local_name = btf__name_by_offset(local_btf, local_member->name_off); + + n = btf_vlen(targ_type); + m = btf_members(targ_type); + for (i = 0; i < n; i++, m++) { + __u32 offset; + + /* bitfield relocations not supported */ + if (btf_member_bitfield_size(targ_type, i)) + continue; + offset = btf_member_bit_offset(targ_type, i); + if (offset % 8) + continue; + + /* too deep struct/union/array nesting */ + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + /* speculate this member will be the good one */ + spec->offset += offset / 8; + spec->raw_spec[spec->raw_len++] = i; + + targ_name = btf__name_by_offset(targ_btf, m->name_off); + if (str_is_empty(targ_name)) { + /* embedded struct/union, we need to go deeper */ + found = bpf_core_match_member(local_btf, local_acc, + targ_btf, m->type, + spec, next_targ_id); + if (found) /* either found or error */ + return found; + } else if (strcmp(local_name, targ_name) == 0) { + /* matching named field */ + struct bpf_core_accessor *targ_acc; + + targ_acc = &spec->spec[spec->len++]; + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + + *next_targ_id = m->type; + found = bpf_core_fields_are_compat(local_btf, + local_member->type, + targ_btf, m->type); + if (!found) + spec->len--; /* pop accessor */ + return found; + } + /* member turned out not to be what we looked for */ + spec->offset -= offset / 8; + spec->raw_len--; + } + + return 0; +} + +/* + * Try to match local spec to a target type and, if successful, produce full + * target spec (high-level, low-level + offset). + */ +static int bpf_core_spec_match(struct bpf_core_spec *local_spec, + const struct btf *targ_btf, __u32 targ_id, + struct bpf_core_spec *targ_spec) +{ + const struct btf_type *targ_type; + const struct bpf_core_accessor *local_acc; + struct bpf_core_accessor *targ_acc; + int i, sz, matched; + + memset(targ_spec, 0, sizeof(*targ_spec)); + targ_spec->btf = targ_btf; + + local_acc = &local_spec->spec[0]; + targ_acc = &targ_spec->spec[0]; + + for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) { + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, + &targ_id); + if (!targ_type) + return -EINVAL; + + if (local_acc->name) { + matched = bpf_core_match_member(local_spec->btf, + local_acc, + targ_btf, targ_id, + targ_spec, &targ_id); + if (matched <= 0) + return matched; + } else { + /* for i=0, targ_id is already treated as array element + * type (because it's the original struct), for others + * we should find array element type first + */ + if (i > 0) { + const struct btf_array *a; + + if (!btf_is_array(targ_type)) + return 0; + + a = btf_array(targ_type); + if (local_acc->idx >= a->nelems) + return 0; + if (!skip_mods_and_typedefs(targ_btf, a->type, + &targ_id)) + return -EINVAL; + } + + /* too deep struct/union/array nesting */ + if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + targ_acc->type_id = targ_id; + targ_acc->idx = local_acc->idx; + targ_acc->name = NULL; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + + sz = btf__resolve_size(targ_btf, targ_id); + if (sz < 0) + return sz; + targ_spec->offset += local_acc->idx * sz; + } + } + + return 1; +} + +/* + * Patch relocatable BPF instruction. + * Expected insn->imm value is provided for validation, as well as the new + * relocated value. + * + * Currently three kinds of BPF instructions are supported: + * 1. rX = <imm> (assignment with immediate operand); + * 2. rX += <imm> (arithmetic operations with immediate operand); + * 3. *(rX) = <imm> (indirect memory assignment with immediate operand). + * + * If actual insn->imm value is wrong, bail out. + */ +static int bpf_core_reloc_insn(struct bpf_program *prog, int insn_off, + __u32 orig_off, __u32 new_off) +{ + struct bpf_insn *insn; + int insn_idx; + __u8 class; + + if (insn_off % sizeof(struct bpf_insn)) + return -EINVAL; + insn_idx = insn_off / sizeof(struct bpf_insn); + + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (insn->imm != orig_off) + return -EINVAL; + insn->imm = new_off; + pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n", + bpf_program__title(prog, false), + insn_idx, orig_off, new_off); + } else { + pr_warning("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), + insn_idx, insn->code, insn->src_reg, insn->dst_reg, + insn->off, insn->imm); + return -EINVAL; + } + return 0; +} + +static struct btf *btf_load_raw(const char *path) +{ + struct btf *btf; + size_t read_cnt; + struct stat st; + void *data; + FILE *f; + + if (stat(path, &st)) + return ERR_PTR(-errno); + + data = malloc(st.st_size); + if (!data) + return ERR_PTR(-ENOMEM); + + f = fopen(path, "rb"); + if (!f) { + btf = ERR_PTR(-errno); + goto cleanup; + } + + read_cnt = fread(data, 1, st.st_size, f); + fclose(f); + if (read_cnt < st.st_size) { + btf = ERR_PTR(-EBADF); + goto cleanup; + } + + btf = btf__new(data, read_cnt); + +cleanup: + free(data); + return btf; +} + +/* + * Probe few well-known locations for vmlinux kernel image and try to load BTF + * data out of it to use for target BTF. + */ +static struct btf *bpf_core_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, + /* fall back to trying to find vmlinux ELF on disk otherwise */ + { "/boot/vmlinux-%1$s" }, + { "/lib/modules/%1$s/vmlinux-%1$s" }, + { "/lib/modules/%1$s/build/vmlinux" }, + { "/usr/lib/modules/%1$s/kernel/vmlinux" }, + { "/usr/lib/debug/boot/vmlinux-%1$s" }, + { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, + { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warning("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} + +/* Output spec definition in the format: + * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, + * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b + */ +static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +{ + const struct btf_type *t; + const char *s; + __u32 type_id; + int i; + + type_id = spec->spec[0].type_id; + t = btf__type_by_id(spec->btf, type_id); + s = btf__name_by_offset(spec->btf, t->name_off); + libbpf_print(level, "[%u] %s + ", type_id, s); + + for (i = 0; i < spec->raw_len; i++) + libbpf_print(level, "%d%s", spec->raw_spec[i], + i == spec->raw_len - 1 ? " => " : ":"); + + libbpf_print(level, "%u @ &x", spec->offset); + + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + libbpf_print(level, ".%s", spec->spec[i].name); + else + libbpf_print(level, "[%u]", spec->spec[i].idx); + } + +} + +static size_t bpf_core_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +/* + * CO-RE relocate single instruction. + * + * The outline and important points of the algorithm: + * 1. For given local type, find corresponding candidate target types. + * Candidate type is a type with the same "essential" name, ignoring + * everything after last triple underscore (___). E.g., `sample`, + * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates + * for each other. Names with triple underscore are referred to as + * "flavors" and are useful, among other things, to allow to + * specify/support incompatible variations of the same kernel struct, which + * might differ between different kernel versions and/or build + * configurations. + * + * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C + * converter, when deduplicated BTF of a kernel still contains more than + * one different types with the same name. In that case, ___2, ___3, etc + * are appended starting from second name conflict. But start flavors are + * also useful to be defined "locally", in BPF program, to extract same + * data from incompatible changes between different kernel + * versions/configurations. For instance, to handle field renames between + * kernel versions, one can use two flavors of the struct name with the + * same common name and use conditional relocations to extract that field, + * depending on target kernel version. + * 2. For each candidate type, try to match local specification to this + * candidate target type. Matching involves finding corresponding + * high-level spec accessors, meaning that all named fields should match, + * as well as all array accesses should be within the actual bounds. Also, + * types should be compatible (see bpf_core_fields_are_compat for details). + * 3. It is supported and expected that there might be multiple flavors + * matching the spec. As long as all the specs resolve to the same set of + * offsets across all candidates, there is not error. If there is any + * ambiguity, CO-RE relocation will fail. This is necessary to accomodate + * imprefection of BTF deduplication, which can cause slight duplication of + * the same BTF type, if some directly or indirectly referenced (by + * pointer) type gets resolved to different actual types in different + * object files. If such situation occurs, deduplicated BTF will end up + * with two (or more) structurally identical types, which differ only in + * types they refer to through pointer. This should be OK in most cases and + * is not an error. + * 4. Candidate types search is performed by linearly scanning through all + * types in target BTF. It is anticipated that this is overall more + * efficient memory-wise and not significantly worse (if not better) + * CPU-wise compared to prebuilding a map from all local type names to + * a list of candidate type names. It's also sped up by caching resolved + * list of matching candidates per each local "root" type ID, that has at + * least one bpf_offset_reloc associated with it. This list is shared + * between multiple relocations for the same type ID and is updated as some + * of the candidates are pruned due to structural incompatibility. + */ +static int bpf_core_reloc_offset(struct bpf_program *prog, + const struct bpf_offset_reloc *relo, + int relo_idx, + const struct btf *local_btf, + const struct btf *targ_btf, + struct hashmap *cand_cache) +{ + const char *prog_name = bpf_program__title(prog, false); + struct bpf_core_spec local_spec, cand_spec, targ_spec; + const void *type_key = u32_as_hash_key(relo->type_id); + const struct btf_type *local_type, *cand_type; + const char *local_name, *cand_name; + struct ids_vec *cand_ids; + __u32 local_id, cand_id; + const char *spec_str; + int i, j, err; + + local_id = relo->type_id; + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) + return -EINVAL; + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(local_name)) + return -EINVAL; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + if (str_is_empty(spec_str)) + return -EINVAL; + + err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec); + if (err) { + pr_warning("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n", + prog_name, relo_idx, local_id, local_name, spec_str, + err); + return -EINVAL; + } + + pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx); + bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + libbpf_print(LIBBPF_DEBUG, "\n"); + + if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { + cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); + if (IS_ERR(cand_ids)) { + pr_warning("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld", + prog_name, relo_idx, local_id, local_name, + PTR_ERR(cand_ids)); + return PTR_ERR(cand_ids); + } + err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); + if (err) { + bpf_core_free_cands(cand_ids); + return err; + } + } + + for (i = 0, j = 0; i < cand_ids->len; i++) { + cand_id = cand_ids->data[i]; + cand_type = btf__type_by_id(targ_btf, cand_id); + cand_name = btf__name_by_offset(targ_btf, cand_type->name_off); + + err = bpf_core_spec_match(&local_spec, targ_btf, + cand_id, &cand_spec); + pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ", + prog_name, relo_idx, i, cand_name); + bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + libbpf_print(LIBBPF_DEBUG, ": %d\n", err); + if (err < 0) { + pr_warning("prog '%s': relo #%d: matching error: %d\n", + prog_name, relo_idx, err); + return err; + } + if (err == 0) + continue; + + if (j == 0) { + targ_spec = cand_spec; + } else if (cand_spec.offset != targ_spec.offset) { + /* if there are many candidates, they should all + * resolve to the same offset + */ + pr_warning("prog '%s': relo #%d: offset ambiguity: %u != %u\n", + prog_name, relo_idx, cand_spec.offset, + targ_spec.offset); + return -EINVAL; + } + + cand_ids->data[j++] = cand_spec.spec[0].type_id; + } + + cand_ids->len = j; + if (cand_ids->len == 0) { + pr_warning("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); + return -ESRCH; + } + + err = bpf_core_reloc_insn(prog, relo->insn_off, + local_spec.offset, targ_spec.offset); + if (err) { + pr_warning("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", + prog_name, relo_idx, relo->insn_off, err); + return -EINVAL; + } + + return 0; +} + +static int +bpf_core_reloc_offsets(struct bpf_object *obj, const char *targ_btf_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_offset_reloc *rec; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct bpf_program *prog; + struct btf *targ_btf; + const char *sec_name; + int i, err = 0; + + if (targ_btf_path) + targ_btf = btf__parse_elf(targ_btf_path, NULL); + else + targ_btf = bpf_core_find_kernel_btf(); + if (IS_ERR(targ_btf)) { + pr_warning("failed to get target BTF: %ld\n", + PTR_ERR(targ_btf)); + return PTR_ERR(targ_btf); + } + + cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &obj->btf_ext->offset_reloc_info; + for_each_btf_ext_sec(seg, sec) { + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) { + err = -EINVAL; + goto out; + } + prog = bpf_object__find_program_by_title(obj, sec_name); + if (!prog) { + pr_warning("failed to find program '%s' for CO-RE offset relocation\n", + sec_name); + err = -EINVAL; + goto out; + } + + pr_debug("prog '%s': performing %d CO-RE offset relocs\n", + sec_name, sec->num_info); + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = bpf_core_reloc_offset(prog, rec, i, obj->btf, + targ_btf, cand_cache); + if (err) { + pr_warning("prog '%s': relo #%d: failed to relocate: %d\n", + sec_name, i, err); + goto out; + } + } + } + +out: + btf__free(targ_btf); + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + return err; +} + +static int +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) +{ + int err = 0; + + if (obj->btf_ext->offset_reloc_info.len) + err = bpf_core_reloc_offsets(obj, targ_btf_path); + + return err; +} + static int bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, struct reloc_desc *relo) @@ -2395,14 +3291,21 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; } - static int -bpf_object__relocate(struct bpf_object *obj) +bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; size_t i; int err; + if (obj->btf_ext) { + err = bpf_object__relocate_core(obj, targ_btf_path); + if (err) { + pr_warning("failed to perform CO-RE relocations: %d\n", + err); + return err; + } + } for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; @@ -2808,7 +3711,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) obj->loaded = true; CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj), err, out); + CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); return 0; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 5cbf459ece0b..e8f70977d137 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -57,7 +57,7 @@ enum libbpf_print_level { typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, const char *, va_list ap); -LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn); +LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ struct bpf_object; @@ -92,6 +92,7 @@ LIBBPF_API void bpf_object__close(struct bpf_object *object); struct bpf_object_load_attr { struct bpf_object *obj; int log_level; + const char *target_btf_path; }; /* Load/unload object into/from kernel */ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 2ac29bd36226..2e83a34f8c79 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -29,6 +29,10 @@ #ifndef max # define max(x, y) ((x) < (y) ? (y) : (x)) #endif +#ifndef offsetofend +# define offsetofend(TYPE, FIELD) \ + (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) +#endif extern void libbpf_print(enum libbpf_print_level level, const char *format, ...) @@ -46,4 +50,105 @@ do { \ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +struct btf_ext_info { + /* + * info points to the individual info section (e.g. func_info and + * line_info) from the .BTF.ext. It does not include the __u32 rec_size. + */ + void *info; + __u32 rec_size; + __u32 len; +}; + +#define for_each_btf_ext_sec(seg, sec) \ + for (sec = (seg)->info; \ + (void *)sec < (seg)->info + (seg)->len; \ + sec = (void *)sec + sizeof(struct btf_ext_info_sec) + \ + (seg)->rec_size * sec->num_info) + +#define for_each_btf_ext_rec(seg, sec, i, rec) \ + for (i = 0, rec = (void *)&(sec)->data; \ + i < (sec)->num_info; \ + i++, rec = (void *)rec + (seg)->rec_size) + +struct btf_ext { + union { + struct btf_ext_header *hdr; + void *data; + }; + struct btf_ext_info func_info; + struct btf_ext_info line_info; + struct btf_ext_info offset_reloc_info; + __u32 data_size; +}; + +struct btf_ext_info_sec { + __u32 sec_name_off; + __u32 num_info; + /* Followed by num_info * record_size number of bytes */ + __u8 data[0]; +}; + +/* The minimum bpf_func_info checked by the loader */ +struct bpf_func_info_min { + __u32 insn_off; + __u32 type_id; +}; + +/* The minimum bpf_line_info checked by the loader */ +struct bpf_line_info_min { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +/* The minimum bpf_offset_reloc checked by the loader + * + * Offset relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual offset; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * offset; + * - access_str_off - offset into corresponding .BTF string section. String + * itself encodes an accessed field using a sequence of field and array + * indicies, separated by colon (:). It's conceptually very close to LLVM's + * getelementptr ([0]) instruction's arguments for identifying offset to + * a field. + * + * Example to provide a better feel. + * + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int x = &s->a; // encoded as "0:0" (a is field #0) + * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit offset relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_offset_reloc { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; +}; + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index ace1a0708d99..4b0b0364f5fc 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -244,6 +244,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_XSKMAP: diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c085964e1d05..29001f944db7 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -236,18 +236,12 @@ PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h PROG_TESTS_FILES := $(wildcard prog_tests/*.c) test_progs.c: $(PROG_TESTS_H) $(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) -$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES) +$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_FILES) | $(PROG_TESTS_H) $(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR) $(shell ( cd prog_tests/; \ echo '/* Generated header, do not edit */'; \ - echo '#ifdef DECLARE'; \ ls *.c 2> /dev/null | \ - sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \ - echo '#endif'; \ - echo '#ifdef CALL'; \ - ls *.c 2> /dev/null | \ - sed -e 's@\([^\.]*\)\.c@test_\1();@'; \ - echo '#endif' \ + sed -e 's@\([^\.]*\)\.c@DEFINE_TEST(\1)@'; \ ) > $(PROG_TESTS_H)) MAP_TESTS_DIR = $(OUTPUT)/map_tests @@ -257,7 +251,7 @@ MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h MAP_TESTS_FILES := $(wildcard map_tests/*.c) test_maps.c: $(MAP_TESTS_H) $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS) -$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES) +$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_FILES) | $(MAP_TESTS_H) $(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR) $(shell ( cd map_tests/; \ echo '/* Generated header, do not edit */'; \ @@ -278,7 +272,7 @@ VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h VERIFIER_TEST_FILES := $(wildcard verifier/*.c) test_verifier.c: $(VERIFIER_TESTS_H) $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) -$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H) +$(OUTPUT)/test_verifier: test_verifier.c | $(VERIFIER_TEST_FILES) $(VERIFIER_TESTS_H) $(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR) $(shell ( cd verifier/; \ echo '/* Generated header, do not edit */'; \ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index f804f210244e..8b503ea142f0 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -228,6 +228,9 @@ static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk, static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) = (void *)BPF_FUNC_sk_storage_delete; static int (*bpf_send_signal)(unsigned sig) = (void *)BPF_FUNC_send_signal; +static long long (*bpf_tcp_gen_syncookie)(struct bpf_sock *sk, void *ip, + int ip_len, void *tcp, int tcp_len) = + (void *) BPF_FUNC_tcp_gen_syncookie; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -501,4 +504,24 @@ struct pt_regs; (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) #endif +/* + * BPF_CORE_READ abstracts away bpf_probe_read() call and captures offset + * relocation for source address using __builtin_preserve_access_index() + * built-in, provided by Clang. + * + * __builtin_preserve_access_index() takes as an argument an expression of + * taking an address of a field within struct/union. It makes compiler emit + * a relocation, which records BTF type ID describing root struct/union and an + * accessor string which describes exact embedded field that was used to take + * an address. See detailed description of this relocation format and + * semantics in comments to struct bpf_offset_reloc in libbpf_internal.h. + * + * This relocation allows libbpf to adjust BPF instruction to use correct + * actual field offset, based on target kernel BTF type that matches original + * (local) BTF, used to record relocation. + */ +#define BPF_CORE_READ(dst, src) \ + bpf_probe_read((dst), sizeof(*(src)), \ + __builtin_preserve_access_index(src)) + #endif diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index cb827383db4d..fb5840a62548 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -106,8 +106,8 @@ void test_bpf_obj_id(void) if (CHECK(err || prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || info_len != sizeof(struct bpf_prog_info) || - (jit_enabled && !prog_infos[i].jited_prog_len) || - (jit_enabled && + (env.jit_enabled && !prog_infos[i].jited_prog_len) || + (env.jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))) || !prog_infos[i].xlated_prog_len || !memcmp(xlated_insns, zeros, sizeof(zeros)) || @@ -121,7 +121,7 @@ void test_bpf_obj_id(void) err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), - jit_enabled, + env.jit_enabled, prog_infos[i].jited_prog_len, prog_infos[i].xlated_prog_len, !!memcmp(jited_insns, zeros, sizeof(zeros)), diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index e1b55261526f..1a1eae356f81 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -4,12 +4,15 @@ static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { - if (level != LIBBPF_DEBUG) - return vfprintf(stderr, format, args); + if (level != LIBBPF_DEBUG) { + vprintf(format, args); + return 0; + } if (!strstr(format, "verifier log")) return 0; - return vfprintf(stderr, "%s", args); + vprintf("%s", args); + return 0; } static int check_load(const char *file, enum bpf_prog_type type) @@ -30,14 +33,25 @@ static int check_load(const char *file, enum bpf_prog_type type) return err; } +struct scale_test_def { + const char *file; + enum bpf_prog_type attach_type; + bool fails; +}; + void test_bpf_verif_scale(void) { - const char *sched_cls[] = { - "./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o", - }; - const char *raw_tp[] = { + struct scale_test_def tests[] = { + { "loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */ }, + + { "test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS }, + { "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS }, + { "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS }, + /* full unroll by llvm */ - "./pyperf50.o", "./pyperf100.o", "./pyperf180.o", + { "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* partial unroll. llvm will unroll loop ~150 times. * C loop count -> 600. @@ -45,7 +59,7 @@ void test_bpf_verif_scale(void) * 16k insns in loop body. * Total of 5 such loops. Total program size ~82k insns. */ - "./pyperf600.o", + { "pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* no unroll at all. * C loop count -> 600. @@ -53,48 +67,52 @@ void test_bpf_verif_scale(void) * ~110 insns in loop body. * Total of 5 such loops. Total program size ~1500 insns. */ - "./pyperf600_nounroll.o", + { "pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - "./loop1.o", "./loop2.o", + { "loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "loop4.o", BPF_PROG_TYPE_SCHED_CLS }, + { "loop5.o", BPF_PROG_TYPE_SCHED_CLS }, /* partial unroll. 19k insn in a loop. * Total program size 20.8k insn. * ~350k processed_insns */ - "./strobemeta.o", + { "strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* no unroll, tiny loops */ - "./strobemeta_nounroll1.o", - "./strobemeta_nounroll2.o", - }; - const char *cg_sysctl[] = { - "./test_sysctl_loop1.o", "./test_sysctl_loop2.o", - }; - int err, i; + { "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - if (verifier_stats) - libbpf_set_print(libbpf_debug_print); + { "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, + { "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, - err = check_load("./loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:loop3:%s\n", err ? (error_cnt--, "OK") : "FAIL"); + { "test_xdp_loop.o", BPF_PROG_TYPE_XDP }, + { "test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL }, + }; + libbpf_print_fn_t old_print_fn = NULL; + int err, i; - for (i = 0; i < ARRAY_SIZE(sched_cls); i++) { - err = check_load(sched_cls[i], BPF_PROG_TYPE_SCHED_CLS); - printf("test_scale:%s:%s\n", sched_cls[i], err ? "FAIL" : "OK"); + if (env.verifier_stats) { + test__force_log(); + old_print_fn = libbpf_set_print(libbpf_debug_print); } - for (i = 0; i < ARRAY_SIZE(raw_tp); i++) { - err = check_load(raw_tp[i], BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:%s:%s\n", raw_tp[i], err ? "FAIL" : "OK"); - } + for (i = 0; i < ARRAY_SIZE(tests); i++) { + const struct scale_test_def *test = &tests[i]; + + if (!test__start_subtest(test->file)) + continue; - for (i = 0; i < ARRAY_SIZE(cg_sysctl); i++) { - err = check_load(cg_sysctl[i], BPF_PROG_TYPE_CGROUP_SYSCTL); - printf("test_scale:%s:%s\n", cg_sysctl[i], err ? "FAIL" : "OK"); + err = check_load(test->file, test->attach_type); + if (test->fails) { /* expected to fail */ + if (err) + error_cnt--; + else + error_cnt++; + } } - err = check_load("./test_xdp_loop.o", BPF_PROG_TYPE_XDP); - printf("test_scale:test_xdp_loop:%s\n", err ? "FAIL" : "OK"); - err = check_load("./test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL); - printf("test_scale:test_seg6_loop:%s\n", err ? "FAIL" : "OK"); + if (env.verifier_stats) + libbpf_set_print(old_print_fn); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c new file mode 100644 index 000000000000..f3863f976a48 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "progs/core_reloc_types.h" + +#define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name) + +#define FLAVORS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = 42, \ + .b = 0xc001, \ + .c = 0xbeef, \ +} + +#define FLAVORS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_flavors.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" \ + +#define FLAVORS_CASE(name) { \ + FLAVORS_CASE_COMMON(name), \ + .input = FLAVORS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = FLAVORS_DATA(core_reloc_flavors), \ + .output_len = sizeof(struct core_reloc_flavors), \ +} + +#define FLAVORS_ERR_CASE(name) { \ + FLAVORS_CASE_COMMON(name), \ + .fails = true, \ +} + +#define NESTING_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = { .a = { .a = 42 } }, \ + .b = { .b = { .b = 0xc001 } }, \ +} + +#define NESTING_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_nesting.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define NESTING_CASE(name) { \ + NESTING_CASE_COMMON(name), \ + .input = NESTING_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = NESTING_DATA(core_reloc_nesting), \ + .output_len = sizeof(struct core_reloc_nesting) \ +} + +#define NESTING_ERR_CASE(name) { \ + NESTING_CASE_COMMON(name), \ + .fails = true, \ +} + +#define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = { [2] = 1 }, \ + .b = { [1] = { [2] = { [3] = 2 } } }, \ + .c = { [1] = { .c = 3 } }, \ + .d = { [0] = { [0] = { .d = 4 } } }, \ +} + +#define ARRAYS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_arrays.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define ARRAYS_CASE(name) { \ + ARRAYS_CASE_COMMON(name), \ + .input = ARRAYS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) { \ + .a2 = 1, \ + .b123 = 2, \ + .c1c = 3, \ + .d00d = 4, \ + }, \ + .output_len = sizeof(struct core_reloc_arrays_output) \ +} + +#define ARRAYS_ERR_CASE(name) { \ + ARRAYS_CASE_COMMON(name), \ + .fails = true, \ +} + +#define PRIMITIVES_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = 1, \ + .b = 2, \ + .c = 3, \ + .d = (void *)4, \ + .f = (void *)5, \ +} + +#define PRIMITIVES_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_primitives.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define PRIMITIVES_CASE(name) { \ + PRIMITIVES_CASE_COMMON(name), \ + .input = PRIMITIVES_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = PRIMITIVES_DATA(core_reloc_primitives), \ + .output_len = sizeof(struct core_reloc_primitives), \ +} + +#define PRIMITIVES_ERR_CASE(name) { \ + PRIMITIVES_CASE_COMMON(name), \ + .fails = true, \ +} + +#define MODS_CASE(name) { \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_mods.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .input = STRUCT_TO_CHAR_PTR(core_reloc_##name) { \ + .a = 1, \ + .b = 2, \ + .c = (void *)3, \ + .d = (void *)4, \ + .e = { [2] = 5 }, \ + .f = { [1] = 6 }, \ + .g = { .x = 7 }, \ + .h = { .y = 8 }, \ + }, \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_mods_output) { \ + .a = 1, .b = 2, .c = 3, .d = 4, \ + .e = 5, .f = 6, .g = 7, .h = 8, \ + }, \ + .output_len = sizeof(struct core_reloc_mods_output), \ +} + +#define PTR_AS_ARR_CASE(name) { \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_ptr_as_arr.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .input = (const char *)&(struct core_reloc_##name []){ \ + { .a = 1 }, \ + { .a = 2 }, \ + { .a = 3 }, \ + }, \ + .input_len = 3 * sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_ptr_as_arr) { \ + .a = 3, \ + }, \ + .output_len = sizeof(struct core_reloc_ptr_as_arr), \ +} + +#define INTS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .u8_field = 1, \ + .s8_field = 2, \ + .u16_field = 3, \ + .s16_field = 4, \ + .u32_field = 5, \ + .s32_field = 6, \ + .u64_field = 7, \ + .s64_field = 8, \ +} + +#define INTS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_ints.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define INTS_CASE(name) { \ + INTS_CASE_COMMON(name), \ + .input = INTS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = INTS_DATA(core_reloc_ints), \ + .output_len = sizeof(struct core_reloc_ints), \ +} + +#define INTS_ERR_CASE(name) { \ + INTS_CASE_COMMON(name), \ + .fails = true, \ +} + +struct core_reloc_test_case { + const char *case_name; + const char *bpf_obj_file; + const char *btf_src_file; + const char *input; + int input_len; + const char *output; + int output_len; + bool fails; +}; + +static struct core_reloc_test_case test_cases[] = { + /* validate we can find kernel image and use its BTF for relocs */ + { + .case_name = "kernel", + .bpf_obj_file = "test_core_reloc_kernel.o", + .btf_src_file = NULL, /* load from /lib/modules/$(uname -r) */ + .input = "", + .input_len = 0, + .output = "\1", /* true */ + .output_len = 1, + }, + + /* validate BPF program can use multiple flavors to match against + * single target BTF type + */ + FLAVORS_CASE(flavors), + + FLAVORS_ERR_CASE(flavors__err_wrong_name), + + /* various struct/enum nesting and resolution scenarios */ + NESTING_CASE(nesting), + NESTING_CASE(nesting___anon_embed), + NESTING_CASE(nesting___struct_union_mixup), + NESTING_CASE(nesting___extra_nesting), + NESTING_CASE(nesting___dup_compat_types), + + NESTING_ERR_CASE(nesting___err_missing_field), + NESTING_ERR_CASE(nesting___err_array_field), + NESTING_ERR_CASE(nesting___err_missing_container), + NESTING_ERR_CASE(nesting___err_nonstruct_container), + NESTING_ERR_CASE(nesting___err_array_container), + NESTING_ERR_CASE(nesting___err_dup_incompat_types), + NESTING_ERR_CASE(nesting___err_partial_match_dups), + NESTING_ERR_CASE(nesting___err_too_deep), + + /* various array access relocation scenarios */ + ARRAYS_CASE(arrays), + ARRAYS_CASE(arrays___diff_arr_dim), + ARRAYS_CASE(arrays___diff_arr_val_sz), + + ARRAYS_ERR_CASE(arrays___err_too_small), + ARRAYS_ERR_CASE(arrays___err_too_shallow), + ARRAYS_ERR_CASE(arrays___err_non_array), + ARRAYS_ERR_CASE(arrays___err_wrong_val_type1), + ARRAYS_ERR_CASE(arrays___err_wrong_val_type2), + + /* enum/ptr/int handling scenarios */ + PRIMITIVES_CASE(primitives), + PRIMITIVES_CASE(primitives___diff_enum_def), + PRIMITIVES_CASE(primitives___diff_func_proto), + PRIMITIVES_CASE(primitives___diff_ptr_type), + + PRIMITIVES_ERR_CASE(primitives___err_non_enum), + PRIMITIVES_ERR_CASE(primitives___err_non_int), + PRIMITIVES_ERR_CASE(primitives___err_non_ptr), + + /* const/volatile/restrict and typedefs scenarios */ + MODS_CASE(mods), + MODS_CASE(mods___mod_swap), + MODS_CASE(mods___typedefs), + + /* handling "ptr is an array" semantics */ + PTR_AS_ARR_CASE(ptr_as_arr), + PTR_AS_ARR_CASE(ptr_as_arr___diff_sz), + + /* int signedness/sizing/bitfield handling */ + INTS_CASE(ints), + INTS_CASE(ints___bool), + INTS_CASE(ints___reverse_sign), + + INTS_ERR_CASE(ints___err_bitfield), + INTS_ERR_CASE(ints___err_wrong_sz_8), + INTS_ERR_CASE(ints___err_wrong_sz_16), + INTS_ERR_CASE(ints___err_wrong_sz_32), + INTS_ERR_CASE(ints___err_wrong_sz_64), + + /* validate edge cases of capturing relocations */ + { + .case_name = "misc", + .bpf_obj_file = "test_core_reloc_misc.o", + .btf_src_file = "btf__core_reloc_misc.o", + .input = (const char *)&(struct core_reloc_misc_extensible[]){ + { .a = 1 }, + { .a = 2 }, /* not read */ + { .a = 3 }, + }, + .input_len = 4 * sizeof(int), + .output = STRUCT_TO_CHAR_PTR(core_reloc_misc_output) { + .a = 1, + .b = 1, + .c = 0, /* BUG in clang, should be 3 */ + }, + .output_len = sizeof(struct core_reloc_misc_output), + }, +}; + +struct data { + char in[256]; + char out[256]; +}; + +void test_core_reloc(void) +{ + const char *probe_name = "raw_tracepoint/sys_enter"; + struct bpf_object_load_attr load_attr = {}; + struct core_reloc_test_case *test_case; + int err, duration = 0, i, equal; + struct bpf_link *link = NULL; + struct bpf_map *data_map; + struct bpf_program *prog; + struct bpf_object *obj; + const int zero = 0; + struct data data; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + test_case = &test_cases[i]; + + if (!test__start_subtest(test_case->case_name)) + continue; + + obj = bpf_object__open(test_case->bpf_obj_file); + if (CHECK(IS_ERR_OR_NULL(obj), "obj_open", + "failed to open '%s': %ld\n", + test_case->bpf_obj_file, PTR_ERR(obj))) + continue; + + prog = bpf_object__find_program_by_title(obj, probe_name); + if (CHECK(!prog, "find_probe", + "prog '%s' not found\n", probe_name)) + goto cleanup; + bpf_program__set_type(prog, BPF_PROG_TYPE_RAW_TRACEPOINT); + + load_attr.obj = obj; + load_attr.log_level = 0; + load_attr.target_btf_path = test_case->btf_src_file; + err = bpf_object__load_xattr(&load_attr); + if (test_case->fails) { + CHECK(!err, "obj_load_fail", + "should fail to load prog '%s'\n", probe_name); + goto cleanup; + } else { + if (CHECK(err, "obj_load", + "failed to load prog '%s': %d\n", + probe_name, err)) + goto cleanup; + } + + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", + PTR_ERR(link))) + goto cleanup; + + data_map = bpf_object__find_map_by_name(obj, "test_cor.bss"); + if (CHECK(!data_map, "find_data_map", "data map not found\n")) + goto cleanup; + + memset(&data, 0, sizeof(data)); + memcpy(data.in, test_case->input, test_case->input_len); + + err = bpf_map_update_elem(bpf_map__fd(data_map), + &zero, &data, 0); + if (CHECK(err, "update_data_map", + "failed to update .data map: %d\n", err)) + goto cleanup; + + /* trigger test run */ + usleep(1); + + err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &data); + if (CHECK(err, "get_result", + "failed to get output data: %d\n", err)) + goto cleanup; + + equal = memcmp(data.out, test_case->output, + test_case->output_len) == 0; + if (CHECK(!equal, "check_result", + "input/output data don't match\n")) { + int j; + + for (j = 0; j < test_case->input_len; j++) { + printf("input byte #%d: 0x%02hhx\n", + j, test_case->input[j]); + } + for (j = 0; j < test_case->output_len; j++) { + printf("output byte #%d: EXP 0x%02hhx GOT 0x%02hhx\n", + j, test_case->output[j], data.out[j]); + } + goto cleanup; + } + +cleanup: + if (!IS_ERR_OR_NULL(link)) { + bpf_link__destroy(link); + link = NULL; + } + bpf_object__close(obj); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index c938283ac232..6892b88ae065 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -5,6 +5,10 @@ #include <linux/if_tun.h> #include <sys/uio.h> +#ifndef IP_MF +#define IP_MF 0x2000 +#endif + #define CHECK_FLOW_KEYS(desc, got, expected) \ CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ desc, \ @@ -16,6 +20,7 @@ "is_encap=%u/%u " \ "ip_proto=0x%x/0x%x " \ "n_proto=0x%x/0x%x " \ + "flow_label=0x%x/0x%x " \ "sport=%u/%u " \ "dport=%u/%u\n", \ got.nhoff, expected.nhoff, \ @@ -26,6 +31,7 @@ got.is_encap, expected.is_encap, \ got.ip_proto, expected.ip_proto, \ got.n_proto, expected.n_proto, \ + got.flow_label, expected.flow_label, \ got.sport, expected.sport, \ got.dport, expected.dport) @@ -35,6 +41,13 @@ struct ipv4_pkt { struct tcphdr tcp; } __packed; +struct ipip_pkt { + struct ethhdr eth; + struct iphdr iph; + struct iphdr iph_inner; + struct tcphdr tcp; +} __packed; + struct svlan_ipv4_pkt { struct ethhdr eth; __u16 vlan_tci; @@ -49,6 +62,18 @@ struct ipv6_pkt { struct tcphdr tcp; } __packed; +struct ipv6_frag_pkt { + struct ethhdr eth; + struct ipv6hdr iph; + struct frag_hdr { + __u8 nexthdr; + __u8 reserved; + __be16 frag_off; + __be32 identification; + } ipf; + struct tcphdr tcp; +} __packed; + struct dvlan_ipv6_pkt { struct ethhdr eth; __u16 vlan_tci; @@ -64,10 +89,13 @@ struct test { union { struct ipv4_pkt ipv4; struct svlan_ipv4_pkt svlan_ipv4; + struct ipip_pkt ipip; struct ipv6_pkt ipv6; + struct ipv6_frag_pkt ipv6_frag; struct dvlan_ipv6_pkt dvlan_ipv6; } pkt; struct bpf_flow_keys keys; + __u32 flags; }; #define VLAN_HLEN 4 @@ -81,6 +109,8 @@ struct test tests[] = { .iph.protocol = IPPROTO_TCP, .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN, @@ -88,6 +118,8 @@ struct test tests[] = { .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), + .sport = 80, + .dport = 8080, }, }, { @@ -97,6 +129,8 @@ struct test tests[] = { .iph.nexthdr = IPPROTO_TCP, .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN, @@ -104,6 +138,8 @@ struct test tests[] = { .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, }, }, { @@ -115,6 +151,8 @@ struct test tests[] = { .iph.protocol = IPPROTO_TCP, .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN + VLAN_HLEN, @@ -122,6 +160,8 @@ struct test tests[] = { .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), + .sport = 80, + .dport = 8080, }, }, { @@ -133,6 +173,8 @@ struct test tests[] = { .iph.nexthdr = IPPROTO_TCP, .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN + VLAN_HLEN * 2, @@ -141,8 +183,206 @@ struct test tests[] = { .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, }, }, + { + .name = "ipv4-frag", + .pkt.ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.frag_off = __bpf_constant_htons(IP_MF), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_frag = true, + .is_first_frag = true, + .sport = 80, + .dport = 8080, + }, + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + }, + { + .name = "ipv4-no-frag", + .pkt.ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.frag_off = __bpf_constant_htons(IP_MF), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_frag = true, + .is_first_frag = true, + }, + }, + { + .name = "ipv6-frag", + .pkt.ipv6_frag = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_FRAGMENT, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .ipf.nexthdr = IPPROTO_TCP, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr) + + sizeof(struct frag_hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .is_frag = true, + .is_first_frag = true, + .sport = 80, + .dport = 8080, + }, + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + }, + { + .name = "ipv6-no-frag", + .pkt.ipv6_frag = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_FRAGMENT, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .ipf.nexthdr = IPPROTO_TCP, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr) + + sizeof(struct frag_hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .is_frag = true, + .is_first_frag = true, + }, + }, + { + .name = "ipv6-flow-label", + .pkt.ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.flow_lbl = { 0xb, 0xee, 0xef }, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, + .flow_label = __bpf_constant_htonl(0xbeeef), + }, + }, + { + .name = "ipv6-no-flow-label", + .pkt.ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.flow_lbl = { 0xb, 0xee, 0xef }, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .flow_label = __bpf_constant_htonl(0xbeeef), + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, + }, + { + .name = "ipip-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_IPIP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES) - + sizeof(struct iphdr), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = 0, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr) + + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + .sport = 80, + .dport = 8080, + }, + }, + { + .name = "ipip-no-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_IPIP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES) - + sizeof(struct iphdr), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_IPIP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + }, }; static int create_tap(const char *ifname) @@ -225,6 +465,13 @@ void test_flow_dissector(void) .data_size_in = sizeof(tests[i].pkt), .data_out = &flow_keys, }; + static struct bpf_flow_keys ctx = {}; + + if (tests[i].flags) { + tattr.ctx_in = &ctx; + tattr.ctx_size_in = sizeof(ctx); + ctx.flags = tests[i].flags; + } err = bpf_prog_test_run_xattr(&tattr); CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || @@ -251,9 +498,20 @@ void test_flow_dissector(void) CHECK(err, "ifup", "err %d errno %d\n", err, errno); for (i = 0; i < ARRAY_SIZE(tests); i++) { - struct bpf_flow_keys flow_keys = {}; + /* Keep in sync with 'flags' from eth_get_headlen. */ + __u32 eth_get_headlen_flags = + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; struct bpf_prog_test_run_attr tattr = {}; - __u32 key = 0; + struct bpf_flow_keys flow_keys = {}; + __u32 key = (__u32)(tests[i].keys.sport) << 16 | + tests[i].keys.dport; + + /* For skb-less case we can't pass input flags; run + * only the tests that have a matching set of flags. + */ + + if (tests[i].flags != eth_get_headlen_flags) + continue; err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); @@ -263,6 +521,9 @@ void test_flow_dissector(void) CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + + err = bpf_map_delete_elem(keys_fd, &key); + CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err); } bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index c2a0a9d5591b..3d59b3c841fe 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -1,8 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <pthread.h> +#include <sched.h> +#include <sys/socket.h> #include <test_progs.h> #define MAX_CNT_RAWTP 10ull #define MAX_STACK_RAWTP 100 + +static int duration = 0; + struct get_stack_trace_t { int pid; int kern_stack_size; @@ -13,7 +20,7 @@ struct get_stack_trace_t { struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; }; -static int get_stack_print_output(void *data, int size) +static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) { bool good_kern_stack = false, good_user_stack = false; const char *nonjit_func = "___bpf_prog_run"; @@ -34,7 +41,7 @@ static int get_stack_print_output(void *data, int size) * just assume it is good if the stack is not empty. * This could be improved in the future. */ - if (jit_enabled) { + if (env.jit_enabled) { found = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { @@ -51,7 +58,7 @@ static int get_stack_print_output(void *data, int size) } } else { num_stack = e->kern_stack_size / sizeof(__u64); - if (jit_enabled) { + if (env.jit_enabled) { good_kern_stack = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { @@ -65,75 +72,76 @@ static int get_stack_print_output(void *data, int size) if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) good_user_stack = true; } - if (!good_kern_stack || !good_user_stack) - return LIBBPF_PERF_EVENT_ERROR; - if (cnt == MAX_CNT_RAWTP) - return LIBBPF_PERF_EVENT_DONE; - - return LIBBPF_PERF_EVENT_CONT; + if (!good_kern_stack) + CHECK(!good_kern_stack, "kern_stack", "corrupted kernel stack\n"); + if (!good_user_stack) + CHECK(!good_user_stack, "user_stack", "corrupted user stack\n"); } void test_get_stack_raw_tp(void) { const char *file = "./test_get_stack_rawtp.o"; - int i, efd, err, prog_fd, pmu_fd, perfmap_fd; - struct perf_event_attr attr = {}; + const char *prog_name = "raw_tracepoint/sys_enter"; + int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP; + struct perf_buffer_opts pb_opts = {}; + struct perf_buffer *pb = NULL; + struct bpf_link *link = NULL; struct timespec tv = {0, 10}; - __u32 key = 0, duration = 0; + struct bpf_program *prog; struct bpf_object *obj; + struct bpf_map *map; + cpu_set_t cpu_set; err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) return; - efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); - if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + prog = bpf_object__find_program_by_title(obj, prog_name); + if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) goto close_prog; - perfmap_fd = bpf_find_map(__func__, obj, "perfmap"); - if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n", - perfmap_fd, errno)) + map = bpf_object__find_map_by_name(obj, "perfmap"); + if (CHECK(!map, "bpf_find_map", "not found\n")) goto close_prog; err = load_kallsyms(); if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno)) goto close_prog; - attr.sample_type = PERF_SAMPLE_RAW; - attr.type = PERF_TYPE_SOFTWARE; - attr.config = PERF_COUNT_SW_BPF_OUTPUT; - pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/, - -1/*group_fd*/, 0); - if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, - errno)) + CPU_ZERO(&cpu_set); + CPU_SET(0, &cpu_set); + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); + if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno)) goto close_prog; - err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY); - if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err, - errno)) + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) goto close_prog; - err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); - if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n", - err, errno)) - goto close_prog; - - err = perf_event_mmap(pmu_fd); - if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno)) + pb_opts.sample_cb = get_stack_print_output; + pb = perf_buffer__new(bpf_map__fd(map), 8, &pb_opts); + if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) goto close_prog; /* trigger some syscall action */ for (i = 0; i < MAX_CNT_RAWTP; i++) nanosleep(&tv, NULL); - err = perf_event_poller(pmu_fd, get_stack_print_output); - if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno)) - goto close_prog; + while (exp_cnt > 0) { + err = perf_buffer__poll(pb, 100); + if (err < 0 && CHECK(err < 0, "pb__poll", "err %d\n", err)) + goto close_prog; + exp_cnt -= err; + } goto close_prog_noerr; close_prog: error_cnt++; close_prog_noerr: + if (!IS_ERR_OR_NULL(link)) + bpf_link__destroy(link); + if (!IS_ERR_OR_NULL(pb)) + perf_buffer__free(pb); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index 5633be43828f..4a4f428d1a78 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -1,15 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> -static int libbpf_debug_print(enum libbpf_print_level level, - const char *format, va_list args) -{ - if (level == LIBBPF_DEBUG) - return 0; - - return vfprintf(stderr, format, args); -} - void test_reference_tracking(void) { const char *file = "./test_sk_lookup_kern.o"; @@ -36,9 +27,11 @@ void test_reference_tracking(void) /* Expect verifier failure if test name has 'fail' */ if (strstr(title, "fail") != NULL) { - libbpf_set_print(NULL); + libbpf_print_fn_t old_print_fn; + + old_print_fn = libbpf_set_print(NULL); err = !bpf_program__load(prog, "GPL", 0); - libbpf_set_print(libbpf_debug_print); + libbpf_set_print(old_print_fn); } else { err = bpf_program__load(prog, "GPL", 0); } diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 54218ee3c004..1575f0a1f586 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -203,7 +203,7 @@ static int test_send_signal_nmi(void) if (pmu_fd == -1) { if (errno == ENOENT) { printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", - __func__); + __func__); return 0; } /* Let the test fail with a more informative message */ @@ -219,11 +219,10 @@ void test_send_signal(void) { int ret = 0; - ret |= test_send_signal_tracepoint(); - ret |= test_send_signal_perf(); - ret |= test_send_signal_nmi(); - if (!ret) - printf("test_send_signal:OK\n"); - else - printf("test_send_signal:FAIL\n"); + if (test__start_subtest("send_signal_tracepoint")) + ret |= test_send_signal_tracepoint(); + if (test__start_subtest("send_signal_perf")) + ret |= test_send_signal_perf(); + if (test__start_subtest("send_signal_nmi")) + ret |= test_send_signal_nmi(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c index 09e6b46f5515..15f7c272edb0 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c @@ -75,7 +75,8 @@ void test_xdp_noinline(void) } if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) { error_cnt++; - printf("test_xdp_noinline:FAIL:stats %lld %lld\n", bytes, pkts); + printf("test_xdp_noinline:FAIL:stats %lld %lld\n", + bytes, pkts); } out: bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 5ae485a6af3f..040a44206f29 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -65,8 +65,8 @@ struct { } jmp_table SEC(".maps"); struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); __type(key, __u32); __type(value, struct bpf_flow_keys); } last_dissection SEC(".maps"); @@ -74,15 +74,20 @@ struct { static __always_inline int export_flow_keys(struct bpf_flow_keys *keys, int ret) { - struct bpf_flow_keys *val; - __u32 key = 0; + __u32 key = (__u32)(keys->sport) << 16 | keys->dport; + struct bpf_flow_keys val; - val = bpf_map_lookup_elem(&last_dissection, &key); - if (val) - memcpy(val, keys, sizeof(*val)); + memcpy(&val, keys, sizeof(val)); + bpf_map_update_elem(&last_dissection, &key, &val, BPF_ANY); return ret; } +#define IPV6_FLOWLABEL_MASK __bpf_constant_htonl(0x000FFFFF) +static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) +{ + return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; +} + static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb, __u16 hdr_size, void *buffer) @@ -153,7 +158,6 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) struct tcphdr *tcp, _tcp; struct udphdr *udp, _udp; - keys->ip_proto = proto; switch (proto) { case IPPROTO_ICMP: icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp); @@ -162,9 +166,15 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) return export_flow_keys(keys, BPF_OK); case IPPROTO_IPIP: keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + return parse_eth_proto(skb, bpf_htons(ETH_P_IP)); case IPPROTO_IPV6: keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6)); case IPPROTO_GRE: gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre); @@ -184,6 +194,8 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) keys->thoff += 4; /* Step over sequence number */ keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); if (gre->proto == bpf_htons(ETH_P_TEB)) { eth = bpf_flow_dissect_get_header(skb, sizeof(*eth), @@ -231,7 +243,6 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) { struct bpf_flow_keys *keys = skb->flow_keys; - keys->ip_proto = nexthdr; switch (nexthdr) { case IPPROTO_HOPOPTS: case IPPROTO_DSTOPTS: @@ -266,6 +277,7 @@ PROG(IP)(struct __sk_buff *skb) keys->addr_proto = ETH_P_IP; keys->ipv4_src = iph->saddr; keys->ipv4_dst = iph->daddr; + keys->ip_proto = iph->protocol; keys->thoff += iph->ihl << 2; if (data + keys->thoff > data_end) @@ -273,13 +285,20 @@ PROG(IP)(struct __sk_buff *skb) if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) { keys->is_frag = true; - if (iph->frag_off & bpf_htons(IP_OFFSET)) + if (iph->frag_off & bpf_htons(IP_OFFSET)) { /* From second fragment on, packets do not have headers * we can parse. */ done = true; - else + } else { keys->is_first_frag = true; + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + done = true; + } } if (done) @@ -301,6 +320,11 @@ PROG(IPV6)(struct __sk_buff *skb) memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr)); keys->thoff += sizeof(struct ipv6hdr); + keys->ip_proto = ip6h->nexthdr; + keys->flow_label = ip6_flowlabel(ip6h); + + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) + return export_flow_keys(keys, BPF_OK); return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -317,7 +341,8 @@ PROG(IPV6OP)(struct __sk_buff *skb) /* hlen is in 8-octets and does not include the first 8 bytes * of the header */ - skb->flow_keys->thoff += (1 + ip6h->hdrlen) << 3; + keys->thoff += (1 + ip6h->hdrlen) << 3; + keys->ip_proto = ip6h->nexthdr; return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -333,9 +358,18 @@ PROG(IPV6FR)(struct __sk_buff *skb) keys->thoff += sizeof(*fragh); keys->is_frag = true; - if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) + keys->ip_proto = fragh->nexthdr; + + if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) { keys->is_first_frag = true; + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + return export_flow_keys(keys, BPF_OK); + } + return parse_ipv6_proto(skb, fragh->nexthdr); } diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c new file mode 100644 index 000000000000..018ed7fbba3a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c new file mode 100644 index 000000000000..13d662c57014 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_dim x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c new file mode 100644 index 000000000000..a351f418c85d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_val_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c new file mode 100644 index 000000000000..a8735009becc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_non_array x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c new file mode 100644 index 000000000000..2a67c28b1e75 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_shallow x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c new file mode 100644 index 000000000000..1142c08c925f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_small x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c new file mode 100644 index 000000000000..795a5b729176 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_wrong_val_type1 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c new file mode 100644 index 000000000000..3af74b837c4d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_wrong_val_type2 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c new file mode 100644 index 000000000000..b74455b91227 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c new file mode 100644 index 000000000000..7b6035f86ee6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors__err_wrong_name x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c new file mode 100644 index 000000000000..7d0f041042c5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c new file mode 100644 index 000000000000..f9359450186e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___bool x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c new file mode 100644 index 000000000000..50369e8320a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_bitfield x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c new file mode 100644 index 000000000000..823bac13d641 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_16 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c new file mode 100644 index 000000000000..b44f3be18535 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_32 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c new file mode 100644 index 000000000000..9a3dd2099c0f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_64 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c new file mode 100644 index 000000000000..9f11ef5f6e88 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_8 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c new file mode 100644 index 000000000000..aafb1c5819d7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___reverse_sign x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c new file mode 100644 index 000000000000..ed9ad8b5b4f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_misc___a x) {} +void f2(struct core_reloc_misc___b x) {} +void f3(struct core_reloc_misc_extensible x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c new file mode 100644 index 000000000000..124197a2e813 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c new file mode 100644 index 000000000000..f8a6592ca75f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___mod_swap x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c new file mode 100644 index 000000000000..5c0d73687247 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___typedefs x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c new file mode 100644 index 000000000000..4480fcc0f183 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c new file mode 100644 index 000000000000..13e108f76ece --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___anon_embed x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c new file mode 100644 index 000000000000..76b54fda5fbb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___dup_compat_types x) {} +void f2(struct core_reloc_nesting___dup_compat_types__2 x) {} +void f3(struct core_reloc_nesting___dup_compat_types__3 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c new file mode 100644 index 000000000000..975fb95db810 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c new file mode 100644 index 000000000000..ad66c67e7980 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c new file mode 100644 index 000000000000..35c5f8da6812 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_dup_incompat_types__1 x) {} +void f2(struct core_reloc_nesting___err_dup_incompat_types__2 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c new file mode 100644 index 000000000000..142e332041db --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c new file mode 100644 index 000000000000..efcae167fab9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c new file mode 100644 index 000000000000..97aaaedd8ada --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_nonstruct_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c new file mode 100644 index 000000000000..ffde35086e90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_partial_match_dups__a x) {} +void f2(struct core_reloc_nesting___err_partial_match_dups__b x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c new file mode 100644 index 000000000000..39a2fadd8e95 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_too_deep x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c new file mode 100644 index 000000000000..a09d9dfb20df --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___extra_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c new file mode 100644 index 000000000000..3d8a1a74012f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___struct_union_mixup x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c new file mode 100644 index 000000000000..96b90e39242a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c new file mode 100644 index 000000000000..6e87233a3ed0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_enum_def x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c new file mode 100644 index 000000000000..d9f48e80b9d9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_func_proto x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c new file mode 100644 index 000000000000..c718f75f8f3b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_ptr_type x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c new file mode 100644 index 000000000000..b8a120830891 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_enum x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c new file mode 100644 index 000000000000..ad8b3c9aa76f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_int x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c new file mode 100644 index 000000000000..e20bc1d42d0a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_ptr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c new file mode 100644 index 000000000000..8da52432ba17 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c new file mode 100644 index 000000000000..003acfc9a3e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr___diff_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h new file mode 100644 index 000000000000..f686a8138d90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -0,0 +1,667 @@ +#include <stdint.h> +#include <stdbool.h> + +/* + * FLAVORS + */ +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* this is not a flavor, as it doesn't have triple underscore */ +struct core_reloc_flavors__err_wrong_name { + int a; + int b; + int c; +}; + +/* + * NESTING + */ +/* original set up, used to record relocations in BPF program */ +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +/* inlined anonymous struct/union instead of named structs in original */ +struct core_reloc_nesting___anon_embed { + int __just_for_padding; + union { + struct { + int a; + } a; + } a; + struct { + union { + int b; + } b; + } b; +}; + +/* different mix of nested structs/unions than in original */ +struct core_reloc_nesting___struct_union_mixup { + int __a; + struct { + int __a; + union { + char __a; + int a; + } a; + } a; + int __b; + union { + int __b; + union { + char __b; + int b; + } b; + } b; +}; + +/* extra anon structs/unions, but still valid a.a.a and b.b.b accessors */ +struct core_reloc_nesting___extra_nesting { + int __padding; + struct { + struct { + struct { + struct { + union { + int a; + } a; + }; + }; + } a; + int __some_more; + struct { + union { + union { + union { + struct { + int b; + }; + } b; + }; + } b; + }; + }; +}; + +/* three flavors of same struct with different structure but same layout for + * a.a.a and b.b.b, thus successfully resolved and relocatable */ +struct core_reloc_nesting___dup_compat_types { + char __just_for_padding; + /* 3 more bytes of padding */ + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + long long __more_padding; + struct { + struct { + int b; /* offset 16 */ + } b; + } b; +}; + +struct core_reloc_nesting___dup_compat_types__2 { + int __aligned_padding; + struct { + int __trickier_noop[0]; + struct { + char __some_more_noops[0]; + int a; /* offset 4 */ + } a; + } a; + int __more_padding; + struct { + struct { + struct { + int __critical_padding; + int b; /* offset 16 */ + } b; + int __does_not_matter; + }; + } b; + int __more_irrelevant_stuff; +}; + +struct core_reloc_nesting___dup_compat_types__3 { + char __correct_padding[4]; + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + /* 8 byte padding due to next struct's alignment */ + struct { + struct { + int b; + } b; + } b __attribute__((aligned(16))); +}; + +/* b.b.b field is missing */ +struct core_reloc_nesting___err_missing_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int x; + } b; + } b; +}; + +/* b.b.b field is an array of integers instead of plain int */ +struct core_reloc_nesting___err_array_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b[1]; + } b; + } b; +}; + +/* middle b container is missing */ +struct core_reloc_nesting___err_missing_container { + struct { + struct { + int a; + } a; + } a; + struct { + int x; + } b; +}; + +/* middle b container is referenced through pointer instead of being embedded */ +struct core_reloc_nesting___err_nonstruct_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } *b; + } b; +}; + +/* middle b container is an array of structs instead of plain struct */ +struct core_reloc_nesting___err_array_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } b[1]; + } b; +}; + +/* two flavors of same struct with incompatible layout for b.b.b */ +struct core_reloc_nesting___err_dup_incompat_types__1 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + struct { + struct { + int b; /* offset 4 */ + } b; + } b; +}; + +struct core_reloc_nesting___err_dup_incompat_types__2 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + int __extra_padding; + struct { + struct { + int b; /* offset 8 (!) */ + } b; + } b; +}; + +/* two flavors of same struct having one of a.a.a and b.b.b, but not both */ +struct core_reloc_nesting___err_partial_match_dups__a { + struct { + struct { + int a; + } a; + } a; +}; + +struct core_reloc_nesting___err_partial_match_dups__b { + struct { + struct { + int b; + } b; + } b; +}; + +struct core_reloc_nesting___err_too_deep { + struct { + struct { + int a; + } a; + } a; + /* 65 levels of nestedness for b.b.b */ + struct { + struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + /* this one is one too much */ + struct { + int b; + }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + } b; + } b; +}; + +/* + * ARRAYS + */ +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +/* bigger array dimensions */ +struct core_reloc_arrays___diff_arr_dim { + int a[7]; + char b[3][4][5]; + struct core_reloc_arrays_substruct c[4]; + struct core_reloc_arrays_substruct d[2][3]; +}; + +/* different size of array's value (struct) */ +struct core_reloc_arrays___diff_arr_val_sz { + int a[5]; + char b[2][3][4]; + struct { + int __padding1; + int c; + int __padding2; + } c[3]; + struct { + int __padding1; + int d; + int __padding2; + } d[1][2]; +}; + +struct core_reloc_arrays___err_too_small { + int a[2]; /* this one is too small */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_too_shallow { + int a[5]; + char b[2][3]; /* this one lacks one dimension */ + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_non_array { + int a; /* not an array */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_wrong_val_type1 { + char a[5]; /* char instead of int */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_wrong_val_type2 { + int a[5]; + char b[2][3][4]; + int c[3]; /* value is not a struct */ + struct core_reloc_arrays_substruct d[1][2]; +}; + +/* + * PRIMITIVES + */ +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___diff_enum_def { + char a; + int b; + void *d; + int (*f)(const char *); + enum { + X = 100, + Y = 200, + } c; /* inline enum def with differing set of values */ +}; + +struct core_reloc_primitives___diff_func_proto { + void (*f)(int); /* incompatible function prototype */ + void *d; + enum core_reloc_primitives_enum c; + int b; + char a; +}; + +struct core_reloc_primitives___diff_ptr_type { + const char * const d; /* different pointee type + modifiers */ + char a; + int b; + enum core_reloc_primitives_enum c; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_enum { + char a[1]; + int b; + int c; /* int instead of enum */ + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_int { + char a[1]; + int *b; /* ptr instead of int */ + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_ptr { + char a[1]; + int b; + enum core_reloc_primitives_enum c; + int d; /* int instead of ptr */ + int (*f)(const char *); +}; + +/* + * MODS + */ +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c; + char_ptr_t d; + int e[3]; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +/* a/b, c/d, e/f, and g/h pairs are swapped */ +struct core_reloc_mods___mod_swap { + int b; + int_t a; + char *d; + char_ptr_t c; + int f[3]; + arr_t e; + struct { + int y; + int x; + } h; + core_reloc_mods_substruct_t g; +}; + +typedef int int1_t; +typedef int1_t int2_t; +typedef int2_t int3_t; + +typedef int arr1_t[5]; +typedef arr1_t arr2_t; +typedef arr2_t arr3_t; +typedef arr3_t arr4_t; + +typedef const char * const volatile fancy_char_ptr_t; + +typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt; + +/* we need more typedefs */ +struct core_reloc_mods___typedefs { + core_reloc_mods_substruct_tt g; + core_reloc_mods_substruct_tt h; + arr4_t f; + arr4_t e; + fancy_char_ptr_t d; + fancy_char_ptr_t c; + int3_t b; + int3_t a; +}; + +/* + * PTR_AS_ARR + */ +struct core_reloc_ptr_as_arr { + int a; +}; + +struct core_reloc_ptr_as_arr___diff_sz { + int :32; /* padding */ + char __some_more_padding; + int a; +}; + +/* + * INTS + */ +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +/* signed/unsigned types swap */ +struct core_reloc_ints___reverse_sign { + int8_t u8_field; + uint8_t s8_field; + int16_t u16_field; + uint16_t s16_field; + int32_t u32_field; + uint32_t s32_field; + int64_t u64_field; + uint64_t s64_field; +}; + +struct core_reloc_ints___bool { + bool u8_field; /* bool instead of uint8 */ + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_bitfield { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field: 32; /* bitfields are not supported */ + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_8 { + uint16_t u8_field; /* not 8-bit anymore */ + int16_t s8_field; /* not 8-bit anymore */ + + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_16 { + uint8_t u8_field; + int8_t s8_field; + + uint32_t u16_field; /* not 16-bit anymore */ + int32_t s16_field; /* not 16-bit anymore */ + + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_32 { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + + uint64_t u32_field; /* not 32-bit anymore */ + int64_t s32_field; /* not 32-bit anymore */ + + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_64 { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + + uint32_t u64_field; /* not 64-bit anymore */ + int32_t s64_field; /* not 64-bit anymore */ +}; + +/* + * MISC + */ +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* this one extends core_reloc_misc_extensible struct from BPF prog */ +struct core_reloc_misc_extensible { + int a; + int b; + int c; + int d; +}; diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c new file mode 100644 index 000000000000..650859022771 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop4.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int combinations(volatile struct __sk_buff* skb) +{ + int ret = 0, i; + +#pragma nounroll + for (i = 0; i < 20; i++) + if (skb->len) + ret |= 1 << i; + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c new file mode 100644 index 000000000000..28d1d668f07c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop5.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" +#define barrier() __asm__ __volatile__("": : :"memory") + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int while_true(volatile struct __sk_buff* skb) +{ + int i = 0; + + while (1) { + if (skb->len) + i += 3; + else + i += 7; + if (i == 9) + break; + barrier(); + if (i == 10) + break; + barrier(); + if (i == 13) + break; + barrier(); + if (i == 14) + break; + } + return i; +} diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 076122c898e9..9a3d1c79e6fe 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#include <string.h> #include <netinet/in.h> +#include <netinet/tcp.h> #include <linux/bpf.h> #include "bpf_helpers.h" @@ -42,6 +44,14 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Not interested in SOL_TCP:TCP_CONGESTION; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ @@ -91,6 +101,18 @@ int _setsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Always use cubic */ + + if (optval + 5 > optval_end) + return 0; /* EPERM, bounds check */ + + memcpy(optval, "cubic", 5); + ctx->optlen = 5; + + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c new file mode 100644 index 000000000000..bf67f0fdf743 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_arrays(void *ctx) +{ + struct core_reloc_arrays *in = (void *)&data.in; + struct core_reloc_arrays_output *out = (void *)&data.out; + + /* in->a[2] */ + if (BPF_CORE_READ(&out->a2, &in->a[2])) + return 1; + /* in->b[1][2][3] */ + if (BPF_CORE_READ(&out->b123, &in->b[1][2][3])) + return 1; + /* in->c[1].c */ + if (BPF_CORE_READ(&out->c1c, &in->c[1].c)) + return 1; + /* in->d[0][0].d */ + if (BPF_CORE_READ(&out->d00d, &in->d[0][0].d)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c new file mode 100644 index 000000000000..9fda73e87972 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* local flavor with reversed layout */ +struct core_reloc_flavors___reversed { + int c; + int b; + int a; +}; + +/* local flavor with nested/overlapping layout */ +struct core_reloc_flavors___weird { + struct { + int b; + }; + /* a and c overlap in local flavor, but this should still work + * correctly with target original flavor + */ + union { + int a; + int c; + }; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_flavors(void *ctx) +{ + struct core_reloc_flavors *in_orig = (void *)&data.in; + struct core_reloc_flavors___reversed *in_rev = (void *)&data.in; + struct core_reloc_flavors___weird *in_weird = (void *)&data.in; + struct core_reloc_flavors *out = (void *)&data.out; + + /* read a using weird layout */ + if (BPF_CORE_READ(&out->a, &in_weird->a)) + return 1; + /* read b using reversed layout */ + if (BPF_CORE_READ(&out->b, &in_rev->b)) + return 1; + /* read c using original layout */ + if (BPF_CORE_READ(&out->c, &in_orig->c)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c new file mode 100644 index 000000000000..d99233c8008a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_ints(void *ctx) +{ + struct core_reloc_ints *in = (void *)&data.in; + struct core_reloc_ints *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->u8_field, &in->u8_field) || + BPF_CORE_READ(&out->s8_field, &in->s8_field) || + BPF_CORE_READ(&out->u16_field, &in->u16_field) || + BPF_CORE_READ(&out->s16_field, &in->s16_field) || + BPF_CORE_READ(&out->u32_field, &in->u32_field) || + BPF_CORE_READ(&out->s32_field, &in->s32_field) || + BPF_CORE_READ(&out->u64_field, &in->u64_field) || + BPF_CORE_READ(&out->s64_field, &in->s64_field)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c new file mode 100644 index 000000000000..37e02aa3f0c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct task_struct { + int pid; + int tgid; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_kernel(void *ctx) +{ + struct task_struct *task = (void *)bpf_get_current_task(); + uint64_t pid_tgid = bpf_get_current_pid_tgid(); + int pid, tgid; + + if (BPF_CORE_READ(&pid, &task->pid) || + BPF_CORE_READ(&tgid, &task->tgid)) + return 1; + + /* validate pid + tgid matches */ + data.out[0] = (((uint64_t)pid << 32) | tgid) == pid_tgid; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c new file mode 100644 index 000000000000..c59984bd3e23 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* fixed two first members, can be extended with new fields */ +struct core_reloc_misc_extensible { + int a; + int b; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_misc(void *ctx) +{ + struct core_reloc_misc___a *in_a = (void *)&data.in; + struct core_reloc_misc___b *in_b = (void *)&data.in; + struct core_reloc_misc_extensible *in_ext = (void *)&data.in; + struct core_reloc_misc_output *out = (void *)&data.out; + + /* record two different relocations with the same accessor string */ + if (BPF_CORE_READ(&out->a, &in_a->a1) || /* accessor: 0:0 */ + BPF_CORE_READ(&out->b, &in_b->b1)) /* accessor: 0:0 */ + return 1; + + /* Validate relocations capture array-only accesses for structs with + * fixed header, but with potentially extendable tail. This will read + * first 4 bytes of 2nd element of in_ext array of potentially + * variably sized struct core_reloc_misc_extensible. */ + if (BPF_CORE_READ(&out->c, &in_ext[2])) /* accessor: 2 */ + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c new file mode 100644 index 000000000000..f98b942c062b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c; + char_ptr_t d; + int e[3]; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_mods(void *ctx) +{ + struct core_reloc_mods *in = (void *)&data.in; + struct core_reloc_mods_output *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in->a) || + BPF_CORE_READ(&out->b, &in->b) || + BPF_CORE_READ(&out->c, &in->c) || + BPF_CORE_READ(&out->d, &in->d) || + BPF_CORE_READ(&out->e, &in->e[2]) || + BPF_CORE_READ(&out->f, &in->f[1]) || + BPF_CORE_READ(&out->g, &in->g.x) || + BPF_CORE_READ(&out->h, &in->h.y)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c new file mode 100644 index 000000000000..3ca30cec2b39 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +/* int a.a.a and b.b.b accesses */ +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_nesting(void *ctx) +{ + struct core_reloc_nesting *in = (void *)&data.in; + struct core_reloc_nesting *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a.a.a, &in->a.a.a)) + return 1; + if (BPF_CORE_READ(&out->b.b.b, &in->b.b.b)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c new file mode 100644 index 000000000000..add52f23ab35 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_primitives(void *ctx) +{ + struct core_reloc_primitives *in = (void *)&data.in; + struct core_reloc_primitives *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in->a) || + BPF_CORE_READ(&out->b, &in->b) || + BPF_CORE_READ(&out->c, &in->c) || + BPF_CORE_READ(&out->d, &in->d) || + BPF_CORE_READ(&out->f, &in->f)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c new file mode 100644 index 000000000000..526b7ddc7ea1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_ptr_as_arr { + int a; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_ptr_as_arr(void *ctx) +{ + struct core_reloc_ptr_as_arr *in = (void *)&data.in; + struct core_reloc_ptr_as_arr *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in[2].a)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index 33254b771384..f8ffa3f3d44b 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -55,7 +55,7 @@ struct { __type(value, raw_stack_trace_t); } rawdata_map SEC(".maps"); -SEC("tracepoint/raw_syscalls/sys_enter") +SEC("raw_tracepoint/sys_enter") int bpf_prog1(void *ctx) { int max_len, max_buildid_len, usize, ksize, total_size; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index 1ab095bcacd8..d8803dfa8d32 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -19,10 +19,29 @@ struct bpf_map_def SEC("maps") results = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = 1, + .value_size = sizeof(__u32), + .max_entries = 3, }; +static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, + void *iph, __u32 ip_size, + struct tcphdr *tcph) +{ + __u32 thlen = tcph->doff * 4; + + if (tcph->syn && !tcph->ack) { + // packet should only have an MSS option + if (thlen != 24) + return 0; + + if ((void *)tcph + thlen > data_end) + return 0; + + return bpf_tcp_gen_syncookie(sk, iph, ip_size, tcph, thlen); + } + return 0; +} + static __always_inline void check_syncookie(void *ctx, void *data, void *data_end) { @@ -33,8 +52,10 @@ static __always_inline void check_syncookie(void *ctx, void *data, struct ipv6hdr *ipv6h; struct tcphdr *tcph; int ret; + __u32 key_mss = 2; + __u32 key_gen = 1; __u32 key = 0; - __u64 value = 1; + __s64 seq_mss; ethh = data; if (ethh + 1 > data_end) @@ -66,6 +87,9 @@ static __always_inline void check_syncookie(void *ctx, void *data, if (sk->state != BPF_TCP_LISTEN) goto release; + seq_mss = gen_syncookie(data_end, sk, ipv4h, sizeof(*ipv4h), + tcph); + ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h), tcph, sizeof(*tcph)); break; @@ -95,6 +119,9 @@ static __always_inline void check_syncookie(void *ctx, void *data, if (sk->state != BPF_TCP_LISTEN) goto release; + seq_mss = gen_syncookie(data_end, sk, ipv6h, sizeof(*ipv6h), + tcph); + ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h), tcph, sizeof(*tcph)); break; @@ -103,8 +130,19 @@ static __always_inline void check_syncookie(void *ctx, void *data, return; } - if (ret == 0) - bpf_map_update_elem(&results, &key, &value, 0); + if (seq_mss > 0) { + __u32 cookie = (__u32)seq_mss; + __u32 mss = seq_mss >> 32; + + bpf_map_update_elem(&results, &key_gen, &cookie, 0); + bpf_map_update_elem(&results, &key_mss, &mss, 0); + } + + if (ret == 0) { + __u32 cookie = bpf_ntohl(tcph->ack_seq) - 1; + + bpf_map_update_elem(&results, &key, &cookie, 0); + } release: bpf_sk_release(sk); diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 5443b9bd75ed..e1f1becda529 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -508,6 +508,21 @@ static void test_devmap(unsigned int task, void *data) close(fd); } +static void test_devmap_hash(unsigned int task, void *data) +{ + int fd; + __u32 key, value; + + fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP_HASH, sizeof(key), sizeof(value), + 2, 0); + if (fd < 0) { + printf("Failed to create devmap_hash '%s'!\n", strerror(errno)); + exit(1); + } + + close(fd); +} + static void test_queuemap(unsigned int task, void *data) { const int MAP_SIZE = 32; @@ -1684,6 +1699,7 @@ static void run_all_tests(void) test_arraymap_percpu_many_keys(); test_devmap(0, NULL); + test_devmap_hash(0, NULL); test_sockmap(0, NULL); test_map_large(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index dae0819b1141..12895d03d58b 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -3,10 +3,107 @@ */ #include "test_progs.h" #include "bpf_rlimit.h" +#include <argp.h> +#include <string.h> +/* defined in test_progs.h */ +struct test_env env; int error_cnt, pass_cnt; -bool jit_enabled; -bool verifier_stats = false; + +struct prog_test_def { + const char *test_name; + int test_num; + void (*run_test)(void); + bool force_log; + int pass_cnt; + int error_cnt; + bool tested; + + const char *subtest_name; + int subtest_num; + + /* store counts before subtest started */ + int old_pass_cnt; + int old_error_cnt; +}; + +static bool should_run(struct test_selector *sel, int num, const char *name) +{ + if (sel->name && sel->name[0] && !strstr(name, sel->name)) + return false; + + if (!sel->num_set) + return true; + + return num < sel->num_set_len && sel->num_set[num]; +} + +static void dump_test_log(const struct prog_test_def *test, bool failed) +{ + if (stdout == env.stdout) + return; + + fflush(stdout); /* exports env.log_buf & env.log_cnt */ + + if (env.verbose || test->force_log || failed) { + if (env.log_cnt) { + fprintf(env.stdout, "%s", env.log_buf); + if (env.log_buf[env.log_cnt - 1] != '\n') + fprintf(env.stdout, "\n"); + } + } + + fseeko(stdout, 0, SEEK_SET); /* rewind */ +} + +void test__end_subtest() +{ + struct prog_test_def *test = env.test; + int sub_error_cnt = error_cnt - test->old_error_cnt; + + if (sub_error_cnt) + env.fail_cnt++; + else + env.sub_succ_cnt++; + + dump_test_log(test, sub_error_cnt); + + fprintf(env.stdout, "#%d/%d %s:%s\n", + test->test_num, test->subtest_num, + test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); +} + +bool test__start_subtest(const char *name) +{ + struct prog_test_def *test = env.test; + + if (test->subtest_name) { + test__end_subtest(); + test->subtest_name = NULL; + } + + test->subtest_num++; + + if (!name || !name[0]) { + fprintf(env.stderr, + "Subtest #%d didn't provide sub-test name!\n", + test->subtest_num); + return false; + } + + if (!should_run(&env.subtest_selector, test->subtest_num, name)) + return false; + + test->subtest_name = name; + env.test->old_pass_cnt = pass_cnt; + env.test->old_error_cnt = error_cnt; + + return true; +} + +void test__force_log() { + env.test->force_log = true; +} struct ipv4_packet pkt_v4 = { .eth.h_proto = __bpf_constant_htons(ETH_P_IP), @@ -156,23 +253,276 @@ void *spin_lock_thread(void *arg) pthread_exit(arg); } -#define DECLARE +/* extern declarations for test funcs */ +#define DEFINE_TEST(name) extern void test_##name(); +#include <prog_tests/tests.h> +#undef DEFINE_TEST + +static struct prog_test_def prog_test_defs[] = { +#define DEFINE_TEST(name) { \ + .test_name = #name, \ + .run_test = &test_##name, \ +}, #include <prog_tests/tests.h> -#undef DECLARE +#undef DEFINE_TEST +}; +const int prog_test_cnt = ARRAY_SIZE(prog_test_defs); + +const char *argp_program_version = "test_progs 0.1"; +const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; +const char argp_program_doc[] = "BPF selftests test runner"; + +enum ARG_KEYS { + ARG_TEST_NUM = 'n', + ARG_TEST_NAME = 't', + ARG_VERIFIER_STATS = 's', + ARG_VERBOSE = 'v', +}; + +static const struct argp_option opts[] = { + { "num", ARG_TEST_NUM, "NUM", 0, + "Run test number NUM only " }, + { "name", ARG_TEST_NAME, "NAME", 0, + "Run tests with names containing NAME" }, + { "verifier-stats", ARG_VERIFIER_STATS, NULL, 0, + "Output verifier statistics", }, + { "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL, + "Verbose output (use -vv for extra verbose output)" }, + {}, +}; + +static int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (!env.very_verbose && level == LIBBPF_DEBUG) + return 0; + vprintf(format, args); + return 0; +} + +int parse_num_list(const char *s, struct test_selector *sel) +{ + int i, set_len = 0, num, start = 0, end = -1; + bool *set = NULL, *tmp, parsing_end = false; + char *next; + + while (s[0]) { + errno = 0; + num = strtol(s, &next, 10); + if (errno) + return -errno; + + if (parsing_end) + end = num; + else + start = num; + + if (!parsing_end && *next == '-') { + s = next + 1; + parsing_end = true; + continue; + } else if (*next == ',') { + parsing_end = false; + s = next + 1; + end = num; + } else if (*next == '\0') { + parsing_end = false; + s = next; + end = num; + } else { + return -EINVAL; + } + + if (start > end) + return -EINVAL; -int main(int ac, char **av) + if (end + 1 > set_len) { + set_len = end + 1; + tmp = realloc(set, set_len); + if (!tmp) { + free(set); + return -ENOMEM; + } + set = tmp; + } + for (i = start; i <= end; i++) { + set[i] = true; + } + + } + + if (!set) + return -EINVAL; + + sel->num_set = set; + sel->num_set_len = set_len; + + return 0; +} + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + struct test_env *env = state->input; + + switch (key) { + case ARG_TEST_NUM: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + if (parse_num_list(subtest_str + 1, + &env->subtest_selector)) { + fprintf(stderr, + "Failed to parse subtest numbers.\n"); + return -EINVAL; + } + } + if (parse_num_list(arg, &env->test_selector)) { + fprintf(stderr, "Failed to parse test numbers.\n"); + return -EINVAL; + } + break; + } + case ARG_TEST_NAME: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + env->subtest_selector.name = strdup(subtest_str + 1); + if (!env->subtest_selector.name) + return -ENOMEM; + } + env->test_selector.name = strdup(arg); + if (!env->test_selector.name) + return -ENOMEM; + break; + } + case ARG_VERIFIER_STATS: + env->verifier_stats = true; + break; + case ARG_VERBOSE: + if (arg) { + if (strcmp(arg, "v") == 0) { + env->very_verbose = true; + } else { + fprintf(stderr, + "Unrecognized verbosity setting ('%s'), only -v and -vv are supported\n", + arg); + return -EINVAL; + } + } + env->verbose = true; + break; + case ARGP_KEY_ARG: + argp_usage(state); + break; + case ARGP_KEY_END: + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +static void stdio_hijack(void) { +#ifdef __GLIBC__ + env.stdout = stdout; + env.stderr = stderr; + + if (env.verbose) { + /* nothing to do, output to stdout by default */ + return; + } + + /* stdout and stderr -> buffer */ + fflush(stdout); + + stdout = open_memstream(&env.log_buf, &env.log_cnt); + if (!stdout) { + stdout = env.stdout; + perror("open_memstream"); + return; + } + + stderr = stdout; +#endif +} + +static void stdio_restore(void) +{ +#ifdef __GLIBC__ + if (stdout == env.stdout) + return; + + fclose(stdout); + free(env.log_buf); + + env.log_buf = NULL; + env.log_cnt = 0; + + stdout = env.stdout; + stderr = env.stderr; +#endif +} + +int main(int argc, char **argv) +{ + static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + }; + int err, i; + + err = argp_parse(&argp, argc, argv, 0, NULL, &env); + if (err) + return err; + + libbpf_set_print(libbpf_print_fn); + srand(time(NULL)); - jit_enabled = is_jit_enabled(); + env.jit_enabled = is_jit_enabled(); - if (ac == 2 && strcmp(av[1], "-s") == 0) - verifier_stats = true; + stdio_hijack(); + for (i = 0; i < prog_test_cnt; i++) { + struct prog_test_def *test = &prog_test_defs[i]; + int old_pass_cnt = pass_cnt; + int old_error_cnt = error_cnt; -#define CALL -#include <prog_tests/tests.h> -#undef CALL + env.test = test; + test->test_num = i + 1; + + if (!should_run(&env.test_selector, + test->test_num, test->test_name)) + continue; + + test->run_test(); + /* ensure last sub-test is finalized properly */ + if (test->subtest_name) + test__end_subtest(); + + test->tested = true; + test->pass_cnt = pass_cnt - old_pass_cnt; + test->error_cnt = error_cnt - old_error_cnt; + if (test->error_cnt) + env.fail_cnt++; + else + env.succ_cnt++; + + dump_test_log(test, test->error_cnt); + + fprintf(env.stdout, "#%d %s:%s\n", + test->test_num, test->test_name, + test->error_cnt ? "FAIL" : "OK"); + } + stdio_restore(); + printf("Summary: %d/%d PASSED, %d FAILED\n", + env.succ_cnt, env.sub_succ_cnt, env.fail_cnt); + + free(env.test_selector.num_set); + free(env.subtest_selector.num_set); - printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; } diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 49e0f7d85643..37d427f5a1e5 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -38,9 +38,40 @@ typedef __u16 __sum16; #include "trace_helpers.h" #include "flow_dissector_load.h" -extern int error_cnt, pass_cnt; -extern bool jit_enabled; -extern bool verifier_stats; +struct prog_test_def; + +struct test_selector { + const char *name; + bool *num_set; + int num_set_len; +}; + +struct test_env { + struct test_selector test_selector; + struct test_selector subtest_selector; + bool verifier_stats; + bool verbose; + bool very_verbose; + + bool jit_enabled; + + struct prog_test_def *test; + FILE *stdout; + FILE *stderr; + char *log_buf; + size_t log_cnt; + + int succ_cnt; /* successful tests */ + int sub_succ_cnt; /* successful sub-tests */ + int fail_cnt; /* total failed tests + sub-tests */ +}; + +extern int error_cnt; +extern int pass_cnt; +extern struct test_env env; + +extern void test__force_log(); +extern bool test__start_subtest(const char *name); #define MAGIC_BYTES 123 @@ -68,7 +99,8 @@ extern struct ipv6_packet pkt_v6; printf(format); \ } else { \ pass_cnt++; \ - printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\ + printf("%s:PASS:%s %d nsec\n", \ + __func__, tag, duration); \ } \ __ret; \ }) diff --git a/tools/testing/selftests/bpf/test_sockopt_sk.c b/tools/testing/selftests/bpf/test_sockopt_sk.c index 036b652e5ca9..e4f6055d92e9 100644 --- a/tools/testing/selftests/bpf/test_sockopt_sk.c +++ b/tools/testing/selftests/bpf/test_sockopt_sk.c @@ -6,6 +6,7 @@ #include <sys/types.h> #include <sys/socket.h> #include <netinet/in.h> +#include <netinet/tcp.h> #include <linux/filter.h> #include <bpf/bpf.h> @@ -25,6 +26,7 @@ static int getsetsockopt(void) union { char u8[4]; __u32 u32; + char cc[16]; /* TCP_CA_NAME_MAX */ } buf = {}; socklen_t optlen; @@ -115,6 +117,29 @@ static int getsetsockopt(void) goto err; } + /* TCP_CONGESTION can extend the string */ + + strcpy(buf.cc, "nv"); + err = setsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, strlen("nv")); + if (err) { + log_err("Failed to call setsockopt(TCP_CONGESTION)"); + goto err; + } + + + optlen = sizeof(buf.cc); + err = getsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(TCP_CONGESTION)"); + goto err; + } + + if (strcmp(buf.cc, "cubic") != 0) { + log_err("Unexpected getsockopt(TCP_CONGESTION) %s != %s", + buf.cc, "cubic"); + goto err; + } + close(fd); return 0; err: diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index d48e51716d19..9b3617d770a5 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -37,6 +37,9 @@ setup() ns1_exec ip link set lo up ns1_exec sysctl -w net.ipv4.tcp_syncookies=2 + ns1_exec sysctl -w net.ipv4.tcp_window_scaling=0 + ns1_exec sysctl -w net.ipv4.tcp_timestamps=0 + ns1_exec sysctl -w net.ipv4.tcp_sack=0 wait_for_ip 127.0.0.1 wait_for_ip ::1 diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index 87829c86c746..b9e991d43155 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -2,6 +2,7 @@ // Copyright (c) 2018 Facebook // Copyright (c) 2019 Cloudflare +#include <limits.h> #include <string.h> #include <stdlib.h> #include <unistd.h> @@ -77,7 +78,7 @@ out: return fd; } -static int get_map_fd_by_prog_id(int prog_id) +static int get_map_fd_by_prog_id(int prog_id, bool *xdp) { struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); @@ -104,6 +105,8 @@ static int get_map_fd_by_prog_id(int prog_id) goto err; } + *xdp = info.type == BPF_PROG_TYPE_XDP; + map_fd = bpf_map_get_fd_by_id(map_ids[0]); if (map_fd < 0) log_err("Failed to get fd by map id %d", map_ids[0]); @@ -113,18 +116,32 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd) +static int run_test(int server_fd, int results_fd, bool xdp) { int client = -1, srv_client = -1; int ret = 0; __u32 key = 0; - __u64 value = 0; + __u32 key_gen = 1; + __u32 key_mss = 2; + __u32 value = 0; + __u32 value_gen = 0; + __u32 value_mss = 0; if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) { log_err("Can't clear results"); goto err; } + if (bpf_map_update_elem(results_fd, &key_gen, &value_gen, 0) < 0) { + log_err("Can't clear results"); + goto err; + } + + if (bpf_map_update_elem(results_fd, &key_mss, &value_mss, 0) < 0) { + log_err("Can't clear results"); + goto err; + } + client = connect_to_server(server_fd); if (client == -1) goto err; @@ -140,8 +157,35 @@ static int run_test(int server_fd, int results_fd) goto err; } - if (value != 1) { - log_err("Didn't match syncookie: %llu", value); + if (value == 0) { + log_err("Didn't match syncookie: %u", value); + goto err; + } + + if (bpf_map_lookup_elem(results_fd, &key_gen, &value_gen) < 0) { + log_err("Can't lookup result"); + goto err; + } + + if (xdp && value_gen == 0) { + // SYN packets do not get passed through generic XDP, skip the + // rest of the test. + printf("Skipping XDP cookie check\n"); + goto out; + } + + if (bpf_map_lookup_elem(results_fd, &key_mss, &value_mss) < 0) { + log_err("Can't lookup result"); + goto err; + } + + if (value != value_gen) { + log_err("BPF generated cookie does not match kernel one"); + goto err; + } + + if (value_mss < 536 || value_mss > USHRT_MAX) { + log_err("Unexpected MSS retrieved"); goto err; } @@ -163,13 +207,14 @@ int main(int argc, char **argv) int server_v6 = -1; int results = -1; int err = 0; + bool xdp; if (argc < 2) { fprintf(stderr, "Usage: %s prog_id\n", argv[0]); exit(1); } - results = get_map_fd_by_prog_id(atoi(argv[1])); + results = get_map_fd_by_prog_id(atoi(argv[1]), &xdp); if (results < 0) { log_err("Can't get map"); goto err; @@ -194,10 +239,10 @@ int main(int argc, char **argv) if (server_v6 == -1) goto err; - if (run_test(server, results)) + if (run_test(server, results, xdp)) goto err; - if (run_test(server_v6, results)) + if (run_test(server_v6, results, xdp)) goto err; printf("ok\n"); diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index 86152d9ae95b..f9765ddf0761 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -17,6 +17,7 @@ #include <linux/rtnetlink.h> #include <signal.h> #include <linux/perf_event.h> +#include <linux/err.h> #include "bpf_rlimit.h" #include "bpf_util.h" @@ -30,28 +31,34 @@ pthread_t tid; int rx_callbacks; -static int dummyfn(void *data, int size) +static void dummyfn(void *ctx, int cpu, void *data, __u32 size) { struct tcp_notifier *t = data; if (t->type != 0xde || t->subtype != 0xad || t->source != 0xbe || t->hash != 0xef) - return 1; + return; rx_callbacks++; - return 0; } -void tcp_notifier_poller(int fd) +void tcp_notifier_poller(struct perf_buffer *pb) { - while (1) - perf_event_poller(fd, dummyfn); + int err; + + while (1) { + err = perf_buffer__poll(pb, 100); + if (err < 0 && err != -EINTR) { + printf("failed perf_buffer__poll: %d\n", err); + return; + } + } } static void *poller_thread(void *arg) { - int fd = *(int *)arg; + struct perf_buffer *pb = arg; - tcp_notifier_poller(fd); + tcp_notifier_poller(pb); return arg; } @@ -60,52 +67,20 @@ int verify_result(const struct tcpnotify_globals *result) return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1); } -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); -} - -static int setup_bpf_perf_event(int mapfd) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - }; - int key = 0; - int pmu_fd; - - pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0); - if (pmu_fd < 0) - return pmu_fd; - bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY); - - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); - return pmu_fd; -} - int main(int argc, char **argv) { const char *file = "test_tcpnotify_kern.o"; - int prog_fd, map_fd, perf_event_fd; + struct bpf_map *perf_map, *global_map; + struct perf_buffer_opts pb_opts = {}; struct tcpnotify_globals g = {0}; + struct perf_buffer *pb = NULL; const char *cg_path = "/foo"; + int prog_fd, rv, cg_fd = -1; int error = EXIT_FAILURE; struct bpf_object *obj; - int cg_fd = -1; - __u32 key = 0; - int rv; char test_script[80]; - int pmu_fd; cpu_set_t cpuset; + __u32 key = 0; CPU_ZERO(&cpuset); CPU_SET(0, &cpuset); @@ -133,19 +108,24 @@ int main(int argc, char **argv) goto err; } - perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map"); - if (perf_event_fd < 0) + perf_map = bpf_object__find_map_by_name(obj, "perf_event_map"); + if (!perf_map) { + printf("FAIL:map '%s' not found\n", "perf_event_map"); goto err; + } - map_fd = bpf_find_map(__func__, obj, "global_map"); - if (map_fd < 0) - goto err; + global_map = bpf_object__find_map_by_name(obj, "global_map"); + if (!global_map) { + printf("FAIL:map '%s' not found\n", "global_map"); + return -1; + } - pmu_fd = setup_bpf_perf_event(perf_event_fd); - if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0) + pb_opts.sample_cb = dummyfn; + pb = perf_buffer__new(bpf_map__fd(perf_map), 8, &pb_opts); + if (IS_ERR(pb)) goto err; - pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd); + pthread_create(&tid, NULL, poller_thread, pb); sprintf(test_script, "iptables -A INPUT -p tcp --dport %d -j DROP", @@ -162,7 +142,7 @@ int main(int argc, char **argv) TESTPORT); system(test_script); - rv = bpf_map_lookup_elem(map_fd, &key, &g); + rv = bpf_map_lookup_elem(bpf_map__fd(global_map), &key, &g); if (rv != 0) { printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); goto err; @@ -182,5 +162,7 @@ err: bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); close(cg_fd); cleanup_cgroup_environment(); + if (!IS_ERR_OR_NULL(pb)) + perf_buffer__free(pb); return error; } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 84135d5f4b35..44e2d640b088 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -50,7 +50,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 18 +#define MAX_NR_MAPS 19 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -84,6 +84,7 @@ struct bpf_test { int fixup_map_array_wo[MAX_FIXUPS]; int fixup_map_array_small[MAX_FIXUPS]; int fixup_sk_storage_map[MAX_FIXUPS]; + int fixup_map_event_output[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t insn_processed; @@ -632,6 +633,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_array_wo = test->fixup_map_array_wo; int *fixup_map_array_small = test->fixup_map_array_small; int *fixup_sk_storage_map = test->fixup_sk_storage_map; + int *fixup_map_event_output = test->fixup_map_event_output; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -793,6 +795,14 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_sk_storage_map++; } while (*fixup_sk_storage_map); } + if (*fixup_map_event_output) { + map_fds[18] = __create_map(BPF_MAP_TYPE_PERF_EVENT_ARRAY, + sizeof(int), sizeof(int), 1, 0); + do { + prog[*fixup_map_event_output].imm = map_fds[18]; + fixup_map_event_output++; + } while (*fixup_map_event_output); + } } static int set_admin(bool admin) diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index b47f205f0310..7f989b3e4e22 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -86,128 +86,3 @@ long ksym_get_addr(const char *name) return 0; } - -static int page_size; -static int page_cnt = 8; -static struct perf_event_mmap_page *header; - -int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header) -{ - void *base; - int mmap_size; - - page_size = getpagesize(); - mmap_size = page_size * (page_cnt + 1); - - base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - if (base == MAP_FAILED) { - printf("mmap err\n"); - return -1; - } - - *header = base; - return 0; -} - -int perf_event_mmap(int fd) -{ - return perf_event_mmap_header(fd, &header); -} - -static int perf_event_poll(int fd) -{ - struct pollfd pfd = { .fd = fd, .events = POLLIN }; - - return poll(&pfd, 1, 1000); -} - -struct perf_event_sample { - struct perf_event_header header; - __u32 size; - char data[]; -}; - -static enum bpf_perf_event_ret -bpf_perf_event_print(struct perf_event_header *hdr, void *private_data) -{ - struct perf_event_sample *e = (struct perf_event_sample *)hdr; - perf_event_print_fn fn = private_data; - int ret; - - if (e->header.type == PERF_RECORD_SAMPLE) { - ret = fn(e->data, e->size); - if (ret != LIBBPF_PERF_EVENT_CONT) - return ret; - } else if (e->header.type == PERF_RECORD_LOST) { - struct { - struct perf_event_header header; - __u64 id; - __u64 lost; - } *lost = (void *) e; - printf("lost %lld events\n", lost->lost); - } else { - printf("unknown event type=%d size=%d\n", - e->header.type, e->header.size); - } - - return LIBBPF_PERF_EVENT_CONT; -} - -int perf_event_poller(int fd, perf_event_print_fn output_fn) -{ - enum bpf_perf_event_ret ret; - void *buf = NULL; - size_t len = 0; - - for (;;) { - perf_event_poll(fd); - ret = bpf_perf_event_read_simple(header, page_cnt * page_size, - page_size, &buf, &len, - bpf_perf_event_print, - output_fn); - if (ret != LIBBPF_PERF_EVENT_CONT) - break; - } - free(buf); - - return ret; -} - -int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers, - int num_fds, perf_event_print_fn output_fn) -{ - enum bpf_perf_event_ret ret; - struct pollfd *pfds; - void *buf = NULL; - size_t len = 0; - int i; - - pfds = calloc(num_fds, sizeof(*pfds)); - if (!pfds) - return LIBBPF_PERF_EVENT_ERROR; - - for (i = 0; i < num_fds; i++) { - pfds[i].fd = fds[i]; - pfds[i].events = POLLIN; - } - - for (;;) { - poll(pfds, num_fds, 1000); - for (i = 0; i < num_fds; i++) { - if (!pfds[i].revents) - continue; - - ret = bpf_perf_event_read_simple(headers[i], - page_cnt * page_size, - page_size, &buf, &len, - bpf_perf_event_print, - output_fn); - if (ret != LIBBPF_PERF_EVENT_CONT) - break; - } - } - free(buf); - free(pfds); - - return ret; -} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 18924f23db1b..aa4dcfe18050 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -3,7 +3,6 @@ #define __TRACE_HELPER_H #include <libbpf.h> -#include <linux/perf_event.h> struct ksym { long addr; @@ -14,12 +13,4 @@ int load_kallsyms(void); struct ksym *ksym_search(long key); long ksym_get_addr(const char *name); -typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size); - -int perf_event_mmap(int fd); -int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header); -/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */ -int perf_event_poller(int fd, perf_event_print_fn output_fn); -int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers, - int num_fds, perf_event_print_fn output_fn); #endif diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c new file mode 100644 index 000000000000..130553e19eca --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -0,0 +1,94 @@ +/* instructions used to output a skb based software event, produced + * from code snippet: + * struct TMP { + * uint64_t tmp; + * } tt; + * tt.tmp = 5; + * bpf_perf_event_output(skb, &connection_tracking_event_map, 0, + * &tt, sizeof(tt)); + * return 1; + * + * the bpf assembly from llvm is: + * 0: b7 02 00 00 05 00 00 00 r2 = 5 + * 1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2 + * 2: bf a4 00 00 00 00 00 00 r4 = r10 + * 3: 07 04 00 00 f8 ff ff ff r4 += -8 + * 4: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0ll + * 6: b7 03 00 00 00 00 00 00 r3 = 0 + * 7: b7 05 00 00 08 00 00 00 r5 = 8 + * 8: 85 00 00 00 19 00 00 00 call 25 + * 9: b7 00 00 00 01 00 00 00 r0 = 1 + * 10: 95 00 00 00 00 00 00 00 exit + * + * The reason I put the code here instead of fill_helpers is that map fixup + * is against the insns, instead of filled prog. + */ + +#define __PERF_EVENT_INSNS__ \ + BPF_MOV64_IMM(BPF_REG_2, 5), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), \ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), \ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), \ + BPF_LD_MAP_FD(BPF_REG_2, 0), \ + BPF_MOV64_IMM(BPF_REG_3, 0), \ + BPF_MOV64_IMM(BPF_REG_5, 8), \ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, \ + BPF_FUNC_perf_event_output), \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_EXIT_INSN(), +{ + "perfevent for sockops", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SOCK_OPS, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for tc", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for lwt out", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_LWT_OUT, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for xdp", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_XDP, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for socket filter", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for sk_skb", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup skb", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 40f16f2a3afd..5cbff8038f84 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -36,8 +36,6 @@ source $lib_dir/lib.sh h1_create() { - local dscp; - simple_if_init $h1 192.0.2.1/28 tc qdisc add dev $h1 clsact dscp_capture_install $h1 10 @@ -67,6 +65,7 @@ h2_destroy() dscp_map() { local base=$1; shift + local prio for prio in {0..7}; do echo app=$prio,5,$((base + prio)) @@ -138,6 +137,7 @@ dscp_ping_test() local prio=$1; shift local dev_10=$1; shift local dev_20=$1; shift + local key local dscp_10=$(((prio + 10) << 2)) local dscp_20=$(((prio + 20) << 2)) @@ -175,6 +175,8 @@ dscp_ping_test() test_dscp() { + local prio + for prio in {0..7}; do dscp_ping_test v$h1 192.0.2.1 192.0.2.2 $prio $h1 $h2 done diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh index 9faf02e32627..c745ce3befee 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh @@ -31,6 +31,7 @@ ALL_TESTS=" ping_ipv4 test_update test_no_update + test_dscp_leftover " lib_dir=$(dirname $0)/../../../net/forwarding @@ -50,10 +51,13 @@ reprioritize() echo ${reprio[$in]} } -h1_create() +zero() { - local dscp; + echo 0 +} +h1_create() +{ simple_if_init $h1 192.0.2.1/28 tc qdisc add dev $h1 clsact dscp_capture_install $h1 0 @@ -87,6 +91,7 @@ h2_destroy() dscp_map() { local base=$1; shift + local prio for prio in {0..7}; do echo app=$prio,5,$((base + prio)) @@ -156,6 +161,7 @@ dscp_ping_test() local reprio=$1; shift local dev1=$1; shift local dev2=$1; shift + local i local prio2=$($reprio $prio) # ICMP Request egress prio local prio3=$($reprio $prio2) # ICMP Response egress prio @@ -205,6 +211,7 @@ __test_update() { local update=$1; shift local reprio=$1; shift + local prio sysctl_restore net.ipv4.ip_forward_update_priority sysctl_set net.ipv4.ip_forward_update_priority $update @@ -224,6 +231,19 @@ test_no_update() __test_update 0 echo } +# Test that when the last APP rule is removed, the prio->DSCP map is properly +# set to zeroes, and that the last APP rule does not stay active in the ASIC. +test_dscp_leftover() +{ + lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null + lldpad_app_wait_del + + __test_update 0 zero + + lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null + lldpad_app_wait_set $swp2 +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 9d8baf5d14b3..115837355eaf 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -3,7 +3,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding -ALL_TESTS="fw_flash_test" +ALL_TESTS="fw_flash_test params_test regions_test" NUM_NETIFS=0 source $lib_dir/lib.sh @@ -30,6 +30,118 @@ fw_flash_test() log_test "fw flash test" } +param_get() +{ + local name=$1 + + cmd_jq "devlink dev param show $DL_HANDLE name $name -j" \ + '.[][][].values[] | select(.cmode == "driverinit").value' +} + +param_set() +{ + local name=$1 + local value=$2 + + devlink dev param set $DL_HANDLE name $name cmode driverinit value $value +} + +check_value() +{ + local name=$1 + local phase_name=$2 + local expected_param_value=$3 + local expected_debugfs_value=$4 + local value + + value=$(param_get $name) + check_err $? "Failed to get $name param value" + [ "$value" == "$expected_param_value" ] + check_err $? "Unexpected $phase_name $name param value" + value=$(<$DEBUGFS_DIR/$name) + check_err $? "Failed to get $name debugfs value" + [ "$value" == "$expected_debugfs_value" ] + check_err $? "Unexpected $phase_name $name debugfs value" +} + +params_test() +{ + RET=0 + + local max_macs + local test1 + + check_value max_macs initial 32 32 + check_value test1 initial true Y + + param_set max_macs 16 + check_err $? "Failed to set max_macs param value" + param_set test1 false + check_err $? "Failed to set test1 param value" + + check_value max_macs post-set 16 32 + check_value test1 post-set false Y + + devlink dev reload $DL_HANDLE + + check_value max_macs post-reload 16 16 + check_value test1 post-reload false N + + log_test "params test" +} + +check_region_size() +{ + local name=$1 + local size + + size=$(devlink region show $DL_HANDLE/$name -j | jq -e -r '.[][].size') + check_err $? "Failed to get $name region size" + [ $size -eq 32768 ] + check_err $? "Invalid $name region size" +} + +check_region_snapshot_count() +{ + local name=$1 + local phase_name=$2 + local expected_count=$3 + local count + + count=$(devlink region show $DL_HANDLE/$name -j | jq -e -r '.[][].snapshot | length') + [ $count -eq $expected_count ] + check_err $? "Unexpected $phase_name snapshot count" +} + +regions_test() +{ + RET=0 + + local count + + check_region_size dummy + check_region_snapshot_count dummy initial 0 + + echo ""> $DEBUGFS_DIR/take_snapshot + check_err $? "Failed to take first dummy region snapshot" + check_region_snapshot_count dummy post-first-snapshot 1 + + echo ""> $DEBUGFS_DIR/take_snapshot + check_err $? "Failed to take second dummy region snapshot" + check_region_snapshot_count dummy post-second-snapshot 2 + + echo ""> $DEBUGFS_DIR/take_snapshot + check_err $? "Failed to take third dummy region snapshot" + check_region_snapshot_count dummy post-third-snapshot 3 + + devlink region del $DL_HANDLE/dummy snapshot 1 + check_err $? "Failed to delete first dummy region snapshot" + + check_region_snapshot_count dummy post-first-delete 2 + + log_test "regions test" +} + setup_prepare() { modprobe netdevsim diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh new file mode 100755 index 000000000000..f101ab9441e2 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh @@ -0,0 +1,364 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking devlink-trap functionality. It makes use of +# netdevsim which implements the required callbacks. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + init_test + trap_action_test + trap_metadata_test + bad_trap_test + bad_trap_action_test + trap_stats_test + trap_group_action_test + bad_trap_group_test + trap_group_stats_test + port_del_test + dev_del_test +" +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR=1337 +DEV=netdevsim${DEV_ADDR} +DEVLINK_DEV=netdevsim/${DEV} +SLEEP_TIME=1 +NETDEV="" +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +require_command udevadm + +modprobe netdevsim &> /dev/null +if [ ! -d "$NETDEVSIM_PATH" ]; then + echo "SKIP: No netdevsim support" + exit 1 +fi + +if [ -d "${NETDEVSIM_PATH}/devices/netdevsim${DEV_ADDR}" ]; then + echo "SKIP: Device netdevsim${DEV_ADDR} already exists" + exit 1 +fi + +init_test() +{ + RET=0 + + test $(devlink_traps_num_get) -ne 0 + check_err $? "No traps were registered" + + log_test "Initialization" +} + +trap_action_test() +{ + local orig_action + local trap_name + local action + + RET=0 + + for trap_name in $(devlink_traps_get); do + # The action of non-drop traps cannot be changed. + if [ $(devlink_trap_type_get $trap_name) = "drop" ]; then + devlink_trap_action_set $trap_name "trap" + action=$(devlink_trap_action_get $trap_name) + if [ $action != "trap" ]; then + check_err 1 "Trap $trap_name did not change action to trap" + fi + + devlink_trap_action_set $trap_name "drop" + action=$(devlink_trap_action_get $trap_name) + if [ $action != "drop" ]; then + check_err 1 "Trap $trap_name did not change action to drop" + fi + else + orig_action=$(devlink_trap_action_get $trap_name) + + devlink_trap_action_set $trap_name "trap" + action=$(devlink_trap_action_get $trap_name) + if [ $action != $orig_action ]; then + check_err 1 "Trap $trap_name changed action when should not" + fi + + devlink_trap_action_set $trap_name "drop" + action=$(devlink_trap_action_get $trap_name) + if [ $action != $orig_action ]; then + check_err 1 "Trap $trap_name changed action when should not" + fi + fi + done + + log_test "Trap action" +} + +trap_metadata_test() +{ + local trap_name + + RET=0 + + for trap_name in $(devlink_traps_get); do + devlink_trap_metadata_test $trap_name "input_port" + check_err $? "Input port not reported as metadata of trap $trap_name" + done + + log_test "Trap metadata" +} + +bad_trap_test() +{ + RET=0 + + devlink_trap_action_set "made_up_trap" "drop" + check_fail $? "Did not get an error for non-existing trap" + + log_test "Non-existing trap" +} + +bad_trap_action_test() +{ + local traps_arr + local trap_name + + RET=0 + + # Pick first trap. + traps_arr=($(devlink_traps_get)) + trap_name=${traps_arr[0]} + + devlink_trap_action_set $trap_name "made_up_action" + check_fail $? "Did not get an error for non-existing trap action" + + log_test "Non-existing trap action" +} + +trap_stats_test() +{ + local trap_name + + RET=0 + + for trap_name in $(devlink_traps_get); do + devlink_trap_stats_idle_test $trap_name + check_err $? "Stats of trap $trap_name not idle when netdev down" + + ip link set dev $NETDEV up + + if [ $(devlink_trap_type_get $trap_name) = "drop" ]; then + devlink_trap_action_set $trap_name "trap" + devlink_trap_stats_idle_test $trap_name + check_fail $? "Stats of trap $trap_name idle when action is trap" + + devlink_trap_action_set $trap_name "drop" + devlink_trap_stats_idle_test $trap_name + check_err $? "Stats of trap $trap_name not idle when action is drop" + else + devlink_trap_stats_idle_test $trap_name + check_fail $? "Stats of non-drop trap $trap_name idle when should not" + fi + + ip link set dev $NETDEV down + done + + log_test "Trap statistics" +} + +trap_group_action_test() +{ + local curr_group group_name + local trap_name + local trap_type + local action + + RET=0 + + for group_name in $(devlink_trap_groups_get); do + devlink_trap_group_action_set $group_name "trap" + + for trap_name in $(devlink_traps_get); do + curr_group=$(devlink_trap_group_get $trap_name) + if [ $curr_group != $group_name ]; then + continue + fi + + trap_type=$(devlink_trap_type_get $trap_name) + if [ $trap_type != "drop" ]; then + continue + fi + + action=$(devlink_trap_action_get $trap_name) + if [ $action != "trap" ]; then + check_err 1 "Trap $trap_name did not change action to trap" + fi + done + + devlink_trap_group_action_set $group_name "drop" + + for trap_name in $(devlink_traps_get); do + curr_group=$(devlink_trap_group_get $trap_name) + if [ $curr_group != $group_name ]; then + continue + fi + + trap_type=$(devlink_trap_type_get $trap_name) + if [ $trap_type != "drop" ]; then + continue + fi + + action=$(devlink_trap_action_get $trap_name) + if [ $action != "drop" ]; then + check_err 1 "Trap $trap_name did not change action to drop" + fi + done + done + + log_test "Trap group action" +} + +bad_trap_group_test() +{ + RET=0 + + devlink_trap_group_action_set "made_up_trap_group" "drop" + check_fail $? "Did not get an error for non-existing trap group" + + log_test "Non-existing trap group" +} + +trap_group_stats_test() +{ + local group_name + + RET=0 + + for group_name in $(devlink_trap_groups_get); do + devlink_trap_group_stats_idle_test $group_name + check_err $? "Stats of trap group $group_name not idle when netdev down" + + ip link set dev $NETDEV up + + devlink_trap_group_action_set $group_name "trap" + devlink_trap_group_stats_idle_test $group_name + check_fail $? "Stats of trap group $group_name idle when action is trap" + + devlink_trap_group_action_set $group_name "drop" + ip link set dev $NETDEV down + done + + log_test "Trap group statistics" +} + +port_del_test() +{ + local group_name + local i + + # The test never fails. It is meant to exercise different code paths + # and make sure we properly dismantle a port while packets are + # in-flight. + RET=0 + + devlink_traps_enable_all + + for i in $(seq 1 10); do + ip link set dev $NETDEV up + + sleep $SLEEP_TIME + + netdevsim_port_destroy + netdevsim_port_create + udevadm settle + done + + devlink_traps_disable_all + + log_test "Port delete" +} + +dev_del_test() +{ + local group_name + local i + + # The test never fails. It is meant to exercise different code paths + # and make sure we properly unregister traps while packets are + # in-flight. + RET=0 + + devlink_traps_enable_all + + for i in $(seq 1 10); do + ip link set dev $NETDEV up + + sleep $SLEEP_TIME + + cleanup + setup_prepare + done + + devlink_traps_disable_all + + log_test "Device delete" +} + +netdevsim_dev_create() +{ + echo "$DEV_ADDR 0" > ${NETDEVSIM_PATH}/new_device +} + +netdevsim_dev_destroy() +{ + echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device +} + +netdevsim_port_create() +{ + echo 1 > ${NETDEVSIM_PATH}/devices/${DEV}/new_port +} + +netdevsim_port_destroy() +{ + echo 1 > ${NETDEVSIM_PATH}/devices/${DEV}/del_port +} + +setup_prepare() +{ + local netdev + + netdevsim_dev_create + + if [ ! -d "${NETDEVSIM_PATH}/devices/${DEV}" ]; then + echo "Failed to create netdevsim device" + exit 1 + fi + + netdevsim_port_create + + if [ ! -d "${NETDEVSIM_PATH}/devices/${DEV}/net/" ]; then + echo "Failed to create netdevsim port" + exit 1 + fi + + # Wait for udev to rename newly created netdev. + udevadm settle + + NETDEV=$(ls ${NETDEVSIM_PATH}/devices/${DEV}/net/) +} + +cleanup() +{ + pre_cleanup + netdevsim_port_destroy + netdevsim_dev_destroy +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 1b24e36b4047..0bd6b23c97ef 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -10,9 +10,9 @@ TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh -TEST_PROGS += tcp_fastopen_backup_key.sh +TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh TEST_PROGS_EXTENDED := in_netns.sh -TEST_GEN_FILES = socket +TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh new file mode 100755 index 000000000000..9fd3a0b97f0d --- /dev/null +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -0,0 +1,3432 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2019 David Ahern <dsahern@gmail.com>. All rights reserved. +# +# IPv4 and IPv6 functional tests focusing on VRF and routing lookups +# for various permutations: +# 1. icmp, tcp, udp and netfilter +# 2. client, server, no-server +# 3. global address on interface +# 4. global address on 'lo' +# 5. remote and local traffic +# 6. VRF and non-VRF permutations +# +# Setup: +# ns-A | ns-B +# No VRF case: +# [ lo ] [ eth1 ]---|---[ eth1 ] [ lo ] +# remote address +# VRF case: +# [ red ]---[ eth1 ]---|---[ eth1 ] [ lo ] +# +# ns-A: +# eth1: 172.16.1.1/24, 2001:db8:1::1/64 +# lo: 127.0.0.1/8, ::1/128 +# 172.16.2.1/32, 2001:db8:2::1/128 +# red: 127.0.0.1/8, ::1/128 +# 172.16.3.1/32, 2001:db8:3::1/128 +# +# ns-B: +# eth1: 172.16.1.2/24, 2001:db8:1::2/64 +# lo2: 127.0.0.1/8, ::1/128 +# 172.16.2.2/32, 2001:db8:2::2/128 +# +# server / client nomenclature relative to ns-A + +VERBOSE=0 + +NSA_DEV=eth1 +NSB_DEV=eth1 +VRF=red +VRF_TABLE=1101 + +# IPv4 config +NSA_IP=172.16.1.1 +NSB_IP=172.16.1.2 +VRF_IP=172.16.3.1 + +# IPv6 config +NSA_IP6=2001:db8:1::1 +NSB_IP6=2001:db8:1::2 +VRF_IP6=2001:db8:3::1 + +NSA_LO_IP=172.16.2.1 +NSB_LO_IP=172.16.2.2 +NSA_LO_IP6=2001:db8:2::1 +NSB_LO_IP6=2001:db8:2::2 + +MCAST=ff02::1 +# set after namespace create +NSA_LINKIP6= +NSB_LINKIP6= + +NSA=ns-A +NSB=ns-B + +NSA_CMD="ip netns exec ${NSA}" +NSB_CMD="ip netns exec ${NSB}" + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + [ "${VERBOSE}" = "1" ] && echo + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "TEST: %-70s [ OK ]\n" "${msg}" + else + nfail=$((nfail+1)) + printf "TEST: %-70s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + + kill_procs +} + +log_test_addr() +{ + local addr=$1 + local rc=$2 + local expected=$3 + local msg="$4" + local astr + + astr=$(addr2str ${addr}) + log_test $rc $expected "$msg - ${astr}" +} + +log_section() +{ + echo + echo "###########################################################################" + echo "$*" + echo "###########################################################################" + echo +} + +log_subsection() +{ + echo + echo "#################################################################" + echo "$*" + echo +} + +log_start() +{ + # make sure we have no test instances running + kill_procs + + if [ "${VERBOSE}" = "1" ]; then + echo + echo "#######################################################" + fi +} + +log_debug() +{ + if [ "${VERBOSE}" = "1" ]; then + echo + echo "$*" + echo + fi +} + +show_hint() +{ + if [ "${VERBOSE}" = "1" ]; then + echo "HINT: $*" + echo + fi +} + +kill_procs() +{ + killall nettest ping ping6 >/dev/null 2>&1 + sleep 1 +} + +do_run_cmd() +{ + local cmd="$*" + local out + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: ${cmd}" + fi + + out=$($cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo "$out" + fi + + return $rc +} + +run_cmd() +{ + do_run_cmd ${NSA_CMD} $* +} + +run_cmd_nsb() +{ + do_run_cmd ${NSB_CMD} $* +} + +setup_cmd() +{ + local cmd="$*" + local rc + + run_cmd ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + +setup_cmd_nsb() +{ + local cmd="$*" + local rc + + run_cmd_nsb ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + +# set sysctl values in NS-A +set_sysctl() +{ + echo "SYSCTL: $*" + echo + run_cmd sysctl -q -w $* +} + +################################################################################ +# Setup for tests + +addr2str() +{ + case "$1" in + 127.0.0.1) echo "loopback";; + ::1) echo "IPv6 loopback";; + + ${NSA_IP}) echo "ns-A IP";; + ${NSA_IP6}) echo "ns-A IPv6";; + ${NSA_LO_IP}) echo "ns-A loopback IP";; + ${NSA_LO_IP6}) echo "ns-A loopback IPv6";; + ${NSA_LINKIP6}|${NSA_LINKIP6}%*) echo "ns-A IPv6 LLA";; + + ${NSB_IP}) echo "ns-B IP";; + ${NSB_IP6}) echo "ns-B IPv6";; + ${NSB_LO_IP}) echo "ns-B loopback IP";; + ${NSB_LO_IP6}) echo "ns-B loopback IPv6";; + ${NSB_LINKIP6}|${NSB_LINKIP6}%*) echo "ns-B IPv6 LLA";; + + ${VRF_IP}) echo "VRF IP";; + ${VRF_IP6}) echo "VRF IPv6";; + + ${MCAST}%*) echo "multicast IP";; + + *) echo "unknown";; + esac +} + +get_linklocal() +{ + local ns=$1 + local dev=$2 + local addr + + addr=$(ip -netns ${ns} -6 -br addr show dev ${dev} | \ + awk '{ + for (i = 3; i <= NF; ++i) { + if ($i ~ /^fe80/) + print $i + } + }' + ) + addr=${addr/\/*} + + [ -z "$addr" ] && return 1 + + echo $addr + + return 0 +} + +################################################################################ +# create namespaces and vrf + +create_vrf() +{ + local ns=$1 + local vrf=$2 + local table=$3 + local addr=$4 + local addr6=$5 + + ip -netns ${ns} link add ${vrf} type vrf table ${table} + ip -netns ${ns} link set ${vrf} up + ip -netns ${ns} route add vrf ${vrf} unreachable default metric 8192 + ip -netns ${ns} -6 route add vrf ${vrf} unreachable default metric 8192 + + ip -netns ${ns} addr add 127.0.0.1/8 dev ${vrf} + ip -netns ${ns} -6 addr add ::1 dev ${vrf} nodad + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev ${vrf} ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev ${vrf} ${addr6} + fi + + ip -netns ${ns} ru del pref 0 + ip -netns ${ns} ru add pref 32765 from all lookup local + ip -netns ${ns} -6 ru del pref 0 + ip -netns ${ns} -6 ru add pref 32765 from all lookup local +} + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + + ip -netns ${ns1} li add ${ns1_dev} type veth peer name tmp + ip -netns ${ns1} li set ${ns1_dev} up + ip -netns ${ns1} li set tmp netns ${ns2} name ${ns2_dev} + ip -netns ${ns2} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr6} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr6} + fi +} + +cleanup() +{ + # explicit cleanups to check those code paths + ip netns | grep -q ${NSA} + if [ $? -eq 0 ]; then + ip -netns ${NSA} link delete ${VRF} + ip -netns ${NSA} ro flush table ${VRF_TABLE} + + ip -netns ${NSA} addr flush dev ${NSA_DEV} + ip -netns ${NSA} -6 addr flush dev ${NSA_DEV} + ip -netns ${NSA} link set dev ${NSA_DEV} down + ip -netns ${NSA} link del dev ${NSA_DEV} + + ip netns del ${NSA} + fi + + ip netns del ${NSB} +} + +setup() +{ + local with_vrf=${1} + + # make sure we are starting with a clean slate + kill_procs + cleanup 2>/dev/null + + log_debug "Configuring network namespaces" + set -e + + create_ns ${NSA} ${NSA_LO_IP}/32 ${NSA_LO_IP6}/128 + create_ns ${NSB} ${NSB_LO_IP}/32 ${NSB_LO_IP6}/128 + connect_ns ${NSA} ${NSA_DEV} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSB} ${NSB_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 + + NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV}) + NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV}) + + # tell ns-A how to get to remote addresses of ns-B + if [ "${with_vrf}" = "yes" ]; then + create_vrf ${NSA} ${VRF} ${VRF_TABLE} ${VRF_IP} ${VRF_IP6} + + ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF} + ip -netns ${NSA} ro add vrf ${VRF} ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} + ip -netns ${NSA} -6 ro add vrf ${VRF} ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} + + ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} + ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + else + ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} + ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} + fi + + + # tell ns-B how to get to remote addresses of ns-A + ip -netns ${NSB} ro add ${NSA_LO_IP}/32 via ${NSA_IP} dev ${NSB_DEV} + ip -netns ${NSB} ro add ${NSA_LO_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + + set +e + + sleep 1 +} + +################################################################################ +# IPv4 + +ipv4_ping_novrf() +{ + local a + + # + # out + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping out" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_LO_IP} ${a} + log_test_addr ${a} $? 0 "ping out, address bind" + done + + # + # in + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping local" + done + + # + # local traffic, socket bound to device + # + # address on device + a=${NSA_IP} + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + + # loopback addresses not reachable from device bind + # fails in a really weird way though because ipv4 special cases + # route lookups with oif set. + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Fails since address on loopback device is out of device scope" + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 1 "ping local, device bind" + done + + # + # ip rule blocks reachability to remote address + # + log_start + setup_cmd ip rule add pref 32765 from all lookup local + setup_cmd ip rule del pref 0 from all lookup local + setup_cmd ip rule add pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule add pref 51 from ${NSB_IP} prohibit + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite the rule + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + + a=${NSA_LO_IP} + log_start + show_hint "Response generates ICMP (or arp request is ignored) due to ip rule" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + [ "$VERBOSE" = "1" ] && echo + setup_cmd ip rule del pref 32765 from all lookup local + setup_cmd ip rule add pref 0 from all lookup local + setup_cmd ip rule del pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule del pref 51 from ${NSB_IP} prohibit + + # + # route blocks reachability to remote address + # + log_start + setup_cmd ip route replace unreachable ${NSB_LO_IP} + setup_cmd ip route replace unreachable ${NSB_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by route" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite not having a route for the address + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + + a=${NSA_LO_IP} + log_start + show_hint "Response is dropped (or arp request is ignored) due to ip route" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by route" + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip ro del ${NSB_LO_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable default route" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite not having a route for the address + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} +} + +ipv4_ping_vrf() +{ + local a + + # should default on; does not exist on older kernels + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + + # + # out + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping out, VRF bind" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ip vrf exec ${VRF} ping -c1 -w1 -I ${NSA_IP} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device + dev address bind" + + log_start + run_cmd ip vrf exec ${VRF} ping -c1 -w1 -I ${VRF_IP} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device + vrf address bind" + done + + # + # in + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic, local address + # + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Source address should be ${a}" + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping local, VRF bind" + done + + # + # local traffic, socket bound to device + # + # address on device + a=${NSA_IP} + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + + # vrf device is out of scope + for a in ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Fails since address on vrf device is out of device scope" + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 1 "ping local, device bind" + done + + # + # ip rule blocks address + # + log_start + setup_cmd ip rule add pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule add pref 51 from ${NSB_IP} prohibit + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 2 "ping out, vrf bind, blocked by rule" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + [ "$VERBOSE" = "1" ] && echo + setup_cmd ip rule del pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule del pref 51 from ${NSB_IP} prohibit + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip ro del vrf ${VRF} ${NSB_LO_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 2 "ping out, vrf bind, unreachable route" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" + + a=${NSA_LO_IP} + log_start + show_hint "Response lost by unreachable route" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, unreachable route" +} + +ipv4_ping() +{ + log_section "IPv4 ping" + + log_subsection "No VRF" + setup + set_sysctl net.ipv4.raw_l3mdev_accept=0 2>/dev/null + ipv4_ping_novrf + setup + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + ipv4_ping_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_ping_vrf +} + +################################################################################ +# IPv4 TCP + +ipv4_tcp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # verify TCP reset sent and received + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" +} + +ipv4_tcp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "Global server" + + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # verify TCP reset received + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + # (${VRF_IP} and 127.0.0.1 both timeout) + a=${NSA_IP} + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, local connection" + + # + # enable VRF global server + # + log_subsection "VRF Global server enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "client socket should be bound to VRF" + run_cmd nettest -s -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + show_hint "client socket should be bound to VRF" + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + # verify TCP reset received + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + a=${NSA_IP} + log_start + show_hint "client socket should be bound to device" + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # local address tests + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Should fail 'No route to host' since client is not bound to VRF" + run_cmd nettest -s -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "Global server, local connection" + done + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} + log_test_addr ${a} $? 0 "Client, VRF bind" + + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "No server, VRF client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local connection" + + log_start + show_hint "Should fail 'No route to host' since client is out of VRF scope" + run_cmd nettest -s -d ${VRF} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "VRF server, unbound client, local connection" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local connection" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" +} + +ipv4_tcp() +{ + log_section "IPv4/TCP" + log_subsection "No VRF" + setup + + # tcp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "tcp_l3mdev_accept disabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + ipv4_tcp_novrf + log_subsection "tcp_l3mdev_accept enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + ipv4_tcp_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_tcp_vrf +} + +################################################################################ +# IPv4 UDP + +ipv4_udp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + a=${NSA_IP} + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device send via cmsg" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device bind via IP_UNICAST_IF" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused' since address is out of device scope" + run_cmd nettest -s -D -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -C -r ${a} + log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection" + + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -S -r ${a} + log_test_addr ${a} $? 0 "Global server, device client via IP_UNICAST_IF, local connection" + + # IPv4 with device bind has really weird behavior - it overrides the + # fib lookup, generates an rtable and tries to send the packet. This + # causes failures for local traffic at different places + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 2 "Global server, device client, local connection" + + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C + log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection" + + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S + log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -D -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 2 "No server, device client, local conn" +} + +ipv4_udp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Fails because ingress is in a VRF and global server is disabled" + run_cmd nettest -D -s & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "Global server" + + log_start + run_cmd nettest -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + + log_start + show_hint "Should fail 'Connection refused' since global server is out of scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "Global server, VRF client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, enslaved device client, local connection" + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + # enable global server + log_subsection "Global server enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client tests + # + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -d ${VRF} -D -r ${NSB_IP} -1 ${NSA_IP} + log_test $? 0 "VRF client" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -d ${NSA_DEV} -D -r ${NSB_IP} -1 ${NSA_IP} + log_test $? 0 "Enslaved device client" + + # negative test - should fail + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${VRF} -r ${NSB_IP} + log_test $? 1 "No server, VRF client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${NSA_DEV} -r ${NSB_IP} + log_test $? 1 "No server, enslaved device client" + + # + # local address tests + # + a=${NSA_IP} + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + for a in ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -D -s -2 ${VRF} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + done + + for a in ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + done + + # negative test - should fail + # verifies ECONNREFUSED + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "No server, VRF client, local conn" + done +} + +ipv4_udp() +{ + log_section "IPv4/UDP" + log_subsection "No VRF" + + setup + + # udp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "udp_l3mdev_accept disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + ipv4_udp_novrf + log_subsection "udp_l3mdev_accept enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + ipv4_udp_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_udp_vrf +} + +################################################################################ +# IPv4 address bind +# +# verifies ability or inability to bind to an address / device + +ipv4_addr_bind_novrf() +{ + # + # raw socket + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -s -R -P icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + # + # tcp sockets + # + a=${NSA_IP} + log_start + run_cmd nettest -l ${a} -r ${NSB_IP} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -l ${a} -r ${NSB_IP} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. The only restriction + # is that the address is valid in the L3 domain. So this test + # passes when it really should not + #a=${NSA_LO_IP} + #log_start + #show_hint "Should fail with 'Cannot assign requested address'" + #run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + #log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" +} + +ipv4_addr_bind_vrf() +{ + # + # raw socket + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s -R -P icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after VRF bind" + done + + a=${NSA_LO_IP} + log_start + show_hint "Address on loopback is out of VRF scope" + run_cmd nettest -s -R -P icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind" + + # + # tcp sockets + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + done + + a=${NSA_LO_IP} + log_start + show_hint "Address on loopback out of scope for VRF" + run_cmd nettest -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for VRF" + + log_start + show_hint "Address on loopback out of scope for device in VRF" + run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for device bind" +} + +ipv4_addr_bind() +{ + log_section "IPv4 address binds" + + log_subsection "No VRF" + setup + ipv4_addr_bind_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_addr_bind_vrf +} + +################################################################################ +# IPv4 runtime tests + +ipv4_rt() +{ + local desc="$1" + local varg="$2" + local with_vrf="yes" + local a + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server" + + setup ${with_vrf} + done + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server" + + setup ${with_vrf} + done + + a=${NSA_IP} + log_start + run_cmd nettest ${varg} -s -d ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server" + + setup ${with_vrf} + + # + # client test + # + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF client" + + setup ${with_vrf} + + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device client" + + setup ${with_vrf} + + # + # local address tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, VRF client, local" + + setup ${with_vrf} + done + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server and client, local" + + setup ${with_vrf} + done + + a=${NSA_IP} + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, enslaved device client, local" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server, enslaved device client, local" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server and client, local" +} + +ipv4_ping_rt() +{ + local with_vrf="yes" + local a + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd_nsb ping -f ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping in" + + setup ${with_vrf} + done + + a=${NSB_IP} + log_start + run_cmd ping -f -I ${VRF} ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping out" +} + +ipv4_runtime() +{ + log_section "Run time tests - ipv4" + + setup "yes" + ipv4_ping_rt + + setup "yes" + ipv4_rt "TCP active socket" "-n -1" + + setup "yes" + ipv4_rt "TCP passive socket" "-i" +} + +################################################################################ +# IPv6 + +ipv6_ping_novrf() +{ + local a + + # should not have an impact, but make a known state + set_sysctl net.ipv4.raw_l3mdev_accept=0 2>/dev/null + + # + # out + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping out" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_LO_IP6} ${a} + log_test_addr ${a} $? 0 "ping out, loopback address bind" + done + + # + # in + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} ${MCAST}%${NSB_DEV} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic, local address + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping local, no bind" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + done + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Fails since address on loopback is out of device scope" + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping local, device bind" + done + + # + # ip rule blocks address + # + log_start + setup_cmd ip -6 rule add pref 32765 from all lookup local + setup_cmd ip -6 rule del pref 0 from all lookup local + setup_cmd ip -6 rule add pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule add pref 51 from ${NSB_IP6} prohibit + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + setup_cmd ip -6 rule add pref 0 from all lookup local + setup_cmd ip -6 rule del pref 32765 from all lookup local + setup_cmd ip -6 rule del pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule del pref 51 from ${NSB_IP6} prohibit + + # + # route blocks reachability to remote address + # + log_start + setup_cmd ip -6 route del ${NSB_LO_IP6} + setup_cmd ip -6 route add unreachable ${NSB_LO_IP6} metric 10 + setup_cmd ip -6 route add unreachable ${NSB_IP6} metric 10 + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by route" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip route" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by route" + + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip -6 ro del unreachable ${NSB_LO_IP6} + setup_cmd ip -6 ro del unreachable ${NSB_IP6} + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" +} + +ipv6_ping_vrf() +{ + local a + + # should default on; does not exist on older kernels + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + + # + # out + # + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping out, VRF bind" + done + + for a in ${NSB_LINKIP6}%${VRF} ${MCAST}%${VRF} + do + log_start + show_hint "Fails since VRF device does not support linklocal or multicast" + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, VRF bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd ip vrf exec ${VRF} ${ping6} -c1 -w1 -I ${VRF_IP6} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device+address bind" + done + + # + # in + # + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} ${MCAST}%${NSB_DEV} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + a=${NSA_LO_IP6} + log_start + show_hint "Fails since loopback address is out of VRF scope" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in" + + # + # local traffic, local address + # + for a in ${NSA_IP6} ${VRF_IP6} ::1 + do + log_start + show_hint "Source address should be ${a}" + run_cmd ${ping6} -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping local, VRF bind" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + done + + # LLA to GUA - remove ipv6 global addresses from ns-B + setup_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr del ${NSB_LO_IP6}/128 dev lo + setup_cmd_nsb ip -6 ro add ${NSA_IP6}/128 via ${NSA_LINKIP6} dev ${NSB_DEV} + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test_addr ${a} $? 0 "ping in, LLA to GUA" + done + + setup_cmd_nsb ip -6 ro del ${NSA_IP6}/128 via ${NSA_LINKIP6} dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr add ${NSB_LO_IP6}/128 dev lo + + # + # ip rule blocks address + # + log_start + setup_cmd ip -6 rule add pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule add pref 51 from ${NSB_IP6} prohibit + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + log_start + setup_cmd ip -6 rule del pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule del pref 51 from ${NSB_IP6} prohibit + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip -6 ro del ${NSB_LO_IP6} vrf ${VRF} + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" + + ip -netns ${NSB} -6 ro del ${NSA_LO_IP6} + a=${NSA_LO_IP6} + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping in, unreachable route" +} + +ipv6_ping() +{ + log_section "IPv6 ping" + + log_subsection "No VRF" + setup + ipv6_ping_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_ping_vrf +} + +################################################################################ +# IPv6 TCP + +ipv6_tcp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Client" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -6 -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + done +} + +ipv6_tcp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + # link local is always bound to ingress device + a=${NSA_LINKIP6}%${NSB_DEV} + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + a=${NSA_IP6} + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, local connection" + + # + # enable VRF global server + # + log_subsection "VRF Global server enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + # For LLA, child socket is bound to device + a=${NSA_LINKIP6}%${NSB_DEV} + log_start + run_cmd nettest -6 -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Fails 'No route to host' since client is not in VRF" + run_cmd nettest -6 -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server, local connection" + done + + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 0 "Client, VRF bind" + done + + a=${NSB_LINKIP6} + log_start + show_hint "Fails since VRF device does not allow linklocal addresses" + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "Client, VRF bind" + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "No server, VRF client" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + for a in ${NSA_IP6} ${VRF_IP6} ::1 + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local connection" + + a=${NSA_IP6} + log_start + show_hint "Should fail since unbound client is out of VRF scope" + run_cmd nettest -6 -s -d ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "VRF server, unbound client, local connection" + + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local connection" + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" + done +} + +ipv6_tcp() +{ + log_section "IPv6/TCP" + log_subsection "No VRF" + setup + + # tcp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "tcp_l3mdev_accept disabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + ipv6_tcp_novrf + log_subsection "tcp_l3mdev_accept enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + ipv6_tcp_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_tcp_vrf +} + +################################################################################ +# IPv6 UDP + +ipv6_udp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + a=${NSA_LO_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + # should fail since loopback address is out of scope for a device + # bound server, but it does not - hence this is more documenting + # behavior. + #log_start + #show_hint "Should fail since loopback address is out of scope" + #run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + #sleep 1 + #run_cmd_nsb nettest -6 -D -r ${a} + #log_test_addr ${a} $? 1 "Device server" + + # negative test - should fail + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device send via cmsg" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device bind via IPV6_UNICAST_IF" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 + do + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since address is out of device scope" + run_cmd nettest -6 -s -D -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "Device server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -C -r ${a} + log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection" + + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -S -r ${a} + log_test_addr ${a} $? 0 "Global server, device client via IPV6_UNICAST_IF, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C + log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection" + + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S + log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + + # LLA to GUA + run_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${NSA_IP6} + log_test $? 0 "UDP in - LLA to GUA" + + run_cmd_nsb ip -6 ro del ${NSA_IP6}/128 dev ${NSB_DEV} + run_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} nodad +} + +ipv6_udp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + done + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "Global server, VRF client, local conn" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + done + + a=${NSA_IP6} + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "Global server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + # disable global server + log_subsection "Global server enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + done + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client tests + # + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${NSB_IP6} + log_test $? 0 "VRF client" + + # negative test - should fail + log_start + run_cmd nettest -6 -D -d ${VRF} -r ${NSB_IP6} + log_test $? 1 "No server, VRF client" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_IP6} + log_test $? 0 "Enslaved device client" + + # negative test - should fail + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_IP6} + log_test $? 1 "No server, enslaved device client" + + # + # local address tests + # + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + #log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + + a=${VRF_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "No server, VRF client, local conn" + done + + # device to global IP + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + + + # link local addresses + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd_nsb nettest -6 -D -d ${NSB_DEV} -r ${NSA_LINKIP6} + log_test $? 0 "Global server, linklocal IP" + + log_start + run_cmd_nsb nettest -6 -D -d ${NSB_DEV} -r ${NSA_LINKIP6} + log_test $? 1 "No server, linklocal IP" + + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_LINKIP6} + log_test $? 0 "Enslaved device client, linklocal IP" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_LINKIP6} + log_test $? 1 "No server, device client, peer linklocal IP" + + + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSA_LINKIP6} + log_test $? 0 "Enslaved device client, local conn - linklocal IP" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSA_LINKIP6} + log_test $? 1 "No server, device client, local conn - linklocal IP" + + # LLA to GUA + run_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${NSA_IP6} + log_test $? 0 "UDP in - LLA to GUA" + + run_cmd_nsb ip -6 ro del ${NSA_IP6}/128 dev ${NSB_DEV} + run_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} nodad +} + +ipv6_udp() +{ + # should not matter, but set to known state + set_sysctl net.ipv4.udp_early_demux=1 + + log_section "IPv6/UDP" + log_subsection "No VRF" + setup + + # udp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "udp_l3mdev_accept disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + ipv6_udp_novrf + log_subsection "udp_l3mdev_accept enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + ipv6_udp_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_udp_vrf +} + +################################################################################ +# IPv6 address bind + +ipv6_addr_bind_novrf() +{ + # + # raw socket + # + for a in ${NSA_IP6} ${NSA_LO_IP6} + do + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + # + # tcp sockets + # + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + + a=${NSA_LO_IP6} + log_start + show_hint "Should fail with 'Cannot assign requested address'" + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" +} + +ipv6_addr_bind_vrf() +{ + # + # raw socket + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after vrf bind" + + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + a=${NSA_LO_IP6} + log_start + show_hint "Address on loopback is out of VRF scope" + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 1 "Raw socket bind to invalid local address after vrf bind" + + # + # tcp sockets + # + # address on enslaved device is valid for the VRF or device in a VRF + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address with VRF bind" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind" + + a=${VRF_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind" + + a=${NSA_LO_IP6} + log_start + show_hint "Address on loopback out of scope for VRF" + run_cmd nettest -6 -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for VRF" + + log_start + show_hint "Address on loopback out of scope for device in VRF" + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for device bind" + +} + +ipv6_addr_bind() +{ + log_section "IPv6 address binds" + + log_subsection "No VRF" + setup + ipv6_addr_bind_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_addr_bind_vrf +} + +################################################################################ +# IPv6 runtime tests + +ipv6_rt() +{ + local desc="$1" + local varg="-6 $2" + local with_vrf="yes" + local a + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server" + + setup ${with_vrf} + done + + # + # client test + # + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP6} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test 0 0 "${desc}, VRF client" + + setup ${with_vrf} + + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP6} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test 0 0 "${desc}, enslaved device client" + + setup ${with_vrf} + + + # + # local address tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, VRF client" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server and client" + + setup ${with_vrf} + done + + a=${NSA_IP6} + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, device client" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server, device client" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, device server, device client" +} + +ipv6_ping_rt() +{ + local with_vrf="yes" + local a + + a=${NSA_IP6} + log_start + run_cmd_nsb ${ping6} -f ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping in" + + setup ${with_vrf} + + log_start + run_cmd ${ping6} -f ${NSB_IP6} -I ${VRF} & + sleep 1 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping out" +} + +ipv6_runtime() +{ + log_section "Run time tests - ipv6" + + setup "yes" + ipv6_ping_rt + + setup "yes" + ipv6_rt "TCP active socket" "-n -1" + + setup "yes" + ipv6_rt "TCP passive socket" "-i" + + setup "yes" + ipv6_rt "UDP active socket" "-D -n -1" +} + +################################################################################ +# netfilter blocking connections + +netfilter_tcp_reset() +{ + local a + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx" + done +} + +netfilter_icmp() +{ + local stype="$1" + local arg + local a + + [ "${stype}" = "UDP" ] && arg="-D" + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${arg} -s & + sleep 1 + run_cmd_nsb nettest ${arg} -r ${a} + log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach" + done +} + +ipv4_netfilter() +{ + log_section "IPv4 Netfilter" + log_subsection "TCP reset" + + setup "yes" + run_cmd iptables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset + + netfilter_tcp_reset + + log_start + log_subsection "ICMP unreachable" + + log_start + run_cmd iptables -F + run_cmd iptables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with icmp-port-unreachable + run_cmd iptables -A INPUT -p udp --dport 12345 -j REJECT --reject-with icmp-port-unreachable + + netfilter_icmp "TCP" + netfilter_icmp "UDP" + + log_start + iptables -F +} + +netfilter_tcp6_reset() +{ + local a + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx" + done +} + +netfilter_icmp6() +{ + local stype="$1" + local arg + local a + + [ "${stype}" = "UDP" ] && arg="$arg -D" + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s ${arg} & + sleep 1 + run_cmd_nsb nettest -6 ${arg} -r ${a} + log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach" + done +} + +ipv6_netfilter() +{ + log_section "IPv6 Netfilter" + log_subsection "TCP reset" + + setup "yes" + run_cmd ip6tables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset + + netfilter_tcp6_reset + + log_subsection "ICMP unreachable" + + log_start + run_cmd ip6tables -F + run_cmd ip6tables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with icmp6-port-unreachable + run_cmd ip6tables -A INPUT -p udp --dport 12345 -j REJECT --reject-with icmp6-port-unreachable + + netfilter_icmp6 "TCP" + netfilter_icmp6 "UDP" + + log_start + ip6tables -F +} + +################################################################################ +# specific use cases + +# VRF only. +# ns-A device enslaved to bridge. Verify traffic with and without +# br_netfilter module loaded. Repeat with SVI on bridge. +use_case_br() +{ + setup "yes" + + setup_cmd ip link set ${NSA_DEV} down + setup_cmd ip addr del dev ${NSA_DEV} ${NSA_IP}/24 + setup_cmd ip -6 addr del dev ${NSA_DEV} ${NSA_IP6}/64 + + setup_cmd ip link add br0 type bridge + setup_cmd ip addr add dev br0 ${NSA_IP}/24 + setup_cmd ip -6 addr add dev br0 ${NSA_IP6}/64 nodad + + setup_cmd ip li set ${NSA_DEV} master br0 + setup_cmd ip li set ${NSA_DEV} up + setup_cmd ip li set br0 up + setup_cmd ip li set br0 vrf ${VRF} + + rmmod br_netfilter 2>/dev/null + sleep 5 # DAD + + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0 ${NSB_IP} + log_test $? 0 "Bridge into VRF - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0 ${NSB_IP6} + log_test $? 0 "Bridge into VRF - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 ${NSA_IP} + log_test $? 0 "Bridge into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test $? 0 "Bridge into VRF - IPv6 ping in" + + modprobe br_netfilter + if [ $? -eq 0 ]; then + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0 ${NSB_IP} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0 ${NSB_IP6} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 ${NSA_IP} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv6 ping in" + fi + + setup_cmd ip li set br0 nomaster + setup_cmd ip li add br0.100 link br0 type vlan id 100 + setup_cmd ip li set br0.100 vrf ${VRF} up + setup_cmd ip addr add dev br0.100 172.16.101.1/24 + setup_cmd ip -6 addr add dev br0.100 2001:db8:101::1/64 nodad + + setup_cmd_nsb ip li add vlan100 link ${NSB_DEV} type vlan id 100 + setup_cmd_nsb ip addr add dev vlan100 172.16.101.2/24 + setup_cmd_nsb ip -6 addr add dev vlan100 2001:db8:101::2/64 nodad + setup_cmd_nsb ip li set vlan100 up + sleep 1 + + rmmod br_netfilter 2>/dev/null + + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0.100 172.16.101.2 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0.100 2001:db8:101::2 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 172.16.101.1 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 2001:db8:101::1 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping in" + + modprobe br_netfilter + if [ $? -eq 0 ]; then + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0.100 172.16.101.2 + log_test $? 0 "Bridge vlan into VRF with br_netfilter - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0.100 2001:db8:101::2 + log_test $? 0 "Bridge vlan into VRF with br_netfilter - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 172.16.101.1 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 2001:db8:101::1 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping in" + fi + + setup_cmd ip li del br0 2>/dev/null + setup_cmd_nsb ip li del vlan100 2>/dev/null +} + +use_cases() +{ + log_section "Use cases" + use_case_br +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -4 IPv4 tests only + -6 IPv6 tests only + -t <test> Test name/set to run + -p Pause on fail + -P Pause after each test + -v Be verbose +EOF +} + +################################################################################ +# main + +TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter" +TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter" +TESTS_OTHER="use_cases" + +PAUSE_ON_FAIL=no +PAUSE=no + +while getopts :46t:pPvh o +do + case $o in + 4) TESTS=ipv4;; + 6) TESTS=ipv6;; + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=1;; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +# +# show user test config +# +if [ -z "$TESTS" ]; then + TESTS="$TESTS_IPV4 $TESTS_IPV6 $TESTS_OTHER" +elif [ "$TESTS" = "ipv4" ]; then + TESTS="$TESTS_IPV4" +elif [ "$TESTS" = "ipv6" ]; then + TESTS="$TESTS_IPV6" +fi + +which nettest >/dev/null +if [ $? -ne 0 ]; then + echo "'nettest' command not found; skipping tests" + exit 0 +fi + +declare -i nfail=0 +declare -i nsuccess=0 + +for t in $TESTS +do + case $t in + ipv4_ping|ping) ipv4_ping;; + ipv4_tcp|tcp) ipv4_tcp;; + ipv4_udp|udp) ipv4_udp;; + ipv4_bind|bind) ipv4_addr_bind;; + ipv4_runtime) ipv4_runtime;; + ipv4_netfilter) ipv4_netfilter;; + + ipv6_ping|ping6) ipv6_ping;; + ipv6_tcp|tcp6) ipv6_tcp;; + ipv6_udp|udp6) ipv6_udp;; + ipv6_bind|bind6) ipv6_addr_bind;; + ipv6_runtime) ipv6_runtime;; + ipv6_netfilter) ipv6_netfilter;; + + use_cases) use_cases;; + + # setup namespaces and config, but do not run any tests + setup) setup; exit 0;; + vrf_setup) setup "yes"; exit 0;; + + help) echo "Test names: $TESTS"; exit 0;; + esac +done + +cleanup 2>/dev/null + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 8553a67a2322..13d03a6d85ba 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -4,19 +4,21 @@ ############################################################################## # Defines -DEVLINK_DEV=$(devlink port show "${NETIFS[p1]}" -j \ - | jq -r '.port | keys[]' | cut -d/ -f-2) -if [ -z "$DEVLINK_DEV" ]; then - echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it" - exit 1 -fi -if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then - echo "SKIP: devlink device's bus is not PCI" - exit 1 -fi +if [[ ! -v DEVLINK_DEV ]]; then + DEVLINK_DEV=$(devlink port show "${NETIFS[p1]}" -j \ + | jq -r '.port | keys[]' | cut -d/ -f-2) + if [ -z "$DEVLINK_DEV" ]; then + echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it" + exit 1 + fi + if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then + echo "SKIP: devlink device's bus is not PCI" + exit 1 + fi -DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ - -n | cut -d" " -f3) + DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ + -n | cut -d" " -f3) +fi ############################################################################## # Sanity checks @@ -27,6 +29,12 @@ if [ $? -ne 0 ]; then exit 1 fi +devlink help 2>&1 | grep trap &> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing devlink trap support" + exit 1 +fi + ############################################################################## # Devlink helpers @@ -190,3 +198,160 @@ devlink_tc_bind_pool_th_restore() devlink sb tc bind set $port tc $tc type $dir \ pool ${orig[0]} th ${orig[1]} } + +devlink_traps_num_get() +{ + devlink -j trap | jq '.[]["'$DEVLINK_DEV'"] | length' +} + +devlink_traps_get() +{ + devlink -j trap | jq -r '.[]["'$DEVLINK_DEV'"][].name' +} + +devlink_trap_type_get() +{ + local trap_name=$1; shift + + devlink -j trap show $DEVLINK_DEV trap $trap_name \ + | jq -r '.[][][].type' +} + +devlink_trap_action_set() +{ + local trap_name=$1; shift + local action=$1; shift + + # Pipe output to /dev/null to avoid expected warnings. + devlink trap set $DEVLINK_DEV trap $trap_name \ + action $action &> /dev/null +} + +devlink_trap_action_get() +{ + local trap_name=$1; shift + + devlink -j trap show $DEVLINK_DEV trap $trap_name \ + | jq -r '.[][][].action' +} + +devlink_trap_group_get() +{ + devlink -j trap show $DEVLINK_DEV trap $trap_name \ + | jq -r '.[][][].group' +} + +devlink_trap_metadata_test() +{ + local trap_name=$1; shift + local metadata=$1; shift + + devlink -jv trap show $DEVLINK_DEV trap $trap_name \ + | jq -e '.[][][].metadata | contains(["'$metadata'"])' \ + &> /dev/null +} + +devlink_trap_rx_packets_get() +{ + local trap_name=$1; shift + + devlink -js trap show $DEVLINK_DEV trap $trap_name \ + | jq '.[][][]["stats"]["rx"]["packets"]' +} + +devlink_trap_rx_bytes_get() +{ + local trap_name=$1; shift + + devlink -js trap show $DEVLINK_DEV trap $trap_name \ + | jq '.[][][]["stats"]["rx"]["bytes"]' +} + +devlink_trap_stats_idle_test() +{ + local trap_name=$1; shift + local t0_packets t0_bytes + local t1_packets t1_bytes + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + sleep 1 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + return 0 + else + return 1 + fi +} + +devlink_traps_enable_all() +{ + local trap_name + + for trap_name in $(devlink_traps_get); do + devlink_trap_action_set $trap_name "trap" + done +} + +devlink_traps_disable_all() +{ + for trap_name in $(devlink_traps_get); do + devlink_trap_action_set $trap_name "drop" + done +} + +devlink_trap_groups_get() +{ + devlink -j trap group | jq -r '.[]["'$DEVLINK_DEV'"][].name' +} + +devlink_trap_group_action_set() +{ + local group_name=$1; shift + local action=$1; shift + + # Pipe output to /dev/null to avoid expected warnings. + devlink trap group set $DEVLINK_DEV group $group_name action $action \ + &> /dev/null +} + +devlink_trap_group_rx_packets_get() +{ + local group_name=$1; shift + + devlink -js trap group show $DEVLINK_DEV group $group_name \ + | jq '.[][][]["stats"]["rx"]["packets"]' +} + +devlink_trap_group_rx_bytes_get() +{ + local group_name=$1; shift + + devlink -js trap group show $DEVLINK_DEV group $group_name \ + | jq '.[][][]["stats"]["rx"]["bytes"]' +} + +devlink_trap_group_stats_idle_test() +{ + local group_name=$1; shift + local t0_packets t0_bytes + local t1_packets t1_bytes + + t0_packets=$(devlink_trap_group_rx_packets_get $group_name) + t0_bytes=$(devlink_trap_group_rx_bytes_get $group_name) + + sleep 1 + + t1_packets=$(devlink_trap_group_rx_packets_get $group_name) + t1_bytes=$(devlink_trap_group_rx_bytes_get $group_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + return 0 + else + return 1 + fi +} diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9385dc971269..85c587a03c8a 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -250,6 +250,25 @@ setup_wait() sleep $WAIT_TIME } +cmd_jq() +{ + local cmd=$1 + local jq_exp=$2 + local ret + local output + + output="$($cmd)" + # it the command fails, return error right away + ret=$? + if [[ $ret -ne 0 ]]; then + return $ret + fi + output=$(echo $output | jq -r "$jq_exp") + echo $output + # return success only in case of non-empty output + [ ! -z "$output" ] +} + lldpad_app_wait_set() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index 9d3b64a2a264..315e934358d4 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -8,18 +8,9 @@ tc_check_packets() local id=$1 local handle=$2 local count=$3 - local ret - output="$(tc -j -s filter show $id)" - # workaround the jq bug which causes jq to return 0 in case input is "" - ret=$? - if [[ $ret -ne 0 ]]; then - return $ret - fi - echo $output | \ - jq -e ".[] \ - | select(.options.handle == $handle) \ - | select(.options.actions[0].stats.packets == $count)" \ - &> /dev/null - return $? + cmd_jq "tc -j -s filter show $id" \ + ".[] | select(.options.handle == $handle) | \ + select(.options.actions[0].stats.packets == $count)" \ + &> /dev/null } diff --git a/tools/testing/selftests/net/l2tp.sh b/tools/testing/selftests/net/l2tp.sh new file mode 100644 index 000000000000..5782433886fc --- /dev/null +++ b/tools/testing/selftests/net/l2tp.sh @@ -0,0 +1,382 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# L2TPv3 tunnel between 2 hosts +# +# host-1 | router | host-2 +# | | +# lo l2tp | | l2tp lo +# 172.16.101.1 172.16.1.1 | | 172.16.1.2 172.16.101.2 +# fc00:101::1 fc00:1::1 | | fc00:1::2 fc00:101::2 +# | | +# eth0 | | eth0 +# 10.1.1.1 | | 10.1.2.1 +# 2001:db8:1::1 | | 2001:db8:2::1 + +VERBOSE=0 +PAUSE_ON_FAIL=no + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +run_cmd() +{ + local ns + local cmd + local out + local rc + + ns="$1" + shift + cmd="$*" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + fi + + out=$(eval ip netns exec ${ns} ${cmd} 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +################################################################################ +# create namespaces and interconnects + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + [ -z "${addr}" ] && addr="-" + [ -z "${addr6}" ] && addr6="-" + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.accept_dad=0 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + + ip -netns ${ns1} li add ${ns1_dev} type veth peer name tmp + ip -netns ${ns1} li set ${ns1_dev} up + ip -netns ${ns1} li set tmp netns ${ns2} name ${ns2_dev} + ip -netns ${ns2} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr6} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr6} + fi +} + +################################################################################ +# test setup + +cleanup() +{ + local ns + + for ns in host-1 host-2 router + do + ip netns del ${ns} 2>/dev/null + done +} + +setup_l2tp_ipv4() +{ + # + # configure l2tpv3 tunnel on host-1 + # + ip -netns host-1 l2tp add tunnel tunnel_id 1041 peer_tunnel_id 1042 \ + encap ip local 10.1.1.1 remote 10.1.2.1 + ip -netns host-1 l2tp add session name l2tp4 tunnel_id 1041 \ + session_id 1041 peer_session_id 1042 + ip -netns host-1 link set dev l2tp4 up + ip -netns host-1 addr add dev l2tp4 172.16.1.1 peer 172.16.1.2 + + # + # configure l2tpv3 tunnel on host-2 + # + ip -netns host-2 l2tp add tunnel tunnel_id 1042 peer_tunnel_id 1041 \ + encap ip local 10.1.2.1 remote 10.1.1.1 + ip -netns host-2 l2tp add session name l2tp4 tunnel_id 1042 \ + session_id 1042 peer_session_id 1041 + ip -netns host-2 link set dev l2tp4 up + ip -netns host-2 addr add dev l2tp4 172.16.1.2 peer 172.16.1.1 + + # + # add routes to loopback addresses + # + ip -netns host-1 ro add 172.16.101.2/32 via 172.16.1.2 + ip -netns host-2 ro add 172.16.101.1/32 via 172.16.1.1 +} + +setup_l2tp_ipv6() +{ + # + # configure l2tpv3 tunnel on host-1 + # + ip -netns host-1 l2tp add tunnel tunnel_id 1061 peer_tunnel_id 1062 \ + encap ip local 2001:db8:1::1 remote 2001:db8:2::1 + ip -netns host-1 l2tp add session name l2tp6 tunnel_id 1061 \ + session_id 1061 peer_session_id 1062 + ip -netns host-1 link set dev l2tp6 up + ip -netns host-1 addr add dev l2tp6 fc00:1::1 peer fc00:1::2 + + # + # configure l2tpv3 tunnel on host-2 + # + ip -netns host-2 l2tp add tunnel tunnel_id 1062 peer_tunnel_id 1061 \ + encap ip local 2001:db8:2::1 remote 2001:db8:1::1 + ip -netns host-2 l2tp add session name l2tp6 tunnel_id 1062 \ + session_id 1062 peer_session_id 1061 + ip -netns host-2 link set dev l2tp6 up + ip -netns host-2 addr add dev l2tp6 fc00:1::2 peer fc00:1::1 + + # + # add routes to loopback addresses + # + ip -netns host-1 -6 ro add fc00:101::2/128 via fc00:1::2 + ip -netns host-2 -6 ro add fc00:101::1/128 via fc00:1::1 +} + +setup() +{ + # start clean + cleanup + + set -e + create_ns host-1 172.16.101.1/32 fc00:101::1/128 + create_ns host-2 172.16.101.2/32 fc00:101::2/128 + create_ns router + + connect_ns host-1 eth0 10.1.1.1/24 2001:db8:1::1/64 \ + router eth1 10.1.1.2/24 2001:db8:1::2/64 + + connect_ns host-2 eth0 10.1.2.1/24 2001:db8:2::1/64 \ + router eth2 10.1.2.2/24 2001:db8:2::2/64 + + ip -netns host-1 ro add 10.1.2.0/24 via 10.1.1.2 + ip -netns host-1 -6 ro add 2001:db8:2::/64 via 2001:db8:1::2 + + ip -netns host-2 ro add 10.1.1.0/24 via 10.1.2.2 + ip -netns host-2 -6 ro add 2001:db8:1::/64 via 2001:db8:2::2 + + setup_l2tp_ipv4 + setup_l2tp_ipv6 + set +e +} + +setup_ipsec() +{ + # + # IPv4 + # + run_cmd host-1 ip xfrm policy add \ + src 10.1.1.1 dst 10.1.2.1 dir out \ + tmpl proto esp mode transport + + run_cmd host-1 ip xfrm policy add \ + src 10.1.2.1 dst 10.1.1.1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip xfrm policy add \ + src 10.1.1.1 dst 10.1.2.1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip xfrm policy add \ + src 10.1.2.1 dst 10.1.1.1 dir out \ + tmpl proto esp mode transport + + ip -netns host-1 xfrm state add \ + src 10.1.1.1 dst 10.1.2.1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-1 xfrm state add \ + src 10.1.2.1 dst 10.1.1.1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 xfrm state add \ + src 10.1.1.1 dst 10.1.2.1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 xfrm state add \ + src 10.1.2.1 dst 10.1.1.1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + # + # IPV6 + # + run_cmd host-1 ip -6 xfrm policy add \ + src 2001:db8:1::1 dst 2001:db8:2::1 dir out \ + tmpl proto esp mode transport + + run_cmd host-1 ip -6 xfrm policy add \ + src 2001:db8:2::1 dst 2001:db8:1::1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip -6 xfrm policy add \ + src 2001:db8:1::1 dst 2001:db8:2::1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip -6 xfrm policy add \ + src 2001:db8:2::1 dst 2001:db8:1::1 dir out \ + tmpl proto esp mode transport + + ip -netns host-1 -6 xfrm state add \ + src 2001:db8:1::1 dst 2001:db8:2::1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-1 -6 xfrm state add \ + src 2001:db8:2::1 dst 2001:db8:1::1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 -6 xfrm state add \ + src 2001:db8:1::1 dst 2001:db8:2::1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 -6 xfrm state add \ + src 2001:db8:2::1 dst 2001:db8:1::1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport +} + +teardown_ipsec() +{ + run_cmd host-1 ip xfrm state flush + run_cmd host-1 ip xfrm policy flush + run_cmd host-2 ip xfrm state flush + run_cmd host-2 ip xfrm policy flush +} + +################################################################################ +# generate traffic through tunnel for various cases + +run_ping() +{ + local desc="$1" + + run_cmd host-1 ping -c1 -w1 172.16.1.2 + log_test $? 0 "IPv4 basic L2TP tunnel ${desc}" + + run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2 + log_test $? 0 "IPv4 route through L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2 + log_test $? 0 "IPv6 basic L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2 + log_test $? 0 "IPv6 route through L2TP tunnel ${desc}" +} + +run_tests() +{ + local desc + + setup + run_ping + + setup_ipsec + run_ping "- with IPsec" + run_cmd host-1 ping -c1 -w1 172.16.1.2 + log_test $? 0 "IPv4 basic L2TP tunnel ${desc}" + + run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2 + log_test $? 0 "IPv4 route through L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2 + log_test $? 0 "IPv6 basic L2TP tunnel - with IPsec" + + run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2 + log_test $? 0 "IPv6 route through L2TP tunnel - with IPsec" + + teardown_ipsec + run_ping "- after IPsec teardown" +} + +################################################################################ +# main + +declare -i nfail=0 +declare -i nsuccess=0 + +while getopts :pv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + *) exit 1;; + esac +done + +run_tests +cleanup + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c new file mode 100644 index 000000000000..c08f4db8330d --- /dev/null +++ b/tools/testing/selftests/net/nettest.c @@ -0,0 +1,1757 @@ +// SPDX-License-Identifier: GPL-2.0 +/* nettest - used for functional tests of networking APIs + * + * Copyright (c) 2013-2019 David Ahern <dsahern@gmail.com>. All rights reserved. + */ + +#define _GNU_SOURCE +#include <features.h> +#include <sys/types.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <linux/tcp.h> +#include <arpa/inet.h> +#include <net/if.h> +#include <netinet/in.h> +#include <netdb.h> +#include <fcntl.h> +#include <libgen.h> +#include <limits.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <time.h> +#include <errno.h> + +#ifndef IPV6_UNICAST_IF +#define IPV6_UNICAST_IF 76 +#endif +#ifndef IPV6_MULTICAST_IF +#define IPV6_MULTICAST_IF 17 +#endif + +#define DEFAULT_PORT 12345 + +#ifndef MAX +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +#endif +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + +struct sock_args { + /* local address */ + union { + struct in_addr in; + struct in6_addr in6; + } local_addr; + + /* remote address */ + union { + struct in_addr in; + struct in6_addr in6; + } remote_addr; + int scope_id; /* remote scope; v6 send only */ + + struct in_addr grp; /* multicast group */ + + unsigned int has_local_ip:1, + has_remote_ip:1, + has_grp:1, + has_expected_laddr:1, + has_expected_raddr:1, + bind_test_only:1; + + unsigned short port; + + int type; /* DGRAM, STREAM, RAW */ + int protocol; + int version; /* AF_INET/AF_INET6 */ + + int use_setsockopt; + int use_cmsg; + const char *dev; + int ifindex; + const char *password; + + /* expected addresses and device index for connection */ + int expected_ifindex; + + /* local address */ + union { + struct in_addr in; + struct in6_addr in6; + } expected_laddr; + + /* remote address */ + union { + struct in_addr in; + struct in6_addr in6; + } expected_raddr; +}; + +static int server_mode; +static unsigned int prog_timeout = 5; +static unsigned int interactive; +static int iter = 1; +static char *msg = "Hello world!"; +static int msglen; +static int quiet; +static int try_broadcast = 1; + +static char *timestamp(char *timebuf, int buflen) +{ + time_t now; + + now = time(NULL); + if (strftime(timebuf, buflen, "%T", localtime(&now)) == 0) { + memset(timebuf, 0, buflen); + strncpy(timebuf, "00:00:00", buflen-1); + } + + return timebuf; +} + +static void log_msg(const char *format, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stdout, "%s %s:", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, format); + vfprintf(stdout, format, args); + va_end(args); + + fflush(stdout); +} + +static void log_error(const char *format, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stderr, "%s %s:", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, format); + vfprintf(stderr, format, args); + va_end(args); + + fflush(stderr); +} + +static void log_err_errno(const char *fmt, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stderr, "%s %s: ", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, fmt); + vfprintf(stderr, fmt, args); + va_end(args); + + fprintf(stderr, ": %d: %s\n", errno, strerror(errno)); + fflush(stderr); +} + +static void log_address(const char *desc, struct sockaddr *sa) +{ + char addrstr[64]; + + if (quiet) + return; + + if (sa->sa_family == AF_INET) { + struct sockaddr_in *s = (struct sockaddr_in *) sa; + + log_msg("%s %s:%d", + desc, + inet_ntop(AF_INET, &s->sin_addr, addrstr, + sizeof(addrstr)), + ntohs(s->sin_port)); + + } else if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + + log_msg("%s [%s]:%d", + desc, + inet_ntop(AF_INET6, &s6->sin6_addr, addrstr, + sizeof(addrstr)), + ntohs(s6->sin6_port)); + } + + printf("\n"); + + fflush(stdout); +} + +static int tcp_md5sig(int sd, void *addr, socklen_t alen, const char *password) +{ + struct tcp_md5sig md5sig; + int keylen = password ? strlen(password) : 0; + int rc; + + memset(&md5sig, 0, sizeof(md5sig)); + memcpy(&md5sig.tcpm_addr, addr, alen); + md5sig.tcpm_keylen = keylen; + + if (keylen) + memcpy(md5sig.tcpm_key, password, keylen); + + rc = setsockopt(sd, IPPROTO_TCP, TCP_MD5SIG, &md5sig, sizeof(md5sig)); + if (rc < 0) { + /* ENOENT is harmless. Returned when a password is cleared */ + if (errno == ENOENT) + rc = 0; + else + log_err_errno("setsockopt(TCP_MD5SIG)"); + } + + return rc; +} + +static int tcp_md5_remote(int sd, struct sock_args *args) +{ + struct sockaddr_in sin = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 sin6 = { + .sin6_family = AF_INET6, + }; + void *addr; + int alen; + + switch (args->version) { + case AF_INET: + sin.sin_port = htons(args->port); + sin.sin_addr = args->remote_addr.in; + addr = &sin; + alen = sizeof(sin); + break; + case AF_INET6: + sin6.sin6_port = htons(args->port); + sin6.sin6_addr = args->remote_addr.in6; + addr = &sin6; + alen = sizeof(sin6); + break; + default: + log_error("unknown address family\n"); + exit(1); + } + + if (tcp_md5sig(sd, addr, alen, args->password)) + return -1; + + return 0; +} + +static int get_ifidx(const char *ifname) +{ + struct ifreq ifdata; + int sd, rc; + + if (!ifname || *ifname == '\0') + return -1; + + memset(&ifdata, 0, sizeof(ifdata)); + + strcpy(ifdata.ifr_name, ifname); + + sd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); + if (sd < 0) { + log_err_errno("socket failed"); + return -1; + } + + rc = ioctl(sd, SIOCGIFINDEX, (char *)&ifdata); + close(sd); + if (rc != 0) { + log_err_errno("ioctl(SIOCGIFINDEX) failed"); + return -1; + } + + return ifdata.ifr_ifindex; +} + +static int bind_to_device(int sd, const char *name) +{ + int rc; + + rc = setsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, strlen(name)+1); + if (rc < 0) + log_err_errno("setsockopt(SO_BINDTODEVICE)"); + + return rc; +} + +static int get_bind_to_device(int sd, char *name, size_t len) +{ + int rc; + socklen_t optlen = len; + + name[0] = '\0'; + rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); + if (rc < 0) + log_err_errno("setsockopt(SO_BINDTODEVICE)"); + + return rc; +} + +static int check_device(int sd, struct sock_args *args) +{ + int ifindex = 0; + char name[32]; + + if (get_bind_to_device(sd, name, sizeof(name))) + *name = '\0'; + else + ifindex = get_ifidx(name); + + log_msg(" bound to device %s/%d\n", + *name ? name : "<none>", ifindex); + + if (!args->expected_ifindex) + return 0; + + if (args->expected_ifindex != ifindex) { + log_error("Device index mismatch: expected %d have %d\n", + args->expected_ifindex, ifindex); + return 1; + } + + log_msg("Device index matches: expected %d have %d\n", + args->expected_ifindex, ifindex); + + return 0; +} + +static int set_pktinfo_v4(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_PKTINFO, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IP_PKTINFO)"); + + return rc; +} + +static int set_recvpktinfo_v6(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IPV6, IPV6_RECVPKTINFO, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IPV6_RECVPKTINFO)"); + + return rc; +} + +static int set_recverr_v4(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_RECVERR, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IP_RECVERR)"); + + return rc; +} + +static int set_recverr_v6(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IPV6, IPV6_RECVERR, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IPV6_RECVERR)"); + + return rc; +} + +static int set_unicast_if(int sd, int ifindex, int version) +{ + int opt = IP_UNICAST_IF; + int level = SOL_IP; + int rc; + + ifindex = htonl(ifindex); + + if (version == AF_INET6) { + opt = IPV6_UNICAST_IF; + level = SOL_IPV6; + } + rc = setsockopt(sd, level, opt, &ifindex, sizeof(ifindex)); + if (rc < 0) + log_err_errno("setsockopt(IP_UNICAST_IF)"); + + return rc; +} + +static int set_multicast_if(int sd, int ifindex) +{ + struct ip_mreqn mreq = { .imr_ifindex = ifindex }; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_MULTICAST_IF, &mreq, sizeof(mreq)); + if (rc < 0) + log_err_errno("setsockopt(IP_MULTICAST_IF)"); + + return rc; +} + +static int set_membership(int sd, uint32_t grp, uint32_t addr, int ifindex) +{ + uint32_t if_addr = addr; + struct ip_mreqn mreq; + int rc; + + if (addr == htonl(INADDR_ANY) && !ifindex) { + log_error("Either local address or device needs to be given for multicast membership\n"); + return -1; + } + + mreq.imr_multiaddr.s_addr = grp; + mreq.imr_address.s_addr = if_addr; + mreq.imr_ifindex = ifindex; + + rc = setsockopt(sd, IPPROTO_IP, IP_ADD_MEMBERSHIP, &mreq, sizeof(mreq)); + if (rc < 0) { + log_err_errno("setsockopt(IP_ADD_MEMBERSHIP)"); + return -1; + } + + return 0; +} + +static int set_broadcast(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_BROADCAST, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_BROADCAST)"); + rc = -1; + } + + return rc; +} + +static int set_reuseport(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_REUSEPORT)"); + rc = -1; + } + + return rc; +} + +static int set_reuseaddr(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_REUSEADDR)"); + rc = -1; + } + + return rc; +} + +static int str_to_uint(const char *str, int min, int max, unsigned int *value) +{ + int number; + char *end; + + errno = 0; + number = (unsigned int) strtoul(str, &end, 0); + + /* entire string should be consumed by conversion + * and value should be between min and max + */ + if (((*end == '\0') || (*end == '\n')) && (end != str) && + (errno != ERANGE) && (min <= number) && (number <= max)) { + *value = number; + return 0; + } + + return -1; +} + +static int expected_addr_match(struct sockaddr *sa, void *expected, + const char *desc) +{ + char addrstr[64]; + int rc = 0; + + if (sa->sa_family == AF_INET) { + struct sockaddr_in *s = (struct sockaddr_in *) sa; + struct in_addr *exp_in = (struct in_addr *) expected; + + if (s->sin_addr.s_addr != exp_in->s_addr) { + log_error("%s address does not match expected %s", + desc, + inet_ntop(AF_INET, exp_in, + addrstr, sizeof(addrstr))); + rc = 1; + } + } else if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + struct in6_addr *exp_in = (struct in6_addr *) expected; + + if (memcmp(&s6->sin6_addr, exp_in, sizeof(*exp_in))) { + log_error("%s address does not match expected %s", + desc, + inet_ntop(AF_INET6, exp_in, + addrstr, sizeof(addrstr))); + rc = 1; + } + } else { + log_error("%s address does not match expected - unknown family", + desc); + rc = 1; + } + + if (!rc) + log_msg("%s address matches expected\n", desc); + + return rc; +} + +static int show_sockstat(int sd, struct sock_args *args) +{ + struct sockaddr_in6 local_addr, remote_addr; + socklen_t alen = sizeof(local_addr); + struct sockaddr *sa; + const char *desc; + int rc = 0; + + desc = server_mode ? "server local:" : "client local:"; + sa = (struct sockaddr *) &local_addr; + if (getsockname(sd, sa, &alen) == 0) { + log_address(desc, sa); + + if (args->has_expected_laddr) { + rc = expected_addr_match(sa, &args->expected_laddr, + "local"); + } + } else { + log_err_errno("getsockname failed"); + } + + sa = (struct sockaddr *) &remote_addr; + desc = server_mode ? "server peer:" : "client peer:"; + if (getpeername(sd, sa, &alen) == 0) { + log_address(desc, sa); + + if (args->has_expected_raddr) { + rc |= expected_addr_match(sa, &args->expected_raddr, + "remote"); + } + } else { + log_err_errno("getpeername failed"); + } + + return rc; +} + +static int get_index_from_cmsg(struct msghdr *m) +{ + struct cmsghdr *cm; + int ifindex = 0; + char buf[64]; + + for (cm = (struct cmsghdr *)CMSG_FIRSTHDR(m); + m->msg_controllen != 0 && cm; + cm = (struct cmsghdr *)CMSG_NXTHDR(m, cm)) { + + if (cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_PKTINFO) { + struct in_pktinfo *pi; + + pi = (struct in_pktinfo *)(CMSG_DATA(cm)); + inet_ntop(AF_INET, &pi->ipi_addr, buf, sizeof(buf)); + ifindex = pi->ipi_ifindex; + } else if (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *pi6; + + pi6 = (struct in6_pktinfo *)(CMSG_DATA(cm)); + inet_ntop(AF_INET6, &pi6->ipi6_addr, buf, sizeof(buf)); + ifindex = pi6->ipi6_ifindex; + } + } + + if (ifindex) { + log_msg(" pktinfo: ifindex %d dest addr %s\n", + ifindex, buf); + } + return ifindex; +} + +static int send_msg_no_cmsg(int sd, void *addr, socklen_t alen) +{ + int err; + +again: + err = sendto(sd, msg, msglen, 0, addr, alen); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + + log_err_errno("sendto failed"); + return 1; + } + + return 0; +} + +static int send_msg_cmsg(int sd, void *addr, socklen_t alen, + int ifindex, int version) +{ + unsigned char cmsgbuf[64]; + struct iovec iov[2]; + struct cmsghdr *cm; + struct msghdr m; + int err; + + iov[0].iov_base = msg; + iov[0].iov_len = msglen; + m.msg_iov = iov; + m.msg_iovlen = 1; + m.msg_name = (caddr_t)addr; + m.msg_namelen = alen; + + memset(cmsgbuf, 0, sizeof(cmsgbuf)); + cm = (struct cmsghdr *)cmsgbuf; + m.msg_control = (caddr_t)cm; + + if (version == AF_INET) { + struct in_pktinfo *pi; + + cm->cmsg_level = SOL_IP; + cm->cmsg_type = IP_PKTINFO; + cm->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo)); + pi = (struct in_pktinfo *)(CMSG_DATA(cm)); + pi->ipi_ifindex = ifindex; + + m.msg_controllen = cm->cmsg_len; + + } else if (version == AF_INET6) { + struct in6_pktinfo *pi6; + + cm->cmsg_level = SOL_IPV6; + cm->cmsg_type = IPV6_PKTINFO; + cm->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo)); + + pi6 = (struct in6_pktinfo *)(CMSG_DATA(cm)); + pi6->ipi6_ifindex = ifindex; + + m.msg_controllen = cm->cmsg_len; + } + +again: + err = sendmsg(sd, &m, 0); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + + log_err_errno("sendmsg failed"); + return 1; + } + + return 0; +} + + +static int send_msg(int sd, void *addr, socklen_t alen, struct sock_args *args) +{ + if (args->type == SOCK_STREAM) { + if (write(sd, msg, msglen) < 0) { + log_err_errno("write failed sending msg to peer"); + return 1; + } + } else if (args->ifindex && args->use_cmsg) { + if (send_msg_cmsg(sd, addr, alen, args->ifindex, args->version)) + return 1; + } else { + if (send_msg_no_cmsg(sd, addr, alen)) + return 1; + } + + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", msg, msglen > 24 ? " ..." : ""); + + return 0; +} + +static int socket_read_dgram(int sd, struct sock_args *args) +{ + unsigned char addr[sizeof(struct sockaddr_in6)]; + struct sockaddr *sa = (struct sockaddr *) addr; + socklen_t alen = sizeof(addr); + struct iovec iov[2]; + struct msghdr m = { + .msg_name = (caddr_t)addr, + .msg_namelen = alen, + .msg_iov = iov, + .msg_iovlen = 1, + }; + unsigned char cmsgbuf[256]; + struct cmsghdr *cm = (struct cmsghdr *)cmsgbuf; + char buf[16*1024]; + int ifindex; + int len; + + iov[0].iov_base = (caddr_t)buf; + iov[0].iov_len = sizeof(buf); + + memset(cmsgbuf, 0, sizeof(cmsgbuf)); + m.msg_control = (caddr_t)cm; + m.msg_controllen = sizeof(cmsgbuf); + + len = recvmsg(sd, &m, 0); + if (len == 0) { + log_msg("peer closed connection.\n"); + return 0; + } else if (len < 0) { + log_msg("failed to read message: %d: %s\n", + errno, strerror(errno)); + return -1; + } + + buf[len] = '\0'; + + log_address("Message from:", sa); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + ifindex = get_index_from_cmsg(&m); + if (args->expected_ifindex) { + if (args->expected_ifindex != ifindex) { + log_error("Device index mismatch: expected %d have %d\n", + args->expected_ifindex, ifindex); + return -1; + } + log_msg("Device index matches: expected %d have %d\n", + args->expected_ifindex, ifindex); + } + + if (!interactive && server_mode) { + if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + struct in6_addr *in6 = &s6->sin6_addr; + + if (IN6_IS_ADDR_V4MAPPED(in6)) { + const uint32_t *pa = (uint32_t *) &in6->s6_addr; + struct in_addr in4; + struct sockaddr_in *sin; + + sin = (struct sockaddr_in *) addr; + pa += 3; + in4.s_addr = *pa; + sin->sin_addr = in4; + sin->sin_family = AF_INET; + if (send_msg_cmsg(sd, addr, alen, + ifindex, AF_INET) < 0) + goto out_err; + } + } +again: + iov[0].iov_len = len; + + if (args->version == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + + if (args->dev) { + /* avoid PKTINFO conflicts with bindtodev */ + if (sendto(sd, buf, len, 0, + (void *) addr, alen) < 0) + goto out_err; + } else { + /* kernel is allowing scope_id to be set to VRF + * index for LLA. for sends to global address + * reset scope id + */ + s6->sin6_scope_id = ifindex; + if (sendmsg(sd, &m, 0) < 0) + goto out_err; + } + } else { + int err; + + err = sendmsg(sd, &m, 0); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + goto out_err; + } + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + } + + return 1; +out_err: + log_err_errno("failed to send msg to peer"); + return -1; +} + +static int socket_read_stream(int sd) +{ + char buf[1024]; + int len; + + len = read(sd, buf, sizeof(buf)-1); + if (len == 0) { + log_msg("client closed connection.\n"); + return 0; + } else if (len < 0) { + log_msg("failed to read message\n"); + return -1; + } + + buf[len] = '\0'; + log_msg("Incoming message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + if (!interactive && server_mode) { + if (write(sd, buf, len) < 0) { + log_err_errno("failed to send buf"); + return -1; + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + } + + return 1; +} + +static int socket_read(int sd, struct sock_args *args) +{ + if (args->type == SOCK_STREAM) + return socket_read_stream(sd); + + return socket_read_dgram(sd, args); +} + +static int stdin_to_socket(int sd, int type, void *addr, socklen_t alen) +{ + char buf[1024]; + int len; + + if (fgets(buf, sizeof(buf), stdin) == NULL) + return 0; + + len = strlen(buf); + if (type == SOCK_STREAM) { + if (write(sd, buf, len) < 0) { + log_err_errno("failed to send buf"); + return -1; + } + } else { + int err; + +again: + err = sendto(sd, buf, len, 0, addr, alen); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + log_err_errno("failed to send msg to peer"); + return -1; + } + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + return 1; +} + +static void set_recv_attr(int sd, int version) +{ + if (version == AF_INET6) { + set_recvpktinfo_v6(sd); + set_recverr_v6(sd); + } else { + set_pktinfo_v4(sd); + set_recverr_v4(sd); + } +} + +static int msg_loop(int client, int sd, void *addr, socklen_t alen, + struct sock_args *args) +{ + struct timeval timeout = { .tv_sec = prog_timeout }, *ptval = NULL; + fd_set rfds; + int nfds; + int rc; + + if (args->type != SOCK_STREAM) + set_recv_attr(sd, args->version); + + if (msg) { + msglen = strlen(msg); + + /* client sends first message */ + if (client) { + if (send_msg(sd, addr, alen, args)) + return 1; + } + if (!interactive) { + ptval = &timeout; + if (!prog_timeout) + timeout.tv_sec = 5; + } + } + + nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; + while (1) { + FD_ZERO(&rfds); + FD_SET(sd, &rfds); + if (interactive) + FD_SET(fileno(stdin), &rfds); + + rc = select(nfds, &rfds, NULL, NULL, ptval); + if (rc < 0) { + if (errno == EINTR) + continue; + + rc = 1; + log_err_errno("select failed"); + break; + } else if (rc == 0) { + log_error("Timed out waiting for response\n"); + rc = 2; + break; + } + + if (FD_ISSET(sd, &rfds)) { + rc = socket_read(sd, args); + if (rc < 0) { + rc = 1; + break; + } + if (rc == 0) + break; + } + + rc = 0; + + if (FD_ISSET(fileno(stdin), &rfds)) { + if (stdin_to_socket(sd, args->type, addr, alen) <= 0) + break; + } + + if (interactive) + continue; + + if (iter != -1) { + --iter; + if (iter == 0) + break; + } + + log_msg("Going into quiet mode\n"); + quiet = 1; + + if (client) { + if (send_msg(sd, addr, alen, args)) { + rc = 1; + break; + } + } + } + + return rc; +} + +static int msock_init(struct sock_args *args, int server) +{ + uint32_t if_addr = htonl(INADDR_ANY); + struct sockaddr_in laddr = { + .sin_family = AF_INET, + .sin_port = htons(args->port), + }; + int one = 1; + int sd; + + if (!server && args->has_local_ip) + if_addr = args->local_addr.in.s_addr; + + sd = socket(PF_INET, SOCK_DGRAM, 0); + if (sd < 0) { + log_err_errno("socket"); + return -1; + } + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)) < 0) { + log_err_errno("Setting SO_REUSEADDR error"); + goto out_err; + } + + if (setsockopt(sd, SOL_SOCKET, SO_BROADCAST, + (char *)&one, sizeof(one)) < 0) + log_err_errno("Setting SO_BROADCAST error"); + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto out_err; + else if (args->use_setsockopt && + set_multicast_if(sd, args->ifindex)) + goto out_err; + + laddr.sin_addr.s_addr = if_addr; + + if (bind(sd, (struct sockaddr *) &laddr, sizeof(laddr)) < 0) { + log_err_errno("bind failed"); + goto out_err; + } + + if (server && + set_membership(sd, args->grp.s_addr, + args->local_addr.in.s_addr, args->ifindex)) + goto out_err; + + return sd; +out_err: + close(sd); + return -1; +} + +static int msock_server(struct sock_args *args) +{ + return msock_init(args, 1); +} + +static int msock_client(struct sock_args *args) +{ + return msock_init(args, 0); +} + +static int bind_socket(int sd, struct sock_args *args) +{ + struct sockaddr_in serv_addr = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 serv6_addr = { + .sin6_family = AF_INET6, + }; + void *addr; + socklen_t alen; + + if (!args->has_local_ip && args->type == SOCK_RAW) + return 0; + + switch (args->version) { + case AF_INET: + serv_addr.sin_port = htons(args->port); + serv_addr.sin_addr = args->local_addr.in; + addr = &serv_addr; + alen = sizeof(serv_addr); + break; + + case AF_INET6: + serv6_addr.sin6_port = htons(args->port); + serv6_addr.sin6_addr = args->local_addr.in6; + addr = &serv6_addr; + alen = sizeof(serv6_addr); + break; + + default: + log_error("Invalid address family\n"); + return -1; + } + + if (bind(sd, addr, alen) < 0) { + log_err_errno("error binding socket"); + return -1; + } + + return 0; +} + +static int lsock_init(struct sock_args *args) +{ + long flags; + int sd; + + sd = socket(args->version, args->type, args->protocol); + if (sd < 0) { + log_err_errno("Error opening socket"); + return -1; + } + + if (set_reuseaddr(sd) != 0) + goto err; + + if (set_reuseport(sd) != 0) + goto err; + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto err; + else if (args->use_setsockopt && + set_unicast_if(sd, args->ifindex, args->version)) + goto err; + + if (bind_socket(sd, args)) + goto err; + + if (args->bind_test_only) + goto out; + + if (args->type == SOCK_STREAM && listen(sd, 1) < 0) { + log_err_errno("listen failed"); + goto err; + } + + flags = fcntl(sd, F_GETFL); + if ((flags < 0) || (fcntl(sd, F_SETFL, flags|O_NONBLOCK) < 0)) { + log_err_errno("Failed to set non-blocking option"); + goto err; + } + + if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0) + log_err_errno("Failed to set close-on-exec flag"); + +out: + return sd; + +err: + close(sd); + return -1; +} + +static int do_server(struct sock_args *args) +{ + struct timeval timeout = { .tv_sec = prog_timeout }, *ptval = NULL; + unsigned char addr[sizeof(struct sockaddr_in6)] = {}; + socklen_t alen = sizeof(addr); + int lsd, csd = -1; + + fd_set rfds; + int rc; + + if (prog_timeout) + ptval = &timeout; + + if (args->has_grp) + lsd = msock_server(args); + else + lsd = lsock_init(args); + + if (lsd < 0) + return 1; + + if (args->bind_test_only) { + close(lsd); + return 0; + } + + if (args->type != SOCK_STREAM) { + rc = msg_loop(0, lsd, (void *) addr, alen, args); + close(lsd); + return rc; + } + + if (args->password && tcp_md5_remote(lsd, args)) { + close(lsd); + return -1; + } + + while (1) { + log_msg("\n"); + log_msg("waiting for client connection.\n"); + FD_ZERO(&rfds); + FD_SET(lsd, &rfds); + + rc = select(lsd+1, &rfds, NULL, NULL, ptval); + if (rc == 0) { + rc = 2; + break; + } + + if (rc < 0) { + if (errno == EINTR) + continue; + + log_err_errno("select failed"); + break; + } + + if (FD_ISSET(lsd, &rfds)) { + + csd = accept(lsd, (void *) addr, &alen); + if (csd < 0) { + log_err_errno("accept failed"); + break; + } + + rc = show_sockstat(csd, args); + if (rc) + break; + + rc = check_device(csd, args); + if (rc) + break; + } + + rc = msg_loop(0, csd, (void *) addr, alen, args); + close(csd); + + if (!interactive) + break; + } + + close(lsd); + + return rc; +} + +static int wait_for_connect(int sd) +{ + struct timeval _tv = { .tv_sec = prog_timeout }, *tv = NULL; + fd_set wfd; + int val = 0, sz = sizeof(val); + int rc; + + FD_ZERO(&wfd); + FD_SET(sd, &wfd); + + if (prog_timeout) + tv = &_tv; + + rc = select(FD_SETSIZE, NULL, &wfd, NULL, tv); + if (rc == 0) { + log_error("connect timed out\n"); + return -2; + } else if (rc < 0) { + log_err_errno("select failed"); + return -3; + } + + if (getsockopt(sd, SOL_SOCKET, SO_ERROR, &val, (socklen_t *)&sz) < 0) { + log_err_errno("getsockopt(SO_ERROR) failed"); + return -4; + } + + if (val != 0) { + log_error("connect failed: %d: %s\n", val, strerror(val)); + return -1; + } + + return 0; +} + +static int connectsock(void *addr, socklen_t alen, struct sock_args *args) +{ + int sd, rc = -1; + long flags; + + sd = socket(args->version, args->type, args->protocol); + if (sd < 0) { + log_err_errno("Failed to create socket"); + return -1; + } + + flags = fcntl(sd, F_GETFL); + if ((flags < 0) || (fcntl(sd, F_SETFL, flags|O_NONBLOCK) < 0)) { + log_err_errno("Failed to set non-blocking option"); + goto err; + } + + if (set_reuseport(sd) != 0) + goto err; + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto err; + else if (args->use_setsockopt && + set_unicast_if(sd, args->ifindex, args->version)) + goto err; + + if (args->has_local_ip && bind_socket(sd, args)) + goto err; + + if (args->type != SOCK_STREAM) + goto out; + + if (args->password && tcp_md5sig(sd, addr, alen, args->password)) + goto err; + + if (args->bind_test_only) + goto out; + + if (connect(sd, addr, alen) < 0) { + if (errno != EINPROGRESS) { + log_err_errno("Failed to connect to remote host"); + rc = -1; + goto err; + } + rc = wait_for_connect(sd); + if (rc < 0) + goto err; + } +out: + return sd; + +err: + close(sd); + return rc; +} + +static int do_client(struct sock_args *args) +{ + struct sockaddr_in sin = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 sin6 = { + .sin6_family = AF_INET6, + }; + void *addr; + int alen; + int rc = 0; + int sd; + + if (!args->has_remote_ip && !args->has_grp) { + fprintf(stderr, "remote IP or multicast group not given\n"); + return 1; + } + + switch (args->version) { + case AF_INET: + sin.sin_port = htons(args->port); + if (args->has_grp) + sin.sin_addr = args->grp; + else + sin.sin_addr = args->remote_addr.in; + addr = &sin; + alen = sizeof(sin); + break; + case AF_INET6: + sin6.sin6_port = htons(args->port); + sin6.sin6_addr = args->remote_addr.in6; + sin6.sin6_scope_id = args->scope_id; + addr = &sin6; + alen = sizeof(sin6); + break; + } + + if (args->has_grp) + sd = msock_client(args); + else + sd = connectsock(addr, alen, args); + + if (sd < 0) + return -sd; + + if (args->bind_test_only) + goto out; + + if (args->type == SOCK_STREAM) { + rc = show_sockstat(sd, args); + if (rc != 0) + goto out; + } + + rc = msg_loop(1, sd, addr, alen, args); + +out: + close(sd); + + return rc; +} + +enum addr_type { + ADDR_TYPE_LOCAL, + ADDR_TYPE_REMOTE, + ADDR_TYPE_MCAST, + ADDR_TYPE_EXPECTED_LOCAL, + ADDR_TYPE_EXPECTED_REMOTE, +}; + +static int convert_addr(struct sock_args *args, const char *_str, + enum addr_type atype) +{ + int family = args->version; + struct in6_addr *in6; + struct in_addr *in; + const char *desc; + char *str, *dev; + void *addr; + int rc = 0; + + str = strdup(_str); + if (!str) + return -ENOMEM; + + switch (atype) { + case ADDR_TYPE_LOCAL: + desc = "local"; + addr = &args->local_addr; + break; + case ADDR_TYPE_REMOTE: + desc = "remote"; + addr = &args->remote_addr; + break; + case ADDR_TYPE_MCAST: + desc = "mcast grp"; + addr = &args->grp; + break; + case ADDR_TYPE_EXPECTED_LOCAL: + desc = "expected local"; + addr = &args->expected_laddr; + break; + case ADDR_TYPE_EXPECTED_REMOTE: + desc = "expected remote"; + addr = &args->expected_raddr; + break; + default: + log_error("unknown address type"); + exit(1); + } + + switch (family) { + case AF_INET: + in = (struct in_addr *) addr; + if (str) { + if (inet_pton(AF_INET, str, in) == 0) { + log_error("Invalid %s IP address\n", desc); + rc = -1; + goto out; + } + } else { + in->s_addr = htonl(INADDR_ANY); + } + break; + + case AF_INET6: + dev = strchr(str, '%'); + if (dev) { + *dev = '\0'; + dev++; + } + + in6 = (struct in6_addr *) addr; + if (str) { + if (inet_pton(AF_INET6, str, in6) == 0) { + log_error("Invalid %s IPv6 address\n", desc); + rc = -1; + goto out; + } + } else { + *in6 = in6addr_any; + } + if (dev) { + args->scope_id = get_ifidx(dev); + if (args->scope_id < 0) { + log_error("Invalid scope on %s IPv6 address\n", + desc); + rc = -1; + goto out; + } + } + break; + + default: + log_error("Invalid address family\n"); + } + +out: + free(str); + return rc; +} + +static char *random_msg(int len) +{ + int i, n = 0, olen = len + 1; + char *m; + + if (len <= 0) + return NULL; + + m = malloc(olen); + if (!m) + return NULL; + + while (len > 26) { + i = snprintf(m + n, olen - n, "%.26s", + "abcdefghijklmnopqrstuvwxyz"); + n += i; + len -= i; + } + i = snprintf(m + n, olen - n, "%.*s", len, + "abcdefghijklmnopqrstuvwxyz"); + return m; +} + +#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:d:SCi6L:0:1:2:Fbq" + +static void print_usage(char *prog) +{ + printf( + "usage: %s OPTS\n" + "Required:\n" + " -r addr remote address to connect to (client mode only)\n" + " -p port port to connect to (client mode)/listen on (server mode)\n" + " (default: %d)\n" + " -s server mode (default: client mode)\n" + " -t timeout seconds (default: none)\n" + "\n" + "Optional:\n" + " -F Restart server loop\n" + " -6 IPv6 (default is IPv4)\n" + " -P proto protocol for socket: icmp, ospf (default: none)\n" + " -D|R datagram (D) / raw (R) socket (default stream)\n" + " -l addr local address to bind to\n" + "\n" + " -d dev bind socket to given device name\n" + " -S use setsockopt (IP_UNICAST_IF or IP_MULTICAST_IF)\n" + " to set device binding\n" + " -C use cmsg and IP_PKTINFO to specify device binding\n" + "\n" + " -L len send random message of given length\n" + " -n num number of times to send message\n" + "\n" + " -M password use MD5 sum protection\n" + " -g grp multicast group (e.g., 239.1.1.1)\n" + " -i interactive mode (default is echo and terminate)\n" + "\n" + " -0 addr Expected local address\n" + " -1 addr Expected remote address\n" + " -2 dev Expected device name (or index) to receive packet\n" + "\n" + " -b Bind test only.\n" + " -q Be quiet. Run test without printing anything.\n" + , prog, DEFAULT_PORT); +} + +int main(int argc, char *argv[]) +{ + struct sock_args args = { + .version = AF_INET, + .type = SOCK_STREAM, + .port = DEFAULT_PORT, + }; + struct protoent *pe; + unsigned int tmp; + int forever = 0; + + /* process inputs */ + extern char *optarg; + int rc = 0; + + /* + * process input args + */ + + while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) { + switch (rc) { + case 's': + server_mode = 1; + break; + case 'F': + forever = 1; + break; + case 'l': + args.has_local_ip = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_LOCAL) < 0) + return 1; + break; + case 'r': + args.has_remote_ip = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_REMOTE) < 0) + return 1; + break; + case 'p': + if (str_to_uint(optarg, 1, 65535, &tmp) != 0) { + fprintf(stderr, "Invalid port\n"); + return 1; + } + args.port = (unsigned short) tmp; + break; + case 't': + if (str_to_uint(optarg, 0, INT_MAX, + &prog_timeout) != 0) { + fprintf(stderr, "Invalid timeout\n"); + return 1; + } + break; + case 'D': + args.type = SOCK_DGRAM; + break; + case 'R': + args.type = SOCK_RAW; + args.port = 0; + break; + case 'P': + pe = getprotobyname(optarg); + if (pe) { + args.protocol = pe->p_proto; + } else { + if (str_to_uint(optarg, 0, 0xffff, &tmp) != 0) { + fprintf(stderr, "Invalid protocol\n"); + return 1; + } + args.protocol = tmp; + } + break; + case 'n': + iter = atoi(optarg); + break; + case 'L': + msg = random_msg(atoi(optarg)); + break; + case 'M': + args.password = optarg; + break; + case 'S': + args.use_setsockopt = 1; + break; + case 'C': + args.use_cmsg = 1; + break; + case 'd': + args.dev = optarg; + args.ifindex = get_ifidx(optarg); + if (args.ifindex < 0) { + fprintf(stderr, "Invalid device name\n"); + return 1; + } + break; + case 'i': + interactive = 1; + break; + case 'g': + args.has_grp = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_MCAST) < 0) + return 1; + args.type = SOCK_DGRAM; + break; + case '6': + args.version = AF_INET6; + break; + case 'b': + args.bind_test_only = 1; + break; + case '0': + args.has_expected_laddr = 1; + if (convert_addr(&args, optarg, + ADDR_TYPE_EXPECTED_LOCAL)) + return 1; + break; + case '1': + args.has_expected_raddr = 1; + if (convert_addr(&args, optarg, + ADDR_TYPE_EXPECTED_REMOTE)) + return 1; + + break; + case '2': + if (str_to_uint(optarg, 0, INT_MAX, &tmp) == 0) { + args.expected_ifindex = (int)tmp; + } else { + args.expected_ifindex = get_ifidx(optarg); + if (args.expected_ifindex < 0) { + fprintf(stderr, + "Invalid expected device\n"); + return 1; + } + } + break; + case 'q': + quiet = 1; + break; + default: + print_usage(argv[0]); + return 1; + } + } + + if (args.password && + (!args.has_remote_ip || args.type != SOCK_STREAM)) { + log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); + return 1; + } + + if ((args.use_setsockopt || args.use_cmsg) && !args.ifindex) { + fprintf(stderr, "Device binding not specified\n"); + return 1; + } + if (args.use_setsockopt || args.use_cmsg) + args.dev = NULL; + + if (iter == 0) { + fprintf(stderr, "Invalid number of messages to send\n"); + return 1; + } + + if (args.type == SOCK_STREAM && !args.protocol) + args.protocol = IPPROTO_TCP; + if (args.type == SOCK_DGRAM && !args.protocol) + args.protocol = IPPROTO_UDP; + + if ((args.type == SOCK_STREAM || args.type == SOCK_DGRAM) && + args.port == 0) { + fprintf(stderr, "Invalid port number\n"); + return 1; + } + + if (!server_mode && !args.has_grp && + !args.has_remote_ip && !args.has_local_ip) { + fprintf(stderr, + "Local (server mode) or remote IP (client IP) required\n"); + return 1; + } + + if (interactive) { + prog_timeout = 0; + msg = NULL; + } + + if (server_mode) { + do { + rc = do_server(&args); + } while (forever); + + return rc; + } + return do_client(&args); +} diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README index 22e5da9008fd..b0954c873e2f 100644 --- a/tools/testing/selftests/tc-testing/README +++ b/tools/testing/selftests/tc-testing/README @@ -128,7 +128,9 @@ optional arguments: -v, --verbose Show the commands that are being run -N, --notap Suppress tap results for command under test -d DEVICE, --device DEVICE - Execute the test case in flower category + Execute test cases that use a physical device, where + DEVICE is its name. (If not defined, tests that require + a physical device will be skipped) -P, --pause Pause execution just before post-suite stage selection: diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json new file mode 100644 index 000000000000..5f24c0598624 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json @@ -0,0 +1,391 @@ +[ + { + "id": "f62b", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ip matchall action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "7f09", + "name": "Add egress matchall filter for protocol ipv4 and action PASS", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 1 protocol ip matchall action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 1 protocol ip matchall", + "matchPattern": "^filter parent 1: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "0596", + "name": "Add ingress matchall filter for protocol ipv6 and action DROP", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "41df", + "name": "Add egress matchall filter for protocol ipv6 and action DROP", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 1 protocol ipv6 matchall action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent 1: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "e1da", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS with priority at 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 65535 protocol ipv4 matchall action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 65535 protocol ipv4 matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "3de5", + "name": "Add egress matchall filter for protocol ipv4 and action PASS with priority at 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 65535 protocol ipv4 matchall action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 65535 protocol ipv4 matchall", + "matchPattern": "^filter parent 1: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "72d7", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS with priority exceeding 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 655355 protocol ipv4 matchall action pass", + "expExitCode": "255", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 655355 protocol ipv4 matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "41d3", + "name": "Add egress matchall filter for protocol ipv4 and action PASS with priority exceeding 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 655355 protocol ipv4 matchall action pass", + "expExitCode": "255", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 655355 protocol ipv4 matchall", + "matchPattern": "^filter parent 1: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "f755", + "name": "Add ingress matchall filter for all protocols and action CONTINUE with handle at 32-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0xffffffff prio 1 protocol all matchall action continue", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xffffffff prio 1 protocol all matchall", + "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "2c33", + "name": "Add egress matchall filter for all protocols and action CONTINUE with handle at 32-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0xffffffff prio 1 protocol all matchall action continue", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 0xffffffff prio 1 protocol all matchall", + "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "0e4a", + "name": "Add ingress matchall filter for all protocols and action RECLASSIFY with skip_hw flag", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall", + "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "7f60", + "name": "Add egress matchall filter for all protocols and action RECLASSIFY with skip_hw flag", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 0x1 prio 1 protocol all matchall", + "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "8bd2", + "name": "Add ingress matchall filter for protocol ipv6 and action PASS with classid", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:1 action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "2a4a", + "name": "Add ingress matchall filter for protocol ipv6 and action PASS with invalid classid", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 6789defg action pass", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 6789defg.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "eaf8", + "name": "Delete single ingress matchall filter", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:2 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:2.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "76ad", + "name": "Delete all ingress matchall filters", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x3 prio 3 protocol all matchall classid 1:4 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x4 prio 4 protocol all matchall classid 1:5 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff:", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", + "matchPattern": "^filter protocol all pref.*matchall.*handle.*flowid.*gact action pass", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "1eb9", + "name": "Delete single ingress matchall filter out of multiple", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x3 prio 3 protocol all matchall classid 1:4 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x4 prio 4 protocol all matchall classid 1:5 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol all handle 0x2 prio 2 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", + "matchPattern": "^filter protocol all pref 2 matchall.*handle 0x2 flowid 1:2.*gact action pass", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "6d63", + "name": "Delete ingress matchall filter by chain ID", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all chain 1 matchall classid 1:1 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv4 chain 2 matchall classid 1:3 action continue" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: chain 2", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", + "matchPattern": "^filter protocol all pref 1 matchall chain 1 handle 0x1 flowid 1:1.*gact action pass", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json new file mode 100644 index 000000000000..9de61fa10878 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json @@ -0,0 +1,304 @@ +[ + { + "id": "a519", + "name": "Add bfifo qdisc with system default parameters on egress", + "__comment": "When omitted, queue size in bfifo is calculated as: txqueuelen * (MTU + LinkLayerHdrSize), where LinkLayerHdrSize=14 for Ethernet", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root bfifo", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root.*limit [0-9]+b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root bfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "585c", + "name": "Add pfifo qdisc with system default parameters on egress", + "__comment": "When omitted, queue size in pfifo is defaulted to the interface's txqueuelen value.", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root pfifo", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc pfifo 1: root.*limit [0-9]+p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root pfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "a86e", + "name": "Add bfifo qdisc with system default parameters on egress with handle of maximum value", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 root handle ffff: bfifo", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo ffff: root.*limit [0-9]+b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle ffff: root bfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "9ac8", + "name": "Add bfifo qdisc on egress with queue size of 3000 bytes", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root bfifo limit 3000b", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root.*limit 3000b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root bfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "f4e6", + "name": "Add pfifo qdisc on egress with queue size of 3000 packets", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 txqueuelen 3000 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root pfifo limit 3000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc pfifo 1: root.*limit 3000p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root pfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "b1b1", + "name": "Add bfifo qdisc with system default parameters on egress with invalid handle exceeding maximum value", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 root handle 10000: bfifo", + "expExitCode": "255", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 10000: root.*limit [0-9]+b", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "8d5e", + "name": "Add bfifo qdisc on egress with unsupported argument", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root bfifo foorbar", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "7787", + "name": "Add pfifo qdisc on egress with unsupported argument", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root pfifo foorbar", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc pfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "c4b6", + "name": "Replace bfifo qdisc on egress with new queue size", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link del dev $DEV1 type dummy || /bin/true", + "$IP link add dev $DEV1 txqueuelen 1000 type dummy", + "$TC qdisc add dev $DEV1 handle 1: root bfifo" + ], + "cmdUnderTest": "$TC qdisc replace dev $DEV1 handle 1: root bfifo limit 3000b", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root.*limit 3000b", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root bfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "3df6", + "name": "Replace pfifo qdisc on egress with new queue size", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link del dev $DEV1 type dummy || /bin/true", + "$IP link add dev $DEV1 txqueuelen 1000 type dummy", + "$TC qdisc add dev $DEV1 handle 1: root pfifo" + ], + "cmdUnderTest": "$TC qdisc replace dev $DEV1 handle 1: root pfifo limit 30", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc pfifo 1: root.*limit 30p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root pfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "7a67", + "name": "Add bfifo qdisc on egress with queue size in invalid format", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root bfifo limit foo-bar", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root.*limit foo-bar", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "1298", + "name": "Add duplicate bfifo qdisc on egress", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 handle 1: root bfifo" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 handle 1: root bfifo", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root bfifo", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "45a0", + "name": "Delete nonexistent bfifo qdisc", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc del dev $DEV1 root handle 1: bfifo", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "972b", + "name": "Add prio qdisc on egress with invalid format for handles", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DEV1 root handle 123^ bfifo limit 100b", + "expExitCode": "255", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 123 root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "4d39", + "name": "Delete bfifo qdisc twice", + "category": [ + "qdisc", + "fifo" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: bfifo", + "$TC qdisc del dev $DEV1 root handle 1: bfifo" + ], + "cmdUnderTest": "$TC qdisc del dev $DEV1 handle 1: root bfifo", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc bfifo 1: root", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DEV1 type dummy" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index f04321ace9fb..e566c70e64a1 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -356,12 +356,14 @@ def test_runner(pm, args, filtered_tests): time.sleep(2) for tidx in testlist: if "flower" in tidx["category"] and args.device == None: + errmsg = "Tests using the DEV2 variable must define the name of a " + errmsg += "physical NIC with the -d option when running tdc.\n" + errmsg += "Test has been skipped." if args.verbose > 1: - print('Not executing test {} {} because DEV2 not defined'. - format(tidx['id'], tidx['name'])) + print(errmsg) res = TestResult(tidx['id'], tidx['name']) res.set_result(ResultState.skip) - res.set_errormsg('Not executed because DEV2 is not defined') + res.set_errormsg(errmsg) tsr.add_resultdata(res) continue try: @@ -499,7 +501,9 @@ def set_args(parser): choices=['none', 'xunit', 'tap'], help='Specify the format for test results. (Default: TAP)') parser.add_argument('-d', '--device', - help='Execute the test case in flower category') + help='Execute test cases that use a physical device, ' + + 'where DEVICE is its name. (If not defined, tests ' + + 'that require a physical device will be skipped)') parser.add_argument( '-P', '--pause', action='store_true', help='Pause execution just before post-suite stage') |