diff options
1061 files changed, 40420 insertions, 15733 deletions
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 4150f74c521a..f86b5e1623c6 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -365,6 +365,15 @@ new netns has been created. Default : 0 (for compatibility reasons) +txrehash +-------- + +Controls default hash rethink behaviour on listening socket when SO_TXREHASH +option is set to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt). + +If set to 1 (default), hash rethink is performed on listening socket. +If set to 0, hash rethink is not performed. + 2. /proc/sys/net/unix - Parameters for Unix domain sockets ---------------------------------------------------------- diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 1ebf4c5c7ddc..7940da9bc6c1 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -503,6 +503,19 @@ valid index (starting from 0) pointing to a member or an argument. * ``info.vlen``: 0 * ``type``: the type with ``btf_type_tag`` attribute +Currently, ``BTF_KIND_TYPE_TAG`` is only emitted for pointer types. +It has the following btf type chain: +:: + + ptr -> [type_tag]* + -> [const | volatile | restrict | typedef]* + -> base_type + +Basically, a pointer type points to zero or more +type_tag, then zero or more const/volatile/restrict/typedef +and finally the base type. The base type is one of +int, ptr, array, struct, union, enum, func_proto and float types. + 3. BTF Kernel API ================= @@ -565,18 +578,15 @@ A map can be created with ``btf_fd`` and specified key/value type id.:: In libbpf, the map can be defined with extra annotation like below: :: - struct bpf_map_def SEC("maps") btf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct ipv_counts), - .max_entries = 4, - }; - BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); + struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct ipv_counts); + __uint(max_entries, 4); + } btf_map SEC(".maps"); -Here, the parameters for macro BPF_ANNOTATE_KV_PAIR are map name, key and -value types for the map. During ELF parsing, libbpf is able to extract -key/value type_id's and assign them to BPF_MAP_CREATE attributes -automatically. +During ELF parsing, libbpf is able to extract key/value type_id's and assign +them to BPF_MAP_CREATE attributes automatically. .. _BPF_Prog_Load: @@ -824,13 +834,12 @@ structure has bitfields. For example, for the following map,:: ___A b1:4; enum A b2:4; }; - struct bpf_map_def SEC("maps") tmpmap = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tmp_t), - .max_entries = 1, - }; - BPF_ANNOTATE_KV_PAIR(tmpmap, int, struct tmp_t); + struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct tmp_t); + __uint(max_entries, 1); + } tmpmap SEC(".maps"); bpftool is able to pretty print like below: :: diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst index 3704836fe6df..5300837ac2c9 100644 --- a/Documentation/bpf/instruction-set.rst +++ b/Documentation/bpf/instruction-set.rst @@ -22,7 +22,13 @@ necessary across calls. Instruction encoding ==================== -eBPF uses 64-bit instructions with the following encoding: +eBPF has two instruction encodings: + + * the basic instruction encoding, which uses 64 bits to encode an instruction + * the wide instruction encoding, which appends a second 64-bit immediate value + (imm64) after the basic instruction for a total of 128 bits. + +The basic instruction encoding looks as follows: ============= ======= =============== ==================== ============ 32 bits (MSB) 16 bits 4 bits 4 bits 8 bits (LSB) @@ -82,9 +88,9 @@ BPF_ALU uses 32-bit wide operands while BPF_ALU64 uses 64-bit wide operands for otherwise identical operations. The code field encodes the operation as below: - ======== ===== ========================== + ======== ===== ================================================= code value description - ======== ===== ========================== + ======== ===== ================================================= BPF_ADD 0x00 dst += src BPF_SUB 0x10 dst -= src BPF_MUL 0x20 dst \*= src @@ -98,8 +104,8 @@ The code field encodes the operation as below: BPF_XOR 0xa0 dst ^= src BPF_MOV 0xb0 dst = src BPF_ARSH 0xc0 sign extending shift right - BPF_END 0xd0 endianness conversion - ======== ===== ========================== + BPF_END 0xd0 byte swap operations (see separate section below) + ======== ===== ================================================= BPF_ADD | BPF_X | BPF_ALU means:: @@ -118,6 +124,42 @@ BPF_XOR | BPF_K | BPF_ALU64 means:: src_reg = src_reg ^ imm32 +Byte swap instructions +---------------------- + +The byte swap instructions use an instruction class of ``BFP_ALU`` and a 4-bit +code field of ``BPF_END``. + +The byte swap instructions instructions operate on the destination register +only and do not use a separate source register or immediate value. + +The 1-bit source operand field in the opcode is used to to select what byte +order the operation convert from or to: + + ========= ===== ================================================= + source value description + ========= ===== ================================================= + BPF_TO_LE 0x00 convert between host byte order and little endian + BPF_TO_BE 0x08 convert between host byte order and big endian + ========= ===== ================================================= + +The imm field encodes the width of the swap operations. The following widths +are supported: 16, 32 and 64. + +Examples: + +``BPF_ALU | BPF_TO_LE | BPF_END`` with imm = 16 means:: + + dst_reg = htole16(dst_reg) + +``BPF_ALU | BPF_TO_BE | BPF_END`` with imm = 64 means:: + + dst_reg = htobe64(dst_reg) + +``BPF_FROM_LE`` and ``BPF_FROM_BE`` exist as aliases for ``BPF_TO_LE`` and +``BPF_TO_LE`` respetively. + + Jump instructions ----------------- @@ -176,63 +218,96 @@ The mode modifier is one of: ============= ===== ==================================== mode modifier value description ============= ===== ==================================== - BPF_IMM 0x00 used for 64-bit mov - BPF_ABS 0x20 legacy BPF packet access - BPF_IND 0x40 legacy BPF packet access - BPF_MEM 0x60 all normal load and store operations + BPF_IMM 0x00 64-bit immediate instructions + BPF_ABS 0x20 legacy BPF packet access (absolute) + BPF_IND 0x40 legacy BPF packet access (indirect) + BPF_MEM 0x60 regular load and store operations BPF_ATOMIC 0xc0 atomic operations ============= ===== ==================================== -BPF_MEM | <size> | BPF_STX means:: + +Regular load and store operations +--------------------------------- + +The ``BPF_MEM`` mode modifier is used to encode regular load and store +instructions that transfer data between a register and memory. + +``BPF_MEM | <size> | BPF_STX`` means:: *(size *) (dst_reg + off) = src_reg -BPF_MEM | <size> | BPF_ST means:: +``BPF_MEM | <size> | BPF_ST`` means:: *(size *) (dst_reg + off) = imm32 -BPF_MEM | <size> | BPF_LDX means:: +``BPF_MEM | <size> | BPF_LDX`` means:: dst_reg = *(size *) (src_reg + off) -Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. +Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW``. Atomic operations ----------------- -eBPF includes atomic operations, which use the immediate field for extra -encoding:: +Atomic operations are operations that operate on memory and can not be +interrupted or corrupted by other access to the same memory region +by other eBPF programs or means outside of this specification. + +All atomic operations supported by eBPF are encoded as store operations +that use the ``BPF_ATOMIC`` mode modifier as follows: + + * ``BPF_ATOMIC | BPF_W | BPF_STX`` for 32-bit operations + * ``BPF_ATOMIC | BPF_DW | BPF_STX`` for 64-bit operations + * 8-bit and 16-bit wide atomic operations are not supported. - .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_W | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg - .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg +The imm field is used to encode the actual atomic operation. +Simple atomic operation use a subset of the values defined to encode +arithmetic operations in the imm field to encode the atomic operation: -The basic atomic operations supported are:: + ======== ===== =========== + imm value description + ======== ===== =========== + BPF_ADD 0x00 atomic add + BPF_OR 0x40 atomic or + BPF_AND 0x50 atomic and + BPF_XOR 0xa0 atomic xor + ======== ===== =========== - BPF_ADD - BPF_AND - BPF_OR - BPF_XOR -Each having equivalent semantics with the ``BPF_ADD`` example, that is: the -memory location addresed by ``dst_reg + off`` is atomically modified, with -``src_reg`` as the other operand. If the ``BPF_FETCH`` flag is set in the -immediate, then these operations also overwrite ``src_reg`` with the -value that was in memory before it was modified. +``BPF_ATOMIC | BPF_W | BPF_STX`` with imm = BPF_ADD means:: -The more special operations are:: + *(u32 *)(dst_reg + off16) += src_reg - BPF_XCHG +``BPF_ATOMIC | BPF_DW | BPF_STX`` with imm = BPF ADD means:: -This atomically exchanges ``src_reg`` with the value addressed by ``dst_reg + -off``. :: + *(u64 *)(dst_reg + off16) += src_reg - BPF_CMPXCHG +``BPF_XADD`` is a deprecated name for ``BPF_ATOMIC | BPF_ADD``. -This atomically compares the value addressed by ``dst_reg + off`` with -``R0``. If they match it is replaced with ``src_reg``. In either case, the -value that was there before is zero-extended and loaded back to ``R0``. +In addition to the simple atomic operations, there also is a modifier and +two complex atomic operations: -Note that 1 and 2 byte atomic operations are not supported. + =========== ================ =========================== + imm value description + =========== ================ =========================== + BPF_FETCH 0x01 modifier: return old value + BPF_XCHG 0xe0 | BPF_FETCH atomic exchange + BPF_CMPXCHG 0xf0 | BPF_FETCH atomic compare and exchange + =========== ================ =========================== + +The ``BPF_FETCH`` modifier is optional for simple atomic operations, and +always set for the complex atomic operations. If the ``BPF_FETCH`` flag +is set, then the operation also overwrites ``src_reg`` with the value that +was in memory before it was modified. + +The ``BPF_XCHG`` operation atomically exchanges ``src_reg`` with the value +addressed by ``dst_reg + off``. + +The ``BPF_CMPXCHG`` operation atomically compares the value addressed by +``dst_reg + off`` with ``R0``. If they match, the value addressed by +``dst_reg + off`` is replaced with ``src_reg``. In either case, the +value that was at ``dst_reg + off`` before the operation is zero-extended +and loaded back to ``R0``. Clang can generate atomic instructions by default when ``-mcpu=v3`` is enabled. If a lower version for ``-mcpu`` is set, the only atomic instruction @@ -240,40 +315,52 @@ Clang can generate is ``BPF_ADD`` *without* ``BPF_FETCH``. If you need to enable the atomics features, while keeping a lower ``-mcpu`` version, you can use ``-Xclang -target-feature -Xclang +alu32``. -You may encounter ``BPF_XADD`` - this is a legacy name for ``BPF_ATOMIC``, -referring to the exclusive-add operation encoded when the immediate field is -zero. +64-bit immediate instructions +----------------------------- -16-byte instructions --------------------- +Instructions with the ``BPF_IMM`` mode modifier use the wide instruction +encoding for an extra imm64 value. -eBPF has one 16-byte instruction: ``BPF_LD | BPF_DW | BPF_IMM`` which consists -of two consecutive ``struct bpf_insn`` 8-byte blocks and interpreted as single -instruction that loads 64-bit immediate value into a dst_reg. +There is currently only one such instruction. -Packet access instructions --------------------------- +``BPF_LD | BPF_DW | BPF_IMM`` means:: -eBPF has two non-generic instructions: (BPF_ABS | <size> | BPF_LD) and -(BPF_IND | <size> | BPF_LD) which are used to access packet data. + dst_reg = imm64 -They had to be carried over from classic BPF to have strong performance of -socket filters running in eBPF interpreter. These instructions can only -be used when interpreter context is a pointer to ``struct sk_buff`` and -have seven implicit operands. Register R6 is an implicit input that must -contain pointer to sk_buff. Register R0 is an implicit output which contains -the data fetched from the packet. Registers R1-R5 are scratch registers -and must not be used to store the data across BPF_ABS | BPF_LD or -BPF_IND | BPF_LD instructions. -These instructions have implicit program exit condition as well. When -eBPF program is trying to access the data beyond the packet boundary, -the interpreter will abort the execution of the program. JIT compilers -therefore must preserve this property. src_reg and imm32 fields are -explicit inputs to these instructions. +Legacy BPF Packet access instructions +------------------------------------- -For example, BPF_IND | BPF_W | BPF_LD means:: +eBPF has special instructions for access to packet data that have been +carried over from classic BPF to retain the performance of legacy socket +filters running in the eBPF interpreter. - R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32)) +The instructions come in two forms: ``BPF_ABS | <size> | BPF_LD`` and +``BPF_IND | <size> | BPF_LD``. -and R1 - R5 are clobbered. +These instructions are used to access packet data and can only be used when +the program context is a pointer to networking packet. ``BPF_ABS`` +accesses packet data at an absolute offset specified by the immediate data +and ``BPF_IND`` access packet data at an offset that includes the value of +a register in addition to the immediate data. + +These instructions have seven implicit operands: + + * Register R6 is an implicit input that must contain pointer to a + struct sk_buff. + * Register R0 is an implicit output which contains the data fetched from + the packet. + * Registers R1-R5 are scratch registers that are clobbered after a call to + ``BPF_ABS | BPF_LD`` or ``BPF_IND`` | BPF_LD instructions. + +These instructions have an implicit program exit condition as well. When an +eBPF program is trying to access the data beyond the packet boundary, the +program execution will be aborted. + +``BPF_ABS | BPF_W | BPF_LD`` means:: + + R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + imm32)) + +``BPF_IND | BPF_W | BPF_LD`` means:: + + R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32)) diff --git a/Documentation/devicetree/bindings/net/cdns,macb.yaml b/Documentation/devicetree/bindings/net/cdns,macb.yaml index 8dd06db34169..6cd3d853dcba 100644 --- a/Documentation/devicetree/bindings/net/cdns,macb.yaml +++ b/Documentation/devicetree/bindings/net/cdns,macb.yaml @@ -81,6 +81,25 @@ properties: phy-handle: true + phys: + maxItems: 1 + + phy-names: + const: sgmii-phy + description: + Required with ZynqMP SoC when in SGMII mode. + Should reference PS-GTR generic PHY device for this controller + instance. See ZynqMP example. + + resets: + maxItems: 1 + description: + Recommended with ZynqMP, specify reset control for this + controller instance with zynqmp-reset driver. + + reset-names: + maxItems: 1 + fixed-link: true iommus: @@ -157,3 +176,40 @@ examples: reset-gpios = <&pioE 6 1>; }; }; + + - | + #include <dt-bindings/clock/xlnx-zynqmp-clk.h> + #include <dt-bindings/power/xlnx-zynqmp-power.h> + #include <dt-bindings/reset/xlnx-zynqmp-resets.h> + #include <dt-bindings/phy/phy.h> + + bus { + #address-cells = <2>; + #size-cells = <2>; + gem1: ethernet@ff0c0000 { + compatible = "cdns,zynqmp-gem", "cdns,gem"; + interrupt-parent = <&gic>; + interrupts = <0 59 4>, <0 59 4>; + reg = <0x0 0xff0c0000 0x0 0x1000>; + clocks = <&zynqmp_clk LPD_LSBUS>, <&zynqmp_clk GEM1_REF>, + <&zynqmp_clk GEM1_TX>, <&zynqmp_clk GEM1_RX>, + <&zynqmp_clk GEM_TSU>; + clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk"; + #address-cells = <1>; + #size-cells = <0>; + #stream-id-cells = <1>; + iommus = <&smmu 0x875>; + power-domains = <&zynqmp_firmware PD_ETH_1>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>; + reset-names = "gem1_rst"; + status = "okay"; + phy-mode = "sgmii"; + phy-names = "sgmii-phy"; + phys = <&psgtr 1 PHY_TYPE_SGMII 1 1>; + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/davicom,dm9051.yaml b/Documentation/devicetree/bindings/net/davicom,dm9051.yaml new file mode 100644 index 000000000000..52e852fef753 --- /dev/null +++ b/Documentation/devicetree/bindings/net/davicom,dm9051.yaml @@ -0,0 +1,62 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/davicom,dm9051.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Davicom DM9051 SPI Ethernet Controller + +maintainers: + - Joseph CHANG <josright123@gmail.com> + +description: | + The DM9051 is a fully integrated and cost-effective low pin count single + chip Fast Ethernet controller with a Serial Peripheral Interface (SPI). + +allOf: + - $ref: ethernet-controller.yaml# + +properties: + compatible: + const: davicom,dm9051 + + reg: + maxItems: 1 + + spi-max-frequency: + maximum: 45000000 + + interrupts: + maxItems: 1 + + local-mac-address: true + + mac-address: true + +required: + - compatible + - reg + - spi-max-frequency + - interrupts + +additionalProperties: false + +examples: + # Raspberry Pi platform + - | + /* for Raspberry Pi with pin control stuff for GPIO irq */ + #include <dt-bindings/interrupt-controller/irq.h> + #include <dt-bindings/gpio/gpio.h> + spi { + #address-cells = <1>; + #size-cells = <0>; + + ethernet@0 { + compatible = "davicom,dm9051"; + reg = <0>; /* spi chip select */ + local-mac-address = [00 00 00 00 00 00]; + interrupt-parent = <&gpio>; + interrupts = <26 IRQ_TYPE_LEVEL_LOW>; + spi-max-frequency = <31200000>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index 84985f53bffd..184152087b60 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -42,6 +42,12 @@ properties: description: Set if the output SYNCLKO frequency should be set to 125MHz instead of 25MHz. + microchip,synclko-disable: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set if the output SYNCLKO clock should be disabled. Do not mix with + microchip,synclko-125. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt b/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt deleted file mode 100644 index 7959ec237983..000000000000 --- a/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt +++ /dev/null @@ -1,240 +0,0 @@ -Realtek SMI-based Switches -========================== - -The SMI "Simple Management Interface" is a two-wire protocol using -bit-banged GPIO that while it reuses the MDIO lines MCK and MDIO does -not use the MDIO protocol. This binding defines how to specify the -SMI-based Realtek devices. - -Required properties: - -- compatible: must be exactly one of: - "realtek,rtl8365mb" (4+1 ports) - "realtek,rtl8366" - "realtek,rtl8366rb" (4+1 ports) - "realtek,rtl8366s" (4+1 ports) - "realtek,rtl8367" - "realtek,rtl8367b" - "realtek,rtl8368s" (8 port) - "realtek,rtl8369" - "realtek,rtl8370" (8 port) - -Required properties: -- mdc-gpios: GPIO line for the MDC clock line. -- mdio-gpios: GPIO line for the MDIO data line. -- reset-gpios: GPIO line for the reset signal. - -Optional properties: -- realtek,disable-leds: if the LED drivers are not used in the - hardware design this will disable them so they are not turned on - and wasting power. - -Required subnodes: - -- interrupt-controller - - This defines an interrupt controller with an IRQ line (typically - a GPIO) that will demultiplex and handle the interrupt from the single - interrupt line coming out of one of the SMI-based chips. It most - importantly provides link up/down interrupts to the PHY blocks inside - the ASIC. - -Required properties of interrupt-controller: - -- interrupt: parent interrupt, see interrupt-controller/interrupts.txt -- interrupt-controller: see interrupt-controller/interrupts.txt -- #address-cells: should be <0> -- #interrupt-cells: should be <1> - -- mdio - - This defines the internal MDIO bus of the SMI device, mostly for the - purpose of being able to hook the interrupts to the right PHY and - the right PHY to the corresponding port. - -Required properties of mdio: - -- compatible: should be set to "realtek,smi-mdio" for all SMI devices - -See net/mdio.txt for additional MDIO bus properties. - -See net/dsa/dsa.txt for a list of additional required and optional properties -and subnodes of DSA switches. - -Examples: - -An example for the RTL8366RB: - -switch { - compatible = "realtek,rtl8366rb"; - /* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */ - mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>; - mdio-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>; - reset-gpios = <&gpio0 14 GPIO_ACTIVE_LOW>; - - switch_intc: interrupt-controller { - /* GPIO 15 provides the interrupt */ - interrupt-parent = <&gpio0>; - interrupts = <15 IRQ_TYPE_LEVEL_LOW>; - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <1>; - }; - - ports { - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - port@0 { - reg = <0>; - label = "lan0"; - phy-handle = <&phy0>; - }; - port@1 { - reg = <1>; - label = "lan1"; - phy-handle = <&phy1>; - }; - port@2 { - reg = <2>; - label = "lan2"; - phy-handle = <&phy2>; - }; - port@3 { - reg = <3>; - label = "lan3"; - phy-handle = <&phy3>; - }; - port@4 { - reg = <4>; - label = "wan"; - phy-handle = <&phy4>; - }; - port@5 { - reg = <5>; - label = "cpu"; - ethernet = <&gmac0>; - phy-mode = "rgmii"; - fixed-link { - speed = <1000>; - full-duplex; - }; - }; - }; - - mdio { - compatible = "realtek,smi-mdio", "dsa-mdio"; - #address-cells = <1>; - #size-cells = <0>; - - phy0: phy@0 { - reg = <0>; - interrupt-parent = <&switch_intc>; - interrupts = <0>; - }; - phy1: phy@1 { - reg = <1>; - interrupt-parent = <&switch_intc>; - interrupts = <1>; - }; - phy2: phy@2 { - reg = <2>; - interrupt-parent = <&switch_intc>; - interrupts = <2>; - }; - phy3: phy@3 { - reg = <3>; - interrupt-parent = <&switch_intc>; - interrupts = <3>; - }; - phy4: phy@4 { - reg = <4>; - interrupt-parent = <&switch_intc>; - interrupts = <12>; - }; - }; -}; - -An example for the RTL8365MB-VC: - -switch { - compatible = "realtek,rtl8365mb"; - mdc-gpios = <&gpio1 16 GPIO_ACTIVE_HIGH>; - mdio-gpios = <&gpio1 17 GPIO_ACTIVE_HIGH>; - reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; - - switch_intc: interrupt-controller { - interrupt-parent = <&gpio5>; - interrupts = <1 IRQ_TYPE_LEVEL_LOW>; - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <1>; - }; - - ports { - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - port@0 { - reg = <0>; - label = "swp0"; - phy-handle = <ðphy0>; - }; - port@1 { - reg = <1>; - label = "swp1"; - phy-handle = <ðphy1>; - }; - port@2 { - reg = <2>; - label = "swp2"; - phy-handle = <ðphy2>; - }; - port@3 { - reg = <3>; - label = "swp3"; - phy-handle = <ðphy3>; - }; - port@6 { - reg = <6>; - label = "cpu"; - ethernet = <&fec1>; - phy-mode = "rgmii"; - tx-internal-delay-ps = <2000>; - rx-internal-delay-ps = <2000>; - - fixed-link { - speed = <1000>; - full-duplex; - pause; - }; - }; - }; - - mdio { - compatible = "realtek,smi-mdio"; - #address-cells = <1>; - #size-cells = <0>; - - ethphy0: phy@0 { - reg = <0>; - interrupt-parent = <&switch_intc>; - interrupts = <0>; - }; - ethphy1: phy@1 { - reg = <1>; - interrupt-parent = <&switch_intc>; - interrupts = <1>; - }; - ethphy2: phy@2 { - reg = <2>; - interrupt-parent = <&switch_intc>; - interrupts = <2>; - }; - ethphy3: phy@3 { - reg = <3>; - interrupt-parent = <&switch_intc>; - interrupts = <3>; - }; - }; -}; diff --git a/Documentation/devicetree/bindings/net/dsa/realtek.yaml b/Documentation/devicetree/bindings/net/dsa/realtek.yaml new file mode 100644 index 000000000000..8756060895a8 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/realtek.yaml @@ -0,0 +1,394 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/realtek.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Realtek switches for unmanaged switches + +allOf: + - $ref: dsa.yaml# + +maintainers: + - Linus Walleij <linus.walleij@linaro.org> + +description: + Realtek advertises these chips as fast/gigabit switches or unmanaged + switches. They can be controlled using different interfaces, like SMI, + MDIO or SPI. + + The SMI "Simple Management Interface" is a two-wire protocol using + bit-banged GPIO that while it reuses the MDIO lines MCK and MDIO does + not use the MDIO protocol. This binding defines how to specify the + SMI-based Realtek devices. The realtek-smi driver is a platform driver + and it must be inserted inside a platform node. + + The MDIO-connected switches use MDIO protocol to access their registers. + The realtek-mdio driver is an MDIO driver and it must be inserted inside + an MDIO node. + +properties: + compatible: + enum: + - realtek,rtl8365mb + - realtek,rtl8366 + - realtek,rtl8366rb + - realtek,rtl8366s + - realtek,rtl8367 + - realtek,rtl8367b + - realtek,rtl8367rb + - realtek,rtl8367s + - realtek,rtl8368s + - realtek,rtl8369 + - realtek,rtl8370 + description: | + realtek,rtl8365mb: 4+1 ports + realtek,rtl8366: 5+1 ports + realtek,rtl8366rb: 5+1 ports + realtek,rtl8366s: 5+1 ports + realtek,rtl8367: + realtek,rtl8367b: + realtek,rtl8367rb: 5+2 ports + realtek,rtl8367s: 5+2 ports + realtek,rtl8368s: 8 ports + realtek,rtl8369: 8+1 ports + realtek,rtl8370: 8+2 ports + + mdc-gpios: + description: GPIO line for the MDC clock line. + maxItems: 1 + + mdio-gpios: + description: GPIO line for the MDIO data line. + maxItems: 1 + + reset-gpios: + description: GPIO to be used to reset the whole device + maxItems: 1 + + realtek,disable-leds: + type: boolean + description: | + if the LED drivers are not used in the hardware design, + this will disable them so they are not turned on + and wasting power. + + interrupt-controller: + type: object + description: | + This defines an interrupt controller with an IRQ line (typically + a GPIO) that will demultiplex and handle the interrupt from the single + interrupt line coming out of one of the Realtek switch chips. It most + importantly provides link up/down interrupts to the PHY blocks inside + the ASIC. + + properties: + + interrupt-controller: true + + interrupts: + maxItems: 1 + description: + A single IRQ line from the switch, either active LOW or HIGH + + '#address-cells': + const: 0 + + '#interrupt-cells': + const: 1 + + required: + - interrupt-controller + - '#address-cells' + - '#interrupt-cells' + + mdio: + $ref: /schemas/net/mdio.yaml# + unevaluatedProperties: false + + properties: + compatible: + const: realtek,smi-mdio + +if: + required: + - reg + +then: + not: + required: + - mdc-gpios + - mdio-gpios + - mdio + + properties: + mdc-gpios: false + mdio-gpios: false + mdio: false + +else: + required: + - mdc-gpios + - mdio-gpios + - mdio + - reset-gpios + +required: + - compatible + + # - mdc-gpios + # - mdio-gpios + # - reset-gpios + # - mdio + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + platform { + switch { + compatible = "realtek,rtl8366rb"; + /* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */ + mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>; + mdio-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio0 14 GPIO_ACTIVE_LOW>; + + switch_intc1: interrupt-controller { + /* GPIO 15 provides the interrupt */ + interrupt-parent = <&gpio0>; + interrupts = <15 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + label = "lan0"; + phy-handle = <&phy0>; + }; + port@1 { + reg = <1>; + label = "lan1"; + phy-handle = <&phy1>; + }; + port@2 { + reg = <2>; + label = "lan2"; + phy-handle = <&phy2>; + }; + port@3 { + reg = <3>; + label = "lan3"; + phy-handle = <&phy3>; + }; + port@4 { + reg = <4>; + label = "wan"; + phy-handle = <&phy4>; + }; + port@5 { + reg = <5>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "rgmii"; + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + + mdio { + compatible = "realtek,smi-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + phy0: ethernet-phy@0 { + reg = <0>; + interrupt-parent = <&switch_intc1>; + interrupts = <0>; + }; + phy1: ethernet-phy@1 { + reg = <1>; + interrupt-parent = <&switch_intc1>; + interrupts = <1>; + }; + phy2: ethernet-phy@2 { + reg = <2>; + interrupt-parent = <&switch_intc1>; + interrupts = <2>; + }; + phy3: ethernet-phy@3 { + reg = <3>; + interrupt-parent = <&switch_intc1>; + interrupts = <3>; + }; + phy4: ethernet-phy@4 { + reg = <4>; + interrupt-parent = <&switch_intc1>; + interrupts = <12>; + }; + }; + }; + }; + + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + platform { + switch { + compatible = "realtek,rtl8365mb"; + mdc-gpios = <&gpio1 16 GPIO_ACTIVE_HIGH>; + mdio-gpios = <&gpio1 17 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; + + switch_intc2: interrupt-controller { + interrupt-parent = <&gpio5>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + label = "swp0"; + phy-handle = <ðphy0>; + }; + port@1 { + reg = <1>; + label = "swp1"; + phy-handle = <ðphy1>; + }; + port@2 { + reg = <2>; + label = "swp2"; + phy-handle = <ðphy2>; + }; + port@3 { + reg = <3>; + label = "swp3"; + phy-handle = <ðphy3>; + }; + port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&fec1>; + phy-mode = "rgmii"; + tx-internal-delay-ps = <2000>; + rx-internal-delay-ps = <2000>; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + + mdio { + compatible = "realtek,smi-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + ethphy0: ethernet-phy@0 { + reg = <0>; + interrupt-parent = <&switch_intc2>; + interrupts = <0>; + }; + ethphy1: ethernet-phy@1 { + reg = <1>; + interrupt-parent = <&switch_intc2>; + interrupts = <1>; + }; + ethphy2: ethernet-phy@2 { + reg = <2>; + interrupt-parent = <&switch_intc2>; + interrupts = <2>; + }; + ethphy3: ethernet-phy@3 { + reg = <3>; + interrupt-parent = <&switch_intc2>; + interrupts = <3>; + }; + }; + }; + }; + + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switch@29 { + compatible = "realtek,rtl8367s"; + reg = <29>; + + reset-gpios = <&gpio2 20 GPIO_ACTIVE_LOW>; + + switch_intc3: interrupt-controller { + interrupt-parent = <&gpio0>; + interrupts = <11 IRQ_TYPE_EDGE_FALLING>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan4"; + }; + + port@1 { + reg = <1>; + label = "lan3"; + }; + + port@2 { + reg = <2>; + label = "lan2"; + }; + + port@3 { + reg = <3>; + label = "lan1"; + }; + + port@4 { + reg = <4>; + label = "wan"; + }; + + port@7 { + reg = <7>; + ethernet = <ðernet>; + phy-mode = "rgmii"; + tx-internal-delay-ps = <2000>; + rx-internal-delay-ps = <0>; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index 020337f3c05f..801efc7d6818 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -388,14 +388,24 @@ PROPERTIES Value type: <prop-encoded-array> Definition: A standard property. -- bus-frequency +- clocks + Usage: optional + Value type: <phandle> + Definition: A reference to the input clock of the controller + from which the MDC frequency is derived. + +- clock-frequency Usage: optional Value type: <u32> - Definition: Specifies the external MDIO bus clock speed to - be used, if different from the standard 2.5 MHz. - This may be due to the standard speed being unsupported (e.g. - due to a hardware problem), or to advertise that all relevant - components in the system support a faster speed. + Definition: Specifies the external MDC frequency, in Hertz, to + be used. Requires that the input clock is specified in the + "clocks" property. See also: mdio.yaml. + +- suppress-preamble + Usage: optional + Value type: <boolean> + Definition: Disable generation of preamble bits. See also: + mdio.yaml. - interrupts Usage: required for external MDIO diff --git a/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml b/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml index e79e4e166ad8..13812768b923 100644 --- a/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml +++ b/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml @@ -38,6 +38,7 @@ properties: - description: register based extraction - description: frame dma based extraction - description: analyzer interrupt + - description: ptp interrupt interrupt-names: minItems: 1 @@ -45,6 +46,7 @@ properties: - const: xtr - const: fdma - const: ana + - const: ptp resets: items: diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml index bda821065a2b..ee2ccacc39ff 100644 --- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml +++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml @@ -45,8 +45,10 @@ properties: - items: - enum: + - renesas,r9a07g043-gbeth # RZ/G2UL - renesas,r9a07g044-gbeth # RZ/G2{L,LC} - - const: renesas,rzg2l-gbeth # RZ/G2L + - renesas,r9a07g054-gbeth # RZ/V2L + - const: renesas,rzg2l-gbeth # RZ/{G2L,G2UL,V2L} family reg: true diff --git a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml index 269cd63fb544..025f4242f8f7 100644 --- a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml +++ b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml @@ -69,6 +69,15 @@ properties: calibration data is generic and specific calibration data should be pulled from the OTP ROM + mediatek,disable-radar-background: + type: boolean + description: + Disable/enable radar/CAC detection running on a dedicated offchannel + chain available on some hw. + Background radar/CAC detection allows to avoid the CAC downtime + switching on a different channel during CAC detection on the selected + radar channel. + led: type: object $ref: /schemas/leds/common.yaml# diff --git a/Documentation/devicetree/bindings/phy/transmit-amplitude.yaml b/Documentation/devicetree/bindings/phy/transmit-amplitude.yaml new file mode 100644 index 000000000000..51492fe738ec --- /dev/null +++ b/Documentation/devicetree/bindings/phy/transmit-amplitude.yaml @@ -0,0 +1,103 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/phy/transmit-amplitude.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Common PHY and network PCS transmit amplitude property binding + +description: + Binding describing the peak-to-peak transmit amplitude for common PHYs + and network PCSes. + +maintainers: + - Marek Behún <kabel@kernel.org> + +properties: + tx-p2p-microvolt: + description: + Transmit amplitude voltages in microvolts, peak-to-peak. If this property + contains multiple values for various PHY modes, the + 'tx-p2p-microvolt-names' property must be provided and contain + corresponding mode names. + + tx-p2p-microvolt-names: + description: | + Names of the modes corresponding to voltages in the 'tx-p2p-microvolt' + property. Required only if multiple voltages are provided. + + If a value of 'default' is provided, the system should use it for any PHY + mode that is otherwise not defined here. If 'default' is not provided, the + system should use manufacturer default value. + minItems: 1 + maxItems: 16 + items: + enum: + - default + + # ethernet modes + - sgmii + - qsgmii + - xgmii + - 1000base-x + - 2500base-x + - 5gbase-r + - rxaui + - xaui + - 10gbase-kr + - usxgmii + - 10gbase-r + - 25gbase-r + + # PCIe modes + - pcie + - pcie1 + - pcie2 + - pcie3 + - pcie4 + - pcie5 + - pcie6 + + # USB modes + - usb + - usb-ls + - usb-fs + - usb-hs + - usb-ss + - usb-ss+ + - usb-4 + + # storage modes + - sata + - ufs-hs + - ufs-hs-a + - ufs-hs-b + + # display modes + - lvds + - dp + - dp-rbr + - dp-hbr + - dp-hbr2 + - dp-hbr3 + - dp-uhbr-10 + - dp-uhbr-13.5 + - dp-uhbr-20 + + # camera modes + - mipi-dphy + - mipi-dphy-univ + - mipi-dphy-v2.5-univ + +dependencies: + tx-p2p-microvolt-names: [ tx-p2p-microvolt ] + +additionalProperties: true + +examples: + - | + phy: phy { + #phy-cells = <1>; + tx-p2p-microvolt = <915000>, <1100000>, <1200000>; + tx-p2p-microvolt-names = "2500base-x", "usb-hs", "usb-ss"; + }; diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 9d98e0511249..cae28af7a476 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -860,8 +860,16 @@ Kernel response contents: ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split ==================================== ====== =========================== +``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with +page-flipping TCP zero-copy receive (``getsockopt(TCP_ZEROCOPY_RECEIVE)``). +If enabled the device is configured to place frame headers and data into +separate buffers. The device configuration must make it possible to receive +full memory pages of data, for example because MTU is high enough or through +HW-GRO. + RINGS_SET ========= diff --git a/Documentation/networking/mctp.rst b/Documentation/networking/mctp.rst index 46f74bffce0f..c628cb5406d2 100644 --- a/Documentation/networking/mctp.rst +++ b/Documentation/networking/mctp.rst @@ -212,6 +212,54 @@ remote address is already known, or the message does not require a reply. Like the send calls, sockets will only receive responses to requests they have sent (TO=1) and may only respond (TO=0) to requests they have received. +``ioctl(SIOCMCTPALLOCTAG)`` and ``ioctl(SIOCMCTPDROPTAG)`` +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +These tags give applications more control over MCTP message tags, by allocating +(and dropping) tag values explicitly, rather than the kernel automatically +allocating a per-message tag at ``sendmsg()`` time. + +In general, you will only need to use these ioctls if your MCTP protocol does +not fit the usual request/response model. For example, if you need to persist +tags across multiple requests, or a request may generate more than one response. +In these cases, the ioctls allow you to decouple the tag allocation (and +release) from individual message send and receive operations. + +Both ioctls are passed a pointer to a ``struct mctp_ioc_tag_ctl``: + +.. code-block:: C + + struct mctp_ioc_tag_ctl { + mctp_eid_t peer_addr; + __u8 tag; + __u16 flags; + }; + +``SIOCMCTPALLOCTAG`` allocates a tag for a specific peer, which an application +can use in future ``sendmsg()`` calls. The application populates the +``peer_addr`` member with the remote EID. Other fields must be zero. + +On return, the ``tag`` member will be populated with the allocated tag value. +The allocated tag will have the following tag bits set: + + - ``MCTP_TAG_OWNER``: it only makes sense to allocate tags if you're the tag + owner + + - ``MCTP_TAG_PREALLOC``: to indicate to ``sendmsg()`` that this is a + preallocated tag. + + - ... and the actual tag value, within the least-significant three bits + (``MCTP_TAG_MASK``). Note that zero is a valid tag value. + +The tag value should be used as-is for the ``smctp_tag`` member of ``struct +sockaddr_mctp``. + +``SIOCMCTPDROPTAG`` releases a tag that has been previously allocated by a +``SIOCMCTPALLOCTAG`` ioctl. The ``peer_addr`` must be the same as used for the +allocation, and the ``tag`` value must match exactly the tag returned from the +allocation (including the ``MCTP_TAG_OWNER`` and ``MCTP_TAG_PREALLOC`` bits). +The ``flags`` field must be zero. + Kernel internals ================ diff --git a/MAINTAINERS b/MAINTAINERS index 6db79f3b209e..65f5043ae48d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3527,6 +3527,8 @@ F: net/sched/act_bpf.c F: net/sched/cls_bpf.c F: samples/bpf/ F: scripts/bpf_doc.py +F: scripts/pahole-flags.sh +F: scripts/pahole-version.sh F: tools/bpf/ F: tools/lib/bpf/ F: tools/testing/selftests/bpf/ @@ -16372,8 +16374,7 @@ REALTEK RTL83xx SMI DSA ROUTER CHIPS M: Linus Walleij <linus.walleij@linaro.org> S: Maintained F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt -F: drivers/net/dsa/realtek-smi* -F: drivers/net/dsa/rtl83* +F: drivers/net/dsa/realtek/* REALTEK WIRELESS DRIVER (rtlwifi family) M: Ping-Ke Shih <pkshih@realtek.com> diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 284d28755b8d..7d81535893af 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -133,6 +133,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 74e66443e4ce..9bec3ba20c69 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -512,6 +512,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x874>; power-domains = <&zynqmp_firmware PD_ETH_0>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM0>; + reset-names = "gem0_rst"; }; gem1: ethernet@ff0c0000 { @@ -526,6 +528,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x875>; power-domains = <&zynqmp_firmware PD_ETH_1>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>; + reset-names = "gem1_rst"; }; gem2: ethernet@ff0d0000 { @@ -540,6 +544,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x876>; power-domains = <&zynqmp_firmware PD_ETH_2>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM2>; + reset-names = "gem2_rst"; }; gem3: ethernet@ff0e0000 { @@ -554,6 +560,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x877>; power-domains = <&zynqmp_firmware PD_ETH_3>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM3>; + reset-names = "gem3_rst"; }; gpio: gpio@ff0a0000 { diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index e96d4d87291f..74f9a9b6a053 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1143,6 +1143,11 @@ out: return prog; } +bool bpf_jit_supports_kfunc_call(void) +{ + return true; +} + u64 bpf_jit_alloc_exec_limit(void) { return VMALLOC_END - VMALLOC_START; diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 24e0efb360f6..1d55e57b8466 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -144,6 +144,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 845ddc63c882..654061e0964e 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -125,6 +125,8 @@ #define SO_RESERVE_MEM 0x4047 +#define SO_TXREHASH 0x4048 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 56dd1f4e3e44..a4f4d347e6bd 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -264,7 +264,7 @@ skip_codegen_passes: fp->jited = 1; fp->jited_len = proglen + FUNCTION_DESCR_SIZE; - bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE)); + bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + bpf_hdr->size); if (!fp->is_func || extra_pass) { bpf_jit_binary_lock_ro(bpf_hdr); bpf_prog_fill_jited_linfo(fp, addrs); diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 2672dd03faf3..666f81e617ea 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -126,6 +126,8 @@ #define SO_RESERVE_MEM 0x0052 +#define SO_TXREHASH 0x0053 + #if !defined(__KERNEL__) diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index b1e38784eb23..fa0759bfe498 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1599,7 +1599,7 @@ skip_init_ctx: if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, image_size, pass, ctx.image); - bpf_flush_icache(header, (u8 *)header + (header->pages * PAGE_SIZE)); + bpf_flush_icache(header, (u8 *)header + header->size); if (!prog->is_func || extra_pass) { bpf_jit_binary_lock_ro(header); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9f5bd41bf660..995f2dc28631 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -158,6 +158,7 @@ config X86 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE + select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if X86_64 diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index b7421780e4e9..4cc18ba1b75e 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -44,6 +44,7 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len); extern void *text_poke(void *addr, const void *opcode, size_t len); extern void text_poke_sync(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); +extern void *text_poke_copy(void *addr, const void *opcode, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5007c3ffe96f..018b61febf0e 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1102,6 +1102,40 @@ void *text_poke_kgdb(void *addr, const void *opcode, size_t len) return __text_poke(addr, opcode, len); } +/** + * text_poke_copy - Copy instructions into (an unused part of) RX memory + * @addr: address to modify + * @opcode: source of the copy + * @len: length to copy, could be more than 2x PAGE_SIZE + * + * Not safe against concurrent execution; useful for JITs to dump + * new code blocks into unused regions of RX memory. Can be used in + * conjunction with synchronize_rcu_tasks() to wait for existing + * execution to quiesce after having made sure no existing functions + * pointers are live. + */ +void *text_poke_copy(void *addr, const void *opcode, size_t len) +{ + unsigned long start = (unsigned long)addr; + size_t patched = 0; + + if (WARN_ON_ONCE(core_kernel_text(start))) + return NULL; + + mutex_lock(&text_mutex); + while (patched < len) { + unsigned long ptr = start + patched; + size_t s; + + s = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(ptr), len - patched); + + __text_poke((void *)ptr, opcode + patched, s); + patched += s; + } + mutex_unlock(&text_mutex); + return addr; +} + static void do_sync_core(void *info) { sync_core(); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2b1e266ff95c..c7db0fe4de2f 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -330,8 +330,7 @@ static int emit_jump(u8 **pprog, void *func, void *ip) } static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, - void *old_addr, void *new_addr, - const bool text_live) + void *old_addr, void *new_addr) { const u8 *nop_insn = x86_nops[5]; u8 old_insn[X86_PATCH_SIZE]; @@ -365,10 +364,7 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, goto out; ret = 1; if (memcmp(ip, new_insn, X86_PATCH_SIZE)) { - if (text_live) - text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); - else - memcpy(ip, new_insn, X86_PATCH_SIZE); + text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); ret = 0; } out: @@ -384,7 +380,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, /* BPF poking in modules is not supported */ return -EINVAL; - return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true); + return __bpf_arch_text_poke(ip, t, old_addr, new_addr); } #define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8) @@ -558,24 +554,15 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) mutex_lock(&array->aux->poke_mutex); target = array->ptrs[poke->tail_call.key]; if (target) { - /* Plain memcpy is used when image is not live yet - * and still not locked as read-only. Once poke - * location is active (poke->tailcall_target_stable), - * any parallel bpf_arch_text_poke() might occur - * still on the read-write image until we finally - * locked it as read-only. Both modifications on - * the given image are under text_mutex to avoid - * interference. - */ ret = __bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, NULL, (u8 *)target->bpf_func + - poke->adj_off, false); + poke->adj_off); BUG_ON(ret < 0); ret = __bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, (u8 *)poke->tailcall_target + - X86_PATCH_SIZE, NULL, false); + X86_PATCH_SIZE, NULL); BUG_ON(ret < 0); } WRITE_ONCE(poke->tailcall_target_stable, true); @@ -787,7 +774,6 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, /* emit opcode */ switch (atomic_op) { case BPF_ADD: - case BPF_SUB: case BPF_AND: case BPF_OR: case BPF_XOR: @@ -867,7 +853,7 @@ static void emit_nops(u8 **pprog, int len) #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) -static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, +static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { bool tail_call_reachable = bpf_prog->aux->tail_call_reachable; @@ -894,8 +880,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, push_callee_regs(&prog, callee_regs_used); ilen = prog - temp; - if (image) - memcpy(image + proglen, temp, ilen); + if (rw_image) + memcpy(rw_image + proglen, temp, ilen); proglen += ilen; addrs[0] = proglen; prog = temp; @@ -1324,6 +1310,9 @@ st: if (is_imm8(insn->off)) pr_err("extable->insn doesn't fit into 32-bit\n"); return -EFAULT; } + /* switch ex to rw buffer for writes */ + ex = (void *)rw_image + ((void *)ex - (void *)image); + ex->insn = delta; ex->data = EX_TYPE_BPF; @@ -1706,7 +1695,7 @@ emit_jmp: pr_err("bpf_jit: fatal error\n"); return -EFAULT; } - memcpy(image + proglen, temp, ilen); + memcpy(rw_image + proglen, temp, ilen); } proglen += ilen; addrs[i] = proglen; @@ -2247,6 +2236,7 @@ int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs) } struct x64_jit_data { + struct bpf_binary_header *rw_header; struct bpf_binary_header *header; int *addrs; u8 *image; @@ -2259,6 +2249,7 @@ struct x64_jit_data { struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { + struct bpf_binary_header *rw_header = NULL; struct bpf_binary_header *header = NULL; struct bpf_prog *tmp, *orig_prog = prog; struct x64_jit_data *jit_data; @@ -2267,6 +2258,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bool tmp_blinded = false; bool extra_pass = false; bool padding = false; + u8 *rw_image = NULL; u8 *image = NULL; int *addrs; int pass; @@ -2302,6 +2294,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) oldproglen = jit_data->proglen; image = jit_data->image; header = jit_data->header; + rw_header = jit_data->rw_header; + rw_image = (void *)rw_header + ((void *)image - (void *)header); extra_pass = true; padding = true; goto skip_init_addrs; @@ -2332,12 +2326,12 @@ skip_init_addrs: for (pass = 0; pass < MAX_PASSES || image; pass++) { if (!padding && pass >= PADDING_PASSES) padding = true; - proglen = do_jit(prog, addrs, image, oldproglen, &ctx, padding); + proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding); if (proglen <= 0) { out_image: image = NULL; if (header) - bpf_jit_binary_free(header); + bpf_jit_binary_pack_free(header, rw_header); prog = orig_prog; goto out_addrs; } @@ -2361,8 +2355,9 @@ out_image: sizeof(struct exception_table_entry); /* allocate module memory for x86 insns and extable */ - header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size, - &image, align, jit_fill_hole); + header = bpf_jit_binary_pack_alloc(roundup(proglen, align) + extable_size, + &image, align, &rw_header, &rw_image, + jit_fill_hole); if (!header) { prog = orig_prog; goto out_addrs; @@ -2378,14 +2373,26 @@ out_image: if (image) { if (!prog->is_func || extra_pass) { + /* + * bpf_jit_binary_pack_finalize fails in two scenarios: + * 1) header is not pointing to proper module memory; + * 2) the arch doesn't support bpf_arch_text_copy(). + * + * Both cases are serious bugs and justify WARN_ON. + */ + if (WARN_ON(bpf_jit_binary_pack_finalize(prog, header, rw_header))) { + prog = orig_prog; + goto out_addrs; + } + bpf_tail_call_direct_fixup(prog); - bpf_jit_binary_lock_ro(header); } else { jit_data->addrs = addrs; jit_data->ctx = ctx; jit_data->proglen = proglen; jit_data->image = image; jit_data->header = header; + jit_data->rw_header = rw_header; } prog->bpf_func = (void *)image; prog->jited = 1; @@ -2413,3 +2420,10 @@ bool bpf_jit_supports_kfunc_call(void) { return true; } + +void *bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + if (text_poke_copy(dst, src, len) == NULL) + return ERR_PTR(-EINVAL); + return dst; +} diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 1a4f8b227eac..06514ed66022 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2428,10 +2428,15 @@ static int btintel_setup_combined(struct hci_dev *hdev) /* Apply the device specific HCI quirks * - * WBS for SdP - SdP and Stp have a same hw_varaint but - * different fw_variant + * WBS for SdP - For the Legacy ROM products, only SdP + * supports the WBS. But the version information is not + * enough to use here because the StP2 and SdP have same + * hw_variant and fw_variant. So, this flag is set by + * the transport driver (btusb) based on the HW info + * (idProduct) */ - if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22) + if (!btintel_test_flag(hdev, + INTEL_ROM_LEGACY_NO_WBS_SUPPORT)) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index c9b24e9299e2..e0060e58573c 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -152,6 +152,7 @@ enum { INTEL_BROKEN_INITIAL_NCMD, INTEL_BROKEN_SHUTDOWN_LED, INTEL_ROM_LEGACY, + INTEL_ROM_LEGACY_NO_WBS_SUPPORT, __INTEL_NUM_FLAGS, }; diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c index c4867576be00..db35b917aecf 100644 --- a/drivers/bluetooth/btmrvl_debugfs.c +++ b/drivers/bluetooth/btmrvl_debugfs.c @@ -1,4 +1,4 @@ -/** +/* * Marvell Bluetooth driver: debugfs related functions * * Copyright (C) 2009, Marvell International Ltd. diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 68378b42ea7f..b8ef66f89fc1 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -1,4 +1,4 @@ -/** +/* * Marvell BT-over-SDIO driver: SDIO interface related functions. * * Copyright (C) 2009, Marvell International Ltd. diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index 6e7b0c7567c0..fb76d9765ce0 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -7,8 +7,12 @@ #define HCI_WMT_MAX_EVENT_SIZE 64 +#define BTMTK_WMT_REG_WRITE 0x1 #define BTMTK_WMT_REG_READ 0x2 +#define MT7921_PINMUX_0 0x70005050 +#define MT7921_PINMUX_1 0x70005054 + enum { BTMTK_WMT_PATCH_DWNLD = 0x1, BTMTK_WMT_TEST = 0x2, @@ -68,6 +72,37 @@ struct btmtk_tci_sleep { u8 time_compensation; } __packed; +struct btmtk_wakeon { + u8 mode; + u8 gpo; + u8 active_high; + __le16 enable_delay; + __le16 wakeup_delay; +} __packed; + +struct btmtk_sco { + u8 clock_config; + u8 transmit_format_config; + u8 channel_format_config; + u8 channel_select_config; +} __packed; + +struct reg_read_cmd { + u8 type; + u8 rsv; + u8 num; + __le32 addr; +} __packed; + +struct reg_write_cmd { + u8 type; + u8 rsv; + u8 num; + __le32 addr; + __le32 data; + __le32 mask; +} __packed; + struct btmtk_hci_wmt_params { u8 op; u8 flag; diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index b5ea8d3bffaa..8be763ab3bf4 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -31,28 +31,32 @@ #define VERSION "0.1" -#define MTKBTSDIO_AUTOSUSPEND_DELAY 8000 +#define MTKBTSDIO_AUTOSUSPEND_DELAY 1000 -static bool enable_autosuspend; +static bool enable_autosuspend = true; struct btmtksdio_data { const char *fwname; u16 chipid; + bool lp_mbox_supported; }; static const struct btmtksdio_data mt7663_data = { .fwname = FIRMWARE_MT7663, .chipid = 0x7663, + .lp_mbox_supported = false, }; static const struct btmtksdio_data mt7668_data = { .fwname = FIRMWARE_MT7668, .chipid = 0x7668, + .lp_mbox_supported = false, }; static const struct btmtksdio_data mt7921_data = { .fwname = FIRMWARE_MT7961, .chipid = 0x7921, + .lp_mbox_supported = true, }; static const struct sdio_device_id btmtksdio_table[] = { @@ -87,8 +91,17 @@ MODULE_DEVICE_TABLE(sdio, btmtksdio_table); #define RX_DONE_INT BIT(1) #define TX_EMPTY BIT(2) #define TX_FIFO_OVERFLOW BIT(8) +#define FW_MAILBOX_INT BIT(15) +#define INT_MASK GENMASK(15, 0) #define RX_PKT_LEN GENMASK(31, 16) +#define MTK_REG_CSICR 0xc0 +#define CSICR_CLR_MBOX_ACK BIT(0) +#define MTK_REG_PH2DSM0R 0xc4 +#define PH2DSM0R_DRIVER_OWN BIT(0) +#define MTK_REG_PD2HRM0R 0xdc +#define PD2HRM0R_DRV_OWN BIT(0) + #define MTK_REG_CTDR 0x18 #define MTK_REG_CRDR 0x1c @@ -100,6 +113,7 @@ MODULE_DEVICE_TABLE(sdio, btmtksdio_table); #define BTMTKSDIO_TX_WAIT_VND_EVT 1 #define BTMTKSDIO_HW_TX_READY 2 #define BTMTKSDIO_FUNC_ENABLED 3 +#define BTMTKSDIO_PATCH_ENABLED 4 struct mtkbtsdio_hdr { __le16 len; @@ -278,6 +292,78 @@ static u32 btmtksdio_drv_own_query(struct btmtksdio_dev *bdev) return sdio_readl(bdev->func, MTK_REG_CHLPCR, NULL); } +static u32 btmtksdio_drv_own_query_79xx(struct btmtksdio_dev *bdev) +{ + return sdio_readl(bdev->func, MTK_REG_PD2HRM0R, NULL); +} + +static int btmtksdio_fw_pmctrl(struct btmtksdio_dev *bdev) +{ + u32 status; + int err; + + sdio_claim_host(bdev->func); + + if (bdev->data->lp_mbox_supported && + test_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state)) { + sdio_writel(bdev->func, CSICR_CLR_MBOX_ACK, MTK_REG_CSICR, + &err); + err = readx_poll_timeout(btmtksdio_drv_own_query_79xx, bdev, + status, !(status & PD2HRM0R_DRV_OWN), + 2000, 1000000); + if (err < 0) { + bt_dev_err(bdev->hdev, "mailbox ACK not cleared"); + goto out; + } + } + + /* Return ownership to the device */ + sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, &err); + if (err < 0) + goto out; + + err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, + !(status & C_COM_DRV_OWN), 2000, 1000000); + +out: + sdio_release_host(bdev->func); + + if (err < 0) + bt_dev_err(bdev->hdev, "Cannot return ownership to device"); + + return err; +} + +static int btmtksdio_drv_pmctrl(struct btmtksdio_dev *bdev) +{ + u32 status; + int err; + + sdio_claim_host(bdev->func); + + /* Get ownership from the device */ + sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err); + if (err < 0) + goto out; + + err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, + status & C_COM_DRV_OWN, 2000, 1000000); + + if (!err && bdev->data->lp_mbox_supported && + test_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state)) + err = readx_poll_timeout(btmtksdio_drv_own_query_79xx, bdev, + status, status & PD2HRM0R_DRV_OWN, + 2000, 1000000); + +out: + sdio_release_host(bdev->func); + + if (err < 0) + bt_dev_err(bdev->hdev, "Cannot get ownership from device"); + + return err; +} + static int btmtksdio_recv_event(struct hci_dev *hdev, struct sk_buff *skb) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); @@ -480,6 +566,13 @@ static void btmtksdio_txrx_work(struct work_struct *work) * FIFO. */ sdio_writel(bdev->func, int_status, MTK_REG_CHISR, NULL); + int_status &= INT_MASK; + + if ((int_status & FW_MAILBOX_INT) && + bdev->data->chipid == 0x7921) { + sdio_writel(bdev->func, PH2DSM0R_DRIVER_OWN, + MTK_REG_PH2DSM0R, 0); + } if (int_status & FW_OWN_BACK_INT) bt_dev_dbg(bdev->hdev, "Get fw own back"); @@ -531,7 +624,7 @@ static void btmtksdio_interrupt(struct sdio_func *func) static int btmtksdio_open(struct hci_dev *hdev) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); - u32 status, val; + u32 val; int err; sdio_claim_host(bdev->func); @@ -542,18 +635,10 @@ static int btmtksdio_open(struct hci_dev *hdev) set_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state); - /* Get ownership from the device */ - sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err); + err = btmtksdio_drv_pmctrl(bdev); if (err < 0) goto err_disable_func; - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - status & C_COM_DRV_OWN, 2000, 1000000); - if (err < 0) { - bt_dev_err(bdev->hdev, "Cannot get ownership from device"); - goto err_disable_func; - } - /* Disable interrupt & mask out all interrupt sources */ sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, &err); if (err < 0) @@ -623,8 +708,6 @@ err_release_host: static int btmtksdio_close(struct hci_dev *hdev) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); - u32 status; - int err; sdio_claim_host(bdev->func); @@ -635,13 +718,7 @@ static int btmtksdio_close(struct hci_dev *hdev) cancel_work_sync(&bdev->txrx_work); - /* Return ownership to the device */ - sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, NULL); - - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - !(status & C_COM_DRV_OWN), 2000, 1000000); - if (err < 0) - bt_dev_err(bdev->hdev, "Cannot return ownership to device"); + btmtksdio_fw_pmctrl(bdev); clear_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state); sdio_disable_func(bdev->func); @@ -686,6 +763,7 @@ static int btmtksdio_func_query(struct hci_dev *hdev) static int mt76xx_setup(struct hci_dev *hdev, const char *fwname) { + struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); struct btmtk_hci_wmt_params wmt_params; struct btmtk_tci_sleep tci_sleep; struct sk_buff *skb; @@ -746,6 +824,8 @@ ignore_setup_fw: return err; } + set_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state); + ignore_func_on: /* Apply the low power environment setup */ tci_sleep.mode = 0x5; @@ -768,6 +848,7 @@ ignore_func_on: static int mt79xx_setup(struct hci_dev *hdev, const char *fwname) { + struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); struct btmtk_hci_wmt_params wmt_params; u8 param = 0x1; int err; @@ -793,19 +874,15 @@ static int mt79xx_setup(struct hci_dev *hdev, const char *fwname) hci_set_msft_opcode(hdev, 0xFD30); hci_set_aosp_capable(hdev); + set_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state); return err; } -static int btsdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) +static int btmtksdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) { struct btmtk_hci_wmt_params wmt_params; - struct reg_read_cmd { - u8 type; - u8 rsv; - u8 num; - __le32 addr; - } __packed reg_read = { + struct reg_read_cmd reg_read = { .type = 1, .num = 1, }; @@ -821,7 +898,7 @@ static int btsdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) err = mtk_hci_wmt_sync(hdev, &wmt_params); if (err < 0) { - bt_dev_err(hdev, "Failed to read reg(%d)", err); + bt_dev_err(hdev, "Failed to read reg (%d)", err); return err; } @@ -830,6 +907,66 @@ static int btsdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) return err; } +static int btmtksdio_mtk_reg_write(struct hci_dev *hdev, u32 reg, u32 val, u32 mask) +{ + struct btmtk_hci_wmt_params wmt_params; + const struct reg_write_cmd reg_write = { + .type = 1, + .num = 1, + .addr = cpu_to_le32(reg), + .data = cpu_to_le32(val), + .mask = cpu_to_le32(mask), + }; + int err, status; + + wmt_params.op = BTMTK_WMT_REGISTER; + wmt_params.flag = BTMTK_WMT_REG_WRITE; + wmt_params.dlen = sizeof(reg_write); + wmt_params.data = ®_write; + wmt_params.status = &status; + + err = mtk_hci_wmt_sync(hdev, &wmt_params); + if (err < 0) + bt_dev_err(hdev, "Failed to write reg (%d)", err); + + return err; +} + +static int btmtksdio_sco_setting(struct hci_dev *hdev) +{ + const struct btmtk_sco sco_setting = { + .clock_config = 0x49, + .channel_format_config = 0x80, + }; + struct sk_buff *skb; + u32 val; + int err; + + /* Enable SCO over I2S/PCM for MediaTek chipset */ + skb = __hci_cmd_sync(hdev, 0xfc72, sizeof(sco_setting), + &sco_setting, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + kfree_skb(skb); + + err = btmtksdio_mtk_reg_read(hdev, MT7921_PINMUX_0, &val); + if (err < 0) + return err; + + val |= 0x11000000; + err = btmtksdio_mtk_reg_write(hdev, MT7921_PINMUX_0, val, ~0); + if (err < 0) + return err; + + err = btmtksdio_mtk_reg_read(hdev, MT7921_PINMUX_1, &val); + if (err < 0) + return err; + + val |= 0x00000101; + return btmtksdio_mtk_reg_write(hdev, MT7921_PINMUX_1, val, ~0); +} + static int btmtksdio_setup(struct hci_dev *hdev) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); @@ -844,13 +981,13 @@ static int btmtksdio_setup(struct hci_dev *hdev) switch (bdev->data->chipid) { case 0x7921: - err = btsdio_mtk_reg_read(hdev, 0x70010200, &dev_id); + err = btmtksdio_mtk_reg_read(hdev, 0x70010200, &dev_id); if (err < 0) { bt_dev_err(hdev, "Failed to get device id (%d)", err); return err; } - err = btsdio_mtk_reg_read(hdev, 0x80021004, &fw_version); + err = btmtksdio_mtk_reg_read(hdev, 0x80021004, &fw_version); if (err < 0) { bt_dev_err(hdev, "Failed to get fw version (%d)", err); return err; @@ -862,6 +999,22 @@ static int btmtksdio_setup(struct hci_dev *hdev) err = mt79xx_setup(hdev, fwname); if (err < 0) return err; + + err = btmtksdio_fw_pmctrl(bdev); + if (err < 0) + return err; + + err = btmtksdio_drv_pmctrl(bdev); + if (err < 0) + return err; + + /* Enable SCO over I2S/PCM */ + err = btmtksdio_sco_setting(hdev); + if (err < 0) { + bt_dev_err(hdev, "Failed to enable SCO setting (%d)", err); + return err; + } + break; case 0x7663: case 0x7668: @@ -958,6 +1111,32 @@ static int btmtksdio_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return 0; } +static bool btmtksdio_sdio_wakeup(struct hci_dev *hdev) +{ + struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); + bool may_wakeup = device_may_wakeup(bdev->dev); + const struct btmtk_wakeon bt_awake = { + .mode = 0x1, + .gpo = 0, + .active_high = 0x1, + .enable_delay = cpu_to_le16(0xc80), + .wakeup_delay = cpu_to_le16(0x20), + }; + + if (may_wakeup && bdev->data->chipid == 0x7921) { + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, 0xfc27, sizeof(bt_awake), + &bt_awake, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) + may_wakeup = false; + + kfree_skb(skb); + } + + return may_wakeup; +} + static int btmtksdio_probe(struct sdio_func *func, const struct sdio_device_id *id) { @@ -997,6 +1176,7 @@ static int btmtksdio_probe(struct sdio_func *func, hdev->setup = btmtksdio_setup; hdev->shutdown = btmtksdio_shutdown; hdev->send = btmtksdio_send_frame; + hdev->wakeup = btmtksdio_sdio_wakeup; hdev->set_bdaddr = btmtk_set_bdaddr; SET_HCIDEV_DEV(hdev, &func->dev); @@ -1032,7 +1212,11 @@ static int btmtksdio_probe(struct sdio_func *func, */ pm_runtime_put_noidle(bdev->dev); - return 0; + err = device_init_wakeup(bdev->dev, true); + if (err) + bt_dev_err(hdev, "failed to initialize device wakeup"); + + return err; } static void btmtksdio_remove(struct sdio_func *func) @@ -1058,7 +1242,6 @@ static int btmtksdio_runtime_suspend(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); struct btmtksdio_dev *bdev; - u32 status; int err; bdev = sdio_get_drvdata(func); @@ -1070,18 +1253,9 @@ static int btmtksdio_runtime_suspend(struct device *dev) sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER); - sdio_claim_host(bdev->func); + err = btmtksdio_fw_pmctrl(bdev); - sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, &err); - if (err < 0) - goto out; - - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - !(status & C_COM_DRV_OWN), 2000, 1000000); -out: - bt_dev_info(bdev->hdev, "status (%d) return ownership to device", err); - - sdio_release_host(bdev->func); + bt_dev_dbg(bdev->hdev, "status (%d) return ownership to device", err); return err; } @@ -1090,7 +1264,6 @@ static int btmtksdio_runtime_resume(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); struct btmtksdio_dev *bdev; - u32 status; int err; bdev = sdio_get_drvdata(func); @@ -1100,18 +1273,9 @@ static int btmtksdio_runtime_resume(struct device *dev) if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state)) return 0; - sdio_claim_host(bdev->func); + err = btmtksdio_drv_pmctrl(bdev); - sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err); - if (err < 0) - goto out; - - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - status & C_COM_DRV_OWN, 2000, 1000000); -out: - bt_dev_info(bdev->hdev, "status (%d) get ownership from device", err); - - sdio_release_host(bdev->func); + bt_dev_dbg(bdev->hdev, "status (%d) get ownership from device", err); return err; } diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index c2bdd1e6060e..c2030f7e25b4 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -149,6 +149,14 @@ static const struct id_table ic_id_table[] = { .cfg_name = "rtl_bt/rtl8761bu_config" }, /* 8822C with UART interface */ + { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0x8, HCI_UART), + .config_needed = true, + .has_rom_version = true, + .has_msft_ext = true, + .fw_name = "rtl_bt/rtl8822cs_fw.bin", + .cfg_name = "rtl_bt/rtl8822cs_config" }, + + /* 8822C with UART interface */ { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_UART), .config_needed = true, .has_rom_version = true, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index c30d131da784..aefa0ee293f3 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -62,6 +62,7 @@ static struct usb_driver btusb_driver; #define BTUSB_QCA_WCN6855 0x1000000 #define BTUSB_INTEL_BROKEN_SHUTDOWN_LED 0x2000000 #define BTUSB_INTEL_BROKEN_INITIAL_NCMD 0x4000000 +#define BTUSB_INTEL_NO_WBS_SUPPORT 0x8000000 static const struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ @@ -385,9 +386,11 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x8087, 0x0033), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL_COMBINED | + BTUSB_INTEL_NO_WBS_SUPPORT | BTUSB_INTEL_BROKEN_INITIAL_NCMD | BTUSB_INTEL_BROKEN_SHUTDOWN_LED }, { USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL_COMBINED | + BTUSB_INTEL_NO_WBS_SUPPORT | BTUSB_INTEL_BROKEN_SHUTDOWN_LED }, { USB_DEVICE(0x8087, 0x0a2b), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x0aa7), .driver_info = BTUSB_INTEL_COMBINED | @@ -405,6 +408,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, /* Realtek 8852AE Bluetooth devices */ + { USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0xc852), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x385a), .driver_info = BTUSB_REALTEK | @@ -2057,10 +2062,10 @@ static int btusb_setup_csr(struct hci_dev *hdev) * These controllers are really messed-up. * * 1. Their bulk RX endpoint will never report any data unless - * the device was suspended at least once (yes, really). + * the device was suspended at least once (yes, really). * 2. They will not wakeup when autosuspended and receiving data - * on their bulk RX endpoint from e.g. a keyboard or mouse - * (IOW remote-wakeup support is broken for the bulk endpoint). + * on their bulk RX endpoint from e.g. a keyboard or mouse + * (IOW remote-wakeup support is broken for the bulk endpoint). * * To fix 1. enable runtime-suspend, force-suspend the * HCI and then wake-it up by disabling runtime-suspend. @@ -3737,6 +3742,9 @@ static int btusb_probe(struct usb_interface *intf, hdev->send = btusb_send_frame_intel; hdev->cmd_timeout = btusb_intel_cmd_timeout; + if (id->driver_info & BTUSB_INTEL_NO_WBS_SUPPORT) + btintel_set_flag(hdev, INTEL_ROM_LEGACY_NO_WBS_SUPPORT); + if (id->driver_info & BTUSB_INTEL_BROKEN_INITIAL_NCMD) btintel_set_flag(hdev, INTEL_BROKEN_INITIAL_NCMD); diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 34286ffe0568..fdf504b0d265 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -966,6 +966,11 @@ static void h5_btrtl_open(struct h5 *h5) pm_runtime_enable(&h5->hu->serdev->dev); } + /* The controller needs reset to startup */ + gpiod_set_value_cansleep(h5->enable_gpio, 0); + gpiod_set_value_cansleep(h5->device_wake_gpio, 0); + msleep(100); + /* The controller needs up to 500ms to wakeup */ gpiod_set_value_cansleep(h5->enable_gpio, 1); gpiod_set_value_cansleep(h5->device_wake_gpio, 1); diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index eb1e736efeeb..4eb420a9ed04 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -509,7 +509,7 @@ static int send_command_from_firmware(struct ll_device *lldev, return 0; } -/** +/* * download_firmware - * internal function which parses through the .bts firmware * script file intreprets SEND, DELAY actions only as of now diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 3b00d82d36cf..4cda890ce647 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -305,6 +305,8 @@ int hci_uart_register_device(struct hci_uart *hu, if (err) return err; + percpu_init_rwsem(&hu->proto_lock); + err = p->open(hu); if (err) goto err_open; @@ -327,7 +329,6 @@ int hci_uart_register_device(struct hci_uart *hu, INIT_WORK(&hu->init_ready, hci_uart_init_work); INIT_WORK(&hu->write_work, hci_uart_write_work); - percpu_init_rwsem(&hu->proto_lock); /* Only when vendor specific setup callback is provided, consider * the manufacturer information valid. This avoids filling in the diff --git a/drivers/net/amt.c b/drivers/net/amt.c index f1a36d7e2151..10455c9b9da0 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -2373,7 +2373,7 @@ static bool amt_membership_query_handler(struct amt_dev *amt, skb->pkt_type = PACKET_MULTICAST; skb->ip_summed = CHECKSUM_NONE; len = skb->len; - if (netif_rx(skb) == NET_RX_SUCCESS) { + if (__netif_rx(skb) == NET_RX_SUCCESS) { amt_update_gw_status(amt, AMT_STATUS_RECEIVED_QUERY, true); dev_sw_netstats_rx_add(amt->dev, len); } else { @@ -2470,7 +2470,7 @@ report: skb->pkt_type = PACKET_MULTICAST; skb->ip_summed = CHECKSUM_NONE; len = skb->len; - if (netif_rx(skb) == NET_RX_SUCCESS) { + if (__netif_rx(skb) == NET_RX_SUCCESS) { amt_update_relay_status(tunnel, AMT_STATUS_RECEIVED_UPDATE, true); dev_sw_netstats_rx_add(amt->dev, len); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 533e476988f2..303c8d32d451 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -19,6 +19,7 @@ #include <linux/in.h> #include <net/arp.h> #include <net/ipv6.h> +#include <net/ndisc.h> #include <asm/byteorder.h> #include <net/bonding.h> #include <net/bond_alb.h> @@ -1269,6 +1270,27 @@ unwind: return res; } +/* determine if the packet is NA or NS */ +static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) +{ + struct ipv6hdr *ip6hdr; + struct icmp6hdr *hdr; + + if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) + return true; + + ip6hdr = ipv6_hdr(skb); + if (ip6hdr->nexthdr != IPPROTO_ICMPV6) + return false; + + if (!pskb_network_may_pull(skb, sizeof(*ip6hdr) + sizeof(*hdr))) + return true; + + hdr = icmp6_hdr(skb); + return hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT || + hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION; +} + /************************ exported alb functions ************************/ int bond_alb_initialize(struct bonding *bond, int rlb_enabled) @@ -1348,8 +1370,11 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, /* Do not TX balance any multicast or broadcast */ if (!is_multicast_ether_addr(eth_data->h_dest)) { switch (skb->protocol) { - case htons(ETH_P_IP): case htons(ETH_P_IPV6): + if (alb_determine_nd(skb, bond)) + break; + fallthrough; + case htons(ETH_P_IP): hash_index = bond_xmit_hash(bond, skb); if (bond->params.tlb_dynamic_lb) { tx_slave = tlb_choose_channel(bond, @@ -1432,10 +1457,12 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, break; } - if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) { + if (alb_determine_nd(skb, bond)) { do_tx_balance = false; break; } + + /* The IPv6 header is pulled by alb_determine_nd */ /* Additionally, DAD probes should not be tx-balanced as that * will lead to false positives for duplicate addresses and * prevent address configuration from working. diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index aebeb46e6fa6..57d182c9f7d5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -6047,27 +6047,38 @@ static int __net_init bond_net_init(struct net *net) return 0; } -static void __net_exit bond_net_exit(struct net *net) +static void __net_exit bond_net_exit_batch(struct list_head *net_list) { - struct bond_net *bn = net_generic(net, bond_net_id); - struct bonding *bond, *tmp_bond; + struct bond_net *bn; + struct net *net; LIST_HEAD(list); - bond_destroy_sysfs(bn); + list_for_each_entry(net, net_list, exit_list) { + bn = net_generic(net, bond_net_id); + bond_destroy_sysfs(bn); + } /* Kill off any bonds created after unregistering bond rtnl ops */ rtnl_lock(); - list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) - unregister_netdevice_queue(bond->dev, &list); + list_for_each_entry(net, net_list, exit_list) { + struct bonding *bond, *tmp_bond; + + bn = net_generic(net, bond_net_id); + list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) + unregister_netdevice_queue(bond->dev, &list); + } unregister_netdevice_many(&list); rtnl_unlock(); - bond_destroy_proc_dir(bn); + list_for_each_entry(net, net_list, exit_list) { + bn = net_generic(net, bond_net_id); + bond_destroy_proc_dir(bn); + } } static struct pernet_operations bond_net_ops = { .init = bond_net_init, - .exit = bond_net_exit, + .exit_batch = bond_net_exit_batch, .id = &bond_net_id, .size = sizeof(struct bond_net), }; diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 46b150e6289e..cfe37be42be4 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -307,7 +307,6 @@ void __net_init bond_create_proc_dir(struct bond_net *bn) } /* Destroy the bonding directory under /proc/net, if empty. - * Caller must hold rtnl_lock. */ void __net_exit bond_destroy_proc_dir(struct bond_net *bn) { diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 0029d279616f..37a3dabdce31 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -68,17 +68,7 @@ config NET_DSA_QCA8K This enables support for the Qualcomm Atheros QCA8K Ethernet switch chips. -config NET_DSA_REALTEK_SMI - tristate "Realtek SMI Ethernet switch family support" - select NET_DSA_TAG_RTL4_A - select NET_DSA_TAG_RTL8_4 - select FIXED_PHY - select IRQ_DOMAIN - select REALTEK_PHY - select REGMAP - help - This enables support for the Realtek SMI-based switch - chips, currently only RTL8366RB. +source "drivers/net/dsa/realtek/Kconfig" config NET_DSA_SMSC_LAN9303 tristate diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index 8da1569a34e6..e73838c12256 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -9,8 +9,6 @@ obj-$(CONFIG_NET_DSA_LANTIQ_GSWIP) += lantiq_gswip.o obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o -obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o -realtek-smi-objs := realtek-smi-core.o rtl8366.o rtl8366rb.o rtl8365mb.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o @@ -23,5 +21,6 @@ obj-y += microchip/ obj-y += mv88e6xxx/ obj-y += ocelot/ obj-y += qca/ +obj-y += realtek/ obj-y += sja1105/ obj-y += xrs700x/ diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 3867f3d4545f..a3b98992f180 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2186,7 +2186,7 @@ int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy) { int ret; - ret = phy_init_eee(phy, 0); + ret = phy_init_eee(phy, false); if (ret) return 0; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 6afb5db8244c..cf82b1fa9725 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -712,49 +712,25 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) PHY_BRCM_IDDQ_SUSPEND; } -static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void bcm_sf2_sw_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { + unsigned long *interfaces = config->supported_interfaces; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - - if (!phy_interface_mode_is_rgmii(state->interface) && - state->interface != PHY_INTERFACE_MODE_MII && - state->interface != PHY_INTERFACE_MODE_REVMII && - state->interface != PHY_INTERFACE_MODE_GMII && - state->interface != PHY_INTERFACE_MODE_INTERNAL && - state->interface != PHY_INTERFACE_MODE_MOCA) { - linkmode_zero(supported); - if (port != core_readl(priv, CORE_IMP0_PRT_ID)) - dev_err(ds->dev, - "Unsupported interface: %d for port %d\n", - state->interface, port); - return; - } - - /* Allow all the expected bits */ - phylink_set(mask, Autoneg); - phylink_set_port_modes(mask); - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - /* With the exclusion of MII and Reverse MII, we support Gigabit, - * including Half duplex - */ - if (state->interface != PHY_INTERFACE_MODE_MII && - state->interface != PHY_INTERFACE_MODE_REVMII) { - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseT_Half); + if (priv->int_phy_mask & BIT(port)) { + __set_bit(PHY_INTERFACE_MODE_INTERNAL, interfaces); + } else if (priv->moca_port == port) { + __set_bit(PHY_INTERFACE_MODE_MOCA, interfaces); + } else { + __set_bit(PHY_INTERFACE_MODE_MII, interfaces); + __set_bit(PHY_INTERFACE_MODE_REVMII, interfaces); + __set_bit(PHY_INTERFACE_MODE_GMII, interfaces); + phy_interface_set_rgmii(interfaces); } - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; } static void bcm_sf2_sw_mac_config(struct dsa_switch *ds, int port, @@ -1221,7 +1197,7 @@ static const struct dsa_switch_ops bcm_sf2_ops = { .get_sset_count = bcm_sf2_sw_get_sset_count, .get_ethtool_phy_stats = b53_get_ethtool_phy_stats, .get_phy_flags = bcm_sf2_sw_get_phy_flags, - .phylink_validate = bcm_sf2_sw_validate, + .phylink_get_caps = bcm_sf2_sw_get_caps, .phylink_mac_config = bcm_sf2_sw_mac_config, .phylink_mac_link_down = bcm_sf2_sw_mac_link_down, .phylink_mac_link_up = bcm_sf2_sw_mac_link_up, diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 991b9c6b6ce7..5dc9899bc0a6 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1461,27 +1461,22 @@ static int ksz8_setup(struct dsa_switch *ds) return 0; } -static void ksz8_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void ksz8_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; struct ksz_device *dev = ds->priv; if (port == dev->cpu_port) { - if (state->interface != PHY_INTERFACE_MODE_RMII && - state->interface != PHY_INTERFACE_MODE_MII && - state->interface != PHY_INTERFACE_MODE_NA) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_RMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_MII, + config->supported_interfaces); } else { - if (state->interface != PHY_INTERFACE_MODE_INTERNAL && - state->interface != PHY_INTERFACE_MODE_NA) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); } - /* Allow all the expected bits */ - phylink_set_port_modes(mask); - phylink_set(mask, Autoneg); + config->mac_capabilities = MAC_10 | MAC_100; /* Silicon Errata Sheet (DS80000830A): * "Port 1 does not respond to received flow control PAUSE frames" @@ -1489,27 +1484,11 @@ static void ksz8_validate(struct dsa_switch *ds, int port, * switches. */ if (!ksz_is_ksz88x3(dev) || port) - phylink_set(mask, Pause); + config->mac_capabilities |= MAC_SYM_PAUSE; /* Asym pause is not supported on KSZ8863 and KSZ8873 */ if (!ksz_is_ksz88x3(dev)) - phylink_set(mask, Asym_Pause); - - /* 10M and 100M are only supported */ - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); - - return; - -unsupported: - linkmode_zero(supported); - dev_err(ds->dev, "Unsupported interface: %s, port: %d\n", - phy_modes(state->interface), port); + config->mac_capabilities |= MAC_ASYM_PAUSE; } static const struct dsa_switch_ops ksz8_switch_ops = { @@ -1518,7 +1497,7 @@ static const struct dsa_switch_ops ksz8_switch_ops = { .setup = ksz8_setup, .phy_read = ksz_phy_read16, .phy_write = ksz_phy_write16, - .phylink_validate = ksz8_validate, + .phylink_get_caps = ksz8_get_caps, .phylink_mac_link_down = ksz_mac_link_down, .port_enable = ksz_enable_port, .get_strings = ksz8_get_strings, diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 353b5f981740..a85d990896b0 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -222,9 +222,12 @@ static int ksz9477_reset_switch(struct ksz_device *dev) (BROADCAST_STORM_VALUE * BROADCAST_STORM_PROT_RATE) / 100); - if (dev->synclko_125) - ksz_write8(dev, REG_SW_GLOBAL_OUTPUT_CTRL__1, - SW_ENABLE_REFCLKO | SW_REFCLKO_IS_125MHZ); + data8 = SW_ENABLE_REFCLKO; + if (dev->synclko_disable) + data8 = 0; + else if (dev->synclko_125) + data8 = SW_ENABLE_REFCLKO | SW_REFCLKO_IS_125MHZ; + ksz_write8(dev, REG_SW_GLOBAL_OUTPUT_CTRL__1, data8); return 0; } diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 55dbda04ea62..7e33ec73f803 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -434,6 +434,12 @@ int ksz_switch_register(struct ksz_device *dev, } dev->synclko_125 = of_property_read_bool(dev->dev->of_node, "microchip,synclko-125"); + dev->synclko_disable = of_property_read_bool(dev->dev->of_node, + "microchip,synclko-disable"); + if (dev->synclko_125 && dev->synclko_disable) { + dev_err(dev->dev, "inconsistent synclko settings\n"); + return -EINVAL; + } } ret = dsa_register_switch(dev->ds); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index df8ae59c8525..3db63f62f0a1 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -75,6 +75,7 @@ struct ksz_device { u32 regs_size; bool phy_errata_9477; bool synclko_125; + bool synclko_disable; struct vlan_table *vlan_cache; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index ff3c267d0f26..f74f25f479ed 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2846,7 +2846,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port, mcr |= PMCR_RX_FC_EN; } - if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, 0) >= 0) { + if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, false) >= 0) { switch (speed) { case SPEED_1000: mcr |= PMCR_FORCE_EEE1G; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index ab1676553714..7d5e72cdc125 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -86,12 +86,16 @@ int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val) int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask, u16 val) { + const unsigned long timeout = jiffies + msecs_to_jiffies(50); u16 data; int err; int i; - /* There's no bus specific operation to wait for a mask */ - for (i = 0; i < 16; i++) { + /* There's no bus specific operation to wait for a mask. Even + * if the initial poll takes longer than 50ms, always do at + * least one more attempt. + */ + for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) { err = mv88e6xxx_read(chip, addr, reg, &data); if (err) return err; @@ -99,7 +103,10 @@ int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, if ((data & mask) == val) return 0; - usleep_range(1000, 2000); + if (i < 2) + cpu_relax(); + else + usleep_range(1000, 2000); } dev_err(chip->dev, "Timeout while waiting for switch\n"); @@ -563,133 +570,268 @@ static int mv88e6xxx_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port, return 0; } -static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static const u8 mv88e6185_phy_interface_modes[] = { + [MV88E6185_PORT_STS_CMODE_GMII_FD] = PHY_INTERFACE_MODE_GMII, + [MV88E6185_PORT_STS_CMODE_MII_100_FD_PS] = PHY_INTERFACE_MODE_MII, + [MV88E6185_PORT_STS_CMODE_MII_100] = PHY_INTERFACE_MODE_MII, + [MV88E6185_PORT_STS_CMODE_MII_10] = PHY_INTERFACE_MODE_MII, + [MV88E6185_PORT_STS_CMODE_SERDES] = PHY_INTERFACE_MODE_1000BASEX, + [MV88E6185_PORT_STS_CMODE_1000BASE_X] = PHY_INTERFACE_MODE_1000BASEX, + [MV88E6185_PORT_STS_CMODE_PHY] = PHY_INTERFACE_MODE_SGMII, +}; + +static void mv88e6095_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (!phy_interface_mode_is_8023z(state->interface)) { - /* 10M and 100M are only supported in non-802.3z mode */ - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); + u8 cmode = chip->ports[port].cmode; + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100; + + if (mv88e6xxx_phy_is_internal(chip->ds, port)) { + __set_bit(PHY_INTERFACE_MODE_MII, config->supported_interfaces); + } else { + if (cmode < ARRAY_SIZE(mv88e6185_phy_interface_modes) && + mv88e6185_phy_interface_modes[cmode]) + __set_bit(mv88e6185_phy_interface_modes[cmode], + config->supported_interfaces); + + config->mac_capabilities |= MAC_1000FD; } } -static void mv88e6185_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6185_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - /* FIXME: if the port is in 1000Base-X mode, then it only supports - * 1000M FD speeds. In this case, CMODE will indicate 5. + u8 cmode = chip->ports[port].cmode; + + if (cmode < ARRAY_SIZE(mv88e6185_phy_interface_modes) && + mv88e6185_phy_interface_modes[cmode]) + __set_bit(mv88e6185_phy_interface_modes[cmode], + config->supported_interfaces); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; +} + +static const u8 mv88e6xxx_phy_interface_modes[] = { + [MV88E6XXX_PORT_STS_CMODE_MII_PHY] = PHY_INTERFACE_MODE_MII, + [MV88E6XXX_PORT_STS_CMODE_MII] = PHY_INTERFACE_MODE_MII, + [MV88E6XXX_PORT_STS_CMODE_GMII] = PHY_INTERFACE_MODE_GMII, + [MV88E6XXX_PORT_STS_CMODE_RMII_PHY] = PHY_INTERFACE_MODE_RMII, + [MV88E6XXX_PORT_STS_CMODE_RMII] = PHY_INTERFACE_MODE_RMII, + [MV88E6XXX_PORT_STS_CMODE_100BASEX] = PHY_INTERFACE_MODE_100BASEX, + [MV88E6XXX_PORT_STS_CMODE_1000BASEX] = PHY_INTERFACE_MODE_1000BASEX, + [MV88E6XXX_PORT_STS_CMODE_SGMII] = PHY_INTERFACE_MODE_SGMII, + /* higher interface modes are not needed here, since ports supporting + * them are writable, and so the supported interfaces are filled in the + * corresponding .phylink_set_interfaces() implementation below */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); +}; - mv88e6065_phylink_validate(chip, port, mask, state); +static void mv88e6xxx_translate_cmode(u8 cmode, unsigned long *supported) +{ + if (cmode < ARRAY_SIZE(mv88e6xxx_phy_interface_modes) && + mv88e6xxx_phy_interface_modes[cmode]) + __set_bit(mv88e6xxx_phy_interface_modes[cmode], supported); + else if (cmode == MV88E6XXX_PORT_STS_CMODE_RGMII) + phy_interface_set_rgmii(supported); } -static void mv88e6341_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (port >= 5) - phylink_set(mask, 2500baseX_Full); + unsigned long *supported = config->supported_interfaces; - /* No ethtool bits for 200Mbps */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); - mv88e6065_phylink_validate(chip, port, mask, state); + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100; } -static void mv88e6352_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static int mv88e6352_get_port4_serdes_cmode(struct mv88e6xxx_chip *chip) { - /* No ethtool bits for 200Mbps */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + u16 reg, val; + int err; + + err = mv88e6xxx_port_read(chip, 4, MV88E6XXX_PORT_STS, ®); + if (err) + return err; + + /* If PHY_DETECT is zero, then we are not in auto-media mode */ + if (!(reg & MV88E6XXX_PORT_STS_PHY_DETECT)) + return 0xf; + + val = reg & ~MV88E6XXX_PORT_STS_PHY_DETECT; + err = mv88e6xxx_port_write(chip, 4, MV88E6XXX_PORT_STS, val); + if (err) + return err; + + err = mv88e6xxx_port_read(chip, 4, MV88E6XXX_PORT_STS, &val); + if (err) + return err; - mv88e6065_phylink_validate(chip, port, mask, state); + /* Restore PHY_DETECT value */ + err = mv88e6xxx_port_write(chip, 4, MV88E6XXX_PORT_STS, reg); + if (err) + return err; + + return val & MV88E6XXX_PORT_STS_CMODE_MASK; } -static void mv88e6390_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6352_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (port >= 9) { - phylink_set(mask, 2500baseX_Full); - phylink_set(mask, 2500baseT_Full); + unsigned long *supported = config->supported_interfaces; + int err, cmode; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; + + /* Port 4 supports automedia if the serdes is associated with it. */ + if (port == 4) { + mv88e6xxx_reg_lock(chip); + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err < 0) + dev_err(chip->dev, "p%d: failed to read scratch\n", + port); + if (err <= 0) + goto unlock; + + cmode = mv88e6352_get_port4_serdes_cmode(chip); + if (cmode < 0) + dev_err(chip->dev, "p%d: failed to read serdes cmode\n", + port); + else + mv88e6xxx_translate_cmode(cmode, supported); +unlock: + mv88e6xxx_reg_unlock(chip); } +} + +static void mv88e6341_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) +{ + unsigned long *supported = config->supported_interfaces; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); /* No ethtool bits for 200Mbps */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; - mv88e6065_phylink_validate(chip, port, mask, state); + /* The C_Mode field is programmable on port 5 */ + if (port == 5) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); + + config->mac_capabilities |= MAC_2500FD; + } } -static void mv88e6390x_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6390_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (port >= 9) { - phylink_set(mask, 10000baseT_Full); - phylink_set(mask, 10000baseKR_Full); + unsigned long *supported = config->supported_interfaces; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + /* No ethtool bits for 200Mbps */ + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; + + /* The C_Mode field is programmable on ports 9 and 10 */ + if (port == 9 || port == 10) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); + + config->mac_capabilities |= MAC_2500FD; } +} + +static void mv88e6390x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) +{ + unsigned long *supported = config->supported_interfaces; + + mv88e6390_phylink_get_caps(chip, port, config); - mv88e6390_phylink_validate(chip, port, mask, state); + /* For the 6x90X, ports 2-7 can be in automedia mode. + * (Note that 6x90 doesn't support RXAUI nor XAUI). + * + * Port 2 can also support 1000BASE-X in automedia mode if port 9 is + * configured for 1000BASE-X, SGMII or 2500BASE-X. + * Port 3-4 can also support 1000BASE-X in automedia mode if port 9 is + * configured for RXAUI, 1000BASE-X, SGMII or 2500BASE-X. + * + * Port 5 can also support 1000BASE-X in automedia mode if port 10 is + * configured for 1000BASE-X, SGMII or 2500BASE-X. + * Port 6-7 can also support 1000BASE-X in automedia mode if port 10 is + * configured for RXAUI, 1000BASE-X, SGMII or 2500BASE-X. + * + * For now, be permissive (as the old code was) and allow 1000BASE-X + * on ports 2..7. + */ + if (port >= 2 && port <= 7) + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); + + /* The C_Mode field can also be programmed for 10G speeds */ + if (port == 9 || port == 10) { + __set_bit(PHY_INTERFACE_MODE_XAUI, supported); + __set_bit(PHY_INTERFACE_MODE_RXAUI, supported); + + config->mac_capabilities |= MAC_10000FD; + } } -static void mv88e6393x_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6393x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { + unsigned long *supported = config->supported_interfaces; bool is_6191x = chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6191X; - if (((port == 0 || port == 9) && !is_6191x) || port == 10) { - phylink_set(mask, 10000baseT_Full); - phylink_set(mask, 10000baseKR_Full); - phylink_set(mask, 10000baseCR_Full); - phylink_set(mask, 10000baseSR_Full); - phylink_set(mask, 10000baseLR_Full); - phylink_set(mask, 10000baseLRM_Full); - phylink_set(mask, 10000baseER_Full); - phylink_set(mask, 5000baseT_Full); - phylink_set(mask, 2500baseX_Full); - phylink_set(mask, 2500baseT_Full); - } + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + /* The C_Mode field can be programmed for ports 0, 9 and 10 */ + if (port == 0 || port == 9 || port == 10) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); - mv88e6065_phylink_validate(chip, port, mask, state); + /* 6191X supports >1G modes only on port 10 */ + if (!is_6191x || port == 10) { + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); + __set_bit(PHY_INTERFACE_MODE_5GBASER, supported); + __set_bit(PHY_INTERFACE_MODE_10GBASER, supported); + /* FIXME: USXGMII is not supported yet */ + /* __set_bit(PHY_INTERFACE_MODE_USXGMII, supported); */ + + config->mac_capabilities |= MAC_2500FD | MAC_5000FD | + MAC_10000FD; + } + } } -static void mv88e6xxx_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; struct mv88e6xxx_chip *chip = ds->priv; - /* Allow all the expected bits */ - phylink_set(mask, Autoneg); - phylink_set(mask, Pause); - phylink_set_port_modes(mask); - - if (chip->info->ops->phylink_validate) - chip->info->ops->phylink_validate(chip, port, mask, state); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + chip->info->ops->phylink_get_caps(chip, port, config); - /* We can only operate at 2500BaseX or 1000BaseX. If requested - * to advertise both, only report advertising at 2500BaseX. - */ - phylink_helper_basex_speed(state); + /* Internal ports need GMII for PHYLIB */ + if (mv88e6xxx_phy_is_internal(ds, port)) + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); } static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, @@ -1283,8 +1425,15 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) pvlan = 0; - /* Frames from user ports can egress any local DSA links and CPU ports, - * as well as any local member of their bridge group. + /* Frames from standalone user ports can only egress on the + * upstream port. + */ + if (!dsa_port_bridge_dev_get(dp)) + return BIT(dsa_switch_upstream_port(ds)); + + /* Frames from bridged user ports can egress any local DSA + * links and CPU ports, as well as any local member of their + * bridge group. */ dsa_switch_for_each_port(other_dp, ds) if (other_dp->type == DSA_PORT_TYPE_CPU || @@ -1616,21 +1765,11 @@ static int mv88e6xxx_fid_map_vlan(struct mv88e6xxx_chip *chip, int mv88e6xxx_fid_map(struct mv88e6xxx_chip *chip, unsigned long *fid_bitmap) { - int i, err; - u16 fid; - bitmap_zero(fid_bitmap, MV88E6XXX_N_FID); - /* Set every FID bit used by the (un)bridged ports */ - for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { - err = mv88e6xxx_port_get_fid(chip, i, &fid); - if (err) - return err; - - set_bit(fid, fid_bitmap); - } - - /* Set every FID bit used by the VLAN entries */ + /* Every FID has an associated VID, so walking the VTU + * will discover the full set of FIDs in use. + */ return mv88e6xxx_vtu_walk(chip, mv88e6xxx_fid_map_vlan, fid_bitmap); } @@ -1643,10 +1782,7 @@ static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) if (err) return err; - /* The reset value 0x000 is used to indicate that multiple address - * databases are not needed. Return the next positive available. - */ - *fid = find_next_zero_bit(fid_bitmap, MV88E6XXX_N_FID, 1); + *fid = find_first_zero_bit(fid_bitmap, MV88E6XXX_N_FID); if (unlikely(*fid >= mv88e6xxx_num_databases(chip))) return -ENOSPC; @@ -2138,6 +2274,9 @@ static int mv88e6xxx_port_vlan_join(struct mv88e6xxx_chip *chip, int port, if (!vlan.valid) { memset(&vlan, 0, sizeof(vlan)); + if (vid == MV88E6XXX_VID_STANDALONE) + vlan.policy = true; + err = mv88e6xxx_atu_new(chip, &vlan.fid); if (err) return err; @@ -2487,6 +2626,10 @@ static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, if (err) goto unlock; + err = mv88e6xxx_port_set_map_da(chip, port, true); + if (err) + goto unlock; + err = mv88e6xxx_port_commit_pvid(chip, port); if (err) goto unlock; @@ -2521,6 +2664,12 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, mv88e6xxx_port_vlan_map(chip, port)) dev_err(ds->dev, "failed to remap in-chip Port VLAN\n"); + err = mv88e6xxx_port_set_map_da(chip, port, false); + if (err) + dev_err(ds->dev, + "port %d failed to restore map-DA: %pe\n", + port, ERR_PTR(err)); + err = mv88e6xxx_port_commit_pvid(chip, port); if (err) dev_err(ds->dev, @@ -2864,7 +3013,10 @@ static int mv88e6xxx_setup_upstream_port(struct mv88e6xxx_chip *chip, int port) static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) { + struct device_node *phy_handle = NULL; struct dsa_switch *ds = chip->ds; + struct dsa_port *dp; + int tx_amp; int err; u16 reg; @@ -2918,12 +3070,13 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; /* Port Control 2: don't force a good FCS, set the MTU size to - * 10222 bytes, disable 802.1q tags checking, don't discard tagged or - * untagged frames on this port, do a destination address lookup on all - * received packets as usual, disable ARP mirroring and don't send a - * copy of all transmitted/received frames on this port to the CPU. + * 10222 bytes, disable 802.1q tags checking, don't discard + * tagged or untagged frames on this port, skip destination + * address lookup on user ports, disable ARP mirroring and don't + * send a copy of all transmitted/received frames on this port + * to the CPU. */ - err = mv88e6xxx_port_set_map_da(chip, port); + err = mv88e6xxx_port_set_map_da(chip, port, !dsa_is_user_port(ds, port)); if (err) return err; @@ -2931,8 +3084,44 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; + /* On chips that support it, set all downstream DSA ports' + * VLAN policy to TRAP. In combination with loading + * MV88E6XXX_VID_STANDALONE as a policy entry in the VTU, this + * provides a better isolation barrier between standalone + * ports, as the ATU is bypassed on any intermediate switches + * between the incoming port and the CPU. + */ + if (dsa_is_downstream_port(ds, port) && + chip->info->ops->port_set_policy) { + err = chip->info->ops->port_set_policy(chip, port, + MV88E6XXX_POLICY_MAPPING_VTU, + MV88E6XXX_POLICY_ACTION_TRAP); + if (err) + return err; + } + + /* User ports start out in standalone mode and 802.1Q is + * therefore disabled. On DSA ports, all valid VIDs are always + * loaded in the VTU - therefore, enable 802.1Q in order to take + * advantage of VLAN policy on chips that supports it. + */ err = mv88e6xxx_port_set_8021q_mode(chip, port, - MV88E6XXX_PORT_CTL2_8021Q_MODE_DISABLED); + dsa_is_user_port(ds, port) ? + MV88E6XXX_PORT_CTL2_8021Q_MODE_DISABLED : + MV88E6XXX_PORT_CTL2_8021Q_MODE_SECURE); + if (err) + return err; + + /* Bind MV88E6XXX_VID_STANDALONE to MV88E6XXX_FID_STANDALONE by + * virtue of the fact that mv88e6xxx_atu_new() will pick it as + * the first free FID. This will be used as the private PVID for + * unbridged ports. Shared (DSA and CPU) ports must also be + * members of this VID, in order to trap all frames assigned to + * it to the CPU. + */ + err = mv88e6xxx_port_vlan_join(chip, port, MV88E6XXX_VID_STANDALONE, + MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNMODIFIED, + false); if (err) return err; @@ -2945,7 +3134,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) * relying on their port default FID. */ err = mv88e6xxx_port_vlan_join(chip, port, MV88E6XXX_VID_BRIDGED, - MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNTAGGED, + MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNMODIFIED, false); if (err) return err; @@ -3018,6 +3207,23 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; } + if (chip->info->ops->serdes_set_tx_amplitude) { + dp = dsa_to_port(ds, port); + if (dp) + phy_handle = of_parse_phandle(dp->dn, "phy-handle", 0); + + if (phy_handle && !of_property_read_u32(phy_handle, + "tx-p2p-microvolt", + &tx_amp)) + err = chip->info->ops->serdes_set_tx_amplitude(chip, + port, tx_amp); + if (phy_handle) { + of_node_put(phy_handle); + if (err) + return err; + } + } + /* Port based VLAN map: give each port the same default address * database, and allow bidirectional communication between the * CPU and DSA port(s), and the other ports. @@ -3589,7 +3795,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3623,7 +3829,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = { .reset = mv88e6185_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6095_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3639,6 +3845,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_sync_link = mv88e6185_port_sync_link, .port_set_speed_duplex = mv88e6185_port_set_speed_duplex, .port_tag_remap = mv88e6095_port_tag_remap, + .port_set_policy = mv88e6352_port_set_policy, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, @@ -3669,7 +3876,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6095_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3706,7 +3913,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3747,7 +3954,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = { .reset = mv88e6185_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6141_ops = { @@ -3811,7 +4018,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6341_phylink_validate, + .phylink_get_caps = mv88e6341_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6161_ops = { @@ -3853,7 +4060,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .avb_ops = &mv88e6165_avb_ops, .ptp_ops = &mv88e6165_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3889,7 +4096,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .avb_ops = &mv88e6165_avb_ops, .ptp_ops = &mv88e6165_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6171_ops = { @@ -3931,7 +4138,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6172_ops = { @@ -3986,7 +4193,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6352_phylink_validate, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6175_ops = { @@ -4028,7 +4235,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6176_ops = { @@ -4085,8 +4292,9 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .serdes_irq_status = mv88e6352_serdes_irq_status, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, + .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6352_phylink_validate, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6185_ops = { @@ -4125,7 +4333,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = { .reset = mv88e6185_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -4187,7 +4395,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6190x_ops = { @@ -4248,7 +4456,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6390x_phylink_validate, + .phylink_get_caps = mv88e6390x_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6191_ops = { @@ -4308,7 +4516,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .serdes_get_regs = mv88e6390_serdes_get_regs, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6240_ops = { @@ -4365,10 +4573,11 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .serdes_irq_status = mv88e6352_serdes_irq_status, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, + .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6352_phylink_validate, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6250_ops = { @@ -4408,7 +4617,7 @@ static const struct mv88e6xxx_ops mv88e6250_ops = { .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6250_ptp_ops, - .phylink_validate = mv88e6065_phylink_validate, + .phylink_get_caps = mv88e6250_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6290_ops = { @@ -4470,7 +4679,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6320_ops = { @@ -4514,7 +4723,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6321_ops = { @@ -4556,7 +4765,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6341_ops = { @@ -4622,7 +4831,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6341_phylink_validate, + .phylink_get_caps = mv88e6341_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6350_ops = { @@ -4664,7 +4873,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6351_ops = { @@ -4708,7 +4917,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6352_ops = { @@ -4771,7 +4980,8 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .serdes_get_stats = mv88e6352_serdes_get_stats, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .phylink_validate = mv88e6352_phylink_validate, + .serdes_set_tx_amplitude = mv88e6352_serdes_set_tx_amplitude, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6390_ops = { @@ -4836,7 +5046,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6390x_ops = { @@ -4900,7 +5110,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6390x_phylink_validate, + .phylink_get_caps = mv88e6390x_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6393x_ops = { @@ -4964,7 +5174,7 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6393x_phylink_validate, + .phylink_get_caps = mv88e6393x_phylink_get_caps, }; static const struct mv88e6xxx_info mv88e6xxx_table[] = { @@ -6233,7 +6443,7 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .teardown = mv88e6xxx_teardown, .port_setup = mv88e6xxx_port_setup, .port_teardown = mv88e6xxx_port_teardown, - .phylink_validate = mv88e6xxx_validate, + .phylink_get_caps = mv88e6xxx_get_caps, .phylink_mac_link_state = mv88e6xxx_serdes_pcs_get_state, .phylink_mac_config = mv88e6xxx_mac_config, .phylink_mac_an_restart = mv88e6xxx_serdes_pcs_an_restart, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 8271b8aa7b71..30b92a265613 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -179,6 +179,7 @@ struct mv88e6xxx_vtu_entry { u16 fid; u8 sid; bool valid; + bool policy; u8 member[DSA_MAX_PORTS]; u8 state[DSA_MAX_PORTS]; }; @@ -392,6 +393,7 @@ struct mv88e6xxx_chip { struct mv88e6xxx_bus_ops { int (*read)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int (*write)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); + int (*init)(struct mv88e6xxx_chip *chip); }; struct mv88e6xxx_mdio_bus { @@ -586,6 +588,10 @@ struct mv88e6xxx_ops { void (*serdes_get_regs)(struct mv88e6xxx_chip *chip, int port, void *_p); + /* SERDES SGMII/Fiber Output Amplitude */ + int (*serdes_set_tx_amplitude)(struct mv88e6xxx_chip *chip, int port, + int val); + /* Address Translation Unit operations */ int (*atu_get_hash)(struct mv88e6xxx_chip *chip, u8 *hash); int (*atu_set_hash)(struct mv88e6xxx_chip *chip, u8 hash); @@ -609,9 +615,8 @@ struct mv88e6xxx_ops { const struct mv88e6xxx_ptp_ops *ptp_ops; /* Phylink */ - void (*phylink_validate)(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state); + void (*phylink_get_caps)(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config); /* Max Frame Size */ int (*set_max_frame_size)(struct mv88e6xxx_chip *chip, int mtu); diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 4f3dbb015f77..2c1607c858a1 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -46,6 +46,7 @@ /* Offset 0x02: VTU FID Register */ #define MV88E6352_G1_VTU_FID 0x02 +#define MV88E6352_G1_VTU_FID_VID_POLICY 0x1000 #define MV88E6352_G1_VTU_FID_MASK 0x0fff /* Offset 0x03: VTU SID Register */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c index ae12c981923e..b1bd9274a562 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c @@ -27,7 +27,7 @@ static int mv88e6xxx_g1_vtu_fid_read(struct mv88e6xxx_chip *chip, return err; entry->fid = val & MV88E6352_G1_VTU_FID_MASK; - + entry->policy = !!(val & MV88E6352_G1_VTU_FID_VID_POLICY); return 0; } @@ -36,6 +36,9 @@ static int mv88e6xxx_g1_vtu_fid_write(struct mv88e6xxx_chip *chip, { u16 val = entry->fid & MV88E6352_G1_VTU_FID_MASK; + if (entry->policy) + val |= MV88E6352_G1_VTU_FID_VID_POLICY; + return mv88e6xxx_g1_write(chip, MV88E6352_G1_VTU_FID, val); } diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index f3e27573a386..807aeaad9830 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -299,6 +299,8 @@ #define MV88E6352_G2_SCRATCH_CONFIG_DATA1_NO_CPU BIT(2) #define MV88E6352_G2_SCRATCH_CONFIG_DATA2 0x72 #define MV88E6352_G2_SCRATCH_CONFIG_DATA2_P0_MODE_MASK 0x3 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA3 0x73 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA3_S_SEL BIT(1) #define MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO 0 #define MV88E6352_G2_SCRATCH_GPIO_PCTL_TRIG 1 @@ -370,6 +372,7 @@ extern const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops; int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, bool external); +int mv88e6352_g2_scratch_port_has_serdes(struct mv88e6xxx_chip *chip, int port); int mv88e6xxx_g2_atu_stats_set(struct mv88e6xxx_chip *chip, u16 kind, u16 bin); int mv88e6xxx_g2_atu_stats_get(struct mv88e6xxx_chip *chip, u16 *stats); diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c index eda710062933..a9d6e40321a2 100644 --- a/drivers/net/dsa/mv88e6xxx/global2_scratch.c +++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c @@ -289,3 +289,31 @@ int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, return mv88e6xxx_g2_scratch_write(chip, misc_cfg, val); } + +/** + * mv88e6352_g2_scratch_port_has_serdes - indicate if a port can have a serdes + * @chip: chip private data + * @port: port number to check for serdes + * + * Indicates whether the port may have a serdes attached according to the + * pin strapping. Returns negative error number, 0 if the port is not + * configured to have a serdes, and 1 if the port is configured to have a + * serdes attached. + */ +int mv88e6352_g2_scratch_port_has_serdes(struct mv88e6xxx_chip *chip, int port) +{ + u8 config3, p; + int err; + + err = mv88e6xxx_g2_scratch_read(chip, MV88E6352_G2_SCRATCH_CONFIG_DATA3, + &config3); + if (err) + return err; + + if (config3 & MV88E6352_G2_SCRATCH_CONFIG_DATA3_S_SEL) + p = 5; + else + p = 4; + + return port == p; +} diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index ab41619a809b..ceb450113f88 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -1278,7 +1278,7 @@ int mv88e6xxx_port_drop_untagged(struct mv88e6xxx_chip *chip, int port, return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL2, new); } -int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port) +int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port, bool map) { u16 reg; int err; @@ -1287,7 +1287,10 @@ int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port) if (err) return err; - reg |= MV88E6XXX_PORT_CTL2_MAP_DA; + if (map) + reg |= MV88E6XXX_PORT_CTL2_MAP_DA; + else + reg &= ~MV88E6XXX_PORT_CTL2_MAP_DA; return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL2, reg); } diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 03382b66f800..3a13db2ec27b 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -42,6 +42,11 @@ #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_MII_PHY 0x0001 +#define MV88E6XXX_PORT_STS_CMODE_MII 0x0002 +#define MV88E6XXX_PORT_STS_CMODE_GMII 0x0003 +#define MV88E6XXX_PORT_STS_CMODE_RMII_PHY 0x0004 +#define MV88E6XXX_PORT_STS_CMODE_RMII 0x0005 #define MV88E6XXX_PORT_STS_CMODE_RGMII 0x0007 #define MV88E6XXX_PORT_STS_CMODE_100BASEX 0x0008 #define MV88E6XXX_PORT_STS_CMODE_1000BASEX 0x0009 @@ -425,7 +430,7 @@ int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); int mv88e6xxx_port_drop_untagged(struct mv88e6xxx_chip *chip, int port, bool drop_untagged); -int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port); +int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port, bool map); int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port); int mv88e6xxx_port_set_mirror(struct mv88e6xxx_chip *chip, int port, diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 2b05ead515cd..7b37d45bc9fb 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -272,14 +272,6 @@ int mv88e6352_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) return lane; } -static bool mv88e6352_port_has_serdes(struct mv88e6xxx_chip *chip, int port) -{ - if (mv88e6xxx_serdes_get_lane(chip, port) >= 0) - return true; - - return false; -} - struct mv88e6352_serdes_hw_stat { char string[ETH_GSTRING_LEN]; int sizeof_stat; @@ -293,20 +285,24 @@ static struct mv88e6352_serdes_hw_stat mv88e6352_serdes_hw_stats[] = { int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port) { - if (mv88e6352_port_has_serdes(chip, port)) - return ARRAY_SIZE(mv88e6352_serdes_hw_stats); + int err; - return 0; + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) + return err; + + return ARRAY_SIZE(mv88e6352_serdes_hw_stats); } int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, uint8_t *data) { struct mv88e6352_serdes_hw_stat *stat; - int i; + int err, i; - if (!mv88e6352_port_has_serdes(chip, port)) - return 0; + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) + return err; for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_hw_stats); i++) { stat = &mv88e6352_serdes_hw_stats[i]; @@ -348,11 +344,12 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, { struct mv88e6xxx_port *mv88e6xxx_port = &chip->ports[port]; struct mv88e6352_serdes_hw_stat *stat; + int i, err; u64 value; - int i; - if (!mv88e6352_port_has_serdes(chip, port)) - return 0; + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) + return err; BUILD_BUG_ON(ARRAY_SIZE(mv88e6352_serdes_hw_stats) > ARRAY_SIZE(mv88e6xxx_port->serdes_stats)); @@ -419,8 +416,13 @@ unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port) int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port) { - if (!mv88e6352_port_has_serdes(chip, port)) - return 0; + int err; + + mv88e6xxx_reg_lock(chip); + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + mv88e6xxx_reg_unlock(chip); + if (err <= 0) + return err; return 32 * sizeof(u16); } @@ -432,7 +434,8 @@ void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) int err; int i; - if (!mv88e6352_port_has_serdes(chip, port)) + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) return; for (i = 0 ; i < 32; i++) { @@ -1310,6 +1313,44 @@ void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) } } +static const int mv88e6352_serdes_p2p_to_reg[] = { + /* Index of value in microvolts corresponds to the register value */ + 14000, 112000, 210000, 308000, 406000, 504000, 602000, 700000, +}; + +int mv88e6352_serdes_set_tx_amplitude(struct mv88e6xxx_chip *chip, int port, + int val) +{ + bool found = false; + u16 ctrl, reg; + int err; + int i; + + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) + return err; + + for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_p2p_to_reg); ++i) { + if (mv88e6352_serdes_p2p_to_reg[i] == val) { + reg = i; + found = true; + break; + } + } + + if (!found) + return -EINVAL; + + err = mv88e6352_serdes_read(chip, MV88E6352_SERDES_SPEC_CTRL2, &ctrl); + if (err) + return err; + + ctrl &= ~MV88E6352_SERDES_OUT_AMP_MASK; + ctrl |= reg; + + return mv88e6352_serdes_write(chip, MV88E6352_SERDES_SPEC_CTRL2, ctrl); +} + static int mv88e6393x_serdes_power_lane(struct mv88e6xxx_chip *chip, int lane, bool on) { diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index 8dd8ed225b45..29bb4e91e2f6 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -27,6 +27,8 @@ #define MV88E6352_SERDES_INT_FIBRE_ENERGY BIT(4) #define MV88E6352_SERDES_INT_STATUS 0x13 +#define MV88E6352_SERDES_SPEC_CTRL2 0x1a +#define MV88E6352_SERDES_OUT_AMP_MASK 0x0007 #define MV88E6341_PORT5_LANE 0x15 @@ -176,6 +178,9 @@ void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); int mv88e6390_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port); void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); +int mv88e6352_serdes_set_tx_amplitude(struct mv88e6xxx_chip *chip, int port, + int val); + /* Return the (first) SERDES lane address a port is using, -errno otherwise. */ static inline int mv88e6xxx_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) diff --git a/drivers/net/dsa/mv88e6xxx/smi.c b/drivers/net/dsa/mv88e6xxx/smi.c index 282fe08db050..a990271b7482 100644 --- a/drivers/net/dsa/mv88e6xxx/smi.c +++ b/drivers/net/dsa/mv88e6xxx/smi.c @@ -55,11 +55,15 @@ static int mv88e6xxx_smi_direct_write(struct mv88e6xxx_chip *chip, static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, int dev, int reg, int bit, int val) { + const unsigned long timeout = jiffies + msecs_to_jiffies(50); u16 data; int err; int i; - for (i = 0; i < 16; i++) { + /* Even if the initial poll takes longer than 50ms, always do + * at least one more attempt. + */ + for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) { err = mv88e6xxx_smi_direct_read(chip, dev, reg, &data); if (err) return err; @@ -67,7 +71,10 @@ static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, if (!!(data & BIT(bit)) == !!val) return 0; - usleep_range(1000, 2000); + if (i < 2) + cpu_relax(); + else + usleep_range(1000, 2000); } return -ETIMEDOUT; @@ -104,11 +111,6 @@ static int mv88e6xxx_smi_indirect_read(struct mv88e6xxx_chip *chip, { int err; - err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, - MV88E6XXX_SMI_CMD, 15, 0); - if (err) - return err; - err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr, MV88E6XXX_SMI_CMD, MV88E6XXX_SMI_CMD_BUSY | @@ -132,11 +134,6 @@ static int mv88e6xxx_smi_indirect_write(struct mv88e6xxx_chip *chip, { int err; - err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, - MV88E6XXX_SMI_CMD, 15, 0); - if (err) - return err; - err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr, MV88E6XXX_SMI_DATA, data); if (err) @@ -155,9 +152,20 @@ static int mv88e6xxx_smi_indirect_write(struct mv88e6xxx_chip *chip, MV88E6XXX_SMI_CMD, 15, 0); } +static int mv88e6xxx_smi_indirect_init(struct mv88e6xxx_chip *chip) +{ + /* Ensure that the chip starts out in the ready state. As both + * reads and writes always ensure this on return, they can + * safely depend on the chip not being busy on entry. + */ + return mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, + MV88E6XXX_SMI_CMD, 15, 0); +} + static const struct mv88e6xxx_bus_ops mv88e6xxx_smi_indirect_ops = { .read = mv88e6xxx_smi_indirect_read, .write = mv88e6xxx_smi_indirect_write, + .init = mv88e6xxx_smi_indirect_init, }; int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip, @@ -175,5 +183,8 @@ int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip, chip->bus = bus; chip->sw_addr = sw_addr; + if (chip->smi_ops->init) + return chip->smi_ops->init(chip); + return 0; } diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 9957772201d5..9ffd5491bf2d 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -50,7 +50,7 @@ static int felix_tag_8021q_rxvlan_add(struct felix *felix, int port, u16 vid, outer_tagging_rule->key_type = OCELOT_VCAP_KEY_ANY; outer_tagging_rule->prio = 1; - outer_tagging_rule->id.cookie = port; + outer_tagging_rule->id.cookie = OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port); outer_tagging_rule->id.tc_offload = false; outer_tagging_rule->block_id = VCAP_ES0; outer_tagging_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; @@ -103,7 +103,7 @@ static int felix_tag_8021q_txvlan_add(struct felix *felix, int port, u16 vid, untagging_rule->vlan.vid.value = vid; untagging_rule->vlan.vid.mask = VLAN_VID_MASK; untagging_rule->prio = 1; - untagging_rule->id.cookie = port; + untagging_rule->id.cookie = OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port); untagging_rule->id.tc_offload = false; untagging_rule->block_id = VCAP_IS1; untagging_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; @@ -124,7 +124,7 @@ static int felix_tag_8021q_txvlan_add(struct felix *felix, int port, u16 vid, redirect_rule->ingress_port_mask = BIT(upstream); redirect_rule->pag = port; redirect_rule->prio = 1; - redirect_rule->id.cookie = port; + redirect_rule->id.cookie = OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port); redirect_rule->id.tc_offload = false; redirect_rule->block_id = VCAP_IS2; redirect_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; @@ -267,148 +267,82 @@ static void felix_8021q_cpu_port_deinit(struct ocelot *ocelot, int port) mutex_unlock(&ocelot->fwd_domain_lock); } -/* Set up a VCAP IS2 rule for delivering PTP frames to the CPU port module. - * If the quirk_no_xtr_irq is in place, then also copy those PTP frames to the - * tag_8021q CPU port. +/* On switches with no extraction IRQ wired, trapped packets need to be + * replicated over Ethernet as well, otherwise we'd get no notification of + * their arrival when using the ocelot-8021q tagging protocol. */ -static int felix_setup_mmio_filtering(struct felix *felix) +static int felix_update_trapping_destinations(struct dsa_switch *ds, + bool using_tag_8021q) { - unsigned long user_ports = dsa_user_ports(felix->ds); - struct ocelot_vcap_filter *redirect_rule; - struct ocelot_vcap_filter *tagging_rule; - struct ocelot *ocelot = &felix->ocelot; - struct dsa_switch *ds = felix->ds; - int cpu = -1, port, ret; + struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + struct ocelot_vcap_filter *trap; + enum ocelot_mask_mode mask_mode; + unsigned long port_mask; + struct dsa_port *dp; + bool cpu_copy_ena; + int cpu = -1, err; - tagging_rule = kzalloc(sizeof(struct ocelot_vcap_filter), GFP_KERNEL); - if (!tagging_rule) - return -ENOMEM; + if (!felix->info->quirk_no_xtr_irq) + return 0; - redirect_rule = kzalloc(sizeof(struct ocelot_vcap_filter), GFP_KERNEL); - if (!redirect_rule) { - kfree(tagging_rule); - return -ENOMEM; + /* Figure out the current CPU port */ + dsa_switch_for_each_cpu_port(dp, ds) { + cpu = dp->index; + break; } - for (port = 0; port < ocelot->num_phys_ports; port++) { - if (dsa_is_cpu_port(ds, port)) { - cpu = port; - break; + /* We are sure that "cpu" was found, otherwise + * dsa_tree_setup_default_cpu() would have failed earlier. + */ + + /* Make sure all traps are set up for that destination */ + list_for_each_entry(trap, &ocelot->traps, trap_list) { + /* Figure out the current trapping destination */ + if (using_tag_8021q) { + /* Redirect to the tag_8021q CPU port. If timestamps + * are necessary, also copy trapped packets to the CPU + * port module. + */ + mask_mode = OCELOT_MASK_MODE_REDIRECT; + port_mask = BIT(cpu); + cpu_copy_ena = !!trap->take_ts; + } else { + /* Trap packets only to the CPU port module, which is + * redirected to the NPI port (the DSA CPU port) + */ + mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; + port_mask = 0; + cpu_copy_ena = true; } - } - if (cpu < 0) { - kfree(tagging_rule); - kfree(redirect_rule); - return -EINVAL; - } + if (trap->action.mask_mode == mask_mode && + trap->action.port_mask == port_mask && + trap->action.cpu_copy_ena == cpu_copy_ena) + continue; - tagging_rule->key_type = OCELOT_VCAP_KEY_ETYPE; - *(__be16 *)tagging_rule->key.etype.etype.value = htons(ETH_P_1588); - *(__be16 *)tagging_rule->key.etype.etype.mask = htons(0xffff); - tagging_rule->ingress_port_mask = user_ports; - tagging_rule->prio = 1; - tagging_rule->id.cookie = ocelot->num_phys_ports; - tagging_rule->id.tc_offload = false; - tagging_rule->block_id = VCAP_IS1; - tagging_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; - tagging_rule->lookup = 0; - tagging_rule->action.pag_override_mask = 0xff; - tagging_rule->action.pag_val = ocelot->num_phys_ports; - - ret = ocelot_vcap_filter_add(ocelot, tagging_rule, NULL); - if (ret) { - kfree(tagging_rule); - kfree(redirect_rule); - return ret; - } + trap->action.mask_mode = mask_mode; + trap->action.port_mask = port_mask; + trap->action.cpu_copy_ena = cpu_copy_ena; - redirect_rule->key_type = OCELOT_VCAP_KEY_ANY; - redirect_rule->ingress_port_mask = user_ports; - redirect_rule->pag = ocelot->num_phys_ports; - redirect_rule->prio = 1; - redirect_rule->id.cookie = ocelot->num_phys_ports; - redirect_rule->id.tc_offload = false; - redirect_rule->block_id = VCAP_IS2; - redirect_rule->type = OCELOT_VCAP_FILTER_OFFLOAD; - redirect_rule->lookup = 0; - redirect_rule->action.cpu_copy_ena = true; - if (felix->info->quirk_no_xtr_irq) { - /* Redirect to the tag_8021q CPU but also copy PTP packets to - * the CPU port module - */ - redirect_rule->action.mask_mode = OCELOT_MASK_MODE_REDIRECT; - redirect_rule->action.port_mask = BIT(cpu); - } else { - /* Trap PTP packets only to the CPU port module (which is - * redirected to the NPI port) - */ - redirect_rule->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; - redirect_rule->action.port_mask = 0; - } - - ret = ocelot_vcap_filter_add(ocelot, redirect_rule, NULL); - if (ret) { - ocelot_vcap_filter_del(ocelot, tagging_rule); - kfree(redirect_rule); - return ret; + err = ocelot_vcap_filter_replace(ocelot, trap); + if (err) + return err; } - /* The ownership of the CPU port module's queues might have just been - * transferred to the tag_8021q tagger from the NPI-based tagger. - * So there might still be all sorts of crap in the queues. On the - * other hand, the MMIO-based matching of PTP frames is very brittle, - * so we need to be careful that there are no extra frames to be - * dequeued over MMIO, since we would never know to discard them. - */ - ocelot_drain_cpu_queue(ocelot, 0); - return 0; } -static int felix_teardown_mmio_filtering(struct felix *felix) -{ - struct ocelot_vcap_filter *tagging_rule, *redirect_rule; - struct ocelot_vcap_block *block_vcap_is1; - struct ocelot_vcap_block *block_vcap_is2; - struct ocelot *ocelot = &felix->ocelot; - int err; - - block_vcap_is1 = &ocelot->block[VCAP_IS1]; - block_vcap_is2 = &ocelot->block[VCAP_IS2]; - - tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, - ocelot->num_phys_ports, - false); - if (!tagging_rule) - return -ENOENT; - - err = ocelot_vcap_filter_del(ocelot, tagging_rule); - if (err) - return err; - - redirect_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, - ocelot->num_phys_ports, - false); - if (!redirect_rule) - return -ENOENT; - - return ocelot_vcap_filter_del(ocelot, redirect_rule); -} - static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) { struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); unsigned long cpu_flood; - int port, err; + struct dsa_port *dp; + int err; felix_8021q_cpu_port_init(ocelot, cpu); - for (port = 0; port < ds->num_ports; port++) { - if (dsa_is_unused_port(ds, port)) - continue; - + dsa_switch_for_each_available_port(dp, ds) { /* This overwrites ocelot_init(): * Do not forward BPDU frames to the CPU port module, * for 2 reasons: @@ -421,7 +355,7 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) */ ocelot_write_gix(ocelot, ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0), - ANA_PORT_CPU_FWD_BPDU_CFG, port); + ANA_PORT_CPU_FWD_BPDU_CFG, dp->index); } /* In tag_8021q mode, the CPU port module is unused, except for PTP @@ -437,10 +371,19 @@ static int felix_setup_tag_8021q(struct dsa_switch *ds, int cpu) if (err) return err; - err = felix_setup_mmio_filtering(felix); + err = felix_update_trapping_destinations(ds, true); if (err) goto out_tag_8021q_unregister; + /* The ownership of the CPU port module's queues might have just been + * transferred to the tag_8021q tagger from the NPI-based tagger. + * So there might still be all sorts of crap in the queues. On the + * other hand, the MMIO-based matching of PTP frames is very brittle, + * so we need to be careful that there are no extra frames to be + * dequeued over MMIO, since we would never know to discard them. + */ + ocelot_drain_cpu_queue(ocelot, 0); + return 0; out_tag_8021q_unregister: @@ -451,27 +394,24 @@ out_tag_8021q_unregister: static void felix_teardown_tag_8021q(struct dsa_switch *ds, int cpu) { struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); - int err, port; + struct dsa_port *dp; + int err; - err = felix_teardown_mmio_filtering(felix); + err = felix_update_trapping_destinations(ds, false); if (err) dev_err(ds->dev, "felix_teardown_mmio_filtering returned %d", err); dsa_tag_8021q_unregister(ds); - for (port = 0; port < ds->num_ports; port++) { - if (dsa_is_unused_port(ds, port)) - continue; - + dsa_switch_for_each_available_port(dp, ds) { /* Restore the logic from ocelot_init: * do not forward BPDU frames to the front ports. */ ocelot_write_gix(ocelot, ANA_PORT_CPU_FWD_BPDU_CFG_BPDU_REDIR_ENA(0xffff), ANA_PORT_CPU_FWD_BPDU_CFG, - port); + dp->index); } felix_8021q_cpu_port_deinit(ocelot, cpu); @@ -1192,7 +1132,8 @@ static int felix_setup(struct dsa_switch *ds) { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); - int port, err; + struct dsa_port *dp; + int err; err = felix_init_structs(felix, ds->num_ports); if (err) @@ -1211,30 +1152,24 @@ static int felix_setup(struct dsa_switch *ds) } } - for (port = 0; port < ds->num_ports; port++) { - if (dsa_is_unused_port(ds, port)) - continue; - - ocelot_init_port(ocelot, port); + dsa_switch_for_each_available_port(dp, ds) { + ocelot_init_port(ocelot, dp->index); /* Set the default QoS Classification based on PCP and DEI * bits of vlan tag. */ - felix_port_qos_map_init(ocelot, port); + felix_port_qos_map_init(ocelot, dp->index); } err = ocelot_devlink_sb_register(ocelot); if (err) goto out_deinit_ports; - for (port = 0; port < ds->num_ports; port++) { - if (!dsa_is_cpu_port(ds, port)) - continue; - + dsa_switch_for_each_cpu_port(dp, ds) { /* The initial tag protocol is NPI which always returns 0, so * there's no real point in checking for errors. */ - felix_set_tag_protocol(ds, port, felix->tag_proto); + felix_set_tag_protocol(ds, dp->index, felix->tag_proto); break; } @@ -1244,12 +1179,8 @@ static int felix_setup(struct dsa_switch *ds) return 0; out_deinit_ports: - for (port = 0; port < ocelot->num_phys_ports; port++) { - if (dsa_is_unused_port(ds, port)) - continue; - - ocelot_deinit_port(ocelot, port); - } + dsa_switch_for_each_available_port(dp, ds) + ocelot_deinit_port(ocelot, dp->index); ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -1265,22 +1196,15 @@ static void felix_teardown(struct dsa_switch *ds) { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); - int port; - - for (port = 0; port < ds->num_ports; port++) { - if (!dsa_is_cpu_port(ds, port)) - continue; + struct dsa_port *dp; - felix_del_tag_protocol(ds, port, felix->tag_proto); + dsa_switch_for_each_cpu_port(dp, ds) { + felix_del_tag_protocol(ds, dp->index, felix->tag_proto); break; } - for (port = 0; port < ocelot->num_phys_ports; port++) { - if (dsa_is_unused_port(ds, port)) - continue; - - ocelot_deinit_port(ocelot, port); - } + dsa_switch_for_each_available_port(dp, ds) + ocelot_deinit_port(ocelot, dp->index); ocelot_devlink_sb_unregister(ocelot); ocelot_deinit_timestamp(ocelot); @@ -1302,8 +1226,17 @@ static int felix_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) { struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + bool using_tag_8021q; + int err; + + err = ocelot_hwstamp_set(ocelot, port, ifr); + if (err) + return err; + + using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q; - return ocelot_hwstamp_set(ocelot, port, ifr); + return felix_update_trapping_destinations(ds, using_tag_8021q); } static bool felix_check_xtr_pkt(struct ocelot *ocelot, unsigned int ptp_type) @@ -1430,8 +1363,17 @@ static int felix_cls_flower_add(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress) { struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + bool using_tag_8021q; + int err; + + err = ocelot_cls_flower_replace(ocelot, port, cls, ingress); + if (err) + return err; + + using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q; - return ocelot_cls_flower_replace(ocelot, port, cls, ingress); + return felix_update_trapping_destinations(ds, using_tag_8021q); } static int felix_cls_flower_del(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index c39de2a4c1fe..e5098cfe44bc 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -499,52 +499,27 @@ static enum dsa_tag_protocol ar9331_sw_get_tag_protocol(struct dsa_switch *ds, return DSA_TAG_PROTO_AR9331; } -static void ar9331_sw_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void ar9331_sw_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; switch (port) { case 0: - if (state->interface != PHY_INTERFACE_MODE_GMII) - goto unsupported; - - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseT_Half); + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); + config->mac_capabilities |= MAC_1000; break; case 1: case 2: case 3: case 4: case 5: - if (state->interface != PHY_INTERFACE_MODE_INTERNAL) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); break; - default: - linkmode_zero(supported); - dev_err(ds->dev, "Unsupported port: %i\n", port); - return; } - - phylink_set_port_modes(mask); - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); - - return; - -unsupported: - linkmode_zero(supported); - dev_err(ds->dev, "Unsupported interface: %d, port: %d\n", - state->interface, port); } static void ar9331_sw_phylink_mac_config(struct dsa_switch *ds, int port, @@ -697,7 +672,7 @@ static const struct dsa_switch_ops ar9331_sw_ops = { .get_tag_protocol = ar9331_sw_get_tag_protocol, .setup = ar9331_sw_setup, .port_disable = ar9331_sw_port_disable, - .phylink_validate = ar9331_sw_phylink_validate, + .phylink_get_caps = ar9331_sw_phylink_get_caps, .phylink_mac_config = ar9331_sw_phylink_mac_config, .phylink_mac_link_down = ar9331_sw_phylink_mac_link_down, .phylink_mac_link_up = ar9331_sw_phylink_mac_link_up, diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 039694518788..c09d1569e66b 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -20,6 +20,7 @@ #include <linux/phylink.h> #include <linux/gpio/consumer.h> #include <linux/etherdevice.h> +#include <linux/dsa/tag_qca.h> #include "qca8k.h" @@ -74,12 +75,6 @@ static const struct qca8k_mib_desc ar8327_mib[] = { MIB_DESC(1, 0xac, "TXUnicast"), }; -/* The 32bit switch registers are accessed indirectly. To achieve this we need - * to set the page of the register. Track the last page that was set to reduce - * mdio writes - */ -static u16 qca8k_current_page = 0xffff; - static void qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page) { @@ -94,6 +89,44 @@ qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page) } static int +qca8k_set_lo(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 lo) +{ + u16 *cached_lo = &priv->mdio_cache.lo; + struct mii_bus *bus = priv->bus; + int ret; + + if (lo == *cached_lo) + return 0; + + ret = bus->write(bus, phy_id, regnum, lo); + if (ret < 0) + dev_err_ratelimited(&bus->dev, + "failed to write qca8k 32bit lo register\n"); + + *cached_lo = lo; + return 0; +} + +static int +qca8k_set_hi(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 hi) +{ + u16 *cached_hi = &priv->mdio_cache.hi; + struct mii_bus *bus = priv->bus; + int ret; + + if (hi == *cached_hi) + return 0; + + ret = bus->write(bus, phy_id, regnum, hi); + if (ret < 0) + dev_err_ratelimited(&bus->dev, + "failed to write qca8k 32bit hi register\n"); + + *cached_hi = hi; + return 0; +} + +static int qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val) { int ret; @@ -116,7 +149,7 @@ qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val) } static void -qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val) +qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val) { u16 lo, hi; int ret; @@ -124,20 +157,19 @@ qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val) lo = val & 0xffff; hi = (u16)(val >> 16); - ret = bus->write(bus, phy_id, regnum, lo); + ret = qca8k_set_lo(priv, phy_id, regnum, lo); if (ret >= 0) - ret = bus->write(bus, phy_id, regnum + 1, hi); - if (ret < 0) - dev_err_ratelimited(&bus->dev, - "failed to write qca8k 32bit register\n"); + ret = qca8k_set_hi(priv, phy_id, regnum + 1, hi); } static int -qca8k_set_page(struct mii_bus *bus, u16 page) +qca8k_set_page(struct qca8k_priv *priv, u16 page) { + u16 *cached_page = &priv->mdio_cache.page; + struct mii_bus *bus = priv->bus; int ret; - if (page == qca8k_current_page) + if (page == *cached_page) return 0; ret = bus->write(bus, 0x18, 0, page); @@ -147,7 +179,7 @@ qca8k_set_page(struct mii_bus *bus, u16 page) return ret; } - qca8k_current_page = page; + *cached_page = page; usleep_range(1000, 2000); return 0; } @@ -170,6 +202,252 @@ qca8k_rmw(struct qca8k_priv *priv, u32 reg, u32 mask, u32 write_val) return regmap_update_bits(priv->regmap, reg, mask, write_val); } +static void qca8k_rw_reg_ack_handler(struct dsa_switch *ds, struct sk_buff *skb) +{ + struct qca8k_mgmt_eth_data *mgmt_eth_data; + struct qca8k_priv *priv = ds->priv; + struct qca_mgmt_ethhdr *mgmt_ethhdr; + u8 len, cmd; + + mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb_mac_header(skb); + mgmt_eth_data = &priv->mgmt_eth_data; + + cmd = FIELD_GET(QCA_HDR_MGMT_CMD, mgmt_ethhdr->command); + len = FIELD_GET(QCA_HDR_MGMT_LENGTH, mgmt_ethhdr->command); + + /* Make sure the seq match the requested packet */ + if (mgmt_ethhdr->seq == mgmt_eth_data->seq) + mgmt_eth_data->ack = true; + + if (cmd == MDIO_READ) { + mgmt_eth_data->data[0] = mgmt_ethhdr->mdio_data; + + /* Get the rest of the 12 byte of data. + * The read/write function will extract the requested data. + */ + if (len > QCA_HDR_MGMT_DATA1_LEN) + memcpy(mgmt_eth_data->data + 1, skb->data, + QCA_HDR_MGMT_DATA2_LEN); + } + + complete(&mgmt_eth_data->rw_done); +} + +static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 *val, + int priority, unsigned int len) +{ + struct qca_mgmt_ethhdr *mgmt_ethhdr; + unsigned int real_len; + struct sk_buff *skb; + u32 *data2; + u16 hdr; + + skb = dev_alloc_skb(QCA_HDR_MGMT_PKT_LEN); + if (!skb) + return NULL; + + /* Max value for len reg is 15 (0xf) but the switch actually return 16 byte + * Actually for some reason the steps are: + * 0: nothing + * 1-4: first 4 byte + * 5-6: first 12 byte + * 7-15: all 16 byte + */ + if (len == 16) + real_len = 15; + else + real_len = len; + + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb->len); + + mgmt_ethhdr = skb_push(skb, QCA_HDR_MGMT_HEADER_LEN + QCA_HDR_LEN); + + hdr = FIELD_PREP(QCA_HDR_XMIT_VERSION, QCA_HDR_VERSION); + hdr |= FIELD_PREP(QCA_HDR_XMIT_PRIORITY, priority); + hdr |= QCA_HDR_XMIT_FROM_CPU; + hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(0)); + hdr |= FIELD_PREP(QCA_HDR_XMIT_CONTROL, QCA_HDR_XMIT_TYPE_RW_REG); + + mgmt_ethhdr->command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); + mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); + mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); + mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, + QCA_HDR_MGMT_CHECK_CODE_VAL); + + if (cmd == MDIO_WRITE) + mgmt_ethhdr->mdio_data = *val; + + mgmt_ethhdr->hdr = htons(hdr); + + data2 = skb_put_zero(skb, QCA_HDR_MGMT_DATA2_LEN + QCA_HDR_MGMT_PADDING_LEN); + if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) + memcpy(data2, val + 1, len - QCA_HDR_MGMT_DATA1_LEN); + + return skb; +} + +static void qca8k_mdio_header_fill_seq_num(struct sk_buff *skb, u32 seq_num) +{ + struct qca_mgmt_ethhdr *mgmt_ethhdr; + + mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb->data; + mgmt_ethhdr->seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); +} + +static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + struct qca8k_mgmt_eth_data *mgmt_eth_data = &priv->mgmt_eth_data; + struct sk_buff *skb; + bool ack; + int ret; + + skb = qca8k_alloc_mdio_header(MDIO_READ, reg, NULL, + QCA8K_ETHERNET_MDIO_PRIORITY, len); + if (!skb) + return -ENOMEM; + + mutex_lock(&mgmt_eth_data->mutex); + + /* Check mgmt_master if is operational */ + if (!priv->mgmt_master) { + kfree_skb(skb); + mutex_unlock(&mgmt_eth_data->mutex); + return -EINVAL; + } + + skb->dev = priv->mgmt_master; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the mdio pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT)); + + *val = mgmt_eth_data->data[0]; + if (len > QCA_HDR_MGMT_DATA1_LEN) + memcpy(val + 1, mgmt_eth_data->data + 1, len - QCA_HDR_MGMT_DATA1_LEN); + + ack = mgmt_eth_data->ack; + + mutex_unlock(&mgmt_eth_data->mutex); + + if (ret <= 0) + return -ETIMEDOUT; + + if (!ack) + return -EINVAL; + + return 0; +} + +static int qca8k_write_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + struct qca8k_mgmt_eth_data *mgmt_eth_data = &priv->mgmt_eth_data; + struct sk_buff *skb; + bool ack; + int ret; + + skb = qca8k_alloc_mdio_header(MDIO_WRITE, reg, val, + QCA8K_ETHERNET_MDIO_PRIORITY, len); + if (!skb) + return -ENOMEM; + + mutex_lock(&mgmt_eth_data->mutex); + + /* Check mgmt_master if is operational */ + if (!priv->mgmt_master) { + kfree_skb(skb); + mutex_unlock(&mgmt_eth_data->mutex); + return -EINVAL; + } + + skb->dev = priv->mgmt_master; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the mdio pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT)); + + ack = mgmt_eth_data->ack; + + mutex_unlock(&mgmt_eth_data->mutex); + + if (ret <= 0) + return -ETIMEDOUT; + + if (!ack) + return -EINVAL; + + return 0; +} + +static int +qca8k_regmap_update_bits_eth(struct qca8k_priv *priv, u32 reg, u32 mask, u32 write_val) +{ + u32 val = 0; + int ret; + + ret = qca8k_read_eth(priv, reg, &val, sizeof(val)); + if (ret) + return ret; + + val &= ~mask; + val |= write_val; + + return qca8k_write_eth(priv, reg, &val, sizeof(val)); +} + +static int +qca8k_bulk_read(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + int i, count = len / sizeof(u32), ret; + + if (priv->mgmt_master && !qca8k_read_eth(priv, reg, val, len)) + return 0; + + for (i = 0; i < count; i++) { + ret = regmap_read(priv->regmap, reg + (i * 4), val + i); + if (ret < 0) + return ret; + } + + return 0; +} + +static int +qca8k_bulk_write(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + int i, count = len / sizeof(u32), ret; + u32 tmp; + + if (priv->mgmt_master && !qca8k_write_eth(priv, reg, val, len)) + return 0; + + for (i = 0; i < count; i++) { + tmp = val[i]; + + ret = regmap_write(priv->regmap, reg + (i * 4), tmp); + if (ret < 0) + return ret; + } + + return 0; +} + static int qca8k_regmap_read(void *ctx, uint32_t reg, uint32_t *val) { @@ -178,11 +456,14 @@ qca8k_regmap_read(void *ctx, uint32_t reg, uint32_t *val) u16 r1, r2, page; int ret; + if (!qca8k_read_eth(priv, reg, val, sizeof(*val))) + return 0; + qca8k_split_addr(reg, &r1, &r2, &page); mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret < 0) goto exit; @@ -201,15 +482,18 @@ qca8k_regmap_write(void *ctx, uint32_t reg, uint32_t val) u16 r1, r2, page; int ret; + if (!qca8k_write_eth(priv, reg, &val, sizeof(val))) + return 0; + qca8k_split_addr(reg, &r1, &r2, &page); mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret < 0) goto exit; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); exit: mutex_unlock(&bus->mdio_lock); @@ -225,11 +509,14 @@ qca8k_regmap_update_bits(void *ctx, uint32_t reg, uint32_t mask, uint32_t write_ u32 val; int ret; + if (!qca8k_regmap_update_bits_eth(priv, reg, mask, write_val)) + return 0; + qca8k_split_addr(reg, &r1, &r2, &page); mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret < 0) goto exit; @@ -239,7 +526,7 @@ qca8k_regmap_update_bits(void *ctx, uint32_t reg, uint32_t mask, uint32_t write_ val &= ~mask; val |= write_val; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); exit: mutex_unlock(&bus->mdio_lock); @@ -296,17 +583,13 @@ qca8k_busy_wait(struct qca8k_priv *priv, u32 reg, u32 mask) static int qca8k_fdb_read(struct qca8k_priv *priv, struct qca8k_fdb *fdb) { - u32 reg[4], val; - int i, ret; + u32 reg[3]; + int ret; /* load the ARL table into an array */ - for (i = 0; i < 4; i++) { - ret = qca8k_read(priv, QCA8K_REG_ATU_DATA0 + (i * 4), &val); - if (ret < 0) - return ret; - - reg[i] = val; - } + ret = qca8k_bulk_read(priv, QCA8K_REG_ATU_DATA0, reg, sizeof(reg)); + if (ret) + return ret; /* vid - 83:72 */ fdb->vid = FIELD_GET(QCA8K_ATU_VID_MASK, reg[2]); @@ -330,7 +613,6 @@ qca8k_fdb_write(struct qca8k_priv *priv, u16 vid, u8 port_mask, const u8 *mac, u8 aging) { u32 reg[3] = { 0 }; - int i; /* vid - 83:72 */ reg[2] = FIELD_PREP(QCA8K_ATU_VID_MASK, vid); @@ -347,8 +629,7 @@ qca8k_fdb_write(struct qca8k_priv *priv, u16 vid, u8 port_mask, const u8 *mac, reg[0] |= FIELD_PREP(QCA8K_ATU_ADDR5_MASK, mac[5]); /* load the array into the ARL table */ - for (i = 0; i < 3; i++) - qca8k_write(priv, QCA8K_REG_ATU_DATA0 + (i * 4), reg[i]); + qca8k_bulk_write(priv, QCA8K_REG_ATU_DATA0, reg, sizeof(reg)); } static int @@ -632,7 +913,10 @@ qca8k_mib_init(struct qca8k_priv *priv) int ret; mutex_lock(&priv->reg_mutex); - ret = regmap_set_bits(priv->regmap, QCA8K_REG_MIB, QCA8K_MIB_FLUSH | QCA8K_MIB_BUSY); + ret = regmap_update_bits(priv->regmap, QCA8K_REG_MIB, + QCA8K_MIB_FUNC | QCA8K_MIB_BUSY, + FIELD_PREP(QCA8K_MIB_FUNC, QCA8K_MIB_FLUSH) | + QCA8K_MIB_BUSY); if (ret) goto exit; @@ -666,6 +950,199 @@ qca8k_port_set_status(struct qca8k_priv *priv, int port, int enable) regmap_clear_bits(priv->regmap, QCA8K_REG_PORT_STATUS(port), mask); } +static int +qca8k_phy_eth_busy_wait(struct qca8k_mgmt_eth_data *mgmt_eth_data, + struct sk_buff *read_skb, u32 *val) +{ + struct sk_buff *skb = skb_copy(read_skb, GFP_KERNEL); + bool ack; + int ret; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the copy pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + ack = mgmt_eth_data->ack; + + if (ret <= 0) + return -ETIMEDOUT; + + if (!ack) + return -EINVAL; + + *val = mgmt_eth_data->data[0]; + + return 0; +} + +static int +qca8k_phy_eth_command(struct qca8k_priv *priv, bool read, int phy, + int regnum, u16 data) +{ + struct sk_buff *write_skb, *clear_skb, *read_skb; + struct qca8k_mgmt_eth_data *mgmt_eth_data; + u32 write_val, clear_val = 0, val; + struct net_device *mgmt_master; + int ret, ret1; + bool ack; + + if (regnum >= QCA8K_MDIO_MASTER_MAX_REG) + return -EINVAL; + + mgmt_eth_data = &priv->mgmt_eth_data; + + write_val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN | + QCA8K_MDIO_MASTER_PHY_ADDR(phy) | + QCA8K_MDIO_MASTER_REG_ADDR(regnum); + + if (read) { + write_val |= QCA8K_MDIO_MASTER_READ; + } else { + write_val |= QCA8K_MDIO_MASTER_WRITE; + write_val |= QCA8K_MDIO_MASTER_DATA(data); + } + + /* Prealloc all the needed skb before the lock */ + write_skb = qca8k_alloc_mdio_header(MDIO_WRITE, QCA8K_MDIO_MASTER_CTRL, &write_val, + QCA8K_ETHERNET_PHY_PRIORITY, sizeof(write_val)); + if (!write_skb) + return -ENOMEM; + + clear_skb = qca8k_alloc_mdio_header(MDIO_WRITE, QCA8K_MDIO_MASTER_CTRL, &clear_val, + QCA8K_ETHERNET_PHY_PRIORITY, sizeof(clear_val)); + if (!clear_skb) { + ret = -ENOMEM; + goto err_clear_skb; + } + + read_skb = qca8k_alloc_mdio_header(MDIO_READ, QCA8K_MDIO_MASTER_CTRL, &clear_val, + QCA8K_ETHERNET_PHY_PRIORITY, sizeof(clear_val)); + if (!read_skb) { + ret = -ENOMEM; + goto err_read_skb; + } + + /* Actually start the request: + * 1. Send mdio master packet + * 2. Busy Wait for mdio master command + * 3. Get the data if we are reading + * 4. Reset the mdio master (even with error) + */ + mutex_lock(&mgmt_eth_data->mutex); + + /* Check if mgmt_master is operational */ + mgmt_master = priv->mgmt_master; + if (!mgmt_master) { + mutex_unlock(&mgmt_eth_data->mutex); + ret = -EINVAL; + goto err_mgmt_master; + } + + read_skb->dev = mgmt_master; + clear_skb->dev = mgmt_master; + write_skb->dev = mgmt_master; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the write pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(write_skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(write_skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + ack = mgmt_eth_data->ack; + + if (ret <= 0) { + ret = -ETIMEDOUT; + kfree_skb(read_skb); + goto exit; + } + + if (!ack) { + ret = -EINVAL; + kfree_skb(read_skb); + goto exit; + } + + ret = read_poll_timeout(qca8k_phy_eth_busy_wait, ret1, + !(val & QCA8K_MDIO_MASTER_BUSY), 0, + QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false, + mgmt_eth_data, read_skb, &val); + + if (ret < 0 && ret1 < 0) { + ret = ret1; + goto exit; + } + + if (read) { + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the read pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(read_skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(read_skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + ack = mgmt_eth_data->ack; + + if (ret <= 0) { + ret = -ETIMEDOUT; + goto exit; + } + + if (!ack) { + ret = -EINVAL; + goto exit; + } + + ret = mgmt_eth_data->data[0] & QCA8K_MDIO_MASTER_DATA_MASK; + } else { + kfree_skb(read_skb); + } +exit: + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the clear pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(clear_skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(clear_skb); + + wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + mutex_unlock(&mgmt_eth_data->mutex); + + return ret; + + /* Error handling before lock */ +err_mgmt_master: + kfree_skb(read_skb); +err_read_skb: + kfree_skb(clear_skb); +err_clear_skb: + kfree_skb(write_skb); + + return ret; +} + static u32 qca8k_port_to_phy(int port) { @@ -704,8 +1181,9 @@ qca8k_mdio_busy_wait(struct mii_bus *bus, u32 reg, u32 mask) } static int -qca8k_mdio_write(struct mii_bus *bus, int phy, int regnum, u16 data) +qca8k_mdio_write(struct qca8k_priv *priv, int phy, int regnum, u16 data) { + struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -722,18 +1200,18 @@ qca8k_mdio_write(struct mii_bus *bus, int phy, int regnum, u16 data) mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret) goto exit; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL, QCA8K_MDIO_MASTER_BUSY); exit: /* even if the busy_wait timeouts try to clear the MASTER_EN */ - qca8k_mii_write32(bus, 0x10 | r2, r1, 0); + qca8k_mii_write32(priv, 0x10 | r2, r1, 0); mutex_unlock(&bus->mdio_lock); @@ -741,8 +1219,9 @@ exit: } static int -qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) +qca8k_mdio_read(struct qca8k_priv *priv, int phy, int regnum) { + struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -758,11 +1237,11 @@ qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret) goto exit; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL, QCA8K_MDIO_MASTER_BUSY); @@ -773,7 +1252,7 @@ qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) exit: /* even if the busy_wait timeouts try to clear the MASTER_EN */ - qca8k_mii_write32(bus, 0x10 | r2, r1, 0); + qca8k_mii_write32(priv, 0x10 | r2, r1, 0); mutex_unlock(&bus->mdio_lock); @@ -787,24 +1266,35 @@ static int qca8k_internal_mdio_write(struct mii_bus *slave_bus, int phy, int regnum, u16 data) { struct qca8k_priv *priv = slave_bus->priv; - struct mii_bus *bus = priv->bus; + int ret; - return qca8k_mdio_write(bus, phy, regnum, data); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, false, phy, regnum, data); + if (!ret) + return 0; + + return qca8k_mdio_write(priv, phy, regnum, data); } static int qca8k_internal_mdio_read(struct mii_bus *slave_bus, int phy, int regnum) { struct qca8k_priv *priv = slave_bus->priv; - struct mii_bus *bus = priv->bus; + int ret; - return qca8k_mdio_read(bus, phy, regnum); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, true, phy, regnum, 0); + if (ret >= 0) + return ret; + + return qca8k_mdio_read(priv, phy, regnum); } static int qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) { struct qca8k_priv *priv = ds->priv; + int ret; /* Check if the legacy mapping should be used and the * port is not correctly mapped to the right PHY in the @@ -813,7 +1303,12 @@ qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) if (priv->legacy_phy_port_mapping) port = qca8k_port_to_phy(port) % PHY_MAX_ADDR; - return qca8k_mdio_write(priv->bus, port, regnum, data); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, false, port, regnum, 0); + if (!ret) + return ret; + + return qca8k_mdio_write(priv, port, regnum, data); } static int @@ -829,7 +1324,12 @@ qca8k_phy_read(struct dsa_switch *ds, int port, int regnum) if (priv->legacy_phy_port_mapping) port = qca8k_port_to_phy(port) % PHY_MAX_ADDR; - ret = qca8k_mdio_read(priv->bus, port, regnum); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, true, port, regnum, 0); + if (ret >= 0) + return ret; + + ret = qca8k_mdio_read(priv, port, regnum); if (ret < 0) return 0xffff; @@ -1531,67 +2031,39 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, } } -static void -qca8k_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void qca8k_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - switch (port) { case 0: /* 1st CPU port */ - if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != PHY_INTERFACE_MODE_RGMII && - state->interface != PHY_INTERFACE_MODE_RGMII_ID && - state->interface != PHY_INTERFACE_MODE_RGMII_TXID && - state->interface != PHY_INTERFACE_MODE_RGMII_RXID && - state->interface != PHY_INTERFACE_MODE_SGMII) - goto unsupported; + phy_interface_set_rgmii(config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, + config->supported_interfaces); break; + case 1: case 2: case 3: case 4: case 5: /* Internal PHY */ - if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != PHY_INTERFACE_MODE_GMII && - state->interface != PHY_INTERFACE_MODE_INTERNAL) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); break; + case 6: /* 2nd CPU port / external PHY */ - if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != PHY_INTERFACE_MODE_RGMII && - state->interface != PHY_INTERFACE_MODE_RGMII_ID && - state->interface != PHY_INTERFACE_MODE_RGMII_TXID && - state->interface != PHY_INTERFACE_MODE_RGMII_RXID && - state->interface != PHY_INTERFACE_MODE_SGMII && - state->interface != PHY_INTERFACE_MODE_1000BASEX) - goto unsupported; + phy_interface_set_rgmii(config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + config->supported_interfaces); break; - default: -unsupported: - linkmode_zero(supported); - return; } - phylink_set_port_modes(mask); - phylink_set(mask, Autoneg); - - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - if (state->interface == PHY_INTERFACE_MODE_1000BASEX) - phylink_set(mask, 1000baseX_Full); - - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000FD; } static int @@ -1703,6 +2175,97 @@ qca8k_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) ETH_GSTRING_LEN); } +static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *skb) +{ + const struct qca8k_match_data *match_data; + struct qca8k_mib_eth_data *mib_eth_data; + struct qca8k_priv *priv = ds->priv; + const struct qca8k_mib_desc *mib; + struct mib_ethhdr *mib_ethhdr; + int i, mib_len, offset = 0; + u64 *data; + u8 port; + + mib_ethhdr = (struct mib_ethhdr *)skb_mac_header(skb); + mib_eth_data = &priv->mib_eth_data; + + /* The switch autocast every port. Ignore other packet and + * parse only the requested one. + */ + port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, ntohs(mib_ethhdr->hdr)); + if (port != mib_eth_data->req_port) + goto exit; + + match_data = device_get_match_data(priv->dev); + data = mib_eth_data->data; + + for (i = 0; i < match_data->mib_count; i++) { + mib = &ar8327_mib[i]; + + /* First 3 mib are present in the skb head */ + if (i < 3) { + data[i] = mib_ethhdr->data[i]; + continue; + } + + mib_len = sizeof(uint32_t); + + /* Some mib are 64 bit wide */ + if (mib->size == 2) + mib_len = sizeof(uint64_t); + + /* Copy the mib value from packet to the */ + memcpy(data + i, skb->data + offset, mib_len); + + /* Set the offset for the next mib */ + offset += mib_len; + } + +exit: + /* Complete on receiving all the mib packet */ + if (refcount_dec_and_test(&mib_eth_data->port_parsed)) + complete(&mib_eth_data->rw_done); +} + +static int +qca8k_get_ethtool_stats_eth(struct dsa_switch *ds, int port, u64 *data) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct qca8k_mib_eth_data *mib_eth_data; + struct qca8k_priv *priv = ds->priv; + int ret; + + mib_eth_data = &priv->mib_eth_data; + + mutex_lock(&mib_eth_data->mutex); + + reinit_completion(&mib_eth_data->rw_done); + + mib_eth_data->req_port = dp->index; + mib_eth_data->data = data; + refcount_set(&mib_eth_data->port_parsed, QCA8K_NUM_PORTS); + + mutex_lock(&priv->reg_mutex); + + /* Send mib autocast request */ + ret = regmap_update_bits(priv->regmap, QCA8K_REG_MIB, + QCA8K_MIB_FUNC | QCA8K_MIB_BUSY, + FIELD_PREP(QCA8K_MIB_FUNC, QCA8K_MIB_CAST) | + QCA8K_MIB_BUSY); + + mutex_unlock(&priv->reg_mutex); + + if (ret) + goto exit; + + ret = wait_for_completion_timeout(&mib_eth_data->rw_done, QCA8K_ETHERNET_TIMEOUT); + +exit: + mutex_unlock(&mib_eth_data->mutex); + + return ret; +} + static void qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) @@ -1714,6 +2277,10 @@ qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, u32 hi = 0; int ret; + if (priv->mgmt_master && + qca8k_get_ethtool_stats_eth(ds, port, data) > 0) + return; + match_data = of_device_get_match_data(priv->dev); for (i = 0; i < match_data->mib_count; i++) { @@ -2383,6 +2950,46 @@ qca8k_port_lag_leave(struct dsa_switch *ds, int port, return qca8k_lag_refresh_portmap(ds, port, lag, true); } +static void +qca8k_master_change(struct dsa_switch *ds, const struct net_device *master, + bool operational) +{ + struct dsa_port *dp = master->dsa_ptr; + struct qca8k_priv *priv = ds->priv; + + /* Ethernet MIB/MDIO is only supported for CPU port 0 */ + if (dp->index != 0) + return; + + mutex_lock(&priv->mgmt_eth_data.mutex); + mutex_lock(&priv->mib_eth_data.mutex); + + priv->mgmt_master = operational ? (struct net_device *)master : NULL; + + mutex_unlock(&priv->mib_eth_data.mutex); + mutex_unlock(&priv->mgmt_eth_data.mutex); +} + +static int qca8k_connect_tag_protocol(struct dsa_switch *ds, + enum dsa_tag_protocol proto) +{ + struct qca_tagger_data *tagger_data; + + switch (proto) { + case DSA_TAG_PROTO_QCA: + tagger_data = ds->tagger_data; + + tagger_data->rw_reg_ack_handler = qca8k_rw_reg_ack_handler; + tagger_data->mib_autocast_handler = qca8k_mib_autocast_handler; + + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + static const struct dsa_switch_ops qca8k_switch_ops = { .get_tag_protocol = qca8k_get_tag_protocol, .setup = qca8k_setup, @@ -2410,7 +3017,7 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .port_vlan_filtering = qca8k_port_vlan_filtering, .port_vlan_add = qca8k_port_vlan_add, .port_vlan_del = qca8k_port_vlan_del, - .phylink_validate = qca8k_phylink_validate, + .phylink_get_caps = qca8k_phylink_get_caps, .phylink_mac_link_state = qca8k_phylink_mac_link_state, .phylink_mac_config = qca8k_phylink_mac_config, .phylink_mac_link_down = qca8k_phylink_mac_link_down, @@ -2418,6 +3025,8 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .get_phy_flags = qca8k_get_phy_flags, .port_lag_join = qca8k_port_lag_join, .port_lag_leave = qca8k_port_lag_leave, + .master_state_change = qca8k_master_change, + .connect_tag_protocol = qca8k_connect_tag_protocol, }; static int qca8k_read_switch_id(struct qca8k_priv *priv) @@ -2488,6 +3097,10 @@ qca8k_sw_probe(struct mdio_device *mdiodev) return PTR_ERR(priv->regmap); } + priv->mdio_cache.page = 0xffff; + priv->mdio_cache.lo = 0xffff; + priv->mdio_cache.hi = 0xffff; + /* Check the detected switch id */ ret = qca8k_read_switch_id(priv); if (ret) @@ -2497,6 +3110,12 @@ qca8k_sw_probe(struct mdio_device *mdiodev) if (!priv->ds) return -ENOMEM; + mutex_init(&priv->mgmt_eth_data.mutex); + init_completion(&priv->mgmt_eth_data.rw_done); + + mutex_init(&priv->mib_eth_data.mutex); + init_completion(&priv->mib_eth_data.rw_done); + priv->ds->dev = &mdiodev->dev; priv->ds->num_ports = QCA8K_NUM_PORTS; priv->ds->priv = priv; diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index ab4a417b25a9..c3d3c2269b1d 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -11,6 +11,11 @@ #include <linux/delay.h> #include <linux/regmap.h> #include <linux/gpio.h> +#include <linux/dsa/tag_qca.h> + +#define QCA8K_ETHERNET_MDIO_PRIORITY 7 +#define QCA8K_ETHERNET_PHY_PRIORITY 6 +#define QCA8K_ETHERNET_TIMEOUT 100 #define QCA8K_NUM_PORTS 7 #define QCA8K_NUM_CPU_PORTS 2 @@ -63,7 +68,7 @@ #define QCA8K_REG_MODULE_EN 0x030 #define QCA8K_MODULE_EN_MIB BIT(0) #define QCA8K_REG_MIB 0x034 -#define QCA8K_MIB_FLUSH BIT(24) +#define QCA8K_MIB_FUNC GENMASK(26, 24) #define QCA8K_MIB_CPU_KEEP BIT(20) #define QCA8K_MIB_BUSY BIT(17) #define QCA8K_MDIO_MASTER_CTRL 0x3c @@ -313,6 +318,12 @@ enum qca8k_vlan_cmd { QCA8K_VLAN_READ = 6, }; +enum qca8k_mid_cmd { + QCA8K_MIB_FLUSH = 1, + QCA8K_MIB_FLUSH_PORT = 2, + QCA8K_MIB_CAST = 3, +}; + struct ar8xxx_port_status { int enabled; }; @@ -328,6 +339,22 @@ enum { QCA8K_CPU_PORT6, }; +struct qca8k_mgmt_eth_data { + struct completion rw_done; + struct mutex mutex; /* Enforce one mdio read/write at time */ + bool ack; + u32 seq; + u32 data[4]; +}; + +struct qca8k_mib_eth_data { + struct completion rw_done; + struct mutex mutex; /* Process one command at time */ + refcount_t port_parsed; /* Counter to track parsed port */ + u8 req_port; + u64 *data; /* pointer to ethtool data */ +}; + struct qca8k_ports_config { bool sgmii_rx_clk_falling_edge; bool sgmii_tx_clk_falling_edge; @@ -336,6 +363,19 @@ struct qca8k_ports_config { u8 rgmii_tx_delay[QCA8K_NUM_CPU_PORTS]; /* 0: CPU port0, 1: CPU port6 */ }; +struct qca8k_mdio_cache { +/* The 32bit switch registers are accessed indirectly. To achieve this we need + * to set the page of the register. Track the last page that was set to reduce + * mdio writes + */ + u16 page; +/* lo and hi can also be cached and from Documentation we can skip one + * extra mdio write if lo or hi is didn't change. + */ + u16 lo; + u16 hi; +}; + struct qca8k_priv { u8 switch_id; u8 switch_revision; @@ -353,6 +393,10 @@ struct qca8k_priv { struct dsa_switch_ops ops; struct gpio_desc *reset_gpio; unsigned int port_mtu[QCA8K_NUM_PORTS]; + struct net_device *mgmt_master; /* Track if mdio/mib Ethernet is available */ + struct qca8k_mgmt_eth_data mgmt_eth_data; + struct qca8k_mib_eth_data mib_eth_data; + struct qca8k_mdio_cache mdio_cache; }; struct qca8k_mib_desc { diff --git a/drivers/net/dsa/realtek-smi-core.c b/drivers/net/dsa/realtek-smi-core.c deleted file mode 100644 index aae46ada8d83..000000000000 --- a/drivers/net/dsa/realtek-smi-core.c +++ /dev/null @@ -1,523 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* Realtek Simple Management Interface (SMI) driver - * It can be discussed how "simple" this interface is. - * - * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels - * but the protocol is not MDIO at all. Instead it is a Realtek - * pecularity that need to bit-bang the lines in a special way to - * communicate with the switch. - * - * ASICs we intend to support with this driver: - * - * RTL8366 - The original version, apparently - * RTL8369 - Similar enough to have the same datsheet as RTL8366 - * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite - * different register layout from the other two - * RTL8366S - Is this "RTL8366 super"? - * RTL8367 - Has an OpenWRT driver as well - * RTL8368S - Seems to be an alternative name for RTL8366RB - * RTL8370 - Also uses SMI - * - * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> - * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com> - * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv> - * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com> - * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org> - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/device.h> -#include <linux/spinlock.h> -#include <linux/skbuff.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/of_mdio.h> -#include <linux/delay.h> -#include <linux/gpio/consumer.h> -#include <linux/platform_device.h> -#include <linux/regmap.h> -#include <linux/bitops.h> -#include <linux/if_bridge.h> - -#include "realtek-smi-core.h" - -#define REALTEK_SMI_ACK_RETRY_COUNT 5 -#define REALTEK_SMI_HW_STOP_DELAY 25 /* msecs */ -#define REALTEK_SMI_HW_START_DELAY 100 /* msecs */ - -static inline void realtek_smi_clk_delay(struct realtek_smi *smi) -{ - ndelay(smi->clk_delay); -} - -static void realtek_smi_start(struct realtek_smi *smi) -{ - /* Set GPIO pins to output mode, with initial state: - * SCK = 0, SDA = 1 - */ - gpiod_direction_output(smi->mdc, 0); - gpiod_direction_output(smi->mdio, 1); - realtek_smi_clk_delay(smi); - - /* CLK 1: 0 -> 1, 1 -> 0 */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - - /* CLK 2: */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 1); -} - -static void realtek_smi_stop(struct realtek_smi *smi) -{ - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 0); - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 1); - - /* Add a click */ - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 1); - - /* Set GPIO pins to input mode */ - gpiod_direction_input(smi->mdio); - gpiod_direction_input(smi->mdc); -} - -static void realtek_smi_write_bits(struct realtek_smi *smi, u32 data, u32 len) -{ - for (; len > 0; len--) { - realtek_smi_clk_delay(smi); - - /* Prepare data */ - gpiod_set_value(smi->mdio, !!(data & (1 << (len - 1)))); - realtek_smi_clk_delay(smi); - - /* Clocking */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - } -} - -static void realtek_smi_read_bits(struct realtek_smi *smi, u32 len, u32 *data) -{ - gpiod_direction_input(smi->mdio); - - for (*data = 0; len > 0; len--) { - u32 u; - - realtek_smi_clk_delay(smi); - - /* Clocking */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - u = !!gpiod_get_value(smi->mdio); - gpiod_set_value(smi->mdc, 0); - - *data |= (u << (len - 1)); - } - - gpiod_direction_output(smi->mdio, 0); -} - -static int realtek_smi_wait_for_ack(struct realtek_smi *smi) -{ - int retry_cnt; - - retry_cnt = 0; - do { - u32 ack; - - realtek_smi_read_bits(smi, 1, &ack); - if (ack == 0) - break; - - if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) { - dev_err(smi->dev, "ACK timeout\n"); - return -ETIMEDOUT; - } - } while (1); - - return 0; -} - -static int realtek_smi_write_byte(struct realtek_smi *smi, u8 data) -{ - realtek_smi_write_bits(smi, data, 8); - return realtek_smi_wait_for_ack(smi); -} - -static int realtek_smi_write_byte_noack(struct realtek_smi *smi, u8 data) -{ - realtek_smi_write_bits(smi, data, 8); - return 0; -} - -static int realtek_smi_read_byte0(struct realtek_smi *smi, u8 *data) -{ - u32 t; - - /* Read data */ - realtek_smi_read_bits(smi, 8, &t); - *data = (t & 0xff); - - /* Send an ACK */ - realtek_smi_write_bits(smi, 0x00, 1); - - return 0; -} - -static int realtek_smi_read_byte1(struct realtek_smi *smi, u8 *data) -{ - u32 t; - - /* Read data */ - realtek_smi_read_bits(smi, 8, &t); - *data = (t & 0xff); - - /* Send an ACK */ - realtek_smi_write_bits(smi, 0x01, 1); - - return 0; -} - -static int realtek_smi_read_reg(struct realtek_smi *smi, u32 addr, u32 *data) -{ - unsigned long flags; - u8 lo = 0; - u8 hi = 0; - int ret; - - spin_lock_irqsave(&smi->lock, flags); - - realtek_smi_start(smi); - - /* Send READ command */ - ret = realtek_smi_write_byte(smi, smi->cmd_read); - if (ret) - goto out; - - /* Set ADDR[7:0] */ - ret = realtek_smi_write_byte(smi, addr & 0xff); - if (ret) - goto out; - - /* Set ADDR[15:8] */ - ret = realtek_smi_write_byte(smi, addr >> 8); - if (ret) - goto out; - - /* Read DATA[7:0] */ - realtek_smi_read_byte0(smi, &lo); - /* Read DATA[15:8] */ - realtek_smi_read_byte1(smi, &hi); - - *data = ((u32)lo) | (((u32)hi) << 8); - - ret = 0; - - out: - realtek_smi_stop(smi); - spin_unlock_irqrestore(&smi->lock, flags); - - return ret; -} - -static int realtek_smi_write_reg(struct realtek_smi *smi, - u32 addr, u32 data, bool ack) -{ - unsigned long flags; - int ret; - - spin_lock_irqsave(&smi->lock, flags); - - realtek_smi_start(smi); - - /* Send WRITE command */ - ret = realtek_smi_write_byte(smi, smi->cmd_write); - if (ret) - goto out; - - /* Set ADDR[7:0] */ - ret = realtek_smi_write_byte(smi, addr & 0xff); - if (ret) - goto out; - - /* Set ADDR[15:8] */ - ret = realtek_smi_write_byte(smi, addr >> 8); - if (ret) - goto out; - - /* Write DATA[7:0] */ - ret = realtek_smi_write_byte(smi, data & 0xff); - if (ret) - goto out; - - /* Write DATA[15:8] */ - if (ack) - ret = realtek_smi_write_byte(smi, data >> 8); - else - ret = realtek_smi_write_byte_noack(smi, data >> 8); - if (ret) - goto out; - - ret = 0; - - out: - realtek_smi_stop(smi); - spin_unlock_irqrestore(&smi->lock, flags); - - return ret; -} - -/* There is one single case when we need to use this accessor and that - * is when issueing soft reset. Since the device reset as soon as we write - * that bit, no ACK will come back for natural reasons. - */ -int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr, - u32 data) -{ - return realtek_smi_write_reg(smi, addr, data, false); -} -EXPORT_SYMBOL_GPL(realtek_smi_write_reg_noack); - -/* Regmap accessors */ - -static int realtek_smi_write(void *ctx, u32 reg, u32 val) -{ - struct realtek_smi *smi = ctx; - - return realtek_smi_write_reg(smi, reg, val, true); -} - -static int realtek_smi_read(void *ctx, u32 reg, u32 *val) -{ - struct realtek_smi *smi = ctx; - - return realtek_smi_read_reg(smi, reg, val); -} - -static const struct regmap_config realtek_smi_mdio_regmap_config = { - .reg_bits = 10, /* A4..A0 R4..R0 */ - .val_bits = 16, - .reg_stride = 1, - /* PHY regs are at 0x8000 */ - .max_register = 0xffff, - .reg_format_endian = REGMAP_ENDIAN_BIG, - .reg_read = realtek_smi_read, - .reg_write = realtek_smi_write, - .cache_type = REGCACHE_NONE, -}; - -static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum) -{ - struct realtek_smi *smi = bus->priv; - - return smi->ops->phy_read(smi, addr, regnum); -} - -static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum, - u16 val) -{ - struct realtek_smi *smi = bus->priv; - - return smi->ops->phy_write(smi, addr, regnum, val); -} - -int realtek_smi_setup_mdio(struct realtek_smi *smi) -{ - struct device_node *mdio_np; - int ret; - - mdio_np = of_get_compatible_child(smi->dev->of_node, "realtek,smi-mdio"); - if (!mdio_np) { - dev_err(smi->dev, "no MDIO bus node\n"); - return -ENODEV; - } - - smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev); - if (!smi->slave_mii_bus) { - ret = -ENOMEM; - goto err_put_node; - } - smi->slave_mii_bus->priv = smi; - smi->slave_mii_bus->name = "SMI slave MII"; - smi->slave_mii_bus->read = realtek_smi_mdio_read; - smi->slave_mii_bus->write = realtek_smi_mdio_write; - snprintf(smi->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d", - smi->ds->index); - smi->slave_mii_bus->dev.of_node = mdio_np; - smi->slave_mii_bus->parent = smi->dev; - smi->ds->slave_mii_bus = smi->slave_mii_bus; - - ret = devm_of_mdiobus_register(smi->dev, smi->slave_mii_bus, mdio_np); - if (ret) { - dev_err(smi->dev, "unable to register MDIO bus %s\n", - smi->slave_mii_bus->id); - goto err_put_node; - } - - return 0; - -err_put_node: - of_node_put(mdio_np); - - return ret; -} - -static int realtek_smi_probe(struct platform_device *pdev) -{ - const struct realtek_smi_variant *var; - struct device *dev = &pdev->dev; - struct realtek_smi *smi; - struct device_node *np; - int ret; - - var = of_device_get_match_data(dev); - np = dev->of_node; - - smi = devm_kzalloc(dev, sizeof(*smi) + var->chip_data_sz, GFP_KERNEL); - if (!smi) - return -ENOMEM; - smi->chip_data = (void *)smi + sizeof(*smi); - smi->map = devm_regmap_init(dev, NULL, smi, - &realtek_smi_mdio_regmap_config); - if (IS_ERR(smi->map)) { - ret = PTR_ERR(smi->map); - dev_err(dev, "regmap init failed: %d\n", ret); - return ret; - } - - /* Link forward and backward */ - smi->dev = dev; - smi->clk_delay = var->clk_delay; - smi->cmd_read = var->cmd_read; - smi->cmd_write = var->cmd_write; - smi->ops = var->ops; - - dev_set_drvdata(dev, smi); - spin_lock_init(&smi->lock); - - /* TODO: if power is software controlled, set up any regulators here */ - - /* Assert then deassert RESET */ - smi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(smi->reset)) { - dev_err(dev, "failed to get RESET GPIO\n"); - return PTR_ERR(smi->reset); - } - msleep(REALTEK_SMI_HW_STOP_DELAY); - gpiod_set_value(smi->reset, 0); - msleep(REALTEK_SMI_HW_START_DELAY); - dev_info(dev, "deasserted RESET\n"); - - /* Fetch MDIO pins */ - smi->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW); - if (IS_ERR(smi->mdc)) - return PTR_ERR(smi->mdc); - smi->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW); - if (IS_ERR(smi->mdio)) - return PTR_ERR(smi->mdio); - - smi->leds_disabled = of_property_read_bool(np, "realtek,disable-leds"); - - ret = smi->ops->detect(smi); - if (ret) { - dev_err(dev, "unable to detect switch\n"); - return ret; - } - - smi->ds = devm_kzalloc(dev, sizeof(*smi->ds), GFP_KERNEL); - if (!smi->ds) - return -ENOMEM; - - smi->ds->dev = dev; - smi->ds->num_ports = smi->num_ports; - smi->ds->priv = smi; - - smi->ds->ops = var->ds_ops; - ret = dsa_register_switch(smi->ds); - if (ret) { - dev_err_probe(dev, ret, "unable to register switch\n"); - return ret; - } - return 0; -} - -static int realtek_smi_remove(struct platform_device *pdev) -{ - struct realtek_smi *smi = platform_get_drvdata(pdev); - - if (!smi) - return 0; - - dsa_unregister_switch(smi->ds); - if (smi->slave_mii_bus) - of_node_put(smi->slave_mii_bus->dev.of_node); - gpiod_set_value(smi->reset, 1); - - platform_set_drvdata(pdev, NULL); - - return 0; -} - -static void realtek_smi_shutdown(struct platform_device *pdev) -{ - struct realtek_smi *smi = platform_get_drvdata(pdev); - - if (!smi) - return; - - dsa_switch_shutdown(smi->ds); - - platform_set_drvdata(pdev, NULL); -} - -static const struct of_device_id realtek_smi_of_match[] = { - { - .compatible = "realtek,rtl8366rb", - .data = &rtl8366rb_variant, - }, - { - /* FIXME: add support for RTL8366S and more */ - .compatible = "realtek,rtl8366s", - .data = NULL, - }, - { - .compatible = "realtek,rtl8365mb", - .data = &rtl8365mb_variant, - }, - { /* sentinel */ }, -}; -MODULE_DEVICE_TABLE(of, realtek_smi_of_match); - -static struct platform_driver realtek_smi_driver = { - .driver = { - .name = "realtek-smi", - .of_match_table = of_match_ptr(realtek_smi_of_match), - }, - .probe = realtek_smi_probe, - .remove = realtek_smi_remove, - .shutdown = realtek_smi_shutdown, -}; -module_platform_driver(realtek_smi_driver); - -MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig new file mode 100644 index 000000000000..b7427a8292b2 --- /dev/null +++ b/drivers/net/dsa/realtek/Kconfig @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0-only +menuconfig NET_DSA_REALTEK + tristate "Realtek Ethernet switch family support" + depends on NET_DSA + select FIXED_PHY + select IRQ_DOMAIN + select REALTEK_PHY + select REGMAP + help + Select to enable support for Realtek Ethernet switch chips. + +config NET_DSA_REALTEK_MDIO + tristate "Realtek MDIO connected switch driver" + depends on NET_DSA_REALTEK + help + Select to enable support for registering switches configured + through MDIO. + +config NET_DSA_REALTEK_SMI + tristate "Realtek SMI connected switch driver" + depends on NET_DSA_REALTEK + help + Select to enable support for registering switches connected + through SMI. + +config NET_DSA_REALTEK_RTL8365MB + tristate "Realtek RTL8365MB switch subdriver" + depends on NET_DSA_REALTEK + depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + select NET_DSA_TAG_RTL8_4 + help + Select to enable support for Realtek RTL8365MB-VC and RTL8367S. + +config NET_DSA_REALTEK_RTL8366RB + tristate "Realtek RTL8366RB switch subdriver" + depends on NET_DSA_REALTEK + depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + select NET_DSA_TAG_RTL4_A + help + Select to enable support for Realtek RTL8366RB diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile new file mode 100644 index 000000000000..0aab57252a7c --- /dev/null +++ b/drivers/net/dsa/realtek/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_NET_DSA_REALTEK_MDIO) += realtek-mdio.o +obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o +obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o +rtl8366-objs := rtl8366-core.o rtl8366rb.o +obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c new file mode 100644 index 000000000000..0308be95d00a --- /dev/null +++ b/drivers/net/dsa/realtek/realtek-mdio.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Realtek MDIO interface driver + * + * ASICs we intend to support with this driver: + * + * RTL8366 - The original version, apparently + * RTL8369 - Similar enough to have the same datsheet as RTL8366 + * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite + * different register layout from the other two + * RTL8366S - Is this "RTL8366 super"? + * RTL8367 - Has an OpenWRT driver as well + * RTL8368S - Seems to be an alternative name for RTL8366RB + * RTL8370 - Also uses SMI + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com> + * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv> + * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com> + * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org> + */ + +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regmap.h> + +#include "realtek.h" + +/* Read/write via mdiobus */ +#define REALTEK_MDIO_CTRL0_REG 31 +#define REALTEK_MDIO_START_REG 29 +#define REALTEK_MDIO_CTRL1_REG 21 +#define REALTEK_MDIO_ADDRESS_REG 23 +#define REALTEK_MDIO_DATA_WRITE_REG 24 +#define REALTEK_MDIO_DATA_READ_REG 25 + +#define REALTEK_MDIO_START_OP 0xFFFF +#define REALTEK_MDIO_ADDR_OP 0x000E +#define REALTEK_MDIO_READ_OP 0x0001 +#define REALTEK_MDIO_WRITE_OP 0x0003 + +static int realtek_mdio_write(void *ctx, u32 reg, u32 val) +{ + struct realtek_priv *priv = ctx; + struct mii_bus *bus = priv->bus; + int ret; + + mutex_lock(&bus->mdio_lock); + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL0_REG, REALTEK_MDIO_ADDR_OP); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_ADDRESS_REG, reg); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_DATA_WRITE_REG, val); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL1_REG, REALTEK_MDIO_WRITE_OP); + +out_unlock: + mutex_unlock(&bus->mdio_lock); + + return ret; +} + +static int realtek_mdio_read(void *ctx, u32 reg, u32 *val) +{ + struct realtek_priv *priv = ctx; + struct mii_bus *bus = priv->bus; + int ret; + + mutex_lock(&bus->mdio_lock); + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL0_REG, REALTEK_MDIO_ADDR_OP); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_ADDRESS_REG, reg); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL1_REG, REALTEK_MDIO_READ_OP); + if (ret) + goto out_unlock; + + ret = bus->read(bus, priv->mdio_addr, REALTEK_MDIO_DATA_READ_REG); + if (ret >= 0) { + *val = ret; + ret = 0; + } + +out_unlock: + mutex_unlock(&bus->mdio_lock); + + return ret; +} + +static const struct regmap_config realtek_mdio_regmap_config = { + .reg_bits = 10, /* A4..A0 R4..R0 */ + .val_bits = 16, + .reg_stride = 1, + /* PHY regs are at 0x8000 */ + .max_register = 0xffff, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .reg_read = realtek_mdio_read, + .reg_write = realtek_mdio_write, + .cache_type = REGCACHE_NONE, +}; + +static int realtek_mdio_probe(struct mdio_device *mdiodev) +{ + struct realtek_priv *priv; + struct device *dev = &mdiodev->dev; + const struct realtek_variant *var; + int ret; + struct device_node *np; + + var = of_device_get_match_data(dev); + if (!var) + return -EINVAL; + + priv = devm_kzalloc(&mdiodev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->map = devm_regmap_init(dev, NULL, priv, &realtek_mdio_regmap_config); + if (IS_ERR(priv->map)) { + ret = PTR_ERR(priv->map); + dev_err(dev, "regmap init failed: %d\n", ret); + return ret; + } + + priv->mdio_addr = mdiodev->addr; + priv->bus = mdiodev->bus; + priv->dev = &mdiodev->dev; + priv->chip_data = (void *)priv + sizeof(*priv); + + priv->clk_delay = var->clk_delay; + priv->cmd_read = var->cmd_read; + priv->cmd_write = var->cmd_write; + priv->ops = var->ops; + + priv->write_reg_noack = realtek_mdio_write; + + np = dev->of_node; + + dev_set_drvdata(dev, priv); + + /* TODO: if power is software controlled, set up any regulators here */ + priv->leds_disabled = of_property_read_bool(np, "realtek,disable-leds"); + + priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(priv->reset)) { + dev_err(dev, "failed to get RESET GPIO\n"); + return PTR_ERR(priv->reset); + } + + if (priv->reset) { + gpiod_set_value(priv->reset, 1); + dev_dbg(dev, "asserted RESET\n"); + msleep(REALTEK_HW_STOP_DELAY); + gpiod_set_value(priv->reset, 0); + msleep(REALTEK_HW_START_DELAY); + dev_dbg(dev, "deasserted RESET\n"); + } + + ret = priv->ops->detect(priv); + if (ret) { + dev_err(dev, "unable to detect switch\n"); + return ret; + } + + priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL); + if (!priv->ds) + return -ENOMEM; + + priv->ds->dev = dev; + priv->ds->num_ports = priv->num_ports; + priv->ds->priv = priv; + priv->ds->ops = var->ds_ops_mdio; + + ret = dsa_register_switch(priv->ds); + if (ret) { + dev_err(priv->dev, "unable to register switch ret = %d\n", ret); + return ret; + } + + return 0; +} + +static void realtek_mdio_remove(struct mdio_device *mdiodev) +{ + struct realtek_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_unregister_switch(priv->ds); + + /* leave the device reset asserted */ + if (priv->reset) + gpiod_set_value(priv->reset, 1); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void realtek_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct realtek_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static const struct of_device_id realtek_mdio_of_match[] = { +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB) + { .compatible = "realtek,rtl8366rb", .data = &rtl8366rb_variant, }, +#endif +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) + { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, + { .compatible = "realtek,rtl8367s", .data = &rtl8365mb_variant, }, +#endif + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, realtek_mdio_of_match); + +static struct mdio_driver realtek_mdio_driver = { + .mdiodrv.driver = { + .name = "realtek-mdio", + .of_match_table = of_match_ptr(realtek_mdio_of_match), + }, + .probe = realtek_mdio_probe, + .remove = realtek_mdio_remove, + .shutdown = realtek_mdio_shutdown, +}; + +mdio_module_driver(realtek_mdio_driver); + +MODULE_AUTHOR("Luiz Angelo Daros de Luca <luizluca@gmail.com>"); +MODULE_DESCRIPTION("Driver for Realtek ethernet switch connected via MDIO interface"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c new file mode 100644 index 000000000000..8806b74bd7a8 --- /dev/null +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -0,0 +1,539 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Realtek Simple Management Interface (SMI) driver + * It can be discussed how "simple" this interface is. + * + * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels + * but the protocol is not MDIO at all. Instead it is a Realtek + * pecularity that need to bit-bang the lines in a special way to + * communicate with the switch. + * + * ASICs we intend to support with this driver: + * + * RTL8366 - The original version, apparently + * RTL8369 - Similar enough to have the same datsheet as RTL8366 + * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite + * different register layout from the other two + * RTL8366S - Is this "RTL8366 super"? + * RTL8367 - Has an OpenWRT driver as well + * RTL8368S - Seems to be an alternative name for RTL8366RB + * RTL8370 - Also uses SMI + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com> + * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv> + * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com> + * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_mdio.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/bitops.h> +#include <linux/if_bridge.h> + +#include "realtek.h" + +#define REALTEK_SMI_ACK_RETRY_COUNT 5 + +static inline void realtek_smi_clk_delay(struct realtek_priv *priv) +{ + ndelay(priv->clk_delay); +} + +static void realtek_smi_start(struct realtek_priv *priv) +{ + /* Set GPIO pins to output mode, with initial state: + * SCK = 0, SDA = 1 + */ + gpiod_direction_output(priv->mdc, 0); + gpiod_direction_output(priv->mdio, 1); + realtek_smi_clk_delay(priv); + + /* CLK 1: 0 -> 1, 1 -> 0 */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + + /* CLK 2: */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 1); +} + +static void realtek_smi_stop(struct realtek_priv *priv) +{ + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 0); + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 1); + + /* Add a click */ + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 1); + + /* Set GPIO pins to input mode */ + gpiod_direction_input(priv->mdio); + gpiod_direction_input(priv->mdc); +} + +static void realtek_smi_write_bits(struct realtek_priv *priv, u32 data, u32 len) +{ + for (; len > 0; len--) { + realtek_smi_clk_delay(priv); + + /* Prepare data */ + gpiod_set_value(priv->mdio, !!(data & (1 << (len - 1)))); + realtek_smi_clk_delay(priv); + + /* Clocking */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + } +} + +static void realtek_smi_read_bits(struct realtek_priv *priv, u32 len, u32 *data) +{ + gpiod_direction_input(priv->mdio); + + for (*data = 0; len > 0; len--) { + u32 u; + + realtek_smi_clk_delay(priv); + + /* Clocking */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + u = !!gpiod_get_value(priv->mdio); + gpiod_set_value(priv->mdc, 0); + + *data |= (u << (len - 1)); + } + + gpiod_direction_output(priv->mdio, 0); +} + +static int realtek_smi_wait_for_ack(struct realtek_priv *priv) +{ + int retry_cnt; + + retry_cnt = 0; + do { + u32 ack; + + realtek_smi_read_bits(priv, 1, &ack); + if (ack == 0) + break; + + if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) { + dev_err(priv->dev, "ACK timeout\n"); + return -ETIMEDOUT; + } + } while (1); + + return 0; +} + +static int realtek_smi_write_byte(struct realtek_priv *priv, u8 data) +{ + realtek_smi_write_bits(priv, data, 8); + return realtek_smi_wait_for_ack(priv); +} + +static int realtek_smi_write_byte_noack(struct realtek_priv *priv, u8 data) +{ + realtek_smi_write_bits(priv, data, 8); + return 0; +} + +static int realtek_smi_read_byte0(struct realtek_priv *priv, u8 *data) +{ + u32 t; + + /* Read data */ + realtek_smi_read_bits(priv, 8, &t); + *data = (t & 0xff); + + /* Send an ACK */ + realtek_smi_write_bits(priv, 0x00, 1); + + return 0; +} + +static int realtek_smi_read_byte1(struct realtek_priv *priv, u8 *data) +{ + u32 t; + + /* Read data */ + realtek_smi_read_bits(priv, 8, &t); + *data = (t & 0xff); + + /* Send an ACK */ + realtek_smi_write_bits(priv, 0x01, 1); + + return 0; +} + +static int realtek_smi_read_reg(struct realtek_priv *priv, u32 addr, u32 *data) +{ + unsigned long flags; + u8 lo = 0; + u8 hi = 0; + int ret; + + spin_lock_irqsave(&priv->lock, flags); + + realtek_smi_start(priv); + + /* Send READ command */ + ret = realtek_smi_write_byte(priv, priv->cmd_read); + if (ret) + goto out; + + /* Set ADDR[7:0] */ + ret = realtek_smi_write_byte(priv, addr & 0xff); + if (ret) + goto out; + + /* Set ADDR[15:8] */ + ret = realtek_smi_write_byte(priv, addr >> 8); + if (ret) + goto out; + + /* Read DATA[7:0] */ + realtek_smi_read_byte0(priv, &lo); + /* Read DATA[15:8] */ + realtek_smi_read_byte1(priv, &hi); + + *data = ((u32)lo) | (((u32)hi) << 8); + + ret = 0; + + out: + realtek_smi_stop(priv); + spin_unlock_irqrestore(&priv->lock, flags); + + return ret; +} + +static int realtek_smi_write_reg(struct realtek_priv *priv, + u32 addr, u32 data, bool ack) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&priv->lock, flags); + + realtek_smi_start(priv); + + /* Send WRITE command */ + ret = realtek_smi_write_byte(priv, priv->cmd_write); + if (ret) + goto out; + + /* Set ADDR[7:0] */ + ret = realtek_smi_write_byte(priv, addr & 0xff); + if (ret) + goto out; + + /* Set ADDR[15:8] */ + ret = realtek_smi_write_byte(priv, addr >> 8); + if (ret) + goto out; + + /* Write DATA[7:0] */ + ret = realtek_smi_write_byte(priv, data & 0xff); + if (ret) + goto out; + + /* Write DATA[15:8] */ + if (ack) + ret = realtek_smi_write_byte(priv, data >> 8); + else + ret = realtek_smi_write_byte_noack(priv, data >> 8); + if (ret) + goto out; + + ret = 0; + + out: + realtek_smi_stop(priv); + spin_unlock_irqrestore(&priv->lock, flags); + + return ret; +} + +/* There is one single case when we need to use this accessor and that + * is when issueing soft reset. Since the device reset as soon as we write + * that bit, no ACK will come back for natural reasons. + */ +static int realtek_smi_write_reg_noack(void *ctx, u32 reg, u32 val) +{ + return realtek_smi_write_reg(ctx, reg, val, false); +} + +/* Regmap accessors */ + +static int realtek_smi_write(void *ctx, u32 reg, u32 val) +{ + struct realtek_priv *priv = ctx; + + return realtek_smi_write_reg(priv, reg, val, true); +} + +static int realtek_smi_read(void *ctx, u32 reg, u32 *val) +{ + struct realtek_priv *priv = ctx; + + return realtek_smi_read_reg(priv, reg, val); +} + +static const struct regmap_config realtek_smi_mdio_regmap_config = { + .reg_bits = 10, /* A4..A0 R4..R0 */ + .val_bits = 16, + .reg_stride = 1, + /* PHY regs are at 0x8000 */ + .max_register = 0xffff, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .reg_read = realtek_smi_read, + .reg_write = realtek_smi_write, + .cache_type = REGCACHE_NONE, +}; + +static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum) +{ + struct realtek_priv *priv = bus->priv; + + return priv->ops->phy_read(priv, addr, regnum); +} + +static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum, + u16 val) +{ + struct realtek_priv *priv = bus->priv; + + return priv->ops->phy_write(priv, addr, regnum, val); +} + +static int realtek_smi_setup_mdio(struct dsa_switch *ds) +{ + struct realtek_priv *priv = ds->priv; + struct device_node *mdio_np; + int ret; + + mdio_np = of_get_compatible_child(priv->dev->of_node, "realtek,smi-mdio"); + if (!mdio_np) { + dev_err(priv->dev, "no MDIO bus node\n"); + return -ENODEV; + } + + priv->slave_mii_bus = devm_mdiobus_alloc(priv->dev); + if (!priv->slave_mii_bus) { + ret = -ENOMEM; + goto err_put_node; + } + priv->slave_mii_bus->priv = priv; + priv->slave_mii_bus->name = "SMI slave MII"; + priv->slave_mii_bus->read = realtek_smi_mdio_read; + priv->slave_mii_bus->write = realtek_smi_mdio_write; + snprintf(priv->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d", + ds->index); + priv->slave_mii_bus->dev.of_node = mdio_np; + priv->slave_mii_bus->parent = priv->dev; + ds->slave_mii_bus = priv->slave_mii_bus; + + ret = devm_of_mdiobus_register(priv->dev, priv->slave_mii_bus, mdio_np); + if (ret) { + dev_err(priv->dev, "unable to register MDIO bus %s\n", + priv->slave_mii_bus->id); + goto err_put_node; + } + + return 0; + +err_put_node: + of_node_put(mdio_np); + + return ret; +} + +static int realtek_smi_probe(struct platform_device *pdev) +{ + const struct realtek_variant *var; + struct device *dev = &pdev->dev; + struct realtek_priv *priv; + struct device_node *np; + int ret; + + var = of_device_get_match_data(dev); + np = dev->of_node; + + priv = devm_kzalloc(dev, sizeof(*priv) + var->chip_data_sz, GFP_KERNEL); + if (!priv) + return -ENOMEM; + priv->chip_data = (void *)priv + sizeof(*priv); + priv->map = devm_regmap_init(dev, NULL, priv, + &realtek_smi_mdio_regmap_config); + if (IS_ERR(priv->map)) { + ret = PTR_ERR(priv->map); + dev_err(dev, "regmap init failed: %d\n", ret); + return ret; + } + + /* Link forward and backward */ + priv->dev = dev; + priv->clk_delay = var->clk_delay; + priv->cmd_read = var->cmd_read; + priv->cmd_write = var->cmd_write; + priv->ops = var->ops; + + priv->setup_interface = realtek_smi_setup_mdio; + priv->write_reg_noack = realtek_smi_write_reg_noack; + + dev_set_drvdata(dev, priv); + spin_lock_init(&priv->lock); + + /* TODO: if power is software controlled, set up any regulators here */ + + priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(priv->reset)) { + dev_err(dev, "failed to get RESET GPIO\n"); + return PTR_ERR(priv->reset); + } + if (priv->reset) { + gpiod_set_value(priv->reset, 1); + dev_dbg(dev, "asserted RESET\n"); + msleep(REALTEK_HW_STOP_DELAY); + gpiod_set_value(priv->reset, 0); + msleep(REALTEK_HW_START_DELAY); + dev_dbg(dev, "deasserted RESET\n"); + } + + /* Fetch MDIO pins */ + priv->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW); + if (IS_ERR(priv->mdc)) + return PTR_ERR(priv->mdc); + priv->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW); + if (IS_ERR(priv->mdio)) + return PTR_ERR(priv->mdio); + + priv->leds_disabled = of_property_read_bool(np, "realtek,disable-leds"); + + ret = priv->ops->detect(priv); + if (ret) { + dev_err(dev, "unable to detect switch\n"); + return ret; + } + + priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL); + if (!priv->ds) + return -ENOMEM; + + priv->ds->dev = dev; + priv->ds->num_ports = priv->num_ports; + priv->ds->priv = priv; + + priv->ds->ops = var->ds_ops_smi; + ret = dsa_register_switch(priv->ds); + if (ret) { + dev_err_probe(dev, ret, "unable to register switch\n"); + return ret; + } + return 0; +} + +static int realtek_smi_remove(struct platform_device *pdev) +{ + struct realtek_priv *priv = platform_get_drvdata(pdev); + + if (!priv) + return 0; + + dsa_unregister_switch(priv->ds); + if (priv->slave_mii_bus) + of_node_put(priv->slave_mii_bus->dev.of_node); + + /* leave the device reset asserted */ + if (priv->reset) + gpiod_set_value(priv->reset, 1); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static void realtek_smi_shutdown(struct platform_device *pdev) +{ + struct realtek_priv *priv = platform_get_drvdata(pdev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + platform_set_drvdata(pdev, NULL); +} + +static const struct of_device_id realtek_smi_of_match[] = { +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB) + { + .compatible = "realtek,rtl8366rb", + .data = &rtl8366rb_variant, + }, +#endif + { + /* FIXME: add support for RTL8366S and more */ + .compatible = "realtek,rtl8366s", + .data = NULL, + }, +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) + { + .compatible = "realtek,rtl8365mb", + .data = &rtl8365mb_variant, + }, + { + .compatible = "realtek,rtl8367s", + .data = &rtl8365mb_variant, + }, +#endif + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, realtek_smi_of_match); + +static struct platform_driver realtek_smi_driver = { + .driver = { + .name = "realtek-smi", + .of_match_table = of_match_ptr(realtek_smi_of_match), + }, + .probe = realtek_smi_probe, + .remove = realtek_smi_remove, + .shutdown = realtek_smi_shutdown, +}; +module_platform_driver(realtek_smi_driver); + +MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>"); +MODULE_DESCRIPTION("Driver for Realtek ethernet switch connected via SMI interface"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek/realtek.h index 5bfa53e2480a..e7d3e1bcf8b8 100644 --- a/drivers/net/dsa/realtek-smi-core.h +++ b/drivers/net/dsa/realtek/realtek.h @@ -5,15 +5,18 @@ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org> */ -#ifndef _REALTEK_SMI_H -#define _REALTEK_SMI_H +#ifndef _REALTEK_H +#define _REALTEK_H #include <linux/phy.h> #include <linux/platform_device.h> #include <linux/gpio/consumer.h> #include <net/dsa.h> -struct realtek_smi_ops; +#define REALTEK_HW_STOP_DELAY 25 /* msecs */ +#define REALTEK_HW_START_DELAY 100 /* msecs */ + +struct realtek_ops; struct dentry; struct inode; struct file; @@ -25,7 +28,7 @@ struct rtl8366_mib_counter { const char *name; }; -/** +/* * struct rtl8366_vlan_mc - Virtual LAN member configuration */ struct rtl8366_vlan_mc { @@ -43,13 +46,15 @@ struct rtl8366_vlan_4k { u8 fid; }; -struct realtek_smi { +struct realtek_priv { struct device *dev; struct gpio_desc *reset; struct gpio_desc *mdc; struct gpio_desc *mdio; struct regmap *map; struct mii_bus *slave_mii_bus; + struct mii_bus *bus; + int mdio_addr; unsigned int clk_delay; u8 cmd_read; @@ -65,7 +70,9 @@ struct realtek_smi { unsigned int num_mib_counters; struct rtl8366_mib_counter *mib_counters; - const struct realtek_smi_ops *ops; + const struct realtek_ops *ops; + int (*setup_interface)(struct dsa_switch *ds); + int (*write_reg_noack)(void *ctx, u32 addr, u32 data); int vlan_enabled; int vlan4k_enabled; @@ -74,61 +81,57 @@ struct realtek_smi { void *chip_data; /* Per-chip extra variant data */ }; -/** - * struct realtek_smi_ops - vtable for the per-SMI-chiptype operations +/* + * struct realtek_ops - vtable for the per-SMI-chiptype operations * @detect: detects the chiptype */ -struct realtek_smi_ops { - int (*detect)(struct realtek_smi *smi); - int (*reset_chip)(struct realtek_smi *smi); - int (*setup)(struct realtek_smi *smi); - void (*cleanup)(struct realtek_smi *smi); - int (*get_mib_counter)(struct realtek_smi *smi, +struct realtek_ops { + int (*detect)(struct realtek_priv *priv); + int (*reset_chip)(struct realtek_priv *priv); + int (*setup)(struct realtek_priv *priv); + void (*cleanup)(struct realtek_priv *priv); + int (*get_mib_counter)(struct realtek_priv *priv, int port, struct rtl8366_mib_counter *mib, u64 *mibvalue); - int (*get_vlan_mc)(struct realtek_smi *smi, u32 index, + int (*get_vlan_mc)(struct realtek_priv *priv, u32 index, struct rtl8366_vlan_mc *vlanmc); - int (*set_vlan_mc)(struct realtek_smi *smi, u32 index, + int (*set_vlan_mc)(struct realtek_priv *priv, u32 index, const struct rtl8366_vlan_mc *vlanmc); - int (*get_vlan_4k)(struct realtek_smi *smi, u32 vid, + int (*get_vlan_4k)(struct realtek_priv *priv, u32 vid, struct rtl8366_vlan_4k *vlan4k); - int (*set_vlan_4k)(struct realtek_smi *smi, + int (*set_vlan_4k)(struct realtek_priv *priv, const struct rtl8366_vlan_4k *vlan4k); - int (*get_mc_index)(struct realtek_smi *smi, int port, int *val); - int (*set_mc_index)(struct realtek_smi *smi, int port, int index); - bool (*is_vlan_valid)(struct realtek_smi *smi, unsigned int vlan); - int (*enable_vlan)(struct realtek_smi *smi, bool enable); - int (*enable_vlan4k)(struct realtek_smi *smi, bool enable); - int (*enable_port)(struct realtek_smi *smi, int port, bool enable); - int (*phy_read)(struct realtek_smi *smi, int phy, int regnum); - int (*phy_write)(struct realtek_smi *smi, int phy, int regnum, + int (*get_mc_index)(struct realtek_priv *priv, int port, int *val); + int (*set_mc_index)(struct realtek_priv *priv, int port, int index); + bool (*is_vlan_valid)(struct realtek_priv *priv, unsigned int vlan); + int (*enable_vlan)(struct realtek_priv *priv, bool enable); + int (*enable_vlan4k)(struct realtek_priv *priv, bool enable); + int (*enable_port)(struct realtek_priv *priv, int port, bool enable); + int (*phy_read)(struct realtek_priv *priv, int phy, int regnum); + int (*phy_write)(struct realtek_priv *priv, int phy, int regnum, u16 val); }; -struct realtek_smi_variant { - const struct dsa_switch_ops *ds_ops; - const struct realtek_smi_ops *ops; +struct realtek_variant { + const struct dsa_switch_ops *ds_ops_smi; + const struct dsa_switch_ops *ds_ops_mdio; + const struct realtek_ops *ops; unsigned int clk_delay; u8 cmd_read; u8 cmd_write; size_t chip_data_sz; }; -/* SMI core calls */ -int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr, - u32 data); -int realtek_smi_setup_mdio(struct realtek_smi *smi); - /* RTL8366 library helpers */ -int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used); -int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, +int rtl8366_mc_is_used(struct realtek_priv *priv, int mc_index, int *used); +int rtl8366_set_vlan(struct realtek_priv *priv, int vid, u32 member, u32 untag, u32 fid); -int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, +int rtl8366_set_pvid(struct realtek_priv *priv, unsigned int port, unsigned int vid); -int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable); -int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable); -int rtl8366_reset_vlan(struct realtek_smi *smi); +int rtl8366_enable_vlan4k(struct realtek_priv *priv, bool enable); +int rtl8366_enable_vlan(struct realtek_priv *priv, bool enable); +int rtl8366_reset_vlan(struct realtek_priv *priv); int rtl8366_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); @@ -139,7 +142,7 @@ void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset, int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset); void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); -extern const struct realtek_smi_variant rtl8366rb_variant; -extern const struct realtek_smi_variant rtl8365mb_variant; +extern const struct realtek_variant rtl8366rb_variant; +extern const struct realtek_variant rtl8365mb_variant; -#endif /* _REALTEK_SMI_H */ +#endif /* _REALTEK_H */ diff --git a/drivers/net/dsa/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index 3b729544798b..2ed592147c20 100644 --- a/drivers/net/dsa/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -99,18 +99,28 @@ #include <linux/regmap.h> #include <linux/if_bridge.h> -#include "realtek-smi-core.h" +#include "realtek.h" /* Chip-specific data and limits */ -#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367 -#define RTL8365MB_CPU_PORT_NUM_8365MB_VC 6 -#define RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC 2112 +#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367 +#define RTL8365MB_CHIP_VER_8365MB_VC 0x0040 + +#define RTL8365MB_CHIP_ID_8367S 0x6367 +#define RTL8365MB_CHIP_VER_8367S 0x00A0 + +#define RTL8365MB_CHIP_ID_8367RB 0x6367 +#define RTL8365MB_CHIP_VER_8367RB 0x0020 /* Family-specific data and limits */ -#define RTL8365MB_PHYADDRMAX 7 -#define RTL8365MB_NUM_PHYREGS 32 -#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1) -#define RTL8365MB_MAX_NUM_PORTS (RTL8365MB_CPU_PORT_NUM_8365MB_VC + 1) +#define RTL8365MB_PHYADDRMAX 7 +#define RTL8365MB_NUM_PHYREGS 32 +#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1) +/* RTL8370MB and RTL8310SR, possibly suportable by this driver, have 10 ports */ +#define RTL8365MB_MAX_NUM_PORTS 10 +#define RTL8365MB_LEARN_LIMIT_MAX 2112 + +/* valid for all 6-port or less variants */ +static const int rtl8365mb_extint_port_map[] = { -1, -1, -1, -1, -1, -1, 1, 2, -1, -1}; /* Chip identification registers */ #define RTL8365MB_CHIP_ID_REG 0x1300 @@ -191,7 +201,7 @@ /* The PHY OCP addresses of PHY registers 0~31 start here */ #define RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE 0xA400 -/* EXT port interface mode values - used in DIGITAL_INTERFACE_SELECT */ +/* EXT interface port mode values - used in DIGITAL_INTERFACE_SELECT */ #define RTL8365MB_EXT_PORT_MODE_DISABLE 0 #define RTL8365MB_EXT_PORT_MODE_RGMII 1 #define RTL8365MB_EXT_PORT_MODE_MII_MAC 2 @@ -207,39 +217,56 @@ #define RTL8365MB_EXT_PORT_MODE_1000X 12 #define RTL8365MB_EXT_PORT_MODE_100FX 13 -/* EXT port interface mode configuration registers 0~1 */ -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305 -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3 -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extport) \ - (RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 + \ - ((_extport) >> 1) * (0x13C3 - 0x1305)) -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extport) \ - (0xF << (((_extport) % 2))) -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extport) \ - (((_extport) % 2) * 4) - -/* EXT port RGMII TX/RX delay configuration registers 1~2 */ -#define RTL8365MB_EXT_RGMXF_REG1 0x1307 -#define RTL8365MB_EXT_RGMXF_REG2 0x13C5 -#define RTL8365MB_EXT_RGMXF_REG(_extport) \ - (RTL8365MB_EXT_RGMXF_REG1 + \ - (((_extport) >> 1) * (0x13C5 - 0x1307))) +/* Realtek docs and driver uses logic number as EXT_PORT0=16, EXT_PORT1=17, + * EXT_PORT2=18, to interact with switch ports. That logic number is internally + * converted to either a physical port number (0..9) or an external interface id (0..2), + * depending on which function was called. The external interface id is calculated as + * (ext_id=logic_port-15), while the logical to physical map depends on the chip id/version. + * + * EXT_PORT0 mentioned in datasheets and rtl8367c driver is used in this driver + * as extid==1, EXT_PORT2, mentioned in Realtek rtl8367c driver for 10-port switches, + * would have an ext_id of 3 (out of range for most extint macros) and ext_id 0 does + * not seem to be used as well for this family. + */ + +/* EXT interface mode configuration registers 0~1 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305 /* EXT1 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3 /* EXT2 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extint) \ + ((_extint) == 1 ? RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 : \ + (_extint) == 2 ? RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 : \ + 0x0) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extint) \ + (0xF << (((_extint) % 2))) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extint) \ + (((_extint) % 2) * 4) + +/* EXT interface RGMII TX/RX delay configuration registers 0~2 */ +#define RTL8365MB_EXT_RGMXF_REG0 0x1306 /* EXT0 */ +#define RTL8365MB_EXT_RGMXF_REG1 0x1307 /* EXT1 */ +#define RTL8365MB_EXT_RGMXF_REG2 0x13C5 /* EXT2 */ +#define RTL8365MB_EXT_RGMXF_REG(_extint) \ + ((_extint) == 0 ? RTL8365MB_EXT_RGMXF_REG0 : \ + (_extint) == 1 ? RTL8365MB_EXT_RGMXF_REG1 : \ + (_extint) == 2 ? RTL8365MB_EXT_RGMXF_REG2 : \ + 0x0) #define RTL8365MB_EXT_RGMXF_RXDELAY_MASK 0x0007 #define RTL8365MB_EXT_RGMXF_TXDELAY_MASK 0x0008 -/* External port speed values - used in DIGITAL_INTERFACE_FORCE */ +/* External interface port speed values - used in DIGITAL_INTERFACE_FORCE */ #define RTL8365MB_PORT_SPEED_10M 0 #define RTL8365MB_PORT_SPEED_100M 1 #define RTL8365MB_PORT_SPEED_1000M 2 -/* EXT port force configuration registers 0~2 */ -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310 -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311 -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4 -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extport) \ - (RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 + \ - ((_extport) & 0x1) + \ - ((((_extport) >> 1) & 0x1) * (0x13C4 - 0x1310))) +/* EXT interface force configuration registers 0~2 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310 /* EXT0 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311 /* EXT1 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4 /* EXT2 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extint) \ + ((_extint) == 0 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 : \ + (_extint) == 1 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 : \ + (_extint) == 2 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 : \ + 0x0) #define RTL8365MB_DIGITAL_INTERFACE_FORCE_EN_MASK 0x1000 #define RTL8365MB_DIGITAL_INTERFACE_FORCE_NWAY_MASK 0x0080 #define RTL8365MB_DIGITAL_INTERFACE_FORCE_TXPAUSE_MASK 0x0040 @@ -516,7 +543,7 @@ struct rtl8365mb_cpu { /** * struct rtl8365mb_port - private per-port data - * @smi: pointer to parent realtek_smi data + * @priv: pointer to parent realtek_priv data * @index: DSA port index, same as dsa_port::index * @stats: link statistics populated by rtl8365mb_stats_poll, ready for atomic * access via rtl8365mb_get_stats64 @@ -524,7 +551,7 @@ struct rtl8365mb_cpu { * @mib_work: delayed work for polling MIB counters */ struct rtl8365mb_port { - struct realtek_smi *smi; + struct realtek_priv *priv; unsigned int index; struct rtnl_link_stats64 stats; spinlock_t stats_lock; @@ -533,13 +560,12 @@ struct rtl8365mb_port { /** * struct rtl8365mb - private chip-specific driver data - * @smi: pointer to parent realtek_smi data + * @priv: pointer to parent realtek_priv data * @irq: registered IRQ or zero * @chip_id: chip identifier * @chip_ver: chip silicon revision * @port_mask: mask of all ports * @learn_limit_max: maximum number of L2 addresses the chip can learn - * @cpu: CPU tagging and CPU port configuration for this chip * @mib_lock: prevent concurrent reads of MIB counters * @ports: per-port data * @jam_table: chip-specific initialization jam table @@ -548,29 +574,28 @@ struct rtl8365mb_port { * Private data for this driver. */ struct rtl8365mb { - struct realtek_smi *smi; + struct realtek_priv *priv; int irq; u32 chip_id; u32 chip_ver; u32 port_mask; u32 learn_limit_max; - struct rtl8365mb_cpu cpu; struct mutex mib_lock; struct rtl8365mb_port ports[RTL8365MB_MAX_NUM_PORTS]; const struct rtl8365mb_jam_tbl_entry *jam_table; size_t jam_size; }; -static int rtl8365mb_phy_poll_busy(struct realtek_smi *smi) +static int rtl8365mb_phy_poll_busy(struct realtek_priv *priv) { u32 val; - return regmap_read_poll_timeout(smi->map, + return regmap_read_poll_timeout(priv->map, RTL8365MB_INDIRECT_ACCESS_STATUS_REG, val, !val, 10, 100); } -static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, +static int rtl8365mb_phy_ocp_prepare(struct realtek_priv *priv, int phy, u32 ocp_addr) { u32 val; @@ -579,7 +604,7 @@ static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, /* Set OCP prefix */ val = FIELD_GET(RTL8365MB_PHY_OCP_ADDR_PREFIX_MASK, ocp_addr); ret = regmap_update_bits( - smi->map, RTL8365MB_GPHY_OCP_MSB_0_REG, + priv->map, RTL8365MB_GPHY_OCP_MSB_0_REG, RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, FIELD_PREP(RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, val)); if (ret) @@ -592,7 +617,7 @@ static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, ocp_addr >> 1); val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK, ocp_addr >> 6); - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG, + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG, val); if (ret) return ret; @@ -600,17 +625,17 @@ static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, return 0; } -static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, +static int rtl8365mb_phy_ocp_read(struct realtek_priv *priv, int phy, u32 ocp_addr, u16 *data) { u32 val; int ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; - ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + ret = rtl8365mb_phy_ocp_prepare(priv, phy, ocp_addr); if (ret) return ret; @@ -619,16 +644,16 @@ static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, RTL8365MB_INDIRECT_ACCESS_CTRL_RW_READ); - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); if (ret) return ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; /* Get PHY register data */ - ret = regmap_read(smi->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG, + ret = regmap_read(priv->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG, &val); if (ret) return ret; @@ -638,22 +663,22 @@ static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, return 0; } -static int rtl8365mb_phy_ocp_write(struct realtek_smi *smi, int phy, +static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy, u32 ocp_addr, u16 data) { u32 val; int ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; - ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + ret = rtl8365mb_phy_ocp_prepare(priv, phy, ocp_addr); if (ret) return ret; /* Set PHY register data */ - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG, + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG, data); if (ret) return ret; @@ -663,18 +688,18 @@ static int rtl8365mb_phy_ocp_write(struct realtek_smi *smi, int phy, RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, RTL8365MB_INDIRECT_ACCESS_CTRL_RW_WRITE); - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); if (ret) return ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; return 0; } -static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum) +static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum) { u32 ocp_addr; u16 val; @@ -688,21 +713,21 @@ static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum) ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; - ret = rtl8365mb_phy_ocp_read(smi, phy, ocp_addr, &val); + ret = rtl8365mb_phy_ocp_read(priv, phy, ocp_addr, &val); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to read PHY%d reg %02x @ %04x, ret %d\n", phy, regnum, ocp_addr, ret); return ret; } - dev_dbg(smi->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n", + dev_dbg(priv->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n", phy, regnum, ocp_addr, val); return val; } -static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum, +static int rtl8365mb_phy_write(struct realtek_priv *priv, int phy, int regnum, u16 val) { u32 ocp_addr; @@ -716,20 +741,31 @@ static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum, ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; - ret = rtl8365mb_phy_ocp_write(smi, phy, ocp_addr, val); + ret = rtl8365mb_phy_ocp_write(priv, phy, ocp_addr, val); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to write PHY%d reg %02x @ %04x, ret %d\n", phy, regnum, ocp_addr, ret); return ret; } - dev_dbg(smi->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n", + dev_dbg(priv->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n", phy, regnum, ocp_addr, val); return 0; } +static int rtl8365mb_dsa_phy_read(struct dsa_switch *ds, int phy, int regnum) +{ + return rtl8365mb_phy_read(ds->priv, phy, regnum); +} + +static int rtl8365mb_dsa_phy_write(struct dsa_switch *ds, int phy, int regnum, + u16 val) +{ + return rtl8365mb_phy_write(ds->priv, phy, regnum, val); +} + static enum dsa_tag_protocol rtl8365mb_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -737,25 +773,25 @@ rtl8365mb_get_tag_protocol(struct dsa_switch *ds, int port, return DSA_TAG_PROTO_RTL8_4; } -static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, +static int rtl8365mb_ext_config_rgmii(struct realtek_priv *priv, int port, phy_interface_t interface) { struct device_node *dn; struct dsa_port *dp; int tx_delay = 0; int rx_delay = 0; - int ext_port; + int ext_int; u32 val; int ret; - if (port == smi->cpu_port) { - ext_port = 1; - } else { - dev_err(smi->dev, "only one EXT port is currently supported\n"); + ext_int = rtl8365mb_extint_port_map[port]; + + if (ext_int <= 0) { + dev_err(priv->dev, "Port %d is not an external interface port\n", port); return -EINVAL; } - dp = dsa_to_port(smi->ds, port); + dp = dsa_to_port(priv->ds, port); dn = dp->dn; /* Set the RGMII TX/RX delay @@ -786,8 +822,8 @@ static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, if (val == 0 || val == 2) tx_delay = val / 2; else - dev_warn(smi->dev, - "EXT port TX delay must be 0 or 2 ns\n"); + dev_warn(priv->dev, + "EXT interface TX delay must be 0 or 2 ns\n"); } if (!of_property_read_u32(dn, "rx-internal-delay-ps", &val)) { @@ -796,12 +832,12 @@ static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, if (val <= 7) rx_delay = val; else - dev_warn(smi->dev, - "EXT port RX delay must be 0 to 2.1 ns\n"); + dev_warn(priv->dev, + "EXT interface RX delay must be 0 to 2.1 ns\n"); } ret = regmap_update_bits( - smi->map, RTL8365MB_EXT_RGMXF_REG(ext_port), + priv->map, RTL8365MB_EXT_RGMXF_REG(ext_int), RTL8365MB_EXT_RGMXF_TXDELAY_MASK | RTL8365MB_EXT_RGMXF_RXDELAY_MASK, FIELD_PREP(RTL8365MB_EXT_RGMXF_TXDELAY_MASK, tx_delay) | @@ -810,18 +846,18 @@ static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, return ret; ret = regmap_update_bits( - smi->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_port), - RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_port), + priv->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_int), + RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_int), RTL8365MB_EXT_PORT_MODE_RGMII << RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET( - ext_port)); + ext_int)); if (ret) return ret; return 0; } -static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, +static int rtl8365mb_ext_config_forcemode(struct realtek_priv *priv, int port, bool link, int speed, int duplex, bool tx_pause, bool rx_pause) { @@ -830,14 +866,14 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, u32 r_duplex; u32 r_speed; u32 r_link; - int ext_port; + int ext_int; int val; int ret; - if (port == smi->cpu_port) { - ext_port = 1; - } else { - dev_err(smi->dev, "only one EXT port is currently supported\n"); + ext_int = rtl8365mb_extint_port_map[port]; + + if (ext_int <= 0) { + dev_err(priv->dev, "Port %d is not an external interface port\n", port); return -EINVAL; } @@ -854,7 +890,7 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, } else if (speed == SPEED_10) { r_speed = RTL8365MB_PORT_SPEED_10M; } else { - dev_err(smi->dev, "unsupported port speed %s\n", + dev_err(priv->dev, "unsupported port speed %s\n", phy_speed_to_str(speed)); return -EINVAL; } @@ -864,7 +900,7 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, } else if (duplex == DUPLEX_HALF) { r_duplex = 0; } else { - dev_err(smi->dev, "unsupported duplex %s\n", + dev_err(priv->dev, "unsupported duplex %s\n", phy_duplex_to_str(duplex)); return -EINVAL; } @@ -886,8 +922,8 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_DUPLEX_MASK, r_duplex) | FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_SPEED_MASK, r_speed); - ret = regmap_write(smi->map, - RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_port), + ret = regmap_write(priv->map, + RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_int), val); if (ret) return ret; @@ -898,13 +934,17 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port, phy_interface_t interface) { - if (dsa_is_user_port(ds, port) && + int ext_int; + + ext_int = rtl8365mb_extint_port_map[port]; + + if (ext_int < 0 && (interface == PHY_INTERFACE_MODE_NA || interface == PHY_INTERFACE_MODE_INTERNAL || interface == PHY_INTERFACE_MODE_GMII)) /* Internal PHY */ return true; - else if (dsa_is_cpu_port(ds, port) && + else if ((ext_int >= 1) && phy_interface_mode_is_rgmii(interface)) /* Extension MAC */ return true; @@ -912,65 +952,43 @@ static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port, return false; } -static void rtl8365mb_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void rtl8365mb_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - struct realtek_smi *smi = ds->priv; - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0 }; - - /* include/linux/phylink.h says: - * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink - * expects the MAC driver to return all supported link modes. - */ - if (state->interface != PHY_INTERFACE_MODE_NA && - !rtl8365mb_phy_mode_supported(ds, port, state->interface)) { - dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", - phy_modes(state->interface), port); - linkmode_zero(supported); - return; - } - - phylink_set_port_modes(mask); - - phylink_set(mask, Autoneg); - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - phylink_set(mask, 1000baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + if (dsa_is_user_port(ds, port)) + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + else if (dsa_is_cpu_port(ds, port)) + phy_interface_set_rgmii(config->supported_interfaces); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000FD; } static void rtl8365mb_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; if (!rtl8365mb_phy_mode_supported(ds, port, state->interface)) { - dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", + dev_err(priv->dev, "phy mode %s is unsupported on port %d\n", phy_modes(state->interface), port); return; } if (mode != MLO_AN_PHY && mode != MLO_AN_FIXED) { - dev_err(smi->dev, + dev_err(priv->dev, "port %d supports only conventional PHY or fixed-link\n", port); return; } if (phy_interface_mode_is_rgmii(state->interface)) { - ret = rtl8365mb_ext_config_rgmii(smi, port, state->interface); + ret = rtl8365mb_ext_config_rgmii(priv, port, state->interface); if (ret) - dev_err(smi->dev, + dev_err(priv->dev, "failed to configure RGMII mode on port %d: %d\n", port, ret); return; @@ -985,20 +1003,20 @@ static void rtl8365mb_phylink_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_port *p; struct rtl8365mb *mb; int ret; - mb = smi->chip_data; + mb = priv->chip_data; p = &mb->ports[port]; cancel_delayed_work_sync(&p->mib_work); if (phy_interface_mode_is_rgmii(interface)) { - ret = rtl8365mb_ext_config_forcemode(smi, port, false, 0, 0, + ret = rtl8365mb_ext_config_forcemode(priv, port, false, 0, 0, false, false); if (ret) - dev_err(smi->dev, + dev_err(priv->dev, "failed to reset forced mode on port %d: %d\n", port, ret); @@ -1013,21 +1031,21 @@ static void rtl8365mb_phylink_mac_link_up(struct dsa_switch *ds, int port, int duplex, bool tx_pause, bool rx_pause) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_port *p; struct rtl8365mb *mb; int ret; - mb = smi->chip_data; + mb = priv->chip_data; p = &mb->ports[port]; schedule_delayed_work(&p->mib_work, 0); if (phy_interface_mode_is_rgmii(interface)) { - ret = rtl8365mb_ext_config_forcemode(smi, port, true, speed, + ret = rtl8365mb_ext_config_forcemode(priv, port, true, speed, duplex, tx_pause, rx_pause); if (ret) - dev_err(smi->dev, + dev_err(priv->dev, "failed to force mode on port %d: %d\n", port, ret); @@ -1038,7 +1056,7 @@ static void rtl8365mb_phylink_mac_link_up(struct dsa_switch *ds, int port, static void rtl8365mb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; enum rtl8365mb_stp_state val; int msti = 0; @@ -1057,36 +1075,36 @@ static void rtl8365mb_port_stp_state_set(struct dsa_switch *ds, int port, val = RTL8365MB_STP_STATE_FORWARDING; break; default: - dev_err(smi->dev, "invalid STP state: %u\n", state); + dev_err(priv->dev, "invalid STP state: %u\n", state); return; } - regmap_update_bits(smi->map, RTL8365MB_MSTI_CTRL_REG(msti, port), + regmap_update_bits(priv->map, RTL8365MB_MSTI_CTRL_REG(msti, port), RTL8365MB_MSTI_CTRL_PORT_STATE_MASK(port), val << RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET(port)); } -static int rtl8365mb_port_set_learning(struct realtek_smi *smi, int port, +static int rtl8365mb_port_set_learning(struct realtek_priv *priv, int port, bool enable) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; /* Enable/disable learning by limiting the number of L2 addresses the * port can learn. Realtek documentation states that a limit of zero * disables learning. When enabling learning, set it to the chip's * maximum. */ - return regmap_write(smi->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port), + return regmap_write(priv->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port), enable ? mb->learn_limit_max : 0); } -static int rtl8365mb_port_set_isolation(struct realtek_smi *smi, int port, +static int rtl8365mb_port_set_isolation(struct realtek_priv *priv, int port, u32 mask) { - return regmap_write(smi->map, RTL8365MB_PORT_ISOLATION_REG(port), mask); + return regmap_write(priv->map, RTL8365MB_PORT_ISOLATION_REG(port), mask); } -static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, +static int rtl8365mb_mib_counter_read(struct realtek_priv *priv, int port, u32 offset, u32 length, u64 *mibvalue) { u64 tmpvalue = 0; @@ -1098,13 +1116,13 @@ static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, * and then poll the control register before reading the value from some * counter registers. */ - ret = regmap_write(smi->map, RTL8365MB_MIB_ADDRESS_REG, + ret = regmap_write(priv->map, RTL8365MB_MIB_ADDRESS_REG, RTL8365MB_MIB_ADDRESS(port, offset)); if (ret) return ret; /* Poll for completion */ - ret = regmap_read_poll_timeout(smi->map, RTL8365MB_MIB_CTRL0_REG, val, + ret = regmap_read_poll_timeout(priv->map, RTL8365MB_MIB_CTRL0_REG, val, !(val & RTL8365MB_MIB_CTRL0_BUSY_MASK), 10, 100); if (ret) @@ -1126,7 +1144,7 @@ static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, /* Read the MIB counter 16 bits at a time */ for (i = 0; i < length; i++) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8365MB_MIB_COUNTER_REG(offset - i), &val); if (ret) return ret; @@ -1142,21 +1160,21 @@ static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, static void rtl8365mb_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb *mb; int ret; int i; - mb = smi->chip_data; + mb = priv->chip_data; mutex_lock(&mb->mib_lock); for (i = 0; i < RTL8365MB_MIB_END; i++) { struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; - ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + ret = rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &data[i]); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to read port %d counters: %d\n", port, ret); break; @@ -1190,15 +1208,15 @@ static int rtl8365mb_get_sset_count(struct dsa_switch *ds, int port, int sset) static void rtl8365mb_get_phy_stats(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_mib_counter *mib; struct rtl8365mb *mb; - mb = smi->chip_data; + mb = priv->chip_data; mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3StatsSymbolErrors]; mutex_lock(&mb->mib_lock); - rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &phy_stats->SymbolErrorDuringCarrier); mutex_unlock(&mb->mib_lock); } @@ -1226,12 +1244,12 @@ static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, [RTL8365MB_MIB_dot3StatsExcessiveCollisions] = 1, }; - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb *mb; int ret; int i; - mb = smi->chip_data; + mb = priv->chip_data; mutex_lock(&mb->mib_lock); for (i = 0; i < RTL8365MB_MIB_END; i++) { @@ -1241,7 +1259,7 @@ static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, if (!cnt[i]) continue; - ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + ret = rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &cnt[i]); if (ret) break; @@ -1291,20 +1309,20 @@ static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, static void rtl8365mb_get_ctrl_stats(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_mib_counter *mib; struct rtl8365mb *mb; - mb = smi->chip_data; + mb = priv->chip_data; mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3ControlInUnknownOpcodes]; mutex_lock(&mb->mib_lock); - rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &ctrl_stats->UnsupportedOpcodesReceived); mutex_unlock(&mb->mib_lock); } -static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) +static void rtl8365mb_stats_update(struct realtek_priv *priv, int port) { u64 cnt[RTL8365MB_MIB_END] = { [RTL8365MB_MIB_ifOutOctets] = 1, @@ -1323,7 +1341,7 @@ static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) [RTL8365MB_MIB_dot3StatsFCSErrors] = 1, [RTL8365MB_MIB_dot3StatsLateCollisions] = 1, }; - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; struct rtnl_link_stats64 *stats; int ret; int i; @@ -1338,7 +1356,7 @@ static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) if (!cnt[i]) continue; - ret = rtl8365mb_mib_counter_read(smi, port, c->offset, + ret = rtl8365mb_mib_counter_read(priv, port, c->offset, c->length, &cnt[i]); if (ret) break; @@ -1388,9 +1406,9 @@ static void rtl8365mb_stats_poll(struct work_struct *work) struct rtl8365mb_port *p = container_of(to_delayed_work(work), struct rtl8365mb_port, mib_work); - struct realtek_smi *smi = p->smi; + struct realtek_priv *priv = p->priv; - rtl8365mb_stats_update(smi, p->index); + rtl8365mb_stats_update(priv, p->index); schedule_delayed_work(&p->mib_work, RTL8365MB_STATS_INTERVAL_JIFFIES); } @@ -1398,11 +1416,11 @@ static void rtl8365mb_stats_poll(struct work_struct *work) static void rtl8365mb_get_stats64(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_port *p; struct rtl8365mb *mb; - mb = smi->chip_data; + mb = priv->chip_data; p = &mb->ports[port]; spin_lock(&p->stats_lock); @@ -1410,9 +1428,9 @@ static void rtl8365mb_get_stats64(struct dsa_switch *ds, int port, spin_unlock(&p->stats_lock); } -static void rtl8365mb_stats_setup(struct realtek_smi *smi) +static void rtl8365mb_stats_setup(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int i; /* Per-chip global mutex to protect MIB counter access, since doing @@ -1420,10 +1438,10 @@ static void rtl8365mb_stats_setup(struct realtek_smi *smi) */ mutex_init(&mb->mib_lock); - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { struct rtl8365mb_port *p = &mb->ports[i]; - if (dsa_is_unused_port(smi->ds, i)) + if (dsa_is_unused_port(priv->ds, i)) continue; /* Per-port spinlock to protect the stats64 data */ @@ -1436,45 +1454,45 @@ static void rtl8365mb_stats_setup(struct realtek_smi *smi) } } -static void rtl8365mb_stats_teardown(struct realtek_smi *smi) +static void rtl8365mb_stats_teardown(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int i; - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { struct rtl8365mb_port *p = &mb->ports[i]; - if (dsa_is_unused_port(smi->ds, i)) + if (dsa_is_unused_port(priv->ds, i)) continue; cancel_delayed_work_sync(&p->mib_work); } } -static int rtl8365mb_get_and_clear_status_reg(struct realtek_smi *smi, u32 reg, +static int rtl8365mb_get_and_clear_status_reg(struct realtek_priv *priv, u32 reg, u32 *val) { int ret; - ret = regmap_read(smi->map, reg, val); + ret = regmap_read(priv->map, reg, val); if (ret) return ret; - return regmap_write(smi->map, reg, *val); + return regmap_write(priv->map, reg, *val); } static irqreturn_t rtl8365mb_irq(int irq, void *data) { - struct realtek_smi *smi = data; + struct realtek_priv *priv = data; unsigned long line_changes = 0; struct rtl8365mb *mb; u32 stat; int line; int ret; - mb = smi->chip_data; + mb = priv->chip_data; - ret = rtl8365mb_get_and_clear_status_reg(smi, RTL8365MB_INTR_STATUS_REG, + ret = rtl8365mb_get_and_clear_status_reg(priv, RTL8365MB_INTR_STATUS_REG, &stat); if (ret) goto out_error; @@ -1485,14 +1503,14 @@ static irqreturn_t rtl8365mb_irq(int irq, void *data) u32 val; ret = rtl8365mb_get_and_clear_status_reg( - smi, RTL8365MB_PORT_LINKUP_IND_REG, &val); + priv, RTL8365MB_PORT_LINKUP_IND_REG, &val); if (ret) goto out_error; linkup_ind = FIELD_GET(RTL8365MB_PORT_LINKUP_IND_MASK, val); ret = rtl8365mb_get_and_clear_status_reg( - smi, RTL8365MB_PORT_LINKDOWN_IND_REG, &val); + priv, RTL8365MB_PORT_LINKDOWN_IND_REG, &val); if (ret) goto out_error; @@ -1504,8 +1522,8 @@ static irqreturn_t rtl8365mb_irq(int irq, void *data) if (!line_changes) goto out_none; - for_each_set_bit(line, &line_changes, smi->num_ports) { - int child_irq = irq_find_mapping(smi->irqdomain, line); + for_each_set_bit(line, &line_changes, priv->num_ports) { + int child_irq = irq_find_mapping(priv->irqdomain, line); handle_nested_irq(child_irq); } @@ -1513,7 +1531,7 @@ static irqreturn_t rtl8365mb_irq(int irq, void *data) return IRQ_HANDLED; out_error: - dev_err(smi->dev, "failed to read interrupt status: %d\n", ret); + dev_err(priv->dev, "failed to read interrupt status: %d\n", ret); out_none: return IRQ_NONE; @@ -1548,27 +1566,27 @@ static const struct irq_domain_ops rtl8365mb_irqdomain_ops = { .xlate = irq_domain_xlate_onecell, }; -static int rtl8365mb_set_irq_enable(struct realtek_smi *smi, bool enable) +static int rtl8365mb_set_irq_enable(struct realtek_priv *priv, bool enable) { - return regmap_update_bits(smi->map, RTL8365MB_INTR_CTRL_REG, + return regmap_update_bits(priv->map, RTL8365MB_INTR_CTRL_REG, RTL8365MB_INTR_LINK_CHANGE_MASK, FIELD_PREP(RTL8365MB_INTR_LINK_CHANGE_MASK, enable ? 1 : 0)); } -static int rtl8365mb_irq_enable(struct realtek_smi *smi) +static int rtl8365mb_irq_enable(struct realtek_priv *priv) { - return rtl8365mb_set_irq_enable(smi, true); + return rtl8365mb_set_irq_enable(priv, true); } -static int rtl8365mb_irq_disable(struct realtek_smi *smi) +static int rtl8365mb_irq_disable(struct realtek_priv *priv) { - return rtl8365mb_set_irq_enable(smi, false); + return rtl8365mb_set_irq_enable(priv, false); } -static int rtl8365mb_irq_setup(struct realtek_smi *smi) +static int rtl8365mb_irq_setup(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; struct device_node *intc; u32 irq_trig; int virq; @@ -1577,9 +1595,9 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) int ret; int i; - intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller"); + intc = of_get_child_by_name(priv->dev->of_node, "interrupt-controller"); if (!intc) { - dev_err(smi->dev, "missing child interrupt-controller node\n"); + dev_err(priv->dev, "missing child interrupt-controller node\n"); return -EINVAL; } @@ -1587,24 +1605,24 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) irq = of_irq_get(intc, 0); if (irq <= 0) { if (irq != -EPROBE_DEFER) - dev_err(smi->dev, "failed to get parent irq: %d\n", + dev_err(priv->dev, "failed to get parent irq: %d\n", irq); ret = irq ? irq : -EINVAL; goto out_put_node; } - smi->irqdomain = irq_domain_add_linear(intc, smi->num_ports, - &rtl8365mb_irqdomain_ops, smi); - if (!smi->irqdomain) { - dev_err(smi->dev, "failed to add irq domain\n"); + priv->irqdomain = irq_domain_add_linear(intc, priv->num_ports, + &rtl8365mb_irqdomain_ops, priv); + if (!priv->irqdomain) { + dev_err(priv->dev, "failed to add irq domain\n"); ret = -ENOMEM; goto out_put_node; } - for (i = 0; i < smi->num_ports; i++) { - virq = irq_create_mapping(smi->irqdomain, i); + for (i = 0; i < priv->num_ports; i++) { + virq = irq_create_mapping(priv->irqdomain, i); if (!virq) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to create irq domain mapping\n"); ret = -EINVAL; goto out_remove_irqdomain; @@ -1625,40 +1643,40 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) val = RTL8365MB_INTR_POLARITY_LOW; break; default: - dev_err(smi->dev, "unsupported irq trigger type %u\n", + dev_err(priv->dev, "unsupported irq trigger type %u\n", irq_trig); ret = -EINVAL; goto out_remove_irqdomain; } - ret = regmap_update_bits(smi->map, RTL8365MB_INTR_POLARITY_REG, + ret = regmap_update_bits(priv->map, RTL8365MB_INTR_POLARITY_REG, RTL8365MB_INTR_POLARITY_MASK, FIELD_PREP(RTL8365MB_INTR_POLARITY_MASK, val)); if (ret) goto out_remove_irqdomain; /* Disable the interrupt in case the chip has it enabled on reset */ - ret = rtl8365mb_irq_disable(smi); + ret = rtl8365mb_irq_disable(priv); if (ret) goto out_remove_irqdomain; /* Clear the interrupt status register */ - ret = regmap_write(smi->map, RTL8365MB_INTR_STATUS_REG, + ret = regmap_write(priv->map, RTL8365MB_INTR_STATUS_REG, RTL8365MB_INTR_ALL_MASK); if (ret) goto out_remove_irqdomain; ret = request_threaded_irq(irq, NULL, rtl8365mb_irq, IRQF_ONESHOT, - "rtl8365mb", smi); + "rtl8365mb", priv); if (ret) { - dev_err(smi->dev, "failed to request irq: %d\n", ret); + dev_err(priv->dev, "failed to request irq: %d\n", ret); goto out_remove_irqdomain; } /* Store the irq so that we know to free it during teardown */ mb->irq = irq; - ret = rtl8365mb_irq_enable(smi); + ret = rtl8365mb_irq_enable(priv); if (ret) goto out_free_irq; @@ -1667,17 +1685,17 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) return 0; out_free_irq: - free_irq(mb->irq, smi); + free_irq(mb->irq, priv); mb->irq = 0; out_remove_irqdomain: - for (i = 0; i < smi->num_ports; i++) { - virq = irq_find_mapping(smi->irqdomain, i); + for (i = 0; i < priv->num_ports; i++) { + virq = irq_find_mapping(priv->irqdomain, i); irq_dispose_mapping(virq); } - irq_domain_remove(smi->irqdomain); - smi->irqdomain = NULL; + irq_domain_remove(priv->irqdomain); + priv->irqdomain = NULL; out_put_node: of_node_put(intc); @@ -1685,36 +1703,34 @@ out_put_node: return ret; } -static void rtl8365mb_irq_teardown(struct realtek_smi *smi) +static void rtl8365mb_irq_teardown(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int virq; int i; if (mb->irq) { - free_irq(mb->irq, smi); + free_irq(mb->irq, priv); mb->irq = 0; } - if (smi->irqdomain) { - for (i = 0; i < smi->num_ports; i++) { - virq = irq_find_mapping(smi->irqdomain, i); + if (priv->irqdomain) { + for (i = 0; i < priv->num_ports; i++) { + virq = irq_find_mapping(priv->irqdomain, i); irq_dispose_mapping(virq); } - irq_domain_remove(smi->irqdomain); - smi->irqdomain = NULL; + irq_domain_remove(priv->irqdomain); + priv->irqdomain = NULL; } } -static int rtl8365mb_cpu_config(struct realtek_smi *smi) +static int rtl8365mb_cpu_config(struct realtek_priv *priv, const struct rtl8365mb_cpu *cpu) { - struct rtl8365mb *mb = smi->chip_data; - struct rtl8365mb_cpu *cpu = &mb->cpu; u32 val; int ret; - ret = regmap_update_bits(smi->map, RTL8365MB_CPU_PORT_MASK_REG, + ret = regmap_update_bits(priv->map, RTL8365MB_CPU_PORT_MASK_REG, RTL8365MB_CPU_PORT_MASK_MASK, FIELD_PREP(RTL8365MB_CPU_PORT_MASK_MASK, cpu->mask)); @@ -1726,26 +1742,26 @@ static int rtl8365mb_cpu_config(struct realtek_smi *smi) FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_POSITION_MASK, cpu->position) | FIELD_PREP(RTL8365MB_CPU_CTRL_RXBYTECOUNT_MASK, cpu->rx_length) | FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_FORMAT_MASK, cpu->format) | - FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port & 0x7) | FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_EXT_MASK, - cpu->trap_port >> 3); - ret = regmap_write(smi->map, RTL8365MB_CPU_CTRL_REG, val); + cpu->trap_port >> 3 & 0x1); + ret = regmap_write(priv->map, RTL8365MB_CPU_CTRL_REG, val); if (ret) return ret; return 0; } -static int rtl8365mb_switch_init(struct realtek_smi *smi) +static int rtl8365mb_switch_init(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int ret; int i; /* Do any chip-specific init jam before getting to the common stuff */ if (mb->jam_table) { for (i = 0; i < mb->jam_size; i++) { - ret = regmap_write(smi->map, mb->jam_table[i].reg, + ret = regmap_write(priv->map, mb->jam_table[i].reg, mb->jam_table[i].val); if (ret) return ret; @@ -1754,7 +1770,7 @@ static int rtl8365mb_switch_init(struct realtek_smi *smi) /* Common init jam */ for (i = 0; i < ARRAY_SIZE(rtl8365mb_init_jam_common); i++) { - ret = regmap_write(smi->map, rtl8365mb_init_jam_common[i].reg, + ret = regmap_write(priv->map, rtl8365mb_init_jam_common[i].reg, rtl8365mb_init_jam_common[i].val); if (ret) return ret; @@ -1763,75 +1779,86 @@ static int rtl8365mb_switch_init(struct realtek_smi *smi) return 0; } -static int rtl8365mb_reset_chip(struct realtek_smi *smi) +static int rtl8365mb_reset_chip(struct realtek_priv *priv) { u32 val; - realtek_smi_write_reg_noack(smi, RTL8365MB_CHIP_RESET_REG, - FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK, - 1)); + priv->write_reg_noack(priv, RTL8365MB_CHIP_RESET_REG, + FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK, 1)); /* Realtek documentation says the chip needs 1 second to reset. Sleep * for 100 ms before accessing any registers to prevent ACK timeouts. */ msleep(100); - return regmap_read_poll_timeout(smi->map, RTL8365MB_CHIP_RESET_REG, val, + return regmap_read_poll_timeout(priv->map, RTL8365MB_CHIP_RESET_REG, val, !(val & RTL8365MB_CHIP_RESET_HW_MASK), 20000, 1e6); } static int rtl8365mb_setup(struct dsa_switch *ds) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; + struct rtl8365mb_cpu cpu = {0}; + struct dsa_port *cpu_dp; struct rtl8365mb *mb; int ret; int i; - mb = smi->chip_data; + mb = priv->chip_data; - ret = rtl8365mb_reset_chip(smi); + ret = rtl8365mb_reset_chip(priv); if (ret) { - dev_err(smi->dev, "failed to reset chip: %d\n", ret); + dev_err(priv->dev, "failed to reset chip: %d\n", ret); goto out_error; } /* Configure switch to vendor-defined initial state */ - ret = rtl8365mb_switch_init(smi); + ret = rtl8365mb_switch_init(priv); if (ret) { - dev_err(smi->dev, "failed to initialize switch: %d\n", ret); + dev_err(priv->dev, "failed to initialize switch: %d\n", ret); goto out_error; } /* Set up cascading IRQs */ - ret = rtl8365mb_irq_setup(smi); + ret = rtl8365mb_irq_setup(priv); if (ret == -EPROBE_DEFER) return ret; else if (ret) - dev_info(smi->dev, "no interrupt support\n"); + dev_info(priv->dev, "no interrupt support\n"); /* Configure CPU tagging */ - ret = rtl8365mb_cpu_config(smi); + cpu.trap_port = RTL8365MB_MAX_NUM_PORTS; + dsa_switch_for_each_cpu_port(cpu_dp, priv->ds) { + cpu.mask |= BIT(cpu_dp->index); + + if (cpu.trap_port == RTL8365MB_MAX_NUM_PORTS) + cpu.trap_port = cpu_dp->index; + } + + cpu.enable = cpu.mask > 0; + cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL; + cpu.position = RTL8365MB_CPU_POS_AFTER_SA; + cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES; + cpu.format = RTL8365MB_CPU_FORMAT_8BYTES; + + ret = rtl8365mb_cpu_config(priv, &cpu); if (ret) goto out_teardown_irq; /* Configure ports */ - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { struct rtl8365mb_port *p = &mb->ports[i]; - if (dsa_is_unused_port(smi->ds, i)) + if (dsa_is_unused_port(priv->ds, i)) continue; - /* Set up per-port private data */ - p->smi = smi; - p->index = i; - /* Forward only to the CPU */ - ret = rtl8365mb_port_set_isolation(smi, i, BIT(smi->cpu_port)); + ret = rtl8365mb_port_set_isolation(priv, i, cpu.mask); if (ret) goto out_teardown_irq; /* Disable learning */ - ret = rtl8365mb_port_set_learning(smi, i, false); + ret = rtl8365mb_port_set_learning(priv, i, false); if (ret) goto out_teardown_irq; @@ -1839,29 +1866,35 @@ static int rtl8365mb_setup(struct dsa_switch *ds) * ports will still forward frames to the CPU despite being * administratively down by default. */ - rtl8365mb_port_stp_state_set(smi->ds, i, BR_STATE_DISABLED); + rtl8365mb_port_stp_state_set(priv->ds, i, BR_STATE_DISABLED); + + /* Set up per-port private data */ + p->priv = priv; + p->index = i; } /* Set maximum packet length to 1536 bytes */ - ret = regmap_update_bits(smi->map, RTL8365MB_CFG0_MAX_LEN_REG, + ret = regmap_update_bits(priv->map, RTL8365MB_CFG0_MAX_LEN_REG, RTL8365MB_CFG0_MAX_LEN_MASK, FIELD_PREP(RTL8365MB_CFG0_MAX_LEN_MASK, 1536)); if (ret) goto out_teardown_irq; - ret = realtek_smi_setup_mdio(smi); - if (ret) { - dev_err(smi->dev, "could not set up MDIO bus\n"); - goto out_teardown_irq; + if (priv->setup_interface) { + ret = priv->setup_interface(ds); + if (ret) { + dev_err(priv->dev, "could not set up MDIO bus\n"); + goto out_teardown_irq; + } } /* Start statistics counter polling */ - rtl8365mb_stats_setup(smi); + rtl8365mb_stats_setup(priv); return 0; out_teardown_irq: - rtl8365mb_irq_teardown(smi); + rtl8365mb_irq_teardown(priv); out_error: return ret; @@ -1869,10 +1902,10 @@ out_error: static void rtl8365mb_teardown(struct dsa_switch *ds) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; - rtl8365mb_stats_teardown(smi); - rtl8365mb_irq_teardown(smi); + rtl8365mb_stats_teardown(priv); + rtl8365mb_irq_teardown(priv); } static int rtl8365mb_get_chip_id_and_ver(struct regmap *map, u32 *id, u32 *ver) @@ -1902,48 +1935,57 @@ static int rtl8365mb_get_chip_id_and_ver(struct regmap *map, u32 *id, u32 *ver) return 0; } -static int rtl8365mb_detect(struct realtek_smi *smi) +static int rtl8365mb_detect(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; u32 chip_id; u32 chip_ver; int ret; - ret = rtl8365mb_get_chip_id_and_ver(smi->map, &chip_id, &chip_ver); + ret = rtl8365mb_get_chip_id_and_ver(priv->map, &chip_id, &chip_ver); if (ret) { - dev_err(smi->dev, "failed to read chip id and version: %d\n", + dev_err(priv->dev, "failed to read chip id and version: %d\n", ret); return ret; } switch (chip_id) { case RTL8365MB_CHIP_ID_8365MB_VC: - dev_info(smi->dev, - "found an RTL8365MB-VC switch (ver=0x%04x)\n", - chip_ver); + switch (chip_ver) { + case RTL8365MB_CHIP_VER_8365MB_VC: + dev_info(priv->dev, + "found an RTL8365MB-VC switch (ver=0x%04x)\n", + chip_ver); + break; + case RTL8365MB_CHIP_VER_8367RB: + dev_info(priv->dev, + "found an RTL8367RB-VB switch (ver=0x%04x)\n", + chip_ver); + break; + case RTL8365MB_CHIP_VER_8367S: + dev_info(priv->dev, + "found an RTL8367S switch (ver=0x%04x)\n", + chip_ver); + break; + default: + dev_err(priv->dev, "unrecognized switch version (ver=0x%04x)", + chip_ver); + return -ENODEV; + } - smi->cpu_port = RTL8365MB_CPU_PORT_NUM_8365MB_VC; - smi->num_ports = smi->cpu_port + 1; + priv->num_ports = RTL8365MB_MAX_NUM_PORTS; - mb->smi = smi; + mb->priv = priv; mb->chip_id = chip_id; mb->chip_ver = chip_ver; - mb->port_mask = BIT(smi->num_ports) - 1; - mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC; + mb->port_mask = GENMASK(priv->num_ports - 1, 0); + mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX; mb->jam_table = rtl8365mb_init_jam_8365mb_vc; mb->jam_size = ARRAY_SIZE(rtl8365mb_init_jam_8365mb_vc); - mb->cpu.enable = 1; - mb->cpu.mask = BIT(smi->cpu_port); - mb->cpu.trap_port = smi->cpu_port; - mb->cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL; - mb->cpu.position = RTL8365MB_CPU_POS_AFTER_SA; - mb->cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES; - mb->cpu.format = RTL8365MB_CPU_FORMAT_8BYTES; - break; default: - dev_err(smi->dev, + dev_err(priv->dev, "found an unknown Realtek switch (id=0x%04x, ver=0x%04x)\n", chip_id, chip_ver); return -ENODEV; @@ -1952,14 +1994,34 @@ static int rtl8365mb_detect(struct realtek_smi *smi) return 0; } -static const struct dsa_switch_ops rtl8365mb_switch_ops = { +static const struct dsa_switch_ops rtl8365mb_switch_ops_smi = { + .get_tag_protocol = rtl8365mb_get_tag_protocol, + .setup = rtl8365mb_setup, + .teardown = rtl8365mb_teardown, + .phylink_get_caps = rtl8365mb_phylink_get_caps, + .phylink_mac_config = rtl8365mb_phylink_mac_config, + .phylink_mac_link_down = rtl8365mb_phylink_mac_link_down, + .phylink_mac_link_up = rtl8365mb_phylink_mac_link_up, + .port_stp_state_set = rtl8365mb_port_stp_state_set, + .get_strings = rtl8365mb_get_strings, + .get_ethtool_stats = rtl8365mb_get_ethtool_stats, + .get_sset_count = rtl8365mb_get_sset_count, + .get_eth_phy_stats = rtl8365mb_get_phy_stats, + .get_eth_mac_stats = rtl8365mb_get_mac_stats, + .get_eth_ctrl_stats = rtl8365mb_get_ctrl_stats, + .get_stats64 = rtl8365mb_get_stats64, +}; + +static const struct dsa_switch_ops rtl8365mb_switch_ops_mdio = { .get_tag_protocol = rtl8365mb_get_tag_protocol, .setup = rtl8365mb_setup, .teardown = rtl8365mb_teardown, - .phylink_validate = rtl8365mb_phylink_validate, + .phylink_get_caps = rtl8365mb_phylink_get_caps, .phylink_mac_config = rtl8365mb_phylink_mac_config, .phylink_mac_link_down = rtl8365mb_phylink_mac_link_down, .phylink_mac_link_up = rtl8365mb_phylink_mac_link_up, + .phy_read = rtl8365mb_dsa_phy_read, + .phy_write = rtl8365mb_dsa_phy_write, .port_stp_state_set = rtl8365mb_port_stp_state_set, .get_strings = rtl8365mb_get_strings, .get_ethtool_stats = rtl8365mb_get_ethtool_stats, @@ -1970,18 +2032,23 @@ static const struct dsa_switch_ops rtl8365mb_switch_ops = { .get_stats64 = rtl8365mb_get_stats64, }; -static const struct realtek_smi_ops rtl8365mb_smi_ops = { +static const struct realtek_ops rtl8365mb_ops = { .detect = rtl8365mb_detect, .phy_read = rtl8365mb_phy_read, .phy_write = rtl8365mb_phy_write, }; -const struct realtek_smi_variant rtl8365mb_variant = { - .ds_ops = &rtl8365mb_switch_ops, - .ops = &rtl8365mb_smi_ops, +const struct realtek_variant rtl8365mb_variant = { + .ds_ops_smi = &rtl8365mb_switch_ops_smi, + .ds_ops_mdio = &rtl8365mb_switch_ops_mdio, + .ops = &rtl8365mb_ops, .clk_delay = 10, .cmd_read = 0xb9, .cmd_write = 0xb8, .chip_data_sz = sizeof(struct rtl8365mb), }; EXPORT_SYMBOL_GPL(rtl8365mb_variant); + +MODULE_AUTHOR("Alvin Å ipraga <alsi@bang-olufsen.dk>"); +MODULE_DESCRIPTION("Driver for RTL8365MB-VC ethernet switch"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/realtek/rtl8366-core.c index bdb8d8d34880..dc5f75be3017 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/realtek/rtl8366-core.c @@ -11,18 +11,18 @@ #include <linux/if_bridge.h> #include <net/dsa.h> -#include "realtek-smi-core.h" +#include "realtek.h" -int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used) +int rtl8366_mc_is_used(struct realtek_priv *priv, int mc_index, int *used) { int ret; int i; *used = 0; - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { int index = 0; - ret = smi->ops->get_mc_index(smi, i, &index); + ret = priv->ops->get_mc_index(priv, i, &index); if (ret) return ret; @@ -38,13 +38,13 @@ EXPORT_SYMBOL_GPL(rtl8366_mc_is_used); /** * rtl8366_obtain_mc() - retrieve or allocate a VLAN member configuration - * @smi: the Realtek SMI device instance + * @priv: the Realtek SMI device instance * @vid: the VLAN ID to look up or allocate * @vlanmc: the pointer will be assigned to a pointer to a valid member config * if successful * @return: index of a new member config or negative error number */ -static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, +static int rtl8366_obtain_mc(struct realtek_priv *priv, int vid, struct rtl8366_vlan_mc *vlanmc) { struct rtl8366_vlan_4k vlan4k; @@ -52,10 +52,10 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, int i; /* Try to find an existing member config entry for this VID */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + for (i = 0; i < priv->num_vlan_mc; i++) { + ret = priv->ops->get_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + dev_err(priv->dev, "error searching for VLAN MC %d for VID %d\n", i, vid); return ret; } @@ -65,19 +65,19 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, } /* We have no MC entry for this VID, try to find an empty one */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + for (i = 0; i < priv->num_vlan_mc; i++) { + ret = priv->ops->get_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + dev_err(priv->dev, "error searching for VLAN MC %d for VID %d\n", i, vid); return ret; } if (vlanmc->vid == 0 && vlanmc->member == 0) { /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k); if (ret) { - dev_err(smi->dev, "error looking for 4K VLAN MC %d for VID %d\n", + dev_err(priv->dev, "error looking for 4K VLAN MC %d for VID %d\n", i, vid); return ret; } @@ -86,30 +86,30 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, vlanmc->member = vlan4k.member; vlanmc->untag = vlan4k.untag; vlanmc->fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + ret = priv->ops->set_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + dev_err(priv->dev, "unable to set/update VLAN MC %d for VID %d\n", i, vid); return ret; } - dev_dbg(smi->dev, "created new MC at index %d for VID %d\n", + dev_dbg(priv->dev, "created new MC at index %d for VID %d\n", i, vid); return i; } } /* MC table is full, try to find an unused entry and replace it */ - for (i = 0; i < smi->num_vlan_mc; i++) { + for (i = 0; i < priv->num_vlan_mc; i++) { int used; - ret = rtl8366_mc_is_used(smi, i, &used); + ret = rtl8366_mc_is_used(priv, i, &used); if (ret) return ret; if (!used) { /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k); if (ret) return ret; @@ -117,23 +117,23 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, vlanmc->member = vlan4k.member; vlanmc->untag = vlan4k.untag; vlanmc->fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + ret = priv->ops->set_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + dev_err(priv->dev, "unable to set/update VLAN MC %d for VID %d\n", i, vid); return ret; } - dev_dbg(smi->dev, "recycled MC at index %i for VID %d\n", + dev_dbg(priv->dev, "recycled MC at index %i for VID %d\n", i, vid); return i; } } - dev_err(smi->dev, "all VLAN member configurations are in use\n"); + dev_err(priv->dev, "all VLAN member configurations are in use\n"); return -ENOSPC; } -int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, +int rtl8366_set_vlan(struct realtek_priv *priv, int vid, u32 member, u32 untag, u32 fid) { struct rtl8366_vlan_mc vlanmc; @@ -141,31 +141,31 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, int mc; int ret; - if (!smi->ops->is_vlan_valid(smi, vid)) + if (!priv->ops->is_vlan_valid(priv, vid)) return -EINVAL; - dev_dbg(smi->dev, + dev_dbg(priv->dev, "setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", vid, member, untag); /* Update the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k); if (ret) return ret; vlan4k.member |= member; vlan4k.untag |= untag; vlan4k.fid = fid; - ret = smi->ops->set_vlan_4k(smi, &vlan4k); + ret = priv->ops->set_vlan_4k(priv, &vlan4k); if (ret) return ret; - dev_dbg(smi->dev, + dev_dbg(priv->dev, "resulting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", vid, vlan4k.member, vlan4k.untag); /* Find or allocate a member config for this VID */ - ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + ret = rtl8366_obtain_mc(priv, vid, &vlanmc); if (ret < 0) return ret; mc = ret; @@ -176,12 +176,12 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, vlanmc.fid = fid; /* Commit updates to the MC entry */ - ret = smi->ops->set_vlan_mc(smi, mc, &vlanmc); + ret = priv->ops->set_vlan_mc(priv, mc, &vlanmc); if (ret) - dev_err(smi->dev, "failed to commit changes to VLAN MC index %d for VID %d\n", + dev_err(priv->dev, "failed to commit changes to VLAN MC index %d for VID %d\n", mc, vid); else - dev_dbg(smi->dev, + dev_dbg(priv->dev, "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", vid, vlanmc.member, vlanmc.untag); @@ -189,37 +189,37 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, } EXPORT_SYMBOL_GPL(rtl8366_set_vlan); -int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, +int rtl8366_set_pvid(struct realtek_priv *priv, unsigned int port, unsigned int vid) { struct rtl8366_vlan_mc vlanmc; int mc; int ret; - if (!smi->ops->is_vlan_valid(smi, vid)) + if (!priv->ops->is_vlan_valid(priv, vid)) return -EINVAL; /* Find or allocate a member config for this VID */ - ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + ret = rtl8366_obtain_mc(priv, vid, &vlanmc); if (ret < 0) return ret; mc = ret; - ret = smi->ops->set_mc_index(smi, port, mc); + ret = priv->ops->set_mc_index(priv, port, mc); if (ret) { - dev_err(smi->dev, "set PVID: failed to set MC index %d for port %d\n", + dev_err(priv->dev, "set PVID: failed to set MC index %d for port %d\n", mc, port); return ret; } - dev_dbg(smi->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n", + dev_dbg(priv->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n", port, vid, mc); return 0; } EXPORT_SYMBOL_GPL(rtl8366_set_pvid); -int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable) +int rtl8366_enable_vlan4k(struct realtek_priv *priv, bool enable) { int ret; @@ -229,52 +229,52 @@ int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable) */ if (enable) { /* Make sure VLAN is ON */ - ret = smi->ops->enable_vlan(smi, true); + ret = priv->ops->enable_vlan(priv, true); if (ret) return ret; - smi->vlan_enabled = true; + priv->vlan_enabled = true; } - ret = smi->ops->enable_vlan4k(smi, enable); + ret = priv->ops->enable_vlan4k(priv, enable); if (ret) return ret; - smi->vlan4k_enabled = enable; + priv->vlan4k_enabled = enable; return 0; } EXPORT_SYMBOL_GPL(rtl8366_enable_vlan4k); -int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable) +int rtl8366_enable_vlan(struct realtek_priv *priv, bool enable) { int ret; - ret = smi->ops->enable_vlan(smi, enable); + ret = priv->ops->enable_vlan(priv, enable); if (ret) return ret; - smi->vlan_enabled = enable; + priv->vlan_enabled = enable; /* If we turn VLAN off, make sure that we turn off * 4k VLAN as well, if that happened to be on. */ if (!enable) { - smi->vlan4k_enabled = false; - ret = smi->ops->enable_vlan4k(smi, false); + priv->vlan4k_enabled = false; + ret = priv->ops->enable_vlan4k(priv, false); } return ret; } EXPORT_SYMBOL_GPL(rtl8366_enable_vlan); -int rtl8366_reset_vlan(struct realtek_smi *smi) +int rtl8366_reset_vlan(struct realtek_priv *priv) { struct rtl8366_vlan_mc vlanmc; int ret; int i; - rtl8366_enable_vlan(smi, false); - rtl8366_enable_vlan4k(smi, false); + rtl8366_enable_vlan(priv, false); + rtl8366_enable_vlan4k(priv, false); /* Clear the 16 VLAN member configurations */ vlanmc.vid = 0; @@ -282,8 +282,8 @@ int rtl8366_reset_vlan(struct realtek_smi *smi) vlanmc.member = 0; vlanmc.untag = 0; vlanmc.fid = 0; - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + for (i = 0; i < priv->num_vlan_mc; i++) { + ret = priv->ops->set_vlan_mc(priv, i, &vlanmc); if (ret) return ret; } @@ -298,12 +298,12 @@ int rtl8366_vlan_add(struct dsa_switch *ds, int port, { bool untagged = !!(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED); bool pvid = !!(vlan->flags & BRIDGE_VLAN_INFO_PVID); - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; u32 member = 0; u32 untag = 0; int ret; - if (!smi->ops->is_vlan_valid(smi, vlan->vid)) { + if (!priv->ops->is_vlan_valid(priv, vlan->vid)) { NL_SET_ERR_MSG_MOD(extack, "VLAN ID not valid"); return -EINVAL; } @@ -312,13 +312,13 @@ int rtl8366_vlan_add(struct dsa_switch *ds, int port, * FIXME: what's with this 4k business? * Just rtl8366_enable_vlan() seems inconclusive. */ - ret = rtl8366_enable_vlan4k(smi, true); + ret = rtl8366_enable_vlan4k(priv, true); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Failed to enable VLAN 4K"); return ret; } - dev_dbg(smi->dev, "add VLAN %d on port %d, %s, %s\n", + dev_dbg(priv->dev, "add VLAN %d on port %d, %s, %s\n", vlan->vid, port, untagged ? "untagged" : "tagged", pvid ? "PVID" : "no PVID"); @@ -327,18 +327,18 @@ int rtl8366_vlan_add(struct dsa_switch *ds, int port, if (untagged) untag |= BIT(port); - ret = rtl8366_set_vlan(smi, vlan->vid, member, untag, 0); + ret = rtl8366_set_vlan(priv, vlan->vid, member, untag, 0); if (ret) { - dev_err(smi->dev, "failed to set up VLAN %04x", vlan->vid); + dev_err(priv->dev, "failed to set up VLAN %04x", vlan->vid); return ret; } if (!pvid) return 0; - ret = rtl8366_set_pvid(smi, port, vlan->vid); + ret = rtl8366_set_pvid(priv, port, vlan->vid); if (ret) { - dev_err(smi->dev, "failed to set PVID on port %d to VLAN %04x", + dev_err(priv->dev, "failed to set PVID on port %d to VLAN %04x", port, vlan->vid); return ret; } @@ -350,15 +350,15 @@ EXPORT_SYMBOL_GPL(rtl8366_vlan_add); int rtl8366_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret, i; - dev_dbg(smi->dev, "del VLAN %d on port %d\n", vlan->vid, port); + dev_dbg(priv->dev, "del VLAN %d on port %d\n", vlan->vid, port); - for (i = 0; i < smi->num_vlan_mc; i++) { + for (i = 0; i < priv->num_vlan_mc; i++) { struct rtl8366_vlan_mc vlanmc; - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); + ret = priv->ops->get_vlan_mc(priv, i, &vlanmc); if (ret) return ret; @@ -376,9 +376,9 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port, vlanmc.priority = 0; vlanmc.fid = 0; } - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + ret = priv->ops->set_vlan_mc(priv, i, &vlanmc); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to remove VLAN %04x\n", vlan->vid); return ret; @@ -394,15 +394,15 @@ EXPORT_SYMBOL_GPL(rtl8366_vlan_del); void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8366_mib_counter *mib; int i; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return; - for (i = 0; i < smi->num_mib_counters; i++) { - mib = &smi->mib_counters[i]; + for (i = 0; i < priv->num_mib_counters; i++) { + mib = &priv->mib_counters[i]; strncpy(data + i * ETH_GSTRING_LEN, mib->name, ETH_GSTRING_LEN); } @@ -411,35 +411,35 @@ EXPORT_SYMBOL_GPL(rtl8366_get_strings); int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; /* We only support SS_STATS */ if (sset != ETH_SS_STATS) return 0; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return -EINVAL; - return smi->num_mib_counters; + return priv->num_mib_counters; } EXPORT_SYMBOL_GPL(rtl8366_get_sset_count); void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int i; int ret; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return; - for (i = 0; i < smi->num_mib_counters; i++) { + for (i = 0; i < priv->num_mib_counters; i++) { struct rtl8366_mib_counter *mib; u64 mibvalue = 0; - mib = &smi->mib_counters[i]; - ret = smi->ops->get_mib_counter(smi, port, mib, &mibvalue); + mib = &priv->mib_counters[i]; + ret = priv->ops->get_mib_counter(priv, port, mib, &mibvalue); if (ret) { - dev_err(smi->dev, "error reading MIB counter %s\n", + dev_err(priv->dev, "error reading MIB counter %s\n", mib->name); } data[i] = mibvalue; diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c index ecc19bd5115f..fb6565e68401 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/realtek/rtl8366rb.c @@ -21,7 +21,7 @@ #include <linux/of_irq.h> #include <linux/regmap.h> -#include "realtek-smi-core.h" +#include "realtek.h" #define RTL8366RB_PORT_NUM_CPU 5 #define RTL8366RB_NUM_PORTS 6 @@ -396,7 +396,7 @@ static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = { { 0, 70, 2, "IfOutBroadcastPkts" }, }; -static int rtl8366rb_get_mib_counter(struct realtek_smi *smi, +static int rtl8366rb_get_mib_counter(struct realtek_priv *priv, int port, struct rtl8366_mib_counter *mib, u64 *mibvalue) @@ -412,12 +412,12 @@ static int rtl8366rb_get_mib_counter(struct realtek_smi *smi, /* Writing access counter address first * then ASIC will prepare 64bits counter wait for being retrived */ - ret = regmap_write(smi->map, addr, 0); /* Write whatever */ + ret = regmap_write(priv->map, addr, 0); /* Write whatever */ if (ret) return ret; /* Read MIB control register */ - ret = regmap_read(smi->map, RTL8366RB_MIB_CTRL_REG, &val); + ret = regmap_read(priv->map, RTL8366RB_MIB_CTRL_REG, &val); if (ret) return -EIO; @@ -430,7 +430,7 @@ static int rtl8366rb_get_mib_counter(struct realtek_smi *smi, /* Read each individual MIB 16 bits at the time */ *mibvalue = 0; for (i = mib->length; i > 0; i--) { - ret = regmap_read(smi->map, addr + (i - 1), &val); + ret = regmap_read(priv->map, addr + (i - 1), &val); if (ret) return ret; *mibvalue = (*mibvalue << 16) | (val & 0xFFFF); @@ -455,38 +455,38 @@ static u32 rtl8366rb_get_irqmask(struct irq_data *d) static void rtl8366rb_mask_irq(struct irq_data *d) { - struct realtek_smi *smi = irq_data_get_irq_chip_data(d); + struct realtek_priv *priv = irq_data_get_irq_chip_data(d); int ret; - ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_MASK_REG, rtl8366rb_get_irqmask(d), 0); if (ret) - dev_err(smi->dev, "could not mask IRQ\n"); + dev_err(priv->dev, "could not mask IRQ\n"); } static void rtl8366rb_unmask_irq(struct irq_data *d) { - struct realtek_smi *smi = irq_data_get_irq_chip_data(d); + struct realtek_priv *priv = irq_data_get_irq_chip_data(d); int ret; - ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_MASK_REG, rtl8366rb_get_irqmask(d), rtl8366rb_get_irqmask(d)); if (ret) - dev_err(smi->dev, "could not unmask IRQ\n"); + dev_err(priv->dev, "could not unmask IRQ\n"); } static irqreturn_t rtl8366rb_irq(int irq, void *data) { - struct realtek_smi *smi = data; + struct realtek_priv *priv = data; u32 stat; int ret; /* This clears the IRQ status register */ - ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG, + ret = regmap_read(priv->map, RTL8366RB_INTERRUPT_STATUS_REG, &stat); if (ret) { - dev_err(smi->dev, "can't read interrupt status\n"); + dev_err(priv->dev, "can't read interrupt status\n"); return IRQ_NONE; } stat &= RTL8366RB_INTERRUPT_VALID; @@ -502,7 +502,7 @@ static irqreturn_t rtl8366rb_irq(int irq, void *data) */ if (line < 12 && line > 5) line -= 5; - child_irq = irq_find_mapping(smi->irqdomain, line); + child_irq = irq_find_mapping(priv->irqdomain, line); handle_nested_irq(child_irq); } return IRQ_HANDLED; @@ -538,7 +538,7 @@ static const struct irq_domain_ops rtl8366rb_irqdomain_ops = { .xlate = irq_domain_xlate_onecell, }; -static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) +static int rtl8366rb_setup_cascaded_irq(struct realtek_priv *priv) { struct device_node *intc; unsigned long irq_trig; @@ -547,24 +547,24 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) u32 val; int i; - intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller"); + intc = of_get_child_by_name(priv->dev->of_node, "interrupt-controller"); if (!intc) { - dev_err(smi->dev, "missing child interrupt-controller node\n"); + dev_err(priv->dev, "missing child interrupt-controller node\n"); return -EINVAL; } /* RB8366RB IRQs cascade off this one */ irq = of_irq_get(intc, 0); if (irq <= 0) { - dev_err(smi->dev, "failed to get parent IRQ\n"); + dev_err(priv->dev, "failed to get parent IRQ\n"); ret = irq ? irq : -EINVAL; goto out_put_node; } /* This clears the IRQ status register */ - ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG, + ret = regmap_read(priv->map, RTL8366RB_INTERRUPT_STATUS_REG, &val); if (ret) { - dev_err(smi->dev, "can't read interrupt status\n"); + dev_err(priv->dev, "can't read interrupt status\n"); goto out_put_node; } @@ -573,48 +573,48 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) switch (irq_trig) { case IRQF_TRIGGER_RISING: case IRQF_TRIGGER_HIGH: - dev_info(smi->dev, "active high/rising IRQ\n"); + dev_info(priv->dev, "active high/rising IRQ\n"); val = 0; break; case IRQF_TRIGGER_FALLING: case IRQF_TRIGGER_LOW: - dev_info(smi->dev, "active low/falling IRQ\n"); + dev_info(priv->dev, "active low/falling IRQ\n"); val = RTL8366RB_INTERRUPT_POLARITY; break; } - ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_CONTROL_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG, RTL8366RB_INTERRUPT_POLARITY, val); if (ret) { - dev_err(smi->dev, "could not configure IRQ polarity\n"); + dev_err(priv->dev, "could not configure IRQ polarity\n"); goto out_put_node; } - ret = devm_request_threaded_irq(smi->dev, irq, NULL, + ret = devm_request_threaded_irq(priv->dev, irq, NULL, rtl8366rb_irq, IRQF_ONESHOT, - "RTL8366RB", smi); + "RTL8366RB", priv); if (ret) { - dev_err(smi->dev, "unable to request irq: %d\n", ret); + dev_err(priv->dev, "unable to request irq: %d\n", ret); goto out_put_node; } - smi->irqdomain = irq_domain_add_linear(intc, - RTL8366RB_NUM_INTERRUPT, - &rtl8366rb_irqdomain_ops, - smi); - if (!smi->irqdomain) { - dev_err(smi->dev, "failed to create IRQ domain\n"); + priv->irqdomain = irq_domain_add_linear(intc, + RTL8366RB_NUM_INTERRUPT, + &rtl8366rb_irqdomain_ops, + priv); + if (!priv->irqdomain) { + dev_err(priv->dev, "failed to create IRQ domain\n"); ret = -EINVAL; goto out_put_node; } - for (i = 0; i < smi->num_ports; i++) - irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq); + for (i = 0; i < priv->num_ports; i++) + irq_set_parent(irq_create_mapping(priv->irqdomain, i), irq); out_put_node: of_node_put(intc); return ret; } -static int rtl8366rb_set_addr(struct realtek_smi *smi) +static int rtl8366rb_set_addr(struct realtek_priv *priv) { u8 addr[ETH_ALEN]; u16 val; @@ -622,18 +622,18 @@ static int rtl8366rb_set_addr(struct realtek_smi *smi) eth_random_addr(addr); - dev_info(smi->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n", + dev_info(priv->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n", addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); val = addr[0] << 8 | addr[1]; - ret = regmap_write(smi->map, RTL8366RB_SMAR0, val); + ret = regmap_write(priv->map, RTL8366RB_SMAR0, val); if (ret) return ret; val = addr[2] << 8 | addr[3]; - ret = regmap_write(smi->map, RTL8366RB_SMAR1, val); + ret = regmap_write(priv->map, RTL8366RB_SMAR1, val); if (ret) return ret; val = addr[4] << 8 | addr[5]; - ret = regmap_write(smi->map, RTL8366RB_SMAR2, val); + ret = regmap_write(priv->map, RTL8366RB_SMAR2, val); if (ret) return ret; @@ -765,7 +765,7 @@ static const struct rtl8366rb_jam_tbl_entry rtl8366rb_green_jam[] = { /* Function that jams the tables in the proper registers */ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, - int jam_size, struct realtek_smi *smi, + int jam_size, struct realtek_priv *priv, bool write_dbg) { u32 val; @@ -774,24 +774,24 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, for (i = 0; i < jam_size; i++) { if ((jam_table[i].reg & 0xBE00) == 0xBE00) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8366RB_PHY_ACCESS_BUSY_REG, &val); if (ret) return ret; if (!(val & RTL8366RB_PHY_INT_BUSY)) { - ret = regmap_write(smi->map, - RTL8366RB_PHY_ACCESS_CTRL_REG, - RTL8366RB_PHY_CTRL_WRITE); + ret = regmap_write(priv->map, + RTL8366RB_PHY_ACCESS_CTRL_REG, + RTL8366RB_PHY_CTRL_WRITE); if (ret) return ret; } } if (write_dbg) - dev_dbg(smi->dev, "jam %04x into register %04x\n", + dev_dbg(priv->dev, "jam %04x into register %04x\n", jam_table[i].val, jam_table[i].reg); - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, jam_table[i].reg, jam_table[i].val); if (ret) @@ -802,7 +802,7 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, static int rtl8366rb_setup(struct dsa_switch *ds) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; const struct rtl8366rb_jam_tbl_entry *jam_table; struct rtl8366rb *rb; u32 chip_ver = 0; @@ -812,11 +812,11 @@ static int rtl8366rb_setup(struct dsa_switch *ds) int ret; int i; - rb = smi->chip_data; + rb = priv->chip_data; - ret = regmap_read(smi->map, RTL8366RB_CHIP_ID_REG, &chip_id); + ret = regmap_read(priv->map, RTL8366RB_CHIP_ID_REG, &chip_id); if (ret) { - dev_err(smi->dev, "unable to read chip id\n"); + dev_err(priv->dev, "unable to read chip id\n"); return ret; } @@ -824,18 +824,18 @@ static int rtl8366rb_setup(struct dsa_switch *ds) case RTL8366RB_CHIP_ID_8366: break; default: - dev_err(smi->dev, "unknown chip id (%04x)\n", chip_id); + dev_err(priv->dev, "unknown chip id (%04x)\n", chip_id); return -ENODEV; } - ret = regmap_read(smi->map, RTL8366RB_CHIP_VERSION_CTRL_REG, + ret = regmap_read(priv->map, RTL8366RB_CHIP_VERSION_CTRL_REG, &chip_ver); if (ret) { - dev_err(smi->dev, "unable to read chip version\n"); + dev_err(priv->dev, "unable to read chip version\n"); return ret; } - dev_info(smi->dev, "RTL%04x ver %u chip found\n", + dev_info(priv->dev, "RTL%04x ver %u chip found\n", chip_id, chip_ver & RTL8366RB_CHIP_VERSION_MASK); /* Do the init dance using the right jam table */ @@ -872,20 +872,20 @@ static int rtl8366rb_setup(struct dsa_switch *ds) jam_size = ARRAY_SIZE(rtl8366rb_init_jam_dgn3500); } - ret = rtl8366rb_jam_table(jam_table, jam_size, smi, true); + ret = rtl8366rb_jam_table(jam_table, jam_size, priv, true); if (ret) return ret; /* Isolate all user ports so they can only send packets to itself and the CPU port */ for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { - ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(i), + ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(i), RTL8366RB_PORT_ISO_PORTS(BIT(RTL8366RB_PORT_NUM_CPU)) | RTL8366RB_PORT_ISO_EN); if (ret) return ret; } /* CPU port can send packets to all ports */ - ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU), + ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU), RTL8366RB_PORT_ISO_PORTS(dsa_user_ports(ds)) | RTL8366RB_PORT_ISO_EN); if (ret) @@ -893,26 +893,26 @@ static int rtl8366rb_setup(struct dsa_switch *ds) /* Set up the "green ethernet" feature */ ret = rtl8366rb_jam_table(rtl8366rb_green_jam, - ARRAY_SIZE(rtl8366rb_green_jam), smi, false); + ARRAY_SIZE(rtl8366rb_green_jam), priv, false); if (ret) return ret; - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, RTL8366RB_GREEN_FEATURE_REG, (chip_ver == 1) ? 0x0007 : 0x0003); if (ret) return ret; /* Vendor driver sets 0x240 in registers 0xc and 0xd (undocumented) */ - ret = regmap_write(smi->map, 0x0c, 0x240); + ret = regmap_write(priv->map, 0x0c, 0x240); if (ret) return ret; - ret = regmap_write(smi->map, 0x0d, 0x240); + ret = regmap_write(priv->map, 0x0d, 0x240); if (ret) return ret; /* Set some random MAC address */ - ret = rtl8366rb_set_addr(smi); + ret = rtl8366rb_set_addr(priv); if (ret) return ret; @@ -921,21 +921,21 @@ static int rtl8366rb_setup(struct dsa_switch *ds) * If you set RTL8368RB_CPU_NO_TAG (bit 15) in this registers * the custom tag is turned off. */ - ret = regmap_update_bits(smi->map, RTL8368RB_CPU_CTRL_REG, + ret = regmap_update_bits(priv->map, RTL8368RB_CPU_CTRL_REG, 0xFFFF, - BIT(smi->cpu_port)); + BIT(priv->cpu_port)); if (ret) return ret; /* Make sure we default-enable the fixed CPU port */ - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, - BIT(smi->cpu_port), + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, + BIT(priv->cpu_port), 0); if (ret) return ret; /* Set maximum packet length to 1536 bytes */ - ret = regmap_update_bits(smi->map, RTL8366RB_SGCR, + ret = regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_MAX_LENGTH_MASK, RTL8366RB_SGCR_MAX_LENGTH_1536); if (ret) @@ -945,13 +945,13 @@ static int rtl8366rb_setup(struct dsa_switch *ds) rb->max_mtu[i] = 1532; /* Disable learning for all ports */ - ret = regmap_write(smi->map, RTL8366RB_PORT_LEARNDIS_CTRL, + ret = regmap_write(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL, RTL8366RB_PORT_ALL); if (ret) return ret; /* Enable auto ageing for all ports */ - ret = regmap_write(smi->map, RTL8366RB_SECURITY_CTRL, 0); + ret = regmap_write(priv->map, RTL8366RB_SECURITY_CTRL, 0); if (ret) return ret; @@ -962,30 +962,30 @@ static int rtl8366rb_setup(struct dsa_switch *ds) * connected to something exotic such as fiber, then this might * be worth experimenting with. */ - ret = regmap_update_bits(smi->map, RTL8366RB_PMC0, + ret = regmap_update_bits(priv->map, RTL8366RB_PMC0, RTL8366RB_PMC0_P4_IOMODE_MASK, 0 << RTL8366RB_PMC0_P4_IOMODE_SHIFT); if (ret) return ret; /* Accept all packets by default, we enable filtering on-demand */ - ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, + ret = regmap_write(priv->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, 0); if (ret) return ret; - ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, + ret = regmap_write(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, 0); if (ret) return ret; /* Don't drop packets whose DA has not been learned */ - ret = regmap_update_bits(smi->map, RTL8366RB_SSCR2, + ret = regmap_update_bits(priv->map, RTL8366RB_SSCR2, RTL8366RB_SSCR2_DROP_UNKNOWN_DA, 0); if (ret) return ret; /* Set blinking, TODO: make this configurable */ - ret = regmap_update_bits(smi->map, RTL8366RB_LED_BLINKRATE_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_BLINKRATE_REG, RTL8366RB_LED_BLINKRATE_MASK, RTL8366RB_LED_BLINKRATE_56MS); if (ret) @@ -996,15 +996,15 @@ static int rtl8366rb_setup(struct dsa_switch *ds) * behaviour (no individual config) but we can set up each * LED separately. */ - if (smi->leds_disabled) { + if (priv->leds_disabled) { /* Turn everything off */ - regmap_update_bits(smi->map, + regmap_update_bits(priv->map, RTL8366RB_LED_0_1_CTRL_REG, 0x0FFF, 0); - regmap_update_bits(smi->map, + regmap_update_bits(priv->map, RTL8366RB_LED_2_3_CTRL_REG, 0x0FFF, 0); - regmap_update_bits(smi->map, + regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG, RTL8366RB_P4_RGMII_LED, 0); @@ -1014,7 +1014,7 @@ static int rtl8366rb_setup(struct dsa_switch *ds) val = RTL8366RB_LED_FORCE; } for (i = 0; i < 4; i++) { - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_CTRL_REG, 0xf << (i * 4), val << (i * 4)); @@ -1022,18 +1022,20 @@ static int rtl8366rb_setup(struct dsa_switch *ds) return ret; } - ret = rtl8366_reset_vlan(smi); + ret = rtl8366_reset_vlan(priv); if (ret) return ret; - ret = rtl8366rb_setup_cascaded_irq(smi); + ret = rtl8366rb_setup_cascaded_irq(priv); if (ret) - dev_info(smi->dev, "no interrupt support\n"); + dev_info(priv->dev, "no interrupt support\n"); - ret = realtek_smi_setup_mdio(smi); - if (ret) { - dev_info(smi->dev, "could not set up MDIO bus\n"); - return -ENODEV; + if (priv->setup_interface) { + ret = priv->setup_interface(ds); + if (ret) { + dev_err(priv->dev, "could not set up MDIO bus\n"); + return -ENODEV; + } } return 0; @@ -1052,35 +1054,35 @@ rtl8366rb_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, struct phy_device *phydev, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - if (port != smi->cpu_port) + if (port != priv->cpu_port) return; - dev_dbg(smi->dev, "MAC link up on CPU port (%d)\n", port); + dev_dbg(priv->dev, "MAC link up on CPU port (%d)\n", port); /* Force the fixed CPU port into 1Gbit mode, no autonegotiation */ - ret = regmap_update_bits(smi->map, RTL8366RB_MAC_FORCE_CTRL_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_MAC_FORCE_CTRL_REG, BIT(port), BIT(port)); if (ret) { - dev_err(smi->dev, "failed to force 1Gbit on CPU port\n"); + dev_err(priv->dev, "failed to force 1Gbit on CPU port\n"); return; } - ret = regmap_update_bits(smi->map, RTL8366RB_PAACR2, + ret = regmap_update_bits(priv->map, RTL8366RB_PAACR2, 0xFF00U, RTL8366RB_PAACR_CPU_PORT << 8); if (ret) { - dev_err(smi->dev, "failed to set PAACR on CPU port\n"); + dev_err(priv->dev, "failed to set PAACR on CPU port\n"); return; } /* Enable the CPU port */ - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), 0); if (ret) { - dev_err(smi->dev, "failed to enable the CPU port\n"); + dev_err(priv->dev, "failed to enable the CPU port\n"); return; } } @@ -1089,99 +1091,99 @@ static void rtl8366rb_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - if (port != smi->cpu_port) + if (port != priv->cpu_port) return; - dev_dbg(smi->dev, "MAC link down on CPU port (%d)\n", port); + dev_dbg(priv->dev, "MAC link down on CPU port (%d)\n", port); /* Disable the CPU port */ - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), BIT(port)); if (ret) { - dev_err(smi->dev, "failed to disable the CPU port\n"); + dev_err(priv->dev, "failed to disable the CPU port\n"); return; } } -static void rb8366rb_set_port_led(struct realtek_smi *smi, +static void rb8366rb_set_port_led(struct realtek_priv *priv, int port, bool enable) { u16 val = enable ? 0x3f : 0; int ret; - if (smi->leds_disabled) + if (priv->leds_disabled) return; switch (port) { case 0: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_0_1_CTRL_REG, 0x3F, val); break; case 1: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_0_1_CTRL_REG, 0x3F << RTL8366RB_LED_1_OFFSET, val << RTL8366RB_LED_1_OFFSET); break; case 2: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_2_3_CTRL_REG, 0x3F, val); break; case 3: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_2_3_CTRL_REG, 0x3F << RTL8366RB_LED_3_OFFSET, val << RTL8366RB_LED_3_OFFSET); break; case 4: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG, RTL8366RB_P4_RGMII_LED, enable ? RTL8366RB_P4_RGMII_LED : 0); break; default: - dev_err(smi->dev, "no LED for port %d\n", port); + dev_err(priv->dev, "no LED for port %d\n", port); return; } if (ret) - dev_err(smi->dev, "error updating LED on port %d\n", port); + dev_err(priv->dev, "error updating LED on port %d\n", port); } static int rtl8366rb_port_enable(struct dsa_switch *ds, int port, struct phy_device *phy) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - dev_dbg(smi->dev, "enable port %d\n", port); - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + dev_dbg(priv->dev, "enable port %d\n", port); + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), 0); if (ret) return ret; - rb8366rb_set_port_led(smi, port, true); + rb8366rb_set_port_led(priv, port, true); return 0; } static void rtl8366rb_port_disable(struct dsa_switch *ds, int port) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - dev_dbg(smi->dev, "disable port %d\n", port); - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + dev_dbg(priv->dev, "disable port %d\n", port); + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), BIT(port)); if (ret) return; - rb8366rb_set_port_led(smi, port, false); + rb8366rb_set_port_led(priv, port, false); } static int @@ -1189,7 +1191,7 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; unsigned int port_bitmap = 0; int ret, i; @@ -1202,17 +1204,17 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Join this port to each other port on the bridge */ - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i), RTL8366RB_PORT_ISO_PORTS(BIT(port)), RTL8366RB_PORT_ISO_PORTS(BIT(port))); if (ret) - dev_err(smi->dev, "failed to join port %d\n", port); + dev_err(priv->dev, "failed to join port %d\n", port); port_bitmap |= BIT(i); } /* Set the bits for the ports we can access */ - return regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port), + return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), RTL8366RB_PORT_ISO_PORTS(port_bitmap), RTL8366RB_PORT_ISO_PORTS(port_bitmap)); } @@ -1221,7 +1223,7 @@ static void rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; unsigned int port_bitmap = 0; int ret, i; @@ -1234,28 +1236,30 @@ rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Remove this port from any other port on the bridge */ - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i), RTL8366RB_PORT_ISO_PORTS(BIT(port)), 0); if (ret) - dev_err(smi->dev, "failed to leave port %d\n", port); + dev_err(priv->dev, "failed to leave port %d\n", port); port_bitmap |= BIT(i); } /* Clear the bits for the ports we can not access, leave ourselves */ - regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port), + regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), RTL8366RB_PORT_ISO_PORTS(port_bitmap), 0); } /** * rtl8366rb_drop_untagged() - make the switch drop untagged and C-tagged frames - * @smi: SMI state container + * @priv: SMI state container * @port: the port to drop untagged and C-tagged frames on * @drop: whether to drop or pass untagged and C-tagged frames + * + * Return: zero for success, a negative number on error. */ -static int rtl8366rb_drop_untagged(struct realtek_smi *smi, int port, bool drop) +static int rtl8366rb_drop_untagged(struct realtek_priv *priv, int port, bool drop) { - return regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, + return regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port), drop ? RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port) : 0); } @@ -1264,17 +1268,17 @@ static int rtl8366rb_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8366rb *rb; int ret; - rb = smi->chip_data; + rb = priv->chip_data; - dev_dbg(smi->dev, "port %d: %s VLAN filtering\n", port, + dev_dbg(priv->dev, "port %d: %s VLAN filtering\n", port, vlan_filtering ? "enable" : "disable"); /* If the port is not in the member set, the frame will be dropped */ - ret = regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, BIT(port), vlan_filtering ? BIT(port) : 0); if (ret) return ret; @@ -1284,9 +1288,9 @@ static int rtl8366rb_vlan_filtering(struct dsa_switch *ds, int port, * filtering on a port, we need to accept any frames. */ if (vlan_filtering) - ret = rtl8366rb_drop_untagged(smi, port, !rb->pvid_enabled[port]); + ret = rtl8366rb_drop_untagged(priv, port, !rb->pvid_enabled[port]); else - ret = rtl8366rb_drop_untagged(smi, port, false); + ret = rtl8366rb_drop_untagged(priv, port, false); return ret; } @@ -1308,11 +1312,11 @@ rtl8366rb_port_bridge_flags(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; if (flags.mask & BR_LEARNING) { - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_LEARNDIS_CTRL, + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL, BIT(port), (flags.val & BR_LEARNING) ? 0 : BIT(port)); if (ret) @@ -1325,7 +1329,7 @@ rtl8366rb_port_bridge_flags(struct dsa_switch *ds, int port, static void rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; u32 val; int i; @@ -1344,13 +1348,13 @@ rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) val = RTL8366RB_STP_STATE_FORWARDING; break; default: - dev_err(smi->dev, "unknown bridge state requested\n"); + dev_err(priv->dev, "unknown bridge state requested\n"); return; } /* Set the same status for the port on all the FIDs */ for (i = 0; i < RTL8366RB_NUM_FIDS; i++) { - regmap_update_bits(smi->map, RTL8366RB_STP_STATE_BASE + i, + regmap_update_bits(priv->map, RTL8366RB_STP_STATE_BASE + i, RTL8366RB_STP_STATE_MASK(port), RTL8366RB_STP_STATE(port, val)); } @@ -1359,26 +1363,26 @@ rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) static void rtl8366rb_port_fast_age(struct dsa_switch *ds, int port) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; /* This will age out any learned L2 entries */ - regmap_update_bits(smi->map, RTL8366RB_SECURITY_CTRL, + regmap_update_bits(priv->map, RTL8366RB_SECURITY_CTRL, BIT(port), BIT(port)); /* Restore the normal state of things */ - regmap_update_bits(smi->map, RTL8366RB_SECURITY_CTRL, + regmap_update_bits(priv->map, RTL8366RB_SECURITY_CTRL, BIT(port), 0); } static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8366rb *rb; unsigned int max_mtu; u32 len; int i; /* Cache the per-port MTU setting */ - rb = smi->chip_data; + rb = priv->chip_data; rb->max_mtu[port] = new_mtu; /* Roof out the MTU for the entire switch to the greatest @@ -1406,7 +1410,7 @@ static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu) else len = RTL8366RB_SGCR_MAX_LENGTH_16000; - return regmap_update_bits(smi->map, RTL8366RB_SGCR, + return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_MAX_LENGTH_MASK, len); } @@ -1419,7 +1423,7 @@ static int rtl8366rb_max_mtu(struct dsa_switch *ds, int port) return 15996; } -static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid, +static int rtl8366rb_get_vlan_4k(struct realtek_priv *priv, u32 vid, struct rtl8366_vlan_4k *vlan4k) { u32 data[3]; @@ -1432,19 +1436,19 @@ static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid, return -EINVAL; /* write VID */ - ret = regmap_write(smi->map, RTL8366RB_VLAN_TABLE_WRITE_BASE, + ret = regmap_write(priv->map, RTL8366RB_VLAN_TABLE_WRITE_BASE, vid & RTL8366RB_VLAN_VID_MASK); if (ret) return ret; /* write table access control word */ - ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, RTL8366RB_TABLE_VLAN_READ_CTRL); if (ret) return ret; for (i = 0; i < 3; i++) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8366RB_VLAN_TABLE_READ_BASE + i, &data[i]); if (ret) @@ -1460,7 +1464,7 @@ static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid, return 0; } -static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi, +static int rtl8366rb_set_vlan_4k(struct realtek_priv *priv, const struct rtl8366_vlan_4k *vlan4k) { u32 data[3]; @@ -1480,7 +1484,7 @@ static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi, data[2] = vlan4k->fid & RTL8366RB_VLAN_FID_MASK; for (i = 0; i < 3; i++) { - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, RTL8366RB_VLAN_TABLE_WRITE_BASE + i, data[i]); if (ret) @@ -1488,13 +1492,13 @@ static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi, } /* write table access control word */ - ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, RTL8366RB_TABLE_VLAN_WRITE_CTRL); return ret; } -static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index, +static int rtl8366rb_get_vlan_mc(struct realtek_priv *priv, u32 index, struct rtl8366_vlan_mc *vlanmc) { u32 data[3]; @@ -1507,7 +1511,7 @@ static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index, return -EINVAL; for (i = 0; i < 3; i++) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8366RB_VLAN_MC_BASE(index) + i, &data[i]); if (ret) @@ -1525,7 +1529,7 @@ static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index, return 0; } -static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index, +static int rtl8366rb_set_vlan_mc(struct realtek_priv *priv, u32 index, const struct rtl8366_vlan_mc *vlanmc) { u32 data[3]; @@ -1549,7 +1553,7 @@ static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index, data[2] = vlanmc->fid & RTL8366RB_VLAN_FID_MASK; for (i = 0; i < 3; i++) { - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, RTL8366RB_VLAN_MC_BASE(index) + i, data[i]); if (ret) @@ -1559,15 +1563,15 @@ static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index, return 0; } -static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val) +static int rtl8366rb_get_mc_index(struct realtek_priv *priv, int port, int *val) { u32 data; int ret; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return -EINVAL; - ret = regmap_read(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), + ret = regmap_read(priv->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), &data); if (ret) return ret; @@ -1578,22 +1582,22 @@ static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val) return 0; } -static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index) +static int rtl8366rb_set_mc_index(struct realtek_priv *priv, int port, int index) { struct rtl8366rb *rb; bool pvid_enabled; int ret; - rb = smi->chip_data; + rb = priv->chip_data; pvid_enabled = !!index; - if (port >= smi->num_ports || index >= RTL8366RB_NUM_VLANS) + if (port >= priv->num_ports || index >= RTL8366RB_NUM_VLANS) return -EINVAL; - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), - RTL8366RB_PORT_VLAN_CTRL_MASK << + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), + RTL8366RB_PORT_VLAN_CTRL_MASK << RTL8366RB_PORT_VLAN_CTRL_SHIFT(port), - (index & RTL8366RB_PORT_VLAN_CTRL_MASK) << + (index & RTL8366RB_PORT_VLAN_CTRL_MASK) << RTL8366RB_PORT_VLAN_CTRL_SHIFT(port)); if (ret) return ret; @@ -1604,17 +1608,17 @@ static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index) * not drop any untagged or C-tagged frames. Make sure to update the * filtering setting. */ - if (dsa_port_is_vlan_filtering(dsa_to_port(smi->ds, port))) - ret = rtl8366rb_drop_untagged(smi, port, !pvid_enabled); + if (dsa_port_is_vlan_filtering(dsa_to_port(priv->ds, port))) + ret = rtl8366rb_drop_untagged(priv, port, !pvid_enabled); return ret; } -static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan) +static bool rtl8366rb_is_vlan_valid(struct realtek_priv *priv, unsigned int vlan) { unsigned int max = RTL8366RB_NUM_VLANS - 1; - if (smi->vlan4k_enabled) + if (priv->vlan4k_enabled) max = RTL8366RB_NUM_VIDS - 1; if (vlan > max) @@ -1623,23 +1627,23 @@ static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan) return true; } -static int rtl8366rb_enable_vlan(struct realtek_smi *smi, bool enable) +static int rtl8366rb_enable_vlan(struct realtek_priv *priv, bool enable) { - dev_dbg(smi->dev, "%s VLAN\n", enable ? "enable" : "disable"); - return regmap_update_bits(smi->map, + dev_dbg(priv->dev, "%s VLAN\n", enable ? "enable" : "disable"); + return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN, enable ? RTL8366RB_SGCR_EN_VLAN : 0); } -static int rtl8366rb_enable_vlan4k(struct realtek_smi *smi, bool enable) +static int rtl8366rb_enable_vlan4k(struct realtek_priv *priv, bool enable) { - dev_dbg(smi->dev, "%s VLAN 4k\n", enable ? "enable" : "disable"); - return regmap_update_bits(smi->map, RTL8366RB_SGCR, + dev_dbg(priv->dev, "%s VLAN 4k\n", enable ? "enable" : "disable"); + return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN_4KTB, enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0); } -static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum) +static int rtl8366rb_phy_read(struct realtek_priv *priv, int phy, int regnum) { u32 val; u32 reg; @@ -1648,32 +1652,32 @@ static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum) if (phy > RTL8366RB_PHY_NO_MAX) return -EINVAL; - ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_PHY_ACCESS_CTRL_REG, RTL8366RB_PHY_CTRL_READ); if (ret) return ret; reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum; - ret = regmap_write(smi->map, reg, 0); + ret = regmap_write(priv->map, reg, 0); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to write PHY%d reg %04x @ %04x, ret %d\n", phy, regnum, reg, ret); return ret; } - ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val); + ret = regmap_read(priv->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val); if (ret) return ret; - dev_dbg(smi->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n", + dev_dbg(priv->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n", phy, regnum, reg, val); return val; } -static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum, +static int rtl8366rb_phy_write(struct realtek_priv *priv, int phy, int regnum, u16 val) { u32 reg; @@ -1682,34 +1686,45 @@ static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum, if (phy > RTL8366RB_PHY_NO_MAX) return -EINVAL; - ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_PHY_ACCESS_CTRL_REG, RTL8366RB_PHY_CTRL_WRITE); if (ret) return ret; reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum; - dev_dbg(smi->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n", + dev_dbg(priv->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n", phy, regnum, reg, val); - ret = regmap_write(smi->map, reg, val); + ret = regmap_write(priv->map, reg, val); if (ret) return ret; return 0; } -static int rtl8366rb_reset_chip(struct realtek_smi *smi) +static int rtl8366rb_dsa_phy_read(struct dsa_switch *ds, int phy, int regnum) +{ + return rtl8366rb_phy_read(ds->priv, phy, regnum); +} + +static int rtl8366rb_dsa_phy_write(struct dsa_switch *ds, int phy, int regnum, + u16 val) +{ + return rtl8366rb_phy_write(ds->priv, phy, regnum, val); +} + +static int rtl8366rb_reset_chip(struct realtek_priv *priv) { int timeout = 10; u32 val; int ret; - realtek_smi_write_reg_noack(smi, RTL8366RB_RESET_CTRL_REG, - RTL8366RB_CHIP_CTRL_RESET_HW); + priv->write_reg_noack(priv, RTL8366RB_RESET_CTRL_REG, + RTL8366RB_CHIP_CTRL_RESET_HW); do { usleep_range(20000, 25000); - ret = regmap_read(smi->map, RTL8366RB_RESET_CTRL_REG, &val); + ret = regmap_read(priv->map, RTL8366RB_RESET_CTRL_REG, &val); if (ret) return ret; @@ -1718,21 +1733,21 @@ static int rtl8366rb_reset_chip(struct realtek_smi *smi) } while (--timeout); if (!timeout) { - dev_err(smi->dev, "timeout waiting for the switch to reset\n"); + dev_err(priv->dev, "timeout waiting for the switch to reset\n"); return -EIO; } return 0; } -static int rtl8366rb_detect(struct realtek_smi *smi) +static int rtl8366rb_detect(struct realtek_priv *priv) { - struct device *dev = smi->dev; + struct device *dev = priv->dev; int ret; u32 val; /* Detect device */ - ret = regmap_read(smi->map, 0x5c, &val); + ret = regmap_read(priv->map, 0x5c, &val); if (ret) { dev_err(dev, "can't get chip ID (%d)\n", ret); return ret; @@ -1745,11 +1760,11 @@ static int rtl8366rb_detect(struct realtek_smi *smi) return -ENODEV; case 0x5937: dev_info(dev, "found an RTL8366RB switch\n"); - smi->cpu_port = RTL8366RB_PORT_NUM_CPU; - smi->num_ports = RTL8366RB_NUM_PORTS; - smi->num_vlan_mc = RTL8366RB_NUM_VLANS; - smi->mib_counters = rtl8366rb_mib_counters; - smi->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters); + priv->cpu_port = RTL8366RB_PORT_NUM_CPU; + priv->num_ports = RTL8366RB_NUM_PORTS; + priv->num_vlan_mc = RTL8366RB_NUM_VLANS; + priv->mib_counters = rtl8366rb_mib_counters; + priv->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters); break; default: dev_info(dev, "found an Unknown Realtek switch (id=0x%04x)\n", @@ -1757,14 +1772,14 @@ static int rtl8366rb_detect(struct realtek_smi *smi) break; } - ret = rtl8366rb_reset_chip(smi); + ret = rtl8366rb_reset_chip(priv); if (ret) return ret; return 0; } -static const struct dsa_switch_ops rtl8366rb_switch_ops = { +static const struct dsa_switch_ops rtl8366rb_switch_ops_smi = { .get_tag_protocol = rtl8366_get_tag_protocol, .setup = rtl8366rb_setup, .phylink_mac_link_up = rtl8366rb_mac_link_up, @@ -1787,7 +1802,32 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops = { .port_max_mtu = rtl8366rb_max_mtu, }; -static const struct realtek_smi_ops rtl8366rb_smi_ops = { +static const struct dsa_switch_ops rtl8366rb_switch_ops_mdio = { + .get_tag_protocol = rtl8366_get_tag_protocol, + .setup = rtl8366rb_setup, + .phy_read = rtl8366rb_dsa_phy_read, + .phy_write = rtl8366rb_dsa_phy_write, + .phylink_mac_link_up = rtl8366rb_mac_link_up, + .phylink_mac_link_down = rtl8366rb_mac_link_down, + .get_strings = rtl8366_get_strings, + .get_ethtool_stats = rtl8366_get_ethtool_stats, + .get_sset_count = rtl8366_get_sset_count, + .port_bridge_join = rtl8366rb_port_bridge_join, + .port_bridge_leave = rtl8366rb_port_bridge_leave, + .port_vlan_filtering = rtl8366rb_vlan_filtering, + .port_vlan_add = rtl8366_vlan_add, + .port_vlan_del = rtl8366_vlan_del, + .port_enable = rtl8366rb_port_enable, + .port_disable = rtl8366rb_port_disable, + .port_pre_bridge_flags = rtl8366rb_port_pre_bridge_flags, + .port_bridge_flags = rtl8366rb_port_bridge_flags, + .port_stp_state_set = rtl8366rb_port_stp_state_set, + .port_fast_age = rtl8366rb_port_fast_age, + .port_change_mtu = rtl8366rb_change_mtu, + .port_max_mtu = rtl8366rb_max_mtu, +}; + +static const struct realtek_ops rtl8366rb_ops = { .detect = rtl8366rb_detect, .get_vlan_mc = rtl8366rb_get_vlan_mc, .set_vlan_mc = rtl8366rb_set_vlan_mc, @@ -1803,12 +1843,17 @@ static const struct realtek_smi_ops rtl8366rb_smi_ops = { .phy_write = rtl8366rb_phy_write, }; -const struct realtek_smi_variant rtl8366rb_variant = { - .ds_ops = &rtl8366rb_switch_ops, - .ops = &rtl8366rb_smi_ops, +const struct realtek_variant rtl8366rb_variant = { + .ds_ops_smi = &rtl8366rb_switch_ops_smi, + .ds_ops_mdio = &rtl8366rb_switch_ops_mdio, + .ops = &rtl8366rb_ops, .clk_delay = 10, .cmd_read = 0xa9, .cmd_write = 0xa8, .chip_data_sz = sizeof(struct rtl8366rb), }; EXPORT_SYMBOL_GPL(rtl8366rb_variant); + +MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>"); +MODULE_DESCRIPTION("Driver for RTL8366RB ethernet switch"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 0730352cdd57..bc06fe6bac6b 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -442,34 +442,27 @@ static void xrs700x_teardown(struct dsa_switch *ds) cancel_delayed_work_sync(&priv->mib_work); } -static void xrs700x_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void xrs700x_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - switch (port) { case 0: + __set_bit(PHY_INTERFACE_MODE_RMII, + config->supported_interfaces); + config->mac_capabilities = MAC_10FD | MAC_100FD; break; + case 1: case 2: case 3: - phylink_set(mask, 1000baseT_Full); + phy_interface_set_rgmii(config->supported_interfaces); + config->mac_capabilities = MAC_10FD | MAC_100FD | MAC_1000FD; break; + default: - linkmode_zero(supported); dev_err(ds->dev, "Unsupported port: %i\n", port); - return; + break; } - - phylink_set_port_modes(mask); - - /* The switch only supports full duplex. */ - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); } static void xrs700x_mac_link_up(struct dsa_switch *ds, int port, @@ -703,7 +696,7 @@ static const struct dsa_switch_ops xrs700x_ops = { .setup = xrs700x_setup, .teardown = xrs700x_teardown, .port_stp_state_set = xrs700x_port_stp_state_set, - .phylink_validate = xrs700x_phylink_validate, + .phylink_get_caps = xrs700x_phylink_get_caps, .phylink_mac_link_up = xrs700x_mac_link_up, .get_strings = xrs700x_get_strings, .get_sset_count = xrs700x_get_sset_count, diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index 8aec5d9fbfef..ad57209007e1 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -138,11 +138,6 @@ MODULE_PARM_DESC(use_mmio, "Use MMIO (1) or PIO(0) to access the NIC. " module_param(rx_copybreak, int, 0); module_param(use_mmio, int, 0); -#if defined(NETIF_F_TSO) && MAX_SKB_FRAGS > 32 -#warning Typhoon only supports 32 entries in its SG list for TSO, disabling TSO -#undef NETIF_F_TSO -#endif - #if TXLO_ENTRIES <= (2 * MAX_SKB_FRAGS) #error TX ring too small! #endif @@ -2261,9 +2256,28 @@ out: return mode; } +#if MAX_SKB_FRAGS > 32 + +#include <net/vxlan.h> + +static netdev_features_t typhoon_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + if (skb_shinfo(skb)->nr_frags > 32 && skb_is_gso(skb)) + features &= ~NETIF_F_GSO_MASK; + + features = vlan_features_check(skb, features); + return vxlan_features_check(skb, features); +} +#endif + static const struct net_device_ops typhoon_netdev_ops = { .ndo_open = typhoon_open, .ndo_stop = typhoon_close, +#if MAX_SKB_FRAGS > 32 + .ndo_features_check = typhoon_features_check, +#endif .ndo_start_xmit = typhoon_start_tx, .ndo_set_rx_mode = typhoon_set_rx_mode, .ndo_tx_timeout = typhoon_tx_timeout, diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 537e6a85e18d..fbf4588994ac 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2413,11 +2413,13 @@ static void et131x_tx_dma_memory_free(struct et131x_adapter *adapter) kfree(tx_ring->tcb_ring); } +#define MAX_TX_DESC_PER_PKT 24 + /* nic_send_packet - NIC specific send handler for version B silicon. */ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) { u32 i; - struct tx_desc desc[24]; + struct tx_desc desc[MAX_TX_DESC_PER_PKT]; u32 frag = 0; u32 thiscopy, remainder; struct sk_buff *skb = tcb->skb; @@ -2432,9 +2434,6 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) * more than 5 fragments. */ - /* nr_frags should be no more than 18. */ - BUILD_BUG_ON(MAX_SKB_FRAGS + 1 > 23); - memset(desc, 0, sizeof(struct tx_desc) * (nr_frags + 1)); for (i = 0; i < nr_frags; i++) { @@ -3762,6 +3761,13 @@ static netdev_tx_t et131x_tx(struct sk_buff *skb, struct net_device *netdev) struct et131x_adapter *adapter = netdev_priv(netdev); struct tx_ring *tx_ring = &adapter->tx_ring; + /* This driver does not support TSO, it is very unlikely + * this condition is true. + */ + if (unlikely(skb_shinfo(skb)->nr_frags > MAX_TX_DESC_PER_PKT - 2)) { + if (skb_linearize(skb)) + goto drop_err; + } /* stop the queue if it's getting full */ if (tx_ring->used >= NUM_TCB - 1 && !netif_queue_stopped(netdev)) netif_stop_queue(netdev); diff --git a/drivers/net/ethernet/altera/altera_sgdma.c b/drivers/net/ethernet/altera/altera_sgdma.c index db97170da8c7..7f247ccbe6ba 100644 --- a/drivers/net/ethernet/altera/altera_sgdma.c +++ b/drivers/net/ethernet/altera/altera_sgdma.c @@ -513,7 +513,7 @@ static int sgdma_txbusy(struct altera_tse_private *priv) { int delay = 0; - /* if DMA is busy, wait for current transactino to finish */ + /* if DMA is busy, wait for current transaction to finish */ while ((csrrd32(priv->tx_dma_csr, sgdma_csroffs(status)) & SGDMA_STSREG_BUSY) && (delay++ < 100)) udelay(1); diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 993b2fb42961..a3816264c35c 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -72,7 +72,7 @@ MODULE_PARM_DESC(dma_tx_num, "Number of descriptors in the TX list"); */ #define ALTERA_RXDMABUFFER_SIZE 2048 -/* Allow network stack to resume queueing packets after we've +/* Allow network stack to resume queuing packets after we've * finished transmitting at least 1/4 of the packets in the queue. */ #define TSE_TX_THRESH(x) (x->tx_ring_size / 4) @@ -390,7 +390,7 @@ static int tse_rx(struct altera_tse_private *priv, int limit) "RCV pktstatus %08X pktlength %08X\n", pktstatus, pktlength); - /* DMA trasfer from TSE starts with 2 aditional bytes for + /* DMA transfer from TSE starts with 2 additional bytes for * IP payload alignment. Status returned by get_rx_status() * contains DMA transfer length. Packet is 2 bytes shorter. */ @@ -1044,7 +1044,7 @@ static void altera_tse_set_mcfilterall(struct net_device *dev) csrwr32(1, priv->mac_dev, tse_csroffs(hash_table) + i * 4); } -/* Set or clear the multicast filter for this adaptor +/* Set or clear the multicast filter for this adapter */ static void tse_set_rx_mode_hashfilter(struct net_device *dev) { @@ -1064,7 +1064,7 @@ static void tse_set_rx_mode_hashfilter(struct net_device *dev) spin_unlock(&priv->mac_cfg_lock); } -/* Set or clear the multicast filter for this adaptor +/* Set or clear the multicast filter for this adapter */ static void tse_set_rx_mode(struct net_device *dev) { diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 53080fd143dc..07444aead3fd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1400,10 +1400,9 @@ static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, void *first_frag) struct sk_buff *skb; if (!first_frag) - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - rx_ring->rx_copybreak); + skb = napi_alloc_skb(rx_ring->napi, rx_ring->rx_copybreak); else - skb = build_skb(first_frag, ENA_PAGE_SIZE); + skb = napi_build_skb(first_frag, ENA_PAGE_SIZE); if (unlikely(!skb)) { ena_increase_stat(&rx_ring->rx_stats.skb_alloc_fail, 1, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index a19dd6797070..447a75ea0cc1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1271,7 +1271,7 @@ struct bnx2x_fw_stats_data { struct per_port_stats port; struct per_pf_stats pf; struct fcoe_statistics_params fcoe; - struct per_queue_stats queue_stats[1]; + struct per_queue_stats queue_stats[]; }; /* Public slow path states */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4f94136a011a..c313221348c5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -233,6 +233,7 @@ static const u16 bnxt_async_events_arr[] = { ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST, ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP, ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT, + ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE, }; static struct workqueue_struct *bnxt_pf_wq; @@ -2079,6 +2080,16 @@ static void bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2) (BNXT_EVENT_RING_TYPE(data2) == \ ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX) +#define BNXT_EVENT_PHC_EVENT_TYPE(data1) \ + (((data1) & ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK) >>\ + ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT) + +#define BNXT_EVENT_PHC_RTC_UPDATE(data1) \ + (((data1) & ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK) >>\ + ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT) + +#define BNXT_PHC_BITS 48 + static int bnxt_async_event_process(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl) { @@ -2258,6 +2269,24 @@ static int bnxt_async_event_process(struct bnxt *bp, bnxt_event_error_report(bp, data1, data2); goto async_event_process_exit; } + case ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE: { + switch (BNXT_EVENT_PHC_EVENT_TYPE(data1)) { + case ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE: + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u64 ns; + + spin_lock_bh(&ptp->ptp_lock); + bnxt_ptp_update_current_time(bp); + ns = (((u64)BNXT_EVENT_PHC_RTC_UPDATE(data1) << + BNXT_PHC_BITS) | ptp->current_time); + bnxt_ptp_rtc_timecounter_init(ptp, ns); + spin_unlock_bh(&ptp->ptp_lock); + } + break; + } + goto async_event_process_exit; + } case ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE: { u16 seq_id = le32_to_cpu(cmpl->event_data2) & 0xffff; @@ -7414,6 +7443,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) struct hwrm_port_mac_ptp_qcfg_output *resp; struct hwrm_port_mac_ptp_qcfg_input *req; struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + bool phc_cfg; u8 flags; int rc; @@ -7456,7 +7486,8 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) rc = -ENODEV; goto exit; } - rc = bnxt_ptp_init(bp); + phc_cfg = (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED) != 0; + rc = bnxt_ptp_init(bp, phc_cfg); if (rc) netdev_warn(bp->dev, "PTP initialization failed.\n"); exit: @@ -7514,6 +7545,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->fw_cap |= BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED)) bp->fw_cap |= BNXT_FW_CAP_PTP_PPS; + if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_PTP_RTC; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT)) bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED)) @@ -10288,6 +10321,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* VF-reps may need to be re-opened after the PF is re-opened */ if (BNXT_PF(bp)) bnxt_vf_reps_open(bp); + bnxt_ptp_init_rtc(bp, true); return 0; open_err_irq: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 440dfeb4948b..4b023e35c765 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1957,6 +1957,7 @@ struct bnxt { #define BNXT_FW_CAP_EXT_STATS_SUPPORTED 0x00040000 #define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000 #define BNXT_FW_CAP_HOT_RESET 0x00200000 + #define BNXT_FW_CAP_PTP_RTC 0x00400000 #define BNXT_FW_CAP_VLAN_RX_STRIP 0x01000000 #define BNXT_FW_CAP_VLAN_TX_INSERT 0x02000000 #define BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED 0x04000000 diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 003330e8cd58..5edbee92f5c4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -11,6 +11,7 @@ #include <linux/ctype.h> #include <linux/stringify.h> #include <linux/ethtool.h> +#include <linux/ethtool_netlink.h> #include <linux/linkmode.h> #include <linux/interrupt.h> #include <linux/pci.h> @@ -802,9 +803,11 @@ static void bnxt_get_ringparam(struct net_device *dev, if (bp->flags & BNXT_FLAG_AGG_RINGS) { ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT_JUM_ENA; ering->rx_jumbo_max_pending = BNXT_MAX_RX_JUM_DESC_CNT; + kernel_ering->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED; } else { ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT; ering->rx_jumbo_max_pending = 0; + kernel_ering->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_DISABLED; } ering->tx_max_pending = BNXT_MAX_TX_DESC_CNT; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index ea86c54247c7..b7100edbd6dd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -369,6 +369,12 @@ struct cmd_nums { #define HWRM_FUNC_PTP_EXT_CFG 0x1a0UL #define HWRM_FUNC_PTP_EXT_QCFG 0x1a1UL #define HWRM_FUNC_KEY_CTX_ALLOC 0x1a2UL + #define HWRM_FUNC_BACKING_STORE_CFG_V2 0x1a3UL + #define HWRM_FUNC_BACKING_STORE_QCFG_V2 0x1a4UL + #define HWRM_FUNC_DBR_PACING_CFG 0x1a5UL + #define HWRM_FUNC_DBR_PACING_QCFG 0x1a6UL + #define HWRM_FUNC_DBR_PACING_BROADCAST_EVENT 0x1a7UL + #define HWRM_FUNC_BACKING_STORE_QCAPS_V2 0x1a8UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -390,6 +396,9 @@ struct cmd_nums { #define HWRM_MFG_PRVSN_IMPORT_CERT 0x212UL #define HWRM_MFG_PRVSN_GET_STATE 0x213UL #define HWRM_MFG_GET_NVM_MEASUREMENT 0x214UL + #define HWRM_MFG_PSOC_QSTATUS 0x215UL + #define HWRM_MFG_SELFTEST_QLIST 0x216UL + #define HWRM_MFG_SELFTEST_EXEC 0x217UL #define HWRM_TF 0x2bcUL #define HWRM_TF_VERSION_GET 0x2bdUL #define HWRM_TF_SESSION_OPEN 0x2c6UL @@ -532,8 +541,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 2 -#define HWRM_VERSION_RSVD 63 -#define HWRM_VERSION_STR "1.10.2.63" +#define HWRM_VERSION_RSVD 73 +#define HWRM_VERSION_STR "1.10.2.73" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -757,10 +766,11 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE 0x40UL #define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE 0x41UL #define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST 0x42UL - #define ASYNC_EVENT_CMPL_EVENT_ID_PHC_MASTER 0x43UL + #define ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE 0x43UL #define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP 0x44UL #define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT 0x45UL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x46UL + #define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_THRESHOLD 0x46UL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x47UL #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 @@ -1112,34 +1122,37 @@ struct hwrm_async_event_cmpl_echo_request { __le32 event_data1; }; -/* hwrm_async_event_cmpl_phc_master (size:128b/16B) */ -struct hwrm_async_event_cmpl_phc_master { +/* hwrm_async_event_cmpl_phc_update (size:128b/16B) */ +struct hwrm_async_event_cmpl_phc_update { __le16 type; - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_MASK 0x3fUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_SFT 0 - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT 0x2eUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_LAST ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT __le16 event_id; - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER 0x43UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE 0x43UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE __le32 event_data2; - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_SFT 0 - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_MASK 0xffff0000UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_SFT 16 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_MASK 0xffff0000UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_SFT 16 u8 opaque_v; - #define ASYNC_EVENT_CMPL_PHC_MASTER_V 0x1UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_MASK 0xfeUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_SFT 1 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_V 0x1UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_SFT 1 u8 timestamp_lo; __le16 timestamp_hi; __le32 event_data1; - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_MASK 0xfUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_SFT 0 - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_MASTER 0x1UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_SECONDARY 0x2UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER 0x3UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK 0xfUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_MASTER 0x1UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_SECONDARY 0x2UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_FAILOVER 0x3UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE 0x4UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK 0xffff0UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT 4 }; /* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */ @@ -1330,6 +1343,30 @@ struct hwrm_async_event_cmpl_error_report_nvm { #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE }; +/* hwrm_async_event_cmpl_error_report_doorbell_drop_threshold (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_report_doorbell_drop_threshold { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT + __le32 event_data2; + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD +}; + /* hwrm_func_reset_input (size:192b/24B) */ struct hwrm_func_reset_input { __le16 req_type; @@ -1589,6 +1626,10 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL 0x800000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED 0x1000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP 0x2000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED 0x4000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_REQUIRED 0x8000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED 0x10000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_DBR_PACING_SUPPORTED 0x20000000UL u8 max_schqs; u8 mpc_chnls_cap; #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE 0x1UL @@ -2455,7 +2496,7 @@ struct hwrm_func_backing_store_qcaps_output { __le16 rkc_entry_size; __le32 tkc_max_entries; __le32 rkc_max_entries; - u8 rsvd[7]; + u8 rsvd1[7]; u8 valid; }; @@ -3164,7 +3205,7 @@ struct hwrm_func_ptp_pin_cfg_output { u8 valid; }; -/* hwrm_func_ptp_cfg_input (size:320b/40B) */ +/* hwrm_func_ptp_cfg_input (size:384b/48B) */ struct hwrm_func_ptp_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -3178,6 +3219,7 @@ struct hwrm_func_ptp_cfg_input { #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD 0x8UL #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP 0x10UL #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE 0x20UL + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME 0x40UL u8 ptp_pps_event; #define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL 0x1UL #define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL 0x2UL @@ -3204,6 +3246,7 @@ struct hwrm_func_ptp_cfg_input { __le32 ptp_freq_adj_ext_up; __le32 ptp_freq_adj_ext_phase_lower; __le32 ptp_freq_adj_ext_phase_upper; + __le64 ptp_set_time; }; /* hwrm_func_ptp_cfg_output (size:128b/16B) */ @@ -3243,6 +3286,308 @@ struct hwrm_func_ptp_ts_query_output { u8 valid; }; +/* hwrm_func_ptp_ext_cfg_input (size:256b/32B) */ +struct hwrm_func_ptp_ext_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 enables; + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_MASTER_FID 0x1UL + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_FID 0x2UL + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_MODE 0x4UL + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_FAILOVER_TIMER 0x8UL + __le16 phc_master_fid; + __le16 phc_sec_fid; + u8 phc_sec_mode; + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_SWITCH 0x0UL + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_ALL 0x1UL + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY 0x2UL + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_LAST FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY + u8 unused_0; + __le32 failover_timer; + u8 unused_1[4]; +}; + +/* hwrm_func_ptp_ext_cfg_output (size:128b/16B) */ +struct hwrm_func_ptp_ext_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_func_ptp_ext_qcfg_input (size:192b/24B) */ +struct hwrm_func_ptp_ext_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 unused_0[8]; +}; + +/* hwrm_func_ptp_ext_qcfg_output (size:256b/32B) */ +struct hwrm_func_ptp_ext_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 phc_master_fid; + __le16 phc_sec_fid; + __le16 phc_active_fid0; + __le16 phc_active_fid1; + __le32 last_failover_event; + __le16 from_fid; + __le16 to_fid; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_func_backing_store_cfg_v2_input (size:448b/56B) */ +struct hwrm_func_backing_store_cfg_v2_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 type; + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID + __le16 instance; + __le32 flags; + #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE 0x1UL + __le64 page_dir; + __le32 num_entries; + __le16 entry_size; + u8 page_size_pbl_level; + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_SFT 0 + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LAST FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2 + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G + u8 subtype_valid_cnt; + __le32 split_entry_0; + __le32 split_entry_1; + __le32 split_entry_2; + __le32 split_entry_3; +}; + +/* hwrm_func_backing_store_cfg_v2_output (size:128b/16B) */ +struct hwrm_func_backing_store_cfg_v2_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 rsvd0[7]; + u8 valid; +}; + +/* hwrm_func_backing_store_qcfg_v2_input (size:192b/24B) */ +struct hwrm_func_backing_store_qcfg_v2_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 type; + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID + __le16 instance; + u8 rsvd[4]; +}; + +/* hwrm_func_backing_store_qcfg_v2_output (size:448b/56B) */ +struct hwrm_func_backing_store_qcfg_v2_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 type; + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID + __le16 instance; + __le32 flags; + __le64 page_dir; + __le32 num_entries; + u8 page_size_pbl_level; + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_MASK 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_SFT 0 + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2 + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_SFT 4 + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G + u8 subtype_valid_cnt; + u8 rsvd[2]; + __le32 split_entry_0; + __le32 split_entry_1; + __le32 split_entry_2; + __le32 split_entry_3; + u8 rsvd2[7]; + u8 valid; +}; + +/* qpc_split_entries (size:128b/16B) */ +struct qpc_split_entries { + __le32 qp_num_l2_entries; + __le32 qp_num_qp1_entries; + __le32 rsvd[2]; +}; + +/* srq_split_entries (size:128b/16B) */ +struct srq_split_entries { + __le32 srq_num_l2_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* cq_split_entries (size:128b/16B) */ +struct cq_split_entries { + __le32 cq_num_l2_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* vnic_split_entries (size:128b/16B) */ +struct vnic_split_entries { + __le32 vnic_num_vnic_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* mrav_split_entries (size:128b/16B) */ +struct mrav_split_entries { + __le32 mrav_num_av_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */ +struct hwrm_func_backing_store_qcaps_v2_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 type; + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID + u8 rsvd[6]; +}; + +/* hwrm_func_backing_store_qcaps_v2_output (size:448b/56B) */ +struct hwrm_func_backing_store_qcaps_v2_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 type; + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID + __le16 entry_size; + __le32 flags; + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID 0x2UL + __le32 instance_bit_map; + u8 ctx_init_value; + u8 ctx_init_offset; + u8 entry_multiple; + u8 rsvd; + __le32 max_num_entries; + __le32 min_num_entries; + __le16 next_valid_type; + u8 subtype_valid_cnt; + u8 rsvd2; + __le32 split_entry_0; + __le32 split_entry_1; + __le32 split_entry_2; + __le32 split_entry_3; + u8 rsvd3[3]; + u8 valid; +}; + /* hwrm_func_drv_if_change_input (size:192b/24B) */ struct hwrm_func_drv_if_change_input { __le16 req_type; @@ -3741,7 +4086,7 @@ struct hwrm_port_phy_qcfg_output { u8 valid; }; -/* hwrm_port_mac_cfg_input (size:384b/48B) */ +/* hwrm_port_mac_cfg_input (size:448b/56B) */ struct hwrm_port_mac_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -3807,7 +4152,8 @@ struct hwrm_port_mac_cfg_input { #define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT 5 u8 unused_0[3]; __le32 ptp_freq_adj_ppb; - __le32 ptp_adj_phase; + u8 unused_1[4]; + __le64 ptp_adj_phase; }; /* hwrm_port_mac_cfg_output (size:128b/16B) */ @@ -3850,6 +4196,7 @@ struct hwrm_port_mac_ptp_qcfg_output { #define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS 0x4UL #define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS 0x8UL #define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK 0x10UL + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED 0x20UL u8 unused_0[3]; __le32 rx_ts_reg_off_lower; __le32 rx_ts_reg_off_upper; @@ -4339,7 +4686,8 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_PORT_CNT_2 0x2UL #define PORT_PHY_QCAPS_RESP_PORT_CNT_3 0x3UL #define PORT_PHY_QCAPS_RESP_PORT_CNT_4 0x4UL - #define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST PORT_PHY_QCAPS_RESP_PORT_CNT_4 + #define PORT_PHY_QCAPS_RESP_PORT_CNT_12 0xcUL + #define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST PORT_PHY_QCAPS_RESP_PORT_CNT_12 __le16 supported_speeds_force_mode; #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB 0x2UL @@ -4399,7 +4747,7 @@ struct hwrm_port_phy_qcaps_output { __le16 flags2; #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL - u8 unused_0[1]; + u8 internal_port_cnt; u8 valid; }; @@ -6221,12 +6569,13 @@ struct hwrm_vnic_rss_cfg_input { __le16 target_id; __le64 resp_addr; __le32 hash_type; - #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 0x1UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 0x2UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 0x4UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 0x8UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 0x10UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6 0x20UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 0x1UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 0x2UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 0x4UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 0x8UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 0x10UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6 0x20UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL 0x40UL __le16 vnic_id; u8 ring_table_pair_index; u8 hash_mode_flags; @@ -7898,6 +8247,7 @@ struct hwrm_cfa_adv_flow_mgnt_qcaps_output { u8 valid; }; +/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */ struct hwrm_tunnel_dst_port_query_input { __le16 req_type; __le16 cmpl_ring; @@ -8909,6 +9259,50 @@ struct hwrm_dbg_qcfg_output { u8 valid; }; +/* hwrm_dbg_crashdump_medium_cfg_input (size:320b/40B) */ +struct hwrm_dbg_crashdump_medium_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 output_dest_flags; + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR 0x1UL + __le16 pg_size_lvl; + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_MASK 0x3UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_SFT 0 + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_0 0x0UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_1 0x1UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2 0x2UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LAST DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2 + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_MASK 0x1cUL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_SFT 2 + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K (0x0UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K (0x1UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K (0x2UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_2M (0x3UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8M (0x4UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G (0x5UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_LAST DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_MASK 0xffe0UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_SFT 5 + __le32 size; + __le32 coredump_component_disable_flags; + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_NVRAM 0x1UL + __le32 unused_0; + __le64 pbl; +}; + +/* hwrm_dbg_crashdump_medium_cfg_output (size:128b/16B) */ +struct hwrm_dbg_crashdump_medium_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_1[7]; + u8 valid; +}; + /* coredump_segment_record (size:128b/16B) */ struct coredump_segment_record { __le16 component_id; @@ -9372,8 +9766,35 @@ struct hwrm_nvm_install_update_output { __le16 resp_len; __le64 installed_items; u8 result; - #define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS 0x0UL - #define NVM_INSTALL_UPDATE_RESP_RESULT_LAST NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS + #define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS 0x0UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_FAILURE 0xffUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_MALLOC_FAILURE 0xfdUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER 0xfbUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER 0xf3UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE 0xf2UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER 0xecUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE 0xebUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM 0xeaUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH 0xe9UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST 0xe8UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER 0xe7UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM 0xe6UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM 0xe5UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH 0xe4UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE 0xe1UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV 0xceUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID 0xcdUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR 0xccUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID 0xcbUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM 0xc5UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM 0xc4UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM 0xc3UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR 0xb9UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR 0xb8UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR 0xb7UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND 0xb0UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED 0xa7UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_LAST NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED u8 problem_item; #define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_NONE 0x0UL #define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE 0xffUL diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 48520967746f..a0b321a19361 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -19,6 +19,20 @@ #include "bnxt_hwrm.h" #include "bnxt_ptp.h" +static int bnxt_ptp_cfg_settime(struct bnxt *bp, u64 time) +{ + struct hwrm_func_ptp_cfg_input *req; + int rc; + + rc = hwrm_req_init(bp, req, HWRM_FUNC_PTP_CFG); + if (rc) + return rc; + + req->enables = cpu_to_le16(FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME); + req->ptp_set_time = cpu_to_le64(time); + return hwrm_req_send(bp, req); +} + int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off) { unsigned int ptp_class; @@ -48,6 +62,9 @@ static int bnxt_ptp_settime(struct ptp_clock_info *ptp_info, ptp_info); u64 ns = timespec64_to_ns(ts); + if (ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC) + return bnxt_ptp_cfg_settime(ptp->bp, ns); + spin_lock_bh(&ptp->ptp_lock); timecounter_init(&ptp->tc, &ptp->cc, ns); spin_unlock_bh(&ptp->ptp_lock); @@ -131,11 +148,47 @@ static int bnxt_ptp_gettimex(struct ptp_clock_info *ptp_info, return 0; } +/* Caller holds ptp_lock */ +void bnxt_ptp_update_current_time(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + bnxt_refclk_read(ptp->bp, NULL, &ptp->current_time); + WRITE_ONCE(ptp->old_time, ptp->current_time); +} + +static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta) +{ + struct hwrm_port_mac_cfg_input *req; + int rc; + + rc = hwrm_req_init(ptp->bp, req, HWRM_PORT_MAC_CFG); + if (rc) + return rc; + + req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE); + req->ptp_adj_phase = cpu_to_le64(delta); + + rc = hwrm_req_send(ptp->bp, req); + if (rc) { + netdev_err(ptp->bp->dev, "ptp adjphc failed. rc = %x\n", rc); + } else { + spin_lock_bh(&ptp->ptp_lock); + bnxt_ptp_update_current_time(ptp->bp); + spin_unlock_bh(&ptp->ptp_lock); + } + + return rc; +} + static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) { struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, ptp_info); + if (ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC) + return bnxt_ptp_adjphc(ptp, delta); + spin_lock_bh(&ptp->ptp_lock); timecounter_adjtime(&ptp->tc, delta); spin_unlock_bh(&ptp->ptp_lock); @@ -714,7 +767,70 @@ static bool bnxt_pps_config_ok(struct bnxt *bp) return !(bp->fw_cap & BNXT_FW_CAP_PTP_PPS) == !ptp->ptp_info.pin_config; } -int bnxt_ptp_init(struct bnxt *bp) +static void bnxt_ptp_timecounter_init(struct bnxt *bp, bool init_tc) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (!ptp->ptp_clock) { + memset(&ptp->cc, 0, sizeof(ptp->cc)); + ptp->cc.read = bnxt_cc_read; + ptp->cc.mask = CYCLECOUNTER_MASK(48); + ptp->cc.shift = 0; + ptp->cc.mult = 1; + ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; + } + if (init_tc) + timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); +} + +/* Caller holds ptp_lock */ +void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns) +{ + timecounter_init(&ptp->tc, &ptp->cc, ns); + /* For RTC, cycle_last must be in sync with the timecounter value. */ + ptp->tc.cycle_last = ns & ptp->cc.mask; +} + +int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg) +{ + struct timespec64 tsp; + u64 ns; + int rc; + + if (!bp->ptp_cfg || !(bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) + return -ENODEV; + + if (!phc_cfg) { + ktime_get_real_ts64(&tsp); + ns = timespec64_to_ns(&tsp); + rc = bnxt_ptp_cfg_settime(bp, ns); + if (rc) + return rc; + } else { + rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME, &ns); + if (rc) + return rc; + } + spin_lock_bh(&bp->ptp_cfg->ptp_lock); + bnxt_ptp_rtc_timecounter_init(bp->ptp_cfg, ns); + spin_unlock_bh(&bp->ptp_cfg->ptp_lock); + + return 0; +} + +static void bnxt_ptp_free(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (ptp->ptp_clock) { + ptp_clock_unregister(ptp->ptp_clock); + ptp->ptp_clock = NULL; + kfree(ptp->ptp_info.pin_config); + ptp->ptp_info.pin_config = NULL; + } +} + +int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; int rc; @@ -726,26 +842,23 @@ int bnxt_ptp_init(struct bnxt *bp) if (rc) return rc; + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + bnxt_ptp_timecounter_init(bp, false); + rc = bnxt_ptp_init_rtc(bp, phc_cfg); + if (rc) + goto out; + } + if (ptp->ptp_clock && bnxt_pps_config_ok(bp)) return 0; - if (ptp->ptp_clock) { - ptp_clock_unregister(ptp->ptp_clock); - ptp->ptp_clock = NULL; - kfree(ptp->ptp_info.pin_config); - ptp->ptp_info.pin_config = NULL; - } + bnxt_ptp_free(bp); + atomic_set(&ptp->tx_avail, BNXT_MAX_TX_TS); spin_lock_init(&ptp->ptp_lock); - memset(&ptp->cc, 0, sizeof(ptp->cc)); - ptp->cc.read = bnxt_cc_read; - ptp->cc.mask = CYCLECOUNTER_MASK(48); - ptp->cc.shift = 0; - ptp->cc.mult = 1; - - ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; - timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); + if (!(bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) + bnxt_ptp_timecounter_init(bp, true); ptp->ptp_info = bnxt_ptp_caps; if ((bp->fw_cap & BNXT_FW_CAP_PTP_PPS)) { @@ -757,8 +870,8 @@ int bnxt_ptp_init(struct bnxt *bp) int err = PTR_ERR(ptp->ptp_clock); ptp->ptp_clock = NULL; - bnxt_unmap_ptp_regs(bp); - return err; + rc = err; + goto out; } if (bp->flags & BNXT_FLAG_CHIP_P5) { spin_lock_bh(&ptp->ptp_lock); @@ -768,6 +881,11 @@ int bnxt_ptp_init(struct bnxt *bp) ptp_schedule_worker(ptp->ptp_clock, 0); } return 0; + +out: + bnxt_ptp_free(bp); + bnxt_unmap_ptp_regs(bp); + return rc; } void bnxt_ptp_clear(struct bnxt *bp) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 7c528e1f8713..373baf45884b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -131,12 +131,15 @@ do { \ #endif int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off); +void bnxt_ptp_update_current_time(struct bnxt *bp); void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2); void bnxt_ptp_reapply_pps(struct bnxt *bp); int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr); int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr); int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb); int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts); -int bnxt_ptp_init(struct bnxt *bp); +void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns); +int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg); +int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg); void bnxt_ptp_clear(struct bnxt *bp); #endif diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 87f1056e29ff..cfe09117fe6c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1368,7 +1368,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) if (!p->eee_enabled) { bcmgenet_eee_enable_set(dev, false); } else { - ret = phy_init_eee(dev->phydev, 0); + ret = phy_init_eee(dev->phydev, false); if (ret) { netif_err(priv, hw, dev, "EEE initialization failed\n"); return ret; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 9ddbee7de72b..f0a7d8396a4a 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -12,6 +12,7 @@ #include <linux/ptp_clock_kernel.h> #include <linux/net_tstamp.h> #include <linux/interrupt.h> +#include <linux/phy/phy.h> #if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP) #define MACB_EXT_DESC @@ -1291,6 +1292,9 @@ struct macb { u32 wol; struct macb_ptp_info *ptp_info; /* macb-ptp interface */ + + struct phy *sgmii_phy; /* for ZynqMP SGMII mode */ + #ifdef MACB_EXT_DESC uint8_t hw_dma_cap; #endif diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 98498a76ae16..4c231159b562 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -34,7 +34,9 @@ #include <linux/udp.h> #include <linux/tcp.h> #include <linux/iopoll.h> +#include <linux/phy/phy.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include "macb.h" /* This structure is only used for MACB on SiFive FU540 devices */ @@ -2739,10 +2741,14 @@ static int macb_open(struct net_device *dev) macb_init_hw(bp); - err = macb_phylink_connect(bp); + err = phy_power_on(bp->sgmii_phy); if (err) goto reset_hw; + err = macb_phylink_connect(bp); + if (err) + goto phy_off; + netif_tx_start_all_queues(dev); if (bp->ptp_info) @@ -2750,6 +2756,9 @@ static int macb_open(struct net_device *dev) return 0; +phy_off: + phy_power_off(bp->sgmii_phy); + reset_hw: macb_reset_hw(bp); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) @@ -2775,6 +2784,8 @@ static int macb_close(struct net_device *dev) phylink_stop(bp->phylink); phylink_disconnect_phy(bp->phylink); + phy_power_off(bp->sgmii_phy); + spin_lock_irqsave(&bp->lock, flags); macb_reset_hw(bp); netif_carrier_off(dev); @@ -4544,13 +4555,55 @@ static const struct macb_config np4_config = { .usrio = &macb_default_usrio, }; +static int zynqmp_init(struct platform_device *pdev) +{ + struct net_device *dev = platform_get_drvdata(pdev); + struct macb *bp = netdev_priv(dev); + int ret; + + if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) { + /* Ensure PS-GTR PHY device used in SGMII mode is ready */ + bp->sgmii_phy = devm_phy_get(&pdev->dev, "sgmii-phy"); + + if (IS_ERR(bp->sgmii_phy)) { + ret = PTR_ERR(bp->sgmii_phy); + dev_err_probe(&pdev->dev, ret, + "failed to get PS-GTR PHY\n"); + return ret; + } + + ret = phy_init(bp->sgmii_phy); + if (ret) { + dev_err(&pdev->dev, "failed to init PS-GTR PHY: %d\n", + ret); + return ret; + } + } + + /* Fully reset GEM controller at hardware level using zynqmp-reset driver, + * if mapped in device tree. + */ + ret = device_reset_optional(&pdev->dev); + if (ret) { + dev_err_probe(&pdev->dev, ret, "failed to reset controller"); + phy_exit(bp->sgmii_phy); + return ret; + } + + ret = macb_init(pdev); + if (ret) + phy_exit(bp->sgmii_phy); + + return ret; +} + static const struct macb_config zynqmp_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH, .dma_burst_length = 16, .clk_init = macb_clk_init, - .init = macb_init, + .init = zynqmp_init, .jumbo_max_len = 10240, .usrio = &macb_default_usrio, }; @@ -4767,7 +4820,7 @@ static int macb_probe(struct platform_device *pdev) err = macb_mii_init(bp); if (err) - goto err_out_free_netdev; + goto err_out_phy_exit; netif_carrier_off(dev); @@ -4792,6 +4845,9 @@ err_out_unregister_mdio: mdiobus_unregister(bp->mii_bus); mdiobus_free(bp->mii_bus); +err_out_phy_exit: + phy_exit(bp->sgmii_phy); + err_out_free_netdev: free_netdev(dev); @@ -4813,6 +4869,7 @@ static int macb_remove(struct platform_device *pdev) if (dev) { bp = netdev_priv(dev); + phy_exit(bp->sgmii_phy); mdiobus_unregister(bp->mii_bus); mdiobus_free(bp->mii_bus); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 574a32f23f96..2f6484dc186a 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1409,7 +1409,8 @@ static acpi_status bgx_acpi_register_phy(acpi_handle handle, struct device *dev = &bgx->pdev->dev; struct acpi_device *adev; - if (acpi_bus_get_device(handle, &adev)) + adev = acpi_fetch_acpi_dev(handle); + if (!adev) goto out; acpi_get_mac_address(dev, adev, bgx->lmac[bgx->acpi_lmac_idx].mac); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index c78b99a497df..8014eb33937c 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2363,11 +2363,13 @@ static void gemini_port_save_mac_addr(struct gemini_ethernet_port *port) static int gemini_ethernet_port_probe(struct platform_device *pdev) { char *port_names[2] = { "ethernet0", "ethernet1" }; + struct device_node *np = pdev->dev.of_node; struct gemini_ethernet_port *port; struct device *dev = &pdev->dev; struct gemini_ethernet *geth; struct net_device *netdev; struct device *parent; + u8 mac[ETH_ALEN]; unsigned int id; int irq; int ret; @@ -2473,6 +2475,12 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) netif_napi_add(netdev, &port->napi, gmac_napi_poll, DEFAULT_NAPI_WEIGHT); + ret = of_get_mac_address(np, mac); + if (!ret) { + dev_info(dev, "Setting macaddr from DT %pM\n", mac); + memcpy(port->mac_addr, mac, ETH_ALEN); + } + if (is_valid_ether_addr((void *)port->mac_addr)) { eth_hw_addr_set(netdev, (u8 *)port->mac_addr); } else { diff --git a/drivers/net/ethernet/davicom/Kconfig b/drivers/net/ethernet/davicom/Kconfig index 7af86b6d4150..02e0caff98e3 100644 --- a/drivers/net/ethernet/davicom/Kconfig +++ b/drivers/net/ethernet/davicom/Kconfig @@ -3,6 +3,19 @@ # Davicom device configuration # +config NET_VENDOR_DAVICOM + bool "Davicom devices" + default y + help + If you have a network (Ethernet) card belonging to this class, say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Davicom devices. If you say Y, you will be asked + for your specific card in the following selections. + +if NET_VENDOR_DAVICOM + config DM9000 tristate "DM9000 support" depends on ARM || MIPS || COLDFIRE || NIOS2 || COMPILE_TEST @@ -22,3 +35,21 @@ config DM9000_FORCE_SIMPLE_PHY_POLL bit to determine if the link is up or down instead of the more costly MII PHY reads. Note, this will not work if the chip is operating with an external PHY. + +config DM9051 + tristate "DM9051 SPI support" + depends on SPI + select CRC32 + select MDIO + select PHYLIB + select REGMAP_SPI + help + Support for DM9051 SPI chipset. + + To compile this driver as a module, choose M here. The module + will be called dm9051. + + The SPI mode for the host's SPI master to access DM9051 is mode + 0 on the SPI bus. + +endif # NET_VENDOR_DAVICOM diff --git a/drivers/net/ethernet/davicom/Makefile b/drivers/net/ethernet/davicom/Makefile index 173c87d21076..225f85bc1f53 100644 --- a/drivers/net/ethernet/davicom/Makefile +++ b/drivers/net/ethernet/davicom/Makefile @@ -4,3 +4,4 @@ # obj-$(CONFIG_DM9000) += dm9000.o +obj-$(CONFIG_DM9051) += dm9051.o diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c new file mode 100644 index 000000000000..6a2bcfbfe891 --- /dev/null +++ b/drivers/net/ethernet/davicom/dm9051.c @@ -0,0 +1,1260 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 Davicom Semiconductor,Inc. + * Davicom DM9051 SPI Fast Ethernet Linux driver + */ + +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/mii.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/phy.h> +#include <linux/regmap.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <linux/spi/spi.h> +#include <linux/types.h> + +#include "dm9051.h" + +#define DRVNAME_9051 "dm9051" + +/** + * struct rx_ctl_mach - rx activities record + * @status_err_counter: rx status error counter + * @large_err_counter: rx get large packet length error counter + * @rx_err_counter: receive packet error counter + * @tx_err_counter: transmit packet error counter + * @fifo_rst_counter: reset operation counter + * + * To keep track for the driver operation statistics + */ +struct rx_ctl_mach { + u16 status_err_counter; + u16 large_err_counter; + u16 rx_err_counter; + u16 tx_err_counter; + u16 fifo_rst_counter; +}; + +/** + * struct dm9051_rxctrl - dm9051 driver rx control + * @hash_table: Multicast hash-table data + * @rcr_all: KS_RXCR1 register setting + * + * The settings needs to control the receive filtering + * such as the multicast hash-filter and the receive register settings + */ +struct dm9051_rxctrl { + u16 hash_table[4]; + u8 rcr_all; +}; + +/** + * struct dm9051_rxhdr - rx packet data header + * @headbyte: lead byte equal to 0x01 notifies a valid packet + * @status: status bits for the received packet + * @rxlen: packet length + * + * The Rx packed, entered into the FIFO memory, start with these + * four bytes which is the Rx header, followed by the ethernet + * packet data and ends with an appended 4-byte CRC data. + * Both Rx packet and CRC data are for check purpose and finally + * are dropped by this driver + */ +struct dm9051_rxhdr { + u8 headbyte; + u8 status; + __le16 rxlen; +}; + +/** + * struct board_info - maintain the saved data + * @spidev: spi device structure + * @ndev: net device structure + * @mdiobus: mii bus structure + * @phydev: phy device structure + * @txq: tx queue structure + * @regmap_dm: regmap for register read/write + * @regmap_dmbulk: extra regmap for bulk read/write + * @rxctrl_work: Work queue for updating RX mode and multicast lists + * @tx_work: Work queue for tx packets + * @pause: ethtool pause parameter structure + * @spi_lockm: between threads lock structure + * @reg_mutex: regmap access lock structure + * @bc: rx control statistics structure + * @rxhdr: rx header structure + * @rctl: rx control setting structure + * @msg_enable: message level value + * @imr_all: to store operating imr value for register DM9051_IMR + * @lcr_all: to store operating rcr value for register DM9051_LMCR + * + * The saved data variables, keep up to date for retrieval back to use + */ +struct board_info { + u32 msg_enable; + struct spi_device *spidev; + struct net_device *ndev; + struct mii_bus *mdiobus; + struct phy_device *phydev; + struct sk_buff_head txq; + struct regmap *regmap_dm; + struct regmap *regmap_dmbulk; + struct work_struct rxctrl_work; + struct work_struct tx_work; + struct ethtool_pauseparam pause; + struct mutex spi_lockm; + struct mutex reg_mutex; + struct rx_ctl_mach bc; + struct dm9051_rxhdr rxhdr; + struct dm9051_rxctrl rctl; + u8 imr_all; + u8 lcr_all; +}; + +static int dm9051_set_reg(struct board_info *db, unsigned int reg, unsigned int val) +{ + int ret; + + ret = regmap_write(db->regmap_dm, reg, val); + if (ret < 0) + netif_err(db, drv, db->ndev, "%s: error %d set reg %02x\n", + __func__, ret, reg); + return ret; +} + +static int dm9051_update_bits(struct board_info *db, unsigned int reg, unsigned int mask, + unsigned int val) +{ + int ret; + + ret = regmap_update_bits(db->regmap_dm, reg, mask, val); + if (ret < 0) + netif_err(db, drv, db->ndev, "%s: error %d update bits reg %02x\n", + __func__, ret, reg); + return ret; +} + +/* skb buffer exhausted, just discard the received data + */ +static int dm9051_dumpblk(struct board_info *db, u8 reg, size_t count) +{ + struct net_device *ndev = db->ndev; + unsigned int rb; + int ret; + + /* no skb buffer, + * both reg and &rb must be noinc, + * read once one byte via regmap_read + */ + do { + ret = regmap_read(db->regmap_dm, reg, &rb); + if (ret < 0) { + netif_err(db, drv, ndev, "%s: error %d dumping read reg %02x\n", + __func__, ret, reg); + break; + } + } while (--count); + + return ret; +} + +static int dm9051_set_regs(struct board_info *db, unsigned int reg, const void *val, + size_t val_count) +{ + int ret; + + ret = regmap_bulk_write(db->regmap_dmbulk, reg, val, val_count); + if (ret < 0) + netif_err(db, drv, db->ndev, "%s: error %d bulk writing regs %02x\n", + __func__, ret, reg); + return ret; +} + +static int dm9051_get_regs(struct board_info *db, unsigned int reg, void *val, + size_t val_count) +{ + int ret; + + ret = regmap_bulk_read(db->regmap_dmbulk, reg, val, val_count); + if (ret < 0) + netif_err(db, drv, db->ndev, "%s: error %d bulk reading regs %02x\n", + __func__, ret, reg); + return ret; +} + +static int dm9051_write_mem(struct board_info *db, unsigned int reg, const void *buff, + size_t len) +{ + int ret; + + ret = regmap_noinc_write(db->regmap_dm, reg, buff, len); + if (ret < 0) + netif_err(db, drv, db->ndev, "%s: error %d noinc writing regs %02x\n", + __func__, ret, reg); + return ret; +} + +static int dm9051_read_mem(struct board_info *db, unsigned int reg, void *buff, + size_t len) +{ + int ret; + + ret = regmap_noinc_read(db->regmap_dm, reg, buff, len); + if (ret < 0) + netif_err(db, drv, db->ndev, "%s: error %d noinc reading regs %02x\n", + __func__, ret, reg); + return ret; +} + +/* waiting tx-end rather than tx-req + * got faster + */ +static int dm9051_nsr_poll(struct board_info *db) +{ + unsigned int mval; + int ret; + + ret = regmap_read_poll_timeout(db->regmap_dm, DM9051_NSR, mval, + mval & (NSR_TX2END | NSR_TX1END), 1, 20); + if (ret == -ETIMEDOUT) + netdev_err(db->ndev, "timeout in checking for tx end\n"); + return ret; +} + +static int dm9051_epcr_poll(struct board_info *db) +{ + unsigned int mval; + int ret; + + ret = regmap_read_poll_timeout(db->regmap_dm, DM9051_EPCR, mval, + !(mval & EPCR_ERRE), 100, 10000); + if (ret == -ETIMEDOUT) + netdev_err(db->ndev, "eeprom/phy in processing get timeout\n"); + return ret; +} + +static int dm9051_irq_flag(struct board_info *db) +{ + struct spi_device *spi = db->spidev; + int irq_type = irq_get_trigger_type(spi->irq); + + if (irq_type) + return irq_type; + + return IRQF_TRIGGER_LOW; +} + +static unsigned int dm9051_intcr_value(struct board_info *db) +{ + return (dm9051_irq_flag(db) == IRQF_TRIGGER_LOW) ? + INTCR_POL_LOW : INTCR_POL_HIGH; +} + +static int dm9051_set_fcr(struct board_info *db) +{ + u8 fcr = 0; + + if (db->pause.rx_pause) + fcr |= FCR_BKPM | FCR_FLCE; + if (db->pause.tx_pause) + fcr |= FCR_TXPEN; + + return dm9051_set_reg(db, DM9051_FCR, fcr); +} + +static int dm9051_set_recv(struct board_info *db) +{ + int ret; + + ret = dm9051_set_regs(db, DM9051_MAR, db->rctl.hash_table, sizeof(db->rctl.hash_table)); + if (ret) + return ret; + + return dm9051_set_reg(db, DM9051_RCR, db->rctl.rcr_all); /* enable rx */ +} + +static int dm9051_core_reset(struct board_info *db) +{ + int ret; + + db->bc.fifo_rst_counter++; + + ret = regmap_write(db->regmap_dm, DM9051_NCR, NCR_RST); /* NCR reset */ + if (ret) + return ret; + ret = regmap_write(db->regmap_dm, DM9051_MBNDRY, MBNDRY_BYTE); /* MemBound */ + if (ret) + return ret; + ret = regmap_write(db->regmap_dm, DM9051_PPCR, PPCR_PAUSE_COUNT); /* Pause Count */ + if (ret) + return ret; + ret = regmap_write(db->regmap_dm, DM9051_LMCR, db->lcr_all); /* LEDMode1 */ + if (ret) + return ret; + + return dm9051_set_reg(db, DM9051_INTCR, dm9051_intcr_value(db)); +} + +static int dm9051_update_fcr(struct board_info *db) +{ + u8 fcr = 0; + + if (db->pause.rx_pause) + fcr |= FCR_BKPM | FCR_FLCE; + if (db->pause.tx_pause) + fcr |= FCR_TXPEN; + + return dm9051_update_bits(db, DM9051_FCR, FCR_RXTX_BITS, fcr); +} + +static int dm9051_disable_interrupt(struct board_info *db) +{ + return dm9051_set_reg(db, DM9051_IMR, IMR_PAR); /* disable int */ +} + +static int dm9051_enable_interrupt(struct board_info *db) +{ + return dm9051_set_reg(db, DM9051_IMR, db->imr_all); /* enable int */ +} + +static int dm9051_stop_mrcmd(struct board_info *db) +{ + return dm9051_set_reg(db, DM9051_ISR, ISR_STOP_MRCMD); /* to stop mrcmd */ +} + +static int dm9051_clear_interrupt(struct board_info *db) +{ + return dm9051_update_bits(db, DM9051_ISR, ISR_CLR_INT, ISR_CLR_INT); +} + +static int dm9051_eeprom_read(struct board_info *db, int offset, u8 *to) +{ + int ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPAR, offset); + if (ret) + return ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPCR, EPCR_ERPRR); + if (ret) + return ret; + + ret = dm9051_epcr_poll(db); + if (ret) + return ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPCR, 0); + if (ret) + return ret; + + return regmap_bulk_read(db->regmap_dmbulk, DM9051_EPDRL, to, 2); +} + +static int dm9051_eeprom_write(struct board_info *db, int offset, u8 *data) +{ + int ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPAR, offset); + if (ret) + return ret; + + ret = regmap_bulk_write(db->regmap_dmbulk, DM9051_EPDRL, data, 2); + if (ret < 0) + return ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPCR, EPCR_WEP | EPCR_ERPRW); + if (ret) + return ret; + + ret = dm9051_epcr_poll(db); + if (ret) + return ret; + + return regmap_write(db->regmap_dm, DM9051_EPCR, 0); +} + +static int dm9051_phyread(void *context, unsigned int reg, unsigned int *val) +{ + struct board_info *db = context; + int ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPAR, DM9051_PHY | reg); + if (ret) + return ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPCR, EPCR_ERPRR | EPCR_EPOS); + if (ret) + return ret; + + ret = dm9051_epcr_poll(db); + if (ret) + return ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPCR, 0); + if (ret) + return ret; + + /* this is a 4 bytes data, clear to zero since following regmap_bulk_read + * only fill lower 2 bytes + */ + *val = 0; + return regmap_bulk_read(db->regmap_dmbulk, DM9051_EPDRL, val, 2); +} + +static int dm9051_phywrite(void *context, unsigned int reg, unsigned int val) +{ + struct board_info *db = context; + int ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPAR, DM9051_PHY | reg); + if (ret) + return ret; + + ret = regmap_bulk_write(db->regmap_dmbulk, DM9051_EPDRL, &val, 2); + if (ret < 0) + return ret; + + ret = regmap_write(db->regmap_dm, DM9051_EPCR, EPCR_EPOS | EPCR_ERPRW); + if (ret) + return ret; + + ret = dm9051_epcr_poll(db); + if (ret) + return ret; + + return regmap_write(db->regmap_dm, DM9051_EPCR, 0); +} + +static int dm9051_mdio_read(struct mii_bus *bus, int addr, int regnum) +{ + struct board_info *db = bus->priv; + unsigned int val = 0xffff; + int ret; + + if (addr == DM9051_PHY_ADDR) { + ret = dm9051_phyread(db, regnum, &val); + if (ret) + return ret; + } + + return val; +} + +static int dm9051_mdio_write(struct mii_bus *bus, int addr, int regnum, u16 val) +{ + struct board_info *db = bus->priv; + + if (addr == DM9051_PHY_ADDR) + return dm9051_phywrite(db, regnum, val); + + return -ENODEV; +} + +static void dm9051_reg_lock_mutex(void *dbcontext) +{ + struct board_info *db = dbcontext; + + mutex_lock(&db->reg_mutex); +} + +static void dm9051_reg_unlock_mutex(void *dbcontext) +{ + struct board_info *db = dbcontext; + + mutex_unlock(&db->reg_mutex); +} + +static struct regmap_config regconfigdm = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0xff, + .reg_stride = 1, + .cache_type = REGCACHE_NONE, + .read_flag_mask = 0, + .write_flag_mask = DM_SPI_WR, + .val_format_endian = REGMAP_ENDIAN_LITTLE, + .lock = dm9051_reg_lock_mutex, + .unlock = dm9051_reg_unlock_mutex, +}; + +static struct regmap_config regconfigdmbulk = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0xff, + .reg_stride = 1, + .cache_type = REGCACHE_NONE, + .read_flag_mask = 0, + .write_flag_mask = DM_SPI_WR, + .val_format_endian = REGMAP_ENDIAN_LITTLE, + .lock = dm9051_reg_lock_mutex, + .unlock = dm9051_reg_unlock_mutex, + .use_single_read = true, + .use_single_write = true, +}; + +static int dm9051_map_init(struct spi_device *spi, struct board_info *db) +{ + /* create two regmap instances, + * split read/write and bulk_read/bulk_write to individual regmap + * to resolve regmap execution confliction problem + */ + regconfigdm.lock_arg = db; + db->regmap_dm = devm_regmap_init_spi(db->spidev, ®configdm); + if (IS_ERR(db->regmap_dm)) + return PTR_ERR(db->regmap_dm); + + regconfigdmbulk.lock_arg = db; + db->regmap_dmbulk = devm_regmap_init_spi(db->spidev, ®configdmbulk); + if (IS_ERR(db->regmap_dmbulk)) + return PTR_ERR(db->regmap_dmbulk); + + return 0; +} + +static int dm9051_map_chipid(struct board_info *db) +{ + struct device *dev = &db->spidev->dev; + unsigned short wid; + u8 buff[6]; + int ret; + + ret = dm9051_get_regs(db, DM9051_VIDL, buff, sizeof(buff)); + if (ret < 0) + return ret; + + wid = get_unaligned_le16(buff + 2); + if (wid != DM9051_ID) { + dev_err(dev, "chipid error as %04x !\n", wid); + return -ENODEV; + } + + dev_info(dev, "chip %04x found\n", wid); + return 0; +} + +/* Read DM9051_PAR registers which is the mac address loaded from EEPROM while power-on + */ +static int dm9051_map_etherdev_par(struct net_device *ndev, struct board_info *db) +{ + u8 addr[ETH_ALEN]; + int ret; + + ret = dm9051_get_regs(db, DM9051_PAR, addr, sizeof(addr)); + if (ret < 0) + return ret; + + if (!is_valid_ether_addr(addr)) { + eth_hw_addr_random(ndev); + + ret = dm9051_set_regs(db, DM9051_PAR, ndev->dev_addr, sizeof(ndev->dev_addr)); + if (ret < 0) + return ret; + + dev_dbg(&db->spidev->dev, "Use random MAC address\n"); + return 0; + } + + eth_hw_addr_set(ndev, addr); + return 0; +} + +/* ethtool-ops + */ +static void dm9051_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) +{ + strscpy(info->driver, DRVNAME_9051, sizeof(info->driver)); +} + +static void dm9051_set_msglevel(struct net_device *ndev, u32 value) +{ + struct board_info *db = to_dm9051_board(ndev); + + db->msg_enable = value; +} + +static u32 dm9051_get_msglevel(struct net_device *ndev) +{ + struct board_info *db = to_dm9051_board(ndev); + + return db->msg_enable; +} + +static int dm9051_get_eeprom_len(struct net_device *dev) +{ + return 128; +} + +static int dm9051_get_eeprom(struct net_device *ndev, + struct ethtool_eeprom *ee, u8 *data) +{ + struct board_info *db = to_dm9051_board(ndev); + int offset = ee->offset; + int len = ee->len; + int i, ret; + + if ((len | offset) & 1) + return -EINVAL; + + ee->magic = DM_EEPROM_MAGIC; + + for (i = 0; i < len; i += 2) { + ret = dm9051_eeprom_read(db, (offset + i) / 2, data + i); + if (ret) + break; + } + return ret; +} + +static int dm9051_set_eeprom(struct net_device *ndev, + struct ethtool_eeprom *ee, u8 *data) +{ + struct board_info *db = to_dm9051_board(ndev); + int offset = ee->offset; + int len = ee->len; + int i, ret; + + if ((len | offset) & 1) + return -EINVAL; + + if (ee->magic != DM_EEPROM_MAGIC) + return -EINVAL; + + for (i = 0; i < len; i += 2) { + ret = dm9051_eeprom_write(db, (offset + i) / 2, data + i); + if (ret) + break; + } + return ret; +} + +static void dm9051_get_pauseparam(struct net_device *ndev, + struct ethtool_pauseparam *pause) +{ + struct board_info *db = to_dm9051_board(ndev); + + *pause = db->pause; +} + +static int dm9051_set_pauseparam(struct net_device *ndev, + struct ethtool_pauseparam *pause) +{ + struct board_info *db = to_dm9051_board(ndev); + + db->pause = *pause; + + if (pause->autoneg == AUTONEG_DISABLE) + return dm9051_update_fcr(db); + + phy_set_sym_pause(db->phydev, pause->rx_pause, pause->tx_pause, + pause->autoneg); + phy_start_aneg(db->phydev); + return 0; +} + +static const struct ethtool_ops dm9051_ethtool_ops = { + .get_drvinfo = dm9051_get_drvinfo, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, + .get_msglevel = dm9051_get_msglevel, + .set_msglevel = dm9051_set_msglevel, + .nway_reset = phy_ethtool_nway_reset, + .get_link = ethtool_op_get_link, + .get_eeprom_len = dm9051_get_eeprom_len, + .get_eeprom = dm9051_get_eeprom, + .set_eeprom = dm9051_set_eeprom, + .get_pauseparam = dm9051_get_pauseparam, + .set_pauseparam = dm9051_set_pauseparam, +}; + +static int dm9051_all_start(struct board_info *db) +{ + int ret; + + /* GPR power on of the internal phy + */ + ret = dm9051_set_reg(db, DM9051_GPR, 0); + if (ret) + return ret; + + /* dm9051 chip registers could not be accessed within 1 ms + * after GPR power on, delay 1 ms is essential + */ + msleep(1); + + ret = dm9051_core_reset(db); + if (ret) + return ret; + + return dm9051_enable_interrupt(db); +} + +static int dm9051_all_stop(struct board_info *db) +{ + int ret; + + /* GPR power off of the internal phy, + * The internal phy still could be accessed after this GPR power off control + */ + ret = dm9051_set_reg(db, DM9051_GPR, GPR_PHY_OFF); + if (ret) + return ret; + + return dm9051_set_reg(db, DM9051_RCR, RCR_RX_DISABLE); +} + +/* fifo reset while rx error found + */ +static int dm9051_all_restart(struct board_info *db) +{ + struct net_device *ndev = db->ndev; + int ret; + + ret = dm9051_core_reset(db); + if (ret) + return ret; + + ret = dm9051_enable_interrupt(db); + if (ret) + return ret; + + netdev_dbg(ndev, " rxstatus_Er & rxlen_Er %d, RST_c %d\n", + db->bc.status_err_counter + db->bc.large_err_counter, + db->bc.fifo_rst_counter); + + ret = dm9051_set_recv(db); + if (ret) + return ret; + + return dm9051_set_fcr(db); +} + +/* read packets from the fifo memory + * return value, + * > 0 - read packet number, caller can repeat the rx operation + * 0 - no error, caller need stop further rx operation + * -EBUSY - read data error, caller escape from rx operation + */ +static int dm9051_loop_rx(struct board_info *db) +{ + struct net_device *ndev = db->ndev; + unsigned int rxbyte; + int ret, rxlen; + struct sk_buff *skb; + u8 *rdptr; + int scanrr = 0; + + do { + ret = dm9051_read_mem(db, DM_SPI_MRCMDX, &rxbyte, 2); + if (ret) + return ret; + + if ((rxbyte & GENMASK(7, 0)) != DM9051_PKT_RDY) + break; /* exhaust-empty */ + + ret = dm9051_read_mem(db, DM_SPI_MRCMD, &db->rxhdr, DM_RXHDR_SIZE); + if (ret) + return ret; + + ret = dm9051_stop_mrcmd(db); + if (ret) + return ret; + + rxlen = le16_to_cpu(db->rxhdr.rxlen); + if (db->rxhdr.status & RSR_ERR_BITS || rxlen > DM9051_PKT_MAX) { + netdev_dbg(ndev, "rxhdr-byte (%02x)\n", + db->rxhdr.headbyte); + + if (db->rxhdr.status & RSR_ERR_BITS) { + db->bc.status_err_counter++; + netdev_dbg(ndev, "check rxstatus-error (%02x)\n", + db->rxhdr.status); + } else { + db->bc.large_err_counter++; + netdev_dbg(ndev, "check rxlen large-error (%d > %d)\n", + rxlen, DM9051_PKT_MAX); + } + return dm9051_all_restart(db); + } + + skb = dev_alloc_skb(rxlen); + if (!skb) { + ret = dm9051_dumpblk(db, DM_SPI_MRCMD, rxlen); + if (ret) + return ret; + return scanrr; + } + + rdptr = skb_put(skb, rxlen - 4); + ret = dm9051_read_mem(db, DM_SPI_MRCMD, rdptr, rxlen); + if (ret) { + db->bc.rx_err_counter++; + dev_kfree_skb(skb); + return ret; + } + + ret = dm9051_stop_mrcmd(db); + if (ret) + return ret; + + skb->protocol = eth_type_trans(skb, db->ndev); + if (db->ndev->features & NETIF_F_RXCSUM) + skb_checksum_none_assert(skb); + netif_rx_ni(skb); + db->ndev->stats.rx_bytes += rxlen; + db->ndev->stats.rx_packets++; + scanrr++; + } while (!ret); + + return scanrr; +} + +/* transmit a packet, + * return value, + * 0 - succeed + * -ETIMEDOUT - timeout error + */ +static int dm9051_single_tx(struct board_info *db, u8 *buff, unsigned int len) +{ + int ret; + + ret = dm9051_nsr_poll(db); + if (ret) + return ret; + + ret = dm9051_write_mem(db, DM_SPI_MWCMD, buff, len); + if (ret) + return ret; + + ret = dm9051_set_regs(db, DM9051_TXPLL, &len, 2); + if (ret < 0) + return ret; + + return dm9051_set_reg(db, DM9051_TCR, TCR_TXREQ); +} + +static int dm9051_loop_tx(struct board_info *db) +{ + struct net_device *ndev = db->ndev; + int ntx = 0; + int ret; + + while (!skb_queue_empty(&db->txq)) { + struct sk_buff *skb; + + skb = skb_dequeue(&db->txq); + if (skb) { + ntx++; + ret = dm9051_single_tx(db, skb->data, skb->len); + dev_kfree_skb(skb); + if (ret < 0) { + db->bc.tx_err_counter++; + return 0; + } + ndev->stats.tx_bytes += skb->len; + ndev->stats.tx_packets++; + } + + if (netif_queue_stopped(ndev) && + (skb_queue_len(&db->txq) < DM9051_TX_QUE_LO_WATER)) + netif_wake_queue(ndev); + } + + return ntx; +} + +static irqreturn_t dm9051_rx_threaded_irq(int irq, void *pw) +{ + struct board_info *db = pw; + int result, result_tx; + + mutex_lock(&db->spi_lockm); + + result = dm9051_disable_interrupt(db); + if (result) + goto out_unlock; + + result = dm9051_clear_interrupt(db); + if (result) + goto out_unlock; + + do { + result = dm9051_loop_rx(db); /* threaded irq rx */ + if (result < 0) + goto out_unlock; + result_tx = dm9051_loop_tx(db); /* more tx better performance */ + if (result_tx < 0) + goto out_unlock; + } while (result > 0); + + dm9051_enable_interrupt(db); + + /* To exit and has mutex unlock while rx or tx error + */ +out_unlock: + mutex_unlock(&db->spi_lockm); + + return IRQ_HANDLED; +} + +static void dm9051_tx_delay(struct work_struct *work) +{ + struct board_info *db = container_of(work, struct board_info, tx_work); + int result; + + mutex_lock(&db->spi_lockm); + + result = dm9051_loop_tx(db); + if (result < 0) + netdev_err(db->ndev, "transmit packet error\n"); + + mutex_unlock(&db->spi_lockm); +} + +static void dm9051_rxctl_delay(struct work_struct *work) +{ + struct board_info *db = container_of(work, struct board_info, rxctrl_work); + struct net_device *ndev = db->ndev; + int result; + + mutex_lock(&db->spi_lockm); + + result = dm9051_set_regs(db, DM9051_PAR, ndev->dev_addr, sizeof(ndev->dev_addr)); + if (result < 0) + goto out_unlock; + + dm9051_set_recv(db); + + /* To has mutex unlock and return from this function if regmap function fail + */ +out_unlock: + mutex_unlock(&db->spi_lockm); +} + +/* Open network device + * Called when the network device is marked active, such as a user executing + * 'ifconfig up' on the device + */ +static int dm9051_open(struct net_device *ndev) +{ + struct board_info *db = to_dm9051_board(ndev); + struct spi_device *spi = db->spidev; + int ret; + + db->imr_all = IMR_PAR | IMR_PRM; + db->lcr_all = LMCR_MODE1; + db->rctl.rcr_all = RCR_DIS_LONG | RCR_DIS_CRC | RCR_RXEN; + memset(db->rctl.hash_table, 0, sizeof(db->rctl.hash_table)); + + ndev->irq = spi->irq; /* by dts */ + ret = request_threaded_irq(spi->irq, NULL, dm9051_rx_threaded_irq, + dm9051_irq_flag(db) | IRQF_ONESHOT, + ndev->name, db); + if (ret < 0) { + netdev_err(ndev, "failed to get irq\n"); + return ret; + } + + phy_support_sym_pause(db->phydev); + phy_start(db->phydev); + + /* flow control parameters init */ + db->pause.rx_pause = true; + db->pause.tx_pause = true; + db->pause.autoneg = AUTONEG_DISABLE; + + if (db->phydev->autoneg) + db->pause.autoneg = AUTONEG_ENABLE; + + ret = dm9051_all_start(db); + if (ret) { + phy_stop(db->phydev); + free_irq(spi->irq, db); + return ret; + } + + netif_wake_queue(ndev); + + return 0; +} + +/* Close network device + * Called to close down a network device which has been active. Cancel any + * work, shutdown the RX and TX process and then place the chip into a low + * power state while it is not being used + */ +static int dm9051_stop(struct net_device *ndev) +{ + struct board_info *db = to_dm9051_board(ndev); + int ret; + + ret = dm9051_all_stop(db); + if (ret) + return ret; + + flush_work(&db->tx_work); + flush_work(&db->rxctrl_work); + + phy_stop(db->phydev); + + free_irq(db->spidev->irq, db); + + netif_stop_queue(ndev); + + skb_queue_purge(&db->txq); + + return 0; +} + +/* event: play a schedule starter in condition + */ +static netdev_tx_t dm9051_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct board_info *db = to_dm9051_board(ndev); + + skb_queue_tail(&db->txq, skb); + if (skb_queue_len(&db->txq) > DM9051_TX_QUE_HI_WATER) + netif_stop_queue(ndev); /* enforce limit queue size */ + + schedule_work(&db->tx_work); + + return NETDEV_TX_OK; +} + +/* event: play with a schedule starter + */ +static void dm9051_set_rx_mode(struct net_device *ndev) +{ + struct board_info *db = to_dm9051_board(ndev); + struct dm9051_rxctrl rxctrl; + struct netdev_hw_addr *ha; + u8 rcr = RCR_DIS_LONG | RCR_DIS_CRC | RCR_RXEN; + u32 hash_val; + + memset(&rxctrl, 0, sizeof(rxctrl)); + + /* rx control */ + if (ndev->flags & IFF_PROMISC) { + rcr |= RCR_PRMSC; + netdev_dbg(ndev, "set_multicast rcr |= RCR_PRMSC, rcr= %02x\n", rcr); + } + + if (ndev->flags & IFF_ALLMULTI) { + rcr |= RCR_ALL; + netdev_dbg(ndev, "set_multicast rcr |= RCR_ALLMULTI, rcr= %02x\n", rcr); + } + + rxctrl.rcr_all = rcr; + + /* broadcast address */ + rxctrl.hash_table[0] = 0; + rxctrl.hash_table[1] = 0; + rxctrl.hash_table[2] = 0; + rxctrl.hash_table[3] = 0x8000; + + /* the multicast address in Hash Table : 64 bits */ + netdev_for_each_mc_addr(ha, ndev) { + hash_val = ether_crc_le(ETH_ALEN, ha->addr) & GENMASK(5, 0); + rxctrl.hash_table[hash_val / 16] |= BIT(0) << (hash_val % 16); + } + + /* schedule work to do the actual set of the data if needed */ + + if (memcmp(&db->rctl, &rxctrl, sizeof(rxctrl))) { + memcpy(&db->rctl, &rxctrl, sizeof(rxctrl)); + schedule_work(&db->rxctrl_work); + } +} + +/* event: write into the mac registers and eeprom directly + */ +static int dm9051_set_mac_address(struct net_device *ndev, void *p) +{ + struct board_info *db = to_dm9051_board(ndev); + int ret; + + ret = eth_prepare_mac_addr_change(ndev, p); + if (ret < 0) + return ret; + + eth_commit_mac_addr_change(ndev, p); + return dm9051_set_regs(db, DM9051_PAR, ndev->dev_addr, sizeof(ndev->dev_addr)); +} + +static const struct net_device_ops dm9051_netdev_ops = { + .ndo_open = dm9051_open, + .ndo_stop = dm9051_stop, + .ndo_start_xmit = dm9051_start_xmit, + .ndo_set_rx_mode = dm9051_set_rx_mode, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = dm9051_set_mac_address, +}; + +static void dm9051_operation_clear(struct board_info *db) +{ + db->bc.status_err_counter = 0; + db->bc.large_err_counter = 0; + db->bc.rx_err_counter = 0; + db->bc.tx_err_counter = 0; + db->bc.fifo_rst_counter = 0; +} + +static int dm9051_mdio_register(struct board_info *db) +{ + struct spi_device *spi = db->spidev; + int ret; + + db->mdiobus = devm_mdiobus_alloc(&spi->dev); + if (!db->mdiobus) + return -ENOMEM; + + db->mdiobus->priv = db; + db->mdiobus->read = dm9051_mdio_read; + db->mdiobus->write = dm9051_mdio_write; + db->mdiobus->name = "dm9051-mdiobus"; + db->mdiobus->phy_mask = (u32)~BIT(1); + db->mdiobus->parent = &spi->dev; + snprintf(db->mdiobus->id, MII_BUS_ID_SIZE, + "dm9051-%s.%u", dev_name(&spi->dev), spi->chip_select); + + ret = devm_mdiobus_register(&spi->dev, db->mdiobus); + if (ret) + dev_err(&spi->dev, "Could not register MDIO bus\n"); + + return ret; +} + +static void dm9051_handle_link_change(struct net_device *ndev) +{ + struct board_info *db = to_dm9051_board(ndev); + + phy_print_status(db->phydev); + + /* only write pause settings to mac. since mac and phy are integrated + * together, such as link state, speed and duplex are sync already + */ + if (db->phydev->link) { + if (db->phydev->pause) { + db->pause.rx_pause = true; + db->pause.tx_pause = true; + } + dm9051_update_fcr(db); + } +} + +/* phy connect as poll mode + */ +static int dm9051_phy_connect(struct board_info *db) +{ + char phy_id[MII_BUS_ID_SIZE + 3]; + + snprintf(phy_id, sizeof(phy_id), PHY_ID_FMT, + db->mdiobus->id, DM9051_PHY_ADDR); + + db->phydev = phy_connect(db->ndev, phy_id, dm9051_handle_link_change, + PHY_INTERFACE_MODE_MII); + if (IS_ERR(db->phydev)) + return PTR_ERR_OR_ZERO(db->phydev); + return 0; +} + +static int dm9051_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct net_device *ndev; + struct board_info *db; + int ret; + + ndev = devm_alloc_etherdev(dev, sizeof(struct board_info)); + if (!ndev) + return -ENOMEM; + + SET_NETDEV_DEV(ndev, dev); + dev_set_drvdata(dev, ndev); + + db = netdev_priv(ndev); + + db->msg_enable = 0; + db->spidev = spi; + db->ndev = ndev; + + ndev->netdev_ops = &dm9051_netdev_ops; + ndev->ethtool_ops = &dm9051_ethtool_ops; + + mutex_init(&db->spi_lockm); + mutex_init(&db->reg_mutex); + + INIT_WORK(&db->rxctrl_work, dm9051_rxctl_delay); + INIT_WORK(&db->tx_work, dm9051_tx_delay); + + ret = dm9051_map_init(spi, db); + if (ret) + return ret; + + ret = dm9051_map_chipid(db); + if (ret) + return ret; + + ret = dm9051_map_etherdev_par(ndev, db); + if (ret < 0) + return ret; + + ret = dm9051_mdio_register(db); + if (ret) + return ret; + + ret = dm9051_phy_connect(db); + if (ret) + return ret; + + dm9051_operation_clear(db); + skb_queue_head_init(&db->txq); + + ret = devm_register_netdev(dev, ndev); + if (ret) { + phy_disconnect(db->phydev); + return dev_err_probe(dev, ret, "device register failed"); + } + + return 0; +} + +static int dm9051_drv_remove(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct net_device *ndev = dev_get_drvdata(dev); + struct board_info *db = to_dm9051_board(ndev); + + phy_disconnect(db->phydev); + + return 0; +} + +static const struct of_device_id dm9051_match_table[] = { + { .compatible = "davicom,dm9051" }, + {} +}; + +static const struct spi_device_id dm9051_id_table[] = { + { "dm9051", 0 }, + {} +}; + +static struct spi_driver dm9051_driver = { + .driver = { + .name = DRVNAME_9051, + .of_match_table = dm9051_match_table, + }, + .probe = dm9051_probe, + .remove = dm9051_drv_remove, + .id_table = dm9051_id_table, +}; +module_spi_driver(dm9051_driver); + +MODULE_AUTHOR("Joseph CHANG <joseph_chang@davicom.com.tw>"); +MODULE_DESCRIPTION("Davicom DM9051 network SPI driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/davicom/dm9051.h b/drivers/net/ethernet/davicom/dm9051.h new file mode 100644 index 000000000000..fef3120edd7c --- /dev/null +++ b/drivers/net/ethernet/davicom/dm9051.h @@ -0,0 +1,162 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 Davicom Semiconductor,Inc. + * Davicom DM9051 SPI Fast Ethernet Linux driver + */ + +#ifndef _DM9051_H_ +#define _DM9051_H_ + +#include <linux/bits.h> +#include <linux/netdevice.h> +#include <linux/types.h> + +#define DM9051_ID 0x9051 + +#define DM9051_NCR 0x00 +#define DM9051_NSR 0x01 +#define DM9051_TCR 0x02 +#define DM9051_RCR 0x05 +#define DM9051_BPTR 0x08 +#define DM9051_FCR 0x0A +#define DM9051_EPCR 0x0B +#define DM9051_EPAR 0x0C +#define DM9051_EPDRL 0x0D +#define DM9051_EPDRH 0x0E +#define DM9051_PAR 0x10 +#define DM9051_MAR 0x16 +#define DM9051_GPCR 0x1E +#define DM9051_GPR 0x1F + +#define DM9051_VIDL 0x28 +#define DM9051_VIDH 0x29 +#define DM9051_PIDL 0x2A +#define DM9051_PIDH 0x2B +#define DM9051_SMCR 0x2F +#define DM9051_ATCR 0x30 +#define DM9051_SPIBCR 0x38 +#define DM9051_INTCR 0x39 +#define DM9051_PPCR 0x3D + +#define DM9051_MPCR 0x55 +#define DM9051_LMCR 0x57 +#define DM9051_MBNDRY 0x5E + +#define DM9051_MRRL 0x74 +#define DM9051_MRRH 0x75 +#define DM9051_MWRL 0x7A +#define DM9051_MWRH 0x7B +#define DM9051_TXPLL 0x7C +#define DM9051_TXPLH 0x7D +#define DM9051_ISR 0x7E +#define DM9051_IMR 0x7F + +#define DM_SPI_MRCMDX 0x70 +#define DM_SPI_MRCMD 0x72 +#define DM_SPI_MWCMD 0x78 + +#define DM_SPI_WR 0x80 + +/* dm9051 Ethernet controller registers bits + */ +/* 0x00 */ +#define NCR_WAKEEN BIT(6) +#define NCR_FDX BIT(3) +#define NCR_RST BIT(0) +/* 0x01 */ +#define NSR_SPEED BIT(7) +#define NSR_LINKST BIT(6) +#define NSR_WAKEST BIT(5) +#define NSR_TX2END BIT(3) +#define NSR_TX1END BIT(2) +/* 0x02 */ +#define TCR_DIS_JABBER_TIMER BIT(6) /* for Jabber Packet support */ +#define TCR_TXREQ BIT(0) +/* 0x05 */ +#define RCR_DIS_WATCHDOG_TIMER BIT(6) /* for Jabber Packet support */ +#define RCR_DIS_LONG BIT(5) +#define RCR_DIS_CRC BIT(4) +#define RCR_ALL BIT(3) +#define RCR_PRMSC BIT(1) +#define RCR_RXEN BIT(0) +#define RCR_RX_DISABLE (RCR_DIS_LONG | RCR_DIS_CRC) +/* 0x06 */ +#define RSR_RF BIT(7) +#define RSR_MF BIT(6) +#define RSR_LCS BIT(5) +#define RSR_RWTO BIT(4) +#define RSR_PLE BIT(3) +#define RSR_AE BIT(2) +#define RSR_CE BIT(1) +#define RSR_FOE BIT(0) +#define RSR_ERR_BITS (RSR_RF | RSR_LCS | RSR_RWTO | RSR_PLE | \ + RSR_AE | RSR_CE | RSR_FOE) +/* 0x0A */ +#define FCR_TXPEN BIT(5) +#define FCR_BKPM BIT(3) +#define FCR_FLCE BIT(0) +#define FCR_RXTX_BITS (FCR_TXPEN | FCR_BKPM | FCR_FLCE) +/* 0x0B */ +#define EPCR_WEP BIT(4) +#define EPCR_EPOS BIT(3) +#define EPCR_ERPRR BIT(2) +#define EPCR_ERPRW BIT(1) +#define EPCR_ERRE BIT(0) +/* 0x1E */ +#define GPCR_GEP_CNTL BIT(0) +/* 0x1F */ +#define GPR_PHY_OFF BIT(0) +/* 0x30 */ +#define ATCR_AUTO_TX BIT(7) +/* 0x39 */ +#define INTCR_POL_LOW (1 << 0) +#define INTCR_POL_HIGH (0 << 0) +/* 0x3D */ +/* Pause Packet Control Register - default = 1 */ +#define PPCR_PAUSE_COUNT 0x08 +/* 0x55 */ +#define MPCR_RSTTX BIT(1) +#define MPCR_RSTRX BIT(0) +/* 0x57 */ +/* LEDMode Control Register - LEDMode1 */ +/* Value 0x81 : bit[7] = 1, bit[2] = 0, bit[1:0] = 01b */ +#define LMCR_NEWMOD BIT(7) +#define LMCR_TYPED1 BIT(1) +#define LMCR_TYPED0 BIT(0) +#define LMCR_MODE1 (LMCR_NEWMOD | LMCR_TYPED0) +/* 0x5E */ +#define MBNDRY_BYTE BIT(7) +/* 0xFE */ +#define ISR_MBS BIT(7) +#define ISR_LNKCHG BIT(5) +#define ISR_ROOS BIT(3) +#define ISR_ROS BIT(2) +#define ISR_PTS BIT(1) +#define ISR_PRS BIT(0) +#define ISR_CLR_INT (ISR_LNKCHG | ISR_ROOS | ISR_ROS | \ + ISR_PTS | ISR_PRS) +#define ISR_STOP_MRCMD (ISR_MBS) +/* 0xFF */ +#define IMR_PAR BIT(7) +#define IMR_LNKCHGI BIT(5) +#define IMR_PTM BIT(1) +#define IMR_PRM BIT(0) + +/* Const + */ +#define DM9051_PHY_ADDR 1 /* PHY id */ +#define DM9051_PHY 0x40 /* PHY address 0x01 */ +#define DM9051_PKT_RDY 0x01 /* Packet ready to receive */ +#define DM9051_PKT_MAX 1536 /* Received packet max size */ +#define DM9051_TX_QUE_HI_WATER 50 +#define DM9051_TX_QUE_LO_WATER 25 +#define DM_EEPROM_MAGIC 0x9051 + +#define DM_RXHDR_SIZE sizeof(struct dm9051_rxhdr) + +static inline struct board_info *to_dm9051_board(struct net_device *ndev) +{ + return netdev_priv(ndev); +} + +#endif /* _DM9051_H_ */ diff --git a/drivers/net/ethernet/dec/tulip/pnic.c b/drivers/net/ethernet/dec/tulip/pnic.c index 3fb39e32e1b4..653bde48ef44 100644 --- a/drivers/net/ethernet/dec/tulip/pnic.c +++ b/drivers/net/ethernet/dec/tulip/pnic.c @@ -21,7 +21,7 @@ void pnic_do_nway(struct net_device *dev) struct tulip_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->base_addr; u32 phy_reg = ioread32(ioaddr + 0xB8); - u32 new_csr6 = tp->csr6 & ~0x40C40200; + u32 new_csr6; if (phy_reg & 0x78000000) { /* Ignore baseT4 */ if (phy_reg & 0x20000000) dev->if_port = 5; diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index c710dc17be90..8dd7bf9014ec 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -340,7 +340,7 @@ enum wake_event_bits { struct netdev_desc { __le32 next_desc; __le32 status; - struct desc_frag { __le32 addr, length; } frag[1]; + struct desc_frag { __le32 addr, length; } frag; }; /* Bits in netdev_desc.status */ @@ -980,8 +980,8 @@ static void tx_timeout(struct net_device *dev, unsigned int txqueue) le32_to_cpu(np->tx_ring[i].next_desc), le32_to_cpu(np->tx_ring[i].status), (le32_to_cpu(np->tx_ring[i].status) >> 2) & 0xff, - le32_to_cpu(np->tx_ring[i].frag[0].addr), - le32_to_cpu(np->tx_ring[i].frag[0].length)); + le32_to_cpu(np->tx_ring[i].frag.addr), + le32_to_cpu(np->tx_ring[i].frag.length)); } printk(KERN_DEBUG "TxListPtr=%08x netif_queue_stopped=%d\n", ioread32(np->base + TxListPtr), @@ -1027,7 +1027,7 @@ static void init_ring(struct net_device *dev) np->rx_ring[i].next_desc = cpu_to_le32(np->rx_ring_dma + ((i+1)%RX_RING_SIZE)*sizeof(*np->rx_ring)); np->rx_ring[i].status = 0; - np->rx_ring[i].frag[0].length = 0; + np->rx_ring[i].frag.length = 0; np->rx_skbuff[i] = NULL; } @@ -1039,16 +1039,16 @@ static void init_ring(struct net_device *dev) if (skb == NULL) break; skb_reserve(skb, 2); /* 16 byte align the IP header. */ - np->rx_ring[i].frag[0].addr = cpu_to_le32( + np->rx_ring[i].frag.addr = cpu_to_le32( dma_map_single(&np->pci_dev->dev, skb->data, np->rx_buf_sz, DMA_FROM_DEVICE)); if (dma_mapping_error(&np->pci_dev->dev, - np->rx_ring[i].frag[0].addr)) { + np->rx_ring[i].frag.addr)) { dev_kfree_skb(skb); np->rx_skbuff[i] = NULL; break; } - np->rx_ring[i].frag[0].length = cpu_to_le32(np->rx_buf_sz | LastFrag); + np->rx_ring[i].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag); } np->dirty_rx = (unsigned int)(i - RX_RING_SIZE); @@ -1097,12 +1097,12 @@ start_tx (struct sk_buff *skb, struct net_device *dev) txdesc->next_desc = 0; txdesc->status = cpu_to_le32 ((entry << 2) | DisableAlign); - txdesc->frag[0].addr = cpu_to_le32(dma_map_single(&np->pci_dev->dev, + txdesc->frag.addr = cpu_to_le32(dma_map_single(&np->pci_dev->dev, skb->data, skb->len, DMA_TO_DEVICE)); if (dma_mapping_error(&np->pci_dev->dev, - txdesc->frag[0].addr)) + txdesc->frag.addr)) goto drop_frame; - txdesc->frag[0].length = cpu_to_le32 (skb->len | LastFrag); + txdesc->frag.length = cpu_to_le32 (skb->len | LastFrag); /* Increment cur_tx before tasklet_schedule() */ np->cur_tx++; @@ -1151,7 +1151,7 @@ reset_tx (struct net_device *dev) skb = np->tx_skbuff[i]; if (skb) { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[i].frag[0].addr), + le32_to_cpu(np->tx_ring[i].frag.addr), skb->len, DMA_TO_DEVICE); dev_kfree_skb_any(skb); np->tx_skbuff[i] = NULL; @@ -1271,12 +1271,12 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) skb = np->tx_skbuff[entry]; /* Free the original skb. */ dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[entry].frag[0].addr), + le32_to_cpu(np->tx_ring[entry].frag.addr), skb->len, DMA_TO_DEVICE); dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; - np->tx_ring[entry].frag[0].addr = 0; - np->tx_ring[entry].frag[0].length = 0; + np->tx_ring[entry].frag.addr = 0; + np->tx_ring[entry].frag.length = 0; } spin_unlock(&np->lock); } else { @@ -1290,12 +1290,12 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) skb = np->tx_skbuff[entry]; /* Free the original skb. */ dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[entry].frag[0].addr), + le32_to_cpu(np->tx_ring[entry].frag.addr), skb->len, DMA_TO_DEVICE); dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; - np->tx_ring[entry].frag[0].addr = 0; - np->tx_ring[entry].frag[0].length = 0; + np->tx_ring[entry].frag.addr = 0; + np->tx_ring[entry].frag.length = 0; } spin_unlock(&np->lock); } @@ -1372,16 +1372,16 @@ static void rx_poll(struct tasklet_struct *t) (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ dma_sync_single_for_cpu(&np->pci_dev->dev, - le32_to_cpu(desc->frag[0].addr), + le32_to_cpu(desc->frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, np->rx_skbuff[entry]->data, pkt_len); dma_sync_single_for_device(&np->pci_dev->dev, - le32_to_cpu(desc->frag[0].addr), + le32_to_cpu(desc->frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); skb_put(skb, pkt_len); } else { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(desc->frag[0].addr), + le32_to_cpu(desc->frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); skb_put(skb = np->rx_skbuff[entry], pkt_len); np->rx_skbuff[entry] = NULL; @@ -1427,18 +1427,18 @@ static void refill_rx (struct net_device *dev) if (skb == NULL) break; /* Better luck next round. */ skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ - np->rx_ring[entry].frag[0].addr = cpu_to_le32( + np->rx_ring[entry].frag.addr = cpu_to_le32( dma_map_single(&np->pci_dev->dev, skb->data, np->rx_buf_sz, DMA_FROM_DEVICE)); if (dma_mapping_error(&np->pci_dev->dev, - np->rx_ring[entry].frag[0].addr)) { + np->rx_ring[entry].frag.addr)) { dev_kfree_skb_irq(skb); np->rx_skbuff[entry] = NULL; break; } } /* Perhaps we need not reset this field. */ - np->rx_ring[entry].frag[0].length = + np->rx_ring[entry].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag); np->rx_ring[entry].status = 0; cnt++; @@ -1870,14 +1870,14 @@ static int netdev_close(struct net_device *dev) (int)(np->tx_ring_dma)); for (i = 0; i < TX_RING_SIZE; i++) printk(KERN_DEBUG " #%d desc. %4.4x %8.8x %8.8x.\n", - i, np->tx_ring[i].status, np->tx_ring[i].frag[0].addr, - np->tx_ring[i].frag[0].length); + i, np->tx_ring[i].status, np->tx_ring[i].frag.addr, + np->tx_ring[i].frag.length); printk(KERN_DEBUG " Rx ring %8.8x:\n", (int)(np->rx_ring_dma)); for (i = 0; i < /*RX_RING_SIZE*/4 ; i++) { printk(KERN_DEBUG " #%d desc. %4.4x %4.4x %8.8x\n", - i, np->rx_ring[i].status, np->rx_ring[i].frag[0].addr, - np->rx_ring[i].frag[0].length); + i, np->rx_ring[i].status, np->rx_ring[i].frag.addr, + np->rx_ring[i].frag.length); } } #endif /* __i386__ debugging only */ @@ -1892,19 +1892,19 @@ static int netdev_close(struct net_device *dev) skb = np->rx_skbuff[i]; if (skb) { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->rx_ring[i].frag[0].addr), + le32_to_cpu(np->rx_ring[i].frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); dev_kfree_skb(skb); np->rx_skbuff[i] = NULL; } - np->rx_ring[i].frag[0].addr = cpu_to_le32(0xBADF00D0); /* poison */ + np->rx_ring[i].frag.addr = cpu_to_le32(0xBADF00D0); /* poison */ } for (i = 0; i < TX_RING_SIZE; i++) { np->tx_ring[i].next_desc = 0; skb = np->tx_skbuff[i]; if (skb) { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[i].frag[0].addr), + le32_to_cpu(np->tx_ring[i].frag.addr), skb->len, DMA_TO_DEVICE); dev_kfree_skb(skb); np->tx_skbuff[i] = NULL; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 0f90d2d5bb60..6b5484543d09 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -18,6 +18,7 @@ #include <linux/ptp_classify.h> #include <net/pkt_cls.h> #include <net/sock.h> +#include <net/tso.h> #include "dpaa2-eth.h" @@ -760,6 +761,39 @@ static void dpaa2_eth_enable_tx_tstamp(struct dpaa2_eth_priv *priv, } } +static void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv) +{ + struct dpaa2_eth_sgt_cache *sgt_cache; + void *sgt_buf = NULL; + int sgt_buf_size; + + sgt_cache = this_cpu_ptr(priv->sgt_cache); + sgt_buf_size = priv->tx_data_offset + + DPAA2_ETH_SG_ENTRIES_MAX * sizeof(struct dpaa2_sg_entry); + + if (sgt_cache->count == 0) + sgt_buf = napi_alloc_frag_align(sgt_buf_size, DPAA2_ETH_TX_BUF_ALIGN); + else + sgt_buf = sgt_cache->buf[--sgt_cache->count]; + if (!sgt_buf) + return NULL; + + memset(sgt_buf, 0, sgt_buf_size); + + return sgt_buf; +} + +static void dpaa2_eth_sgt_recycle(struct dpaa2_eth_priv *priv, void *sgt_buf) +{ + struct dpaa2_eth_sgt_cache *sgt_cache; + + sgt_cache = this_cpu_ptr(priv->sgt_cache); + if (sgt_cache->count >= DPAA2_ETH_SGT_CACHE_SIZE) + skb_free_frag(sgt_buf); + else + sgt_cache->buf[sgt_cache->count++] = sgt_buf; +} + /* Create a frame descriptor based on a fragmented skb */ static int dpaa2_eth_build_sg_fd(struct dpaa2_eth_priv *priv, struct sk_buff *skb, @@ -805,12 +839,11 @@ static int dpaa2_eth_build_sg_fd(struct dpaa2_eth_priv *priv, /* Prepare the HW SGT structure */ sgt_buf_size = priv->tx_data_offset + sizeof(struct dpaa2_sg_entry) * num_dma_bufs; - sgt_buf = napi_alloc_frag_align(sgt_buf_size, DPAA2_ETH_TX_BUF_ALIGN); + sgt_buf = dpaa2_eth_sgt_get(priv); if (unlikely(!sgt_buf)) { err = -ENOMEM; goto sgt_buf_alloc_failed; } - memset(sgt_buf, 0, sgt_buf_size); sgt = (struct dpaa2_sg_entry *)(sgt_buf + priv->tx_data_offset); @@ -846,6 +879,7 @@ static int dpaa2_eth_build_sg_fd(struct dpaa2_eth_priv *priv, err = -ENOMEM; goto dma_map_single_failed; } + memset(fd, 0, sizeof(struct dpaa2_fd)); dpaa2_fd_set_offset(fd, priv->tx_data_offset); dpaa2_fd_set_format(fd, dpaa2_fd_sg); dpaa2_fd_set_addr(fd, addr); @@ -855,7 +889,7 @@ static int dpaa2_eth_build_sg_fd(struct dpaa2_eth_priv *priv, return 0; dma_map_single_failed: - skb_free_frag(sgt_buf); + dpaa2_eth_sgt_recycle(priv, sgt_buf); sgt_buf_alloc_failed: dma_unmap_sg(dev, scl, num_sg, DMA_BIDIRECTIONAL); dma_map_sg_failed: @@ -875,7 +909,6 @@ static int dpaa2_eth_build_sg_fd_single_buf(struct dpaa2_eth_priv *priv, void **swa_addr) { struct device *dev = priv->net_dev->dev.parent; - struct dpaa2_eth_sgt_cache *sgt_cache; struct dpaa2_sg_entry *sgt; struct dpaa2_eth_swa *swa; dma_addr_t addr, sgt_addr; @@ -884,18 +917,10 @@ static int dpaa2_eth_build_sg_fd_single_buf(struct dpaa2_eth_priv *priv, int err; /* Prepare the HW SGT structure */ - sgt_cache = this_cpu_ptr(priv->sgt_cache); sgt_buf_size = priv->tx_data_offset + sizeof(struct dpaa2_sg_entry); - - if (sgt_cache->count == 0) - sgt_buf = kzalloc(sgt_buf_size + DPAA2_ETH_TX_BUF_ALIGN, - GFP_ATOMIC); - else - sgt_buf = sgt_cache->buf[--sgt_cache->count]; + sgt_buf = dpaa2_eth_sgt_get(priv); if (unlikely(!sgt_buf)) return -ENOMEM; - - sgt_buf = PTR_ALIGN(sgt_buf, DPAA2_ETH_TX_BUF_ALIGN); sgt = (struct dpaa2_sg_entry *)(sgt_buf + priv->tx_data_offset); addr = dma_map_single(dev, skb->data, skb->len, DMA_BIDIRECTIONAL); @@ -923,6 +948,7 @@ static int dpaa2_eth_build_sg_fd_single_buf(struct dpaa2_eth_priv *priv, goto sgt_map_failed; } + memset(fd, 0, sizeof(struct dpaa2_fd)); dpaa2_fd_set_offset(fd, priv->tx_data_offset); dpaa2_fd_set_format(fd, dpaa2_fd_sg); dpaa2_fd_set_addr(fd, sgt_addr); @@ -934,10 +960,7 @@ static int dpaa2_eth_build_sg_fd_single_buf(struct dpaa2_eth_priv *priv, sgt_map_failed: dma_unmap_single(dev, addr, skb->len, DMA_BIDIRECTIONAL); data_map_failed: - if (sgt_cache->count >= DPAA2_ETH_SGT_CACHE_SIZE) - kfree(sgt_buf); - else - sgt_cache->buf[sgt_cache->count++] = sgt_buf; + dpaa2_eth_sgt_recycle(priv, sgt_buf); return err; } @@ -978,6 +1001,7 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv, if (unlikely(dma_mapping_error(dev, addr))) return -ENOMEM; + memset(fd, 0, sizeof(struct dpaa2_fd)); dpaa2_fd_set_addr(fd, addr); dpaa2_fd_set_offset(fd, (u16)(skb->data - buffer_start)); dpaa2_fd_set_len(fd, skb->len); @@ -1005,9 +1029,9 @@ static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, struct dpaa2_eth_swa *swa; u8 fd_format = dpaa2_fd_get_format(fd); u32 fd_len = dpaa2_fd_get_len(fd); - - struct dpaa2_eth_sgt_cache *sgt_cache; struct dpaa2_sg_entry *sgt; + int should_free_skb = 1; + int i; fd_addr = dpaa2_fd_get_addr(fd); buffer_start = dpaa2_iova_to_virt(priv->iommu_domain, fd_addr); @@ -1039,6 +1063,28 @@ static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, /* Unmap the SGT buffer */ dma_unmap_single(dev, fd_addr, swa->sg.sgt_size, DMA_BIDIRECTIONAL); + } else if (swa->type == DPAA2_ETH_SWA_SW_TSO) { + skb = swa->tso.skb; + + sgt = (struct dpaa2_sg_entry *)(buffer_start + + priv->tx_data_offset); + + /* Unmap and free the header */ + dma_unmap_single(dev, dpaa2_sg_get_addr(sgt), TSO_HEADER_SIZE, + DMA_TO_DEVICE); + kfree(dpaa2_iova_to_virt(priv->iommu_domain, dpaa2_sg_get_addr(sgt))); + + /* Unmap the other SG entries for the data */ + for (i = 1; i < swa->tso.num_sg; i++) + dma_unmap_single(dev, dpaa2_sg_get_addr(&sgt[i]), + dpaa2_sg_get_len(&sgt[i]), DMA_TO_DEVICE); + + /* Unmap the SGT buffer */ + dma_unmap_single(dev, fd_addr, swa->sg.sgt_size, + DMA_BIDIRECTIONAL); + + if (!swa->tso.is_last_fd) + should_free_skb = 0; } else { skb = swa->single.skb; @@ -1067,55 +1113,195 @@ static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv, } /* Get the timestamp value */ - if (skb->cb[0] == TX_TSTAMP) { - struct skb_shared_hwtstamps shhwtstamps; - __le64 *ts = dpaa2_get_ts(buffer_start, true); - u64 ns; - - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - - ns = DPAA2_PTP_CLK_PERIOD_NS * le64_to_cpup(ts); - shhwtstamps.hwtstamp = ns_to_ktime(ns); - skb_tstamp_tx(skb, &shhwtstamps); - } else if (skb->cb[0] == TX_TSTAMP_ONESTEP_SYNC) { - mutex_unlock(&priv->onestep_tstamp_lock); + if (swa->type != DPAA2_ETH_SWA_SW_TSO) { + if (skb->cb[0] == TX_TSTAMP) { + struct skb_shared_hwtstamps shhwtstamps; + __le64 *ts = dpaa2_get_ts(buffer_start, true); + u64 ns; + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + + ns = DPAA2_PTP_CLK_PERIOD_NS * le64_to_cpup(ts); + shhwtstamps.hwtstamp = ns_to_ktime(ns); + skb_tstamp_tx(skb, &shhwtstamps); + } else if (skb->cb[0] == TX_TSTAMP_ONESTEP_SYNC) { + mutex_unlock(&priv->onestep_tstamp_lock); + } } /* Free SGT buffer allocated on tx */ - if (fd_format != dpaa2_fd_single) { - sgt_cache = this_cpu_ptr(priv->sgt_cache); - if (swa->type == DPAA2_ETH_SWA_SG) { - skb_free_frag(buffer_start); - } else { - if (sgt_cache->count >= DPAA2_ETH_SGT_CACHE_SIZE) - kfree(buffer_start); - else - sgt_cache->buf[sgt_cache->count++] = buffer_start; + if (fd_format != dpaa2_fd_single) + dpaa2_eth_sgt_recycle(priv, buffer_start); + + /* Move on with skb release. If we are just confirming multiple FDs + * from the same TSO skb then only the last one will need to free the + * skb. + */ + if (should_free_skb) + napi_consume_skb(skb, in_napi); +} + +static int dpaa2_eth_build_gso_fd(struct dpaa2_eth_priv *priv, + struct sk_buff *skb, struct dpaa2_fd *fd, + int *num_fds, u32 *total_fds_len) +{ + struct device *dev = priv->net_dev->dev.parent; + int hdr_len, total_len, data_left, fd_len; + int num_sge, err, i, sgt_buf_size; + struct dpaa2_fd *fd_start = fd; + struct dpaa2_sg_entry *sgt; + struct dpaa2_eth_swa *swa; + dma_addr_t sgt_addr, addr; + dma_addr_t tso_hdr_dma; + unsigned int index = 0; + struct tso_t tso; + char *tso_hdr; + void *sgt_buf; + + /* Initialize the TSO handler, and prepare the first payload */ + hdr_len = tso_start(skb, &tso); + *total_fds_len = 0; + + total_len = skb->len - hdr_len; + while (total_len > 0) { + /* Prepare the HW SGT structure for this frame */ + sgt_buf = dpaa2_eth_sgt_get(priv); + if (unlikely(!sgt_buf)) { + netdev_err(priv->net_dev, "dpaa2_eth_sgt_get() failed\n"); + err = -ENOMEM; + goto err_sgt_get; } + sgt = (struct dpaa2_sg_entry *)(sgt_buf + priv->tx_data_offset); + + /* Determine the data length of this frame */ + data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len); + total_len -= data_left; + fd_len = data_left + hdr_len; + + /* Prepare packet headers: MAC + IP + TCP */ + tso_hdr = kmalloc(TSO_HEADER_SIZE, GFP_ATOMIC); + if (!tso_hdr) { + err = -ENOMEM; + goto err_alloc_tso_hdr; + } + + tso_build_hdr(skb, tso_hdr, &tso, data_left, total_len == 0); + tso_hdr_dma = dma_map_single(dev, tso_hdr, TSO_HEADER_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dev, tso_hdr_dma)) { + netdev_err(priv->net_dev, "dma_map_single(tso_hdr) failed\n"); + err = -ENOMEM; + goto err_map_tso_hdr; + } + + /* Setup the SG entry for the header */ + dpaa2_sg_set_addr(sgt, tso_hdr_dma); + dpaa2_sg_set_len(sgt, hdr_len); + dpaa2_sg_set_final(sgt, data_left <= 0); + + /* Compose the SG entries for each fragment of data */ + num_sge = 1; + while (data_left > 0) { + int size; + + /* Move to the next SG entry */ + sgt++; + size = min_t(int, tso.size, data_left); + + addr = dma_map_single(dev, tso.data, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, addr)) { + netdev_err(priv->net_dev, "dma_map_single(tso.data) failed\n"); + err = -ENOMEM; + goto err_map_data; + } + dpaa2_sg_set_addr(sgt, addr); + dpaa2_sg_set_len(sgt, size); + dpaa2_sg_set_final(sgt, size == data_left); + + num_sge++; + + /* Build the data for the __next__ fragment */ + data_left -= size; + tso_build_data(skb, &tso, size); + } + + /* Store the skb backpointer in the SGT buffer */ + sgt_buf_size = priv->tx_data_offset + num_sge * sizeof(struct dpaa2_sg_entry); + swa = (struct dpaa2_eth_swa *)sgt_buf; + swa->type = DPAA2_ETH_SWA_SW_TSO; + swa->tso.skb = skb; + swa->tso.num_sg = num_sge; + swa->tso.sgt_size = sgt_buf_size; + swa->tso.is_last_fd = total_len == 0 ? 1 : 0; + + /* Separately map the SGT buffer */ + sgt_addr = dma_map_single(dev, sgt_buf, sgt_buf_size, DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(dev, sgt_addr))) { + netdev_err(priv->net_dev, "dma_map_single(sgt_buf) failed\n"); + err = -ENOMEM; + goto err_map_sgt; + } + + /* Setup the frame descriptor */ + memset(fd, 0, sizeof(struct dpaa2_fd)); + dpaa2_fd_set_offset(fd, priv->tx_data_offset); + dpaa2_fd_set_format(fd, dpaa2_fd_sg); + dpaa2_fd_set_addr(fd, sgt_addr); + dpaa2_fd_set_len(fd, fd_len); + dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA); + + *total_fds_len += fd_len; + /* Advance to the next frame descriptor */ + fd++; + index++; } - /* Move on with skb release */ - napi_consume_skb(skb, in_napi); + *num_fds = index; + + return 0; + +err_map_sgt: +err_map_data: + /* Unmap all the data S/G entries for the current FD */ + sgt = (struct dpaa2_sg_entry *)(sgt_buf + priv->tx_data_offset); + for (i = 1; i < num_sge; i++) + dma_unmap_single(dev, dpaa2_sg_get_addr(&sgt[i]), + dpaa2_sg_get_len(&sgt[i]), DMA_TO_DEVICE); + + /* Unmap the header entry */ + dma_unmap_single(dev, tso_hdr_dma, TSO_HEADER_SIZE, DMA_TO_DEVICE); +err_map_tso_hdr: + kfree(tso_hdr); +err_alloc_tso_hdr: + dpaa2_eth_sgt_recycle(priv, sgt_buf); +err_sgt_get: + /* Free all the other FDs that were already fully created */ + for (i = 0; i < index; i++) + dpaa2_eth_free_tx_fd(priv, NULL, &fd_start[i], false); + + return err; } static netdev_tx_t __dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - struct dpaa2_fd fd; - struct rtnl_link_stats64 *percpu_stats; + int total_enqueued = 0, retries = 0, enqueued; struct dpaa2_eth_drv_stats *percpu_extras; + struct rtnl_link_stats64 *percpu_stats; + unsigned int needed_headroom; + int num_fds = 1, max_retries; struct dpaa2_eth_fq *fq; struct netdev_queue *nq; + struct dpaa2_fd *fd; u16 queue_mapping; - unsigned int needed_headroom; - u32 fd_len; + void *swa = NULL; u8 prio = 0; int err, i; - void *swa; + u32 fd_len; percpu_stats = this_cpu_ptr(priv->percpu_stats); percpu_extras = this_cpu_ptr(priv->percpu_extras); + fd = (this_cpu_ptr(priv->fd))->array; needed_headroom = dpaa2_eth_needed_headroom(skb); @@ -1130,20 +1316,28 @@ static netdev_tx_t __dpaa2_eth_tx(struct sk_buff *skb, } /* Setup the FD fields */ - memset(&fd, 0, sizeof(fd)); - if (skb_is_nonlinear(skb)) { - err = dpaa2_eth_build_sg_fd(priv, skb, &fd, &swa); + if (skb_is_gso(skb)) { + err = dpaa2_eth_build_gso_fd(priv, skb, fd, &num_fds, &fd_len); + percpu_extras->tx_sg_frames += num_fds; + percpu_extras->tx_sg_bytes += fd_len; + percpu_extras->tx_tso_frames += num_fds; + percpu_extras->tx_tso_bytes += fd_len; + } else if (skb_is_nonlinear(skb)) { + err = dpaa2_eth_build_sg_fd(priv, skb, fd, &swa); percpu_extras->tx_sg_frames++; percpu_extras->tx_sg_bytes += skb->len; + fd_len = dpaa2_fd_get_len(fd); } else if (skb_headroom(skb) < needed_headroom) { - err = dpaa2_eth_build_sg_fd_single_buf(priv, skb, &fd, &swa); + err = dpaa2_eth_build_sg_fd_single_buf(priv, skb, fd, &swa); percpu_extras->tx_sg_frames++; percpu_extras->tx_sg_bytes += skb->len; percpu_extras->tx_converted_sg_frames++; percpu_extras->tx_converted_sg_bytes += skb->len; + fd_len = dpaa2_fd_get_len(fd); } else { - err = dpaa2_eth_build_single_fd(priv, skb, &fd, &swa); + err = dpaa2_eth_build_single_fd(priv, skb, fd, &swa); + fd_len = dpaa2_fd_get_len(fd); } if (unlikely(err)) { @@ -1151,11 +1345,12 @@ static netdev_tx_t __dpaa2_eth_tx(struct sk_buff *skb, goto err_build_fd; } - if (skb->cb[0]) - dpaa2_eth_enable_tx_tstamp(priv, &fd, swa, skb); + if (swa && skb->cb[0]) + dpaa2_eth_enable_tx_tstamp(priv, fd, swa, skb); /* Tracing point */ - trace_dpaa2_tx_fd(net_dev, &fd); + for (i = 0; i < num_fds; i++) + trace_dpaa2_tx_fd(net_dev, &fd[i]); /* TxConf FQ selection relies on queue id from the stack. * In case of a forwarded frame from another DPNI interface, we choose @@ -1175,27 +1370,32 @@ static netdev_tx_t __dpaa2_eth_tx(struct sk_buff *skb, queue_mapping %= dpaa2_eth_queue_count(priv); } fq = &priv->fq[queue_mapping]; - - fd_len = dpaa2_fd_get_len(&fd); nq = netdev_get_tx_queue(net_dev, queue_mapping); netdev_tx_sent_queue(nq, fd_len); /* Everything that happens after this enqueues might race with * the Tx confirmation callback for this frame */ - for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { - err = priv->enqueue(priv, fq, &fd, prio, 1, NULL); - if (err != -EBUSY) - break; + max_retries = num_fds * DPAA2_ETH_ENQUEUE_RETRIES; + while (total_enqueued < num_fds && retries < max_retries) { + err = priv->enqueue(priv, fq, &fd[total_enqueued], + prio, num_fds - total_enqueued, &enqueued); + if (err == -EBUSY) { + retries++; + continue; + } + + total_enqueued += enqueued; } - percpu_extras->tx_portal_busy += i; + percpu_extras->tx_portal_busy += retries; + if (unlikely(err < 0)) { percpu_stats->tx_errors++; /* Clean up everything, including freeing the skb */ - dpaa2_eth_free_tx_fd(priv, fq, &fd, false); + dpaa2_eth_free_tx_fd(priv, fq, fd, false); netdev_tx_completed_queue(nq, 1, fd_len); } else { - percpu_stats->tx_packets++; + percpu_stats->tx_packets += total_enqueued; percpu_stats->tx_bytes += fd_len; } @@ -1523,7 +1723,7 @@ static void dpaa2_eth_sgt_cache_drain(struct dpaa2_eth_priv *priv) count = sgt_cache->count; for (i = 0; i < count; i++) - kfree(sgt_cache->buf[i]); + skb_free_frag(sgt_cache->buf[i]); sgt_cache->count = 0; } } @@ -4115,7 +4315,8 @@ static int dpaa2_eth_netdev_init(struct net_device *net_dev) net_dev->features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | - NETIF_F_LLTX | NETIF_F_HW_TC; + NETIF_F_LLTX | NETIF_F_HW_TC | NETIF_F_TSO; + net_dev->gso_max_segs = DPAA2_ETH_ENQUEUE_MAX_FDS; net_dev->hw_features = net_dev->features; if (priv->dpni_attrs.vlan_filter_entries) @@ -4397,6 +4598,13 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) goto err_alloc_sgt_cache; } + priv->fd = alloc_percpu(*priv->fd); + if (!priv->fd) { + dev_err(dev, "alloc_percpu(fds) failed\n"); + err = -ENOMEM; + goto err_alloc_fds; + } + err = dpaa2_eth_netdev_init(net_dev); if (err) goto err_netdev_init; @@ -4484,6 +4692,8 @@ err_poll_thread: err_alloc_rings: err_csum: err_netdev_init: + free_percpu(priv->fd); +err_alloc_fds: free_percpu(priv->sgt_cache); err_alloc_sgt_cache: free_percpu(priv->percpu_extras); @@ -4539,6 +4749,7 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) fsl_mc_free_irqs(ls_dev); dpaa2_eth_free_rings(priv); + free_percpu(priv->fd); free_percpu(priv->sgt_cache); free_percpu(priv->percpu_stats); free_percpu(priv->percpu_extras); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index e54e70ebdd05..b79831cd1a94 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -122,6 +122,7 @@ enum dpaa2_eth_swa_type { DPAA2_ETH_SWA_SINGLE, DPAA2_ETH_SWA_SG, DPAA2_ETH_SWA_XDP, + DPAA2_ETH_SWA_SW_TSO, }; /* Must keep this struct smaller than DPAA2_ETH_SWA_SIZE */ @@ -142,6 +143,12 @@ struct dpaa2_eth_swa { int dma_size; struct xdp_frame *xdpf; } xdp; + struct { + struct sk_buff *skb; + int num_sg; + int sgt_size; + int is_last_fd; + } tso; }; }; @@ -354,6 +361,8 @@ struct dpaa2_eth_drv_stats { __u64 tx_conf_bytes; __u64 tx_sg_frames; __u64 tx_sg_bytes; + __u64 tx_tso_frames; + __u64 tx_tso_bytes; __u64 rx_sg_frames; __u64 rx_sg_bytes; /* Linear skbs sent as a S/G FD due to insufficient headroom */ @@ -493,8 +502,15 @@ struct dpaa2_eth_trap_data { struct dpaa2_eth_priv *priv; }; +#define DPAA2_ETH_SG_ENTRIES_MAX (PAGE_SIZE / sizeof(struct scatterlist)) + #define DPAA2_ETH_DEFAULT_COPYBREAK 512 +#define DPAA2_ETH_ENQUEUE_MAX_FDS 200 +struct dpaa2_eth_fds { + struct dpaa2_fd array[DPAA2_ETH_ENQUEUE_MAX_FDS]; +}; + /* Driver private data */ struct dpaa2_eth_priv { struct net_device *net_dev; @@ -577,6 +593,8 @@ struct dpaa2_eth_priv { struct devlink_port devlink_port; u32 rx_copybreak; + + struct dpaa2_eth_fds __percpu *fd; }; struct dpaa2_eth_devlink_priv { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 3fdbf87dccb1..eea7d7a07c00 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -44,6 +44,8 @@ static char dpaa2_ethtool_extras[][ETH_GSTRING_LEN] = { "[drv] tx conf bytes", "[drv] tx sg frames", "[drv] tx sg bytes", + "[drv] tx tso frames", + "[drv] tx tso bytes", "[drv] rx sg frames", "[drv] rx sg bytes", "[drv] tx converted sg frames", diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 623d113b6581..521f036d1c00 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -100,6 +100,14 @@ static int dpaa2_mac_get_if_mode(struct fwnode_handle *dpmac_node, return err; } +static struct phylink_pcs *dpaa2_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct dpaa2_mac *mac = phylink_to_dpaa2_mac(config); + + return mac->pcs; +} + static void dpaa2_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -172,6 +180,7 @@ static void dpaa2_mac_link_down(struct phylink_config *config, static const struct phylink_mac_ops dpaa2_mac_phylink_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = dpaa2_mac_select_pcs, .mac_config = dpaa2_mac_config, .mac_link_up = dpaa2_mac_link_up, .mac_link_down = dpaa2_mac_link_down, @@ -303,9 +312,6 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) } mac->phylink = phylink; - if (mac->pcs) - phylink_set_pcs(mac->phylink, mac->pcs); - err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0); if (err) { netdev_err(net_dev, "phylink_fwnode_phy_connect() = %d\n", err); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index fb39e406b7fc..68d806dc3701 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -18,6 +18,8 @@ #define ENETC_MAX_MTU (ENETC_MAC_MAXFRM_SIZE - \ (ETH_FCS_LEN + ETH_HLEN + VLAN_HLEN)) +#define ENETC_CBD_DATA_MEM_ALIGN 64 + struct enetc_tx_swbd { union { struct sk_buff *skb; @@ -415,6 +417,42 @@ int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count); int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count); int enetc_send_cmd(struct enetc_si *si, struct enetc_cbd *cbd); +static inline void *enetc_cbd_alloc_data_mem(struct enetc_si *si, + struct enetc_cbd *cbd, + int size, dma_addr_t *dma, + void **data_align) +{ + struct enetc_cbdr *ring = &si->cbd_ring; + dma_addr_t dma_align; + void *data; + + data = dma_alloc_coherent(ring->dma_dev, + size + ENETC_CBD_DATA_MEM_ALIGN, + dma, GFP_KERNEL); + if (!data) { + dev_err(ring->dma_dev, "CBD alloc data memory failed!\n"); + return NULL; + } + + dma_align = ALIGN(*dma, ENETC_CBD_DATA_MEM_ALIGN); + *data_align = PTR_ALIGN(data, ENETC_CBD_DATA_MEM_ALIGN); + + cbd->addr[0] = cpu_to_le32(lower_32_bits(dma_align)); + cbd->addr[1] = cpu_to_le32(upper_32_bits(dma_align)); + cbd->length = cpu_to_le16(size); + + return data; +} + +static inline void enetc_cbd_free_data_mem(struct enetc_si *si, int size, + void *data, dma_addr_t *dma) +{ + struct enetc_cbdr *ring = &si->cbd_ring; + + dma_free_coherent(ring->dma_dev, size + ENETC_CBD_DATA_MEM_ALIGN, + data, *dma); +} + #ifdef CONFIG_FSL_ENETC_QOS int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data); void enetc_sched_speed_set(struct enetc_ndev_priv *priv, int speed); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c index 073e56dcca4e..af68dc46a795 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c @@ -166,70 +166,55 @@ int enetc_set_mac_flt_entry(struct enetc_si *si, int index, return enetc_send_cmd(si, &cbd); } -#define RFSE_ALIGN 64 /* Set entry in RFS table */ int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse, int index) { struct enetc_cbdr *ring = &si->cbd_ring; struct enetc_cbd cbd = {.cmd = 0}; - dma_addr_t dma, dma_align; void *tmp, *tmp_align; + dma_addr_t dma; int err; /* fill up the "set" descriptor */ cbd.cmd = 0; cbd.cls = 4; cbd.index = cpu_to_le16(index); - cbd.length = cpu_to_le16(sizeof(*rfse)); cbd.opt[3] = cpu_to_le32(0); /* SI */ - tmp = dma_alloc_coherent(ring->dma_dev, sizeof(*rfse) + RFSE_ALIGN, - &dma, GFP_KERNEL); - if (!tmp) { - dev_err(ring->dma_dev, "DMA mapping of RFS entry failed!\n"); + tmp = enetc_cbd_alloc_data_mem(si, &cbd, sizeof(*rfse), + &dma, &tmp_align); + if (!tmp) return -ENOMEM; - } - dma_align = ALIGN(dma, RFSE_ALIGN); - tmp_align = PTR_ALIGN(tmp, RFSE_ALIGN); memcpy(tmp_align, rfse, sizeof(*rfse)); - cbd.addr[0] = cpu_to_le32(lower_32_bits(dma_align)); - cbd.addr[1] = cpu_to_le32(upper_32_bits(dma_align)); - err = enetc_send_cmd(si, &cbd); if (err) dev_err(ring->dma_dev, "FS entry add failed (%d)!", err); - dma_free_coherent(ring->dma_dev, sizeof(*rfse) + RFSE_ALIGN, - tmp, dma); + enetc_cbd_free_data_mem(si, sizeof(*rfse), tmp, &dma); return err; } -#define RSSE_ALIGN 64 static int enetc_cmd_rss_table(struct enetc_si *si, u32 *table, int count, bool read) { struct enetc_cbdr *ring = &si->cbd_ring; struct enetc_cbd cbd = {.cmd = 0}; - dma_addr_t dma, dma_align; u8 *tmp, *tmp_align; + dma_addr_t dma; int err, i; - if (count < RSSE_ALIGN) + if (count < ENETC_CBD_DATA_MEM_ALIGN) /* HW only takes in a full 64 entry table */ return -EINVAL; - tmp = dma_alloc_coherent(ring->dma_dev, count + RSSE_ALIGN, - &dma, GFP_KERNEL); - if (!tmp) { - dev_err(ring->dma_dev, "DMA mapping of RSS table failed!\n"); + tmp = enetc_cbd_alloc_data_mem(si, &cbd, count, + &dma, (void *)&tmp_align); + if (!tmp) return -ENOMEM; - } - dma_align = ALIGN(dma, RSSE_ALIGN); - tmp_align = PTR_ALIGN(tmp, RSSE_ALIGN); if (!read) for (i = 0; i < count; i++) @@ -238,10 +223,6 @@ static int enetc_cmd_rss_table(struct enetc_si *si, u32 *table, int count, /* fill up the descriptor */ cbd.cmd = read ? 2 : 1; cbd.cls = 3; - cbd.length = cpu_to_le16(count); - - cbd.addr[0] = cpu_to_le32(lower_32_bits(dma_align)); - cbd.addr[1] = cpu_to_le32(upper_32_bits(dma_align)); err = enetc_send_cmd(si, &cbd); if (err) @@ -251,7 +232,7 @@ static int enetc_cmd_rss_table(struct enetc_si *si, u32 *table, int count, for (i = 0; i < count; i++) table[i] = tmp_align[i]; - dma_free_coherent(ring->dma_dev, count + RSSE_ALIGN, tmp, dma); + enetc_cbd_free_data_mem(si, count, tmp, &dma); return err; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index ed16a5ac9ad0..a0c75c717073 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -934,18 +934,21 @@ static void enetc_mdiobus_destroy(struct enetc_pf *pf) enetc_imdio_remove(pf); } +static struct phylink_pcs * +enetc_pl_mac_select_pcs(struct phylink_config *config, phy_interface_t iface) +{ + struct enetc_pf *pf = phylink_to_enetc_pf(config); + + return pf->pcs; +} + static void enetc_pl_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { struct enetc_pf *pf = phylink_to_enetc_pf(config); - struct enetc_ndev_priv *priv; enetc_mac_config(&pf->si->hw, state->interface); - - priv = netdev_priv(pf->si->ndev); - if (pf->pcs) - phylink_set_pcs(priv->phylink, pf->pcs); } static void enetc_force_rgmii_mac(struct enetc_hw *hw, int speed, int duplex) @@ -1062,6 +1065,7 @@ static void enetc_pl_mac_link_down(struct phylink_config *config, static const struct phylink_mac_ops enetc_mac_phylink_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = enetc_pl_mac_select_pcs, .mac_config = enetc_pl_mac_config, .mac_link_up = enetc_pl_mac_link_up, .mac_link_down = enetc_pl_mac_link_down, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 3555c12edb45..5a3eea1a718b 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -52,10 +52,11 @@ static int enetc_setup_taprio(struct net_device *ndev, struct enetc_cbd cbd = {.cmd = 0}; struct tgs_gcl_conf *gcl_config; struct tgs_gcl_data *gcl_data; - struct gce *gce; dma_addr_t dma; + struct gce *gce; u16 data_size; u16 gcl_len; + void *tmp; u32 tge; int err; int i; @@ -82,8 +83,9 @@ static int enetc_setup_taprio(struct net_device *ndev, gcl_config = &cbd.gcl_conf; data_size = struct_size(gcl_data, entry, gcl_len); - gcl_data = kzalloc(data_size, __GFP_DMA | GFP_KERNEL); - if (!gcl_data) + tmp = enetc_cbd_alloc_data_mem(priv->si, &cbd, data_size, + &dma, (void *)&gcl_data); + if (!tmp) return -ENOMEM; gce = (struct gce *)(gcl_data + 1); @@ -107,19 +109,8 @@ static int enetc_setup_taprio(struct net_device *ndev, temp_gce->period = cpu_to_le32(temp_entry->interval); } - cbd.length = cpu_to_le16(data_size); cbd.status_flags = 0; - dma = dma_map_single(&priv->si->pdev->dev, gcl_data, - data_size, DMA_TO_DEVICE); - if (dma_mapping_error(&priv->si->pdev->dev, dma)) { - netdev_err(priv->si->ndev, "DMA mapping failed!\n"); - kfree(gcl_data); - return -ENOMEM; - } - - cbd.addr[0] = cpu_to_le32(lower_32_bits(dma)); - cbd.addr[1] = cpu_to_le32(upper_32_bits(dma)); cbd.cls = BDCR_CMD_PORT_GCL; cbd.status_flags = 0; @@ -132,8 +123,7 @@ static int enetc_setup_taprio(struct net_device *ndev, ENETC_QBV_PTGCR_OFFSET, tge & (~ENETC_QBV_TGE)); - dma_unmap_single(&priv->si->pdev->dev, dma, data_size, DMA_TO_DEVICE); - kfree(gcl_data); + enetc_cbd_free_data_mem(priv->si, data_size, tmp, &dma); return err; } @@ -450,6 +440,7 @@ static struct actions_fwd enetc_act_fwd[] = { }; static struct enetc_psfp epsfp = { + .dev_bitmap = 0, .psfp_sfi_bitmap = NULL, }; @@ -463,8 +454,9 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, struct enetc_cbd cbd = {.cmd = 0}; struct streamid_data *si_data; struct streamid_conf *si_conf; - u16 data_size; dma_addr_t dma; + u16 data_size; + void *tmp; int port; int err; @@ -485,21 +477,11 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, cbd.status_flags = 0; data_size = sizeof(struct streamid_data); - si_data = kzalloc(data_size, __GFP_DMA | GFP_KERNEL); - if (!si_data) + tmp = enetc_cbd_alloc_data_mem(priv->si, &cbd, data_size, + &dma, (void *)&si_data); + if (!tmp) return -ENOMEM; - cbd.length = cpu_to_le16(data_size); - dma = dma_map_single(&priv->si->pdev->dev, si_data, - data_size, DMA_FROM_DEVICE); - if (dma_mapping_error(&priv->si->pdev->dev, dma)) { - netdev_err(priv->si->ndev, "DMA mapping failed!\n"); - err = -ENOMEM; - goto out; - } - - cbd.addr[0] = cpu_to_le32(lower_32_bits(dma)); - cbd.addr[1] = cpu_to_le32(upper_32_bits(dma)); eth_broadcast_addr(si_data->dmac); si_data->vid_vidm_tg = (ENETC_CBDR_SID_VID_MASK + ((0x3 << 14) | ENETC_CBDR_SID_VIDM)); @@ -520,11 +502,6 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, goto out; /* Enable the entry overwrite again incase space flushed by hardware */ - memset(&cbd, 0, sizeof(cbd)); - - cbd.index = cpu_to_le16((u16)sid->index); - cbd.cmd = 0; - cbd.cls = BDCR_CMD_STREAM_IDENTIFY; cbd.status_flags = 0; si_conf->en = 0x80; @@ -537,11 +514,6 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, memset(si_data, 0, data_size); - cbd.length = cpu_to_le16(data_size); - - cbd.addr[0] = cpu_to_le32(lower_32_bits(dma)); - cbd.addr[1] = cpu_to_le32(upper_32_bits(dma)); - /* VIDM default to be 1. * VID Match. If set (b1) then the VID must match, otherwise * any VID is considered a match. VIDM setting is only used @@ -561,10 +533,7 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, err = enetc_send_cmd(priv->si, &cbd); out: - if (!dma_mapping_error(&priv->si->pdev->dev, dma)) - dma_unmap_single(&priv->si->pdev->dev, dma, data_size, DMA_FROM_DEVICE); - - kfree(si_data); + enetc_cbd_free_data_mem(priv->si, data_size, tmp, &dma); return err; } @@ -635,6 +604,7 @@ static int enetc_streamcounter_hw_get(struct enetc_ndev_priv *priv, struct sfi_counter_data *data_buf; dma_addr_t dma; u16 data_size; + void *tmp; int err; cbd.index = cpu_to_le16((u16)index); @@ -643,21 +613,11 @@ static int enetc_streamcounter_hw_get(struct enetc_ndev_priv *priv, cbd.status_flags = 0; data_size = sizeof(struct sfi_counter_data); - data_buf = kzalloc(data_size, __GFP_DMA | GFP_KERNEL); - if (!data_buf) - return -ENOMEM; - - dma = dma_map_single(&priv->si->pdev->dev, data_buf, - data_size, DMA_FROM_DEVICE); - if (dma_mapping_error(&priv->si->pdev->dev, dma)) { - netdev_err(priv->si->ndev, "DMA mapping failed!\n"); - err = -ENOMEM; - goto exit; - } - cbd.addr[0] = cpu_to_le32(lower_32_bits(dma)); - cbd.addr[1] = cpu_to_le32(upper_32_bits(dma)); - cbd.length = cpu_to_le16(data_size); + tmp = enetc_cbd_alloc_data_mem(priv->si, &cbd, data_size, + &dma, (void *)&data_buf); + if (!tmp) + return -ENOMEM; err = enetc_send_cmd(priv->si, &cbd); if (err) @@ -684,7 +644,8 @@ static int enetc_streamcounter_hw_get(struct enetc_ndev_priv *priv, data_buf->flow_meter_dropl; exit: - kfree(data_buf); + enetc_cbd_free_data_mem(priv->si, data_size, tmp, &dma); + return err; } @@ -726,6 +687,7 @@ static int enetc_streamgate_hw_set(struct enetc_ndev_priv *priv, dma_addr_t dma; u16 data_size; int err, i; + void *tmp; u64 now; cbd.index = cpu_to_le16(sgi->index); @@ -772,24 +734,10 @@ static int enetc_streamgate_hw_set(struct enetc_ndev_priv *priv, sgcl_config->acl_len = (sgi->num_entries - 1) & 0x3; data_size = struct_size(sgcl_data, sgcl, sgi->num_entries); - - sgcl_data = kzalloc(data_size, __GFP_DMA | GFP_KERNEL); - if (!sgcl_data) - return -ENOMEM; - - cbd.length = cpu_to_le16(data_size); - - dma = dma_map_single(&priv->si->pdev->dev, - sgcl_data, data_size, - DMA_FROM_DEVICE); - if (dma_mapping_error(&priv->si->pdev->dev, dma)) { - netdev_err(priv->si->ndev, "DMA mapping failed!\n"); - kfree(sgcl_data); + tmp = enetc_cbd_alloc_data_mem(priv->si, &cbd, data_size, + &dma, (void *)&sgcl_data); + if (!tmp) return -ENOMEM; - } - - cbd.addr[0] = cpu_to_le32(lower_32_bits(dma)); - cbd.addr[1] = cpu_to_le32(upper_32_bits(dma)); sgce = &sgcl_data->sgcl[0]; @@ -844,8 +792,7 @@ static int enetc_streamgate_hw_set(struct enetc_ndev_priv *priv, err = enetc_send_cmd(priv->si, &cbd); exit: - kfree(sgcl_data); - + enetc_cbd_free_data_mem(priv->si, data_size, tmp, &dma); return err; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 796133de527e..11227f51404c 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2797,7 +2797,7 @@ static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable) int ret = 0; if (enable) { - ret = phy_init_eee(ndev->phydev, 0); + ret = phy_init_eee(ndev->phydev, false); if (ret) return ret; diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index af99017a5453..7d49c28215f3 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -101,7 +101,6 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable) u32 val, tempval; struct timespec64 ts; u64 ns; - val = 0; if (fep->pps_enable == enable) return 0; diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index 266e562bd67a..ef8058a17188 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -14,6 +14,7 @@ #include <linux/acpi.h> #include <linux/acpi_mdio.h> +#include <linux/clk.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/mdio.h> @@ -36,9 +37,10 @@ struct tgec_mdio_controller { } __packed; #define MDIO_STAT_ENC BIT(6) -#define MDIO_STAT_CLKDIV(x) (((x>>1) & 0xff) << 8) +#define MDIO_STAT_CLKDIV(x) (((x) & 0x1ff) << 7) #define MDIO_STAT_BSY BIT(0) #define MDIO_STAT_RD_ER BIT(1) +#define MDIO_STAT_PRE_DIS BIT(5) #define MDIO_CTL_DEV_ADDR(x) (x & 0x1f) #define MDIO_CTL_PORT_ADDR(x) ((x & 0x1f) << 5) #define MDIO_CTL_PRE_DIS BIT(10) @@ -50,6 +52,8 @@ struct tgec_mdio_controller { struct mdio_fsl_priv { struct tgec_mdio_controller __iomem *mdio_base; + struct clk *enet_clk; + u32 mdc_freq; bool is_little_endian; bool has_a009885; bool has_a011043; @@ -254,6 +258,50 @@ irq_restore: return ret; } +static int xgmac_mdio_set_mdc_freq(struct mii_bus *bus) +{ + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; + struct device *dev = bus->parent; + u32 mdio_stat, div; + + if (device_property_read_u32(dev, "clock-frequency", &priv->mdc_freq)) + return 0; + + priv->enet_clk = devm_clk_get(dev, NULL); + if (IS_ERR(priv->enet_clk)) { + dev_err(dev, "Input clock unknown, not changing MDC frequency"); + return PTR_ERR(priv->enet_clk); + } + + div = ((clk_get_rate(priv->enet_clk) / priv->mdc_freq) - 1) / 2; + if (div < 5 || div > 0x1ff) { + dev_err(dev, "Requested MDC frequency is out of range, ignoring"); + return -EINVAL; + } + + mdio_stat = xgmac_read32(®s->mdio_stat, priv->is_little_endian); + mdio_stat &= ~MDIO_STAT_CLKDIV(0x1ff); + mdio_stat |= MDIO_STAT_CLKDIV(div); + xgmac_write32(mdio_stat, ®s->mdio_stat, priv->is_little_endian); + return 0; +} + +static void xgmac_mdio_set_suppress_preamble(struct mii_bus *bus) +{ + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; + struct device *dev = bus->parent; + u32 mdio_stat; + + if (!device_property_read_bool(dev, "suppress-preamble")) + return; + + mdio_stat = xgmac_read32(®s->mdio_stat, priv->is_little_endian); + mdio_stat |= MDIO_STAT_PRE_DIS; + xgmac_write32(mdio_stat, ®s->mdio_stat, priv->is_little_endian); +} + static int xgmac_mdio_probe(struct platform_device *pdev) { struct fwnode_handle *fwnode; @@ -273,7 +321,7 @@ static int xgmac_mdio_probe(struct platform_device *pdev) return -EINVAL; } - bus = mdiobus_alloc_size(sizeof(struct mdio_fsl_priv)); + bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(struct mdio_fsl_priv)); if (!bus) return -ENOMEM; @@ -284,13 +332,11 @@ static int xgmac_mdio_probe(struct platform_device *pdev) bus->probe_capabilities = MDIOBUS_C22_C45; snprintf(bus->id, MII_BUS_ID_SIZE, "%pa", &res->start); - /* Set the PHY base address */ priv = bus->priv; - priv->mdio_base = ioremap(res->start, resource_size(res)); - if (!priv->mdio_base) { - ret = -ENOMEM; - goto err_ioremap; - } + priv->mdio_base = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!priv->mdio_base) + return -ENOMEM; /* For both ACPI and DT cases, endianness of MDIO controller * needs to be specified using "little-endian" property. @@ -303,6 +349,12 @@ static int xgmac_mdio_probe(struct platform_device *pdev) priv->has_a011043 = device_property_read_bool(&pdev->dev, "fsl,erratum-a011043"); + xgmac_mdio_set_suppress_preamble(bus); + + ret = xgmac_mdio_set_mdc_freq(bus); + if (ret) + return ret; + fwnode = pdev->dev.fwnode; if (is_of_node(fwnode)) ret = of_mdiobus_register(bus, to_of_node(fwnode)); @@ -312,32 +364,12 @@ static int xgmac_mdio_probe(struct platform_device *pdev) ret = -EINVAL; if (ret) { dev_err(&pdev->dev, "cannot register MDIO bus\n"); - goto err_registration; + return ret; } platform_set_drvdata(pdev, bus); return 0; - -err_registration: - iounmap(priv->mdio_base); - -err_ioremap: - mdiobus_free(bus); - - return ret; -} - -static int xgmac_mdio_remove(struct platform_device *pdev) -{ - struct mii_bus *bus = platform_get_drvdata(pdev); - struct mdio_fsl_priv *priv = bus->priv; - - mdiobus_unregister(bus); - iounmap(priv->mdio_base); - mdiobus_free(bus); - - return 0; } static const struct of_device_id xgmac_mdio_match[] = { @@ -364,7 +396,6 @@ static struct platform_driver xgmac_mdio_driver = { .acpi_match_table = xgmac_acpi_match, }, .probe = xgmac_mdio_probe, - .remove = xgmac_mdio_remove, }; module_platform_driver(xgmac_mdio_driver); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 54e51c8221b8..6cafee55efc3 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -857,8 +857,7 @@ static int gve_alloc_qpls(struct gve_priv *priv) int i, j; int err; - /* Raw addressing means no QPLs */ - if (priv->queue_format == GVE_GQI_RDA_FORMAT) + if (num_qpls == 0) return 0; priv->qpls = kvcalloc(num_qpls, sizeof(*priv->qpls), GFP_KERNEL); @@ -901,8 +900,7 @@ static void gve_free_qpls(struct gve_priv *priv) int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv); int i; - /* Raw addressing means no QPLs */ - if (priv->queue_format == GVE_GQI_RDA_FORMAT) + if (num_qpls == 0) return; kvfree(priv->qpl_cfg.qpl_id_map); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 9298fbecb31a..6f18c9a03231 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -167,6 +167,7 @@ struct hnae3_handle; struct hnae3_queue { void __iomem *io_base; + void __iomem *mem_base; struct hnae3_ae_algo *ae_algo; struct hnae3_handle *handle; int tqp_index; /* index in a handle */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index babc5d7a3b52..0b8a73c40b12 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2028,9 +2028,73 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring, return bd_num; } +static void hns3_tx_push_bd(struct hns3_enet_ring *ring, int num) +{ +#define HNS3_BYTES_PER_64BIT 8 + + struct hns3_desc desc[HNS3_MAX_PUSH_BD_NUM] = {}; + int offset = 0; + + /* make sure everything is visible to device before + * excuting tx push or updating doorbell + */ + dma_wmb(); + + do { + int idx = (ring->next_to_use - num + ring->desc_num) % + ring->desc_num; + + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_push++; + u64_stats_update_end(&ring->syncp); + memcpy(&desc[offset], &ring->desc[idx], + sizeof(struct hns3_desc)); + offset++; + } while (--num); + + __iowrite64_copy(ring->tqp->mem_base, desc, + (sizeof(struct hns3_desc) * HNS3_MAX_PUSH_BD_NUM) / + HNS3_BYTES_PER_64BIT); + + io_stop_wc(); +} + +static void hns3_tx_mem_doorbell(struct hns3_enet_ring *ring) +{ +#define HNS3_MEM_DOORBELL_OFFSET 64 + + __le64 bd_num = cpu_to_le64((u64)ring->pending_buf); + + /* make sure everything is visible to device before + * excuting tx push or updating doorbell + */ + dma_wmb(); + + __iowrite64_copy(ring->tqp->mem_base + HNS3_MEM_DOORBELL_OFFSET, + &bd_num, 1); + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_mem_doorbell += ring->pending_buf; + u64_stats_update_end(&ring->syncp); + + io_stop_wc(); +} + static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, bool doorbell) { + struct net_device *netdev = ring_to_netdev(ring); + struct hns3_nic_priv *priv = netdev_priv(netdev); + + /* when tx push is enabled, the packet whose number of BD below + * HNS3_MAX_PUSH_BD_NUM can be pushed directly. + */ + if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num && + !ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) { + hns3_tx_push_bd(ring, num); + WRITE_ONCE(ring->last_to_use, ring->next_to_use); + return; + } + ring->pending_buf += num; if (!doorbell) { @@ -2038,11 +2102,12 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, return; } - if (!ring->pending_buf) - return; + if (ring->tqp->mem_base) + hns3_tx_mem_doorbell(ring); + else + writel(ring->pending_buf, + ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG); - writel(ring->pending_buf, - ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG); ring->pending_buf = 0; WRITE_ONCE(ring->last_to_use, ring->next_to_use); } @@ -2732,6 +2797,9 @@ static void hns3_dump_queue_stats(struct net_device *ndev, "seg_pkt_cnt: %llu, tx_more: %llu, restart_queue: %llu, tx_busy: %llu\n", tx_ring->stats.seg_pkt_cnt, tx_ring->stats.tx_more, tx_ring->stats.restart_queue, tx_ring->stats.tx_busy); + + netdev_info(ndev, "tx_push: %llu, tx_mem_doorbell: %llu\n", + tx_ring->stats.tx_push, tx_ring->stats.tx_mem_doorbell); } static void hns3_dump_queue_reg(struct net_device *ndev, @@ -5094,6 +5162,9 @@ static void hns3_state_init(struct hnae3_handle *handle) set_bit(HNS3_NIC_STATE_INITED, &priv->state); + if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps)) + set_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state); + if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index a05a0c7423ce..4a3253692dcc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -7,6 +7,7 @@ #include <linux/dim.h> #include <linux/if_vlan.h> #include <net/page_pool.h> +#include <asm/barrier.h> #include "hnae3.h" @@ -25,9 +26,12 @@ enum hns3_nic_state { HNS3_NIC_STATE2_RESET_REQUESTED, HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, + HNS3_NIC_STATE_TX_PUSH_ENABLE, HNS3_NIC_STATE_MAX }; +#define HNS3_MAX_PUSH_BD_NUM 2 + #define HNS3_RING_RX_RING_BASEADDR_L_REG 0x00000 #define HNS3_RING_RX_RING_BASEADDR_H_REG 0x00004 #define HNS3_RING_RX_RING_BD_NUM_REG 0x00008 @@ -410,6 +414,8 @@ struct ring_stats { u64 tx_pkts; u64 tx_bytes; u64 tx_more; + u64 tx_push; + u64 tx_mem_doorbell; u64 restart_queue; u64 tx_busy; u64 tx_copy; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index c06c39ece80d..6469238ae090 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -23,6 +23,8 @@ static const struct hns3_stats hns3_txq_stats[] = { HNS3_TQP_STAT("packets", tx_pkts), HNS3_TQP_STAT("bytes", tx_bytes), HNS3_TQP_STAT("more", tx_more), + HNS3_TQP_STAT("push", tx_push), + HNS3_TQP_STAT("mem_doorbell", tx_mem_doorbell), HNS3_TQP_STAT("wake", restart_queue), HNS3_TQP_STAT("busy", tx_busy), HNS3_TQP_STAT("copy", tx_copy), diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 24f7afacae02..78d0498bdabc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1643,6 +1643,7 @@ static int hclge_config_gro(struct hclge_dev *hdev) static int hclge_alloc_tqps(struct hclge_dev *hdev) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); struct hclge_comm_tqp *tqp; int i; @@ -1676,6 +1677,14 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev) (i - HCLGE_TQP_MAX_SIZE_DEV_V2) * HCLGE_TQP_REG_SIZE; + /* when device supports tx push and has device memory, + * the queue can execute push mode or doorbell mode on + * device memory. + */ + if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps)) + tqp->q.mem_base = hdev->hw.hw.mem_base + + HCLGE_TQP_MEM_OFFSET(hdev, i); + tqp++; } @@ -11008,8 +11017,6 @@ static void hclge_uninit_client_instance(struct hnae3_client *client, static int hclge_dev_mem_map(struct hclge_dev *hdev) { -#define HCLGE_MEM_BAR 4 - struct pci_dev *pdev = hdev->pdev; struct hclge_hw *hw = &hdev->hw; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index adfb26e79262..fc92ae385e30 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -169,6 +169,14 @@ enum HLCGE_PORT_TYPE { #define HCLGE_VECTOR0_ALL_MSIX_ERR_B 6U #define HCLGE_TRIGGER_IMP_RESET_B 7U +#define HCLGE_TQP_MEM_SIZE 0x10000 +#define HCLGE_MEM_BAR 4 +/* in the bar4, the first half is for roce, and the second half is for nic */ +#define HCLGE_NIC_MEM_OFFSET(hdev) \ + (pci_resource_len((hdev)->pdev, HCLGE_MEM_BAR) >> 1) +#define HCLGE_TQP_MEM_OFFSET(hdev, i) \ + (HCLGE_NIC_MEM_OFFSET(hdev) + HCLGE_TQP_MEM_SIZE * (i)) + #define HCLGE_MAC_DEFAULT_FRAME \ (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN) #define HCLGE_MAC_MIN_FRAME 64 @@ -1060,11 +1068,6 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue) return tqp->index; } -static inline bool hclge_is_reset_pending(struct hclge_dev *hdev) -{ - return !!hdev->reset_pending; -} - int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport); int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex); int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 21442a9bb996..93389bec8d89 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -321,6 +321,7 @@ static int hclgevf_get_pf_media_type(struct hclgevf_dev *hdev) static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); struct hclge_comm_tqp *tqp; int i; @@ -354,6 +355,14 @@ static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev) (i - HCLGEVF_TQP_MAX_SIZE_DEV_V2) * HCLGEVF_TQP_REG_SIZE; + /* when device supports tx push and has device memory, + * the queue can execute push mode or doorbell mode on + * device memory. + */ + if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps)) + tqp->q.mem_base = hdev->hw.hw.mem_base + + HCLGEVF_TQP_MEM_OFFSET(hdev, i); + tqp++; } @@ -2546,8 +2555,6 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client, static int hclgevf_dev_mem_map(struct hclgevf_dev *hdev) { -#define HCLGEVF_MEM_BAR 4 - struct pci_dev *pdev = hdev->pdev; struct hclgevf_hw *hw = &hdev->hw; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 502ca1ce1a90..4b00fd44f118 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -96,6 +96,14 @@ #define HCLGEVF_RSS_IND_TBL_SIZE 512 +#define HCLGEVF_TQP_MEM_SIZE 0x10000 +#define HCLGEVF_MEM_BAR 4 +/* in the bar4, the first half is for roce, and the second half is for nic */ +#define HCLGEVF_NIC_MEM_OFFSET(hdev) \ + (pci_resource_len((hdev)->pdev, HCLGEVF_MEM_BAR) >> 1) +#define HCLGEVF_TQP_MEM_OFFSET(hdev, i) \ + (HCLGEVF_NIC_MEM_OFFSET(hdev) + HCLGEVF_TQP_MEM_SIZE * (i)) + #define HCLGEVF_MAC_MAX_FRAME 9728 #define HCLGEVF_STATS_TIMER_INTERVAL 36U diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a42aeb555f34..6fb3437f68e0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7388,9 +7388,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) resource_size_t flash_start, flash_len; static int cards_found; u16 aspm_disable_flag = 0; - int bars, i, err, pci_using_dac; u16 eeprom_data = 0; u16 eeprom_apme_mask = E1000_EEPROM_APME; + int bars, i, err; s32 ret_val = 0; if (ei->flags2 & FLAG2_DISABLE_ASPM_L0S) @@ -7404,17 +7404,11 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } bars = pci_select_bars(pdev, IORESOURCE_MEM); @@ -7550,10 +7544,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_UNICAST_FLT; - if (pci_using_dac) { - netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= NETIF_F_HIGHDMA; - } + netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= NETIF_F_HIGHDMA; /* MTU range: 68 - max_hw_frame_size */ netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 80c5cecaf2b5..55c6bce5da61 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -854,6 +854,10 @@ struct i40e_vsi { u64 tx_force_wb; u64 rx_buf_failed; u64 rx_page_failed; + u64 rx_page_reuse; + u64 rx_page_alloc; + u64 rx_page_waive; + u64 rx_page_busy; /* These are containers of ring pointers, allocated at run-time */ struct i40e_ring **rx_rings; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 7abef88801fb..42439f725aa4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -769,7 +769,7 @@ static bool i40e_asq_done(struct i40e_hw *hw) } /** - * i40e_asq_send_command_atomic - send command to Admin Queue + * i40e_asq_send_command_atomic_exec - send command to Admin Queue * @hw: pointer to the hw struct * @desc: prefilled descriptor describing the command (non DMA mem) * @buff: buffer to use for indirect commands @@ -780,11 +780,13 @@ static bool i40e_asq_done(struct i40e_hw *hw) * This is the main send command driver routine for the Admin Queue send * queue. It runs the queue, cleans the queue, etc **/ -i40e_status -i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ u16 buff_size, - struct i40e_asq_cmd_details *cmd_details, - bool is_atomic_context) +static i40e_status +i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context) { i40e_status status = 0; struct i40e_dma_mem *dma_buff = NULL; @@ -794,8 +796,6 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, u16 retval = 0; u32 val = 0; - mutex_lock(&hw->aq.asq_mutex); - if (hw->aq.asq.count == 0) { i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: Admin queue not initialized.\n"); @@ -969,6 +969,36 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, } asq_send_command_error: + return status; +} + +/** + * i40e_asq_send_command_atomic - send command to Admin Queue + * @hw: pointer to the hw struct + * @desc: prefilled descriptor describing the command (non DMA mem) + * @buff: buffer to use for indirect commands + * @buff_size: size of buffer for indirect commands + * @cmd_details: pointer to command details structure + * @is_atomic_context: is the function called in an atomic context? + * + * Acquires the lock and calls the main send command execution + * routine. + **/ +i40e_status +i40e_asq_send_command_atomic(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context) +{ + i40e_status status; + + mutex_lock(&hw->aq.asq_mutex); + status = i40e_asq_send_command_atomic_exec(hw, desc, buff, buff_size, + cmd_details, + is_atomic_context); + mutex_unlock(&hw->aq.asq_mutex); return status; } @@ -983,6 +1013,52 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, } /** + * i40e_asq_send_command_atomic_v2 - send command to Admin Queue + * @hw: pointer to the hw struct + * @desc: prefilled descriptor describing the command (non DMA mem) + * @buff: buffer to use for indirect commands + * @buff_size: size of buffer for indirect commands + * @cmd_details: pointer to command details structure + * @is_atomic_context: is the function called in an atomic context? + * @aq_status: pointer to Admin Queue status return value + * + * Acquires the lock and calls the main send command execution + * routine. Returns the last Admin Queue status in aq_status + * to avoid race conditions in access to hw->aq.asq_last_status. + **/ +i40e_status +i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context, + enum i40e_admin_queue_err *aq_status) +{ + i40e_status status; + + mutex_lock(&hw->aq.asq_mutex); + status = i40e_asq_send_command_atomic_exec(hw, desc, buff, + buff_size, + cmd_details, + is_atomic_context); + if (aq_status) + *aq_status = hw->aq.asq_last_status; + mutex_unlock(&hw->aq.asq_mutex); + return status; +} + +i40e_status +i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status) +{ + return i40e_asq_send_command_atomic_v2(hw, desc, buff, buff_size, + cmd_details, true, aq_status); +} + +/** * i40e_fill_default_direct_cmd_desc - AQ descriptor helper function * @desc: pointer to the temp descriptor (non DMA mem) * @opcode: the opcode can be used to decide which flags to turn off or on diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 9ddeb015eb7e..6aefffd83615 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1899,8 +1899,9 @@ i40e_status i40e_aq_add_vsi(struct i40e_hw *hw, desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); - status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info, - sizeof(vsi_ctx->info), cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info, + sizeof(vsi_ctx->info), + cmd_details, true); if (status) goto aq_add_vsi_exit; @@ -2287,8 +2288,9 @@ i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw, desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); - status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info, - sizeof(vsi_ctx->info), cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info, + sizeof(vsi_ctx->info), + cmd_details, true); vsi_ctx->vsis_allocated = le16_to_cpu(resp->vsi_used); vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); @@ -2632,33 +2634,28 @@ get_veb_exit: } /** - * i40e_aq_add_macvlan - * @hw: pointer to the hw struct - * @seid: VSI for the mac address + * i40e_prepare_add_macvlan * @mv_list: list of macvlans to be added + * @desc: pointer to AQ descriptor structure * @count: length of the list - * @cmd_details: pointer to command details structure or NULL + * @seid: VSI for the mac address * - * Add MAC/VLAN addresses to the HW filtering + * Internal helper function that prepares the add macvlan request + * and returns the buffer size. **/ -i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, - struct i40e_aqc_add_macvlan_element_data *mv_list, - u16 count, struct i40e_asq_cmd_details *cmd_details) +static u16 +i40e_prepare_add_macvlan(struct i40e_aqc_add_macvlan_element_data *mv_list, + struct i40e_aq_desc *desc, u16 count, u16 seid) { - struct i40e_aq_desc desc; struct i40e_aqc_macvlan *cmd = - (struct i40e_aqc_macvlan *)&desc.params.raw; - i40e_status status; + (struct i40e_aqc_macvlan *)&desc->params.raw; u16 buf_size; int i; - if (count == 0 || !mv_list || !hw) - return I40E_ERR_PARAM; - buf_size = count * sizeof(*mv_list); /* prep the rest of the request */ - i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_macvlan); + i40e_fill_default_direct_cmd_desc(desc, i40e_aqc_opc_add_macvlan); cmd->num_addresses = cpu_to_le16(count); cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid); cmd->seid[1] = 0; @@ -2669,14 +2666,71 @@ i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, mv_list[i].flags |= cpu_to_le16(I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC); - desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + desc->flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); if (buf_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc->flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - status = i40e_asq_send_command(hw, &desc, mv_list, buf_size, - cmd_details); + return buf_size; +} - return status; +/** + * i40e_aq_add_macvlan + * @hw: pointer to the hw struct + * @seid: VSI for the mac address + * @mv_list: list of macvlans to be added + * @count: length of the list + * @cmd_details: pointer to command details structure or NULL + * + * Add MAC/VLAN addresses to the HW filtering + **/ +i40e_status +i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_add_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + u16 buf_size; + + if (count == 0 || !mv_list || !hw) + return I40E_ERR_PARAM; + + buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid); + + return i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size, + cmd_details, true); +} + +/** + * i40e_aq_add_macvlan_v2 + * @hw: pointer to the hw struct + * @seid: VSI for the mac address + * @mv_list: list of macvlans to be added + * @count: length of the list + * @cmd_details: pointer to command details structure or NULL + * @aq_status: pointer to Admin Queue status return value + * + * Add MAC/VLAN addresses to the HW filtering. + * The _v2 version returns the last Admin Queue status in aq_status + * to avoid race conditions in access to hw->aq.asq_last_status. + * It also calls _v2 versions of asq_send_command functions to + * get the aq_status on the stack. + **/ +i40e_status +i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_add_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status) +{ + struct i40e_aq_desc desc; + u16 buf_size; + + if (count == 0 || !mv_list || !hw) + return I40E_ERR_PARAM; + + buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid); + + return i40e_asq_send_command_atomic_v2(hw, &desc, mv_list, buf_size, + cmd_details, true, aq_status); } /** @@ -2715,13 +2769,59 @@ i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, if (buf_size > I40E_AQ_LARGE_BUF) desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - status = i40e_asq_send_command(hw, &desc, mv_list, buf_size, - cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size, + cmd_details, true); return status; } /** + * i40e_aq_remove_macvlan_v2 + * @hw: pointer to the hw struct + * @seid: VSI for the mac address + * @mv_list: list of macvlans to be removed + * @count: length of the list + * @cmd_details: pointer to command details structure or NULL + * @aq_status: pointer to Admin Queue status return value + * + * Remove MAC/VLAN addresses from the HW filtering. + * The _v2 version returns the last Admin Queue status in aq_status + * to avoid race conditions in access to hw->aq.asq_last_status. + * It also calls _v2 versions of asq_send_command functions to + * get the aq_status on the stack. + **/ +i40e_status +i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_remove_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status) +{ + struct i40e_aqc_macvlan *cmd; + struct i40e_aq_desc desc; + u16 buf_size; + + if (count == 0 || !mv_list || !hw) + return I40E_ERR_PARAM; + + buf_size = count * sizeof(*mv_list); + + /* prep the rest of the request */ + i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_macvlan); + cmd = (struct i40e_aqc_macvlan *)&desc.params.raw; + cmd->num_addresses = cpu_to_le16(count); + cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid); + cmd->seid[1] = 0; + cmd->seid[2] = 0; + + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + if (buf_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + + return i40e_asq_send_command_atomic_v2(hw, &desc, mv_list, buf_size, + cmd_details, true, aq_status); +} + +/** * i40e_mirrorrule_op - Internal helper function to add/delete mirror rule * @hw: pointer to the hw struct * @opcode: AQ opcode for add or delete mirror rule @@ -3868,7 +3968,8 @@ i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, cmd->seid = cpu_to_le16(seid); - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, NULL, 0, + cmd_details, true); return status; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 1e57cc8c47d7..90fff05fbd2b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -275,9 +275,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->rx_stats.alloc_page_failed, rx_ring->rx_stats.alloc_buff_failed); dev_info(&pf->pdev->dev, - " rx_rings[%i]: rx_stats: realloc_count = %lld, page_reuse_count = %lld\n", + " rx_rings[%i]: rx_stats: realloc_count = 0, page_reuse_count = %lld\n", i, - rx_ring->rx_stats.realloc_count, rx_ring->rx_stats.page_reuse_count); dev_info(&pf->pdev->dev, " rx_rings[%i]: size = %i\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 091f36adbbe1..e48499624d22 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -295,6 +295,10 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = { I40E_VSI_STAT("tx_busy", tx_busy), I40E_VSI_STAT("rx_alloc_fail", rx_buf_failed), I40E_VSI_STAT("rx_pg_alloc_fail", rx_page_failed), + I40E_VSI_STAT("rx_cache_reuse", rx_page_reuse), + I40E_VSI_STAT("rx_cache_alloc", rx_page_alloc), + I40E_VSI_STAT("rx_cache_waive", rx_page_waive), + I40E_VSI_STAT("rx_cache_busy", rx_page_busy), }; /* These PF_STATs might look like duplicates of some NETDEV_STATs, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0c4b7dfb3b35..9b7ce6d9a92b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -773,6 +773,7 @@ void i40e_update_veb_stats(struct i40e_veb *veb) **/ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) { + u64 rx_page, rx_buf, rx_reuse, rx_alloc, rx_waive, rx_busy; struct i40e_pf *pf = vsi->back; struct rtnl_link_stats64 *ons; struct rtnl_link_stats64 *ns; /* netdev stats */ @@ -780,7 +781,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) struct i40e_eth_stats *es; /* device's eth stats */ u64 tx_restart, tx_busy; struct i40e_ring *p; - u64 rx_page, rx_buf; u64 bytes, packets; unsigned int start; u64 tx_linearize; @@ -806,6 +806,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) tx_restart = tx_busy = tx_linearize = tx_force_wb = 0; rx_page = 0; rx_buf = 0; + rx_reuse = 0; + rx_alloc = 0; + rx_waive = 0; + rx_busy = 0; rcu_read_lock(); for (q = 0; q < vsi->num_queue_pairs; q++) { /* locate Tx ring */ @@ -839,6 +843,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rx_p += packets; rx_buf += p->rx_stats.alloc_buff_failed; rx_page += p->rx_stats.alloc_page_failed; + rx_reuse += p->rx_stats.page_reuse_count; + rx_alloc += p->rx_stats.page_alloc_count; + rx_waive += p->rx_stats.page_waive_count; + rx_busy += p->rx_stats.page_busy_count; if (i40e_enabled_xdp_vsi(vsi)) { /* locate XDP ring */ @@ -866,6 +874,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) vsi->tx_force_wb = tx_force_wb; vsi->rx_page_failed = rx_page; vsi->rx_buf_failed = rx_buf; + vsi->rx_page_reuse = rx_reuse; + vsi->rx_page_alloc = rx_alloc; + vsi->rx_page_waive = rx_waive; + vsi->rx_page_busy = rx_busy; ns->rx_packets = rx_p; ns->rx_bytes = rx_b; @@ -2143,19 +2155,19 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, int num_del, int *retval) { struct i40e_hw *hw = &vsi->back->hw; + enum i40e_admin_queue_err aq_status; i40e_status aq_ret; - int aq_err; - aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, list, num_del, NULL); - aq_err = hw->aq.asq_last_status; + aq_ret = i40e_aq_remove_macvlan_v2(hw, vsi->seid, list, num_del, NULL, + &aq_status); /* Explicitly ignore and do not report when firmware returns ENOENT */ - if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { + if (aq_ret && !(aq_status == I40E_AQ_RC_ENOENT)) { *retval = -EIO; dev_info(&vsi->back->pdev->dev, "ignoring delete macvlan error on %s, err %s, aq_err %s\n", vsi_name, i40e_stat_str(hw, aq_ret), - i40e_aq_str(hw, aq_err)); + i40e_aq_str(hw, aq_status)); } } @@ -2178,10 +2190,10 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, int num_add) { struct i40e_hw *hw = &vsi->back->hw; - int aq_err, fcnt; + enum i40e_admin_queue_err aq_status; + int fcnt; - i40e_aq_add_macvlan(hw, vsi->seid, list, num_add, NULL); - aq_err = hw->aq.asq_last_status; + i40e_aq_add_macvlan_v2(hw, vsi->seid, list, num_add, NULL, &aq_status); fcnt = i40e_update_filter_state(num_add, list, add_head); if (fcnt != num_add) { @@ -2189,17 +2201,19 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, promiscuous mode forced on\n", - i40e_aq_str(hw, aq_err), vsi_name); + i40e_aq_str(hw, aq_status), vsi_name); } else if (vsi->type == I40E_VSI_SRIOV || vsi->type == I40E_VSI_VMDQ1 || vsi->type == I40E_VSI_VMDQ2) { dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n", - i40e_aq_str(hw, aq_err), vsi_name, vsi_name); + i40e_aq_str(hw, aq_status), vsi_name, + vsi_name); } else { dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, incorrect VSI type: %i.\n", - i40e_aq_str(hw, aq_err), vsi_name, vsi->type); + i40e_aq_str(hw, aq_status), vsi_name, + vsi->type); } } } @@ -12722,7 +12736,8 @@ static int i40e_set_features(struct net_device *netdev, else i40e_vlan_stripping_disable(vsi); - if (!(features & NETIF_F_HW_TC) && pf->num_cloud_filters) { + if (!(features & NETIF_F_HW_TC) && + (netdev->features & NETIF_F_HW_TC) && pf->num_cloud_filters) { dev_err(&pf->pdev->dev, "Offloaded tc filters active, can't turn hw_tc_offload off"); return -EINVAL; @@ -13478,6 +13493,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->features &= ~NETIF_F_HW_TC; + if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, hw->mac.perm_addr); @@ -15341,12 +15358,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* set up for high or low dma */ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; } /* set up pci connections */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 9241b6005ad3..ebdcde6f1aeb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -27,10 +27,25 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details); i40e_status +i40e_asq_send_command_v2(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status); +i40e_status i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details, bool is_atomic_context); +i40e_status +i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context, + enum i40e_admin_queue_err *aq_status); /* debug function for adminq */ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, @@ -150,9 +165,19 @@ i40e_status i40e_aq_get_veb_parameters(struct i40e_hw *hw, i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 vsi_id, struct i40e_aqc_add_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details); +i40e_status +i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_add_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status); i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id, struct i40e_aqc_remove_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details); +i40e_status +i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_remove_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status); i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list, struct i40e_asq_cmd_details *cmd_details, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 66cc79500c10..0eae5858f2fe 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -830,8 +830,6 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) i40e_clean_tx_ring(tx_ring); kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; - kfree(tx_ring->xsk_descs); - tx_ring->xsk_descs = NULL; if (tx_ring->desc) { dma_free_coherent(tx_ring->dev, tx_ring->size, @@ -1382,8 +1380,6 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, new_buff->page_offset = old_buff->page_offset; new_buff->pagecnt_bias = old_buff->pagecnt_bias; - rx_ring->rx_stats.page_reuse_count++; - /* clear contents of buffer_info */ old_buff->page = NULL; } @@ -1433,13 +1429,6 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) if (!tx_ring->tx_bi) goto err; - if (ring_is_xdp(tx_ring)) { - tx_ring->xsk_descs = kcalloc(I40E_MAX_NUM_DESCRIPTORS, sizeof(*tx_ring->xsk_descs), - GFP_KERNEL); - if (!tx_ring->xsk_descs) - goto err; - } - u64_stats_init(&tx_ring->syncp); /* round up to nearest 4K */ @@ -1463,8 +1452,6 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) return 0; err: - kfree(tx_ring->xsk_descs); - tx_ring->xsk_descs = NULL; kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; return -ENOMEM; @@ -1675,6 +1662,8 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, return false; } + rx_ring->rx_stats.page_alloc_count++; + /* map page for use */ dma = dma_map_page_attrs(rx_ring->dev, page, 0, i40e_rx_pg_size(rx_ring), @@ -1982,32 +1971,43 @@ static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb, /** * i40e_can_reuse_rx_page - Determine if page can be reused for another Rx * @rx_buffer: buffer containing the page + * @rx_stats: rx stats structure for the rx ring * @rx_buffer_pgcnt: buffer page refcount pre xdp_do_redirect() call * * If page is reusable, we have a green light for calling i40e_reuse_rx_page, * which will assign the current buffer to the buffer that next_to_alloc is * pointing to; otherwise, the DMA mapping needs to be destroyed and - * page freed + * page freed. + * + * rx_stats will be updated to indicate whether the page was waived + * or busy if it could not be reused. */ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, + struct i40e_rx_queue_stats *rx_stats, int rx_buffer_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; /* Is any reuse possible? */ - if (!dev_page_is_reusable(page)) + if (!dev_page_is_reusable(page)) { + rx_stats->page_waive_count++; return false; + } #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) { + rx_stats->page_busy_count++; return false; + } #else #define I40E_LAST_OFFSET \ (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) - if (rx_buffer->page_offset > I40E_LAST_OFFSET) + if (rx_buffer->page_offset > I40E_LAST_OFFSET) { + rx_stats->page_busy_count++; return false; + } #endif /* If we have drained the page fragment pool we need to update @@ -2237,7 +2237,7 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer, int rx_buffer_pgcnt) { - if (i40e_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { + if (i40e_can_reuse_rx_page(rx_buffer, &rx_ring->rx_stats, rx_buffer_pgcnt)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); } else { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index bfc2845c99d1..c471c2da313c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -298,7 +298,9 @@ struct i40e_rx_queue_stats { u64 alloc_page_failed; u64 alloc_buff_failed; u64 page_reuse_count; - u64 realloc_count; + u64 page_alloc_count; + u64 page_waive_count; + u64 page_busy_count; }; enum i40e_ring_state_t { @@ -390,7 +392,6 @@ struct i40e_ring { u16 rx_offset; struct xdp_rxq_info xdp_rxq; struct xsk_buff_pool *xsk_pool; - struct xdp_desc *xsk_descs; /* For storing descriptors in the AF_XDP ZC path */ } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 945b1bb9c6f4..5a997b0d07d8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -241,21 +241,25 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) { + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; struct sk_buff *skb; + net_prefetch(xdp->data_meta); + /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - xdp->data_end - xdp->data_hard_start, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) goto out; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } out: xsk_buff_free(xdp); @@ -467,11 +471,11 @@ static void i40e_set_rs_bit(struct i40e_ring *xdp_ring) **/ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) { - struct xdp_desc *descs = xdp_ring->xsk_descs; + struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs; u32 nb_pkts, nb_processed = 0; unsigned int total_bytes = 0; - nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget); + nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget); if (!nb_pkts) return true; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8125b9120615..b0bd95c85480 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4368,12 +4368,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; } err = pci_request_regions(pdev, iavf_driver_name); diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index c36faa7d1471..389fff70d22e 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -18,8 +18,12 @@ ice-y := ice_main.o \ ice_txrx_lib.o \ ice_txrx.o \ ice_fltr.o \ + ice_pf_vsi_vlan_ops.o \ + ice_vsi_vlan_ops.o \ + ice_vsi_vlan_lib.o \ ice_fdir.o \ ice_ethtool_fdir.o \ + ice_vlan_mode.o \ ice_flex_pipe.o \ ice_flow.o \ ice_idc.o \ @@ -29,8 +33,12 @@ ice-y := ice_main.o \ ice_ethtool.o \ ice_repr.o \ ice_tc_lib.o -ice-$(CONFIG_PCI_IOV) += ice_virtchnl_allowlist.o -ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice_virtchnl_fdir.o +ice-$(CONFIG_PCI_IOV) += \ + ice_virtchnl_allowlist.o \ + ice_virtchnl_fdir.o \ + ice_sriov.o \ + ice_vf_vsi_vlan_ops.o \ + ice_virtchnl_pf.o ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index a9fa701aaa95..8f40f6f9b8eb 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -72,6 +72,7 @@ #include "ice_repr.h" #include "ice_eswitch.h" #include "ice_lag.h" +#include "ice_vsi_vlan_ops.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -368,6 +369,8 @@ struct ice_vsi { u8 irqs_ready:1; u8 current_isup:1; /* Sync 'link up' logging */ u8 stat_offsets_loaded:1; + struct ice_vsi_vlan_ops inner_vlan_ops; + struct ice_vsi_vlan_ops outer_vlan_ops; u16 num_vlan; /* queue information */ @@ -468,7 +471,6 @@ enum ice_pf_flags { ICE_FLAG_FD_ENA, ICE_FLAG_PTP_SUPPORTED, /* PTP is supported by NVM */ ICE_FLAG_PTP, /* PTP is enabled by software */ - ICE_FLAG_AUX_ENA, ICE_FLAG_ADV_FEATURES, ICE_FLAG_TC_MQPRIO, /* support for Multi queue TC */ ICE_FLAG_CLS_FLOWER, @@ -482,6 +484,7 @@ enum ice_pf_flags { ICE_FLAG_LEGACY_RX, ICE_FLAG_VF_TRUE_PROMISC_ENA, ICE_FLAG_MDD_AUTO_RESET_VF, + ICE_FLAG_VF_VLAN_PRUNING, ICE_FLAG_LINK_LENIENT_MODE_ENA, ICE_FLAG_PLUG_AUX_DEV, ICE_PF_FLAGS_NBITS /* must be last */ @@ -887,7 +890,6 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) { if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) { set_bit(ICE_FLAG_RDMA_ENA, pf->flags); - set_bit(ICE_FLAG_AUX_ENA, pf->flags); set_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags); } } @@ -900,6 +902,5 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { ice_unplug_aux_dev(pf); clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - clear_bit(ICE_FLAG_AUX_ENA, pf->flags); } #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index ad1dcfa5ff65..fd8ee5b7f596 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -226,6 +226,15 @@ struct ice_aqc_get_sw_cfg_resp_elem { #define ICE_AQC_GET_SW_CONF_RESP_IS_VF BIT(15) }; +/* Set Port parameters, (direct, 0x0203) */ +struct ice_aqc_set_port_params { + __le16 cmd_flags; +#define ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA BIT(2) + __le16 bad_frame_vsi; + __le16 swid; + u8 reserved[10]; +}; + /* These resource type defines are used for all switch resource * commands where a resource type is required, such as: * Get Resource Allocation command (indirect 0x0204) @@ -283,6 +292,40 @@ struct ice_aqc_alloc_free_res_elem { struct ice_aqc_res_elem elem[]; }; +/* Request buffer for Set VLAN Mode AQ command (indirect 0x020C) */ +struct ice_aqc_set_vlan_mode { + u8 reserved; + u8 l2tag_prio_tagging; +#define ICE_AQ_VLAN_PRIO_TAG_S 0 +#define ICE_AQ_VLAN_PRIO_TAG_M (0x7 << ICE_AQ_VLAN_PRIO_TAG_S) +#define ICE_AQ_VLAN_PRIO_TAG_NOT_SUPPORTED 0x0 +#define ICE_AQ_VLAN_PRIO_TAG_STAG 0x1 +#define ICE_AQ_VLAN_PRIO_TAG_OUTER_CTAG 0x2 +#define ICE_AQ_VLAN_PRIO_TAG_OUTER_VLAN 0x3 +#define ICE_AQ_VLAN_PRIO_TAG_INNER_CTAG 0x4 +#define ICE_AQ_VLAN_PRIO_TAG_MAX 0x4 +#define ICE_AQ_VLAN_PRIO_TAG_ERROR 0x7 + u8 l2tag_reserved[64]; + u8 rdma_packet; +#define ICE_AQ_VLAN_RDMA_TAG_S 0 +#define ICE_AQ_VLAN_RDMA_TAG_M (0x3F << ICE_AQ_VLAN_RDMA_TAG_S) +#define ICE_AQ_SVM_VLAN_RDMA_PKT_FLAG_SETTING 0x10 +#define ICE_AQ_DVM_VLAN_RDMA_PKT_FLAG_SETTING 0x1A + u8 rdma_reserved[2]; + u8 mng_vlan_prot_id; +#define ICE_AQ_VLAN_MNG_PROTOCOL_ID_OUTER 0x10 +#define ICE_AQ_VLAN_MNG_PROTOCOL_ID_INNER 0x11 + u8 prot_id_reserved[30]; +}; + +/* Response buffer for Get VLAN Mode AQ command (indirect 0x020D) */ +struct ice_aqc_get_vlan_mode { + u8 vlan_mode; +#define ICE_AQ_VLAN_MODE_DVM_ENA BIT(0) + u8 l2tag_prio_tagging; + u8 reserved[98]; +}; + /* Add VSI (indirect 0x0210) * Update VSI (indirect 0x0211) * Get VSI (indirect 0x0212) @@ -343,108 +386,113 @@ struct ice_aqc_vsi_props { #define ICE_AQ_VSI_SW_FLAG_SRC_PRUNE BIT(7) u8 sw_flags2; #define ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_S 0 -#define ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M \ - (0xF << ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_S) +#define ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M (0xF << ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_S) #define ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA BIT(0) #define ICE_AQ_VSI_SW_FLAG_LAN_ENA BIT(4) u8 veb_stat_id; #define ICE_AQ_VSI_SW_VEB_STAT_ID_S 0 -#define ICE_AQ_VSI_SW_VEB_STAT_ID_M (0x1F << ICE_AQ_VSI_SW_VEB_STAT_ID_S) +#define ICE_AQ_VSI_SW_VEB_STAT_ID_M (0x1F << ICE_AQ_VSI_SW_VEB_STAT_ID_S) #define ICE_AQ_VSI_SW_VEB_STAT_ID_VALID BIT(5) /* security section */ u8 sec_flags; #define ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD BIT(0) #define ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF BIT(2) -#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S 4 -#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_M (0xF << ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S) +#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S 4 +#define ICE_AQ_VSI_SEC_TX_PRUNE_ENA_M (0xF << ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S) #define ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA BIT(0) u8 sec_reserved; /* VLAN section */ - __le16 pvid; /* VLANS include priority bits */ - u8 pvlan_reserved[2]; - u8 vlan_flags; -#define ICE_AQ_VSI_VLAN_MODE_S 0 -#define ICE_AQ_VSI_VLAN_MODE_M (0x3 << ICE_AQ_VSI_VLAN_MODE_S) -#define ICE_AQ_VSI_VLAN_MODE_UNTAGGED 0x1 -#define ICE_AQ_VSI_VLAN_MODE_TAGGED 0x2 -#define ICE_AQ_VSI_VLAN_MODE_ALL 0x3 -#define ICE_AQ_VSI_PVLAN_INSERT_PVID BIT(2) -#define ICE_AQ_VSI_VLAN_EMOD_S 3 -#define ICE_AQ_VSI_VLAN_EMOD_M (0x3 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_STR_BOTH (0x0 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_STR_UP (0x1 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_STR (0x2 << ICE_AQ_VSI_VLAN_EMOD_S) -#define ICE_AQ_VSI_VLAN_EMOD_NOTHING (0x3 << ICE_AQ_VSI_VLAN_EMOD_S) - u8 pvlan_reserved2[3]; + __le16 port_based_inner_vlan; /* VLANS include priority bits */ + u8 inner_vlan_reserved[2]; + u8 inner_vlan_flags; +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_S 0 +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_M (0x3 << ICE_AQ_VSI_INNER_VLAN_TX_MODE_S) +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED 0x1 +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTTAGGED 0x2 +#define ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL 0x3 +#define ICE_AQ_VSI_INNER_VLAN_INSERT_PVID BIT(2) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_S 3 +#define ICE_AQ_VSI_INNER_VLAN_EMODE_M (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH (0x0 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR_UP (0x1 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_STR (0x2 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) +#define ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING (0x3 << ICE_AQ_VSI_INNER_VLAN_EMODE_S) + u8 inner_vlan_reserved2[3]; /* ingress egress up sections */ __le32 ingress_table; /* bitmap, 3 bits per up */ -#define ICE_AQ_VSI_UP_TABLE_UP0_S 0 -#define ICE_AQ_VSI_UP_TABLE_UP0_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP0_S) -#define ICE_AQ_VSI_UP_TABLE_UP1_S 3 -#define ICE_AQ_VSI_UP_TABLE_UP1_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP1_S) -#define ICE_AQ_VSI_UP_TABLE_UP2_S 6 -#define ICE_AQ_VSI_UP_TABLE_UP2_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP2_S) -#define ICE_AQ_VSI_UP_TABLE_UP3_S 9 -#define ICE_AQ_VSI_UP_TABLE_UP3_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP3_S) -#define ICE_AQ_VSI_UP_TABLE_UP4_S 12 -#define ICE_AQ_VSI_UP_TABLE_UP4_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP4_S) -#define ICE_AQ_VSI_UP_TABLE_UP5_S 15 -#define ICE_AQ_VSI_UP_TABLE_UP5_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP5_S) -#define ICE_AQ_VSI_UP_TABLE_UP6_S 18 -#define ICE_AQ_VSI_UP_TABLE_UP6_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP6_S) -#define ICE_AQ_VSI_UP_TABLE_UP7_S 21 -#define ICE_AQ_VSI_UP_TABLE_UP7_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP7_S) +#define ICE_AQ_VSI_UP_TABLE_UP0_S 0 +#define ICE_AQ_VSI_UP_TABLE_UP0_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP0_S) +#define ICE_AQ_VSI_UP_TABLE_UP1_S 3 +#define ICE_AQ_VSI_UP_TABLE_UP1_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP1_S) +#define ICE_AQ_VSI_UP_TABLE_UP2_S 6 +#define ICE_AQ_VSI_UP_TABLE_UP2_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP2_S) +#define ICE_AQ_VSI_UP_TABLE_UP3_S 9 +#define ICE_AQ_VSI_UP_TABLE_UP3_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP3_S) +#define ICE_AQ_VSI_UP_TABLE_UP4_S 12 +#define ICE_AQ_VSI_UP_TABLE_UP4_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP4_S) +#define ICE_AQ_VSI_UP_TABLE_UP5_S 15 +#define ICE_AQ_VSI_UP_TABLE_UP5_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP5_S) +#define ICE_AQ_VSI_UP_TABLE_UP6_S 18 +#define ICE_AQ_VSI_UP_TABLE_UP6_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP6_S) +#define ICE_AQ_VSI_UP_TABLE_UP7_S 21 +#define ICE_AQ_VSI_UP_TABLE_UP7_M (0x7 << ICE_AQ_VSI_UP_TABLE_UP7_S) __le32 egress_table; /* same defines as for ingress table */ /* outer tags section */ - __le16 outer_tag; - u8 outer_tag_flags; -#define ICE_AQ_VSI_OUTER_TAG_MODE_S 0 -#define ICE_AQ_VSI_OUTER_TAG_MODE_M (0x3 << ICE_AQ_VSI_OUTER_TAG_MODE_S) -#define ICE_AQ_VSI_OUTER_TAG_NOTHING 0x0 -#define ICE_AQ_VSI_OUTER_TAG_REMOVE 0x1 -#define ICE_AQ_VSI_OUTER_TAG_COPY 0x2 -#define ICE_AQ_VSI_OUTER_TAG_TYPE_S 2 -#define ICE_AQ_VSI_OUTER_TAG_TYPE_M (0x3 << ICE_AQ_VSI_OUTER_TAG_TYPE_S) -#define ICE_AQ_VSI_OUTER_TAG_NONE 0x0 -#define ICE_AQ_VSI_OUTER_TAG_STAG 0x1 -#define ICE_AQ_VSI_OUTER_TAG_VLAN_8100 0x2 -#define ICE_AQ_VSI_OUTER_TAG_VLAN_9100 0x3 -#define ICE_AQ_VSI_OUTER_TAG_INSERT BIT(4) -#define ICE_AQ_VSI_OUTER_TAG_ACCEPT_HOST BIT(6) - u8 outer_tag_reserved; + __le16 port_based_outer_vlan; + u8 outer_vlan_flags; +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_S 0 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_M (0x3 << ICE_AQ_VSI_OUTER_VLAN_EMODE_S) +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_BOTH 0x0 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_UP 0x1 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW 0x2 +#define ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING 0x3 +#define ICE_AQ_VSI_OUTER_TAG_TYPE_S 2 +#define ICE_AQ_VSI_OUTER_TAG_TYPE_M (0x3 << ICE_AQ_VSI_OUTER_TAG_TYPE_S) +#define ICE_AQ_VSI_OUTER_TAG_NONE 0x0 +#define ICE_AQ_VSI_OUTER_TAG_STAG 0x1 +#define ICE_AQ_VSI_OUTER_TAG_VLAN_8100 0x2 +#define ICE_AQ_VSI_OUTER_TAG_VLAN_9100 0x3 +#define ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT BIT(4) +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S 5 +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M (0x3 << ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTUNTAGGED 0x1 +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTTAGGED 0x2 +#define ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL 0x3 +#define ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC BIT(7) + u8 outer_vlan_reserved; /* queue mapping section */ __le16 mapping_flags; -#define ICE_AQ_VSI_Q_MAP_CONTIG 0x0 -#define ICE_AQ_VSI_Q_MAP_NONCONTIG BIT(0) +#define ICE_AQ_VSI_Q_MAP_CONTIG 0x0 +#define ICE_AQ_VSI_Q_MAP_NONCONTIG BIT(0) __le16 q_mapping[16]; -#define ICE_AQ_VSI_Q_S 0 -#define ICE_AQ_VSI_Q_M (0x7FF << ICE_AQ_VSI_Q_S) +#define ICE_AQ_VSI_Q_S 0 +#define ICE_AQ_VSI_Q_M (0x7FF << ICE_AQ_VSI_Q_S) __le16 tc_mapping[8]; -#define ICE_AQ_VSI_TC_Q_OFFSET_S 0 -#define ICE_AQ_VSI_TC_Q_OFFSET_M (0x7FF << ICE_AQ_VSI_TC_Q_OFFSET_S) -#define ICE_AQ_VSI_TC_Q_NUM_S 11 -#define ICE_AQ_VSI_TC_Q_NUM_M (0xF << ICE_AQ_VSI_TC_Q_NUM_S) +#define ICE_AQ_VSI_TC_Q_OFFSET_S 0 +#define ICE_AQ_VSI_TC_Q_OFFSET_M (0x7FF << ICE_AQ_VSI_TC_Q_OFFSET_S) +#define ICE_AQ_VSI_TC_Q_NUM_S 11 +#define ICE_AQ_VSI_TC_Q_NUM_M (0xF << ICE_AQ_VSI_TC_Q_NUM_S) /* queueing option section */ u8 q_opt_rss; -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_S 0 -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI 0x0 -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_PF 0x2 -#define ICE_AQ_VSI_Q_OPT_RSS_LUT_GBL 0x3 -#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S 2 -#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M (0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S) -#define ICE_AQ_VSI_Q_OPT_RSS_HASH_S 6 -#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_TPLZ (0x0 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_SYM_TPLZ (0x1 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_XOR (0x2 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) -#define ICE_AQ_VSI_Q_OPT_RSS_JHASH (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_S 0 +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI 0x0 +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_PF 0x2 +#define ICE_AQ_VSI_Q_OPT_RSS_LUT_GBL 0x3 +#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S 2 +#define ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M (0xF << ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_S) +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_S 6 +#define ICE_AQ_VSI_Q_OPT_RSS_HASH_M (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_TPLZ (0x0 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_SYM_TPLZ (0x1 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_XOR (0x2 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) +#define ICE_AQ_VSI_Q_OPT_RSS_JHASH (0x3 << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) u8 q_opt_tc; -#define ICE_AQ_VSI_Q_OPT_TC_OVR_S 0 -#define ICE_AQ_VSI_Q_OPT_TC_OVR_M (0x1F << ICE_AQ_VSI_Q_OPT_TC_OVR_S) -#define ICE_AQ_VSI_Q_OPT_PROF_TC_OVR BIT(7) +#define ICE_AQ_VSI_Q_OPT_TC_OVR_S 0 +#define ICE_AQ_VSI_Q_OPT_TC_OVR_M (0x1F << ICE_AQ_VSI_Q_OPT_TC_OVR_S) +#define ICE_AQ_VSI_Q_OPT_PROF_TC_OVR BIT(7) u8 q_opt_flags; -#define ICE_AQ_VSI_Q_OPT_PE_FLTR_EN BIT(0) +#define ICE_AQ_VSI_Q_OPT_PE_FLTR_EN BIT(0) u8 q_opt_reserved[3]; /* outer up section */ __le32 outer_up_table; /* same structure and defines as ingress tbl */ @@ -452,27 +500,27 @@ struct ice_aqc_vsi_props { __le16 sect_10_reserved; /* flow director section */ __le16 fd_options; -#define ICE_AQ_VSI_FD_ENABLE BIT(0) -#define ICE_AQ_VSI_FD_TX_AUTO_ENABLE BIT(1) -#define ICE_AQ_VSI_FD_PROG_ENABLE BIT(3) +#define ICE_AQ_VSI_FD_ENABLE BIT(0) +#define ICE_AQ_VSI_FD_TX_AUTO_ENABLE BIT(1) +#define ICE_AQ_VSI_FD_PROG_ENABLE BIT(3) __le16 max_fd_fltr_dedicated; __le16 max_fd_fltr_shared; __le16 fd_def_q; -#define ICE_AQ_VSI_FD_DEF_Q_S 0 -#define ICE_AQ_VSI_FD_DEF_Q_M (0x7FF << ICE_AQ_VSI_FD_DEF_Q_S) -#define ICE_AQ_VSI_FD_DEF_GRP_S 12 -#define ICE_AQ_VSI_FD_DEF_GRP_M (0x7 << ICE_AQ_VSI_FD_DEF_GRP_S) +#define ICE_AQ_VSI_FD_DEF_Q_S 0 +#define ICE_AQ_VSI_FD_DEF_Q_M (0x7FF << ICE_AQ_VSI_FD_DEF_Q_S) +#define ICE_AQ_VSI_FD_DEF_GRP_S 12 +#define ICE_AQ_VSI_FD_DEF_GRP_M (0x7 << ICE_AQ_VSI_FD_DEF_GRP_S) __le16 fd_report_opt; -#define ICE_AQ_VSI_FD_REPORT_Q_S 0 -#define ICE_AQ_VSI_FD_REPORT_Q_M (0x7FF << ICE_AQ_VSI_FD_REPORT_Q_S) -#define ICE_AQ_VSI_FD_DEF_PRIORITY_S 12 -#define ICE_AQ_VSI_FD_DEF_PRIORITY_M (0x7 << ICE_AQ_VSI_FD_DEF_PRIORITY_S) -#define ICE_AQ_VSI_FD_DEF_DROP BIT(15) +#define ICE_AQ_VSI_FD_REPORT_Q_S 0 +#define ICE_AQ_VSI_FD_REPORT_Q_M (0x7FF << ICE_AQ_VSI_FD_REPORT_Q_S) +#define ICE_AQ_VSI_FD_DEF_PRIORITY_S 12 +#define ICE_AQ_VSI_FD_DEF_PRIORITY_M (0x7 << ICE_AQ_VSI_FD_DEF_PRIORITY_S) +#define ICE_AQ_VSI_FD_DEF_DROP BIT(15) /* PASID section */ __le32 pasid_id; -#define ICE_AQ_VSI_PASID_ID_S 0 -#define ICE_AQ_VSI_PASID_ID_M (0xFFFFF << ICE_AQ_VSI_PASID_ID_S) -#define ICE_AQ_VSI_PASID_ID_VALID BIT(31) +#define ICE_AQ_VSI_PASID_ID_S 0 +#define ICE_AQ_VSI_PASID_ID_M (0xFFFFF << ICE_AQ_VSI_PASID_ID_S) +#define ICE_AQ_VSI_PASID_ID_VALID BIT(31) u8 reserved[24]; }; @@ -489,9 +537,13 @@ struct ice_aqc_add_get_recipe { struct ice_aqc_recipe_content { u8 rid; +#define ICE_AQ_RECIPE_ID_S 0 +#define ICE_AQ_RECIPE_ID_M (0x3F << ICE_AQ_RECIPE_ID_S) #define ICE_AQ_RECIPE_ID_IS_ROOT BIT(7) #define ICE_AQ_SW_ID_LKUP_IDX 0 u8 lkup_indx[5]; +#define ICE_AQ_RECIPE_LKUP_DATA_S 0 +#define ICE_AQ_RECIPE_LKUP_DATA_M (0x3F << ICE_AQ_RECIPE_LKUP_DATA_S) #define ICE_AQ_RECIPE_LKUP_IGNORE BIT(7) #define ICE_AQ_SW_ID_LKUP_MASK 0x00FF __le16 mask[5]; @@ -502,15 +554,25 @@ struct ice_aqc_recipe_content { u8 rsvd0[3]; u8 act_ctrl_join_priority; u8 act_ctrl_fwd_priority; +#define ICE_AQ_RECIPE_FWD_PRIORITY_S 0 +#define ICE_AQ_RECIPE_FWD_PRIORITY_M (0xF << ICE_AQ_RECIPE_FWD_PRIORITY_S) u8 act_ctrl; +#define ICE_AQ_RECIPE_ACT_NEED_PASS_L2 BIT(0) +#define ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2 BIT(1) #define ICE_AQ_RECIPE_ACT_INV_ACT BIT(2) +#define ICE_AQ_RECIPE_ACT_PRUNE_INDX_S 4 +#define ICE_AQ_RECIPE_ACT_PRUNE_INDX_M (0x3 << ICE_AQ_RECIPE_ACT_PRUNE_INDX_S) u8 rsvd1; __le32 dflt_act; +#define ICE_AQ_RECIPE_DFLT_ACT_S 0 +#define ICE_AQ_RECIPE_DFLT_ACT_M (0x7FFFF << ICE_AQ_RECIPE_DFLT_ACT_S) +#define ICE_AQ_RECIPE_DFLT_ACT_VALID BIT(31) }; struct ice_aqc_recipe_data_elem { u8 recipe_indx; u8 resp_bits; +#define ICE_AQ_RECIPE_WAS_UPDATED BIT(0) u8 rsvd0[2]; u8 recipe_bitmap[8]; u8 rsvd1[4]; @@ -1883,7 +1945,7 @@ struct ice_aqc_get_clear_fw_log { }; /* Download Package (indirect 0x0C40) */ -/* Also used for Update Package (indirect 0x0C42) */ +/* Also used for Update Package (indirect 0x0C41 and 0x0C42) */ struct ice_aqc_download_pkg { u8 flags; #define ICE_AQC_DOWNLOAD_PKG_LAST_BUF 0x01 @@ -2009,6 +2071,7 @@ struct ice_aq_desc { struct ice_aqc_sff_eeprom read_write_sff_param; struct ice_aqc_set_port_id_led set_port_id_led; struct ice_aqc_get_sw_cfg get_sw_conf; + struct ice_aqc_set_port_params set_port_params; struct ice_aqc_sw_rules sw_rules; struct ice_aqc_add_get_recipe add_get_recipe; struct ice_aqc_recipe_to_profile recipe_to_profile; @@ -2110,10 +2173,13 @@ enum ice_adminq_opc { /* internal switch commands */ ice_aqc_opc_get_sw_cfg = 0x0200, + ice_aqc_opc_set_port_params = 0x0203, /* Alloc/Free/Get Resources */ ice_aqc_opc_alloc_res = 0x0208, ice_aqc_opc_free_res = 0x0209, + ice_aqc_opc_set_vlan_mode_parameters = 0x020C, + ice_aqc_opc_get_vlan_mode_parameters = 0x020D, /* VSI commands */ ice_aqc_opc_add_vsi = 0x0210, @@ -2204,6 +2270,7 @@ enum ice_adminq_opc { /* package commands */ ice_aqc_opc_download_pkg = 0x0C40, + ice_aqc_opc_upload_section = 0x0C41, ice_aqc_opc_update_pkg = 0x0C42, ice_aqc_opc_get_pkg_info_list = 0x0C43, diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1a5ece3bce79..2360e6abdb1e 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -5,6 +5,7 @@ #include "ice_base.h" #include "ice_lib.h" #include "ice_dcb_lib.h" +#include "ice_virtchnl_pf.h" static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring) { @@ -418,8 +419,22 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ rlan_ctx.crcstrip = 1; - /* L2TSEL flag defines the reported L2 Tags in the receive descriptor */ - rlan_ctx.l2tsel = 1; + /* L2TSEL flag defines the reported L2 Tags in the receive descriptor + * and it needs to remain 1 for non-DVM capable configurations to not + * break backward compatibility for VF drivers. Setting this field to 0 + * will cause the single/outer VLAN tag to be stripped to the L2TAG2_2ND + * field in the Rx descriptor. Setting it to 1 allows the VLAN tag to + * be stripped in L2TAG1 of the Rx descriptor, which is where VFs will + * check for the tag + */ + if (ice_is_dvm_ena(hw)) + if (vsi->type == ICE_VSI_VF && + ice_vf_is_port_vlan_ena(&vsi->back->vf[vsi->vf_id])) + rlan_ctx.l2tsel = 1; + else + rlan_ctx.l2tsel = 0; + else + rlan_ctx.l2tsel = 1; rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index a6d7d3eff186..c57e5fc41cf8 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1518,16 +1518,27 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, /* When a package download is in process (i.e. when the firmware's * Global Configuration Lock resource is held), only the Download - * Package, Get Version, Get Package Info List and Release Resource - * (with resource ID set to Global Config Lock) AdminQ commands are - * allowed; all others must block until the package download completes - * and the Global Config Lock is released. See also - * ice_acquire_global_cfg_lock(). + * Package, Get Version, Get Package Info List, Upload Section, + * Update Package, Set Port Parameters, Get/Set VLAN Mode Parameters, + * Add Recipe, Set Recipes to Profile Association, Get Recipe, and Get + * Recipes to Profile Association, and Release Resource (with resource + * ID set to Global Config Lock) AdminQ commands are allowed; all others + * must block until the package download completes and the Global Config + * Lock is released. See also ice_acquire_global_cfg_lock(). */ switch (le16_to_cpu(desc->opcode)) { case ice_aqc_opc_download_pkg: case ice_aqc_opc_get_pkg_info_list: case ice_aqc_opc_get_ver: + case ice_aqc_opc_upload_section: + case ice_aqc_opc_update_pkg: + case ice_aqc_opc_set_port_params: + case ice_aqc_opc_get_vlan_mode_parameters: + case ice_aqc_opc_set_vlan_mode_parameters: + case ice_aqc_opc_add_recipe: + case ice_aqc_opc_recipe_to_profile: + case ice_aqc_opc_get_recipe: + case ice_aqc_opc_get_recipe_to_profile: break; case ice_aqc_opc_release_res: if (le16_to_cpu(cmd->res_id) == ICE_AQC_RES_ID_GLBL_LOCK) @@ -2737,6 +2748,34 @@ void ice_clear_pxe_mode(struct ice_hw *hw) } /** + * ice_aq_set_port_params - set physical port parameters. + * @pi: pointer to the port info struct + * @double_vlan: if set double VLAN is enabled + * @cd: pointer to command details structure or NULL + * + * Set Physical port parameters (0x0203) + */ +int +ice_aq_set_port_params(struct ice_port_info *pi, bool double_vlan, + struct ice_sq_cd *cd) + +{ + struct ice_aqc_set_port_params *cmd; + struct ice_hw *hw = pi->hw; + struct ice_aq_desc desc; + u16 cmd_flags = 0; + + cmd = &desc.params.set_port_params; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params); + if (double_vlan) + cmd_flags |= ICE_AQC_SET_P_PARAMS_DOUBLE_VLAN_ENA; + cmd->cmd_flags = cpu_to_le16(cmd_flags); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); +} + +/** * ice_get_link_speed_based_on_phy_type - returns link speed * @phy_type_low: lower part of phy_type * @phy_type_high: higher part of phy_type diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 1c57097ddf0b..d28749edd92f 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -85,6 +85,9 @@ int ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, struct ice_sq_cd *cd); int +ice_aq_set_port_params(struct ice_port_info *pi, bool double_vlan, + struct ice_sq_cd *cd); +int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index b94d8daeaa58..add90e75f05c 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -916,7 +916,8 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, return; /* Insert 802.1p priority into VLAN header */ - if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN) || + if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN || + first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) || skb->priority != TC_PRIO_CONTROL) { first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M; /* Mask the lower 3 bits to set the 802.1p priority */ @@ -925,7 +926,10 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ - first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; + if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) + first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; + else + first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; } } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 864692b157b6..e1cb6682eee2 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -115,9 +115,12 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; struct net_device *uplink_netdev = uplink_vsi->netdev; struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_vsi_vlan_ops *vlan_ops; bool rule_added = false; - ice_vsi_manage_vlan_stripping(ctrl_vsi, false); + vlan_ops = ice_get_compat_vsi_vlan_ops(ctrl_vsi); + if (vlan_ops->dis_stripping(ctrl_vsi)) + return -ENODEV; ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); @@ -126,7 +129,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) __dev_mc_unsync(uplink_netdev, NULL); netif_addr_unlock_bh(uplink_netdev); - if (ice_vsi_add_vlan(uplink_vsi, 0, ICE_FWD_TO_VSI)) + if (ice_vsi_add_vlan_zero(uplink_vsi)) goto err_def_rx; if (!ice_is_dflt_vsi_in_use(uplink_vsi->vsw)) { @@ -230,7 +233,7 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) goto err; } - if (ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI)) { + if (ice_vsi_add_vlan_zero(vsi)) { ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index e2e3ef7fba7f..a3492754d0d3 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -164,6 +164,7 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { ICE_PRIV_FLAG("vf-true-promisc-support", ICE_FLAG_VF_TRUE_PROMISC_ENA), ICE_PRIV_FLAG("mdd-auto-reset-vf", ICE_FLAG_MDD_AUTO_RESET_VF), + ICE_PRIV_FLAG("vf-vlan-pruning", ICE_FLAG_VF_VLAN_PRUNING), ICE_PRIV_FLAG("legacy-rx", ICE_FLAG_LEGACY_RX), }; @@ -1295,6 +1296,14 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) change_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags); ret = -EAGAIN; } + + if (test_bit(ICE_FLAG_VF_VLAN_PRUNING, change_flags) && + pf->num_alloc_vfs) { + dev_err(dev, "vf-vlan-pruning: VLAN pruning cannot be changed while VFs are active.\n"); + /* toggle bit back to previous state */ + change_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags); + ret = -EOPNOTSUPP; + } ethtool_exit: clear_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags); return ret; @@ -2803,6 +2812,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, /* clone ring and setup updated count */ xdp_rings[i] = *vsi->xdp_rings[i]; xdp_rings[i].count = new_tx_cnt; + xdp_rings[i].next_dd = ICE_RING_QUARTER(&xdp_rings[i]) - 1; + xdp_rings[i].next_rs = ICE_RING_QUARTER(&xdp_rings[i]) - 1; xdp_rings[i].desc = NULL; xdp_rings[i].tx_buf = NULL; err = ice_setup_tx_ring(&xdp_rings[i]); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 4deb2c9446ec..38fe0a7e6975 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -5,9 +5,17 @@ #include "ice_flex_pipe.h" #include "ice_flow.h" +/* For supporting double VLAN mode, it is necessary to enable or disable certain + * boost tcam entries. The metadata labels names that match the following + * prefixes will be saved to allow enabling double VLAN mode. + */ +#define ICE_DVM_PRE "BOOST_MAC_VLAN_DVM" /* enable these entries */ +#define ICE_SVM_PRE "BOOST_MAC_VLAN_SVM" /* disable these entries */ + /* To support tunneling entries by PF, the package will append the PF number to * the label; for example TNL_VXLAN_PF0, TNL_VXLAN_PF1, TNL_VXLAN_PF2, etc. */ +#define ICE_TNL_PRE "TNL_" static const struct ice_tunnel_type_scan tnls[] = { { TNL_VXLAN, "TNL_VXLAN_PF" }, { TNL_GENEVE, "TNL_GENEVE_PF" }, @@ -523,6 +531,55 @@ ice_enum_labels(struct ice_seg *ice_seg, u32 type, struct ice_pkg_enum *state, } /** + * ice_add_tunnel_hint + * @hw: pointer to the HW structure + * @label_name: label text + * @val: value of the tunnel port boost entry + */ +static void ice_add_tunnel_hint(struct ice_hw *hw, char *label_name, u16 val) +{ + if (hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) { + u16 i; + + for (i = 0; tnls[i].type != TNL_LAST; i++) { + size_t len = strlen(tnls[i].label_prefix); + + /* Look for matching label start, before continuing */ + if (strncmp(label_name, tnls[i].label_prefix, len)) + continue; + + /* Make sure this label matches our PF. Note that the PF + * character ('0' - '7') will be located where our + * prefix string's null terminator is located. + */ + if ((label_name[len] - '0') == hw->pf_id) { + hw->tnl.tbl[hw->tnl.count].type = tnls[i].type; + hw->tnl.tbl[hw->tnl.count].valid = false; + hw->tnl.tbl[hw->tnl.count].boost_addr = val; + hw->tnl.tbl[hw->tnl.count].port = 0; + hw->tnl.count++; + break; + } + } + } +} + +/** + * ice_add_dvm_hint + * @hw: pointer to the HW structure + * @val: value of the boost entry + * @enable: true if entry needs to be enabled, or false if needs to be disabled + */ +static void ice_add_dvm_hint(struct ice_hw *hw, u16 val, bool enable) +{ + if (hw->dvm_upd.count < ICE_DVM_MAX_ENTRIES) { + hw->dvm_upd.tbl[hw->dvm_upd.count].boost_addr = val; + hw->dvm_upd.tbl[hw->dvm_upd.count].enable = enable; + hw->dvm_upd.count++; + } +} + +/** * ice_init_pkg_hints * @hw: pointer to the HW structure * @ice_seg: pointer to the segment of the package scan (non-NULL) @@ -548,32 +605,23 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg) label_name = ice_enum_labels(ice_seg, ICE_SID_LBL_RXPARSER_TMEM, &state, &val); - while (label_name && hw->tnl.count < ICE_TUNNEL_MAX_ENTRIES) { - for (i = 0; tnls[i].type != TNL_LAST; i++) { - size_t len = strlen(tnls[i].label_prefix); + while (label_name) { + if (!strncmp(label_name, ICE_TNL_PRE, strlen(ICE_TNL_PRE))) + /* check for a tunnel entry */ + ice_add_tunnel_hint(hw, label_name, val); - /* Look for matching label start, before continuing */ - if (strncmp(label_name, tnls[i].label_prefix, len)) - continue; + /* check for a dvm mode entry */ + else if (!strncmp(label_name, ICE_DVM_PRE, strlen(ICE_DVM_PRE))) + ice_add_dvm_hint(hw, val, true); - /* Make sure this label matches our PF. Note that the PF - * character ('0' - '7') will be located where our - * prefix string's null terminator is located. - */ - if ((label_name[len] - '0') == hw->pf_id) { - hw->tnl.tbl[hw->tnl.count].type = tnls[i].type; - hw->tnl.tbl[hw->tnl.count].valid = false; - hw->tnl.tbl[hw->tnl.count].boost_addr = val; - hw->tnl.tbl[hw->tnl.count].port = 0; - hw->tnl.count++; - break; - } - } + /* check for a svm mode entry */ + else if (!strncmp(label_name, ICE_SVM_PRE, strlen(ICE_SVM_PRE))) + ice_add_dvm_hint(hw, val, false); label_name = ice_enum_labels(NULL, 0, &state, &val); } - /* Cache the appropriate boost TCAM entry pointers */ + /* Cache the appropriate boost TCAM entry pointers for tunnels */ for (i = 0; i < hw->tnl.count; i++) { ice_find_boost_entry(ice_seg, hw->tnl.tbl[i].boost_addr, &hw->tnl.tbl[i].boost_entry); @@ -583,6 +631,11 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg) hw->tnl.valid_count[hw->tnl.tbl[i].type]++; } } + + /* Cache the appropriate boost TCAM entry pointers for DVM and SVM */ + for (i = 0; i < hw->dvm_upd.count; i++) + ice_find_boost_entry(ice_seg, hw->dvm_upd.tbl[i].boost_addr, + &hw->dvm_upd.tbl[i].boost_entry); } /* Key creation */ @@ -874,6 +927,27 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, } /** + * ice_aq_upload_section + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer which will receive the section + * @buf_size: the size of the package buffer + * @cd: pointer to command details structure or NULL + * + * Upload Section (0x0C41) + */ +int +ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); +} + +/** * ice_aq_update_pkg * @hw: pointer to the hardware structure * @pkg_buf: the package cmd buffer @@ -957,25 +1031,21 @@ ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, } /** - * ice_update_pkg + * ice_update_pkg_no_lock * @hw: pointer to the hardware structure * @bufs: pointer to an array of buffers * @count: the number of buffers in the array - * - * Obtains change lock and updates package. */ -static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +static int +ice_update_pkg_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 count) { - u32 offset, info, i; - int status; - - status = ice_acquire_change_lock(hw, ICE_RES_WRITE); - if (status) - return status; + int status = 0; + u32 i; for (i = 0; i < count; i++) { struct ice_buf_hdr *bh = (struct ice_buf_hdr *)(bufs + i); bool last = ((i + 1) == count); + u32 offset, info; status = ice_aq_update_pkg(hw, bh, le16_to_cpu(bh->data_end), last, &offset, &info, NULL); @@ -987,6 +1057,27 @@ static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) } } + return status; +} + +/** + * ice_update_pkg + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + * + * Obtains change lock and updates package. + */ +static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +{ + int status; + + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + return status; + + status = ice_update_pkg_no_lock(hw, bufs, count); + ice_release_change_lock(hw); return status; @@ -1080,6 +1171,13 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) break; } + if (!status) { + status = ice_set_vlan_mode(hw); + if (status) + ice_debug(hw, ICE_DBG_PKG, "Failed to set VLAN mode: err %d\n", + status); + } + ice_release_global_cfg_lock(hw); return state; @@ -1117,6 +1215,7 @@ static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) { struct ice_buf_table *ice_buf_tbl; + int status; ice_debug(hw, ICE_DBG_PKG, "Segment format version: %d.%d.%d.%d\n", ice_seg->hdr.seg_format_ver.major, @@ -1133,8 +1232,12 @@ ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", le32_to_cpu(ice_buf_tbl->buf_count)); - return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, - le32_to_cpu(ice_buf_tbl->buf_count)); + status = ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, + le32_to_cpu(ice_buf_tbl->buf_count)); + + ice_post_pkg_dwnld_vlan_mode_cfg(hw); + + return status; } /** @@ -1897,7 +2000,7 @@ void ice_init_prof_result_bm(struct ice_hw *hw) * * Frees a package buffer */ -static void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld) +void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld) { devm_kfree(ice_hw_to_dev(hw), bld); } @@ -1997,6 +2100,43 @@ ice_pkg_buf_alloc_section(struct ice_buf_build *bld, u32 type, u16 size) } /** + * ice_pkg_buf_alloc_single_section + * @hw: pointer to the HW structure + * @type: the section type value + * @size: the size of the section to reserve (in bytes) + * @section: returns pointer to the section + * + * Allocates a package buffer with a single section. + * Note: all package contents must be in Little Endian form. + */ +struct ice_buf_build * +ice_pkg_buf_alloc_single_section(struct ice_hw *hw, u32 type, u16 size, + void **section) +{ + struct ice_buf_build *buf; + + if (!section) + return NULL; + + buf = ice_pkg_buf_alloc(hw); + if (!buf) + return NULL; + + if (ice_pkg_buf_reserve_section(buf, 1)) + goto ice_pkg_buf_alloc_single_section_err; + + *section = ice_pkg_buf_alloc_section(buf, type, size); + if (!*section) + goto ice_pkg_buf_alloc_single_section_err; + + return buf; + +ice_pkg_buf_alloc_single_section_err: + ice_pkg_buf_free(hw, buf); + return NULL; +} + +/** * ice_pkg_buf_get_active_sections * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) * @@ -2023,7 +2163,7 @@ static u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld) * * Return a pointer to the buffer's header */ -static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) +struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) { if (!bld) return NULL; @@ -2060,6 +2200,89 @@ ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, } /** + * ice_upd_dvm_boost_entry + * @hw: pointer to the HW structure + * @entry: pointer to double vlan boost entry info + */ +static int +ice_upd_dvm_boost_entry(struct ice_hw *hw, struct ice_dvm_entry *entry) +{ + struct ice_boost_tcam_section *sect_rx, *sect_tx; + int status = -ENOSPC; + struct ice_buf_build *bld; + u8 val, dc, nm; + + bld = ice_pkg_buf_alloc(hw); + if (!bld) + return -ENOMEM; + + /* allocate 2 sections, one for Rx parser, one for Tx parser */ + if (ice_pkg_buf_reserve_section(bld, 2)) + goto ice_upd_dvm_boost_entry_err; + + sect_rx = ice_pkg_buf_alloc_section(bld, ICE_SID_RXPARSER_BOOST_TCAM, + struct_size(sect_rx, tcam, 1)); + if (!sect_rx) + goto ice_upd_dvm_boost_entry_err; + sect_rx->count = cpu_to_le16(1); + + sect_tx = ice_pkg_buf_alloc_section(bld, ICE_SID_TXPARSER_BOOST_TCAM, + struct_size(sect_tx, tcam, 1)); + if (!sect_tx) + goto ice_upd_dvm_boost_entry_err; + sect_tx->count = cpu_to_le16(1); + + /* copy original boost entry to update package buffer */ + memcpy(sect_rx->tcam, entry->boost_entry, sizeof(*sect_rx->tcam)); + + /* re-write the don't care and never match bits accordingly */ + if (entry->enable) { + /* all bits are don't care */ + val = 0x00; + dc = 0xFF; + nm = 0x00; + } else { + /* disable, one never match bit, the rest are don't care */ + val = 0x00; + dc = 0xF7; + nm = 0x08; + } + + ice_set_key((u8 *)§_rx->tcam[0].key, sizeof(sect_rx->tcam[0].key), + &val, NULL, &dc, &nm, 0, sizeof(u8)); + + /* exact copy of entry to Tx section entry */ + memcpy(sect_tx->tcam, sect_rx->tcam, sizeof(*sect_tx->tcam)); + + status = ice_update_pkg_no_lock(hw, ice_pkg_buf(bld), 1); + +ice_upd_dvm_boost_entry_err: + ice_pkg_buf_free(hw, bld); + + return status; +} + +/** + * ice_set_dvm_boost_entries + * @hw: pointer to the HW structure + * + * Enable double vlan by updating the appropriate boost tcam entries. + */ +int ice_set_dvm_boost_entries(struct ice_hw *hw) +{ + int status; + u16 i; + + for (i = 0; i < hw->dvm_upd.count; i++) { + status = ice_upd_dvm_boost_entry(hw, &hw->dvm_upd.tbl[i]); + if (status) + return status; + } + + return 0; +} + +/** * ice_tunnel_idx_to_entry - convert linear index to the sparse one * @hw: pointer to the HW structure * @type: type of tunnel diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 6cbc29bcb02f..2fd5312494c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -89,6 +89,12 @@ ice_init_prof_result_bm(struct ice_hw *hw); int ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, unsigned long *bm, struct list_head *fv_list); +int +ice_pkg_buf_unreserve_section(struct ice_buf_build *bld, u16 count); +u16 ice_pkg_buf_get_free_space(struct ice_buf_build *bld); +int +ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, struct ice_sq_cd *cd); bool ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, enum ice_tunnel_type type); @@ -96,6 +102,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); +int ice_set_dvm_boost_entries(struct ice_hw *hw); /* Rx parser PTYPE functions */ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); @@ -119,4 +126,10 @@ void ice_fill_blk_tbls(struct ice_hw *hw); void ice_clear_hw_tbls(struct ice_hw *hw); void ice_free_hw_tbls(struct ice_hw *hw); int ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id); +struct ice_buf_build * +ice_pkg_buf_alloc_single_section(struct ice_hw *hw, u32 type, u16 size, + void **section); +struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld); +void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld); + #endif /* _ICE_FLEX_PIPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index fc087e0b5292..5735e9542a49 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -162,6 +162,7 @@ struct ice_meta_sect { #define ICE_SID_RXPARSER_MARKER_PTYPE 55 #define ICE_SID_RXPARSER_BOOST_TCAM 56 +#define ICE_SID_RXPARSER_METADATA_INIT 58 #define ICE_SID_TXPARSER_BOOST_TCAM 66 #define ICE_SID_XLT0_PE 80 @@ -442,6 +443,19 @@ struct ice_tunnel_table { u16 valid_count[__TNL_TYPE_CNT]; }; +struct ice_dvm_entry { + u16 boost_addr; + u16 enable; + struct ice_boost_tcam_entry *boost_entry; +}; + +#define ICE_DVM_MAX_ENTRIES 48 + +struct ice_dvm_table { + struct ice_dvm_entry tbl[ICE_DVM_MAX_ENTRIES]; + u16 count; +}; + struct ice_pkg_es { __le16 count; __le16 offset; @@ -662,4 +676,30 @@ enum ice_prof_type { ICE_PROF_TUN_ALL = 0x6, ICE_PROF_ALL = 0xFF, }; + +/* Number of bits/bytes contained in meta init entry. Note, this should be a + * multiple of 32 bits. + */ +#define ICE_META_INIT_BITS 192 +#define ICE_META_INIT_DW_CNT (ICE_META_INIT_BITS / (sizeof(__le32) * \ + BITS_PER_BYTE)) + +/* The meta init Flag field starts at this bit */ +#define ICE_META_FLAGS_ST 123 + +/* The entry and bit to check for Double VLAN Mode (DVM) support */ +#define ICE_META_VLAN_MODE_ENTRY 0 +#define ICE_META_FLAG_VLAN_MODE 60 +#define ICE_META_VLAN_MODE_BIT (ICE_META_FLAGS_ST + \ + ICE_META_FLAG_VLAN_MODE) + +struct ice_meta_init_entry { + __le32 bm[ICE_META_INIT_DW_CNT]; +}; + +struct ice_meta_init_section { + __le16 count; + __le16 offset; + struct ice_meta_init_entry entry; +}; #endif /* _ICE_FLEX_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index c29177c6bb9d..af57eb114966 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -203,21 +203,22 @@ ice_fltr_add_mac_to_list(struct ice_vsi *vsi, struct list_head *list, * ice_fltr_add_vlan_to_list - add VLAN filter info to exsisting list * @vsi: pointer to VSI struct * @list: list to add filter info to - * @vlan_id: VLAN ID to add - * @action: filter action + * @vlan: VLAN filter details */ static int ice_fltr_add_vlan_to_list(struct ice_vsi *vsi, struct list_head *list, - u16 vlan_id, enum ice_sw_fwd_act_type action) + struct ice_vlan *vlan) { struct ice_fltr_info info = { 0 }; info.flag = ICE_FLTR_TX; info.src_id = ICE_SRC_ID_VSI; info.lkup_type = ICE_SW_LKUP_VLAN; - info.fltr_act = action; + info.fltr_act = ICE_FWD_TO_VSI; info.vsi_handle = vsi->idx; - info.l_data.vlan.vlan_id = vlan_id; + info.l_data.vlan.vlan_id = vlan->vid; + info.l_data.vlan.tpid = vlan->tpid; + info.l_data.vlan.tpid_valid = true; return ice_fltr_add_entry_to_list(ice_pf_to_dev(vsi->back), &info, list); @@ -310,19 +311,17 @@ ice_fltr_prepare_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac, /** * ice_fltr_prepare_vlan - add or remove VLAN filter * @vsi: pointer to VSI struct - * @vlan_id: VLAN ID to add - * @action: action to be performed on filter match + * @vlan: VLAN filter details * @vlan_action: pointer to add or remove VLAN function */ static int -ice_fltr_prepare_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action, +ice_fltr_prepare_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan, int (*vlan_action)(struct ice_vsi *, struct list_head *)) { LIST_HEAD(tmp_list); int result; - if (ice_fltr_add_vlan_to_list(vsi, &tmp_list, vlan_id, action)) + if (ice_fltr_add_vlan_to_list(vsi, &tmp_list, vlan)) return -ENOMEM; result = vlan_action(vsi, &tmp_list); @@ -395,27 +394,21 @@ int ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, /** * ice_fltr_add_vlan - add single VLAN filter * @vsi: pointer to VSI struct - * @vlan_id: VLAN ID to add - * @action: action to be performed on filter match + * @vlan: VLAN filter details */ -int ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action) +int ice_fltr_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) { - return ice_fltr_prepare_vlan(vsi, vlan_id, action, - ice_fltr_add_vlan_list); + return ice_fltr_prepare_vlan(vsi, vlan, ice_fltr_add_vlan_list); } /** * ice_fltr_remove_vlan - remove VLAN filter * @vsi: pointer to VSI struct - * @vlan_id: filter VLAN to remove - * @action: action to remove + * @vlan: VLAN filter details */ -int ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action) +int ice_fltr_remove_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) { - return ice_fltr_prepare_vlan(vsi, vlan_id, action, - ice_fltr_remove_vlan_list); + return ice_fltr_prepare_vlan(vsi, vlan, ice_fltr_remove_vlan_list); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.h b/drivers/net/ethernet/intel/ice/ice_fltr.h index 3eb42479175f..0f3dbc308eec 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.h +++ b/drivers/net/ethernet/intel/ice/ice_fltr.h @@ -4,6 +4,8 @@ #ifndef _ICE_FLTR_H_ #define _ICE_FLTR_H_ +#include "ice_vlan.h" + void ice_fltr_free_list(struct device *dev, struct list_head *h); int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, @@ -32,12 +34,8 @@ ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action); int ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list); -int -ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vid, - enum ice_sw_fwd_act_type action); -int -ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vid, - enum ice_sw_fwd_act_type action); +int ice_fltr_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_fltr_remove_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); int ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index fc3580167e7b..73aa520317d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -79,7 +79,7 @@ int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) dev = ice_pf_to_dev(pf); - if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + if (!ice_is_rdma_ena(pf)) return -EINVAL; vsi = ice_get_main_vsi(pf); @@ -227,6 +227,11 @@ void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; + + qos->pfc_mode = dcbx_cfg->pfc_mode; + if (qos->pfc_mode == IIDC_DSCP_PFC_MODE) + for (i = 0; i < IIDC_MAX_DSCP_MAPPING; i++) + qos->dscp_map[i] = dcbx_cfg->dscp_map[i]; } EXPORT_SYMBOL_GPL(ice_get_qos_params); @@ -236,7 +241,7 @@ EXPORT_SYMBOL_GPL(ice_get_qos_params); */ static int ice_reserve_rdma_qvector(struct ice_pf *pf) { - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + if (ice_is_rdma_ena(pf)) { int index; index = ice_get_res(pf, pf->irq_tracker, pf->num_rdma_msix, @@ -274,7 +279,7 @@ int ice_plug_aux_dev(struct ice_pf *pf) /* if this PF doesn't support a technology that requires auxiliary * devices, then gracefully exit */ - if (!ice_is_aux_ena(pf)) + if (!ice_is_rdma_ena(pf)) return 0; iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); 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 85a612838a89..b3baf7c3f910 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -424,6 +424,8 @@ enum ice_rx_flex_desc_status_error_0_bits { enum ice_rx_flex_desc_status_error_1_bits { /* Note: These are predefined bit offsets */ ICE_RX_FLEX_DESC_STATUS1_NAT_S = 4, + /* [10:5] reserved */ + ICE_RX_FLEX_DESC_STATUS1_L2TAG2P_S = 11, ICE_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 53256aca27c7..2d15bb73a074 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -8,6 +8,7 @@ #include "ice_fltr.h" #include "ice_dcb_lib.h" #include "ice_devlink.h" +#include "ice_vsi_vlan_ops.h" /** * ice_vsi_type_str - maps VSI type enum to string equivalents @@ -732,14 +733,14 @@ bool ice_is_safe_mode(struct ice_pf *pf) } /** - * ice_is_aux_ena + * ice_is_rdma_ena * @pf: pointer to the PF struct * - * returns true if AUX devices/drivers are supported, false otherwise + * returns true if RDMA is currently supported, false otherwise */ -bool ice_is_aux_ena(struct ice_pf *pf) +bool ice_is_rdma_ena(struct ice_pf *pf) { - return test_bit(ICE_FLAG_AUX_ENA, pf->flags); + return test_bit(ICE_FLAG_RDMA_ENA, pf->flags); } /** @@ -838,11 +839,12 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) /** * ice_set_dflt_vsi_ctx - Set default VSI context before adding a VSI + * @hw: HW structure used to determine the VLAN mode of the device * @ctxt: the VSI context being set * * This initializes a default VSI context for all sections except the Queues. */ -static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) +static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) { u32 table = 0; @@ -853,13 +855,27 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE; /* Traffic from VSI can be sent to LAN */ ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; - /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy - * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all - * packets untagged/tagged. + /* allow all untagged/tagged packets by default on Tx */ + ctxt->info.inner_vlan_flags = ((ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL & + ICE_AQ_VSI_INNER_VLAN_TX_MODE_M) >> + ICE_AQ_VSI_INNER_VLAN_TX_MODE_S); + /* SVM - by default bits 3 and 4 in inner_vlan_flags are 0's which + * results in legacy behavior (show VLAN, DEI, and UP) in descriptor. + * + * DVM - leave inner VLAN in packet by default */ - ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL & - ICE_AQ_VSI_VLAN_MODE_M) >> - ICE_AQ_VSI_VLAN_MODE_S); + if (ice_is_dvm_ena(hw)) { + ctxt->info.inner_vlan_flags |= + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + ctxt->info.outer_vlan_flags = + (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M; + ctxt->info.outer_vlan_flags |= + (ICE_AQ_VSI_OUTER_TAG_VLAN_8100 << + ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M; + } /* Have 1:1 UP mapping for both ingress/egress tables */ table |= ICE_UP_TABLE_TRANSLATE(0, 0); table |= ICE_UP_TABLE_TRANSLATE(1, 1); @@ -1136,7 +1152,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; } - ice_set_dflt_vsi_ctx(ctxt); + ice_set_dflt_vsi_ctx(hw, ctxt); if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) ice_set_fd_vsi_ctx(ctxt, vsi); /* if the switch is in VEB mode, allow VSI loopback */ @@ -1168,25 +1184,6 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); } - /* enable/disable MAC and VLAN anti-spoof when spoofchk is on/off - * respectively - */ - if (vsi->type == ICE_VSI_VF) { - ctxt->info.valid_sections |= - cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); - if (pf->vf[vsi->vf_id].spoofchk) { - ctxt->info.sec_flags |= - ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); - } else { - ctxt->info.sec_flags &= - ~(ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S)); - } - } - /* Allow control frames out of main VSI */ if (vsi->type == ICE_VSI_PF) { ctxt->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; @@ -1431,6 +1428,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) */ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) { + bool dvm_ena = ice_is_dvm_ena(&vsi->back->hw); struct ice_pf *pf = vsi->back; struct device *dev; u16 i; @@ -1452,6 +1450,10 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; + if (dvm_ena) + ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG2; + else + ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG1; WRITE_ONCE(vsi->tx_rings[i], ring); } @@ -1763,62 +1765,6 @@ void ice_update_eth_stats(struct ice_vsi *vsi) } /** - * ice_vsi_add_vlan - Add VSI membership for given VLAN - * @vsi: the VSI being configured - * @vid: VLAN ID to be added - * @action: filter action to be performed on match - */ -int -ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - int err = 0; - - dev = ice_pf_to_dev(pf); - - if (!ice_fltr_add_vlan(vsi, vid, action)) { - vsi->num_vlan++; - } else { - err = -ENODEV; - dev_err(dev, "Failure Adding VLAN %d on VSI %i\n", vid, - vsi->vsi_num); - } - - return err; -} - -/** - * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN - * @vsi: the VSI being configured - * @vid: VLAN ID to be removed - * - * Returns 0 on success and negative on failure - */ -int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - int err; - - dev = ice_pf_to_dev(pf); - - err = ice_fltr_remove_vlan(vsi, vid, ICE_FWD_TO_VSI); - if (!err) { - vsi->num_vlan--; - } else if (err == -ENOENT) { - dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, error: %d\n", - vid, vsi->vsi_num, err); - err = 0; - } else { - dev_err(dev, "Error removing VLAN %d on vsi %i error: %d\n", - vid, vsi->vsi_num, err); - } - - return err; -} - -/** * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length * @vsi: VSI */ @@ -2146,95 +2092,6 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi) } /** - * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx - * @vsi: the VSI being changed - */ -int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) -{ - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx *ctxt; - int ret; - - ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - /* Here we are configuring the VSI to let the driver add VLAN tags by - * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag - * insertion happens in the Tx hot path, in ice_tx_map. - */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL; - - /* Preserve existing VLAN strip setting */ - ctxt->info.vlan_flags |= (vsi->info.vlan_flags & - ICE_AQ_VSI_VLAN_EMOD_M); - - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - - ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (ret) { - dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %s\n", - ret, ice_aq_str(hw->adminq.sq_last_status)); - goto out; - } - - vsi->info.vlan_flags = ctxt->info.vlan_flags; -out: - kfree(ctxt); - return ret; -} - -/** - * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx - * @vsi: the VSI being changed - * @ena: boolean value indicating if this is a enable or disable request - */ -int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) -{ - struct ice_hw *hw = &vsi->back->hw; - struct ice_vsi_ctx *ctxt; - int ret; - - /* do not allow modifying VLAN stripping when a port VLAN is configured - * on this VSI - */ - if (vsi->info.pvid) - return 0; - - ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - /* Here we are configuring what the VSI should do with the VLAN tag in - * the Rx packet. We can either leave the tag in the packet or put it in - * the Rx descriptor. - */ - if (ena) - /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH; - else - /* Disable stripping. Leave tag in packet */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; - - /* Allow all packets untagged/tagged */ - ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; - - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - - ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (ret) { - dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %s\n", - ena, ret, ice_aq_str(hw->adminq.sq_last_status)); - goto out; - } - - vsi->info.vlan_flags = ctxt->info.vlan_flags; -out: - kfree(ctxt); - return ret; -} - -/** * ice_vsi_start_all_rx_rings - start/enable all of a VSI's Rx rings * @vsi: the VSI whose rings are to be enabled * @@ -2327,61 +2184,6 @@ bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) return (vsi->info.sw_flags2 & ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA); } -/** - * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI - * @vsi: VSI to enable or disable VLAN pruning on - * @ena: set to true to enable VLAN pruning and false to disable it - * - * returns 0 if VSI is updated, negative otherwise - */ -int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) -{ - struct ice_vsi_ctx *ctxt; - struct ice_pf *pf; - int status; - - if (!vsi) - return -EINVAL; - - /* Don't enable VLAN pruning if the netdev is currently in promiscuous - * mode. VLAN pruning will be enabled when the interface exits - * promiscuous mode if any VLAN filters are active. - */ - if (vsi->netdev && vsi->netdev->flags & IFF_PROMISC && ena) - return 0; - - pf = vsi->back; - ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - ctxt->info = vsi->info; - - if (ena) - ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - else - ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); - - status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL); - if (status) { - netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %s\n", - ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, - status, ice_aq_str(pf->hw.adminq.sq_last_status)); - goto err_out; - } - - vsi->info.sw_flags2 = ctxt->info.sw_flags2; - - kfree(ctxt); - return 0; - -err_out: - kfree(ctxt); - return -EIO; -} - static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) { if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { @@ -2661,6 +2463,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_get_qs; + ice_vsi_init_vlan_ops(vsi); + switch (vsi->type) { case ICE_VSI_CTRL: case ICE_VSI_SWITCHDEV_CTRL: @@ -2681,17 +2485,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; - /* Always add VLAN ID 0 switch rule by default. This is needed - * in order to allow all untagged and 0 tagged priority traffic - * if Rx VLAN pruning is enabled. Also there are cases where we - * don't get the call to add VLAN 0 via ice_vlan_rx_add_vid() - * so this handles those cases (i.e. adding the PF to a bridge - * without the 8021q module loaded). - */ - ret = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI); - if (ret) - goto unroll_clear_rings; - ice_vsi_map_rings_to_vectors(vsi); /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ @@ -3324,6 +3117,8 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) if (vtype == ICE_VSI_VF) vf = &pf->vf[vsi->vf_id]; + ice_vsi_init_vlan_ops(vsi); + coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); if (!coalesce) @@ -4137,6 +3932,115 @@ int ice_set_link(struct ice_vsi *vsi, bool ena) } /** + * ice_vsi_add_vlan_zero - add VLAN 0 filter(s) for this VSI + * @vsi: VSI used to add VLAN filters + * + * In Single VLAN Mode (SVM), single VLAN filters via ICE_SW_LKUP_VLAN are based + * on the inner VLAN ID, so the VLAN TPID (i.e. 0x8100 or 0x888a8) doesn't + * matter. In Double VLAN Mode (DVM), outer/single VLAN filters via + * ICE_SW_LKUP_VLAN are based on the outer/single VLAN ID + VLAN TPID. + * + * For both modes add a VLAN 0 + no VLAN TPID filter to handle untagged traffic + * when VLAN pruning is enabled. Also, this handles VLAN 0 priority tagged + * traffic in SVM, since the VLAN TPID isn't part of filtering. + * + * If DVM is enabled then an explicit VLAN 0 + VLAN TPID filter needs to be + * added to allow VLAN 0 priority tagged traffic in DVM, since the VLAN TPID is + * part of filtering. + */ +int ice_vsi_add_vlan_zero(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct ice_vlan vlan; + int err; + + vlan = ICE_VLAN(0, 0, 0); + err = vlan_ops->add_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + /* in SVM both VLAN 0 filters are identical */ + if (!ice_is_dvm_ena(&vsi->back->hw)) + return 0; + + vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); + err = vlan_ops->add_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + return 0; +} + +/** + * ice_vsi_del_vlan_zero - delete VLAN 0 filter(s) for this VSI + * @vsi: VSI used to add VLAN filters + * + * Delete the VLAN 0 filters in the same manner that they were added in + * ice_vsi_add_vlan_zero. + */ +int ice_vsi_del_vlan_zero(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + struct ice_vlan vlan; + int err; + + vlan = ICE_VLAN(0, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + /* in SVM both VLAN 0 filters are identical */ + if (!ice_is_dvm_ena(&vsi->back->hw)) + return 0; + + vlan = ICE_VLAN(ETH_P_8021Q, 0, 0); + err = vlan_ops->del_vlan(vsi, &vlan); + if (err && err != -EEXIST) + return err; + + return 0; +} + +/** + * ice_vsi_num_zero_vlans - get number of VLAN 0 filters based on VLAN mode + * @vsi: VSI used to get the VLAN mode + * + * If DVM is enabled then 2 VLAN 0 filters are added, else if SVM is enabled + * then 1 VLAN 0 filter is added. See ice_vsi_add_vlan_zero for more details. + */ +static u16 ice_vsi_num_zero_vlans(struct ice_vsi *vsi) +{ +#define ICE_DVM_NUM_ZERO_VLAN_FLTRS 2 +#define ICE_SVM_NUM_ZERO_VLAN_FLTRS 1 + /* no VLAN 0 filter is created when a port VLAN is active */ + if (vsi->type == ICE_VSI_VF && + ice_vf_is_port_vlan_ena(&vsi->back->vf[vsi->vf_id])) + return 0; + if (ice_is_dvm_ena(&vsi->back->hw)) + return ICE_DVM_NUM_ZERO_VLAN_FLTRS; + else + return ICE_SVM_NUM_ZERO_VLAN_FLTRS; +} + +/** + * ice_vsi_has_non_zero_vlans - check if VSI has any non-zero VLANs + * @vsi: VSI used to determine if any non-zero VLANs have been added + */ +bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi) +{ + return (vsi->num_vlan > ice_vsi_num_zero_vlans(vsi)); +} + +/** + * ice_vsi_num_non_zero_vlans - get the number of non-zero VLANs for this VSI + * @vsi: VSI used to get the number of non-zero VLANs added + */ +u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi) +{ + return (vsi->num_vlan - ice_vsi_num_zero_vlans(vsi)); +} + +/** * ice_is_feature_supported * @pf: pointer to the struct ice_pf instance * @f: feature enum to be checked diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index b2ed189527d6..491f13f98797 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -5,6 +5,7 @@ #define _ICE_LIB_H_ #include "ice.h" +#include "ice_vlan.h" const char *ice_vsi_type_str(enum ice_vsi_type vsi_type); @@ -22,15 +23,6 @@ int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi); void ice_vsi_cfg_msix(struct ice_vsi *vsi); -int -ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action); - -int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid); - -int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi); - -int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena); - int ice_vsi_start_all_rx_rings(struct ice_vsi *vsi); int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi); @@ -45,8 +37,6 @@ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi); -int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena); - void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); @@ -110,7 +100,7 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); int ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); bool ice_is_safe_mode(struct ice_pf *pf); -bool ice_is_aux_ena(struct ice_pf *pf); +bool ice_is_rdma_ena(struct ice_pf *pf); bool ice_is_dflt_vsi_in_use(struct ice_sw *sw); bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); @@ -132,7 +122,10 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); - +int ice_vsi_add_vlan_zero(struct ice_vsi *vsi); +int ice_vsi_del_vlan_zero(struct ice_vsi *vsi); +bool ice_vsi_has_non_zero_vlans(struct ice_vsi *vsi); +u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi); bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 17a9bb461dc3..cff476f735ef 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -21,6 +21,7 @@ #include "ice_trace.h" #include "ice_eswitch.h" #include "ice_tc_lib.h" +#include "ice_vsi_vlan_ops.h" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" static const char ice_driver_string[] = DRV_SUMMARY; @@ -244,7 +245,7 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (vsi->num_vlan > 1) + if (ice_vsi_has_non_zero_vlans(vsi)) status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); else status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); @@ -264,7 +265,7 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (vsi->num_vlan > 1) + if (ice_vsi_has_non_zero_vlans(vsi)) status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); else status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); @@ -279,6 +280,7 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) */ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) { + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); struct device *dev = ice_pf_to_dev(vsi->back); struct net_device *netdev = vsi->netdev; bool promisc_forced_on = false; @@ -352,7 +354,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { - if (vsi->num_vlan > 1) + if (ice_vsi_has_non_zero_vlans(vsi)) promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; else promisc_m = ICE_MCAST_PROMISC_BITS; @@ -366,7 +368,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) } } else { /* !(vsi->current_netdev_flags & IFF_ALLMULTI) */ - if (vsi->num_vlan > 1) + if (ice_vsi_has_non_zero_vlans(vsi)) promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; else promisc_m = ICE_MCAST_PROMISC_BITS; @@ -396,7 +398,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) goto out_promisc; } err = 0; - ice_cfg_vlan_pruning(vsi, false); + vlan_ops->dis_rx_filtering(vsi); } } else { /* Clear Rx filter to remove traffic from wire */ @@ -409,8 +411,9 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) IFF_PROMISC; goto out_promisc; } - if (vsi->num_vlan > 1) - ice_cfg_vlan_pruning(vsi, true); + if (vsi->current_netdev_flags & + NETIF_F_HW_VLAN_CTAG_FILTER) + vlan_ops->ena_rx_filtering(vsi); } } } @@ -2498,10 +2501,10 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx]; xdp_ring->vsi = vsi; xdp_ring->netdev = NULL; - xdp_ring->next_dd = ICE_TX_THRESH - 1; - xdp_ring->next_rs = ICE_TX_THRESH - 1; xdp_ring->dev = dev; xdp_ring->count = vsi->num_tx_desc; + xdp_ring->next_dd = ICE_RING_QUARTER(xdp_ring) - 1; + xdp_ring->next_rs = ICE_RING_QUARTER(xdp_ring) - 1; WRITE_ONCE(vsi->xdp_rings[i], xdp_ring); if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; @@ -3233,6 +3236,7 @@ static void ice_set_ops(struct net_device *netdev) static void ice_set_netdev_features(struct net_device *netdev) { struct ice_pf *pf = ice_netdev_to_pf(netdev); + bool is_dvm_ena = ice_is_dvm_ena(&pf->hw); netdev_features_t csumo_features; netdev_features_t vlano_features; netdev_features_t dflt_features; @@ -3259,6 +3263,10 @@ static void ice_set_netdev_features(struct net_device *netdev) NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + /* Enable CTAG/STAG filtering by default in Double VLAN Mode (DVM) */ + if (is_dvm_ena) + vlano_features |= NETIF_F_HW_VLAN_STAG_FILTER; + tso_features = NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | @@ -3290,6 +3298,15 @@ static void ice_set_netdev_features(struct net_device *netdev) tso_features; netdev->vlan_features |= dflt_features | csumo_features | tso_features; + + /* advertise support but don't enable by default since only one type of + * VLAN offload can be enabled at a time (i.e. CTAG or STAG). When one + * type turns on the other has to be turned off. This is enforced by the + * ice_fix_features() ndo callback. + */ + if (is_dvm_ena) + netdev->hw_features |= NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_TX; } /** @@ -3405,34 +3422,31 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) /** * ice_vlan_rx_add_vid - Add a VLAN ID filter to HW offload * @netdev: network interface to be adjusted - * @proto: unused protocol + * @proto: VLAN TPID * @vid: VLAN ID to be added * * net_device_ops implementation for adding VLAN IDs */ static int -ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, - u16 vid) +ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi_vlan_ops *vlan_ops; struct ice_vsi *vsi = np->vsi; + struct ice_vlan vlan; int ret; /* VLAN 0 is added by default during load/reset */ if (!vid) return 0; - /* Enable VLAN pruning when a VLAN other than 0 is added */ - if (!ice_vsi_is_vlan_pruning_ena(vsi)) { - ret = ice_cfg_vlan_pruning(vsi, true); - if (ret) - return ret; - } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged * packets aren't pruned by the device's internal switch on Rx */ - ret = ice_vsi_add_vlan(vsi, vid, ICE_FWD_TO_VSI); + vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); + ret = vlan_ops->add_vlan(vsi, &vlan); if (!ret) set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); @@ -3442,36 +3456,36 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, /** * ice_vlan_rx_kill_vid - Remove a VLAN ID filter from HW offload * @netdev: network interface to be adjusted - * @proto: unused protocol + * @proto: VLAN TPID * @vid: VLAN ID to be removed * * net_device_ops implementation for removing VLAN IDs */ static int -ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, - u16 vid) +ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi_vlan_ops *vlan_ops; struct ice_vsi *vsi = np->vsi; + struct ice_vlan vlan; int ret; /* don't allow removal of VLAN 0 */ if (!vid) return 0; - /* Make sure ice_vsi_kill_vlan is successful before updating VLAN + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + /* Make sure VLAN delete is successful before updating VLAN * information */ - ret = ice_vsi_kill_vlan(vsi, vid); + vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); + ret = vlan_ops->del_vlan(vsi, &vlan); if (ret) return ret; - /* Disable pruning when VLAN 0 is the only VLAN rule */ - if (vsi->num_vlan == 1 && ice_vsi_is_vlan_pruning_ena(vsi)) - ret = ice_cfg_vlan_pruning(vsi, false); - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); - return ret; + return 0; } /** @@ -3540,12 +3554,17 @@ static int ice_tc_indir_block_register(struct ice_vsi *vsi) static int ice_setup_pf_sw(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); + bool dvm = ice_is_dvm_ena(&pf->hw); struct ice_vsi *vsi; int status; if (ice_is_reset_in_progress(pf->state)) return -EBUSY; + status = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); + if (status) + return -EIO; + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); if (!vsi) return -ENOMEM; @@ -3680,11 +3699,8 @@ static void ice_set_pf_caps(struct ice_pf *pf) struct ice_hw_func_caps *func_caps = &pf->hw.func_caps; clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - clear_bit(ICE_FLAG_AUX_ENA, pf->flags); - if (func_caps->common_cap.rdma) { + if (func_caps->common_cap.rdma) set_bit(ICE_FLAG_RDMA_ENA, pf->flags); - set_bit(ICE_FLAG_AUX_ENA, pf->flags); - } clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); if (func_caps->common_cap.dcb) set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); @@ -3812,7 +3828,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) v_left -= needed; /* reserve vectors for RDMA auxiliary driver */ - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + if (ice_is_rdma_ena(pf)) { needed = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; if (v_left < needed) goto no_hw_vecs_left_err; @@ -3853,7 +3869,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) int v_remain = v_actual - v_other; int v_rdma = 0, v_min_rdma = 0; - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + if (ice_is_rdma_ena(pf)) { /* Need at least 1 interrupt in addition to * AEQ MSIX */ @@ -3887,7 +3903,7 @@ static int ice_ena_msix_range(struct ice_pf *pf) dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", pf->num_lan_msix); - if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + if (ice_is_rdma_ena(pf)) dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", pf->num_rdma_msix); } @@ -4067,8 +4083,8 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; /* allow all VLANs on Tx and don't strip on Rx */ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL | - ICE_AQ_VSI_VLAN_EMOD_NOTHING; + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL | + ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { @@ -4077,7 +4093,7 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) } else { vsi->info.sec_flags = ctxt->info.sec_flags; vsi->info.sw_flags2 = ctxt->info.sw_flags2; - vsi->info.vlan_flags = ctxt->info.vlan_flags; + vsi->info.inner_vlan_flags = ctxt->info.inner_vlan_flags; } kfree(ctxt); @@ -4462,8 +4478,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) /* set up for high or low DMA */ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - if (err) - err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (err) { dev_err(dev, "DMA configuration failed: 0x%x\n", err); return err; @@ -4715,7 +4729,7 @@ probe_done: /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); - if (ice_is_aux_ena(pf)) { + if (ice_is_rdma_ena(pf)) { pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL); if (pf->aux_idx < 0) { dev_err(dev, "Failed to allocate device ID for AUX driver\n"); @@ -5573,6 +5587,194 @@ ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[], return err; } +#define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_CTAG_TX | \ + NETIF_F_HW_VLAN_STAG_RX | \ + NETIF_F_HW_VLAN_STAG_TX) + +#define NETIF_VLAN_FILTERING_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ + NETIF_F_HW_VLAN_STAG_FILTER) + +/** + * ice_fix_features - fix the netdev features flags based on device limitations + * @netdev: ptr to the netdev that flags are being fixed on + * @features: features that need to be checked and possibly fixed + * + * Make sure any fixups are made to features in this callback. This enables the + * driver to not have to check unsupported configurations throughout the driver + * because that's the responsiblity of this callback. + * + * Single VLAN Mode (SVM) Supported Features: + * NETIF_F_HW_VLAN_CTAG_FILTER + * NETIF_F_HW_VLAN_CTAG_RX + * NETIF_F_HW_VLAN_CTAG_TX + * + * Double VLAN Mode (DVM) Supported Features: + * NETIF_F_HW_VLAN_CTAG_FILTER + * NETIF_F_HW_VLAN_CTAG_RX + * NETIF_F_HW_VLAN_CTAG_TX + * + * NETIF_F_HW_VLAN_STAG_FILTER + * NETIF_HW_VLAN_STAG_RX + * NETIF_HW_VLAN_STAG_TX + * + * Features that need fixing: + * Cannot simultaneously enable CTAG and STAG stripping and/or insertion. + * These are mutually exlusive as the VSI context cannot support multiple + * VLAN ethertypes simultaneously for stripping and/or insertion. If this + * is not done, then default to clearing the requested STAG offload + * settings. + * + * All supported filtering has to be enabled or disabled together. For + * example, in DVM, CTAG and STAG filtering have to be enabled and disabled + * together. If this is not done, then default to VLAN filtering disabled. + * These are mutually exclusive as there is currently no way to + * enable/disable VLAN filtering based on VLAN ethertype when using VLAN + * prune rules. + */ +static netdev_features_t +ice_fix_features(struct net_device *netdev, netdev_features_t features) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + netdev_features_t supported_vlan_filtering; + netdev_features_t requested_vlan_filtering; + struct ice_vsi *vsi = np->vsi; + + requested_vlan_filtering = features & NETIF_VLAN_FILTERING_FEATURES; + + /* make sure supported_vlan_filtering works for both SVM and DVM */ + supported_vlan_filtering = NETIF_F_HW_VLAN_CTAG_FILTER; + if (ice_is_dvm_ena(&vsi->back->hw)) + supported_vlan_filtering |= NETIF_F_HW_VLAN_STAG_FILTER; + + if (requested_vlan_filtering && + requested_vlan_filtering != supported_vlan_filtering) { + if (requested_vlan_filtering & NETIF_F_HW_VLAN_CTAG_FILTER) { + netdev_warn(netdev, "cannot support requested VLAN filtering settings, enabling all supported VLAN filtering settings\n"); + features |= supported_vlan_filtering; + } else { + netdev_warn(netdev, "cannot support requested VLAN filtering settings, clearing all supported VLAN filtering settings\n"); + features &= ~supported_vlan_filtering; + } + } + + if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX)) && + (features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX))) { + netdev_warn(netdev, "cannot support CTAG and STAG VLAN stripping and/or insertion simultaneously since CTAG and STAG offloads are mutually exclusive, clearing STAG offload settings\n"); + features &= ~(NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_TX); + } + + return features; +} + +/** + * ice_set_vlan_offload_features - set VLAN offload features for the PF VSI + * @vsi: PF's VSI + * @features: features used to determine VLAN offload settings + * + * First, determine the vlan_ethertype based on the VLAN offload bits in + * features. Then determine if stripping and insertion should be enabled or + * disabled. Finally enable or disable VLAN stripping and insertion. + */ +static int +ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features) +{ + bool enable_stripping = true, enable_insertion = true; + struct ice_vsi_vlan_ops *vlan_ops; + int strip_err = 0, insert_err = 0; + u16 vlan_ethertype = 0; + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + if (features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX)) + vlan_ethertype = ETH_P_8021AD; + else if (features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX)) + vlan_ethertype = ETH_P_8021Q; + + if (!(features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_CTAG_RX))) + enable_stripping = false; + if (!(features & (NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_CTAG_TX))) + enable_insertion = false; + + if (enable_stripping) + strip_err = vlan_ops->ena_stripping(vsi, vlan_ethertype); + else + strip_err = vlan_ops->dis_stripping(vsi); + + if (enable_insertion) + insert_err = vlan_ops->ena_insertion(vsi, vlan_ethertype); + else + insert_err = vlan_ops->dis_insertion(vsi); + + if (strip_err || insert_err) + return -EIO; + + return 0; +} + +/** + * ice_set_vlan_filtering_features - set VLAN filtering features for the PF VSI + * @vsi: PF's VSI + * @features: features used to determine VLAN filtering settings + * + * Enable or disable Rx VLAN filtering based on the VLAN filtering bits in the + * features. + */ +static int +ice_set_vlan_filtering_features(struct ice_vsi *vsi, netdev_features_t features) +{ + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + int err = 0; + + /* support Single VLAN Mode (SVM) and Double VLAN Mode (DVM) by checking + * if either bit is set + */ + if (features & + (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) + err = vlan_ops->ena_rx_filtering(vsi); + else + err = vlan_ops->dis_rx_filtering(vsi); + + return err; +} + +/** + * ice_set_vlan_features - set VLAN settings based on suggested feature set + * @netdev: ptr to the netdev being adjusted + * @features: the feature set that the stack is suggesting + * + * Only update VLAN settings if the requested_vlan_features are different than + * the current_vlan_features. + */ +static int +ice_set_vlan_features(struct net_device *netdev, netdev_features_t features) +{ + netdev_features_t current_vlan_features, requested_vlan_features; + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + int err; + + current_vlan_features = netdev->features & NETIF_VLAN_OFFLOAD_FEATURES; + requested_vlan_features = features & NETIF_VLAN_OFFLOAD_FEATURES; + if (current_vlan_features ^ requested_vlan_features) { + err = ice_set_vlan_offload_features(vsi, features); + if (err) + return err; + } + + current_vlan_features = netdev->features & + NETIF_VLAN_FILTERING_FEATURES; + requested_vlan_features = features & NETIF_VLAN_FILTERING_FEATURES; + if (current_vlan_features ^ requested_vlan_features) { + err = ice_set_vlan_filtering_features(vsi, features); + if (err) + return err; + } + + return 0; +} + /** * ice_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted @@ -5607,26 +5809,9 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) netdev->features & NETIF_F_RXHASH) ice_vsi_manage_rss_lut(vsi, false); - if ((features & NETIF_F_HW_VLAN_CTAG_RX) && - !(netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) - ret = ice_vsi_manage_vlan_stripping(vsi, true); - else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && - (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) - ret = ice_vsi_manage_vlan_stripping(vsi, false); - - if ((features & NETIF_F_HW_VLAN_CTAG_TX) && - !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) - ret = ice_vsi_manage_vlan_insertion(vsi); - else if (!(features & NETIF_F_HW_VLAN_CTAG_TX) && - (netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) - ret = ice_vsi_manage_vlan_insertion(vsi); - - if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && - !(netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - ret = ice_cfg_vlan_pruning(vsi, true); - else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && - (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - ret = ice_cfg_vlan_pruning(vsi, false); + ret = ice_set_vlan_features(netdev, features); + if (ret) + return ret; if ((features & NETIF_F_NTUPLE) && !(netdev->features & NETIF_F_NTUPLE)) { @@ -5650,23 +5835,26 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) else clear_bit(ICE_FLAG_CLS_FLOWER, pf->flags); - return ret; + return 0; } /** - * ice_vsi_vlan_setup - Setup VLAN offload properties on a VSI + * ice_vsi_vlan_setup - Setup VLAN offload properties on a PF VSI * @vsi: VSI to setup VLAN properties for */ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) { - int ret = 0; + int err; - if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) - ret = ice_vsi_manage_vlan_stripping(vsi, true); - if (vsi->netdev->features & NETIF_F_HW_VLAN_CTAG_TX) - ret = ice_vsi_manage_vlan_insertion(vsi); + err = ice_set_vlan_offload_features(vsi, vsi->netdev->features); + if (err) + return err; - return ret; + err = ice_set_vlan_filtering_features(vsi, vsi->netdev->features); + if (err) + return err; + + return ice_vsi_add_vlan_zero(vsi); } /** @@ -6267,11 +6455,12 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) */ int ice_down(struct ice_vsi *vsi) { - int i, tx_err, rx_err, link_err = 0; + int i, tx_err, rx_err, link_err = 0, vlan_err = 0; WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state)); if (vsi->netdev && vsi->type == ICE_VSI_PF) { + vlan_err = ice_vsi_del_vlan_zero(vsi); if (!ice_is_e810(&vsi->back->hw)) ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); netif_carrier_off(vsi->netdev); @@ -6313,7 +6502,7 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); - if (tx_err || rx_err || link_err) { + if (tx_err || rx_err || link_err || vlan_err) { netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); return -EIO; @@ -6623,6 +6812,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; + bool dvm; int err; if (test_bit(ICE_DOWN, pf->state)) @@ -6686,6 +6876,12 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_init_ctrlq; } + dvm = ice_is_dvm_ena(hw); + + err = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); + if (err) + goto err_init_ctrlq; + err = ice_sched_init_port(hw->port_info); if (err) goto err_sched_init_port; @@ -8594,6 +8790,7 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_start_xmit = ice_start_xmit, .ndo_select_queue = ice_select_queue, .ndo_features_check = ice_features_check, + .ndo_fix_features = ice_fix_features, .ndo_set_rx_mode = ice_set_rx_mode, .ndo_set_mac_address = ice_set_mac_address, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h index f57c414bc0a9..380e8ae94fc9 100644 --- a/drivers/net/ethernet/intel/ice/ice_osdep.h +++ b/drivers/net/ethernet/intel/ice/ice_osdep.h @@ -9,6 +9,7 @@ #ifndef CONFIG_64BIT #include <linux/io-64-nonatomic-lo-hi.h> #endif +#include <net/udp_tunnel.h> #define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) #define rd32(a, reg) readl((a)->hw_addr + (reg)) diff --git a/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.c new file mode 100644 index 000000000000..976a03d3bdd5 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_vsi_vlan_ops.h" +#include "ice_vsi_vlan_lib.h" +#include "ice_vlan_mode.h" +#include "ice.h" +#include "ice_pf_vsi_vlan_ops.h" + +void ice_pf_vsi_init_vlan_ops(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + + if (ice_is_dvm_ena(&vsi->back->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + } else { + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + } +} + diff --git a/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.h new file mode 100644 index 000000000000..6741ec8c5f6b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_pf_vsi_vlan_ops.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_PF_VSI_VLAN_OPS_H_ +#define _ICE_PF_VSI_VLAN_OPS_H_ + +#include "ice_vsi_vlan_ops.h" + +struct ice_vsi; + +void ice_pf_vsi_init_vlan_ops(struct ice_vsi *vsi); + +#endif /* _ICE_PF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 11ae0bee3590..4143728a1919 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1097,6 +1097,64 @@ ice_aq_get_recipe(struct ice_hw *hw, } /** + * ice_update_recipe_lkup_idx - update a default recipe based on the lkup_idx + * @hw: pointer to the HW struct + * @params: parameters used to update the default recipe + * + * This function only supports updating default recipes and it only supports + * updating a single recipe based on the lkup_idx at a time. + * + * This is done as a read-modify-write operation. First, get the current recipe + * contents based on the recipe's ID. Then modify the field vector index and + * mask if it's valid at the lkup_idx. Finally, use the add recipe AQ to update + * the pre-existing recipe with the modifications. + */ +int +ice_update_recipe_lkup_idx(struct ice_hw *hw, + struct ice_update_recipe_lkup_idx_params *params) +{ + struct ice_aqc_recipe_data_elem *rcp_list; + u16 num_recps = ICE_MAX_NUM_RECIPES; + int status; + + rcp_list = kcalloc(num_recps, sizeof(*rcp_list), GFP_KERNEL); + if (!rcp_list) + return -ENOMEM; + + /* read current recipe list from firmware */ + rcp_list->recipe_indx = params->rid; + status = ice_aq_get_recipe(hw, rcp_list, &num_recps, params->rid, NULL); + if (status) { + ice_debug(hw, ICE_DBG_SW, "Failed to get recipe %d, status %d\n", + params->rid, status); + goto error_out; + } + + /* only modify existing recipe's lkup_idx and mask if valid, while + * leaving all other fields the same, then update the recipe firmware + */ + rcp_list->content.lkup_indx[params->lkup_idx] = params->fv_idx; + if (params->mask_valid) + rcp_list->content.mask[params->lkup_idx] = + cpu_to_le16(params->mask); + + if (params->ignore_valid) + rcp_list->content.lkup_indx[params->lkup_idx] |= + ICE_AQ_RECIPE_LKUP_IGNORE; + + status = ice_aq_add_recipe(hw, &rcp_list[0], 1, NULL); + if (status) + ice_debug(hw, ICE_DBG_SW, "Failed to update recipe %d lkup_idx %d fv_idx %d mask %d mask_valid %s, status %d\n", + params->rid, params->lkup_idx, params->fv_idx, + params->mask, params->mask_valid ? "true" : "false", + status); + +error_out: + kfree(rcp_list); + return status; +} + +/** * ice_aq_map_recipe_to_profile - Map recipe to packet profile * @hw: pointer to the HW struct * @profile_id: package profile ID to associate the recipe with @@ -1539,6 +1597,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, struct ice_aqc_sw_rules_elem *s_rule, enum ice_adminq_opc opc) { u16 vlan_id = ICE_MAX_VLAN_ID + 1; + u16 vlan_tpid = ETH_P_8021Q; void *daddr = NULL; u16 eth_hdr_sz; u8 *eth_hdr; @@ -1611,6 +1670,8 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, break; case ICE_SW_LKUP_VLAN: vlan_id = f_info->l_data.vlan.vlan_id; + if (f_info->l_data.vlan.tpid_valid) + vlan_tpid = f_info->l_data.vlan.tpid; if (f_info->fltr_act == ICE_FWD_TO_VSI || f_info->fltr_act == ICE_FWD_TO_VSI_LIST) { act |= ICE_SINGLE_ACT_PRUNE; @@ -1653,6 +1714,8 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, if (!(vlan_id > ICE_MAX_VLAN_ID)) { off = (__force __be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET); *off = cpu_to_be16(vlan_id); + off = (__force __be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET); + *off = cpu_to_be16(vlan_tpid); } /* Create the switch rule with the final dummy Ethernet header */ @@ -3868,6 +3931,23 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, } /** + * ice_change_proto_id_to_dvm - change proto id in prot_id_tbl + * + * As protocol id for outer vlan is different in dvm and svm, if dvm is + * supported protocol array record for outer vlan has to be modified to + * reflect the value proper for DVM. + */ +void ice_change_proto_id_to_dvm(void) +{ + u8 i; + + for (i = 0; i < ARRAY_SIZE(ice_prot_id_tbl); i++) + if (ice_prot_id_tbl[i].type == ICE_VLAN_OFOS && + ice_prot_id_tbl[i].protocol_id != ICE_VLAN_OF_HW) + ice_prot_id_tbl[i].protocol_id = ICE_VLAN_OF_HW; +} + +/** * ice_prot_type_to_id - get protocol ID from protocol type * @type: protocol type * @id: pointer to variable that will receive the ID diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index d8334beaaa8a..7b42c51a3eb0 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -33,15 +33,6 @@ struct ice_vsi_ctx { struct ice_q_ctx *rdma_q_ctx[ICE_MAX_TRAFFIC_CLASS]; }; -enum ice_sw_fwd_act_type { - ICE_FWD_TO_VSI = 0, - ICE_FWD_TO_VSI_LIST, /* Do not use this when adding filter */ - ICE_FWD_TO_Q, - ICE_FWD_TO_QGRP, - ICE_DROP_PACKET, - ICE_INVAL_ACT -}; - /* Switch recipe ID enum values are specific to hardware */ enum ice_sw_lkup_type { ICE_SW_LKUP_ETHERTYPE = 0, @@ -86,6 +77,8 @@ struct ice_fltr_info { } mac_vlan; struct { u16 vlan_id; + u16 tpid; + u8 tpid_valid; } vlan; /* Set lkup_type as ICE_SW_LKUP_ETHERTYPE * if just using ethertype as filter. Set lkup_type as @@ -125,6 +118,15 @@ struct ice_fltr_info { u8 lan_en; /* Indicate if packet can be forwarded to the uplink */ }; +struct ice_update_recipe_lkup_idx_params { + u16 rid; + u16 fv_idx; + bool ignore_valid; + u16 mask; + bool mask_valid; + u8 lkup_idx; +}; + struct ice_adv_lkup_elem { enum ice_protocol_type type; union ice_prot_hdr h_u; /* Header values */ @@ -367,4 +369,8 @@ void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd); +int +ice_update_recipe_lkup_idx(struct ice_hw *hw, + struct ice_update_recipe_lkup_idx_params *params); +void ice_change_proto_id_to_dvm(void); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 3e38695f1c9d..ff93ec71aed6 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -173,6 +173,8 @@ tx_skip_free: tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; + tx_ring->next_dd = ICE_RING_QUARTER(tx_ring) - 1; + tx_ring->next_rs = ICE_RING_QUARTER(tx_ring) - 1; if (!tx_ring->netdev) return; @@ -983,15 +985,17 @@ static struct sk_buff * ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct xdp_buff *xdp) { + unsigned int metasize = xdp->data - xdp->data_meta; unsigned int size = xdp->data_end - xdp->data; unsigned int headlen; struct sk_buff *skb; /* prefetch first cache line of first page */ - net_prefetch(xdp->data); + net_prefetch(xdp->data_meta); /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + ICE_RX_HDR_SIZE + metasize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -1003,8 +1007,13 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, - sizeof(long))); + memcpy(__skb_put(skb, headlen + metasize), xdp->data_meta, + ALIGN(headlen + metasize, sizeof(long))); + + if (metasize) { + skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } /* if we exhaust the linear part then add what is left as a frag */ size -= headlen; @@ -1080,7 +1089,7 @@ ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) { /* if we are the last buffer then there is nothing else to do */ #define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S) - if (likely(ice_test_staterr(rx_desc, ICE_RXD_EOF))) + if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF))) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1142,7 +1151,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) * hardware wrote DD then it will be non-zero */ stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); - if (!ice_test_staterr(rx_desc, stat_err_bits)) + if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) break; /* This memory barrier is needed to keep us from reading @@ -1228,14 +1237,13 @@ construct_skb: continue; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); - if (unlikely(ice_test_staterr(rx_desc, stat_err_bits))) { + if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, + stat_err_bits))) { dev_kfree_skb_any(skb); continue; } - stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S); - if (ice_test_staterr(rx_desc, stat_err_bits)) - vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1); + vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); /* pad the skb if needed, to make a valid ethernet frame */ if (eth_skb_pad(skb)) { @@ -1460,7 +1468,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) bool wd; if (tx_ring->xsk_pool) - wd = ice_clean_tx_irq_zc(tx_ring, budget); + wd = ice_xmit_zc(tx_ring, ICE_DESC_UNUSED(tx_ring), budget); else if (ice_ring_is_xdp(tx_ring)) wd = true; else @@ -1513,7 +1521,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) /* Exit the polling mode, but don't re-enable interrupts if stack might * poll us due to busy-polling */ - if (likely(napi_complete_done(napi, work_done))) { + if (napi_complete_done(napi, work_done)) { ice_net_dim(q_vector); ice_enable_interrupt(q_vector); } else { @@ -1917,12 +1925,16 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) if (!skb_vlan_tag_present(skb) && eth_type_vlan(skb->protocol)) return; - /* currently, we always assume 802.1Q for VLAN insertion as VLAN - * insertion for 802.1AD is not supported + /* the VLAN ethertype/tpid is determined by VSI configuration and netdev + * feature flags, which the driver only allows either 802.1Q or 802.1ad + * VLAN offloads exclusively so we only care about the VLAN ID here */ if (skb_vlan_tag_present(skb)) { first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S; - first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; + if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) + first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; + else + first->tx_flags |= ICE_TX_FLAGS_HW_VLAN; } ice_tx_prepare_vlan_flags_dcb(tx_ring, first); @@ -2295,6 +2307,13 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) /* prepare the VLAN tagging flags for Tx */ ice_tx_prepare_vlan_flags(tx_ring, first); + if (first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) { + offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | + (ICE_TX_CTX_DESC_IL2TAG2 << + ICE_TXD_CTX_QW1_CMD_S)); + offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> + ICE_TX_FLAGS_VLAN_S; + } /* set up TSO offload */ tso = ice_tso(first, &offload); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index b7b3bd4816f0..cead3eb149bd 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -13,7 +13,6 @@ #define ICE_MAX_CHAINED_RX_BUFS 5 #define ICE_MAX_BUF_TXD 8 #define ICE_MIN_TX_LEN 17 -#define ICE_TX_THRESH 32 /* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to @@ -111,6 +110,8 @@ static inline int ice_skb_pad(void) (u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) +#define ICE_RING_QUARTER(R) ((R)->count >> 2) + #define ICE_TX_FLAGS_TSO BIT(0) #define ICE_TX_FLAGS_HW_VLAN BIT(1) #define ICE_TX_FLAGS_SW_VLAN BIT(2) @@ -122,6 +123,7 @@ static inline int ice_skb_pad(void) #define ICE_TX_FLAGS_IPV4 BIT(5) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) +#define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) #define ICE_TX_FLAGS_VLAN_M 0xffff0000 #define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000 #define ICE_TX_FLAGS_VLAN_PR_S 29 @@ -321,18 +323,21 @@ struct ice_tx_ring { u16 count; /* Number of descriptors */ u16 q_index; /* Queue number of ring */ /* stats structs */ - struct ice_q_stats stats; - struct u64_stats_sync syncp; struct ice_txq_stats tx_stats; - /* CL3 - 3rd cacheline starts here */ + struct ice_q_stats stats; + struct u64_stats_sync syncp; struct rcu_head rcu; /* to avoid race on free */ DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ struct ice_channel *ch; struct ice_ptp_tx *tx_tstamps; spinlock_t tx_lock; u32 txq_teid; /* Added Tx queue TEID */ + /* CL4 - 4th cacheline starts here */ + u16 xdp_tx_active; #define ICE_TX_FLAGS_RING_XDP BIT(0) +#define ICE_TX_FLAGS_RING_VLAN_L2TAG1 BIT(1) +#define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) u8 flags; u8 dcb_tc; /* Traffic class of ring */ u8 ptp_tx; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 0e87b98e0966..7ee38d02d1e5 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -209,9 +209,14 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, void ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { - if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && - (vlan_tag & VLAN_VID_MASK)) + netdev_features_t features = rx_ring->netdev->features; + bool non_zero_vlan = !!(vlan_tag & VLAN_VID_MASK); + + if ((features & NETIF_F_HW_VLAN_CTAG_RX) && non_zero_vlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); + else if ((features & NETIF_F_HW_VLAN_STAG_RX) && non_zero_vlan) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), vlan_tag); + napi_gro_receive(&rx_ring->q_vector->napi, skb); } @@ -222,6 +227,7 @@ ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) { unsigned int total_bytes = 0, total_pkts = 0; + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); u16 ntc = xdp_ring->next_to_clean; struct ice_tx_desc *next_dd_desc; u16 next_dd = xdp_ring->next_dd; @@ -233,7 +239,7 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) return; - for (i = 0; i < ICE_TX_THRESH; i++) { + for (i = 0; i < tx_thresh; i++) { tx_buf = &xdp_ring->tx_buf[ntc]; total_bytes += tx_buf->bytecount; @@ -254,9 +260,9 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) } next_dd_desc->cmd_type_offset_bsz = 0; - xdp_ring->next_dd = xdp_ring->next_dd + ICE_TX_THRESH; + xdp_ring->next_dd = xdp_ring->next_dd + tx_thresh; if (xdp_ring->next_dd > xdp_ring->count) - xdp_ring->next_dd = ICE_TX_THRESH - 1; + xdp_ring->next_dd = tx_thresh - 1; xdp_ring->next_to_clean = ntc; ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes); } @@ -269,12 +275,13 @@ static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) */ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) { + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); u16 i = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; dma_addr_t dma; - if (ICE_DESC_UNUSED(xdp_ring) < ICE_TX_THRESH) + if (ICE_DESC_UNUSED(xdp_ring) < tx_thresh) ice_clean_xdp_irq(xdp_ring); if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) { @@ -300,13 +307,14 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, 0, size, 0); + xdp_ring->xdp_tx_active++; i++; if (i == xdp_ring->count) { i = 0; tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); tx_desc->cmd_type_offset_bsz |= cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs = ICE_TX_THRESH - 1; + xdp_ring->next_rs = tx_thresh - 1; } xdp_ring->next_to_use = i; @@ -314,7 +322,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); tx_desc->cmd_type_offset_bsz |= cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs += ICE_TX_THRESH; + xdp_ring->next_rs += tx_thresh; } return ICE_XDP_TX; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 11b6c1601986..c7d2954dc9ea 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -7,7 +7,7 @@ /** * ice_test_staterr - tests bits in Rx descriptor status and error fields - * @rx_desc: pointer to receive descriptor (in le64 format) + * @status_err_n: Rx descriptor status_error0 or status_error1 bits * @stat_err_bits: value to mask * * This function does some fast chicanery in order to return the @@ -16,9 +16,9 @@ * at offset zero. */ static inline bool -ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc, const u16 stat_err_bits) +ice_test_staterr(__le16 status_err_n, const u16 stat_err_bits) { - return !!(rx_desc->wb.status_error0 & cpu_to_le16(stat_err_bits)); + return !!(status_err_n & cpu_to_le16(stat_err_bits)); } static inline __le64 @@ -32,6 +32,30 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) } /** + * ice_get_vlan_tag_from_rx_desc - get VLAN from Rx flex descriptor + * @rx_desc: Rx 32b flex descriptor with RXDID=2 + * + * The OS and current PF implementation only support stripping a single VLAN tag + * at a time, so there should only ever be 0 or 1 tags in the l2tag* fields. If + * one is found return the tag, else return 0 to mean no VLAN tag was found. + */ +static inline u16 +ice_get_vlan_tag_from_rx_desc(union ice_32b_rx_flex_desc *rx_desc) +{ + u16 stat_err_bits; + + stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S); + if (ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) + return le16_to_cpu(rx_desc->wb.l2tag1); + + stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS1_L2TAG2P_S); + if (ice_test_staterr(rx_desc->wb.status_error1, stat_err_bits)) + return le16_to_cpu(rx_desc->wb.l2tag2_2nd); + + return 0; +} + +/** * ice_xdp_ring_update_tail - Updates the XDP Tx ring tail register * @xdp_ring: XDP Tx ring * diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 546145dd1f02..28fcab26b868 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -15,6 +15,7 @@ #include "ice_flex_type.h" #include "ice_protocol_type.h" #include "ice_sbq_cmd.h" +#include "ice_vlan_mode.h" static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -54,6 +55,11 @@ static inline u32 ice_round_to_num(u32 N, u32 R) #define ICE_DBG_AQ_DESC BIT_ULL(25) #define ICE_DBG_AQ_DESC_BUF BIT_ULL(26) #define ICE_DBG_AQ_CMD BIT_ULL(27) +#define ICE_DBG_AQ (ICE_DBG_AQ_MSG | \ + ICE_DBG_AQ_DESC | \ + ICE_DBG_AQ_DESC_BUF | \ + ICE_DBG_AQ_CMD) + #define ICE_DBG_USER BIT_ULL(31) enum ice_aq_res_ids { @@ -920,6 +926,9 @@ struct ice_hw { struct udp_tunnel_nic_shared udp_tunnel_shared; struct udp_tunnel_nic_info udp_tunnel_nic; + /* dvm boost update information */ + struct ice_dvm_table dvm_upd; + /* HW block tables */ struct ice_blk_info blk[ICE_BLK_COUNT]; struct mutex fl_profs_locks[ICE_BLK_COUNT]; /* lock fltr profiles */ @@ -943,6 +952,7 @@ struct ice_hw { struct list_head rss_list_head; struct ice_mbx_snapshot mbx_snapshot; DECLARE_BITMAP(hw_ptype, ICE_FLOW_PTYPE_MAX); + u8 dvm_ena; u16 io_expander_handle; }; @@ -1008,6 +1018,15 @@ struct ice_hw_port_stats { u64 fd_sb_match; }; +enum ice_sw_fwd_act_type { + ICE_FWD_TO_VSI = 0, + ICE_FWD_TO_VSI_LIST, /* Do not use this when adding filter */ + ICE_FWD_TO_Q, + ICE_FWD_TO_QGRP, + ICE_DROP_PACKET, + ICE_INVAL_ACT +}; + struct ice_aq_get_set_rss_lut_params { u16 vsi_handle; /* software VSI handle */ u16 lut_size; /* size of the LUT buffer */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c new file mode 100644 index 000000000000..39f2d36cabba --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_vsi_vlan_ops.h" +#include "ice_vsi_vlan_lib.h" +#include "ice_vlan_mode.h" +#include "ice.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_virtchnl_pf.h" + +static int +noop_vlan_arg(struct ice_vsi __always_unused *vsi, + struct ice_vlan __always_unused *vlan) +{ + return 0; +} + +static int +noop_vlan(struct ice_vsi __always_unused *vsi) +{ + return 0; +} + +/** + * ice_vf_vsi_init_vlan_ops - Initialize default VSI VLAN ops for VF VSI + * @vsi: VF's VSI being configured + * + * If Double VLAN Mode (DVM) is enabled, assume that the VF supports the new + * VIRTCHNL_VF_VLAN_OFFLOAD_V2 capability and set up the VLAN ops accordingly. + * If SVM is enabled maintain the same level of VLAN support previous to + * VIRTCHNL_VF_VLAN_OFFLOAD_V2. + */ +void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vsi->back; + struct ice_vf *vf; + + vf = &pf->vf[vsi->vf_id]; + + if (ice_is_dvm_ena(&pf->hw)) { + vlan_ops = &vsi->outer_vlan_ops; + + /* outer VLAN ops regardless of port VLAN config */ + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; + vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; + + if (ice_vf_is_port_vlan_ena(vf)) { + /* setup outer VLAN ops */ + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + vlan_ops->add_vlan = noop_vlan_arg; + vlan_ops->del_vlan = noop_vlan_arg; + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + } else { + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) + vlan_ops->ena_rx_filtering = noop_vlan; + else + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; + + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_outer_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_outer_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + } + } else { + vlan_ops = &vsi->inner_vlan_ops; + + /* inner VLAN ops regardless of port VLAN config */ + vlan_ops->add_vlan = ice_vsi_add_vlan; + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; + vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; + + if (ice_vf_is_port_vlan_ena(vf)) { + vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; + } else { + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) + vlan_ops->ena_rx_filtering = noop_vlan; + else + vlan_ops->ena_rx_filtering = + ice_vsi_ena_rx_vlan_filtering; + + vlan_ops->del_vlan = ice_vsi_del_vlan; + vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; + vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; + vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; + vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; + } + } +} + +/** + * ice_vf_vsi_cfg_dvm_legacy_vlan_mode - Config VLAN mode for old VFs in DVM + * @vsi: VF's VSI being configured + * + * This should only be called when Double VLAN Mode (DVM) is enabled, there + * is not a port VLAN enabled on this VF, and the VF negotiates + * VIRTCHNL_VF_OFFLOAD_VLAN. + * + * This function sets up the VF VSI's inner and outer ice_vsi_vlan_ops and also + * initializes software only VLAN mode (i.e. allow all VLANs). Also, use no-op + * implementations for any functions that may be called during the lifetime of + * the VF so these methods do nothing and succeed. + */ +void ice_vf_vsi_cfg_dvm_legacy_vlan_mode(struct ice_vsi *vsi) +{ + struct ice_vf *vf = &vsi->back->vf[vsi->vf_id]; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi_vlan_ops *vlan_ops; + + if (!ice_is_dvm_ena(&vsi->back->hw) || ice_vf_is_port_vlan_ena(vf)) + return; + + vlan_ops = &vsi->outer_vlan_ops; + + /* Rx VLAN filtering always disabled to allow software offloaded VLANs + * for VFs that only support VIRTCHNL_VF_OFFLOAD_VLAN and don't have a + * port VLAN configured + */ + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + /* Don't fail when attempting to enable Rx VLAN filtering */ + vlan_ops->ena_rx_filtering = noop_vlan; + + /* Tx VLAN filtering always disabled to allow software offloaded VLANs + * for VFs that only support VIRTCHNL_VF_OFFLOAD_VLAN and don't have a + * port VLAN configured + */ + vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; + /* Don't fail when attempting to enable Tx VLAN filtering */ + vlan_ops->ena_tx_filtering = noop_vlan; + + if (vlan_ops->dis_rx_filtering(vsi)) + dev_dbg(dev, "Failed to disable Rx VLAN filtering for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + if (vlan_ops->dis_tx_filtering(vsi)) + dev_dbg(dev, "Failed to disable Tx VLAN filtering for old VF without VIRTHCNL_VF_OFFLOAD_VLAN_V2 support\n"); + + /* All outer VLAN offloads must be disabled */ + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + + if (vlan_ops->dis_stripping(vsi)) + dev_dbg(dev, "Failed to disable outer VLAN stripping for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + + if (vlan_ops->dis_insertion(vsi)) + dev_dbg(dev, "Failed to disable outer VLAN insertion for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + + /* All inner VLAN offloads must be disabled */ + vlan_ops = &vsi->inner_vlan_ops; + + vlan_ops->dis_stripping = ice_vsi_dis_outer_stripping; + vlan_ops->dis_insertion = ice_vsi_dis_outer_insertion; + + if (vlan_ops->dis_stripping(vsi)) + dev_dbg(dev, "Failed to disable inner VLAN stripping for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); + + if (vlan_ops->dis_insertion(vsi)) + dev_dbg(dev, "Failed to disable inner VLAN insertion for old VF without VIRTCHNL_VF_OFFLOAD_VLAN_V2 support\n"); +} + +/** + * ice_vf_vsi_cfg_svm_legacy_vlan_mode - Config VLAN mode for old VFs in SVM + * @vsi: VF's VSI being configured + * + * This should only be called when Single VLAN Mode (SVM) is enabled, there is + * not a port VLAN enabled on this VF, and the VF negotiates + * VIRTCHNL_VF_OFFLOAD_VLAN. + * + * All of the normal SVM VLAN ops are identical for this case. However, by + * default Rx VLAN filtering should be turned off by default in this case. + */ +void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi) +{ + struct ice_vf *vf = &vsi->back->vf[vsi->vf_id]; + + if (ice_is_dvm_ena(&vsi->back->hw) || ice_vf_is_port_vlan_ena(vf)) + return; + + if (vsi->inner_vlan_ops.dis_rx_filtering(vsi)) + dev_dbg(ice_pf_to_dev(vf->pf), "Failed to disable Rx VLAN filtering for old VF with VIRTCHNL_VF_OFFLOAD_VLAN support\n"); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h new file mode 100644 index 000000000000..875a4e615f39 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VF_VSI_VLAN_OPS_H_ +#define _ICE_VF_VSI_VLAN_OPS_H_ + +#include "ice_vsi_vlan_ops.h" + +struct ice_vsi; + +void ice_vf_vsi_cfg_dvm_legacy_vlan_mode(struct ice_vsi *vsi); +void ice_vf_vsi_cfg_svm_legacy_vlan_mode(struct ice_vsi *vsi); + +#ifdef CONFIG_PCI_IOV +void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi); +#else +static inline void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) { } +#endif /* CONFIG_PCI_IOV */ +#endif /* _ICE_PF_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 9feebe5f556c..5a82216e7d03 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -55,6 +55,15 @@ static const u32 vlan_allowlist_opcodes[] = { VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, }; +/* VIRTCHNL_VF_OFFLOAD_VLAN_V2 */ +static const u32 vlan_v2_allowlist_opcodes[] = { + VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS, VIRTCHNL_OP_ADD_VLAN_V2, + VIRTCHNL_OP_DEL_VLAN_V2, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2, + VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2, + VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2, +}; + /* VIRTCHNL_VF_OFFLOAD_RSS_PF */ static const u32 rss_pf_allowlist_opcodes[] = { VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT, @@ -89,6 +98,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_RSS_PF, rss_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 39b80124d282..02a8c15d2bf3 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -10,6 +10,8 @@ #include "ice_eswitch.h" #include "ice_virtchnl_allowlist.h" #include "ice_flex_pipe.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_vlan.h" #define FIELD_SELECTOR(proto_hdr_field) \ BIT((proto_hdr_field) & PROTO_HDR_FIELD_MASK) @@ -643,55 +645,6 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) } /** - * ice_vsi_manage_pvid - Enable or disable port VLAN for VSI - * @vsi: the VSI to update - * @pvid_info: VLAN ID and QoS used to set the PVID VSI context field - * @enable: true for enable PVID false for disable - */ -static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 pvid_info, bool enable) -{ - struct ice_hw *hw = &vsi->back->hw; - struct ice_aqc_vsi_props *info; - struct ice_vsi_ctx *ctxt; - int ret; - - ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); - if (!ctxt) - return -ENOMEM; - - ctxt->info = vsi->info; - info = &ctxt->info; - if (enable) { - info->vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED | - ICE_AQ_VSI_PVLAN_INSERT_PVID | - ICE_AQ_VSI_VLAN_EMOD_STR; - info->sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - } else { - info->vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING | - ICE_AQ_VSI_VLAN_MODE_ALL; - info->sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - } - - info->pvid = cpu_to_le16(pvid_info); - info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | - ICE_AQ_VSI_PROP_SW_VALID); - - ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (ret) { - dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n", - ret, ice_aq_str(hw->adminq.sq_last_status)); - goto out; - } - - vsi->info.vlan_flags = info->vlan_flags; - vsi->info.sw_flags2 = info->sw_flags2; - vsi->info.pvid = info->pvid; -out: - kfree(ctxt); - return ret; -} - -/** * ice_vf_get_port_info - Get the VF's port info structure * @vf: VF used to get the port info structure for */ @@ -800,43 +753,151 @@ static int ice_vf_rebuild_host_tx_rate_cfg(struct ice_vf *vf) return 0; } +static u16 ice_vf_get_port_vlan_id(struct ice_vf *vf) +{ + return vf->port_vlan_info.vid; +} + +static u8 ice_vf_get_port_vlan_prio(struct ice_vf *vf) +{ + return vf->port_vlan_info.prio; +} + +bool ice_vf_is_port_vlan_ena(struct ice_vf *vf) +{ + return (ice_vf_get_port_vlan_id(vf) || ice_vf_get_port_vlan_prio(vf)); +} + +static u16 ice_vf_get_port_vlan_tpid(struct ice_vf *vf) +{ + return vf->port_vlan_info.tpid; +} + /** * ice_vf_rebuild_host_vlan_cfg - add VLAN 0 filter or rebuild the Port VLAN * @vf: VF to add MAC filters for + * @vsi: Pointer to VSI * * Called after a VF VSI has been re-added/rebuilt during reset. The PF driver * always re-adds either a VLAN 0 or port VLAN based filter after reset. */ -static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf) +static int ice_vf_rebuild_host_vlan_cfg(struct ice_vf *vf, struct ice_vsi *vsi) { + struct ice_vsi_vlan_ops *vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); struct device *dev = ice_pf_to_dev(vf->pf); - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - u16 vlan_id = 0; int err; - if (vf->port_vlan_info) { - err = ice_vsi_manage_pvid(vsi, vf->port_vlan_info, true); + if (ice_vf_is_port_vlan_ena(vf)) { + err = vlan_ops->set_port_vlan(vsi, &vf->port_vlan_info); if (err) { dev_err(dev, "failed to configure port VLAN via VSI parameters for VF %u, error %d\n", vf->vf_id, err); return err; } - vlan_id = vf->port_vlan_info & VLAN_VID_MASK; + err = vlan_ops->add_vlan(vsi, &vf->port_vlan_info); + } else { + err = ice_vsi_add_vlan_zero(vsi); } - /* vlan_id will either be 0 or the port VLAN number */ - err = ice_vsi_add_vlan(vsi, vlan_id, ICE_FWD_TO_VSI); if (err) { - dev_err(dev, "failed to add %s VLAN %u filter for VF %u, error %d\n", - vf->port_vlan_info ? "port" : "", vlan_id, vf->vf_id, - err); + dev_err(dev, "failed to add VLAN %u filter for VF %u during VF rebuild, error %d\n", + ice_vf_is_port_vlan_ena(vf) ? + ice_vf_get_port_vlan_id(vf) : 0, vf->vf_id, err); return err; } + err = vlan_ops->ena_rx_filtering(vsi); + if (err) + dev_warn(dev, "failed to enable Rx VLAN filtering for VF %d VSI %d during VF rebuild, error %d\n", + vf->vf_id, vsi->idx, err); + return 0; } +static int ice_cfg_mac_antispoof(struct ice_vsi *vsi, bool enable) +{ + struct ice_vsi_ctx *ctx; + int err; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->info.sec_flags = vsi->info.sec_flags; + ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + + if (enable) + ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; + else + ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; + + err = ice_update_vsi(&vsi->back->hw, vsi->idx, ctx, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "Failed to configure Tx MAC anti-spoof %s for VSI %d, error %d\n", + enable ? "ON" : "OFF", vsi->vsi_num, err); + else + vsi->info.sec_flags = ctx->info.sec_flags; + + kfree(ctx); + + return err; +} + +/** + * ice_vsi_ena_spoofchk - enable Tx spoof checking for this VSI + * @vsi: VSI to enable Tx spoof checking for + */ +static int ice_vsi_ena_spoofchk(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + int err; + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + err = vlan_ops->ena_tx_filtering(vsi); + if (err) + return err; + + return ice_cfg_mac_antispoof(vsi, true); +} + +/** + * ice_vsi_dis_spoofchk - disable Tx spoof checking for this VSI + * @vsi: VSI to disable Tx spoof checking for + */ +static int ice_vsi_dis_spoofchk(struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + int err; + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + + err = vlan_ops->dis_tx_filtering(vsi); + if (err) + return err; + + return ice_cfg_mac_antispoof(vsi, false); +} + +/** + * ice_vf_set_spoofchk_cfg - apply Tx spoof checking setting + * @vf: VF set spoofchk for + * @vsi: VSI associated to the VF + */ +static int +ice_vf_set_spoofchk_cfg(struct ice_vf *vf, struct ice_vsi *vsi) +{ + int err; + + if (vf->spoofchk) + err = ice_vsi_ena_spoofchk(vsi); + else + err = ice_vsi_dis_spoofchk(vsi); + + return err; +} + /** * ice_vf_rebuild_host_mac_cfg - add broadcast and the VF's perm_addr/LAA * @vf: VF to add MAC filters for @@ -1227,10 +1288,10 @@ ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) struct ice_hw *hw = &vsi->back->hw; int status; - if (vf->port_vlan_info) + if (ice_vf_is_port_vlan_ena(vf)) status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_info & VLAN_VID_MASK); - else if (vsi->num_vlan > 1) + ice_vf_get_port_vlan_id(vf)); + else if (ice_vsi_has_non_zero_vlans(vsi)) status = ice_fltr_set_vlan_vsi_promisc(hw, vsi, promisc_m); else status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, 0); @@ -1250,10 +1311,10 @@ ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) struct ice_hw *hw = &vsi->back->hw; int status; - if (vf->port_vlan_info) + if (ice_vf_is_port_vlan_ena(vf)) status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_info & VLAN_VID_MASK); - else if (vsi->num_vlan > 1) + ice_vf_get_port_vlan_id(vf)); + else if (ice_vsi_has_non_zero_vlans(vsi)) status = ice_fltr_clear_vlan_vsi_promisc(hw, vsi, promisc_m); else status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, 0); @@ -1338,7 +1399,7 @@ static void ice_vf_rebuild_host_cfg(struct ice_vf *vf) dev_err(dev, "failed to rebuild default MAC configuration for VF %d\n", vf->vf_id); - if (ice_vf_rebuild_host_vlan_cfg(vf)) + if (ice_vf_rebuild_host_vlan_cfg(vf, vsi)) dev_err(dev, "failed to rebuild VLAN configuration for VF %u\n", vf->vf_id); @@ -1346,6 +1407,10 @@ static void ice_vf_rebuild_host_cfg(struct ice_vf *vf) dev_err(dev, "failed to rebuild Tx rate limiting configuration for VF %u\n", vf->vf_id); + if (ice_vf_set_spoofchk_cfg(vf, vsi)) + dev_err(dev, "failed to rebuild spoofchk configuration for VF %d\n", + vf->vf_id); + /* rebuild aggregator node config for main VF VSI */ ice_vf_rebuild_aggregator_node_cfg(vsi); } @@ -1406,6 +1471,7 @@ static void ice_vf_set_initialized(struct ice_vf *vf) clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); clear_bit(ICE_VF_STATE_DIS, vf->vf_states); set_bit(ICE_VF_STATE_INIT, vf->vf_states); + memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); } /** @@ -1623,7 +1689,7 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) */ if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) { - if (vf->port_vlan_info || vsi->num_vlan) + if (ice_vf_is_port_vlan_ena(vf) || vsi->num_vlan) promisc_m = ICE_UCAST_VLAN_PROMISC_BITS; else promisc_m = ICE_UCAST_PROMISC_BITS; @@ -1732,6 +1798,7 @@ static void ice_vc_notify_vf_reset(struct ice_vf *vf) */ static int ice_init_vf_vsi_res(struct ice_vf *vf) { + struct ice_vsi_vlan_ops *vlan_ops; struct ice_pf *pf = vf->pf; u8 broadcast[ETH_ALEN]; struct ice_vsi *vsi; @@ -1745,13 +1812,21 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) if (!vsi) return -ENOMEM; - err = ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI); + err = ice_vsi_add_vlan_zero(vsi); if (err) { dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n", vf->vf_id); goto release_vsi; } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + err = vlan_ops->ena_rx_filtering(vsi); + if (err) { + dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n", + vf->vf_id); + goto release_vsi; + } + eth_broadcast_addr(broadcast); err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); if (err) { @@ -1760,6 +1835,13 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) goto release_vsi; } + err = ice_vf_set_spoofchk_cfg(vf, vsi); + if (err) { + dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n", + vf->vf_id); + goto release_vsi; + } + vf->num_mac = 1; return 0; @@ -2239,7 +2321,7 @@ static u16 ice_vc_get_max_frame_size(struct ice_vf *vf) max_frame_size = pi->phy.link_info.max_frame_size; - if (vf->port_vlan_info) + if (ice_vf_is_port_vlan_ena(vf)) max_frame_size -= VLAN_HLEN; return max_frame_size; @@ -2288,8 +2370,33 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) goto err; } - if (!vsi->info.pvid) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN_V2) { + /* VLAN offloads based on current device configuration */ + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN_V2; + } else if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN) { + /* allow VF to negotiate VIRTCHNL_VF_OFFLOAD explicitly for + * these two conditions, which amounts to guest VLAN filtering + * and offloads being based on the inner VLAN or the + * inner/single VLAN respectively and don't allow VF to + * negotiate VIRTCHNL_VF_OFFLOAD in any other cases + */ + if (ice_is_dvm_ena(&pf->hw) && ice_vf_is_port_vlan_ena(vf)) { + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; + } else if (!ice_is_dvm_ena(&pf->hw) && + !ice_vf_is_port_vlan_ena(vf)) { + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; + /* configure backward compatible support for VFs that + * only support VIRTCHNL_VF_OFFLOAD_VLAN, the PF is + * configured in SVM, and no port VLAN is configured + */ + ice_vf_vsi_cfg_svm_legacy_vlan_mode(vsi); + } else if (ice_is_dvm_ena(&pf->hw)) { + /* configure software offloaded VLAN support when DVM + * is enabled, but no port VLAN is enabled + */ + ice_vf_vsi_cfg_dvm_legacy_vlan_mode(vsi); + } + } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; @@ -2892,7 +2999,6 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_pf *pf = np->vsi->back; - struct ice_vsi_ctx *ctx; struct ice_vsi *vf_vsi; struct device *dev; struct ice_vf *vf; @@ -2925,37 +3031,16 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) return 0; } - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; - - ctx->info.sec_flags = vf_vsi->info.sec_flags; - ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); - if (ena) { - ctx->info.sec_flags |= - ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); - } else { - ctx->info.sec_flags &= - ~(ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | - (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << - ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S)); - } - - ret = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL); - if (ret) { - dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d\n", - ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, ret); - goto out; - } - - /* only update spoofchk state and VSI context on success */ - vf_vsi->info.sec_flags = ctx->info.sec_flags; - vf->spoofchk = ena; + if (ena) + ret = ice_vsi_ena_spoofchk(vf_vsi); + else + ret = ice_vsi_dis_spoofchk(vf_vsi); + if (ret) + dev_err(dev, "Failed to set spoofchk %s for VF %d VSI %d\n error %d\n", + ena ? "ON" : "OFF", vf->vf_id, vf_vsi->vsi_num, ret); + else + vf->spoofchk = ena; -out: - kfree(ctx); return ret; } @@ -2995,6 +3080,7 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) bool rm_promisc, alluni = false, allmulti = false; struct virtchnl_promisc_info *info = (struct virtchnl_promisc_info *)msg; + struct ice_vsi_vlan_ops *vlan_ops; int mcast_err = 0, ucast_err = 0; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; @@ -3033,16 +3119,15 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) rm_promisc = !allmulti && !alluni; - if (vsi->num_vlan || vf->port_vlan_info) { - if (rm_promisc) - ret = ice_cfg_vlan_pruning(vsi, true); - else - ret = ice_cfg_vlan_pruning(vsi, false); - if (ret) { - dev_err(dev, "Failed to configure VLAN pruning in promiscuous mode\n"); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + if (rm_promisc) + ret = vlan_ops->ena_rx_filtering(vsi); + else + ret = vlan_ops->dis_rx_filtering(vsi); + if (ret) { + dev_err(dev, "Failed to configure VLAN pruning in promiscuous mode\n"); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; } if (!test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) { @@ -3069,7 +3154,8 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) } else { u8 mcast_m, ucast_m; - if (vf->port_vlan_info || vsi->num_vlan > 1) { + if (ice_vf_is_port_vlan_ena(vf) || + ice_vsi_has_non_zero_vlans(vsi)) { mcast_m = ICE_MCAST_VLAN_PROMISC_BITS; ucast_m = ICE_UCAST_VLAN_PROMISC_BITS; } else { @@ -3652,7 +3738,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) /* add space for the port VLAN since the VF driver is not * expected to account for it in the MTU calculation */ - if (vf->port_vlan_info) + if (ice_vf_is_port_vlan_ena(vf)) vsi->max_frame += VLAN_HLEN; if (ice_vsi_cfg_single_rxq(vsi, q_idx)) { @@ -4064,6 +4150,33 @@ error_param: } /** + * ice_is_supported_port_vlan_proto - make sure the vlan_proto is supported + * @hw: hardware structure used to check the VLAN mode + * @vlan_proto: VLAN TPID being checked + * + * If the device is configured in Double VLAN Mode (DVM), then both ETH_P_8021Q + * and ETH_P_8021AD are supported. If the device is configured in Single VLAN + * Mode (SVM), then only ETH_P_8021Q is supported. + */ +static bool +ice_is_supported_port_vlan_proto(struct ice_hw *hw, u16 vlan_proto) +{ + bool is_supported = false; + + switch (vlan_proto) { + case ETH_P_8021Q: + is_supported = true; + break; + case ETH_P_8021AD: + if (ice_is_dvm_ena(hw)) + is_supported = true; + break; + } + + return is_supported; +} + +/** * ice_set_vf_port_vlan * @netdev: network interface device structure * @vf_id: VF identifier @@ -4078,9 +4191,9 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, __be16 vlan_proto) { struct ice_pf *pf = ice_netdev_to_pf(netdev); + u16 local_vlan_proto = ntohs(vlan_proto); struct device *dev; struct ice_vf *vf; - u16 vlanprio; int ret; dev = ice_pf_to_dev(pf); @@ -4093,8 +4206,9 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, return -EINVAL; } - if (vlan_proto != htons(ETH_P_8021Q)) { - dev_err(dev, "VF VLAN protocol is not supported\n"); + if (!ice_is_supported_port_vlan_proto(&pf->hw, local_vlan_proto)) { + dev_err(dev, "VF VLAN protocol 0x%04x is not supported\n", + local_vlan_proto); return -EPROTONOSUPPORT; } @@ -4103,21 +4217,21 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (ret) return ret; - vlanprio = vlan_id | (qos << VLAN_PRIO_SHIFT); - - if (vf->port_vlan_info == vlanprio) { + if (ice_vf_get_port_vlan_prio(vf) == qos && + ice_vf_get_port_vlan_tpid(vf) == local_vlan_proto && + ice_vf_get_port_vlan_id(vf) == vlan_id) { /* duplicate request, so just return success */ - dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio); + dev_dbg(dev, "Duplicate port VLAN %u, QoS %u, TPID 0x%04x request\n", + vlan_id, qos, local_vlan_proto); return 0; } mutex_lock(&vf->cfg_lock); - vf->port_vlan_info = vlanprio; - - if (vf->port_vlan_info) - dev_info(dev, "Setting VLAN %d, QoS 0x%x on VF %d\n", - vlan_id, qos, vf_id); + vf->port_vlan_info = ICE_VLAN(local_vlan_proto, vlan_id, qos); + if (ice_vf_is_port_vlan_ena(vf)) + dev_info(dev, "Setting VLAN %u, QoS %u, TPID 0x%04x on VF %d\n", + vlan_id, qos, local_vlan_proto, vf_id); else dev_info(dev, "Clearing port VLAN on VF %d\n", vf_id); @@ -4139,6 +4253,83 @@ static bool ice_vf_vlan_offload_ena(u32 caps) } /** + * ice_is_vlan_promisc_allowed - check if VLAN promiscuous config is allowed + * @vf: VF used to determine if VLAN promiscuous config is allowed + */ +static bool ice_is_vlan_promisc_allowed(struct ice_vf *vf) +{ + if ((test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || + test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) && + test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, vf->pf->flags)) + return true; + + return false; +} + +/** + * ice_vf_ena_vlan_promisc - Enable Tx/Rx VLAN promiscuous for the VLAN + * @vsi: VF's VSI used to enable VLAN promiscuous mode + * @vlan: VLAN used to enable VLAN promiscuous + * + * This function should only be called if VLAN promiscuous mode is allowed, + * which can be determined via ice_is_vlan_promisc_allowed(). + */ +static int ice_vf_ena_vlan_promisc(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + u8 promisc_m = ICE_PROMISC_VLAN_TX | ICE_PROMISC_VLAN_RX; + int status; + + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, + vlan->vid); + if (status && status != -EEXIST) + return status; + + return 0; +} + +/** + * ice_vf_dis_vlan_promisc - Disable Tx/Rx VLAN promiscuous for the VLAN + * @vsi: VF's VSI used to disable VLAN promiscuous mode for + * @vlan: VLAN used to disable VLAN promiscuous + * + * This function should only be called if VLAN promiscuous mode is allowed, + * which can be determined via ice_is_vlan_promisc_allowed(). + */ +static int ice_vf_dis_vlan_promisc(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + u8 promisc_m = ICE_PROMISC_VLAN_TX | ICE_PROMISC_VLAN_RX; + int status; + + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, + vlan->vid); + if (status && status != -ENOENT) + return status; + + return 0; +} + +/** + * ice_vf_has_max_vlans - check if VF already has the max allowed VLAN filters + * @vf: VF to check against + * @vsi: VF's VSI + * + * If the VF is trusted then the VF is allowed to add as many VLANs as it + * wants to, so return false. + * + * When the VF is untrusted compare the number of non-zero VLANs + 1 to the max + * allowed VLANs for an untrusted VF. Return the result of this comparison. + */ +static bool ice_vf_has_max_vlans(struct ice_vf *vf, struct ice_vsi *vsi) +{ + if (ice_is_vf_trusted(vf)) + return false; + +#define ICE_VF_ADDED_VLAN_ZERO_FLTRS 1 + return ((ice_vsi_num_non_zero_vlans(vsi) + + ICE_VF_ADDED_VLAN_ZERO_FLTRS) >= ICE_MAX_VLAN_PER_VF); +} + +/** * ice_vc_process_vlan_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -4155,9 +4346,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) bool vlan_promisc = false; struct ice_vsi *vsi; struct device *dev; - struct ice_hw *hw; int status = 0; - u8 promisc_m; int i; dev = ice_pf_to_dev(pf); @@ -4185,15 +4374,13 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) } } - hw = &pf->hw; vsi = ice_get_vf_vsi(vf); if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (add_v && !ice_is_vf_trusted(vf) && - vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) { + if (add_v && ice_vf_has_max_vlans(vf, vsi)) { dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", vf->vf_id); /* There is no need to let VF know about being not trusted, @@ -4202,22 +4389,28 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) goto error_param; } - if (vsi->info.pvid) { + /* in DVM a VF can add/delete inner VLAN filters when + * VIRTCHNL_VF_OFFLOAD_VLAN is negotiated, so only reject in SVM + */ + if (ice_vf_is_port_vlan_ena(vf) && !ice_is_dvm_ena(&pf->hw)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if ((test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || - test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) && - test_bit(ICE_FLAG_VF_TRUE_PROMISC_ENA, pf->flags)) - vlan_promisc = true; + /* in DVM VLAN promiscuous is based on the outer VLAN, which would be + * the port VLAN if VIRTCHNL_VF_OFFLOAD_VLAN was negotiated, so only + * allow vlan_promisc = true in SVM and if no port VLAN is configured + */ + vlan_promisc = ice_is_vlan_promisc_allowed(vf) && + !ice_is_dvm_ena(&pf->hw) && + !ice_vf_is_port_vlan_ena(vf); if (add_v) { for (i = 0; i < vfl->num_elements; i++) { u16 vid = vfl->vlan_id[i]; + struct ice_vlan vlan; - if (!ice_is_vf_trusted(vf) && - vsi->num_vlan >= ICE_MAX_VLAN_PER_VF) { + if (ice_vf_has_max_vlans(vf, vsi)) { dev_info(dev, "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n", vf->vf_id); /* There is no need to let VF know about being @@ -4234,29 +4427,23 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) if (!vid) continue; - status = ice_vsi_add_vlan(vsi, vid, ICE_FWD_TO_VSI); + vlan = ICE_VLAN(ETH_P_8021Q, vid, 0); + status = vsi->inner_vlan_ops.add_vlan(vsi, &vlan); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - /* Enable VLAN pruning when non-zero VLAN is added */ - if (!vlan_promisc && vid && - !ice_vsi_is_vlan_pruning_ena(vsi)) { - status = ice_cfg_vlan_pruning(vsi, true); - if (status) { + /* Enable VLAN filtering on first non-zero VLAN */ + if (!vlan_promisc && vid && !ice_is_dvm_ena(&pf->hw)) { + if (vsi->inner_vlan_ops.ena_rx_filtering(vsi)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n", vid, status); goto error_param; } } else if (vlan_promisc) { - /* Enable Ucast/Mcast VLAN promiscuous mode */ - promisc_m = ICE_PROMISC_VLAN_TX | - ICE_PROMISC_VLAN_RX; - - status = ice_set_vsi_promisc(hw, vsi->idx, - promisc_m, vid); + status = ice_vf_ena_vlan_promisc(vsi, &vlan); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; dev_err(dev, "Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n", @@ -4277,6 +4464,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) num_vf_vlan = vsi->num_vlan; for (i = 0; i < vfl->num_elements && i < num_vf_vlan; i++) { u16 vid = vfl->vlan_id[i]; + struct ice_vlan vlan; /* we add VLAN 0 by default for each VF so we can enable * Tx VLAN anti-spoof without triggering MDD events so @@ -4285,28 +4473,19 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) if (!vid) continue; - /* Make sure ice_vsi_kill_vlan is successful before - * updating VLAN information - */ - status = ice_vsi_kill_vlan(vsi, vid); + vlan = ICE_VLAN(ETH_P_8021Q, vid, 0); + status = vsi->inner_vlan_ops.del_vlan(vsi, &vlan); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - /* Disable VLAN pruning when only VLAN 0 is left */ - if (vsi->num_vlan == 1 && - ice_vsi_is_vlan_pruning_ena(vsi)) - ice_cfg_vlan_pruning(vsi, false); + /* Disable VLAN filtering when only VLAN 0 is left */ + if (!ice_vsi_has_non_zero_vlans(vsi)) + vsi->inner_vlan_ops.dis_rx_filtering(vsi); - /* Disable Unicast/Multicast VLAN promiscuous mode */ - if (vlan_promisc) { - promisc_m = ICE_PROMISC_VLAN_TX | - ICE_PROMISC_VLAN_RX; - - ice_clear_vsi_promisc(hw, vsi->idx, - promisc_m, vid); - } + if (vlan_promisc) + ice_vf_dis_vlan_promisc(vsi, &vlan); } } @@ -4366,7 +4545,7 @@ static int ice_vc_ena_vlan_stripping(struct ice_vf *vf) } vsi = ice_get_vf_vsi(vf); - if (ice_vsi_manage_vlan_stripping(vsi, true)) + if (vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; error_param: @@ -4401,7 +4580,7 @@ static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) goto error_param; } - if (ice_vsi_manage_vlan_stripping(vsi, false)) + if (vsi->inner_vlan_ops.dis_stripping(vsi)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; error_param: @@ -4413,11 +4592,8 @@ error_param: * ice_vf_init_vlan_stripping - enable/disable VLAN stripping on initialization * @vf: VF to enable/disable VLAN stripping for on initialization * - * If the VIRTCHNL_VF_OFFLOAD_VLAN flag is set enable VLAN stripping, else if - * the flag is cleared then we want to disable stripping. For example, the flag - * will be cleared when port VLANs are configured by the administrator before - * passing the VF to the guest or if the AVF driver doesn't support VLAN - * offloads. + * Set the default for VLAN stripping based on whether a port VLAN is configured + * and the current VLAN mode of the device. */ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) { @@ -4426,14 +4602,965 @@ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) if (!vsi) return -EINVAL; - /* don't modify stripping if port VLAN is configured */ - if (vsi->info.pvid) + /* don't modify stripping if port VLAN is configured in SVM since the + * port VLAN is based on the inner/single VLAN in SVM + */ + if (ice_vf_is_port_vlan_ena(vf) && !ice_is_dvm_ena(&vsi->back->hw)) return 0; if (ice_vf_vlan_offload_ena(vf->driver_caps)) - return ice_vsi_manage_vlan_stripping(vsi, true); + return vsi->inner_vlan_ops.ena_stripping(vsi, ETH_P_8021Q); + else + return vsi->inner_vlan_ops.dis_stripping(vsi); +} + +static u16 ice_vc_get_max_vlan_fltrs(struct ice_vf *vf) +{ + if (vf->trusted) + return VLAN_N_VID; else - return ice_vsi_manage_vlan_stripping(vsi, false); + return ICE_MAX_VLAN_PER_VF; +} + +/** + * ice_vf_outer_vlan_not_allowed - check outer VLAN can be used when the device is in DVM + * @vf: VF that being checked for + */ +static bool ice_vf_outer_vlan_not_allowed(struct ice_vf *vf) +{ + if (ice_vf_is_port_vlan_ena(vf)) + return true; + + return false; +} + +/** + * ice_vc_set_dvm_caps - set VLAN capabilities when the device is in DVM + * @vf: VF that capabilities are being set for + * @caps: VLAN capabilities to populate + * + * Determine VLAN capabilities support based on whether a port VLAN is + * configured. If a port VLAN is configured then the VF should use the inner + * filtering/offload capabilities since the port VLAN is using the outer VLAN + * capabilies. + */ +static void +ice_vc_set_dvm_caps(struct ice_vf *vf, struct virtchnl_vlan_caps *caps) +{ + struct virtchnl_vlan_supported_caps *supported_caps; + + if (ice_vf_outer_vlan_not_allowed(vf)) { + /* until support for inner VLAN filtering is added when a port + * VLAN is configured, only support software offloaded inner + * VLANs when a port VLAN is confgured in DVM + */ + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + caps->offloads.ethertype_match = + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + } else { + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100 | + VIRTCHNL_VLAN_ETHERTYPE_AND; + caps->filtering.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100 | + VIRTCHNL_VLAN_ETHERTYPE_XOR | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_ETHERTYPE_88A8 | + VIRTCHNL_VLAN_ETHERTYPE_9100 | + VIRTCHNL_VLAN_ETHERTYPE_XOR | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + + caps->offloads.ethertype_match = + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + } + + caps->filtering.max_filters = ice_vc_get_max_vlan_fltrs(vf); +} + +/** + * ice_vc_set_svm_caps - set VLAN capabilities when the device is in SVM + * @vf: VF that capabilities are being set for + * @caps: VLAN capabilities to populate + * + * Determine VLAN capabilities support based on whether a port VLAN is + * configured. If a port VLAN is configured then the VF does not have any VLAN + * filtering or offload capabilities since the port VLAN is using the inner VLAN + * capabilities in single VLAN mode (SVM). Otherwise allow the VF to use inner + * VLAN fitlering and offload capabilities. + */ +static void +ice_vc_set_svm_caps(struct ice_vf *vf, struct virtchnl_vlan_caps *caps) +{ + struct virtchnl_vlan_supported_caps *supported_caps; + + if (ice_vf_is_port_vlan_ena(vf)) { + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_UNSUPPORTED; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_UNSUPPORTED; + caps->offloads.ethertype_match = VIRTCHNL_VLAN_UNSUPPORTED; + caps->filtering.max_filters = 0; + } else { + supported_caps = &caps->filtering.filtering_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + caps->filtering.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + + supported_caps = &caps->offloads.stripping_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + supported_caps = &caps->offloads.insertion_support; + supported_caps->inner = VIRTCHNL_VLAN_ETHERTYPE_8100 | + VIRTCHNL_VLAN_TOGGLE | + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1; + supported_caps->outer = VIRTCHNL_VLAN_UNSUPPORTED; + + caps->offloads.ethertype_init = VIRTCHNL_VLAN_ETHERTYPE_8100; + caps->offloads.ethertype_match = + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + caps->filtering.max_filters = ice_vc_get_max_vlan_fltrs(vf); + } +} + +/** + * ice_vc_get_offload_vlan_v2_caps - determine VF's VLAN capabilities + * @vf: VF to determine VLAN capabilities for + * + * This will only be called if the VF and PF successfully negotiated + * VIRTCHNL_VF_OFFLOAD_VLAN_V2. + * + * Set VLAN capabilities based on the current VLAN mode and whether a port VLAN + * is configured or not. + */ +static int ice_vc_get_offload_vlan_v2_caps(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_caps *caps = NULL; + int err, len = 0; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + caps = kzalloc(sizeof(*caps), GFP_KERNEL); + if (!caps) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto out; + } + len = sizeof(*caps); + + if (ice_is_dvm_ena(&vf->pf->hw)) + ice_vc_set_dvm_caps(vf, caps); + else + ice_vc_set_svm_caps(vf, caps); + + /* store negotiated caps to prevent invalid VF messages */ + memcpy(&vf->vlan_v2_caps, caps, sizeof(*caps)); + +out: + err = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS, + v_ret, (u8 *)caps, len); + kfree(caps); + return err; +} + +/** + * ice_vc_validate_vlan_tpid - validate VLAN TPID + * @filtering_caps: negotiated/supported VLAN filtering capabilities + * @tpid: VLAN TPID used for validation + * + * Convert the VLAN TPID to a VIRTCHNL_VLAN_ETHERTYPE_* and then compare against + * the negotiated/supported filtering caps to see if the VLAN TPID is valid. + */ +static bool ice_vc_validate_vlan_tpid(u16 filtering_caps, u16 tpid) +{ + enum virtchnl_vlan_support vlan_ethertype = VIRTCHNL_VLAN_UNSUPPORTED; + + switch (tpid) { + case ETH_P_8021Q: + vlan_ethertype = VIRTCHNL_VLAN_ETHERTYPE_8100; + break; + case ETH_P_8021AD: + vlan_ethertype = VIRTCHNL_VLAN_ETHERTYPE_88A8; + break; + case ETH_P_QINQ1: + vlan_ethertype = VIRTCHNL_VLAN_ETHERTYPE_9100; + break; + } + + if (!(filtering_caps & vlan_ethertype)) + return false; + + return true; +} + +/** + * ice_vc_is_valid_vlan - validate the virtchnl_vlan + * @vc_vlan: virtchnl_vlan to validate + * + * If the VLAN TCI and VLAN TPID are 0, then this filter is invalid, so return + * false. Otherwise return true. + */ +static bool ice_vc_is_valid_vlan(struct virtchnl_vlan *vc_vlan) +{ + if (!vc_vlan->tci || !vc_vlan->tpid) + return false; + + return true; +} + +/** + * ice_vc_validate_vlan_filter_list - validate the filter list from the VF + * @vfc: negotiated/supported VLAN filtering capabilities + * @vfl: VLAN filter list from VF to validate + * + * Validate all of the filters in the VLAN filter list from the VF. If any of + * the checks fail then return false. Otherwise return true. + */ +static bool +ice_vc_validate_vlan_filter_list(struct virtchnl_vlan_filtering_caps *vfc, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + u16 i; + + if (!vfl->num_elements) + return false; + + for (i = 0; i < vfl->num_elements; i++) { + struct virtchnl_vlan_supported_caps *filtering_support = + &vfc->filtering_support; + struct virtchnl_vlan_filter *vlan_fltr = &vfl->filters[i]; + struct virtchnl_vlan *outer = &vlan_fltr->outer; + struct virtchnl_vlan *inner = &vlan_fltr->inner; + + if ((ice_vc_is_valid_vlan(outer) && + filtering_support->outer == VIRTCHNL_VLAN_UNSUPPORTED) || + (ice_vc_is_valid_vlan(inner) && + filtering_support->inner == VIRTCHNL_VLAN_UNSUPPORTED)) + return false; + + if ((outer->tci_mask && + !(filtering_support->outer & VIRTCHNL_VLAN_FILTER_MASK)) || + (inner->tci_mask && + !(filtering_support->inner & VIRTCHNL_VLAN_FILTER_MASK))) + return false; + + if (((outer->tci & VLAN_PRIO_MASK) && + !(filtering_support->outer & VIRTCHNL_VLAN_PRIO)) || + ((inner->tci & VLAN_PRIO_MASK) && + !(filtering_support->inner & VIRTCHNL_VLAN_PRIO))) + return false; + + if ((ice_vc_is_valid_vlan(outer) && + !ice_vc_validate_vlan_tpid(filtering_support->outer, outer->tpid)) || + (ice_vc_is_valid_vlan(inner) && + !ice_vc_validate_vlan_tpid(filtering_support->inner, inner->tpid))) + return false; + } + + return true; +} + +/** + * ice_vc_to_vlan - transform from struct virtchnl_vlan to struct ice_vlan + * @vc_vlan: struct virtchnl_vlan to transform + */ +static struct ice_vlan ice_vc_to_vlan(struct virtchnl_vlan *vc_vlan) +{ + struct ice_vlan vlan = { 0 }; + + vlan.prio = (vc_vlan->tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + vlan.vid = vc_vlan->tci & VLAN_VID_MASK; + vlan.tpid = vc_vlan->tpid; + + return vlan; +} + +/** + * ice_vc_vlan_action - action to perform on the virthcnl_vlan + * @vsi: VF's VSI used to perform the action + * @vlan_action: function to perform the action with (i.e. add/del) + * @vlan: VLAN filter to perform the action with + */ +static int +ice_vc_vlan_action(struct ice_vsi *vsi, + int (*vlan_action)(struct ice_vsi *, struct ice_vlan *), + struct ice_vlan *vlan) +{ + int err; + + err = vlan_action(vsi, vlan); + if (err) + return err; + + return 0; +} + +/** + * ice_vc_del_vlans - delete VLAN(s) from the virtchnl filter list + * @vf: VF used to delete the VLAN(s) + * @vsi: VF's VSI used to delete the VLAN(s) + * @vfl: virthchnl filter list used to delete the filters + */ +static int +ice_vc_del_vlans(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + bool vlan_promisc = ice_is_vlan_promisc_allowed(vf); + int err; + u16 i; + + for (i = 0; i < vfl->num_elements; i++) { + struct virtchnl_vlan_filter *vlan_fltr = &vfl->filters[i]; + struct virtchnl_vlan *vc_vlan; + + vc_vlan = &vlan_fltr->outer; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->outer_vlan_ops.del_vlan, + &vlan); + if (err) + return err; + + if (vlan_promisc) + ice_vf_dis_vlan_promisc(vsi, &vlan); + } + + vc_vlan = &vlan_fltr->inner; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->inner_vlan_ops.del_vlan, + &vlan); + if (err) + return err; + + /* no support for VLAN promiscuous on inner VLAN unless + * we are in Single VLAN Mode (SVM) + */ + if (!ice_is_dvm_ena(&vsi->back->hw) && vlan_promisc) + ice_vf_dis_vlan_promisc(vsi, &vlan); + } + } + + return 0; +} + +/** + * ice_vc_remove_vlan_v2_msg - virtchnl handler for VIRTCHNL_OP_DEL_VLAN_V2 + * @vf: VF the message was received from + * @msg: message received from the VF + */ +static int ice_vc_remove_vlan_v2_msg(struct ice_vf *vf, u8 *msg) +{ + struct virtchnl_vlan_filter_list_v2 *vfl = + (struct virtchnl_vlan_filter_list_v2 *)msg; + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct ice_vsi *vsi; + + if (!ice_vc_validate_vlan_filter_list(&vf->vlan_v2_caps.filtering, + vfl)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (ice_vc_del_vlans(vf, vsi, vfl)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN_V2, v_ret, NULL, + 0); +} + +/** + * ice_vc_add_vlans - add VLAN(s) from the virtchnl filter list + * @vf: VF used to add the VLAN(s) + * @vsi: VF's VSI used to add the VLAN(s) + * @vfl: virthchnl filter list used to add the filters + */ +static int +ice_vc_add_vlans(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + bool vlan_promisc = ice_is_vlan_promisc_allowed(vf); + int err; + u16 i; + + for (i = 0; i < vfl->num_elements; i++) { + struct virtchnl_vlan_filter *vlan_fltr = &vfl->filters[i]; + struct virtchnl_vlan *vc_vlan; + + vc_vlan = &vlan_fltr->outer; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->outer_vlan_ops.add_vlan, + &vlan); + if (err) + return err; + + if (vlan_promisc) { + err = ice_vf_ena_vlan_promisc(vsi, &vlan); + if (err) + return err; + } + } + + vc_vlan = &vlan_fltr->inner; + if (ice_vc_is_valid_vlan(vc_vlan)) { + struct ice_vlan vlan = ice_vc_to_vlan(vc_vlan); + + err = ice_vc_vlan_action(vsi, + vsi->inner_vlan_ops.add_vlan, + &vlan); + if (err) + return err; + + /* no support for VLAN promiscuous on inner VLAN unless + * we are in Single VLAN Mode (SVM) + */ + if (!ice_is_dvm_ena(&vsi->back->hw) && vlan_promisc) { + err = ice_vf_ena_vlan_promisc(vsi, &vlan); + if (err) + return err; + } + } + } + + return 0; +} + +/** + * ice_vc_validate_add_vlan_filter_list - validate add filter list from the VF + * @vsi: VF VSI used to get number of existing VLAN filters + * @vfc: negotiated/supported VLAN filtering capabilities + * @vfl: VLAN filter list from VF to validate + * + * Validate all of the filters in the VLAN filter list from the VF during the + * VIRTCHNL_OP_ADD_VLAN_V2 opcode. If any of the checks fail then return false. + * Otherwise return true. + */ +static bool +ice_vc_validate_add_vlan_filter_list(struct ice_vsi *vsi, + struct virtchnl_vlan_filtering_caps *vfc, + struct virtchnl_vlan_filter_list_v2 *vfl) +{ + u16 num_requested_filters = vsi->num_vlan + vfl->num_elements; + + if (num_requested_filters > vfc->max_filters) + return false; + + return ice_vc_validate_vlan_filter_list(vfc, vfl); +} + +/** + * ice_vc_add_vlan_v2_msg - virtchnl handler for VIRTCHNL_OP_ADD_VLAN_V2 + * @vf: VF the message was received from + * @msg: message received from the VF + */ +static int ice_vc_add_vlan_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_filter_list_v2 *vfl = + (struct virtchnl_vlan_filter_list_v2 *)msg; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, vfl->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_validate_add_vlan_filter_list(vsi, + &vf->vlan_v2_caps.filtering, + vfl)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (ice_vc_add_vlans(vf, vsi, vfl)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN_V2, v_ret, NULL, + 0); +} + +/** + * ice_vc_valid_vlan_setting - validate VLAN setting + * @negotiated_settings: negotiated VLAN settings during VF init + * @ethertype_setting: ethertype(s) requested for the VLAN setting + */ +static bool +ice_vc_valid_vlan_setting(u32 negotiated_settings, u32 ethertype_setting) +{ + if (ethertype_setting && !(negotiated_settings & ethertype_setting)) + return false; + + /* only allow a single VIRTCHNL_VLAN_ETHERTYPE if + * VIRTHCNL_VLAN_ETHERTYPE_AND is not negotiated/supported + */ + if (!(negotiated_settings & VIRTCHNL_VLAN_ETHERTYPE_AND) && + hweight32(ethertype_setting) > 1) + return false; + + /* ability to modify the VLAN setting was not negotiated */ + if (!(negotiated_settings & VIRTCHNL_VLAN_TOGGLE)) + return false; + + return true; +} + +/** + * ice_vc_valid_vlan_setting_msg - validate the VLAN setting message + * @caps: negotiated VLAN settings during VF init + * @msg: message to validate + * + * Used to validate any VLAN virtchnl message sent as a + * virtchnl_vlan_setting structure. Validates the message against the + * negotiated/supported caps during VF driver init. + */ +static bool +ice_vc_valid_vlan_setting_msg(struct virtchnl_vlan_supported_caps *caps, + struct virtchnl_vlan_setting *msg) +{ + if ((!msg->outer_ethertype_setting && + !msg->inner_ethertype_setting) || + (!caps->outer && !caps->inner)) + return false; + + if (msg->outer_ethertype_setting && + !ice_vc_valid_vlan_setting(caps->outer, + msg->outer_ethertype_setting)) + return false; + + if (msg->inner_ethertype_setting && + !ice_vc_valid_vlan_setting(caps->inner, + msg->inner_ethertype_setting)) + return false; + + return true; +} + +/** + * ice_vc_get_tpid - transform from VIRTCHNL_VLAN_ETHERTYPE_* to VLAN TPID + * @ethertype_setting: VIRTCHNL_VLAN_ETHERTYPE_* used to get VLAN TPID + * @tpid: VLAN TPID to populate + */ +static int ice_vc_get_tpid(u32 ethertype_setting, u16 *tpid) +{ + switch (ethertype_setting) { + case VIRTCHNL_VLAN_ETHERTYPE_8100: + *tpid = ETH_P_8021Q; + break; + case VIRTCHNL_VLAN_ETHERTYPE_88A8: + *tpid = ETH_P_8021AD; + break; + case VIRTCHNL_VLAN_ETHERTYPE_9100: + *tpid = ETH_P_QINQ1; + break; + default: + *tpid = 0; + return -EINVAL; + } + + return 0; +} + +/** + * ice_vc_ena_vlan_offload - enable VLAN offload based on the ethertype_setting + * @vsi: VF's VSI used to enable the VLAN offload + * @ena_offload: function used to enable the VLAN offload + * @ethertype_setting: VIRTCHNL_VLAN_ETHERTYPE_* to enable offloads for + */ +static int +ice_vc_ena_vlan_offload(struct ice_vsi *vsi, + int (*ena_offload)(struct ice_vsi *vsi, u16 tpid), + u32 ethertype_setting) +{ + u16 tpid; + int err; + + err = ice_vc_get_tpid(ethertype_setting, &tpid); + if (err) + return err; + + err = ena_offload(vsi, tpid); + if (err) + return err; + + return 0; +} + +#define ICE_L2TSEL_QRX_CONTEXT_REG_IDX 3 +#define ICE_L2TSEL_BIT_OFFSET 23 +enum ice_l2tsel { + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND, + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG1, +}; + +/** + * ice_vsi_update_l2tsel - update l2tsel field for all Rx rings on this VSI + * @vsi: VSI used to update l2tsel on + * @l2tsel: l2tsel setting requested + * + * Use the l2tsel setting to update all of the Rx queue context bits for l2tsel. + * This will modify which descriptor field the first offloaded VLAN will be + * stripped into. + */ +static void ice_vsi_update_l2tsel(struct ice_vsi *vsi, enum ice_l2tsel l2tsel) +{ + struct ice_hw *hw = &vsi->back->hw; + u32 l2tsel_bit; + int i; + + if (l2tsel == ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND) + l2tsel_bit = 0; + else + l2tsel_bit = BIT(ICE_L2TSEL_BIT_OFFSET); + + for (i = 0; i < vsi->alloc_rxq; i++) { + u16 pfq = vsi->rxq_map[i]; + u32 qrx_context_offset; + u32 regval; + + qrx_context_offset = + QRX_CONTEXT(ICE_L2TSEL_QRX_CONTEXT_REG_IDX, pfq); + + regval = rd32(hw, qrx_context_offset); + regval &= ~BIT(ICE_L2TSEL_BIT_OFFSET); + regval |= l2tsel_bit; + wr32(hw, qrx_context_offset, regval); + } +} + +/** + * ice_vc_ena_vlan_stripping_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 + */ +static int ice_vc_ena_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *stripping_support; + struct virtchnl_vlan_setting *strip_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, strip_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + stripping_support = &vf->vlan_v2_caps.offloads.stripping_support; + if (!ice_vc_valid_vlan_setting_msg(stripping_support, strip_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = strip_msg->outer_ethertype_setting; + if (ethertype_setting) { + if (ice_vc_ena_vlan_offload(vsi, + vsi->outer_vlan_ops.ena_stripping, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } else { + enum ice_l2tsel l2tsel = + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG2_2ND; + + /* PF tells the VF that the outer VLAN tag is always + * extracted to VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2 and + * inner is always extracted to + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1. This is needed to + * support outer stripping so the first tag always ends + * up in L2TAG2_2ND and the second/inner tag, if + * enabled, is extracted in L2TAG1. + */ + ice_vsi_update_l2tsel(vsi, l2tsel); + } + } + + ethertype_setting = strip_msg->inner_ethertype_setting; + if (ethertype_setting && + ice_vc_ena_vlan_offload(vsi, vsi->inner_vlan_ops.ena_stripping, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2, v_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_stripping_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 + */ +static int ice_vc_dis_vlan_stripping_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *stripping_support; + struct virtchnl_vlan_setting *strip_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, strip_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + stripping_support = &vf->vlan_v2_caps.offloads.stripping_support; + if (!ice_vc_valid_vlan_setting_msg(stripping_support, strip_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = strip_msg->outer_ethertype_setting; + if (ethertype_setting) { + if (vsi->outer_vlan_ops.dis_stripping(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } else { + enum ice_l2tsel l2tsel = + ICE_L2TSEL_EXTRACT_FIRST_TAG_L2TAG1; + + /* PF tells the VF that the outer VLAN tag is always + * extracted to VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2 and + * inner is always extracted to + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1. This is needed to + * support inner stripping while outer stripping is + * disabled so that the first and only tag is extracted + * in L2TAG1. + */ + ice_vsi_update_l2tsel(vsi, l2tsel); + } + } + + ethertype_setting = strip_msg->inner_ethertype_setting; + if (ethertype_setting && vsi->inner_vlan_ops.dis_stripping(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2, v_ret, NULL, 0); +} + +/** + * ice_vc_ena_vlan_insertion_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 + */ +static int ice_vc_ena_vlan_insertion_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *insertion_support; + struct virtchnl_vlan_setting *insertion_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, insertion_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + insertion_support = &vf->vlan_v2_caps.offloads.insertion_support; + if (!ice_vc_valid_vlan_setting_msg(insertion_support, insertion_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->outer_ethertype_setting; + if (ethertype_setting && + ice_vc_ena_vlan_offload(vsi, vsi->outer_vlan_ops.ena_insertion, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->inner_ethertype_setting; + if (ethertype_setting && + ice_vc_ena_vlan_offload(vsi, vsi->inner_vlan_ops.ena_insertion, + ethertype_setting)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2, v_ret, NULL, 0); +} + +/** + * ice_vc_dis_vlan_insertion_v2_msg + * @vf: VF the message was received from + * @msg: message received from the VF + * + * virthcnl handler for VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 + */ +static int ice_vc_dis_vlan_insertion_v2_msg(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_vlan_supported_caps *insertion_support; + struct virtchnl_vlan_setting *insertion_msg = + (struct virtchnl_vlan_setting *)msg; + u32 ethertype_setting; + struct ice_vsi *vsi; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + if (!ice_vc_isvalid_vsi_id(vf, insertion_msg->vport_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + insertion_support = &vf->vlan_v2_caps.offloads.insertion_support; + if (!ice_vc_valid_vlan_setting_msg(insertion_support, insertion_msg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->outer_ethertype_setting; + if (ethertype_setting && vsi->outer_vlan_ops.dis_insertion(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + + ethertype_setting = insertion_msg->inner_ethertype_setting; + if (ethertype_setting && vsi->inner_vlan_ops.dis_insertion(vsi)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto out; + } + +out: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2, v_ret, NULL, 0); } static struct ice_vc_vf_ops ice_vc_vf_dflt_ops = { @@ -4458,6 +5585,13 @@ static struct ice_vc_vf_ops ice_vc_vf_dflt_ops = { .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, .add_fdir_fltr_msg = ice_vc_add_fdir_fltr, .del_fdir_fltr_msg = ice_vc_del_fdir_fltr, + .get_offload_vlan_v2_caps = ice_vc_get_offload_vlan_v2_caps, + .add_vlan_v2_msg = ice_vc_add_vlan_v2_msg, + .remove_vlan_v2_msg = ice_vc_remove_vlan_v2_msg, + .ena_vlan_stripping_v2_msg = ice_vc_ena_vlan_stripping_v2_msg, + .dis_vlan_stripping_v2_msg = ice_vc_dis_vlan_stripping_v2_msg, + .ena_vlan_insertion_v2_msg = ice_vc_ena_vlan_insertion_v2_msg, + .dis_vlan_insertion_v2_msg = ice_vc_dis_vlan_insertion_v2_msg, }; void ice_vc_set_dflt_vf_ops(struct ice_vc_vf_ops *ops) @@ -4686,7 +5820,7 @@ error_handler: case VIRTCHNL_OP_GET_VF_RESOURCES: err = ops->get_vf_res_msg(vf, msg); if (ice_vf_init_vlan_stripping(vf)) - dev_err(dev, "Failed to initialize VLAN stripping for VF %d\n", + dev_dbg(dev, "Failed to initialize VLAN stripping for VF %d\n", vf->vf_id); ice_vc_notify_vf_link_state(vf); break; @@ -4751,6 +5885,27 @@ error_handler: case VIRTCHNL_OP_DEL_RSS_CFG: err = ops->handle_rss_cfg_msg(vf, msg, false); break; + case VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS: + err = ops->get_offload_vlan_v2_caps(vf); + break; + case VIRTCHNL_OP_ADD_VLAN_V2: + err = ops->add_vlan_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_DEL_VLAN_V2: + err = ops->remove_vlan_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2: + err = ops->ena_vlan_stripping_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2: + err = ops->dis_vlan_stripping_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2: + err = ops->ena_vlan_insertion_v2_msg(vf, msg); + break; + case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2: + err = ops->dis_vlan_insertion_v2_msg(vf, msg); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, @@ -4797,8 +5952,10 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr); /* VF configuration for VLAN and applicable QoS */ - ivi->vlan = vf->port_vlan_info & VLAN_VID_MASK; - ivi->qos = (vf->port_vlan_info & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + ivi->vlan = ice_vf_get_port_vlan_id(vf); + ivi->qos = ice_vf_get_port_vlan_prio(vf); + if (ice_vf_is_port_vlan_ena(vf)) + ivi->vlan_proto = cpu_to_be16(ice_vf_get_port_vlan_tpid(vf)); ivi->trusted = vf->trusted; ivi->spoofchk = vf->spoofchk; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 752487a1bdd6..4f4961043638 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -5,6 +5,7 @@ #define _ICE_VIRTCHNL_PF_H_ #include "ice.h" #include "ice_virtchnl_fdir.h" +#include "ice_vsi_vlan_ops.h" /* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ #define ICE_MAX_VLAN_PER_VF 8 @@ -94,6 +95,13 @@ struct ice_vc_vf_ops { int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add); int (*add_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); int (*del_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); + int (*get_offload_vlan_v2_caps)(struct ice_vf *vf); + int (*add_vlan_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*remove_vlan_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_vlan_stripping_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*dis_vlan_stripping_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg); + int (*dis_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg); }; /* VF information structure */ @@ -119,7 +127,8 @@ struct ice_vf { struct ice_time_mac legacy_last_added_umac; DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF); DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF); - u16 port_vlan_info; /* Port VLAN ID and QoS */ + struct ice_vlan port_vlan_info; /* Port VLAN ID, QoS, and TPID */ + struct virtchnl_vlan_caps vlan_v2_caps; u8 pf_set_mac:1; /* VF MAC address set by VMM admin */ u8 trusted:1; u8 spoofchk:1; @@ -210,6 +219,7 @@ int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, enum virtchnl_status_code v_retval, u8 *msg, u16 msglen); bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id); +bool ice_vf_is_port_vlan_ena(struct ice_vf *vf); #else /* CONFIG_PCI_IOV */ static inline void ice_process_vflr_event(struct ice_pf *pf) { } static inline void ice_free_vfs(struct ice_pf *pf) { } @@ -342,5 +352,10 @@ static inline bool ice_is_any_vf_in_promisc(struct ice_pf __always_unused *pf) { return false; } + +static inline bool ice_vf_is_port_vlan_ena(struct ice_vf __always_unused *vf) +{ + return false; +} #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_VIRTCHNL_PF_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vlan.h b/drivers/net/ethernet/intel/ice/ice_vlan.h new file mode 100644 index 000000000000..bc4550a03173 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vlan.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VLAN_H_ +#define _ICE_VLAN_H_ + +#include <linux/types.h> +#include "ice_type.h" + +struct ice_vlan { + u16 tpid; + u16 vid; + u8 prio; +}; + +#define ICE_VLAN(tpid, vid, prio) ((struct ice_vlan){ tpid, vid, prio }) + +#endif /* _ICE_VLAN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c new file mode 100644 index 000000000000..1b618de592b7 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c @@ -0,0 +1,439 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_common.h" + +/** + * ice_pkg_get_supported_vlan_mode - determine if DDP supports Double VLAN mode + * @hw: pointer to the HW struct + * @dvm: output variable to determine if DDP supports DVM(true) or SVM(false) + */ +static int +ice_pkg_get_supported_vlan_mode(struct ice_hw *hw, bool *dvm) +{ + u16 meta_init_size = sizeof(struct ice_meta_init_section); + struct ice_meta_init_section *sect; + struct ice_buf_build *bld; + int status; + + /* if anything fails, we assume there is no DVM support */ + *dvm = false; + + bld = ice_pkg_buf_alloc_single_section(hw, + ICE_SID_RXPARSER_METADATA_INIT, + meta_init_size, (void **)§); + if (!bld) + return -ENOMEM; + + /* only need to read a single section */ + sect->count = cpu_to_le16(1); + sect->offset = cpu_to_le16(ICE_META_VLAN_MODE_ENTRY); + + status = ice_aq_upload_section(hw, + (struct ice_buf_hdr *)ice_pkg_buf(bld), + ICE_PKG_BUF_SIZE, NULL); + if (!status) { + DECLARE_BITMAP(entry, ICE_META_INIT_BITS); + u32 arr[ICE_META_INIT_DW_CNT]; + u16 i; + + /* convert to host bitmap format */ + for (i = 0; i < ICE_META_INIT_DW_CNT; i++) + arr[i] = le32_to_cpu(sect->entry.bm[i]); + + bitmap_from_arr32(entry, arr, (u16)ICE_META_INIT_BITS); + + /* check if DVM is supported */ + *dvm = test_bit(ICE_META_VLAN_MODE_BIT, entry); + } + + ice_pkg_buf_free(hw, bld); + + return status; +} + +/** + * ice_aq_get_vlan_mode - get the VLAN mode of the device + * @hw: pointer to the HW structure + * @get_params: structure FW fills in based on the current VLAN mode config + * + * Get VLAN Mode Parameters (0x020D) + */ +static int +ice_aq_get_vlan_mode(struct ice_hw *hw, + struct ice_aqc_get_vlan_mode *get_params) +{ + struct ice_aq_desc desc; + + if (!get_params) + return -EINVAL; + + ice_fill_dflt_direct_cmd_desc(&desc, + ice_aqc_opc_get_vlan_mode_parameters); + + return ice_aq_send_cmd(hw, &desc, get_params, sizeof(*get_params), + NULL); +} + +/** + * ice_aq_is_dvm_ena - query FW to check if double VLAN mode is enabled + * @hw: pointer to the HW structure + * + * Returns true if the hardware/firmware is configured in double VLAN mode, + * else return false signaling that the hardware/firmware is configured in + * single VLAN mode. + * + * Also, return false if this call fails for any reason (i.e. firmware doesn't + * support this AQ call). + */ +static bool ice_aq_is_dvm_ena(struct ice_hw *hw) +{ + struct ice_aqc_get_vlan_mode get_params = { 0 }; + int status; + + status = ice_aq_get_vlan_mode(hw, &get_params); + if (status) { + ice_debug(hw, ICE_DBG_AQ, "Failed to get VLAN mode, status %d\n", + status); + return false; + } + + return (get_params.vlan_mode & ICE_AQ_VLAN_MODE_DVM_ENA); +} + +/** + * ice_is_dvm_ena - check if double VLAN mode is enabled + * @hw: pointer to the HW structure + * + * The device is configured in single or double VLAN mode on initialization and + * this cannot be dynamically changed during runtime. Based on this there is no + * need to make an AQ call every time the driver needs to know the VLAN mode. + * Instead, use the cached VLAN mode. + */ +bool ice_is_dvm_ena(struct ice_hw *hw) +{ + return hw->dvm_ena; +} + +/** + * ice_cache_vlan_mode - cache VLAN mode after DDP is downloaded + * @hw: pointer to the HW structure + * + * This is only called after downloading the DDP and after the global + * configuration lock has been released because all ports on a device need to + * cache the VLAN mode. + */ +static void ice_cache_vlan_mode(struct ice_hw *hw) +{ + hw->dvm_ena = ice_aq_is_dvm_ena(hw) ? true : false; +} + +/** + * ice_pkg_supports_dvm - find out if DDP supports DVM + * @hw: pointer to the HW structure + */ +static bool ice_pkg_supports_dvm(struct ice_hw *hw) +{ + bool pkg_supports_dvm; + int status; + + status = ice_pkg_get_supported_vlan_mode(hw, &pkg_supports_dvm); + if (status) { + ice_debug(hw, ICE_DBG_PKG, "Failed to get supported VLAN mode, status %d\n", + status); + return false; + } + + return pkg_supports_dvm; +} + +/** + * ice_fw_supports_dvm - find out if FW supports DVM + * @hw: pointer to the HW structure + */ +static bool ice_fw_supports_dvm(struct ice_hw *hw) +{ + struct ice_aqc_get_vlan_mode get_vlan_mode = { 0 }; + int status; + + /* If firmware returns success, then it supports DVM, else it only + * supports SVM + */ + status = ice_aq_get_vlan_mode(hw, &get_vlan_mode); + if (status) { + ice_debug(hw, ICE_DBG_NVM, "Failed to get VLAN mode, status %d\n", + status); + return false; + } + + return true; +} + +/** + * ice_is_dvm_supported - check if Double VLAN Mode is supported + * @hw: pointer to the hardware structure + * + * Returns true if Double VLAN Mode (DVM) is supported and false if only Single + * VLAN Mode (SVM) is supported. In order for DVM to be supported the DDP and + * firmware must support it, otherwise only SVM is supported. This function + * should only be called while the global config lock is held and after the + * package has been successfully downloaded. + */ +static bool ice_is_dvm_supported(struct ice_hw *hw) +{ + if (!ice_pkg_supports_dvm(hw)) { + ice_debug(hw, ICE_DBG_PKG, "DDP doesn't support DVM\n"); + return false; + } + + if (!ice_fw_supports_dvm(hw)) { + ice_debug(hw, ICE_DBG_PKG, "FW doesn't support DVM\n"); + return false; + } + + return true; +} + +#define ICE_EXTERNAL_VLAN_ID_FV_IDX 11 +#define ICE_SW_LKUP_VLAN_LOC_LKUP_IDX 1 +#define ICE_SW_LKUP_VLAN_PKT_FLAGS_LKUP_IDX 2 +#define ICE_SW_LKUP_PROMISC_VLAN_LOC_LKUP_IDX 2 +#define ICE_PKT_FLAGS_0_TO_15_FV_IDX 1 +#define ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK 0xD000 +static struct ice_update_recipe_lkup_idx_params ice_dvm_dflt_recipes[] = { + { + /* Update recipe ICE_SW_LKUP_VLAN to filter based on the + * outer/single VLAN in DVM + */ + .rid = ICE_SW_LKUP_VLAN, + .fv_idx = ICE_EXTERNAL_VLAN_ID_FV_IDX, + .ignore_valid = true, + .mask = 0, + .mask_valid = false, /* use pre-existing mask */ + .lkup_idx = ICE_SW_LKUP_VLAN_LOC_LKUP_IDX, + }, + { + /* Update recipe ICE_SW_LKUP_VLAN to filter based on the VLAN + * packet flags to support VLAN filtering on multiple VLAN + * ethertypes (i.e. 0x8100 and 0x88a8) in DVM + */ + .rid = ICE_SW_LKUP_VLAN, + .fv_idx = ICE_PKT_FLAGS_0_TO_15_FV_IDX, + .ignore_valid = false, + .mask = ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK, + .mask_valid = true, + .lkup_idx = ICE_SW_LKUP_VLAN_PKT_FLAGS_LKUP_IDX, + }, + { + /* Update recipe ICE_SW_LKUP_PROMISC_VLAN to filter based on the + * outer/single VLAN in DVM + */ + .rid = ICE_SW_LKUP_PROMISC_VLAN, + .fv_idx = ICE_EXTERNAL_VLAN_ID_FV_IDX, + .ignore_valid = true, + .mask = 0, + .mask_valid = false, /* use pre-existing mask */ + .lkup_idx = ICE_SW_LKUP_PROMISC_VLAN_LOC_LKUP_IDX, + }, +}; + +/** + * ice_dvm_update_dflt_recipes - update default switch recipes in DVM + * @hw: hardware structure used to update the recipes + */ +static int ice_dvm_update_dflt_recipes(struct ice_hw *hw) +{ + unsigned long i; + + for (i = 0; i < ARRAY_SIZE(ice_dvm_dflt_recipes); i++) { + struct ice_update_recipe_lkup_idx_params *params; + int status; + + params = &ice_dvm_dflt_recipes[i]; + + status = ice_update_recipe_lkup_idx(hw, params); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to update RID %d lkup_idx %d fv_idx %d mask_valid %s mask 0x%04x\n", + params->rid, params->lkup_idx, params->fv_idx, + params->mask_valid ? "true" : "false", + params->mask); + return status; + } + } + + return 0; +} + +/** + * ice_aq_set_vlan_mode - set the VLAN mode of the device + * @hw: pointer to the HW structure + * @set_params: requested VLAN mode configuration + * + * Set VLAN Mode Parameters (0x020C) + */ +static int +ice_aq_set_vlan_mode(struct ice_hw *hw, + struct ice_aqc_set_vlan_mode *set_params) +{ + u8 rdma_packet, mng_vlan_prot_id; + struct ice_aq_desc desc; + + if (!set_params) + return -EINVAL; + + if (set_params->l2tag_prio_tagging > ICE_AQ_VLAN_PRIO_TAG_MAX) + return -EINVAL; + + rdma_packet = set_params->rdma_packet; + if (rdma_packet != ICE_AQ_SVM_VLAN_RDMA_PKT_FLAG_SETTING && + rdma_packet != ICE_AQ_DVM_VLAN_RDMA_PKT_FLAG_SETTING) + return -EINVAL; + + mng_vlan_prot_id = set_params->mng_vlan_prot_id; + if (mng_vlan_prot_id != ICE_AQ_VLAN_MNG_PROTOCOL_ID_OUTER && + mng_vlan_prot_id != ICE_AQ_VLAN_MNG_PROTOCOL_ID_INNER) + return -EINVAL; + + ice_fill_dflt_direct_cmd_desc(&desc, + ice_aqc_opc_set_vlan_mode_parameters); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + return ice_aq_send_cmd(hw, &desc, set_params, sizeof(*set_params), + NULL); +} + +/** + * ice_set_dvm - sets up software and hardware for double VLAN mode + * @hw: pointer to the hardware structure + */ +static int ice_set_dvm(struct ice_hw *hw) +{ + struct ice_aqc_set_vlan_mode params = { 0 }; + int status; + + params.l2tag_prio_tagging = ICE_AQ_VLAN_PRIO_TAG_OUTER_CTAG; + params.rdma_packet = ICE_AQ_DVM_VLAN_RDMA_PKT_FLAG_SETTING; + params.mng_vlan_prot_id = ICE_AQ_VLAN_MNG_PROTOCOL_ID_OUTER; + + status = ice_aq_set_vlan_mode(hw, ¶ms); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set double VLAN mode parameters, status %d\n", + status); + return status; + } + + status = ice_dvm_update_dflt_recipes(hw); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to update default recipes for double VLAN mode, status %d\n", + status); + return status; + } + + status = ice_aq_set_port_params(hw->port_info, true, NULL); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set port in double VLAN mode, status %d\n", + status); + return status; + } + + status = ice_set_dvm_boost_entries(hw); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set boost TCAM entries for double VLAN mode, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_set_svm - set single VLAN mode + * @hw: pointer to the HW structure + */ +static int ice_set_svm(struct ice_hw *hw) +{ + struct ice_aqc_set_vlan_mode *set_params; + int status; + + status = ice_aq_set_port_params(hw->port_info, false, NULL); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to set port parameters for single VLAN mode\n"); + return status; + } + + set_params = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*set_params), + GFP_KERNEL); + if (!set_params) + return -ENOMEM; + + /* default configuration for SVM configurations */ + set_params->l2tag_prio_tagging = ICE_AQ_VLAN_PRIO_TAG_INNER_CTAG; + set_params->rdma_packet = ICE_AQ_SVM_VLAN_RDMA_PKT_FLAG_SETTING; + set_params->mng_vlan_prot_id = ICE_AQ_VLAN_MNG_PROTOCOL_ID_INNER; + + status = ice_aq_set_vlan_mode(hw, set_params); + if (status) + ice_debug(hw, ICE_DBG_INIT, "Failed to configure port in single VLAN mode\n"); + + devm_kfree(ice_hw_to_dev(hw), set_params); + return status; +} + +/** + * ice_set_vlan_mode + * @hw: pointer to the HW structure + */ +int ice_set_vlan_mode(struct ice_hw *hw) +{ + if (!ice_is_dvm_supported(hw)) + return 0; + + if (!ice_set_dvm(hw)) + return 0; + + return ice_set_svm(hw); +} + +/** + * ice_print_dvm_not_supported - print if DDP and/or FW doesn't support DVM + * @hw: pointer to the HW structure + * + * The purpose of this function is to print that QinQ is not supported due to + * incompatibilty from the DDP and/or FW. This will give a hint to the user to + * update one and/or both components if they expect QinQ functionality. + */ +static void ice_print_dvm_not_supported(struct ice_hw *hw) +{ + bool pkg_supports_dvm = ice_pkg_supports_dvm(hw); + bool fw_supports_dvm = ice_fw_supports_dvm(hw); + + if (!fw_supports_dvm && !pkg_supports_dvm) + dev_info(ice_hw_to_dev(hw), "QinQ functionality cannot be enabled on this device. Update your DDP package and NVM to versions that support QinQ.\n"); + else if (!pkg_supports_dvm) + dev_info(ice_hw_to_dev(hw), "QinQ functionality cannot be enabled on this device. Update your DDP package to a version that supports QinQ.\n"); + else if (!fw_supports_dvm) + dev_info(ice_hw_to_dev(hw), "QinQ functionality cannot be enabled on this device. Update your NVM to a version that supports QinQ.\n"); +} + +/** + * ice_post_pkg_dwnld_vlan_mode_cfg - configure VLAN mode after DDP download + * @hw: pointer to the HW structure + * + * This function is meant to configure any VLAN mode specific functionality + * after the global configuration lock has been released and the DDP has been + * downloaded. + * + * Since only one PF downloads the DDP and configures the VLAN mode there needs + * to be a way to configure the other PFs after the DDP has been downloaded and + * the global configuration lock has been released. All such code should go in + * this function. + */ +void ice_post_pkg_dwnld_vlan_mode_cfg(struct ice_hw *hw) +{ + ice_cache_vlan_mode(hw); + + if (ice_is_dvm_ena(hw)) + ice_change_proto_id_to_dvm(); + else + ice_print_dvm_not_supported(hw); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vlan_mode.h b/drivers/net/ethernet/intel/ice/ice_vlan_mode.h new file mode 100644 index 000000000000..a0fb743d08e2 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vlan_mode.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VLAN_MODE_H_ +#define _ICE_VLAN_MODE_H_ + +struct ice_hw; + +bool ice_is_dvm_ena(struct ice_hw *hw); +int ice_set_vlan_mode(struct ice_hw *hw); +void ice_post_pkg_dwnld_vlan_mode_cfg(struct ice_hw *hw); + +#endif /* _ICE_VLAN_MODE_H */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c new file mode 100644 index 000000000000..5b4a0abb4607 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -0,0 +1,707 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_vsi_vlan_lib.h" +#include "ice_lib.h" +#include "ice_fltr.h" +#include "ice.h" + +static void print_invalid_tpid(struct ice_vsi *vsi, u16 tpid) +{ + dev_err(ice_pf_to_dev(vsi->back), "%s %d specified invalid VLAN tpid 0x%04x\n", + ice_vsi_type_str(vsi->type), vsi->idx, tpid); +} + +/** + * validate_vlan - check if the ice_vlan passed in is valid + * @vsi: VSI used for printing error message + * @vlan: ice_vlan structure to validate + * + * Return true if the VLAN TPID is valid or if the VLAN TPID is 0 and the VLAN + * VID is 0, which allows for non-zero VLAN filters with the specified VLAN TPID + * and untagged VLAN 0 filters to be added to the prune list respectively. + */ +static bool validate_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + if (vlan->tpid != ETH_P_8021Q && vlan->tpid != ETH_P_8021AD && + vlan->tpid != ETH_P_QINQ1 && (vlan->tpid || vlan->vid)) { + print_invalid_tpid(vsi, vlan->tpid); + return false; + } + + return true; +} + +/** + * ice_vsi_add_vlan - default add VLAN implementation for all VSI types + * @vsi: VSI being configured + * @vlan: VLAN filter to add + */ +int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + int err; + + if (!validate_vlan(vsi, vlan)) + return -EINVAL; + + err = ice_fltr_add_vlan(vsi, vlan); + if (err && err != -EEXIST) { + dev_err(ice_pf_to_dev(vsi->back), "Failure Adding VLAN %d on VSI %i, status %d\n", + vlan->vid, vsi->vsi_num, err); + return err; + } + + vsi->num_vlan++; + return 0; +} + +/** + * ice_vsi_del_vlan - default del VLAN implementation for all VSI types + * @vsi: VSI being configured + * @vlan: VLAN filter to delete + */ +int ice_vsi_del_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + struct ice_pf *pf = vsi->back; + struct device *dev; + int err; + + if (!validate_vlan(vsi, vlan)) + return -EINVAL; + + dev = ice_pf_to_dev(pf); + + err = ice_fltr_remove_vlan(vsi, vlan); + if (!err) + vsi->num_vlan--; + else if (err == -ENOENT || err == -EBUSY) + err = 0; + else + dev_err(dev, "Error removing VLAN %d on VSI %i error: %d\n", + vlan->vid, vsi->vsi_num, err); + + return err; +} + +/** + * ice_vsi_manage_vlan_insertion - Manage VLAN insertion for the VSI for Tx + * @vsi: the VSI being changed + */ +static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + /* Here we are configuring the VSI to let the driver add VLAN tags by + * setting inner_vlan_flags to ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL. The actual VLAN tag + * insertion happens in the Tx hot path, in ice_tx_map. + */ + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; + + /* Preserve existing VLAN strip setting */ + ctxt->info.inner_vlan_flags |= (vsi->info.inner_vlan_flags & + ICE_AQ_VSI_INNER_VLAN_EMODE_M); + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + goto out; + } + + vsi->info.inner_vlan_flags = ctxt->info.inner_vlan_flags; +out: + kfree(ctxt); + return err; +} + +/** + * ice_vsi_manage_vlan_stripping - Manage VLAN stripping for the VSI for Rx + * @vsi: the VSI being changed + * @ena: boolean value indicating if this is a enable or disable request + */ +static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + /* do not allow modifying VLAN stripping when a port VLAN is configured + * on this VSI + */ + if (vsi->info.port_based_inner_vlan) + return 0; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + /* Here we are configuring what the VSI should do with the VLAN tag in + * the Rx packet. We can either leave the tag in the packet or put it in + * the Rx descriptor. + */ + if (ena) + /* Strip VLAN tag from Rx packet and put it in the desc */ + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_STR_BOTH; + else + /* Disable stripping. Leave tag in packet */ + ctxt->info.inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_EMODE_NOTHING; + + /* Allow all packets untagged/tagged */ + ctxt->info.inner_vlan_flags |= ICE_AQ_VSI_INNER_VLAN_TX_MODE_ALL; + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %s\n", + ena, err, ice_aq_str(hw->adminq.sq_last_status)); + goto out; + } + + vsi->info.inner_vlan_flags = ctxt->info.inner_vlan_flags; +out: + kfree(ctxt); + return err; +} + +int ice_vsi_ena_inner_stripping(struct ice_vsi *vsi, const u16 tpid) +{ + if (tpid != ETH_P_8021Q) { + print_invalid_tpid(vsi, tpid); + return -EINVAL; + } + + return ice_vsi_manage_vlan_stripping(vsi, true); +} + +int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi) +{ + return ice_vsi_manage_vlan_stripping(vsi, false); +} + +int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, const u16 tpid) +{ + if (tpid != ETH_P_8021Q) { + print_invalid_tpid(vsi, tpid); + return -EINVAL; + } + + return ice_vsi_manage_vlan_insertion(vsi); +} + +int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi) +{ + return ice_vsi_manage_vlan_insertion(vsi); +} + +/** + * __ice_vsi_set_inner_port_vlan - set port VLAN VSI context settings to enable a port VLAN + * @vsi: the VSI to update + * @pvid_info: VLAN ID and QoS used to set the PVID VSI context field + */ +static int __ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, u16 pvid_info) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_aqc_vsi_props *info; + struct ice_vsi_ctx *ctxt; + int ret; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + info = &ctxt->info; + info->inner_vlan_flags = ICE_AQ_VSI_INNER_VLAN_TX_MODE_ACCEPTUNTAGGED | + ICE_AQ_VSI_INNER_VLAN_INSERT_PVID | + ICE_AQ_VSI_INNER_VLAN_EMODE_STR; + info->sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + + info->port_based_inner_vlan = cpu_to_le16(pvid_info); + info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) { + dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); + goto out; + } + + vsi->info.inner_vlan_flags = info->inner_vlan_flags; + vsi->info.sw_flags2 = info->sw_flags2; + vsi->info.port_based_inner_vlan = info->port_based_inner_vlan; +out: + kfree(ctxt); + return ret; +} + +int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + u16 port_vlan_info; + + if (vlan->tpid != ETH_P_8021Q) + return -EINVAL; + + if (vlan->prio > 7) + return -EINVAL; + + port_vlan_info = vlan->vid | (vlan->prio << VLAN_PRIO_SHIFT); + + return __ice_vsi_set_inner_port_vlan(vsi, port_vlan_info); +} + +/** + * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI + * @vsi: VSI to enable or disable VLAN pruning on + * @ena: set to true to enable VLAN pruning and false to disable it + * + * returns 0 if VSI is updated, negative otherwise + */ +static int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) +{ + struct ice_vsi_ctx *ctxt; + struct ice_pf *pf; + int status; + + if (!vsi) + return -EINVAL; + + /* Don't enable VLAN pruning if the netdev is currently in promiscuous + * mode. VLAN pruning will be enabled when the interface exits + * promiscuous mode if any VLAN filters are active. + */ + if (vsi->netdev && vsi->netdev->flags & IFF_PROMISC && ena) + return 0; + + pf = vsi->back; + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + if (ena) + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + else + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + + status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL); + if (status) { + netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %s\n", + ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status, + ice_aq_str(pf->hw.adminq.sq_last_status)); + goto err_out; + } + + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + + kfree(ctxt); + return 0; + +err_out: + kfree(ctxt); + return status; +} + +int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_pruning(vsi, true); +} + +int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_pruning(vsi, false); +} + +static int ice_cfg_vlan_antispoof(struct ice_vsi *vsi, bool enable) +{ + struct ice_vsi_ctx *ctx; + int err; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->info.sec_flags = vsi->info.sec_flags; + ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + + if (enable) + ctx->info.sec_flags |= ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; + else + ctx->info.sec_flags &= ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); + + err = ice_update_vsi(&vsi->back->hw, vsi->idx, ctx, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "Failed to configure Tx VLAN anti-spoof %s for VSI %d, error %d\n", + enable ? "ON" : "OFF", vsi->vsi_num, err); + else + vsi->info.sec_flags = ctx->info.sec_flags; + + kfree(ctx); + + return err; +} + +int ice_vsi_ena_tx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_antispoof(vsi, true); +} + +int ice_vsi_dis_tx_vlan_filtering(struct ice_vsi *vsi) +{ + return ice_cfg_vlan_antispoof(vsi, false); +} + +/** + * tpid_to_vsi_outer_vlan_type - convert from TPID to VSI context based tag_type + * @tpid: tpid used to translate into VSI context based tag_type + * @tag_type: output variable to hold the VSI context based tag type + */ +static int tpid_to_vsi_outer_vlan_type(u16 tpid, u8 *tag_type) +{ + switch (tpid) { + case ETH_P_8021Q: + *tag_type = ICE_AQ_VSI_OUTER_TAG_VLAN_8100; + break; + case ETH_P_8021AD: + *tag_type = ICE_AQ_VSI_OUTER_TAG_STAG; + break; + case ETH_P_QINQ1: + *tag_type = ICE_AQ_VSI_OUTER_TAG_VLAN_9100; + break; + default: + *tag_type = 0; + return -EINVAL; + } + + return 0; +} + +/** + * ice_vsi_ena_outer_stripping - enable outer VLAN stripping + * @vsi: VSI to configure + * @tpid: TPID to enable outer VLAN stripping for + * + * Enable outer VLAN stripping via VSI context. This function should only be + * used if DVM is supported. Also, this function should never be called directly + * as it should be part of ice_vsi_vlan_ops if it's needed. + * + * Since the VSI context only supports a single TPID for insertion and + * stripping, setting the TPID for stripping will affect the TPID for insertion. + * Callers need to be aware of this limitation. + * + * Only modify outer VLAN stripping settings and the VLAN TPID. Outer VLAN + * insertion settings are unmodified. + * + * This enables hardware to strip a VLAN tag with the specified TPID to be + * stripped from the packet and placed in the receive descriptor. + */ +int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + u8 tag_type; + int err; + + /* do not allow modifying VLAN stripping when a port VLAN is configured + * on this VSI + */ + if (vsi->info.port_based_outer_vlan) + return 0; + + if (tpid_to_vsi_outer_vlan_type(tpid, &tag_type)) + return -EINVAL; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN strip settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~(ICE_AQ_VSI_OUTER_VLAN_EMODE_M | ICE_AQ_VSI_OUTER_TAG_TYPE_M); + ctxt->info.outer_vlan_flags |= + ((ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW_BOTH << + ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | + ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M)); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for enabling outer VLAN stripping failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_dis_outer_stripping - disable outer VLAN stripping + * @vsi: VSI to configure + * + * Disable outer VLAN stripping via VSI context. This function should only be + * used if DVM is supported. Also, this function should never be called directly + * as it should be part of ice_vsi_vlan_ops if it's needed. + * + * Only modify the outer VLAN stripping settings. The VLAN TPID and outer VLAN + * insertion settings are unmodified. + * + * This tells the hardware to not strip any VLAN tagged packets, thus leaving + * them in the packet. This enables software offloaded VLAN stripping and + * disables hardware offloaded VLAN stripping. + */ +int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + if (vsi->info.port_based_outer_vlan) + return 0; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN strip settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~ICE_AQ_VSI_OUTER_VLAN_EMODE_M; + ctxt->info.outer_vlan_flags |= ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING << + ICE_AQ_VSI_OUTER_VLAN_EMODE_S; + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for disabling outer VLAN stripping failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_ena_outer_insertion - enable outer VLAN insertion + * @vsi: VSI to configure + * @tpid: TPID to enable outer VLAN insertion for + * + * Enable outer VLAN insertion via VSI context. This function should only be + * used if DVM is supported. Also, this function should never be called directly + * as it should be part of ice_vsi_vlan_ops if it's needed. + * + * Since the VSI context only supports a single TPID for insertion and + * stripping, setting the TPID for insertion will affect the TPID for stripping. + * Callers need to be aware of this limitation. + * + * Only modify outer VLAN insertion settings and the VLAN TPID. Outer VLAN + * stripping settings are unmodified. + * + * This allows a VLAN tag with the specified TPID to be inserted in the transmit + * descriptor. + */ +int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + u8 tag_type; + int err; + + if (vsi->info.port_based_outer_vlan) + return 0; + + if (tpid_to_vsi_outer_vlan_type(tpid, &tag_type)) + return -EINVAL; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN insertion settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~(ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT | + ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M | + ICE_AQ_VSI_OUTER_TAG_TYPE_M); + ctxt->info.outer_vlan_flags |= + ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M) | + ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for enabling outer VLAN insertion failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_dis_outer_insertion - disable outer VLAN insertion + * @vsi: VSI to configure + * + * Disable outer VLAN insertion via VSI context. This function should only be + * used if DVM is supported. Also, this function should never be called directly + * as it should be part of ice_vsi_vlan_ops if it's needed. + * + * Only modify the outer VLAN insertion settings. The VLAN TPID and outer VLAN + * settings are unmodified. + * + * This tells the hardware to not allow any VLAN tagged packets in the transmit + * descriptor. This enables software offloaded VLAN insertion and disables + * hardware offloaded VLAN insertion. + */ +int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + int err; + + if (vsi->info.port_based_outer_vlan) + return 0; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID); + /* clear current outer VLAN insertion settings */ + ctxt->info.outer_vlan_flags = vsi->info.outer_vlan_flags & + ~(ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT | + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); + ctxt->info.outer_vlan_flags |= + ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | + ((ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ALL << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) & + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_M); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "update VSI for disabling outer VLAN insertion failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + else + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + + kfree(ctxt); + return err; +} + +/** + * __ice_vsi_set_outer_port_vlan - set the outer port VLAN and related settings + * @vsi: VSI to configure + * @vlan_info: packed u16 that contains the VLAN prio and ID + * @tpid: TPID of the port VLAN + * + * Set the port VLAN prio, ID, and TPID. + * + * Enable VLAN pruning so the VSI doesn't receive any traffic that doesn't match + * a VLAN prune rule. The caller should take care to add a VLAN prune rule that + * matches the port VLAN ID and TPID. + * + * Tell hardware to strip outer VLAN tagged packets on receive and don't put + * them in the receive descriptor. VSI(s) in port VLANs should not be aware of + * the port VLAN ID or TPID they are assigned to. + * + * Tell hardware to prevent outer VLAN tag insertion on transmit and only allow + * untagged outer packets from the transmit descriptor. + * + * Also, tell the hardware to insert the port VLAN on transmit. + */ +static int +__ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, u16 vlan_info, u16 tpid) +{ + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx *ctxt; + u8 tag_type; + int err; + + if (tpid_to_vsi_outer_vlan_type(tpid, &tag_type)) + return -EINVAL; + + ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + + ctxt->info.port_based_outer_vlan = cpu_to_le16(vlan_info); + ctxt->info.outer_vlan_flags = + (ICE_AQ_VSI_OUTER_VLAN_EMODE_SHOW << + ICE_AQ_VSI_OUTER_VLAN_EMODE_S) | + ((tag_type << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & + ICE_AQ_VSI_OUTER_TAG_TYPE_M) | + ICE_AQ_VSI_OUTER_VLAN_BLOCK_TX_DESC | + (ICE_AQ_VSI_OUTER_VLAN_TX_MODE_ACCEPTUNTAGGED << + ICE_AQ_VSI_OUTER_VLAN_TX_MODE_S) | + ICE_AQ_VSI_OUTER_VLAN_PORT_BASED_INSERT; + + ctxt->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_OUTER_TAG_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + + err = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (err) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for setting outer port based VLAN failed, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + } else { + vsi->info.port_based_outer_vlan = ctxt->info.port_based_outer_vlan; + vsi->info.outer_vlan_flags = ctxt->info.outer_vlan_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + } + + kfree(ctxt); + return err; +} + +/** + * ice_vsi_set_outer_port_vlan - public version of __ice_vsi_set_outer_port_vlan + * @vsi: VSI to configure + * @vlan: ice_vlan structure used to set the port VLAN + * + * Set the outer port VLAN via VSI context. This function should only be + * used if DVM is supported. Also, this function should never be called directly + * as it should be part of ice_vsi_vlan_ops if it's needed. + * + * This function does not support clearing the port VLAN as there is currently + * no use case for this. + * + * Use the ice_vlan structure passed in to set this VSI in a port VLAN. + */ +int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) +{ + u16 port_vlan_info; + + if (vlan->prio > (VLAN_PRIO_MASK >> VLAN_PRIO_SHIFT)) + return -EINVAL; + + port_vlan_info = vlan->vid | (vlan->prio << VLAN_PRIO_SHIFT); + + return __ice_vsi_set_outer_port_vlan(vsi, port_vlan_info, vlan->tpid); +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h new file mode 100644 index 000000000000..f459909490ec --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VSI_VLAN_LIB_H_ +#define _ICE_VSI_VLAN_LIB_H_ + +#include <linux/types.h> +#include "ice_vlan.h" + +struct ice_vsi; + +int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); +int ice_vsi_del_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); + +int ice_vsi_ena_inner_stripping(struct ice_vsi *vsi, u16 tpid); +int ice_vsi_dis_inner_stripping(struct ice_vsi *vsi); +int ice_vsi_ena_inner_insertion(struct ice_vsi *vsi, u16 tpid); +int ice_vsi_dis_inner_insertion(struct ice_vsi *vsi); +int ice_vsi_set_inner_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); + +int ice_vsi_ena_rx_vlan_filtering(struct ice_vsi *vsi); +int ice_vsi_dis_rx_vlan_filtering(struct ice_vsi *vsi); +int ice_vsi_ena_tx_vlan_filtering(struct ice_vsi *vsi); +int ice_vsi_dis_tx_vlan_filtering(struct ice_vsi *vsi); + +int ice_vsi_ena_outer_stripping(struct ice_vsi *vsi, u16 tpid); +int ice_vsi_dis_outer_stripping(struct ice_vsi *vsi); +int ice_vsi_ena_outer_insertion(struct ice_vsi *vsi, u16 tpid); +int ice_vsi_dis_outer_insertion(struct ice_vsi *vsi); +int ice_vsi_set_outer_port_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan); + +#endif /* _ICE_VSI_VLAN_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c new file mode 100644 index 000000000000..4a6c850d83ac --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice_pf_vsi_vlan_ops.h" +#include "ice_vf_vsi_vlan_ops.h" +#include "ice_lib.h" +#include "ice.h" + +static int +op_unsupported_vlan_arg(struct ice_vsi * __always_unused vsi, + struct ice_vlan * __always_unused vlan) +{ + return -EOPNOTSUPP; +} + +static int +op_unsupported_tpid_arg(struct ice_vsi *__always_unused vsi, + u16 __always_unused tpid) +{ + return -EOPNOTSUPP; +} + +static int op_unsupported(struct ice_vsi *__always_unused vsi) +{ + return -EOPNOTSUPP; +} + +/* If any new ops are added to the VSI VLAN ops interface then an unsupported + * implementation should be set here. + */ +static struct ice_vsi_vlan_ops ops_unsupported = { + .add_vlan = op_unsupported_vlan_arg, + .del_vlan = op_unsupported_vlan_arg, + .ena_stripping = op_unsupported_tpid_arg, + .dis_stripping = op_unsupported, + .ena_insertion = op_unsupported_tpid_arg, + .dis_insertion = op_unsupported, + .ena_rx_filtering = op_unsupported, + .dis_rx_filtering = op_unsupported, + .ena_tx_filtering = op_unsupported, + .dis_tx_filtering = op_unsupported, + .set_port_vlan = op_unsupported_vlan_arg, +}; + +/** + * ice_vsi_init_unsupported_vlan_ops - init all VSI VLAN ops to unsupported + * @vsi: VSI to initialize VSI VLAN ops to unsupported for + * + * By default all inner and outer VSI VLAN ops return -EOPNOTSUPP. This was done + * as oppsed to leaving the ops null to prevent unexpected crashes. Instead if + * an unsupported VSI VLAN op is called it will just return -EOPNOTSUPP. + * + */ +static void ice_vsi_init_unsupported_vlan_ops(struct ice_vsi *vsi) +{ + vsi->outer_vlan_ops = ops_unsupported; + vsi->inner_vlan_ops = ops_unsupported; +} + +/** + * ice_vsi_init_vlan_ops - initialize type specific VSI VLAN ops + * @vsi: VSI to initialize ops for + * + * If any VSI types are added and/or require different ops than the PF or VF VSI + * then they will have to add a case here to handle that. Also, VSI type + * specific files should be added in the same manner that was done for PF VSI. + */ +void ice_vsi_init_vlan_ops(struct ice_vsi *vsi) +{ + /* Initialize all VSI types to have unsupported VSI VLAN ops */ + ice_vsi_init_unsupported_vlan_ops(vsi); + + switch (vsi->type) { + case ICE_VSI_PF: + case ICE_VSI_SWITCHDEV_CTRL: + ice_pf_vsi_init_vlan_ops(vsi); + break; + case ICE_VSI_VF: + ice_vf_vsi_init_vlan_ops(vsi); + break; + default: + dev_dbg(ice_pf_to_dev(vsi->back), "%s does not support VLAN operations\n", + ice_vsi_type_str(vsi->type)); + break; + } +} + +/** + * ice_get_compat_vsi_vlan_ops - Get VSI VLAN ops based on VLAN mode + * @vsi: VSI used to get the VSI VLAN ops + * + * This function is meant to be used when the caller doesn't know which VLAN ops + * to use (i.e. inner or outer). This allows backward compatibility for VLANs + * since most of the Outer VSI VLAN functins are not supported when + * the device is configured in Single VLAN Mode (SVM). + */ +struct ice_vsi_vlan_ops *ice_get_compat_vsi_vlan_ops(struct ice_vsi *vsi) +{ + if (ice_is_dvm_ena(&vsi->back->hw)) + return &vsi->outer_vlan_ops; + else + return &vsi->inner_vlan_ops; +} diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h new file mode 100644 index 000000000000..5b47568f6256 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_VSI_VLAN_OPS_H_ +#define _ICE_VSI_VLAN_OPS_H_ + +#include "ice_type.h" +#include "ice_vsi_vlan_lib.h" + +struct ice_vsi; + +struct ice_vsi_vlan_ops { + int (*add_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*del_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); + int (*ena_stripping)(struct ice_vsi *vsi, const u16 tpid); + int (*dis_stripping)(struct ice_vsi *vsi); + int (*ena_insertion)(struct ice_vsi *vsi, const u16 tpid); + int (*dis_insertion)(struct ice_vsi *vsi); + int (*ena_rx_filtering)(struct ice_vsi *vsi); + int (*dis_rx_filtering)(struct ice_vsi *vsi); + int (*ena_tx_filtering)(struct ice_vsi *vsi); + int (*dis_tx_filtering)(struct ice_vsi *vsi); + int (*set_port_vlan)(struct ice_vsi *vsi, struct ice_vlan *vlan); +}; + +void ice_vsi_init_vlan_ops(struct ice_vsi *vsi); +struct ice_vsi_vlan_ops *ice_get_compat_vsi_vlan_ops(struct ice_vsi *vsi); + +#endif /* _ICE_VSI_VLAN_OPS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 2388837d6d6c..88853a6ed931 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -327,6 +327,13 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) bool if_running, pool_present = !!pool; int ret = 0, pool_failure = 0; + if (!is_power_of_2(vsi->rx_rings[qid]->count) || + !is_power_of_2(vsi->tx_rings[qid]->count)) { + netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n"); + pool_failure = -EINVAL; + goto failure; + } + if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi); if (if_running) { @@ -349,6 +356,7 @@ xsk_pool_if_up: netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret); } +failure: if (pool_failure) { netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n", pool_present ? "en" : "dis", pool_failure); @@ -359,33 +367,28 @@ xsk_pool_if_up: } /** - * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers - * @rx_ring: Rx ring + * ice_fill_rx_descs - pick buffers from XSK buffer pool and use it + * @pool: XSK Buffer pool to pull the buffers from + * @xdp: SW ring of xdp_buff that will hold the buffers + * @rx_desc: Pointer to Rx descriptors that will be filled * @count: The number of buffers to allocate * * This function allocates a number of Rx buffers from the fill ring * or the internal recycle mechanism and places them on the Rx ring. * - * Returns true if all allocations were successful, false if any fail. + * Note that ring wrap should be handled by caller of this function. + * + * Returns the amount of allocated Rx descriptors */ -bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, + union ice_32b_rx_flex_desc *rx_desc, u16 count) { - union ice_32b_rx_flex_desc *rx_desc; - u16 ntu = rx_ring->next_to_use; - struct xdp_buff **xdp; - u32 nb_buffs, i; dma_addr_t dma; + u16 buffs; + int i; - rx_desc = ICE_RX_DESC(rx_ring, ntu); - xdp = ice_xdp_buf(rx_ring, ntu); - - nb_buffs = min_t(u16, count, rx_ring->count - ntu); - nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs); - if (!nb_buffs) - return false; - - i = nb_buffs; - while (i--) { + buffs = xsk_buff_alloc_batch(pool, xdp, count); + for (i = 0; i < buffs; i++) { dma = xsk_buff_xdp_get_dma(*xdp); rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; @@ -394,13 +397,77 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) xdp++; } + return buffs; +} + +/** + * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * Place the @count of descriptors onto Rx ring. Handle the ring wrap + * for case where space from next_to_use up to the end of ring is less + * than @count. Finally do a tail bump. + * + * Returns true if all allocations were successful, false if any fail. + */ +static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +{ + union ice_32b_rx_flex_desc *rx_desc; + u32 nb_buffs_extra = 0, nb_buffs; + u16 ntu = rx_ring->next_to_use; + u16 total_count = count; + struct xdp_buff **xdp; + + rx_desc = ICE_RX_DESC(rx_ring, ntu); + xdp = ice_xdp_buf(rx_ring, ntu); + + if (ntu + count >= rx_ring->count) { + nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, + rx_desc, + rx_ring->count - ntu); + rx_desc = ICE_RX_DESC(rx_ring, 0); + xdp = ice_xdp_buf(rx_ring, 0); + ntu = 0; + count -= nb_buffs_extra; + ice_release_rx_desc(rx_ring, 0); + } + + nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count); + ntu += nb_buffs; if (ntu == rx_ring->count) ntu = 0; - ice_release_rx_desc(rx_ring, ntu); + if (rx_ring->next_to_use != ntu) + ice_release_rx_desc(rx_ring, ntu); + + return total_count == (nb_buffs_extra + nb_buffs); +} + +/** + * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * Wrapper for internal allocation routine; figure out how many tail + * bumps should take place based on the given threshold + * + * Returns true if all calls to internal alloc routine succeeded + */ +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) +{ + u16 rx_thresh = ICE_RING_QUARTER(rx_ring); + u16 batched, leftover, i, tail_bumps; + + batched = ALIGN_DOWN(count, rx_thresh); + tail_bumps = batched / rx_thresh; + leftover = count & (rx_thresh - 1); - return count == nb_buffs; + for (i = 0; i < tail_bumps; i++) + if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh)) + return false; + return __ice_alloc_rx_bufs_zc(rx_ring, leftover); } /** @@ -428,20 +495,24 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring) static struct sk_buff * ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { - unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start; + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; struct sk_buff *skb; - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard, + net_prefetch(xdp->data_meta); + + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } xsk_buff_free(xdp); return skb; @@ -528,7 +599,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); - if (!ice_test_staterr(rx_desc, stat_err_bits)) + if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) break; /* This memory barrier is needed to keep us from reading @@ -583,9 +654,7 @@ construct_skb: total_rx_bytes += skb->len; total_rx_packets++; - stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S); - if (ice_test_staterr(rx_desc, stat_err_bits)) - vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1); + vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & ICE_RX_FLEX_DESC_PTYPE_M; @@ -612,134 +681,221 @@ construct_skb: } /** - * ice_xmit_zc - Completes AF_XDP entries, and cleans XDP entries + * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer * @xdp_ring: XDP Tx ring - * @budget: max number of frames to xmit + * @tx_buf: Tx buffer to clean + */ +static void +ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) +{ + xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf); + xdp_ring->xdp_tx_active--; + dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); +} + +/** + * ice_clean_xdp_irq_zc - Reclaim resources after transmit completes on XDP ring + * @xdp_ring: XDP ring to clean + * @napi_budget: amount of descriptors that NAPI allows us to clean * - * Returns true if cleanup/transmission is done. + * Returns count of cleaned descriptors */ -static bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, int budget) +static u16 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring, int napi_budget) { - struct ice_tx_desc *tx_desc = NULL; - bool work_done = true; - struct xdp_desc desc; - dma_addr_t dma; + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); + int budget = napi_budget / tx_thresh; + u16 next_dd = xdp_ring->next_dd; + u16 ntc, cleared_dds = 0; - while (likely(budget-- > 0)) { + do { + struct ice_tx_desc *next_dd_desc; + u16 desc_cnt = xdp_ring->count; struct ice_tx_buf *tx_buf; + u32 xsk_frames; + u16 i; - if (unlikely(!ICE_DESC_UNUSED(xdp_ring))) { - xdp_ring->tx_stats.tx_busy++; - work_done = false; + next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd); + if (!(next_dd_desc->cmd_type_offset_bsz & + cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) break; - } - tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use]; - - if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc)) - break; - - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, - desc.len); - - tx_buf->bytecount = desc.len; + cleared_dds++; + xsk_frames = 0; + if (likely(!xdp_ring->xdp_tx_active)) { + xsk_frames = tx_thresh; + goto skip; + } - tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use); - tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = - ice_build_ctob(ICE_TXD_LAST_DESC_CMD, 0, desc.len, 0); + ntc = xdp_ring->next_to_clean; - xdp_ring->next_to_use++; - if (xdp_ring->next_to_use == xdp_ring->count) - xdp_ring->next_to_use = 0; - } + for (i = 0; i < tx_thresh; i++) { + tx_buf = &xdp_ring->tx_buf[ntc]; - if (tx_desc) { - ice_xdp_ring_update_tail(xdp_ring); - xsk_tx_release(xdp_ring->xsk_pool); - } + if (tx_buf->raw_buf) { + ice_clean_xdp_tx_buf(xdp_ring, tx_buf); + tx_buf->raw_buf = NULL; + } else { + xsk_frames++; + } - return budget > 0 && work_done; + ntc++; + if (ntc >= xdp_ring->count) + ntc = 0; + } +skip: + xdp_ring->next_to_clean += tx_thresh; + if (xdp_ring->next_to_clean >= desc_cnt) + xdp_ring->next_to_clean -= desc_cnt; + if (xsk_frames) + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + next_dd_desc->cmd_type_offset_bsz = 0; + next_dd = next_dd + tx_thresh; + if (next_dd >= desc_cnt) + next_dd = tx_thresh - 1; + } while (budget--); + + xdp_ring->next_dd = next_dd; + + return cleared_dds * tx_thresh; } /** - * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer - * @xdp_ring: XDP Tx ring - * @tx_buf: Tx buffer to clean + * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor + * @xdp_ring: XDP ring to produce the HW Tx descriptor on + * @desc: AF_XDP descriptor to pull the DMA address and length from + * @total_bytes: bytes accumulator that will be used for stats update */ -static void -ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) +static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc, + unsigned int *total_bytes) { - xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf); - dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), - dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); - dma_unmap_len_set(tx_buf, len, 0); + struct ice_tx_desc *tx_desc; + dma_addr_t dma; + + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len); + + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++); + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + 0, desc->len, 0); + + *total_bytes += desc->len; } /** - * ice_clean_tx_irq_zc - Completes AF_XDP entries, and cleans XDP entries - * @xdp_ring: XDP Tx ring - * @budget: NAPI budget - * - * Returns true if cleanup/tranmission is done. + * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from + * @total_bytes: bytes accumulator that will be used for stats update */ -bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget) +static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, + unsigned int *total_bytes) { - int total_packets = 0, total_bytes = 0; - s16 ntc = xdp_ring->next_to_clean; + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); + u16 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; - struct ice_tx_buf *tx_buf; - u32 xsk_frames = 0; - bool xmit_done; + u32 i; - tx_desc = ICE_TX_DESC(xdp_ring, ntc); - tx_buf = &xdp_ring->tx_buf[ntc]; - ntc -= xdp_ring->count; + loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + dma_addr_t dma; - do { - if (!(tx_desc->cmd_type_offset_bsz & - cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) - break; + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len); - total_bytes += tx_buf->bytecount; - total_packets++; + tx_desc = ICE_TX_DESC(xdp_ring, ntu++); + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + 0, descs[i].len, 0); - if (tx_buf->raw_buf) { - ice_clean_xdp_tx_buf(xdp_ring, tx_buf); - tx_buf->raw_buf = NULL; - } else { - xsk_frames++; - } + *total_bytes += descs[i].len; + } - tx_desc->cmd_type_offset_bsz = 0; - tx_buf++; - tx_desc++; - ntc++; + xdp_ring->next_to_use = ntu; - if (unlikely(!ntc)) { - ntc -= xdp_ring->count; - tx_buf = xdp_ring->tx_buf; - tx_desc = ICE_TX_DESC(xdp_ring, 0); - } + if (xdp_ring->next_to_use > xdp_ring->next_rs) { + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + xdp_ring->next_rs += tx_thresh; + } +} - prefetch(tx_desc); +/** + * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from + * @nb_pkts: count of packets to be send + * @total_bytes: bytes accumulator that will be used for stats update + */ +static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs, + u32 nb_pkts, unsigned int *total_bytes) +{ + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); + u32 batched, leftover, i; + + batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH); + leftover = nb_pkts & (PKTS_PER_BATCH - 1); + for (i = 0; i < batched; i += PKTS_PER_BATCH) + ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes); + for (; i < batched + leftover; i++) + ice_xmit_pkt(xdp_ring, &descs[i], total_bytes); + + if (xdp_ring->next_to_use > xdp_ring->next_rs) { + struct ice_tx_desc *tx_desc; + + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + xdp_ring->next_rs += tx_thresh; + } +} - } while (likely(--budget)); +/** + * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * @budget: number of free descriptors on HW Tx ring that can be used + * @napi_budget: amount of descriptors that NAPI allows us to clean + * + * Returns true if there is no more work that needs to be done, false otherwise + */ +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget) +{ + struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs; + u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); + u32 nb_pkts, nb_processed = 0; + unsigned int total_bytes = 0; + + if (budget < tx_thresh) + budget += ice_clean_xdp_irq_zc(xdp_ring, napi_budget); + + nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget); + if (!nb_pkts) + return true; + + if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { + struct ice_tx_desc *tx_desc; + + nb_processed = xdp_ring->count - xdp_ring->next_to_use; + ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes); + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + xdp_ring->next_rs = tx_thresh - 1; + xdp_ring->next_to_use = 0; + } - ntc += xdp_ring->count; - xdp_ring->next_to_clean = ntc; + ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed, + &total_bytes); - if (xsk_frames) - xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); + ice_xdp_ring_update_tail(xdp_ring); + ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes); if (xsk_uses_need_wakeup(xdp_ring->xsk_pool)) xsk_set_tx_need_wakeup(xdp_ring->xsk_pool); - ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes); - xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK); - - return budget > 0 && xmit_done; + return nb_pkts < budget; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 4c7bd8e9dfc4..0cbb5793b5b8 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -6,19 +6,37 @@ #include "ice_txrx.h" #include "ice.h" +#define PKTS_PER_BATCH 8 + +#ifdef __clang__ +#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for +#elif __GNUC__ >= 4 +#define loop_unrolled_for _Pragma("GCC unroll 8") for +#else +#define loop_unrolled_for for +#endif + struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget); -bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); +bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget); #else +static inline bool +ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring, + u32 __always_unused budget, + int __always_unused napi_budget) +{ + return false; +} + static inline int ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, struct xsk_buff_pool __always_unused *pool, @@ -35,13 +53,6 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, } static inline bool -ice_clean_tx_irq_zc(struct ice_tx_ring __always_unused *xdp_ring, - int __always_unused budget) -{ - return false; -} - -static inline bool ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring, u16 __always_unused count) { diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 51a2dcaf553d..2a5782063f4c 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -965,10 +965,6 @@ static int igb_set_ringparam(struct net_device *netdev, memcpy(&temp_ring[i], adapter->rx_ring[i], sizeof(struct igb_ring)); - /* Clear copied XDP RX-queue info */ - memset(&temp_ring[i].xdp_rxq, 0, - sizeof(temp_ring[i].xdp_rxq)); - temp_ring[i].count = new_rx_count; err = igb_setup_rx_resources(&temp_ring[i]); if (err) { diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 38ba92022cd4..34b33b21e0dc 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3164,8 +3164,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) s32 ret_val; static int global_quad_port_a; /* global quad port a indication */ const struct e1000_info *ei = igb_info_tbl[ent->driver_data]; - int err, pci_using_dac; u8 part_str[E1000_PBANUM_LENGTH]; + int err; /* Catch broken hardware that put the wrong VF device ID in * the PCIe SR-IOV capability. @@ -3180,17 +3180,11 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, igb_driver_name); @@ -3306,8 +3300,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->mac.type >= e1000_i350) netdev->hw_features |= NETIF_F_NTUPLE; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_HW_CSUM; @@ -4352,7 +4345,18 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) { struct igb_adapter *adapter = netdev_priv(rx_ring->netdev); struct device *dev = rx_ring->dev; - int size; + int size, res; + + /* XDP RX-queue info */ + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, + rx_ring->queue_index, 0); + if (res < 0) { + dev_err(dev, "Failed to register xdp_rxq index %u\n", + rx_ring->queue_index); + return res; + } size = sizeof(struct igb_rx_buffer) * rx_ring->count; @@ -4375,14 +4379,10 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) rx_ring->xdp_prog = adapter->xdp_prog; - /* XDP RX-queue info */ - if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, 0) < 0) - goto err; - return 0; err: + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index b78407289741..43ced78c3a2e 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2684,25 +2684,18 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct igbvf_adapter *adapter; struct e1000_hw *hw; const struct igbvf_info *ei = igbvf_info_tbl[ent->driver_data]; - static int cards_found; - int err, pci_using_dac; + int err; err = pci_enable_device_mem(pdev); if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_regions(pdev, igbvf_driver_name); @@ -2783,10 +2776,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features |= NETIF_F_GSO_PARTIAL | IGBVF_GSO_PARTIAL_FEATURES; - netdev->features = netdev->hw_features; - - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features = netdev->hw_features | NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_HW_CSUM; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 2f17f36e94fd..74b2c590ed5d 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -505,6 +505,9 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) u8 index = rx_ring->queue_index; int size, desc_len, res; + /* XDP RX-queue info */ + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, ndev, index, rx_ring->q_vector->napi.napi_id); if (res < 0) { @@ -2446,19 +2449,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, struct xdp_buff *xdp) { + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; - unsigned int totalsize = metasize + datasize; struct sk_buff *skb; - skb = __napi_alloc_skb(&ring->q_vector->napi, - xdp->data_end - xdp->data_hard_start, + net_prefetch(xdp->data_meta); + + skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); - memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize); + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + if (metasize) { skb_metadata_set(skb, metasize); __skb_pull(skb, metasize); @@ -6251,23 +6255,17 @@ static int igc_probe(struct pci_dev *pdev, struct net_device *netdev; struct igc_hw *hw; const struct igc_info *ei = igc_info_tbl[ent->driver_data]; - int err, pci_using_dac; + int err; err = pci_enable_device_mem(pdev); if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, igc_driver_name); @@ -6367,8 +6365,7 @@ static int igc_probe(struct pci_dev *pdev, netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; netdev->hw_features |= netdev->features; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_HW_CSUM; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 99d481904ce6..affdefcca7e3 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -361,7 +361,6 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev = NULL; struct ixgb_adapter *adapter; static int cards_found = 0; - int pci_using_dac; u8 addr[ETH_ALEN]; int i; int err; @@ -370,16 +369,10 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - pr_err("No usable DMA configuration, aborting\n"); - goto err_dma_mask; - } + if (err) { + pr_err("No usable DMA configuration, aborting\n"); + goto err_dma_mask; } err = pci_request_regions(pdev, ixgb_driver_name); @@ -444,10 +437,8 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_RXCSUM; - if (pci_using_dac) { - netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= NETIF_F_HIGHDMA; - } + netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= NETIF_F_HIGHDMA; /* MTU range: 68 - 16114 */ netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 89b467006291..2c8a4a06f56a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10632,9 +10632,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ixgbe_adapter *adapter = NULL; struct ixgbe_hw *hw; const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data]; - int i, err, pci_using_dac, expected_gts; unsigned int indices = MAX_TX_QUEUES; u8 part_str[IXGBE_PBANUM_LENGTH]; + int i, err, expected_gts; bool disable_dev = false; #ifdef IXGBE_FCOE u16 device_caps; @@ -10654,16 +10654,11 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } - pci_using_dac = 0; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, ixgbe_driver_name); @@ -10861,8 +10856,7 @@ skip_sriov: netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->hw_enc_features |= netdev->vlan_features; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index b3fd8e5cd85b..ee28929b9c5f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -207,26 +207,28 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) } static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi) + const struct xdp_buff *xdp) { - unsigned int metasize = bi->xdp->data - bi->xdp->data_meta; - unsigned int datasize = bi->xdp->data_end - bi->xdp->data; + unsigned int totalsize = xdp->data_end - xdp->data_meta; + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; + net_prefetch(xdp->data_meta); + /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - bi->xdp->data_end - bi->xdp->data_hard_start, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } - xsk_buff_free(bi->xdp); - bi->xdp = NULL; return skb; } @@ -317,12 +319,15 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } /* XDP_PASS path */ - skb = ixgbe_construct_skb_zc(rx_ring, bi); + skb = ixgbe_construct_skb_zc(rx_ring, bi->xdp); if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; break; } + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + cleaned_count++; ixgbe_inc_ntc(rx_ring); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 0f293acd17e8..17fbc450da61 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4512,22 +4512,17 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ixgbevf_adapter *adapter = NULL; struct ixgbe_hw *hw = NULL; const struct ixgbevf_info *ii = ixgbevf_info_tbl[ent->driver_data]; - int err, pci_using_dac; bool disable_dev = false; + int err; err = pci_enable_device(pdev); if (err) return err; - if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "No usable DMA configuration, aborting\n"); - goto err_dma; - } - pci_using_dac = 0; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_regions(pdev, ixgbevf_driver_name); @@ -4607,10 +4602,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features |= NETIF_F_GSO_PARTIAL | IXGBEVF_GSO_PARTIAL_FEATURES; - netdev->features = netdev->hw_features; - - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features = netdev->hw_features | NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_SG | diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 83c8908f0cc7..f1335a1ed695 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1884,8 +1884,8 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp, bytes_compl += buf->skb->len; pkts_compl++; dev_kfree_skb_any(buf->skb); - } else if (buf->type == MVNETA_TYPE_XDP_TX || - buf->type == MVNETA_TYPE_XDP_NDO) { + } else if ((buf->type == MVNETA_TYPE_XDP_TX || + buf->type == MVNETA_TYPE_XDP_NDO) && buf->xdpf) { if (napi && buf->type == MVNETA_TYPE_XDP_TX) xdp_return_frame_rx_napi(buf->xdpf); else @@ -2060,61 +2060,104 @@ int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq) static void mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, - struct xdp_buff *xdp, struct skb_shared_info *sinfo, - int sync_len) + struct xdp_buff *xdp, int sync_len) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i; + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + for (i = 0; i < sinfo->nr_frags; i++) page_pool_put_full_page(rxq->page_pool, skb_frag_page(&sinfo->frags[i]), true); + +out: page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), sync_len, true); } static int mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq, - struct xdp_frame *xdpf, bool dma_map) + struct xdp_frame *xdpf, int *nxmit_byte, bool dma_map) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); + struct device *dev = pp->dev->dev.parent; struct mvneta_tx_desc *tx_desc; - struct mvneta_tx_buf *buf; - dma_addr_t dma_addr; + int i, num_frames = 1; + struct page *page; - if (txq->count >= txq->tx_stop_threshold) + if (unlikely(xdp_frame_has_frags(xdpf))) + num_frames += sinfo->nr_frags; + + if (txq->count + num_frames >= txq->size) return MVNETA_XDP_DROPPED; - tx_desc = mvneta_txq_next_desc_get(txq); + for (i = 0; i < num_frames; i++) { + struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index]; + skb_frag_t *frag = NULL; + int len = xdpf->len; + dma_addr_t dma_addr; - buf = &txq->buf[txq->txq_put_index]; - if (dma_map) { - /* ndo_xdp_xmit */ - dma_addr = dma_map_single(pp->dev->dev.parent, xdpf->data, - xdpf->len, DMA_TO_DEVICE); - if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) { - mvneta_txq_desc_put(txq); - return MVNETA_XDP_DROPPED; + if (unlikely(i)) { /* paged area */ + frag = &sinfo->frags[i - 1]; + len = skb_frag_size(frag); } - buf->type = MVNETA_TYPE_XDP_NDO; - } else { - struct page *page = virt_to_page(xdpf->data); - dma_addr = page_pool_get_dma_addr(page) + - sizeof(*xdpf) + xdpf->headroom; - dma_sync_single_for_device(pp->dev->dev.parent, dma_addr, - xdpf->len, DMA_BIDIRECTIONAL); - buf->type = MVNETA_TYPE_XDP_TX; - } - buf->xdpf = xdpf; + tx_desc = mvneta_txq_next_desc_get(txq); + if (dma_map) { + /* ndo_xdp_xmit */ + void *data; + + data = unlikely(frag) ? skb_frag_address(frag) + : xdpf->data; + dma_addr = dma_map_single(dev, data, len, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + mvneta_txq_desc_put(txq); + goto unmap; + } + + buf->type = MVNETA_TYPE_XDP_NDO; + } else { + page = unlikely(frag) ? skb_frag_page(frag) + : virt_to_page(xdpf->data); + dma_addr = page_pool_get_dma_addr(page); + if (unlikely(frag)) + dma_addr += skb_frag_off(frag); + else + dma_addr += sizeof(*xdpf) + xdpf->headroom; + dma_sync_single_for_device(dev, dma_addr, len, + DMA_BIDIRECTIONAL); + buf->type = MVNETA_TYPE_XDP_TX; + } + buf->xdpf = unlikely(i) ? NULL : xdpf; - tx_desc->command = MVNETA_TXD_FLZ_DESC; - tx_desc->buf_phys_addr = dma_addr; - tx_desc->data_size = xdpf->len; + tx_desc->command = unlikely(i) ? 0 : MVNETA_TXD_F_DESC; + tx_desc->buf_phys_addr = dma_addr; + tx_desc->data_size = len; + *nxmit_byte += len; - mvneta_txq_inc_put(txq); - txq->pending++; - txq->count++; + mvneta_txq_inc_put(txq); + } + /*last descriptor */ + tx_desc->command |= MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD; + + txq->pending += num_frames; + txq->count += num_frames; return MVNETA_XDP_TX; + +unmap: + for (i--; i >= 0; i--) { + mvneta_txq_desc_put(txq); + tx_desc = txq->descs + txq->next_desc_to_proc; + dma_unmap_single(dev, tx_desc->buf_phys_addr, + tx_desc->data_size, + DMA_TO_DEVICE); + } + + return MVNETA_XDP_DROPPED; } static int @@ -2123,8 +2166,8 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp) struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); struct mvneta_tx_queue *txq; struct netdev_queue *nq; + int cpu, nxmit_byte = 0; struct xdp_frame *xdpf; - int cpu; u32 ret; xdpf = xdp_convert_buff_to_frame(xdp); @@ -2136,10 +2179,10 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp) nq = netdev_get_tx_queue(pp->dev, txq->id); __netif_tx_lock(nq, cpu); - ret = mvneta_xdp_submit_frame(pp, txq, xdpf, false); + ret = mvneta_xdp_submit_frame(pp, txq, xdpf, &nxmit_byte, false); if (ret == MVNETA_XDP_TX) { u64_stats_update_begin(&stats->syncp); - stats->es.ps.tx_bytes += xdpf->len; + stats->es.ps.tx_bytes += nxmit_byte; stats->es.ps.tx_packets++; stats->es.ps.xdp_tx++; u64_stats_update_end(&stats->syncp); @@ -2178,11 +2221,11 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame, __netif_tx_lock(nq, cpu); for (i = 0; i < num_frame; i++) { - ret = mvneta_xdp_submit_frame(pp, txq, frames[i], true); + ret = mvneta_xdp_submit_frame(pp, txq, frames[i], &nxmit_byte, + true); if (ret != MVNETA_XDP_TX) break; - nxmit_byte += frames[i]->len; nxmit++; } @@ -2205,7 +2248,6 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct bpf_prog *prog, struct xdp_buff *xdp, u32 frame_sz, struct mvneta_stats *stats) { - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); unsigned int len, data_len, sync; u32 ret, act; @@ -2226,7 +2268,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, err = xdp_do_redirect(pp->dev, xdp, prog); if (unlikely(err)) { - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, sync); ret = MVNETA_XDP_DROPPED; } else { ret = MVNETA_XDP_REDIR; @@ -2237,7 +2279,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, case XDP_TX: ret = mvneta_xdp_xmit_back(pp, xdp); if (ret != MVNETA_XDP_TX) - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, sync); break; default: bpf_warn_invalid_xdp_action(pp->dev, prog, act); @@ -2246,7 +2288,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, trace_xdp_exception(pp->dev, prog, act); fallthrough; case XDP_DROP: - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, sync); ret = MVNETA_XDP_DROPPED; stats->xdp_drop++; break; @@ -2269,7 +2311,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, int data_len = -MVNETA_MH_SIZE, len; struct net_device *dev = pp->dev; enum dma_data_direction dma_dir; - struct skb_shared_info *sinfo; if (*size > MVNETA_MAX_RX_BUF_SIZE) { len = MVNETA_MAX_RX_BUF_SIZE; @@ -2289,11 +2330,9 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, /* Prefetch header */ prefetch(data); + xdp_buff_clear_frags_flag(xdp); xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE, data_len, false); - - sinfo = xdp_get_shared_info_from_buff(xdp); - sinfo->nr_frags = 0; } static void @@ -2301,9 +2340,9 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, struct mvneta_rx_desc *rx_desc, struct mvneta_rx_queue *rxq, struct xdp_buff *xdp, int *size, - struct skb_shared_info *xdp_sinfo, struct page *page) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); struct net_device *dev = pp->dev; enum dma_data_direction dma_dir; int data_len, len; @@ -2321,25 +2360,25 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, len, dma_dir); rx_desc->buf_phys_addr = 0; - if (data_len > 0 && xdp_sinfo->nr_frags < MAX_SKB_FRAGS) { - skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++]; + if (!xdp_buff_has_frags(xdp)) + sinfo->nr_frags = 0; + + if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) { + skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags++]; skb_frag_off_set(frag, pp->rx_offset_correction); skb_frag_size_set(frag, data_len); __skb_frag_set_page(frag, page); + + if (!xdp_buff_has_frags(xdp)) { + sinfo->xdp_frags_size = *size; + xdp_buff_set_frags_flag(xdp); + } + if (page_is_pfmemalloc(page)) + xdp_buff_set_frag_pfmemalloc(xdp); } else { page_pool_put_full_page(rxq->page_pool, page, true); } - - /* last fragment */ - if (len == *size) { - struct skb_shared_info *sinfo; - - sinfo = xdp_get_shared_info_from_buff(xdp); - sinfo->nr_frags = xdp_sinfo->nr_frags; - memcpy(sinfo->frags, xdp_sinfo->frags, - sinfo->nr_frags * sizeof(skb_frag_t)); - } *size -= len; } @@ -2348,8 +2387,11 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, struct xdp_buff *xdp, u32 desc_status) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); - int i, num_frags = sinfo->nr_frags; struct sk_buff *skb; + u8 num_frags; + + if (unlikely(xdp_buff_has_frags(xdp))) + num_frags = sinfo->nr_frags; skb = build_skb(xdp->data_hard_start, PAGE_SIZE); if (!skb) @@ -2361,13 +2403,11 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, skb_put(skb, xdp->data_end - xdp->data); skb->ip_summed = mvneta_rx_csum(pp, desc_status); - for (i = 0; i < num_frags; i++) { - skb_frag_t *frag = &sinfo->frags[i]; - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - skb_frag_page(frag), skb_frag_off(frag), - skb_frag_size(frag), PAGE_SIZE); - } + if (unlikely(xdp_buff_has_frags(xdp))) + xdp_update_skb_shared_info(skb, num_frags, + sinfo->xdp_frags_size, + num_frags * xdp->frame_sz, + xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } @@ -2379,7 +2419,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi, { int rx_proc = 0, rx_todo, refill, size = 0; struct net_device *dev = pp->dev; - struct skb_shared_info sinfo; struct mvneta_stats ps = {}; struct bpf_prog *xdp_prog; u32 desc_status, frame_sz; @@ -2388,8 +2427,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi, xdp_init_buff(&xdp_buf, PAGE_SIZE, &rxq->xdp_rxq); xdp_buf.data_hard_start = NULL; - sinfo.nr_frags = 0; - /* Get number of received packets */ rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq); @@ -2431,7 +2468,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, } mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf, - &size, &sinfo, page); + &size, page); } /* Middle or Last descriptor */ if (!(rx_status & MVNETA_RXD_LAST_DESC)) @@ -2439,7 +2476,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, continue; if (size) { - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1); goto next; } @@ -2451,7 +2488,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, if (IS_ERR(skb)) { struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1); u64_stats_update_begin(&stats->syncp); stats->es.skb_alloc_error++; @@ -2468,11 +2505,10 @@ static int mvneta_rx_swbm(struct napi_struct *napi, napi_gro_receive(napi, skb); next: xdp_buf.data_hard_start = NULL; - sinfo.nr_frags = 0; } if (xdp_buf.data_hard_start) - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1); if (ps.xdp_redirect) xdp_do_flush_map(); @@ -3260,7 +3296,8 @@ static int mvneta_create_page_pool(struct mvneta_port *pp, return err; } - err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0); + err = __xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0, + PAGE_SIZE); if (err < 0) goto err_free_pp; @@ -3740,6 +3777,7 @@ static void mvneta_percpu_disable(void *arg) static int mvneta_change_mtu(struct net_device *dev, int mtu) { struct mvneta_port *pp = netdev_priv(dev); + struct bpf_prog *prog = pp->xdp_prog; int ret; if (!IS_ALIGNED(MVNETA_RX_PKT_SIZE(mtu), 8)) { @@ -3748,8 +3786,11 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8); } - if (pp->xdp_prog && mtu > MVNETA_MAX_RX_BUF_SIZE) { - netdev_info(dev, "Illegal MTU value %d for XDP mode\n", mtu); + if (prog && !prog->aux->xdp_has_frags && + mtu > MVNETA_MAX_RX_BUF_SIZE) { + netdev_info(dev, "Illegal MTU %d for XDP prog without frags\n", + mtu); + return -EINVAL; } @@ -3969,6 +4010,15 @@ static const struct phylink_pcs_ops mvneta_phylink_pcs_ops = { .pcs_an_restart = mvneta_pcs_an_restart, }; +static struct phylink_pcs *mvneta_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct mvneta_port *pp = netdev_priv(ndev); + + return &pp->phylink_pcs; +} + static int mvneta_mac_prepare(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { @@ -4169,13 +4219,14 @@ static void mvneta_mac_link_up(struct phylink_config *config, mvneta_port_up(pp); if (phy && pp->eee_enabled) { - pp->eee_active = phy_init_eee(phy, 0) >= 0; + pp->eee_active = phy_init_eee(phy, false) >= 0; mvneta_set_eee(pp, pp->eee_active && pp->tx_lpi_enabled); } } static const struct phylink_mac_ops mvneta_phylink_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = mvneta_mac_select_pcs, .mac_prepare = mvneta_mac_prepare, .mac_config = mvneta_mac_config, .mac_finish = mvneta_mac_finish, @@ -4490,8 +4541,9 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog, struct mvneta_port *pp = netdev_priv(dev); struct bpf_prog *old_prog; - if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) { - NL_SET_ERR_MSG_MOD(extack, "MTU too large for XDP"); + if (prog && !prog->aux->xdp_has_frags && + dev->mtu > MVNETA_MAX_RX_BUF_SIZE) { + NL_SET_ERR_MSG_MOD(extack, "prog does not support XDP frags"); return -EOPNOTSUPP; } @@ -5321,26 +5373,62 @@ static int mvneta_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; - dev->irq = irq_of_parse_and_map(dn, 0); - if (dev->irq == 0) - return -EINVAL; + dev->tx_queue_len = MVNETA_MAX_TXD; + dev->watchdog_timeo = 5 * HZ; + dev->netdev_ops = &mvneta_netdev_ops; + dev->ethtool_ops = &mvneta_eth_tool_ops; + + pp = netdev_priv(dev); + spin_lock_init(&pp->lock); + pp->dn = dn; + + pp->rxq_def = rxq_def; + pp->indir[0] = rxq_def; err = of_get_phy_mode(dn, &phy_mode); if (err) { dev_err(&pdev->dev, "incorrect phy-mode\n"); - goto err_free_irq; + return err; } + pp->phy_interface = phy_mode; + comphy = devm_of_phy_get(&pdev->dev, dn, NULL); - if (comphy == ERR_PTR(-EPROBE_DEFER)) { - err = -EPROBE_DEFER; - goto err_free_irq; - } else if (IS_ERR(comphy)) { + if (comphy == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + + if (IS_ERR(comphy)) comphy = NULL; + + pp->comphy = comphy; + + pp->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pp->base)) + return PTR_ERR(pp->base); + + /* Get special SoC configurations */ + if (of_device_is_compatible(dn, "marvell,armada-3700-neta")) + pp->neta_armada3700 = true; + + dev->irq = irq_of_parse_and_map(dn, 0); + if (dev->irq == 0) + return -EINVAL; + + pp->clk = devm_clk_get(&pdev->dev, "core"); + if (IS_ERR(pp->clk)) + pp->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pp->clk)) { + err = PTR_ERR(pp->clk); + goto err_free_irq; } - pp = netdev_priv(dev); - spin_lock_init(&pp->lock); + clk_prepare_enable(pp->clk); + + pp->clk_bus = devm_clk_get(&pdev->dev, "bus"); + if (!IS_ERR(pp->clk_bus)) + clk_prepare_enable(pp->clk_bus); + + pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops; pp->phylink_config.dev = &dev->dev; pp->phylink_config.type = PHYLINK_NETDEV; @@ -5377,55 +5465,16 @@ static int mvneta_probe(struct platform_device *pdev) phy_mode, &mvneta_phylink_ops); if (IS_ERR(phylink)) { err = PTR_ERR(phylink); - goto err_free_irq; - } - - dev->tx_queue_len = MVNETA_MAX_TXD; - dev->watchdog_timeo = 5 * HZ; - dev->netdev_ops = &mvneta_netdev_ops; - - dev->ethtool_ops = &mvneta_eth_tool_ops; - - pp->phylink = phylink; - pp->comphy = comphy; - pp->phy_interface = phy_mode; - pp->dn = dn; - - pp->rxq_def = rxq_def; - pp->indir[0] = rxq_def; - - /* Get special SoC configurations */ - if (of_device_is_compatible(dn, "marvell,armada-3700-neta")) - pp->neta_armada3700 = true; - - pp->clk = devm_clk_get(&pdev->dev, "core"); - if (IS_ERR(pp->clk)) - pp->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(pp->clk)) { - err = PTR_ERR(pp->clk); - goto err_free_phylink; - } - - clk_prepare_enable(pp->clk); - - pp->clk_bus = devm_clk_get(&pdev->dev, "bus"); - if (!IS_ERR(pp->clk_bus)) - clk_prepare_enable(pp->clk_bus); - - pp->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(pp->base)) { - err = PTR_ERR(pp->base); goto err_clk; } - pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops; - phylink_set_pcs(phylink, &pp->phylink_pcs); + pp->phylink = phylink; /* Alloc per-cpu port structure */ pp->ports = alloc_percpu(struct mvneta_pcpu_port); if (!pp->ports) { err = -ENOMEM; - goto err_clk; + goto err_free_phylink; } /* Alloc per-cpu stats */ @@ -5569,12 +5618,12 @@ err_netdev: free_percpu(pp->stats); err_free_ports: free_percpu(pp->ports); -err_clk: - clk_disable_unprepare(pp->clk_bus); - clk_disable_unprepare(pp->clk); err_free_phylink: if (pp->phylink) phylink_destroy(pp->phylink); +err_clk: + clk_disable_unprepare(pp->clk_bus); + clk_disable_unprepare(pp->clk); err_free_irq: irq_dispose_mapping(dev->irq); return err; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 3631d612aaca..25491edc35ce 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -578,31 +578,78 @@ void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable) } } +static int cgx_lmac_get_pause_frm_status(void *cgxd, int lmac_id, + u8 *tx_pause, u8 *rx_pause) +{ + struct cgx *cgx = cgxd; + u64 cfg; + + if (is_dev_rpm(cgx)) + return 0; + + if (!is_lmac_valid(cgx, lmac_id)) + return -ENODEV; + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + *rx_pause = !!(cfg & CGX_SMUX_RX_FRM_CTL_CTL_BCK); + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_TX_CTL); + *tx_pause = !!(cfg & CGX_SMUX_TX_CTL_L2P_BP_CONV); + return 0; +} + /* Enable or disable forwarding received pause frames to Tx block */ void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable) { struct cgx *cgx = cgxd; + u8 rx_pause, tx_pause; + bool is_pfc_enabled; + struct lmac *lmac; u64 cfg; if (!cgx) return; - if (enable) { - cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); - cfg |= CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + lmac = lmac_pdata(lmac_id, cgx); + if (!lmac) + return; - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); - cfg |= CGX_SMUX_RX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + /* Pause frames are not enabled just return */ + if (!bitmap_weight(lmac->rx_fc_pfvf_bmap.bmap, lmac->rx_fc_pfvf_bmap.max)) + return; + + cgx_lmac_get_pause_frm_status(cgx, lmac_id, &rx_pause, &tx_pause); + is_pfc_enabled = rx_pause ? false : true; + + if (enable) { + if (!is_pfc_enabled) { + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg |= CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + cfg |= CGX_SMUX_RX_FRM_CTL_CTL_BCK; + cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + } else { + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_CBFC_CTL); + cfg |= CGXX_SMUX_CBFC_CTL_BCK_EN; + cgx_write(cgx, lmac_id, CGXX_SMUX_CBFC_CTL, cfg); + } } else { - cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); - cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); - cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + if (!is_pfc_enabled) { + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; + cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + } else { + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_CBFC_CTL); + cfg &= ~CGXX_SMUX_CBFC_CTL_BCK_EN; + cgx_write(cgx, lmac_id, CGXX_SMUX_CBFC_CTL, cfg); + } } } @@ -722,26 +769,6 @@ int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable) return !!(last & DATA_PKT_TX_EN); } -static int cgx_lmac_get_pause_frm_status(void *cgxd, int lmac_id, - u8 *tx_pause, u8 *rx_pause) -{ - struct cgx *cgx = cgxd; - u64 cfg; - - if (is_dev_rpm(cgx)) - return 0; - - if (!is_lmac_valid(cgx, lmac_id)) - return -ENODEV; - - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); - *rx_pause = !!(cfg & CGX_SMUX_RX_FRM_CTL_CTL_BCK); - - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_TX_CTL); - *tx_pause = !!(cfg & CGX_SMUX_TX_CTL_L2P_BP_CONV); - return 0; -} - static int cgx_lmac_enadis_pause_frm(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause) { @@ -782,21 +809,8 @@ static void cgx_lmac_pause_frm_config(void *cgxd, int lmac_id, bool enable) if (!is_lmac_valid(cgx, lmac_id)) return; - if (enable) { - /* Enable receive pause frames */ - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); - cfg |= CGX_SMUX_RX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); - - cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); - cfg |= CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); - - /* Enable pause frames transmission */ - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_TX_CTL); - cfg |= CGX_SMUX_TX_CTL_L2P_BP_CONV; - cgx_write(cgx, lmac_id, CGXX_SMUX_TX_CTL, cfg); + if (enable) { /* Set pause time and interval */ cgx_write(cgx, lmac_id, CGXX_SMUX_TX_PAUSE_PKT_TIME, DEFAULT_PAUSE_TIME); @@ -813,21 +827,120 @@ static void cgx_lmac_pause_frm_config(void *cgxd, int lmac_id, bool enable) cfg &= ~0xFFFFULL; cgx_write(cgx, lmac_id, CGXX_GMP_GMI_TX_PAUSE_PKT_INTERVAL, cfg | (DEFAULT_PAUSE_TIME / 2)); - } else { - /* ALL pause frames received are completely ignored */ - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); - cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + } - cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); - cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; - cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + /* ALL pause frames received are completely ignored */ + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); + cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; + cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); + + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + + /* Disable pause frames transmission */ + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_TX_CTL); + cfg &= ~CGX_SMUX_TX_CTL_L2P_BP_CONV; + cgx_write(cgx, lmac_id, CGXX_SMUX_TX_CTL, cfg); + + cfg = cgx_read(cgx, 0, CGXX_CMR_RX_OVR_BP); + cfg |= CGX_CMR_RX_OVR_BP_EN(lmac_id); + cfg &= ~CGX_CMR_RX_OVR_BP_BP(lmac_id); + cgx_write(cgx, 0, CGXX_CMR_RX_OVR_BP, cfg); +} + +int verify_lmac_fc_cfg(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause, + int pfvf_idx) +{ + struct cgx *cgx = cgxd; + struct lmac *lmac; + + lmac = lmac_pdata(lmac_id, cgx); + if (!lmac) + return -ENODEV; + + if (!rx_pause) + clear_bit(pfvf_idx, lmac->rx_fc_pfvf_bmap.bmap); + else + set_bit(pfvf_idx, lmac->rx_fc_pfvf_bmap.bmap); + + if (!tx_pause) + clear_bit(pfvf_idx, lmac->tx_fc_pfvf_bmap.bmap); + else + set_bit(pfvf_idx, lmac->tx_fc_pfvf_bmap.bmap); + + /* check if other pfvfs are using flow control */ + if (!rx_pause && bitmap_weight(lmac->rx_fc_pfvf_bmap.bmap, lmac->rx_fc_pfvf_bmap.max)) { + dev_warn(&cgx->pdev->dev, + "Receive Flow control disable not permitted as its used by other PFVFs\n"); + return -EPERM; + } + + if (!tx_pause && bitmap_weight(lmac->tx_fc_pfvf_bmap.bmap, lmac->tx_fc_pfvf_bmap.max)) { + dev_warn(&cgx->pdev->dev, + "Transmit Flow control disable not permitted as its used by other PFVFs\n"); + return -EPERM; + } + + return 0; +} + +int cgx_lmac_pfc_config(void *cgxd, int lmac_id, u8 tx_pause, + u8 rx_pause, u16 pfc_en) +{ + struct cgx *cgx = cgxd; + u64 cfg; + + if (!is_lmac_valid(cgx, lmac_id)) + return -ENODEV; + + /* Return as no traffic classes are requested */ + if (tx_pause && !pfc_en) + return 0; + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_CBFC_CTL); - /* Disable pause frames transmission */ - cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_TX_CTL); - cfg &= ~CGX_SMUX_TX_CTL_L2P_BP_CONV; - cgx_write(cgx, lmac_id, CGXX_SMUX_TX_CTL, cfg); + if (rx_pause) { + cfg |= (CGXX_SMUX_CBFC_CTL_RX_EN | + CGXX_SMUX_CBFC_CTL_BCK_EN | + CGXX_SMUX_CBFC_CTL_DRP_EN); + } else { + cfg &= ~(CGXX_SMUX_CBFC_CTL_RX_EN | + CGXX_SMUX_CBFC_CTL_BCK_EN | + CGXX_SMUX_CBFC_CTL_DRP_EN); } + + if (tx_pause) + cfg |= CGXX_SMUX_CBFC_CTL_TX_EN; + else + cfg &= ~CGXX_SMUX_CBFC_CTL_TX_EN; + + cfg = FIELD_SET(CGX_PFC_CLASS_MASK, pfc_en, cfg); + + cgx_write(cgx, lmac_id, CGXX_SMUX_CBFC_CTL, cfg); + + /* Write source MAC address which will be filled into PFC packet */ + cfg = cgx_lmac_addr_get(cgx->cgx_id, lmac_id); + cgx_write(cgx, lmac_id, CGXX_SMUX_SMAC, cfg); + + return 0; +} + +int cgx_lmac_get_pfc_frm_cfg(void *cgxd, int lmac_id, u8 *tx_pause, + u8 *rx_pause) +{ + struct cgx *cgx = cgxd; + u64 cfg; + + if (!is_lmac_valid(cgx, lmac_id)) + return -ENODEV; + + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_CBFC_CTL); + + *rx_pause = !!(cfg & CGXX_SMUX_CBFC_CTL_RX_EN); + *tx_pause = !!(cfg & CGXX_SMUX_CBFC_CTL_TX_EN); + + return 0; } void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable) @@ -1489,6 +1602,16 @@ static int cgx_lmac_init(struct cgx *cgx) /* Reserve first entry for default MAC address */ set_bit(0, lmac->mac_to_index_bmap.bmap); + lmac->rx_fc_pfvf_bmap.max = 128; + err = rvu_alloc_bitmap(&lmac->rx_fc_pfvf_bmap); + if (err) + goto err_dmac_bmap_free; + + lmac->tx_fc_pfvf_bmap.max = 128; + err = rvu_alloc_bitmap(&lmac->tx_fc_pfvf_bmap); + if (err) + goto err_rx_fc_bmap_free; + init_waitqueue_head(&lmac->wq_cmd_cmplt); mutex_init(&lmac->cmd_lock); spin_lock_init(&lmac->event_cb_lock); @@ -1505,6 +1628,10 @@ static int cgx_lmac_init(struct cgx *cgx) return cgx_lmac_verify_fwi_version(cgx); err_bitmap_free: + rvu_free_bitmap(&lmac->tx_fc_pfvf_bmap); +err_rx_fc_bmap_free: + rvu_free_bitmap(&lmac->rx_fc_pfvf_bmap); +err_dmac_bmap_free: rvu_free_bitmap(&lmac->mac_to_index_bmap); err_name_free: kfree(lmac->name); @@ -1572,6 +1699,8 @@ static struct mac_ops cgx_mac_ops = { .mac_enadis_ptp_config = cgx_lmac_ptp_config, .mac_rx_tx_enable = cgx_lmac_rx_tx_enable, .mac_tx_enable = cgx_lmac_tx_enable, + .pfc_config = cgx_lmac_pfc_config, + .mac_get_pfc_frm_cfg = cgx_lmac_get_pfc_frm_cfg, }; static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index ab1e4abdea38..bd2f33a26eee 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -76,6 +76,13 @@ #define CGXX_SMUX_TX_CTL 0x20178 #define CGXX_SMUX_TX_PAUSE_PKT_TIME 0x20110 #define CGXX_SMUX_TX_PAUSE_PKT_INTERVAL 0x20120 +#define CGXX_SMUX_SMAC 0x20108 +#define CGXX_SMUX_CBFC_CTL 0x20218 +#define CGXX_SMUX_CBFC_CTL_RX_EN BIT_ULL(0) +#define CGXX_SMUX_CBFC_CTL_TX_EN BIT_ULL(1) +#define CGXX_SMUX_CBFC_CTL_DRP_EN BIT_ULL(2) +#define CGXX_SMUX_CBFC_CTL_BCK_EN BIT_ULL(3) +#define CGX_PFC_CLASS_MASK GENMASK_ULL(47, 32) #define CGXX_GMP_GMI_TX_PAUSE_PKT_TIME 0x38230 #define CGXX_GMP_GMI_TX_PAUSE_PKT_INTERVAL 0x38248 #define CGX_SMUX_TX_CTL_L2P_BP_CONV BIT_ULL(7) @@ -172,4 +179,10 @@ u64 cgx_lmac_read(int cgx_id, int lmac_id, u64 offset); int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index); u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id); u64 cgx_read_dmac_entry(void *cgxd, int index); +int cgx_lmac_pfc_config(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause, + u16 pfc_en); +int cgx_lmac_get_pfc_frm_cfg(void *cgxd, int lmac_id, u8 *tx_pause, + u8 *rx_pause); +int verify_lmac_fc_cfg(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause, + int pfvf_idx); #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index b33e7d1d0851..f30581bf0688 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -17,6 +17,8 @@ * @resp: command response * @link_info: link related information * @mac_to_index_bmap: Mac address to CGX table index mapping + * @rx_fc_pfvf_bmap: Receive flow control enabled netdev mapping + * @tx_fc_pfvf_bmap: Transmit flow control enabled netdev mapping * @event_cb: callback for linkchange events * @event_cb_lock: lock for serializing callback with unregister * @cgx: parent cgx port @@ -33,6 +35,8 @@ struct lmac { u64 resp; struct cgx_link_user_info link_info; struct rsrc_bmap mac_to_index_bmap; + struct rsrc_bmap rx_fc_pfvf_bmap; + struct rsrc_bmap tx_fc_pfvf_bmap; struct cgx_event_cb event_cb; /* lock for serializing callback with unregister */ spinlock_t event_cb_lock; @@ -110,6 +114,12 @@ struct mac_ops { int (*mac_rx_tx_enable)(void *cgxd, int lmac_id, bool enable); int (*mac_tx_enable)(void *cgxd, int lmac_id, bool enable); + int (*pfc_config)(void *cgxd, int lmac_id, + u8 tx_pause, u8 rx_pause, u16 pfc_en); + + int (*mac_get_pfc_frm_cfg)(void *cgxd, int lmac_id, + u8 *tx_pause, u8 *rx_pause); + }; struct cgx { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 58e2aeebc14f..550cb11197bf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -172,6 +172,8 @@ M(RPM_STATS, 0x21C, rpm_stats, msg_req, rpm_stats_rsp) \ M(CGX_MAC_ADDR_RESET, 0x21D, cgx_mac_addr_reset, msg_req, msg_rsp) \ M(CGX_MAC_ADDR_UPDATE, 0x21E, cgx_mac_addr_update, cgx_mac_addr_update_req, \ msg_rsp) \ +M(CGX_PRIO_FLOW_CTRL_CFG, 0x21F, cgx_prio_flow_ctrl_cfg, cgx_pfc_cfg, \ + cgx_pfc_rsp) \ /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ M(NPA_LF_ALLOC, 0x400, npa_lf_alloc, \ npa_lf_alloc_req, npa_lf_alloc_rsp) \ @@ -609,6 +611,21 @@ struct rpm_stats_rsp { u64 tx_stats[RPM_TX_STATS_COUNT]; }; +struct cgx_pfc_cfg { + struct mbox_msghdr hdr; + u8 rx_pause; + u8 tx_pause; + u16 pfc_en; /* bitmap indicating pfc enabled traffic classes */ +}; + +struct cgx_pfc_rsp { + struct mbox_msghdr hdr; + u8 rx_pause; + u8 tx_pause; +}; + + /* NPA mbox message formats */ + struct npc_set_pkind { struct mbox_msghdr hdr; #define OTX2_PRIV_FLAGS_DEFAULT BIT_ULL(0) @@ -1603,6 +1620,8 @@ enum cgx_af_status { LMAC_AF_ERR_INVALID_PARAM = -1101, LMAC_AF_ERR_PF_NOT_MAPPED = -1102, LMAC_AF_ERR_PERM_DENIED = -1103, + LMAC_AF_ERR_PFC_ENADIS_PERM_DENIED = -1104, + LMAC_AF_ERR_8023PAUSE_ENADIS_PERM_DENIED = -1105, }; #endif /* MBOX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index 9ea2f6ac38ec..47e83d7a5804 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -32,6 +32,8 @@ static struct mac_ops rpm_mac_ops = { .mac_enadis_ptp_config = rpm_lmac_ptp_config, .mac_rx_tx_enable = rpm_lmac_rx_tx_enable, .mac_tx_enable = rpm_lmac_tx_enable, + .pfc_config = rpm_lmac_pfc_config, + .mac_get_pfc_frm_cfg = rpm_lmac_get_pfc_frm_cfg, }; struct mac_ops *rpm_get_mac_ops(void) @@ -96,11 +98,20 @@ int rpm_lmac_rx_tx_enable(void *rpmd, int lmac_id, bool enable) void rpm_lmac_enadis_rx_pause_fwding(void *rpmd, int lmac_id, bool enable) { rpm_t *rpm = rpmd; + struct lmac *lmac; u64 cfg; if (!rpm) return; + lmac = lmac_pdata(lmac_id, rpm); + if (!lmac) + return; + + /* Pause frames are not enabled just return */ + if (!bitmap_weight(lmac->rx_fc_pfvf_bmap.bmap, lmac->rx_fc_pfvf_bmap.max)) + return; + if (enable) { cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE; @@ -122,13 +133,94 @@ int rpm_lmac_get_pause_frm_status(void *rpmd, int lmac_id, return -ENODEV; cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - *rx_pause = !(cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE); + if (!(cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_PFC_MODE)) { + *rx_pause = !(cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE); + *tx_pause = !(cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE); + } - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - *tx_pause = !(cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE); return 0; } +static void rpm_cfg_pfc_quanta_thresh(rpm_t *rpm, int lmac_id, + unsigned long pfc_en, + bool enable) +{ + u64 quanta_offset = 0, quanta_thresh = 0, cfg; + int i, shift; + + /* Set pause time and interval */ + for_each_set_bit(i, &pfc_en, 16) { + switch (i) { + case 0: + case 1: + quanta_offset = RPMX_MTI_MAC100X_CL01_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL01_QUANTA_THRESH; + break; + case 2: + case 3: + quanta_offset = RPMX_MTI_MAC100X_CL23_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL23_QUANTA_THRESH; + break; + case 4: + case 5: + quanta_offset = RPMX_MTI_MAC100X_CL45_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL45_QUANTA_THRESH; + break; + case 6: + case 7: + quanta_offset = RPMX_MTI_MAC100X_CL67_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL67_QUANTA_THRESH; + break; + case 8: + case 9: + quanta_offset = RPMX_MTI_MAC100X_CL89_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL89_QUANTA_THRESH; + break; + case 10: + case 11: + quanta_offset = RPMX_MTI_MAC100X_CL1011_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL1011_QUANTA_THRESH; + break; + case 12: + case 13: + quanta_offset = RPMX_MTI_MAC100X_CL1213_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL1213_QUANTA_THRESH; + break; + case 14: + case 15: + quanta_offset = RPMX_MTI_MAC100X_CL1415_PAUSE_QUANTA; + quanta_thresh = RPMX_MTI_MAC100X_CL1415_QUANTA_THRESH; + break; + } + + if (!quanta_offset || !quanta_thresh) + continue; + + shift = (i % 2) ? 1 : 0; + cfg = rpm_read(rpm, lmac_id, quanta_offset); + if (enable) { + cfg |= ((u64)RPM_DEFAULT_PAUSE_TIME << shift * 16); + } else { + if (!shift) + cfg &= ~GENMASK_ULL(15, 0); + else + cfg &= ~GENMASK_ULL(31, 16); + } + rpm_write(rpm, lmac_id, quanta_offset, cfg); + + cfg = rpm_read(rpm, lmac_id, quanta_thresh); + if (enable) { + cfg |= ((u64)(RPM_DEFAULT_PAUSE_TIME / 2) << shift * 16); + } else { + if (!shift) + cfg &= ~GENMASK_ULL(15, 0); + else + cfg &= ~GENMASK_ULL(31, 16); + } + rpm_write(rpm, lmac_id, quanta_thresh, cfg); + } +} + int rpm_lmac_enadis_pause_frm(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause) { @@ -152,8 +244,12 @@ int rpm_lmac_enadis_pause_frm(void *rpmd, int lmac_id, u8 tx_pause, cfg = rpm_read(rpm, 0, RPMX_CMR_RX_OVR_BP); if (tx_pause) { + /* Configure CL0 Pause Quanta & threshold for 802.3X frames */ + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 1, true); cfg &= ~RPMX_CMR_RX_OVR_BP_EN(lmac_id); } else { + /* Disable all Pause Quanta & threshold values */ + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xffff, false); cfg |= RPMX_CMR_RX_OVR_BP_EN(lmac_id); cfg &= ~RPMX_CMR_RX_OVR_BP_BP(lmac_id); } @@ -166,56 +262,20 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable) rpm_t *rpm = rpmd; u64 cfg; - if (enable) { - /* Enable 802.3 pause frame mode */ - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PFC_MODE; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - - /* Enable receive pause frames */ - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - - /* Enable forward pause to TX block */ - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - - /* Enable pause frames transmission */ - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - - /* Set pause time and interval */ - cfg = rpm_read(rpm, lmac_id, - RPMX_MTI_MAC100X_CL01_PAUSE_QUANTA); - cfg &= ~0xFFFFULL; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_CL01_PAUSE_QUANTA, - cfg | RPM_DEFAULT_PAUSE_TIME); - /* Set pause interval as the hardware default is too short */ - cfg = rpm_read(rpm, lmac_id, - RPMX_MTI_MAC100X_CL01_QUANTA_THRESH); - cfg &= ~0xFFFFULL; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_CL01_QUANTA_THRESH, - cfg | (RPM_DEFAULT_PAUSE_TIME / 2)); - - } else { - /* ALL pause frames received are completely ignored */ - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* ALL pause frames received are completely ignored */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - /* Disable forward pause to TX block */ - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Disable forward pause to TX block */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - /* Disable pause frames transmission */ - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); - cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; - rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); - } + /* Disable pause frames transmission */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); } int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat) @@ -323,3 +383,65 @@ void rpm_lmac_ptp_config(void *rpmd, int lmac_id, bool enable) cfg &= ~RPMX_RX_TS_PREPEND; rpm_write(rpm, lmac_id, RPMX_CMRX_CFG, cfg); } + +int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 pfc_en) +{ + rpm_t *rpm = rpmd; + u64 cfg; + + if (!is_lmac_valid(rpm, lmac_id)) + return -ENODEV; + + /* reset PFC class quanta and threshold */ + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xffff, false); + + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + + if (rx_pause) { + cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + } else { + cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + } + + if (tx_pause) { + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, pfc_en, true); + cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; + } else { + rpm_cfg_pfc_quanta_thresh(rpm, lmac_id, 0xfff, false); + cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; + } + + if (!rx_pause && !tx_pause) + cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PFC_MODE; + else + cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_PFC_MODE; + + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + + cfg = rpm_read(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL); + cfg = FIELD_SET(RPM_PFC_CLASS_MASK, pfc_en, cfg); + rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, cfg); + + return 0; +} + +int rpm_lmac_get_pfc_frm_cfg(void *rpmd, int lmac_id, u8 *tx_pause, u8 *rx_pause) +{ + rpm_t *rpm = rpmd; + u64 cfg; + + if (!is_lmac_valid(rpm, lmac_id)) + return -ENODEV; + + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + if (cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_PFC_MODE) { + *rx_pause = !(cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE); + *tx_pause = !(cfg & RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE); + } + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h index ff580311edd0..9ab8d49dd180 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h @@ -33,7 +33,21 @@ #define RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE BIT_ULL(8) #define RPMX_MTI_MAC100X_COMMAND_CONFIG_PFC_MODE BIT_ULL(19) #define RPMX_MTI_MAC100X_CL01_PAUSE_QUANTA 0x80A8 +#define RPMX_MTI_MAC100X_CL23_PAUSE_QUANTA 0x80B0 +#define RPMX_MTI_MAC100X_CL45_PAUSE_QUANTA 0x80B8 +#define RPMX_MTI_MAC100X_CL67_PAUSE_QUANTA 0x80C0 #define RPMX_MTI_MAC100X_CL01_QUANTA_THRESH 0x80C8 +#define RPMX_MTI_MAC100X_CL23_QUANTA_THRESH 0x80D0 +#define RPMX_MTI_MAC100X_CL45_QUANTA_THRESH 0x80D8 +#define RPMX_MTI_MAC100X_CL67_QUANTA_THRESH 0x80E0 +#define RPMX_MTI_MAC100X_CL89_PAUSE_QUANTA 0x8108 +#define RPMX_MTI_MAC100X_CL1011_PAUSE_QUANTA 0x8110 +#define RPMX_MTI_MAC100X_CL1213_PAUSE_QUANTA 0x8118 +#define RPMX_MTI_MAC100X_CL1415_PAUSE_QUANTA 0x8120 +#define RPMX_MTI_MAC100X_CL89_QUANTA_THRESH 0x8128 +#define RPMX_MTI_MAC100X_CL1011_QUANTA_THRESH 0x8130 +#define RPMX_MTI_MAC100X_CL1213_QUANTA_THRESH 0x8138 +#define RPMX_MTI_MAC100X_CL1415_QUANTA_THRESH 0x8140 #define RPM_DEFAULT_PAUSE_TIME 0xFFFF #define RPMX_CMR_RX_OVR_BP 0x4120 #define RPMX_CMR_RX_OVR_BP_EN(x) BIT_ULL((x) + 8) @@ -45,6 +59,18 @@ #define RPM_LMAC_FWI 0xa #define RPM_TX_EN BIT_ULL(0) #define RPM_RX_EN BIT_ULL(1) +#define RPMX_CMRX_PRT_CBFC_CTL 0x5B08 +#define RPMX_CMRX_PRT_CBFC_CTL_LOGL_EN_RX_SHIFT 33 +#define RPMX_CMRX_PRT_CBFC_CTL_PHYS_BP_SHIFT 16 +#define RPMX_CMRX_PRT_CBFC_CTL_LOGL_EN_TX_SHIFT 0 +#define RPM_PFC_CLASS_MASK GENMASK_ULL(48, 33) +#define RPMX_MTI_MAC100X_CL89_QUANTA_THRESH 0x8128 +#define RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_PAD_EN BIT_ULL(11) +#define RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE BIT_ULL(8) +#define RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD BIT_ULL(7) +#define RPMX_MTI_MAC100X_CL01_PAUSE_QUANTA 0x80A8 +#define RPMX_MTI_MAC100X_CL89_PAUSE_QUANTA 0x8108 +#define RPM_DEFAULT_PAUSE_TIME 0xFFFF /* Function Declarations */ int rpm_get_nr_lmacs(void *rpmd); @@ -61,4 +87,8 @@ int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat); void rpm_lmac_ptp_config(void *rpmd, int lmac_id, bool enable); int rpm_lmac_rx_tx_enable(void *rpmd, int lmac_id, bool enable); int rpm_lmac_tx_enable(void *rpmd, int lmac_id, bool enable); +int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, + u16 pfc_en); +int rpm_lmac_get_pfc_frm_cfg(void *rpmd, int lmac_id, u8 *tx_pause, + u8 *rx_pause); #endif /* RPM_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 5ed94cfb47d2..513b43ecd5be 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -807,6 +807,9 @@ u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable); +int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause, + u16 pfc_en); +int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause); int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 8a7ac5a8b821..9ffe99830e34 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -863,6 +863,45 @@ int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req, return 0; } +int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause) +{ + int pf = rvu_get_pf(pcifunc); + u8 rx_pfc = 0, tx_pfc = 0; + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; + + if (!is_mac_feature_supported(rvu, pf, RVU_LMAC_FEAT_FC)) + return 0; + + /* This msg is expected only from PF/VFs that are mapped to CGX LMACs, + * if received from other PF/VF simply ACK, nothing to do. + */ + if (!is_pf_cgxmapped(rvu, pf)) + return LMAC_AF_ERR_PF_NOT_MAPPED; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + mac_ops->mac_get_pfc_frm_cfg(cgxd, lmac_id, &tx_pfc, &rx_pfc); + if (tx_pfc || rx_pfc) { + dev_warn(rvu->dev, + "Can not configure 802.3X flow control as PFC frames are enabled"); + return LMAC_AF_ERR_8023PAUSE_ENADIS_PERM_DENIED; + } + + mutex_lock(&rvu->rsrc_lock); + if (verify_lmac_fc_cfg(cgxd, lmac_id, tx_pause, rx_pause, + pcifunc & RVU_PFVF_FUNC_MASK)) { + mutex_unlock(&rvu->rsrc_lock); + return LMAC_AF_ERR_PERM_DENIED; + } + mutex_unlock(&rvu->rsrc_lock); + + return mac_ops->mac_enadis_pause_frm(cgxd, lmac_id, tx_pause, rx_pause); +} + int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu, struct cgx_pause_frm_cfg *req, struct cgx_pause_frm_cfg *rsp) @@ -870,11 +909,9 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu, int pf = rvu_get_pf(req->hdr.pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; + int err = 0; void *cgxd; - if (!is_mac_feature_supported(rvu, pf, RVU_LMAC_FEAT_FC)) - return 0; - /* This msg is expected only from PF/VFs that are mapped to CGX LMACs, * if received from other PF/VF simply ACK, nothing to do. */ @@ -886,13 +923,11 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu, mac_ops = get_mac_ops(cgxd); if (req->set) - mac_ops->mac_enadis_pause_frm(cgxd, lmac_id, - req->tx_pause, req->rx_pause); + err = rvu_cgx_cfg_pause_frm(rvu, req->hdr.pcifunc, req->tx_pause, req->rx_pause); else - mac_ops->mac_get_pause_frm_status(cgxd, lmac_id, - &rsp->tx_pause, - &rsp->rx_pause); - return 0; + mac_ops->mac_get_pause_frm_status(cgxd, lmac_id, &rsp->tx_pause, &rsp->rx_pause); + + return err; } int rvu_mbox_handler_cgx_get_phy_fec_stats(struct rvu *rvu, struct msg_req *req, @@ -1079,3 +1114,67 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu, rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); return cgx_lmac_addr_update(cgx_id, lmac_id, req->mac_addr, req->index); } + +int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, + u8 rx_pause, u16 pfc_en) +{ + int pf = rvu_get_pf(pcifunc); + u8 rx_8023 = 0, tx_8023 = 0; + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; + + /* This msg is expected only from PF/VFs that are mapped to CGX LMACs, + * if received from other PF/VF simply ACK, nothing to do. + */ + if (!is_pf_cgxmapped(rvu, pf)) + return -ENODEV; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + mac_ops->mac_get_pause_frm_status(cgxd, lmac_id, &tx_8023, &rx_8023); + if (tx_8023 || rx_8023) { + dev_warn(rvu->dev, + "Can not configure PFC as 802.3X pause frames are enabled"); + return LMAC_AF_ERR_PFC_ENADIS_PERM_DENIED; + } + + mutex_lock(&rvu->rsrc_lock); + if (verify_lmac_fc_cfg(cgxd, lmac_id, tx_pause, rx_pause, + pcifunc & RVU_PFVF_FUNC_MASK)) { + mutex_unlock(&rvu->rsrc_lock); + return LMAC_AF_ERR_PERM_DENIED; + } + mutex_unlock(&rvu->rsrc_lock); + + return mac_ops->pfc_config(cgxd, lmac_id, tx_pause, rx_pause, pfc_en); +} + +int rvu_mbox_handler_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, + struct cgx_pfc_cfg *req, + struct cgx_pfc_rsp *rsp) +{ + int pf = rvu_get_pf(req->hdr.pcifunc); + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; + int err; + + /* This msg is expected only from PF/VFs that are mapped to CGX LMACs, + * if received from other PF/VF simply ACK, nothing to do. + */ + if (!is_pf_cgxmapped(rvu, pf)) + return -ENODEV; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + err = rvu_cgx_prio_flow_ctrl_cfg(rvu, req->hdr.pcifunc, req->tx_pause, + req->rx_pause, req->pfc_en); + + mac_ops->mac_get_pfc_frm_cfg(cgxd, lmac_id, &rsp->tx_pause, &rsp->rx_pause); + return err; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 97fb61915379..0fa625e2528e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -296,7 +296,6 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf, struct rvu_hwinfo *hw = rvu->hw; struct sdp_node_info *sdp_info; int pkind, pf, vf, lbkid, vfid; - struct mac_ops *mac_ops; u8 cgx_id, lmac_id; bool from_vf; int err; @@ -326,13 +325,6 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf, cgx_set_pkind(rvu_cgx_pdata(cgx_id, rvu), lmac_id, pkind); rvu_npc_set_pkind(rvu, pkind, pfvf); - mac_ops = get_mac_ops(rvu_cgx_pdata(cgx_id, rvu)); - - /* By default we enable pause frames */ - if ((pcifunc & RVU_PFVF_FUNC_MASK) == 0) - mac_ops->mac_enadis_pause_frm(rvu_cgx_pdata(cgx_id, - rvu), - lmac_id, true, true); break; case NIX_INTF_TYPE_LBK: vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1; @@ -533,7 +525,7 @@ static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, */ switch (type) { case NIX_INTF_TYPE_CGX: - if ((req->chan_base + req->chan_cnt) > 15) + if ((req->chan_base + req->chan_cnt) > 16) return -EINVAL; rvu_get_cgx_lmac_id(pfvf->cgx_lmac, &cgx_id, &lmac_id); /* Assign bpid based on cgx, lmac and chan id */ @@ -4578,6 +4570,12 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) pfvf->hw_rx_tstamp_en = false; } + /* reset priority flow control config */ + rvu_cgx_prio_flow_ctrl_cfg(rvu, pcifunc, 0, 0, 0); + + /* reset 802.3x flow control config */ + rvu_cgx_cfg_pause_frm(rvu, pcifunc, 0, 0); + nix_ctx_free(rvu, pfvf); nix_free_all_bandprof(rvu, pcifunc); @@ -5314,6 +5312,7 @@ int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc, aq_req.ctype = NIX_AQ_CTYPE_BANDPROF; aq_req.op = NIX_AQ_INSTOP_WRITE; memcpy(&aq_req.prof, &aq_rsp.prof, sizeof(struct nix_bandprof_s)); + memset((char *)&aq_req.prof_mask, 0xff, sizeof(struct nix_bandprof_s)); /* Clear higher layer enable bit in the mid profile, just in case */ aq_req.prof.hl_en = 0; aq_req.prof_mask.hl_en = 1; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 0048b5946712..d463dc72d80a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -11,4 +11,7 @@ rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_devlink.o rvu_nicvf-y := otx2_vf.o otx2_devlink.o +rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o +rvu_nicvf-$(CONFIG_DCB) += otx2_dcbnl.o + ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 66da31f30d3e..2c9760814bc3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -222,8 +222,11 @@ EXPORT_SYMBOL(otx2_set_mac_address); int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) { struct nix_frs_cfg *req; + u16 maxlen; int err; + maxlen = otx2_get_max_mtu(pfvf) + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + mutex_lock(&pfvf->mbox.lock); req = otx2_mbox_alloc_msg_nix_set_hw_frs(&pfvf->mbox); if (!req) { @@ -233,6 +236,10 @@ int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) req->maxlen = pfvf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + /* Use max receive length supported by hardware for loopback devices */ + if (is_otx2_lbkvf(pfvf->pdev)) + req->maxlen = maxlen; + err = otx2_sync_mbox_msg(&pfvf->mbox); mutex_unlock(&pfvf->mbox.lock); return err; @@ -262,6 +269,7 @@ unlock: mutex_unlock(&pfvf->mbox.lock); return err; } +EXPORT_SYMBOL(otx2_config_pause_frm); int otx2_set_flowkey_cfg(struct otx2_nic *pfvf) { @@ -931,7 +939,11 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) if (!is_otx2_lbkvf(pfvf->pdev)) { /* Enable receive CQ backpressure */ aq->cq.bp_ena = 1; +#ifdef CONFIG_DCB + aq->cq.bpid = pfvf->bpid[pfvf->queue_to_pfc_map[qidx]]; +#else aq->cq.bpid = pfvf->bpid[0]; +#endif /* Set backpressure level is same as cq pass level */ aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt); @@ -1211,7 +1223,11 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, */ if (pfvf->nix_blkaddr == BLKADDR_NIX1) aq->aura.bp_ena = 1; +#ifdef CONFIG_DCB + aq->aura.nix0_bpid = pfvf->bpid[pfvf->queue_to_pfc_map[aura_id]]; +#else aq->aura.nix0_bpid = pfvf->bpid[0]; +#endif /* Set backpressure level for RQ's Aura */ aq->aura.bp = RQ_BP_LVL_AURA; @@ -1538,11 +1554,18 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable) return -ENOMEM; req->chan_base = 0; - req->chan_cnt = 1; +#ifdef CONFIG_DCB + req->chan_cnt = pfvf->pfc_en ? IEEE_8021QAZ_MAX_TCS : 1; + req->bpid_per_chan = pfvf->pfc_en ? 1 : 0; +#else + req->chan_cnt = 1; req->bpid_per_chan = 0; +#endif + return otx2_sync_mbox_msg(&pfvf->mbox); } +EXPORT_SYMBOL(otx2_nix_config_bp); /* Mbox message handlers */ void mbox_handler_cgx_stats(struct otx2_nic *pfvf, @@ -1704,6 +1727,56 @@ out: } EXPORT_SYMBOL(otx2_get_max_mtu); +int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t features) +{ + netdev_features_t changed = features ^ netdev->features; + struct otx2_nic *pfvf = netdev_priv(netdev); + bool ntuple = !!(features & NETIF_F_NTUPLE); + bool tc = !!(features & NETIF_F_HW_TC); + + if ((changed & NETIF_F_NTUPLE) && !ntuple) + otx2_destroy_ntuple_flows(pfvf); + + if ((changed & NETIF_F_NTUPLE) && ntuple) { + if (!pfvf->flow_cfg->max_flows) { + netdev_err(netdev, + "Can't enable NTUPLE, MCAM entries not allocated\n"); + return -EINVAL; + } + } + + if ((changed & NETIF_F_HW_TC) && tc) { + if (!pfvf->flow_cfg->max_flows) { + netdev_err(netdev, + "Can't enable TC, MCAM entries not allocated\n"); + return -EINVAL; + } + } + + if ((changed & NETIF_F_HW_TC) && !tc && + pfvf->flow_cfg && pfvf->flow_cfg->nr_flows) { + netdev_err(netdev, "Can't disable TC hardware offload while flows are active\n"); + return -EBUSY; + } + + if ((changed & NETIF_F_NTUPLE) && ntuple && + (netdev->features & NETIF_F_HW_TC) && !(changed & NETIF_F_HW_TC)) { + netdev_err(netdev, + "Can't enable NTUPLE when TC is active, disable TC and retry\n"); + return -EINVAL; + } + + if ((changed & NETIF_F_HW_TC) && tc && + (netdev->features & NETIF_F_NTUPLE) && !(changed & NETIF_F_NTUPLE)) { + netdev_err(netdev, + "Can't enable TC when NTUPLE is active, disable NTUPLE and retry\n"); + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL(otx2_handle_ntuple_tc_features); + #define M(_name, _id, _fn_name, _req_type, _rsp_type) \ int __weak \ otx2_mbox_up_handler_ ## _fn_name(struct otx2_nic *pfvf, \ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 14509fc64cce..7724f17ec31f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -178,6 +178,9 @@ struct otx2_hw { u16 rqpool_cnt; u16 sqpool_cnt; +#define OTX2_DEFAULT_RBUF_LEN 2048 + u16 rbuf_len; + /* NPA */ u32 stack_pg_ptrs; /* No of ptrs per stack page */ u32 stack_pg_bytes; /* Size of stack page */ @@ -396,6 +399,11 @@ struct otx2_nic { /* Devlink */ struct otx2_devlink *dl; +#ifdef CONFIG_DCB + /* PFC */ + u8 pfc_en; + u8 *queue_to_pfc_map; +#endif }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) @@ -863,6 +871,8 @@ int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable); int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf); bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx); u16 otx2_get_max_mtu(struct otx2_nic *pfvf); +int otx2_handle_ntuple_tc_features(struct net_device *netdev, + netdev_features_t features); /* tc support */ int otx2_init_tc(struct otx2_nic *nic); void otx2_shutdown_tc(struct otx2_nic *nic); @@ -876,4 +886,11 @@ int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac, u8 bit_pos); int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos); void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf); void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf); + +#ifdef CONFIG_DCB +/* DCB support*/ +void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx, bool pfc_enable); +int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf); +int otx2_dcbnl_set_ops(struct net_device *dev); +#endif #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c new file mode 100644 index 000000000000..723d2506d309 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Ethernet driver + * + * Copyright (C) 2021 Marvell. + * + */ + +#include "otx2_common.h" + +int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf) +{ + struct cgx_pfc_cfg *req; + struct cgx_pfc_rsp *rsp; + int err = 0; + + if (is_otx2_lbkvf(pfvf->pdev)) + return 0; + + mutex_lock(&pfvf->mbox.lock); + req = otx2_mbox_alloc_msg_cgx_prio_flow_ctrl_cfg(&pfvf->mbox); + if (!req) { + err = -ENOMEM; + goto unlock; + } + + if (pfvf->pfc_en) { + req->rx_pause = true; + req->tx_pause = true; + } else { + req->rx_pause = false; + req->tx_pause = false; + } + req->pfc_en = pfvf->pfc_en; + + if (!otx2_sync_mbox_msg(&pfvf->mbox)) { + rsp = (struct cgx_pfc_rsp *) + otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr); + if (req->rx_pause != rsp->rx_pause || req->tx_pause != rsp->tx_pause) { + dev_warn(pfvf->dev, + "Failed to config PFC\n"); + err = -EPERM; + } + } +unlock: + mutex_unlock(&pfvf->mbox.lock); + return err; +} + +void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx, + bool pfc_enable) +{ + bool if_up = netif_running(pfvf->netdev); + struct npa_aq_enq_req *npa_aq; + struct nix_aq_enq_req *aq; + int err = 0; + + if (pfvf->queue_to_pfc_map[qidx] && pfc_enable) { + dev_warn(pfvf->dev, + "PFC enable not permitted as Priority %d already mapped to Queue %d\n", + pfvf->queue_to_pfc_map[qidx], qidx); + return; + } + + if (if_up) { + netif_tx_stop_all_queues(pfvf->netdev); + netif_carrier_off(pfvf->netdev); + } + + pfvf->queue_to_pfc_map[qidx] = vlan_prio; + + aq = otx2_mbox_alloc_msg_nix_aq_enq(&pfvf->mbox); + if (!aq) { + err = -ENOMEM; + goto out; + } + + aq->cq.bpid = pfvf->bpid[vlan_prio]; + aq->cq_mask.bpid = GENMASK(8, 0); + + /* Fill AQ info */ + aq->qidx = qidx; + aq->ctype = NIX_AQ_CTYPE_CQ; + aq->op = NIX_AQ_INSTOP_WRITE; + + otx2_sync_mbox_msg(&pfvf->mbox); + + npa_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox); + if (!npa_aq) { + err = -ENOMEM; + goto out; + } + npa_aq->aura.nix0_bpid = pfvf->bpid[vlan_prio]; + npa_aq->aura_mask.nix0_bpid = GENMASK(8, 0); + + /* Fill NPA AQ info */ + npa_aq->aura_id = qidx; + npa_aq->ctype = NPA_AQ_CTYPE_AURA; + npa_aq->op = NPA_AQ_INSTOP_WRITE; + otx2_sync_mbox_msg(&pfvf->mbox); + +out: + if (if_up) { + netif_carrier_on(pfvf->netdev); + netif_tx_start_all_queues(pfvf->netdev); + } + + if (err) + dev_warn(pfvf->dev, + "Updating BPIDs in CQ and Aura contexts of RQ%d failed with err %d\n", + qidx, err); +} + +static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) +{ + struct otx2_nic *pfvf = netdev_priv(dev); + + pfc->pfc_cap = IEEE_8021QAZ_MAX_TCS; + pfc->pfc_en = pfvf->pfc_en; + + return 0; +} + +static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) +{ + struct otx2_nic *pfvf = netdev_priv(dev); + int err; + + /* Save PFC configuration to interface */ + pfvf->pfc_en = pfc->pfc_en; + + err = otx2_config_priority_flow_ctrl(pfvf); + if (err) + return err; + + /* Request Per channel Bpids */ + if (pfc->pfc_en) + otx2_nix_config_bp(pfvf, true); + + return 0; +} + +static u8 otx2_dcbnl_getdcbx(struct net_device __always_unused *dev) +{ + return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; +} + +static u8 otx2_dcbnl_setdcbx(struct net_device __always_unused *dev, u8 mode) +{ + return (mode != (DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE)) ? 1 : 0; +} + +static const struct dcbnl_rtnl_ops otx2_dcbnl_ops = { + .ieee_getpfc = otx2_dcbnl_ieee_getpfc, + .ieee_setpfc = otx2_dcbnl_ieee_setpfc, + .getdcbx = otx2_dcbnl_getdcbx, + .setdcbx = otx2_dcbnl_setdcbx, +}; + +int otx2_dcbnl_set_ops(struct net_device *dev) +{ + struct otx2_nic *pfvf = netdev_priv(dev); + + pfvf->queue_to_pfc_map = devm_kzalloc(pfvf->dev, pfvf->hw.rx_queues, + GFP_KERNEL); + if (!pfvf->queue_to_pfc_map) + return -ENOMEM; + dev->dcbnl_ops = &otx2_dcbnl_ops; + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index d85db90632d6..abe5267210ef 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -371,6 +371,7 @@ static void otx2_get_ringparam(struct net_device *netdev, ring->rx_pending = qs->rqe_cnt ? qs->rqe_cnt : Q_COUNT(Q_SIZE_256); ring->tx_max_pending = Q_COUNT(Q_SIZE_MAX); ring->tx_pending = qs->sqe_cnt ? qs->sqe_cnt : Q_COUNT(Q_SIZE_4K); + kernel_ring->rx_buf_len = pfvf->hw.rbuf_len; } static int otx2_set_ringparam(struct net_device *netdev, @@ -379,6 +380,8 @@ static int otx2_set_ringparam(struct net_device *netdev, struct netlink_ext_ack *extack) { struct otx2_nic *pfvf = netdev_priv(netdev); + u32 rx_buf_len = kernel_ring->rx_buf_len; + u32 old_rx_buf_len = pfvf->hw.rbuf_len; bool if_up = netif_running(netdev); struct otx2_qset *qs = &pfvf->qset; u32 rx_count, tx_count; @@ -386,6 +389,15 @@ static int otx2_set_ringparam(struct net_device *netdev, if (ring->rx_mini_pending || ring->rx_jumbo_pending) return -EINVAL; + /* Hardware supports max size of 32k for a receive buffer + * and 1536 is typical ethernet frame size. + */ + if (rx_buf_len && (rx_buf_len < 1536 || rx_buf_len > 32768)) { + netdev_err(netdev, + "Receive buffer range is 1536 - 32768"); + return -EINVAL; + } + /* Permitted lengths are 16 64 256 1K 4K 16K 64K 256K 1M */ rx_count = ring->rx_pending; /* On some silicon variants a skid or reserved CQEs are @@ -403,7 +415,8 @@ static int otx2_set_ringparam(struct net_device *netdev, Q_COUNT(Q_SIZE_4K), Q_COUNT(Q_SIZE_MAX)); tx_count = Q_COUNT(Q_SIZE(tx_count, 3)); - if (tx_count == qs->sqe_cnt && rx_count == qs->rqe_cnt) + if (tx_count == qs->sqe_cnt && rx_count == qs->rqe_cnt && + rx_buf_len == old_rx_buf_len) return 0; if (if_up) @@ -413,6 +426,8 @@ static int otx2_set_ringparam(struct net_device *netdev, qs->sqe_cnt = tx_count; qs->rqe_cnt = rx_count; + pfvf->hw.rbuf_len = rx_buf_len; + if (if_up) return netdev->netdev_ops->ndo_open(netdev); @@ -1207,6 +1222,7 @@ end: static const struct ethtool_ops otx2_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, + .supported_ring_params = ETHTOOL_RING_USE_RX_BUF_LEN, .get_link = otx2_get_link, .get_drvinfo = otx2_get_drvinfo, .get_strings = otx2_get_strings, @@ -1326,6 +1342,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev, static const struct ethtool_ops otx2vf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, + .supported_ring_params = ETHTOOL_RING_USE_RX_BUF_LEN, .get_link = otx2_get_link, .get_drvinfo = otx2vf_get_drvinfo, .get_strings = otx2vf_get_strings, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 77a13fb555fb..54f235c216a9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -21,8 +21,10 @@ struct otx2_flow { u16 entry; bool is_vf; u8 rss_ctx_id; +#define DMAC_FILTER_RULE BIT(0) +#define PFC_FLOWCTRL_RULE BIT(1) + u16 rule_type; int vf; - bool dmac_filter; }; enum dmac_req { @@ -899,6 +901,9 @@ static int otx2_is_flow_rule_dmacfilter(struct otx2_nic *pfvf, static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow) { u64 ring_cookie = flow->flow_spec.ring_cookie; +#ifdef CONFIG_DCB + int vlan_prio, qidx, pfc_rule = 0; +#endif struct npc_install_flow_req *req; int err, vf = 0; @@ -940,6 +945,24 @@ static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow) mutex_unlock(&pfvf->mbox.lock); return -EINVAL; } + +#ifdef CONFIG_DCB + /* Identify PFC rule if PFC enabled and ntuple rule is vlan */ + if (!vf && (req->features & BIT_ULL(NPC_OUTER_VID)) && + pfvf->pfc_en && req->op != NIX_RX_ACTIONOP_RSS) { + vlan_prio = ntohs(req->packet.vlan_tci) & + ntohs(req->mask.vlan_tci); + + /* Get the priority */ + vlan_prio >>= 13; + flow->rule_type |= PFC_FLOWCTRL_RULE; + /* Check if PFC enabled for this priority */ + if (pfvf->pfc_en & BIT(vlan_prio)) { + pfc_rule = true; + qidx = req->index; + } + } +#endif } /* ethtool ring_cookie has (VF + 1) for VF */ @@ -951,6 +974,12 @@ static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow) /* Send message to AF */ err = otx2_sync_mbox_msg(&pfvf->mbox); + +#ifdef CONFIG_DCB + if (!err && pfc_rule) + otx2_update_bpid_in_rqctx(pfvf, vlan_prio, qidx, true); +#endif + mutex_unlock(&pfvf->mbox.lock); return err; } @@ -966,7 +995,7 @@ static int otx2_add_flow_with_pfmac(struct otx2_nic *pfvf, return -ENOMEM; pf_mac->entry = 0; - pf_mac->dmac_filter = true; + pf_mac->rule_type |= DMAC_FILTER_RULE; pf_mac->location = pfvf->flow_cfg->max_flows; memcpy(&pf_mac->flow_spec, &flow->flow_spec, sizeof(struct ethtool_rx_flow_spec)); @@ -1031,7 +1060,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) eth_hdr = &flow->flow_spec.h_u.ether_spec; /* Sync dmac filter table with updated fields */ - if (flow->dmac_filter) + if (flow->rule_type & DMAC_FILTER_RULE) return otx2_dmacflt_update(pfvf, eth_hdr->h_dest, flow->entry); @@ -1052,7 +1081,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (!test_bit(0, &flow_cfg->dmacflt_bmap)) otx2_add_flow_with_pfmac(pfvf, flow); - flow->dmac_filter = true; + flow->rule_type |= DMAC_FILTER_RULE; flow->entry = find_first_zero_bit(&flow_cfg->dmacflt_bmap, flow_cfg->dmacflt_max_flows); fsp->location = flow_cfg->max_flows + flow->entry; @@ -1120,7 +1149,7 @@ static void otx2_update_rem_pfmac(struct otx2_nic *pfvf, int req) bool found = false; list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) { - if (iter->dmac_filter && iter->entry == 0) { + if ((iter->rule_type & DMAC_FILTER_RULE) && iter->entry == 0) { eth_hdr = &iter->flow_spec.h_u.ether_spec; if (req == DMAC_ADDR_DEL) { otx2_dmacflt_remove(pfvf, eth_hdr->h_dest, @@ -1156,7 +1185,7 @@ int otx2_remove_flow(struct otx2_nic *pfvf, u32 location) if (!flow) return -ENOENT; - if (flow->dmac_filter) { + if (flow->rule_type & DMAC_FILTER_RULE) { struct ethhdr *eth_hdr = &flow->flow_spec.h_u.ether_spec; /* user not allowed to remove dmac filter with interface mac */ @@ -1174,6 +1203,13 @@ int otx2_remove_flow(struct otx2_nic *pfvf, u32 location) flow_cfg->dmacflt_max_flows) == 1) otx2_update_rem_pfmac(pfvf, DMAC_ADDR_DEL); } else { +#ifdef CONFIG_DCB + if (flow->rule_type & PFC_FLOWCTRL_RULE) + otx2_update_bpid_in_rqctx(pfvf, 0, + flow->flow_spec.ring_cookie, + false); +#endif + err = otx2_remove_flow_msg(pfvf, flow->entry, false); } @@ -1383,7 +1419,7 @@ void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf) struct ethhdr *eth_hdr; list_for_each_entry(iter, &pf->flow_cfg->flow_list, list) { - if (iter->dmac_filter) { + if (iter->rule_type & DMAC_FILTER_RULE) { eth_hdr = &iter->flow_spec.h_u.ether_spec; otx2_dmacflt_add(pf, eth_hdr->h_dest, iter->entry); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index d39341e4ab37..a5369167ab54 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1311,6 +1311,9 @@ static int otx2_get_rbuf_size(struct otx2_nic *pf, int mtu) int total_size; int rbuf_size; + if (pf->hw.rbuf_len) + return ALIGN(pf->hw.rbuf_len, OTX2_ALIGN) + OTX2_HEAD_ROOM; + /* The data transferred by NIX to memory consists of actual packet * plus additional data which has timestamp and/or EDSA/HIGIG2 * headers if interface is configured in corresponding modes. @@ -1694,9 +1697,6 @@ int otx2_open(struct net_device *netdev) if (pf->linfo.link_up && !(pf->pcifunc & RVU_PFVF_FUNC_MASK)) otx2_handle_link_event(pf); - /* Restore pause frame settings */ - otx2_config_pause_frm(pf); - /* Install DMAC Filters */ if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT) otx2_dmacflt_reinstall_flows(pf); @@ -1863,9 +1863,7 @@ static int otx2_set_features(struct net_device *netdev, netdev_features_t features) { netdev_features_t changed = features ^ netdev->features; - bool ntuple = !!(features & NETIF_F_NTUPLE); struct otx2_nic *pf = netdev_priv(netdev); - bool tc = !!(features & NETIF_F_HW_TC); if ((changed & NETIF_F_LOOPBACK) && netif_running(netdev)) return otx2_cgx_config_loopback(pf, @@ -1875,46 +1873,7 @@ static int otx2_set_features(struct net_device *netdev, return otx2_enable_rxvlan(pf, features & NETIF_F_HW_VLAN_CTAG_RX); - if ((changed & NETIF_F_NTUPLE) && !ntuple) - otx2_destroy_ntuple_flows(pf); - - if ((changed & NETIF_F_NTUPLE) && ntuple) { - if (!pf->flow_cfg->max_flows) { - netdev_err(netdev, - "Can't enable NTUPLE, MCAM entries not allocated\n"); - return -EINVAL; - } - } - - if ((changed & NETIF_F_HW_TC) && tc) { - if (!pf->flow_cfg->max_flows) { - netdev_err(netdev, - "Can't enable TC, MCAM entries not allocated\n"); - return -EINVAL; - } - } - - if ((changed & NETIF_F_HW_TC) && !tc && - pf->flow_cfg && pf->flow_cfg->nr_flows) { - netdev_err(netdev, "Can't disable TC hardware offload while flows are active\n"); - return -EBUSY; - } - - if ((changed & NETIF_F_NTUPLE) && ntuple && - (netdev->features & NETIF_F_HW_TC) && !(changed & NETIF_F_HW_TC)) { - netdev_err(netdev, - "Can't enable NTUPLE when TC is active, disable TC and retry\n"); - return -EINVAL; - } - - if ((changed & NETIF_F_HW_TC) && tc && - (netdev->features & NETIF_F_NTUPLE) && !(changed & NETIF_F_NTUPLE)) { - netdev_err(netdev, - "Can't enable TC when NTUPLE is active, disable NTUPLE and retry\n"); - return -EINVAL; - } - - return 0; + return otx2_handle_ntuple_tc_features(netdev, features); } static void otx2_reset_task(struct work_struct *work) @@ -2625,6 +2584,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->tx_queues = qcount; hw->tot_tx_queues = qcount; hw->max_queues = qcount; + hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN; num_vec = pci_msix_vec_count(pdev); hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, @@ -2778,9 +2738,11 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Enable link notifications */ otx2_cgx_config_linkevents(pf, true); - /* Enable pause frames by default */ - pf->flags |= OTX2_FLAG_RX_PAUSE_ENABLED; - pf->flags |= OTX2_FLAG_TX_PAUSE_ENABLED; +#ifdef CONFIG_DCB + err = otx2_dcbnl_set_ops(netdev); + if (err) + goto err_pf_sriov_init; +#endif return 0; @@ -2925,6 +2887,21 @@ static void otx2_remove(struct pci_dev *pdev) if (pf->flags & OTX2_FLAG_RX_TSTAMP_ENABLED) otx2_config_hw_rx_tstamp(pf, false); + /* Disable 802.3x pause frames */ + if (pf->flags & OTX2_FLAG_RX_PAUSE_ENABLED || + (pf->flags & OTX2_FLAG_TX_PAUSE_ENABLED)) { + pf->flags &= ~OTX2_FLAG_RX_PAUSE_ENABLED; + pf->flags &= ~OTX2_FLAG_TX_PAUSE_ENABLED; + otx2_config_pause_frm(pf); + } + +#ifdef CONFIG_DCB + /* Disable PFC config */ + if (pf->pfc_en) { + pf->pfc_en = 0; + otx2_config_priority_flow_ctrl(pf); + } +#endif cancel_work_sync(&pf->reset_task); /* Disable link notifications */ otx2_cgx_config_linkevents(pf, false); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 626961a41089..0593106d7161 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -58,7 +58,7 @@ int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic) { struct otx2_tc_info *tc = &nic->tc_info; - if (!nic->flow_cfg->max_flows || is_otx2_vf(nic->pcifunc)) + if (!nic->flow_cfg->max_flows) return 0; /* Max flows changed, free the existing bitmap */ @@ -1023,6 +1023,7 @@ int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type, return -EOPNOTSUPP; } } +EXPORT_SYMBOL(otx2_setup_tc); static const struct rhashtable_params tc_flow_ht_params = { .head_offset = offsetof(struct otx2_tc_flow, node), @@ -1052,6 +1053,7 @@ int otx2_init_tc(struct otx2_nic *nic) tc->flow_ht_params = tc_flow_ht_params; return rhashtable_init(&tc->flow_table, &tc->flow_ht_params); } +EXPORT_SYMBOL(otx2_init_tc); void otx2_shutdown_tc(struct otx2_nic *nic) { @@ -1060,3 +1062,4 @@ void otx2_shutdown_tc(struct otx2_nic *nic) kfree(tc->tc_entries_bitmap); rhashtable_destroy(&tc->flow_table); } +EXPORT_SYMBOL(otx2_shutdown_tc); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 925b74ebb8b0..a232e202f6a4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -472,23 +472,7 @@ static void otx2vf_reset_task(struct work_struct *work) static int otx2vf_set_features(struct net_device *netdev, netdev_features_t features) { - netdev_features_t changed = features ^ netdev->features; - bool ntuple_enabled = !!(features & NETIF_F_NTUPLE); - struct otx2_nic *vf = netdev_priv(netdev); - - if (changed & NETIF_F_NTUPLE) { - if (!ntuple_enabled) { - otx2_mcam_flow_del(vf); - return 0; - } - - if (!otx2_get_maxflows(vf->flow_cfg)) { - netdev_err(netdev, - "Can't enable NTUPLE, MCAM entries not allocated\n"); - return -EINVAL; - } - } - return 0; + return otx2_handle_ntuple_tc_features(netdev, features); } static const struct net_device_ops otx2vf_netdev_ops = { @@ -502,6 +486,7 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_get_stats64 = otx2_get_stats64, .ndo_tx_timeout = otx2_tx_timeout, .ndo_eth_ioctl = otx2_ioctl, + .ndo_setup_tc = otx2_setup_tc, }; static int otx2_wq_init(struct otx2_nic *vf) @@ -586,6 +571,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->tx_queues = qcount; hw->max_queues = qcount; hw->tot_tx_queues = qcount; + hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN; hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, GFP_KERNEL); @@ -662,6 +648,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->hw_features |= NETIF_F_NTUPLE; netdev->hw_features |= NETIF_F_RXALL; + netdev->hw_features |= NETIF_F_HW_TC; netif_set_gso_max_segs(netdev, OTX2_MAX_GSO_SEGS); netdev->watchdog_timeo = OTX2_TX_TIMEOUT; @@ -697,16 +684,24 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_unreg_netdev; - err = otx2_register_dl(vf); + err = otx2_init_tc(vf); if (err) goto err_unreg_netdev; - /* Enable pause frames by default */ - vf->flags |= OTX2_FLAG_RX_PAUSE_ENABLED; - vf->flags |= OTX2_FLAG_TX_PAUSE_ENABLED; + err = otx2_register_dl(vf); + if (err) + goto err_shutdown_tc; + +#ifdef CONFIG_DCB + err = otx2_dcbnl_set_ops(netdev); + if (err) + goto err_shutdown_tc; +#endif return 0; +err_shutdown_tc: + otx2_shutdown_tc(vf); err_unreg_netdev: unregister_netdev(netdev); err_ptp_destroy: @@ -739,6 +734,22 @@ static void otx2vf_remove(struct pci_dev *pdev) vf = netdev_priv(netdev); + /* Disable 802.3x pause frames */ + if (vf->flags & OTX2_FLAG_RX_PAUSE_ENABLED || + (vf->flags & OTX2_FLAG_TX_PAUSE_ENABLED)) { + vf->flags &= ~OTX2_FLAG_RX_PAUSE_ENABLED; + vf->flags &= ~OTX2_FLAG_TX_PAUSE_ENABLED; + otx2_config_pause_frm(vf); + } + +#ifdef CONFIG_DCB + /* Disable PFC config */ + if (vf->pfc_en) { + vf->pfc_en = 0; + otx2_config_priority_flow_ctrl(vf); + } +#endif + cancel_work_sync(&vf->reset_task); otx2_unregister_dl(vf); unregister_netdev(netdev); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.c b/drivers/net/ethernet/marvell/prestera/prestera_acl.c index f0d9f592173b..06303e31b32a 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_acl.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.c @@ -22,6 +22,7 @@ struct prestera_acl { struct prestera_acl_ruleset_ht_key { struct prestera_flow_block *block; + u32 chain_index; }; struct prestera_acl_rule_entry { @@ -34,6 +35,10 @@ struct prestera_acl_rule_entry { u8 valid:1; } accept, drop, trap; struct { + struct prestera_acl_action_jump i; + u8 valid:1; + } jump; + struct { u32 id; struct prestera_counter_block *block; } counter; @@ -49,6 +54,7 @@ struct prestera_acl_ruleset { refcount_t refcount; void *keymask; u32 vtcam_id; + u32 index; u16 pcl_id; bool offload; }; @@ -83,20 +89,45 @@ static const struct rhashtable_params __prestera_acl_rule_entry_ht_params = { .automatic_shrinking = true, }; +int prestera_acl_chain_to_client(u32 chain_index, u32 *client) +{ + u32 client_map[] = { + PRESTERA_HW_COUNTER_CLIENT_LOOKUP_0, + PRESTERA_HW_COUNTER_CLIENT_LOOKUP_1, + PRESTERA_HW_COUNTER_CLIENT_LOOKUP_2 + }; + + if (chain_index > ARRAY_SIZE(client_map)) + return -EINVAL; + + *client = client_map[chain_index]; + return 0; +} + +static bool prestera_acl_chain_is_supported(u32 chain_index) +{ + return (chain_index & ~PRESTERA_ACL_CHAIN_MASK) == 0; +} + static struct prestera_acl_ruleset * prestera_acl_ruleset_create(struct prestera_acl *acl, - struct prestera_flow_block *block) + struct prestera_flow_block *block, + u32 chain_index) { struct prestera_acl_ruleset *ruleset; u32 uid = 0; int err; + if (!prestera_acl_chain_is_supported(chain_index)) + return ERR_PTR(-EINVAL); + ruleset = kzalloc(sizeof(*ruleset), GFP_KERNEL); if (!ruleset) return ERR_PTR(-ENOMEM); ruleset->acl = acl; ruleset->ht_key.block = block; + ruleset->ht_key.chain_index = chain_index; refcount_set(&ruleset->refcount, 1); err = rhashtable_init(&ruleset->rule_ht, &prestera_acl_rule_ht_params); @@ -108,7 +139,9 @@ prestera_acl_ruleset_create(struct prestera_acl *acl, goto err_ruleset_create; /* make pcl-id based on uid */ - ruleset->pcl_id = (u8)uid; + ruleset->pcl_id = PRESTERA_ACL_PCL_ID_MAKE((u8)uid, chain_index); + ruleset->index = uid; + err = rhashtable_insert_fast(&acl->ruleset_ht, &ruleset->ht_node, prestera_acl_ruleset_ht_params); if (err) @@ -133,35 +166,64 @@ void prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset, int prestera_acl_ruleset_offload(struct prestera_acl_ruleset *ruleset) { + struct prestera_acl_iface iface; u32 vtcam_id; int err; if (ruleset->offload) return -EEXIST; - err = prestera_acl_vtcam_id_get(ruleset->acl, 0, + err = prestera_acl_vtcam_id_get(ruleset->acl, + ruleset->ht_key.chain_index, ruleset->keymask, &vtcam_id); if (err) - return err; + goto err_vtcam_create; + + if (ruleset->ht_key.chain_index) { + /* for chain > 0, bind iface index to pcl-id to be able + * to jump from any other ruleset to this one using the index. + */ + iface.index = ruleset->index; + iface.type = PRESTERA_ACL_IFACE_TYPE_INDEX; + err = prestera_hw_vtcam_iface_bind(ruleset->acl->sw, &iface, + vtcam_id, ruleset->pcl_id); + if (err) + goto err_ruleset_bind; + } ruleset->vtcam_id = vtcam_id; ruleset->offload = true; return 0; + +err_ruleset_bind: + prestera_acl_vtcam_id_put(ruleset->acl, ruleset->vtcam_id); +err_vtcam_create: + return err; } static void prestera_acl_ruleset_destroy(struct prestera_acl_ruleset *ruleset) { struct prestera_acl *acl = ruleset->acl; u8 uid = ruleset->pcl_id & PRESTERA_ACL_KEYMASK_PCL_ID_USER; + int err; rhashtable_remove_fast(&acl->ruleset_ht, &ruleset->ht_node, prestera_acl_ruleset_ht_params); - if (ruleset->offload) + if (ruleset->offload) { + if (ruleset->ht_key.chain_index) { + struct prestera_acl_iface iface = { + .type = PRESTERA_ACL_IFACE_TYPE_INDEX, + .index = ruleset->index + }; + err = prestera_hw_vtcam_iface_unbind(acl->sw, &iface, + ruleset->vtcam_id); + WARN_ON(err); + } WARN_ON(prestera_acl_vtcam_id_put(acl, ruleset->vtcam_id)); + } idr_remove(&acl->uid, uid); - rhashtable_destroy(&ruleset->rule_ht); kfree(ruleset->keymask); kfree(ruleset); @@ -169,23 +231,26 @@ static void prestera_acl_ruleset_destroy(struct prestera_acl_ruleset *ruleset) static struct prestera_acl_ruleset * __prestera_acl_ruleset_lookup(struct prestera_acl *acl, - struct prestera_flow_block *block) + struct prestera_flow_block *block, + u32 chain_index) { struct prestera_acl_ruleset_ht_key ht_key; memset(&ht_key, 0, sizeof(ht_key)); ht_key.block = block; + ht_key.chain_index = chain_index; return rhashtable_lookup_fast(&acl->ruleset_ht, &ht_key, prestera_acl_ruleset_ht_params); } struct prestera_acl_ruleset * prestera_acl_ruleset_lookup(struct prestera_acl *acl, - struct prestera_flow_block *block) + struct prestera_flow_block *block, + u32 chain_index) { struct prestera_acl_ruleset *ruleset; - ruleset = __prestera_acl_ruleset_lookup(acl, block); + ruleset = __prestera_acl_ruleset_lookup(acl, block, chain_index); if (!ruleset) return ERR_PTR(-ENOENT); @@ -195,17 +260,18 @@ prestera_acl_ruleset_lookup(struct prestera_acl *acl, struct prestera_acl_ruleset * prestera_acl_ruleset_get(struct prestera_acl *acl, - struct prestera_flow_block *block) + struct prestera_flow_block *block, + u32 chain_index) { struct prestera_acl_ruleset *ruleset; - ruleset = __prestera_acl_ruleset_lookup(acl, block); + ruleset = __prestera_acl_ruleset_lookup(acl, block, chain_index); if (ruleset) { refcount_inc(&ruleset->refcount); return ruleset; } - return prestera_acl_ruleset_create(acl, block); + return prestera_acl_ruleset_create(acl, block, chain_index); } void prestera_acl_ruleset_put(struct prestera_acl_ruleset *ruleset) @@ -293,6 +359,11 @@ prestera_acl_rule_lookup(struct prestera_acl_ruleset *ruleset, prestera_acl_rule_ht_params); } +u32 prestera_acl_ruleset_index_get(const struct prestera_acl_ruleset *ruleset) +{ + return ruleset->index; +} + bool prestera_acl_ruleset_is_offload(struct prestera_acl_ruleset *ruleset) { return ruleset->offload; @@ -300,7 +371,7 @@ bool prestera_acl_ruleset_is_offload(struct prestera_acl_ruleset *ruleset) struct prestera_acl_rule * prestera_acl_rule_create(struct prestera_acl_ruleset *ruleset, - unsigned long cookie) + unsigned long cookie, u32 chain_index) { struct prestera_acl_rule *rule; @@ -310,6 +381,7 @@ prestera_acl_rule_create(struct prestera_acl_ruleset *ruleset, rule->ruleset = ruleset; rule->cookie = cookie; + rule->chain_index = chain_index; refcount_inc(&ruleset->refcount); @@ -324,6 +396,10 @@ void prestera_acl_rule_priority_set(struct prestera_acl_rule *rule, void prestera_acl_rule_destroy(struct prestera_acl_rule *rule) { + if (rule->jump_ruleset) + /* release ruleset kept by jump action */ + prestera_acl_ruleset_put(rule->jump_ruleset); + prestera_acl_ruleset_put(rule->ruleset); kfree(rule); } @@ -347,7 +423,10 @@ int prestera_acl_rule_add(struct prestera_switch *sw, /* setup counter */ rule->re_arg.count.valid = true; - rule->re_arg.count.client = PRESTERA_HW_COUNTER_CLIENT_LOOKUP_0; + err = prestera_acl_chain_to_client(ruleset->ht_key.chain_index, + &rule->re_arg.count.client); + if (err) + goto err_rule_add; rule->re = prestera_acl_rule_entry_find(sw->acl, &rule->re_key); err = WARN_ON(rule->re) ? -EEXIST : 0; @@ -360,8 +439,10 @@ int prestera_acl_rule_add(struct prestera_switch *sw, if (err) goto err_rule_add; - /* bind the block (all ports) to chain index 0 */ - if (!ruleset->rule_count) { + /* bind the block (all ports) to chain index 0, rest of + * the chains are bound to goto action + */ + if (!ruleset->ht_key.chain_index && !ruleset->rule_count) { err = prestera_acl_ruleset_block_bind(ruleset, block); if (err) goto err_acl_block_bind; @@ -395,7 +476,7 @@ void prestera_acl_rule_del(struct prestera_switch *sw, prestera_acl_rule_entry_destroy(sw->acl, rule->re); /* unbind block (all ports) */ - if (!ruleset->rule_count) + if (!ruleset->ht_key.chain_index && !ruleset->rule_count) prestera_acl_ruleset_block_unbind(ruleset, block); } @@ -459,6 +540,12 @@ static int __prestera_acl_rule_entry2hw_add(struct prestera_switch *sw, act_hw[act_num].id = PRESTERA_ACL_RULE_ACTION_TRAP; act_num++; } + /* jump */ + if (e->jump.valid) { + act_hw[act_num].id = PRESTERA_ACL_RULE_ACTION_JUMP; + act_hw[act_num].jump = e->jump.i; + act_num++; + } /* counter */ if (e->counter.block) { act_hw[act_num].id = PRESTERA_ACL_RULE_ACTION_COUNT; @@ -505,6 +592,9 @@ __prestera_acl_rule_entry_act_construct(struct prestera_switch *sw, e->drop.valid = arg->drop.valid; /* trap */ e->trap.valid = arg->trap.valid; + /* jump */ + e->jump.valid = arg->jump.valid; + e->jump.i = arg->jump.i; /* counter */ if (arg->count.valid) { int err; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.h b/drivers/net/ethernet/marvell/prestera/prestera_acl.h index 40f6c1d961fa..6d2ad27682d1 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_acl.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.h @@ -10,6 +10,14 @@ #define PRESTERA_ACL_KEYMASK_PCL_ID 0x3FF #define PRESTERA_ACL_KEYMASK_PCL_ID_USER \ (PRESTERA_ACL_KEYMASK_PCL_ID & 0x00FF) +#define PRESTERA_ACL_KEYMASK_PCL_ID_CHAIN \ + (PRESTERA_ACL_KEYMASK_PCL_ID & 0xFF00) +#define PRESTERA_ACL_CHAIN_MASK \ + (PRESTERA_ACL_KEYMASK_PCL_ID >> 8) + +#define PRESTERA_ACL_PCL_ID_MAKE(uid, chain_id) \ + (((uid) & PRESTERA_ACL_KEYMASK_PCL_ID_USER) | \ + (((chain_id) << 8) & PRESTERA_ACL_KEYMASK_PCL_ID_CHAIN)) #define rule_match_set_n(match_p, type, val_p, size) \ memcpy(&(match_p)[PRESTERA_ACL_RULE_MATCH_TYPE_##type], \ @@ -46,6 +54,7 @@ enum prestera_acl_rule_action { PRESTERA_ACL_RULE_ACTION_ACCEPT = 0, PRESTERA_ACL_RULE_ACTION_DROP = 1, PRESTERA_ACL_RULE_ACTION_TRAP = 2, + PRESTERA_ACL_RULE_ACTION_JUMP = 5, PRESTERA_ACL_RULE_ACTION_COUNT = 7, PRESTERA_ACL_RULE_ACTION_MAX @@ -61,6 +70,10 @@ struct prestera_acl_match { __be32 mask[__PRESTERA_ACL_RULE_MATCH_TYPE_MAX]; }; +struct prestera_acl_action_jump { + u32 index; +}; + struct prestera_acl_action_count { u32 id; }; @@ -74,6 +87,7 @@ struct prestera_acl_hw_action_info { enum prestera_acl_rule_action id; union { struct prestera_acl_action_count count; + struct prestera_acl_action_jump jump; }; }; @@ -88,6 +102,10 @@ struct prestera_acl_rule_entry_arg { u8 valid:1; } accept, drop, trap; struct { + struct prestera_acl_action_jump i; + u8 valid:1; + } jump; + struct { u8 valid:1; u32 client; } count; @@ -98,7 +116,9 @@ struct prestera_acl_rule { struct rhash_head ht_node; /* Member of acl HT */ struct list_head list; struct prestera_acl_ruleset *ruleset; + struct prestera_acl_ruleset *jump_ruleset; unsigned long cookie; + u32 chain_index; u32 priority; struct prestera_acl_rule_entry_key re_key; struct prestera_acl_rule_entry_arg re_arg; @@ -122,7 +142,7 @@ void prestera_acl_fini(struct prestera_switch *sw); struct prestera_acl_rule * prestera_acl_rule_create(struct prestera_acl_ruleset *ruleset, - unsigned long cookie); + unsigned long cookie, u32 chain_index); void prestera_acl_rule_priority_set(struct prestera_acl_rule *rule, u32 priority); void prestera_acl_rule_destroy(struct prestera_acl_rule *rule); @@ -147,10 +167,12 @@ prestera_acl_rule_entry_create(struct prestera_acl *acl, struct prestera_acl_rule_entry_arg *arg); struct prestera_acl_ruleset * prestera_acl_ruleset_get(struct prestera_acl *acl, - struct prestera_flow_block *block); + struct prestera_flow_block *block, + u32 chain_index); struct prestera_acl_ruleset * prestera_acl_ruleset_lookup(struct prestera_acl *acl, - struct prestera_flow_block *block); + struct prestera_flow_block *block, + u32 chain_index); void prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset, void *keymask); bool prestera_acl_ruleset_is_offload(struct prestera_acl_ruleset *ruleset); @@ -160,6 +182,7 @@ int prestera_acl_ruleset_bind(struct prestera_acl_ruleset *ruleset, struct prestera_port *port); int prestera_acl_ruleset_unbind(struct prestera_acl_ruleset *ruleset, struct prestera_port *port); +u32 prestera_acl_ruleset_index_get(const struct prestera_acl_ruleset *ruleset); void prestera_acl_rule_keymask_pcl_id_set(struct prestera_acl_rule *rule, u16 pcl_id); @@ -167,5 +190,6 @@ prestera_acl_rule_keymask_pcl_id_set(struct prestera_acl_rule *rule, int prestera_acl_vtcam_id_get(struct prestera_acl *acl, u8 lookup, void *keymask, u32 *vtcam_id); int prestera_acl_vtcam_id_put(struct prestera_acl *acl, u32 vtcam_id); +int prestera_acl_chain_to_client(u32 chain_index, u32 *client); #endif /* _PRESTERA_ACL_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.c b/drivers/net/ethernet/marvell/prestera/prestera_flow.c index d849f046ece7..05c3ad98eba9 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flow.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.c @@ -29,9 +29,6 @@ static int prestera_flow_block_mall_cb(struct prestera_flow_block *block, static int prestera_flow_block_flower_cb(struct prestera_flow_block *block, struct flow_cls_offload *f) { - if (f->common.chain_index != 0) - return -EOPNOTSUPP; - switch (f->command) { case FLOW_CLS_REPLACE: return prestera_flower_replace(block, f); @@ -71,6 +68,7 @@ static void prestera_flow_block_destroy(void *cb_priv) prestera_flower_template_cleanup(block); + WARN_ON(!list_empty(&block->template_list)); WARN_ON(!list_empty(&block->binding_list)); kfree(block); @@ -86,6 +84,7 @@ prestera_flow_block_create(struct prestera_switch *sw, struct net *net) return NULL; INIT_LIST_HEAD(&block->binding_list); + INIT_LIST_HEAD(&block->template_list); block->net = net; block->sw = sw; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.h b/drivers/net/ethernet/marvell/prestera/prestera_flow.h index 1ea5b745bf72..6550278b166a 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flow.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.h @@ -8,7 +8,6 @@ struct prestera_port; struct prestera_switch; -struct prestera_flower_template; struct prestera_flow_block_binding { struct list_head list; @@ -22,7 +21,7 @@ struct prestera_flow_block { struct net *net; struct prestera_acl_ruleset *ruleset_zero; struct flow_block_cb *block_cb; - struct prestera_flower_template *tmplt; + struct list_head template_list; unsigned int rule_count; }; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c index 19c1417fd05f..580fb986496a 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flower.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c @@ -8,26 +8,60 @@ struct prestera_flower_template { struct prestera_acl_ruleset *ruleset; + struct list_head list; + u32 chain_index; }; void prestera_flower_template_cleanup(struct prestera_flow_block *block) { - if (block->tmplt) { - /* put the reference to the ruleset kept in create */ - prestera_acl_ruleset_put(block->tmplt->ruleset); - kfree(block->tmplt); - block->tmplt = NULL; - return; + struct prestera_flower_template *template; + struct list_head *pos, *n; + + /* put the reference to all rulesets kept in tmpl create */ + list_for_each_safe(pos, n, &block->template_list) { + template = list_entry(pos, typeof(*template), list); + prestera_acl_ruleset_put(template->ruleset); + list_del(&template->list); + kfree(template); } } +static int +prestera_flower_parse_goto_action(struct prestera_flow_block *block, + struct prestera_acl_rule *rule, + u32 chain_index, + const struct flow_action_entry *act) +{ + struct prestera_acl_ruleset *ruleset; + + if (act->chain_index <= chain_index) + /* we can jump only forward */ + return -EINVAL; + + if (rule->re_arg.jump.valid) + return -EEXIST; + + ruleset = prestera_acl_ruleset_get(block->sw->acl, block, + act->chain_index); + if (IS_ERR(ruleset)) + return PTR_ERR(ruleset); + + rule->re_arg.jump.valid = 1; + rule->re_arg.jump.i.index = prestera_acl_ruleset_index_get(ruleset); + + rule->jump_ruleset = ruleset; + + return 0; +} + static int prestera_flower_parse_actions(struct prestera_flow_block *block, struct prestera_acl_rule *rule, struct flow_action *flow_action, + u32 chain_index, struct netlink_ext_ack *extack) { const struct flow_action_entry *act; - int i; + int err, i; /* whole struct (rule->re_arg) must be initialized with 0 */ if (!flow_action_has_entries(flow_action)) @@ -53,6 +87,13 @@ static int prestera_flower_parse_actions(struct prestera_flow_block *block, rule->re_arg.trap.valid = 1; break; + case FLOW_ACTION_GOTO: + err = prestera_flower_parse_goto_action(block, rule, + chain_index, + act); + if (err) + return err; + break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported action"); pr_err("Unsupported action\n"); @@ -259,6 +300,7 @@ static int prestera_flower_parse(struct prestera_flow_block *block, } return prestera_flower_parse_actions(block, rule, &f->rule->action, + f->common.chain_index, f->common.extack); } @@ -270,12 +312,13 @@ int prestera_flower_replace(struct prestera_flow_block *block, struct prestera_acl_rule *rule; int err; - ruleset = prestera_acl_ruleset_get(acl, block); + ruleset = prestera_acl_ruleset_get(acl, block, f->common.chain_index); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); /* increments the ruleset reference */ - rule = prestera_acl_rule_create(ruleset, f->cookie); + rule = prestera_acl_rule_create(ruleset, f->cookie, + f->common.chain_index); if (IS_ERR(rule)) { err = PTR_ERR(rule); goto err_rule_create; @@ -312,7 +355,8 @@ void prestera_flower_destroy(struct prestera_flow_block *block, struct prestera_acl_ruleset *ruleset; struct prestera_acl_rule *rule; - ruleset = prestera_acl_ruleset_lookup(block->sw->acl, block); + ruleset = prestera_acl_ruleset_lookup(block->sw->acl, block, + f->common.chain_index); if (IS_ERR(ruleset)) return; @@ -345,7 +389,8 @@ int prestera_flower_tmplt_create(struct prestera_flow_block *block, } prestera_acl_rule_keymask_pcl_id_set(&rule, 0); - ruleset = prestera_acl_ruleset_get(block->sw->acl, block); + ruleset = prestera_acl_ruleset_get(block->sw->acl, block, + f->common.chain_index); if (IS_ERR_OR_NULL(ruleset)) { err = -EINVAL; goto err_ruleset_get; @@ -364,7 +409,8 @@ int prestera_flower_tmplt_create(struct prestera_flow_block *block, /* keep the reference to the ruleset */ template->ruleset = ruleset; - block->tmplt = template; + template->chain_index = f->common.chain_index; + list_add_rcu(&template->list, &block->template_list); return 0; err_ruleset_get: @@ -390,7 +436,8 @@ int prestera_flower_stats(struct prestera_flow_block *block, u64 bytes; int err; - ruleset = prestera_acl_ruleset_lookup(block->sw->acl, block); + ruleset = prestera_acl_ruleset_lookup(block->sw->acl, block, + f->common.chain_index); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.h b/drivers/net/ethernet/marvell/prestera/prestera_flower.h index dc3aa4280e9f..495f151e6fa9 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flower.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.h @@ -6,7 +6,6 @@ #include <net/pkt_cls.h> -struct prestera_switch; struct prestera_flow_block; int prestera_flower_replace(struct prestera_flow_block *block, diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_hw.c index e6bfadc874c5..d4c0f0577b26 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_hw.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.c @@ -424,6 +424,9 @@ struct prestera_msg_acl_action { __le32 __reserved; union { struct { + __le32 index; + } jump; + struct { __le32 id; } count; __le32 reserved[6]; @@ -1164,6 +1167,9 @@ prestera_acl_rule_add_put_action(struct prestera_msg_acl_action *action, case PRESTERA_ACL_RULE_ACTION_TRAP: /* just rule action id, no specific data */ break; + case PRESTERA_ACL_RULE_ACTION_JUMP: + action->jump.index = __cpu_to_le32(info->jump.index); + break; case PRESTERA_ACL_RULE_ACTION_COUNT: action->count.id = __cpu_to_le32(info->count.id); break; diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 89ca7960b225..4cd0747edaff 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -1556,6 +1556,7 @@ static int mtk_star_probe(struct platform_device *pdev) return devm_register_netdev(dev, ndev); } +#ifdef CONFIG_OF static const struct of_device_id mtk_star_of_match[] = { { .compatible = "mediatek,mt8516-eth", }, { .compatible = "mediatek,mt8518-eth", }, @@ -1563,6 +1564,7 @@ static const struct of_device_id mtk_star_of_match[] = { { } }; MODULE_DEVICE_TABLE(of, mtk_star_of_match); +#endif static SIMPLE_DEV_PM_OPS(mtk_star_pm_ops, mtk_star_suspend, mtk_star_resume); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index fcfd38fa9e6c..a7170ab3af97 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -28,7 +28,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \ en_selftest.o en/port.o en/monitor_stats.o en/health.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \ - en/qos.o en/trap.o en/fs_tt_redirect.o + en/qos.o en/trap.o en/fs_tt_redirect.o en/selq.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index c14e06ca64d8..2704c7537481 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -59,6 +59,7 @@ #include "lib/hv_vhca.h" #include "lib/clock.h" #include "en/rx_res.h" +#include "en/selq.h" extern const struct net_device_ops mlx5e_netdev_ops; struct page_pool; @@ -172,8 +173,9 @@ struct page_pool; #define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\ ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT) -#define MLX5E_MAX_KLM_PER_WQE \ - MLX5E_KLM_ENTRIES_PER_WQE(MLX5E_TX_MPW_MAX_NUM_DS << MLX5_MKEY_BSF_OCTO_SIZE) +#define MLX5E_MAX_KLM_PER_WQE(mdev) \ + MLX5E_KLM_ENTRIES_PER_WQE(mlx5e_get_sw_max_sq_mpw_wqebbs(mlx5e_get_max_sq_wqebbs(mdev)) \ + << MLX5_MKEY_BSF_OCTO_SIZE) #define MLX5E_MSG_LEVEL NETIF_MSG_LINK @@ -221,6 +223,32 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS); } +/* The maximum WQE size can be retrieved by max_wqe_sz_sq in + * bytes units. Driver hardens the limitation to 1KB (16 + * WQEBBs), unless firmware capability is stricter. + */ +static inline u16 mlx5e_get_max_sq_wqebbs(struct mlx5_core_dev *mdev) +{ + return min_t(u16, MLX5_SEND_WQE_MAX_WQEBBS, + MLX5_CAP_GEN(mdev, max_wqe_sz_sq) / MLX5_SEND_WQE_BB); +} + +static inline u16 mlx5e_get_sw_max_sq_mpw_wqebbs(u16 max_sq_wqebbs) +{ +/* The return value will be multiplied by MLX5_SEND_WQEBB_NUM_DS. + * Since max_sq_wqebbs may be up to MLX5_SEND_WQE_MAX_WQEBBS == 16, + * see mlx5e_get_max_sq_wqebbs(), the multiplication (16 * 4 == 64) + * overflows the 6-bit DS field of Ctrl Segment. Use a bound lower + * than MLX5_SEND_WQE_MAX_WQEBBS to let a full-session WQE be + * cache-aligned. + */ +#if L1_CACHE_BYTES < 128 + return min_t(u16, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 1); +#else + return min_t(u16, max_sq_wqebbs, MLX5_SEND_WQE_MAX_WQEBBS - 2); +#endif +} + struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; @@ -427,12 +455,12 @@ struct mlx5e_txqsq { struct netdev_queue *txq; u32 sqn; u16 stop_room; + u16 max_sq_mpw_wqebbs; u8 min_inline_mode; struct device *pdev; __be32 mkey_be; unsigned long state; unsigned int hw_mtu; - struct hwtstamp_config *tstamp; struct mlx5_clock *clock; struct net_device *netdev; struct mlx5_core_dev *mdev; @@ -446,6 +474,7 @@ struct mlx5e_txqsq { struct work_struct recover_work; struct mlx5e_ptpsq *ptpsq; cqe_ts_to_ns ptp_cyc2time; + u16 max_sq_wqebbs; } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { @@ -540,6 +569,8 @@ struct mlx5e_xdpsq { u32 sqn; struct device *pdev; __be32 mkey_be; + u16 stop_room; + u16 max_sq_mpw_wqebbs; u8 min_inline_mode; unsigned long state; unsigned int hw_mtu; @@ -547,6 +578,7 @@ struct mlx5e_xdpsq { /* control path */ struct mlx5_wq_ctrl wq_ctrl; struct mlx5e_channel *channel; + u16 max_sq_wqebbs; } ____cacheline_aligned_in_smp; struct mlx5e_ktls_resync_resp; @@ -575,6 +607,7 @@ struct mlx5e_icosq { /* control path */ struct mlx5_wq_ctrl wq_ctrl; struct mlx5e_channel *channel; + u16 max_sq_wqebbs; struct work_struct recover_work; } ____cacheline_aligned_in_smp; @@ -681,6 +714,7 @@ struct mlx5e_rq { u8 umr_in_progress; u8 umr_last_bulk; u8 umr_completed; + u8 min_wqe_bulk; struct mlx5e_shampo_hd *shampo; } mpwqe; }; @@ -876,9 +910,8 @@ struct mlx5e_trap; struct mlx5e_priv { /* priv data path fields - start */ + struct mlx5e_selq selq; struct mlx5e_txqsq **txq2sq; - int **channel_tc2realtxq; - int port_ptp_tc2realtxq[MLX5E_MAX_NUM_TC]; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx_dp dcbx_dp; #endif @@ -921,7 +954,6 @@ struct mlx5e_priv { u16 drop_rq_q_counter; struct notifier_block events_nb; struct notifier_block blocking_events_nb; - int num_tc_x_num_ch; struct udp_tunnel_nic_info nic_info; #ifdef CONFIG_MLX5_CORE_EN_DCB diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 66180ffb4606..0bd8698f7226 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -178,6 +178,12 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); } +u8 mlx5e_mpwqe_get_min_wqe_bulk(unsigned int wq_sz) +{ +#define UMR_WQE_BULK (2) + return min_t(unsigned int, UMR_WQE_BULK, wq_sz / 2 - 1); +} + u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) @@ -196,13 +202,13 @@ u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *par u16 stop_room; stop_room = mlx5e_tls_get_stop_room(mdev, params); - stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + stop_room += mlx5e_stop_room_for_max_wqe(mdev); if (is_mpwqe) /* A MPWQE can take up to the maximum-sized WQE + all the normal * stop room can be taken if a new packet breaks the active * MPWQE session and allocates its WQEs right away. */ - stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + stop_room += mlx5e_stop_room_for_max_wqe(mdev); return stop_room; } @@ -359,12 +365,13 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, { /* Prefer Striding RQ, unless any of the following holds: * - Striding RQ configuration is not possible/supported. - * - Slow PCI heuristic. + * - CQE compression is ON, and stride_index mini_cqe layout is not supported. * - Legacy RQ would use linear SKB while Striding RQ would use non-linear. * * No XSK params: checking the availability of striding RQ in general. */ - if (!slow_pci_heuristic(mdev) && + if ((!MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) || + MLX5_CAP_GEN(mdev, mini_cqe_resp_stride_index)) && mlx5e_striding_rq_possible(mdev, params) && (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) || !mlx5e_rx_is_linear_skb(params, NULL))) @@ -717,7 +724,7 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev, int wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); u32 wqebbs; - max_klm_per_umr = MLX5E_MAX_KLM_PER_WQE; + max_klm_per_umr = MLX5E_MAX_KLM_PER_WQE(mdev); max_hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rq_param); max_num_of_umr_per_wqe = max_hd_per_wqe / max_klm_per_umr; rest = max_hd_per_wqe % max_klm_per_umr; @@ -774,10 +781,10 @@ static void mlx5e_build_async_icosq_param(struct mlx5_core_dev *mdev, void *wq = MLX5_ADDR_OF(sqc, sqc, wq); mlx5e_build_sq_param_common(mdev, param); - param->stop_room = mlx5e_stop_room_for_wqe(1); /* for XSK NOP */ + param->stop_room = mlx5e_stop_room_for_wqe(mdev, 1); /* for XSK NOP */ param->is_tls = mlx5e_accel_is_ktls_rx(mdev); if (param->is_tls) - param->stop_room += mlx5e_stop_room_for_wqe(1); /* for TLS RX resync NOP */ + param->stop_room += mlx5e_stop_room_for_wqe(mdev, 1); /* for TLS RX resync NOP */ MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(mdev, reg_umr_sq)); MLX5_SET(wq, wq, log_wq_sz, log_wq_size); mlx5e_build_ico_cq_param(mdev, log_wq_size, ¶m->cqp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 433e6967692d..47a368112e31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -129,6 +129,7 @@ u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); +u8 mlx5e_mpwqe_get_min_wqe_bulk(unsigned int wq_sz); u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 82baafd3c00c..335b20b6383b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -195,7 +195,6 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix, int node; sq->pdev = c->pdev; - sq->tstamp = c->tstamp; sq->clock = &mdev->clock; sq->mkey_be = c->mkey_be; sq->netdev = c->netdev; @@ -449,7 +448,7 @@ static void mlx5e_ptp_build_sq_param(struct mlx5_core_dev *mdev, wq = MLX5_ADDR_OF(sqc, sqc, wq); MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size); - param->stop_room = mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + param->stop_room = mlx5e_stop_room_for_max_wqe(mdev); mlx5e_build_tx_cq_param(mdev, params, ¶m->cqp); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index c1e07496c89c..9db677e9ca9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -50,7 +50,6 @@ static int mlx5e_find_unused_qos_qid(struct mlx5e_priv *priv) struct mlx5e_qos_node { struct hlist_node hnode; - struct rcu_head rcu; struct mlx5e_qos_node *parent; u64 rate; u32 bw_share; @@ -132,7 +131,11 @@ static void mlx5e_sw_node_delete(struct mlx5e_priv *priv, struct mlx5e_qos_node __clear_bit(node->qid, priv->htb.qos_used_qids); mlx5e_update_tx_netdev_queues(priv); } - kfree_rcu(node, rcu); + /* Make sure this qid is no longer selected by mlx5e_select_queue, so + * that mlx5e_reactivate_qos_sq can safely restart the netdev TX queue. + */ + synchronize_net(); + kfree(node); } /* TX datapath API */ @@ -273,10 +276,18 @@ err_free_sq: static void mlx5e_activate_qos_sq(struct mlx5e_priv *priv, struct mlx5e_qos_node *node) { struct mlx5e_txqsq *sq; + u16 qid; sq = mlx5e_get_qos_sq(priv, node->qid); - WRITE_ONCE(priv->txq2sq[mlx5e_qid_from_qos(&priv->channels, node->qid)], sq); + qid = mlx5e_qid_from_qos(&priv->channels, node->qid); + + /* If it's a new queue, it will be marked as started at this point. + * Stop it before updating txq2sq. + */ + mlx5e_tx_disable_queue(netdev_get_tx_queue(priv->netdev, qid)); + + priv->txq2sq[qid] = sq; /* Make the change to txq2sq visible before the queue is started. * As mlx5e_xmit runs under a spinlock, there is an implicit ACQUIRE, @@ -299,8 +310,13 @@ static void mlx5e_deactivate_qos_sq(struct mlx5e_priv *priv, u16 qid) qos_dbg(priv->mdev, "Deactivate QoS SQ qid %u\n", qid); mlx5e_deactivate_txqsq(sq); - /* The queue is disabled, no synchronization with datapath is needed. */ priv->txq2sq[mlx5e_qid_from_qos(&priv->channels, qid)] = NULL; + + /* Make the change to txq2sq visible before the queue is started again. + * As mlx5e_xmit runs under a spinlock, there is an implicit ACQUIRE, + * which pairs with this barrier. + */ + smp_wmb(); } static void mlx5e_close_qos_sq(struct mlx5e_priv *priv, u16 qid) @@ -485,9 +501,11 @@ int mlx5e_htb_root_add(struct mlx5e_priv *priv, u16 htb_maj_id, u16 htb_defcls, opened = test_bit(MLX5E_STATE_OPENED, &priv->state); if (opened) { + mlx5e_selq_prepare(&priv->selq, &priv->channels.params, true); + err = mlx5e_qos_alloc_queues(priv, &priv->channels); if (err) - return err; + goto err_cancel_selq; } root = mlx5e_sw_node_create_root(priv); @@ -508,6 +526,9 @@ int mlx5e_htb_root_add(struct mlx5e_priv *priv, u16 htb_maj_id, u16 htb_defcls, */ smp_store_release(&priv->htb.maj_id, htb_maj_id); + if (opened) + mlx5e_selq_apply(&priv->selq); + return 0; err_sw_node_delete: @@ -516,6 +537,8 @@ err_sw_node_delete: err_free_queues: if (opened) mlx5e_qos_close_all_queues(&priv->channels); +err_cancel_selq: + mlx5e_selq_cancel(&priv->selq); return err; } @@ -526,8 +549,15 @@ int mlx5e_htb_root_del(struct mlx5e_priv *priv) qos_dbg(priv->mdev, "TC_HTB_DESTROY\n"); + /* Wait until real_num_tx_queues is updated for mlx5e_select_queue, + * so that we can safely switch to its non-HTB non-PTP fastpath. + */ + synchronize_net(); + + mlx5e_selq_prepare(&priv->selq, &priv->channels.params, false); + mlx5e_selq_apply(&priv->selq); + WRITE_ONCE(priv->htb.maj_id, 0); - synchronize_rcu(); /* Sync with mlx5e_select_htb_queue and TX data path. */ root = mlx5e_sw_node_find(priv, MLX5E_HTB_CLASSID_ROOT); if (!root) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 0991345c4ae5..86fa0bdbee36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -263,14 +263,14 @@ int mlx5e_rep_tc_init(struct mlx5e_rep_priv *rpriv) INIT_LIST_HEAD(&uplink_priv->unready_flows); /* init shared tc flow table */ - err = mlx5e_tc_esw_init(&uplink_priv->tc_ht); + err = mlx5e_tc_esw_init(uplink_priv); return err; } void mlx5e_rep_tc_cleanup(struct mlx5e_rep_priv *rpriv) { /* delete shared tc flow table */ - mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht); + mlx5e_tc_esw_cleanup(&rpriv->uplink_priv); mutex_destroy(&rpriv->uplink_priv.unready_flows_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index c1cdd8c2e37a..7f93426b88b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -442,7 +442,7 @@ int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, goto inner_tir; err = mlx5e_tir_modify(tir, builder); if (err) { - mlx5e_rss_warn(rss->mdev, "Failed to update LRO state of indirect TIR %#x for traffic type %d: err = %d\n", + mlx5e_rss_warn(rss->mdev, "Failed to update packet merge state of indirect TIR %#x for traffic type %d: err = %d\n", mlx5e_tir_get_tirn(tir), tt, err); if (!final_err) final_err = err; @@ -457,7 +457,7 @@ inner_tir: continue; err = mlx5e_tir_modify(tir, builder); if (err) { - mlx5e_rss_warn(rss->mdev, "Failed to update LRO state of inner indirect TIR %#x for traffic type %d: err = %d\n", + mlx5e_rss_warn(rss->mdev, "Failed to update packet merge state of inner indirect TIR %#x for traffic type %d: err = %d\n", mlx5e_tir_get_tirn(tir), tt, err); if (!final_err) final_err = err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c new file mode 100644 index 000000000000..d98a277eb7f8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "selq.h" +#include <linux/slab.h> +#include <linux/netdevice.h> +#include <linux/rcupdate.h> +#include "en.h" +#include "en/ptp.h" + +struct mlx5e_selq_params { + unsigned int num_regular_queues; + unsigned int num_channels; + unsigned int num_tcs; + union { + u8 is_special_queues; + struct { + bool is_htb : 1; + bool is_ptp : 1; + }; + }; +}; + +int mlx5e_selq_init(struct mlx5e_selq *selq, struct mutex *state_lock) +{ + struct mlx5e_selq_params *init_params; + + selq->state_lock = state_lock; + + selq->standby = kvzalloc(sizeof(*selq->standby), GFP_KERNEL); + if (!selq->standby) + return -ENOMEM; + + init_params = kvzalloc(sizeof(*selq->active), GFP_KERNEL); + if (!init_params) { + kvfree(selq->standby); + selq->standby = NULL; + return -ENOMEM; + } + /* Assign dummy values, so that mlx5e_select_queue won't crash. */ + *init_params = (struct mlx5e_selq_params) { + .num_regular_queues = 1, + .num_channels = 1, + .num_tcs = 1, + .is_htb = false, + .is_ptp = false, + }; + rcu_assign_pointer(selq->active, init_params); + + return 0; +} + +void mlx5e_selq_cleanup(struct mlx5e_selq *selq) +{ + WARN_ON_ONCE(selq->is_prepared); + + kvfree(selq->standby); + selq->standby = NULL; + selq->is_prepared = true; + + mlx5e_selq_apply(selq); + + kvfree(selq->standby); + selq->standby = NULL; +} + +void mlx5e_selq_prepare(struct mlx5e_selq *selq, struct mlx5e_params *params, bool htb) +{ + lockdep_assert_held(selq->state_lock); + WARN_ON_ONCE(selq->is_prepared); + + selq->is_prepared = true; + + selq->standby->num_channels = params->num_channels; + selq->standby->num_tcs = mlx5e_get_dcb_num_tc(params); + selq->standby->num_regular_queues = + selq->standby->num_channels * selq->standby->num_tcs; + selq->standby->is_htb = htb; + selq->standby->is_ptp = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_TX_PORT_TS); +} + +void mlx5e_selq_apply(struct mlx5e_selq *selq) +{ + struct mlx5e_selq_params *old_params; + + WARN_ON_ONCE(!selq->is_prepared); + + selq->is_prepared = false; + + old_params = rcu_replace_pointer(selq->active, selq->standby, + lockdep_is_held(selq->state_lock)); + synchronize_net(); /* Wait until ndo_select_queue starts emitting correct values. */ + selq->standby = old_params; +} + +void mlx5e_selq_cancel(struct mlx5e_selq *selq) +{ + lockdep_assert_held(selq->state_lock); + WARN_ON_ONCE(!selq->is_prepared); + + selq->is_prepared = false; +} + +#ifdef CONFIG_MLX5_CORE_EN_DCB +static int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb) +{ + int dscp_cp = 0; + + if (skb->protocol == htons(ETH_P_IP)) + dscp_cp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; + else if (skb->protocol == htons(ETH_P_IPV6)) + dscp_cp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; + + return priv->dcbx_dp.dscp2prio[dscp_cp]; +} +#endif + +static int mlx5e_get_up(struct mlx5e_priv *priv, struct sk_buff *skb) +{ +#ifdef CONFIG_MLX5_CORE_EN_DCB + if (READ_ONCE(priv->dcbx_dp.trust_state) == MLX5_QPTS_TRUST_DSCP) + return mlx5e_get_dscp_up(priv, skb); +#endif + if (skb_vlan_tag_present(skb)) + return skb_vlan_tag_get_prio(skb); + return 0; +} + +static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb, + struct mlx5e_selq_params *selq) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + int up; + + up = selq->num_tcs > 1 ? mlx5e_get_up(priv, skb) : 0; + + return selq->num_regular_queues + up; +} + +static int mlx5e_select_htb_queue(struct mlx5e_priv *priv, struct sk_buff *skb) +{ + u16 classid; + + /* Order maj_id before defcls - pairs with mlx5e_htb_root_add. */ + if ((TC_H_MAJ(skb->priority) >> 16) == smp_load_acquire(&priv->htb.maj_id)) + classid = TC_H_MIN(skb->priority); + else + classid = READ_ONCE(priv->htb.defcls); + + if (!classid) + return 0; + + return mlx5e_get_txq_by_classid(priv, classid); +} + +u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_selq_params *selq; + int txq_ix, up; + + selq = rcu_dereference_bh(priv->selq.active); + + /* This is a workaround needed only for the mlx5e_netdev_change_profile + * flow that zeroes out the whole priv without unregistering the netdev + * and without preventing ndo_select_queue from being called. + */ + if (unlikely(!selq)) + return 0; + + if (likely(!selq->is_special_queues)) { + /* No special queues, netdev_pick_tx returns one of the regular ones. */ + + txq_ix = netdev_pick_tx(dev, skb, NULL); + + if (selq->num_tcs <= 1) + return txq_ix; + + up = mlx5e_get_up(priv, skb); + + /* Normalize any picked txq_ix to [0, num_channels), + * So we can return a txq_ix that matches the channel and + * packet UP. + */ + return mlx5e_txq_to_ch_ix(txq_ix, selq->num_channels) + + up * selq->num_channels; + } + + if (unlikely(selq->is_htb)) { + /* num_tcs == 1, shortcut for PTP */ + + txq_ix = mlx5e_select_htb_queue(priv, skb); + if (txq_ix > 0) + return txq_ix; + + if (unlikely(selq->is_ptp && mlx5e_use_ptpsq(skb))) + return selq->num_channels; + + txq_ix = netdev_pick_tx(dev, skb, NULL); + + /* Fix netdev_pick_tx() not to choose ptp_channel and HTB txqs. + * If they are selected, switch to regular queues. + * Driver to select these queues only at mlx5e_select_ptpsq() + * and mlx5e_select_htb_queue(). + */ + return mlx5e_txq_to_ch_ix_htb(txq_ix, selq->num_channels); + } + + /* PTP is enabled */ + + if (mlx5e_use_ptpsq(skb)) + return mlx5e_select_ptpsq(dev, skb, selq); + + txq_ix = netdev_pick_tx(dev, skb, NULL); + + /* Normalize any picked txq_ix to [0, num_channels). Queues in range + * [0, num_regular_queues) will be mapped to the corresponding channel + * index, so that we can apply the packet's UP (if num_tcs > 1). + * If netdev_pick_tx() picks ptp_channel, switch to a regular queue, + * because driver should select the PTP only at mlx5e_select_ptpsq(). + */ + txq_ix = mlx5e_txq_to_ch_ix(txq_ix, selq->num_channels); + + if (selq->num_tcs <= 1) + return txq_ix; + + up = mlx5e_get_up(priv, skb); + + return txq_ix + up * selq->num_channels; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.h b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.h new file mode 100644 index 000000000000..6c070141d8f1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_EN_SELQ_H__ +#define __MLX5_EN_SELQ_H__ + +#include <linux/kernel.h> + +struct mlx5e_selq_params; + +struct mlx5e_selq { + struct mlx5e_selq_params __rcu *active; + struct mlx5e_selq_params *standby; + struct mutex *state_lock; /* points to priv->state_lock */ + bool is_prepared; +}; + +struct mlx5e_params; +struct net_device; +struct sk_buff; + +int mlx5e_selq_init(struct mlx5e_selq *selq, struct mutex *state_lock); +void mlx5e_selq_cleanup(struct mlx5e_selq *selq); +void mlx5e_selq_prepare(struct mlx5e_selq *selq, struct mlx5e_params *params, bool htb); +void mlx5e_selq_apply(struct mlx5e_selq *selq); +void mlx5e_selq_cancel(struct mlx5e_selq *selq); + +static inline u16 mlx5e_txq_to_ch_ix(u16 txq, u16 num_channels) +{ + while (unlikely(txq >= num_channels)) + txq -= num_channels; + return txq; +} + +static inline u16 mlx5e_txq_to_ch_ix_htb(u16 txq, u16 num_channels) +{ + if (unlikely(txq >= num_channels)) { + if (unlikely(txq >= num_channels << 3)) + txq %= num_channels; + else + do + txq -= num_channels; + while (txq >= num_channels); + } + return txq; +} + +u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev); + +#endif /* __MLX5_EN_SELQ_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c index b0de6b999675..21aab96357b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_accept(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -18,9 +19,8 @@ tc_act_parse_accept(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - attr->flags |= MLX5_ESW_ATTR_FLAG_ACCEPT; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->flags |= MLX5_ATTR_FLAG_ACCEPT; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index e600924e30ea..cb8f7593a00c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -2,6 +2,7 @@ // Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. #include "act.h" +#include "en/tc/post_act.h" #include "en/tc_priv.h" #include "mlx5_core.h" @@ -101,3 +102,75 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, parse_state->num_actions = flow_action->num_entries; parse_state->extack = extack; } + +void +mlx5e_tc_act_reorder_flow_actions(struct flow_action *flow_action, + struct mlx5e_tc_flow_action *flow_action_reorder) +{ + struct flow_action_entry *act; + int i, j = 0; + + flow_action_for_each(i, act, flow_action) { + /* Add CT action to be first. */ + if (act->id == FLOW_ACTION_CT) + flow_action_reorder->entries[j++] = act; + } + + flow_action_for_each(i, act, flow_action) { + if (act->id == FLOW_ACTION_CT) + continue; + flow_action_reorder->entries[j++] = act; + } +} + +int +mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, + struct flow_action *flow_action, + struct mlx5_flow_attr *attr, + enum mlx5_flow_namespace_type ns_type) +{ + struct flow_action_entry *act; + struct mlx5e_tc_act *tc_act; + struct mlx5e_priv *priv; + int err = 0, i; + + priv = parse_state->flow->priv; + + flow_action_for_each(i, act, flow_action) { + tc_act = mlx5e_tc_act_get(act->id, ns_type); + if (!tc_act || !tc_act->post_parse || + !tc_act->can_offload(parse_state, act, i, attr)) + continue; + + err = tc_act->post_parse(parse_state, priv, attr); + if (err) + goto out; + } + +out: + return err; +} + +int +mlx5e_tc_act_set_next_post_act(struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct mlx5_flow_attr *next_attr) +{ + struct mlx5_core_dev *mdev = flow->priv->mdev; + struct mlx5e_tc_mod_hdr_acts *mod_acts; + int err; + + mod_acts = &attr->parse_attr->mod_hdr_acts; + + /* Set handle on current post act rule to next post act rule. */ + err = mlx5e_tc_post_act_set_handle(mdev, next_attr->post_act_handle, mod_acts); + if (err) { + mlx5_core_warn(mdev, "Failed setting post action handle"); + return err; + } + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h index 26efa33de56f..519fa1056d9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -16,12 +16,13 @@ struct mlx5e_tc_act_parse_state { unsigned int num_actions; struct mlx5e_tc_flow *flow; struct netlink_ext_ack *extack; + u32 actions; + bool ct; bool encap; bool decap; bool mpls_push; bool ptype_host; const struct ip_tunnel_info *tun_info; - struct pedit_headers_action hdrs[__PEDIT_CMD_MAX]; int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; int if_count; struct mlx5_tc_ct_priv *ct_priv; @@ -30,7 +31,8 @@ struct mlx5e_tc_act_parse_state { struct mlx5e_tc_act { bool (*can_offload)(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index); + int act_index, + struct mlx5_flow_attr *attr); int (*parse_action)(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, @@ -40,6 +42,15 @@ struct mlx5e_tc_act { int (*post_parse)(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr); + + bool (*is_multi_table_act)(struct mlx5e_priv *priv, + const struct flow_action_entry *act, + struct mlx5_flow_attr *attr); +}; + +struct mlx5e_tc_flow_action { + unsigned int num_entries; + struct flow_action_entry **entries; }; extern struct mlx5e_tc_act mlx5e_tc_act_drop; @@ -72,4 +83,19 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, struct flow_action *flow_action, struct netlink_ext_ack *extack); +void +mlx5e_tc_act_reorder_flow_actions(struct flow_action *flow_action, + struct mlx5e_tc_flow_action *flow_action_reorder); + +int +mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, + struct flow_action *flow_action, + struct mlx5_flow_attr *attr, + enum mlx5_flow_namespace_type ns_type); + +int +mlx5e_tc_act_set_next_post_act(struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct mlx5_flow_attr *next_attr); + #endif /* __MLX5_EN_TC_ACT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c index 29920ef0180a..c0f08ae6a57f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c @@ -38,11 +38,12 @@ csum_offload_supported(struct mlx5e_priv *priv, static bool tc_act_can_offload_csum(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct mlx5e_tc_flow *flow = parse_state->flow; - return csum_offload_supported(flow->priv, flow->attr->action, + return csum_offload_supported(flow->priv, attr->action, act->csum_flags, parse_state->extack); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c index 06ec30cdb269..7368f95f2310 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c @@ -8,13 +8,14 @@ static bool tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; struct netlink_ext_ack *extack = parse_state->extack; - if (flow_flag_test(parse_state->flow, SAMPLE)) { - NL_SET_ERR_MSG_MOD(extack, - "Sample action with connection tracking is not supported"); + if (parse_state->ct && !clear_action) { + NL_SET_ERR_MSG_MOD(extack, "Multiple CT actions are not supported"); return false; } @@ -27,6 +28,7 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; int err; err = mlx5_tc_ct_parse_action(parse_state->ct_priv, attr, @@ -35,16 +37,33 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, if (err) return err; - flow_flag_set(parse_state->flow, CT); if (mlx5e_is_eswitch_flow(parse_state->flow)) attr->esw_attr->split_count = attr->esw_attr->out_count; + if (!clear_action) { + attr->flags |= MLX5_ATTR_FLAG_CT; + flow_flag_set(parse_state->flow, CT); + parse_state->ct = true; + } + return 0; } +static bool +tc_act_is_multi_table_act_ct(struct mlx5e_priv *priv, + const struct flow_action_entry *act, + struct mlx5_flow_attr *attr) +{ + if (act->ct.action & TCA_CT_ACT_CLEAR) + return false; + + return true; +} + struct mlx5e_tc_act mlx5e_tc_act_ct = { .can_offload = tc_act_can_offload_ct, .parse_action = tc_act_parse_ct, + .is_multi_table_act = tc_act_is_multi_table_act_ct, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c index 2e29a23bed12..dd025a95c439 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_drop(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -18,8 +19,7 @@ tc_act_parse_drop(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c index f44515061228..4726bcb46eec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c @@ -8,6 +8,7 @@ static int validate_goto_chain(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { @@ -32,7 +33,7 @@ validate_goto_chain(struct mlx5e_priv *priv, } if (!mlx5_chains_backwards_supported(chains) && - dest_chain <= flow->attr->chain) { + dest_chain <= attr->chain) { NL_SET_ERR_MSG_MOD(extack, "Goto lower numbered chain isn't supported"); return -EOPNOTSUPP; } @@ -43,8 +44,8 @@ validate_goto_chain(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (flow->attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | - MLX5_FLOW_CONTEXT_ACTION_DECAP) && + if (attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | + MLX5_FLOW_CONTEXT_ACTION_DECAP) && !reformat_and_fwd) { NL_SET_ERR_MSG_MOD(extack, "Goto chain is not allowed if action has reformat or decap"); @@ -57,12 +58,13 @@ validate_goto_chain(struct mlx5e_priv *priv, static bool tc_act_can_offload_goto(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_tc_flow *flow = parse_state->flow; - if (validate_goto_chain(flow->priv, flow, act, extack)) + if (validate_goto_chain(flow->priv, flow, attr, act, extack)) return false; return true; @@ -74,8 +76,7 @@ tc_act_parse_goto(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; attr->dest_chain = act->chain_index; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c index d775c3d9edf3..e8d227595b3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_mark(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { if (act->mark & ~MLX5E_TC_FLOW_ID_MASK) { NL_SET_ERR_MSG_MOD(parse_state->extack, "Bad flow mark, only 16 bit supported"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index c614fc7fdc9c..d08abec93704 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -99,7 +99,8 @@ get_fdb_out_dev(struct net_device *uplink_dev, struct net_device *out_dev) static bool tc_act_can_offload_mirred(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_tc_flow *flow = parse_state->flow; @@ -108,8 +109,8 @@ tc_act_can_offload_mirred(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv = flow->priv; struct mlx5_esw_flow_attr *esw_attr; - parse_attr = flow->attr->parse_attr; - esw_attr = flow->attr->esw_attr; + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; if (!out_dev) { /* out_dev is NULL when filters with @@ -295,8 +296,7 @@ tc_act_parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, if (err) return err; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c index 2c74567b6d25..90b4c1b34776 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_mirred_nic(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_tc_flow *flow = parse_state->flow; @@ -39,8 +40,7 @@ tc_act_parse_mirred_nic(struct mlx5e_tc_act_parse_state *parse_state, { attr->parse_attr->mirred_ifindex[0] = act->dev->ifindex; flow_flag_set(parse_state->flow, HAIRPIN); - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c index 784fc4f68b1e..40332949509a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c @@ -8,7 +8,8 @@ static bool tc_act_can_offload_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_priv *priv = parse_state->flow->priv; @@ -36,13 +37,13 @@ tc_act_parse_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, static bool tc_act_can_offload_mpls_pop(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; - struct mlx5e_tc_flow *flow = parse_state->flow; struct net_device *filter_dev; - filter_dev = flow->attr->parse_attr->filter_dev; + filter_dev = attr->parse_attr->filter_dev; /* we only support mpls pop if it is the first action * and the filter net device is bareudp. Subsequent diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c index 79addbbef087..39f8f71bed9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c @@ -46,9 +46,9 @@ static int parse_pedit_to_modify_hdr(struct mlx5e_priv *priv, const struct flow_action_entry *act, int namespace, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { + struct pedit_headers_action *hdrs = parse_attr->hdrs; u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1; u8 htype = act->mangle.htype; int err = -EOPNOTSUPP; @@ -110,20 +110,20 @@ int mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv, const struct flow_action_entry *act, int namespace, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { if (flow && flow_flag_test(flow, L3_TO_L2_DECAP)) return parse_pedit_to_reformat(act, parse_attr, extack); - return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, hdrs, extack); + return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, extack); } static bool tc_act_can_offload_pedit(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -141,8 +141,7 @@ tc_act_parse_pedit(struct mlx5e_tc_act_parse_state *parse_state, ns_type = mlx5e_get_flow_namespace(flow); - err = mlx5e_tc_act_pedit_parse_action(flow->priv, act, ns_type, - attr->parse_attr, parse_state->hdrs, + err = mlx5e_tc_act_pedit_parse_action(flow->priv, act, ns_type, attr->parse_attr, flow, parse_state->extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h index da8ab03af58f..258f030a2dc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h @@ -25,7 +25,6 @@ int mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv, const struct flow_action_entry *act, int namespace, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c index 0819110193dc..6454b031ff7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_ptype(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c index 1c32e24e528d..ad09a8a5f36e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c @@ -7,16 +7,16 @@ static bool tc_act_can_offload_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; - struct mlx5e_tc_flow *flow = parse_state->flow; struct mlx5e_tc_flow_parse_attr *parse_attr; struct net_device *out_dev = act->dev; struct mlx5_esw_flow_attr *esw_attr; - parse_attr = flow->attr->parse_attr; - esw_attr = flow->attr->esw_attr; + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; if (!out_dev) return false; @@ -58,8 +58,7 @@ tc_act_parse_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state, struct net_device *out_dev = act->dev; int err; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; err = mlx5e_set_fwd_to_int_port_actions(priv, attr, out_dev->ifindex, MLX5E_TC_INT_PORT_INGRESS, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c index 6699bdf5cf01..2c0196431302 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c @@ -4,17 +4,21 @@ #include <net/psample.h> #include "act.h" #include "en/tc_priv.h" +#include "en/tc/act/sample.h" static bool tc_act_can_offload_sample(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; + bool ct_nat; - if (flow_flag_test(parse_state->flow, CT)) { - NL_SET_ERR_MSG_MOD(extack, - "Sample action with connection tracking is not supported"); + ct_nat = attr->ct_attr.ct_action & TCA_CT_ACT_NAT; + + if (flow_flag_test(parse_state->flow, CT) && ct_nat) { + NL_SET_ERR_MSG_MOD(extack, "Sample action with CT NAT is not supported"); return false; } @@ -27,11 +31,7 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { - struct mlx5e_sample_attr *sample_attr; - - sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL); - if (!sample_attr) - return -ENOMEM; + struct mlx5e_sample_attr *sample_attr = &attr->sample_attr; sample_attr->rate = act->sample.rate; sample_attr->group_num = act->sample.psample_group->group_num; @@ -39,13 +39,33 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state, if (act->sample.truncate) sample_attr->trunc_size = act->sample.trunc_size; - attr->sample_attr = sample_attr; + attr->flags |= MLX5_ATTR_FLAG_SAMPLE; flow_flag_set(parse_state->flow, SAMPLE); return 0; } +bool +mlx5e_tc_act_sample_is_multi_table(struct mlx5_core_dev *mdev, + struct mlx5_flow_attr *attr) +{ + if (MLX5_CAP_GEN(mdev, reg_c_preserve) || + attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) + return true; + + return false; +} + +static bool +tc_act_is_multi_table_act_sample(struct mlx5e_priv *priv, + const struct flow_action_entry *act, + struct mlx5_flow_attr *attr) +{ + return mlx5e_tc_act_sample_is_multi_table(priv->mdev, attr); +} + struct mlx5e_tc_act mlx5e_tc_act_sample = { .can_offload = tc_act_can_offload_sample, .parse_action = tc_act_parse_sample, + .is_multi_table_act = tc_act_is_multi_table_act_sample, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.h new file mode 100644 index 000000000000..3efb3a15c5d2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_EN_TC_ACT_SAMPLE_H__ +#define __MLX5_EN_TC_ACT_SAMPLE_H__ + +#include <net/flow_offload.h> +#include "en/tc_priv.h" + +bool +mlx5e_tc_act_sample_is_multi_table(struct mlx5_core_dev *mdev, + struct mlx5_flow_attr *attr); + +#endif /* __MLX5_EN_TC_ACT_SAMPLE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c index 046b64c2cec4..a7d9eab19e4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; @@ -25,9 +26,8 @@ tc_act_parse_trap(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c index 6f4a2cf46afd..b4fa2de9711d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c @@ -8,7 +8,8 @@ static bool tc_act_can_offload_tun_encap(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { if (!act->tunnel) { NL_SET_ERR_MSG_MOD(parse_state->extack, @@ -34,7 +35,8 @@ tc_act_parse_tun_encap(struct mlx5e_tc_act_parse_state *parse_state, static bool tc_act_can_offload_tun_decap(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c index 70fc0c2d8813..6378b7558ba2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c @@ -9,7 +9,6 @@ static int add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, u32 *action, struct netlink_ext_ack *extack) { const struct flow_action_entry prio_tag_act = { @@ -26,7 +25,7 @@ add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv, }; return mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, - &prio_tag_act, parse_attr, hdrs, action, + &prio_tag_act, parse_attr, action, extack); } @@ -151,7 +150,8 @@ mlx5e_tc_act_vlan_add_pop_action(struct mlx5e_priv *priv, static bool tc_act_can_offload_vlan(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -170,8 +170,8 @@ tc_act_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, /* Replace vlan pop+push with vlan modify */ attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; err = mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, act, - attr->parse_attr, parse_state->hdrs, - &attr->action, parse_state->extack); + attr->parse_attr, &attr->action, + parse_state->extack); } else { err = parse_tc_vlan_action(priv, act, esw_attr, &attr->action, parse_state->extack); @@ -191,7 +191,6 @@ tc_act_post_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5_flow_attr *attr) { struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; - struct pedit_headers_action *hdrs = parse_state->hdrs; struct netlink_ext_ack *extack = parse_state->extack; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int err; @@ -202,7 +201,7 @@ tc_act_post_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, * tag rewrite. */ attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, hdrs, + err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, &attr->action, extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h index 3d62f13ab61f..2fa58c6f44eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h @@ -24,7 +24,6 @@ int mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, const struct flow_action_entry *act, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, u32 *action, struct netlink_ext_ack *extack); #endif /* __MLX5_EN_TC_ACT_VLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c index 63e36e7f53e3..28444d4ffd73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c @@ -12,7 +12,6 @@ int mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, const struct flow_action_entry *act, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, u32 *action, struct netlink_ext_ack *extack) { u16 mask16 = VLAN_VID_MASK; @@ -44,7 +43,7 @@ mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, return -EOPNOTSUPP; } - err = mlx5e_tc_act_pedit_parse_action(priv, &pedit_act, namespace, parse_attr, hdrs, + err = mlx5e_tc_act_pedit_parse_action(priv, &pedit_act, namespace, parse_attr, NULL, extack); *action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; @@ -54,7 +53,8 @@ mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, static bool tc_act_can_offload_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -69,8 +69,7 @@ tc_act_parse_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state, int err; ns_type = mlx5e_get_flow_namespace(parse_state->flow); - err = mlx5e_tc_act_vlan_add_rewrite_action(priv, ns_type, act, - attr->parse_attr, parse_state->hdrs, + err = mlx5e_tc_act_vlan_add_rewrite_action(priv, ns_type, act, attr->parse_attr, &attr->action, parse_state->extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 31b4e39be2d3..dea137dd744b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. +#include "en/tc_priv.h" #include "en_tc.h" #include "post_act.h" #include "mlx5_core.h" @@ -75,21 +76,47 @@ mlx5e_tc_post_act_destroy(struct mlx5e_post_act *post_act) kfree(post_act); } +int +mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act, + struct mlx5e_post_act_handle *handle) +{ + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + /* Post action rule matches on fte_id and executes original rule's tc rule action */ + mlx5e_tc_match_to_reg_match(spec, FTEID_TO_REG, handle->id, MLX5_POST_ACTION_MASK); + + handle->rule = mlx5e_tc_rule_offload(post_act->priv, spec, handle->attr); + if (IS_ERR(handle->rule)) { + err = PTR_ERR(handle->rule); + netdev_warn(post_act->priv->netdev, "Failed to add post action rule"); + goto err_rule; + } + + kvfree(spec); + return 0; + +err_rule: + kvfree(spec); + return err; +} + struct mlx5e_post_act_handle * mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *attr) { u32 attr_sz = ns_to_attr_sz(post_act->ns_type); - struct mlx5e_post_act_handle *handle = NULL; - struct mlx5_flow_attr *post_attr = NULL; - struct mlx5_flow_spec *spec = NULL; + struct mlx5e_post_act_handle *handle; + struct mlx5_flow_attr *post_attr; int err; handle = kzalloc(sizeof(*handle), GFP_KERNEL); - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); post_attr = mlx5_alloc_flow_attr(post_act->ns_type); - if (!handle || !spec || !post_attr) { + if (!handle || !post_attr) { kfree(post_attr); - kvfree(spec); kfree(handle); return ERR_PTR(-ENOMEM); } @@ -100,7 +127,7 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *at post_attr->ft = post_act->ft; post_attr->inner_match_level = MLX5_MATCH_NONE; post_attr->outer_match_level = MLX5_MATCH_NONE; - post_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP); + post_attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_DECAP; handle->ns_type = post_act->ns_type; /* Splits were handled before post action */ @@ -112,36 +139,29 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *at if (err) goto err_xarray; - /* Post action rule matches on fte_id and executes original rule's - * tc rule action - */ - mlx5e_tc_match_to_reg_match(spec, FTEID_TO_REG, - handle->id, MLX5_POST_ACTION_MASK); - - handle->rule = mlx5_tc_rule_insert(post_act->priv, spec, post_attr); - if (IS_ERR(handle->rule)) { - err = PTR_ERR(handle->rule); - netdev_warn(post_act->priv->netdev, "Failed to add post action rule"); - goto err_rule; - } handle->attr = post_attr; - kvfree(spec); return handle; -err_rule: - xa_erase(&post_act->ids, handle->id); err_xarray: kfree(post_attr); - kvfree(spec); kfree(handle); return ERR_PTR(err); } void +mlx5e_tc_post_act_unoffload(struct mlx5e_post_act *post_act, + struct mlx5e_post_act_handle *handle) +{ + mlx5e_tc_rule_unoffload(post_act->priv, handle->rule, handle->attr); + handle->rule = NULL; +} + +void mlx5e_tc_post_act_del(struct mlx5e_post_act *post_act, struct mlx5e_post_act_handle *handle) { - mlx5_tc_rule_delete(post_act->priv, handle->rule, handle->attr); + if (!IS_ERR_OR_NULL(handle->rule)) + mlx5e_tc_post_act_unoffload(post_act, handle); xa_erase(&post_act->ids, handle->id); kfree(handle->attr); kfree(handle); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h index b530ec1981a5..f476774c0b75 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.h @@ -24,6 +24,14 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *at void mlx5e_tc_post_act_del(struct mlx5e_post_act *post_act, struct mlx5e_post_act_handle *handle); +int +mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act, + struct mlx5e_post_act_handle *handle); + +void +mlx5e_tc_post_act_unoffload(struct mlx5e_post_act *post_act, + struct mlx5e_post_act_handle *handle); + struct mlx5_flow_table * mlx5e_tc_post_act_get_ft(struct mlx5e_post_act *post_act); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index ff4b4f8a5a9d..fd4504518578 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -5,6 +5,7 @@ #include <net/psample.h> #include "en/mapping.h" #include "en/tc/post_act.h" +#include "en/tc/act/sample.h" #include "en/mod_hdr.h" #include "sample.h" #include "eswitch.h" @@ -46,14 +47,12 @@ struct mlx5e_sample_flow { struct mlx5_flow_handle *pre_rule; struct mlx5_flow_attr *post_attr; struct mlx5_flow_handle *post_rule; - struct mlx5e_post_act_handle *post_act_handle; }; struct mlx5e_sample_restore { struct hlist_node hlist; struct mlx5_modify_hdr *modify_hdr; struct mlx5_flow_handle *rule; - struct mlx5e_post_act_handle *post_act_handle; u32 obj_id; int count; }; @@ -231,69 +230,46 @@ sampler_put(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sampler *sampler) */ static struct mlx5_modify_hdr * sample_modify_hdr_get(struct mlx5_core_dev *mdev, u32 obj_id, - struct mlx5e_post_act_handle *handle) + struct mlx5e_tc_mod_hdr_acts *mod_acts) { - struct mlx5e_tc_mod_hdr_acts mod_acts = {}; struct mlx5_modify_hdr *modify_hdr; int err; - err = mlx5e_tc_match_to_reg_set(mdev, &mod_acts, MLX5_FLOW_NAMESPACE_FDB, + err = mlx5e_tc_match_to_reg_set(mdev, mod_acts, MLX5_FLOW_NAMESPACE_FDB, CHAIN_TO_REG, obj_id); if (err) goto err_set_regc0; - if (handle) { - err = mlx5e_tc_post_act_set_handle(mdev, handle, &mod_acts); - if (err) - goto err_post_act; - } - modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB, - mod_acts.num_actions, - mod_acts.actions); + mod_acts->num_actions, + mod_acts->actions); if (IS_ERR(modify_hdr)) { err = PTR_ERR(modify_hdr); goto err_modify_hdr; } - mlx5e_mod_hdr_dealloc(&mod_acts); + mlx5e_mod_hdr_dealloc(mod_acts); return modify_hdr; err_modify_hdr: -err_post_act: - mlx5e_mod_hdr_dealloc(&mod_acts); + mlx5e_mod_hdr_dealloc(mod_acts); err_set_regc0: return ERR_PTR(err); } -static u32 -restore_hash(u32 obj_id, struct mlx5e_post_act_handle *post_act_handle) -{ - return jhash_2words(obj_id, hash32_ptr(post_act_handle), 0); -} - -static bool -restore_equal(struct mlx5e_sample_restore *restore, u32 obj_id, - struct mlx5e_post_act_handle *post_act_handle) -{ - return restore->obj_id == obj_id && restore->post_act_handle == post_act_handle; -} - static struct mlx5e_sample_restore * sample_restore_get(struct mlx5e_tc_psample *tc_psample, u32 obj_id, - struct mlx5e_post_act_handle *post_act_handle) + struct mlx5e_tc_mod_hdr_acts *mod_acts) { struct mlx5_eswitch *esw = tc_psample->esw; struct mlx5_core_dev *mdev = esw->dev; struct mlx5e_sample_restore *restore; struct mlx5_modify_hdr *modify_hdr; - u32 hash_key; int err; mutex_lock(&tc_psample->restore_lock); - hash_key = restore_hash(obj_id, post_act_handle); - hash_for_each_possible(tc_psample->restore_hashtbl, restore, hlist, hash_key) - if (restore_equal(restore, obj_id, post_act_handle)) + hash_for_each_possible(tc_psample->restore_hashtbl, restore, hlist, obj_id) + if (restore->obj_id == obj_id) goto add_ref; restore = kzalloc(sizeof(*restore), GFP_KERNEL); @@ -302,9 +278,8 @@ sample_restore_get(struct mlx5e_tc_psample *tc_psample, u32 obj_id, goto err_alloc; } restore->obj_id = obj_id; - restore->post_act_handle = post_act_handle; - modify_hdr = sample_modify_hdr_get(mdev, obj_id, post_act_handle); + modify_hdr = sample_modify_hdr_get(mdev, obj_id, mod_acts); if (IS_ERR(modify_hdr)) { err = PTR_ERR(modify_hdr); goto err_modify_hdr; @@ -317,7 +292,7 @@ sample_restore_get(struct mlx5e_tc_psample *tc_psample, u32 obj_id, goto err_restore; } - hash_add(tc_psample->restore_hashtbl, &restore->hlist, hash_key); + hash_add(tc_psample->restore_hashtbl, &restore->hlist, obj_id); add_ref: restore->count++; mutex_unlock(&tc_psample->restore_lock); @@ -403,7 +378,7 @@ add_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow, post_attr->chain = 0; post_attr->prio = 0; post_attr->ft = default_tbl; - post_attr->flags = MLX5_ESW_ATTR_FLAG_NO_IN_PORT; + post_attr->flags = MLX5_ATTR_FLAG_NO_IN_PORT; /* When offloading sample and encap action, if there is no valid * neigh data struct, a slow path rule is offloaded first. Source @@ -492,16 +467,16 @@ del_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow, struct mlx5_flow_handle * mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr, - u32 tunnel_id) + struct mlx5_flow_attr *attr) { - struct mlx5e_post_act_handle *post_act_handle = NULL; struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; struct mlx5_esw_flow_attr *pre_esw_attr; struct mlx5_mapped_obj restore_obj = {}; + struct mlx5e_tc_mod_hdr_acts *mod_acts; struct mlx5e_sample_flow *sample_flow; struct mlx5e_sample_attr *sample_attr; struct mlx5_flow_attr *pre_attr; + u32 tunnel_id = attr->tunnel_id; struct mlx5_eswitch *esw; u32 default_tbl_id; u32 obj_id; @@ -513,7 +488,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL); if (!sample_flow) return ERR_PTR(-ENOMEM); - sample_attr = attr->sample_attr; + sample_attr = &attr->sample_attr; sample_attr->sample_flow = sample_flow; /* For NICs with reg_c_preserve support or decap action, use @@ -522,18 +497,11 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, * original flow table. */ esw = tc_psample->esw; - if (MLX5_CAP_GEN(esw->dev, reg_c_preserve) || - attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + if (mlx5e_tc_act_sample_is_multi_table(esw->dev, attr)) { struct mlx5_flow_table *ft; ft = mlx5e_tc_post_act_get_ft(tc_psample->post_act); default_tbl_id = ft->id; - post_act_handle = mlx5e_tc_post_act_add(tc_psample->post_act, attr); - if (IS_ERR(post_act_handle)) { - err = PTR_ERR(post_act_handle); - goto err_post_act; - } - sample_flow->post_act_handle = post_act_handle; } else { err = add_post_rule(esw, sample_flow, spec, attr, &default_tbl_id); if (err) @@ -546,6 +514,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, err = PTR_ERR(sample_flow->sampler); goto err_sampler; } + sample_attr->sampler_id = sample_flow->sampler->sampler_id; /* Create an id mapping reg_c0 value to sample object. */ restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE; @@ -559,7 +528,8 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, sample_attr->restore_obj_id = obj_id; /* Create sample restore context. */ - sample_flow->restore = sample_restore_get(tc_psample, obj_id, post_act_handle); + mod_acts = &attr->parse_attr->mod_hdr_acts; + sample_flow->restore = sample_restore_get(tc_psample, obj_id, mod_acts); if (IS_ERR(sample_flow->restore)) { err = PTR_ERR(sample_flow->restore); goto err_sample_restore; @@ -580,13 +550,13 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, if (tunnel_id) pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; pre_attr->modify_hdr = sample_flow->restore->modify_hdr; - pre_attr->flags = MLX5_ESW_ATTR_FLAG_SAMPLE; + pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE; pre_attr->inner_match_level = attr->inner_match_level; pre_attr->outer_match_level = attr->outer_match_level; pre_attr->chain = attr->chain; pre_attr->prio = attr->prio; - pre_attr->sample_attr = attr->sample_attr; - sample_attr->sampler_id = sample_flow->sampler->sampler_id; + pre_attr->ft = attr->ft; + pre_attr->sample_attr = *sample_attr; pre_esw_attr = pre_attr->esw_attr; pre_esw_attr->in_mdev = esw_attr->in_mdev; pre_esw_attr->in_rep = esw_attr->in_rep; @@ -611,9 +581,6 @@ err_sampler: if (sample_flow->post_rule) del_post_rule(esw, sample_flow, attr); err_post_rule: - if (post_act_handle) - mlx5e_tc_post_act_del(tc_psample->post_act, post_act_handle); -err_post_act: kfree(sample_flow); return ERR_PTR(err); } @@ -633,15 +600,13 @@ mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample, * will hit fw syndromes. */ esw = tc_psample->esw; - sample_flow = attr->sample_attr->sample_flow; + sample_flow = attr->sample_attr.sample_flow; mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr); sample_restore_put(tc_psample, sample_flow->restore); - mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id); + mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr.restore_obj_id); sampler_put(tc_psample, sample_flow->sampler); - if (sample_flow->post_act_handle) - mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle); - else + if (sample_flow->post_rule) del_post_rule(esw, sample_flow, attr); kfree(sample_flow->pre_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h index 9ef8a49d7801..a569367eae4d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h @@ -26,8 +26,7 @@ void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj struct mlx5_flow_handle * mlx5e_tc_sample_offload(struct mlx5e_tc_psample *sample_priv, struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr, - u32 tunnel_id); + struct mlx5_flow_attr *attr); void mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *sample_priv, @@ -45,8 +44,7 @@ mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample); static inline struct mlx5_flow_handle * mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr, - u32 tunnel_id) + struct mlx5_flow_attr *attr) { return ERR_PTR(-EOPNOTSUPP); } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 4a0d38d219ed..875e77af0ae6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -18,6 +18,7 @@ #include "lib/fs_chains.h" #include "en/tc_ct.h" +#include "en/tc_priv.h" #include "en/mod_hdr.h" #include "en/mapping.h" #include "en/tc/post_act.h" @@ -68,7 +69,6 @@ struct mlx5_tc_ct_priv { struct mlx5_ct_flow { struct mlx5_flow_attr *pre_ct_attr; struct mlx5_flow_handle *pre_ct_rule; - struct mlx5e_post_act_handle *post_act_handle; struct mlx5_ct_ft *ft; u32 chain_mapping; }; @@ -809,7 +809,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct; attr->outer_match_level = MLX5_MATCH_L4; attr->counter = entry->counter->counter; - attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT; + attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT; if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB) attr->esw_attr->in_mdev = priv->mdev; @@ -1756,7 +1756,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) /* We translate the tc filter with CT action to the following HW model: * * +---------------------+ - * + ft prio (tc chain) + + * + ft prio (tc chain) + * + original match + * +---------------------+ * | set chain miss mapping @@ -1766,7 +1766,7 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) * v * +---------------------+ * + pre_ct/pre_ct_nat + if matches +-------------------------+ - * + zone+nat match +---------------->+ post_act (see below) + + * + zone+nat match +---------------->+ post_act (see below) + * +---------------------+ set zone +-------------------------+ * | set zone * v @@ -1781,21 +1781,19 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) * | do nat (if needed) * v * +--------------+ - * + post_act + original filter actions + * + post_act + original filter actions * + fte_id match +------------------------> * +--------------+ */ static struct mlx5_flow_handle * __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *orig_spec, struct mlx5_flow_attr *attr) { bool nat = attr->ct_attr.ct_action & TCA_CT_ACT_NAT; struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev); - struct mlx5e_tc_mod_hdr_acts pre_mod_acts = {}; + struct mlx5e_tc_mod_hdr_acts *pre_mod_acts; u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type); - struct mlx5e_post_act_handle *handle; struct mlx5_flow_attr *pre_ct_attr; struct mlx5_modify_hdr *mod_hdr; struct mlx5_ct_flow *ct_flow; @@ -1818,14 +1816,6 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, } ct_flow->ft = ft; - handle = mlx5e_tc_post_act_add(ct_priv->post_act, attr); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - ct_dbg("Failed to allocate post action handle"); - goto err_post_act_handle; - } - ct_flow->post_act_handle = handle; - /* Base flow attributes of both rules on original rule attribute */ ct_flow->pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type); if (!ct_flow->pre_ct_attr) { @@ -1835,6 +1825,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, pre_ct_attr = ct_flow->pre_ct_attr; memcpy(pre_ct_attr, attr, attr_sz); + pre_mod_acts = &pre_ct_attr->parse_attr->mod_hdr_acts; /* Modify the original rule's action to fwd and modify, leave decap */ pre_ct_attr->action = attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP; @@ -1853,30 +1844,22 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, } ct_flow->chain_mapping = chain_mapping; - err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts, ct_priv->ns_type, + err = mlx5e_tc_match_to_reg_set(priv->mdev, pre_mod_acts, ct_priv->ns_type, CHAIN_TO_REG, chain_mapping); if (err) { ct_dbg("Failed to set chain register mapping"); goto err_mapping; } - err = mlx5e_tc_post_act_set_handle(priv->mdev, handle, &pre_mod_acts); - if (err) { - ct_dbg("Failed to set post action handle"); - goto err_mapping; - } - /* If original flow is decap, we do it before going into ct table * so add a rewrite for the tunnel match_id. */ if ((pre_ct_attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) && attr->chain == 0) { - u32 tun_id = mlx5e_tc_get_flow_tun_id(flow); - - err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts, + err = mlx5e_tc_match_to_reg_set(priv->mdev, pre_mod_acts, ct_priv->ns_type, TUNNEL_TO_REG, - tun_id); + attr->tunnel_id); if (err) { ct_dbg("Failed to set tunnel register mapping"); goto err_mapping; @@ -1884,8 +1867,8 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, } mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type, - pre_mod_acts.num_actions, - pre_mod_acts.actions); + pre_mod_acts->num_actions, + pre_mod_acts->actions); if (IS_ERR(mod_hdr)) { err = PTR_ERR(mod_hdr); ct_dbg("Failed to create pre ct mod hdr"); @@ -1905,20 +1888,18 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, } attr->ct_attr.ct_flow = ct_flow; - mlx5e_mod_hdr_dealloc(&pre_mod_acts); + mlx5e_mod_hdr_dealloc(pre_mod_acts); return ct_flow->pre_ct_rule; err_insert_orig: mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr); err_mapping: - mlx5e_mod_hdr_dealloc(&pre_mod_acts); + mlx5e_mod_hdr_dealloc(pre_mod_acts); mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping); err_get_chain: kfree(ct_flow->pre_ct_attr); err_alloc_pre: - mlx5e_tc_post_act_del(ct_priv->post_act, handle); -err_post_act_handle: mlx5_tc_ct_del_ft_cb(ct_priv, ft); err_ft: kfree(ct_flow); @@ -1926,87 +1907,19 @@ err_ft: return ERR_PTR(err); } -static struct mlx5_flow_handle * -__mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, - struct mlx5_flow_spec *orig_spec, - struct mlx5_flow_attr *attr, - struct mlx5e_tc_mod_hdr_acts *mod_acts) -{ - struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev); - u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type); - struct mlx5_flow_attr *pre_ct_attr; - struct mlx5_modify_hdr *mod_hdr; - struct mlx5_flow_handle *rule; - struct mlx5_ct_flow *ct_flow; - int err; - - ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL); - if (!ct_flow) - return ERR_PTR(-ENOMEM); - - /* Base esw attributes on original rule attribute */ - pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type); - if (!pre_ct_attr) { - err = -ENOMEM; - goto err_attr; - } - - memcpy(pre_ct_attr, attr, attr_sz); - - mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type, - mod_acts->num_actions, - mod_acts->actions); - if (IS_ERR(mod_hdr)) { - err = PTR_ERR(mod_hdr); - ct_dbg("Failed to add create ct clear mod hdr"); - goto err_mod_hdr; - } - - pre_ct_attr->modify_hdr = mod_hdr; - - rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - ct_dbg("Failed to add ct clear rule"); - goto err_insert; - } - - attr->ct_attr.ct_flow = ct_flow; - ct_flow->pre_ct_attr = pre_ct_attr; - ct_flow->pre_ct_rule = rule; - return rule; - -err_insert: - mlx5_modify_header_dealloc(priv->mdev, mod_hdr); -err_mod_hdr: - netdev_warn(priv->netdev, - "Failed to offload ct clear flow, err %d\n", err); - kfree(pre_ct_attr); -err_attr: - kfree(ct_flow); - - return ERR_PTR(err); -} - struct mlx5_flow_handle * mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts) { - bool clear_action = attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR; struct mlx5_flow_handle *rule; if (!priv) return ERR_PTR(-EOPNOTSUPP); mutex_lock(&priv->control_lock); - - if (clear_action) - rule = __mlx5_tc_ct_flow_offload_clear(priv, spec, attr, mod_hdr_acts); - else - rule = __mlx5_tc_ct_flow_offload(priv, flow, spec, attr); + rule = __mlx5_tc_ct_flow_offload(priv, spec, attr); mutex_unlock(&priv->control_lock); return rule; @@ -2014,21 +1927,17 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, static void __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv, - struct mlx5e_tc_flow *flow, - struct mlx5_ct_flow *ct_flow) + struct mlx5_ct_flow *ct_flow, + struct mlx5_flow_attr *attr) { struct mlx5_flow_attr *pre_ct_attr = ct_flow->pre_ct_attr; struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev); - mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule, - pre_ct_attr); + mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule, pre_ct_attr); mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr); - if (ct_flow->post_act_handle) { - mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping); - mlx5e_tc_post_act_del(ct_priv->post_act, ct_flow->post_act_handle); - mlx5_tc_ct_del_ft_cb(ct_priv, ct_flow->ft); - } + mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping); + mlx5_tc_ct_del_ft_cb(ct_priv, ct_flow->ft); kfree(ct_flow->pre_ct_attr); kfree(ct_flow); @@ -2036,7 +1945,6 @@ __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv, void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { struct mlx5_ct_flow *ct_flow = attr->ct_attr.ct_flow; @@ -2048,7 +1956,7 @@ mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, return; mutex_lock(&priv->control_lock); - __mlx5_tc_ct_delete_flow(priv, flow, ct_flow); + __mlx5_tc_ct_delete_flow(priv, ct_flow, attr); mutex_unlock(&priv->control_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 99662af1e41a..2b21c7b97a52 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -116,13 +116,11 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_handle * mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts); void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr); bool @@ -183,7 +181,6 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, static inline struct mlx5_flow_handle * mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts) @@ -193,7 +190,6 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, static inline void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index f832c26ff2c3..f76624699a8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -37,6 +37,7 @@ struct mlx5e_tc_flow_parse_attr { const struct ip_tunnel_info *tun_info[MLX5_MAX_FLOW_FWD_VPORTS]; struct net_device *filter_dev; struct mlx5_flow_spec spec; + struct pedit_headers_action hdrs[__PEDIT_CMD_MAX]; struct mlx5e_tc_mod_hdr_acts mod_hdr_acts; int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; struct ethhdr eth; @@ -107,10 +108,20 @@ struct mlx5e_tc_flow { struct rcu_head rcu_head; struct completion init_done; struct completion del_hw_done; - int tunnel_id; /* the mapped tunnel id of this flow */ struct mlx5_flow_attr *attr; + struct list_head attrs; }; +struct mlx5_flow_handle * +mlx5e_tc_rule_offload(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr); + +void +mlx5e_tc_rule_unoffload(struct mlx5e_priv *priv, + struct mlx5_flow_handle *rule, + struct mlx5_flow_attr *attr); + u8 mlx5e_tc_get_ip_version(struct mlx5_flow_spec *spec, bool outer); struct mlx5_flow_handle * @@ -119,6 +130,12 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr); +struct mlx5_flow_attr * +mlx5e_tc_get_encap_attr(struct mlx5e_tc_flow *flow); + +void mlx5e_tc_unoffload_flow_post_acts(struct mlx5e_tc_flow *flow); +int mlx5e_tc_offload_flow_post_acts(struct mlx5e_tc_flow *flow); + bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow); bool mlx5e_is_ft_flow(struct mlx5e_tc_flow *flow); bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow); @@ -173,6 +190,7 @@ struct mlx5_flow_handle * mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec); + void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 9918ed8c059b..171bc6b36aa4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -173,19 +173,29 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, list_for_each_entry(flow, flow_list, tmp_list) { if (!mlx5e_is_offloaded_flow(flow) || !flow_flag_test(flow, SLOW)) continue; - attr = flow->attr; - esw_attr = attr->esw_attr; - spec = &attr->parse_attr->spec; + spec = &flow->attr->parse_attr->spec; + + attr = mlx5e_tc_get_encap_attr(flow); + esw_attr = attr->esw_attr; esw_attr->dests[flow->tmp_entry_index].pkt_reformat = e->pkt_reformat; esw_attr->dests[flow->tmp_entry_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; /* Do not offload flows with unresolved neighbors */ if (!mlx5e_tc_flow_all_encaps_valid(esw_attr)) continue; + + err = mlx5e_tc_offload_flow_post_acts(flow); + if (err) { + mlx5_core_warn(priv->mdev, "Failed to update flow post acts, %d\n", + err); + continue; + } + /* update from slow path rule to encap rule */ - rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, attr); + rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, flow->attr); if (IS_ERR(rule)) { + mlx5e_tc_unoffload_flow_post_acts(flow); err = PTR_ERR(rule); mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n", err); @@ -214,12 +224,13 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, list_for_each_entry(flow, flow_list, tmp_list) { if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW)) continue; - attr = flow->attr; - esw_attr = attr->esw_attr; - spec = &attr->parse_attr->spec; + spec = &flow->attr->parse_attr->spec; /* update from encap rule to slow path rule */ rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); + + attr = mlx5e_tc_get_encap_attr(flow); + esw_attr = attr->esw_attr; /* mark the flow's encap dest as non-valid */ esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; @@ -230,7 +241,8 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, continue; } - mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); + mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->attr); + mlx5e_tc_unoffload_flow_post_acts(flow); flow->rule[0] = rule; /* was unset when fast path rule removed */ flow_flag_set(flow, OFFLOADED); @@ -488,12 +500,17 @@ static void mlx5e_detach_encap_route(struct mlx5e_priv *priv, int out_index); void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index) + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + int out_index) { struct mlx5e_encap_entry *e = flow->encaps[out_index].e; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - if (flow->attr->esw_attr->dests[out_index].flags & + if (!mlx5e_is_eswitch_flow(flow)) + return; + + if (attr->esw_attr->dests[out_index].flags & MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) mlx5e_detach_encap_route(priv, flow, out_index); @@ -733,6 +750,7 @@ static unsigned int mlx5e_route_tbl_get_last_update(struct mlx5e_priv *priv) static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct mlx5e_encap_entry *e, bool new_encap_entry, unsigned long tbl_time_before, @@ -740,6 +758,7 @@ static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, @@ -748,7 +767,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_flow_attr *attr = flow->attr; const struct ip_tunnel_info *tun_info; unsigned long tbl_time_before = 0; struct mlx5e_encap_entry *e; @@ -834,8 +852,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, e->compl_result = 1; attach_flow: - err = mlx5e_attach_encap_route(priv, flow, e, entry_created, tbl_time_before, - out_index); + err = mlx5e_attach_encap_route(priv, flow, attr, e, entry_created, + tbl_time_before, out_index); if (err) goto out_err; @@ -1198,6 +1216,7 @@ out: static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct mlx5e_encap_entry *e, bool new_encap_entry, unsigned long tbl_time_before, @@ -1206,7 +1225,6 @@ static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; unsigned long tbl_time_after = tbl_time_before; struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_flow_attr *attr = flow->attr; const struct ip_tunnel_info *tun_info; struct mlx5_esw_flow_attr *esw_attr; struct mlx5e_route_entry *r; @@ -1357,17 +1375,19 @@ static void mlx5e_reoffload_encap(struct mlx5e_priv *priv, list_for_each_entry(flow, encap_flows, tmp_list) { struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_flow_handle *rule; + struct mlx5_flow_attr *attr; struct mlx5_flow_spec *spec; if (flow_flag_test(flow, FAILED)) continue; + spec = &flow->attr->parse_attr->spec; + + attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; parse_attr = attr->parse_attr; - spec = &parse_attr->spec; err = mlx5e_update_vf_tunnel(esw, esw_attr, &parse_attr->mod_hdr_acts, e->out_dev, e->route_dev_ifindex, @@ -1377,7 +1397,7 @@ static void mlx5e_reoffload_encap(struct mlx5e_priv *priv, continue; } - err = mlx5e_tc_add_flow_mod_hdr(priv, parse_attr, flow); + err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr); if (err) { mlx5_core_warn(priv->mdev, "Failed to update flow mod_hdr err=%d", err); @@ -1389,9 +1409,18 @@ static void mlx5e_reoffload_encap(struct mlx5e_priv *priv, esw_attr->dests[flow->tmp_entry_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; if (!mlx5e_tc_flow_all_encaps_valid(esw_attr)) goto offload_to_slow_path; + + err = mlx5e_tc_offload_flow_post_acts(flow); + if (err) { + mlx5_core_warn(priv->mdev, "Failed to update flow post acts, %d\n", + err); + goto offload_to_slow_path; + } + /* update from slow path rule to encap rule */ - rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, attr); + rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, flow->attr); if (IS_ERR(rule)) { + mlx5e_tc_unoffload_flow_post_acts(flow); err = PTR_ERR(rule); mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index 3391504d9a08..d542b8476491 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -7,15 +7,19 @@ #include "tc_priv.h" void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index); + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + int out_index); int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, struct net_device **encap_dev, bool *encap_valid); + int mlx5e_attach_decap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index b789af07829c..210d23bf3701 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -9,19 +9,6 @@ #define MLX5E_TX_WQE_EMPTY_DS_COUNT (sizeof(struct mlx5e_tx_wqe) / 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_TX_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) -#else -#define MLX5E_TX_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) -#endif - -#define MLX5E_TX_MPW_MAX_NUM_DS (MLX5E_TX_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS) - #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start)) #define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND) @@ -68,8 +55,6 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq); void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq); /* TX */ -u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev); netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq); @@ -308,9 +293,9 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma) void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit_more); void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq); -static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session) +static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs) { - return session->ds_count == MLX5E_TX_MPW_MAX_NUM_DS; + return session->ds_count == max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS; } static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq) @@ -431,10 +416,10 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, } } -static inline u16 mlx5e_stop_room_for_wqe(u16 wqe_size) -{ - BUILD_BUG_ON(PAGE_SIZE / MLX5_SEND_WQE_BB < MLX5_SEND_WQE_MAX_WQEBBS); +#define MLX5E_STOP_ROOM(wqebbs) ((wqebbs) * 2 - 1) +static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_size) +{ /* A WQE must not cross the page boundary, hence two conditions: * 1. Its size must not exceed the page size. * 2. If the WQE size is X, and the space remaining in a page is less @@ -443,18 +428,28 @@ static inline u16 mlx5e_stop_room_for_wqe(u16 wqe_size) * stop room of X-1 + X. * WQE size is also limited by the hardware limit. */ + WARN_ONCE(wqe_size > mlx5e_get_max_sq_wqebbs(mdev), + "wqe_size %u is greater than max SQ WQEBBs %u", + wqe_size, mlx5e_get_max_sq_wqebbs(mdev)); - if (__builtin_constant_p(wqe_size)) - BUILD_BUG_ON(wqe_size > MLX5_SEND_WQE_MAX_WQEBBS); - else - WARN_ON_ONCE(wqe_size > MLX5_SEND_WQE_MAX_WQEBBS); - return wqe_size * 2 - 1; + return MLX5E_STOP_ROOM(wqe_size); +} + +static inline u16 mlx5e_stop_room_for_max_wqe(struct mlx5_core_dev *mdev) +{ + return MLX5E_STOP_ROOM(mlx5e_get_max_sq_wqebbs(mdev)); } static inline bool mlx5e_icosq_can_post_wqe(struct mlx5e_icosq *sq, u16 wqe_size) { - u16 room = sq->reserved_room + mlx5e_stop_room_for_wqe(wqe_size); + u16 room = sq->reserved_room; + + WARN_ONCE(wqe_size > sq->max_sq_wqebbs, + "wqe_size %u is greater than max SQ WQEBBs %u", + wqe_size, sq->max_sq_wqebbs); + + room += MLX5E_STOP_ROOM(wqe_size); return mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 56e10c84a706..a7f020399370 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -199,7 +199,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) struct mlx5e_tx_wqe *wqe; u16 pi; - pi = mlx5e_xdpsq_get_next_pi(sq, MLX5E_TX_MPW_MAX_WQEBBS); + pi = mlx5e_xdpsq_get_next_pi(sq, sq->max_sq_mpw_wqebbs); wqe = MLX5E_TX_FETCH_WQE(sq, pi); net_prefetchw(wqe->data); @@ -245,10 +245,8 @@ enum { INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq) { if (unlikely(!sq->mpwqe.wqe)) { - const u16 stop_room = mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - stop_room))) { + sq->stop_room))) { /* SQ is full, ring doorbell */ mlx5e_xmit_xdp_doorbell(sq); sq->stats->full++; @@ -288,7 +286,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats); - if (unlikely(mlx5e_xdp_mpqwe_is_full(session))) + if (unlikely(mlx5e_xdp_mpqwe_is_full(session, sq->max_sq_mpw_wqebbs))) 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 8d991c3b7a50..c62f11d7ef6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -123,12 +123,13 @@ static inline bool mlx5e_xdp_get_inline_state(struct mlx5e_xdpsq *sq, bool cur) return cur; } -static inline bool mlx5e_xdp_mpqwe_is_full(struct mlx5e_tx_mpwqe *session) +static inline bool mlx5e_xdp_mpqwe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs) { if (session->inline_on) return session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > - MLX5E_TX_MPW_MAX_NUM_DS; - return mlx5e_tx_mpwqe_is_full(session); + max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS; + + return mlx5e_tx_mpwqe_is_full(session, max_sq_mpw_wqebbs); } struct mlx5e_xdp_wqe_info { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 9ad3459fb63a..aaf11c66bf4c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -32,9 +32,9 @@ u16 mlx5e_ktls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *pa num_dumps = mlx5e_ktls_dumps_num_wqes(params, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE); - stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS); - stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS); - stop_room += num_dumps * mlx5e_stop_room_for_wqe(MLX5E_KTLS_DUMP_WQEBBS); + stop_room += mlx5e_stop_room_for_wqe(mdev, MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS); + stop_room += mlx5e_stop_room_for_wqe(mdev, MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS); + stop_room += num_dumps * mlx5e_stop_room_for_wqe(mdev, MLX5E_KTLS_DUMP_WQEBBS); return stop_room; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c index 7a700f913582..a05580cea481 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c @@ -386,5 +386,5 @@ u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *par /* FPGA */ /* Resync SKB. */ - return mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + return mlx5e_stop_room_for_max_wqe(mdev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index a4c8d8d00d5a..d659fe07d464 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1142,7 +1142,7 @@ static int mlx5e_update_trust_state_hw(struct mlx5e_priv *priv, void *context) err = mlx5_set_trust_state(priv->mdev, *trust_state); if (err) return err; - priv->dcbx_dp.trust_state = *trust_state; + WRITE_ONCE(priv->dcbx_dp.trust_state, *trust_state); return 0; } @@ -1187,16 +1187,18 @@ static int mlx5e_set_dscp2prio(struct mlx5e_priv *priv, u8 dscp, u8 prio) static int mlx5e_trust_initialize(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; + u8 trust_state; int err; - priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP; - - if (!MLX5_DSCP_SUPPORTED(mdev)) + if (!MLX5_DSCP_SUPPORTED(mdev)) { + WRITE_ONCE(priv->dcbx_dp.trust_state, MLX5_QPTS_TRUST_PCP); return 0; + } - err = mlx5_query_trust_state(priv->mdev, &priv->dcbx_dp.trust_state); + err = mlx5_query_trust_state(priv->mdev, &trust_state); if (err) return err; + WRITE_ONCE(priv->dcbx_dp.trust_state, trust_state); mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &priv->channels.params, priv->dcbx_dp.trust_state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bf80fb612449..b2ed2f6d4a92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -72,12 +72,13 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { - bool striding_rq_umr = MLX5_CAP_GEN(mdev, striding_rq) && - MLX5_CAP_GEN(mdev, umr_ptr_rlky) && - MLX5_CAP_ETH(mdev, reg_umr_sq); - u16 max_wqe_sz_cap = MLX5_CAP_GEN(mdev, max_wqe_sz_sq); - bool inline_umr = MLX5E_UMR_WQE_INLINE_SZ <= max_wqe_sz_cap; + bool striding_rq_umr, inline_umr; + u16 max_wqe_sz_cap; + striding_rq_umr = MLX5_CAP_GEN(mdev, striding_rq) && MLX5_CAP_GEN(mdev, umr_ptr_rlky) && + MLX5_CAP_ETH(mdev, reg_umr_sq); + max_wqe_sz_cap = mlx5e_get_max_sq_wqebbs(mdev) * MLX5_SEND_WQE_BB; + inline_umr = max_wqe_sz_cap >= MLX5E_UMR_WQE_INLINE_SZ; if (!striding_rq_umr) return false; if (!inline_umr) { @@ -594,6 +595,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk)); + rq->mpwqe.min_wqe_bulk = mlx5e_mpwqe_get_min_wqe_bulk(wq_sz); rq->buff.frame0_sz = (1 << rq->mpwqe.log_stride_sz); @@ -1164,6 +1166,9 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, is_redirect ? &c->priv->channel_stats[c->ix]->xdpsq : &c->priv->channel_stats[c->ix]->rq_xdpsq; + sq->max_sq_wqebbs = mlx5e_get_max_sq_wqebbs(mdev); + sq->stop_room = MLX5E_STOP_ROOM(sq->max_sq_wqebbs); + sq->max_sq_mpw_wqebbs = mlx5e_get_sw_max_sq_mpw_wqebbs(sq->max_sq_wqebbs); param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -1238,6 +1243,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; sq->reserved_room = param->stop_room; + sq->max_sq_wqebbs = mlx5e_get_max_sq_wqebbs(mdev); param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -1313,7 +1319,6 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int err; sq->pdev = c->pdev; - sq->tstamp = c->tstamp; sq->clock = &mdev->clock; sq->mkey_be = c->mkey_be; sq->netdev = c->netdev; @@ -1324,6 +1329,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + sq->max_sq_wqebbs = mlx5e_get_max_sq_wqebbs(mdev); + sq->max_sq_mpw_wqebbs = mlx5e_get_sw_max_sq_mpw_wqebbs(sq->max_sq_wqebbs); 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); @@ -2677,39 +2684,41 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) struct mlx5e_txqsq *sq = &c->sq[tc]; priv->txq2sq[sq->txq_ix] = sq; - priv->channel_tc2realtxq[i][tc] = i + tc * ch; } } if (!priv->channels.ptp) - return; + goto out; if (!test_bit(MLX5E_PTP_STATE_TX, priv->channels.ptp->state)) - return; + goto out; for (tc = 0; tc < num_tc; tc++) { struct mlx5e_ptp *c = priv->channels.ptp; struct mlx5e_txqsq *sq = &c->ptpsq[tc].txqsq; priv->txq2sq[sq->txq_ix] = sq; - priv->port_ptp_tc2realtxq[tc] = priv->num_tc_x_num_ch + tc; } -} -static void mlx5e_update_num_tc_x_num_ch(struct mlx5e_priv *priv) -{ - /* Sync with mlx5e_select_queue. */ - WRITE_ONCE(priv->num_tc_x_num_ch, - mlx5e_get_dcb_num_tc(&priv->channels.params) * priv->channels.num); +out: + /* Make the change to txq2sq visible before the queue is started. + * As mlx5e_xmit runs under a spinlock, there is an implicit ACQUIRE, + * which pairs with this barrier. + */ + smp_wmb(); } void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { - mlx5e_update_num_tc_x_num_ch(priv); mlx5e_build_txq_maps(priv); mlx5e_activate_channels(&priv->channels); mlx5e_qos_activate_queues(priv); mlx5e_xdp_tx_enable(priv); + + /* dev_watchdog() wants all TX queues to be started when the carrier is + * OK, including the ones in range real_num_tx_queues..num_tx_queues-1. + * Make it happy to avoid TX timeout false alarms. + */ netif_tx_start_all_queues(priv->netdev); if (mlx5e_is_vport_rep(priv)) @@ -2729,11 +2738,13 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) if (mlx5e_is_vport_rep(priv)) mlx5e_remove_sqs_fwd_rules(priv); - /* FIXME: This is a W/A only for tx timeout watch dog false alarm when - * polling for inactive tx queues. + /* The results of ndo_select_queue are unreliable, while netdev config + * is being changed (real_num_tx_queues, num_tc). Stop all queues to + * prevent ndo_start_xmit from being called, so that it can assume that + * the selected queue is always valid. */ - netif_tx_stop_all_queues(priv->netdev); netif_tx_disable(priv->netdev); + mlx5e_xdp_tx_disable(priv); mlx5e_deactivate_channels(&priv->channels); } @@ -2793,6 +2804,7 @@ static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv, mlx5e_close_channels(&old_chs); priv->profile->update_rx(priv); + mlx5e_selq_apply(&priv->selq); out: mlx5e_activate_priv_channels(priv); @@ -2816,13 +2828,24 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv, return mlx5e_switch_priv_params(priv, params, preactivate, context); new_chs.params = *params; + + mlx5e_selq_prepare(&priv->selq, &new_chs.params, !!priv->htb.maj_id); + err = mlx5e_open_channels(priv, &new_chs); if (err) - return err; + goto err_cancel_selq; + err = mlx5e_switch_priv_channels(priv, &new_chs, preactivate, context); if (err) - mlx5e_close_channels(&new_chs); + goto err_close; + + return 0; + +err_close: + mlx5e_close_channels(&new_chs); +err_cancel_selq: + mlx5e_selq_cancel(&priv->selq); return err; } @@ -2862,6 +2885,8 @@ int mlx5e_open_locked(struct net_device *netdev) struct mlx5e_priv *priv = netdev_priv(netdev); int err; + mlx5e_selq_prepare(&priv->selq, &priv->channels.params, !!priv->htb.maj_id); + set_bit(MLX5E_STATE_OPENED, &priv->state); err = mlx5e_open_channels(priv, &priv->channels); @@ -2869,6 +2894,7 @@ int mlx5e_open_locked(struct net_device *netdev) goto err_clear_state_opened_flag; priv->profile->update_rx(priv); + mlx5e_selq_apply(&priv->selq); mlx5e_activate_priv_channels(priv); mlx5e_apply_traps(priv, true); if (priv->profile->update_carrier) @@ -2879,6 +2905,7 @@ int mlx5e_open_locked(struct net_device *netdev) err_clear_state_opened_flag: clear_bit(MLX5E_STATE_OPENED, &priv->state); + mlx5e_selq_cancel(&priv->selq); return err; } @@ -4637,11 +4664,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 priv->max_nch); mlx5e_params_mqprio_reset(params); - /* Set an initial non-zero value, so that mlx5e_select_queue won't - * divide by zero if called before first activating channels. - */ - priv->num_tc_x_num_ch = params->num_channels * params->mqprio.num_tc; - /* SQ */ params->log_sq_size = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE : @@ -5194,7 +5216,8 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, struct net_device *netdev, struct mlx5_core_dev *mdev) { - int nch, num_txqs, node, i; + int nch, num_txqs, node; + int err; num_txqs = netdev->num_tx_queues; nch = mlx5e_calc_max_nch(mdev, netdev, profile); @@ -5211,6 +5234,11 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, return -ENOMEM; mutex_init(&priv->state_lock); + + err = mlx5e_selq_init(&priv->selq, &priv->state_lock); + if (err) + goto err_free_cpumask; + hash_init(priv->htb.qos_tc2node); INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work); INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work); @@ -5219,7 +5247,7 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, priv->wq = create_singlethread_workqueue("mlx5e"); if (!priv->wq) - goto err_free_cpumask; + goto err_free_selq; priv->txq2sq = kcalloc_node(num_txqs, sizeof(*priv->txq2sq), GFP_KERNEL, node); if (!priv->txq2sq) @@ -5229,36 +5257,21 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, if (!priv->tx_rates) goto err_free_txq2sq; - priv->channel_tc2realtxq = - kcalloc_node(nch, sizeof(*priv->channel_tc2realtxq), GFP_KERNEL, node); - if (!priv->channel_tc2realtxq) - goto err_free_tx_rates; - - for (i = 0; i < nch; i++) { - priv->channel_tc2realtxq[i] = - kcalloc_node(profile->max_tc, sizeof(**priv->channel_tc2realtxq), - GFP_KERNEL, node); - if (!priv->channel_tc2realtxq[i]) - goto err_free_channel_tc2realtxq; - } - priv->channel_stats = kcalloc_node(nch, sizeof(*priv->channel_stats), GFP_KERNEL, node); if (!priv->channel_stats) - goto err_free_channel_tc2realtxq; + goto err_free_tx_rates; return 0; -err_free_channel_tc2realtxq: - while (--i >= 0) - kfree(priv->channel_tc2realtxq[i]); - kfree(priv->channel_tc2realtxq); err_free_tx_rates: kfree(priv->tx_rates); err_free_txq2sq: kfree(priv->txq2sq); err_destroy_workqueue: destroy_workqueue(priv->wq); +err_free_selq: + mlx5e_selq_cleanup(&priv->selq); err_free_cpumask: free_cpumask_var(priv->scratchpad.cpumask); return -ENOMEM; @@ -5275,12 +5288,12 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) for (i = 0; i < priv->stats_nch; i++) kvfree(priv->channel_stats[i]); kfree(priv->channel_stats); - for (i = 0; i < priv->max_nch; i++) - kfree(priv->channel_tc2realtxq[i]); - kfree(priv->channel_tc2realtxq); kfree(priv->tx_rates); kfree(priv->txq2sq); destroy_workqueue(priv->wq); + mutex_lock(&priv->state_lock); + mlx5e_selq_cleanup(&priv->selq); + mutex_unlock(&priv->state_lock); free_cpumask_var(priv->scratchpad.cpumask); for (i = 0; i < priv->htb.max_qos_sqs; i++) @@ -5346,6 +5359,7 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *prof } netif_carrier_off(netdev); + netif_tx_disable(netdev); dev_net_set(netdev, mlx5_core_net(mdev)); return netdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 06d1f46f1688..6b7e7ea6ded2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -55,6 +55,7 @@ #include "diag/en_rep_tracepoint.h" #include "en_accel/ipsec.h" #include "en/tc/int_port.h" +#include "en/ptp.h" #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \ max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE) @@ -401,13 +402,18 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; + int n, tc, nch, num_sqs = 0; struct mlx5e_channel *c; - int n, tc, num_sqs = 0; int err = -ENOMEM; + bool ptp_sq; u32 *sqs; - sqs = kcalloc(priv->channels.num * mlx5e_get_dcb_num_tc(&priv->channels.params), - sizeof(*sqs), GFP_KERNEL); + ptp_sq = !!(priv->channels.ptp && + MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_TX_PORT_TS)); + nch = priv->channels.num + ptp_sq; + + sqs = kcalloc(nch * mlx5e_get_dcb_num_tc(&priv->channels.params), sizeof(*sqs), + GFP_KERNEL); if (!sqs) goto out; @@ -416,6 +422,12 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) for (tc = 0; tc < c->num_tc; tc++) sqs[num_sqs++] = c->sq[tc].sqn; } + if (ptp_sq) { + struct mlx5e_ptp *ptp_ch = priv->channels.ptp; + + for (tc = 0; tc < ptp_ch->num_tc; tc++) + sqs[num_sqs++] = ptp_ch->ptpsq[tc].txqsq.sqn; + } err = mlx5e_sqs2vport_start(esw, rep, sqs, num_sqs); kfree(sqs); @@ -632,11 +644,6 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->mqprio.num_tc = 1; params->tunneled_offload_en = false; - /* Set an initial non-zero value, so that mlx5e_select_queue won't - * divide by zero if called before first activating channels. - */ - priv->num_tc_x_num_ch = params->num_channels * params->mqprio.num_tc; - mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); } @@ -935,15 +942,21 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } + err = mlx5e_tc_ht_init(&rpriv->tc_ht); + if (err) + goto err_ht_init; + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_init_uplink_rep_tx(rpriv); if (err) - goto destroy_tises; + goto err_init_tx; } return 0; -destroy_tises: +err_init_tx: + mlx5e_tc_ht_cleanup(&rpriv->tc_ht); +err_ht_init: mlx5e_destroy_tises(priv); return err; } @@ -963,6 +976,8 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) mlx5e_cleanup_uplink_rep_tx(rpriv); + + mlx5e_tc_ht_cleanup(&rpriv->tc_ht); } static void mlx5e_rep_enable(struct mlx5e_priv *priv) @@ -1099,6 +1114,7 @@ static mlx5e_stats_grp_t mlx5e_ul_rep_stats_grps[] = { &MLX5E_STATS_GRP(ipsec_sw), &MLX5E_STATS_GRP(ipsec_hw), #endif + &MLX5E_STATS_GRP(ptp), }; static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index b01dacb6f527..0b619c7846d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -64,11 +64,6 @@ struct mlx5e_tc_tun_encap; struct mlx5e_post_act; struct mlx5_rep_uplink_priv { - /* Filters DB - instantiated by the uplink representor and shared by - * the uplink's VFs - */ - struct rhashtable tc_ht; - /* indirect block callbacks are invoked on bind/unbind events * on registered higher level devices (e.g. tunnel devices) * @@ -113,6 +108,7 @@ struct mlx5e_rep_priv { 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 rhashtable tc_ht; }; static inline diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index ee0a8f5206e3..4cb7c7135b6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -620,7 +620,7 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) struct mlx5e_icosq *sq = rq->icosq; int i, err, max_klm_entries, len; - max_klm_entries = MLX5E_MAX_KLM_PER_WQE; + max_klm_entries = MLX5E_MAX_KLM_PER_WQE(rq->mdev); klm_entries = bitmap_find_window(shampo->bitmap, shampo->hd_per_wqe, shampo->hd_per_wq, shampo->pi); @@ -960,8 +960,7 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) if (unlikely(rq->mpwqe.umr_in_progress > rq->mpwqe.umr_last_bulk)) rq->stats->congst_umr++; -#define UMR_WQE_BULK (2) - if (likely(missing < UMR_WQE_BULK)) + if (likely(missing < rq->mpwqe.min_wqe_bulk)) return false; if (rq->page_pool) @@ -1489,7 +1488,7 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq, static inline struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va, u32 frag_size, u16 headroom, - u32 cqe_bcnt) + u32 cqe_bcnt, u32 metasize) { struct sk_buff *skb = build_skb(va, frag_size); @@ -1501,6 +1500,9 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va, skb_reserve(skb, headroom); skb_put(skb, cqe_bcnt); + if (metasize) + skb_metadata_set(skb, metasize); + return skb; } @@ -1508,7 +1510,7 @@ static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom, u32 len, struct xdp_buff *xdp) { xdp_init_buff(xdp, rq->buff.frame0_sz, &rq->xdp_rxq); - xdp_prepare_buff(xdp, va, headroom, len, false); + xdp_prepare_buff(xdp, va, headroom, len, true); } static struct sk_buff * @@ -1521,6 +1523,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct sk_buff *skb; void *va, *data; u32 frag_size; + u32 metasize; va = page_address(di->page) + wi->offset; data = va + rx_headroom; @@ -1537,7 +1540,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, rx_headroom = xdp.data - xdp.data_hard_start; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt); - skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt); + metasize = xdp.data - xdp.data_meta; + skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt, metasize); if (unlikely(!skb)) return NULL; @@ -1836,6 +1840,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct sk_buff *skb; void *va, *data; u32 frag_size; + u32 metasize; /* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -1861,7 +1866,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, rx_headroom = xdp.data - xdp.data_hard_start; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32); - skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32); + metasize = xdp.data - xdp.data_meta; + skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32, metasize); if (unlikely(!skb)) return NULL; @@ -1892,7 +1898,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, DMA_FROM_DEVICE); prefetchw(hdr); prefetch(data); - skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size); + skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size, 0); if (unlikely(!skb)) return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 26e326fe503c..3e5d8c788026 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -2348,7 +2348,7 @@ MLX5E_DEFINE_STATS_GRP(channels, 0); MLX5E_DEFINE_STATS_GRP(per_port_buff_congest, 0); MLX5E_DEFINE_STATS_GRP(eth_ext, 0); static MLX5E_DEFINE_STATS_GRP(tls, 0); -static MLX5E_DEFINE_STATS_GRP(ptp, 0); +MLX5E_DEFINE_STATS_GRP(ptp, 0); static MLX5E_DEFINE_STATS_GRP(qos, 0); /* The stats groups order is opposite to the update_stats() order calls */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 2c1ed5b81be6..14eaf923e7b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -459,5 +459,6 @@ extern MLX5E_DECLARE_STATS_GRP(channels); extern MLX5E_DECLARE_STATS_GRP(per_port_buff_congest); extern MLX5E_DECLARE_STATS_GRP(ipsec_hw); extern MLX5E_DECLARE_STATS_GRP(ipsec_sw); +extern MLX5E_DECLARE_STATS_GRP(ptp); #endif /* __MLX5_EN_STATS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 2022fa4a9598..76a015dfc5fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -115,6 +115,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { static struct lock_class_key tc_ht_lock_key; static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); +static void free_flow_post_acts(struct mlx5e_tc_flow *flow); void mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec, @@ -273,6 +274,23 @@ get_sample_priv(struct mlx5e_priv *priv) return NULL; } +static struct mlx5e_post_act * +get_post_action(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_rep_uplink_priv *uplink_priv; + struct mlx5e_rep_priv *uplink_rpriv; + + if (is_mdev_switchdev_mode(priv->mdev)) { + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + uplink_priv = &uplink_rpriv->uplink_priv; + + return uplink_priv->post_act; + } + + return priv->fs.tc.post_act; +} + struct mlx5_flow_handle * mlx5_tc_rule_insert(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, @@ -295,13 +313,62 @@ mlx5_tc_rule_delete(struct mlx5e_priv *priv, if (is_mdev_switchdev_mode(priv->mdev)) { mlx5_eswitch_del_offloaded_rule(esw, rule, attr); - return; } mlx5e_del_offloaded_nic_rule(priv, rule, attr); } +struct mlx5_flow_handle * +mlx5e_tc_rule_offload(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + if (attr->flags & MLX5_ATTR_FLAG_CT) { + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = + &attr->parse_attr->mod_hdr_acts; + + return mlx5_tc_ct_flow_offload(get_ct_priv(priv), + spec, attr, + mod_hdr_acts); + } + + if (!is_mdev_switchdev_mode(priv->mdev)) + return mlx5e_add_offloaded_nic_rule(priv, spec, attr); + + if (attr->flags & MLX5_ATTR_FLAG_SAMPLE) + return mlx5e_tc_sample_offload(get_sample_priv(priv), spec, attr); + + return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); +} + +void +mlx5e_tc_rule_unoffload(struct mlx5e_priv *priv, + struct mlx5_flow_handle *rule, + struct mlx5_flow_attr *attr) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + if (attr->flags & MLX5_ATTR_FLAG_CT) { + mlx5_tc_ct_delete_flow(get_ct_priv(priv), attr); + return; + } + + if (!is_mdev_switchdev_mode(priv->mdev)) { + mlx5e_del_offloaded_nic_rule(priv, rule, attr); + return; + } + + if (attr->flags & MLX5_ATTR_FLAG_SAMPLE) { + mlx5e_tc_sample_unoffload(get_sample_priv(priv), rule, attr); + return; + } + + mlx5_eswitch_del_offloaded_rule(esw, rule, attr); +} + int mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, @@ -1039,6 +1106,21 @@ err_ft_get: } static int +alloc_flow_attr_counter(struct mlx5_core_dev *counter_dev, + struct mlx5_flow_attr *attr) + +{ + struct mlx5_fc *counter; + + counter = mlx5_fc_create(counter_dev, true); + if (IS_ERR(counter)) + return PTR_ERR(counter); + + attr->counter = counter; + return 0; +} + +static int mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) @@ -1046,7 +1128,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_core_dev *dev = priv->mdev; - struct mlx5_fc *counter; int err; parse_attr = attr->parse_attr; @@ -1058,11 +1139,9 @@ 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)) - return PTR_ERR(counter); - - attr->counter = counter; + err = alloc_flow_attr_counter(dev, attr); + if (err) + return err; } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { @@ -1072,8 +1151,8 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, return err; } - if (flow_flag_test(flow, CT)) - flow->rule[0] = mlx5_tc_ct_flow_offload(get_ct_priv(priv), flow, &parse_attr->spec, + if (attr->flags & MLX5_ATTR_FLAG_CT) + flow->rule[0] = mlx5_tc_ct_flow_offload(get_ct_priv(priv), &parse_attr->spec, attr, &parse_attr->mod_hdr_acts); else flow->rule[0] = mlx5e_add_offloaded_nic_rule(priv, &parse_attr->spec, @@ -1107,8 +1186,8 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, flow_flag_clear(flow, OFFLOADED); - if (flow_flag_test(flow, CT)) - mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); + if (attr->flags & MLX5_ATTR_FLAG_CT) + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); else if (!IS_ERR_OR_NULL(flow->rule[0])) mlx5e_del_offloaded_nic_rule(priv, flow->rule[0], attr); @@ -1132,6 +1211,8 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, if (flow_flag_test(flow, HAIRPIN)) mlx5e_hairpin_flow_del(priv, flow); + free_flow_post_acts(flow); + kvfree(attr->parse_attr); kfree(flow->attr); } @@ -1142,40 +1223,27 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) { - struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts; struct mlx5_flow_handle *rule; - if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) + if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); - if (flow_flag_test(flow, CT)) { - mod_hdr_acts = &attr->parse_attr->mod_hdr_acts; - - rule = mlx5_tc_ct_flow_offload(get_ct_priv(flow->priv), - flow, spec, attr, - mod_hdr_acts); - } else if (flow_flag_test(flow, SAMPLE)) { - rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr, - mlx5e_tc_get_flow_tun_id(flow)); - } else { - rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); - } + rule = mlx5e_tc_rule_offload(flow->priv, spec, attr); if (IS_ERR(rule)) return rule; if (attr->esw_attr->split_count) { flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, spec, attr); - if (IS_ERR(flow->rule[1])) { - if (flow_flag_test(flow, CT)) - mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); - else - mlx5_eswitch_del_offloaded_rule(esw, rule, attr); - return flow->rule[1]; - } + if (IS_ERR(flow->rule[1])) + goto err_rule1; } return rule; + +err_rule1: + mlx5e_tc_rule_unoffload(flow->priv, rule, attr); + return flow->rule[1]; } void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, @@ -1184,19 +1252,13 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, { flow_flag_clear(flow, OFFLOADED); - if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) - goto offload_rule_0; + if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) + return mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); if (attr->esw_attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); - if (flow_flag_test(flow, CT)) - mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); - else if (flow_flag_test(flow, SAMPLE)) - mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); - else -offload_rule_0: - mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); + mlx5e_tc_rule_unoffload(flow->priv, flow->rule[0], attr); } struct mlx5_flow_handle * @@ -1214,7 +1276,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ); slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->esw_attr->split_count = 0; - slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); if (!IS_ERR(rule)) @@ -1239,7 +1301,7 @@ void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ); slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->esw_attr->split_count = 0; - slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); flow_flag_clear(flow, SLOW); kfree(slow_attr); @@ -1348,10 +1410,10 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro } int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) { - struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &parse_attr->mod_hdr_acts; + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &attr->parse_attr->mod_hdr_acts; struct mlx5_modify_hdr *mod_hdr; mod_hdr = mlx5_modify_header_alloc(priv->mdev, @@ -1361,13 +1423,107 @@ int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, if (IS_ERR(mod_hdr)) return PTR_ERR(mod_hdr); - WARN_ON(flow->attr->modify_hdr); - flow->attr->modify_hdr = mod_hdr; + WARN_ON(attr->modify_hdr); + attr->modify_hdr = mod_hdr; return 0; } static int +set_encap_dests(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *encap_valid, + bool *vf_tun) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct mlx5_esw_flow_attr *esw_attr; + struct net_device *encap_dev = NULL; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *out_priv; + int out_index; + int err = 0; + + if (!mlx5e_is_eswitch_flow(flow)) + return 0; + + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; + *vf_tun = false; + *encap_valid = true; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; + int mirred_ifindex; + + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mirred_ifindex = parse_attr->mirred_ifindex[out_index]; + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto out; + } + err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, + extack, &encap_dev, encap_valid); + dev_put(out_dev); + if (err) + goto out; + + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) + *vf_tun = true; + + out_priv = netdev_priv(encap_dev); + rpriv = out_priv->ppriv; + esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].mdev = out_priv->mdev; + } + + if (*vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto out; + } + +out: + return err; +} + +static void +clean_encap_dests(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + bool *vf_tun) +{ + struct mlx5_esw_flow_attr *esw_attr; + int out_index; + + if (!mlx5e_is_eswitch_flow(flow)) + return; + + esw_attr = attr->esw_attr; + *vf_tun = false; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) + *vf_tun = true; + + mlx5e_detach_encap(priv, flow, attr, out_index); + kfree(attr->parse_attr->tun_info[out_index]); + } +} + +static int mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) @@ -1375,15 +1531,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; - bool vf_tun = false, encap_valid = true; - struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *out_priv; - struct mlx5_fc *counter; + bool vf_tun, encap_valid; u32 max_prio, max_chain; int err = 0; - int out_index; parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; @@ -1472,50 +1623,17 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; } - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - struct net_device *out_dev; - int mirred_ifindex; - - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); - if (!out_dev) { - NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); - err = -ENODEV; - goto err_out; - } - err = mlx5e_attach_encap(priv, flow, out_dev, out_index, - extack, &encap_dev, &encap_valid); - dev_put(out_dev); - if (err) - goto err_out; - - if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && - !esw_attr->dest_int_port) - vf_tun = true; - out_priv = netdev_priv(encap_dev); - rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; - esw_attr->dests[out_index].mdev = out_priv->mdev; - } - - if (vf_tun && esw_attr->out_count > 1) { - NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); - err = -EOPNOTSUPP; + err = set_encap_dests(priv, flow, attr, extack, &encap_valid, &vf_tun); + if (err) goto err_out; - } err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) goto err_out; - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && - !(attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR)) { + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { if (vf_tun) { - err = mlx5e_tc_add_flow_mod_hdr(priv, parse_attr, flow); + err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr); if (err) goto err_out; } else { @@ -1526,20 +1644,16 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { - counter = mlx5_fc_create(esw_attr->counter_dev, true); - if (IS_ERR(counter)) { - err = PTR_ERR(counter); + err = alloc_flow_attr_counter(esw_attr->counter_dev, attr); + if (err) goto err_out; - } - - attr->counter = counter; } /* we get here if one of the following takes place: * (1) there's no error * (2) there's an encap action and we don't have valid neigh */ - if (!encap_valid) + if (!encap_valid || flow_flag_test(flow, SLOW)) flow->rule[0] = mlx5e_tc_offload_to_slow_path(esw, flow, &parse_attr->spec); else flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); @@ -1576,8 +1690,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - bool vf_tun = false; - int out_index; + bool vf_tun; esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); @@ -1601,16 +1714,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (flow->decap_route) mlx5e_detach_decap_route(priv, flow); - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && - !esw_attr->dest_int_port) - vf_tun = true; - if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) { - mlx5e_detach_encap(priv, flow, out_index); - kfree(attr->parse_attr->tun_info[out_index]); - } - } + clean_encap_dests(priv, flow, attr, &vf_tun); mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); @@ -1634,7 +1738,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); - kfree(attr->sample_attr); + free_flow_post_acts(flow); + kvfree(attr->esw_attr->rx_tun_attr); kvfree(attr->parse_attr); kfree(flow->attr); @@ -1642,7 +1747,10 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) { - return flow->attr->counter; + struct mlx5_flow_attr *attr; + + attr = list_first_entry(&flow->attrs, struct mlx5_flow_attr, list); + return attr->counter; } /* Iterate over tmp_list of flows attached to flow_list head. */ @@ -1854,7 +1962,7 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv, attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; } - flow->tunnel_id = value; + flow->attr->tunnel_id = value; return 0; err_set: @@ -1868,8 +1976,8 @@ err_enc_opts: static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow) { - u32 enc_opts_id = flow->tunnel_id & ENC_OPTS_BITS_MASK; - u32 tun_id = flow->tunnel_id >> ENC_OPTS_BITS; + u32 enc_opts_id = flow->attr->tunnel_id & ENC_OPTS_BITS_MASK; + u32 tun_id = flow->attr->tunnel_id >> ENC_OPTS_BITS; struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; struct mlx5_eswitch *esw; @@ -1885,11 +1993,6 @@ static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow) enc_opts_id); } -u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow) -{ - return flow->tunnel_id; -} - void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev, struct flow_match_basic *match, bool outer, void *headers_c, void *headers_v) @@ -2811,14 +2914,15 @@ static unsigned long mask_to_le(unsigned long mask, int size) return mask; } + static int offload_pedit_fields(struct mlx5e_priv *priv, int namespace, - struct pedit_headers_action *hdrs, struct mlx5e_tc_flow_parse_attr *parse_attr, u32 *action_flags, struct netlink_ext_ack *extack) { struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; + struct pedit_headers_action *hdrs = parse_attr->hdrs; void *headers_c, *headers_v, *action, *vals_p; u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; @@ -2944,35 +3048,43 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, static const struct pedit_headers zero_masks = {}; -static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, - u32 *action_flags, - struct netlink_ext_ack *extack) +static int verify_offload_pedit_fields(struct mlx5e_priv *priv, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { struct pedit_headers *cmd_masks; - int err; u8 cmd; - err = offload_pedit_fields(priv, namespace, hdrs, parse_attr, - action_flags, extack); - if (err < 0) - goto out_dealloc_parsed_actions; - for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) { - cmd_masks = &hdrs[cmd].masks; + cmd_masks = &parse_attr->hdrs[cmd].masks; if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) { - NL_SET_ERR_MSG_MOD(extack, - "attempt to offload an unsupported field"); + NL_SET_ERR_MSG_MOD(extack, "attempt to offload an unsupported field"); netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd); print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS, 16, 1, cmd_masks, sizeof(zero_masks), true); - err = -EOPNOTSUPP; - goto out_dealloc_parsed_actions; + return -EOPNOTSUPP; } } return 0; +} + +static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace, + struct mlx5e_tc_flow_parse_attr *parse_attr, + u32 *action_flags, + struct netlink_ext_ack *extack) +{ + int err; + + err = offload_pedit_fields(priv, namespace, parse_attr, action_flags, extack); + if (err) + goto out_dealloc_parsed_actions; + + err = verify_offload_pedit_fields(priv, parse_attr, extack); + if (err) + goto out_dealloc_parsed_actions; + + return 0; out_dealloc_parsed_actions: mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts); @@ -3176,11 +3288,11 @@ actions_match_supported_fdb(struct mlx5e_priv *priv, static bool actions_match_supported(struct mlx5e_priv *priv, struct flow_action *flow_action, + u32 actions, struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { - u32 actions = flow->attr->action; bool ct_flow, ct_clear; ct_clear = flow->attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR; @@ -3236,57 +3348,13 @@ bool mlx5e_same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) } static int -parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, - struct flow_action *flow_action) -{ - struct netlink_ext_ack *extack = parse_state->extack; - struct mlx5e_tc_flow *flow = parse_state->flow; - struct mlx5_flow_attr *attr = flow->attr; - enum mlx5_flow_namespace_type ns_type; - struct mlx5e_priv *priv = flow->priv; - const struct flow_action_entry *act; - struct mlx5e_tc_act *tc_act; - int err, i; - - ns_type = mlx5e_get_flow_namespace(flow); - - flow_action_for_each(i, act, flow_action) { - tc_act = mlx5e_tc_act_get(act->id, ns_type); - if (!tc_act) { - NL_SET_ERR_MSG_MOD(extack, "Not implemented offload action"); - return -EOPNOTSUPP; - } - - if (!tc_act->can_offload(parse_state, act, i)) - return -EOPNOTSUPP; - - err = tc_act->parse_action(parse_state, act, priv, attr); - if (err) - return err; - } - - flow_action_for_each(i, act, flow_action) { - tc_act = mlx5e_tc_act_get(act->id, ns_type); - if (!tc_act || !tc_act->post_parse || - !tc_act->can_offload(parse_state, act, i)) - continue; - - err = tc_act->post_parse(parse_state, priv, attr); - if (err) - return err; - } - - return 0; -} - -static int actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, - struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; + struct pedit_headers_action *hdrs = parse_attr->hdrs; enum mlx5_flow_namespace_type ns_type; int err; @@ -3296,8 +3364,7 @@ actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv, ns_type = mlx5e_get_flow_namespace(flow); - err = alloc_tc_pedit_action(priv, ns_type, parse_attr, hdrs, - &attr->action, extack); + err = alloc_tc_pedit_action(priv, ns_type, parse_attr, &attr->action, extack); if (err) return err; @@ -3318,6 +3385,299 @@ actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv, return 0; } +static struct mlx5_flow_attr* +mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr, + enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr; + u32 attr_sz = ns_to_attr_sz(ns_type); + struct mlx5_flow_attr *attr2; + + attr2 = mlx5_alloc_flow_attr(ns_type); + parse_attr = kvzalloc(sizeof(*parse_attr), GFP_KERNEL); + if (!attr2 || !parse_attr) { + kvfree(parse_attr); + kfree(attr2); + return attr2; + } + + memcpy(attr2, attr, attr_sz); + INIT_LIST_HEAD(&attr2->list); + parse_attr->filter_dev = attr->parse_attr->filter_dev; + attr2->action = 0; + attr2->flags = 0; + attr2->parse_attr = parse_attr; + return attr2; +} + +static struct mlx5_core_dev * +get_flow_counter_dev(struct mlx5e_tc_flow *flow) +{ + return mlx5e_is_eswitch_flow(flow) ? flow->attr->esw_attr->counter_dev : flow->priv->mdev; +} + +struct mlx5_flow_attr * +mlx5e_tc_get_encap_attr(struct mlx5e_tc_flow *flow) +{ + struct mlx5_esw_flow_attr *esw_attr; + struct mlx5_flow_attr *attr; + int i; + + list_for_each_entry(attr, &flow->attrs, list) { + esw_attr = attr->esw_attr; + for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) { + if (esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) + return attr; + } + } + + return NULL; +} + +void +mlx5e_tc_unoffload_flow_post_acts(struct mlx5e_tc_flow *flow) +{ + struct mlx5e_post_act *post_act = get_post_action(flow->priv); + struct mlx5_flow_attr *attr; + + list_for_each_entry(attr, &flow->attrs, list) { + if (list_is_last(&attr->list, &flow->attrs)) + break; + + mlx5e_tc_post_act_unoffload(post_act, attr->post_act_handle); + } +} + +static void +free_flow_post_acts(struct mlx5e_tc_flow *flow) +{ + struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); + struct mlx5e_post_act *post_act = get_post_action(flow->priv); + struct mlx5_flow_attr *attr, *tmp; + bool vf_tun; + + list_for_each_entry_safe(attr, tmp, &flow->attrs, list) { + if (list_is_last(&attr->list, &flow->attrs)) + break; + + if (attr->post_act_handle) + mlx5e_tc_post_act_del(post_act, attr->post_act_handle); + + clean_encap_dests(flow->priv, flow, attr, &vf_tun); + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) + mlx5_fc_destroy(counter_dev, attr->counter); + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); + if (attr->modify_hdr) + mlx5_modify_header_dealloc(flow->priv->mdev, attr->modify_hdr); + } + + list_del(&attr->list); + kvfree(attr->parse_attr); + kfree(attr); + } +} + +int +mlx5e_tc_offload_flow_post_acts(struct mlx5e_tc_flow *flow) +{ + struct mlx5e_post_act *post_act = get_post_action(flow->priv); + struct mlx5_flow_attr *attr; + int err = 0; + + list_for_each_entry(attr, &flow->attrs, list) { + if (list_is_last(&attr->list, &flow->attrs)) + break; + + err = mlx5e_tc_post_act_offload(post_act, attr->post_act_handle); + if (err) + break; + } + + return err; +} + +/* TC filter rule HW translation: + * + * +---------------------+ + * + ft prio (tc chain) + + * + original match + + * +---------------------+ + * | + * | if multi table action + * | + * v + * +---------------------+ + * + post act ft |<----. + * + match fte id | | split on multi table action + * + do actions |-----' + * +---------------------+ + * | + * | + * v + * Do rest of the actions after last multi table action. + */ +static int +alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) +{ + struct mlx5e_post_act *post_act = get_post_action(flow->priv); + struct mlx5_flow_attr *attr, *next_attr = NULL; + struct mlx5e_post_act_handle *handle; + bool vf_tun, encap_valid = true; + int err; + + /* This is going in reverse order as needed. + * The first entry is the last attribute. + */ + list_for_each_entry(attr, &flow->attrs, list) { + if (!next_attr) { + /* Set counter action on last post act rule. */ + attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + } else { + err = mlx5e_tc_act_set_next_post_act(flow, attr, next_attr); + if (err) + goto out_free; + } + + /* Don't add post_act rule for first attr (last in the list). + * It's being handled by the caller. + */ + if (list_is_last(&attr->list, &flow->attrs)) + break; + + err = set_encap_dests(flow->priv, flow, attr, extack, &encap_valid, &vf_tun); + if (err) + goto out_free; + + if (!encap_valid) + flow_flag_set(flow, SLOW); + + err = actions_prepare_mod_hdr_actions(flow->priv, flow, attr, extack); + if (err) + goto out_free; + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + err = mlx5e_tc_add_flow_mod_hdr(flow->priv, flow, attr); + if (err) + goto out_free; + } + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + err = alloc_flow_attr_counter(get_flow_counter_dev(flow), attr); + if (err) + goto out_free; + } + + handle = mlx5e_tc_post_act_add(post_act, attr); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_free; + } + + attr->post_act_handle = handle; + next_attr = attr; + } + + if (flow_flag_test(flow, SLOW)) + goto out; + + err = mlx5e_tc_offload_flow_post_acts(flow); + if (err) + goto out_free; + +out: + return 0; + +out_free: + free_flow_post_acts(flow); + return err; +} + +static int +parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, + struct flow_action *flow_action) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow_action flow_action_reorder; + struct mlx5e_tc_flow *flow = parse_state->flow; + struct mlx5_flow_attr *attr = flow->attr; + enum mlx5_flow_namespace_type ns_type; + struct mlx5e_priv *priv = flow->priv; + struct flow_action_entry *act, **_act; + struct mlx5e_tc_act *tc_act; + int err, i; + + flow_action_reorder.num_entries = flow_action->num_entries; + flow_action_reorder.entries = kcalloc(flow_action->num_entries, + sizeof(flow_action), GFP_KERNEL); + if (!flow_action_reorder.entries) + return -ENOMEM; + + mlx5e_tc_act_reorder_flow_actions(flow_action, &flow_action_reorder); + + ns_type = mlx5e_get_flow_namespace(flow); + list_add(&attr->list, &flow->attrs); + + flow_action_for_each(i, _act, &flow_action_reorder) { + act = *_act; + tc_act = mlx5e_tc_act_get(act->id, ns_type); + if (!tc_act) { + NL_SET_ERR_MSG_MOD(extack, "Not implemented offload action"); + err = -EOPNOTSUPP; + goto out_free; + } + + if (!tc_act->can_offload(parse_state, act, i, attr)) { + err = -EOPNOTSUPP; + goto out_free; + } + + err = tc_act->parse_action(parse_state, act, priv, attr); + if (err) + goto out_free; + + parse_state->actions |= attr->action; + + /* Split attr for multi table act if not the last act. */ + if (tc_act->is_multi_table_act && + tc_act->is_multi_table_act(priv, act, attr) && + i < flow_action_reorder.num_entries - 1) { + err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + if (err) + goto out_free; + + attr = mlx5e_clone_flow_attr_for_post_act(flow->attr, ns_type); + if (!attr) { + err = -ENOMEM; + goto out_free; + } + + list_add(&attr->list, &flow->attrs); + } + } + + kfree(flow_action_reorder.entries); + + err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + if (err) + goto out_free_post_acts; + + err = alloc_flow_post_acts(flow, extack); + if (err) + goto out_free_post_acts; + + return 0; + +out_free: + kfree(flow_action_reorder.entries); +out_free_post_acts: + free_flow_post_acts(flow); + + return err; +} + static int flow_action_supported(struct flow_action *flow_action, struct netlink_ext_ack *extack) @@ -3345,7 +3705,6 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, struct mlx5e_tc_act_parse_state *parse_state; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; - struct pedit_headers_action *hdrs; int err; err = flow_action_supported(flow_action, extack); @@ -3357,17 +3716,17 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, parse_state = &parse_attr->parse_state; mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack); parse_state->ct_priv = get_ct_priv(priv); - hdrs = parse_state->hdrs; err = parse_tc_actions(parse_state, flow_action); if (err) return err; - err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); + err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack); if (err) return err; - if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) + if (!actions_match_supported(priv, flow_action, parse_state->actions, + parse_attr, flow, extack)) return -EOPNOTSUPP; return 0; @@ -3468,7 +3827,6 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - struct pedit_headers_action *hdrs; int err; err = flow_action_supported(flow_action, extack); @@ -3480,7 +3838,6 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, parse_state = &parse_attr->parse_state; mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack); parse_state->ct_priv = get_ct_priv(priv); - hdrs = parse_state->hdrs; err = parse_tc_actions(parse_state, flow_action); if (err) @@ -3494,11 +3851,12 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); + err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack); if (err) return err; - if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) + if (!actions_match_supported(priv, flow_action, parse_state->actions, + parse_attr, flow, extack)) return -EOPNOTSUPP; return 0; @@ -3533,12 +3891,11 @@ static const struct rhashtable_params tc_ht_params = { 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; + struct mlx5e_rep_priv *rpriv; if (flags & MLX5_TC_FLAG(ESW_OFFLOAD)) { - uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); - return &uplink_rpriv->uplink_priv.tc_ht; + rpriv = priv->ppriv; + return &rpriv->tc_ht; } else /* NIC offload */ return &priv->fs.tc.ht; } @@ -3573,7 +3930,12 @@ mlx5_alloc_flow_attr(enum mlx5_flow_namespace_type type) sizeof(struct mlx5_nic_flow_attr); struct mlx5_flow_attr *attr; - return kzalloc(sizeof(*attr) + ex_attr_size, GFP_KERNEL); + attr = kzalloc(sizeof(*attr) + ex_attr_size, GFP_KERNEL); + if (!attr) + return attr; + + INIT_LIST_HEAD(&attr->list); + return attr; } static int @@ -3607,6 +3969,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, INIT_LIST_HEAD(&flow->encaps[out_index].list); INIT_LIST_HEAD(&flow->hairpin); INIT_LIST_HEAD(&flow->l3_to_l2_reformat); + INIT_LIST_HEAD(&flow->attrs); refcount_set(&flow->refcnt, 1); init_completion(&flow->init_done); init_completion(&flow->del_hw_done); @@ -4371,10 +4734,27 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) mlx5_chains_destroy(tc->chains); } -int mlx5e_tc_esw_init(struct rhashtable *tc_ht) +int mlx5e_tc_ht_init(struct rhashtable *tc_ht) +{ + int err; + + err = rhashtable_init(tc_ht, &tc_ht_params); + if (err) + return err; + + lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key); + + return 0; +} + +void mlx5e_tc_ht_cleanup(struct rhashtable *tc_ht) +{ + rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL); +} + +int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) { const size_t sz_enc_opts = sizeof(struct tunnel_match_enc_opts); - struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *rpriv; struct mapping_ctx *mapping; struct mlx5_eswitch *esw; @@ -4382,7 +4762,6 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) u64 mapping_id; int err = 0; - uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht); rpriv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv); priv = netdev_priv(rpriv->netdev); esw = priv->mdev->priv.eswitch; @@ -4422,12 +4801,6 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) } uplink_priv->tunnel_enc_opts_mapping = mapping; - err = rhashtable_init(tc_ht, &tc_ht_params); - if (err) - goto err_ht_init; - - lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key); - uplink_priv->encap = mlx5e_tc_tun_init(priv); if (IS_ERR(uplink_priv->encap)) { err = PTR_ERR(uplink_priv->encap); @@ -4437,8 +4810,6 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) return 0; err_register_fib_notifier: - rhashtable_destroy(tc_ht); -err_ht_init: mapping_destroy(uplink_priv->tunnel_enc_opts_mapping); err_enc_opts_mapping: mapping_destroy(uplink_priv->tunnel_mapping); @@ -4452,13 +4823,8 @@ err_tun_mapping: return err; } -void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) +void mlx5e_tc_esw_cleanup(struct mlx5_rep_uplink_priv *uplink_priv) { - struct mlx5_rep_uplink_priv *uplink_priv; - - uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht); - - rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL); mlx5e_tc_tun_cleanup(uplink_priv->encap); mapping_destroy(uplink_priv->tunnel_enc_opts_mapping); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 5ffae9b13066..a80b00946f1b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -53,7 +53,6 @@ ESW_FLOW_ATTR_SZ :\ NIC_FLOW_ATTR_SZ) - int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags); struct mlx5e_tc_update_priv { @@ -71,7 +70,7 @@ struct mlx5_flow_attr { struct mlx5_fc *counter; struct mlx5_modify_hdr *modify_hdr; struct mlx5_ct_attr ct_attr; - struct mlx5e_sample_attr *sample_attr; + struct mlx5e_sample_attr sample_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; u32 chain; u16 prio; @@ -82,13 +81,33 @@ struct mlx5_flow_attr { u8 outer_match_level; u8 ip_version; u8 tun_ip_version; + int tunnel_id; /* mapped tunnel id */ u32 flags; + struct list_head list; + struct mlx5e_post_act_handle *post_act_handle; union { struct mlx5_esw_flow_attr esw_attr[0]; struct mlx5_nic_flow_attr nic_attr[0]; }; }; +enum { + MLX5_ATTR_FLAG_VLAN_HANDLED = BIT(0), + MLX5_ATTR_FLAG_SLOW_PATH = BIT(1), + MLX5_ATTR_FLAG_NO_IN_PORT = BIT(2), + MLX5_ATTR_FLAG_SRC_REWRITE = BIT(3), + MLX5_ATTR_FLAG_SAMPLE = BIT(4), + MLX5_ATTR_FLAG_ACCEPT = BIT(5), + MLX5_ATTR_FLAG_CT = BIT(6), +}; + +/* Returns true if any of the flags that require skipping further TC/NF processing are set. */ +static inline bool +mlx5e_tc_attr_flags_skip(u32 attr_flags) +{ + return attr_flags & (MLX5_ATTR_FLAG_SLOW_PATH | MLX5_ATTR_FLAG_ACCEPT); +} + struct mlx5_rx_tun_attr { u16 decap_vport; union { @@ -149,8 +168,11 @@ enum { #define MLX5_TC_FLAG(flag) BIT(MLX5E_TC_FLAG_##flag##_BIT) -int mlx5e_tc_esw_init(struct rhashtable *tc_ht); -void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht); +int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv); +void mlx5e_tc_esw_cleanup(struct mlx5_rep_uplink_priv *uplink_priv); + +int mlx5e_tc_ht_init(struct rhashtable *tc_ht); +void mlx5e_tc_ht_cleanup(struct rhashtable *tc_ht); int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, struct flow_cls_offload *f, unsigned long flags); @@ -243,11 +265,8 @@ int mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev, u32 data); int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow); - -struct mlx5e_tc_flow; -u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow); + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr); void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev, struct flow_match_basic *match, bool outer, @@ -289,6 +308,8 @@ int mlx5e_set_fwd_to_int_port_actions(struct mlx5e_priv *priv, #else /* CONFIG_MLX5_CLS_ACT */ 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_ht_init(struct rhashtable *tc_ht) { return 0; } +static inline void mlx5e_tc_ht_cleanup(struct rhashtable *tc_ht) {} static inline int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index ee7ecb88adc1..2dc48406cd08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -53,117 +53,6 @@ static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma) } } -#ifdef CONFIG_MLX5_CORE_EN_DCB -static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb) -{ - int dscp_cp = 0; - - if (skb->protocol == htons(ETH_P_IP)) - dscp_cp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; - else if (skb->protocol == htons(ETH_P_IPV6)) - dscp_cp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; - - return priv->dcbx_dp.dscp2prio[dscp_cp]; -} -#endif - -static u16 mlx5e_select_ptpsq(struct net_device *dev, struct sk_buff *skb) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - int up = 0; - - if (!netdev_get_num_tc(dev)) - goto return_txq; - -#ifdef CONFIG_MLX5_CORE_EN_DCB - if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP) - up = mlx5e_get_dscp_up(priv, skb); - else -#endif - if (skb_vlan_tag_present(skb)) - up = skb_vlan_tag_get_prio(skb); - -return_txq: - return priv->port_ptp_tc2realtxq[up]; -} - -static int mlx5e_select_htb_queue(struct mlx5e_priv *priv, struct sk_buff *skb, - u16 htb_maj_id) -{ - u16 classid; - - if ((TC_H_MAJ(skb->priority) >> 16) == htb_maj_id) - classid = TC_H_MIN(skb->priority); - else - classid = READ_ONCE(priv->htb.defcls); - - if (!classid) - return 0; - - return mlx5e_get_txq_by_classid(priv, classid); -} - -u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - int num_tc_x_num_ch; - int txq_ix; - int up = 0; - int ch_ix; - - /* Sync with mlx5e_update_num_tc_x_num_ch - avoid refetching. */ - num_tc_x_num_ch = READ_ONCE(priv->num_tc_x_num_ch); - if (unlikely(dev->real_num_tx_queues > num_tc_x_num_ch)) { - struct mlx5e_ptp *ptp_channel; - - /* Order maj_id before defcls - pairs with mlx5e_htb_root_add. */ - u16 htb_maj_id = smp_load_acquire(&priv->htb.maj_id); - - if (unlikely(htb_maj_id)) { - txq_ix = mlx5e_select_htb_queue(priv, skb, htb_maj_id); - if (txq_ix > 0) - return txq_ix; - } - - ptp_channel = READ_ONCE(priv->channels.ptp); - if (unlikely(ptp_channel && - test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state) && - mlx5e_use_ptpsq(skb))) - return mlx5e_select_ptpsq(dev, skb); - - txq_ix = netdev_pick_tx(dev, skb, NULL); - /* Fix netdev_pick_tx() not to choose ptp_channel and HTB txqs. - * If they are selected, switch to regular queues. - * Driver to select these queues only at mlx5e_select_ptpsq() - * and mlx5e_select_htb_queue(). - */ - if (unlikely(txq_ix >= num_tc_x_num_ch)) - txq_ix %= num_tc_x_num_ch; - } else { - txq_ix = netdev_pick_tx(dev, skb, NULL); - } - - if (!netdev_get_num_tc(dev)) - return txq_ix; - -#ifdef CONFIG_MLX5_CORE_EN_DCB - if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP) - up = mlx5e_get_dscp_up(priv, skb); - else -#endif - if (skb_vlan_tag_present(skb)) - up = skb_vlan_tag_get_prio(skb); - - /* Normalize any picked txq_ix to [0, num_channels), - * So we can return a txq_ix that matches the channel and - * packet UP. - */ - ch_ix = priv->txq2sq[txq_ix]->ch_ix; - - return priv->channel_tc2realtxq[ch_ix][up]; -} - static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb) { #define MLX5E_MIN_INLINE (ETH_HLEN + VLAN_HLEN) @@ -544,7 +433,7 @@ static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq, struct mlx5e_tx_wqe *wqe; u16 pi; - pi = mlx5e_txqsq_get_next_pi(sq, MLX5E_TX_MPW_MAX_WQEBBS); + pi = mlx5e_txqsq_get_next_pi(sq, sq->max_sq_mpw_wqebbs); wqe = MLX5E_TX_FETCH_WQE(sq, pi); net_prefetchw(wqe->data); @@ -645,7 +534,7 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5e_tx_skb_update_hwts_flags(skb); - if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe))) { + if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe, sq->max_sq_mpw_wqebbs))) { /* Might stop the queue and affect the retval of __netdev_tx_sent_queue. */ cseg = mlx5e_tx_mpwqe_session_complete(sq); @@ -691,8 +580,21 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) struct mlx5e_txqsq *sq; u16 pi; + /* All changes to txq2sq are performed in sync with mlx5e_xmit, when the + * queue being changed is disabled, and smp_wmb guarantees that the + * changes are visible before mlx5e_xmit tries to read from txq2sq. It + * guarantees that the value of txq2sq[qid] doesn't change while + * mlx5e_xmit is running on queue number qid. smb_wmb is paired with + * HARD_TX_LOCK around ndo_start_xmit, which serves as an ACQUIRE. + */ sq = priv->txq2sq[skb_get_queue_mapping(skb)]; if (unlikely(!sq)) { + /* Two cases when sq can be NULL: + * 1. The HTB node is registered, and mlx5e_select_queue + * selected its queue ID, but the SQ itself is not yet created. + * 2. HTB SQ creation failed. Similar to the previous case, but + * the SQ won't be created. + */ dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c index c275fe028b6d..0abef71cb839 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c @@ -86,7 +86,7 @@ mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw, mlx5_eswitch_is_vf_vport(esw, vport_num) && esw->dev == dest_mdev && attr->ip_version && - attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE; + attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE; } u16 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ead5e8acc8be..44321cdfe928 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -448,22 +448,6 @@ enum { MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE = BIT(2), }; -enum { - MLX5_ESW_ATTR_FLAG_VLAN_HANDLED = BIT(0), - MLX5_ESW_ATTR_FLAG_SLOW_PATH = BIT(1), - MLX5_ESW_ATTR_FLAG_NO_IN_PORT = BIT(2), - MLX5_ESW_ATTR_FLAG_SRC_REWRITE = BIT(3), - MLX5_ESW_ATTR_FLAG_SAMPLE = BIT(4), - MLX5_ESW_ATTR_FLAG_ACCEPT = BIT(5), -}; - -/* Returns true if any of the flags that require skipping further TC/NF processing are set. */ -static inline bool -mlx5_esw_attr_flags_skip(u32 attr_flags) -{ - return attr_flags & (MLX5_ESW_ATTR_FLAG_SLOW_PATH | MLX5_ESW_ATTR_FLAG_ACCEPT); -} - struct mlx5_esw_flow_attr { struct mlx5_eswitch_rep *in_rep; struct mlx5_core_dev *in_mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 9a7b25692505..2b31d8bbd1b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -180,7 +180,7 @@ esw_setup_decap_indir(struct mlx5_eswitch *esw, { struct mlx5_flow_table *ft; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE)) + if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE)) return -EOPNOTSUPP; ft = mlx5_esw_indir_table_get(esw, attr, spec, @@ -201,12 +201,12 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw, static int esw_setup_sampler_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, - struct mlx5_flow_attr *attr, + u32 sampler_id, int i) { flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER; - dest[i].sampler_id = attr->sample_attr->sampler_id; + dest[i].sampler_id = sampler_id; return 0; } @@ -297,7 +297,7 @@ esw_setup_chain_src_port_rewrite(struct mlx5_flow_destination *dest, struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; int err; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE)) + if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE)) return -EOPNOTSUPP; /* flow steering cannot handle more than one dest with the same ft @@ -364,7 +364,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; int j, err; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE)) + if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE)) return -EOPNOTSUPP; for (j = esw_attr->split_count; j < esw_attr->out_count; j++, (*i)++) { @@ -463,15 +463,16 @@ esw_setup_dests(struct mlx5_flow_destination *dest, if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) && esw_src_port_rewrite_supported(esw)) - attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE; + attr->flags |= MLX5_ATTR_FLAG_SRC_REWRITE; - if (attr->flags & MLX5_ESW_ATTR_FLAG_SAMPLE) { - esw_setup_sampler_dest(dest, flow_act, attr, *i); + if (attr->flags & MLX5_ATTR_FLAG_SAMPLE && + !(attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)) { + esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i); (*i)++; } else if (attr->dest_ft) { esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i); (*i)++; - } else if (mlx5_esw_attr_flags_skip(attr->flags)) { + } else if (mlx5e_tc_attr_flags_skip(attr->flags)) { esw_setup_slow_path_dest(dest, flow_act, chains, *i); (*i)++; } else if (attr->dest_chain) { @@ -498,7 +499,7 @@ esw_cleanup_dests(struct mlx5_eswitch *esw, if (attr->dest_ft) { esw_cleanup_decap_indir(esw, attr); - } else if (!mlx5_esw_attr_flags_skip(attr->flags)) { + } else if (!mlx5e_tc_attr_flags_skip(attr->flags)) { if (attr->dest_chain) esw_cleanup_chain_dest(chains, attr->dest_chain, 1, 0); else if (esw_is_indir_table(esw, attr)) @@ -589,7 +590,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, else fdb = attr->ft; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_NO_IN_PORT)) + if (!(attr->flags & MLX5_ATTR_FLAG_NO_IN_PORT)) mlx5_eswitch_set_rule_source_port(esw, spec, attr, esw_attr->in_mdev->priv.eswitch, esw_attr->in_rep->vport); @@ -721,7 +722,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw, mlx5_del_flow_rules(rule); - if (!mlx5_esw_attr_flags_skip(attr->flags)) { + if (!mlx5e_tc_attr_flags_skip(attr->flags)) { /* unref the term table */ for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) { if (esw_attr->dests[i].termtbl) @@ -863,7 +864,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, if (err) goto unlock; - attr->flags &= ~MLX5_ESW_ATTR_FLAG_VLAN_HANDLED; + attr->flags &= ~MLX5_ATTR_FLAG_VLAN_HANDLED; vport = esw_vlan_action_get_vport(esw_attr, push, pop); @@ -871,7 +872,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, /* tracks VF --> wire rules without vlan push action */ if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) { vport->vlan_refcount++; - attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED; + attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; } goto unlock; @@ -902,7 +903,7 @@ skip_set_push: } out: if (!err) - attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED; + attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; unlock: mutex_unlock(&esw->state_lock); return err; @@ -921,7 +922,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) return 0; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_VLAN_HANDLED)) + if (!(attr->flags & MLX5_ATTR_FLAG_VLAN_HANDLED)) return 0; push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 182306bbefaa..ee568bf34ae2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -219,12 +219,14 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) || - mlx5_esw_attr_flags_skip(attr->flags) || + mlx5e_tc_attr_flags_skip(attr->flags) || (!mlx5_eswitch_offload_is_uplink_port(esw, spec) && !esw_attr->int_port)) return false; /* push vlan on RX */ - if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) + if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH && + !(mlx5_fs_get_capabilities(esw->dev, MLX5_FLOW_NAMESPACE_FDB) & + MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX)) return true; /* hairpin */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index dafe341358c7..a0ac17c3f12f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -152,6 +152,12 @@ static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns) return 0; } +static u32 mlx5_cmd_stub_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + return 0; +} + static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master, struct mlx5_core_dev *slave, bool ft_id_valid, @@ -971,6 +977,12 @@ static int mlx5_cmd_create_match_definer(struct mlx5_flow_root_namespace *ns, return err ? err : MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); } +static u32 mlx5_cmd_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + return 0; +} + static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, .destroy_flow_table = mlx5_cmd_destroy_flow_table, @@ -990,6 +1002,7 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, + .get_capabilities = mlx5_cmd_get_capabilities, }; static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { @@ -1011,6 +1024,7 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, + .get_capabilities = mlx5_cmd_stub_get_capabilities, }; const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 220ec632d35a..274004e80f03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -101,6 +101,9 @@ struct mlx5_flow_cmds { u16 format_id, u32 *match_mask); int (*destroy_match_definer)(struct mlx5_flow_root_namespace *ns, int definer_id); + + u32 (*get_capabilities)(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b628917e38e4..42f878e21fea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3040,6 +3040,22 @@ void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev) steering->esw_ingress_root_ns = NULL; } +u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_namespace *ns; + + ns = mlx5_get_flow_namespace(dev, type); + if (!ns) + return 0; + + root = find_root(&ns->node); + if (!root) + return 0; + + return root->cmds->get_capabilities(root, root->table_type); +} + static int init_egress_root_ns(struct mlx5_flow_steering *steering) { int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 5469b08d635f..c488a7c5b07e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -120,6 +120,11 @@ enum mlx5_flow_steering_mode { MLX5_FLOW_STEERING_MODE_SMFS }; +enum mlx5_flow_steering_capabilty { + MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX = 1UL << 0, + MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX = 1UL << 1, +}; + struct mlx5_flow_steering { struct mlx5_core_dev *dev; enum mlx5_flow_steering_mode mode; @@ -301,6 +306,8 @@ void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev); int mlx5_fs_ingress_acls_init(struct mlx5_core_dev *dev, int total_vports); void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev); +u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); + struct mlx5_flow_root_namespace *find_root(struct fs_node *node); #define fs_get_obj(v, _node) {v = container_of((_node), typeof(*v), node); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index a476da2424f8..033757bfdf64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -735,6 +735,16 @@ static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns) return mlx5dr_domain_destroy(ns->fs_dr_domain.dr_domain); } +static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + if (ft_type != FS_FT_FDB || + MLX5_CAP_GEN(ns->dev, steering_format_version) != MLX5_STEERING_FORMAT_CONNECTX_6DX) + return 0; + + return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX | MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX; +} + bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) { return mlx5dr_is_supported(dev); @@ -759,6 +769,7 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = { .set_peer = mlx5_cmd_dr_set_peer, .create_ns = mlx5_cmd_dr_create_ns, .destroy_ns = mlx5_cmd_dr_destroy_ns, + .get_capabilities = mlx5_cmd_dr_get_capabilities, }; const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 866b9357939b..f45df5fbdcc0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -212,6 +212,29 @@ struct mlxsw_event_listener_item { void *priv; }; +static const u8 mlxsw_core_trap_groups[] = { + MLXSW_REG_HTGT_TRAP_GROUP_EMAD, + MLXSW_REG_HTGT_TRAP_GROUP_CORE_EVENT, +}; + +static int mlxsw_core_trap_groups_set(struct mlxsw_core *mlxsw_core) +{ + char htgt_pl[MLXSW_REG_HTGT_LEN]; + int err; + int i; + + for (i = 0; i < ARRAY_SIZE(mlxsw_core_trap_groups); i++) { + mlxsw_reg_htgt_pack(htgt_pl, mlxsw_core_trap_groups[i], + MLXSW_REG_HTGT_INVALID_POLICER, + MLXSW_REG_HTGT_DEFAULT_PRIORITY, + MLXSW_REG_HTGT_DEFAULT_TC); + err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); + if (err) + return err; + } + return 0; +} + /****************** * EMAD processing ******************/ @@ -777,16 +800,10 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) if (err) goto err_trap_register; - err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core); - if (err) - goto err_emad_trap_set; mlxsw_core->emad.use_emad = true; return 0; -err_emad_trap_set: - mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener, - mlxsw_core); err_trap_register: destroy_workqueue(mlxsw_core->emad_wq); return err; @@ -1706,7 +1723,7 @@ static void mlxsw_core_health_listener_func(const struct mlxsw_reg_info *reg, } static const struct mlxsw_listener mlxsw_core_health_listener = - MLXSW_EVENTL(mlxsw_core_health_listener_func, MFDE, MFDE); + MLXSW_CORE_EVENTL(mlxsw_core_health_listener_func, MFDE); static int mlxsw_core_health_fw_fatal_dump_fatal_cause(const char *mfde_pl, @@ -2122,6 +2139,10 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, } } + err = mlxsw_core_trap_groups_set(mlxsw_core); + if (err) + goto err_trap_groups_set; + err = mlxsw_emad_init(mlxsw_core); if (err) goto err_emad_init; @@ -2181,6 +2202,7 @@ err_fw_rev_validate: err_register_params: mlxsw_emad_fini(mlxsw_core); err_emad_init: +err_trap_groups_set: kfree(mlxsw_core->lag.mapping); err_alloc_lag_mapping: mlxsw_ports_fini(mlxsw_core, reload); @@ -2540,6 +2562,45 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_trap_unregister); +int mlxsw_core_traps_register(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv) +{ + int i, err; + + for (i = 0; i < listeners_count; i++) { + err = mlxsw_core_trap_register(mlxsw_core, + &listeners[i], + priv); + if (err) + goto err_listener_register; + } + return 0; + +err_listener_register: + for (i--; i >= 0; i--) { + mlxsw_core_trap_unregister(mlxsw_core, + &listeners[i], + priv); + } + return err; +} +EXPORT_SYMBOL(mlxsw_core_traps_register); + +void mlxsw_core_traps_unregister(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv) +{ + int i; + + for (i = 0; i < listeners_count; i++) { + mlxsw_core_trap_unregister(mlxsw_core, + &listeners[i], + priv); + } +} +EXPORT_SYMBOL(mlxsw_core_traps_unregister); + int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, bool enabled) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index f30bb8614e69..6d304092f4e7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -163,6 +163,9 @@ struct mlxsw_listener { .enabled_on_register = true, \ } +#define MLXSW_CORE_EVENTL(_func, _trap_id) \ + MLXSW_EVENTL(_func, _trap_id, CORE_EVENT) + int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_rx_listener *rxl, void *priv, bool enabled); @@ -181,6 +184,12 @@ int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, void *priv); +int mlxsw_core_traps_register(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv); +void mlxsw_core_traps_unregister(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv); int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, bool enabled); @@ -315,7 +324,6 @@ struct mlxsw_driver { const struct mlxsw_bus_info *mlxsw_bus_info, struct netlink_ext_ack *extack); void (*fini)(struct mlxsw_core *mlxsw_core); - int (*basic_trap_groups_set)(struct mlxsw_core *mlxsw_core); int (*port_type_set)(struct mlxsw_core *mlxsw_core, u16 local_port, enum devlink_port_type new_type); int (*port_split)(struct mlxsw_core *mlxsw_core, u16 local_port, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index 77e82e6cf6e8..fa33caecc91d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -1957,6 +1957,83 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, } EXPORT_SYMBOL(mlxsw_afa_block_append_mcrouter); +/* SIP DIP Action + * -------------- + * The SIP_DIP_ACTION is used for modifying the SIP and DIP fields of the + * packet, e.g. for NAT. The L3 checksum is updated. Also, if the L4 is TCP or + * if the L4 is UDP and the checksum field is not zero, then the L4 checksum is + * updated. + */ + +#define MLXSW_AFA_IP_CODE 0x11 +#define MLXSW_AFA_IP_SIZE 2 + +enum mlxsw_afa_ip_s_d { + /* ip refers to dip */ + MLXSW_AFA_IP_S_D_DIP, + /* ip refers to sip */ + MLXSW_AFA_IP_S_D_SIP, +}; + +/* afa_ip_s_d + * Source or destination. + */ +MLXSW_ITEM32(afa, ip, s_d, 0x00, 31, 1); + +enum mlxsw_afa_ip_m_l { + /* LSB: ip[63:0] refers to ip[63:0] */ + MLXSW_AFA_IP_M_L_LSB, + /* MSB: ip[63:0] refers to ip[127:64] */ + MLXSW_AFA_IP_M_L_MSB, +}; + +/* afa_ip_m_l + * MSB or LSB. + */ +MLXSW_ITEM32(afa, ip, m_l, 0x00, 30, 1); + +/* afa_ip_ip_63_32 + * Bits [63:32] in the IP address to change to. + */ +MLXSW_ITEM32(afa, ip, ip_63_32, 0x08, 0, 32); + +/* afa_ip_ip_31_0 + * Bits [31:0] in the IP address to change to. + */ +MLXSW_ITEM32(afa, ip, ip_31_0, 0x0C, 0, 32); + +static void mlxsw_afa_ip_pack(char *payload, enum mlxsw_afa_ip_s_d s_d, + enum mlxsw_afa_ip_m_l m_l, u32 ip_31_0, + u32 ip_63_32) +{ + mlxsw_afa_ip_s_d_set(payload, s_d); + mlxsw_afa_ip_m_l_set(payload, m_l); + mlxsw_afa_ip_ip_31_0_set(payload, ip_31_0); + mlxsw_afa_ip_ip_63_32_set(payload, ip_63_32); +} + +int mlxsw_afa_block_append_ip(struct mlxsw_afa_block *block, bool is_dip, + bool is_lsb, u32 val_31_0, u32 val_63_32, + struct netlink_ext_ack *extack) +{ + enum mlxsw_afa_ip_s_d s_d = is_dip ? MLXSW_AFA_IP_S_D_DIP : + MLXSW_AFA_IP_S_D_SIP; + enum mlxsw_afa_ip_m_l m_l = is_lsb ? MLXSW_AFA_IP_M_L_LSB : + MLXSW_AFA_IP_M_L_MSB; + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_IP_CODE, + MLXSW_AFA_IP_SIZE); + + if (IS_ERR(act)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot append IP action"); + return PTR_ERR(act); + } + + mlxsw_afa_ip_pack(act, s_d, m_l, val_31_0, val_63_32); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_ip); + /* L4 Port Action * -------------- * The L4_PORT_ACTION is used for modifying the sport and dport fields of the packet, e.g. for NAT. diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 16cbd6acbb01..db58037be46e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -92,6 +92,9 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid, int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, u16 expected_irif, u16 min_mtu, bool rmid_valid, u32 kvdl_index); +int mlxsw_afa_block_append_ip(struct mlxsw_afa_block *block, bool is_dip, + bool is_lsb, u32 val_31_0, u32 val_63_32, + struct netlink_ext_ack *extack); int mlxsw_afa_block_append_l4port(struct mlxsw_afa_block *block, bool is_dport, u16 l4_port, struct netlink_ext_ack *extack); int mlxsw_afa_block_append_police(struct mlxsw_afa_block *block, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 6dd4ae2f45f4..6ea4bf87be0b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -18,6 +18,7 @@ struct mlxsw_env_module_info { int num_ports_mapped; int num_ports_up; enum ethtool_module_power_mode_policy power_mode_policy; + enum mlxsw_reg_pmtm_module_type type; }; struct mlxsw_env { @@ -27,14 +28,47 @@ struct mlxsw_env { struct mlxsw_env_module_info module_info[]; }; -static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, - bool *qsfp, bool *cmis) +static int __mlxsw_env_validate_module_type(struct mlxsw_core *core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(core); + int err; + + switch (mlxsw_env->module_info[module].type) { + case MLXSW_REG_PMTM_MODULE_TYPE_TWISTED_PAIR: + err = -EINVAL; + break; + default: + err = 0; + } + + return err; +} + +static int mlxsw_env_validate_module_type(struct mlxsw_core *core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(core); + int err; + + mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(core, module); + mutex_unlock(&mlxsw_env->module_info_lock); + + return err; +} + +static int +mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, bool *qsfp, + bool *cmis) { char mcia_pl[MLXSW_REG_MCIA_LEN]; char *eeprom_tmp; u8 ident; int err; + err = mlxsw_env_validate_module_type(core, id); + if (err) + return err; + mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1, MLXSW_REG_MCIA_I2C_ADDR_LOW); err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); @@ -206,7 +240,8 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, return 0; } -int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, +int mlxsw_env_get_module_info(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, int module, struct ethtool_modinfo *modinfo) { u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE]; @@ -215,6 +250,13 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, unsigned int read_size; int err; + err = mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + netdev_err(netdev, + "EEPROM is not equipped on port module type"); + return err; + } + err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset, module_info, false, &read_size); if (err) @@ -356,6 +398,13 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, { u32 bytes_read = 0; u16 device_addr; + int err; + + err = mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "EEPROM is not equipped on port module type"); + return err; + } /* Offset cannot be larger than 2 * ETH_MODULE_EEPROM_PAGE_LEN */ device_addr = page->offset; @@ -364,7 +413,6 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, char mcia_pl[MLXSW_REG_MCIA_LEN]; char *eeprom_tmp; u8 size; - int err; size = min_t(u8, page->length - bytes_read, MLXSW_REG_MCIA_EEPROM_SIZE); @@ -419,6 +467,12 @@ int mlxsw_env_reset_module(struct net_device *netdev, mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + netdev_err(netdev, "Reset module is not supported on port module type\n"); + goto out; + } + if (mlxsw_env->module_info[module].num_ports_up) { netdev_err(netdev, "Cannot reset module when ports using it are administratively up\n"); err = -EINVAL; @@ -461,6 +515,12 @@ mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Power mode is not supported on port module type"); + goto out; + } + params->policy = mlxsw_env->module_info[module].power_mode_policy; mlxsw_reg_mcion_pack(mcion_pl, module); @@ -571,6 +631,13 @@ mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Power mode set is not supported on port module type"); + goto out; + } + if (mlxsw_env->module_info[module].power_mode_policy == policy) goto out; @@ -661,13 +728,12 @@ static int mlxsw_env_temp_event_set(struct mlxsw_core *mlxsw_core, return mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtmp), mtmp_pl); } -static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core, - u8 module_count) +static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core) { int i, err, sensor_index; bool has_temp_sensor; - for (i = 0; i < module_count; i++) { + for (i = 0; i < mlxsw_core_env(mlxsw_core)->module_count; i++) { err = mlxsw_env_module_has_temp_sensor(mlxsw_core, i, &has_temp_sensor); if (err) @@ -759,7 +825,7 @@ mlxsw_env_mtwe_listener_func(const struct mlxsw_reg_info *reg, char *mtwe_pl, } static const struct mlxsw_listener mlxsw_env_temp_warn_listener = - MLXSW_EVENTL(mlxsw_env_mtwe_listener_func, MTWE, MTWE); + MLXSW_CORE_EVENTL(mlxsw_env_mtwe_listener_func, MTWE); static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core) { @@ -849,7 +915,7 @@ mlxsw_env_pmpe_listener_func(const struct mlxsw_reg_info *reg, char *pmpe_pl, } static const struct mlxsw_listener mlxsw_env_module_plug_listener = - MLXSW_EVENTL(mlxsw_env_pmpe_listener_func, PMPE, PMPE); + MLXSW_CORE_EVENTL(mlxsw_env_pmpe_listener_func, PMPE); static int mlxsw_env_module_plug_event_register(struct mlxsw_core *mlxsw_core) @@ -876,12 +942,11 @@ mlxsw_env_module_plug_event_unregister(struct mlxsw_env *mlxsw_env) } static int -mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core, - u8 module_count) +mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core) { int i, err; - for (i = 0; i < module_count; i++) { + for (i = 0; i < mlxsw_core_env(mlxsw_core)->module_count; i++) { char pmaos_pl[MLXSW_REG_PMAOS_LEN]; mlxsw_reg_pmaos_pack(pmaos_pl, i); @@ -999,6 +1064,28 @@ out_unlock: } EXPORT_SYMBOL(mlxsw_env_module_port_down); +static int +mlxsw_env_module_type_set(struct mlxsw_core *mlxsw_core) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + int i; + + for (i = 0; i < mlxsw_env->module_count; i++) { + char pmtm_pl[MLXSW_REG_PMTM_LEN]; + int err; + + mlxsw_reg_pmtm_pack(pmtm_pl, 0, i); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtm), pmtm_pl); + if (err) + return err; + + mlxsw_env->module_info[i].type = + mlxsw_reg_pmtm_module_type_get(pmtm_pl); + } + + return 0; +} + int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) { char mgpir_pl[MLXSW_REG_MGPIR_LEN]; @@ -1037,17 +1124,21 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) if (err) goto err_module_plug_event_register; - err = mlxsw_env_module_oper_state_event_enable(mlxsw_core, - env->module_count); + err = mlxsw_env_module_oper_state_event_enable(mlxsw_core); if (err) goto err_oper_state_event_enable; - err = mlxsw_env_module_temp_event_enable(mlxsw_core, env->module_count); + err = mlxsw_env_module_temp_event_enable(mlxsw_core); if (err) goto err_temp_event_enable; + err = mlxsw_env_module_type_set(mlxsw_core); + if (err) + goto err_type_set; + return 0; +err_type_set: err_temp_event_enable: err_oper_state_event_enable: mlxsw_env_module_plug_event_unregister(env); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h index da121b1a84b4..ec6564e5d2ee 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -12,7 +12,8 @@ struct ethtool_eeprom; int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, int off, int *temp); -int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, +int mlxsw_env_get_module_info(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, int module, struct ethtool_modinfo *modinfo); int mlxsw_env_get_module_eeprom(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 10d13f5f9c7d..9ac8ce01c061 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -110,7 +110,8 @@ static int mlxsw_m_get_module_info(struct net_device *netdev, struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev); struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core; - return mlxsw_env_get_module_info(core, mlxsw_m_port->module, modinfo); + return mlxsw_env_get_module_info(netdev, core, mlxsw_m_port->module, + modinfo); } static int diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 24cc65018b41..eebd0479b2bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4482,6 +4482,8 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32); #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 BIT(21) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 BIT(22) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4 BIT(23) +#define MLXSW_REG_PTYS_ETH_SPEED_100BASE_T BIT(24) +#define MLXSW_REG_PTYS_ETH_SPEED_1000BASE_T BIT(25) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR BIT(27) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR BIT(28) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR BIT(29) @@ -6062,6 +6064,58 @@ static inline void mlxsw_reg_pllp_unpack(char *payload, u8 *label_port, *slot_index = mlxsw_reg_pllp_slot_index_get(payload); } +/* PMTM - Port Module Type Mapping Register + * ---------------------------------------- + * The PMTM register allows query or configuration of module types. + * The register can only be set when the module is disabled by PMAOS register + */ +#define MLXSW_REG_PMTM_ID 0x5067 +#define MLXSW_REG_PMTM_LEN 0x10 + +MLXSW_REG_DEFINE(pmtm, MLXSW_REG_PMTM_ID, MLXSW_REG_PMTM_LEN); + +/* reg_pmtm_slot_index + * Slot index. + * Access: Index + */ +MLXSW_ITEM32(reg, pmtm, slot_index, 0x00, 24, 4); + +/* reg_pmtm_module + * Module number. + * Access: Index + */ +MLXSW_ITEM32(reg, pmtm, module, 0x00, 16, 8); + +enum mlxsw_reg_pmtm_module_type { + MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_4_LANES = 0, + MLXSW_REG_PMTM_MODULE_TYPE_QSFP = 1, + MLXSW_REG_PMTM_MODULE_TYPE_SFP = 2, + MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_SINGLE_LANE = 4, + MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_2_LANES = 8, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP4X = 10, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP2X = 11, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP1X = 12, + MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD = 14, + MLXSW_REG_PMTM_MODULE_TYPE_OSFP = 15, + MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD = 16, + MLXSW_REG_PMTM_MODULE_TYPE_DSFP = 17, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP8X = 18, + MLXSW_REG_PMTM_MODULE_TYPE_TWISTED_PAIR = 19, +}; + +/* reg_pmtm_module_type + * Module type. + * Access: RW + */ +MLXSW_ITEM32(reg, pmtm, module_type, 0x04, 0, 5); + +static inline void mlxsw_reg_pmtm_pack(char *payload, u8 slot_index, u8 module) +{ + MLXSW_REG_ZERO(pmtm, payload); + mlxsw_reg_pmtm_slot_index_set(payload, slot_index); + mlxsw_reg_pmtm_module_set(payload, module); +} + /* HTGT - Host Trap Group Table * ---------------------------- * Configures the properties for forwarding to CPU. @@ -6087,9 +6141,7 @@ MLXSW_ITEM32(reg, htgt, type, 0x00, 8, 4); enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_EMAD, - MLXSW_REG_HTGT_TRAP_GROUP_MFDE, - MLXSW_REG_HTGT_TRAP_GROUP_MTWE, - MLXSW_REG_HTGT_TRAP_GROUP_PMPE, + MLXSW_REG_HTGT_TRAP_GROUP_CORE_EVENT, MLXSW_REG_HTGT_TRAP_GROUP_SP_STP, MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP, MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP, @@ -12568,6 +12620,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(pddr), MLXSW_REG(pmmp), MLXSW_REG(pllp), + MLXSW_REG(pmtm), MLXSW_REG(htgt), MLXSW_REG(hpkt), MLXSW_REG(rgcr), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index c7fc650608eb..daacf6291253 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -33,6 +33,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_ACL_MAX_REGIONS, MLXSW_RES_ID_ACL_MAX_GROUPS, MLXSW_RES_ID_ACL_MAX_GROUP_SIZE, + MLXSW_RES_ID_ACL_MAX_DEFAULT_ACTIONS, MLXSW_RES_ID_ACL_FLEX_KEYS, MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE, MLXSW_RES_ID_ACL_ACTIONS_PER_SET, @@ -90,6 +91,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903, [MLXSW_RES_ID_ACL_MAX_GROUPS] = 0x2904, [MLXSW_RES_ID_ACL_MAX_GROUP_SIZE] = 0x2905, + [MLXSW_RES_ID_ACL_MAX_DEFAULT_ACTIONS] = 0x2908, [MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910, [MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911, [MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index aa411dec62f0..a4b94eecea98 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2148,13 +2148,11 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, struct mlxsw_sp *mlxsw_sp = priv; struct mlxsw_sp_port *mlxsw_sp_port; enum mlxsw_reg_pude_oper_status status; - unsigned int max_ports; u16 local_port; - max_ports = mlxsw_core_max_ports(mlxsw_sp->core); local_port = mlxsw_reg_pude_local_port_get(pude_pl); - if (WARN_ON_ONCE(!local_port || local_port >= max_ports)) + if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port))) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) @@ -2393,45 +2391,6 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core) return 0; } -static int mlxsw_sp_traps_register(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_listener listeners[], - size_t listeners_count) -{ - int i; - int err; - - for (i = 0; i < listeners_count; i++) { - err = mlxsw_core_trap_register(mlxsw_sp->core, - &listeners[i], - mlxsw_sp); - if (err) - goto err_listener_register; - - } - return 0; - -err_listener_register: - for (i--; i >= 0; i--) { - mlxsw_core_trap_unregister(mlxsw_sp->core, - &listeners[i], - mlxsw_sp); - } - return err; -} - -static void mlxsw_sp_traps_unregister(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_listener listeners[], - size_t listeners_count) -{ - int i; - - for (i = 0; i < listeners_count; i++) { - mlxsw_core_trap_unregister(mlxsw_sp->core, - &listeners[i], - mlxsw_sp); - } -} - static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_trap *trap; @@ -2456,21 +2415,23 @@ static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_trap_groups_set; - err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp_listener, - ARRAY_SIZE(mlxsw_sp_listener)); + err = mlxsw_core_traps_register(mlxsw_sp->core, mlxsw_sp_listener, + ARRAY_SIZE(mlxsw_sp_listener), + mlxsw_sp); if (err) goto err_traps_register; - err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp->listeners, - mlxsw_sp->listeners_count); + err = mlxsw_core_traps_register(mlxsw_sp->core, mlxsw_sp->listeners, + mlxsw_sp->listeners_count, mlxsw_sp); if (err) goto err_extra_traps_init; return 0; err_extra_traps_init: - mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener, - ARRAY_SIZE(mlxsw_sp_listener)); + mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp_listener, + ARRAY_SIZE(mlxsw_sp_listener), + mlxsw_sp); err_traps_register: err_trap_groups_set: err_cpu_policers_set: @@ -2480,10 +2441,11 @@ err_cpu_policers_set: static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp) { - mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp->listeners, - mlxsw_sp->listeners_count); - mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener, - ARRAY_SIZE(mlxsw_sp_listener)); + mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp->listeners, + mlxsw_sp->listeners_count, + mlxsw_sp); + mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp_listener, + ARRAY_SIZE(mlxsw_sp_listener), mlxsw_sp); kfree(mlxsw_sp->trap); } @@ -2528,42 +2490,6 @@ static void mlxsw_sp_lag_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->lags); } -static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) -{ - char htgt_pl[MLXSW_REG_HTGT_LEN]; - int err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_EMAD, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_MFDE, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_MTWE, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_PMPE, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); -} - static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = { .clock_init = mlxsw_sp1_ptp_clock_init, .clock_fini = mlxsw_sp1_ptp_clock_fini, @@ -3677,7 +3603,6 @@ static struct mlxsw_driver mlxsw_sp1_driver = { .fw_filename = MLXSW_SP1_FW_FILENAME, .init = mlxsw_sp1_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, @@ -3717,7 +3642,6 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .fw_filename = MLXSW_SP2_FW_FILENAME, .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, @@ -3758,7 +3682,6 @@ static struct mlxsw_driver mlxsw_sp3_driver = { .fw_filename = MLXSW_SP3_FW_FILENAME, .init = mlxsw_sp3_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, @@ -3797,7 +3720,6 @@ static struct mlxsw_driver mlxsw_sp4_driver = { .priv_size = sizeof(struct mlxsw_sp), .init = mlxsw_sp4_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, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bb2442e1f705..20588e699588 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -481,6 +481,13 @@ int mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port, bool is_8021ad_tagged, bool is_8021q_tagged); +static inline bool +mlxsw_sp_local_port_is_valid(struct mlxsw_sp *mlxsw_sp, u16 local_port) +{ + unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + + return local_port < max_ports && local_port; +} /* spectrum_buffers.c */ struct mlxsw_sp_hdroom_prio { @@ -813,6 +820,24 @@ int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core); /* spectrum2_kvdl.c */ extern const struct mlxsw_sp_kvdl_ops mlxsw_sp2_kvdl_ops; +enum mlxsw_sp_acl_mangle_field { + MLXSW_SP_ACL_MANGLE_FIELD_IP_DSFIELD, + MLXSW_SP_ACL_MANGLE_FIELD_IP_DSCP, + MLXSW_SP_ACL_MANGLE_FIELD_IP_ECN, + MLXSW_SP_ACL_MANGLE_FIELD_IP_SPORT, + MLXSW_SP_ACL_MANGLE_FIELD_IP_DPORT, + MLXSW_SP_ACL_MANGLE_FIELD_IP4_SIP, + MLXSW_SP_ACL_MANGLE_FIELD_IP4_DIP, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_1, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_2, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_3, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_4, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_1, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_2, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_3, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_4, +}; + struct mlxsw_sp_acl_rule_info { unsigned int priority; struct mlxsw_afk_element_values values; @@ -821,9 +846,14 @@ struct mlxsw_sp_acl_rule_info { ingress_bind_blocker:1, egress_bind_blocker:1, counter_valid:1, - policer_index_valid:1; + policer_index_valid:1, + ipv6_valid:1; unsigned int counter_index; u16 policer_index; + struct { + u32 prev_val; + enum mlxsw_sp_acl_mangle_field prev_field; + } ipv6; }; /* spectrum_flow.c */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c index a9fff8adc75e..d20e794e01ca 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c @@ -213,7 +213,6 @@ mlxsw_sp1_kvdl_part_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp1_kvdl_part *part; bool need_update = true; unsigned int nr_entries; - size_t usage_size; u64 resource_size; int err; @@ -225,8 +224,8 @@ mlxsw_sp1_kvdl_part_init(struct mlxsw_sp *mlxsw_sp, } nr_entries = div_u64(resource_size, info->alloc_size); - usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long); - part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL); + part = kzalloc(struct_size(part, usage, BITS_TO_LONGS(nr_entries)), + GFP_KERNEL); if (!part) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c index ad69913f19c1..5b0210862655 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c @@ -77,7 +77,14 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, int i; int err; + /* Some TCAM regions are not exposed to the host and used internally + * by the device. Allocate KVDL entries for the default actions of + * these regions to avoid the host from overwriting them. + */ tcam->kvdl_count = _tcam->max_regions; + if (MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_DEFAULT_ACTIONS)) + tcam->kvdl_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_DEFAULT_ACTIONS); err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET, tcam->kvdl_count, &tcam->kvdl_index); if (err) @@ -97,7 +104,10 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, goto err_afa_block_continue; enc_actions = mlxsw_afa_block_cur_set(afa_block); - for (i = 0; i < tcam->kvdl_count; i++) { + /* Only write to KVDL entries used by TCAM regions exposed to the + * host. + */ + for (i = 0; i < _tcam->max_regions; i++) { mlxsw_reg_pefa_pack(pefa_pl, tcam->kvdl_index + i, true, enc_actions); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 70c11bfac08f..6c5af018546f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -505,14 +505,6 @@ int mlxsw_sp_acl_rulei_act_priority(struct mlxsw_sp *mlxsw_sp, extack); } -enum mlxsw_sp_acl_mangle_field { - MLXSW_SP_ACL_MANGLE_FIELD_IP_DSFIELD, - MLXSW_SP_ACL_MANGLE_FIELD_IP_DSCP, - MLXSW_SP_ACL_MANGLE_FIELD_IP_ECN, - MLXSW_SP_ACL_MANGLE_FIELD_IP_SPORT, - MLXSW_SP_ACL_MANGLE_FIELD_IP_DPORT, -}; - struct mlxsw_sp_acl_mangle_action { enum flow_action_mangle_base htype; /* Offset is u32-aligned. */ @@ -561,6 +553,18 @@ static struct mlxsw_sp_acl_mangle_action mlxsw_sp_acl_mangle_actions[] = { MLXSW_SP_ACL_MANGLE_ACTION_UDP(0, 0x0000ffff, 16, IP_SPORT), MLXSW_SP_ACL_MANGLE_ACTION_UDP(0, 0xffff0000, 0, IP_DPORT), + + MLXSW_SP_ACL_MANGLE_ACTION_IP4(12, 0x00000000, 0, IP4_SIP), + MLXSW_SP_ACL_MANGLE_ACTION_IP4(16, 0x00000000, 0, IP4_DIP), + + MLXSW_SP_ACL_MANGLE_ACTION_IP6(8, 0x00000000, 0, IP6_SIP_1), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(12, 0x00000000, 0, IP6_SIP_2), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(16, 0x00000000, 0, IP6_SIP_3), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(20, 0x00000000, 0, IP6_SIP_4), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(24, 0x00000000, 0, IP6_DIP_1), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(28, 0x00000000, 0, IP6_DIP_2), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(32, 0x00000000, 0, IP6_DIP_3), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(36, 0x00000000, 0, IP6_DIP_4), }; static int @@ -599,6 +603,22 @@ static int mlxsw_sp1_acl_rulei_act_mangle_field(struct mlxsw_sp *mlxsw_sp, return err; } +static int +mlxsw_sp2_acl_rulei_act_mangle_field_ip_odd(struct mlxsw_sp_acl_rule_info *rulei, + enum mlxsw_sp_acl_mangle_field field, + u32 val, struct netlink_ext_ack *extack) +{ + if (!rulei->ipv6_valid) { + rulei->ipv6.prev_val = val; + rulei->ipv6_valid = true; + rulei->ipv6.prev_field = field; + return 0; + } + + NL_SET_ERR_MSG_MOD(extack, "Unsupported mangle field order"); + return -EOPNOTSUPP; +} + static int mlxsw_sp2_acl_rulei_act_mangle_field(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct mlxsw_sp_acl_mangle_action *mact, @@ -615,6 +635,61 @@ static int mlxsw_sp2_acl_rulei_act_mangle_field(struct mlxsw_sp *mlxsw_sp, return mlxsw_afa_block_append_l4port(rulei->act_block, false, val, extack); case MLXSW_SP_ACL_MANGLE_FIELD_IP_DPORT: return mlxsw_afa_block_append_l4port(rulei->act_block, true, val, extack); + /* IPv4 fields */ + case MLXSW_SP_ACL_MANGLE_FIELD_IP4_SIP: + return mlxsw_afa_block_append_ip(rulei->act_block, false, + true, val, 0, extack); + case MLXSW_SP_ACL_MANGLE_FIELD_IP4_DIP: + return mlxsw_afa_block_append_ip(rulei->act_block, true, + true, val, 0, extack); + /* IPv6 fields */ + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_1: + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_3: + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_1: + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_3: + return mlxsw_sp2_acl_rulei_act_mangle_field_ip_odd(rulei, + mact->field, + val, extack); + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_2: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_1) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + false, false, val, + rulei->ipv6.prev_val, + extack); + } + break; + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_4: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_3) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + false, true, val, + rulei->ipv6.prev_val, + extack); + } + break; + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_2: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_1) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + true, false, val, + rulei->ipv6.prev_val, + extack); + } + break; + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_4: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_3) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + true, true, val, + rulei->ipv6.prev_val, + extack); + } + break; default: break; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 20530712eadb..8b5d7f83b9b0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -1034,13 +1034,10 @@ static int mlxsw_sp_get_module_info(struct net_device *netdev, { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - int err; - - err = mlxsw_env_get_module_info(mlxsw_sp->core, - mlxsw_sp_port->mapping.module, - modinfo); - return err; + return mlxsw_env_get_module_info(netdev, mlxsw_sp->core, + mlxsw_sp_port->mapping.module, + modinfo); } static int mlxsw_sp_get_module_eeprom(struct net_device *netdev, @@ -1048,13 +1045,10 @@ static int mlxsw_sp_get_module_eeprom(struct net_device *netdev, { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - int err; - - err = mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core, - mlxsw_sp_port->mapping.module, ee, - data); - return err; + return mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core, + mlxsw_sp_port->mapping.module, ee, + data); } static int @@ -1273,12 +1267,22 @@ struct mlxsw_sp1_port_link_mode { static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { { + .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T, + .mask_ethtool = ETHTOOL_LINK_MODE_100baseT_Full_BIT, + .speed = SPEED_100, + }, + { .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, .mask_ethtool = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, .speed = SPEED_1000, }, { + .mask = MLXSW_REG_PTYS_ETH_SPEED_1000BASE_T, + .mask_ethtool = ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + .speed = SPEED_1000, + }, + { .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, .mask_ethtool = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index bb417db773b9..f54af3d9a03b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -233,6 +233,12 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return -EOPNOTSUPP; } } + + if (rulei->ipv6_valid) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported mangle field"); + return -EOPNOTSUPP; + } + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 0ff163fbc775..35422e64d89f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -568,12 +568,11 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress, u8 domain_number, u16 sequence_id, u64 timestamp) { - unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); struct mlxsw_sp_port *mlxsw_sp_port; struct mlxsw_sp1_ptp_key key; u8 types; - if (WARN_ON_ONCE(local_port >= max_ports)) + if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port))) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index f9671cc53002..5459490c7790 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -269,9 +269,7 @@ mlxsw_sp_span_entry_bridge_8021q(const struct net_device *br_dev, if (!vid && WARN_ON(br_vlan_get_pvid(br_dev, &vid))) return NULL; - if (!vid || - br_vlan_get_info(br_dev, vid, &vinfo) || - !(vinfo.flags & BRIDGE_VLAN_INFO_BRENTRY)) + if (!vid || br_vlan_get_info(br_dev, vid, &vinfo)) return NULL; edev = br_fdb_find_port(br_dev, dmac, vid); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 65c1724c63b0..3bf12092a8a2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1234,8 +1234,7 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, if (netif_is_bridge_master(orig_dev)) { int err = 0; - if ((vlan->flags & BRIDGE_VLAN_INFO_BRENTRY) && - br_vlan_enabled(orig_dev)) + if (br_vlan_enabled(orig_dev)) err = mlxsw_sp_br_ban_rif_pvid_change(mlxsw_sp, orig_dev, vlan); if (!err) @@ -2616,7 +2615,6 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, char *sfn_pl, int rec_index, bool adding) { - unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; struct mlxsw_sp_bridge_device *bridge_device; struct mlxsw_sp_bridge_port *bridge_port; @@ -2630,7 +2628,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port); - if (WARN_ON_ONCE(local_port >= max_ports)) + if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port))) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) { diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index 91a755efe2e6..5f1e7b8bad4f 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -750,7 +750,7 @@ static int lan743x_ethtool_set_eee(struct net_device *netdev, } if (eee->eee_enabled) { - ret = phy_init_eee(phydev, 0); + ret = phy_init_eee(phydev, false); if (ret) { netif_err(adapter, drv, adapter->netdev, "EEE initialization failed\n"); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 8c6390d95158..5282d25a6f9b 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -18,6 +18,51 @@ #include "lan743x_main.h" #include "lan743x_ethtool.h" +#define MMD_ACCESS_ADDRESS 0 +#define MMD_ACCESS_WRITE 1 +#define MMD_ACCESS_READ 2 +#define MMD_ACCESS_READ_INC 3 + +static void pci11x1x_strap_get_status(struct lan743x_adapter *adapter) +{ + u32 chip_rev; + u32 strap; + + strap = lan743x_csr_read(adapter, STRAP_READ); + if (strap & STRAP_READ_USE_SGMII_EN_) { + if (strap & STRAP_READ_SGMII_EN_) + adapter->is_sgmii_en = true; + else + adapter->is_sgmii_en = false; + netif_dbg(adapter, drv, adapter->netdev, + "STRAP_READ: 0x%08X\n", strap); + } else { + chip_rev = lan743x_csr_read(adapter, FPGA_REV); + if (chip_rev) { + if (chip_rev & FPGA_SGMII_OP) + adapter->is_sgmii_en = true; + else + adapter->is_sgmii_en = false; + netif_dbg(adapter, drv, adapter->netdev, + "FPGA_REV: 0x%08X\n", chip_rev); + } else { + adapter->is_sgmii_en = false; + } + } +} + +static bool is_pci11x1x_chip(struct lan743x_adapter *adapter) +{ + struct lan743x_csr *csr = &adapter->csr; + u32 id_rev = csr->id_rev; + + if (((id_rev & 0xFFFF0000) == ID_REV_ID_A011_) || + ((id_rev & 0xFFFF0000) == ID_REV_ID_A041_)) { + return true; + } + return false; +} + static void lan743x_pci_cleanup(struct lan743x_adapter *adapter) { pci_release_selected_regions(adapter->pdev, @@ -250,7 +295,7 @@ static void lan743x_intr_shared_isr(void *context, u32 int_sts, u32 flags) } } if (int_sts & INT_BIT_ALL_TX_) { - for (channel = 0; channel < LAN743X_USED_TX_CHANNELS; + for (channel = 0; channel < adapter->used_tx_channels; channel++) { u32 int_bit = INT_BIT_DMA_TX_(channel); @@ -410,7 +455,7 @@ static u32 lan743x_intr_get_vector_flags(struct lan743x_adapter *adapter, { int index; - for (index = 0; index < LAN743X_MAX_VECTOR_COUNT; index++) { + for (index = 0; index < adapter->max_vector_count; index++) { if (adapter->intr.vector_list[index].int_mask & int_mask) return adapter->intr.vector_list[index].flags; } @@ -423,9 +468,12 @@ static void lan743x_intr_close(struct lan743x_adapter *adapter) int index = 0; lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_MAS_); - lan743x_csr_write(adapter, INT_VEC_EN_CLR, 0x000000FF); + if (adapter->is_pci11x1x) + lan743x_csr_write(adapter, INT_VEC_EN_CLR, 0x0000FFFF); + else + lan743x_csr_write(adapter, INT_VEC_EN_CLR, 0x000000FF); - for (index = 0; index < LAN743X_MAX_VECTOR_COUNT; index++) { + for (index = 0; index < intr->number_of_vectors; index++) { if (intr->flags & INTR_FLAG_IRQ_REQUESTED(index)) { lan743x_intr_unregister_isr(adapter, index); intr->flags &= ~INTR_FLAG_IRQ_REQUESTED(index); @@ -445,9 +493,11 @@ static void lan743x_intr_close(struct lan743x_adapter *adapter) static int lan743x_intr_open(struct lan743x_adapter *adapter) { - struct msix_entry msix_entries[LAN743X_MAX_VECTOR_COUNT]; + struct msix_entry msix_entries[PCI11X1X_MAX_VECTOR_COUNT]; struct lan743x_intr *intr = &adapter->intr; + unsigned int used_tx_channels; u32 int_vec_en_auto_clr = 0; + u8 max_vector_count; u32 int_vec_map0 = 0; u32 int_vec_map1 = 0; int ret = -ENODEV; @@ -457,13 +507,15 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter) intr->number_of_vectors = 0; /* Try to set up MSIX interrupts */ + max_vector_count = adapter->max_vector_count; memset(&msix_entries[0], 0, - sizeof(struct msix_entry) * LAN743X_MAX_VECTOR_COUNT); - for (index = 0; index < LAN743X_MAX_VECTOR_COUNT; index++) + sizeof(struct msix_entry) * max_vector_count); + for (index = 0; index < max_vector_count; index++) msix_entries[index].entry = index; + used_tx_channels = adapter->used_tx_channels; ret = pci_enable_msix_range(adapter->pdev, msix_entries, 1, - 1 + LAN743X_USED_TX_CHANNELS + + 1 + used_tx_channels + LAN743X_USED_RX_CHANNELS); if (ret > 0) { @@ -556,8 +608,15 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter) lan743x_csr_write(adapter, INT_MOD_CFG5, LAN743X_INT_MOD); lan743x_csr_write(adapter, INT_MOD_CFG6, LAN743X_INT_MOD); lan743x_csr_write(adapter, INT_MOD_CFG7, LAN743X_INT_MOD); - lan743x_csr_write(adapter, INT_MOD_MAP0, 0x00005432); - lan743x_csr_write(adapter, INT_MOD_MAP1, 0x00000001); + if (adapter->is_pci11x1x) { + lan743x_csr_write(adapter, INT_MOD_CFG8, LAN743X_INT_MOD); + lan743x_csr_write(adapter, INT_MOD_CFG9, LAN743X_INT_MOD); + lan743x_csr_write(adapter, INT_MOD_MAP0, 0x00007654); + lan743x_csr_write(adapter, INT_MOD_MAP1, 0x00003210); + } else { + lan743x_csr_write(adapter, INT_MOD_MAP0, 0x00005432); + lan743x_csr_write(adapter, INT_MOD_MAP1, 0x00000001); + } lan743x_csr_write(adapter, INT_MOD_MAP2, 0x00FFFFFF); } @@ -570,8 +629,8 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter) if (intr->number_of_vectors > 1) { int number_of_tx_vectors = intr->number_of_vectors - 1; - if (number_of_tx_vectors > LAN743X_USED_TX_CHANNELS) - number_of_tx_vectors = LAN743X_USED_TX_CHANNELS; + if (number_of_tx_vectors > used_tx_channels) + number_of_tx_vectors = used_tx_channels; flags = LAN743X_VECTOR_FLAG_SOURCE_STATUS_READ | LAN743X_VECTOR_FLAG_SOURCE_STATUS_W2C | LAN743X_VECTOR_FLAG_SOURCE_ENABLE_CHECK | @@ -609,9 +668,9 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter) INT_VEC_EN_(vector)); } } - if ((intr->number_of_vectors - LAN743X_USED_TX_CHANNELS) > 1) { + if ((intr->number_of_vectors - used_tx_channels) > 1) { int number_of_rx_vectors = intr->number_of_vectors - - LAN743X_USED_TX_CHANNELS - 1; + used_tx_channels - 1; if (number_of_rx_vectors > LAN743X_USED_RX_CHANNELS) number_of_rx_vectors = LAN743X_USED_RX_CHANNELS; @@ -632,7 +691,7 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter) LAN743X_VECTOR_FLAG_SOURCE_STATUS_AUTO_CLEAR; } for (index = 0; index < number_of_rx_vectors; index++) { - int vector = index + 1 + LAN743X_USED_TX_CHANNELS; + int vector = index + 1 + used_tx_channels; u32 int_bit = INT_BIT_DMA_RX_(index); /* map RX interrupt to vector */ @@ -760,6 +819,96 @@ static int lan743x_mdiobus_write(struct mii_bus *bus, return ret; } +static u32 lan743x_mac_mmd_access(int id, int index, int op) +{ + u16 dev_addr; + u32 ret; + + dev_addr = (index >> 16) & 0x1f; + ret = (id << MAC_MII_ACC_PHY_ADDR_SHIFT_) & + MAC_MII_ACC_PHY_ADDR_MASK_; + ret |= (dev_addr << MAC_MII_ACC_MIIMMD_SHIFT_) & + MAC_MII_ACC_MIIMMD_MASK_; + if (op == MMD_ACCESS_WRITE) + ret |= MAC_MII_ACC_MIICMD_WRITE_; + else if (op == MMD_ACCESS_READ) + ret |= MAC_MII_ACC_MIICMD_READ_; + else if (op == MMD_ACCESS_READ_INC) + ret |= MAC_MII_ACC_MIICMD_READ_INC_; + else + ret |= MAC_MII_ACC_MIICMD_ADDR_; + ret |= (MAC_MII_ACC_MII_BUSY_ | MAC_MII_ACC_MIICL45_); + + return ret; +} + +static int lan743x_mdiobus_c45_read(struct mii_bus *bus, int phy_id, int index) +{ + struct lan743x_adapter *adapter = bus->priv; + u32 mmd_access; + int ret; + + /* comfirm MII not busy */ + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + if (index & MII_ADDR_C45) { + /* Load Register Address */ + lan743x_csr_write(adapter, MAC_MII_DATA, (u32)(index & 0xffff)); + mmd_access = lan743x_mac_mmd_access(phy_id, index, + MMD_ACCESS_ADDRESS); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + /* Read Data */ + mmd_access = lan743x_mac_mmd_access(phy_id, index, + MMD_ACCESS_READ); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + ret = lan743x_csr_read(adapter, MAC_MII_DATA); + return (int)(ret & 0xFFFF); + } + + ret = lan743x_mdiobus_read(bus, phy_id, index); + return ret; +} + +static int lan743x_mdiobus_c45_write(struct mii_bus *bus, + int phy_id, int index, u16 regval) +{ + struct lan743x_adapter *adapter = bus->priv; + u32 mmd_access; + int ret; + + /* confirm MII not busy */ + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + if (index & MII_ADDR_C45) { + /* Load Register Address */ + lan743x_csr_write(adapter, MAC_MII_DATA, (u32)(index & 0xffff)); + mmd_access = lan743x_mac_mmd_access(phy_id, index, + MMD_ACCESS_ADDRESS); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + if (ret < 0) + return ret; + /* Write Data */ + lan743x_csr_write(adapter, MAC_MII_DATA, (u32)regval); + mmd_access = lan743x_mac_mmd_access(phy_id, index, + MMD_ACCESS_WRITE); + lan743x_csr_write(adapter, MAC_MII_ACC, mmd_access); + ret = lan743x_mac_mii_wait_till_not_busy(adapter); + } else { + ret = lan743x_mdiobus_write(bus, phy_id, index, regval); + } + + return ret; +} + static void lan743x_mac_set_address(struct lan743x_adapter *adapter, u8 *addr) { @@ -2491,7 +2640,8 @@ static int lan743x_netdev_close(struct net_device *netdev) struct lan743x_adapter *adapter = netdev_priv(netdev); int index; - lan743x_tx_close(&adapter->tx[0]); + for (index = 0; index < adapter->used_tx_channels; index++) + lan743x_tx_close(&adapter->tx[index]); for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++) lan743x_rx_close(&adapter->rx[index]); @@ -2537,12 +2687,19 @@ static int lan743x_netdev_open(struct net_device *netdev) goto close_rx; } - ret = lan743x_tx_open(&adapter->tx[0]); - if (ret) - goto close_rx; - + for (index = 0; index < adapter->used_tx_channels; index++) { + ret = lan743x_tx_open(&adapter->tx[index]); + if (ret) + goto close_tx; + } return 0; +close_tx: + for (index = 0; index < adapter->used_tx_channels; index++) { + if (adapter->tx[index].ring_cpu_ptr) + lan743x_tx_close(&adapter->tx[index]); + } + close_rx: for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++) { if (adapter->rx[index].ring_cpu_ptr) @@ -2569,8 +2726,12 @@ static netdev_tx_t lan743x_netdev_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { struct lan743x_adapter *adapter = netdev_priv(netdev); + u8 ch = 0; - return lan743x_tx_xmit_frame(&adapter->tx[0], skb); + if (adapter->is_pci11x1x) + ch = skb->queue_mapping % PCI11X1X_USED_TX_CHANNELS; + + return lan743x_tx_xmit_frame(&adapter->tx[ch], skb); } static int lan743x_netdev_ioctl(struct net_device *netdev, @@ -2701,6 +2862,18 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, int index; int ret; + adapter->is_pci11x1x = is_pci11x1x_chip(adapter); + if (adapter->is_pci11x1x) { + adapter->max_tx_channels = PCI11X1X_MAX_TX_CHANNELS; + adapter->used_tx_channels = PCI11X1X_USED_TX_CHANNELS; + adapter->max_vector_count = PCI11X1X_MAX_VECTOR_COUNT; + pci11x1x_strap_get_status(adapter); + } else { + adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS; + adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS; + adapter->max_vector_count = LAN743X_MAX_VECTOR_COUNT; + } + adapter->intr.irq = adapter->pdev->irq; lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF); @@ -2731,15 +2904,19 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, adapter->rx[index].channel_number = index; } - tx = &adapter->tx[0]; - tx->adapter = adapter; - tx->channel_number = 0; - spin_lock_init(&tx->ring_lock); + for (index = 0; index < adapter->used_tx_channels; index++) { + tx = &adapter->tx[index]; + tx->adapter = adapter; + tx->channel_number = index; + spin_lock_init(&tx->ring_lock); + } + return 0; } static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) { + u32 sgmii_ctl; int ret; adapter->mdiobus = devm_mdiobus_alloc(&adapter->pdev->dev); @@ -2749,9 +2926,35 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) } adapter->mdiobus->priv = (void *)adapter; - adapter->mdiobus->read = lan743x_mdiobus_read; - adapter->mdiobus->write = lan743x_mdiobus_write; - adapter->mdiobus->name = "lan743x-mdiobus"; + if (adapter->is_pci11x1x) { + if (adapter->is_sgmii_en) { + sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); + sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_; + sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_; + lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); + netif_dbg(adapter, drv, adapter->netdev, + "SGMII operation\n"); + } else { + sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); + sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_; + sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_; + lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); + netif_dbg(adapter, drv, adapter->netdev, + "(R)GMII operation\n"); + } + + adapter->mdiobus->probe_capabilities = MDIOBUS_C22_C45; + adapter->mdiobus->read = lan743x_mdiobus_c45_read; + adapter->mdiobus->write = lan743x_mdiobus_c45_write; + adapter->mdiobus->name = "lan743x-mdiobus-c45"; + netif_dbg(adapter, drv, adapter->netdev, "lan743x-mdiobus-c45\n"); + } else { + adapter->mdiobus->read = lan743x_mdiobus_read; + adapter->mdiobus->write = lan743x_mdiobus_write; + adapter->mdiobus->name = "lan743x-mdiobus"; + netif_dbg(adapter, drv, adapter->netdev, "lan743x-mdiobus\n"); + } + snprintf(adapter->mdiobus->id, MII_BUS_ID_SIZE, "pci-%s", pci_name(adapter->pdev)); @@ -2786,8 +2989,17 @@ static int lan743x_pcidev_probe(struct pci_dev *pdev, struct net_device *netdev = NULL; int ret = -ENODEV; - netdev = devm_alloc_etherdev(&pdev->dev, - sizeof(struct lan743x_adapter)); + if (id->device == PCI_DEVICE_ID_SMSC_A011 || + id->device == PCI_DEVICE_ID_SMSC_A041) { + netdev = devm_alloc_etherdev_mqs(&pdev->dev, + sizeof(struct lan743x_adapter), + PCI11X1X_USED_TX_CHANNELS, + LAN743X_USED_RX_CHANNELS); + } else { + netdev = devm_alloc_etherdev(&pdev->dev, + sizeof(struct lan743x_adapter)); + } + if (!netdev) goto return_error; @@ -3056,6 +3268,8 @@ static const struct dev_pm_ops lan743x_pm_ops = { static const struct pci_device_id lan743x_pcidev_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) }, { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7431) }, + { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_A011) }, + { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_A041) }, { 0, } }; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index aaf7aaeaba0c..2c8e76b4e1f7 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -16,8 +16,13 @@ #define ID_REV_ID_MASK_ (0xFFFF0000) #define ID_REV_ID_LAN7430_ (0x74300000) #define ID_REV_ID_LAN7431_ (0x74310000) -#define ID_REV_IS_VALID_CHIP_ID_(id_rev) \ - (((id_rev) & 0xFFF00000) == 0x74300000) +#define ID_REV_ID_LAN743X_ (0x74300000) +#define ID_REV_ID_A011_ (0xA0110000) // PCI11010 +#define ID_REV_ID_A041_ (0xA0410000) // PCI11414 +#define ID_REV_ID_A0X1_ (0xA0010000) +#define ID_REV_IS_VALID_CHIP_ID_(id_rev) \ + ((((id_rev) & 0xFFF00000) == ID_REV_ID_LAN743X_) || \ + (((id_rev) & 0xFF0F0000) == ID_REV_ID_A0X1_)) #define ID_REV_CHIP_REV_MASK_ (0x0000FFFF) #define ID_REV_CHIP_REV_A0_ (0x00000000) #define ID_REV_CHIP_REV_B0_ (0x00000010) @@ -25,6 +30,17 @@ #define FPGA_REV (0x04) #define FPGA_REV_GET_MINOR_(fpga_rev) (((fpga_rev) >> 8) & 0x000000FF) #define FPGA_REV_GET_MAJOR_(fpga_rev) ((fpga_rev) & 0x000000FF) +#define FPGA_SGMII_OP BIT(24) + +#define STRAP_READ (0x0C) +#define STRAP_READ_USE_SGMII_EN_ BIT(22) +#define STRAP_READ_SGMII_EN_ BIT(6) +#define STRAP_READ_SGMII_REFCLK_ BIT(5) +#define STRAP_READ_SGMII_2_5G_ BIT(4) +#define STRAP_READ_BASE_X_ BIT(3) +#define STRAP_READ_RGMII_TXC_DELAY_EN_ BIT(2) +#define STRAP_READ_RGMII_RXC_DELAY_EN_ BIT(1) +#define STRAP_READ_ADV_PM_DISABLE_ BIT(0) #define HW_CFG (0x010) #define HW_CFG_RELOAD_TYPE_ALL_ (0x00000FC0) @@ -135,6 +151,13 @@ #define MAC_RX_ADDRL (0x11C) #define MAC_MII_ACC (0x120) +#define MAC_MII_ACC_MDC_CYCLE_SHIFT_ (16) +#define MAC_MII_ACC_MDC_CYCLE_MASK_ (0x00070000) +#define MAC_MII_ACC_MDC_CYCLE_2_5MHZ_ (0) +#define MAC_MII_ACC_MDC_CYCLE_5MHZ_ (1) +#define MAC_MII_ACC_MDC_CYCLE_12_5MHZ_ (2) +#define MAC_MII_ACC_MDC_CYCLE_25MHZ_ (3) +#define MAC_MII_ACC_MDC_CYCLE_1_25MHZ_ (4) #define MAC_MII_ACC_PHY_ADDR_SHIFT_ (11) #define MAC_MII_ACC_PHY_ADDR_MASK_ (0x0000F800) #define MAC_MII_ACC_MIIRINDA_SHIFT_ (6) @@ -143,6 +166,15 @@ #define MAC_MII_ACC_MII_WRITE_ (0x00000002) #define MAC_MII_ACC_MII_BUSY_ BIT(0) +#define MAC_MII_ACC_MIIMMD_SHIFT_ (6) +#define MAC_MII_ACC_MIIMMD_MASK_ (0x000007C0) +#define MAC_MII_ACC_MIICL45_ BIT(3) +#define MAC_MII_ACC_MIICMD_MASK_ (0x00000006) +#define MAC_MII_ACC_MIICMD_ADDR_ (0x00000000) +#define MAC_MII_ACC_MIICMD_WRITE_ (0x00000002) +#define MAC_MII_ACC_MIICMD_READ_ (0x00000004) +#define MAC_MII_ACC_MIICMD_READ_INC_ (0x00000006) + #define MAC_MII_DATA (0x124) #define MAC_EEE_TX_LPI_REQ_DLY_CNT (0x130) @@ -214,6 +246,11 @@ #define MAC_WUCSR2 (0x600) +#define SGMII_CTL (0x728) +#define SGMII_CTL_SGMII_ENABLE_ BIT(31) +#define SGMII_CTL_LINK_STATUS_SOURCE_ BIT(8) +#define SGMII_CTL_SGMII_POWER_DN_ BIT(1) + #define INT_STS (0x780) #define INT_BIT_DMA_RX_(channel) BIT(24 + (channel)) #define INT_BIT_ALL_RX_ (0x0F000000) @@ -261,6 +298,8 @@ #define INT_MOD_CFG5 (0x7D4) #define INT_MOD_CFG6 (0x7D8) #define INT_MOD_CFG7 (0x7DC) +#define INT_MOD_CFG8 (0x7E0) +#define INT_MOD_CFG9 (0x7E4) #define PTP_CMD_CTL (0x0A00) #define PTP_CMD_CTL_PTP_CLK_STP_NSEC_ BIT(6) @@ -541,10 +580,12 @@ #define LAN743X_MAX_RX_CHANNELS (4) #define LAN743X_MAX_TX_CHANNELS (1) +#define PCI11X1X_MAX_TX_CHANNELS (4) struct lan743x_adapter; #define LAN743X_USED_RX_CHANNELS (4) #define LAN743X_USED_TX_CHANNELS (1) +#define PCI11X1X_USED_TX_CHANNELS (4) #define LAN743X_INT_MOD (400) #if (LAN743X_USED_RX_CHANNELS > LAN743X_MAX_RX_CHANNELS) @@ -553,12 +594,17 @@ struct lan743x_adapter; #if (LAN743X_USED_TX_CHANNELS > LAN743X_MAX_TX_CHANNELS) #error Invalid LAN743X_USED_TX_CHANNELS #endif +#if (PCI11X1X_USED_TX_CHANNELS > PCI11X1X_MAX_TX_CHANNELS) +#error Invalid PCI11X1X_USED_TX_CHANNELS +#endif /* PCI */ /* SMSC acquired EFAR late 1990's, MCHP acquired SMSC 2012 */ #define PCI_VENDOR_ID_SMSC PCI_VENDOR_ID_EFAR #define PCI_DEVICE_ID_SMSC_LAN7430 (0x7430) #define PCI_DEVICE_ID_SMSC_LAN7431 (0x7431) +#define PCI_DEVICE_ID_SMSC_A011 (0xA011) +#define PCI_DEVICE_ID_SMSC_A041 (0xA041) #define PCI_CONFIG_LENGTH (0x1000) @@ -607,13 +653,14 @@ struct lan743x_vector { }; #define LAN743X_MAX_VECTOR_COUNT (8) +#define PCI11X1X_MAX_VECTOR_COUNT (16) struct lan743x_intr { int flags; unsigned int irq; - struct lan743x_vector vector_list[LAN743X_MAX_VECTOR_COUNT]; + struct lan743x_vector vector_list[PCI11X1X_MAX_VECTOR_COUNT]; int number_of_vectors; bool using_vectors; @@ -721,8 +768,13 @@ struct lan743x_adapter { u8 mac_address[ETH_ALEN]; struct lan743x_phy phy; - struct lan743x_tx tx[LAN743X_MAX_TX_CHANNELS]; - struct lan743x_rx rx[LAN743X_MAX_RX_CHANNELS]; + struct lan743x_tx tx[PCI11X1X_USED_TX_CHANNELS]; + struct lan743x_rx rx[LAN743X_USED_RX_CHANNELS]; + bool is_pci11x1x; + bool is_sgmii_en; + u8 max_tx_channels; + u8 used_tx_channels; + u8 max_vector_count; #define LAN743X_ADAPTER_FLAG_OTP BIT(0) u32 flags; diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index 8b7a8d879083..ec082594bbbd 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -1307,21 +1307,21 @@ int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) switch (config.tx_type) { case HWTSTAMP_TX_OFF: - for (index = 0; index < LAN743X_MAX_TX_CHANNELS; - index++) + for (index = 0; index < adapter->used_tx_channels; + index++) lan743x_tx_set_timestamping_mode(&adapter->tx[index], false, false); lan743x_ptp_set_sync_ts_insert(adapter, false); break; case HWTSTAMP_TX_ON: - for (index = 0; index < LAN743X_MAX_TX_CHANNELS; + for (index = 0; index < adapter->used_tx_channels; index++) lan743x_tx_set_timestamping_mode(&adapter->tx[index], true, false); lan743x_ptp_set_sync_ts_insert(adapter, false); break; case HWTSTAMP_TX_ONESTEP_SYNC: - for (index = 0; index < LAN743X_MAX_TX_CHANNELS; + for (index = 0; index < adapter->used_tx_channels; index++) lan743x_tx_set_timestamping_mode(&adapter->tx[index], true, true); diff --git a/drivers/net/ethernet/microchip/lan966x/Kconfig b/drivers/net/ethernet/microchip/lan966x/Kconfig index ac273f84b69e..4241ff0e5098 100644 --- a/drivers/net/ethernet/microchip/lan966x/Kconfig +++ b/drivers/net/ethernet/microchip/lan966x/Kconfig @@ -1,5 +1,6 @@ config LAN966X_SWITCH tristate "Lan966x switch driver" + depends on PTP_1588_CLOCK_OPTIONAL depends on HAS_IOMEM depends on OF depends on NET_SWITCHDEV diff --git a/drivers/net/ethernet/microchip/lan966x/Makefile b/drivers/net/ethernet/microchip/lan966x/Makefile index 040cfff9f577..a9ffc719aa0e 100644 --- a/drivers/net/ethernet/microchip/lan966x/Makefile +++ b/drivers/net/ethernet/microchip/lan966x/Makefile @@ -7,4 +7,5 @@ obj-$(CONFIG_LAN966X_SWITCH) += lan966x-switch.o lan966x-switch-objs := lan966x_main.o lan966x_phylink.o lan966x_port.o \ lan966x_mac.o lan966x_ethtool.o lan966x_switchdev.o \ - lan966x_vlan.o lan966x_fdb.o lan966x_mdb.o + lan966x_vlan.o lan966x_fdb.o lan966x_mdb.o \ + lan966x_ptp.o diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c index 614f12c2fe6a..e58a27fd8b50 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c @@ -545,6 +545,39 @@ static int lan966x_set_pauseparam(struct net_device *dev, return phylink_ethtool_set_pauseparam(port->phylink, pause); } +static int lan966x_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + struct lan966x_phc *phc; + + if (!lan966x->ptp) + return ethtool_op_get_ts_info(dev, info); + + phc = &lan966x->phc[LAN966X_PHC_PORT]; + + info->phc_index = phc->clock ? ptp_clock_index(phc->clock) : -1; + if (info->phc_index == -1) { + info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + return 0; + } + 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; +} + const struct ethtool_ops lan966x_ethtool_ops = { .get_link_ksettings = lan966x_get_link_ksettings, .set_link_ksettings = lan966x_set_link_ksettings, @@ -556,6 +589,7 @@ const struct ethtool_ops lan966x_ethtool_ops = { .get_eth_mac_stats = lan966x_get_eth_mac_stats, .get_rmon_stats = lan966x_get_eth_rmon_stats, .get_link = ethtool_op_get_link, + .get_ts_info = lan966x_get_ts_info, }; static void lan966x_check_stats_work(struct work_struct *work) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 1f60fd125a1d..4e877d9859bf 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -4,11 +4,13 @@ #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/iopoll.h> +#include <linux/ip.h> #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/packing.h> #include <linux/phy/phy.h> #include <linux/reset.h> +#include <net/addrconf.h> #include "lan966x_main.h" @@ -44,6 +46,7 @@ static const struct lan966x_main_io_resource lan966x_main_iomap[] = { { TARGET_ORG, 0, 1 }, /* 0xe2000000 */ { TARGET_GCB, 0x4000, 1 }, /* 0xe2004000 */ { TARGET_QS, 0x8000, 1 }, /* 0xe2008000 */ + { TARGET_PTP, 0xc000, 1 }, /* 0xe200c000 */ { TARGET_CHIP_TOP, 0x10000, 1 }, /* 0xe2010000 */ { TARGET_REW, 0x14000, 1 }, /* 0xe2014000 */ { TARGET_SYS, 0x28000, 1 }, /* 0xe2028000 */ @@ -201,7 +204,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, val = lan_rd(lan966x, QS_INJ_STATUS); if (!(QS_INJ_STATUS_FIFO_RDY_GET(val) & BIT(grp)) || (QS_INJ_STATUS_WMARK_REACHED_GET(val) & BIT(grp))) - return NETDEV_TX_BUSY; + goto err; /* Write start of frame */ lan_wr(QS_INJ_CTRL_GAP_SIZE_SET(1) | @@ -213,7 +216,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, /* Wait until the fifo is ready */ err = lan966x_port_inj_ready(lan966x, grp); if (err) - return NETDEV_TX_BUSY; + goto err; lan_wr((__force u32)ifh[i], lan966x, QS_INJ_WR(grp)); } @@ -225,7 +228,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, /* Wait until the fifo is ready */ err = lan966x_port_inj_ready(lan966x, grp); if (err) - return NETDEV_TX_BUSY; + goto err; lan_wr(((u32 *)skb->data)[i], lan966x, QS_INJ_WR(grp)); } @@ -235,7 +238,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, /* Wait until the fifo is ready */ err = lan966x_port_inj_ready(lan966x, grp); if (err) - return NETDEV_TX_BUSY; + goto err; lan_wr(0, lan966x, QS_INJ_WR(grp)); ++i; @@ -255,8 +258,19 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + return NETDEV_TX_OK; + dev_consume_skb_any(skb); return NETDEV_TX_OK; + +err: + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + lan966x_ptp_txtstamp_release(port, skb); + + return NETDEV_TX_BUSY; } static void lan966x_ifh_set_bypass(void *ifh, u64 bypass) @@ -289,10 +303,23 @@ static void lan966x_ifh_set_vid(void *ifh, u64 vid) IFH_POS_TCI, IFH_LEN * 4, PACK, 0); } +static void lan966x_ifh_set_rew_op(void *ifh, u64 rew_op) +{ + packing(ifh, &rew_op, IFH_POS_REW_CMD + IFH_WID_REW_CMD - 1, + IFH_POS_REW_CMD, IFH_LEN * 4, PACK, 0); +} + +static void lan966x_ifh_set_timestamp(void *ifh, u64 timestamp) +{ + packing(ifh, ×tamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1, + IFH_POS_TIMESTAMP, IFH_LEN * 4, PACK, 0); +} + static int lan966x_port_xmit(struct sk_buff *skb, struct net_device *dev) { struct lan966x_port *port = netdev_priv(dev); __be32 ifh[IFH_LEN]; + int err; memset(ifh, 0x0, sizeof(__be32) * IFH_LEN); @@ -302,6 +329,15 @@ static int lan966x_port_xmit(struct sk_buff *skb, struct net_device *dev) lan966x_ifh_set_ipv(ifh, skb->priority >= 7 ? 0x7 : skb->priority); lan966x_ifh_set_vid(ifh, skb_vlan_tag_get(skb)); + if (port->lan966x->ptp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + err = lan966x_ptp_txtstamp_request(port, skb); + if (err) + return err; + + lan966x_ifh_set_rew_op(ifh, LAN966X_SKB_CB(skb)->rew_op); + lan966x_ifh_set_timestamp(ifh, LAN966X_SKB_CB(skb)->ts_id); + } + return lan966x_port_ifh_xmit(skb, ifh, dev); } @@ -350,6 +386,23 @@ static int lan966x_port_get_parent_id(struct net_device *dev, return 0; } +static int lan966x_port_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) +{ + struct lan966x_port *port = netdev_priv(dev); + + if (!phy_has_hwtstamp(dev->phydev) && port->lan966x->ptp) { + switch (cmd) { + case SIOCSHWTSTAMP: + return lan966x_ptp_hwtstamp_set(port, ifr); + case SIOCGHWTSTAMP: + return lan966x_ptp_hwtstamp_get(port, ifr); + } + } + + return phy_mii_ioctl(dev->phydev, ifr, cmd); +} + static const struct net_device_ops lan966x_port_netdev_ops = { .ndo_open = lan966x_port_open, .ndo_stop = lan966x_port_stop, @@ -360,6 +413,7 @@ static const struct net_device_ops lan966x_port_netdev_ops = { .ndo_get_stats64 = lan966x_stats_get, .ndo_set_mac_address = lan966x_port_set_mac_address, .ndo_get_port_parent_id = lan966x_port_get_parent_id, + .ndo_eth_ioctl = lan966x_port_ioctl, }; bool lan966x_netdevice_check(const struct net_device *dev) @@ -367,6 +421,33 @@ bool lan966x_netdevice_check(const struct net_device *dev) return dev->netdev_ops == &lan966x_port_netdev_ops; } +static bool lan966x_hw_offload(struct lan966x *lan966x, u32 port, + struct sk_buff *skb) +{ + u32 val; + + /* The IGMP and MLD frames are not forward by the HW if + * multicast snooping is enabled, therefor don't mark as + * offload to allow the SW to forward the frames accordingly. + */ + val = lan_rd(lan966x, ANA_CPU_FWD_CFG(port)); + if (!(val & (ANA_CPU_FWD_CFG_IGMP_REDIR_ENA | + ANA_CPU_FWD_CFG_MLD_REDIR_ENA))) + return true; + + if (skb->protocol == htons(ETH_P_IP) && + ip_hdr(skb)->protocol == IPPROTO_IGMP) + return false; + + if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6) && + ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) && + !ipv6_mc_check_mld(skb)) + return false; + + return true; +} + static int lan966x_port_xtr_status(struct lan966x *lan966x, u8 grp) { return lan_rd(lan966x, QS_XTR_RD(grp)); @@ -434,6 +515,12 @@ static void lan966x_ifh_get_len(void *ifh, u64 *len) IFH_POS_LEN, IFH_LEN * 4, UNPACK, 0); } +static void lan966x_ifh_get_timestamp(void *ifh, u64 *timestamp) +{ + packing(ifh, timestamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1, + IFH_POS_TIMESTAMP, IFH_LEN * 4, UNPACK, 0); +} + static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) { struct lan966x *lan966x = args; @@ -443,10 +530,10 @@ static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) return IRQ_NONE; do { + u64 src_port, len, timestamp; struct net_device *dev; struct sk_buff *skb; int sz = 0, buf_len; - u64 src_port, len; u32 ifh[IFH_LEN]; u32 *buf; u32 val; @@ -461,6 +548,7 @@ static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) lan966x_ifh_get_src_port(ifh, &src_port); lan966x_ifh_get_len(ifh, &len); + lan966x_ifh_get_timestamp(ifh, ×tamp); WARN_ON(src_port >= lan966x->num_phys_ports); @@ -501,11 +589,17 @@ static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) *buf = val; } + lan966x_ptp_rxtstamp(lan966x, skb, timestamp); skb->protocol = eth_type_trans(skb, dev); - if (lan966x->bridge_mask & BIT(src_port)) + if (lan966x->bridge_mask & BIT(src_port)) { skb->offload_fwd_mark = 1; + skb_reset_network_header(skb); + if (!lan966x_hw_offload(lan966x, src_port, skb)) + skb->offload_fwd_mark = 0; + } + netif_rx_ni(skb); dev->stats.rx_bytes += len; dev->stats.rx_packets++; @@ -628,7 +722,6 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, } port->phylink = phylink; - phylink_set_pcs(phylink, &port->phylink_pcs); err = register_netdev(dev); if (err) { @@ -708,7 +801,7 @@ static void lan966x_init(struct lan966x *lan966x) /* Setup flooding PGIDs */ lan_wr(ANA_FLOODING_IPMC_FLD_MC4_DATA_SET(PGID_MCIPV4) | ANA_FLOODING_IPMC_FLD_MC4_CTRL_SET(PGID_MC) | - ANA_FLOODING_IPMC_FLD_MC6_DATA_SET(PGID_MC) | + ANA_FLOODING_IPMC_FLD_MC6_DATA_SET(PGID_MCIPV6) | ANA_FLOODING_IPMC_FLD_MC6_CTRL_SET(PGID_MC), lan966x, ANA_FLOODING_IPMC); @@ -770,6 +863,10 @@ static void lan966x_init(struct lan966x *lan966x) ANA_PGID_PGID, lan966x, ANA_PGID(PGID_MCIPV4)); + lan_rmw(GENMASK(lan966x->num_phys_ports - 1, 0), + ANA_PGID_PGID, + lan966x, ANA_PGID(PGID_MCIPV6)); + /* Unicast to all other ports */ lan_rmw(GENMASK(lan966x->num_phys_ports - 1, 0), ANA_PGID_PGID, @@ -897,6 +994,17 @@ static int lan966x_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, err, "Unable to use ana irq"); } + lan966x->ptp_irq = platform_get_irq_byname(pdev, "ptp"); + if (lan966x->ptp_irq > 0) { + err = devm_request_threaded_irq(&pdev->dev, lan966x->ptp_irq, NULL, + lan966x_ptp_irq_handler, IRQF_ONESHOT, + "ptp irq", lan966x); + if (err) + return dev_err_probe(&pdev->dev, err, "Unable to use ptp irq"); + + lan966x->ptp = 1; + } + /* init switch */ lan966x_init(lan966x); lan966x_stats_init(lan966x); @@ -931,8 +1039,15 @@ static int lan966x_probe(struct platform_device *pdev) if (err) goto cleanup_ports; + err = lan966x_ptp_init(lan966x); + if (err) + goto cleanup_fdb; + return 0; +cleanup_fdb: + lan966x_fdb_deinit(lan966x); + cleanup_ports: fwnode_handle_put(portnp); @@ -958,6 +1073,7 @@ static int lan966x_remove(struct platform_device *pdev) lan966x_mac_purge_entries(lan966x); lan966x_mdb_deinit(lan966x); lan966x_fdb_deinit(lan966x); + lan966x_ptp_deinit(lan966x); return 0; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 99c6d0a9f946..058e43531818 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -8,6 +8,7 @@ #include <linux/jiffies.h> #include <linux/phy.h> #include <linux/phylink.h> +#include <linux/ptp_clock_kernel.h> #include <net/switchdev.h> #include "lan966x_regs.h" @@ -50,6 +51,13 @@ #define LAN966X_SPEED_100 2 #define LAN966X_SPEED_10 3 +#define LAN966X_PHC_COUNT 3 +#define LAN966X_PHC_PORT 0 + +#define IFH_REW_OP_NOOP 0x0 +#define IFH_REW_OP_ONE_STEP_PTP 0x3 +#define IFH_REW_OP_TWO_STEP_PTP 0x4 + /* MAC table entry types. * ENTRYTYPE_NORMAL is subject to aging. * ENTRYTYPE_LOCKED is not subject to aging. @@ -70,6 +78,24 @@ struct lan966x_stat_layout { char name[ETH_GSTRING_LEN]; }; +struct lan966x_phc { + struct ptp_clock *clock; + struct ptp_clock_info info; + struct hwtstamp_config hwtstamp_config; + struct lan966x *lan966x; + u8 index; +}; + +struct lan966x_skb_cb { + u8 rew_op; + u16 ts_id; + unsigned long jiffies; +}; + +#define LAN966X_PTP_TIMEOUT msecs_to_jiffies(10) +#define LAN966X_SKB_CB(skb) \ + ((struct lan966x_skb_cb *)((skb)->cb)) + struct lan966x { struct device *dev; @@ -105,6 +131,7 @@ struct lan966x { /* interrupts */ int xtr_irq; int ana_irq; + int ptp_irq; /* worqueue for fdb */ struct workqueue_struct *fdb_work; @@ -113,6 +140,14 @@ struct lan966x { /* mdb */ struct list_head mdb_entries; struct list_head pgid_entries; + + /* ptp */ + bool ptp; + struct lan966x_phc phc[LAN966X_PHC_COUNT]; + spinlock_t ptp_clock_lock; /* lock for phc */ + spinlock_t ptp_ts_id_lock; /* lock for ts_id */ + struct mutex ptp_lock; /* lock for ptp interface state */ + u16 ptp_skbs; }; struct lan966x_port_config { @@ -135,6 +170,7 @@ struct lan966x_port { bool vlan_aware; bool learn_ena; + bool mcast_ena; struct phylink_config phylink_config; struct phylink_pcs phylink_pcs; @@ -142,6 +178,10 @@ struct lan966x_port { struct phylink *phylink; struct phy *serdes; struct fwnode_handle *fwnode; + + u8 ptp_cmd; + u16 ts_id; + struct sk_buff_head tx_skbs; }; extern const struct phylink_mac_ops lan966x_phylink_mac_ops; @@ -227,6 +267,20 @@ int lan966x_handle_port_mdb_del(struct lan966x_port *port, const struct switchdev_obj *obj); void lan966x_mdb_erase_entries(struct lan966x *lan966x, u16 vid); void lan966x_mdb_write_entries(struct lan966x *lan966x, u16 vid); +void lan966x_mdb_clear_entries(struct lan966x *lan966x); +void lan966x_mdb_restore_entries(struct lan966x *lan966x); + +int lan966x_ptp_init(struct lan966x *lan966x); +void lan966x_ptp_deinit(struct lan966x *lan966x); +int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr); +int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr); +void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb, + u64 timestamp); +int lan966x_ptp_txtstamp_request(struct lan966x_port *port, + struct sk_buff *skb); +void lan966x_ptp_txtstamp_release(struct lan966x_port *port, + struct sk_buff *skb); +irqreturn_t lan966x_ptp_irq_handler(int irq, void *args); static inline void __iomem *lan_addr(void __iomem *base[], int id, int tinst, int tcnt, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c index c68d0a99d292..2af55268bf4d 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c @@ -504,3 +504,48 @@ void lan966x_mdb_erase_entries(struct lan966x *lan966x, u16 vid) lan966x_mdb_l2_cpu_remove(lan966x, mdb_entry, type); } } + +void lan966x_mdb_clear_entries(struct lan966x *lan966x) +{ + struct lan966x_mdb_entry *mdb_entry; + enum macaccess_entry_type type; + unsigned char mac[ETH_ALEN]; + + list_for_each_entry(mdb_entry, &lan966x->mdb_entries, list) { + type = lan966x_mdb_classify(mdb_entry->mac); + + lan966x_mdb_encode_mac(mac, mdb_entry, type); + /* Remove just the MAC entry, still keep the PGID in case of L2 + * entries because this can be restored at later point + */ + lan966x_mac_forget(lan966x, mac, mdb_entry->vid, type); + } +} + +void lan966x_mdb_restore_entries(struct lan966x *lan966x) +{ + struct lan966x_mdb_entry *mdb_entry; + enum macaccess_entry_type type; + unsigned char mac[ETH_ALEN]; + bool cpu_copy = false; + + list_for_each_entry(mdb_entry, &lan966x->mdb_entries, list) { + type = lan966x_mdb_classify(mdb_entry->mac); + + lan966x_mdb_encode_mac(mac, mdb_entry, type); + if (type == ENTRYTYPE_MACV4 || type == ENTRYTYPE_MACV6) { + /* Copy the frame to CPU only if the CPU is in the VLAN */ + if (lan966x_vlan_cpu_member_cpu_vlan_mask(lan966x, + mdb_entry->vid) && + mdb_entry->cpu_copy) + cpu_copy = true; + + lan966x_mac_ip_learn(lan966x, cpu_copy, mac, + mdb_entry->vid, type); + } else { + lan966x_mac_learn(lan966x, mdb_entry->pgid->index, + mdb_entry->mac, + mdb_entry->vid, type); + } + } +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c index b66a9aa00ea4..38a7e95d69b4 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c @@ -9,6 +9,14 @@ #include "lan966x_main.h" +static struct phylink_pcs *lan966x_phylink_mac_select(struct phylink_config *config, + phy_interface_t interface) +{ + struct lan966x_port *port = netdev_priv(to_net_dev(config->dev)); + + return &port->phylink_pcs; +} + static void lan966x_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -114,6 +122,7 @@ static void lan966x_pcs_aneg_restart(struct phylink_pcs *pcs) const struct phylink_mac_ops lan966x_phylink_mac_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = lan966x_phylink_mac_select, .mac_config = lan966x_phylink_mac_config, .mac_prepare = lan966x_phylink_mac_prepare, .mac_link_down = lan966x_phylink_mac_link_down, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c new file mode 100644 index 000000000000..ae782778d6dd --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -0,0 +1,618 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/ptp_classify.h> + +#include "lan966x_main.h" + +#define LAN966X_MAX_PTP_ID 512 + +/* Represents 1ppm adjustment in 2^59 format with 6.037735849ns as reference + * The value is calculated as following: (1/1000000)/((2^-59)/6.037735849) + */ +#define LAN966X_1PPM_FORMAT 3480517749723LL + +/* Represents 1ppb adjustment in 2^29 format with 6.037735849ns as reference + * The value is calculated as following: (1/1000000000)/((2^59)/6.037735849) + */ +#define LAN966X_1PPB_FORMAT 3480517749LL + +#define TOD_ACC_PIN 0x5 + +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_TOD +}; + +static u64 lan966x_ptp_get_nominal_value(void) +{ + u64 res = 0x304d2df1; + + res <<= 32; + return res; +} + +int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr) +{ + struct lan966x *lan966x = port->lan966x; + struct hwtstamp_config cfg; + struct lan966x_phc *phc; + + /* For now don't allow to run ptp on ports that are part of a bridge, + * because in case of transparent clock the HW will still forward the + * frames, so there would be duplicate frames + */ + if (lan966x->bridge_mask & BIT(port->chip_port)) + return -EINVAL; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + switch (cfg.tx_type) { + case HWTSTAMP_TX_ON: + port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; + break; + case HWTSTAMP_TX_ONESTEP_SYNC: + port->ptp_cmd = IFH_REW_OP_ONE_STEP_PTP; + break; + case HWTSTAMP_TX_OFF: + port->ptp_cmd = IFH_REW_OP_NOOP; + break; + default: + return -ERANGE; + } + + switch (cfg.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + cfg.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + /* Commit back the result & save it */ + mutex_lock(&lan966x->ptp_lock); + phc = &lan966x->phc[LAN966X_PHC_PORT]; + memcpy(&phc->hwtstamp_config, &cfg, sizeof(cfg)); + mutex_unlock(&lan966x->ptp_lock); + + return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; +} + +int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr) +{ + struct lan966x *lan966x = port->lan966x; + struct lan966x_phc *phc; + + phc = &lan966x->phc[LAN966X_PHC_PORT]; + return copy_to_user(ifr->ifr_data, &phc->hwtstamp_config, + sizeof(phc->hwtstamp_config)) ? -EFAULT : 0; +} + +static int lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb) +{ + struct ptp_header *header; + u8 msgtype; + int type; + + if (port->ptp_cmd == IFH_REW_OP_NOOP) + return IFH_REW_OP_NOOP; + + type = ptp_classify_raw(skb); + if (type == PTP_CLASS_NONE) + return IFH_REW_OP_NOOP; + + header = ptp_parse_header(skb, type); + if (!header) + return IFH_REW_OP_NOOP; + + if (port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + return IFH_REW_OP_TWO_STEP_PTP; + + /* If it is sync and run 1 step then set the correct operation, + * otherwise run as 2 step + */ + msgtype = ptp_get_msgtype(header, type); + if ((msgtype & 0xf) == 0) + return IFH_REW_OP_ONE_STEP_PTP; + + return IFH_REW_OP_TWO_STEP_PTP; +} + +static void lan966x_ptp_txtstamp_old_release(struct lan966x_port *port) +{ + struct sk_buff *skb, *skb_tmp; + unsigned long flags; + + spin_lock_irqsave(&port->tx_skbs.lock, flags); + skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { + if time_after(LAN966X_SKB_CB(skb)->jiffies + LAN966X_PTP_TIMEOUT, + jiffies) + break; + + __skb_unlink(skb, &port->tx_skbs); + dev_kfree_skb_any(skb); + } + spin_unlock_irqrestore(&port->tx_skbs.lock, flags); +} + +int lan966x_ptp_txtstamp_request(struct lan966x_port *port, + struct sk_buff *skb) +{ + struct lan966x *lan966x = port->lan966x; + unsigned long flags; + u8 rew_op; + + rew_op = lan966x_ptp_classify(port, skb); + LAN966X_SKB_CB(skb)->rew_op = rew_op; + + if (rew_op != IFH_REW_OP_TWO_STEP_PTP) + return 0; + + lan966x_ptp_txtstamp_old_release(port); + + spin_lock_irqsave(&lan966x->ptp_ts_id_lock, flags); + if (lan966x->ptp_skbs == LAN966X_MAX_PTP_ID) { + spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags); + return -EBUSY; + } + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + skb_queue_tail(&port->tx_skbs, skb); + LAN966X_SKB_CB(skb)->ts_id = port->ts_id; + LAN966X_SKB_CB(skb)->jiffies = jiffies; + + lan966x->ptp_skbs++; + port->ts_id++; + if (port->ts_id == LAN966X_MAX_PTP_ID) + port->ts_id = 0; + + spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags); + + return 0; +} + +void lan966x_ptp_txtstamp_release(struct lan966x_port *port, + struct sk_buff *skb) +{ + struct lan966x *lan966x = port->lan966x; + unsigned long flags; + + spin_lock_irqsave(&lan966x->ptp_ts_id_lock, flags); + port->ts_id--; + lan966x->ptp_skbs--; + skb_unlink(skb, &port->tx_skbs); + spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags); +} + +static void lan966x_get_hwtimestamp(struct lan966x *lan966x, + struct timespec64 *ts, + u32 nsec) +{ + /* Read current PTP time to get seconds */ + unsigned long flags; + u32 curr_nsec; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_SAVE) | + PTP_PIN_CFG_PIN_DOM_SET(LAN966X_PHC_PORT) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + ts->tv_sec = lan_rd(lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN)); + curr_nsec = lan_rd(lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + + ts->tv_nsec = nsec; + + /* Sec has incremented since the ts was registered */ + if (curr_nsec < nsec) + ts->tv_sec--; + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); +} + +irqreturn_t lan966x_ptp_irq_handler(int irq, void *args) +{ + int budget = LAN966X_MAX_PTP_ID; + struct lan966x *lan966x = args; + + while (budget--) { + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shhwtstamps; + struct lan966x_port *port; + struct timespec64 ts; + unsigned long flags; + u32 val, id, txport; + u32 delay; + + val = lan_rd(lan966x, PTP_TWOSTEP_CTRL); + + /* Check if a timestamp can be retrieved */ + if (!(val & PTP_TWOSTEP_CTRL_VLD)) + break; + + WARN_ON(val & PTP_TWOSTEP_CTRL_OVFL); + + if (!(val & PTP_TWOSTEP_CTRL_STAMP_TX)) + continue; + + /* Retrieve the ts Tx port */ + txport = PTP_TWOSTEP_CTRL_STAMP_PORT_GET(val); + + /* Retrieve its associated skb */ + port = lan966x->ports[txport]; + + /* Retrieve the delay */ + delay = lan_rd(lan966x, PTP_TWOSTEP_STAMP); + delay = PTP_TWOSTEP_STAMP_STAMP_NSEC_GET(delay); + + /* Get next timestamp from fifo, which needs to be the + * rx timestamp which represents the id of the frame + */ + lan_rmw(PTP_TWOSTEP_CTRL_NXT_SET(1), + PTP_TWOSTEP_CTRL_NXT, + lan966x, PTP_TWOSTEP_CTRL); + + val = lan_rd(lan966x, PTP_TWOSTEP_CTRL); + + /* Check if a timestamp can be retried */ + if (!(val & PTP_TWOSTEP_CTRL_VLD)) + break; + + /* Read RX timestamping to get the ID */ + id = lan_rd(lan966x, PTP_TWOSTEP_STAMP); + + spin_lock_irqsave(&port->tx_skbs.lock, flags); + skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { + if (LAN966X_SKB_CB(skb)->ts_id != id) + continue; + + __skb_unlink(skb, &port->tx_skbs); + skb_match = skb; + break; + } + spin_unlock_irqrestore(&port->tx_skbs.lock, flags); + + /* Next ts */ + lan_rmw(PTP_TWOSTEP_CTRL_NXT_SET(1), + PTP_TWOSTEP_CTRL_NXT, + lan966x, PTP_TWOSTEP_CTRL); + + if (WARN_ON(!skb_match)) + continue; + + spin_lock(&lan966x->ptp_ts_id_lock); + lan966x->ptp_skbs--; + spin_unlock(&lan966x->ptp_ts_id_lock); + + /* Get the h/w timestamp */ + lan966x_get_hwtimestamp(lan966x, &ts, delay); + + /* Set the timestamp into the skb */ + shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); + skb_tstamp_tx(skb_match, &shhwtstamps); + + dev_kfree_skb_any(skb_match); + } + + return IRQ_HANDLED; +} + +static int lan966x_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + unsigned long flags; + bool neg_adj = 0; + u64 tod_inc; + u64 ref; + + if (!scaled_ppm) + return 0; + + if (scaled_ppm < 0) { + neg_adj = 1; + scaled_ppm = -scaled_ppm; + } + + tod_inc = lan966x_ptp_get_nominal_value(); + + /* The multiplication is split in 2 separate additions because of + * overflow issues. If scaled_ppm with 16bit fractional part was bigger + * than 20ppm then we got overflow. + */ + ref = LAN966X_1PPM_FORMAT * (scaled_ppm >> 16); + ref += (LAN966X_1PPM_FORMAT * (0xffff & scaled_ppm)) >> 16; + tod_inc = neg_adj ? tod_inc - ref : tod_inc + ref; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(1 << BIT(phc->index)), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + lan_wr((u32)tod_inc & 0xFFFFFFFF, lan966x, + PTP_CLK_PER_CFG(phc->index, 0)); + lan_wr((u32)(tod_inc >> 32), lan966x, + PTP_CLK_PER_CFG(phc->index, 1)); + + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + + return 0; +} + +static int lan966x_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + unsigned long flags; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + /* Must be in IDLE mode before the time can be loaded */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_IDLE) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + /* Set new value */ + lan_wr(PTP_TOD_SEC_MSB_TOD_SEC_MSB_SET(upper_32_bits(ts->tv_sec)), + lan966x, PTP_TOD_SEC_MSB(TOD_ACC_PIN)); + lan_wr(lower_32_bits(ts->tv_sec), + lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN)); + lan_wr(ts->tv_nsec, lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + + /* Apply new values */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_LOAD) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + + return 0; +} + +static int lan966x_ptp_gettime64(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + unsigned long flags; + time64_t s; + s64 ns; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_SAVE) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + s = lan_rd(lan966x, PTP_TOD_SEC_MSB(TOD_ACC_PIN)); + s <<= 32; + s |= lan_rd(lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN)); + ns = lan_rd(lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + ns &= PTP_TOD_NSEC_TOD_NSEC; + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + + /* Deal with negative values */ + if ((ns & 0xFFFFFFF0) == 0x3FFFFFF0) { + s--; + ns &= 0xf; + ns += 999999984; + } + + set_normalized_timespec64(ts, s, ns); + return 0; +} + +static int lan966x_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + + if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) { + unsigned long flags; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + /* Must be in IDLE mode before the time can be loaded */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_IDLE) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + lan_wr(PTP_TOD_NSEC_TOD_NSEC_SET(delta), + lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + + /* Adjust time with the value of PTP_TOD_NSEC */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_DELTA) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + } else { + /* Fall back using lan966x_ptp_settime64 which is not exact */ + struct timespec64 ts; + u64 now; + + lan966x_ptp_gettime64(ptp, &ts); + + now = ktime_to_ns(timespec64_to_ktime(ts)); + ts = ns_to_timespec64(now + delta); + + lan966x_ptp_settime64(ptp, &ts); + } + + return 0; +} + +static struct ptp_clock_info lan966x_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "lan966x ptp", + .max_adj = 200000, + .gettime64 = lan966x_ptp_gettime64, + .settime64 = lan966x_ptp_settime64, + .adjtime = lan966x_ptp_adjtime, + .adjfine = lan966x_ptp_adjfine, +}; + +static int lan966x_ptp_phc_init(struct lan966x *lan966x, + int index, + struct ptp_clock_info *clock_info) +{ + struct lan966x_phc *phc = &lan966x->phc[index]; + + phc->info = *clock_info; + phc->clock = ptp_clock_register(&phc->info, lan966x->dev); + if (IS_ERR(phc->clock)) + return PTR_ERR(phc->clock); + + phc->index = index; + phc->lan966x = lan966x; + + /* PTP Rx stamping is always enabled. */ + phc->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + + return 0; +} + +int lan966x_ptp_init(struct lan966x *lan966x) +{ + u64 tod_adj = lan966x_ptp_get_nominal_value(); + struct lan966x_port *port; + int err, i; + + if (!lan966x->ptp) + return 0; + + for (i = 0; i < LAN966X_PHC_COUNT; ++i) { + err = lan966x_ptp_phc_init(lan966x, i, &lan966x_ptp_clock_info); + if (err) + return err; + } + + spin_lock_init(&lan966x->ptp_clock_lock); + spin_lock_init(&lan966x->ptp_ts_id_lock); + mutex_init(&lan966x->ptp_lock); + + /* Disable master counters */ + lan_wr(PTP_DOM_CFG_ENA_SET(0), lan966x, PTP_DOM_CFG); + + /* Configure the nominal TOD increment per clock cycle */ + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0x7), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + for (i = 0; i < LAN966X_PHC_COUNT; ++i) { + lan_wr((u32)tod_adj & 0xFFFFFFFF, lan966x, + PTP_CLK_PER_CFG(i, 0)); + lan_wr((u32)(tod_adj >> 32), lan966x, + PTP_CLK_PER_CFG(i, 1)); + } + + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + /* Enable master counters */ + lan_wr(PTP_DOM_CFG_ENA_SET(0x7), lan966x, PTP_DOM_CFG); + + for (i = 0; i < lan966x->num_phys_ports; i++) { + port = lan966x->ports[i]; + if (!port) + continue; + + skb_queue_head_init(&port->tx_skbs); + } + + return 0; +} + +void lan966x_ptp_deinit(struct lan966x *lan966x) +{ + struct lan966x_port *port; + int i; + + for (i = 0; i < lan966x->num_phys_ports; i++) { + port = lan966x->ports[i]; + if (!port) + continue; + + skb_queue_purge(&port->tx_skbs); + } + + for (i = 0; i < LAN966X_PHC_COUNT; ++i) + ptp_clock_unregister(lan966x->phc[i].clock); +} + +void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb, + u64 timestamp) +{ + struct skb_shared_hwtstamps *shhwtstamps; + struct lan966x_phc *phc; + struct timespec64 ts; + u64 full_ts_in_ns; + + if (!lan966x->ptp) + return; + + phc = &lan966x->phc[LAN966X_PHC_PORT]; + lan966x_ptp_gettime64(&phc->info, &ts); + + /* Drop the sub-ns precision */ + timestamp = timestamp >> 2; + if (ts.tv_nsec < timestamp) + ts.tv_sec--; + ts.tv_nsec = timestamp; + full_ts_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec); + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = full_ts_in_ns; +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h index 797560172aca..0c0b3e173d53 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h @@ -19,6 +19,7 @@ enum lan966x_target { TARGET_DEV = 13, TARGET_GCB = 27, TARGET_ORG = 36, + TARGET_PTP = 41, TARGET_QS = 42, TARGET_QSYS = 46, TARGET_REW = 47, @@ -298,6 +299,24 @@ enum lan966x_target { /* ANA:PORT:CPU_FWD_CFG */ #define ANA_CPU_FWD_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 96, 0, 1, 4) +#define ANA_CPU_FWD_CFG_MLD_REDIR_ENA BIT(6) +#define ANA_CPU_FWD_CFG_MLD_REDIR_ENA_SET(x)\ + FIELD_PREP(ANA_CPU_FWD_CFG_MLD_REDIR_ENA, x) +#define ANA_CPU_FWD_CFG_MLD_REDIR_ENA_GET(x)\ + FIELD_GET(ANA_CPU_FWD_CFG_MLD_REDIR_ENA, x) + +#define ANA_CPU_FWD_CFG_IGMP_REDIR_ENA BIT(5) +#define ANA_CPU_FWD_CFG_IGMP_REDIR_ENA_SET(x)\ + FIELD_PREP(ANA_CPU_FWD_CFG_IGMP_REDIR_ENA, x) +#define ANA_CPU_FWD_CFG_IGMP_REDIR_ENA_GET(x)\ + FIELD_GET(ANA_CPU_FWD_CFG_IGMP_REDIR_ENA, x) + +#define ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA BIT(4) +#define ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA_SET(x)\ + FIELD_PREP(ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA, x) +#define ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA_GET(x)\ + FIELD_GET(ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA, x) + #define ANA_CPU_FWD_CFG_SRC_COPY_ENA BIT(3) #define ANA_CPU_FWD_CFG_SRC_COPY_ENA_SET(x)\ FIELD_PREP(ANA_CPU_FWD_CFG_SRC_COPY_ENA, x) @@ -559,6 +578,108 @@ enum lan966x_target { #define DEV_PCS1G_STICKY_LINK_DOWN_STICKY_GET(x)\ FIELD_GET(DEV_PCS1G_STICKY_LINK_DOWN_STICKY, x) +/* PTP:PTP_CFG:PTP_DOM_CFG */ +#define PTP_DOM_CFG __REG(TARGET_PTP, 0, 1, 512, 0, 1, 16, 12, 0, 1, 4) + +#define PTP_DOM_CFG_ENA GENMASK(11, 9) +#define PTP_DOM_CFG_ENA_SET(x)\ + FIELD_PREP(PTP_DOM_CFG_ENA, x) +#define PTP_DOM_CFG_ENA_GET(x)\ + FIELD_GET(PTP_DOM_CFG_ENA, x) + +#define PTP_DOM_CFG_CLKCFG_DIS GENMASK(2, 0) +#define PTP_DOM_CFG_CLKCFG_DIS_SET(x)\ + FIELD_PREP(PTP_DOM_CFG_CLKCFG_DIS, x) +#define PTP_DOM_CFG_CLKCFG_DIS_GET(x)\ + FIELD_GET(PTP_DOM_CFG_CLKCFG_DIS, x) + +/* PTP:PTP_TOD_DOMAINS:CLK_PER_CFG */ +#define PTP_CLK_PER_CFG(g, r) __REG(TARGET_PTP, 0, 1, 528, g, 3, 28, 0, r, 2, 4) + +/* PTP:PTP_PINS:PTP_PIN_CFG */ +#define PTP_PIN_CFG(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 0, 0, 1, 4) + +#define PTP_PIN_CFG_PIN_ACTION GENMASK(29, 27) +#define PTP_PIN_CFG_PIN_ACTION_SET(x)\ + FIELD_PREP(PTP_PIN_CFG_PIN_ACTION, x) +#define PTP_PIN_CFG_PIN_ACTION_GET(x)\ + FIELD_GET(PTP_PIN_CFG_PIN_ACTION, x) + +#define PTP_PIN_CFG_PIN_SYNC GENMASK(26, 25) +#define PTP_PIN_CFG_PIN_SYNC_SET(x)\ + FIELD_PREP(PTP_PIN_CFG_PIN_SYNC, x) +#define PTP_PIN_CFG_PIN_SYNC_GET(x)\ + FIELD_GET(PTP_PIN_CFG_PIN_SYNC, x) + +#define PTP_PIN_CFG_PIN_DOM GENMASK(17, 16) +#define PTP_PIN_CFG_PIN_DOM_SET(x)\ + FIELD_PREP(PTP_PIN_CFG_PIN_DOM, x) +#define PTP_PIN_CFG_PIN_DOM_GET(x)\ + FIELD_GET(PTP_PIN_CFG_PIN_DOM, x) + +/* PTP:PTP_PINS:PTP_TOD_SEC_MSB */ +#define PTP_TOD_SEC_MSB(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 4, 0, 1, 4) + +#define PTP_TOD_SEC_MSB_TOD_SEC_MSB GENMASK(15, 0) +#define PTP_TOD_SEC_MSB_TOD_SEC_MSB_SET(x)\ + FIELD_PREP(PTP_TOD_SEC_MSB_TOD_SEC_MSB, x) +#define PTP_TOD_SEC_MSB_TOD_SEC_MSB_GET(x)\ + FIELD_GET(PTP_TOD_SEC_MSB_TOD_SEC_MSB, x) + +/* PTP:PTP_PINS:PTP_TOD_SEC_LSB */ +#define PTP_TOD_SEC_LSB(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 8, 0, 1, 4) + +/* PTP:PTP_PINS:PTP_TOD_NSEC */ +#define PTP_TOD_NSEC(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 12, 0, 1, 4) + +#define PTP_TOD_NSEC_TOD_NSEC GENMASK(29, 0) +#define PTP_TOD_NSEC_TOD_NSEC_SET(x)\ + FIELD_PREP(PTP_TOD_NSEC_TOD_NSEC, x) +#define PTP_TOD_NSEC_TOD_NSEC_GET(x)\ + FIELD_GET(PTP_TOD_NSEC_TOD_NSEC, x) + +/* PTP:PTP_TS_FIFO:PTP_TWOSTEP_CTRL */ +#define PTP_TWOSTEP_CTRL __REG(TARGET_PTP, 0, 1, 612, 0, 1, 12, 0, 0, 1, 4) + +#define PTP_TWOSTEP_CTRL_NXT BIT(11) +#define PTP_TWOSTEP_CTRL_NXT_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_NXT, x) +#define PTP_TWOSTEP_CTRL_NXT_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_NXT, x) + +#define PTP_TWOSTEP_CTRL_VLD BIT(10) +#define PTP_TWOSTEP_CTRL_VLD_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_VLD, x) +#define PTP_TWOSTEP_CTRL_VLD_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_VLD, x) + +#define PTP_TWOSTEP_CTRL_STAMP_TX BIT(9) +#define PTP_TWOSTEP_CTRL_STAMP_TX_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_TX, x) +#define PTP_TWOSTEP_CTRL_STAMP_TX_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_TX, x) + +#define PTP_TWOSTEP_CTRL_STAMP_PORT GENMASK(8, 1) +#define PTP_TWOSTEP_CTRL_STAMP_PORT_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_PORT, x) +#define PTP_TWOSTEP_CTRL_STAMP_PORT_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_PORT, x) + +#define PTP_TWOSTEP_CTRL_OVFL BIT(0) +#define PTP_TWOSTEP_CTRL_OVFL_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_OVFL, x) +#define PTP_TWOSTEP_CTRL_OVFL_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_OVFL, x) + +/* PTP:PTP_TS_FIFO:PTP_TWOSTEP_STAMP */ +#define PTP_TWOSTEP_STAMP __REG(TARGET_PTP, 0, 1, 612, 0, 1, 12, 4, 0, 1, 4) + +#define PTP_TWOSTEP_STAMP_STAMP_NSEC GENMASK(31, 2) +#define PTP_TWOSTEP_STAMP_STAMP_NSEC_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_STAMP_STAMP_NSEC, x) +#define PTP_TWOSTEP_STAMP_STAMP_NSEC_GET(x)\ + FIELD_GET(PTP_TWOSTEP_STAMP_STAMP_NSEC, x) + /* DEVCPU_QS:XTR:XTR_GRP_CFG */ #define QS_XTR_GRP_CFG(r) __REG(TARGET_QS, 0, 1, 0, 0, 1, 36, 0, r, 2, 4) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c index 7de55f6a4da8..85099a51d4c7 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c @@ -9,6 +9,37 @@ static struct notifier_block lan966x_netdevice_nb __read_mostly; static struct notifier_block lan966x_switchdev_nb __read_mostly; static struct notifier_block lan966x_switchdev_blocking_nb __read_mostly; +static void lan966x_port_set_mcast_ip_flood(struct lan966x_port *port, + u32 pgid_ip) +{ + struct lan966x *lan966x = port->lan966x; + u32 flood_mask_ip; + + flood_mask_ip = lan_rd(lan966x, ANA_PGID(pgid_ip)); + flood_mask_ip = ANA_PGID_PGID_GET(flood_mask_ip); + + /* If mcast snooping is not enabled then use mcast flood mask + * to decide to enable multicast flooding or not. + */ + if (!port->mcast_ena) { + u32 flood_mask; + + flood_mask = lan_rd(lan966x, ANA_PGID(PGID_MC)); + flood_mask = ANA_PGID_PGID_GET(flood_mask); + + if (flood_mask & BIT(port->chip_port)) + flood_mask_ip |= BIT(port->chip_port); + else + flood_mask_ip &= ~BIT(port->chip_port); + } else { + flood_mask_ip &= ~BIT(port->chip_port); + } + + lan_rmw(ANA_PGID_PGID_SET(flood_mask_ip), + ANA_PGID_PGID, + lan966x, ANA_PGID(pgid_ip)); +} + static void lan966x_port_set_mcast_flood(struct lan966x_port *port, bool enabled) { @@ -23,6 +54,11 @@ static void lan966x_port_set_mcast_flood(struct lan966x_port *port, lan_rmw(ANA_PGID_PGID_SET(val), ANA_PGID_PGID, port->lan966x, ANA_PGID(PGID_MC)); + + if (!port->mcast_ena) { + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV4); + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV6); + } } static void lan966x_port_set_ucast_flood(struct lan966x_port *port, @@ -144,6 +180,28 @@ static void lan966x_port_ageing_set(struct lan966x_port *port, lan966x_mac_set_ageing(port->lan966x, ageing_time); } +static void lan966x_port_mc_set(struct lan966x_port *port, bool mcast_ena) +{ + struct lan966x *lan966x = port->lan966x; + + port->mcast_ena = mcast_ena; + if (mcast_ena) + lan966x_mdb_restore_entries(lan966x); + else + lan966x_mdb_clear_entries(lan966x); + + lan_rmw(ANA_CPU_FWD_CFG_IGMP_REDIR_ENA_SET(mcast_ena) | + ANA_CPU_FWD_CFG_MLD_REDIR_ENA_SET(mcast_ena) | + ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA_SET(mcast_ena), + ANA_CPU_FWD_CFG_IGMP_REDIR_ENA | + ANA_CPU_FWD_CFG_MLD_REDIR_ENA | + ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA, + lan966x, ANA_CPU_FWD_CFG(port->chip_port)); + + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV4); + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV6); +} + static int lan966x_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) @@ -171,6 +229,9 @@ static int lan966x_port_attr_set(struct net_device *dev, const void *ctx, lan966x_vlan_port_set_vlan_aware(port, attr->u.vlan_filtering); lan966x_vlan_port_apply(port); break; + case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED: + lan966x_port_mc_set(port, !attr->u.mc_disabled); + break; default: err = -EOPNOTSUPP; break; @@ -402,18 +463,6 @@ static int lan966x_handle_port_vlan_add(struct lan966x_port *port, const struct switchdev_obj_port_vlan *v = SWITCHDEV_OBJ_PORT_VLAN(obj); struct lan966x *lan966x = port->lan966x; - /* When adding a port to a vlan, we get a callback for the port but - * also for the bridge. When get the callback for the bridge just bail - * out. Then when the bridge is added to the vlan, then we get a - * callback here but in this case the flags has set: - * BRIDGE_VLAN_INFO_BRENTRY. In this case it means that the CPU - * port is added to the vlan, so the broadcast frames and unicast frames - * with dmac of the bridge should be foward to CPU. - */ - if (netif_is_bridge_master(obj->orig_dev) && - !(v->flags & BRIDGE_VLAN_INFO_BRENTRY)) - return 0; - if (!netif_is_bridge_master(obj->orig_dev)) lan966x_vlan_port_add_vlan(port, v->vid, v->flags & BRIDGE_VLAN_INFO_PVID, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 16266275dd36..394de85d360d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -291,7 +291,6 @@ static int sparx5_create_port(struct sparx5 *sparx5, /* Create a phylink for PHY management. Also handles SFPs */ spx5_port->phylink_config.dev = &spx5_port->ndev->dev; spx5_port->phylink_config.type = PHYLINK_NETDEV; - spx5_port->phylink_config.pcs_poll = true; spx5_port->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD | MAC_5000FD | MAC_10000FD | MAC_25000FD; @@ -328,7 +327,6 @@ static int sparx5_create_port(struct sparx5 *sparx5, return PTR_ERR(phylink); spx5_port->phylink = phylink; - phylink_set_pcs(phylink, &spx5_port->phylink_pcs); return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c index 8ba33bc1a001..830da0e5ff27 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -26,6 +26,15 @@ static bool port_conf_has_changed(struct sparx5_port_config *a, struct sparx5_po return false; } +static struct phylink_pcs * +sparx5_phylink_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct sparx5_port *port = netdev_priv(to_net_dev(config->dev)); + + return &port->phylink_pcs; +} + static void sparx5_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -130,6 +139,7 @@ const struct phylink_pcs_ops sparx5_phylink_pcs_ops = { const struct phylink_mac_ops sparx5_phylink_mac_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = sparx5_phylink_mac_select_pcs, .mac_config = sparx5_phylink_mac_config, .mac_link_down = sparx5_phylink_mac_link_down, .mac_link_up = sparx5_phylink_mac_link_up, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c index 649ca609884a..f5271c3ec133 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c @@ -369,13 +369,11 @@ static int sparx5_handle_port_vlan_add(struct net_device *dev, struct sparx5_port *port = netdev_priv(dev); if (netif_is_bridge_master(dev)) { - if (v->flags & BRIDGE_VLAN_INFO_BRENTRY) { - struct sparx5 *sparx5 = - container_of(nb, struct sparx5, - switchdev_blocking_nb); + struct sparx5 *sparx5 = + container_of(nb, struct sparx5, + switchdev_blocking_nb); - sparx5_sync_bridge_dev_addr(dev, sparx5, v->vid, true); - } + sparx5_sync_bridge_dev_addr(dev, sparx5, v->vid, true); return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 636dfef24a6c..49b85ca578b0 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -663,7 +663,7 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, struct gdma_context *gc = gd->gdma_context; struct hw_channel_context *hwc; u32 length = gmi->length; - u32 req_msg_size; + size_t req_msg_size; int err; int i; @@ -674,7 +674,7 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, return -EINVAL; hwc = gc->hwc.driver_data; - req_msg_size = sizeof(*req) + num_page * sizeof(u64); + req_msg_size = struct_size(req, page_addr_list, num_page); if (req_msg_size > hwc->max_req_msg_size) return -EINVAL; diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h index 9a12607fb511..d36405af9432 100644 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ b/drivers/net/ethernet/microsoft/mana/mana.h @@ -48,7 +48,15 @@ enum TRI_STATE { #define MAX_PORTS_IN_MANA_DEV 256 -struct mana_stats { +struct mana_stats_rx { + u64 packets; + u64 bytes; + u64 xdp_drop; + u64 xdp_tx; + struct u64_stats_sync syncp; +}; + +struct mana_stats_tx { u64 packets; u64 bytes; struct u64_stats_sync syncp; @@ -76,7 +84,7 @@ struct mana_txq { atomic_t pending_sends; - struct mana_stats stats; + struct mana_stats_tx stats; }; /* skb data and frags dma mappings */ @@ -298,10 +306,11 @@ struct mana_rxq { u32 buf_index; - struct mana_stats stats; + struct mana_stats_rx stats; struct bpf_prog __rcu *bpf_prog; struct xdp_rxq_info xdp_rxq; + struct page *xdp_save_page; /* MUST BE THE LAST MEMBER: * Each receive buffer has an associated mana_recv_buf_oob. diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 498d0f999275..b7d3ba1b4d17 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -136,7 +136,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) bool ipv4 = false, ipv6 = false; struct mana_tx_package pkg = {}; struct netdev_queue *net_txq; - struct mana_stats *tx_stats; + struct mana_stats_tx *tx_stats; struct gdma_queue *gdma_sq; unsigned int csum_type; struct mana_txq *txq; @@ -299,7 +299,8 @@ static void mana_get_stats64(struct net_device *ndev, { struct mana_port_context *apc = netdev_priv(ndev); unsigned int num_queues = apc->num_queues; - struct mana_stats *stats; + struct mana_stats_rx *rx_stats; + struct mana_stats_tx *tx_stats; unsigned int start; u64 packets, bytes; int q; @@ -310,26 +311,26 @@ static void mana_get_stats64(struct net_device *ndev, netdev_stats_to_stats64(st, &ndev->stats); for (q = 0; q < num_queues; q++) { - stats = &apc->rxqs[q]->stats; + rx_stats = &apc->rxqs[q]->stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; + } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); st->rx_packets += packets; st->rx_bytes += bytes; } for (q = 0; q < num_queues; q++) { - stats = &apc->tx_qp[q].txq.stats; + tx_stats = &apc->tx_qp[q].txq.stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; + } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); st->tx_packets += packets; st->tx_bytes += bytes; @@ -986,7 +987,7 @@ static struct sk_buff *mana_build_skb(void *buf_va, uint pkt_len, static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq) { - struct mana_stats *rx_stats = &rxq->stats; + struct mana_stats_rx *rx_stats = &rxq->stats; struct net_device *ndev = rxq->ndev; uint pkt_len = cqe->ppi[0].pkt_len; u16 rxq_idx = rxq->rxq_idx; @@ -1007,7 +1008,7 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, act = mana_run_xdp(ndev, rxq, &xdp, buf_va, pkt_len); if (act != XDP_PASS && act != XDP_TX) - goto drop; + goto drop_xdp; skb = mana_build_skb(buf_va, pkt_len, &xdp); @@ -1034,6 +1035,14 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, skb_set_hash(skb, hash_value, PKT_HASH_TYPE_L3); } + u64_stats_update_begin(&rx_stats->syncp); + rx_stats->packets++; + rx_stats->bytes += pkt_len; + + if (act == XDP_TX) + rx_stats->xdp_tx++; + u64_stats_update_end(&rx_stats->syncp); + if (act == XDP_TX) { skb_set_queue_mapping(skb, rxq_idx); mana_xdp_tx(skb, ndev); @@ -1042,15 +1051,19 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, napi_gro_receive(napi, skb); + return; + +drop_xdp: u64_stats_update_begin(&rx_stats->syncp); - rx_stats->packets++; - rx_stats->bytes += pkt_len; + rx_stats->xdp_drop++; u64_stats_update_end(&rx_stats->syncp); - return; drop: - free_page((unsigned long)buf_va); + WARN_ON_ONCE(rxq->xdp_save_page); + rxq->xdp_save_page = virt_to_page(buf_va); + ++ndev->stats.rx_dropped; + return; } @@ -1072,8 +1085,10 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, break; case CQE_RX_TRUNCATED: - netdev_err(ndev, "Dropped a truncated packet\n"); - return; + ++ndev->stats.rx_dropped; + rxbuf_oob = &rxq->rx_oobs[rxq->buf_index]; + netdev_warn_once(ndev, "Dropped a truncated packet\n"); + goto drop; case CQE_RX_COALESCED_4: netdev_err(ndev, "RX coalescing is unsupported\n"); @@ -1089,9 +1104,6 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, return; } - if (oob->cqe_hdr.cqe_type != CQE_RX_OKAY) - return; - pktlen = oob->ppi[0].pkt_len; if (pktlen == 0) { @@ -1105,7 +1117,13 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, rxbuf_oob = &rxq->rx_oobs[curr]; WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1); - new_page = alloc_page(GFP_ATOMIC); + /* Reuse XDP dropped page if available */ + if (rxq->xdp_save_page) { + new_page = rxq->xdp_save_page; + rxq->xdp_save_page = NULL; + } else { + new_page = alloc_page(GFP_ATOMIC); + } if (new_page) { da = dma_map_page(dev, new_page, XDP_PACKET_HEADROOM, rxq->datasize, @@ -1135,6 +1153,7 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, mana_rx_skb(old_buf, oob, rxq); +drop: mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu); mana_post_pkt_rxq(rxq); @@ -1392,6 +1411,9 @@ static void mana_destroy_rxq(struct mana_port_context *apc, mana_deinit_cq(apc, &rxq->rx_cq); + if (rxq->xdp_save_page) + __free_page(rxq->xdp_save_page); + for (i = 0; i < rxq->num_rx_buf; i++) { rx_oob = &rxq->rx_oobs[i]; diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index c3c81ae3fafd..e13f2453eabb 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -23,7 +23,7 @@ static int mana_get_sset_count(struct net_device *ndev, int stringset) if (stringset != ETH_SS_STATS) return -EINVAL; - return ARRAY_SIZE(mana_eth_stats) + num_queues * 4; + return ARRAY_SIZE(mana_eth_stats) + num_queues * 6; } static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) @@ -46,6 +46,10 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) p += ETH_GSTRING_LEN; sprintf(p, "rx_%d_bytes", i); p += ETH_GSTRING_LEN; + sprintf(p, "rx_%d_xdp_drop", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_%d_xdp_tx", i); + p += ETH_GSTRING_LEN; } for (i = 0; i < num_queues; i++) { @@ -62,9 +66,12 @@ static void mana_get_ethtool_stats(struct net_device *ndev, struct mana_port_context *apc = netdev_priv(ndev); unsigned int num_queues = apc->num_queues; void *eth_stats = &apc->eth_stats; - struct mana_stats *stats; + struct mana_stats_rx *rx_stats; + struct mana_stats_tx *tx_stats; unsigned int start; u64 packets, bytes; + u64 xdp_drop; + u64 xdp_tx; int q, i = 0; if (!apc->port_is_up) @@ -74,26 +81,30 @@ static void mana_get_ethtool_stats(struct net_device *ndev, data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); for (q = 0; q < num_queues; q++) { - stats = &apc->rxqs[q]->stats; + rx_stats = &apc->rxqs[q]->stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; + xdp_drop = rx_stats->xdp_drop; + xdp_tx = rx_stats->xdp_tx; + } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; + data[i++] = xdp_drop; + data[i++] = xdp_tx; } for (q = 0; q < num_queues; q++) { - stats = &apc->tx_qp[q].txq.stats; + tx_stats = &apc->tx_qp[q].txq.stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; + } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 15179b9529e1..afb7dcadb8d2 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -510,14 +510,14 @@ static int moxart_mac_probe(struct platform_device *pdev) } priv->tx_buf_base = kmalloc_array(priv->tx_buf_size, TX_DESC_NUM, - GFP_ATOMIC); + GFP_KERNEL); if (!priv->tx_buf_base) { ret = -ENOMEM; goto init_fail; } priv->rx_buf_base = kmalloc_array(priv->rx_buf_size, RX_DESC_NUM, - GFP_ATOMIC); + GFP_KERNEL); if (!priv->rx_buf_base) { ret = -ENOMEM; goto init_fail; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index fd3ceb74620d..2fb713e9baa4 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1472,9 +1472,9 @@ ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) trap->key.ipv6.dport.mask = 0xffff; } -static int ocelot_trap_add(struct ocelot *ocelot, int port, - unsigned long cookie, - void (*populate)(struct ocelot_vcap_filter *f)) +int ocelot_trap_add(struct ocelot *ocelot, int port, + unsigned long cookie, bool take_ts, + void (*populate)(struct ocelot_vcap_filter *f)) { struct ocelot_vcap_block *block_vcap_is2; struct ocelot_vcap_filter *trap; @@ -1500,6 +1500,8 @@ static int ocelot_trap_add(struct ocelot *ocelot, int port, trap->action.cpu_copy_ena = true; trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; trap->action.port_mask = 0; + trap->take_ts = take_ts; + list_add_tail(&trap->trap_list, &ocelot->traps); new = true; } @@ -1511,16 +1513,17 @@ static int ocelot_trap_add(struct ocelot *ocelot, int port, err = ocelot_vcap_filter_replace(ocelot, trap); if (err) { trap->ingress_port_mask &= ~BIT(port); - if (!trap->ingress_port_mask) + if (!trap->ingress_port_mask) { + list_del(&trap->trap_list); kfree(trap); + } return err; } return 0; } -static int ocelot_trap_del(struct ocelot *ocelot, int port, - unsigned long cookie) +int ocelot_trap_del(struct ocelot *ocelot, int port, unsigned long cookie) { struct ocelot_vcap_block *block_vcap_is2; struct ocelot_vcap_filter *trap; @@ -1533,39 +1536,42 @@ static int ocelot_trap_del(struct ocelot *ocelot, int port, return 0; trap->ingress_port_mask &= ~BIT(port); - if (!trap->ingress_port_mask) + if (!trap->ingress_port_mask) { + list_del(&trap->trap_list); + return ocelot_vcap_filter_del(ocelot, trap); + } return ocelot_vcap_filter_replace(ocelot, trap); } static int ocelot_l2_ptp_trap_add(struct ocelot *ocelot, int port) { - unsigned long l2_cookie = ocelot->num_phys_ports + 1; + unsigned long l2_cookie = OCELOT_VCAP_IS2_L2_PTP_TRAP(ocelot); - return ocelot_trap_add(ocelot, port, l2_cookie, + return ocelot_trap_add(ocelot, port, l2_cookie, true, ocelot_populate_l2_ptp_trap_key); } static int ocelot_l2_ptp_trap_del(struct ocelot *ocelot, int port) { - unsigned long l2_cookie = ocelot->num_phys_ports + 1; + unsigned long l2_cookie = OCELOT_VCAP_IS2_L2_PTP_TRAP(ocelot); return ocelot_trap_del(ocelot, port, l2_cookie); } static int ocelot_ipv4_ptp_trap_add(struct ocelot *ocelot, int port) { - unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; - unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + unsigned long ipv4_gen_cookie = OCELOT_VCAP_IS2_IPV4_GEN_PTP_TRAP(ocelot); + unsigned long ipv4_ev_cookie = OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot); int err; - err = ocelot_trap_add(ocelot, port, ipv4_ev_cookie, + err = ocelot_trap_add(ocelot, port, ipv4_ev_cookie, true, ocelot_populate_ipv4_ptp_event_trap_key); if (err) return err; - err = ocelot_trap_add(ocelot, port, ipv4_gen_cookie, + err = ocelot_trap_add(ocelot, port, ipv4_gen_cookie, false, ocelot_populate_ipv4_ptp_general_trap_key); if (err) ocelot_trap_del(ocelot, port, ipv4_ev_cookie); @@ -1575,8 +1581,8 @@ static int ocelot_ipv4_ptp_trap_add(struct ocelot *ocelot, int port) static int ocelot_ipv4_ptp_trap_del(struct ocelot *ocelot, int port) { - unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; - unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + unsigned long ipv4_gen_cookie = OCELOT_VCAP_IS2_IPV4_GEN_PTP_TRAP(ocelot); + unsigned long ipv4_ev_cookie = OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot); int err; err = ocelot_trap_del(ocelot, port, ipv4_ev_cookie); @@ -1586,16 +1592,16 @@ static int ocelot_ipv4_ptp_trap_del(struct ocelot *ocelot, int port) static int ocelot_ipv6_ptp_trap_add(struct ocelot *ocelot, int port) { - unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; - unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + unsigned long ipv6_gen_cookie = OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot); + unsigned long ipv6_ev_cookie = OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot); int err; - err = ocelot_trap_add(ocelot, port, ipv6_ev_cookie, + err = ocelot_trap_add(ocelot, port, ipv6_ev_cookie, true, ocelot_populate_ipv6_ptp_event_trap_key); if (err) return err; - err = ocelot_trap_add(ocelot, port, ipv6_gen_cookie, + err = ocelot_trap_add(ocelot, port, ipv6_gen_cookie, false, ocelot_populate_ipv6_ptp_general_trap_key); if (err) ocelot_trap_del(ocelot, port, ipv6_ev_cookie); @@ -1605,8 +1611,8 @@ static int ocelot_ipv6_ptp_trap_add(struct ocelot *ocelot, int port) static int ocelot_ipv6_ptp_trap_del(struct ocelot *ocelot, int port) { - unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; - unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + unsigned long ipv6_gen_cookie = OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot); + unsigned long ipv6_ev_cookie = OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot); int err; err = ocelot_trap_del(ocelot, port, ipv6_ev_cookie); @@ -1750,28 +1756,36 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data) EXPORT_SYMBOL(ocelot_get_strings); /* Caller must hold &ocelot->stats_lock */ -static void ocelot_update_stats(struct ocelot *ocelot) +static int ocelot_port_update_stats(struct ocelot *ocelot, int port) { - int i, j; + unsigned int idx = port * ocelot->num_stats; + struct ocelot_stats_region *region; + int err, j; - for (i = 0; i < ocelot->num_phys_ports; i++) { - /* Configure the port to read the stats from */ - ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG); + /* Configure the port to read the stats from */ + ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(port), SYS_STAT_CFG); - for (j = 0; j < ocelot->num_stats; j++) { - u32 val; - unsigned int idx = i * ocelot->num_stats + j; + list_for_each_entry(region, &ocelot->stats_regions, node) { + err = ocelot_bulk_read_rix(ocelot, SYS_COUNT_RX_OCTETS, + region->offset, region->buf, + region->count); + if (err) + return err; - val = ocelot_read_rix(ocelot, SYS_COUNT_RX_OCTETS, - ocelot->stats_layout[j].offset); + for (j = 0; j < region->count; j++) { + u64 *stat = &ocelot->stats[idx + j]; + u64 val = region->buf[j]; - if (val < (ocelot->stats[idx] & U32_MAX)) - ocelot->stats[idx] += (u64)1 << 32; + if (val < (*stat & U32_MAX)) + *stat += (u64)1 << 32; - ocelot->stats[idx] = (ocelot->stats[idx] & - ~(u64)U32_MAX) + val; + *stat = (*stat & ~(u64)U32_MAX) + val; } + + idx += region->count; } + + return err; } static void ocelot_check_stats_work(struct work_struct *work) @@ -1779,29 +1793,40 @@ static void ocelot_check_stats_work(struct work_struct *work) struct delayed_work *del_work = to_delayed_work(work); struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work); + int i, err; mutex_lock(&ocelot->stats_lock); - ocelot_update_stats(ocelot); + for (i = 0; i < ocelot->num_phys_ports; i++) { + err = ocelot_port_update_stats(ocelot, i); + if (err) + break; + } mutex_unlock(&ocelot->stats_lock); + if (err) + dev_err(ocelot->dev, "Error %d updating ethtool stats\n", err); + queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); } void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data) { - int i; + int i, err; mutex_lock(&ocelot->stats_lock); /* check and update now */ - ocelot_update_stats(ocelot); + err = ocelot_port_update_stats(ocelot, port); /* Copy all counters */ for (i = 0; i < ocelot->num_stats; i++) *data++ = ocelot->stats[port * ocelot->num_stats + i]; mutex_unlock(&ocelot->stats_lock); + + if (err) + dev_err(ocelot->dev, "Error %d updating ethtool stats\n", err); } EXPORT_SYMBOL(ocelot_get_ethtool_stats); @@ -1814,6 +1839,41 @@ int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset) } EXPORT_SYMBOL(ocelot_get_sset_count); +static int ocelot_prepare_stats_regions(struct ocelot *ocelot) +{ + struct ocelot_stats_region *region = NULL; + unsigned int last; + int i; + + INIT_LIST_HEAD(&ocelot->stats_regions); + + for (i = 0; i < ocelot->num_stats; i++) { + if (region && ocelot->stats_layout[i].offset == last + 1) { + region->count++; + } else { + region = devm_kzalloc(ocelot->dev, sizeof(*region), + GFP_KERNEL); + if (!region) + return -ENOMEM; + + region->offset = ocelot->stats_layout[i].offset; + region->count = 1; + list_add_tail(®ion->node, &ocelot->stats_regions); + } + + last = ocelot->stats_layout[i].offset; + } + + list_for_each_entry(region, &ocelot->stats_regions, node) { + region->buf = devm_kcalloc(ocelot->dev, region->count, + sizeof(*region->buf), GFP_KERNEL); + if (!region->buf) + return -ENOMEM; + } + + return 0; +} + int ocelot_get_ts_info(struct ocelot *ocelot, int port, struct ethtool_ts_info *info) { @@ -2814,6 +2874,13 @@ int ocelot_init(struct ocelot *ocelot) ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6), ANA_CPUQ_8021_CFG, i); + ret = ocelot_prepare_stats_regions(ocelot); + if (ret) { + destroy_workqueue(ocelot->stats_queue); + destroy_workqueue(ocelot->owq); + return ret; + } + INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work); queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index bf4eff6d7086..5277c4b53af4 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -21,6 +21,7 @@ #include <soc/mscc/ocelot_dev.h> #include <soc/mscc/ocelot_ana.h> #include <soc/mscc/ocelot_ptp.h> +#include <soc/mscc/ocelot_vcap.h> #include <soc/mscc/ocelot.h> #include "ocelot_rew.h" #include "ocelot_qs.h" @@ -102,6 +103,11 @@ int ocelot_port_devlink_init(struct ocelot *ocelot, int port, enum devlink_port_flavour flavour); void ocelot_port_devlink_teardown(struct ocelot *ocelot, int port); +int ocelot_trap_add(struct ocelot *ocelot, int port, + unsigned long cookie, bool take_ts, + void (*populate)(struct ocelot_vcap_filter *f)); +int ocelot_trap_del(struct ocelot *ocelot, int port, unsigned long cookie); + extern struct notifier_block ocelot_netdevice_nb; extern struct notifier_block ocelot_switchdev_nb; extern struct notifier_block ocelot_switchdev_blocking_nb; diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 949858891973..7106137f98ee 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -279,6 +279,7 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, filter->action.cpu_copy_ena = true; filter->action.cpu_qu_num = 0; filter->type = OCELOT_VCAP_FILTER_OFFLOAD; + list_add_tail(&filter->trap_list, &ocelot->traps); break; case FLOW_ACTION_POLICE: if (filter->block_id == PSFP_BLOCK_ID) { @@ -840,6 +841,8 @@ int ocelot_cls_flower_replace(struct ocelot *ocelot, int port, ret = ocelot_flower_parse(ocelot, port, ingress, f, filter); if (ret) { + if (!list_empty(&filter->trap_list)) + list_del(&filter->trap_list); kfree(filter); return ret; } diff --git a/drivers/net/ethernet/mscc/ocelot_io.c b/drivers/net/ethernet/mscc/ocelot_io.c index 7390fa3980ec..2067382d0ee1 100644 --- a/drivers/net/ethernet/mscc/ocelot_io.c +++ b/drivers/net/ethernet/mscc/ocelot_io.c @@ -10,6 +10,19 @@ #include "ocelot.h" +int __ocelot_bulk_read_ix(struct ocelot *ocelot, u32 reg, u32 offset, void *buf, + int count) +{ + u16 target = reg >> TARGET_OFFSET; + + WARN_ON(!target); + + return regmap_bulk_read(ocelot->targets[target], + ocelot->map[target][reg & REG_MASK] + offset, + buf, count); +} +EXPORT_SYMBOL_GPL(__ocelot_bulk_read_ix); + u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset) { u16 target = reg >> TARGET_OFFSET; diff --git a/drivers/net/ethernet/mscc/ocelot_mrp.c b/drivers/net/ethernet/mscc/ocelot_mrp.c index 1fa58546abdc..142e897ea2af 100644 --- a/drivers/net/ethernet/mscc/ocelot_mrp.c +++ b/drivers/net/ethernet/mscc/ocelot_mrp.c @@ -60,7 +60,7 @@ static int ocelot_mrp_redirect_add_vcap(struct ocelot *ocelot, int src_port, filter->key_type = OCELOT_VCAP_KEY_ETYPE; filter->prio = 1; - filter->id.cookie = src_port; + filter->id.cookie = OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, src_port); filter->id.tc_offload = false; filter->block_id = VCAP_IS2; filter->type = OCELOT_VCAP_FILTER_OFFLOAD; @@ -77,39 +77,30 @@ static int ocelot_mrp_redirect_add_vcap(struct ocelot *ocelot, int src_port, return err; } -static int ocelot_mrp_copy_add_vcap(struct ocelot *ocelot, int port, - int prio, unsigned long cookie) +static void ocelot_populate_mrp_trap_key(struct ocelot_vcap_filter *filter) { const u8 mrp_mask[] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 }; - struct ocelot_vcap_filter *filter; - int err; - - filter = kzalloc(sizeof(*filter), GFP_KERNEL); - if (!filter) - return -ENOMEM; - filter->key_type = OCELOT_VCAP_KEY_ETYPE; - filter->prio = prio; - filter->id.cookie = cookie; - filter->id.tc_offload = false; - filter->block_id = VCAP_IS2; - filter->type = OCELOT_VCAP_FILTER_OFFLOAD; - filter->ingress_port_mask = BIT(port); /* Here is possible to use control or test dmac because the mask * doesn't cover the LSB */ ether_addr_copy(filter->key.etype.dmac.value, mrp_test_dmac); ether_addr_copy(filter->key.etype.dmac.mask, mrp_mask); - filter->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; - filter->action.port_mask = 0x0; - filter->action.cpu_copy_ena = true; - filter->action.cpu_qu_num = OCELOT_MRP_CPUQ; +} - err = ocelot_vcap_filter_add(ocelot, filter, NULL); - if (err) - kfree(filter); +static int ocelot_mrp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long cookie = OCELOT_VCAP_IS2_MRP_TRAP(ocelot); - return err; + return ocelot_trap_add(ocelot, port, cookie, false, + ocelot_populate_mrp_trap_key); +} + +static int ocelot_mrp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long cookie = OCELOT_VCAP_IS2_MRP_TRAP(ocelot); + + return ocelot_trap_del(ocelot, port, cookie); } static void ocelot_mrp_save_mac(struct ocelot *ocelot, @@ -186,7 +177,7 @@ int ocelot_mrp_add_ring_role(struct ocelot *ocelot, int port, ocelot_mrp_save_mac(ocelot, ocelot_port); if (mrp->ring_role != BR_MRP_RING_ROLE_MRC) - return ocelot_mrp_copy_add_vcap(ocelot, port, 1, port); + return ocelot_mrp_trap_add(ocelot, port); dst_port = ocelot_mrp_find_partner_port(ocelot, ocelot_port); if (dst_port == -1) @@ -196,10 +187,10 @@ int ocelot_mrp_add_ring_role(struct ocelot *ocelot, int port, if (err) return err; - err = ocelot_mrp_copy_add_vcap(ocelot, port, 2, - port + ocelot->num_phys_ports); + err = ocelot_mrp_trap_add(ocelot, port); if (err) { - ocelot_mrp_del_vcap(ocelot, port); + ocelot_mrp_del_vcap(ocelot, + OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port)); return err; } @@ -211,7 +202,7 @@ int ocelot_mrp_del_ring_role(struct ocelot *ocelot, int port, const struct switchdev_obj_ring_role_mrp *mrp) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - int i; + int err, i; if (!ocelot_port) return -EOPNOTSUPP; @@ -222,8 +213,11 @@ int ocelot_mrp_del_ring_role(struct ocelot *ocelot, int port, if (ocelot_port->mrp_ring_id != mrp->ring_id) return 0; - ocelot_mrp_del_vcap(ocelot, port); - ocelot_mrp_del_vcap(ocelot, port + ocelot->num_phys_ports); + err = ocelot_mrp_trap_del(ocelot, port); + if (err) + return err; + + ocelot_mrp_del_vcap(ocelot, OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port)); for (i = 0; i < ocelot->num_phys_ports; ++i) { ocelot_port = ocelot->ports[i]; diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index d3544413a8a4..852054da9db9 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -1401,6 +1401,7 @@ int ocelot_vcap_init(struct ocelot *ocelot) } INIT_LIST_HEAD(&ocelot->dummy_rules); + INIT_LIST_HEAD(&ocelot->traps); INIT_LIST_HEAD(&ocelot->vcap_pol.pol_list); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 0a326e04e692..cd50db779dda 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -356,7 +356,7 @@ __nfp_tun_add_route_to_cache(struct list_head *route_list, return 0; } - entry = kmalloc(sizeof(*entry) + add_len, GFP_ATOMIC); + entry = kmalloc(struct_size(entry, ip_add, add_len), GFP_ATOMIC); if (!entry) { spin_unlock_bh(list_lock); return -ENOMEM; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 3d61a8cb60b0..50007cc5b580 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -1,8 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* Copyright (C) 2015-2018 Netronome Systems, Inc. */ -/* - * nfp_net_ctrl.h +/* nfp_net_ctrl.h * Netronome network device driver: Control BAR layout * Authors: Jakub Kicinski <jakub.kicinski@netronome.com> * Jason McMullan <jason.mcmullan@netronome.com> @@ -15,30 +14,24 @@ #include <linux/types.h> -/** - * Configuration BAR size. +/* Configuration BAR size. * * The configuration BAR is 8K in size, but due to * THB-350, 32k needs to be reserved. */ #define NFP_NET_CFG_BAR_SZ (32 * 1024) -/** - * Offset in Freelist buffer where packet starts on RX - */ +/* Offset in Freelist buffer where packet starts on RX */ #define NFP_NET_RX_OFFSET 32 -/** - * LSO parameters +/* LSO parameters * %NFP_NET_LSO_MAX_HDR_SZ: Maximum header size supported for LSO frames * %NFP_NET_LSO_MAX_SEGS: Maximum number of segments LSO frame can produce */ #define NFP_NET_LSO_MAX_HDR_SZ 255 #define NFP_NET_LSO_MAX_SEGS 64 -/** - * Prepend field types - */ +/* Prepend field types */ #define NFP_NET_META_FIELD_SIZE 4 #define NFP_NET_META_HASH 1 /* next field carries hash type */ #define NFP_NET_META_MARK 2 @@ -49,9 +42,7 @@ #define NFP_META_PORT_ID_CTRL ~0U -/** - * Hash type pre-pended when a RSS hash was computed - */ +/* Hash type pre-pended when a RSS hash was computed */ #define NFP_NET_RSS_NONE 0 #define NFP_NET_RSS_IPV4 1 #define NFP_NET_RSS_IPV6 2 @@ -63,16 +54,14 @@ #define NFP_NET_RSS_IPV6_UDP 8 #define NFP_NET_RSS_IPV6_EX_UDP 9 -/** - * Ring counts +/* Ring counts * %NFP_NET_TXR_MAX: Maximum number of TX rings * %NFP_NET_RXR_MAX: Maximum number of RX rings */ #define NFP_NET_TXR_MAX 64 #define NFP_NET_RXR_MAX 64 -/** - * Read/Write config words (0x0000 - 0x002c) +/* Read/Write config words (0x0000 - 0x002c) * %NFP_NET_CFG_CTRL: Global control * %NFP_NET_CFG_UPDATE: Indicate which fields are updated * %NFP_NET_CFG_TXRS_ENABLE: Bitmask of enabled TX rings @@ -147,8 +136,7 @@ #define NFP_NET_CFG_LSC 0x0020 #define NFP_NET_CFG_MACADDR 0x0024 -/** - * Read-only words (0x0030 - 0x0050): +/* Read-only words (0x0030 - 0x0050): * %NFP_NET_CFG_VERSION: Firmware version number * %NFP_NET_CFG_STS: Status * %NFP_NET_CFG_CAP: Capabilities (same bits as %NFP_NET_CFG_CTRL) @@ -193,36 +181,31 @@ #define NFP_NET_CFG_START_TXQ 0x0048 #define NFP_NET_CFG_START_RXQ 0x004c -/** - * Prepend configuration +/* Prepend configuration */ #define NFP_NET_CFG_RX_OFFSET 0x0050 #define NFP_NET_CFG_RX_OFFSET_DYNAMIC 0 /* Prepend mode */ -/** - * RSS capabilities +/* RSS capabilities * %NFP_NET_CFG_RSS_CAP_HFUNC: supported hash functions (same bits as * %NFP_NET_CFG_RSS_HFUNC) */ #define NFP_NET_CFG_RSS_CAP 0x0054 #define NFP_NET_CFG_RSS_CAP_HFUNC 0xff000000 -/** - * TLV area start +/* TLV area start * %NFP_NET_CFG_TLV_BASE: start anchor of the TLV area */ #define NFP_NET_CFG_TLV_BASE 0x0058 -/** - * VXLAN/UDP encap configuration +/* VXLAN/UDP encap configuration * %NFP_NET_CFG_VXLAN_PORT: Base address of table of tunnels' UDP dst ports * %NFP_NET_CFG_VXLAN_SZ: Size of the UDP port table in bytes */ #define NFP_NET_CFG_VXLAN_PORT 0x0060 #define NFP_NET_CFG_VXLAN_SZ 0x0008 -/** - * BPF section +/* BPF section * %NFP_NET_CFG_BPF_ABI: BPF ABI version * %NFP_NET_CFG_BPF_CAP: BPF capabilities * %NFP_NET_CFG_BPF_MAX_LEN: Maximum size of JITed BPF code in bytes @@ -247,14 +230,12 @@ #define NFP_NET_CFG_BPF_CFG_MASK 7ULL #define NFP_NET_CFG_BPF_ADDR_MASK (~NFP_NET_CFG_BPF_CFG_MASK) -/** - * 40B reserved for future use (0x0098 - 0x00c0) +/* 40B reserved for future use (0x0098 - 0x00c0) */ #define NFP_NET_CFG_RESERVED 0x0098 #define NFP_NET_CFG_RESERVED_SZ 0x0028 -/** - * RSS configuration (0x0100 - 0x01ac): +/* RSS configuration (0x0100 - 0x01ac): * Used only when NFP_NET_CFG_CTRL_RSS is enabled * %NFP_NET_CFG_RSS_CFG: RSS configuration word * %NFP_NET_CFG_RSS_KEY: RSS "secret" key @@ -281,8 +262,7 @@ NFP_NET_CFG_RSS_KEY_SZ) #define NFP_NET_CFG_RSS_ITBL_SZ 0x80 -/** - * TX ring configuration (0x200 - 0x800) +/* TX ring configuration (0x200 - 0x800) * %NFP_NET_CFG_TXR_BASE: Base offset for TX ring configuration * %NFP_NET_CFG_TXR_ADDR: Per TX ring DMA address (8B entries) * %NFP_NET_CFG_TXR_WB_ADDR: Per TX ring write back DMA address (8B entries) @@ -301,8 +281,7 @@ #define NFP_NET_CFG_TXR_IRQ_MOD(_x) (NFP_NET_CFG_TXR_BASE + 0x500 + \ ((_x) * 0x4)) -/** - * RX ring configuration (0x0800 - 0x0c00) +/* RX ring configuration (0x0800 - 0x0c00) * %NFP_NET_CFG_RXR_BASE: Base offset for RX ring configuration * %NFP_NET_CFG_RXR_ADDR: Per RX ring DMA address (8B entries) * %NFP_NET_CFG_RXR_SZ: Per RX ring ring size (1B entries) @@ -318,8 +297,7 @@ #define NFP_NET_CFG_RXR_IRQ_MOD(_x) (NFP_NET_CFG_RXR_BASE + 0x300 + \ ((_x) * 0x4)) -/** - * Interrupt Control/Cause registers (0x0c00 - 0x0d00) +/* Interrupt Control/Cause registers (0x0c00 - 0x0d00) * These registers are only used when MSI-X auto-masking is not * enabled (%NFP_NET_CFG_CTRL_MSIXAUTO not set). The array is index * by MSI-X entry and are 1B in size. If an entry is zero, the @@ -334,8 +312,7 @@ #define NFP_NET_CFG_ICR_RXTX 0x1 #define NFP_NET_CFG_ICR_LSC 0x2 -/** - * General device stats (0x0d00 - 0x0d90) +/* General device stats (0x0d00 - 0x0d90) * all counters are 64bit. */ #define NFP_NET_CFG_STATS_BASE 0x0d00 @@ -368,8 +345,7 @@ #define NFP_NET_CFG_STATS_APP3_FRAMES (NFP_NET_CFG_STATS_BASE + 0xc0) #define NFP_NET_CFG_STATS_APP3_BYTES (NFP_NET_CFG_STATS_BASE + 0xc8) -/** - * Per ring stats (0x1000 - 0x1800) +/* Per ring stats (0x1000 - 0x1800) * options, 64bit per entry * %NFP_NET_CFG_TXR_STATS: TX ring statistics (Packet and Byte count) * %NFP_NET_CFG_RXR_STATS: RX ring statistics (Packet and Byte count) @@ -381,8 +357,7 @@ #define NFP_NET_CFG_RXR_STATS(_x) (NFP_NET_CFG_RXR_STATS_BASE + \ ((_x) * 0x10)) -/** - * General use mailbox area (0x1800 - 0x19ff) +/* General use mailbox area (0x1800 - 0x19ff) * 4B used for update command and 4B return code * followed by a max of 504B of variable length value */ @@ -399,8 +374,7 @@ #define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET 5 #define NFP_NET_CFG_MBOX_CMD_TLV_CMSG 6 -/** - * VLAN filtering using general use mailbox +/* VLAN filtering using general use mailbox * %NFP_NET_CFG_VLAN_FILTER: Base address of VLAN filter mailbox * %NFP_NET_CFG_VLAN_FILTER_VID: VLAN ID to filter * %NFP_NET_CFG_VLAN_FILTER_PROTO: VLAN proto to filter @@ -411,8 +385,7 @@ #define NFP_NET_CFG_VLAN_FILTER_PROTO (NFP_NET_CFG_VLAN_FILTER + 2) #define NFP_NET_CFG_VLAN_FILTER_SZ 0x0004 -/** - * TLV capabilities +/* TLV capabilities * %NFP_NET_CFG_TLV_TYPE: Offset of type within the TLV * %NFP_NET_CFG_TLV_TYPE_REQUIRED: Driver must be able to parse the TLV * %NFP_NET_CFG_TLV_LENGTH: Offset of length within the TLV @@ -438,8 +411,7 @@ #define NFP_NET_CFG_TLV_HEADER_TYPE 0x7fff0000 #define NFP_NET_CFG_TLV_HEADER_LENGTH 0x0000ffff -/** - * Capability TLV types +/* Capability TLV types * * %NFP_NET_CFG_TLV_TYPE_UNKNOWN: * Special TLV type to catch bugs, should never be encountered. Drivers should @@ -512,8 +484,7 @@ struct device; -/** - * struct nfp_net_tlv_caps - parsed control BAR TLV capabilities +/* struct nfp_net_tlv_caps - parsed control BAR TLV capabilities * @me_freq_mhz: ME clock_freq (MHz) * @mbox_off: vNIC mailbox area offset * @mbox_len: vNIC mailbox area length diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h index a3db0cbf6425..786be58a907e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h @@ -4,8 +4,7 @@ #ifndef _NFP_NET_SRIOV_H_ #define _NFP_NET_SRIOV_H_ -/** - * SRIOV VF configuration. +/* SRIOV VF configuration. * The configuration memory begins with a mailbox region for communication with * the firmware followed by individual VF entries. */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index ae4da189d955..df316b9e891d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -132,8 +132,7 @@ void nfp_devlink_port_unregister(struct nfp_port *port); void nfp_devlink_port_type_eth_set(struct nfp_port *port); void nfp_devlink_port_type_clear(struct nfp_port *port); -/** - * Mac stats (0x0000 - 0x0200) +/* Mac stats (0x0000 - 0x0200) * all counters are 64bit. */ #define NFP_MAC_STATS_BASE 0x0000 diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index 10e7d8b21c46..730fea214b8a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -513,7 +513,7 @@ nfp_nsp_command_buf_dma_sg(struct nfp_nsp *nsp, dma_size = BIT_ULL(dma_order); nseg = DIV_ROUND_UP(max_size, chunk_size); - chunks = kzalloc(array_size(sizeof(*chunks), nseg), GFP_KERNEL); + chunks = kcalloc(nseg, sizeof(*chunks), GFP_KERNEL); if (!chunks) return -ENOMEM; diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index 5e25411ff02f..602f4d45d529 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -18,7 +18,7 @@ struct ionic_lif; #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002 #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 -#define DEVCMD_TIMEOUT 10 +#define DEVCMD_TIMEOUT 5 #define IONIC_ADMINQ_TIME_SLICE msecs_to_jiffies(100) #define IONIC_PHC_UPDATE_NS 10000000000 /* 10s in nanoseconds */ @@ -78,6 +78,9 @@ void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, u8 status, int err); int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); +int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_wait); +void ionic_dev_cmd_dev_err_print(struct ionic *ionic, u8 opcode, u8 status, + int err); int ionic_set_dma_mask(struct ionic *ionic); int ionic_setup(struct ionic *ionic); @@ -89,4 +92,6 @@ int ionic_port_identify(struct ionic *ionic); int ionic_port_init(struct ionic *ionic); int ionic_port_reset(struct ionic *ionic); +const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr); + #endif /* _IONIC_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index 7e296fa71b36..6ffc62c41165 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -109,8 +109,8 @@ void ionic_bus_unmap_dbpage(struct ionic *ionic, void __iomem *page) static void ionic_vf_dealloc_locked(struct ionic *ionic) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_STATSADDR }; struct ionic_vf *v; - dma_addr_t dma = 0; int i; if (!ionic->vfs) @@ -120,9 +120,8 @@ static void ionic_vf_dealloc_locked(struct ionic *ionic) v = &ionic->vfs[i]; if (v->stats_pa) { - (void)ionic_set_vf_config(ionic, i, - IONIC_VF_ATTR_STATSADDR, - (u8 *)&dma); + vfc.stats_pa = 0; + (void)ionic_set_vf_config(ionic, i, &vfc); dma_unmap_single(ionic->dev, v->stats_pa, sizeof(v->stats), DMA_FROM_DEVICE); v->stats_pa = 0; @@ -143,6 +142,7 @@ static void ionic_vf_dealloc(struct ionic *ionic) static int ionic_vf_alloc(struct ionic *ionic, int num_vfs) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_STATSADDR }; struct ionic_vf *v; int err = 0; int i; @@ -166,9 +166,10 @@ static int ionic_vf_alloc(struct ionic *ionic, int num_vfs) } ionic->num_vfs++; + /* ignore failures from older FW, we just won't get stats */ - (void)ionic_set_vf_config(ionic, i, IONIC_VF_ATTR_STATSADDR, - (u8 *)&v->stats_pa); + vfc.stats_pa = cpu_to_le64(v->stats_pa); + (void)ionic_set_vf_config(ionic, i, &vfc); } out: @@ -331,6 +332,9 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_deregister_lifs; } + mod_timer(&ionic->watchdog_timer, + round_jiffies(jiffies + ionic->watchdog_period)); + return 0; err_out_deregister_lifs: @@ -348,7 +352,6 @@ err_out_port_reset: err_out_reset: ionic_reset(ionic); err_out_teardown: - del_timer_sync(&ionic->watchdog_timer); pci_clear_master(pdev); /* Don't fail the probe for these errors, keep * the hw interface around for inspection diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index d57e80d44c9d..52a1b5cfd8e7 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -33,7 +33,8 @@ static void ionic_watchdog_cb(struct timer_list *t) !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) ionic_link_status_check_request(lif, CAN_NOT_SLEEP); - if (test_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state)) { + if (test_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state) && + !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) { netdev_err(lif->netdev, "rxmode change dropped\n"); @@ -46,6 +47,24 @@ static void ionic_watchdog_cb(struct timer_list *t) } } +static void ionic_watchdog_init(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + + timer_setup(&ionic->watchdog_timer, ionic_watchdog_cb, 0); + ionic->watchdog_period = IONIC_WATCHDOG_SECS * HZ; + + /* set times to ensure the first check will proceed */ + atomic_long_set(&idev->last_check_time, jiffies - 2 * HZ); + idev->last_hb_time = jiffies - 2 * ionic->watchdog_period; + /* init as ready, so no transition if the first check succeeds */ + idev->last_fw_hb = 0; + idev->fw_hb_ready = true; + idev->fw_status_ready = true; + idev->fw_generation = IONIC_FW_STS_F_GENERATION & + ioread8(&idev->dev_info_regs->fw_status); +} + void ionic_init_devinfo(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; @@ -109,21 +128,7 @@ int ionic_dev_setup(struct ionic *ionic) return -EFAULT; } - timer_setup(&ionic->watchdog_timer, ionic_watchdog_cb, 0); - ionic->watchdog_period = IONIC_WATCHDOG_SECS * HZ; - - /* set times to ensure the first check will proceed */ - atomic_long_set(&idev->last_check_time, jiffies - 2 * HZ); - idev->last_hb_time = jiffies - 2 * ionic->watchdog_period; - /* init as ready, so no transition if the first check succeeds */ - idev->last_fw_hb = 0; - idev->fw_hb_ready = true; - idev->fw_status_ready = true; - idev->fw_generation = IONIC_FW_STS_F_GENERATION & - ioread8(&idev->dev_info_regs->fw_status); - - mod_timer(&ionic->watchdog_timer, - round_jiffies(jiffies + ionic->watchdog_period)); + ionic_watchdog_init(ionic); idev->db_pages = bar->vaddr; idev->phy_db_pages = bar->bus_addr; @@ -132,10 +137,21 @@ int ionic_dev_setup(struct ionic *ionic) } /* Devcmd Interface */ +bool ionic_is_fw_running(struct ionic_dev *idev) +{ + u8 fw_status = ioread8(&idev->dev_info_regs->fw_status); + + /* firmware is useful only if the running bit is set and + * fw_status != 0xff (bad PCI read) + */ + return (fw_status != 0xff) && (fw_status & IONIC_FW_STS_F_RUNNING); +} + int ionic_heartbeat_check(struct ionic *ionic) { - struct ionic_dev *idev = &ionic->idev; unsigned long check_time, last_check_time; + struct ionic_dev *idev = &ionic->idev; + struct ionic_lif *lif = ionic->lif; bool fw_status_ready = true; bool fw_hb_ready; u8 fw_generation; @@ -155,13 +171,10 @@ do_check_time: goto do_check_time; } - /* firmware is useful only if the running bit is set and - * fw_status != 0xff (bad PCI read) - * If fw_status is not ready don't bother with the generation. - */ fw_status = ioread8(&idev->dev_info_regs->fw_status); - if (fw_status == 0xff || !(fw_status & IONIC_FW_STS_F_RUNNING)) { + /* If fw_status is not ready don't bother with the generation */ + if (!ionic_is_fw_running(idev)) { fw_status_ready = false; } else { fw_generation = fw_status & IONIC_FW_STS_F_GENERATION; @@ -176,31 +189,41 @@ do_check_time: * the down, the next watchdog will see the fw is up * and the generation value stable, so will trigger * the fw-up activity. + * + * If we had already moved to FW_RESET from a RESET event, + * it is possible that we never saw the fw_status go to 0, + * so we fake the current idev->fw_status_ready here to + * force the transition and get FW up again. */ - fw_status_ready = false; + if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) + idev->fw_status_ready = false; /* go to running */ + else + fw_status_ready = false; /* go to down */ } } /* is this a transition? */ if (fw_status_ready != idev->fw_status_ready) { - struct ionic_lif *lif = ionic->lif; bool trigger = false; - idev->fw_status_ready = fw_status_ready; - - if (!fw_status_ready) { - dev_info(ionic->dev, "FW stopped %u\n", fw_status); - if (lif && !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) - trigger = true; - } else { - dev_info(ionic->dev, "FW running %u\n", fw_status); - if (lif && test_bit(IONIC_LIF_F_FW_RESET, lif->state)) - trigger = true; + if (!fw_status_ready && lif && + !test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { + dev_info(ionic->dev, "FW stopped 0x%02x\n", fw_status); + trigger = true; + + } else if (fw_status_ready && lif && + test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { + dev_info(ionic->dev, "FW running 0x%02x\n", fw_status); + trigger = true; } if (trigger) { struct ionic_deferred_work *work; + idev->fw_status_ready = fw_status_ready; + work = kzalloc(sizeof(*work), GFP_ATOMIC); if (work) { work->type = IONIC_DW_TYPE_LIF_RESET; @@ -210,12 +233,14 @@ do_check_time: } } - if (!fw_status_ready) + if (!idev->fw_status_ready) return -ENXIO; - /* wait at least one watchdog period since the last heartbeat */ + /* Because of some variability in the actual FW heartbeat, we + * wait longer than the DEVCMD_TIMEOUT before checking again. + */ last_check_time = idev->last_hb_time; - if (time_before(check_time, last_check_time + ionic->watchdog_period)) + if (time_before(check_time, last_check_time + DEVCMD_TIMEOUT * 2 * HZ)) return 0; fw_hb = ioread32(&idev->dev_info_regs->fw_heartbeat); @@ -392,60 +417,63 @@ void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type) } /* VF commands */ -int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data) +int ionic_set_vf_config(struct ionic *ionic, int vf, + struct ionic_vf_setattr_cmd *vfc) { union ionic_dev_cmd cmd = { .vf_setattr.opcode = IONIC_CMD_VF_SETATTR, - .vf_setattr.attr = attr, + .vf_setattr.attr = vfc->attr, .vf_setattr.vf_index = cpu_to_le16(vf), }; int err; + memcpy(cmd.vf_setattr.pad, vfc->pad, sizeof(vfc->pad)); + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_go(&ionic->idev, &cmd); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr, + struct ionic_vf_getattr_comp *comp) +{ + union ionic_dev_cmd cmd = { + .vf_getattr.opcode = IONIC_CMD_VF_GETATTR, + .vf_getattr.attr = attr, + .vf_getattr.vf_index = cpu_to_le16(vf), + }; + int err; + + if (vf >= ionic->num_vfs) + return -EINVAL; + switch (attr) { case IONIC_VF_ATTR_SPOOFCHK: - cmd.vf_setattr.spoofchk = *data; - dev_dbg(ionic->dev, "%s: vf %d spoof %d\n", - __func__, vf, *data); - break; case IONIC_VF_ATTR_TRUST: - cmd.vf_setattr.trust = *data; - dev_dbg(ionic->dev, "%s: vf %d trust %d\n", - __func__, vf, *data); - break; case IONIC_VF_ATTR_LINKSTATE: - cmd.vf_setattr.linkstate = *data; - dev_dbg(ionic->dev, "%s: vf %d linkstate %d\n", - __func__, vf, *data); - break; case IONIC_VF_ATTR_MAC: - ether_addr_copy(cmd.vf_setattr.macaddr, data); - dev_dbg(ionic->dev, "%s: vf %d macaddr %pM\n", - __func__, vf, data); - break; case IONIC_VF_ATTR_VLAN: - cmd.vf_setattr.vlanid = cpu_to_le16(*(u16 *)data); - dev_dbg(ionic->dev, "%s: vf %d vlan %d\n", - __func__, vf, *(u16 *)data); - break; case IONIC_VF_ATTR_RATE: - cmd.vf_setattr.maxrate = cpu_to_le32(*(u32 *)data); - dev_dbg(ionic->dev, "%s: vf %d maxrate %d\n", - __func__, vf, *(u32 *)data); break; case IONIC_VF_ATTR_STATSADDR: - cmd.vf_setattr.stats_pa = cpu_to_le64(*(u64 *)data); - dev_dbg(ionic->dev, "%s: vf %d stats_pa 0x%08llx\n", - __func__, vf, *(u64 *)data); - break; default: return -EINVAL; } mutex_lock(&ionic->dev_cmd_lock); ionic_dev_cmd_go(&ionic->idev, &cmd); - err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + err = ionic_dev_cmd_wait_nomsg(ionic, DEVCMD_TIMEOUT); + memcpy_fromio(comp, &ionic->idev.dev_cmd_regs->comp.vf_getattr, + sizeof(*comp)); mutex_unlock(&ionic->dev_cmd_lock); + if (err && comp->status != IONIC_RC_ENOSUPP) + ionic_dev_cmd_dev_err_print(ionic, cmd.vf_getattr.opcode, + comp->status, err); + return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index e5acf3bd62b2..563c302eb033 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -318,7 +318,10 @@ void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable); void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type); void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type); -int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data); +int ionic_set_vf_config(struct ionic *ionic, int vf, + struct ionic_vf_setattr_cmd *vfc); +int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr, + struct ionic_vf_getattr_comp *comp); void ionic_dev_cmd_queue_identify(struct ionic_dev *idev, u16 lif_type, u8 qtype, u8 qver); void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver); @@ -353,5 +356,6 @@ void ionic_q_rewind(struct ionic_queue *q, struct ionic_desc_info *start); void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, unsigned int stop_index); int ionic_heartbeat_check(struct ionic *ionic); +bool ionic_is_fw_running(struct ionic_dev *idev); #endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 2ff7be17e5af..542e395fb037 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1112,12 +1112,17 @@ static bool ionic_notifyq_service(struct ionic_cq *cq, ionic_link_status_check_request(lif, CAN_NOT_SLEEP); break; case IONIC_EVENT_RESET: - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) { - netdev_err(lif->netdev, "Reset event dropped\n"); - } else { - work->type = IONIC_DW_TYPE_LIF_RESET; - ionic_lif_deferred_enqueue(&lif->deferred, work); + if (lif->ionic->idev.fw_status_ready && + !test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "Reset event dropped\n"); + clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state); + } else { + work->type = IONIC_DW_TYPE_LIF_RESET; + ionic_lif_deferred_enqueue(&lif->deferred, work); + } } break; default: @@ -1782,7 +1787,7 @@ static void ionic_lif_quiesce(struct ionic_lif *lif) err = ionic_adminq_post_wait(lif, &ctx); if (err) - netdev_err(lif->netdev, "lif quiesce failed %d\n", err); + netdev_dbg(lif->netdev, "lif quiesce failed %d\n", err); } static void ionic_txrx_disable(struct ionic_lif *lif) @@ -2152,6 +2157,76 @@ static int ionic_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd } } +static int ionic_update_cached_vf_config(struct ionic *ionic, int vf) +{ + struct ionic_vf_getattr_comp comp = { 0 }; + int err; + u8 attr; + + attr = IONIC_VF_ATTR_VLAN; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].vlanid = comp.vlanid; + + attr = IONIC_VF_ATTR_SPOOFCHK; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].spoofchk = comp.spoofchk; + + attr = IONIC_VF_ATTR_LINKSTATE; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) { + switch (comp.linkstate) { + case IONIC_VF_LINK_STATUS_UP: + ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_ENABLE; + break; + case IONIC_VF_LINK_STATUS_DOWN: + ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_DISABLE; + break; + case IONIC_VF_LINK_STATUS_AUTO: + ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_AUTO; + break; + default: + dev_warn(ionic->dev, "Unexpected link state %u\n", comp.linkstate); + break; + } + } + + attr = IONIC_VF_ATTR_RATE; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].maxrate = comp.maxrate; + + attr = IONIC_VF_ATTR_TRUST; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].trusted = comp.trust; + + attr = IONIC_VF_ATTR_MAC; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ether_addr_copy(ionic->vfs[vf].macaddr, comp.macaddr); + +err_out: + if (err) + dev_err(ionic->dev, "Failed to get %s for VF %d\n", + ionic_vf_attr_to_str(attr), vf); + + return err; +} + static int ionic_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivf) { @@ -2167,14 +2242,18 @@ static int ionic_get_vf_config(struct net_device *netdev, if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ivf->vf = vf; - ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid); - ivf->qos = 0; - ivf->spoofchk = ionic->vfs[vf].spoofchk; - ivf->linkstate = ionic->vfs[vf].linkstate; - ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate); - ivf->trusted = ionic->vfs[vf].trusted; - ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr); + ivf->vf = vf; + ivf->qos = 0; + + ret = ionic_update_cached_vf_config(ionic, vf); + if (!ret) { + ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid); + ivf->spoofchk = ionic->vfs[vf].spoofchk; + ivf->linkstate = ionic->vfs[vf].linkstate; + ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate); + ivf->trusted = ionic->vfs[vf].trusted; + ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr); + } } up_read(&ionic->vf_op_lock); @@ -2220,6 +2299,7 @@ static int ionic_get_vf_stats(struct net_device *netdev, int vf, static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_MAC }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; int ret; @@ -2235,7 +2315,11 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, IONIC_VF_ATTR_MAC, mac); + ether_addr_copy(vfc.macaddr, mac); + dev_dbg(ionic->dev, "%s: vf %d macaddr %pM\n", + __func__, vf, vfc.macaddr); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) ether_addr_copy(ionic->vfs[vf].macaddr, mac); } @@ -2247,6 +2331,7 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, __be16 proto) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_VLAN }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; int ret; @@ -2269,8 +2354,11 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_VLAN, (u8 *)&vlan); + vfc.vlanid = cpu_to_le16(vlan); + dev_dbg(ionic->dev, "%s: vf %d vlan %d\n", + __func__, vf, le16_to_cpu(vfc.vlanid)); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) ionic->vfs[vf].vlanid = cpu_to_le16(vlan); } @@ -2282,6 +2370,7 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, static int ionic_set_vf_rate(struct net_device *netdev, int vf, int tx_min, int tx_max) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_RATE }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; int ret; @@ -2298,8 +2387,11 @@ static int ionic_set_vf_rate(struct net_device *netdev, int vf, if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_RATE, (u8 *)&tx_max); + vfc.maxrate = cpu_to_le32(tx_max); + dev_dbg(ionic->dev, "%s: vf %d maxrate %d\n", + __func__, vf, le32_to_cpu(vfc.maxrate)); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) lif->ionic->vfs[vf].maxrate = cpu_to_le32(tx_max); } @@ -2310,9 +2402,9 @@ static int ionic_set_vf_rate(struct net_device *netdev, int vf, static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_SPOOFCHK }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; - u8 data = set; /* convert to u8 for config */ int ret; if (!netif_device_present(netdev)) @@ -2323,10 +2415,13 @@ static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_SPOOFCHK, &data); + vfc.spoofchk = set; + dev_dbg(ionic->dev, "%s: vf %d spoof %d\n", + __func__, vf, vfc.spoofchk); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) - ionic->vfs[vf].spoofchk = data; + ionic->vfs[vf].spoofchk = set; } up_write(&ionic->vf_op_lock); @@ -2335,9 +2430,9 @@ static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set) static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_TRUST }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; - u8 data = set; /* convert to u8 for config */ int ret; if (!netif_device_present(netdev)) @@ -2348,10 +2443,13 @@ static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_TRUST, &data); + vfc.trust = set; + dev_dbg(ionic->dev, "%s: vf %d trust %d\n", + __func__, vf, vfc.trust); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) - ionic->vfs[vf].trusted = data; + ionic->vfs[vf].trusted = set; } up_write(&ionic->vf_op_lock); @@ -2360,20 +2458,21 @@ static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set) static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_LINKSTATE }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; - u8 data; + u8 vfls; int ret; switch (set) { case IFLA_VF_LINK_STATE_ENABLE: - data = IONIC_VF_LINK_STATUS_UP; + vfls = IONIC_VF_LINK_STATUS_UP; break; case IFLA_VF_LINK_STATE_DISABLE: - data = IONIC_VF_LINK_STATUS_DOWN; + vfls = IONIC_VF_LINK_STATUS_DOWN; break; case IFLA_VF_LINK_STATE_AUTO: - data = IONIC_VF_LINK_STATUS_AUTO; + vfls = IONIC_VF_LINK_STATUS_AUTO; break; default: return -EINVAL; @@ -2387,8 +2486,11 @@ static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_LINKSTATE, &data); + vfc.linkstate = vfls; + dev_dbg(ionic->dev, "%s: vf %d linkstate %d\n", + __func__, vf, vfc.linkstate); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) ionic->vfs[vf].linkstate = set; } @@ -2835,6 +2937,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) mutex_unlock(&lif->queue_lock); + clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state); dev_info(ionic->dev, "FW Down: LIFs stopped\n"); } @@ -2934,8 +3037,6 @@ void ionic_lif_free(struct ionic_lif *lif) /* unmap doorbell page */ ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); lif->kern_dbpage = NULL; - kfree(lif->dbid_inuse); - lif->dbid_inuse = NULL; mutex_destroy(&lif->config_lock); mutex_destroy(&lif->queue_lock); @@ -3135,22 +3236,12 @@ int ionic_lif_init(struct ionic_lif *lif) return -EINVAL; } - lif->dbid_inuse = bitmap_zalloc(lif->dbid_count, GFP_KERNEL); - if (!lif->dbid_inuse) { - dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n"); - return -ENOMEM; - } - - /* first doorbell id reserved for kernel (dbid aka pid == zero) */ - set_bit(0, lif->dbid_inuse); lif->kern_pid = 0; - dbpage_num = ionic_db_page_num(lif, lif->kern_pid); lif->kern_dbpage = ionic_bus_map_dbpage(lif->ionic, dbpage_num); if (!lif->kern_dbpage) { dev_err(dev, "Cannot map dbpage, aborting\n"); - err = -ENOMEM; - goto err_out_free_dbid; + return -ENOMEM; } err = ionic_lif_adminq_init(lif); @@ -3186,15 +3277,13 @@ int ionic_lif_init(struct ionic_lif *lif) return 0; err_out_notifyq_deinit: + napi_disable(&lif->adminqcq->napi); ionic_lif_qcq_deinit(lif, lif->notifyqcq); err_out_adminq_deinit: ionic_lif_qcq_deinit(lif, lif->adminqcq); ionic_lif_reset(lif); ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); lif->kern_dbpage = NULL; -err_out_free_dbid: - kfree(lif->dbid_inuse); - lif->dbid_inuse = NULL; return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 9f7ab2f17f93..a53984bf3544 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -135,6 +135,7 @@ enum ionic_lif_state_flags { IONIC_LIF_F_LINK_CHECK_REQUESTED, IONIC_LIF_F_FILTER_SYNC_NEEDED, IONIC_LIF_F_FW_RESET, + IONIC_LIF_F_FW_STOPPING, IONIC_LIF_F_SPLIT_INTR, IONIC_LIF_F_BROKEN, IONIC_LIF_F_TX_DIM_INTR, @@ -213,7 +214,6 @@ struct ionic_lif { u32 rx_coalesce_hw; /* what the hw is using */ u32 tx_coalesce_usecs; /* what the user asked for */ u32 tx_coalesce_hw; /* what the hw is using */ - unsigned long *dbid_inuse; unsigned int dbid_count; struct ionic_phc *phc; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 875f4ec42efe..4029b4e021f8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -188,6 +188,28 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode) } } +const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr) +{ + switch (attr) { + case IONIC_VF_ATTR_SPOOFCHK: + return "IONIC_VF_ATTR_SPOOFCHK"; + case IONIC_VF_ATTR_TRUST: + return "IONIC_VF_ATTR_TRUST"; + case IONIC_VF_ATTR_LINKSTATE: + return "IONIC_VF_ATTR_LINKSTATE"; + case IONIC_VF_ATTR_MAC: + return "IONIC_VF_ATTR_MAC"; + case IONIC_VF_ATTR_VLAN: + return "IONIC_VF_ATTR_VLAN"; + case IONIC_VF_ATTR_RATE: + return "IONIC_VF_ATTR_RATE"; + case IONIC_VF_ATTR_STATSADDR: + return "IONIC_VF_ATTR_STATSADDR"; + default: + return "IONIC_VF_ATTR_UNKNOWN"; + } +} + static void ionic_adminq_flush(struct ionic_lif *lif) { struct ionic_desc_info *desc_info; @@ -215,9 +237,13 @@ static void ionic_adminq_flush(struct ionic_lif *lif) void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, u8 status, int err) { + const char *stat_str; + + stat_str = (err == -ETIMEDOUT) ? "TIMEOUT" : + ionic_error_to_str(status); + netdev_err(lif->netdev, "%s (%d) failed: %s (%d)\n", - ionic_opcode_to_str(opcode), opcode, - ionic_error_to_str(status), err); + ionic_opcode_to_str(opcode), opcode, stat_str, err); } static int ionic_adminq_check_err(struct ionic_lif *lif, @@ -318,6 +344,7 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, if (do_msg && !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) netdev_err(netdev, "Posting of %s (%d) failed: %d\n", name, ctx->cmd.cmd.opcode, err); + ctx->comp.comp.status = IONIC_RC_ERROR; return err; } @@ -331,11 +358,15 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, if (remaining) break; - /* interrupt the wait if FW stopped */ - if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { + /* force a check of FW status and break out if FW reset */ + (void)ionic_heartbeat_check(lif->ionic); + if ((test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !lif->ionic->idev.fw_status_ready) || + test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { if (do_msg) - netdev_err(netdev, "%s (%d) interrupted, FW in reset\n", - name, ctx->cmd.cmd.opcode); + netdev_warn(netdev, "%s (%d) interrupted, FW in reset\n", + name, ctx->cmd.cmd.opcode); + ctx->comp.comp.status = IONIC_RC_ERROR; return -ENXIO; } @@ -370,21 +401,34 @@ int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx * static void ionic_dev_cmd_clean(struct ionic *ionic) { - union __iomem ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs; + struct ionic_dev *idev = &ionic->idev; - iowrite32(0, ®s->doorbell); - memset_io(®s->cmd, 0, sizeof(regs->cmd)); + iowrite32(0, &idev->dev_cmd_regs->doorbell); + memset_io(&idev->dev_cmd_regs->cmd, 0, sizeof(idev->dev_cmd_regs->cmd)); } -int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) +void ionic_dev_cmd_dev_err_print(struct ionic *ionic, u8 opcode, u8 status, + int err) +{ + const char *stat_str; + + stat_str = (err == -ETIMEDOUT) ? "TIMEOUT" : + ionic_error_to_str(status); + + dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n", + ionic_opcode_to_str(opcode), opcode, stat_str, err); +} + +static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds, + const bool do_msg) { struct ionic_dev *idev = &ionic->idev; unsigned long start_time; unsigned long max_wait; unsigned long duration; + int done = 0; + bool fw_up; int opcode; - int hb = 0; - int done; int err; /* Wait for dev cmd to complete, retrying if we get EAGAIN, @@ -394,31 +438,24 @@ int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) try_again: opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode); start_time = jiffies; - do { + for (fw_up = ionic_is_fw_running(idev); + !done && fw_up && time_before(jiffies, max_wait); + fw_up = ionic_is_fw_running(idev)) { done = ionic_dev_cmd_done(idev); if (done) break; usleep_range(100, 200); - - /* Don't check the heartbeat on FW_CONTROL commands as they are - * notorious for interrupting the firmware's heartbeat update. - */ - if (opcode != IONIC_CMD_FW_CONTROL) - hb = ionic_heartbeat_check(ionic); - } while (!done && !hb && time_before(jiffies, max_wait)); + } duration = jiffies - start_time; dev_dbg(ionic->dev, "DEVCMD %s (%d) done=%d took %ld secs (%ld jiffies)\n", ionic_opcode_to_str(opcode), opcode, done, duration / HZ, duration); - if (!done && hb) { - /* It is possible (but unlikely) that FW was busy and missed a - * heartbeat check but is still alive and will process this - * request, so don't clean the dev_cmd in this case. - */ - dev_dbg(ionic->dev, "DEVCMD %s (%d) failed - FW halted\n", - ionic_opcode_to_str(opcode), opcode); + if (!done && !fw_up) { + ionic_dev_cmd_clean(ionic); + dev_warn(ionic->dev, "DEVCMD %s (%d) interrupted - FW is down\n", + ionic_opcode_to_str(opcode), opcode); return -ENXIO; } @@ -444,9 +481,9 @@ try_again: } if (!(opcode == IONIC_CMD_FW_CONTROL && err == IONIC_RC_EAGAIN)) - dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n", - ionic_opcode_to_str(opcode), opcode, - ionic_error_to_str(err), err); + if (do_msg) + ionic_dev_cmd_dev_err_print(ionic, opcode, err, + ionic_error_to_errno(err)); return ionic_error_to_errno(err); } @@ -454,6 +491,16 @@ try_again: return 0; } +int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) +{ + return __ionic_dev_cmd_wait(ionic, max_seconds, true); +} + +int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_seconds) +{ + return __ionic_dev_cmd_wait(ionic, max_seconds, false); +} + int ionic_setup(struct ionic *ionic) { int err; @@ -540,6 +587,9 @@ int ionic_reset(struct ionic *ionic) struct ionic_dev *idev = &ionic->idev; int err; + if (!ionic_is_fw_running(idev)) + return 0; + mutex_lock(&ionic->dev_cmd_lock); ionic_dev_cmd_reset(idev); err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); @@ -612,15 +662,17 @@ int ionic_port_init(struct ionic *ionic) int ionic_port_reset(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; - int err; + int err = 0; if (!idev->port_info) return 0; - mutex_lock(&ionic->dev_cmd_lock); - ionic_dev_cmd_port_reset(idev); - err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); - mutex_unlock(&ionic->dev_cmd_lock); + if (ionic_is_fw_running(idev)) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_reset(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + } dma_free_coherent(ionic->dev, idev->port_info_sz, idev->port_info, idev->port_info_pa); @@ -628,9 +680,6 @@ int ionic_port_reset(struct ionic *ionic) idev->port_info = NULL; idev->port_info_pa = 0; - if (err) - dev_err(ionic->dev, "Failed to reset port\n"); - return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c index f6e785f949f9..b7363376dfc8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -376,10 +376,24 @@ static int ionic_lif_filter_add(struct ionic_lif *lif, spin_unlock_bh(&lif->rx_filters.lock); - if (err == -ENOSPC) { - if (le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN) - lif->max_vlans = lif->nvlans; + /* store the max_vlans limit that we found */ + if (err == -ENOSPC && + le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN) + lif->max_vlans = lif->nvlans; + + /* Prevent unnecessary error messages on recoverable + * errors as the filter will get retried on the next + * sync attempt. + */ + switch (err) { + case -ENOSPC: + case -ENXIO: + case -ETIMEDOUT: + case -EAGAIN: + case -EBUSY: return 0; + default: + break; } ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode, @@ -494,9 +508,22 @@ static int ionic_lif_filter_del(struct ionic_lif *lif, spin_unlock_bh(&lif->rx_filters.lock); if (state != IONIC_FILTER_STATE_NEW) { - err = ionic_adminq_post_wait(lif, &ctx); - if (err && err != -EEXIST) + err = ionic_adminq_post_wait_nomsg(lif, &ctx); + + switch (err) { + /* ignore these errors */ + case -EEXIST: + case -ENXIO: + case -ETIMEDOUT: + case -EAGAIN: + case -EBUSY: + case 0: + break; + default: + ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode, + ctx.comp.comp.status, err); return err; + } } return 0; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 94384f5d2a22..d197a70a49c9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -669,27 +669,37 @@ dma_fail: return -EIO; } +static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q, + struct ionic_desc_info *desc_info) +{ + struct ionic_buf_info *buf_info = desc_info->bufs; + struct device *dev = q->dev; + unsigned int i; + + if (!desc_info->nbufs) + return; + + dma_unmap_single(dev, (dma_addr_t)buf_info->dma_addr, + buf_info->len, DMA_TO_DEVICE); + buf_info++; + for (i = 1; i < desc_info->nbufs; i++, buf_info++) + dma_unmap_page(dev, (dma_addr_t)buf_info->dma_addr, + buf_info->len, DMA_TO_DEVICE); + + desc_info->nbufs = 0; +} + static void ionic_tx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, struct ionic_cq_info *cq_info, void *cb_arg) { - struct ionic_buf_info *buf_info = desc_info->bufs; struct ionic_tx_stats *stats = q_to_tx_stats(q); struct ionic_qcq *qcq = q_to_qcq(q); struct sk_buff *skb = cb_arg; - struct device *dev = q->dev; - unsigned int i; u16 qi; - if (desc_info->nbufs) { - dma_unmap_single(dev, (dma_addr_t)buf_info->dma_addr, - buf_info->len, DMA_TO_DEVICE); - buf_info++; - for (i = 1; i < desc_info->nbufs; i++, buf_info++) - dma_unmap_page(dev, (dma_addr_t)buf_info->dma_addr, - buf_info->len, DMA_TO_DEVICE); - } + ionic_tx_desc_unmap_bufs(q, desc_info); if (!skb) return; @@ -931,8 +941,11 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) err = ionic_tx_tcp_inner_pseudo_csum(skb); else err = ionic_tx_tcp_pseudo_csum(skb); - if (err) + if (err) { + /* clean up mapping from ionic_tx_map_skb */ + ionic_tx_desc_unmap_bufs(q, desc_info); return err; + } if (encap) hdrlen = skb_inner_transport_header(skb) - skb->data + @@ -1003,8 +1016,8 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) return 0; } -static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) +static void ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, + struct ionic_desc_info *desc_info) { struct ionic_txq_desc *desc = desc_info->txq_desc; struct ionic_buf_info *buf_info = desc_info->bufs; @@ -1038,12 +1051,10 @@ static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, stats->crc32_csum++; else stats->csum++; - - return 0; } -static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) +static void ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, + struct ionic_desc_info *desc_info) { struct ionic_txq_desc *desc = desc_info->txq_desc; struct ionic_buf_info *buf_info = desc_info->bufs; @@ -1074,12 +1085,10 @@ static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, desc->csum_offset = 0; stats->csum_none++; - - return 0; } -static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) +static void ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, + struct ionic_desc_info *desc_info) { struct ionic_txq_sg_desc *sg_desc = desc_info->txq_sg_desc; struct ionic_buf_info *buf_info = &desc_info->bufs[1]; @@ -1093,31 +1102,24 @@ static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, } stats->frags += skb_shinfo(skb)->nr_frags; - - return 0; } static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb) { struct ionic_desc_info *desc_info = &q->info[q->head_idx]; struct ionic_tx_stats *stats = q_to_tx_stats(q); - int err; if (unlikely(ionic_tx_map_skb(q, skb, desc_info))) return -EIO; /* set up the initial descriptor */ if (skb->ip_summed == CHECKSUM_PARTIAL) - err = ionic_tx_calc_csum(q, skb, desc_info); + ionic_tx_calc_csum(q, skb, desc_info); else - err = ionic_tx_calc_no_csum(q, skb, desc_info); - if (err) - return err; + ionic_tx_calc_no_csum(q, skb, desc_info); /* add frags */ - err = ionic_tx_skb_frags(q, skb, desc_info); - if (err) - return err; + ionic_tx_skb_frags(q, skb, desc_info); skb_tx_timestamp(skb); stats->pkts++; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index cc4ec2bb36db..672480c9d195 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -3098,6 +3098,9 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) continue; } + /* Some flows may keep variable set */ + p_hwfn->mcp_info->mcp_handling_status = 0; + rc = qed_calc_hw_mode(p_hwfn); if (rc) return rc; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index da1eadabcb41..9fb1fa479d4b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -140,7 +140,7 @@ static struct qed_mcp_cmd_elem *qed_mcp_cmd_get_elem(struct qed_hwfn *p_hwfn, int qed_mcp_free(struct qed_hwfn *p_hwfn) { if (p_hwfn->mcp_info) { - struct qed_mcp_cmd_elem *p_cmd_elem, *p_tmp; + struct qed_mcp_cmd_elem *p_cmd_elem = NULL, *p_tmp; kfree(p_hwfn->mcp_info->mfw_mb_cur); kfree(p_hwfn->mcp_info->mfw_mb_shadow); @@ -249,6 +249,7 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) /* Initialize the MFW spinlock */ spin_lock_init(&p_info->cmd_lock); spin_lock_init(&p_info->link_lock); + spin_lock_init(&p_info->unload_lock); INIT_LIST_HEAD(&p_info->cmd_list); @@ -614,12 +615,13 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, usecs); } -int qed_mcp_cmd(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - u32 cmd, - u32 param, - u32 *o_mcp_resp, - u32 *o_mcp_param) +static int _qed_mcp_cmd(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param, + bool can_sleep) { struct qed_mcp_mb_params mb_params; int rc; @@ -627,6 +629,7 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, memset(&mb_params, 0, sizeof(mb_params)); mb_params.cmd = cmd; mb_params.param = param; + mb_params.flags = can_sleep ? QED_MB_FLAG_CAN_SLEEP : 0; rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); if (rc) @@ -638,6 +641,28 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, return 0; } +int qed_mcp_cmd(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param) +{ + return (_qed_mcp_cmd(p_hwfn, p_ptt, cmd, param, + o_mcp_resp, o_mcp_param, true)); +} + +int qed_mcp_cmd_nosleep(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param) +{ + return (_qed_mcp_cmd(p_hwfn, p_ptt, cmd, param, + o_mcp_resp, o_mcp_param, false)); +} + static int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -1071,10 +1096,15 @@ int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) return 0; } +#define MFW_COMPLETION_MAX_ITER 5000 +#define MFW_COMPLETION_INTERVAL_MS 1 + int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { struct qed_mcp_mb_params mb_params; + u32 cnt = MFW_COMPLETION_MAX_ITER; u32 wol_param; + int rc; switch (p_hwfn->cdev->wol_config) { case QED_OV_WOL_DISABLED: @@ -1097,7 +1127,23 @@ int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) mb_params.param = wol_param; mb_params.flags = QED_MB_FLAG_CAN_SLEEP | QED_MB_FLAG_AVOID_BLOCK; - return qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); + spin_lock_bh(&p_hwfn->mcp_info->unload_lock); + set_bit(QED_MCP_BYPASS_PROC_BIT, + &p_hwfn->mcp_info->mcp_handling_status); + spin_unlock_bh(&p_hwfn->mcp_info->unload_lock); + + rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); + + while (test_bit(QED_MCP_IN_PROCESSING_BIT, + &p_hwfn->mcp_info->mcp_handling_status) && --cnt) + msleep(MFW_COMPLETION_INTERVAL_MS); + + if (!cnt) + DP_NOTICE(p_hwfn, + "Failed to wait MFW event completion after %d msec\n", + MFW_COMPLETION_MAX_ITER * MFW_COMPLETION_INTERVAL_MS); + + return rc; } int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -1728,8 +1774,8 @@ static void qed_mcp_update_bw(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) qed_configure_pf_max_bandwidth(p_hwfn->cdev, p_info->bandwidth_max); /* Acknowledge the MFW */ - qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_BW_UPDATE_ACK, 0, &resp, - ¶m); + qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_BW_UPDATE_ACK, 0, &resp, + ¶m); } static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -1766,8 +1812,8 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) p_hwfn->mcp_info->func_info.ovlan, p_hwfn->hw_info.hw_mode); /* Acknowledge the MFW */ - qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0, - &resp, ¶m); + qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0, + &resp, ¶m); } static void qed_mcp_handle_fan_failure(struct qed_hwfn *p_hwfn, @@ -1997,6 +2043,19 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn, "Msg [%d] - old CMD 0x%02x, new CMD 0x%02x\n", i, info->mfw_mb_shadow[i], info->mfw_mb_cur[i]); + spin_lock_bh(&p_hwfn->mcp_info->unload_lock); + if (test_bit(QED_MCP_BYPASS_PROC_BIT, + &p_hwfn->mcp_info->mcp_handling_status)) { + spin_unlock_bh(&p_hwfn->mcp_info->unload_lock); + DP_INFO(p_hwfn, + "Msg [%d] is bypassed on unload flow\n", i); + continue; + } + + set_bit(QED_MCP_IN_PROCESSING_BIT, + &p_hwfn->mcp_info->mcp_handling_status); + spin_unlock_bh(&p_hwfn->mcp_info->unload_lock); + switch (i) { case MFW_DRV_MSG_LINK_CHANGE: qed_mcp_handle_link_change(p_hwfn, p_ptt, false); @@ -2050,6 +2109,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn, DP_INFO(p_hwfn, "Unimplemented MFW message %d\n", i); rc = -EINVAL; } + + clear_bit(QED_MCP_IN_PROCESSING_BIT, + &p_hwfn->mcp_info->mcp_handling_status); } /* ACK everything */ @@ -3675,8 +3737,8 @@ static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn, { int rc; - rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, param, - p_mcp_resp, p_mcp_param); + rc = qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, + param, p_mcp_resp, p_mcp_param); if (rc) return rc; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 369e1892450a..9bd0565fe8ab 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -393,11 +393,12 @@ int qed_mcp_get_board_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_board_config); /** - * qed_mcp_cmd(): General function for sending commands to the MCP + * qed_mcp_cmd(): Sleepable function for sending commands to the MCP * mailbox. It acquire mutex lock for the entire * operation, from sending the request until the MCP * response. Waiting for MCP response will be checked up - * to 5 seconds every 5ms. + * to 5 seconds every 10ms. Should not be called from atomic + * context. * * @p_hwfn: HW device data. * @p_ptt: PTT required for register access. @@ -417,6 +418,31 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, u32 *o_mcp_param); /** + * qed_mcp_cmd_nosleep(): Function for sending commands to the MCP + * mailbox. It acquire mutex lock for the entire + * operation, from sending the request until the MCP + * response. Waiting for MCP response will be checked up + * to 5 seconds every 10us. Should be called when sleep + * is not allowed. + * + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @cmd: command to be sent to the MCP. + * @param: Optional param + * @o_mcp_resp: The MCP response code (exclude sequence). + * @o_mcp_param: Optional parameter provided by the MCP + * response + * + * Return: Int - 0 - Operation was successul. + */ +int qed_mcp_cmd_nosleep(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param); + +/** * qed_mcp_drain(): drains the nig, allowing completion to pass in * case of pauses. * (Should be called only from sleepable context) @@ -762,6 +788,14 @@ struct qed_mcp_info { /* S/N for debug data mailbox commands */ atomic_t dbg_data_seq; + + /* Spinlock used to sync the flag mcp_handling_status with + * the mfw events handler + */ + spinlock_t unload_lock; + unsigned long mcp_handling_status; +#define QED_MCP_BYPASS_PROC_BIT 0 +#define QED_MCP_IN_PROCESSING_BIT 1 }; struct qed_mcp_mb_params { diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 19e2621e0645..67014eb76969 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2667,10 +2667,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38: rtl_eri_set_bits(tp, 0xd4, 0x0c00); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: - rtl_eri_set_bits(tp, 0xd4, 0x1f80); - break; - case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_63: r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80); break; default: @@ -2678,13 +2675,48 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp) } } +static void rtl_disable_exit_l1(struct rtl8169_private *tp) +{ + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: + rtl_eri_clear_bits(tp, 0xd4, 0x1f00); + break; + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_63: + r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0); + break; + default: + break; + } +} + static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) { /* Don't enable ASPM in the chip if OS can't control ASPM */ if (enable && tp->aspm_manageable) { RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); + + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_45 ... RTL_GIGA_MAC_VER_48: + case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63: + /* reset ephy tx/rx disable timer */ + r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0); + /* chip can trigger L1.2 */ + r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, BIT(2)); + break; + default: + break; + } } else { + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_45 ... RTL_GIGA_MAC_VER_48: + case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63: + r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0); + break; + default: + break; + } + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); } @@ -4683,7 +4715,7 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl_pci_commit(tp); rtl8169_cleanup(tp, true); - + rtl_disable_exit_l1(tp); rtl_prepare_power_down(tp); } @@ -4843,8 +4875,6 @@ static void rtl8169_net_suspend(struct rtl8169_private *tp) rtl8169_down(tp); } -#ifdef CONFIG_PM - static int rtl8169_runtime_resume(struct device *dev) { struct rtl8169_private *tp = dev_get_drvdata(dev); @@ -4860,7 +4890,7 @@ static int rtl8169_runtime_resume(struct device *dev) return 0; } -static int __maybe_unused rtl8169_suspend(struct device *device) +static int rtl8169_suspend(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); @@ -4873,7 +4903,7 @@ static int __maybe_unused rtl8169_suspend(struct device *device) return 0; } -static int __maybe_unused rtl8169_resume(struct device *device) +static int rtl8169_resume(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); @@ -4915,13 +4945,11 @@ static int rtl8169_runtime_idle(struct device *device) } static const struct dev_pm_ops rtl8169_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(rtl8169_suspend, rtl8169_resume) - SET_RUNTIME_PM_OPS(rtl8169_runtime_suspend, rtl8169_runtime_resume, - rtl8169_runtime_idle) + SYSTEM_SLEEP_PM_OPS(rtl8169_suspend, rtl8169_resume) + RUNTIME_PM_OPS(rtl8169_runtime_suspend, rtl8169_runtime_resume, + rtl8169_runtime_idle) }; -#endif /* CONFIG_PM */ - static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp) { /* WoL fails with 8168b when the receiver is disabled. */ @@ -5255,6 +5283,16 @@ done: rtl_rar_set(tp, mac_addr); } +/* register is set if system vendor successfully tested ASPM 1.2 */ +static bool rtl_aspm_is_safe(struct rtl8169_private *tp) +{ + if (tp->mac_version >= RTL_GIGA_MAC_VER_60 && + r8168_mac_ocp_read(tp, 0xc0b2) & 0xf) + return true; + + return false; +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct rtl8169_private *tp; @@ -5333,7 +5371,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) * Chips from RTL8168h partially have issues with L1.2, but seem * to work fine with L1 and L1.1. */ - if (tp->mac_version >= RTL_GIGA_MAC_VER_45) + if (rtl_aspm_is_safe(tp)) + rc = 0; + else if (tp->mac_version >= RTL_GIGA_MAC_VER_45) rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); else rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1); @@ -5460,9 +5500,7 @@ static struct pci_driver rtl8169_pci_driver = { .probe = rtl_init_one, .remove = rtl_remove_one, .shutdown = rtl_shutdown, -#ifdef CONFIG_PM - .driver.pm = &rtl8169_pm_ops, -#endif + .driver.pm = pm_ptr(&rtl8169_pm_ops), }; module_pci_driver(rtl8169_pci_driver); diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index f7ad5487879b..15c295f90196 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -429,15 +429,6 @@ static const struct phy_reg rtl8168d_1_phy_reg_init_0[] = { { 0x0d, 0xf880 } }; -static const struct phy_reg rtl8168d_1_phy_reg_init_1[] = { - { 0x1f, 0x0002 }, - { 0x05, 0x669a }, - { 0x1f, 0x0005 }, - { 0x05, 0x8330 }, - { 0x06, 0x669a }, - { 0x1f, 0x0002 } -}; - static void rtl8168d_apply_firmware_cond(struct rtl8169_private *tp, struct phy_device *phydev, u16 val) @@ -455,6 +446,29 @@ static void rtl8168d_apply_firmware_cond(struct rtl8169_private *tp, r8169_apply_firmware(tp); } +static void rtl8168d_1_common(struct phy_device *phydev) +{ + u16 val; + + phy_write_paged(phydev, 0x0002, 0x05, 0x669a); + r8168d_phy_param(phydev, 0x8330, 0xffff, 0x669a); + phy_write(phydev, 0x1f, 0x0002); + + val = phy_read(phydev, 0x0d); + + if ((val & 0x00ff) != 0x006c) { + static const u16 set[] = { + 0x0065, 0x0066, 0x0067, 0x0068, + 0x0069, 0x006a, 0x006b, 0x006c + }; + int i; + + val &= 0xff00; + for (i = 0; i < ARRAY_SIZE(set); i++) + phy_write(phydev, 0x0d, val | set[i]); + } +} + static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { @@ -469,25 +483,7 @@ static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp, phy_modify(phydev, 0x0c, 0x5d00, 0xa200); if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) { - int val; - - rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_1); - - val = phy_read(phydev, 0x0d); - - if ((val & 0x00ff) != 0x006c) { - static const u32 set[] = { - 0x0065, 0x0066, 0x0067, 0x0068, - 0x0069, 0x006a, 0x006b, 0x006c - }; - int i; - - phy_write(phydev, 0x1f, 0x0002); - - val &= 0xff00; - for (i = 0; i < ARRAY_SIZE(set); i++) - phy_write(phydev, 0x0d, val | set[i]); - } + rtl8168d_1_common(phydev); } else { phy_write_paged(phydev, 0x0002, 0x05, 0x6662); r8168d_phy_param(phydev, 0x8330, 0xffff, 0x6662); @@ -513,24 +509,7 @@ static void rtl8168d_2_hw_phy_config(struct rtl8169_private *tp, rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_0); if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) { - int val; - - rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_1); - - val = phy_read(phydev, 0x0d); - if ((val & 0x00ff) != 0x006c) { - static const u32 set[] = { - 0x0065, 0x0066, 0x0067, 0x0068, - 0x0069, 0x006a, 0x006b, 0x006c - }; - int i; - - phy_write(phydev, 0x1f, 0x0002); - - val &= 0xff00; - for (i = 0; i < ARRAY_SIZE(set); i++) - phy_write(phydev, 0x0d, val | set[i]); - } + rtl8168d_1_common(phydev); } else { phy_write_paged(phydev, 0x0002, 0x05, 0x2642); r8168d_phy_param(phydev, 0x8330, 0xffff, 0x2642); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index b215cde68e10..24e2635c4c80 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1432,11 +1432,7 @@ static int ravb_phy_init(struct net_device *ndev) * at this time. */ if (soc_device_match(r8a7795es10)) { - err = phy_set_max_speed(phydev, SPEED_100); - if (err) { - netdev_err(ndev, "failed to limit PHY to 100Mbit/s\n"); - goto err_phy_disconnect; - } + phy_set_max_speed(phydev, SPEED_100); netdev_info(ndev, "limited PHY to 100Mbit/s\n"); } @@ -1457,8 +1453,6 @@ static int ravb_phy_init(struct net_device *ndev) return 0; -err_phy_disconnect: - phy_disconnect(phydev); err_deregister_fixed_link: if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); @@ -2854,7 +2848,6 @@ static int ravb_wol_restore(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - int ret; if (info->nc_queues) napi_enable(&priv->napi[RAVB_NC]); @@ -2863,9 +2856,7 @@ static int ravb_wol_restore(struct net_device *ndev) /* Disable MagicPacket */ ravb_modify(ndev, ECMR, ECMR_MPDE, 0); - ret = ravb_close(ndev); - if (ret < 0) - return ret; + ravb_close(ndev); return disable_irq_wake(priv->emac_irq); } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index d947a628e166..67ade78fb767 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2026,14 +2026,8 @@ static int sh_eth_phy_init(struct net_device *ndev) } /* mask with MAC supported features */ - if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) { - int err = phy_set_max_speed(phydev, SPEED_100); - if (err) { - netdev_err(ndev, "failed to limit PHY to 100 Mbit/s\n"); - phy_disconnect(phydev); - return err; - } - } + if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) + phy_set_max_speed(phydev, SPEED_100); phy_attached_info(phydev); @@ -3450,9 +3444,7 @@ static int sh_eth_wol_restore(struct net_device *ndev) * both be reset and all registers restored. This is what * happens during suspend and resume without WoL enabled. */ - ret = sh_eth_close(ndev); - if (ret < 0) - return ret; + sh_eth_close(ndev); ret = sh_eth_open(ndev); if (ret < 0) return ret; @@ -3464,7 +3456,7 @@ static int sh_eth_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct sh_eth_private *mdp = netdev_priv(ndev); - int ret = 0; + int ret; if (!netif_running(ndev)) return 0; @@ -3483,7 +3475,7 @@ static int sh_eth_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct sh_eth_private *mdp = netdev_priv(ndev); - int ret = 0; + int ret; if (!netif_running(ndev)) return 0; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 32161a56726c..77a0d9d7e65a 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -127,7 +127,7 @@ bool sxgbe_eee_init(struct sxgbe_priv_data * const priv) /* MAC core supports the EEE feature. */ if (priv->hw_cap.eee) { /* Check if the PHY supports EEE */ - if (phy_init_eee(ndev->phydev, 1)) + if (phy_init_eee(ndev->phydev, true)) return false; priv->eee_active = 1; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index cf366ed2557c..50d535981a35 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3990,6 +3990,30 @@ static unsigned int ef10_check_caps(const struct efx_nic *efx, } } +static unsigned int efx_ef10_recycle_ring_size(const struct efx_nic *efx) +{ + unsigned int ret = EFX_RECYCLE_RING_SIZE_10G; + + /* There is no difference between PFs and VFs. The side is based on + * the maximum link speed of a given NIC. + */ + switch (efx->pci_dev->device & 0xfff) { + case 0x0903: /* Farmingdale can do up to 10G */ + break; + case 0x0923: /* Greenport can do up to 40G */ + case 0x0a03: /* Medford can do up to 40G */ + ret *= 4; + break; + default: /* Medford2 can do up to 100G */ + ret *= 10; + } + + if (IS_ENABLED(CONFIG_PPC64)) + ret *= 4; + + return ret; +} + #define EF10_OFFLOAD_FEATURES \ (NETIF_F_IP_CSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | \ @@ -4106,6 +4130,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .check_caps = ef10_check_caps, .print_additional_fwver = efx_ef10_print_additional_fwver, .sensor_event = efx_mcdi_sensor_event, + .rx_recycle_ring_size = efx_ef10_recycle_ring_size, }; const struct efx_nic_type efx_hunt_a0_nic_type = { @@ -4243,4 +4268,5 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .check_caps = ef10_check_caps, .print_additional_fwver = efx_ef10_print_additional_fwver, .sensor_event = efx_mcdi_sensor_event, + .rx_recycle_ring_size = efx_ef10_recycle_ring_size, }; diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index f79b14a119ae..a07cbf45a326 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -23,6 +23,7 @@ #include "ef100_rx.h" #include "ef100_tx.h" #include "ef100_netdev.h" +#include "rx_common.h" #define EF100_MAX_VIS 4096 #define EF100_NUM_MCDI_BUFFERS 1 @@ -696,6 +697,12 @@ static unsigned int ef100_check_caps(const struct efx_nic *efx, } } +static unsigned int efx_ef100_recycle_ring_size(const struct efx_nic *efx) +{ + /* Maximum link speed for Riverhead is 100G */ + return 10 * EFX_RECYCLE_RING_SIZE_10G; +} + /* NIC level access functions */ #define EF100_OFFLOAD_FEATURES (NETIF_F_HW_CSUM | NETIF_F_RXCSUM | \ @@ -770,6 +777,7 @@ const struct efx_nic_type ef100_pf_nic_type = { .rx_push_rss_context_config = efx_mcdi_rx_push_rss_context_config, .rx_pull_rss_context_config = efx_mcdi_rx_pull_rss_context_config, .rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts, + .rx_recycle_ring_size = efx_ef100_recycle_ring_size, .reconfigure_mac = ef100_reconfigure_mac, .reconfigure_port = efx_mcdi_port_reconfigure, @@ -849,6 +857,7 @@ const struct efx_nic_type ef100_vf_nic_type = { .rx_pull_rss_config = efx_mcdi_rx_pull_rss_config, .rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config, .rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts, + .rx_recycle_ring_size = efx_ef100_recycle_ring_size, .reconfigure_mac = ef100_reconfigure_mac, .test_nvram = efx_new_mcdi_nvram_test_all, diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index cc15ee8812d9..c75dc75e2857 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1282,6 +1282,7 @@ struct efx_udp_tunnel { * @udp_tnl_has_port: Check if a port has been added as UDP tunnel * @print_additional_fwver: Dump NIC-specific additional FW version info * @sensor_event: Handle a sensor event from MCDI + * @rx_recycle_ring_size: Size of the RX recycle ring * @revision: Hardware architecture revision * @txd_ptr_tbl_base: TX descriptor ring base address * @rxd_ptr_tbl_base: RX descriptor ring base address @@ -1460,6 +1461,7 @@ struct efx_nic_type { size_t (*print_additional_fwver)(struct efx_nic *efx, char *buf, size_t len); void (*sensor_event)(struct efx_nic *efx, efx_qword_t *ev); + unsigned int (*rx_recycle_ring_size)(const struct efx_nic *efx); int revision; unsigned int txd_ptr_tbl_base; diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h index b9cafe9cd568..0cef35c0c559 100644 --- a/drivers/net/ethernet/sfc/nic_common.h +++ b/drivers/net/ethernet/sfc/nic_common.h @@ -195,6 +195,11 @@ static inline void efx_sensor_event(struct efx_nic *efx, efx_qword_t *ev) efx->type->sensor_event(efx, ev); } +static inline unsigned int efx_rx_recycle_ring_size(const struct efx_nic *efx) +{ + return efx->type->rx_recycle_ring_size(efx); +} + /* Some statistics are computed as A - B where A and B each increase * linearly with some hardware counter(s) and the counters are read * asynchronously. If the counters contributing to B are always read diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 633ca77a26fd..1b22c7be0088 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -23,13 +23,6 @@ module_param(rx_refill_threshold, uint, 0444); MODULE_PARM_DESC(rx_refill_threshold, "RX descriptor ring refill threshold (%)"); -/* Number of RX buffers to recycle pages for. When creating the RX page recycle - * ring, this number is divided by the number of buffers per page to calculate - * the number of pages to store in the RX page recycle ring. - */ -#define EFX_RECYCLE_RING_SIZE_IOMMU 4096 -#define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH) - /* RX maximum head room required. * * This must be at least 1 to prevent overflow, plus one packet-worth @@ -141,16 +134,7 @@ static void efx_init_rx_recycle_ring(struct efx_rx_queue *rx_queue) unsigned int bufs_in_recycle_ring, page_ring_size; struct efx_nic *efx = rx_queue->efx; - /* Set the RX recycle ring size */ -#ifdef CONFIG_PPC64 - bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU; -#else - if (iommu_present(&pci_bus_type)) - bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU; - else - bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_NOIOMMU; -#endif /* CONFIG_PPC64 */ - + bufs_in_recycle_ring = efx_rx_recycle_ring_size(efx); page_ring_size = roundup_pow_of_two(bufs_in_recycle_ring / efx->rx_bufs_per_page); rx_queue->page_ring = kcalloc(page_ring_size, diff --git a/drivers/net/ethernet/sfc/rx_common.h b/drivers/net/ethernet/sfc/rx_common.h index 207ccd8ba062..fbd2769307f9 100644 --- a/drivers/net/ethernet/sfc/rx_common.h +++ b/drivers/net/ethernet/sfc/rx_common.h @@ -18,6 +18,12 @@ #define EFX_RX_MAX_FRAGS DIV_ROUND_UP(EFX_MAX_FRAME_LEN(EFX_MAX_MTU), \ EFX_RX_USR_BUF_SIZE) +/* Number of RX buffers to recycle pages for. When creating the RX page recycle + * ring, this number is divided by the number of buffers per page to calculate + * the number of pages to store in the RX page recycle ring. + */ +#define EFX_RECYCLE_RING_SIZE_10G 256 + static inline u8 *efx_rx_buf_va(struct efx_rx_buffer *buf) { return page_address(buf->page) + buf->page_offset; diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index 16347a6d0c47..ce3060e15b54 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -25,6 +25,7 @@ #include "mcdi_port_common.h" #include "selftest.h" #include "siena_sriov.h" +#include "rx_common.h" /* Hardware control for SFC9000 family including SFL9021 (aka Siena). */ @@ -958,6 +959,12 @@ static unsigned int siena_check_caps(const struct efx_nic *efx, return 0; } +static unsigned int efx_siena_recycle_ring_size(const struct efx_nic *efx) +{ + /* Maximum link speed is 10G */ + return EFX_RECYCLE_RING_SIZE_10G; +} + /************************************************************************** * * Revision-dependent attributes used by efx.c and nic.c @@ -1098,4 +1105,5 @@ const struct efx_nic_type siena_a0_nic_type = { .rx_hash_key_size = 16, .check_caps = siena_check_caps, .sensor_event = efx_mcdi_sensor_event, + .rx_recycle_ring_size = efx_siena_recycle_ring_size, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 8e8778cfbbad..5943ff9f21c2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -383,10 +383,10 @@ static int intel_crosststamp(ktime_t *device, /* Repeat until the timestamps are from the FIFO last segment */ for (i = 0; i < num_snapshot; i++) { - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_ptptime(priv, ptpaddr, &ptp_time); *device = ns_to_ktime(ptp_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); get_arttime(priv->mii, intel_priv->mdio_adhoc_addr, &art_time); *system = convert_art_to_tsc(art_time); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 09644ab0d87a..f86cc83003f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -16,6 +16,7 @@ #include <linux/of_net.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> #include <linux/regmap.h> #include <linux/stmmac.h> @@ -57,7 +58,6 @@ struct emac_variant { }; /* struct sunxi_priv_data - hold all sunxi private data - * @tx_clk: reference to MAC TX clock * @ephy_clk: reference to the optional EPHY clock for the internal PHY * @regulator: reference to the optional regulator * @rst_ephy: reference to the optional EPHY reset for the internal PHY @@ -68,7 +68,6 @@ struct emac_variant { * @mux_handle: Internal pointer used by mdio-mux lib */ struct sunxi_priv_data { - struct clk *tx_clk; struct clk *ephy_clk; struct regulator *regulator; struct reset_control *rst_ephy; @@ -579,22 +578,14 @@ static int sun8i_dwmac_init(struct platform_device *pdev, void *priv) } } - ret = clk_prepare_enable(gmac->tx_clk); - if (ret) { - dev_err(&pdev->dev, "Could not enable AHB clock\n"); - goto err_disable_regulator; - } - if (gmac->use_internal_phy) { ret = sun8i_dwmac_power_internal_phy(netdev_priv(ndev)); if (ret) - goto err_disable_clk; + goto err_disable_regulator; } return 0; -err_disable_clk: - clk_disable_unprepare(gmac->tx_clk); err_disable_regulator: if (gmac->regulator) regulator_disable(gmac->regulator); @@ -1043,8 +1034,6 @@ static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv) if (gmac->variant->soc_has_internal_phy) sun8i_dwmac_unpower_internal_phy(gmac); - clk_disable_unprepare(gmac->tx_clk); - if (gmac->regulator) regulator_disable(gmac->regulator); } @@ -1167,12 +1156,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) return -EINVAL; } - gmac->tx_clk = devm_clk_get(dev, "stmmaceth"); - if (IS_ERR(gmac->tx_clk)) { - dev_err(dev, "Could not get TX clock\n"); - return PTR_ERR(gmac->tx_clk); - } - /* Optional regulator for PHY */ gmac->regulator = devm_regulator_get_optional(dev, "phy"); if (IS_ERR(gmac->regulator)) { @@ -1254,6 +1237,12 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) ndev = dev_get_drvdata(&pdev->dev); priv = netdev_priv(ndev); + /* the MAC is runtime suspended after stmmac_dvr_probe(), so we + * need to ensure the MAC resume back before other operations such + * as reset. + */ + pm_runtime_get_sync(&pdev->dev); + /* The mux must be registered after parent MDIO * so after stmmac_dvr_probe() */ @@ -1272,12 +1261,15 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) goto dwmac_remove; } + pm_runtime_put(&pdev->dev); + return 0; dwmac_mux: reset_control_put(gmac->rst_ephy); clk_put(gmac->ephy_clk); dwmac_remove: + pm_runtime_put_noidle(&pdev->dev); stmmac_dvr_remove(&pdev->dev); dwmac_exit: sun8i_dwmac_exit(pdev, gmac); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 5b195d5051d6..57970ae2178d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -263,7 +263,7 @@ struct stmmac_priv { u32 adv_ts; int use_riwt; int irq_wake; - spinlock_t ptp_lock; + rwlock_t ptp_lock; /* Protects auxiliary snapshot registers from concurrent access. */ struct mutex aux_ts_lock; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index a7ec9f4d46ce..22fea0f67245 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -196,9 +196,9 @@ static void timestamp_interrupt(struct stmmac_priv *priv) GMAC_TIMESTAMP_ATSNS_SHIFT; for (i = 0; i < num_snapshot; i++) { - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); get_ptptime(priv->ptpaddr, &ptp_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); event.type = PTP_CLOCK_EXTTS; event.index = 0; event.timestamp = ptp_time; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index bde76ea2deec..b745d624b2cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -938,105 +938,15 @@ static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex) priv->pause, tx_cnt); } -static void stmmac_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - __ETHTOOL_DECLARE_LINK_MODE_MASK(mac_supported) = { 0, }; - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - int tx_cnt = priv->plat->tx_queues_to_use; - int max_speed = priv->plat->max_speed; - - phylink_set(mac_supported, 10baseT_Half); - phylink_set(mac_supported, 10baseT_Full); - phylink_set(mac_supported, 100baseT_Half); - phylink_set(mac_supported, 100baseT_Full); - phylink_set(mac_supported, 1000baseT_Half); - phylink_set(mac_supported, 1000baseT_Full); - phylink_set(mac_supported, 1000baseKX_Full); - - phylink_set(mac_supported, Autoneg); - phylink_set(mac_supported, Pause); - phylink_set(mac_supported, Asym_Pause); - phylink_set_port_modes(mac_supported); - - /* Cut down 1G if asked to */ - if ((max_speed > 0) && (max_speed < 1000)) { - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); - } else if (priv->plat->has_gmac4) { - if (!max_speed || max_speed >= 2500) { - phylink_set(mac_supported, 2500baseT_Full); - phylink_set(mac_supported, 2500baseX_Full); - } - } else if (priv->plat->has_xgmac) { - if (!max_speed || (max_speed >= 2500)) { - phylink_set(mac_supported, 2500baseT_Full); - phylink_set(mac_supported, 2500baseX_Full); - } - if (!max_speed || (max_speed >= 5000)) { - phylink_set(mac_supported, 5000baseT_Full); - } - if (!max_speed || (max_speed >= 10000)) { - phylink_set(mac_supported, 10000baseSR_Full); - phylink_set(mac_supported, 10000baseLR_Full); - phylink_set(mac_supported, 10000baseER_Full); - phylink_set(mac_supported, 10000baseLRM_Full); - phylink_set(mac_supported, 10000baseT_Full); - phylink_set(mac_supported, 10000baseKX4_Full); - phylink_set(mac_supported, 10000baseKR_Full); - } - if (!max_speed || (max_speed >= 25000)) { - phylink_set(mac_supported, 25000baseCR_Full); - phylink_set(mac_supported, 25000baseKR_Full); - phylink_set(mac_supported, 25000baseSR_Full); - } - if (!max_speed || (max_speed >= 40000)) { - phylink_set(mac_supported, 40000baseKR4_Full); - phylink_set(mac_supported, 40000baseCR4_Full); - phylink_set(mac_supported, 40000baseSR4_Full); - phylink_set(mac_supported, 40000baseLR4_Full); - } - if (!max_speed || (max_speed >= 50000)) { - phylink_set(mac_supported, 50000baseCR2_Full); - phylink_set(mac_supported, 50000baseKR2_Full); - phylink_set(mac_supported, 50000baseSR2_Full); - phylink_set(mac_supported, 50000baseKR_Full); - phylink_set(mac_supported, 50000baseSR_Full); - phylink_set(mac_supported, 50000baseCR_Full); - phylink_set(mac_supported, 50000baseLR_ER_FR_Full); - phylink_set(mac_supported, 50000baseDR_Full); - } - if (!max_speed || (max_speed >= 100000)) { - phylink_set(mac_supported, 100000baseKR4_Full); - phylink_set(mac_supported, 100000baseSR4_Full); - phylink_set(mac_supported, 100000baseCR4_Full); - phylink_set(mac_supported, 100000baseLR4_ER4_Full); - phylink_set(mac_supported, 100000baseKR2_Full); - phylink_set(mac_supported, 100000baseSR2_Full); - phylink_set(mac_supported, 100000baseCR2_Full); - phylink_set(mac_supported, 100000baseLR2_ER2_FR2_Full); - phylink_set(mac_supported, 100000baseDR2_Full); - } - } - - /* Half-Duplex can only work with single queue */ - if (tx_cnt > 1) { - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 1000baseT_Half); - } - - linkmode_and(supported, supported, mac_supported); - linkmode_andnot(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mac_supported); - linkmode_andnot(state->advertising, state->advertising, mask); + if (!priv->hw->xpcs) + return NULL; - /* If PCS is supported, check which modes it supports. */ - if (priv->hw->xpcs) - xpcs_validate(priv->hw->xpcs, supported, state); + return &priv->hw->xpcs->pcs; } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, @@ -1175,7 +1085,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops stmmac_phylink_mac_ops = { - .validate = stmmac_validate, + .validate = phylink_generic_validate, + .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, @@ -1255,12 +1166,12 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); + int max_speed = priv->plat->max_speed; int mode = priv->plat->phy_interface; struct phylink *phylink; priv->phylink_config.dev = &priv->dev->dev; priv->phylink_config.type = PHYLINK_NETDEV; - priv->phylink_config.pcs_poll = true; if (priv->plat->mdio_bus_data) priv->phylink_config.ovr_an_inband = mdio_bus_data->xpcs_an_inband; @@ -1268,14 +1179,50 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) if (!fwnode) fwnode = dev_fwnode(priv->device); + /* Set the platform/firmware specified interface mode */ + __set_bit(mode, priv->phylink_config.supported_interfaces); + + /* If we have an xpcs, it defines which PHY interfaces are supported. */ + if (priv->hw->xpcs) + xpcs_get_interfaces(priv->hw->xpcs, + priv->phylink_config.supported_interfaces); + + priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; + + if (!max_speed || max_speed >= 1000) + priv->phylink_config.mac_capabilities |= MAC_1000; + + if (priv->plat->has_gmac4) { + if (!max_speed || max_speed >= 2500) + priv->phylink_config.mac_capabilities |= MAC_2500FD; + } else if (priv->plat->has_xgmac) { + if (!max_speed || max_speed >= 2500) + priv->phylink_config.mac_capabilities |= MAC_2500FD; + if (!max_speed || max_speed >= 5000) + priv->phylink_config.mac_capabilities |= MAC_5000FD; + if (!max_speed || max_speed >= 10000) + priv->phylink_config.mac_capabilities |= MAC_10000FD; + if (!max_speed || max_speed >= 25000) + priv->phylink_config.mac_capabilities |= MAC_25000FD; + if (!max_speed || max_speed >= 40000) + priv->phylink_config.mac_capabilities |= MAC_40000FD; + if (!max_speed || max_speed >= 50000) + priv->phylink_config.mac_capabilities |= MAC_50000FD; + if (!max_speed || max_speed >= 100000) + priv->phylink_config.mac_capabilities |= MAC_100000FD; + } + + /* Half-Duplex can only work with single queue */ + if (priv->plat->tx_queues_to_use > 1) + priv->phylink_config.mac_capabilities &= + ~(MAC_10HD | MAC_100HD | MAC_1000HD); + phylink = phylink_create(&priv->phylink_config, fwnode, mode, &stmmac_phylink_mac_ops); if (IS_ERR(phylink)) return PTR_ERR(phylink); - if (priv->hw->xpcs) - phylink_set_pcs(phylink, &priv->hw->xpcs->pcs); - priv->phylink = phylink; return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 1c9f02f9c317..e45fb191d8e6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -39,9 +39,9 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb) diff = div_u64(adj, 1000000000ULL); addend = neg_adj ? (addend - diff) : (addend + diff); - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); stmmac_config_addend(priv, priv->ptpaddr, addend); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); return 0; } @@ -86,9 +86,9 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) mutex_unlock(&priv->plat->est->lock); } - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); /* Caculate new basetime and re-configured EST after PTP time adjust. */ if (est_rst) { @@ -137,9 +137,9 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts) unsigned long flags; u64 ns = 0; - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_systime(priv, priv->ptpaddr, &ns); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); *ts = ns_to_timespec64(ns); @@ -162,9 +162,9 @@ static int stmmac_set_time(struct ptp_clock_info *ptp, container_of(ptp, struct stmmac_priv, ptp_clock_ops); unsigned long flags; - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); stmmac_init_systime(priv, priv->ptpaddr, ts->tv_sec, ts->tv_nsec); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); return 0; } @@ -194,12 +194,12 @@ static int stmmac_enable(struct ptp_clock_info *ptp, cfg->period.tv_sec = rq->perout.period.sec; cfg->period.tv_nsec = rq->perout.period.nsec; - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); ret = stmmac_flex_pps_config(priv, priv->ioaddr, rq->perout.index, cfg, on, priv->sub_second_inc, priv->systime_flags); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); break; case PTP_CLK_REQ_EXTTS: priv->plat->ext_snapshot_en = on; @@ -314,7 +314,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv) stmmac_ptp_clock_ops.n_per_out = priv->dma_cap.pps_out_num; stmmac_ptp_clock_ops.n_ext_ts = priv->dma_cap.aux_snapshot_n; - spin_lock_init(&priv->ptp_lock); + rwlock_init(&priv->ptp_lock); mutex_init(&priv->aux_ts_lock); priv->ptp_clock_ops = stmmac_ptp_clock_ops; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index be3cb63675a5..9f1759593b94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -1777,9 +1777,9 @@ static int stmmac_test_tbs(struct stmmac_priv *priv) if (ret) return ret; - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_systime(priv, priv->ptpaddr, &curr_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); if (!curr_time) { ret = -EOPNOTSUPP; @@ -1799,9 +1799,9 @@ static int stmmac_test_tbs(struct stmmac_priv *priv) goto fail_disable; /* Check if expected time has elapsed */ - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_systime(priv, priv->ptpaddr, &curr_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); if ((curr_time - start_time) < STMMAC_TBS_LT_OFFSET) ret = -EINVAL; diff --git a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c index 599708a3e81d..d4c56da98a6a 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c +++ b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c @@ -237,15 +237,11 @@ static int am65_cpsw_port_vlans_add(struct am65_cpsw_port *port, { bool untag = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; struct net_device *orig_dev = vlan->obj.orig_dev; - bool cpu_port = netif_is_bridge_master(orig_dev); bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; netdev_dbg(port->ndev, "VID add: %s: vid:%u flags:%X\n", port->ndev->name, vlan->vid, vlan->flags); - if (cpu_port && !(vlan->flags & BRIDGE_VLAN_INFO_BRENTRY)) - return 0; - return am65_cpsw_port_vlan_add(port, untag, pvid, vlan->vid, orig_dev); } diff --git a/drivers/net/ethernet/ti/cpsw_switchdev.c b/drivers/net/ethernet/ti/cpsw_switchdev.c index a7d97d429e06..ce85f7610273 100644 --- a/drivers/net/ethernet/ti/cpsw_switchdev.c +++ b/drivers/net/ethernet/ti/cpsw_switchdev.c @@ -252,15 +252,11 @@ static int cpsw_port_vlans_add(struct cpsw_priv *priv, { bool untag = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; struct net_device *orig_dev = vlan->obj.orig_dev; - bool cpu_port = netif_is_bridge_master(orig_dev); bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; dev_dbg(priv->dev, "VID add: %s: vid:%u flags:%X\n", priv->ndev->name, vlan->vid, vlan->flags); - if (cpu_port && !(vlan->flags & BRIDGE_VLAN_INFO_BRENTRY)) - return 0; - return cpsw_port_vlan_add(priv, untag, pvid, vlan->vid, orig_dev); } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 5b4d153b1492..40108968b350 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -386,6 +386,7 @@ struct axidma_bd { * @phylink: Pointer to phylink instance * @phylink_config: phylink configuration settings * @pcs_phy: Reference to PCS/PMA PHY if used + * @pcs: phylink pcs structure for PCS PHY * @switch_x_sgmii: Whether switchable 1000BaseX/SGMII mode is enabled in the core * @axi_clk: AXI4-Lite bus clock * @misc_clks: Misc ethernet clocks (AXI4-Stream, Ref, MGT clocks) @@ -434,6 +435,7 @@ struct axienet_local { struct phylink_config phylink_config; struct mdio_device *pcs_phy; + struct phylink_pcs pcs; bool switch_x_sgmii; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 377c94ec2486..de0a6372ae0e 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1537,78 +1537,78 @@ static const struct ethtool_ops axienet_ethtool_ops = { .nway_reset = axienet_ethtools_nway_reset, }; -static void axienet_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) +static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs) { - struct net_device *ndev = to_net_dev(config->dev); - struct axienet_local *lp = netdev_priv(ndev); + return container_of(pcs, struct axienet_local, pcs); +} - switch (state->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - phylink_mii_c22_pcs_get_state(lp->pcs_phy, state); - break; - default: - break; - } +static void axienet_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; + + phylink_mii_c22_pcs_get_state(pcs_phy, state); } -static void axienet_mac_an_restart(struct phylink_config *config) +static void axienet_pcs_an_restart(struct phylink_pcs *pcs) { - struct net_device *ndev = to_net_dev(config->dev); - struct axienet_local *lp = netdev_priv(ndev); + struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; - phylink_mii_c22_pcs_an_restart(lp->pcs_phy); + phylink_mii_c22_pcs_an_restart(pcs_phy); } -static int axienet_mac_prepare(struct phylink_config *config, unsigned int mode, - phy_interface_t iface) +static int axienet_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) { - struct net_device *ndev = to_net_dev(config->dev); + struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; + struct net_device *ndev = pcs_to_axienet_local(pcs)->ndev; struct axienet_local *lp = netdev_priv(ndev); int ret; - switch (iface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - if (!lp->switch_x_sgmii) - return 0; - - ret = mdiobus_write(lp->pcs_phy->bus, - lp->pcs_phy->addr, - XLNX_MII_STD_SELECT_REG, - iface == PHY_INTERFACE_MODE_SGMII ? + if (lp->switch_x_sgmii) { + ret = mdiodev_write(pcs_phy, XLNX_MII_STD_SELECT_REG, + interface == PHY_INTERFACE_MODE_SGMII ? XLNX_MII_STD_SELECT_SGMII : 0); - if (ret < 0) - netdev_warn(ndev, "Failed to switch PHY interface: %d\n", + if (ret < 0) { + netdev_warn(ndev, + "Failed to switch PHY interface: %d\n", ret); - return ret; - default: - return 0; + return ret; + } } + + ret = phylink_mii_c22_pcs_config(pcs_phy, mode, interface, advertising); + if (ret < 0) + netdev_warn(ndev, "Failed to configure PCS: %d\n", ret); + + return ret; } -static void axienet_mac_config(struct phylink_config *config, unsigned int mode, - const struct phylink_link_state *state) +static const struct phylink_pcs_ops axienet_pcs_ops = { + .pcs_get_state = axienet_pcs_get_state, + .pcs_config = axienet_pcs_config, + .pcs_an_restart = axienet_pcs_an_restart, +}; + +static struct phylink_pcs *axienet_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { struct net_device *ndev = to_net_dev(config->dev); struct axienet_local *lp = netdev_priv(ndev); - int ret; - switch (state->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - ret = phylink_mii_c22_pcs_config(lp->pcs_phy, mode, - state->interface, - state->advertising); - if (ret < 0) - netdev_warn(ndev, "Failed to configure PCS: %d\n", - ret); - break; + if (interface == PHY_INTERFACE_MODE_1000BASEX || + interface == PHY_INTERFACE_MODE_SGMII) + return &lp->pcs; - default: - break; - } + return NULL; +} + +static void axienet_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ + /* nothing meaningful to do */ } static void axienet_mac_link_down(struct phylink_config *config, @@ -1663,9 +1663,7 @@ static void axienet_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops axienet_phylink_ops = { .validate = phylink_generic_validate, - .mac_pcs_get_state = axienet_mac_pcs_get_state, - .mac_an_restart = axienet_mac_an_restart, - .mac_prepare = axienet_mac_prepare, + .mac_select_pcs = axienet_mac_select_pcs, .mac_config = axienet_mac_config, .mac_link_down = axienet_mac_link_down, .mac_link_up = axienet_mac_link_up, @@ -2079,12 +2077,12 @@ static int axienet_probe(struct platform_device *pdev) ret = -EPROBE_DEFER; goto cleanup_mdio; } - lp->phylink_config.pcs_poll = true; + lp->pcs.ops = &axienet_pcs_ops; + lp->pcs.poll = true; } lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; - lp->phylink_config.legacy_pre_march2020 = true; lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD; diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index ebd287039a54..5805e4a56385 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -1514,10 +1514,9 @@ acpi_find_extended_socket_device(acpi_handle obj_handle, u32 level, { struct acpi_device *device; bool *found = context; - int result; - result = acpi_bus_get_device(obj_handle, &device); - if (result) + device = acpi_fetch_acpi_dev(obj_handle); + if (!device) return AE_OK; if (strcmp(acpi_device_hid(device), ACPI_MOTHERBOARD_RESOURCE_HID)) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index c1fdd721a730..a895ff756093 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -925,7 +925,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, } skb->protocol = eth_type_trans(skb, geneve->dev); - netif_rx(skb); + __netif_rx(skb); dst_release(&rt->dst); return -EMSGSIZE; } @@ -1021,7 +1021,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, } skb->protocol = eth_type_trans(skb, geneve->dev); - netif_rx(skb); + __netif_rx(skb); dst_release(dst); return -EMSGSIZE; } diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 24e5c54d06c1..bf087171bcf0 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -207,7 +207,7 @@ static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, dev_sw_netstats_rx_add(pctx->dev, skb->len); - netif_rx(skb); + __netif_rx(skb); return 0; err: diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index afa81a9480cc..e675d1016c3c 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -154,19 +154,15 @@ static void free_netvsc_device(struct rcu_head *head) kfree(nvdev->extension); - if (nvdev->recv_original_buf) { - hv_unmap_memory(nvdev->recv_buf); + if (nvdev->recv_original_buf) vfree(nvdev->recv_original_buf); - } else { + else vfree(nvdev->recv_buf); - } - if (nvdev->send_original_buf) { - hv_unmap_memory(nvdev->send_buf); + if (nvdev->send_original_buf) vfree(nvdev->send_original_buf); - } else { + else vfree(nvdev->send_buf); - } bitmap_free(nvdev->send_section_map); @@ -765,6 +761,12 @@ void netvsc_device_remove(struct hv_device *device) netvsc_teardown_send_gpadl(device, net_device, ndev); } + if (net_device->recv_original_buf) + hv_unmap_memory(net_device->recv_buf); + + if (net_device->send_original_buf) + hv_unmap_memory(net_device->send_buf); + /* Release all resources */ free_netvsc_device_rcu(net_device); } @@ -1821,6 +1823,12 @@ cleanup: netif_napi_del(&net_device->chan_table[0].napi); cleanup2: + if (net_device->recv_original_buf) + hv_unmap_memory(net_device->recv_buf); + + if (net_device->send_original_buf) + hv_unmap_memory(net_device->send_buf); + free_netvsc_device(&net_device->rcu); return ERR_PTR(ret); diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 2f5e7b31032a..07bafbf94680 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -74,81 +74,6 @@ struct atusb_chip_data { int (*set_txpower)(struct ieee802154_hw*, s32); }; -/* ----- USB commands without data ----------------------------------------- */ - -/* To reduce the number of error checks in the code, we record the first error - * in atusb->err and reject all subsequent requests until the error is cleared. - */ - -static int atusb_control_msg(struct atusb *atusb, unsigned int pipe, - __u8 request, __u8 requesttype, - __u16 value, __u16 index, - void *data, __u16 size, int timeout) -{ - struct usb_device *usb_dev = atusb->usb_dev; - int ret; - - if (atusb->err) - return atusb->err; - - ret = usb_control_msg(usb_dev, pipe, request, requesttype, - value, index, data, size, timeout); - if (ret < size) { - ret = ret < 0 ? ret : -ENODATA; - - atusb->err = ret; - dev_err(&usb_dev->dev, - "%s: req 0x%02x val 0x%x idx 0x%x, error %d\n", - __func__, request, value, index, ret); - } - return ret; -} - -static int atusb_command(struct atusb *atusb, u8 cmd, u8 arg) -{ - struct usb_device *usb_dev = atusb->usb_dev; - - dev_dbg(&usb_dev->dev, "%s: cmd = 0x%x\n", __func__, cmd); - return atusb_control_msg(atusb, usb_sndctrlpipe(usb_dev, 0), - cmd, ATUSB_REQ_TO_DEV, arg, 0, NULL, 0, 1000); -} - -static int atusb_write_reg(struct atusb *atusb, u8 reg, u8 value) -{ - struct usb_device *usb_dev = atusb->usb_dev; - - dev_dbg(&usb_dev->dev, "%s: 0x%02x <- 0x%02x\n", __func__, reg, value); - return atusb_control_msg(atusb, usb_sndctrlpipe(usb_dev, 0), - ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, - value, reg, NULL, 0, 1000); -} - -static int atusb_read_reg(struct atusb *atusb, u8 reg) -{ - struct usb_device *usb_dev = atusb->usb_dev; - int ret; - u8 *buffer; - u8 value; - - buffer = kmalloc(1, GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - dev_dbg(&usb_dev->dev, "%s: reg = 0x%x\n", __func__, reg); - ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), - ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, - 0, reg, buffer, 1, 1000); - - if (ret >= 0) { - value = buffer[0]; - kfree(buffer); - return value; - } else { - kfree(buffer); - return ret; - } -} - static int atusb_write_subreg(struct atusb *atusb, u8 reg, u8 mask, u8 shift, u8 value) { @@ -158,7 +83,10 @@ static int atusb_write_subreg(struct atusb *atusb, u8 reg, u8 mask, dev_dbg(&usb_dev->dev, "%s: 0x%02x <- 0x%02x\n", __func__, reg, value); - orig = atusb_read_reg(atusb, reg); + ret = usb_control_msg_recv(usb_dev, 0, ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, + 0, reg, &orig, 1, 1000, GFP_KERNEL); + if (ret < 0) + return ret; /* Write the value only into that part of the register which is allowed * by the mask. All other bits stay as before. @@ -167,7 +95,8 @@ static int atusb_write_subreg(struct atusb *atusb, u8 reg, u8 mask, tmp |= (value << shift) & mask; if (tmp != orig) - ret = atusb_write_reg(atusb, reg, tmp); + ret = usb_control_msg_send(usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + tmp, reg, NULL, 0, 1000, GFP_KERNEL); return ret; } @@ -176,12 +105,16 @@ static int atusb_read_subreg(struct atusb *lp, unsigned int addr, unsigned int mask, unsigned int shift) { - int rc; + int reg, ret; + + ret = usb_control_msg_recv(lp->usb_dev, 0, ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, + 0, addr, ®, 1, 1000, GFP_KERNEL); + if (ret < 0) + return ret; - rc = atusb_read_reg(lp, addr); - rc = (rc & mask) >> shift; + reg = (reg & mask) >> shift; - return rc; + return reg; } static int atusb_get_and_clear_error(struct atusb *atusb) @@ -419,16 +352,22 @@ static int atusb_set_hw_addr_filt(struct ieee802154_hw *hw, u16 addr = le16_to_cpu(filt->short_addr); dev_vdbg(dev, "%s called for saddr\n", __func__); - atusb_write_reg(atusb, RG_SHORT_ADDR_0, addr); - atusb_write_reg(atusb, RG_SHORT_ADDR_1, addr >> 8); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + addr, RG_SHORT_ADDR_0, NULL, 0, 1000, GFP_KERNEL); + + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + addr >> 8, RG_SHORT_ADDR_1, NULL, 0, 1000, GFP_KERNEL); } if (changed & IEEE802154_AFILT_PANID_CHANGED) { u16 pan = le16_to_cpu(filt->pan_id); dev_vdbg(dev, "%s called for pan id\n", __func__); - atusb_write_reg(atusb, RG_PAN_ID_0, pan); - atusb_write_reg(atusb, RG_PAN_ID_1, pan >> 8); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + pan, RG_PAN_ID_0, NULL, 0, 1000, GFP_KERNEL); + + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + pan >> 8, RG_PAN_ID_1, NULL, 0, 1000, GFP_KERNEL); } if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) { @@ -437,7 +376,9 @@ static int atusb_set_hw_addr_filt(struct ieee802154_hw *hw, memcpy(addr, &filt->ieee_addr, IEEE802154_EXTENDED_ADDR_LEN); dev_vdbg(dev, "%s called for IEEE addr\n", __func__); for (i = 0; i < 8; i++) - atusb_write_reg(atusb, RG_IEEE_ADDR_0 + i, addr[i]); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + addr[i], RG_IEEE_ADDR_0 + i, NULL, 0, + 1000, GFP_KERNEL); } if (changed & IEEE802154_AFILT_PANC_CHANGED) { @@ -459,7 +400,8 @@ static int atusb_start(struct ieee802154_hw *hw) dev_dbg(&usb_dev->dev, "%s\n", __func__); schedule_delayed_work(&atusb->work, 0); - atusb_command(atusb, ATUSB_RX_MODE, 1); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_RX_MODE, ATUSB_REQ_TO_DEV, 1, 0, + NULL, 0, 1000, GFP_KERNEL); ret = atusb_get_and_clear_error(atusb); if (ret < 0) usb_kill_anchored_urbs(&atusb->idle_urbs); @@ -473,7 +415,8 @@ static void atusb_stop(struct ieee802154_hw *hw) dev_dbg(&usb_dev->dev, "%s\n", __func__); usb_kill_anchored_urbs(&atusb->idle_urbs); - atusb_command(atusb, ATUSB_RX_MODE, 0); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_RX_MODE, ATUSB_REQ_TO_DEV, 0, 0, + NULL, 0, 1000, GFP_KERNEL); atusb_get_and_clear_error(atusb); } @@ -580,9 +523,11 @@ atusb_set_cca_mode(struct ieee802154_hw *hw, const struct wpan_phy_cca *cca) static int hulusb_set_cca_ed_level(struct atusb *lp, int rssi_base_val) { - unsigned int cca_ed_thres; + int cca_ed_thres; cca_ed_thres = atusb_read_subreg(lp, SR_CCA_ED_THRES); + if (cca_ed_thres < 0) + return cca_ed_thres; switch (rssi_base_val) { case -98: @@ -799,18 +744,13 @@ static int atusb_get_and_show_revision(struct atusb *atusb) { struct usb_device *usb_dev = atusb->usb_dev; char *hw_name; - unsigned char *buffer; + unsigned char buffer[3]; int ret; - buffer = kmalloc(3, GFP_KERNEL); - if (!buffer) - return -ENOMEM; - /* Get a couple of the ATMega Firmware values */ - ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), - ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0, - buffer, 3, 1000); - if (ret >= 0) { + ret = usb_control_msg_recv(atusb->usb_dev, 0, ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0, + buffer, 3, 1000, GFP_KERNEL); + if (!ret) { atusb->fw_ver_maj = buffer[0]; atusb->fw_ver_min = buffer[1]; atusb->fw_hw_type = buffer[2]; @@ -849,7 +789,6 @@ static int atusb_get_and_show_revision(struct atusb *atusb) dev_info(&usb_dev->dev, "Please update to version 0.2 or newer"); } - kfree(buffer); return ret; } @@ -863,7 +802,6 @@ static int atusb_get_and_show_build(struct atusb *atusb) if (!build) return -ENOMEM; - /* We cannot call atusb_control_msg() here, since this request may read various length data */ ret = usb_control_msg(atusb->usb_dev, usb_rcvctrlpipe(usb_dev, 0), ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0, build, ATUSB_BUILD_SIZE, 1000); if (ret >= 0) { @@ -881,14 +819,27 @@ static int atusb_get_and_conf_chip(struct atusb *atusb) u8 man_id_0, man_id_1, part_num, version_num; const char *chip; struct ieee802154_hw *hw = atusb->hw; + int ret; - man_id_0 = atusb_read_reg(atusb, RG_MAN_ID_0); - man_id_1 = atusb_read_reg(atusb, RG_MAN_ID_1); - part_num = atusb_read_reg(atusb, RG_PART_NUM); - version_num = atusb_read_reg(atusb, RG_VERSION_NUM); + ret = usb_control_msg_recv(usb_dev, 0, ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, + 0, RG_MAN_ID_0, &man_id_0, 1, 1000, GFP_KERNEL); + if (ret < 0) + return ret; - if (atusb->err) - return atusb->err; + ret = usb_control_msg_recv(usb_dev, 0, ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, + 0, RG_MAN_ID_1, &man_id_1, 1, 1000, GFP_KERNEL); + if (ret < 0) + return ret; + + ret = usb_control_msg_recv(usb_dev, 0, ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, + 0, RG_PART_NUM, &part_num, 1, 1000, GFP_KERNEL); + if (ret < 0) + return ret; + + ret = usb_control_msg_recv(usb_dev, 0, ATUSB_REG_READ, ATUSB_REQ_FROM_DEV, + 0, RG_VERSION_NUM, &version_num, 1, 1000, GFP_KERNEL); + if (ret < 0) + return ret; hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT | IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_CSMA_PARAMS; @@ -969,7 +920,7 @@ fail: static int atusb_set_extended_addr(struct atusb *atusb) { struct usb_device *usb_dev = atusb->usb_dev; - unsigned char *buffer; + unsigned char buffer[IEEE802154_EXTENDED_ADDR_LEN]; __le64 extended_addr; u64 addr; int ret; @@ -982,18 +933,12 @@ static int atusb_set_extended_addr(struct atusb *atusb) return 0; } - buffer = kmalloc(IEEE802154_EXTENDED_ADDR_LEN, GFP_KERNEL); - if (!buffer) - return -ENOMEM; - /* Firmware is new enough so we fetch the address from EEPROM */ - ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), - ATUSB_EUI64_READ, ATUSB_REQ_FROM_DEV, 0, 0, - buffer, IEEE802154_EXTENDED_ADDR_LEN, 1000); + ret = usb_control_msg_recv(atusb->usb_dev, 0, ATUSB_EUI64_READ, ATUSB_REQ_FROM_DEV, 0, 0, + buffer, IEEE802154_EXTENDED_ADDR_LEN, 1000, GFP_KERNEL); if (ret < 0) { dev_err(&usb_dev->dev, "failed to fetch extended address, random address set\n"); ieee802154_random_extended_addr(&atusb->hw->phy->perm_extended_addr); - kfree(buffer); return ret; } @@ -1009,7 +954,6 @@ static int atusb_set_extended_addr(struct atusb *atusb) &addr); } - kfree(buffer); return ret; } @@ -1051,7 +995,8 @@ static int atusb_probe(struct usb_interface *interface, hw->parent = &usb_dev->dev; - atusb_command(atusb, ATUSB_RF_RESET, 0); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_RF_RESET, ATUSB_REQ_TO_DEV, 0, 0, + NULL, 0, 1000, GFP_KERNEL); atusb_get_and_conf_chip(atusb); atusb_get_and_show_revision(atusb); atusb_get_and_show_build(atusb); @@ -1076,7 +1021,9 @@ static int atusb_probe(struct usb_interface *interface, * explicitly. Any resets after that will send us straight to TRX_OFF, * making the command below redundant. */ - atusb_write_reg(atusb, RG_TRX_STATE, STATE_FORCE_TRX_OFF); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + STATE_FORCE_TRX_OFF, RG_TRX_STATE, NULL, 0, 1000, GFP_KERNEL); + msleep(1); /* reset => TRX_OFF, tTR13 = 37 us */ #if 0 @@ -1104,7 +1051,8 @@ static int atusb_probe(struct usb_interface *interface, atusb_write_subreg(atusb, SR_RX_SAFE_MODE, 1); #endif - atusb_write_reg(atusb, RG_IRQ_MASK, 0xff); + usb_control_msg_send(atusb->usb_dev, 0, ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV, + 0xff, RG_IRQ_MASK, NULL, 0, 1000, GFP_KERNEL); ret = atusb_get_and_clear_error(atusb); if (!ret) diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 36f1c5aa98fc..38c217bd7c82 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -791,7 +791,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev, phy->idx = idx; INIT_LIST_HEAD(&phy->edges); - hw->flags = IEEE802154_HW_PROMISCUOUS; + hw->flags = IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_RX_DROP_BAD_CKSUM; hw->parent = dev; err = ieee802154_register_hw(hw); diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 1544564bc283..87e1d43c118c 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -320,6 +320,17 @@ gsi_trans_tre_release(struct gsi_trans_info *trans_info, u32 tre_count) atomic_add(tre_count, &trans_info->tre_avail); } +/* Return true if no transactions are allocated, false otherwise */ +bool gsi_channel_trans_idle(struct gsi *gsi, u32 channel_id) +{ + u32 tre_max = gsi_channel_tre_max(gsi, channel_id); + struct gsi_trans_info *trans_info; + + trans_info = &gsi->channel[channel_id].trans_info; + + return atomic_read(&trans_info->tre_avail) == tre_max; +} + /* Allocate a GSI transaction on a channel */ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, u32 tre_count, diff --git a/drivers/net/ipa/gsi_trans.h b/drivers/net/ipa/gsi_trans.h index 17fd1822d8a9..af379b49299e 100644 --- a/drivers/net/ipa/gsi_trans.h +++ b/drivers/net/ipa/gsi_trans.h @@ -130,6 +130,16 @@ void *gsi_trans_pool_alloc_dma(struct gsi_trans_pool *pool, dma_addr_t *addr); void gsi_trans_pool_exit_dma(struct device *dev, struct gsi_trans_pool *pool); /** + * gsi_channel_trans_idle() - Return whether no transactions are allocated + * @gsi: GSI pointer + * @channel_id: Channel the transaction is associated with + * + * Return: True if no transactions are allocated, false otherwise + * + */ +bool gsi_channel_trans_idle(struct gsi *gsi, u32 channel_id); + +/** * gsi_channel_trans_alloc() - Allocate a GSI transaction on a channel * @gsi: GSI pointer * @channel_id: Channel the transaction is associated with diff --git a/drivers/net/ipa/ipa_data-v3.1.c b/drivers/net/ipa/ipa_data-v3.1.c index 06ddb85f39b2..8ff351aefd23 100644 --- a/drivers/net/ipa/ipa_data-v3.1.c +++ b/drivers/net/ipa/ipa_data-v3.1.c @@ -101,6 +101,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -148,6 +149,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v3.5.1.c b/drivers/net/ipa/ipa_data-v3.5.1.c index 760c22bbdf70..d1c466abddb2 100644 --- a/drivers/net/ipa/ipa_data-v3.5.1.c +++ b/drivers/net/ipa/ipa_data-v3.5.1.c @@ -92,6 +92,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -140,6 +141,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.11.c b/drivers/net/ipa/ipa_data-v4.11.c index fea91451a0c3..b1991cc6f0ca 100644 --- a/drivers/net/ipa/ipa_data-v4.11.c +++ b/drivers/net/ipa/ipa_data-v4.11.c @@ -86,6 +86,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -133,6 +134,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 32768, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.2.c b/drivers/net/ipa/ipa_data-v4.2.c index 2a231e79d5e1..1190a43e8743 100644 --- a/drivers/net/ipa/ipa_data-v4.2.c +++ b/drivers/net/ipa/ipa_data-v4.2.c @@ -82,6 +82,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -130,6 +131,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.5.c b/drivers/net/ipa/ipa_data-v4.5.c index 2da2c4194f2e..944f72b0f285 100644 --- a/drivers/net/ipa/ipa_data-v4.5.c +++ b/drivers/net/ipa/ipa_data-v4.5.c @@ -95,6 +95,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -142,6 +143,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.9.c b/drivers/net/ipa/ipa_data-v4.9.c index 2421b5abb5d4..16786bff7ef8 100644 --- a/drivers/net/ipa/ipa_data-v4.9.c +++ b/drivers/net/ipa/ipa_data-v4.9.c @@ -87,6 +87,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -134,6 +135,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data.h b/drivers/net/ipa/ipa_data.h index 6d329e9ce5d2..dbbeecf6df29 100644 --- a/drivers/net/ipa/ipa_data.h +++ b/drivers/net/ipa/ipa_data.h @@ -112,6 +112,7 @@ struct ipa_endpoint_tx_data { /** * struct ipa_endpoint_rx_data - configuration data for RX endpoints + * @buffer_size: requested receive buffer size (bytes) * @pad_align: power-of-2 boundary to which packet payload is aligned * @aggr_close_eof: whether aggregation closes on end-of-frame * @@ -125,6 +126,7 @@ struct ipa_endpoint_tx_data { * a "frame" consisting of several transfers has ended. */ struct ipa_endpoint_rx_data { + u32 buffer_size; u32 pad_align; bool aggr_close_eof; }; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 68291a3efd04..888e94278a84 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -25,10 +25,8 @@ #define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) -#define IPA_REPLENISH_BATCH 16 - -/* RX buffer is 1 page (or a power-of-2 contiguous pages) */ -#define IPA_RX_BUFFER_SIZE 8192 /* PAGE_SIZE > 4096 wastes a LOT */ +/* Hardware is told about receive buffers once a "batch" has been queued */ +#define IPA_REPLENISH_BATCH 16 /* Must be non-zero */ /* The amount of RX buffer space consumed by standard skb overhead */ #define IPA_RX_BUFFER_OVERHEAD (PAGE_SIZE - SKB_MAX_ORDER(NET_SKB_PAD, 0)) @@ -75,6 +73,14 @@ struct ipa_status { #define IPA_STATUS_FLAGS1_RT_RULE_ID_FMASK GENMASK(31, 22) #define IPA_STATUS_FLAGS2_TAG_FMASK GENMASK_ULL(63, 16) +static u32 aggr_byte_limit_max(enum ipa_version version) +{ + if (version < IPA_VERSION_4_5) + return field_max(aggr_byte_limit_fmask(true)); + + return field_max(aggr_byte_limit_fmask(false)); +} + static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *all_data, const struct ipa_gsi_endpoint_data *data) @@ -87,6 +93,9 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, return true; if (!data->toward_ipa) { + u32 buffer_size; + u32 limit; + if (data->endpoint.filter_support) { dev_err(dev, "filtering not supported for " "RX endpoint %u\n", @@ -94,6 +103,41 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, return false; } + /* Nothing more to check for non-AP RX */ + if (data->ee_id != GSI_EE_AP) + return true; + + buffer_size = data->endpoint.config.rx.buffer_size; + /* The buffer size must hold an MTU plus overhead */ + limit = IPA_MTU + IPA_RX_BUFFER_OVERHEAD; + if (buffer_size < limit) { + dev_err(dev, "RX buffer size too small for RX endpoint %u (%u < %u)\n", + data->endpoint_id, buffer_size, limit); + return false; + } + + /* For an endpoint supporting receive aggregation, the + * aggregation byte limit defines the point at which an + * aggregation window will close. It is programmed into the + * IPA hardware as a number of KB. We don't use "hard byte + * limit" aggregation, so we need to supply enough space in + * a receive buffer to hold a complete MTU plus normal skb + * overhead *after* that aggregation byte limit has been + * crossed. + * + * This check just ensures the receive buffer size doesn't + * exceed what's representable in the aggregation limit field. + */ + if (data->endpoint.config.aggregation) { + limit += SZ_1K * aggr_byte_limit_max(ipa->version); + if (buffer_size > limit) { + dev_err(dev, "RX buffer size too large for aggregated RX endpoint %u (%u > %u)\n", + data->endpoint_id, buffer_size, limit); + + return false; + } + } + return true; /* Nothing more to check for RX */ } @@ -156,21 +200,12 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, return true; } -static u32 aggr_byte_limit_max(enum ipa_version version) -{ - if (version < IPA_VERSION_4_5) - return field_max(aggr_byte_limit_fmask(true)); - - return field_max(aggr_byte_limit_fmask(false)); -} - static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *data) { const struct ipa_gsi_endpoint_data *dp = data; struct device *dev = &ipa->pdev->dev; enum ipa_endpoint_name name; - u32 limit; if (count > IPA_ENDPOINT_COUNT) { dev_err(dev, "too many endpoints specified (%u > %u)\n", @@ -178,26 +213,6 @@ static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count, return false; } - /* The aggregation byte limit defines the point at which an - * aggregation window will close. It is programmed into the - * IPA hardware as a number of KB. We don't use "hard byte - * limit" aggregation, which means that we need to supply - * enough space in a receive buffer to hold a complete MTU - * plus normal skb overhead *after* that aggregation byte - * limit has been crossed. - * - * This check ensures we don't define a receive buffer size - * that would exceed what we can represent in the field that - * is used to program its size. - */ - limit = aggr_byte_limit_max(ipa->version) * SZ_1K; - limit += IPA_MTU + IPA_RX_BUFFER_OVERHEAD; - if (limit < IPA_RX_BUFFER_SIZE) { - dev_err(dev, "buffer size too big for aggregation (%u > %u)\n", - IPA_RX_BUFFER_SIZE, limit); - return false; - } - /* Make sure needed endpoints have defined data */ if (ipa_gsi_endpoint_data_empty(&data[IPA_ENDPOINT_AP_COMMAND_TX])) { dev_err(dev, "command TX endpoint not defined\n"); @@ -723,13 +738,15 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) if (endpoint->data->aggregation) { if (!endpoint->toward_ipa) { + const struct ipa_endpoint_rx_data *rx_data; bool close_eof; u32 limit; + rx_data = &endpoint->data->rx; val |= u32_encode_bits(IPA_ENABLE_AGGR, AGGR_EN_FMASK); val |= u32_encode_bits(IPA_GENERIC, AGGR_TYPE_FMASK); - limit = ipa_aggr_size_kb(IPA_RX_BUFFER_SIZE); + limit = ipa_aggr_size_kb(rx_data->buffer_size); val |= aggr_byte_limit_encoded(version, limit); limit = IPA_AGGR_TIME_LIMIT; @@ -737,7 +754,7 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) /* AGGR_PKT_LIMIT is 0 (unlimited) */ - close_eof = endpoint->data->rx.aggr_close_eof; + close_eof = rx_data->aggr_close_eof; val |= aggr_sw_eof_active_encoded(version, close_eof); /* AGGR_HARD_BYTE_LIMIT_ENABLE is 0 */ @@ -1020,134 +1037,98 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) iowrite32(val, ipa->reg_virt + offset); } -static int ipa_endpoint_replenish_one(struct ipa_endpoint *endpoint) +static int ipa_endpoint_replenish_one(struct ipa_endpoint *endpoint, + struct gsi_trans *trans) { - struct gsi_trans *trans; - bool doorbell = false; struct page *page; + u32 buffer_size; u32 offset; u32 len; int ret; - page = dev_alloc_pages(get_order(IPA_RX_BUFFER_SIZE)); + buffer_size = endpoint->data->rx.buffer_size; + page = dev_alloc_pages(get_order(buffer_size)); if (!page) return -ENOMEM; - trans = ipa_endpoint_trans_alloc(endpoint, 1); - if (!trans) - goto err_free_pages; - /* Offset the buffer to make space for skb headroom */ offset = NET_SKB_PAD; - len = IPA_RX_BUFFER_SIZE - offset; + len = buffer_size - offset; ret = gsi_trans_page_add(trans, page, len, offset); if (ret) - goto err_trans_free; - trans->data = page; /* transaction owns page now */ - - if (++endpoint->replenish_ready == IPA_REPLENISH_BATCH) { - doorbell = true; - endpoint->replenish_ready = 0; - } - - gsi_trans_commit(trans, doorbell); - - return 0; - -err_trans_free: - gsi_trans_free(trans); -err_free_pages: - __free_pages(page, get_order(IPA_RX_BUFFER_SIZE)); + __free_pages(page, get_order(buffer_size)); + else + trans->data = page; /* transaction owns page now */ - return -ENOMEM; + return ret; } /** * ipa_endpoint_replenish() - Replenish endpoint receive buffers * @endpoint: Endpoint to be replenished - * @add_one: Whether this is replacing a just-consumed buffer * * The IPA hardware can hold a fixed number of receive buffers for an RX * endpoint, based on the number of entries in the underlying channel ring * buffer. If an endpoint's "backlog" is non-zero, it indicates how many * more receive buffers can be supplied to the hardware. Replenishing for - * an endpoint can be disabled, in which case requests to replenish a - * buffer are "saved", and transferred to the backlog once it is re-enabled - * again. + * an endpoint can be disabled, in which case buffers are not queued to + * the hardware. */ -static void ipa_endpoint_replenish(struct ipa_endpoint *endpoint, bool add_one) +static void ipa_endpoint_replenish(struct ipa_endpoint *endpoint) { - struct gsi *gsi; - u32 backlog; - int delta; + struct gsi_trans *trans; - if (!test_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags)) { - if (add_one) - atomic_inc(&endpoint->replenish_saved); + if (!test_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags)) return; - } - /* If already active, just update the backlog */ - if (test_and_set_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags)) { - if (add_one) - atomic_inc(&endpoint->replenish_backlog); + /* Skip it if it's already active */ + if (test_and_set_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags)) return; - } - while (atomic_dec_not_zero(&endpoint->replenish_backlog)) - if (ipa_endpoint_replenish_one(endpoint)) + while ((trans = ipa_endpoint_trans_alloc(endpoint, 1))) { + bool doorbell; + + if (ipa_endpoint_replenish_one(endpoint, trans)) goto try_again_later; - clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); - if (add_one) - atomic_inc(&endpoint->replenish_backlog); + /* Ring the doorbell if we've got a full batch */ + doorbell = !(++endpoint->replenish_count % IPA_REPLENISH_BATCH); + gsi_trans_commit(trans, doorbell); + } + + clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); return; try_again_later: + gsi_trans_free(trans); clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); - /* The last one didn't succeed, so fix the backlog */ - delta = add_one ? 2 : 1; - backlog = atomic_add_return(delta, &endpoint->replenish_backlog); - /* Whenever a receive buffer transaction completes we'll try to * replenish again. It's unlikely, but if we fail to supply even * one buffer, nothing will trigger another replenish attempt. - * Receive buffer transactions use one TRE, so schedule work to - * try replenishing again if our backlog is *all* available TREs. + * If the hardware has no receive buffers queued, schedule work to + * try replenishing again. */ - gsi = &endpoint->ipa->gsi; - if (backlog == gsi_channel_tre_max(gsi, endpoint->channel_id)) + if (gsi_channel_trans_idle(&endpoint->ipa->gsi, endpoint->channel_id)) schedule_delayed_work(&endpoint->replenish_work, msecs_to_jiffies(1)); } static void ipa_endpoint_replenish_enable(struct ipa_endpoint *endpoint) { - struct gsi *gsi = &endpoint->ipa->gsi; - u32 max_backlog; - u32 saved; - set_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags); - while ((saved = atomic_xchg(&endpoint->replenish_saved, 0))) - atomic_add(saved, &endpoint->replenish_backlog); /* Start replenishing if hardware currently has no buffers */ - max_backlog = gsi_channel_tre_max(gsi, endpoint->channel_id); - if (atomic_read(&endpoint->replenish_backlog) == max_backlog) - ipa_endpoint_replenish(endpoint, false); + if (gsi_channel_trans_idle(&endpoint->ipa->gsi, endpoint->channel_id)) + ipa_endpoint_replenish(endpoint); } static void ipa_endpoint_replenish_disable(struct ipa_endpoint *endpoint) { - u32 backlog; - clear_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags); - while ((backlog = atomic_xchg(&endpoint->replenish_backlog, 0))) - atomic_add(backlog, &endpoint->replenish_saved); } static void ipa_endpoint_replenish_work(struct work_struct *work) @@ -1157,7 +1138,7 @@ static void ipa_endpoint_replenish_work(struct work_struct *work) endpoint = container_of(dwork, struct ipa_endpoint, replenish_work); - ipa_endpoint_replenish(endpoint, false); + ipa_endpoint_replenish(endpoint); } static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint, @@ -1183,15 +1164,16 @@ static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint, static bool ipa_endpoint_skb_build(struct ipa_endpoint *endpoint, struct page *page, u32 len) { + u32 buffer_size = endpoint->data->rx.buffer_size; struct sk_buff *skb; /* Nothing to do if there's no netdev */ if (!endpoint->netdev) return false; - WARN_ON(len > SKB_WITH_OVERHEAD(IPA_RX_BUFFER_SIZE - NET_SKB_PAD)); + WARN_ON(len > SKB_WITH_OVERHEAD(buffer_size - NET_SKB_PAD)); - skb = build_skb(page_address(page), IPA_RX_BUFFER_SIZE); + skb = build_skb(page_address(page), buffer_size); if (skb) { /* Reserve the headroom and account for the data */ skb_reserve(skb, NET_SKB_PAD); @@ -1289,8 +1271,9 @@ static bool ipa_endpoint_status_drop(struct ipa_endpoint *endpoint, static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint, struct page *page, u32 total_len) { + u32 buffer_size = endpoint->data->rx.buffer_size; void *data = page_address(page) + NET_SKB_PAD; - u32 unused = IPA_RX_BUFFER_SIZE - total_len; + u32 unused = buffer_size - total_len; u32 resid = total_len; while (resid) { @@ -1360,10 +1343,8 @@ static void ipa_endpoint_rx_complete(struct ipa_endpoint *endpoint, { struct page *page; - ipa_endpoint_replenish(endpoint, true); - if (trans->cancelled) - return; + goto done; /* Parse or build a socket buffer using the actual received length */ page = trans->data; @@ -1371,6 +1352,8 @@ static void ipa_endpoint_rx_complete(struct ipa_endpoint *endpoint, ipa_endpoint_status_parse(endpoint, page, trans->len); else if (ipa_endpoint_skb_build(endpoint, page, trans->len)) trans->data = NULL; /* Pages have been consumed */ +done: + ipa_endpoint_replenish(endpoint); } void ipa_endpoint_trans_complete(struct ipa_endpoint *endpoint, @@ -1398,8 +1381,11 @@ void ipa_endpoint_trans_release(struct ipa_endpoint *endpoint, } else { struct page *page = trans->data; - if (page) - __free_pages(page, get_order(IPA_RX_BUFFER_SIZE)); + if (page) { + u32 buffer_size = endpoint->data->rx.buffer_size; + + __free_pages(page, get_order(buffer_size)); + } } } @@ -1704,9 +1690,6 @@ static void ipa_endpoint_setup_one(struct ipa_endpoint *endpoint) */ clear_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags); clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); - atomic_set(&endpoint->replenish_saved, - gsi_channel_tre_max(gsi, endpoint->channel_id)); - atomic_set(&endpoint->replenish_backlog, 0); INIT_DELAYED_WORK(&endpoint->replenish_work, ipa_endpoint_replenish_work); } @@ -1882,6 +1865,8 @@ u32 ipa_endpoint_init(struct ipa *ipa, u32 count, enum ipa_endpoint_name name; u32 filter_map; + BUILD_BUG_ON(!IPA_REPLENISH_BATCH); + if (!ipa_endpoint_data_valid(ipa, count, data)) return 0; /* Error */ diff --git a/drivers/net/ipa/ipa_endpoint.h b/drivers/net/ipa/ipa_endpoint.h index 0313cdc607de..12fd5b16c18e 100644 --- a/drivers/net/ipa/ipa_endpoint.h +++ b/drivers/net/ipa/ipa_endpoint.h @@ -65,9 +65,7 @@ enum ipa_replenish_flag { * @evt_ring_id: GSI event ring used by the endpoint * @netdev: Network device pointer, if endpoint uses one * @replenish_flags: Replenishing state flags - * @replenish_ready: Number of replenish transactions without doorbell - * @replenish_saved: Replenish requests held while disabled - * @replenish_backlog: Number of buffers needed to fill hardware queue + * @replenish_count: Total number of replenish transactions committed * @replenish_work: Work item used for repeated replenish failures */ struct ipa_endpoint { @@ -86,9 +84,7 @@ struct ipa_endpoint { /* Receive buffer replenishing for RX endpoints */ DECLARE_BITMAP(replenish_flags, IPA_REPLENISH_COUNT); - u32 replenish_ready; - atomic_t replenish_saved; - atomic_t replenish_backlog; + u64 replenish_count; struct delayed_work replenish_work; /* global wq */ }; diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index ed0edf5884ef..d05f86fe78c9 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -78,7 +78,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, skb_orphan(skb); - /* Before queueing this packet to netif_rx(), + /* Before queueing this packet to __netif_rx(), * make sure dst is refcounted. */ skb_dst_force(skb); @@ -86,7 +86,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, skb->protocol = eth_type_trans(skb, dev); len = skb->len; - if (likely(netif_rx(skb) == NET_RX_SUCCESS)) + if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) dev_lstats_add(dev, len); return NETDEV_TX_OK; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 3d0874331763..832f09ac075e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1033,7 +1033,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) else nskb->pkt_type = PACKET_MULTICAST; - netif_rx(nskb); + __netif_rx(nskb); } continue; } @@ -1056,7 +1056,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) nskb->dev = ndev; - if (netif_rx(nskb) == NET_RX_SUCCESS) { + if (__netif_rx(nskb) == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); @@ -1288,7 +1288,7 @@ nosci: macsec_reset_skb(nskb, macsec->secy.netdev); - ret = netif_rx(nskb); + ret = __netif_rx(nskb); if (ret == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUnknownSCI++; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 6ef5f77be4d0..d87c06c317ed 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -410,7 +410,7 @@ static void macvlan_forward_source_one(struct sk_buff *skb, if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr)) nskb->pkt_type = PACKET_HOST; - ret = netif_rx(nskb); + ret = __netif_rx(nskb); macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); } @@ -468,7 +468,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) /* forward to original port. */ vlan = src; ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?: - netif_rx(skb); + __netif_rx(skb); handle_res = RX_HANDLER_CONSUMED; goto out; } diff --git a/drivers/net/mdio/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c index 7ab4e26db08c..7aafc221b5cf 100644 --- a/drivers/net/mdio/mdio-xgene.c +++ b/drivers/net/mdio/mdio-xgene.c @@ -285,7 +285,8 @@ static acpi_status acpi_register_phy(acpi_handle handle, u32 lvl, const union acpi_object *obj; u32 phy_addr; - if (acpi_bus_get_device(handle, &adev)) + adev = acpi_fetch_acpi_dev(handle); + if (!adev) return AE_OK; if (acpi_dev_get_property(adev, "phy-channel", ACPI_TYPE_INTEGER, &obj)) diff --git a/drivers/net/mhi_net.c b/drivers/net/mhi_net.c index aaa628f859fd..0b1b6f650104 100644 --- a/drivers/net/mhi_net.c +++ b/drivers/net/mhi_net.c @@ -225,7 +225,7 @@ static void mhi_net_dl_callback(struct mhi_device *mhi_dev, u64_stats_inc(&mhi_netdev->stats.rx_packets); u64_stats_add(&mhi_netdev->stats.rx_bytes, skb->len); u64_stats_update_end(&mhi_netdev->stats.rx_syncp); - netif_rx(skb); + __netif_rx(skb); } /* Refill if RX buffers queue becomes low */ diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 98ca6b18415e..80bdc07f2cd3 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -119,7 +119,7 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, skb->protocol = eth_type_trans(skb, ndev); skb->ip_summed = CHECKSUM_NONE; - if (netif_rx(skb) == NET_RX_DROP) { + if (__netif_rx(skb) == NET_RX_DROP) { ndev->stats.rx_errors++; ndev->stats.rx_dropped++; } else { diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index cd6742e6ba8b..61418d4dc0cd 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -632,35 +632,43 @@ static void xpcs_resolve_pma(struct dw_xpcs *xpcs, } } -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state) +static int xpcs_validate(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported) = { 0, }; const struct xpcs_compat *compat; + struct dw_xpcs *xpcs; int i; - /* phylink expects us to report all supported modes with - * PHY_INTERFACE_MODE_NA, just don't limit the supported and - * advertising masks and exit. - */ - if (state->interface == PHY_INTERFACE_MODE_NA) - return; - - linkmode_zero(xpcs_supported); - + xpcs = phylink_pcs_to_xpcs(pcs); compat = xpcs_find_compat(xpcs->id, state->interface); - /* Populate the supported link modes for this - * PHY interface type + /* Populate the supported link modes for this PHY interface type. + * FIXME: what about the port modes and autoneg bit? This masks + * all those away. */ if (compat) for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++) set_bit(compat->supported[i], xpcs_supported); linkmode_and(supported, supported, xpcs_supported); - linkmode_and(state->advertising, state->advertising, xpcs_supported); + + return 0; +} + +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces) +{ + int i, j; + + for (i = 0; i < DW_XPCS_INTERFACE_MAX; i++) { + const struct xpcs_compat *compat = &xpcs->id->compat[i]; + + for (j = 0; j < compat->num_interfaces; j++) + if (compat->interface[j] < PHY_INTERFACE_MODE_MAX) + __set_bit(compat->interface[j], interfaces); + } } -EXPORT_SYMBOL_GPL(xpcs_validate); +EXPORT_SYMBOL_GPL(xpcs_get_interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) { @@ -1106,6 +1114,7 @@ static const struct xpcs_id xpcs_id_list[] = { }; static const struct phylink_pcs_ops xpcs_phylink_ops = { + .pcs_validate = xpcs_validate, .pcs_config = xpcs_config, .pcs_get_state = xpcs_get_state, .pcs_link_up = xpcs_link_up, diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 968dd43a2b1e..a8db1a19011b 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -533,9 +533,7 @@ static int aqcs109_config_init(struct phy_device *phydev) * PMA speed ability bits are the same for all members of the family, * AQCS109 however supports speeds up to 2.5G only. */ - ret = phy_set_max_speed(phydev, SPEED_2500); - if (ret) - return ret; + phy_set_max_speed(phydev, SPEED_2500); return aqr107_set_downshift(phydev, MDIO_AN_VEND_PROV_DOWNSHIFT_DFLT); } diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 29aa811af430..73926006d319 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -19,6 +19,8 @@ #include <linux/regulator/of_regulator.h> #include <linux/regulator/driver.h> #include <linux/regulator/consumer.h> +#include <linux/phylink.h> +#include <linux/sfp.h> #include <dt-bindings/net/qca-ar803x.h> #define AT803X_SPECIFIC_FUNCTION_CONTROL 0x10 @@ -51,6 +53,8 @@ #define AT803X_INTR_ENABLE_PAGE_RECEIVED BIT(12) #define AT803X_INTR_ENABLE_LINK_FAIL BIT(11) #define AT803X_INTR_ENABLE_LINK_SUCCESS BIT(10) +#define AT803X_INTR_ENABLE_LINK_FAIL_BX BIT(8) +#define AT803X_INTR_ENABLE_LINK_SUCCESS_BX BIT(7) #define AT803X_INTR_ENABLE_WIRESPEED_DOWNGRADE BIT(5) #define AT803X_INTR_ENABLE_POLARITY_CHANGED BIT(1) #define AT803X_INTR_ENABLE_WOL BIT(0) @@ -85,7 +89,17 @@ #define AT803X_DEBUG_DATA 0x1E #define AT803X_MODE_CFG_MASK 0x0F -#define AT803X_MODE_CFG_SGMII 0x01 +#define AT803X_MODE_CFG_BASET_RGMII 0x00 +#define AT803X_MODE_CFG_BASET_SGMII 0x01 +#define AT803X_MODE_CFG_BX1000_RGMII_50OHM 0x02 +#define AT803X_MODE_CFG_BX1000_RGMII_75OHM 0x03 +#define AT803X_MODE_CFG_BX1000_CONV_50OHM 0x04 +#define AT803X_MODE_CFG_BX1000_CONV_75OHM 0x05 +#define AT803X_MODE_CFG_FX100_RGMII_50OHM 0x06 +#define AT803X_MODE_CFG_FX100_CONV_50OHM 0x07 +#define AT803X_MODE_CFG_RGMII_AUTO_MDET 0x0B +#define AT803X_MODE_CFG_FX100_RGMII_75OHM 0x0E +#define AT803X_MODE_CFG_FX100_CONV_75OHM 0x0F #define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/ #define AT803X_PSSR_MR_AN_COMPLETE 0x0200 @@ -283,6 +297,8 @@ struct at803x_priv { u16 clk_25m_mask; u8 smarteee_lpi_tw_1g; u8 smarteee_lpi_tw_100m; + bool is_fiber; + bool is_1000basex; struct regulator_dev *vddio_rdev; struct regulator_dev *vddh_rdev; struct regulator *vddio; @@ -650,6 +666,55 @@ static int at8031_register_regulators(struct phy_device *phydev) return 0; } +static int at803x_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) +{ + struct phy_device *phydev = upstream; + __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_support); + __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support); + phy_interface_t iface; + + linkmode_zero(phy_support); + phylink_set(phy_support, 1000baseX_Full); + phylink_set(phy_support, 1000baseT_Full); + phylink_set(phy_support, Autoneg); + phylink_set(phy_support, Pause); + phylink_set(phy_support, Asym_Pause); + + linkmode_zero(sfp_support); + sfp_parse_support(phydev->sfp_bus, id, sfp_support); + /* Some modules support 10G modes as well as others we support. + * Mask out non-supported modes so the correct interface is picked. + */ + linkmode_and(sfp_support, phy_support, sfp_support); + + if (linkmode_empty(sfp_support)) { + dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n"); + return -EINVAL; + } + + iface = sfp_select_interface(phydev->sfp_bus, sfp_support); + + /* Only 1000Base-X is supported by AR8031/8033 as the downstream SerDes + * interface for use with SFP modules. + * However, some copper modules detected as having a preferred SGMII + * interface do default to and function in 1000Base-X mode, so just + * print a warning and allow such modules, as they may have some chance + * of working. + */ + if (iface == PHY_INTERFACE_MODE_SGMII) + dev_warn(&phydev->mdio.dev, "module may not function if 1000Base-X not supported\n"); + else if (iface != PHY_INTERFACE_MODE_1000BASEX) + return -EINVAL; + + return 0; +} + +static const struct sfp_upstream_ops at803x_sfp_ops = { + .attach = phy_sfp_attach, + .detach = phy_sfp_detach, + .module_insert = at803x_sfp_insert, +}; + static int at803x_parse_dt(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; @@ -757,6 +822,11 @@ static int at803x_parse_dt(struct phy_device *phydev) phydev_err(phydev, "failed to get VDDIO regulator\n"); return PTR_ERR(priv->vddio); } + + /* Only AR8031/8033 support 1000Base-X for SFP modules */ + ret = phy_sfp_probe(phydev, &at803x_sfp_ops); + if (ret < 0) + return ret; } return 0; @@ -784,16 +854,24 @@ static int at803x_probe(struct phy_device *phydev) return ret; } - /* Some bootloaders leave the fiber page selected. - * Switch to the copper page, as otherwise we read - * the PHY capabilities from the fiber side. - */ if (phydev->drv->phy_id == ATH8031_PHY_ID) { - phy_lock_mdio_bus(phydev); - ret = at803x_write_page(phydev, AT803X_PAGE_COPPER); - phy_unlock_mdio_bus(phydev); - if (ret) + int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); + int mode_cfg; + + if (ccr < 0) goto err; + mode_cfg = ccr & AT803X_MODE_CFG_MASK; + + switch (mode_cfg) { + case AT803X_MODE_CFG_BX1000_RGMII_50OHM: + case AT803X_MODE_CFG_BX1000_RGMII_75OHM: + priv->is_1000basex = true; + fallthrough; + case AT803X_MODE_CFG_FX100_RGMII_50OHM: + case AT803X_MODE_CFG_FX100_RGMII_75OHM: + priv->is_fiber = true; + break; + } } return 0; @@ -815,6 +893,7 @@ static void at803x_remove(struct phy_device *phydev) static int at803x_get_features(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int err; err = genphy_read_abilities(phydev); @@ -841,12 +920,13 @@ static int at803x_get_features(struct phy_device *phydev) * As a result of that, ESTATUS_1000_XFULL is set * to 1 even when operating in copper TP mode. * - * Remove this mode from the supported link modes, - * as this driver currently only supports copper - * operation. + * Remove this mode from the supported link modes + * when not operating in 1000BaseX mode. */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, - phydev->supported); + if (!priv->is_1000basex) + linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + phydev->supported); + return 0; } @@ -910,8 +990,27 @@ static int at8031_pll_config(struct phy_device *phydev) static int at803x_config_init(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int ret; + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + /* Some bootloaders leave the fiber page selected. + * Switch to the appropriate page (fiber or copper), as otherwise we + * read the PHY capabilities from the wrong page. + */ + phy_lock_mdio_bus(phydev); + ret = at803x_write_page(phydev, + priv->is_fiber ? AT803X_PAGE_FIBER : + AT803X_PAGE_COPPER); + phy_unlock_mdio_bus(phydev); + if (ret) + return ret; + + ret = at8031_pll_config(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 @@ -941,12 +1040,6 @@ static int at803x_config_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->drv->phy_id == ATH8031_PHY_ID) { - ret = at8031_pll_config(phydev); - if (ret < 0) - return ret; - } - /* Ar803x extended next page bit is enabled by default. Cisco * multigig switches read this bit and attempt to negotiate 10Gbps * rates even if the next page bit is disabled. This is incorrect @@ -967,6 +1060,7 @@ static int at803x_ack_interrupt(struct phy_device *phydev) static int at803x_config_intr(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int err; int value; @@ -983,6 +1077,10 @@ static int at803x_config_intr(struct phy_device *phydev) value |= AT803X_INTR_ENABLE_DUPLEX_CHANGED; value |= AT803X_INTR_ENABLE_LINK_FAIL; value |= AT803X_INTR_ENABLE_LINK_SUCCESS; + if (priv->is_fiber) { + value |= AT803X_INTR_ENABLE_LINK_FAIL_BX; + value |= AT803X_INTR_ENABLE_LINK_SUCCESS_BX; + } err = phy_write(phydev, AT803X_INTR_ENABLE, value); } else { @@ -1115,8 +1213,12 @@ static int at803x_read_specific_status(struct phy_device *phydev) static int at803x_read_status(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int err, old_link = phydev->link; + if (priv->is_1000basex) + return genphy_c37_read_status(phydev); + /* Update the link, but return if there was an error */ err = genphy_update_link(phydev); if (err) @@ -1170,6 +1272,7 @@ static int at803x_config_mdix(struct phy_device *phydev, u8 ctrl) static int at803x_config_aneg(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int ret; ret = at803x_config_mdix(phydev, phydev->mdix_ctrl); @@ -1186,6 +1289,9 @@ static int at803x_config_aneg(struct phy_device *phydev) return ret; } + if (priv->is_1000basex) + return genphy_c37_config_aneg(phydev); + /* Do not restart auto-negotiation by setting ret to 0 defautly, * when calling __genphy_config_aneg later. */ diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 271fc01f7f7f..2001f3329133 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -243,7 +243,7 @@ size_t phy_speeds(unsigned int *speeds, size_t size, return count; } -static int __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) +static void __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) { const struct phy_setting *p; int i; @@ -254,13 +254,11 @@ static int __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) else break; } - - return 0; } -static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +static void __set_phy_supported(struct phy_device *phydev, u32 max_speed) { - return __set_linkmode_max_speed(max_speed, phydev->supported); + __set_linkmode_max_speed(max_speed, phydev->supported); } /** @@ -273,17 +271,11 @@ static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) * is connected to a 1G PHY. This function allows the MAC to indicate its * maximum speed, and so limit what the PHY will advertise. */ -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed) { - int err; - - err = __set_phy_supported(phydev, max_speed); - if (err) - return err; + __set_phy_supported(phydev, max_speed); phy_advertise_supported(phydev); - - return 0; } EXPORT_SYMBOL(phy_set_max_speed); @@ -440,7 +432,9 @@ int phy_speed_down_core(struct phy_device *phydev) if (min_common_speed == SPEED_UNKNOWN) return -EINVAL; - return __set_linkmode_max_speed(min_common_speed, phydev->advertising); + __set_linkmode_max_speed(min_common_speed, phydev->advertising); + + return 0; } static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 420201858564..5b53a3e23c89 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -132,17 +132,6 @@ void phylink_set_port_modes(unsigned long *mask) } EXPORT_SYMBOL_GPL(phylink_set_port_modes); -void phylink_set_10g_modes(unsigned long *mask) -{ - phylink_set(mask, 10000baseT_Full); - phylink_set(mask, 10000baseCR_Full); - phylink_set(mask, 10000baseSR_Full); - phylink_set(mask, 10000baseLR_Full); - phylink_set(mask, 10000baseLRM_Full); - phylink_set(mask, 10000baseER_Full); -} -EXPORT_SYMBOL_GPL(phylink_set_10g_modes); - static int phylink_is_empty_linkmode(const unsigned long *linkmode) { __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp) = { 0, }; diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index 1a95f3beb784..39e61e07e489 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -109,7 +109,7 @@ static int rionet_rx_clean(struct net_device *ndev) skb_put(rnet->rx_skb[i], RIO_MAX_MSG_SIZE); rnet->rx_skb[i]->protocol = eth_type_trans(rnet->rx_skb[i], ndev); - error = netif_rx(rnet->rx_skb[i]); + error = __netif_rx(rnet->rx_skb[i]); if (error == NET_RX_DROP) { ndev->stats.rx_dropped++; diff --git a/drivers/net/sb1000.c b/drivers/net/sb1000.c index 57a6d598467b..c3f8020571ad 100644 --- a/drivers/net/sb1000.c +++ b/drivers/net/sb1000.c @@ -872,7 +872,7 @@ printk("cm0: IP identification: %02x%02x fragment offset: %02x%02x\n", buffer[3 /* datagram completed: send to upper level */ skb_trim(skb, dlen); - netif_rx(skb); + __netif_rx(skb); stats->rx_bytes+=dlen; stats->rx_packets++; lp->rx_skb[ns] = NULL; diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index b554054a7560..e62fc4f2aee0 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -358,6 +358,7 @@ config USB_NET_SMSC95XX select BITREVERSE select CRC16 select CRC32 + imply NET_SELFTESTS help This option adds support for SMSC LAN95XX based USB 2.0 10/100 Ethernet adapters. diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h index 2a1e31defe71..4334aafab59a 100644 --- a/drivers/net/usb/asix.h +++ b/drivers/net/usb/asix.h @@ -192,8 +192,8 @@ extern const struct driver_info ax88172a_info; /* ASIX specific flags */ #define FLAG_EEPROM_MAC (1UL << 0) /* init device MAC from eeprom */ -int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data, int in_pm); +int __must_check asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, + u16 size, void *data, int in_pm); int asix_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, u16 size, void *data, int in_pm); diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 71682970be58..524805285019 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -11,8 +11,8 @@ #define AX_HOST_EN_RETRIES 30 -int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data, int in_pm) +int __must_check asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, + u16 size, void *data, int in_pm) { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16); @@ -27,9 +27,12 @@ int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely(ret < size)) { + ret = ret < 0 ? ret : -ENODATA; + netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n", index, ret); + } return ret; } @@ -79,7 +82,7 @@ static int asix_check_host_enable(struct usbnet *dev, int in_pm) 0, 0, 1, &smsr, in_pm); if (ret == -ENODEV) break; - else if (ret < sizeof(smsr)) + else if (ret < 0) continue; else if (smsr & AX_HOST_EN) break; @@ -579,8 +582,12 @@ int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc) return ret; } - asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id, - (__u16)loc, 2, &res, 1); + ret = asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id, + (__u16)loc, 2, &res, 1); + if (ret < 0) { + mutex_unlock(&dev->phy_mutex); + return ret; + } asix_set_hw_mii(dev, 1); mutex_unlock(&dev->phy_mutex); diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 4514d35ef4c4..6ea44e53713a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -755,7 +755,12 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) priv->phy_addr = ret; priv->embd_phy = ((priv->phy_addr & 0x1f) == 0x10); - asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, 0, 0, 1, &chipcode, 0); + ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, 0, 0, 1, &chipcode, 0); + if (ret < 0) { + netdev_dbg(dev->net, "Failed to read STATMNGSTS_REG: %d\n", ret); + return ret; + } + chipcode &= AX_CHIPCODE_MASK; ret = (chipcode == AX_AX88772_CHIPCODE) ? ax88772_hw_reset(dev, 0) : @@ -858,7 +863,6 @@ static int marvell_phy_init(struct usbnet *dev) reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_MARVELL_LED_CTRL); netdev_dbg(dev->net, "MII_MARVELL_LED_CTRL (2) = 0x%04x\n", reg); - reg &= 0xfc0f; } return 0; @@ -920,11 +924,21 @@ static int ax88178_reset(struct usbnet *dev) int gpio0 = 0; u32 phyid; - asix_read_cmd(dev, AX_CMD_READ_GPIOS, 0, 0, 1, &status, 0); + ret = asix_read_cmd(dev, AX_CMD_READ_GPIOS, 0, 0, 1, &status, 0); + if (ret < 0) { + netdev_dbg(dev->net, "Failed to read GPIOS: %d\n", ret); + return ret; + } + netdev_dbg(dev->net, "GPIO Status: 0x%04x\n", status); asix_write_cmd(dev, AX_CMD_WRITE_ENABLE, 0, 0, 0, NULL, 0); - asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x0017, 0, 2, &eeprom, 0); + ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x0017, 0, 2, &eeprom, 0); + if (ret < 0) { + netdev_dbg(dev->net, "Failed to read EEPROM: %d\n", ret); + return ret; + } + asix_write_cmd(dev, AX_CMD_WRITE_DISABLE, 0, 0, 0, NULL, 0); netdev_dbg(dev->net, "EEPROM index 0x17 is 0x%04x\n", eeprom); diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index c0b8b4aa78f3..c89639381eca 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -21,6 +21,7 @@ #include <net/ipv6.h> #include <net/addrconf.h> #include <net/ipv6_stubs.h> +#include <net/ndisc.h> /* alternative VLAN for IP session 0 if not untagged */ #define MBIM_IPS0_VID 4094 diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index f97813a4e8d1..f8221a7acf62 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2319,7 +2319,7 @@ static struct hso_device *hso_create_device(struct usb_interface *intf, { struct hso_device *hso_dev; - hso_dev = kzalloc(sizeof(*hso_dev), GFP_ATOMIC); + hso_dev = kzalloc(sizeof(*hso_dev), GFP_KERNEL); if (!hso_dev) return NULL; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index bc1e3dd67c04..5567220e9d16 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -20,6 +20,8 @@ #include <linux/of_net.h> #include <linux/mdio.h> #include <linux/phy.h> +#include <net/selftests.h> + #include "smsc95xx.h" #define SMSC_CHIPNAME "smsc95xx" @@ -727,6 +729,26 @@ static u32 smsc95xx_get_link(struct net_device *net) return net->phydev->link; } +static void smsc95xx_ethtool_get_strings(struct net_device *netdev, u32 sset, + u8 *data) +{ + switch (sset) { + case ETH_SS_TEST: + net_selftest_get_strings(data); + break; + } +} + +static int smsc95xx_ethtool_get_sset_count(struct net_device *ndev, int sset) +{ + switch (sset) { + case ETH_SS_TEST: + return net_selftest_get_count(); + default: + return -EOPNOTSUPP; + } +} + static const struct ethtool_ops smsc95xx_ethtool_ops = { .get_link = smsc95xx_get_link, .nway_reset = phy_ethtool_nway_reset, @@ -743,6 +765,9 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_ts_info = ethtool_op_get_ts_info, + .self_test = net_selftest, + .get_strings = smsc95xx_ethtool_get_strings, + .get_sset_count = smsc95xx_ethtool_get_sset_count, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index d29fb9759cc9..58b20ea171dd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -287,7 +287,7 @@ static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb, { return __dev_forward_skb(dev, skb) ?: xdp ? veth_xdp_rx(rq, skb) : - netif_rx(skb); + __netif_rx(skb); } /* return true if the specified skb has chances of GRO aggregation diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a801ea40908f..11f26b00a226 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3449,8 +3449,7 @@ static __init int virtio_net_driver_init(void) NULL, virtnet_cpu_dead); if (ret) goto err_dead; - - ret = register_virtio_driver(&virtio_net_driver); + ret = register_virtio_driver(&virtio_net_driver); if (ret) goto err_virtio; return 0; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index e0b1ab99a359..714cafcf6c6c 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -418,7 +418,7 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, skb->protocol = eth_type_trans(skb, dev); - if (likely(netif_rx(skb) == NET_RX_SUCCESS)) + if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) vrf_rx_stats(dev, len); else this_cpu_inc(dev->dstats->rx_drps); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 359d16780dbb..d0dc90d3dac2 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2541,7 +2541,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, tx_stats->tx_bytes += len; u64_stats_update_end(&tx_stats->syncp); - if (netif_rx(skb) == NET_RX_SUCCESS) { + if (__netif_rx(skb) == NET_RX_SUCCESS) { u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; rx_stats->rx_bytes += len; diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 8f5b8eb368fa..9e1f483e1362 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -75,6 +75,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA988X_BOARD_DATA_SZ, .board_ext_size = QCA988X_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca988x_ops, .decap_align_bytes = 4, .spectral_bin_discard = 0, @@ -111,6 +112,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA988X_BOARD_DATA_SZ, .board_ext_size = QCA988X_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca988x_ops, .decap_align_bytes = 4, .spectral_bin_discard = 0, @@ -148,6 +150,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA9887_BOARD_DATA_SZ, .board_ext_size = QCA9887_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca988x_ops, .decap_align_bytes = 4, .spectral_bin_discard = 0, @@ -184,6 +187,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA6174_BOARD_DATA_SZ, .board_ext_size = QCA6174_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca6174_sdio_ops, .hw_clk = qca6174_clk, .target_cpu_freq = 176000000, @@ -216,6 +220,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA6174_BOARD_DATA_SZ, .board_ext_size = QCA6174_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca988x_ops, .decap_align_bytes = 4, .spectral_bin_discard = 0, @@ -252,6 +257,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA6174_BOARD_DATA_SZ, .board_ext_size = QCA6174_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca988x_ops, .decap_align_bytes = 4, .spectral_bin_discard = 0, @@ -288,6 +294,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA6174_BOARD_DATA_SZ, .board_ext_size = QCA6174_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca988x_ops, .decap_align_bytes = 4, .spectral_bin_discard = 0, @@ -325,6 +332,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA6174_BOARD_DATA_SZ, .board_ext_size = QCA6174_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca6174_ops, .hw_clk = qca6174_clk, .target_cpu_freq = 176000000, @@ -370,6 +378,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_ext_size = QCA99X0_BOARD_EXT_DATA_SZ, }, .sw_decrypt_mcast_mgmt = true, + .rx_desc_ops = &qca99x0_rx_desc_ops, .hw_ops = &qca99x0_ops, .decap_align_bytes = 1, .spectral_bin_discard = 4, @@ -415,6 +424,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .ext_board_size = QCA99X0_EXT_BOARD_DATA_SZ, }, .sw_decrypt_mcast_mgmt = true, + .rx_desc_ops = &qca99x0_rx_desc_ops, .hw_ops = &qca99x0_ops, .decap_align_bytes = 1, .spectral_bin_discard = 12, @@ -461,6 +471,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_ext_size = QCA99X0_BOARD_EXT_DATA_SZ, }, .sw_decrypt_mcast_mgmt = true, + .rx_desc_ops = &qca99x0_rx_desc_ops, .hw_ops = &qca99x0_ops, .decap_align_bytes = 1, .spectral_bin_discard = 12, @@ -501,6 +512,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA9377_BOARD_DATA_SZ, .board_ext_size = QCA9377_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca988x_ops, .decap_align_bytes = 4, .spectral_bin_discard = 0, @@ -537,6 +549,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA9377_BOARD_DATA_SZ, .board_ext_size = QCA9377_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca6174_ops, .hw_clk = qca6174_clk, .target_cpu_freq = 176000000, @@ -575,6 +588,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_size = QCA9377_BOARD_DATA_SZ, .board_ext_size = QCA9377_BOARD_EXT_DATA_SZ, }, + .rx_desc_ops = &qca988x_rx_desc_ops, .hw_ops = &qca6174_ops, .hw_clk = qca6174_clk, .target_cpu_freq = 176000000, @@ -611,6 +625,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .board_ext_size = QCA4019_BOARD_EXT_DATA_SZ, }, .sw_decrypt_mcast_mgmt = true, + .rx_desc_ops = &qca99x0_rx_desc_ops, .hw_ops = &qca99x0_ops, .decap_align_bytes = 1, .spectral_bin_discard = 4, @@ -643,6 +658,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .dir = WCN3990_HW_1_0_FW_DIR, }, .sw_decrypt_mcast_mgmt = true, + .rx_desc_ops = &wcn3990_rx_desc_ops, .hw_ops = &wcn3990_ops, .decap_align_bytes = 1, .num_peers = TARGET_HL_TLV_NUM_PEERS, diff --git a/drivers/net/wireless/ath/ath10k/htt.c b/drivers/net/wireless/ath/ath10k/htt.c index 127b4e4980ef..907e1e13871a 100644 --- a/drivers/net/wireless/ath/ath10k/htt.c +++ b/drivers/net/wireless/ath/ath10k/htt.c @@ -131,6 +131,159 @@ static const enum htt_t2h_msg_type htt_10_4_t2h_msg_types[] = { HTT_T2H_MSG_TYPE_PEER_STATS, }; +const struct ath10k_htt_rx_desc_ops qca988x_rx_desc_ops = { + .rx_desc_size = sizeof(struct htt_rx_desc_v1), + .rx_desc_msdu_payload_offset = offsetof(struct htt_rx_desc_v1, msdu_payload) +}; + +static int ath10k_qca99x0_rx_desc_get_l3_pad_bytes(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc = container_of(rxd, + struct htt_rx_desc_v1, + base); + + return MS(__le32_to_cpu(rx_desc->msdu_end.qca99x0.info1), + RX_MSDU_END_INFO1_L3_HDR_PAD); +} + +static bool ath10k_qca99x0_rx_desc_msdu_limit_error(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc = container_of(rxd, + struct htt_rx_desc_v1, + base); + + return !!(rx_desc->msdu_end.common.info0 & + __cpu_to_le32(RX_MSDU_END_INFO0_MSDU_LIMIT_ERR)); +} + +const struct ath10k_htt_rx_desc_ops qca99x0_rx_desc_ops = { + .rx_desc_size = sizeof(struct htt_rx_desc_v1), + .rx_desc_msdu_payload_offset = offsetof(struct htt_rx_desc_v1, msdu_payload), + + .rx_desc_get_l3_pad_bytes = ath10k_qca99x0_rx_desc_get_l3_pad_bytes, + .rx_desc_get_msdu_limit_error = ath10k_qca99x0_rx_desc_msdu_limit_error, +}; + +static void ath10k_rx_desc_wcn3990_get_offsets(struct htt_rx_ring_rx_desc_offsets *off) +{ +#define desc_offset(x) (offsetof(struct htt_rx_desc_v2, x) / 4) + off->mac80211_hdr_offset = __cpu_to_le16(desc_offset(rx_hdr_status)); + off->msdu_payload_offset = __cpu_to_le16(desc_offset(msdu_payload)); + off->ppdu_start_offset = __cpu_to_le16(desc_offset(ppdu_start)); + off->ppdu_end_offset = __cpu_to_le16(desc_offset(ppdu_end)); + off->mpdu_start_offset = __cpu_to_le16(desc_offset(mpdu_start)); + off->mpdu_end_offset = __cpu_to_le16(desc_offset(mpdu_end)); + off->msdu_start_offset = __cpu_to_le16(desc_offset(msdu_start)); + off->msdu_end_offset = __cpu_to_le16(desc_offset(msdu_end)); + off->rx_attention_offset = __cpu_to_le16(desc_offset(attention)); + off->frag_info_offset = __cpu_to_le16(desc_offset(frag_info)); +#undef desc_offset +} + +static struct htt_rx_desc * +ath10k_rx_desc_wcn3990_from_raw_buffer(void *buff) +{ + return &((struct htt_rx_desc_v2 *)buff)->base; +} + +static struct rx_attention * +ath10k_rx_desc_wcn3990_get_attention(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->attention; +} + +static struct rx_frag_info_common * +ath10k_rx_desc_wcn3990_get_frag_info(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->frag_info.common; +} + +static struct rx_mpdu_start * +ath10k_rx_desc_wcn3990_get_mpdu_start(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->mpdu_start; +} + +static struct rx_mpdu_end * +ath10k_rx_desc_wcn3990_get_mpdu_end(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->mpdu_end; +} + +static struct rx_msdu_start_common * +ath10k_rx_desc_wcn3990_get_msdu_start(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->msdu_start.common; +} + +static struct rx_msdu_end_common * +ath10k_rx_desc_wcn3990_get_msdu_end(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->msdu_end.common; +} + +static struct rx_ppdu_start * +ath10k_rx_desc_wcn3990_get_ppdu_start(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->ppdu_start; +} + +static struct rx_ppdu_end_common * +ath10k_rx_desc_wcn3990_get_ppdu_end(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return &rx_desc->ppdu_end.common; +} + +static u8 * +ath10k_rx_desc_wcn3990_get_rx_hdr_status(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return rx_desc->rx_hdr_status; +} + +static u8 * +ath10k_rx_desc_wcn3990_get_msdu_payload(struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v2 *rx_desc = container_of(rxd, struct htt_rx_desc_v2, base); + + return rx_desc->msdu_payload; +} + +const struct ath10k_htt_rx_desc_ops wcn3990_rx_desc_ops = { + .rx_desc_size = sizeof(struct htt_rx_desc_v2), + .rx_desc_msdu_payload_offset = offsetof(struct htt_rx_desc_v2, msdu_payload), + + .rx_desc_from_raw_buffer = ath10k_rx_desc_wcn3990_from_raw_buffer, + .rx_desc_get_offsets = ath10k_rx_desc_wcn3990_get_offsets, + .rx_desc_get_attention = ath10k_rx_desc_wcn3990_get_attention, + .rx_desc_get_frag_info = ath10k_rx_desc_wcn3990_get_frag_info, + .rx_desc_get_mpdu_start = ath10k_rx_desc_wcn3990_get_mpdu_start, + .rx_desc_get_mpdu_end = ath10k_rx_desc_wcn3990_get_mpdu_end, + .rx_desc_get_msdu_start = ath10k_rx_desc_wcn3990_get_msdu_start, + .rx_desc_get_msdu_end = ath10k_rx_desc_wcn3990_get_msdu_end, + .rx_desc_get_ppdu_start = ath10k_rx_desc_wcn3990_get_ppdu_start, + .rx_desc_get_ppdu_end = ath10k_rx_desc_wcn3990_get_ppdu_end, + .rx_desc_get_rx_hdr_status = ath10k_rx_desc_wcn3990_get_rx_hdr_status, + .rx_desc_get_msdu_payload = ath10k_rx_desc_wcn3990_get_msdu_payload, +}; + int ath10k_htt_connect(struct ath10k_htt *htt) { struct ath10k_htc_svc_conn_req conn_req; diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index 9a3a8907389b..f06cf39204e2 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -240,14 +240,7 @@ enum htt_rx_ring_flags { #define HTT_RX_RING_FILL_LEVEL (((HTT_RX_RING_SIZE) / 2) - 1) #define HTT_RX_RING_FILL_LEVEL_DUAL_MAC (HTT_RX_RING_SIZE - 1) -struct htt_rx_ring_setup_ring32 { - __le32 fw_idx_shadow_reg_paddr; - __le32 rx_ring_base_paddr; - __le16 rx_ring_len; /* in 4-byte words */ - __le16 rx_ring_bufsize; /* rx skb size - in bytes */ - __le16 flags; /* %HTT_RX_RING_FLAGS_ */ - __le16 fw_idx_init_val; - +struct htt_rx_ring_rx_desc_offsets { /* the following offsets are in 4-byte units */ __le16 mac80211_hdr_offset; __le16 msdu_payload_offset; @@ -261,6 +254,17 @@ struct htt_rx_ring_setup_ring32 { __le16 frag_info_offset; } __packed; +struct htt_rx_ring_setup_ring32 { + __le32 fw_idx_shadow_reg_paddr; + __le32 rx_ring_base_paddr; + __le16 rx_ring_len; /* in 4-byte words */ + __le16 rx_ring_bufsize; /* rx skb size - in bytes */ + __le16 flags; /* %HTT_RX_RING_FLAGS_ */ + __le16 fw_idx_init_val; + + struct htt_rx_ring_rx_desc_offsets offsets; +} __packed; + struct htt_rx_ring_setup_ring64 { __le64 fw_idx_shadow_reg_paddr; __le64 rx_ring_base_paddr; @@ -269,17 +273,7 @@ struct htt_rx_ring_setup_ring64 { __le16 flags; /* %HTT_RX_RING_FLAGS_ */ __le16 fw_idx_init_val; - /* the following offsets are in 4-byte units */ - __le16 mac80211_hdr_offset; - __le16 msdu_payload_offset; - __le16 ppdu_start_offset; - __le16 ppdu_end_offset; - __le16 mpdu_start_offset; - __le16 mpdu_end_offset; - __le16 msdu_start_offset; - __le16 msdu_end_offset; - __le16 rx_attention_offset; - __le16 frag_info_offset; + struct htt_rx_ring_rx_desc_offsets offsets; } __packed; struct htt_rx_ring_setup_hdr { @@ -2075,12 +2069,22 @@ static inline bool ath10k_htt_rx_proc_rx_frag_ind(struct ath10k_htt *htt, return htt->rx_ops->htt_rx_proc_rx_frag_ind(htt, rx, skb); } +/* the driver strongly assumes that the rx header status be 64 bytes long, + * so all possible rx_desc structures must respect this assumption. + */ #define RX_HTT_HDR_STATUS_LEN 64 -/* This structure layout is programmed via rx ring setup +/* The rx descriptor structure layout is programmed via rx ring setup * so that FW knows how to transfer the rx descriptor to the host. - * Buffers like this are placed on the rx ring. + * Unfortunately, though, QCA6174's firmware doesn't currently behave correctly + * when modifying the structure layout of the rx descriptor beyond what it expects + * (even if it correctly programmed during the rx ring setup). + * Therefore we must keep two different memory layouts, abstract the rx descriptor + * representation and use ath10k_rx_desc_ops + * for correctly accessing rx descriptor data. */ + +/* base struct used for abstracting the rx descritor representation */ struct htt_rx_desc { union { /* This field is filled on the host using the msdu buffer @@ -2089,6 +2093,13 @@ struct htt_rx_desc { struct fw_rx_desc_base fw_desc; u32 pad; } __packed; +} __packed; + +/* rx descriptor for wcn3990 and possibly extensible for newer cards + * Buffers like this are placed on the rx ring. + */ +struct htt_rx_desc_v2 { + struct htt_rx_desc base; struct { struct rx_attention attention; struct rx_frag_info frag_info; @@ -2103,6 +2114,240 @@ struct htt_rx_desc { u8 msdu_payload[]; }; +/* QCA6174, QCA988x, QCA99x0 dedicated rx descriptor to make sure their firmware + * works correctly. We keep a single rx descriptor for all these three + * families of cards because from tests it seems to be the most stable solution, + * e.g. having a rx descriptor only for QCA6174 seldom caused firmware crashes + * during some tests. + * Buffers like this are placed on the rx ring. + */ +struct htt_rx_desc_v1 { + struct htt_rx_desc base; + struct { + struct rx_attention attention; + struct rx_frag_info_v1 frag_info; + struct rx_mpdu_start mpdu_start; + struct rx_msdu_start_v1 msdu_start; + struct rx_msdu_end_v1 msdu_end; + struct rx_mpdu_end mpdu_end; + struct rx_ppdu_start ppdu_start; + struct rx_ppdu_end_v1 ppdu_end; + } __packed; + u8 rx_hdr_status[RX_HTT_HDR_STATUS_LEN]; + u8 msdu_payload[]; +}; + +/* rx_desc abstraction */ +struct ath10k_htt_rx_desc_ops { + /* These fields are mandatory, they must be specified in any instance */ + + /* sizeof() of the rx_desc structure used by this hw */ + size_t rx_desc_size; + + /* offset of msdu_payload inside the rx_desc structure used by this hw */ + size_t rx_desc_msdu_payload_offset; + + /* These fields are options. + * When a field is not provided the default implementation gets used + * (see the ath10k_rx_desc_* operations below for more info about the defaults) + */ + bool (*rx_desc_get_msdu_limit_error)(struct htt_rx_desc *rxd); + int (*rx_desc_get_l3_pad_bytes)(struct htt_rx_desc *rxd); + + /* Safely cast from a void* buffer containing an rx descriptor + * to the proper rx_desc structure + */ + struct htt_rx_desc *(*rx_desc_from_raw_buffer)(void *buff); + + void (*rx_desc_get_offsets)(struct htt_rx_ring_rx_desc_offsets *offs); + struct rx_attention *(*rx_desc_get_attention)(struct htt_rx_desc *rxd); + struct rx_frag_info_common *(*rx_desc_get_frag_info)(struct htt_rx_desc *rxd); + struct rx_mpdu_start *(*rx_desc_get_mpdu_start)(struct htt_rx_desc *rxd); + struct rx_mpdu_end *(*rx_desc_get_mpdu_end)(struct htt_rx_desc *rxd); + struct rx_msdu_start_common *(*rx_desc_get_msdu_start)(struct htt_rx_desc *rxd); + struct rx_msdu_end_common *(*rx_desc_get_msdu_end)(struct htt_rx_desc *rxd); + struct rx_ppdu_start *(*rx_desc_get_ppdu_start)(struct htt_rx_desc *rxd); + struct rx_ppdu_end_common *(*rx_desc_get_ppdu_end)(struct htt_rx_desc *rxd); + u8 *(*rx_desc_get_rx_hdr_status)(struct htt_rx_desc *rxd); + u8 *(*rx_desc_get_msdu_payload)(struct htt_rx_desc *rxd); +}; + +extern const struct ath10k_htt_rx_desc_ops qca988x_rx_desc_ops; +extern const struct ath10k_htt_rx_desc_ops qca99x0_rx_desc_ops; +extern const struct ath10k_htt_rx_desc_ops wcn3990_rx_desc_ops; + +static inline int +ath10k_htt_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + if (hw->rx_desc_ops->rx_desc_get_l3_pad_bytes) + return hw->rx_desc_ops->rx_desc_get_l3_pad_bytes(rxd); + return 0; +} + +static inline bool +ath10k_htt_rx_desc_msdu_limit_error(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + if (hw->rx_desc_ops->rx_desc_get_msdu_limit_error) + return hw->rx_desc_ops->rx_desc_get_msdu_limit_error(rxd); + return false; +} + +/* The default implementation of all these getters is using the old rx_desc, + * so that it is easier to define the ath10k_htt_rx_desc_ops instances. + * But probably, if new wireless cards must be supported, it would be better + * to switch the default implementation to the new rx_desc, since this would + * make the extension easier . + */ +static inline struct htt_rx_desc * +ath10k_htt_rx_desc_from_raw_buffer(struct ath10k_hw_params *hw, void *buff) +{ + if (hw->rx_desc_ops->rx_desc_from_raw_buffer) + return hw->rx_desc_ops->rx_desc_from_raw_buffer(buff); + return &((struct htt_rx_desc_v1 *)buff)->base; +} + +static inline void +ath10k_htt_rx_desc_get_offsets(struct ath10k_hw_params *hw, + struct htt_rx_ring_rx_desc_offsets *off) +{ + if (hw->rx_desc_ops->rx_desc_get_offsets) { + hw->rx_desc_ops->rx_desc_get_offsets(off); + } else { +#define desc_offset(x) (offsetof(struct htt_rx_desc_v1, x) / 4) + off->mac80211_hdr_offset = __cpu_to_le16(desc_offset(rx_hdr_status)); + off->msdu_payload_offset = __cpu_to_le16(desc_offset(msdu_payload)); + off->ppdu_start_offset = __cpu_to_le16(desc_offset(ppdu_start)); + off->ppdu_end_offset = __cpu_to_le16(desc_offset(ppdu_end)); + off->mpdu_start_offset = __cpu_to_le16(desc_offset(mpdu_start)); + off->mpdu_end_offset = __cpu_to_le16(desc_offset(mpdu_end)); + off->msdu_start_offset = __cpu_to_le16(desc_offset(msdu_start)); + off->msdu_end_offset = __cpu_to_le16(desc_offset(msdu_end)); + off->rx_attention_offset = __cpu_to_le16(desc_offset(attention)); + off->frag_info_offset = __cpu_to_le16(desc_offset(frag_info)); +#undef desc_offset + } +} + +static inline struct rx_attention * +ath10k_htt_rx_desc_get_attention(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_attention) + return hw->rx_desc_ops->rx_desc_get_attention(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->attention; +} + +static inline struct rx_frag_info_common * +ath10k_htt_rx_desc_get_frag_info(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_frag_info) + return hw->rx_desc_ops->rx_desc_get_frag_info(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->frag_info.common; +} + +static inline struct rx_mpdu_start * +ath10k_htt_rx_desc_get_mpdu_start(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_mpdu_start) + return hw->rx_desc_ops->rx_desc_get_mpdu_start(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->mpdu_start; +} + +static inline struct rx_mpdu_end * +ath10k_htt_rx_desc_get_mpdu_end(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_mpdu_end) + return hw->rx_desc_ops->rx_desc_get_mpdu_end(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->mpdu_end; +} + +static inline struct rx_msdu_start_common * +ath10k_htt_rx_desc_get_msdu_start(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_msdu_start) + return hw->rx_desc_ops->rx_desc_get_msdu_start(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->msdu_start.common; +} + +static inline struct rx_msdu_end_common * +ath10k_htt_rx_desc_get_msdu_end(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_msdu_end) + return hw->rx_desc_ops->rx_desc_get_msdu_end(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->msdu_end.common; +} + +static inline struct rx_ppdu_start * +ath10k_htt_rx_desc_get_ppdu_start(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_ppdu_start) + return hw->rx_desc_ops->rx_desc_get_ppdu_start(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->ppdu_start; +} + +static inline struct rx_ppdu_end_common * +ath10k_htt_rx_desc_get_ppdu_end(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_ppdu_end) + return hw->rx_desc_ops->rx_desc_get_ppdu_end(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return &rx_desc->ppdu_end.common; +} + +static inline u8 * +ath10k_htt_rx_desc_get_rx_hdr_status(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_rx_hdr_status) + return hw->rx_desc_ops->rx_desc_get_rx_hdr_status(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return rx_desc->rx_hdr_status; +} + +static inline u8 * +ath10k_htt_rx_desc_get_msdu_payload(struct ath10k_hw_params *hw, struct htt_rx_desc *rxd) +{ + struct htt_rx_desc_v1 *rx_desc; + + if (hw->rx_desc_ops->rx_desc_get_msdu_payload) + return hw->rx_desc_ops->rx_desc_get_msdu_payload(rxd); + + rx_desc = container_of(rxd, struct htt_rx_desc_v1, base); + return rx_desc->msdu_payload; +} + #define HTT_RX_DESC_HL_INFO_SEQ_NUM_MASK 0x00000fff #define HTT_RX_DESC_HL_INFO_SEQ_NUM_LSB 0 #define HTT_RX_DESC_HL_INFO_ENCRYPTED_MASK 0x00001000 @@ -2136,7 +2381,14 @@ struct htt_rx_chan_info { * rounded up to a cache line size. */ #define HTT_RX_BUF_SIZE 2048 -#define HTT_RX_MSDU_SIZE (HTT_RX_BUF_SIZE - (int)sizeof(struct htt_rx_desc)) + +/* The HTT_RX_MSDU_SIZE can't be statically computed anymore, + * because it depends on the underlying device rx_desc representation + */ +static inline int ath10k_htt_rx_msdu_size(struct ath10k_hw_params *hw) +{ + return HTT_RX_BUF_SIZE - (int)hw->rx_desc_ops->rx_desc_size; +} /* Refill a bunch of RX buffers for each refill round so that FW/HW can handle * aggregated traffic more nicely. diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index adbaeb67eedf..9ad64ca84beb 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -21,7 +21,10 @@ #define HTT_RX_RING_REFILL_RESCHED_MS 5 -static int ath10k_htt_rx_get_csum_state(struct sk_buff *skb); +/* shortcut to interpret a raw memory buffer as a rx descriptor */ +#define HTT_RX_BUF_TO_RX_DESC(hw, buf) ath10k_htt_rx_desc_from_raw_buffer(hw, buf) + +static int ath10k_htt_rx_get_csum_state(struct ath10k_hw_params *hw, struct sk_buff *skb); static struct sk_buff * ath10k_htt_rx_find_skb_paddr(struct ath10k *ar, u64 paddr) @@ -128,6 +131,7 @@ static void *ath10k_htt_get_vaddr_ring_64(struct ath10k_htt *htt) static int __ath10k_htt_rx_ring_fill_n(struct ath10k_htt *htt, int num) { + struct ath10k_hw_params *hw = &htt->ar->hw_params; struct htt_rx_desc *rx_desc; struct ath10k_skb_rxcb *rxcb; struct sk_buff *skb; @@ -163,8 +167,8 @@ static int __ath10k_htt_rx_ring_fill_n(struct ath10k_htt *htt, int num) skb->data); /* Clear rx_desc attention word before posting to Rx ring */ - rx_desc = (struct htt_rx_desc *)skb->data; - rx_desc->attention.flags = __cpu_to_le32(0); + rx_desc = HTT_RX_BUF_TO_RX_DESC(hw, skb->data); + ath10k_htt_rx_desc_get_attention(hw, rx_desc)->flags = __cpu_to_le32(0); paddr = dma_map_single(htt->ar->dev, skb->data, skb->len + skb_tailroom(skb), @@ -343,9 +347,14 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt, struct sk_buff_head *amsdu) { struct ath10k *ar = htt->ar; + struct ath10k_hw_params *hw = &ar->hw_params; int msdu_len, msdu_chaining = 0; struct sk_buff *msdu; struct htt_rx_desc *rx_desc; + struct rx_attention *rx_desc_attention; + struct rx_frag_info_common *rx_desc_frag_info_common; + struct rx_msdu_start_common *rx_desc_msdu_start_common; + struct rx_msdu_end_common *rx_desc_msdu_end_common; lockdep_assert_held(&htt->rx_ring.lock); @@ -360,13 +369,18 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt, __skb_queue_tail(amsdu, msdu); - rx_desc = (struct htt_rx_desc *)msdu->data; + rx_desc = HTT_RX_BUF_TO_RX_DESC(hw, msdu->data); + rx_desc_attention = ath10k_htt_rx_desc_get_attention(hw, rx_desc); + rx_desc_msdu_start_common = ath10k_htt_rx_desc_get_msdu_start(hw, + rx_desc); + rx_desc_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rx_desc); + rx_desc_frag_info_common = ath10k_htt_rx_desc_get_frag_info(hw, rx_desc); /* FIXME: we must report msdu payload since this is what caller * expects now */ - skb_put(msdu, offsetof(struct htt_rx_desc, msdu_payload)); - skb_pull(msdu, offsetof(struct htt_rx_desc, msdu_payload)); + skb_put(msdu, hw->rx_desc_ops->rx_desc_msdu_payload_offset); + skb_pull(msdu, hw->rx_desc_ops->rx_desc_msdu_payload_offset); /* * Sanity check - confirm the HW is finished filling in the @@ -376,24 +390,24 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt, * To prevent the case that we handle a stale Rx descriptor, * just assert for now until we have a way to recover. */ - if (!(__le32_to_cpu(rx_desc->attention.flags) + if (!(__le32_to_cpu(rx_desc_attention->flags) & RX_ATTENTION_FLAGS_MSDU_DONE)) { __skb_queue_purge(amsdu); return -EIO; } - msdu_len_invalid = !!(__le32_to_cpu(rx_desc->attention.flags) + msdu_len_invalid = !!(__le32_to_cpu(rx_desc_attention->flags) & (RX_ATTENTION_FLAGS_MPDU_LENGTH_ERR | RX_ATTENTION_FLAGS_MSDU_LENGTH_ERR)); - msdu_len = MS(__le32_to_cpu(rx_desc->msdu_start.common.info0), + msdu_len = MS(__le32_to_cpu(rx_desc_msdu_start_common->info0), RX_MSDU_START_INFO0_MSDU_LENGTH); - msdu_chained = rx_desc->frag_info.ring2_more_count; + msdu_chained = rx_desc_frag_info_common->ring2_more_count; if (msdu_len_invalid) msdu_len = 0; skb_trim(msdu, 0); - skb_put(msdu, min(msdu_len, HTT_RX_MSDU_SIZE)); + skb_put(msdu, min(msdu_len, ath10k_htt_rx_msdu_size(hw))); msdu_len -= msdu->len; /* Note: Chained buffers do not contain rx descriptor */ @@ -411,11 +425,12 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt, msdu_chaining = 1; } - last_msdu = __le32_to_cpu(rx_desc->msdu_end.common.info0) & + last_msdu = __le32_to_cpu(rx_desc_msdu_end_common->info0) & RX_MSDU_END_INFO0_LAST_MSDU; - trace_ath10k_htt_rx_desc(ar, &rx_desc->attention, - sizeof(*rx_desc) - sizeof(u32)); + /* FIXME: why are we skipping the first part of the rx_desc? */ + trace_ath10k_htt_rx_desc(ar, rx_desc + sizeof(u32), + hw->rx_desc_ops->rx_desc_size - sizeof(u32)); if (last_msdu) break; @@ -480,6 +495,7 @@ static int ath10k_htt_rx_handle_amsdu_mon_32(struct ath10k_htt *htt, struct htt_rx_in_ord_msdu_desc **msdu_desc) { struct ath10k *ar = htt->ar; + struct ath10k_hw_params *hw = &ar->hw_params; u32 paddr; struct sk_buff *frag_buf; struct sk_buff *prev_frag_buf; @@ -488,12 +504,12 @@ static int ath10k_htt_rx_handle_amsdu_mon_32(struct ath10k_htt *htt, struct htt_rx_desc *rxd; int amsdu_len = __le16_to_cpu(ind_desc->msdu_len); - rxd = (void *)msdu->data; - trace_ath10k_htt_rx_desc(ar, rxd, sizeof(*rxd)); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, msdu->data); + trace_ath10k_htt_rx_desc(ar, rxd, hw->rx_desc_ops->rx_desc_size); - skb_put(msdu, sizeof(struct htt_rx_desc)); - skb_pull(msdu, sizeof(struct htt_rx_desc)); - skb_put(msdu, min(amsdu_len, HTT_RX_MSDU_SIZE)); + skb_put(msdu, hw->rx_desc_ops->rx_desc_size); + skb_pull(msdu, hw->rx_desc_ops->rx_desc_size); + skb_put(msdu, min(amsdu_len, ath10k_htt_rx_msdu_size(hw))); amsdu_len -= msdu->len; last_frag = ind_desc->reserved; @@ -556,6 +572,7 @@ ath10k_htt_rx_handle_amsdu_mon_64(struct ath10k_htt *htt, struct htt_rx_in_ord_msdu_desc_ext **msdu_desc) { struct ath10k *ar = htt->ar; + struct ath10k_hw_params *hw = &ar->hw_params; u64 paddr; struct sk_buff *frag_buf; struct sk_buff *prev_frag_buf; @@ -564,12 +581,12 @@ ath10k_htt_rx_handle_amsdu_mon_64(struct ath10k_htt *htt, struct htt_rx_desc *rxd; int amsdu_len = __le16_to_cpu(ind_desc->msdu_len); - rxd = (void *)msdu->data; - trace_ath10k_htt_rx_desc(ar, rxd, sizeof(*rxd)); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, msdu->data); + trace_ath10k_htt_rx_desc(ar, rxd, hw->rx_desc_ops->rx_desc_size); - skb_put(msdu, sizeof(struct htt_rx_desc)); - skb_pull(msdu, sizeof(struct htt_rx_desc)); - skb_put(msdu, min(amsdu_len, HTT_RX_MSDU_SIZE)); + skb_put(msdu, hw->rx_desc_ops->rx_desc_size); + skb_pull(msdu, hw->rx_desc_ops->rx_desc_size); + skb_put(msdu, min(amsdu_len, ath10k_htt_rx_msdu_size(hw))); amsdu_len -= msdu->len; last_frag = ind_desc->reserved; @@ -631,8 +648,10 @@ static int ath10k_htt_rx_pop_paddr32_list(struct ath10k_htt *htt, struct sk_buff_head *list) { struct ath10k *ar = htt->ar; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_in_ord_msdu_desc *msdu_desc = ev->msdu_descs32; struct htt_rx_desc *rxd; + struct rx_attention *rxd_attention; struct sk_buff *msdu; int msdu_count, ret; bool is_offload; @@ -667,15 +686,16 @@ static int ath10k_htt_rx_pop_paddr32_list(struct ath10k_htt *htt, __skb_queue_tail(list, msdu); if (!is_offload) { - rxd = (void *)msdu->data; + rxd = HTT_RX_BUF_TO_RX_DESC(hw, msdu->data); + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); - trace_ath10k_htt_rx_desc(ar, rxd, sizeof(*rxd)); + trace_ath10k_htt_rx_desc(ar, rxd, hw->rx_desc_ops->rx_desc_size); - skb_put(msdu, sizeof(*rxd)); - skb_pull(msdu, sizeof(*rxd)); + skb_put(msdu, hw->rx_desc_ops->rx_desc_size); + skb_pull(msdu, hw->rx_desc_ops->rx_desc_size); skb_put(msdu, __le16_to_cpu(msdu_desc->msdu_len)); - if (!(__le32_to_cpu(rxd->attention.flags) & + if (!(__le32_to_cpu(rxd_attention->flags) & RX_ATTENTION_FLAGS_MSDU_DONE)) { ath10k_warn(htt->ar, "tried to pop an incomplete frame, oops!\n"); return -EIO; @@ -693,8 +713,10 @@ static int ath10k_htt_rx_pop_paddr64_list(struct ath10k_htt *htt, struct sk_buff_head *list) { struct ath10k *ar = htt->ar; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_in_ord_msdu_desc_ext *msdu_desc = ev->msdu_descs64; struct htt_rx_desc *rxd; + struct rx_attention *rxd_attention; struct sk_buff *msdu; int msdu_count, ret; bool is_offload; @@ -728,15 +750,16 @@ static int ath10k_htt_rx_pop_paddr64_list(struct ath10k_htt *htt, __skb_queue_tail(list, msdu); if (!is_offload) { - rxd = (void *)msdu->data; + rxd = HTT_RX_BUF_TO_RX_DESC(hw, msdu->data); + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); - trace_ath10k_htt_rx_desc(ar, rxd, sizeof(*rxd)); + trace_ath10k_htt_rx_desc(ar, rxd, hw->rx_desc_ops->rx_desc_size); - skb_put(msdu, sizeof(*rxd)); - skb_pull(msdu, sizeof(*rxd)); + skb_put(msdu, hw->rx_desc_ops->rx_desc_size); + skb_pull(msdu, hw->rx_desc_ops->rx_desc_size); skb_put(msdu, __le16_to_cpu(msdu_desc->msdu_len)); - if (!(__le32_to_cpu(rxd->attention.flags) & + if (!(__le32_to_cpu(rxd_attention->flags) & RX_ATTENTION_FLAGS_MSDU_DONE)) { ath10k_warn(htt->ar, "tried to pop an incomplete frame, oops!\n"); return -EIO; @@ -944,16 +967,32 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar, struct ieee80211_rx_status *status, struct htt_rx_desc *rxd) { + struct ath10k_hw_params *hw = &ar->hw_params; + struct rx_attention *rxd_attention; + struct rx_mpdu_start *rxd_mpdu_start; + struct rx_mpdu_end *rxd_mpdu_end; + struct rx_msdu_start_common *rxd_msdu_start_common; + struct rx_msdu_end_common *rxd_msdu_end_common; + struct rx_ppdu_start *rxd_ppdu_start; struct ieee80211_supported_band *sband; u8 cck, rate, bw, sgi, mcs, nss; + u8 *rxd_msdu_payload; u8 preamble = 0; u8 group_id; u32 info1, info2, info3; u32 stbc, nsts_su; - info1 = __le32_to_cpu(rxd->ppdu_start.info1); - info2 = __le32_to_cpu(rxd->ppdu_start.info2); - info3 = __le32_to_cpu(rxd->ppdu_start.info3); + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); + rxd_mpdu_start = ath10k_htt_rx_desc_get_mpdu_start(hw, rxd); + rxd_mpdu_end = ath10k_htt_rx_desc_get_mpdu_end(hw, rxd); + rxd_msdu_start_common = ath10k_htt_rx_desc_get_msdu_start(hw, rxd); + rxd_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rxd); + rxd_ppdu_start = ath10k_htt_rx_desc_get_ppdu_start(hw, rxd); + rxd_msdu_payload = ath10k_htt_rx_desc_get_msdu_payload(hw, rxd); + + info1 = __le32_to_cpu(rxd_ppdu_start->info1); + info2 = __le32_to_cpu(rxd_ppdu_start->info2); + info3 = __le32_to_cpu(rxd_ppdu_start->info3); preamble = MS(info1, RX_PPDU_START_INFO1_PREAMBLE_TYPE); @@ -1022,24 +1061,24 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar, if (mcs > 0x09) { ath10k_warn(ar, "invalid MCS received %u\n", mcs); ath10k_warn(ar, "rxd %08x mpdu start %08x %08x msdu start %08x %08x ppdu start %08x %08x %08x %08x %08x\n", - __le32_to_cpu(rxd->attention.flags), - __le32_to_cpu(rxd->mpdu_start.info0), - __le32_to_cpu(rxd->mpdu_start.info1), - __le32_to_cpu(rxd->msdu_start.common.info0), - __le32_to_cpu(rxd->msdu_start.common.info1), - rxd->ppdu_start.info0, - __le32_to_cpu(rxd->ppdu_start.info1), - __le32_to_cpu(rxd->ppdu_start.info2), - __le32_to_cpu(rxd->ppdu_start.info3), - __le32_to_cpu(rxd->ppdu_start.info4)); + __le32_to_cpu(rxd_attention->flags), + __le32_to_cpu(rxd_mpdu_start->info0), + __le32_to_cpu(rxd_mpdu_start->info1), + __le32_to_cpu(rxd_msdu_start_common->info0), + __le32_to_cpu(rxd_msdu_start_common->info1), + rxd_ppdu_start->info0, + __le32_to_cpu(rxd_ppdu_start->info1), + __le32_to_cpu(rxd_ppdu_start->info2), + __le32_to_cpu(rxd_ppdu_start->info3), + __le32_to_cpu(rxd_ppdu_start->info4)); ath10k_warn(ar, "msdu end %08x mpdu end %08x\n", - __le32_to_cpu(rxd->msdu_end.common.info0), - __le32_to_cpu(rxd->mpdu_end.info0)); + __le32_to_cpu(rxd_msdu_end_common->info0), + __le32_to_cpu(rxd_mpdu_end->info0)); ath10k_dbg_dump(ar, ATH10K_DBG_HTT_DUMP, NULL, "rx desc msdu payload: ", - rxd->msdu_payload, 50); + rxd_msdu_payload, 50); } status->rate_idx = mcs; @@ -1059,6 +1098,10 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar, static struct ieee80211_channel * ath10k_htt_rx_h_peer_channel(struct ath10k *ar, struct htt_rx_desc *rxd) { + struct ath10k_hw_params *hw = &ar->hw_params; + struct rx_attention *rxd_attention; + struct rx_msdu_end_common *rxd_msdu_end_common; + struct rx_mpdu_start *rxd_mpdu_start; struct ath10k_peer *peer; struct ath10k_vif *arvif; struct cfg80211_chan_def def; @@ -1069,15 +1112,19 @@ ath10k_htt_rx_h_peer_channel(struct ath10k *ar, struct htt_rx_desc *rxd) if (!rxd) return NULL; - if (rxd->attention.flags & + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); + rxd_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rxd); + rxd_mpdu_start = ath10k_htt_rx_desc_get_mpdu_start(hw, rxd); + + if (rxd_attention->flags & __cpu_to_le32(RX_ATTENTION_FLAGS_PEER_IDX_INVALID)) return NULL; - if (!(rxd->msdu_end.common.info0 & + if (!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_FIRST_MSDU))) return NULL; - peer_id = MS(__le32_to_cpu(rxd->mpdu_start.info0), + peer_id = MS(__le32_to_cpu(rxd_mpdu_start->info0), RX_MPDU_START_INFO0_PEER_IDX); peer = ath10k_peer_find_by_id(ar, peer_id); @@ -1167,14 +1214,16 @@ static void ath10k_htt_rx_h_signal(struct ath10k *ar, struct ieee80211_rx_status *status, struct htt_rx_desc *rxd) { + struct ath10k_hw_params *hw = &ar->hw_params; + struct rx_ppdu_start *rxd_ppdu_start = ath10k_htt_rx_desc_get_ppdu_start(hw, rxd); int i; for (i = 0; i < IEEE80211_MAX_CHAINS ; i++) { status->chains &= ~BIT(i); - if (rxd->ppdu_start.rssi_chains[i].pri20_mhz != 0x80) { + if (rxd_ppdu_start->rssi_chains[i].pri20_mhz != 0x80) { status->chain_signal[i] = ATH10K_DEFAULT_NOISE_FLOOR + - rxd->ppdu_start.rssi_chains[i].pri20_mhz; + rxd_ppdu_start->rssi_chains[i].pri20_mhz; status->chains |= BIT(i); } @@ -1182,7 +1231,7 @@ static void ath10k_htt_rx_h_signal(struct ath10k *ar, /* FIXME: Get real NF */ status->signal = ATH10K_DEFAULT_NOISE_FLOOR + - rxd->ppdu_start.rssi_comb; + rxd_ppdu_start->rssi_comb; status->flag &= ~RX_FLAG_NO_SIGNAL_VAL; } @@ -1190,13 +1239,18 @@ static void ath10k_htt_rx_h_mactime(struct ath10k *ar, struct ieee80211_rx_status *status, struct htt_rx_desc *rxd) { + struct ath10k_hw_params *hw = &ar->hw_params; + struct rx_ppdu_end_common *rxd_ppdu_end_common; + + rxd_ppdu_end_common = ath10k_htt_rx_desc_get_ppdu_end(hw, rxd); + /* FIXME: TSF is known only at the end of PPDU, in the last MPDU. This * means all prior MSDUs in a PPDU are reported to mac80211 without the * TSF. Is it worth holding frames until end of PPDU is known? * * FIXME: Can we get/compute 64bit TSF? */ - status->mactime = __le32_to_cpu(rxd->ppdu_end.common.tsf_timestamp); + status->mactime = __le32_to_cpu(rxd_ppdu_end_common->tsf_timestamp); status->flag |= RX_FLAG_MACTIME_END; } @@ -1206,7 +1260,9 @@ static void ath10k_htt_rx_h_ppdu(struct ath10k *ar, u32 vdev_id) { struct sk_buff *first; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_desc *rxd; + struct rx_attention *rxd_attention; bool is_first_ppdu; bool is_last_ppdu; @@ -1214,11 +1270,14 @@ static void ath10k_htt_rx_h_ppdu(struct ath10k *ar, return; first = skb_peek(amsdu); - rxd = (void *)first->data - sizeof(*rxd); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)first->data - hw->rx_desc_ops->rx_desc_size); - is_first_ppdu = !!(rxd->attention.flags & + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); + + is_first_ppdu = !!(rxd_attention->flags & __cpu_to_le32(RX_ATTENTION_FLAGS_FIRST_MPDU)); - is_last_ppdu = !!(rxd->attention.flags & + is_last_ppdu = !!(rxd_attention->flags & __cpu_to_le32(RX_ATTENTION_FLAGS_LAST_MPDU)); if (is_first_ppdu) { @@ -1357,7 +1416,9 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar, const u8 first_hdr[64]) { struct ieee80211_hdr *hdr; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_desc *rxd; + struct rx_msdu_end_common *rxd_msdu_end_common; size_t hdr_len; size_t crypto_len; bool is_first; @@ -1366,10 +1427,13 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar, int bytes_aligned = ar->hw_params.decap_align_bytes; u8 *qos; - rxd = (void *)msdu->data - sizeof(*rxd); - is_first = !!(rxd->msdu_end.common.info0 & + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)msdu->data - hw->rx_desc_ops->rx_desc_size); + + rxd_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rxd); + is_first = !!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_FIRST_MSDU)); - is_last = !!(rxd->msdu_end.common.info0 & + is_last = !!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU)); /* Delivered decapped frame: @@ -1387,7 +1451,7 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar, * error packets. If limit exceeds, hw sends all remaining MSDUs as * a single last MSDU with this msdu limit error set. */ - msdu_limit_err = ath10k_rx_desc_msdu_limit_error(&ar->hw_params, rxd); + msdu_limit_err = ath10k_htt_rx_desc_msdu_limit_error(hw, rxd); /* If MSDU limit error happens, then don't warn on, the partial raw MSDU * without first MSDU is expected in that case, and handled later here. @@ -1479,6 +1543,7 @@ static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, const u8 first_hdr[64], enum htt_rx_mpdu_encrypt_type enctype) { + struct ath10k_hw_params *hw = &ar->hw_params; struct ieee80211_hdr *hdr; struct htt_rx_desc *rxd; size_t hdr_len; @@ -1499,9 +1564,10 @@ static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, */ /* pull decapped header and copy SA & DA */ - rxd = (void *)msdu->data - sizeof(*rxd); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, (void *)msdu->data - + hw->rx_desc_ops->rx_desc_size); - l3_pad_bytes = ath10k_rx_desc_get_l3_pad_bytes(&ar->hw_params, rxd); + l3_pad_bytes = ath10k_htt_rx_desc_get_l3_pad_bytes(&ar->hw_params, rxd); skb_put(msdu, l3_pad_bytes); hdr = (struct ieee80211_hdr *)(msdu->data + l3_pad_bytes); @@ -1537,18 +1603,25 @@ static void *ath10k_htt_rx_h_find_rfc1042(struct ath10k *ar, enum htt_rx_mpdu_encrypt_type enctype) { struct ieee80211_hdr *hdr; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_desc *rxd; + struct rx_msdu_end_common *rxd_msdu_end_common; + u8 *rxd_rx_hdr_status; size_t hdr_len, crypto_len; void *rfc1042; bool is_first, is_last, is_amsdu; int bytes_aligned = ar->hw_params.decap_align_bytes; - rxd = (void *)msdu->data - sizeof(*rxd); - hdr = (void *)rxd->rx_hdr_status; + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)msdu->data - hw->rx_desc_ops->rx_desc_size); + + rxd_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rxd); + rxd_rx_hdr_status = ath10k_htt_rx_desc_get_rx_hdr_status(hw, rxd); + hdr = (void *)rxd_rx_hdr_status; - is_first = !!(rxd->msdu_end.common.info0 & + is_first = !!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_FIRST_MSDU)); - is_last = !!(rxd->msdu_end.common.info0 & + is_last = !!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU)); is_amsdu = !(is_first && is_last); @@ -1574,6 +1647,7 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, const u8 first_hdr[64], enum htt_rx_mpdu_encrypt_type enctype) { + struct ath10k_hw_params *hw = &ar->hw_params; struct ieee80211_hdr *hdr; struct ethhdr *eth; size_t hdr_len; @@ -1593,8 +1667,10 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, if (WARN_ON_ONCE(!rfc1042)) return; - rxd = (void *)msdu->data - sizeof(*rxd); - l3_pad_bytes = ath10k_rx_desc_get_l3_pad_bytes(&ar->hw_params, rxd); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)msdu->data - hw->rx_desc_ops->rx_desc_size); + + l3_pad_bytes = ath10k_htt_rx_desc_get_l3_pad_bytes(&ar->hw_params, rxd); skb_put(msdu, l3_pad_bytes); skb_pull(msdu, l3_pad_bytes); @@ -1635,6 +1711,7 @@ static void ath10k_htt_rx_h_undecap_snap(struct ath10k *ar, const u8 first_hdr[64], enum htt_rx_mpdu_encrypt_type enctype) { + struct ath10k_hw_params *hw = &ar->hw_params; struct ieee80211_hdr *hdr; size_t hdr_len; int l3_pad_bytes; @@ -1647,8 +1724,10 @@ static void ath10k_htt_rx_h_undecap_snap(struct ath10k *ar, * [payload] */ - rxd = (void *)msdu->data - sizeof(*rxd); - l3_pad_bytes = ath10k_rx_desc_get_l3_pad_bytes(&ar->hw_params, rxd); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)msdu->data - hw->rx_desc_ops->rx_desc_size); + + l3_pad_bytes = ath10k_htt_rx_desc_get_l3_pad_bytes(&ar->hw_params, rxd); skb_put(msdu, l3_pad_bytes); skb_pull(msdu, sizeof(struct amsdu_subframe_hdr) + l3_pad_bytes); @@ -1673,7 +1752,9 @@ static void ath10k_htt_rx_h_undecap(struct ath10k *ar, enum htt_rx_mpdu_encrypt_type enctype, bool is_decrypted) { + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_desc *rxd; + struct rx_msdu_start_common *rxd_msdu_start_common; enum rx_msdu_decap_format decap; /* First msdu's decapped header: @@ -1687,8 +1768,11 @@ static void ath10k_htt_rx_h_undecap(struct ath10k *ar, * [rfc1042/llc] */ - rxd = (void *)msdu->data - sizeof(*rxd); - decap = MS(__le32_to_cpu(rxd->msdu_start.common.info1), + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)msdu->data - hw->rx_desc_ops->rx_desc_size); + + rxd_msdu_start_common = ath10k_htt_rx_desc_get_msdu_start(hw, rxd); + decap = MS(__le32_to_cpu(rxd_msdu_start_common->info1), RX_MSDU_START_INFO1_DECAP_FORMAT); switch (decap) { @@ -1710,17 +1794,23 @@ static void ath10k_htt_rx_h_undecap(struct ath10k *ar, } } -static int ath10k_htt_rx_get_csum_state(struct sk_buff *skb) +static int ath10k_htt_rx_get_csum_state(struct ath10k_hw_params *hw, struct sk_buff *skb) { struct htt_rx_desc *rxd; + struct rx_attention *rxd_attention; + struct rx_msdu_start_common *rxd_msdu_start_common; u32 flags, info; bool is_ip4, is_ip6; bool is_tcp, is_udp; bool ip_csum_ok, tcpudp_csum_ok; - rxd = (void *)skb->data - sizeof(*rxd); - flags = __le32_to_cpu(rxd->attention.flags); - info = __le32_to_cpu(rxd->msdu_start.common.info1); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)skb->data - hw->rx_desc_ops->rx_desc_size); + + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); + rxd_msdu_start_common = ath10k_htt_rx_desc_get_msdu_start(hw, rxd); + flags = __le32_to_cpu(rxd_attention->flags); + info = __le32_to_cpu(rxd_msdu_start_common->info1); is_ip4 = !!(info & RX_MSDU_START_INFO1_IPV4_PROTO); is_ip6 = !!(info & RX_MSDU_START_INFO1_IPV6_PROTO); @@ -1741,9 +1831,10 @@ static int ath10k_htt_rx_get_csum_state(struct sk_buff *skb) return CHECKSUM_UNNECESSARY; } -static void ath10k_htt_rx_h_csum_offload(struct sk_buff *msdu) +static void ath10k_htt_rx_h_csum_offload(struct ath10k_hw_params *hw, + struct sk_buff *msdu) { - msdu->ip_summed = ath10k_htt_rx_get_csum_state(msdu); + msdu->ip_summed = ath10k_htt_rx_get_csum_state(hw, msdu); } static u64 ath10k_htt_rx_h_get_pn(struct ath10k *ar, struct sk_buff *skb, @@ -1835,7 +1926,11 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, struct sk_buff *first; struct sk_buff *last; struct sk_buff *msdu, *temp; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_desc *rxd; + struct rx_attention *rxd_attention; + struct rx_mpdu_start *rxd_mpdu_start; + struct ieee80211_hdr *hdr; enum htt_rx_mpdu_encrypt_type enctype; u8 first_hdr[64]; @@ -1853,18 +1948,22 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, return; first = skb_peek(amsdu); - rxd = (void *)first->data - sizeof(*rxd); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)first->data - hw->rx_desc_ops->rx_desc_size); - is_mgmt = !!(rxd->attention.flags & + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); + rxd_mpdu_start = ath10k_htt_rx_desc_get_mpdu_start(hw, rxd); + + is_mgmt = !!(rxd_attention->flags & __cpu_to_le32(RX_ATTENTION_FLAGS_MGMT_TYPE)); - enctype = MS(__le32_to_cpu(rxd->mpdu_start.info0), + enctype = MS(__le32_to_cpu(rxd_mpdu_start->info0), RX_MPDU_START_INFO0_ENCRYPT_TYPE); /* First MSDU's Rx descriptor in an A-MSDU contains full 802.11 * decapped header. It'll be used for undecapping of each MSDU. */ - hdr = (void *)rxd->rx_hdr_status; + hdr = (void *)ath10k_htt_rx_desc_get_rx_hdr_status(hw, rxd); memcpy(first_hdr, hdr, RX_HTT_HDR_STATUS_LEN); if (rx_hdr) @@ -1882,8 +1981,11 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, /* Some attention flags are valid only in the last MSDU. */ last = skb_peek_tail(amsdu); - rxd = (void *)last->data - sizeof(*rxd); - attention = __le32_to_cpu(rxd->attention.flags); + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)last->data - hw->rx_desc_ops->rx_desc_size); + + rxd_attention = ath10k_htt_rx_desc_get_attention(hw, rxd); + attention = __le32_to_cpu(rxd_attention->flags); has_fcs_err = !!(attention & RX_ATTENTION_FLAGS_FCS_ERR); has_crypto_err = !!(attention & RX_ATTENTION_FLAGS_DECRYPT_ERR); @@ -1971,7 +2073,7 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, continue; } - ath10k_htt_rx_h_csum_offload(msdu); + ath10k_htt_rx_h_csum_offload(&ar->hw_params, msdu); if (frag && !fill_crypt_header && enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA) @@ -2083,12 +2185,19 @@ static void ath10k_htt_rx_h_unchain(struct ath10k *ar, unsigned long *unchain_cnt) { struct sk_buff *first; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_desc *rxd; + struct rx_msdu_start_common *rxd_msdu_start_common; + struct rx_frag_info_common *rxd_frag_info; enum rx_msdu_decap_format decap; first = skb_peek(amsdu); - rxd = (void *)first->data - sizeof(*rxd); - decap = MS(__le32_to_cpu(rxd->msdu_start.common.info1), + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)first->data - hw->rx_desc_ops->rx_desc_size); + + rxd_msdu_start_common = ath10k_htt_rx_desc_get_msdu_start(hw, rxd); + rxd_frag_info = ath10k_htt_rx_desc_get_frag_info(hw, rxd); + decap = MS(__le32_to_cpu(rxd_msdu_start_common->info1), RX_MSDU_START_INFO1_DECAP_FORMAT); /* FIXME: Current unchaining logic can only handle simple case of raw @@ -2097,7 +2206,7 @@ static void ath10k_htt_rx_h_unchain(struct ath10k *ar, * try re-constructing such frames - it'll be pretty much garbage. */ if (decap != RX_MSDU_DECAP_RAW || - skb_queue_len(amsdu) != 1 + rxd->frag_info.ring2_more_count) { + skb_queue_len(amsdu) != 1 + rxd_frag_info->ring2_more_count) { *drop_cnt += skb_queue_len(amsdu); __skb_queue_purge(amsdu); return; @@ -2112,7 +2221,10 @@ static bool ath10k_htt_rx_validate_amsdu(struct ath10k *ar, u8 *subframe_hdr; struct sk_buff *first; bool is_first, is_last; + struct ath10k_hw_params *hw = &ar->hw_params; struct htt_rx_desc *rxd; + struct rx_msdu_end_common *rxd_msdu_end_common; + struct rx_mpdu_start *rxd_mpdu_start; struct ieee80211_hdr *hdr; size_t hdr_len, crypto_len; enum htt_rx_mpdu_encrypt_type enctype; @@ -2120,12 +2232,16 @@ static bool ath10k_htt_rx_validate_amsdu(struct ath10k *ar, first = skb_peek(amsdu); - rxd = (void *)first->data - sizeof(*rxd); - hdr = (void *)rxd->rx_hdr_status; + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)first->data - hw->rx_desc_ops->rx_desc_size); + + rxd_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rxd); + rxd_mpdu_start = ath10k_htt_rx_desc_get_mpdu_start(hw, rxd); + hdr = (void *)ath10k_htt_rx_desc_get_rx_hdr_status(hw, rxd); - is_first = !!(rxd->msdu_end.common.info0 & + is_first = !!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_FIRST_MSDU)); - is_last = !!(rxd->msdu_end.common.info0 & + is_last = !!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU)); /* Return in case of non-aggregated msdu */ @@ -2136,7 +2252,7 @@ static bool ath10k_htt_rx_validate_amsdu(struct ath10k *ar, if (!is_first) return false; - enctype = MS(__le32_to_cpu(rxd->mpdu_start.info0), + enctype = MS(__le32_to_cpu(rxd_mpdu_start->info0), RX_MPDU_START_INFO0_ENCRYPT_TYPE); hdr_len = ieee80211_hdrlen(hdr->frame_control); @@ -3028,11 +3144,13 @@ static void ath10k_htt_rx_delba(struct ath10k *ar, struct htt_resp *resp) spin_unlock_bh(&ar->data_lock); } -static int ath10k_htt_rx_extract_amsdu(struct sk_buff_head *list, +static int ath10k_htt_rx_extract_amsdu(struct ath10k_hw_params *hw, + struct sk_buff_head *list, struct sk_buff_head *amsdu) { struct sk_buff *msdu; struct htt_rx_desc *rxd; + struct rx_msdu_end_common *rxd_msdu_end_common; if (skb_queue_empty(list)) return -ENOBUFS; @@ -3043,15 +3161,22 @@ static int ath10k_htt_rx_extract_amsdu(struct sk_buff_head *list, while ((msdu = __skb_dequeue(list))) { __skb_queue_tail(amsdu, msdu); - rxd = (void *)msdu->data - sizeof(*rxd); - if (rxd->msdu_end.common.info0 & + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)msdu->data - + hw->rx_desc_ops->rx_desc_size); + + rxd_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rxd); + if (rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU)) break; } msdu = skb_peek_tail(amsdu); - rxd = (void *)msdu->data - sizeof(*rxd); - if (!(rxd->msdu_end.common.info0 & + rxd = HTT_RX_BUF_TO_RX_DESC(hw, + (void *)msdu->data - hw->rx_desc_ops->rx_desc_size); + + rxd_msdu_end_common = ath10k_htt_rx_desc_get_msdu_end(hw, rxd); + if (!(rxd_msdu_end_common->info0 & __cpu_to_le32(RX_MSDU_END_INFO0_LAST_MSDU))) { skb_queue_splice_init(amsdu, list); return -EAGAIN; @@ -3194,7 +3319,7 @@ static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb) while (!skb_queue_empty(&list)) { __skb_queue_head_init(&amsdu); - ret = ath10k_htt_rx_extract_amsdu(&list, &amsdu); + ret = ath10k_htt_rx_extract_amsdu(&ar->hw_params, &list, &amsdu); switch (ret) { case 0: /* Note: The in-order indication may report interleaved diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c index b793eac2cfac..9842a4b2f78f 100644 --- a/drivers/net/wireless/ath/ath10k/htt_tx.c +++ b/drivers/net/wireless/ath/ath10k/htt_tx.c @@ -796,47 +796,26 @@ static int ath10k_htt_send_frag_desc_bank_cfg_64(struct ath10k_htt *htt) return 0; } -static void ath10k_htt_fill_rx_desc_offset_32(void *rx_ring) +static void ath10k_htt_fill_rx_desc_offset_32(struct ath10k_hw_params *hw, void *rx_ring) { struct htt_rx_ring_setup_ring32 *ring = (struct htt_rx_ring_setup_ring32 *)rx_ring; -#define desc_offset(x) (offsetof(struct htt_rx_desc, x) / 4) - ring->mac80211_hdr_offset = __cpu_to_le16(desc_offset(rx_hdr_status)); - ring->msdu_payload_offset = __cpu_to_le16(desc_offset(msdu_payload)); - ring->ppdu_start_offset = __cpu_to_le16(desc_offset(ppdu_start)); - ring->ppdu_end_offset = __cpu_to_le16(desc_offset(ppdu_end)); - ring->mpdu_start_offset = __cpu_to_le16(desc_offset(mpdu_start)); - ring->mpdu_end_offset = __cpu_to_le16(desc_offset(mpdu_end)); - ring->msdu_start_offset = __cpu_to_le16(desc_offset(msdu_start)); - ring->msdu_end_offset = __cpu_to_le16(desc_offset(msdu_end)); - ring->rx_attention_offset = __cpu_to_le16(desc_offset(attention)); - ring->frag_info_offset = __cpu_to_le16(desc_offset(frag_info)); -#undef desc_offset + ath10k_htt_rx_desc_get_offsets(hw, &ring->offsets); } -static void ath10k_htt_fill_rx_desc_offset_64(void *rx_ring) +static void ath10k_htt_fill_rx_desc_offset_64(struct ath10k_hw_params *hw, void *rx_ring) { struct htt_rx_ring_setup_ring64 *ring = (struct htt_rx_ring_setup_ring64 *)rx_ring; -#define desc_offset(x) (offsetof(struct htt_rx_desc, x) / 4) - ring->mac80211_hdr_offset = __cpu_to_le16(desc_offset(rx_hdr_status)); - ring->msdu_payload_offset = __cpu_to_le16(desc_offset(msdu_payload)); - ring->ppdu_start_offset = __cpu_to_le16(desc_offset(ppdu_start)); - ring->ppdu_end_offset = __cpu_to_le16(desc_offset(ppdu_end)); - ring->mpdu_start_offset = __cpu_to_le16(desc_offset(mpdu_start)); - ring->mpdu_end_offset = __cpu_to_le16(desc_offset(mpdu_end)); - ring->msdu_start_offset = __cpu_to_le16(desc_offset(msdu_start)); - ring->msdu_end_offset = __cpu_to_le16(desc_offset(msdu_end)); - ring->rx_attention_offset = __cpu_to_le16(desc_offset(attention)); - ring->frag_info_offset = __cpu_to_le16(desc_offset(frag_info)); -#undef desc_offset + ath10k_htt_rx_desc_get_offsets(hw, &ring->offsets); } static int ath10k_htt_send_rx_ring_cfg_32(struct ath10k_htt *htt) { struct ath10k *ar = htt->ar; + struct ath10k_hw_params *hw = &ar->hw_params; struct sk_buff *skb; struct htt_cmd *cmd; struct htt_rx_ring_setup_ring32 *ring; @@ -896,7 +875,7 @@ static int ath10k_htt_send_rx_ring_cfg_32(struct ath10k_htt *htt) ring->flags = __cpu_to_le16(flags); ring->fw_idx_init_val = __cpu_to_le16(fw_idx); - ath10k_htt_fill_rx_desc_offset_32(ring); + ath10k_htt_fill_rx_desc_offset_32(hw, ring); ret = ath10k_htc_send(&htt->ar->htc, htt->eid, skb); if (ret) { dev_kfree_skb_any(skb); @@ -909,6 +888,7 @@ static int ath10k_htt_send_rx_ring_cfg_32(struct ath10k_htt *htt) static int ath10k_htt_send_rx_ring_cfg_64(struct ath10k_htt *htt) { struct ath10k *ar = htt->ar; + struct ath10k_hw_params *hw = &ar->hw_params; struct sk_buff *skb; struct htt_cmd *cmd; struct htt_rx_ring_setup_ring64 *ring; @@ -965,7 +945,7 @@ static int ath10k_htt_send_rx_ring_cfg_64(struct ath10k_htt *htt) ring->flags = __cpu_to_le16(flags); ring->fw_idx_init_val = __cpu_to_le16(fw_idx); - ath10k_htt_fill_rx_desc_offset_64(ring); + ath10k_htt_fill_rx_desc_offset_64(hw, ring); ret = ath10k_htc_send(&htt->ar->htc, htt->eid, skb); if (ret) { dev_kfree_skb_any(skb); diff --git a/drivers/net/wireless/ath/ath10k/hw.c b/drivers/net/wireless/ath/ath10k/hw.c index 57c58af64a57..e52e41a70321 100644 --- a/drivers/net/wireless/ath/ath10k/hw.c +++ b/drivers/net/wireless/ath/ath10k/hw.c @@ -11,6 +11,7 @@ #include "hif.h" #include "wmi-ops.h" #include "bmi.h" +#include "rx_desc.h" const struct ath10k_hw_regs qca988x_regs = { .rtc_soc_base_address = 0x00004000, @@ -1134,21 +1135,7 @@ const struct ath10k_hw_ops qca988x_ops = { .is_rssi_enable = ath10k_htt_tx_rssi_enable, }; -static int ath10k_qca99x0_rx_desc_get_l3_pad_bytes(struct htt_rx_desc *rxd) -{ - return MS(__le32_to_cpu(rxd->msdu_end.qca99x0.info1), - RX_MSDU_END_INFO1_L3_HDR_PAD); -} - -static bool ath10k_qca99x0_rx_desc_msdu_limit_error(struct htt_rx_desc *rxd) -{ - return !!(rxd->msdu_end.common.info0 & - __cpu_to_le32(RX_MSDU_END_INFO0_MSDU_LIMIT_ERR)); -} - const struct ath10k_hw_ops qca99x0_ops = { - .rx_desc_get_l3_pad_bytes = ath10k_qca99x0_rx_desc_get_l3_pad_bytes, - .rx_desc_get_msdu_limit_error = ath10k_qca99x0_rx_desc_msdu_limit_error, .is_rssi_enable = ath10k_htt_tx_rssi_enable, }; diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h index 591ef7416b61..5215a6816d71 100644 --- a/drivers/net/wireless/ath/ath10k/hw.h +++ b/drivers/net/wireless/ath/ath10k/hw.h @@ -510,6 +510,8 @@ struct ath10k_hw_clk_params { u32 outdiv; }; +struct htt_rx_desc_ops; + struct ath10k_hw_params { u32 id; u16 dev_id; @@ -562,6 +564,9 @@ struct ath10k_hw_params { */ bool sw_decrypt_mcast_mgmt; + /* Rx descriptor abstraction */ + const struct ath10k_htt_rx_desc_ops *rx_desc_ops; + const struct ath10k_hw_ops *hw_ops; /* Number of bytes used for alignment in rx_hdr_status of rx desc. */ @@ -630,16 +635,14 @@ struct ath10k_hw_params { bool dynamic_sar_support; }; -struct htt_rx_desc; struct htt_resp; struct htt_data_tx_completion_ext; +struct htt_rx_ring_rx_desc_offsets; /* Defines needed for Rx descriptor abstraction */ struct ath10k_hw_ops { - int (*rx_desc_get_l3_pad_bytes)(struct htt_rx_desc *rxd); void (*set_coverage_class)(struct ath10k *ar, s16 value); int (*enable_pll_clk)(struct ath10k *ar); - bool (*rx_desc_get_msdu_limit_error)(struct htt_rx_desc *rxd); int (*tx_data_rssi_pad_bytes)(struct htt_resp *htt); int (*is_rssi_enable)(struct htt_resp *resp); }; @@ -653,24 +656,6 @@ extern const struct ath10k_hw_ops wcn3990_ops; extern const struct ath10k_hw_clk_params qca6174_clk[]; static inline int -ath10k_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw, - struct htt_rx_desc *rxd) -{ - if (hw->hw_ops->rx_desc_get_l3_pad_bytes) - return hw->hw_ops->rx_desc_get_l3_pad_bytes(rxd); - return 0; -} - -static inline bool -ath10k_rx_desc_msdu_limit_error(struct ath10k_hw_params *hw, - struct htt_rx_desc *rxd) -{ - if (hw->hw_ops->rx_desc_get_msdu_limit_error) - return hw->hw_ops->rx_desc_get_msdu_limit_error(rxd); - return false; -} - -static inline int ath10k_tx_data_rssi_get_pad_bytes(struct ath10k_hw_params *hw, struct htt_resp *htt) { diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h index 705b6295e466..6ce2a8b1060d 100644 --- a/drivers/net/wireless/ath/ath10k/rx_desc.h +++ b/drivers/net/wireless/ath/ath10k/rx_desc.h @@ -196,17 +196,31 @@ struct rx_attention { * descriptor. */ -struct rx_frag_info { +struct rx_frag_info_common { u8 ring0_more_count; u8 ring1_more_count; u8 ring2_more_count; u8 ring3_more_count; +} __packed; + +struct rx_frag_info_wcn3990 { u8 ring4_more_count; u8 ring5_more_count; u8 ring6_more_count; u8 ring7_more_count; } __packed; +struct rx_frag_info { + struct rx_frag_info_common common; + union { + struct rx_frag_info_wcn3990 wcn3990; + } __packed; +} __packed; + +struct rx_frag_info_v1 { + struct rx_frag_info_common common; +} __packed; + /* * ring0_more_count * Indicates the number of more buffers associated with RX DMA @@ -474,11 +488,17 @@ struct rx_msdu_start_wcn3990 { struct rx_msdu_start { struct rx_msdu_start_common common; union { - struct rx_msdu_start_qca99x0 qca99x0; struct rx_msdu_start_wcn3990 wcn3990; } __packed; } __packed; +struct rx_msdu_start_v1 { + struct rx_msdu_start_common common; + union { + struct rx_msdu_start_qca99x0 qca99x0; + } __packed; +} __packed; + /* * msdu_length * MSDU length in bytes after decapsulation. This field is @@ -612,11 +632,17 @@ struct rx_msdu_end_wcn3990 { struct rx_msdu_end { struct rx_msdu_end_common common; union { - struct rx_msdu_end_qca99x0 qca99x0; struct rx_msdu_end_wcn3990 wcn3990; } __packed; } __packed; +struct rx_msdu_end_v1 { + struct rx_msdu_end_common common; + union { + struct rx_msdu_end_qca99x0 qca99x0; + } __packed; +} __packed; + /* *ip_hdr_chksum * This can include the IP header checksum or the pseudo header @@ -1136,11 +1162,17 @@ struct rx_ppdu_end_wcn3990 { struct rx_ppdu_end { struct rx_ppdu_end_common common; union { + struct rx_ppdu_end_wcn3990 wcn3990; + } __packed; +} __packed; + +struct rx_ppdu_end_v1 { + struct rx_ppdu_end_common common; + union { struct rx_ppdu_end_qca988x qca988x; struct rx_ppdu_end_qca6174 qca6174; struct rx_ppdu_end_qca99x0 qca99x0; struct rx_ppdu_end_qca9984 qca9984; - struct rx_ppdu_end_wcn3990 wcn3990; } __packed; } __packed; diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c index 9513ab696fff..681e1abe7440 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.c +++ b/drivers/net/wireless/ath/ath10k/snoc.c @@ -1306,13 +1306,10 @@ static int ath10k_snoc_resource_init(struct ath10k *ar) } for (i = 0; i < CE_COUNT; i++) { - res = platform_get_resource(ar_snoc->dev, IORESOURCE_IRQ, i); - if (!res) { - ath10k_err(ar, "failed to get IRQ%d\n", i); - ret = -ENODEV; - goto out; - } - ar_snoc->ce_irqs[i].irq_line = res->start; + ret = platform_get_irq(ar_snoc->dev, i); + if (ret < 0) + return ret; + ar_snoc->ce_irqs[i].irq_line = ret; } ret = device_property_read_u32(&pdev->dev, "qcom,xo-cal-data", @@ -1323,10 +1320,8 @@ static int ath10k_snoc_resource_init(struct ath10k *ar) ath10k_dbg(ar, ATH10K_DBG_SNOC, "xo cal data %x\n", ar_snoc->xo_cal_data); } - ret = 0; -out: - return ret; + return 0; } static void ath10k_snoc_quirks_init(struct ath10k *ar) diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c index 6f8b64218894..10123974c3da 100644 --- a/drivers/net/wireless/ath/ath10k/txrx.c +++ b/drivers/net/wireless/ath/ath10k/txrx.c @@ -125,7 +125,7 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt, tx_done->ack_rssi != ATH10K_INVALID_RSSI) { info->status.ack_signal = ATH10K_DEFAULT_NOISE_FLOOR + tx_done->ack_rssi; - info->status.is_valid_ack_signal = true; + info->status.flags |= IEEE80211_TX_STATUS_ACK_SIGNAL_VALID; } ieee80211_tx_status(htt->ar->hw, msdu); diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 62c453a21e49..2b78ed89e1b6 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -2427,7 +2427,7 @@ wmi_process_mgmt_tx_comp(struct ath10k *ar, struct mgmt_tx_compl_params *param) info->flags |= IEEE80211_TX_STAT_ACK; info->status.ack_signal = ATH10K_DEFAULT_NOISE_FLOOR + param->ack_rssi; - info->status.is_valid_ack_signal = true; + info->status.flags |= IEEE80211_TX_STATUS_ACK_SIGNAL_VALID; } ieee80211_tx_status_irqsafe(ar->hw, msdu); diff --git a/drivers/net/wireless/ath/ath10k/wow.c b/drivers/net/wireless/ath/ath10k/wow.c index 7d65c115669f..20b9aa8ddf7d 100644 --- a/drivers/net/wireless/ath/ath10k/wow.c +++ b/drivers/net/wireless/ath/ath10k/wow.c @@ -337,14 +337,15 @@ static int ath10k_vif_wow_set_wakeups(struct ath10k_vif *arvif, if (patterns[i].mask[j / 8] & BIT(j % 8)) bitmask[j] = 0xff; old_pattern.mask = bitmask; - new_pattern = old_pattern; if (ar->wmi.rx_decap_mode == ATH10K_HW_TXRX_NATIVE_WIFI) { - if (patterns[i].pkt_offset < ETH_HLEN) + if (patterns[i].pkt_offset < ETH_HLEN) { ath10k_wow_convert_8023_to_80211(&new_pattern, &old_pattern); - else + } else { + new_pattern = old_pattern; new_pattern.pkt_offset += WOW_HDR_LEN - ETH_HLEN; + } } if (WARN_ON(new_pattern.pattern_len > WOW_MAX_PATTERN_SIZE)) diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 293563b3f784..7c508e9baa6d 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. + * Copyright (c) 2021 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/module.h> @@ -97,6 +98,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .wakeup_mhi = false, .supports_rssi_stats = false, .fw_wmi_diag_event = false, + .current_cc_support = false, }, { .hw_rev = ATH11K_HW_IPQ6018_HW10, @@ -161,6 +163,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .wakeup_mhi = false, .supports_rssi_stats = false, .fw_wmi_diag_event = false, + .current_cc_support = false, }, { .name = "qca6390 hw2.0", @@ -224,6 +227,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .wakeup_mhi = true, .supports_rssi_stats = true, .fw_wmi_diag_event = true, + .current_cc_support = true, }, { .name = "qcn9074 hw1.0", @@ -287,6 +291,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .wakeup_mhi = false, .supports_rssi_stats = false, .fw_wmi_diag_event = false, + .current_cc_support = false, }, { .name = "wcn6855 hw2.0", @@ -350,6 +355,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .wakeup_mhi = true, .supports_rssi_stats = true, .fw_wmi_diag_event = true, + .current_cc_support = true, }, { .name = "wcn6855 hw2.1", @@ -412,6 +418,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .wakeup_mhi = true, .supports_rssi_stats = true, .fw_wmi_diag_event = true, + .current_cc_support = true, }, }; @@ -1404,6 +1411,9 @@ EXPORT_SYMBOL(ath11k_core_deinit); void ath11k_core_free(struct ath11k_base *ab) { + flush_workqueue(ab->workqueue); + destroy_workqueue(ab->workqueue); + kfree(ab); } EXPORT_SYMBOL(ath11k_core_free); diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index 9e88ccca5ca7..4eda15c56b04 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -603,6 +603,7 @@ struct ath11k { struct completion finish_11d_ch_list; bool pending_11d; bool regdom_set_by_user; + int hw_rate_code; }; struct ath11k_band_cap { diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c index 198ade90b725..215b6014c0ef 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs.c +++ b/drivers/net/wireless/ath/ath11k/debugfs.c @@ -666,6 +666,12 @@ static ssize_t ath11k_write_extd_rx_stats(struct file *file, goto exit; } + if (test_bit(ATH11K_FLAG_MONITOR_STARTED, &ar->monitor_flags)) { + ar->debug.extd_rx_stats = enable; + ret = count; + goto exit; + } + if (enable) { rx_filter = HTT_RX_FILTER_TLV_FLAGS_MPDU_START; rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_START; diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index c212a789421e..89b77b94bb20 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -43,6 +43,13 @@ static inline u8 ath11k_dp_rx_h_msdu_start_decap_type(struct ath11k_base *ab, } static inline +bool ath11k_dp_rx_h_msdu_start_ldpc_support(struct ath11k_base *ab, + struct hal_rx_desc *desc) +{ + return ab->hw_params.hw_ops->rx_desc_get_ldpc_support(desc); +} + +static inline u8 ath11k_dp_rx_h_msdu_start_mesh_ctl_present(struct ath11k_base *ab, struct hal_rx_desc *desc) { @@ -2313,7 +2320,7 @@ static void ath11k_dp_rx_h_rate(struct ath11k *ar, struct hal_rx_desc *rx_desc, u8 bw; u8 rate_mcs, nss; u8 sgi; - bool is_cck; + bool is_cck, is_ldpc; pkt_type = ath11k_dp_rx_h_msdu_start_pkt_type(ar->ab, rx_desc); bw = ath11k_dp_rx_h_msdu_start_rx_bw(ar->ab, rx_desc); @@ -2355,6 +2362,9 @@ static void ath11k_dp_rx_h_rate(struct ath11k *ar, struct hal_rx_desc *rx_desc, if (sgi) rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI; rx_status->bw = ath11k_mac_bw_to_mac80211_bw(bw); + is_ldpc = ath11k_dp_rx_h_msdu_start_ldpc_support(ar->ab, rx_desc); + if (is_ldpc) + rx_status->enc_flags |= RX_ENC_FLAG_LDPC; break; case RX_MSDU_START_PKT_TYPE_11AX: rx_status->rate_idx = rate_mcs; @@ -3080,79 +3090,6 @@ move_next: return num_buffs_reaped; } -int ath11k_dp_rx_process_mon_status(struct ath11k_base *ab, int mac_id, - struct napi_struct *napi, int budget) -{ - struct ath11k *ar = ath11k_ab_to_ar(ab, mac_id); - enum hal_rx_mon_status hal_status; - struct sk_buff *skb; - struct sk_buff_head skb_list; - struct hal_rx_mon_ppdu_info ppdu_info; - struct ath11k_peer *peer; - struct ath11k_sta *arsta; - int num_buffs_reaped = 0; - u32 rx_buf_sz; - u16 log_type = 0; - - __skb_queue_head_init(&skb_list); - - num_buffs_reaped = ath11k_dp_rx_reap_mon_status_ring(ab, mac_id, &budget, - &skb_list); - if (!num_buffs_reaped) - goto exit; - - memset(&ppdu_info, 0, sizeof(ppdu_info)); - ppdu_info.peer_id = HAL_INVALID_PEERID; - - while ((skb = __skb_dequeue(&skb_list))) { - if (ath11k_debugfs_is_pktlog_lite_mode_enabled(ar)) { - log_type = ATH11K_PKTLOG_TYPE_LITE_RX; - rx_buf_sz = DP_RX_BUFFER_SIZE_LITE; - } else if (ath11k_debugfs_is_pktlog_rx_stats_enabled(ar)) { - log_type = ATH11K_PKTLOG_TYPE_RX_STATBUF; - rx_buf_sz = DP_RX_BUFFER_SIZE; - } - - if (log_type) - trace_ath11k_htt_rxdesc(ar, skb->data, log_type, rx_buf_sz); - - hal_status = ath11k_hal_rx_parse_mon_status(ab, &ppdu_info, skb); - - if (ppdu_info.peer_id == HAL_INVALID_PEERID || - hal_status != HAL_RX_MON_STATUS_PPDU_DONE) { - dev_kfree_skb_any(skb); - continue; - } - - rcu_read_lock(); - spin_lock_bh(&ab->base_lock); - peer = ath11k_peer_find_by_id(ab, ppdu_info.peer_id); - - if (!peer || !peer->sta) { - ath11k_dbg(ab, ATH11K_DBG_DATA, - "failed to find the peer with peer_id %d\n", - ppdu_info.peer_id); - goto next_skb; - } - - arsta = (struct ath11k_sta *)peer->sta->drv_priv; - ath11k_dp_rx_update_peer_stats(arsta, &ppdu_info); - - if (ath11k_debugfs_is_pktlog_peer_valid(ar, peer->addr)) - trace_ath11k_htt_rxdesc(ar, skb->data, log_type, rx_buf_sz); - -next_skb: - spin_unlock_bh(&ab->base_lock); - rcu_read_unlock(); - - dev_kfree_skb_any(skb); - memset(&ppdu_info, 0, sizeof(ppdu_info)); - ppdu_info.peer_id = HAL_INVALID_PEERID; - } -exit: - return num_buffs_reaped; -} - static void ath11k_dp_rx_frag_timer(struct timer_list *timer) { struct dp_rx_tid *rx_tid = from_timer(rx_tid, timer, frag_timer); @@ -5106,36 +5043,88 @@ static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, int mac_id, } } -static void ath11k_dp_rx_mon_status_process_tlv(struct ath11k *ar, - int mac_id, u32 quota, - struct napi_struct *napi) +int ath11k_dp_rx_process_mon_status(struct ath11k_base *ab, int mac_id, + struct napi_struct *napi, int budget) { - struct ath11k_pdev_dp *dp = &ar->dp; - struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&dp->mon_data; - struct hal_rx_mon_ppdu_info *ppdu_info; - struct sk_buff *status_skb; - u32 tlv_status = HAL_TLV_STATUS_BUF_DONE; - struct ath11k_pdev_mon_stats *rx_mon_stats; + struct ath11k *ar = ath11k_ab_to_ar(ab, mac_id); + enum hal_rx_mon_status hal_status; + struct sk_buff *skb; + struct sk_buff_head skb_list; + struct ath11k_peer *peer; + struct ath11k_sta *arsta; + int num_buffs_reaped = 0; + u32 rx_buf_sz; + u16 log_type = 0; + struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&ar->dp.mon_data; + struct ath11k_pdev_mon_stats *rx_mon_stats = &pmon->rx_mon_stats; + struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info; - ppdu_info = &pmon->mon_ppdu_info; - rx_mon_stats = &pmon->rx_mon_stats; + __skb_queue_head_init(&skb_list); - if (pmon->mon_ppdu_status != DP_PPDU_STATUS_START) - return; + num_buffs_reaped = ath11k_dp_rx_reap_mon_status_ring(ab, mac_id, &budget, + &skb_list); + if (!num_buffs_reaped) + goto exit; - while (!skb_queue_empty(&pmon->rx_status_q)) { - status_skb = skb_dequeue(&pmon->rx_status_q); + memset(ppdu_info, 0, sizeof(*ppdu_info)); + ppdu_info->peer_id = HAL_INVALID_PEERID; - tlv_status = ath11k_hal_rx_parse_mon_status(ar->ab, ppdu_info, - status_skb); - if (tlv_status == HAL_TLV_STATUS_PPDU_DONE) { + while ((skb = __skb_dequeue(&skb_list))) { + if (ath11k_debugfs_is_pktlog_lite_mode_enabled(ar)) { + log_type = ATH11K_PKTLOG_TYPE_LITE_RX; + rx_buf_sz = DP_RX_BUFFER_SIZE_LITE; + } else if (ath11k_debugfs_is_pktlog_rx_stats_enabled(ar)) { + log_type = ATH11K_PKTLOG_TYPE_RX_STATBUF; + rx_buf_sz = DP_RX_BUFFER_SIZE; + } + + if (log_type) + trace_ath11k_htt_rxdesc(ar, skb->data, log_type, rx_buf_sz); + + hal_status = ath11k_hal_rx_parse_mon_status(ab, ppdu_info, skb); + + if (test_bit(ATH11K_FLAG_MONITOR_STARTED, &ar->monitor_flags) && + pmon->mon_ppdu_status == DP_PPDU_STATUS_START && + hal_status == HAL_TLV_STATUS_PPDU_DONE) { rx_mon_stats->status_ppdu_done++; pmon->mon_ppdu_status = DP_PPDU_STATUS_DONE; - ath11k_dp_rx_mon_dest_process(ar, mac_id, quota, napi); + ath11k_dp_rx_mon_dest_process(ar, mac_id, budget, napi); pmon->mon_ppdu_status = DP_PPDU_STATUS_START; } - dev_kfree_skb_any(status_skb); + + if (ppdu_info->peer_id == HAL_INVALID_PEERID || + hal_status != HAL_RX_MON_STATUS_PPDU_DONE) { + dev_kfree_skb_any(skb); + continue; + } + + rcu_read_lock(); + spin_lock_bh(&ab->base_lock); + peer = ath11k_peer_find_by_id(ab, ppdu_info->peer_id); + + if (!peer || !peer->sta) { + ath11k_dbg(ab, ATH11K_DBG_DATA, + "failed to find the peer with peer_id %d\n", + ppdu_info->peer_id); + goto next_skb; + } + + arsta = (struct ath11k_sta *)peer->sta->drv_priv; + ath11k_dp_rx_update_peer_stats(arsta, ppdu_info); + + if (ath11k_debugfs_is_pktlog_peer_valid(ar, peer->addr)) + trace_ath11k_htt_rxdesc(ar, skb->data, log_type, rx_buf_sz); + +next_skb: + spin_unlock_bh(&ab->base_lock); + rcu_read_unlock(); + + dev_kfree_skb_any(skb); + memset(ppdu_info, 0, sizeof(*ppdu_info)); + ppdu_info->peer_id = HAL_INVALID_PEERID; } +exit: + return num_buffs_reaped; } static u32 @@ -5489,22 +5478,6 @@ reap_status_ring: return quota; } -static int ath11k_dp_mon_process_rx(struct ath11k_base *ab, int mac_id, - struct napi_struct *napi, int budget) -{ - struct ath11k *ar = ath11k_ab_to_ar(ab, mac_id); - struct ath11k_pdev_dp *dp = &ar->dp; - struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&dp->mon_data; - int num_buffs_reaped = 0; - - num_buffs_reaped = ath11k_dp_rx_reap_mon_status_ring(ar->ab, mac_id, &budget, - &pmon->rx_status_q); - if (num_buffs_reaped) - ath11k_dp_rx_mon_status_process_tlv(ar, mac_id, budget, napi); - - return num_buffs_reaped; -} - int ath11k_dp_rx_process_mon_rings(struct ath11k_base *ab, int mac_id, struct napi_struct *napi, int budget) { @@ -5514,8 +5487,6 @@ int ath11k_dp_rx_process_mon_rings(struct ath11k_base *ab, int mac_id, if (test_bit(ATH11K_FLAG_MONITOR_STARTED, &ar->monitor_flags) && ab->hw_params.full_monitor_mode) ret = ath11k_dp_full_mon_process_rx(ab, mac_id, napi, budget); - else if (test_bit(ATH11K_FLAG_MONITOR_STARTED, &ar->monitor_flags)) - ret = ath11k_dp_mon_process_rx(ab, mac_id, napi, budget); else ret = ath11k_dp_rx_process_mon_status(ab, mac_id, napi, budget); diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c index 91d6244b6543..6d19547d78be 100644 --- a/drivers/net/wireless/ath/ath11k/dp_tx.c +++ b/drivers/net/wireless/ath/ath11k/dp_tx.c @@ -351,7 +351,8 @@ ath11k_dp_tx_htt_tx_complete_buf(struct ath11k_base *ab, info->flags |= IEEE80211_TX_STAT_ACK; info->status.ack_signal = ATH11K_DEFAULT_NOISE_FLOOR + ts->ack_rssi; - info->status.is_valid_ack_signal = true; + info->status.flags |= + IEEE80211_TX_STATUS_ACK_SIGNAL_VALID; } else { info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED; } @@ -552,7 +553,7 @@ static void ath11k_dp_tx_complete_msdu(struct ath11k *ar, info->flags |= IEEE80211_TX_STAT_ACK; info->status.ack_signal = ATH11K_DEFAULT_NOISE_FLOOR + ts->ack_rssi; - info->status.is_valid_ack_signal = true; + info->status.flags |= IEEE80211_TX_STATUS_ACK_SIGNAL_VALID; } if (ts->status == HAL_WBM_TQM_REL_REASON_CMD_REMOVE_TX && diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.h b/drivers/net/wireless/ath/ath11k/hal_rx.h index 571054c6d7f8..7bba4f0411e1 100644 --- a/drivers/net/wireless/ath/ath11k/hal_rx.h +++ b/drivers/net/wireless/ath/ath11k/hal_rx.h @@ -65,10 +65,6 @@ enum hal_rx_reception_type { HAL_RX_RECEPTION_TYPE_MAX, }; -#define HAL_TLV_STATUS_PPDU_NOT_DONE 0 -#define HAL_TLV_STATUS_PPDU_DONE 1 -#define HAL_TLV_STATUS_BUF_DONE 2 -#define HAL_TLV_STATUS_PPDU_NON_STD_DONE 3 #define HAL_RX_FCS_LEN 4 enum hal_rx_mon_status { @@ -77,6 +73,10 @@ enum hal_rx_mon_status { HAL_RX_MON_STATUS_BUF_DONE, }; +#define HAL_TLV_STATUS_PPDU_NOT_DONE HAL_RX_MON_STATUS_PPDU_NOT_DONE +#define HAL_TLV_STATUS_PPDU_DONE HAL_RX_MON_STATUS_PPDU_DONE +#define HAL_TLV_STATUS_BUF_DONE HAL_RX_MON_STATUS_BUF_DONE + struct hal_sw_mon_ring_entries { dma_addr_t mon_dst_paddr; dma_addr_t mon_status_paddr; diff --git a/drivers/net/wireless/ath/ath11k/hw.c b/drivers/net/wireless/ath/ath11k/hw.c index 3b0fdc1a6b3f..b7e3b668a9c0 100644 --- a/drivers/net/wireless/ath/ath11k/hw.c +++ b/drivers/net/wireless/ath/ath11k/hw.c @@ -273,6 +273,12 @@ static u8 ath11k_hw_ipq8074_rx_desc_get_mesh_ctl(struct hal_rx_desc *desc) __le32_to_cpu(desc->u.ipq8074.msdu_start.info2)); } +static bool ath11k_hw_ipq8074_rx_desc_get_ldpc_support(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO2_LDPC, + __le32_to_cpu(desc->u.ipq8074.msdu_start.info2)); +} + static bool ath11k_hw_ipq8074_rx_desc_get_mpdu_seq_ctl_vld(struct hal_rx_desc *desc) { return !!FIELD_GET(RX_MPDU_START_INFO1_MPDU_SEQ_CTRL_VALID, @@ -444,6 +450,12 @@ static u8 ath11k_hw_qcn9074_rx_desc_get_mesh_ctl(struct hal_rx_desc *desc) __le32_to_cpu(desc->u.qcn9074.msdu_start.info2)); } +static bool ath11k_hw_qcn9074_rx_desc_get_ldpc_support(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO2_LDPC, + __le32_to_cpu(desc->u.qcn9074.msdu_start.info2)); +} + static bool ath11k_hw_qcn9074_rx_desc_get_mpdu_seq_ctl_vld(struct hal_rx_desc *desc) { return !!FIELD_GET(RX_MPDU_START_INFO11_MPDU_SEQ_CTRL_VALID, @@ -815,6 +827,7 @@ const struct ath11k_hw_ops ipq8074_ops = { .rx_desc_get_encrypt_type = ath11k_hw_ipq8074_rx_desc_get_encrypt_type, .rx_desc_get_decap_type = ath11k_hw_ipq8074_rx_desc_get_decap_type, .rx_desc_get_mesh_ctl = ath11k_hw_ipq8074_rx_desc_get_mesh_ctl, + .rx_desc_get_ldpc_support = ath11k_hw_ipq8074_rx_desc_get_ldpc_support, .rx_desc_get_mpdu_seq_ctl_vld = ath11k_hw_ipq8074_rx_desc_get_mpdu_seq_ctl_vld, .rx_desc_get_mpdu_fc_valid = ath11k_hw_ipq8074_rx_desc_get_mpdu_fc_valid, .rx_desc_get_mpdu_start_seq_no = ath11k_hw_ipq8074_rx_desc_get_mpdu_start_seq_no, @@ -853,6 +866,7 @@ const struct ath11k_hw_ops ipq6018_ops = { .rx_desc_get_encrypt_type = ath11k_hw_ipq8074_rx_desc_get_encrypt_type, .rx_desc_get_decap_type = ath11k_hw_ipq8074_rx_desc_get_decap_type, .rx_desc_get_mesh_ctl = ath11k_hw_ipq8074_rx_desc_get_mesh_ctl, + .rx_desc_get_ldpc_support = ath11k_hw_ipq8074_rx_desc_get_ldpc_support, .rx_desc_get_mpdu_seq_ctl_vld = ath11k_hw_ipq8074_rx_desc_get_mpdu_seq_ctl_vld, .rx_desc_get_mpdu_fc_valid = ath11k_hw_ipq8074_rx_desc_get_mpdu_fc_valid, .rx_desc_get_mpdu_start_seq_no = ath11k_hw_ipq8074_rx_desc_get_mpdu_start_seq_no, @@ -891,6 +905,7 @@ const struct ath11k_hw_ops qca6390_ops = { .rx_desc_get_encrypt_type = ath11k_hw_ipq8074_rx_desc_get_encrypt_type, .rx_desc_get_decap_type = ath11k_hw_ipq8074_rx_desc_get_decap_type, .rx_desc_get_mesh_ctl = ath11k_hw_ipq8074_rx_desc_get_mesh_ctl, + .rx_desc_get_ldpc_support = ath11k_hw_ipq8074_rx_desc_get_ldpc_support, .rx_desc_get_mpdu_seq_ctl_vld = ath11k_hw_ipq8074_rx_desc_get_mpdu_seq_ctl_vld, .rx_desc_get_mpdu_fc_valid = ath11k_hw_ipq8074_rx_desc_get_mpdu_fc_valid, .rx_desc_get_mpdu_start_seq_no = ath11k_hw_ipq8074_rx_desc_get_mpdu_start_seq_no, @@ -929,6 +944,7 @@ const struct ath11k_hw_ops qcn9074_ops = { .rx_desc_get_encrypt_type = ath11k_hw_qcn9074_rx_desc_get_encrypt_type, .rx_desc_get_decap_type = ath11k_hw_qcn9074_rx_desc_get_decap_type, .rx_desc_get_mesh_ctl = ath11k_hw_qcn9074_rx_desc_get_mesh_ctl, + .rx_desc_get_ldpc_support = ath11k_hw_qcn9074_rx_desc_get_ldpc_support, .rx_desc_get_mpdu_seq_ctl_vld = ath11k_hw_qcn9074_rx_desc_get_mpdu_seq_ctl_vld, .rx_desc_get_mpdu_fc_valid = ath11k_hw_qcn9074_rx_desc_get_mpdu_fc_valid, .rx_desc_get_mpdu_start_seq_no = ath11k_hw_qcn9074_rx_desc_get_mpdu_start_seq_no, diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h index 29934b36c14e..c10e1a01fb02 100644 --- a/drivers/net/wireless/ath/ath11k/hw.h +++ b/drivers/net/wireless/ath/ath11k/hw.h @@ -192,6 +192,7 @@ struct ath11k_hw_params { bool wakeup_mhi; bool supports_rssi_stats; bool fw_wmi_diag_event; + bool current_cc_support; }; struct ath11k_hw_ops { @@ -210,6 +211,7 @@ struct ath11k_hw_ops { u32 (*rx_desc_get_encrypt_type)(struct hal_rx_desc *desc); u8 (*rx_desc_get_decap_type)(struct hal_rx_desc *desc); u8 (*rx_desc_get_mesh_ctl)(struct hal_rx_desc *desc); + bool (*rx_desc_get_ldpc_support)(struct hal_rx_desc *desc); bool (*rx_desc_get_mpdu_seq_ctl_vld)(struct hal_rx_desc *desc); bool (*rx_desc_get_mpdu_fc_valid)(struct hal_rx_desc *desc); u16 (*rx_desc_get_mpdu_start_seq_no)(struct hal_rx_desc *desc); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 07f499d5ec92..90fcd6adf2d5 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2319,6 +2319,9 @@ static void ath11k_peer_assoc_h_he_6ghz(struct ath11k *ar, if (!arg->he_flag || band != NL80211_BAND_6GHZ || !sta->he_6ghz_capa.capa) return; + if (sta->bandwidth == IEEE80211_STA_RX_BW_40) + arg->bw_40 = true; + if (sta->bandwidth == IEEE80211_STA_RX_BW_80) arg->bw_80 = true; @@ -2862,6 +2865,11 @@ static void ath11k_recalculate_mgmt_rate(struct ath11k *ar, if (ret) ath11k_warn(ar->ab, "failed to set mgmt tx rate %d\n", ret); + /* For WCN6855, firmware will clear this param when vdev starts, hence + * cache it here so that we can reconfigure it once vdev starts. + */ + ar->hw_rate_code = hw_rate_code; + vdev_param = WMI_VDEV_PARAM_BEACON_RATE; ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, vdev_param, hw_rate_code); @@ -4504,24 +4512,30 @@ static int ath11k_mac_op_sta_state(struct ieee80211_hw *hw, sta->addr, arvif->vdev_id); } else if ((old_state == IEEE80211_STA_NONE && new_state == IEEE80211_STA_NOTEXIST)) { - ath11k_dp_peer_cleanup(ar, arvif->vdev_id, sta->addr); + bool skip_peer_delete = ar->ab->hw_params.vdev_start_delay && + vif->type == NL80211_IFTYPE_STATION; - if (ar->ab->hw_params.vdev_start_delay && - vif->type == NL80211_IFTYPE_STATION) - goto free; + ath11k_dp_peer_cleanup(ar, arvif->vdev_id, sta->addr); - ret = ath11k_peer_delete(ar, arvif->vdev_id, sta->addr); - if (ret) - ath11k_warn(ar->ab, "Failed to delete peer: %pM for VDEV: %d\n", - sta->addr, arvif->vdev_id); - else - ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "Removed peer: %pM for VDEV: %d\n", - sta->addr, arvif->vdev_id); + if (!skip_peer_delete) { + ret = ath11k_peer_delete(ar, arvif->vdev_id, sta->addr); + if (ret) + ath11k_warn(ar->ab, + "Failed to delete peer: %pM for VDEV: %d\n", + sta->addr, arvif->vdev_id); + else + ath11k_dbg(ar->ab, + ATH11K_DBG_MAC, + "Removed peer: %pM for VDEV: %d\n", + sta->addr, arvif->vdev_id); + } ath11k_mac_dec_num_stations(arvif, sta); spin_lock_bh(&ar->ab->base_lock); peer = ath11k_peer_find(ar->ab, arvif->vdev_id, sta->addr); - if (peer && peer->sta == sta) { + if (skip_peer_delete && peer) { + peer->sta = NULL; + } else if (peer && peer->sta == sta) { ath11k_warn(ar->ab, "Found peer entry %pM n vdev %i after it was supposedly removed\n", vif->addr, arvif->vdev_id); peer->sta = NULL; @@ -4531,7 +4545,6 @@ static int ath11k_mac_op_sta_state(struct ieee80211_hw *hw, } spin_unlock_bh(&ar->ab->base_lock); -free: kfree(arsta->tx_stats); arsta->tx_stats = NULL; @@ -6955,6 +6968,19 @@ static int ath11k_start_vdev_delay(struct ieee80211_hw *hw, return ret; } + /* Reconfigure hardware rate code since it is cleared by firmware. + */ + if (ar->hw_rate_code > 0) { + u32 vdev_param = WMI_VDEV_PARAM_MGMT_RATE; + + ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, vdev_param, + ar->hw_rate_code); + if (ret) { + ath11k_warn(ar->ab, "failed to set mgmt tx rate %d\n", ret); + return ret; + } + } + if (arvif->vdev_type == WMI_VDEV_TYPE_MONITOR) { ret = ath11k_wmi_vdev_up(ar, arvif->vdev_id, 0, ar->mac_addr); if (ret) { diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index e4250ba8dfee..cccaa348cf21 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -332,6 +332,7 @@ static int ath11k_mhi_read_addr_from_dt(struct mhi_controller *mhi_ctrl) return -ENOENT; ret = of_address_to_resource(np, 0, &res); + of_node_put(np); if (ret) return ret; diff --git a/drivers/net/wireless/ath/ath11k/peer.c b/drivers/net/wireless/ath/ath11k/peer.c index 85471f8b3563..332886bc6b33 100644 --- a/drivers/net/wireless/ath/ath11k/peer.c +++ b/drivers/net/wireless/ath/ath11k/peer.c @@ -252,7 +252,7 @@ int ath11k_peer_create(struct ath11k *ar, struct ath11k_vif *arvif, { struct ath11k_peer *peer; struct ath11k_sta *arsta; - int ret; + int ret, fbret; lockdep_assert_held(&ar->conf_mutex); @@ -291,22 +291,8 @@ int ath11k_peer_create(struct ath11k *ar, struct ath11k_vif *arvif, ath11k_warn(ar->ab, "failed to find peer %pM on vdev %i after creation\n", param->peer_addr, param->vdev_id); - reinit_completion(&ar->peer_delete_done); - - ret = ath11k_wmi_send_peer_delete_cmd(ar, param->peer_addr, - param->vdev_id); - if (ret) { - ath11k_warn(ar->ab, "failed to delete peer vdev_id %d addr %pM\n", - param->vdev_id, param->peer_addr); - return ret; - } - - ret = ath11k_wait_for_peer_delete_done(ar, param->vdev_id, - param->peer_addr); - if (ret) - return ret; - - return -ENOENT; + ret = -ENOENT; + goto cleanup; } peer->pdev_idx = ar->pdev_idx; @@ -335,4 +321,24 @@ int ath11k_peer_create(struct ath11k *ar, struct ath11k_vif *arvif, spin_unlock_bh(&ar->ab->base_lock); return 0; + +cleanup: + reinit_completion(&ar->peer_delete_done); + + fbret = ath11k_wmi_send_peer_delete_cmd(ar, param->peer_addr, + param->vdev_id); + if (fbret) { + ath11k_warn(ar->ab, "failed to delete peer vdev_id %d addr %pM\n", + param->vdev_id, param->peer_addr); + goto exit; + } + + fbret = ath11k_wait_for_peer_delete_done(ar, param->vdev_id, + param->peer_addr); + if (fbret) + ath11k_warn(ar->ab, "failed wait for peer %pM delete done id %d fallback ret %d\n", + param->peer_addr, param->vdev_id, fbret); + +exit: + return ret; } diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c index 65d3c6ba35ae..d0701e8eca9c 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.c +++ b/drivers/net/wireless/ath/ath11k/qmi.c @@ -1932,10 +1932,11 @@ static int ath11k_qmi_assign_target_mem_chunk(struct ath11k_base *ab) if (!hremote_node) { ath11k_dbg(ab, ATH11K_DBG_QMI, "qmi fail to get hremote_node\n"); - return ret; + return -ENODEV; } ret = of_address_to_resource(hremote_node, 0, &res); + of_node_put(hremote_node); if (ret) { ath11k_dbg(ab, ATH11K_DBG_QMI, "qmi fail to get reg from hremote\n"); diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c index d6575feca5a2..81e11cde31d7 100644 --- a/drivers/net/wireless/ath/ath11k/reg.c +++ b/drivers/net/wireless/ath/ath11k/reg.c @@ -48,6 +48,7 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request) { struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy); struct wmi_init_country_params init_country_param; + struct wmi_set_current_country_params set_current_param = {}; struct ath11k *ar = hw->priv; int ret; @@ -76,18 +77,26 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request) return; } - /* Set the country code to the firmware and wait for + /* Set the country code to the firmware and will receive * the WMI_REG_CHAN_LIST_CC EVENT for updating the * reg info */ - init_country_param.flags = ALPHA_IS_SET; - memcpy(&init_country_param.cc_info.alpha2, request->alpha2, 2); - init_country_param.cc_info.alpha2[2] = 0; + if (ar->ab->hw_params.current_cc_support) { + memcpy(&set_current_param.alpha2, request->alpha2, 2); + ret = ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param); + if (ret) + ath11k_warn(ar->ab, + "failed set current country code: %d\n", ret); + } else { + init_country_param.flags = ALPHA_IS_SET; + memcpy(&init_country_param.cc_info.alpha2, request->alpha2, 2); + init_country_param.cc_info.alpha2[2] = 0; - ret = ath11k_wmi_send_init_country_cmd(ar, init_country_param); - if (ret) - ath11k_warn(ar->ab, - "INIT Country code set to fw failed : %d\n", ret); + ret = ath11k_wmi_send_init_country_cmd(ar, init_country_param); + if (ret) + ath11k_warn(ar->ab, + "INIT Country code set to fw failed : %d\n", ret); + } ath11k_mac_11d_scan_stop(ar); ar->regdom_set_by_user = true; diff --git a/drivers/net/wireless/ath/ath5k/ath5k.h b/drivers/net/wireless/ath/ath5k/ath5k.h index 234ea939d316..f595204f493d 100644 --- a/drivers/net/wireless/ath/ath5k/ath5k.h +++ b/drivers/net/wireless/ath/ath5k/ath5k.h @@ -1395,10 +1395,6 @@ struct ath5k_hw { u32 ah_txq_imr_nofrm; u32 ah_txq_isr_txok_all; - u32 ah_txq_isr_txurn; - u32 ah_txq_isr_qcborn; - u32 ah_txq_isr_qcburn; - u32 ah_txq_isr_qtrig; u32 *ah_rf_banks; size_t ah_rf_banks_size; diff --git a/drivers/net/wireless/ath/ath5k/dma.c b/drivers/net/wireless/ath/ath5k/dma.c index e6c52f7c26e7..d9e376eb040e 100644 --- a/drivers/net/wireless/ath/ath5k/dma.c +++ b/drivers/net/wireless/ath/ath5k/dma.c @@ -650,6 +650,7 @@ ath5k_hw_get_isr(struct ath5k_hw *ah, enum ath5k_int *interrupt_mask) */ *interrupt_mask = (pisr & AR5K_INT_COMMON) & ah->ah_imr; + ah->ah_txq_isr_txok_all = 0; /* We treat TXOK,TXDESC, TXERR and TXEOL * the same way (schedule the tx tasklet) @@ -670,13 +671,6 @@ ath5k_hw_get_isr(struct ath5k_hw *ah, enum ath5k_int *interrupt_mask) ah->ah_txq_isr_txok_all |= AR5K_REG_MS(sisr1, AR5K_SISR1_QCU_TXEOL); - /* Currently this is not much useful since we treat - * all queues the same way if we get a TXURN (update - * tx trigger level) but we might need it later on*/ - if (pisr & AR5K_ISR_TXURN) - ah->ah_txq_isr_txurn |= AR5K_REG_MS(sisr2, - AR5K_SISR2_QCU_TXURN); - /* Misc Beacon related interrupts */ /* For AR5211 */ @@ -709,25 +703,16 @@ ath5k_hw_get_isr(struct ath5k_hw *ah, enum ath5k_int *interrupt_mask) *interrupt_mask |= AR5K_INT_BNR; /* A queue got CBR overrun */ - if (unlikely(pisr & (AR5K_ISR_QCBRORN))) { + if (unlikely(pisr & (AR5K_ISR_QCBRORN))) *interrupt_mask |= AR5K_INT_QCBRORN; - ah->ah_txq_isr_qcborn |= AR5K_REG_MS(sisr3, - AR5K_SISR3_QCBRORN); - } /* A queue got CBR underrun */ - if (unlikely(pisr & (AR5K_ISR_QCBRURN))) { + if (unlikely(pisr & (AR5K_ISR_QCBRURN))) *interrupt_mask |= AR5K_INT_QCBRURN; - ah->ah_txq_isr_qcburn |= AR5K_REG_MS(sisr3, - AR5K_SISR3_QCBRURN); - } /* A queue got triggered */ - if (unlikely(pisr & (AR5K_ISR_QTRIG))) { + if (unlikely(pisr & (AR5K_ISR_QTRIG))) *interrupt_mask |= AR5K_INT_QTRIG; - ah->ah_txq_isr_qtrig |= AR5K_REG_MS(sisr4, - AR5K_SISR4_QTRIG); - } data = pisr; } diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c index 1fbc2c19848f..d444b3d70ba2 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.c +++ b/drivers/net/wireless/ath/ath5k/eeprom.c @@ -746,6 +746,9 @@ ath5k_eeprom_convert_pcal_info_5111(struct ath5k_hw *ah, int mode, } } + if (idx == AR5K_EEPROM_N_PD_CURVES) + goto err_out; + ee->ee_pd_gains[mode] = 1; pd = &chinfo[pier].pd_curves[idx]; diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c index e6b3cd49ea18..efb7889142d4 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.c +++ b/drivers/net/wireless/ath/ath9k/eeprom.c @@ -670,8 +670,6 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah, int ath9k_hw_eeprom_init(struct ath_hw *ah) { - int status; - if (AR_SREV_9300_20_OR_LATER(ah)) ah->eep_ops = &eep_ar9300_ops; else if (AR_SREV_9287(ah)) { @@ -685,7 +683,5 @@ int ath9k_hw_eeprom_init(struct ath_hw *ah) if (!ah->eep_ops->fill_eeprom(ah)) return -EIO; - status = ah->eep_ops->check_eeprom(ah); - - return status; + return ah->eep_ops->check_eeprom(ah); } diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c index 510e61e97dbc..994ec48b2f66 100644 --- a/drivers/net/wireless/ath/ath9k/htc_hst.c +++ b/drivers/net/wireless/ath/ath9k/htc_hst.c @@ -30,6 +30,7 @@ static int htc_issue_send(struct htc_target *target, struct sk_buff* skb, hdr->endpoint_id = epid; hdr->flags = flags; hdr->payload_len = cpu_to_be16(len); + memset(hdr->control, 0, sizeof(hdr->control)); status = target->hif->send(target->hif_dev, endpoint->ul_pipeid, skb); @@ -272,6 +273,10 @@ int htc_connect_service(struct htc_target *target, conn_msg->dl_pipeid = endpoint->dl_pipeid; conn_msg->ul_pipeid = endpoint->ul_pipeid; + /* To prevent infoleak */ + conn_msg->svc_meta_len = 0; + conn_msg->pad = 0; + ret = htc_issue_send(target, skb, skb->len, 0, ENDPOINT0); if (ret) goto err; diff --git a/drivers/net/wireless/ath/dfs_pattern_detector.c b/drivers/net/wireless/ath/dfs_pattern_detector.c index 75cb53a3ec15..27f4d74a41c8 100644 --- a/drivers/net/wireless/ath/dfs_pattern_detector.c +++ b/drivers/net/wireless/ath/dfs_pattern_detector.c @@ -197,7 +197,7 @@ static void channel_detector_exit(struct dfs_pattern_detector *dpd, static struct channel_detector * channel_detector_create(struct dfs_pattern_detector *dpd, u16 freq) { - u32 sz, i; + u32 i; struct channel_detector *cd; cd = kmalloc(sizeof(*cd), GFP_ATOMIC); @@ -206,8 +206,8 @@ channel_detector_create(struct dfs_pattern_detector *dpd, u16 freq) INIT_LIST_HEAD(&cd->head); cd->freq = freq; - sz = sizeof(cd->detectors) * dpd->num_radar_types; - cd->detectors = kzalloc(sz, GFP_ATOMIC); + cd->detectors = kmalloc_array(dpd->num_radar_types, + sizeof(*cd->detectors), GFP_ATOMIC); if (cd->detectors == NULL) goto fail; diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index 9575d7373bf2..75661d449712 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -331,6 +331,7 @@ static int wcn36xx_start(struct ieee80211_hw *hw) INIT_LIST_HEAD(&wcn->vif_list); spin_lock_init(&wcn->dxe_lock); + spin_lock_init(&wcn->survey_lock); return 0; @@ -392,11 +393,41 @@ static void wcn36xx_change_opchannel(struct wcn36xx *wcn, int ch) { struct ieee80211_vif *vif = NULL; struct wcn36xx_vif *tmp; + struct ieee80211_supported_band *band; + struct ieee80211_channel *channel; + unsigned long flags; + int i, j; + + for (i = 0; i < ARRAY_SIZE(wcn->hw->wiphy->bands); i++) { + band = wcn->hw->wiphy->bands[i]; + if (!band) + break; + for (j = 0; j < band->n_channels; j++) { + if (HW_VALUE_CHANNEL(band->channels[j].hw_value) == ch) { + channel = &band->channels[j]; + break; + } + } + if (channel) + break; + } + + if (!channel) { + wcn36xx_err("Cannot tune to channel %d\n", ch); + return; + } + + spin_lock_irqsave(&wcn->survey_lock, flags); + wcn->band = band; + wcn->channel = channel; + spin_unlock_irqrestore(&wcn->survey_lock, flags); list_for_each_entry(tmp, &wcn->vif_list, list) { vif = wcn36xx_priv_to_vif(tmp); wcn36xx_smd_switch_channel(wcn, vif, ch); } + + return; } static int wcn36xx_config(struct ieee80211_hw *hw, u32 changed) @@ -1326,6 +1357,49 @@ static void wcn36xx_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, } } +static int wcn36xx_get_survey(struct ieee80211_hw *hw, int idx, + struct survey_info *survey) +{ + struct wcn36xx *wcn = hw->priv; + struct ieee80211_supported_band *sband; + struct wcn36xx_chan_survey *chan_survey; + int band_idx; + unsigned long flags; + + sband = wcn->hw->wiphy->bands[NL80211_BAND_2GHZ]; + band_idx = idx; + if (band_idx >= sband->n_channels) { + band_idx -= sband->n_channels; + sband = wcn->hw->wiphy->bands[NL80211_BAND_5GHZ]; + } + + if (!sband || band_idx >= sband->n_channels) + return -ENOENT; + + spin_lock_irqsave(&wcn->survey_lock, flags); + + chan_survey = &wcn->chan_survey[idx]; + survey->channel = &sband->channels[band_idx]; + survey->noise = chan_survey->rssi - chan_survey->snr; + survey->filled = 0; + + if (chan_survey->rssi > -100 && chan_survey->rssi < 0) + survey->filled |= SURVEY_INFO_NOISE_DBM; + + if (survey->channel == wcn->channel) + survey->filled |= SURVEY_INFO_IN_USE; + + spin_unlock_irqrestore(&wcn->survey_lock, flags); + + wcn36xx_dbg(WCN36XX_DBG_MAC, + "ch %d rssi %d snr %d noise %d filled %x freq %d\n", + HW_VALUE_CHANNEL(survey->channel->hw_value), + chan_survey->rssi, chan_survey->snr, survey->noise, + survey->filled, survey->channel->center_freq); + + return 0; +} + static const struct ieee80211_ops wcn36xx_ops = { .start = wcn36xx_start, .stop = wcn36xx_stop, @@ -1354,6 +1428,7 @@ static const struct ieee80211_ops wcn36xx_ops = { .ipv6_addr_change = wcn36xx_ipv6_addr_change, #endif .flush = wcn36xx_flush, + .get_survey = wcn36xx_get_survey, CFG80211_TESTMODE_CMD(wcn36xx_tm_cmd) }; @@ -1446,25 +1521,20 @@ static int wcn36xx_platform_get_resources(struct wcn36xx *wcn, { struct device_node *mmio_node; struct device_node *iris_node; - struct resource *res; int index; int ret; /* Set TX IRQ */ - res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "tx"); - if (!res) { - wcn36xx_err("failed to get tx_irq\n"); - return -ENOENT; - } - wcn->tx_irq = res->start; + ret = platform_get_irq_byname(pdev, "tx"); + if (ret < 0) + return ret; + wcn->tx_irq = ret; /* Set RX IRQ */ - res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "rx"); - if (!res) { - wcn36xx_err("failed to get rx_irq\n"); - return -ENOENT; - } - wcn->rx_irq = res->start; + ret = platform_get_irq_byname(pdev, "rx"); + if (ret < 0) + return ret; + wcn->rx_irq = ret; /* Acquire SMSM tx enable handle */ wcn->tx_enable_state = qcom_smem_state_get(&pdev->dev, @@ -1535,6 +1605,7 @@ static int wcn36xx_probe(struct platform_device *pdev) void *wcnss; int ret; const u8 *addr; + int n_channels; wcn36xx_dbg(WCN36XX_DBG_MAC, "platform probe\n"); @@ -1562,6 +1633,13 @@ static int wcn36xx_probe(struct platform_device *pdev) goto out_wq; } + n_channels = wcn_band_2ghz.n_channels + wcn_band_5ghz.n_channels; + wcn->chan_survey = devm_kmalloc(wcn->dev, n_channels, GFP_KERNEL); + if (!wcn->chan_survey) { + ret = -ENOMEM; + goto out_wq; + } + ret = dma_set_mask_and_coherent(wcn->dev, DMA_BIT_MASK(32)); if (ret < 0) { wcn36xx_err("failed to set DMA mask: %d\n", ret); diff --git a/drivers/net/wireless/ath/wcn36xx/txrx.c b/drivers/net/wireless/ath/wcn36xx/txrx.c index dd58dde8c836..c04983718d02 100644 --- a/drivers/net/wireless/ath/wcn36xx/txrx.c +++ b/drivers/net/wireless/ath/wcn36xx/txrx.c @@ -23,6 +23,11 @@ static inline int get_rssi0(struct wcn36xx_rx_bd *bd) return 100 - ((bd->phy_stat0 >> 24) & 0xff); } +static inline int get_snr(struct wcn36xx_rx_bd *bd) +{ + return ((bd->phy_stat1 >> 24) & 0xff); +} + struct wcn36xx_rate { u16 bitrate; u16 mcs_or_legacy_index; @@ -266,6 +271,34 @@ static void __skb_queue_purge_irq(struct sk_buff_head *list) dev_kfree_skb_irq(skb); } +static void wcn36xx_update_survey(struct wcn36xx *wcn, int rssi, int snr, + int band, int freq) +{ + static struct ieee80211_channel *channel; + struct ieee80211_supported_band *sband; + int idx; + int i; + + idx = 0; + if (band == NL80211_BAND_5GHZ) + idx = wcn->hw->wiphy->bands[NL80211_BAND_2GHZ]->n_channels; + + sband = wcn->hw->wiphy->bands[band]; + channel = sband->channels; + + for (i = 0; i < sband->n_channels; i++, channel++) { + if (channel->center_freq == freq) { + idx += i; + break; + } + } + + spin_lock(&wcn->survey_lock); + wcn->chan_survey[idx].rssi = rssi; + wcn->chan_survey[idx].snr = snr; + spin_unlock(&wcn->survey_lock); +} + int wcn36xx_rx_skb(struct wcn36xx *wcn, struct sk_buff *skb) { struct ieee80211_rx_status status; @@ -343,6 +376,9 @@ int wcn36xx_rx_skb(struct wcn36xx *wcn, struct sk_buff *skb) status.freq = WCN36XX_CENTER_FREQ(wcn); } + wcn36xx_update_survey(wcn, status.signal, get_snr(bd), + status.band, status.freq); + if (bd->rate_id < ARRAY_SIZE(wcn36xx_rate_table)) { rate = &wcn36xx_rate_table[bd->rate_id]; status.encoding = rate->encoding; diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h index fbd0558c2c19..81eaa74601d0 100644 --- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h +++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h @@ -194,7 +194,14 @@ struct wcn36xx_sta { enum wcn36xx_ampdu_state ampdu_state[16]; int non_agg_frame_ct; }; + struct wcn36xx_dxe_ch; + +struct wcn36xx_chan_survey { + s8 rssi; + u8 snr; +}; + struct wcn36xx { struct ieee80211_hw *hw; struct device *dev; @@ -281,6 +288,12 @@ struct wcn36xx { /* Debug file system entry */ struct wcn36xx_dfs_entry dfs; #endif /* CONFIG_WCN36XX_DEBUGFS */ + + struct ieee80211_supported_band *band; + struct ieee80211_channel *channel; + + spinlock_t survey_lock; /* protects chan_survey */ + struct wcn36xx_chan_survey *chan_survey; }; static inline bool wcn36xx_is_fw_version(struct wcn36xx *wcn, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index ba52318615ae..b2fb9fcacdc9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -16,6 +16,7 @@ #include <brcmu_utils.h> #include <defs.h> #include <brcmu_wifi.h> +#include <brcm_hw_ids.h> #include "core.h" #include "debug.h" #include "tracepoint.h" @@ -7476,6 +7477,16 @@ int brcmf_cfg80211_wait_vif_event(struct brcmf_cfg80211_info *cfg, vif_event_equals(event, action), timeout); } +static bool brmcf_use_iso3166_ccode_fallback(struct brcmf_pub *drvr) +{ + switch (drvr->bus_if->chip) { + case BRCM_CC_4345_CHIP_ID: + return true; + default: + return false; + } +} + static s32 brcmf_translate_country_code(struct brcmf_pub *drvr, char alpha2[2], struct brcmf_fil_country_le *ccreq) { @@ -7484,18 +7495,28 @@ static s32 brcmf_translate_country_code(struct brcmf_pub *drvr, char alpha2[2], s32 found_index; int i; - country_codes = drvr->settings->country_codes; - if (!country_codes) { - brcmf_dbg(TRACE, "No country codes configured for device\n"); - return -EINVAL; - } - if ((alpha2[0] == ccreq->country_abbrev[0]) && (alpha2[1] == ccreq->country_abbrev[1])) { brcmf_dbg(TRACE, "Country code already set\n"); return -EAGAIN; } + country_codes = drvr->settings->country_codes; + if (!country_codes) { + if (brmcf_use_iso3166_ccode_fallback(drvr)) { + brcmf_dbg(TRACE, "No country codes configured for device, using ISO3166 code and 0 rev\n"); + memset(ccreq, 0, sizeof(*ccreq)); + ccreq->country_abbrev[0] = alpha2[0]; + ccreq->country_abbrev[1] = alpha2[1]; + ccreq->ccode[0] = alpha2[0]; + ccreq->ccode[1] = alpha2[1]; + return 0; + } + + brcmf_dbg(TRACE, "No country codes configured for device\n"); + return -EINVAL; + } + found_index = -1; for (i = 0; i < country_codes->table_size; i++) { cc = &country_codes->table[i]; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c index d99140960a82..dcbe55b56e43 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.c @@ -207,6 +207,8 @@ static int brcmf_init_nvram_parser(struct nvram_parser *nvp, size = BRCMF_FW_MAX_NVRAM_SIZE; else size = data_len; + /* Add space for properties we may add */ + size += strlen(BRCMF_FW_DEFAULT_BOARDREV) + 1; /* Alloc for extra 0 byte + roundup by 4 + length field */ size += 1 + 3 + sizeof(u32); nvp->nvram = kzalloc(size, GFP_KERNEL); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c index d5578ca681bb..72fe8bce6eaf 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c @@ -192,7 +192,7 @@ brcmf_fil_cmd_int_get(struct brcmf_if *ifp, u32 cmd, u32 *data) } static u32 -brcmf_create_iovar(char *name, const char *data, u32 datalen, +brcmf_create_iovar(const char *name, const char *data, u32 datalen, char *buf, u32 buflen) { u32 len; @@ -213,7 +213,7 @@ brcmf_create_iovar(char *name, const char *data, u32 datalen, s32 -brcmf_fil_iovar_data_set(struct brcmf_if *ifp, char *name, const void *data, +brcmf_fil_iovar_data_set(struct brcmf_if *ifp, const char *name, const void *data, u32 len) { struct brcmf_pub *drvr = ifp->drvr; @@ -241,7 +241,7 @@ brcmf_fil_iovar_data_set(struct brcmf_if *ifp, char *name, const void *data, } s32 -brcmf_fil_iovar_data_get(struct brcmf_if *ifp, char *name, void *data, +brcmf_fil_iovar_data_get(struct brcmf_if *ifp, const char *name, void *data, u32 len) { struct brcmf_pub *drvr = ifp->drvr; @@ -272,7 +272,7 @@ brcmf_fil_iovar_data_get(struct brcmf_if *ifp, char *name, void *data, } s32 -brcmf_fil_iovar_int_set(struct brcmf_if *ifp, char *name, u32 data) +brcmf_fil_iovar_int_set(struct brcmf_if *ifp, const char *name, u32 data) { __le32 data_le = cpu_to_le32(data); @@ -280,7 +280,7 @@ brcmf_fil_iovar_int_set(struct brcmf_if *ifp, char *name, u32 data) } s32 -brcmf_fil_iovar_int_get(struct brcmf_if *ifp, char *name, u32 *data) +brcmf_fil_iovar_int_get(struct brcmf_if *ifp, const char *name, u32 *data) { __le32 data_le = cpu_to_le32(*data); s32 err; @@ -292,7 +292,7 @@ brcmf_fil_iovar_int_get(struct brcmf_if *ifp, char *name, u32 *data) } static u32 -brcmf_create_bsscfg(s32 bsscfgidx, char *name, char *data, u32 datalen, +brcmf_create_bsscfg(s32 bsscfgidx, const char *name, char *data, u32 datalen, char *buf, u32 buflen) { const s8 *prefix = "bsscfg:"; @@ -337,7 +337,7 @@ brcmf_create_bsscfg(s32 bsscfgidx, char *name, char *data, u32 datalen, } s32 -brcmf_fil_bsscfg_data_set(struct brcmf_if *ifp, char *name, +brcmf_fil_bsscfg_data_set(struct brcmf_if *ifp, const char *name, void *data, u32 len) { struct brcmf_pub *drvr = ifp->drvr; @@ -366,7 +366,7 @@ brcmf_fil_bsscfg_data_set(struct brcmf_if *ifp, char *name, } s32 -brcmf_fil_bsscfg_data_get(struct brcmf_if *ifp, char *name, +brcmf_fil_bsscfg_data_get(struct brcmf_if *ifp, const char *name, void *data, u32 len) { struct brcmf_pub *drvr = ifp->drvr; @@ -396,7 +396,7 @@ brcmf_fil_bsscfg_data_get(struct brcmf_if *ifp, char *name, } s32 -brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, char *name, u32 data) +brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, const char *name, u32 data) { __le32 data_le = cpu_to_le32(data); @@ -405,7 +405,7 @@ brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, char *name, u32 data) } s32 -brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, char *name, u32 *data) +brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, const char *name, u32 *data) { __le32 data_le = cpu_to_le32(*data); s32 err; @@ -417,7 +417,7 @@ brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, char *name, u32 *data) return err; } -static u32 brcmf_create_xtlv(char *name, u16 id, char *data, u32 len, +static u32 brcmf_create_xtlv(const char *name, u16 id, char *data, u32 len, char *buf, u32 buflen) { u32 iolen; @@ -438,7 +438,7 @@ static u32 brcmf_create_xtlv(char *name, u16 id, char *data, u32 len, return iolen; } -s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, char *name, u16 id, +s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, const char *name, u16 id, void *data, u32 len) { struct brcmf_pub *drvr = ifp->drvr; @@ -466,7 +466,7 @@ s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, char *name, u16 id, return err; } -s32 brcmf_fil_xtlv_data_get(struct brcmf_if *ifp, char *name, u16 id, +s32 brcmf_fil_xtlv_data_get(struct brcmf_if *ifp, const char *name, u16 id, void *data, u32 len) { struct brcmf_pub *drvr = ifp->drvr; @@ -495,7 +495,7 @@ s32 brcmf_fil_xtlv_data_get(struct brcmf_if *ifp, char *name, u16 id, return err; } -s32 brcmf_fil_xtlv_int_set(struct brcmf_if *ifp, char *name, u16 id, u32 data) +s32 brcmf_fil_xtlv_int_set(struct brcmf_if *ifp, const char *name, u16 id, u32 data) { __le32 data_le = cpu_to_le32(data); @@ -503,7 +503,7 @@ s32 brcmf_fil_xtlv_int_set(struct brcmf_if *ifp, char *name, u16 id, u32 data) sizeof(data_le)); } -s32 brcmf_fil_xtlv_int_get(struct brcmf_if *ifp, char *name, u16 id, u32 *data) +s32 brcmf_fil_xtlv_int_get(struct brcmf_if *ifp, const char *name, u16 id, u32 *data) { __le32 data_le = cpu_to_le32(*data); s32 err; @@ -514,12 +514,12 @@ s32 brcmf_fil_xtlv_int_get(struct brcmf_if *ifp, char *name, u16 id, u32 *data) return err; } -s32 brcmf_fil_xtlv_int8_get(struct brcmf_if *ifp, char *name, u16 id, u8 *data) +s32 brcmf_fil_xtlv_int8_get(struct brcmf_if *ifp, const char *name, u16 id, u8 *data) { return brcmf_fil_xtlv_data_get(ifp, name, id, data, sizeof(*data)); } -s32 brcmf_fil_xtlv_int16_get(struct brcmf_if *ifp, char *name, u16 id, u16 *data) +s32 brcmf_fil_xtlv_int16_get(struct brcmf_if *ifp, const char *name, u16 id, u16 *data) { __le16 data_le = cpu_to_le16(*data); s32 err; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h index cb26f8c59c21..bc693157c4b1 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h @@ -84,26 +84,26 @@ s32 brcmf_fil_cmd_data_get(struct brcmf_if *ifp, u32 cmd, void *data, u32 len); s32 brcmf_fil_cmd_int_set(struct brcmf_if *ifp, u32 cmd, u32 data); s32 brcmf_fil_cmd_int_get(struct brcmf_if *ifp, u32 cmd, u32 *data); -s32 brcmf_fil_iovar_data_set(struct brcmf_if *ifp, char *name, const void *data, +s32 brcmf_fil_iovar_data_set(struct brcmf_if *ifp, const char *name, const void *data, u32 len); -s32 brcmf_fil_iovar_data_get(struct brcmf_if *ifp, char *name, void *data, +s32 brcmf_fil_iovar_data_get(struct brcmf_if *ifp, const char *name, void *data, u32 len); -s32 brcmf_fil_iovar_int_set(struct brcmf_if *ifp, char *name, u32 data); -s32 brcmf_fil_iovar_int_get(struct brcmf_if *ifp, char *name, u32 *data); +s32 brcmf_fil_iovar_int_set(struct brcmf_if *ifp, const char *name, u32 data); +s32 brcmf_fil_iovar_int_get(struct brcmf_if *ifp, const char *name, u32 *data); -s32 brcmf_fil_bsscfg_data_set(struct brcmf_if *ifp, char *name, void *data, +s32 brcmf_fil_bsscfg_data_set(struct brcmf_if *ifp, const char *name, void *data, u32 len); -s32 brcmf_fil_bsscfg_data_get(struct brcmf_if *ifp, char *name, void *data, +s32 brcmf_fil_bsscfg_data_get(struct brcmf_if *ifp, const char *name, void *data, u32 len); -s32 brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, char *name, u32 data); -s32 brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, char *name, u32 *data); -s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, char *name, u16 id, +s32 brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, const char *name, u32 data); +s32 brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, const char *name, u32 *data); +s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, const char *name, u16 id, void *data, u32 len); -s32 brcmf_fil_xtlv_data_get(struct brcmf_if *ifp, char *name, u16 id, +s32 brcmf_fil_xtlv_data_get(struct brcmf_if *ifp, const char *name, u16 id, void *data, u32 len); -s32 brcmf_fil_xtlv_int_set(struct brcmf_if *ifp, char *name, u16 id, u32 data); -s32 brcmf_fil_xtlv_int_get(struct brcmf_if *ifp, char *name, u16 id, u32 *data); -s32 brcmf_fil_xtlv_int8_get(struct brcmf_if *ifp, char *name, u16 id, u8 *data); -s32 brcmf_fil_xtlv_int16_get(struct brcmf_if *ifp, char *name, u16 id, u16 *data); +s32 brcmf_fil_xtlv_int_set(struct brcmf_if *ifp, const char *name, u16 id, u32 data); +s32 brcmf_fil_xtlv_int_get(struct brcmf_if *ifp, const char *name, u16 id, u32 *data); +s32 brcmf_fil_xtlv_int8_get(struct brcmf_if *ifp, const char *name, u16 id, u8 *data); +s32 brcmf_fil_xtlv_int16_get(struct brcmf_if *ifp, const char *name, u16 id, u16 *data); #endif /* _fwil_h_ */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c index 513c7e6421b2..8623bde5eb70 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c @@ -71,16 +71,18 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, /* Set board-type to the first string of the machine compatible prop */ root = of_find_node_by_path("/"); if (root) { - int i, len; + int i; char *board_type; const char *tmp; of_property_read_string_index(root, "compatible", 0, &tmp); /* get rid of '/' in the compatible string to be able to find the FW */ - len = strlen(tmp) + 1; - board_type = devm_kzalloc(dev, len, GFP_KERNEL); - strscpy(board_type, tmp, len); + board_type = devm_kstrdup(dev, tmp, GFP_KERNEL); + if (!board_type) { + of_node_put(root); + return; + } for (i = 0; i < board_type[i]; i++) { if (board_type[i] == '/') board_type[i] = '-'; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index 4735063e4c03..d3f08d4f380b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -158,7 +158,7 @@ struct brcmf_p2p_pub_act_frame { u8 oui_type; u8 subtype; u8 dialog_token; - u8 elts[1]; + u8 elts[]; }; /** @@ -177,7 +177,7 @@ struct brcmf_p2p_action_frame { u8 type; u8 subtype; u8 dialog_token; - u8 elts[1]; + u8 elts[]; }; /** @@ -192,7 +192,7 @@ struct brcmf_p2psd_gas_pub_act_frame { u8 category; u8 action; u8 dialog_token; - u8 query_data[1]; + u8 query_data[]; }; /** @@ -225,7 +225,7 @@ static bool brcmf_p2p_is_pub_action(void *frame, u32 frame_len) return false; pact_frm = (struct brcmf_p2p_pub_act_frame *)frame; - if (frame_len < sizeof(struct brcmf_p2p_pub_act_frame) - 1) + if (frame_len < sizeof(*pact_frm)) return false; if (pact_frm->category == P2P_PUB_AF_CATEGORY && @@ -253,7 +253,7 @@ static bool brcmf_p2p_is_p2p_action(void *frame, u32 frame_len) return false; act_frm = (struct brcmf_p2p_action_frame *)frame; - if (frame_len < sizeof(struct brcmf_p2p_action_frame) - 1) + if (frame_len < sizeof(*act_frm)) return false; if (act_frm->category == P2P_AF_CATEGORY && @@ -280,7 +280,7 @@ static bool brcmf_p2p_is_gas_action(void *frame, u32 frame_len) return false; sd_act_frm = (struct brcmf_p2psd_gas_pub_act_frame *)frame; - if (frame_len < sizeof(struct brcmf_p2psd_gas_pub_act_frame) - 1) + if (frame_len < sizeof(*sd_act_frm)) return false; if (sd_act_frm->category != P2PSD_ACTION_CATEGORY) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 8b149996fc00..97f0f13dfe50 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/bcma/bcma.h> #include <linux/sched.h> +#include <linux/io.h> #include <asm/unaligned.h> #include <soc.h> @@ -59,6 +60,13 @@ BRCMF_FW_DEF(4366B, "brcmfmac4366b-pcie"); BRCMF_FW_DEF(4366C, "brcmfmac4366c-pcie"); BRCMF_FW_DEF(4371, "brcmfmac4371-pcie"); +/* firmware config files */ +MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-pcie.txt"); +MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-pcie.*.txt"); + +/* per-board firmware binaries */ +MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-pcie.*.bin"); + static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = { BRCMF_FW_ENTRY(BRCM_CC_43602_CHIP_ID, 0xFFFFFFFF, 43602), BRCMF_FW_ENTRY(BRCM_CC_43465_CHIP_ID, 0xFFFFFFF0, 4366C), @@ -448,47 +456,6 @@ brcmf_pcie_write_ram32(struct brcmf_pciedev_info *devinfo, u32 mem_offset, static void -brcmf_pcie_copy_mem_todev(struct brcmf_pciedev_info *devinfo, u32 mem_offset, - void *srcaddr, u32 len) -{ - void __iomem *address = devinfo->tcm + mem_offset; - __le32 *src32; - __le16 *src16; - u8 *src8; - - if (((ulong)address & 4) || ((ulong)srcaddr & 4) || (len & 4)) { - if (((ulong)address & 2) || ((ulong)srcaddr & 2) || (len & 2)) { - src8 = (u8 *)srcaddr; - while (len) { - iowrite8(*src8, address); - address++; - src8++; - len--; - } - } else { - len = len / 2; - src16 = (__le16 *)srcaddr; - while (len) { - iowrite16(le16_to_cpu(*src16), address); - address += 2; - src16++; - len--; - } - } - } else { - len = len / 4; - src32 = (__le32 *)srcaddr; - while (len) { - iowrite32(le32_to_cpu(*src32), address); - address += 4; - src32++; - len--; - } - } -} - - -static void brcmf_pcie_copy_dev_tomem(struct brcmf_pciedev_info *devinfo, u32 mem_offset, void *dstaddr, u32 len) { @@ -777,6 +744,8 @@ static void brcmf_pcie_bus_console_read(struct brcmf_pciedev_info *devinfo, return; console = &devinfo->shared.console; + if (!console->base_addr) + return; addr = console->base_addr + BRCMF_CONSOLE_WRITEIDX_OFFSET; newidx = brcmf_pcie_read_tcm32(devinfo, addr); while (newidx != console->read_idx) { @@ -1348,6 +1317,18 @@ static void brcmf_pcie_down(struct device *dev) { } +static int brcmf_pcie_preinit(struct device *dev) +{ + struct brcmf_bus *bus_if = dev_get_drvdata(dev); + struct brcmf_pciedev *buspub = bus_if->bus_priv.pcie; + + brcmf_dbg(PCIE, "Enter\n"); + + brcmf_pcie_intr_enable(buspub->devinfo); + brcmf_pcie_hostready(buspub->devinfo); + + return 0; +} static int brcmf_pcie_tx(struct device *dev, struct sk_buff *skb) { @@ -1456,6 +1437,7 @@ static int brcmf_pcie_reset(struct device *dev) } static const struct brcmf_bus_ops brcmf_pcie_bus_ops = { + .preinit = brcmf_pcie_preinit, .txdata = brcmf_pcie_tx, .stop = brcmf_pcie_down, .txctl = brcmf_pcie_tx_ctlpkt, @@ -1540,6 +1522,7 @@ brcmf_pcie_init_share_ram_info(struct brcmf_pciedev_info *devinfo, shared->max_rxbufpost, shared->rx_dataoffset); brcmf_pcie_bus_console_init(devinfo); + brcmf_pcie_bus_console_read(devinfo, false); return 0; } @@ -1563,8 +1546,8 @@ static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, return err; brcmf_dbg(PCIE, "Download FW %s\n", devinfo->fw_name); - brcmf_pcie_copy_mem_todev(devinfo, devinfo->ci->rambase, - (void *)fw->data, fw->size); + memcpy_toio(devinfo->tcm + devinfo->ci->rambase, + (void *)fw->data, fw->size); resetintr = get_unaligned_le32(fw->data); release_firmware(fw); @@ -1578,7 +1561,7 @@ static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, brcmf_dbg(PCIE, "Download NVRAM %s\n", devinfo->nvram_name); address = devinfo->ci->rambase + devinfo->ci->ramsize - nvram_len; - brcmf_pcie_copy_mem_todev(devinfo, address, nvram, nvram_len); + memcpy_toio(devinfo->tcm + address, nvram, nvram_len); brcmf_fw_nvram_free(nvram); } else { brcmf_dbg(PCIE, "No matching NVRAM file found %s\n", @@ -1777,6 +1760,8 @@ static void brcmf_pcie_setup(struct device *dev, int ret, ret = brcmf_chip_get_raminfo(devinfo->ci); if (ret) { brcmf_err(bus, "Failed to get RAM info\n"); + release_firmware(fw); + brcmf_fw_nvram_free(nvram); goto fail; } @@ -1826,9 +1811,6 @@ static void brcmf_pcie_setup(struct device *dev, int ret, init_waitqueue_head(&devinfo->mbdata_resp_wait); - brcmf_pcie_intr_enable(devinfo); - brcmf_pcie_hostready(devinfo); - ret = brcmf_attach(&devinfo->pdev->dev); if (ret) goto fail; @@ -1980,6 +1962,7 @@ brcmf_pcie_remove(struct pci_dev *pdev) return; devinfo = bus->bus_priv.pcie->devinfo; + brcmf_pcie_bus_console_read(devinfo, false); devinfo->state = BRCMFMAC_PCIE_STATE_DOWN; if (devinfo->ci) @@ -2106,6 +2089,7 @@ static const struct pci_device_id brcmf_pcie_devid_table[] = { BRCMF_PCIE_DEVICE(BRCM_PCIE_4356_DEVICE_ID), BRCMF_PCIE_DEVICE(BRCM_PCIE_43567_DEVICE_ID), BRCMF_PCIE_DEVICE(BRCM_PCIE_43570_DEVICE_ID), + BRCMF_PCIE_DEVICE(BRCM_PCIE_43570_RAW_DEVICE_ID), BRCMF_PCIE_DEVICE(BRCM_PCIE_4358_DEVICE_ID), BRCMF_PCIE_DEVICE(BRCM_PCIE_4359_DEVICE_ID), BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_DEVICE_ID), diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 8effeb7a7269..5d156e591b35 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -629,7 +629,6 @@ BRCMF_FW_CLM_DEF(43752, "brcmfmac43752-sdio"); /* firmware config files */ MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-sdio.*.txt"); -MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-pcie.*.txt"); /* per-board firmware binaries */ MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-sdio.*.bin"); diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h index 9d81320164ce..3bbe2388ec54 100644 --- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h +++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h @@ -71,6 +71,7 @@ #define BRCM_PCIE_4356_DEVICE_ID 0x43ec #define BRCM_PCIE_43567_DEVICE_ID 0x43d3 #define BRCM_PCIE_43570_DEVICE_ID 0x43d9 +#define BRCM_PCIE_43570_RAW_DEVICE_ID 0xaa31 #define BRCM_PCIE_4358_DEVICE_ID 0x43e9 #define BRCM_PCIE_4359_DEVICE_ID 0x43ef #define BRCM_PCIE_43602_DEVICE_ID 0x43ba diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 295629c5c035..5f3128fc1066 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -209,6 +209,9 @@ static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb, shdr->type != htons(ETH_P_PAE) && shdr->type != htons(ETH_P_TDLS)))) skb->ip_summed = CHECKSUM_NONE; + else + /* mac80211 assumes full CSUM including SNAP header */ + skb_postpush_rcsum(skb, shdr, sizeof(*shdr)); } fraglen = len - headlen; diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 3a9af8931c35..02daeefb0761 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -93,7 +93,7 @@ mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q) { int i; - if (!q) + if (!q || !q->ndesc) return; /* clear descriptors */ @@ -233,7 +233,7 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, struct mt76_queue *q, bool flush) struct mt76_queue_entry entry; int last; - if (!q) + if (!q || !q->ndesc) return; spin_lock_bh(&q->cleanup_lock); @@ -448,6 +448,9 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q) int len = SKB_WITH_OVERHEAD(q->buf_size); int offset = q->buf_offset; + if (!q->ndesc) + return 0; + spin_lock_bh(&q->lock); while (q->queued < q->ndesc - 1) { @@ -465,6 +468,7 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q) qbuf.addr = addr + offset; qbuf.len = len - offset; + qbuf.skip_unmap = false; mt76_dma_add_buf(dev, q, &qbuf, 1, 0, buf, NULL); frames++; } @@ -484,6 +488,9 @@ mt76_dma_rx_cleanup(struct mt76_dev *dev, struct mt76_queue *q) void *buf; bool more; + if (!q->ndesc) + return; + spin_lock_bh(&q->lock); do { buf = mt76_dma_dequeue(dev, q, true, NULL, NULL, &more); @@ -508,6 +515,9 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid) struct mt76_queue *q = &dev->q_rx[qid]; int i; + if (!q->ndesc) + return; + for (i = 0; i < q->ndesc; i++) q->desc[i].ctrl = cpu_to_le32(MT_DMA_CTL_DMA_DONE); diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 8bb1c7ab5b50..a4bb281a74e6 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -180,7 +180,7 @@ static const struct cfg80211_sar_freq_ranges mt76_sar_freq_ranges[] = { { .start_freq = 5725, .end_freq = 5950, }, }; -const struct cfg80211_sar_capa mt76_sar_capa = { +static const struct cfg80211_sar_capa mt76_sar_capa = { .type = NL80211_SAR_TYPE_POWER, .num_freq_ranges = ARRAY_SIZE(mt76_sar_freq_ranges), .freq_ranges = &mt76_sar_freq_ranges[0], @@ -823,6 +823,10 @@ void mt76_set_channel(struct mt76_phy *phy) wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(phy), timeout); mt76_update_survey(phy); + if (phy->chandef.chan->center_freq != chandef->chan->center_freq || + phy->chandef.width != chandef->width) + phy->dfs_state = MT_DFS_STATE_UNKNOWN; + phy->chandef = *chandef; phy->chan_state = mt76_channel_state(phy, chandef->chan); @@ -1604,3 +1608,27 @@ void mt76_ethtool_worker(struct mt76_ethtool_worker_info *wi, wi->worker_stat_count = ei - wi->initial_stat_idx; } EXPORT_SYMBOL_GPL(mt76_ethtool_worker); + +enum mt76_dfs_state mt76_phy_dfs_state(struct mt76_phy *phy) +{ + struct ieee80211_hw *hw = phy->hw; + struct mt76_dev *dev = phy->dev; + + if (dev->region == NL80211_DFS_UNSET || + test_bit(MT76_SCANNING, &phy->state)) + return MT_DFS_STATE_DISABLED; + + if (!hw->conf.radar_enabled) { + if ((hw->conf.flags & IEEE80211_CONF_MONITOR) && + (phy->chandef.chan->flags & IEEE80211_CHAN_RADAR)) + return MT_DFS_STATE_ACTIVE; + + return MT_DFS_STATE_DISABLED; + } + + if (phy->chandef.chan->dfs_state != NL80211_DFS_AVAILABLE) + return MT_DFS_STATE_CAC; + + return MT_DFS_STATE_ACTIVE; +} +EXPORT_SYMBOL_GPL(mt76_phy_dfs_state); diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 404c3d1a70d6..5e10fe156926 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -85,6 +85,7 @@ enum mt76_rxq_id { MT_RXQ_MCU_WA, MT_RXQ_EXT, MT_RXQ_EXT_WA, + MT_RXQ_MAIN_WA, __MT_RXQ_MAX }; @@ -104,6 +105,13 @@ enum mt76_cipher_type { MT_CIPHER_GCMP_256, }; +enum mt76_dfs_state { + MT_DFS_STATE_UNKNOWN, + MT_DFS_STATE_DISABLED, + MT_DFS_STATE_CAC, + MT_DFS_STATE_ACTIVE, +}; + struct mt76_queue_buf { dma_addr_t addr; u16 len; @@ -224,7 +232,7 @@ enum mt76_wcid_flags { MT_WCID_FLAG_HDR_TRANS, }; -#define MT76_N_WCIDS 288 +#define MT76_N_WCIDS 544 /* stored in ieee80211_tx_info::hw_queue */ #define MT_TX_HW_QUEUE_EXT_PHY BIT(3) @@ -496,7 +504,7 @@ struct mt76_usb { } mcu; }; -#define MT76S_XMIT_BUF_SZ (16 * PAGE_SIZE) +#define MT76S_XMIT_BUF_SZ 0x3fe00 #define MT76S_NUM_TX_ENTRIES 256 #define MT76S_NUM_RX_ENTRIES 512 struct mt76_sdio { @@ -506,7 +514,8 @@ struct mt76_sdio { struct work_struct stat_work; - u8 *xmit_buf[IEEE80211_NUM_ACS + 2]; + u8 *xmit_buf; + u32 xmit_buf_sz; struct sdio_func *func; void *intr_data; @@ -621,6 +630,7 @@ struct mt76_vif { u8 band_idx; u8 wmm_idx; u8 scan_seq_num; + u8 cipher; }; struct mt76_phy { @@ -636,6 +646,7 @@ struct mt76_phy { struct ieee80211_channel *main_chan; struct mt76_channel_state *chan_state; + enum mt76_dfs_state dfs_state; ktime_t survey_time; struct mt76_hw_cap cap; @@ -897,8 +908,8 @@ static inline u16 mt76_rev(struct mt76_dev *dev) #define mt76_queue_reset(dev, ...) (dev)->mt76.queue_ops->reset_q(&((dev)->mt76), __VA_ARGS__) #define mt76_for_each_q_rx(dev, i) \ - for (i = 0; i < ARRAY_SIZE((dev)->q_rx) && \ - (dev)->q_rx[i].ndesc; i++) + for (i = 0; i < ARRAY_SIZE((dev)->q_rx); i++) \ + if ((dev)->q_rx[i].ndesc) struct mt76_dev *mt76_alloc_device(struct device *pdev, unsigned int size, const struct ieee80211_ops *ops, @@ -1181,6 +1192,7 @@ void mt76_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *mac); void mt76_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif); +enum mt76_dfs_state mt76_phy_dfs_state(struct mt76_phy *phy); int mt76_testmode_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void *data, int len); int mt76_testmode_dump(struct ieee80211_hw *hw, struct sk_buff *skb, diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c index 2b546bc05d82..83c5eec5b163 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c @@ -641,6 +641,9 @@ mt7603_sta_rate_tbl_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta_rates *sta_rates = rcu_dereference(sta->rates); int i; + if (!sta_rates) + return; + spin_lock_bh(&dev->mt76.lock); for (i = 0; i < ARRAY_SIZE(msta->rates); i++) { msta->rates[i].idx = sta_rates->rate[i].idx; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c index b53528014fbc..ca7efca1543f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c @@ -105,10 +105,10 @@ mt7615_pm_set(void *data, u64 val) if (!mt7615_firmware_offload(dev) || mt76_is_usb(&dev->mt76)) return -EOPNOTSUPP; - if (val == pm->enable) - return 0; + mutex_lock(&dev->mt76.mutex); - mt7615_mutex_acquire(dev); + if (val == pm->enable) + goto out; if (dev->phy.n_beacon_vif) { ret = -EBUSY; @@ -119,9 +119,16 @@ mt7615_pm_set(void *data, u64 val) pm->stats.last_wake_event = jiffies; pm->stats.last_doze_event = jiffies; } + /* make sure the chip is awake here and ps_work is scheduled + * just at end of the this routine. + */ + pm->enable = false; + mt76_connac_pm_wake(&dev->mphy, pm); + pm->enable = val; + mt76_connac_power_save_sched(&dev->mphy, pm); out: - mt7615_mutex_release(dev); + mutex_unlock(&dev->mt76.mutex); return ret; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c index a753c7476d31..a06dcbb8c673 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c @@ -552,7 +552,6 @@ void mt7615_init_device(struct mt7615_dev *dev) dev->pm.stats.last_wake_event = jiffies; dev->pm.stats.last_doze_event = jiffies; mt7615_cap_dbdc_disable(dev); - dev->phy.dfs_state = -1; #ifdef CONFIG_NL80211_TESTMODE dev->mt76.test_ops = &mt7615_testmode_ops; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index ec25e5a95d44..f035cd880696 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -253,12 +253,12 @@ static void mt7615_mac_fill_tm_rx(struct mt7615_phy *phy, __le32 *rxv) static int mt7615_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) { struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb; + struct ethhdr *eth_hdr = (struct ethhdr *)(skb->data + hdr_gap); struct mt7615_sta *msta = (struct mt7615_sta *)status->wcid; + __le32 *rxd = (__le32 *)skb->data; struct ieee80211_sta *sta; struct ieee80211_vif *vif; struct ieee80211_hdr hdr; - struct ethhdr eth_hdr; - __le32 *rxd = (__le32 *)skb->data; __le32 qos_ctrl, ht_ctrl; if (FIELD_GET(MT_RXD1_NORMAL_ADDR_TYPE, le32_to_cpu(rxd[1])) != @@ -275,7 +275,6 @@ static int mt7615_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv); /* store the info from RXD and ethhdr to avoid being overridden */ - memcpy(ð_hdr, skb->data + hdr_gap, sizeof(eth_hdr)); hdr.frame_control = FIELD_GET(MT_RXD4_FRAME_CONTROL, rxd[4]); hdr.seq_ctrl = FIELD_GET(MT_RXD6_SEQ_CTRL, rxd[6]); qos_ctrl = FIELD_GET(MT_RXD6_QOS_CTL, rxd[6]); @@ -290,24 +289,24 @@ static int mt7615_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) ether_addr_copy(hdr.addr3, vif->bss_conf.bssid); break; case IEEE80211_FCTL_FROMDS: - ether_addr_copy(hdr.addr3, eth_hdr.h_source); + ether_addr_copy(hdr.addr3, eth_hdr->h_source); break; case IEEE80211_FCTL_TODS: - ether_addr_copy(hdr.addr3, eth_hdr.h_dest); + ether_addr_copy(hdr.addr3, eth_hdr->h_dest); break; case IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS: - ether_addr_copy(hdr.addr3, eth_hdr.h_dest); - ether_addr_copy(hdr.addr4, eth_hdr.h_source); + ether_addr_copy(hdr.addr3, eth_hdr->h_dest); + ether_addr_copy(hdr.addr4, eth_hdr->h_source); break; default: break; } skb_pull(skb, hdr_gap + sizeof(struct ethhdr) - 2); - if (eth_hdr.h_proto == htons(ETH_P_AARP) || - eth_hdr.h_proto == htons(ETH_P_IPX)) + if (eth_hdr->h_proto == cpu_to_be16(ETH_P_AARP) || + eth_hdr->h_proto == cpu_to_be16(ETH_P_IPX)) ether_addr_copy(skb_push(skb, ETH_ALEN), bridge_tunnel_header); - else if (eth_hdr.h_proto >= htons(ETH_P_802_3_MIN)) + else if (eth_hdr->h_proto >= cpu_to_be16(ETH_P_802_3_MIN)) ether_addr_copy(skb_push(skb, ETH_ALEN), rfc1042_header); else skb_pull(skb, 2); @@ -1642,9 +1641,10 @@ mt7615_mac_tx_free_token(struct mt7615_dev *dev, u16 token) mt7615_txwi_free(dev, txwi); } -static void mt7615_mac_tx_free(struct mt7615_dev *dev, struct sk_buff *skb) +static void mt7615_mac_tx_free(struct mt7615_dev *dev, void *data, int len) { - struct mt7615_tx_free *free = (struct mt7615_tx_free *)skb->data; + struct mt7615_tx_free *free = (struct mt7615_tx_free *)data; + void *end = data + len; u8 i, count; mt76_queue_tx_cleanup(dev, dev->mphy.q_tx[MT_TXQ_PSD], false); @@ -1659,17 +1659,21 @@ static void mt7615_mac_tx_free(struct mt7615_dev *dev, struct sk_buff *skb) if (is_mt7615(&dev->mt76)) { __le16 *token = &free->token[0]; + if (WARN_ON_ONCE((void *)&token[count] > end)) + return; + for (i = 0; i < count; i++) mt7615_mac_tx_free_token(dev, le16_to_cpu(token[i])); } else { __le32 *token = (__le32 *)&free->token[0]; + if (WARN_ON_ONCE((void *)&token[count] > end)) + return; + for (i = 0; i < count; i++) mt7615_mac_tx_free_token(dev, le32_to_cpu(token[i])); } - dev_kfree_skb(skb); - rcu_read_lock(); mt7615_mac_sta_poll(dev); rcu_read_unlock(); @@ -1677,6 +1681,28 @@ static void mt7615_mac_tx_free(struct mt7615_dev *dev, struct sk_buff *skb) mt76_worker_schedule(&dev->mt76.tx_worker); } +bool mt7615_rx_check(struct mt76_dev *mdev, void *data, int len) +{ + struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76); + __le32 *rxd = (__le32 *)data; + __le32 *end = (__le32 *)&rxd[len / 4]; + enum rx_pkt_type type; + + type = FIELD_GET(MT_RXD0_PKT_TYPE, le32_to_cpu(rxd[0])); + switch (type) { + case PKT_TYPE_TXRX_NOTIFY: + mt7615_mac_tx_free(dev, data, len); + return false; + case PKT_TYPE_TXS: + for (rxd++; rxd + 7 <= end; rxd += 7) + mt7615_mac_add_txs(dev, rxd); + return false; + default: + return true; + } +} +EXPORT_SYMBOL_GPL(mt7615_rx_check); + void mt7615_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb) { @@ -1698,7 +1724,8 @@ void mt7615_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, dev_kfree_skb(skb); break; case PKT_TYPE_TXRX_NOTIFY: - mt7615_mac_tx_free(dev, skb); + mt7615_mac_tx_free(dev, skb->data, skb->len); + dev_kfree_skb(skb); break; case PKT_TYPE_RX_EVENT: mt7615_mcu_rx_event(dev, skb); @@ -2068,6 +2095,7 @@ void mt7615_pm_wake_work(struct work_struct *work) int i; if (mt76_is_sdio(mdev)) { + mt76_connac_pm_dequeue_skbs(mphy, &dev->pm); mt76_worker_schedule(&mdev->sdio.txrx_worker); } else { mt76_for_each_q_rx(mdev, i) @@ -2103,6 +2131,14 @@ void mt7615_pm_power_save_work(struct work_struct *work) test_bit(MT76_HW_SCHED_SCANNING, &dev->mphy.state)) goto out; + if (mutex_is_locked(&dev->mt76.mutex)) + /* if mt76 mutex is held we should not put the device + * to sleep since we are currently accessing device + * register map. We need to wait for the next power_save + * trigger. + */ + goto out; + if (time_is_after_jiffies(dev->pm.last_activity + delta)) { delta = dev->pm.last_activity + delta - jiffies; goto out; @@ -2160,21 +2196,24 @@ static void mt7615_dfs_stop_radar_detector(struct mt7615_phy *phy) struct mt7615_dev *dev = phy->dev; if (phy->rdd_state & BIT(0)) - mt7615_mcu_rdd_cmd(dev, RDD_STOP, 0, MT_RX_SEL0, 0); + mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, 0, + MT_RX_SEL0, 0); if (phy->rdd_state & BIT(1)) - mt7615_mcu_rdd_cmd(dev, RDD_STOP, 1, MT_RX_SEL0, 0); + mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, 1, + MT_RX_SEL0, 0); } static int mt7615_dfs_start_rdd(struct mt7615_dev *dev, int chain) { int err; - err = mt7615_mcu_rdd_cmd(dev, RDD_START, chain, MT_RX_SEL0, 0); + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_START, chain, + MT_RX_SEL0, 0); if (err < 0) return err; - return mt7615_mcu_rdd_cmd(dev, RDD_DET_MODE, chain, - MT_RX_SEL0, 1); + return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_DET_MODE, chain, + MT_RX_SEL0, 1); } static int mt7615_dfs_start_radar_detector(struct mt7615_phy *phy) @@ -2185,7 +2224,8 @@ static int mt7615_dfs_start_radar_detector(struct mt7615_phy *phy) int err; /* start CAC */ - err = mt7615_mcu_rdd_cmd(dev, RDD_CAC_START, ext_phy, MT_RX_SEL0, 0); + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_START, ext_phy, + MT_RX_SEL0, 0); if (err < 0) return err; @@ -2246,50 +2286,60 @@ mt7615_dfs_init_radar_specs(struct mt7615_phy *phy) int mt7615_dfs_init_radar_detector(struct mt7615_phy *phy) { - struct cfg80211_chan_def *chandef = &phy->mt76->chandef; struct mt7615_dev *dev = phy->dev; bool ext_phy = phy != &dev->phy; + enum mt76_dfs_state dfs_state, prev_state; int err; if (is_mt7663(&dev->mt76)) return 0; - if (dev->mt76.region == NL80211_DFS_UNSET) { - phy->dfs_state = -1; - if (phy->rdd_state) - goto stop; - - return 0; - } + prev_state = phy->mt76->dfs_state; + dfs_state = mt76_phy_dfs_state(phy->mt76); - if (test_bit(MT76_SCANNING, &phy->mt76->state)) + if (prev_state == dfs_state) return 0; - if (phy->dfs_state == chandef->chan->dfs_state) - return 0; + if (prev_state == MT_DFS_STATE_UNKNOWN) + mt7615_dfs_stop_radar_detector(phy); - err = mt7615_dfs_init_radar_specs(phy); - if (err < 0) { - phy->dfs_state = -1; + if (dfs_state == MT_DFS_STATE_DISABLED) goto stop; - } - phy->dfs_state = chandef->chan->dfs_state; + if (prev_state <= MT_DFS_STATE_DISABLED) { + err = mt7615_dfs_init_radar_specs(phy); + if (err < 0) + return err; + + err = mt7615_dfs_start_radar_detector(phy); + if (err < 0) + return err; + + phy->mt76->dfs_state = MT_DFS_STATE_CAC; + } - if (chandef->chan->flags & IEEE80211_CHAN_RADAR) { - if (chandef->chan->dfs_state != NL80211_DFS_AVAILABLE) - return mt7615_dfs_start_radar_detector(phy); + if (dfs_state == MT_DFS_STATE_CAC) + return 0; - return mt7615_mcu_rdd_cmd(dev, RDD_CAC_END, ext_phy, - MT_RX_SEL0, 0); + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_END, + ext_phy, MT_RX_SEL0, 0); + if (err < 0) { + phy->mt76->dfs_state = MT_DFS_STATE_UNKNOWN; + return err; } + phy->mt76->dfs_state = MT_DFS_STATE_ACTIVE; + return 0; + stop: - err = mt7615_mcu_rdd_cmd(dev, RDD_NORMAL_START, ext_phy, MT_RX_SEL0, 0); + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_NORMAL_START, ext_phy, + MT_RX_SEL0, 0); if (err < 0) return err; mt7615_dfs_stop_radar_detector(phy); + phy->mt76->dfs_state = MT_DFS_STATE_DISABLED; + return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index 82d625a16a62..7dcf1fb97eca 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -291,7 +291,8 @@ static void mt7615_init_dfs_state(struct mt7615_phy *phy) if (hw->conf.flags & IEEE80211_CONF_OFFCHANNEL) return; - if (!(chandef->chan->flags & IEEE80211_CHAN_RADAR)) + if (!(chandef->chan->flags & IEEE80211_CHAN_RADAR) && + !(mphy->chandef.chan->flags & IEEE80211_CHAN_RADAR)) return; if (mphy->chandef.chan->center_freq == chandef->chan->center_freq && @@ -365,6 +366,7 @@ static int mt7615_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ieee80211_key_conf *key) { struct mt7615_dev *dev = mt7615_hw_dev(hw); + struct mt7615_phy *phy = mt7615_hw_phy(hw); struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; struct mt7615_sta *msta = sta ? (struct mt7615_sta *)sta->drv_priv : &mvif->sta; @@ -403,6 +405,11 @@ static int mt7615_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, mt7615_mutex_acquire(dev); + if (cmd == SET_KEY && !sta && !mvif->mt76.cipher) { + mvif->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher); + mt7615_mcu_add_bss_info(phy, vif, NULL, true); + } + if (cmd == SET_KEY) *wcid_keyidx = idx; else if (idx == *wcid_keyidx) @@ -683,6 +690,9 @@ static void mt7615_sta_rate_tbl_update(struct ieee80211_hw *hw, struct ieee80211_sta_rates *sta_rates = rcu_dereference(sta->rates); int i; + if (!sta_rates) + return; + spin_lock_bh(&dev->mt76.lock); for (i = 0; i < ARRAY_SIZE(msta->rates); i++) { msta->rates[i].idx = sta_rates->rate[i].idx; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index 759dcf0e6783..f992e1285eaa 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -71,19 +71,6 @@ struct mt7663_fw_buf { #define IMG_CRC_LEN 4 -#define FW_FEATURE_SET_ENCRYPT BIT(0) -#define FW_FEATURE_SET_KEY_IDX GENMASK(2, 1) - -#define DL_MODE_ENCRYPT BIT(0) -#define DL_MODE_KEY_IDX GENMASK(2, 1) -#define DL_MODE_RESET_SEC_IV BIT(3) -#define DL_MODE_WORKING_PDA_CR4 BIT(4) -#define DL_MODE_VALID_RAM_ENTRY BIT(5) -#define DL_MODE_NEED_RSP BIT(31) - -#define FW_START_OVERRIDE BIT(0) -#define FW_START_WORKING_PDA_CR4 BIT(2) - void mt7615_mcu_fill_msg(struct mt7615_dev *dev, struct sk_buff *skb, int cmd, int *wait_seq) { @@ -756,145 +743,7 @@ out: static int mt7615_mcu_ctrl_pm_state(struct mt7615_dev *dev, int band, int state) { -#define ENTER_PM_STATE 1 -#define EXIT_PM_STATE 2 - struct { - u8 pm_number; - u8 pm_state; - u8 bssid[ETH_ALEN]; - u8 dtim_period; - u8 wlan_idx; - __le16 bcn_interval; - __le32 aid; - __le32 rx_filter; - u8 band_idx; - u8 rsv[3]; - __le32 feature; - u8 omac_idx; - u8 wmm_idx; - u8 bcn_loss_cnt; - u8 bcn_sp_duration; - } __packed req = { - .pm_number = 5, - .pm_state = state ? ENTER_PM_STATE : EXIT_PM_STATE, - .band_idx = band, - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(PM_STATE_CTRL), - &req, sizeof(req), true); -} - -static int -mt7615_mcu_bss_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, struct mt7615_phy *phy, - bool enable) -{ - struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; - u32 type = vif->p2p ? NETWORK_P2P : NETWORK_INFRA; - struct bss_info_basic *bss; - u8 wlan_idx = mvif->sta.wcid.idx; - struct tlv *tlv; - - tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_BASIC, sizeof(*bss)); - - switch (vif->type) { - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_MONITOR: - break; - case NL80211_IFTYPE_STATION: - /* TODO: enable BSS_INFO_UAPSD & BSS_INFO_PM */ - if (enable && sta) { - struct mt7615_sta *msta; - - msta = (struct mt7615_sta *)sta->drv_priv; - wlan_idx = msta->wcid.idx; - } - break; - case NL80211_IFTYPE_ADHOC: - type = NETWORK_IBSS; - break; - default: - WARN_ON(1); - break; - } - - bss = (struct bss_info_basic *)tlv; - bss->network_type = cpu_to_le32(type); - bss->bmc_wcid_lo = wlan_idx; - bss->wmm_idx = mvif->mt76.wmm_idx; - bss->active = enable; - - if (vif->type != NL80211_IFTYPE_MONITOR) { - memcpy(bss->bssid, vif->bss_conf.bssid, ETH_ALEN); - bss->bcn_interval = cpu_to_le16(vif->bss_conf.beacon_int); - bss->dtim_period = vif->bss_conf.dtim_period; - } else { - memcpy(bss->bssid, phy->mt76->macaddr, ETH_ALEN); - } - - return 0; -} - -static void -mt7615_mcu_bss_omac_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) -{ - struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; - u8 omac_idx = mvif->mt76.omac_idx; - struct bss_info_omac *omac; - struct tlv *tlv; - u32 type = 0; - - tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_OMAC, sizeof(*omac)); - - switch (vif->type) { - case NL80211_IFTYPE_MONITOR: - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_AP: - if (vif->p2p) - type = CONNECTION_P2P_GO; - else - type = CONNECTION_INFRA_AP; - break; - case NL80211_IFTYPE_STATION: - if (vif->p2p) - type = CONNECTION_P2P_GC; - else - type = CONNECTION_INFRA_STA; - break; - case NL80211_IFTYPE_ADHOC: - type = CONNECTION_IBSS_ADHOC; - break; - default: - WARN_ON(1); - break; - } - - omac = (struct bss_info_omac *)tlv; - omac->conn_type = cpu_to_le32(type); - omac->omac_idx = mvif->mt76.omac_idx; - omac->band_idx = mvif->mt76.band_idx; - omac->hw_bss_idx = omac_idx > EXT_BSSID_START ? HW_BSSID_0 : omac_idx; -} - -/* SIFS 20us + 512 byte beacon tranmitted by 1Mbps (3906us) */ -#define BCN_TX_ESTIMATE_TIME (4096 + 20) -static void -mt7615_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt7615_vif *mvif) -{ - struct bss_info_ext_bss *ext; - int ext_bss_idx, tsf_offset; - struct tlv *tlv; - - ext_bss_idx = mvif->mt76.omac_idx - EXT_BSSID_START; - if (ext_bss_idx < 0) - return; - - tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_EXT_BSS, sizeof(*ext)); - - ext = (struct bss_info_ext_bss *)tlv; - tsf_offset = ext_bss_idx * BCN_TX_ESTIMATE_TIME; - ext->mbss_tsf_offset = cpu_to_le32(tsf_offset); + return mt76_connac_mcu_set_pm(&dev->mt76, band, state); } static int @@ -913,13 +762,14 @@ mt7615_mcu_add_bss(struct mt7615_phy *phy, struct ieee80211_vif *vif, return PTR_ERR(skb); if (enable) - mt7615_mcu_bss_omac_tlv(skb, vif); + mt76_connac_mcu_bss_omac_tlv(skb, vif); - mt7615_mcu_bss_basic_tlv(skb, vif, sta, phy, enable); + mt76_connac_mcu_bss_basic_tlv(skb, vif, sta, phy->mt76, + mvif->sta.wcid.idx, enable); if (enable && mvif->mt76.omac_idx >= EXT_BSSID_START && mvif->mt76.omac_idx < REPEATER_BSSID_START) - mt7615_mcu_bss_ext_tlv(skb, mvif); + mt76_connac_mcu_bss_ext_tlv(skb, &mvif->mt76); return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD(BSS_INFO_UPDATE), true); @@ -1030,7 +880,7 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif, NULL, wtbl_hdr); if (sta) mt76_connac_mcu_wtbl_ht_tlv(&dev->mt76, wskb, sta, - NULL, wtbl_hdr); + NULL, wtbl_hdr, true); mt76_connac_mcu_wtbl_hdr_trans_tlv(wskb, vif, &msta->wcid, NULL, wtbl_hdr); } @@ -1057,19 +907,7 @@ mt7615_mcu_wtbl_update_hdr_trans(struct mt7615_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - struct mt7615_sta *msta = (struct mt7615_sta *)sta->drv_priv; - struct wtbl_req_hdr *wtbl_hdr; - struct sk_buff *skb = NULL; - - wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(&dev->mt76, &msta->wcid, - WTBL_SET, NULL, &skb); - if (IS_ERR(wtbl_hdr)) - return PTR_ERR(wtbl_hdr); - - mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, vif, &msta->wcid, NULL, - wtbl_hdr); - return mt76_mcu_skb_send_msg(&dev->mt76, skb, - MCU_EXT_CMD(WTBL_UPDATE), true); + return mt76_connac_mcu_wtbl_update_hdr_trans(&dev->mt76, vif, sta); } static const struct mt7615_mcu_ops wtbl_update_ops = { @@ -1303,7 +1141,8 @@ mt7615_mcu_uni_tx_ba(struct mt7615_dev *dev, struct mt7615_sta *sta = (struct mt7615_sta *)params->sta->drv_priv; return mt76_connac_mcu_sta_ba(&dev->mt76, &sta->vif->mt76, params, - enable, true); + MCU_UNI_CMD(STA_REC_UPDATE), enable, + true); } static int @@ -1451,20 +1290,6 @@ release_fw: return ret; } -static u32 mt7615_mcu_gen_dl_mode(u8 feature_set, bool is_cr4) -{ - u32 ret = 0; - - ret |= (feature_set & FW_FEATURE_SET_ENCRYPT) ? - (DL_MODE_ENCRYPT | DL_MODE_RESET_SEC_IV) : 0; - ret |= FIELD_PREP(DL_MODE_KEY_IDX, - FIELD_GET(FW_FEATURE_SET_KEY_IDX, feature_set)); - ret |= DL_MODE_NEED_RSP; - ret |= is_cr4 ? DL_MODE_WORKING_PDA_CR4 : 0; - - return ret; -} - static int mt7615_mcu_send_ram_firmware(struct mt7615_dev *dev, const struct mt7615_fw_trailer *hdr, @@ -1475,7 +1300,8 @@ mt7615_mcu_send_ram_firmware(struct mt7615_dev *dev, u32 len, addr, mode; for (i = 0; i < n_region; i++) { - mode = mt7615_mcu_gen_dl_mode(hdr[i].feature_set, is_cr4); + mode = mt76_connac_mcu_gen_dl_mode(&dev->mt76, + hdr[i].feature_set, is_cr4); len = le32_to_cpu(hdr[i].len) + IMG_CRC_LEN; addr = le32_to_cpu(hdr[i].addr); @@ -1723,7 +1549,8 @@ static int mt7663_load_n9(struct mt7615_dev *dev, const char *name) dev_info(dev->mt76.dev, "Parsing tailer Region: %d\n", i); buf = (const struct mt7663_fw_buf *)(base_addr - shift); - mode = mt7615_mcu_gen_dl_mode(buf->feature_set, false); + mode = mt76_connac_mcu_gen_dl_mode(&dev->mt76, + buf->feature_set, false); addr = le32_to_cpu(buf->img_dest_addr); len = le32_to_cpu(buf->img_size); @@ -2064,27 +1891,6 @@ int mt7615_mcu_del_wtbl_all(struct mt7615_dev *dev) &req, sizeof(req), true); } -int mt7615_mcu_rdd_cmd(struct mt7615_dev *dev, - enum mt7615_rdd_cmd cmd, u8 index, - u8 rx_sel, u8 val) -{ - struct { - u8 ctrl; - u8 rdd_idx; - u8 rdd_rx_sel; - u8 val; - u8 rsv[4]; - } req = { - .ctrl = cmd, - .rdd_idx = index, - .rdd_rx_sel = rx_sel, - .val = val, - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(SET_RDD_CTRL), - &req, sizeof(req), true); -} - int mt7615_mcu_set_fcc5_lpn(struct mt7615_dev *dev, int val) { struct { diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c index 33f72f3657d0..ce45c3bfc443 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c @@ -194,6 +194,7 @@ int mt7615_mmio_probe(struct device *pdev, void __iomem *mem_base, .token_size = MT7615_TOKEN_SIZE, .tx_prepare_skb = mt7615_tx_prepare_skb, .tx_complete_skb = mt7615_tx_complete_skb, + .rx_check = mt7615_rx_check, .rx_skb = mt7615_queue_rx_skb, .rx_poll_complete = mt7615_rx_poll_complete, .sta_ps = mt7615_sta_ps, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h index 6ff6d5800918..600fa2be4da0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h @@ -403,30 +403,9 @@ int mt7615_mcu_set_chan_info(struct mt7615_phy *phy, int cmd); int mt7615_mcu_set_wmm(struct mt7615_dev *dev, u8 queue, const struct ieee80211_tx_queue_params *params); void mt7615_mcu_rx_event(struct mt7615_dev *dev, struct sk_buff *skb); -int mt7615_mcu_rdd_cmd(struct mt7615_dev *dev, - enum mt7615_rdd_cmd cmd, u8 index, - u8 rx_sel, u8 val); int mt7615_mcu_rdd_send_pattern(struct mt7615_dev *dev); int mt7615_mcu_fw_log_2_host(struct mt7615_dev *dev, u8 ctrl); -static inline bool is_mt7622(struct mt76_dev *dev) -{ - if (!IS_ENABLED(CONFIG_MT7622_WMAC)) - return false; - - return mt76_chip(dev) == 0x7622; -} - -static inline bool is_mt7615(struct mt76_dev *dev) -{ - return mt76_chip(dev) == 0x7615 || mt76_chip(dev) == 0x7611; -} - -static inline bool is_mt7611(struct mt76_dev *dev) -{ - return mt76_chip(dev) == 0x7611; -} - static inline void mt7615_irq_enable(struct mt7615_dev *dev, u32 mask) { mt76_set_irq_mask(&dev->mt76, 0, 0, mask); @@ -530,6 +509,7 @@ int mt7615_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, void mt7615_tx_worker(struct mt76_worker *w); void mt7615_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e); void mt7615_tx_token_put(struct mt7615_dev *dev); +bool mt7615_rx_check(struct mt76_dev *mdev, void *data, int len); void mt7615_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb); void mt7615_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c index 31c4a76b7f91..49ab3a1f3b9b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c @@ -56,7 +56,10 @@ static int mt7663s_parse_intr(struct mt76_dev *dev, struct mt76s_intr *intr) struct mt7663s_intr *irq_data = sdio->intr_data; int i, err; + sdio_claim_host(sdio->func); err = sdio_readsb(sdio->func, irq_data, MCR_WHISR, sizeof(*irq_data)); + sdio_release_host(sdio->func); + if (err) return err; @@ -98,7 +101,7 @@ static int mt7663s_probe(struct sdio_func *func, struct ieee80211_ops *ops; struct mt7615_dev *dev; struct mt76_dev *mdev; - int i, ret; + int ret; ops = devm_kmemdup(&func->dev, &mt7615_ops, sizeof(mt7615_ops), GFP_KERNEL); @@ -137,16 +140,6 @@ static int mt7663s_probe(struct sdio_func *func, goto error; } - for (i = 0; i < ARRAY_SIZE(mdev->sdio.xmit_buf); i++) { - mdev->sdio.xmit_buf[i] = devm_kmalloc(mdev->dev, - MT76S_XMIT_BUF_SZ, - GFP_KERNEL); - if (!mdev->sdio.xmit_buf[i]) { - ret = -ENOMEM; - goto error; - } - } - ret = mt76s_alloc_rx_queue(mdev, MT_RXQ_MAIN); if (ret) goto error; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c index 0396ad532ba6..5cad398abf63 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c @@ -17,6 +17,7 @@ static const struct usb_device_id mt7615_device_table[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x0e8d, 0x7663, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x043e, 0x310c, 0xff, 0xff, 0xff) }, { }, }; diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h index e7f01c2978a2..e624843c2a25 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h @@ -45,9 +45,11 @@ enum { }; struct mt76_connac_pm { - bool enable; - bool ds_enable; - bool suspended; + bool enable:1; + bool enable_user:1; + bool ds_enable:1; + bool ds_enable_user:1; + bool suspended:1; spinlock_t txq_lock; struct { @@ -83,6 +85,11 @@ struct mt76_connac_coredump { unsigned long last_activity; }; +struct mt76_connac_sta_key_conf { + s8 keyidx; + u8 key[16]; +}; + extern const struct wiphy_wowlan_support mt76_connac_wowlan_support; static inline bool is_mt7922(struct mt76_dev *dev) @@ -100,6 +107,64 @@ static inline bool is_mt7663(struct mt76_dev *dev) return mt76_chip(dev) == 0x7663; } +static inline bool is_mt7915(struct mt76_dev *dev) +{ + return mt76_chip(dev) == 0x7915; +} + +static inline bool is_mt7916(struct mt76_dev *dev) +{ + return mt76_chip(dev) == 0x7906; +} + +static inline bool is_mt7622(struct mt76_dev *dev) +{ + if (!IS_ENABLED(CONFIG_MT7622_WMAC)) + return false; + + return mt76_chip(dev) == 0x7622; +} + +static inline bool is_mt7615(struct mt76_dev *dev) +{ + return mt76_chip(dev) == 0x7615 || mt76_chip(dev) == 0x7611; +} + +static inline bool is_mt7611(struct mt76_dev *dev) +{ + return mt76_chip(dev) == 0x7611; +} + +static inline bool is_connac_v1(struct mt76_dev *dev) +{ + return is_mt7615(dev) || is_mt7663(dev) || is_mt7622(dev); +} + +static inline u8 mt76_connac_chan_bw(struct cfg80211_chan_def *chandef) +{ + static const u8 width_to_bw[] = { + [NL80211_CHAN_WIDTH_40] = CMD_CBW_40MHZ, + [NL80211_CHAN_WIDTH_80] = CMD_CBW_80MHZ, + [NL80211_CHAN_WIDTH_80P80] = CMD_CBW_8080MHZ, + [NL80211_CHAN_WIDTH_160] = CMD_CBW_160MHZ, + [NL80211_CHAN_WIDTH_5] = CMD_CBW_5MHZ, + [NL80211_CHAN_WIDTH_10] = CMD_CBW_10MHZ, + [NL80211_CHAN_WIDTH_20] = CMD_CBW_20MHZ, + [NL80211_CHAN_WIDTH_20_NOHT] = CMD_CBW_20MHZ, + }; + + if (chandef->width >= ARRAY_SIZE(width_to_bw)) + return 0; + + return width_to_bw[chandef->width]; +} + +static inline u8 mt76_connac_lmac_mapping(u8 ac) +{ + /* LMAC uses the reverse order of mac80211 AC indexes */ + return 3 - ac; +} + int mt76_connac_pm_wake(struct mt76_phy *phy, struct mt76_connac_pm *pm); void mt76_connac_power_save_sched(struct mt76_phy *phy, struct mt76_connac_pm *pm); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index f79e3d5084f3..cdd82a62eeb1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -62,8 +62,8 @@ int mt76_connac_mcu_init_download(struct mt76_dev *dev, u32 addr, u32 len, }; int cmd; - if (is_mt7921(dev) && - (req.addr == cpu_to_le32(MCU_PATCH_ADDRESS) || addr == 0x900000)) + if ((!is_connac_v1(dev) && addr == MCU_PATCH_ADDRESS) || + (is_mt7921(dev) && addr == 0x900000)) cmd = MCU_CMD(PATCH_START_REQ); else cmd = MCU_CMD(TARGET_ADDRESS_LEN_REQ); @@ -266,8 +266,8 @@ mt76_connac_mcu_add_nested_tlv(struct sk_buff *skb, int tag, int len, EXPORT_SYMBOL_GPL(mt76_connac_mcu_add_nested_tlv); struct sk_buff * -mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, - struct mt76_wcid *wcid) +__mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, + struct mt76_wcid *wcid, int len) { struct sta_req_hdr hdr = { .bss_idx = mvif->idx, @@ -278,7 +278,7 @@ mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, mt76_connac_mcu_get_wlan_idx(dev, wcid, &hdr.wlan_idx_lo, &hdr.wlan_idx_hi); - skb = mt76_mcu_msg_alloc(dev, NULL, MT76_CONNAC_STA_UPDATE_MAX_SIZE); + skb = mt76_mcu_msg_alloc(dev, NULL, len); if (!skb) return ERR_PTR(-ENOMEM); @@ -286,7 +286,7 @@ mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, return skb; } -EXPORT_SYMBOL_GPL(mt76_connac_mcu_alloc_sta_req); +EXPORT_SYMBOL_GPL(__mt76_connac_mcu_alloc_sta_req); struct wtbl_req_hdr * mt76_connac_mcu_alloc_wtbl_req(struct mt76_dev *dev, struct mt76_wcid *wcid, @@ -310,12 +310,54 @@ mt76_connac_mcu_alloc_wtbl_req(struct mt76_dev *dev, struct mt76_wcid *wcid, } if (sta_hdr) - sta_hdr->len = cpu_to_le16(sizeof(hdr)); + le16_add_cpu(&sta_hdr->len, sizeof(hdr)); return skb_put_data(nskb, &hdr, sizeof(hdr)); } EXPORT_SYMBOL_GPL(mt76_connac_mcu_alloc_wtbl_req); +void mt76_connac_mcu_bss_omac_tlv(struct sk_buff *skb, + struct ieee80211_vif *vif) +{ + struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + u8 omac_idx = mvif->omac_idx; + struct bss_info_omac *omac; + struct tlv *tlv; + u32 type = 0; + + switch (vif->type) { + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_AP: + if (vif->p2p) + type = CONNECTION_P2P_GO; + else + type = CONNECTION_INFRA_AP; + break; + case NL80211_IFTYPE_STATION: + if (vif->p2p) + type = CONNECTION_P2P_GC; + else + type = CONNECTION_INFRA_STA; + break; + case NL80211_IFTYPE_ADHOC: + type = CONNECTION_IBSS_ADHOC; + break; + default: + WARN_ON(1); + break; + } + + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_OMAC, sizeof(*omac)); + + omac = (struct bss_info_omac *)tlv; + omac->conn_type = cpu_to_le32(type); + omac->omac_idx = mvif->omac_idx; + omac->band_idx = mvif->band_idx; + omac->hw_bss_idx = omac_idx > EXT_BSSID_START ? HW_BSSID_0 : omac_idx; +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_bss_omac_tlv); + void mt76_connac_mcu_sta_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct ieee80211_sta *sta, @@ -376,9 +418,8 @@ void mt76_connac_mcu_sta_basic_tlv(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_basic_tlv); -static void -mt76_connac_mcu_sta_uapsd(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) +void mt76_connac_mcu_sta_uapsd(struct sk_buff *skb, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) { struct sta_rec_uapsd *uapsd; struct tlv *tlv; @@ -407,6 +448,7 @@ mt76_connac_mcu_sta_uapsd(struct sk_buff *skb, struct ieee80211_vif *vif, } uapsd->max_sp = sta->max_sp; } +EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_uapsd); void mt76_connac_mcu_wtbl_hdr_trans_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, @@ -420,13 +462,17 @@ void mt76_connac_mcu_wtbl_hdr_trans_tlv(struct sk_buff *skb, sizeof(*htr), wtbl_tlv, sta_wtbl); htr = (struct wtbl_hdr_trans *)tlv; - htr->no_rx_trans = !test_bit(MT_WCID_FLAG_HDR_TRANS, &wcid->flags); + htr->no_rx_trans = true; if (vif->type == NL80211_IFTYPE_STATION) htr->to_ds = true; else htr->from_ds = true; + if (!wcid) + return; + + htr->no_rx_trans = !test_bit(MT_WCID_FLAG_HDR_TRANS, &wcid->flags); if (test_bit(MT_WCID_FLAG_4ADDR, &wcid->flags)) { htr->to_ds = true; htr->from_ds = true; @@ -461,6 +507,25 @@ int mt76_connac_mcu_sta_update_hdr_trans(struct mt76_dev *dev, } EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_update_hdr_trans); +int mt76_connac_mcu_wtbl_update_hdr_trans(struct mt76_dev *dev, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv; + struct wtbl_req_hdr *wtbl_hdr; + struct sk_buff *skb = NULL; + + wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(dev, wcid, WTBL_SET, NULL, + &skb); + if (IS_ERR(wtbl_hdr)) + return PTR_ERR(wtbl_hdr); + + mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, vif, wcid, NULL, wtbl_hdr); + + return mt76_mcu_skb_send_msg(dev, skb, MCU_EXT_CMD(WTBL_UPDATE), true); +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_wtbl_update_hdr_trans); + void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_vif *vif, @@ -488,8 +553,7 @@ void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, generic->muar_idx = mvif->omac_idx; generic->qos = sta->wme; } else { - if (is_mt7921(dev) && - vif->type == NL80211_IFTYPE_STATION) + if (!is_connac_v1(dev) && vif->type == NL80211_IFTYPE_STATION) memcpy(generic->peer_addr, vif->bss_conf.bssid, ETH_ALEN); else @@ -506,7 +570,7 @@ void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, rx->rca2 = 1; rx->rv = 1; - if (is_mt7921(dev)) + if (!is_connac_v1(dev)) return; tlv = mt76_connac_mcu_add_nested_tlv(skb, WTBL_SPE, sizeof(*spe), @@ -819,9 +883,9 @@ void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_tlv); -static void -mt76_connac_mcu_wtbl_smps_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, - void *sta_wtbl, void *wtbl_tlv) +void mt76_connac_mcu_wtbl_smps_tlv(struct sk_buff *skb, + struct ieee80211_sta *sta, + void *sta_wtbl, void *wtbl_tlv) { struct wtbl_smps *smps; struct tlv *tlv; @@ -829,14 +893,13 @@ mt76_connac_mcu_wtbl_smps_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, tlv = mt76_connac_mcu_add_nested_tlv(skb, WTBL_SMPS, sizeof(*smps), wtbl_tlv, sta_wtbl); smps = (struct wtbl_smps *)tlv; - - if (sta->smps_mode == IEEE80211_SMPS_DYNAMIC) - smps->smps = true; + smps->smps = (sta->smps_mode == IEEE80211_SMPS_DYNAMIC); } +EXPORT_SYMBOL_GPL(mt76_connac_mcu_wtbl_smps_tlv); void mt76_connac_mcu_wtbl_ht_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_sta *sta, void *sta_wtbl, - void *wtbl_tlv) + void *wtbl_tlv, bool ldpc) { struct wtbl_ht *ht = NULL; struct tlv *tlv; @@ -846,7 +909,8 @@ void mt76_connac_mcu_wtbl_ht_tlv(struct mt76_dev *dev, struct sk_buff *skb, tlv = mt76_connac_mcu_add_nested_tlv(skb, WTBL_HT, sizeof(*ht), wtbl_tlv, sta_wtbl); ht = (struct wtbl_ht *)tlv; - ht->ldpc = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING); + ht->ldpc = ldpc && + !!(sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING); ht->af = sta->ht_cap.ampdu_factor; ht->mm = sta->ht_cap.ampdu_density; ht->ht = true; @@ -860,7 +924,8 @@ void mt76_connac_mcu_wtbl_ht_tlv(struct mt76_dev *dev, struct sk_buff *skb, sizeof(*vht), wtbl_tlv, sta_wtbl); vht = (struct wtbl_vht *)tlv; - vht->ldpc = !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC); + vht->ldpc = ldpc && + !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC); vht->vht = true; af = FIELD_GET(IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK, @@ -871,7 +936,7 @@ void mt76_connac_mcu_wtbl_ht_tlv(struct mt76_dev *dev, struct sk_buff *skb, mt76_connac_mcu_wtbl_smps_tlv(skb, sta, sta_wtbl, wtbl_tlv); - if (!is_mt7921(dev) && sta->ht_cap.ht_supported) { + if (is_connac_v1(dev) && sta->ht_cap.ht_supported) { /* sgi */ u32 msk = MT_WTBL_W5_SHORT_GI_20 | MT_WTBL_W5_SHORT_GI_40 | MT_WTBL_W5_SHORT_GI_80 | MT_WTBL_W5_SHORT_GI_160; @@ -939,7 +1004,7 @@ int mt76_connac_mcu_sta_cmd(struct mt76_phy *phy, sta_wtbl, wtbl_hdr); if (info->sta) mt76_connac_mcu_wtbl_ht_tlv(dev, skb, info->sta, - sta_wtbl, wtbl_hdr); + sta_wtbl, wtbl_hdr, true); } return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true); @@ -973,7 +1038,7 @@ void mt76_connac_mcu_wtbl_ba_tlv(struct mt76_dev *dev, struct sk_buff *skb, ba->rst_ba_sb = 1; } - if (is_mt7921(dev)) { + if (!is_connac_v1(dev)) { ba->ba_winsize = enable ? cpu_to_le16(params->buf_size) : 0; return; } @@ -1106,7 +1171,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_ba_tlv); int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, struct ieee80211_ampdu_params *params, - bool enable, bool tx) + int cmd, bool enable, bool tx) { struct mt76_wcid *wcid = (struct mt76_wcid *)params->sta->drv_priv; struct wtbl_req_hdr *wtbl_hdr; @@ -1129,8 +1194,7 @@ int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, mt76_connac_mcu_wtbl_ba_tlv(dev, skb, params, enable, tx, sta_wtbl, wtbl_hdr); - ret = mt76_mcu_skb_send_msg(dev, skb, - MCU_UNI_CMD(STA_REC_UPDATE), true); + ret = mt76_mcu_skb_send_msg(dev, skb, cmd, true); if (ret) return ret; @@ -1140,15 +1204,12 @@ int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, mt76_connac_mcu_sta_ba_tlv(skb, params, enable, tx); - return mt76_mcu_skb_send_msg(dev, skb, - MCU_UNI_CMD(STA_REC_UPDATE), true); + return mt76_mcu_skb_send_msg(dev, skb, cmd, true); } EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_ba); -static u8 -mt76_connac_get_phy_mode(struct mt76_phy *phy, struct ieee80211_vif *vif, - enum nl80211_band band, - struct ieee80211_sta *sta) +u8 mt76_connac_get_phy_mode(struct mt76_phy *phy, struct ieee80211_vif *vif, + enum nl80211_band band, struct ieee80211_sta *sta) { struct mt76_dev *dev = phy->dev; const struct ieee80211_sta_he_cap *he_cap; @@ -1156,7 +1217,7 @@ mt76_connac_get_phy_mode(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta_ht_cap *ht_cap; u8 mode = 0; - if (!is_mt7921(dev)) + if (is_connac_v1(dev)) return 0x38; if (sta) { @@ -1195,8 +1256,9 @@ mt76_connac_get_phy_mode(struct mt76_phy *phy, struct ieee80211_vif *vif, return mode; } +EXPORT_SYMBOL_GPL(mt76_connac_get_phy_mode); -static const struct ieee80211_sta_he_cap * +const struct ieee80211_sta_he_cap * mt76_connac_get_he_phy_cap(struct mt76_phy *phy, struct ieee80211_vif *vif) { enum nl80211_band band = phy->chandef.chan->band; @@ -1206,6 +1268,7 @@ mt76_connac_get_he_phy_cap(struct mt76_phy *phy, struct ieee80211_vif *vif) return ieee80211_get_he_iftype_cap(sband, vif->type); } +EXPORT_SYMBOL_GPL(mt76_connac_get_he_phy_cap); #define DEFAULT_HE_PE_DURATION 4 #define DEFAULT_HE_DURATION_RTS_THRES 1023 @@ -2482,5 +2545,246 @@ void mt76_connac_mcu_reg_wr(struct mt76_dev *dev, u32 offset, u32 val) } EXPORT_SYMBOL_GPL(mt76_connac_mcu_reg_wr); +static int +mt76_connac_mcu_sta_key_tlv(struct mt76_connac_sta_key_conf *sta_key_conf, + struct sk_buff *skb, + struct ieee80211_key_conf *key, + enum set_key_cmd cmd) +{ + struct sta_rec_sec *sec; + u32 len = sizeof(*sec); + struct tlv *tlv; + + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_KEY_V2, sizeof(*sec)); + sec = (struct sta_rec_sec *)tlv; + sec->add = cmd; + + if (cmd == SET_KEY) { + struct sec_key *sec_key; + u8 cipher; + + cipher = mt76_connac_mcu_get_cipher(key->cipher); + if (cipher == MCU_CIPHER_NONE) + return -EOPNOTSUPP; + + sec_key = &sec->key[0]; + sec_key->cipher_len = sizeof(*sec_key); + + if (cipher == MCU_CIPHER_BIP_CMAC_128) { + sec_key->cipher_id = MCU_CIPHER_AES_CCMP; + sec_key->key_id = sta_key_conf->keyidx; + sec_key->key_len = 16; + memcpy(sec_key->key, sta_key_conf->key, 16); + + sec_key = &sec->key[1]; + sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128; + sec_key->cipher_len = sizeof(*sec_key); + sec_key->key_len = 16; + memcpy(sec_key->key, key->key, 16); + sec->n_cipher = 2; + } else { + sec_key->cipher_id = cipher; + sec_key->key_id = key->keyidx; + sec_key->key_len = key->keylen; + memcpy(sec_key->key, key->key, key->keylen); + + if (cipher == MCU_CIPHER_TKIP) { + /* Rx/Tx MIC keys are swapped */ + memcpy(sec_key->key + 16, key->key + 24, 8); + memcpy(sec_key->key + 24, key->key + 16, 8); + } + + /* store key_conf for BIP batch update */ + if (cipher == MCU_CIPHER_AES_CCMP) { + memcpy(sta_key_conf->key, key->key, key->keylen); + sta_key_conf->keyidx = key->keyidx; + } + + len -= sizeof(*sec_key); + sec->n_cipher = 1; + } + } else { + len -= sizeof(sec->key); + sec->n_cipher = 0; + } + sec->len = cpu_to_le16(len); + + return 0; +} + +int mt76_connac_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, + struct mt76_connac_sta_key_conf *sta_key_conf, + struct ieee80211_key_conf *key, int mcu_cmd, + struct mt76_wcid *wcid, enum set_key_cmd cmd) +{ + struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct sk_buff *skb; + int ret; + + skb = mt76_connac_mcu_alloc_sta_req(dev, mvif, wcid); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + ret = mt76_connac_mcu_sta_key_tlv(sta_key_conf, skb, key, cmd); + if (ret) + return ret; + + return mt76_mcu_skb_send_msg(dev, skb, mcu_cmd, true); +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_add_key); + +/* SIFS 20us + 512 byte beacon tranmitted by 1Mbps (3906us) */ +#define BCN_TX_ESTIMATE_TIME (4096 + 20) +void mt76_connac_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt76_vif *mvif) +{ + struct bss_info_ext_bss *ext; + int ext_bss_idx, tsf_offset; + struct tlv *tlv; + + ext_bss_idx = mvif->omac_idx - EXT_BSSID_START; + if (ext_bss_idx < 0) + return; + + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_EXT_BSS, sizeof(*ext)); + + ext = (struct bss_info_ext_bss *)tlv; + tsf_offset = ext_bss_idx * BCN_TX_ESTIMATE_TIME; + ext->mbss_tsf_offset = cpu_to_le32(tsf_offset); +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_bss_ext_tlv); + +int mt76_connac_mcu_bss_basic_tlv(struct sk_buff *skb, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct mt76_phy *phy, u8 wlan_idx, + bool enable) +{ + struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + u32 type = vif->p2p ? NETWORK_P2P : NETWORK_INFRA; + struct bss_info_basic *bss; + struct tlv *tlv; + + switch (vif->type) { + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_MONITOR: + break; + case NL80211_IFTYPE_STATION: + if (enable) { + rcu_read_lock(); + if (!sta) + sta = ieee80211_find_sta(vif, + vif->bss_conf.bssid); + /* TODO: enable BSS_INFO_UAPSD & BSS_INFO_PM */ + if (sta) { + struct mt76_wcid *wcid; + + wcid = (struct mt76_wcid *)sta->drv_priv; + wlan_idx = wcid->idx; + } + rcu_read_unlock(); + } + break; + case NL80211_IFTYPE_ADHOC: + type = NETWORK_IBSS; + break; + default: + WARN_ON(1); + break; + } + + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_BASIC, sizeof(*bss)); + + bss = (struct bss_info_basic *)tlv; + bss->network_type = cpu_to_le32(type); + bss->bmc_wcid_lo = to_wcid_lo(wlan_idx); + bss->bmc_wcid_hi = to_wcid_hi(wlan_idx); + bss->wmm_idx = mvif->wmm_idx; + bss->active = enable; + bss->cipher = mvif->cipher; + + if (vif->type != NL80211_IFTYPE_MONITOR) { + struct cfg80211_chan_def *chandef = &phy->chandef; + + memcpy(bss->bssid, vif->bss_conf.bssid, ETH_ALEN); + bss->bcn_interval = cpu_to_le16(vif->bss_conf.beacon_int); + bss->dtim_period = vif->bss_conf.dtim_period; + bss->phy_mode = mt76_connac_get_phy_mode(phy, vif, + chandef->chan->band, NULL); + } else { + memcpy(bss->bssid, phy->macaddr, ETH_ALEN); + } + + return 0; +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_bss_basic_tlv); + +#define ENTER_PM_STATE 1 +#define EXIT_PM_STATE 2 +int mt76_connac_mcu_set_pm(struct mt76_dev *dev, int band, int enter) +{ + struct { + u8 pm_number; + u8 pm_state; + u8 bssid[ETH_ALEN]; + u8 dtim_period; + u8 wlan_idx_lo; + __le16 bcn_interval; + __le32 aid; + __le32 rx_filter; + u8 band_idx; + u8 wlan_idx_hi; + u8 rsv[2]; + __le32 feature; + u8 omac_idx; + u8 wmm_idx; + u8 bcn_loss_cnt; + u8 bcn_sp_duration; + } __packed req = { + .pm_number = 5, + .pm_state = enter ? ENTER_PM_STATE : EXIT_PM_STATE, + .band_idx = band, + }; + + return mt76_mcu_send_msg(dev, MCU_EXT_CMD(PM_STATE_CTRL), &req, + sizeof(req), true); +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_pm); + +int mt76_connac_mcu_restart(struct mt76_dev *dev) +{ + struct { + u8 power_mode; + u8 rsv[3]; + } req = { + .power_mode = 1, + }; + + return mt76_mcu_send_msg(dev, MCU_CMD(NIC_POWER_CTRL), &req, + sizeof(req), false); +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_restart); + +int mt76_connac_mcu_rdd_cmd(struct mt76_dev *dev, int cmd, u8 index, + u8 rx_sel, u8 val) +{ + struct { + u8 ctrl; + u8 rdd_idx; + u8 rdd_rx_sel; + u8 val; + u8 rsv[4]; + } __packed req = { + .ctrl = cmd, + .rdd_idx = index, + .rdd_rx_sel = rx_sel, + .val = val, + }; + + return mt76_mcu_send_msg(dev, MCU_EXT_CMD(SET_RDD_CTRL), &req, + sizeof(req), true); +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_rdd_cmd); + MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h index 5baf8370b7bd..7b9d82dd3f9d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h @@ -6,6 +6,26 @@ #include "mt76_connac.h" +#define FW_FEATURE_SET_ENCRYPT BIT(0) +#define FW_FEATURE_SET_KEY_IDX GENMASK(2, 1) +#define FW_FEATURE_ENCRY_MODE BIT(4) +#define FW_FEATURE_OVERRIDE_ADDR BIT(5) + +#define DL_MODE_ENCRYPT BIT(0) +#define DL_MODE_KEY_IDX GENMASK(2, 1) +#define DL_MODE_RESET_SEC_IV BIT(3) +#define DL_MODE_WORKING_PDA_CR4 BIT(4) +#define DL_MODE_VALID_RAM_ENTRY BIT(5) +#define DL_CONFIG_ENCRY_MODE_SEL BIT(6) +#define DL_MODE_NEED_RSP BIT(31) + +#define FW_START_OVERRIDE BIT(0) +#define FW_START_WORKING_PDA_CR4 BIT(2) + +#define PATCH_SEC_NOT_SUPPORT GENMASK(31, 0) +#define PATCH_SEC_TYPE_MASK GENMASK(15, 0) +#define PATCH_SEC_TYPE_INFO 0x2 + struct tlv { __le16 tag; __le16 len; @@ -570,6 +590,7 @@ struct wtbl_raw { sizeof(struct sta_rec_muru) + \ sizeof(struct sta_rec_bfee) + \ sizeof(struct sta_rec_ra) + \ + sizeof(struct sta_rec_sec) + \ sizeof(struct sta_rec_ra_fixed) + \ sizeof(struct sta_rec_he_6g_capa) + \ sizeof(struct tlv) + \ @@ -956,6 +977,7 @@ enum { MCU_EXT_CMD_SCS_CTRL = 0x82, MCU_EXT_CMD_TWT_AGRT_UPDATE = 0x94, MCU_EXT_CMD_FW_DBG_CTRL = 0x95, + MCU_EXT_CMD_OFFCH_SCAN_CTRL = 0x9a, MCU_EXT_CMD_SET_RDD_TH = 0x9d, MCU_EXT_CMD_MURU_CTRL = 0x9f, MCU_EXT_CMD_SET_SPR = 0xa8, @@ -996,7 +1018,8 @@ enum { MCU_CE_CMD_SET_BSS_CONNECTED = 0x16, MCU_CE_CMD_SET_BSS_ABORT = 0x17, MCU_CE_CMD_CANCEL_HW_SCAN = 0x1b, - MCU_CE_CMD_SET_ROC = 0x1d, + MCU_CE_CMD_SET_ROC = 0x1c, + MCU_CE_CMD_SET_EDCA_PARMS = 0x1d, MCU_CE_CMD_SET_P2P_OPPPS = 0x33, MCU_CE_CMD_SET_RATE_TX_POWER = 0x5d, MCU_CE_CMD_SCHED_SCAN_ENABLE = 0x61, @@ -1427,6 +1450,51 @@ struct mt76_connac_config { u8 data[320]; } __packed; +static inline enum mcu_cipher_type +mt76_connac_mcu_get_cipher(int cipher) +{ + switch (cipher) { + case WLAN_CIPHER_SUITE_WEP40: + return MCU_CIPHER_WEP40; + case WLAN_CIPHER_SUITE_WEP104: + return MCU_CIPHER_WEP104; + case WLAN_CIPHER_SUITE_TKIP: + return MCU_CIPHER_TKIP; + case WLAN_CIPHER_SUITE_AES_CMAC: + return MCU_CIPHER_BIP_CMAC_128; + case WLAN_CIPHER_SUITE_CCMP: + return MCU_CIPHER_AES_CCMP; + case WLAN_CIPHER_SUITE_CCMP_256: + return MCU_CIPHER_CCMP_256; + case WLAN_CIPHER_SUITE_GCMP: + return MCU_CIPHER_GCMP; + case WLAN_CIPHER_SUITE_GCMP_256: + return MCU_CIPHER_GCMP_256; + case WLAN_CIPHER_SUITE_SMS4: + return MCU_CIPHER_WAPI; + default: + return MCU_CIPHER_NONE; + } +} + +static inline u32 +mt76_connac_mcu_gen_dl_mode(struct mt76_dev *dev, u8 feature_set, bool is_wa) +{ + u32 ret = 0; + + ret |= feature_set & FW_FEATURE_SET_ENCRYPT ? + DL_MODE_ENCRYPT | DL_MODE_RESET_SEC_IV : 0; + if (is_mt7921(dev)) + ret |= feature_set & FW_FEATURE_ENCRY_MODE ? + DL_CONFIG_ENCRY_MODE_SEL : 0; + ret |= FIELD_PREP(DL_MODE_KEY_IDX, + FIELD_GET(FW_FEATURE_SET_KEY_IDX, feature_set)); + ret |= DL_MODE_NEED_RSP; + ret |= is_wa ? DL_MODE_WORKING_PDA_CR4 : 0; + + return ret; +} + #define to_wcid_lo(id) FIELD_GET(GENMASK(7, 0), (u16)id) #define to_wcid_hi(id) FIELD_GET(GENMASK(9, 8), (u16)id) @@ -1436,7 +1504,7 @@ mt76_connac_mcu_get_wlan_idx(struct mt76_dev *dev, struct mt76_wcid *wcid, { *wlan_idx_hi = 0; - if (is_mt7921(dev)) { + if (!is_connac_v1(dev)) { *wlan_idx_lo = wcid ? to_wcid_lo(wcid->idx) : 0; *wlan_idx_hi = wcid ? to_wcid_hi(wcid->idx) : 0; } else { @@ -1445,8 +1513,16 @@ mt76_connac_mcu_get_wlan_idx(struct mt76_dev *dev, struct mt76_wcid *wcid, } struct sk_buff * +__mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, + struct mt76_wcid *wcid, int len); +static inline struct sk_buff * mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, - struct mt76_wcid *wcid); + struct mt76_wcid *wcid) +{ + return __mt76_connac_mcu_alloc_sta_req(dev, mvif, wcid, + MT76_CONNAC_STA_UPDATE_MAX_SIZE); +} + struct wtbl_req_hdr * mt76_connac_mcu_alloc_wtbl_req(struct mt76_dev *dev, struct mt76_wcid *wcid, int cmd, void *sta_wtbl, struct sk_buff **skb); @@ -1476,13 +1552,16 @@ void mt76_connac_mcu_wtbl_hdr_trans_tlv(struct sk_buff *skb, int mt76_connac_mcu_sta_update_hdr_trans(struct mt76_dev *dev, struct ieee80211_vif *vif, struct mt76_wcid *wcid, int cmd); +int mt76_connac_mcu_wtbl_update_hdr_trans(struct mt76_dev *dev, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta); void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb, struct ieee80211_sta *sta, struct ieee80211_vif *vif, u8 rcpi, u8 state); void mt76_connac_mcu_wtbl_ht_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_sta *sta, void *sta_wtbl, - void *wtbl_tlv); + void *wtbl_tlv, bool ldpc); void mt76_connac_mcu_wtbl_ba_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_ampdu_params *params, bool enable, bool tx, void *sta_wtbl, @@ -1496,7 +1575,7 @@ int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy, bool enable); int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif *mvif, struct ieee80211_ampdu_params *params, - bool enable, bool tx); + int cmd, bool enable, bool tx); int mt76_connac_mcu_uni_add_bss(struct mt76_phy *phy, struct ieee80211_vif *vif, struct mt76_wcid *wcid, @@ -1546,4 +1625,32 @@ int mt76_connac_mcu_set_p2p_oppps(struct ieee80211_hw *hw, struct ieee80211_vif *vif); u32 mt76_connac_mcu_reg_rr(struct mt76_dev *dev, u32 offset); void mt76_connac_mcu_reg_wr(struct mt76_dev *dev, u32 offset, u32 val); + +const struct ieee80211_sta_he_cap * +mt76_connac_get_he_phy_cap(struct mt76_phy *phy, struct ieee80211_vif *vif); +u8 mt76_connac_get_phy_mode(struct mt76_phy *phy, struct ieee80211_vif *vif, + enum nl80211_band band, struct ieee80211_sta *sta); + +int mt76_connac_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, + struct mt76_connac_sta_key_conf *sta_key_conf, + struct ieee80211_key_conf *key, int mcu_cmd, + struct mt76_wcid *wcid, enum set_key_cmd cmd); + +void mt76_connac_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt76_vif *mvif); +void mt76_connac_mcu_bss_omac_tlv(struct sk_buff *skb, + struct ieee80211_vif *vif); +int mt76_connac_mcu_bss_basic_tlv(struct sk_buff *skb, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct mt76_phy *phy, u8 wlan_idx, + bool enable); +void mt76_connac_mcu_sta_uapsd(struct sk_buff *skb, struct ieee80211_vif *vif, + struct ieee80211_sta *sta); +void mt76_connac_mcu_wtbl_smps_tlv(struct sk_buff *skb, + struct ieee80211_sta *sta, + void *sta_wtbl, void *wtbl_tlv); +int mt76_connac_mcu_set_pm(struct mt76_dev *dev, int band, int enter); +int mt76_connac_mcu_restart(struct mt76_dev *dev); +int mt76_connac_mcu_rdd_cmd(struct mt76_dev *dev, int cmd, u8 index, + u8 rx_sel, u8 val); #endif /* __MT76_CONNAC_MCU_H */ diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h index 44d1a92d9a90..f76fd22ee035 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h @@ -103,7 +103,8 @@ struct mt76x02_dev { u8 tbtt_count; u32 tx_hang_reset; - u8 tx_hang_check; + u8 tx_hang_check[4]; + u8 beacon_hang_check; u8 mcu_timeout; struct mt76x02_calibration cal; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c index a601350531cd..024a5c0a5a57 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c @@ -823,10 +823,7 @@ EXPORT_SYMBOL_GPL(mt76x02_phy_dfs_adjust_agc); void mt76x02_dfs_init_params(struct mt76x02_dev *dev) { - struct cfg80211_chan_def *chandef = &dev->mphy.chandef; - - if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) && - dev->mt76.region != NL80211_DFS_UNSET) { + if (mt76_phy_dfs_state(&dev->mphy) > MT_DFS_STATE_DISABLED) { mt76x02_dfs_init_sw_detector(dev); mt76x02_dfs_set_bbp_params(dev); /* enable debug mode */ diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c index a404fd7ea968..dc2aeaab72ec 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c @@ -1040,12 +1040,26 @@ EXPORT_SYMBOL_GPL(mt76x02_update_channel); static void mt76x02_check_mac_err(struct mt76x02_dev *dev) { - u32 val = mt76_rr(dev, 0x10f4); + if (dev->mt76.beacon_mask) { + if (mt76_rr(dev, MT_TX_STA_0) & MT_TX_STA_0_BEACONS) { + dev->beacon_hang_check = 0; + return; + } - if (!(val & BIT(29)) || !(val & (BIT(7) | BIT(5)))) - return; + if (++dev->beacon_hang_check < 10) + return; + + dev->beacon_hang_check = 0; + } else { + u32 val = mt76_rr(dev, 0x10f4); + if (!(val & BIT(29)) || !(val & (BIT(7) | BIT(5)))) + return; + } + + dev_err(dev->mt76.dev, "MAC error detected\n"); - dev_err(dev->mt76.dev, "mac specific condition occurred\n"); + mt76_wr(dev, MT_MAC_SYS_CTRL, 0); + mt76x02_wait_for_txrx_idle(&dev->mt76); mt76_set(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR); udelay(10); @@ -1178,8 +1192,7 @@ void mt76x02_mac_work(struct work_struct *work) dev->mt76.aggr_stats[idx++] += val >> 16; } - if (!dev->mt76.beacon_mask) - mt76x02_check_mac_err(dev); + mt76x02_check_mac_err(dev); if (dev->ed_monitor) mt76x02_edcca_check(dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index ec0de691129a..8bcd8afa0d3a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -348,18 +348,20 @@ static bool mt76x02_tx_hang(struct mt76x02_dev *dev) for (i = 0; i < 4; i++) { q = dev->mphy.q_tx[i]; - if (!q->queued) - continue; - prev_dma_idx = dev->mt76.tx_dma_idx[i]; dma_idx = readl(&q->regs->dma_idx); dev->mt76.tx_dma_idx[i] = dma_idx; - if (prev_dma_idx == dma_idx) - break; + if (!q->queued || prev_dma_idx != dma_idx) { + dev->tx_hang_check[i] = 0; + continue; + } + + if (++dev->tx_hang_check[i] >= MT_TX_HANG_TH) + return true; } - return i < 4; + return false; } static void mt76x02_key_sync(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -530,23 +532,13 @@ static void mt76x02_check_tx_hang(struct mt76x02_dev *dev) if (test_bit(MT76_RESTART, &dev->mphy.state)) return; - if (mt76x02_tx_hang(dev)) { - if (++dev->tx_hang_check >= MT_TX_HANG_TH) - goto restart; - } else { - dev->tx_hang_check = 0; - } - - if (dev->mcu_timeout) - goto restart; - - return; + if (!mt76x02_tx_hang(dev) && !dev->mcu_timeout) + return; -restart: mt76x02_watchdog_reset(dev); dev->tx_hang_reset++; - dev->tx_hang_check = 0; + memset(dev->tx_hang_check, 0, sizeof(dev->tx_hang_check)); memset(dev->mt76.tx_dma_idx, 0xff, sizeof(dev->mt76.tx_dma_idx)); } diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h b/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h index fa7872ac22bf..fe0c5e3298bc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h @@ -571,6 +571,8 @@ #define MT_RX_STAT_2_OVERFLOW_ERRORS GENMASK(31, 16) #define MT_TX_STA_0 0x170c +#define MT_TX_STA_0_BEACONS GENMASK(31, 16) + #define MT_TX_STA_1 0x1710 #define MT_TX_STA_2 0x1714 diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig index d98225da694c..6dc4708c230b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig +++ b/drivers/net/wireless/mediatek/mt76/mt7915/Kconfig @@ -1,9 +1,10 @@ # SPDX-License-Identifier: ISC config MT7915E tristate "MediaTek MT7915E (PCIe) support" - select MT76_CORE + select MT76_CONNAC_LIB depends on MAC80211 depends on PCI + select RELAY help This adds support for MT7915-based wireless PCIe devices, which support concurrent dual-band operation at both 5GHz diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c index e96d1c31dd36..280823fc9f92 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c @@ -1,9 +1,13 @@ // SPDX-License-Identifier: ISC /* Copyright (C) 2020 MediaTek Inc. */ +#include <linux/relay.h> #include "mt7915.h" #include "eeprom.h" #include "mcu.h" +#include "mac.h" + +#define FW_BIN_LOG_MAGIC 0x44e98caf /** global debugfs **/ @@ -75,7 +79,11 @@ mt7915_radar_trigger(void *data, u64 val) { struct mt7915_dev *dev = data; - return mt7915_mcu_rdd_cmd(dev, RDD_RADAR_EMULATE, 1, 0, 0); + if (val > MT_RX_SEL2) + return -EINVAL; + + return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_RADAR_EMULATE, + val, 0, 0); } DEFINE_DEBUGFS_ATTRIBUTE(fops_radar_trigger, NULL, @@ -301,6 +309,53 @@ exit: DEFINE_SHOW_ATTRIBUTE(mt7915_muru_stats); static int +mt7915_rdd_monitor(struct seq_file *s, void *data) +{ + struct mt7915_dev *dev = dev_get_drvdata(s->private); + struct cfg80211_chan_def *chandef = &dev->rdd2_chandef; + const char *bw; + int ret = 0; + + mutex_lock(&dev->mt76.mutex); + + if (!cfg80211_chandef_valid(chandef)) { + ret = -EINVAL; + goto out; + } + + if (!dev->rdd2_phy) { + seq_puts(s, "not running\n"); + goto out; + } + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_40: + bw = "40"; + break; + case NL80211_CHAN_WIDTH_80: + bw = "80"; + break; + case NL80211_CHAN_WIDTH_160: + bw = "160"; + break; + case NL80211_CHAN_WIDTH_80P80: + bw = "80P80"; + break; + default: + bw = "20"; + break; + } + + seq_printf(s, "channel %d (%d MHz) width %s MHz center1: %d MHz\n", + chandef->chan->hw_value, chandef->chan->center_freq, + bw, chandef->center_freq1); +out: + mutex_unlock(&dev->mt76.mutex); + + return ret; +} + +static int mt7915_fw_debug_wm_set(void *data, u64 val) { struct mt7915_dev *dev = data; @@ -311,16 +366,31 @@ mt7915_fw_debug_wm_set(void *data, u64 val) DEBUG_SPL, DEBUG_RPT_RX, } debug; + bool tx, rx, en; int ret; dev->fw_debug_wm = val ? MCU_FW_LOG_TO_HOST : 0; - ret = mt7915_mcu_fw_log_2_host(dev, MCU_FW_LOG_WM, dev->fw_debug_wm); + if (dev->fw_debug_bin) + val = 16; + else + val = dev->fw_debug_wm; + + tx = dev->fw_debug_wm || (dev->fw_debug_bin & BIT(1)); + rx = dev->fw_debug_wm || (dev->fw_debug_bin & BIT(2)); + en = dev->fw_debug_wm || (dev->fw_debug_bin & BIT(0)); + + ret = mt7915_mcu_fw_log_2_host(dev, MCU_FW_LOG_WM, val); if (ret) return ret; for (debug = DEBUG_TXCMD; debug <= DEBUG_RPT_RX; debug++) { - ret = mt7915_mcu_fw_dbg_ctrl(dev, debug, !!dev->fw_debug_wm); + if (debug == DEBUG_RPT_RX) + val = en && rx; + else + val = en && tx; + + ret = mt7915_mcu_fw_dbg_ctrl(dev, debug, val); if (ret) return ret; } @@ -376,6 +446,65 @@ mt7915_fw_debug_wa_get(void *data, u64 *val) DEFINE_DEBUGFS_ATTRIBUTE(fops_fw_debug_wa, mt7915_fw_debug_wa_get, mt7915_fw_debug_wa_set, "%lld\n"); +static struct dentry * +create_buf_file_cb(const char *filename, struct dentry *parent, umode_t mode, + struct rchan_buf *buf, int *is_global) +{ + struct dentry *f; + + f = debugfs_create_file("fwlog_data", mode, parent, buf, + &relay_file_operations); + if (IS_ERR(f)) + return NULL; + + *is_global = 1; + + return f; +} + +static int +remove_buf_file_cb(struct dentry *f) +{ + debugfs_remove(f); + + return 0; +} + +static int +mt7915_fw_debug_bin_set(void *data, u64 val) +{ + static struct rchan_callbacks relay_cb = { + .create_buf_file = create_buf_file_cb, + .remove_buf_file = remove_buf_file_cb, + }; + struct mt7915_dev *dev = data; + + if (!dev->relay_fwlog) + dev->relay_fwlog = relay_open("fwlog_data", dev->debugfs_dir, + 1500, 512, &relay_cb, NULL); + if (!dev->relay_fwlog) + return -ENOMEM; + + dev->fw_debug_bin = val; + + relay_reset(dev->relay_fwlog); + + return mt7915_fw_debug_wm_set(dev, dev->fw_debug_wm); +} + +static int +mt7915_fw_debug_bin_get(void *data, u64 *val) +{ + struct mt7915_dev *dev = data; + + *val = dev->fw_debug_bin; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(fops_fw_debug_bin, mt7915_fw_debug_bin_get, + mt7915_fw_debug_bin_set, "%lld\n"); + static int mt7915_fw_util_wm_show(struct seq_file *file, void *data) { @@ -521,14 +650,14 @@ mt7915_tx_stats_show(struct seq_file *file, void *data) DEFINE_SHOW_ATTRIBUTE(mt7915_tx_stats); static void -mt7915_hw_queue_read(struct seq_file *s, u32 base, u32 size, +mt7915_hw_queue_read(struct seq_file *s, u32 size, const struct hw_queue_map *map) { struct mt7915_phy *phy = s->private; struct mt7915_dev *dev = phy->dev; u32 i, val; - val = mt76_rr(dev, base + MT_FL_Q_EMPTY); + val = mt76_rr(dev, MT_FL_Q_EMPTY); for (i = 0; i < size; i++) { u32 ctrl, head, tail, queued; @@ -536,13 +665,13 @@ mt7915_hw_queue_read(struct seq_file *s, u32 base, u32 size, continue; ctrl = BIT(31) | (map[i].pid << 10) | (map[i].qid << 24); - mt76_wr(dev, base + MT_FL_Q0_CTRL, ctrl); + mt76_wr(dev, MT_FL_Q0_CTRL, ctrl); - head = mt76_get_field(dev, base + MT_FL_Q2_CTRL, + head = mt76_get_field(dev, MT_FL_Q2_CTRL, GENMASK(11, 0)); - tail = mt76_get_field(dev, base + MT_FL_Q2_CTRL, + tail = mt76_get_field(dev, MT_FL_Q2_CTRL, GENMASK(27, 16)); - queued = mt76_get_field(dev, base + MT_FL_Q3_CTRL, + queued = mt76_get_field(dev, MT_FL_Q3_CTRL, GENMASK(11, 0)); seq_printf(s, "\t%s: ", map[i].name); @@ -570,8 +699,8 @@ mt7915_sta_hw_queue_read(void *data, struct ieee80211_sta *sta) if (val & BIT(offs)) continue; - mt76_wr(dev, MT_PLE_BASE + MT_FL_Q0_CTRL, ctrl | msta->wcid.idx); - qlen = mt76_get_field(dev, MT_PLE_BASE + MT_FL_Q3_CTRL, + mt76_wr(dev, MT_FL_Q0_CTRL, ctrl | msta->wcid.idx); + qlen = mt76_get_field(dev, MT_FL_Q3_CTRL, GENMASK(11, 0)); seq_printf(s, "\tSTA %pM wcid %d: AC%d%d queued:%d\n", sta->addr, msta->wcid.idx, @@ -633,7 +762,7 @@ mt7915_hw_queues_show(struct seq_file *file, void *data) val, head, tail); seq_puts(file, "PLE non-empty queue info:\n"); - mt7915_hw_queue_read(file, MT_PLE_BASE, ARRAY_SIZE(ple_queue_map), + mt7915_hw_queue_read(file, ARRAY_SIZE(ple_queue_map), &ple_queue_map[0]); /* iterate per-sta ple queue */ @@ -641,7 +770,7 @@ mt7915_hw_queues_show(struct seq_file *file, void *data) mt7915_sta_hw_queue_read, file); /* pse queue */ seq_puts(file, "PSE non-empty queue info:\n"); - mt7915_hw_queue_read(file, MT_PSE_BASE, ARRAY_SIZE(pse_queue_map), + mt7915_hw_queue_read(file, ARRAY_SIZE(pse_queue_map), &pse_queue_map[0]); return 0; @@ -757,6 +886,7 @@ int mt7915_init_debugfs(struct mt7915_phy *phy) debugfs_create_file("tx_stats", 0400, dir, phy, &mt7915_tx_stats_fops); debugfs_create_file("fw_debug_wm", 0600, dir, dev, &fops_fw_debug_wm); debugfs_create_file("fw_debug_wa", 0600, dir, dev, &fops_fw_debug_wa); + debugfs_create_file("fw_debug_bin", 0600, dir, dev, &fops_fw_debug_bin); debugfs_create_file("fw_util_wm", 0400, dir, dev, &mt7915_fw_util_wm_fops); debugfs_create_file("fw_util_wa", 0400, dir, dev, @@ -773,11 +903,72 @@ int mt7915_init_debugfs(struct mt7915_phy *phy) &dev->hw_pattern); debugfs_create_file("radar_trigger", 0200, dir, dev, &fops_radar_trigger); + debugfs_create_devm_seqfile(dev->mt76.dev, "rdd_monitor", dir, + mt7915_rdd_monitor); } + if (!ext_phy) + dev->debugfs_dir = dir; + return 0; } +static void +mt7915_debugfs_write_fwlog(struct mt7915_dev *dev, const void *hdr, int hdrlen, + const void *data, int len) +{ + static DEFINE_SPINLOCK(lock); + unsigned long flags; + void *dest; + + spin_lock_irqsave(&lock, flags); + dest = relay_reserve(dev->relay_fwlog, hdrlen + len + 4); + if (dest) { + *(u32 *)dest = hdrlen + len; + dest += 4; + + if (hdrlen) { + memcpy(dest, hdr, hdrlen); + dest += hdrlen; + } + + memcpy(dest, data, len); + relay_flush(dev->relay_fwlog); + } + spin_unlock_irqrestore(&lock, flags); +} + +void mt7915_debugfs_rx_fw_monitor(struct mt7915_dev *dev, const void *data, int len) +{ + struct { + __le32 magic; + __le32 timestamp; + __le16 msg_type; + __le16 len; + } hdr = { + .magic = cpu_to_le32(FW_BIN_LOG_MAGIC), + .msg_type = PKT_TYPE_RX_FW_MONITOR, + }; + + if (!dev->relay_fwlog) + return; + + hdr.timestamp = mt76_rr(dev, MT_LPON_FRCR(0)); + hdr.len = *(__le16 *)data; + mt7915_debugfs_write_fwlog(dev, &hdr, sizeof(hdr), data, len); +} + +bool mt7915_debugfs_rx_log(struct mt7915_dev *dev, const void *data, int len) +{ + if (get_unaligned_le32(data) != FW_BIN_LOG_MAGIC) + return false; + + if (dev->relay_fwlog) + mt7915_debugfs_write_fwlog(dev, NULL, 0, data, len); + + return true; +} + #ifdef CONFIG_MAC80211_DEBUGFS /** per-station debugfs **/ diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c index 9182568f95c7..2dc2d6bf6f78 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c @@ -5,11 +5,11 @@ #include "../dma.h" #include "mac.h" -int mt7915_init_tx_queues(struct mt7915_phy *phy, int idx, int n_desc) +int mt7915_init_tx_queues(struct mt7915_phy *phy, int idx, int n_desc, int ring_base) { int i, err; - err = mt76_init_tx_queue(phy->mt76, 0, idx, n_desc, MT_TX_RING_BASE); + err = mt76_init_tx_queue(phy->mt76, 0, idx, n_desc, ring_base); if (err < 0) return err; @@ -40,140 +40,388 @@ static int mt7915_poll_tx(struct napi_struct *napi, int budget) return 0; } +static void mt7915_dma_config(struct mt7915_dev *dev) +{ +#define Q_CONFIG(q, wfdma, int, id) do { \ + if (wfdma) \ + dev->wfdma_mask |= (1 << (q)); \ + dev->q_int_mask[(q)] = int; \ + dev->q_id[(q)] = id; \ + } while (0) + +#define MCUQ_CONFIG(q, wfdma, int, id) Q_CONFIG(q, (wfdma), (int), (id)) +#define RXQ_CONFIG(q, wfdma, int, id) Q_CONFIG(__RXQ(q), (wfdma), (int), (id)) +#define TXQ_CONFIG(q, wfdma, int, id) Q_CONFIG(__TXQ(q), (wfdma), (int), (id)) + + if (is_mt7915(&dev->mt76)) { + RXQ_CONFIG(MT_RXQ_MAIN, WFDMA0, MT_INT_RX_DONE_BAND0, MT7915_RXQ_BAND0); + RXQ_CONFIG(MT_RXQ_MCU, WFDMA1, MT_INT_RX_DONE_WM, MT7915_RXQ_MCU_WM); + RXQ_CONFIG(MT_RXQ_MCU_WA, WFDMA1, MT_INT_RX_DONE_WA, MT7915_RXQ_MCU_WA); + RXQ_CONFIG(MT_RXQ_EXT, WFDMA0, MT_INT_RX_DONE_BAND1, MT7915_RXQ_BAND1); + RXQ_CONFIG(MT_RXQ_EXT_WA, WFDMA1, MT_INT_RX_DONE_WA_EXT, MT7915_RXQ_MCU_WA_EXT); + RXQ_CONFIG(MT_RXQ_MAIN_WA, WFDMA1, MT_INT_RX_DONE_WA_MAIN, MT7915_RXQ_MCU_WA); + TXQ_CONFIG(0, WFDMA1, MT_INT_TX_DONE_BAND0, MT7915_TXQ_BAND0); + TXQ_CONFIG(1, WFDMA1, MT_INT_TX_DONE_BAND1, MT7915_TXQ_BAND1); + MCUQ_CONFIG(MT_MCUQ_WM, WFDMA1, MT_INT_TX_DONE_MCU_WM, MT7915_TXQ_MCU_WM); + MCUQ_CONFIG(MT_MCUQ_WA, WFDMA1, MT_INT_TX_DONE_MCU_WA, MT7915_TXQ_MCU_WA); + MCUQ_CONFIG(MT_MCUQ_FWDL, WFDMA1, MT_INT_TX_DONE_FWDL, MT7915_TXQ_FWDL); + } else { + RXQ_CONFIG(MT_RXQ_MAIN, WFDMA0, MT_INT_RX_DONE_BAND0_MT7916, MT7916_RXQ_BAND0); + RXQ_CONFIG(MT_RXQ_MCU, WFDMA0, MT_INT_RX_DONE_WM, MT7916_RXQ_MCU_WM); + RXQ_CONFIG(MT_RXQ_MCU_WA, WFDMA0, MT_INT_RX_DONE_WA, MT7916_RXQ_MCU_WA); + RXQ_CONFIG(MT_RXQ_EXT, WFDMA0, MT_INT_RX_DONE_BAND1_MT7916, MT7916_RXQ_BAND1); + RXQ_CONFIG(MT_RXQ_EXT_WA, WFDMA0, MT_INT_RX_DONE_WA_EXT_MT7916, MT7916_RXQ_MCU_WA_EXT); + RXQ_CONFIG(MT_RXQ_MAIN_WA, WFDMA0, MT_INT_RX_DONE_WA_MAIN_MT7916, MT7916_RXQ_MCU_WA_MAIN); + TXQ_CONFIG(0, WFDMA0, MT_INT_TX_DONE_BAND0, MT7915_TXQ_BAND0); + TXQ_CONFIG(1, WFDMA0, MT_INT_TX_DONE_BAND1, MT7915_TXQ_BAND1); + MCUQ_CONFIG(MT_MCUQ_WM, WFDMA0, MT_INT_TX_DONE_MCU_WM, MT7915_TXQ_MCU_WM); + MCUQ_CONFIG(MT_MCUQ_WA, WFDMA0, MT_INT_TX_DONE_MCU_WA_MT7916, MT7915_TXQ_MCU_WA); + MCUQ_CONFIG(MT_MCUQ_FWDL, WFDMA0, MT_INT_TX_DONE_FWDL, MT7915_TXQ_FWDL); + } +} + static void __mt7915_dma_prefetch(struct mt7915_dev *dev, u32 ofs) { -#define PREFETCH(base, depth) ((base) << 16 | (depth)) - - mt76_wr(dev, MT_WFDMA0_RX_RING0_EXT_CTRL + ofs, PREFETCH(0x0, 0x4)); - mt76_wr(dev, MT_WFDMA0_RX_RING1_EXT_CTRL + ofs, PREFETCH(0x40, 0x4)); - mt76_wr(dev, MT_WFDMA0_RX_RING2_EXT_CTRL + ofs, PREFETCH(0x80, 0x0)); - - mt76_wr(dev, MT_WFDMA1_TX_RING0_EXT_CTRL + ofs, PREFETCH(0x80, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING1_EXT_CTRL + ofs, PREFETCH(0xc0, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING2_EXT_CTRL + ofs, PREFETCH(0x100, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING3_EXT_CTRL + ofs, PREFETCH(0x140, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING4_EXT_CTRL + ofs, PREFETCH(0x180, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING5_EXT_CTRL + ofs, PREFETCH(0x1c0, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING6_EXT_CTRL + ofs, PREFETCH(0x200, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING7_EXT_CTRL + ofs, PREFETCH(0x240, 0x4)); - - mt76_wr(dev, MT_WFDMA1_TX_RING16_EXT_CTRL + ofs, PREFETCH(0x280, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING17_EXT_CTRL + ofs, PREFETCH(0x2c0, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING18_EXT_CTRL + ofs, PREFETCH(0x300, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING19_EXT_CTRL + ofs, PREFETCH(0x340, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING20_EXT_CTRL + ofs, PREFETCH(0x380, 0x4)); - mt76_wr(dev, MT_WFDMA1_TX_RING21_EXT_CTRL + ofs, PREFETCH(0x3c0, 0x0)); - - mt76_wr(dev, MT_WFDMA1_RX_RING0_EXT_CTRL + ofs, PREFETCH(0x3c0, 0x4)); - mt76_wr(dev, MT_WFDMA1_RX_RING1_EXT_CTRL + ofs, PREFETCH(0x400, 0x4)); - mt76_wr(dev, MT_WFDMA1_RX_RING2_EXT_CTRL + ofs, PREFETCH(0x440, 0x4)); - mt76_wr(dev, MT_WFDMA1_RX_RING3_EXT_CTRL + ofs, PREFETCH(0x480, 0x0)); +#define PREFETCH(_base, _depth) ((_base) << 16 | (_depth)) + u32 base = 0; + + /* prefetch SRAM wrapping boundary for tx/rx ring. */ + mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_FWDL) + ofs, PREFETCH(0x0, 0x4)); + mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WM) + ofs, PREFETCH(0x40, 0x4)); + mt76_wr(dev, MT_TXQ_EXT_CTRL(0) + ofs, PREFETCH(0x80, 0x4)); + mt76_wr(dev, MT_TXQ_EXT_CTRL(1) + ofs, PREFETCH(0xc0, 0x4)); + mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WA) + ofs, PREFETCH(0x100, 0x4)); + + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MCU) + ofs, PREFETCH(0x140, 0x4)); + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MCU_WA) + ofs, PREFETCH(0x180, 0x4)); + if (!is_mt7915(&dev->mt76)) { + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MAIN_WA) + ofs, PREFETCH(0x1c0, 0x4)); + base = 0x40; + } + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_EXT_WA) + ofs, PREFETCH(0x1c0 + base, 0x4)); + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_MAIN) + ofs, PREFETCH(0x200 + base, 0x4)); + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_EXT) + ofs, PREFETCH(0x240 + base, 0x4)); + + /* for mt7915, the ring which is next the last + * used ring must be initialized. + */ + if (is_mt7915(&dev->mt76)) { + ofs += 0x4; + mt76_wr(dev, MT_MCUQ_EXT_CTRL(MT_MCUQ_WA) + ofs, PREFETCH(0x140, 0x0)); + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_EXT_WA) + ofs, PREFETCH(0x200 + base, 0x0)); + mt76_wr(dev, MT_RXQ_EXT_CTRL(MT_RXQ_EXT) + ofs, PREFETCH(0x280 + base, 0x0)); + } } void mt7915_dma_prefetch(struct mt7915_dev *dev) { __mt7915_dma_prefetch(dev, 0); if (dev->hif2) - __mt7915_dma_prefetch(dev, MT_WFDMA1_PCIE1_BASE - MT_WFDMA1_BASE); + __mt7915_dma_prefetch(dev, MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0)); } -int mt7915_dma_init(struct mt7915_dev *dev) +static void mt7915_dma_disable(struct mt7915_dev *dev, bool rst) { + struct mt76_dev *mdev = &dev->mt76; u32 hif1_ofs = 0; - int ret; - - mt76_dma_attach(&dev->mt76); if (dev->hif2) - hif1_ofs = MT_WFDMA1_PCIE1_BASE - MT_WFDMA1_BASE; + hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0); + + /* reset */ + if (rst) { + mt76_clear(dev, MT_WFDMA0_RST, + MT_WFDMA0_RST_DMASHDL_ALL_RST | + MT_WFDMA0_RST_LOGIC_RST); + + mt76_set(dev, MT_WFDMA0_RST, + MT_WFDMA0_RST_DMASHDL_ALL_RST | + MT_WFDMA0_RST_LOGIC_RST); + + if (is_mt7915(mdev)) { + mt76_clear(dev, MT_WFDMA1_RST, + MT_WFDMA1_RST_DMASHDL_ALL_RST | + MT_WFDMA1_RST_LOGIC_RST); + + mt76_set(dev, MT_WFDMA1_RST, + MT_WFDMA1_RST_DMASHDL_ALL_RST | + MT_WFDMA1_RST_LOGIC_RST); + } + + if (dev->hif2) { + mt76_clear(dev, MT_WFDMA0_RST + hif1_ofs, + MT_WFDMA0_RST_DMASHDL_ALL_RST | + MT_WFDMA0_RST_LOGIC_RST); + + mt76_set(dev, MT_WFDMA0_RST + hif1_ofs, + MT_WFDMA0_RST_DMASHDL_ALL_RST | + MT_WFDMA0_RST_LOGIC_RST); + + if (is_mt7915(mdev)) { + mt76_clear(dev, MT_WFDMA1_RST + hif1_ofs, + MT_WFDMA1_RST_DMASHDL_ALL_RST | + MT_WFDMA1_RST_LOGIC_RST); + + mt76_set(dev, MT_WFDMA1_RST + hif1_ofs, + MT_WFDMA1_RST_DMASHDL_ALL_RST | + MT_WFDMA1_RST_LOGIC_RST); + } + } + } + + /* disable */ + mt76_clear(dev, MT_WFDMA0_GLO_CFG, + MT_WFDMA0_GLO_CFG_TX_DMA_EN | + MT_WFDMA0_GLO_CFG_RX_DMA_EN | + MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO | + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); + + if (is_mt7915(mdev)) + mt76_clear(dev, MT_WFDMA1_GLO_CFG, + MT_WFDMA1_GLO_CFG_TX_DMA_EN | + MT_WFDMA1_GLO_CFG_RX_DMA_EN | + MT_WFDMA1_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA1_GLO_CFG_OMIT_RX_INFO | + MT_WFDMA1_GLO_CFG_OMIT_RX_INFO_PFET2); + + if (dev->hif2) { + mt76_clear(dev, MT_WFDMA0_GLO_CFG + hif1_ofs, + MT_WFDMA0_GLO_CFG_TX_DMA_EN | + MT_WFDMA0_GLO_CFG_RX_DMA_EN | + MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO | + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); + + if (is_mt7915(mdev)) + mt76_clear(dev, MT_WFDMA1_GLO_CFG + hif1_ofs, + MT_WFDMA1_GLO_CFG_TX_DMA_EN | + MT_WFDMA1_GLO_CFG_RX_DMA_EN | + MT_WFDMA1_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA1_GLO_CFG_OMIT_RX_INFO | + MT_WFDMA1_GLO_CFG_OMIT_RX_INFO_PFET2); + } +} - /* configure global setting */ - mt76_set(dev, MT_WFDMA1_GLO_CFG, - MT_WFDMA1_GLO_CFG_OMIT_TX_INFO | - MT_WFDMA1_GLO_CFG_OMIT_RX_INFO); +static int mt7915_dma_enable(struct mt7915_dev *dev) +{ + struct mt76_dev *mdev = &dev->mt76; + u32 hif1_ofs = 0; + u32 irq_mask; + + if (dev->hif2) + hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0); /* reset dma idx */ mt76_wr(dev, MT_WFDMA0_RST_DTX_PTR, ~0); - mt76_wr(dev, MT_WFDMA1_RST_DTX_PTR, ~0); + if (is_mt7915(mdev)) + mt76_wr(dev, MT_WFDMA1_RST_DTX_PTR, ~0); + if (dev->hif2) { + mt76_wr(dev, MT_WFDMA0_RST_DTX_PTR + hif1_ofs, ~0); + if (is_mt7915(mdev)) + mt76_wr(dev, MT_WFDMA1_RST_DTX_PTR + hif1_ofs, ~0); + } - /* configure delay interrupt */ + /* configure delay interrupt off */ mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG0, 0); - mt76_wr(dev, MT_WFDMA1_PRI_DLY_INT_CFG0, 0); + if (is_mt7915(mdev)) { + mt76_wr(dev, MT_WFDMA1_PRI_DLY_INT_CFG0, 0); + } else { + mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG1, 0); + mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG2, 0); + } + + if (dev->hif2) { + mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG0 + hif1_ofs, 0); + if (is_mt7915(mdev)) { + mt76_wr(dev, MT_WFDMA1_PRI_DLY_INT_CFG0 + + hif1_ofs, 0); + } else { + mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG1 + + hif1_ofs, 0); + mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG2 + + hif1_ofs, 0); + } + } + + /* configure perfetch settings */ + mt7915_dma_prefetch(dev); + + /* hif wait WFDMA idle */ + mt76_set(dev, MT_WFDMA0_BUSY_ENA, + MT_WFDMA0_BUSY_ENA_TX_FIFO0 | + MT_WFDMA0_BUSY_ENA_TX_FIFO1 | + MT_WFDMA0_BUSY_ENA_RX_FIFO); + + if (is_mt7915(mdev)) + mt76_set(dev, MT_WFDMA1_BUSY_ENA, + MT_WFDMA1_BUSY_ENA_TX_FIFO0 | + MT_WFDMA1_BUSY_ENA_TX_FIFO1 | + MT_WFDMA1_BUSY_ENA_RX_FIFO); if (dev->hif2) { - mt76_set(dev, MT_WFDMA1_GLO_CFG + hif1_ofs, + mt76_set(dev, MT_WFDMA0_BUSY_ENA + hif1_ofs, + MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO0 | + MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO1 | + MT_WFDMA0_PCIE1_BUSY_ENA_RX_FIFO); + + if (is_mt7915(mdev)) + mt76_set(dev, MT_WFDMA1_BUSY_ENA + hif1_ofs, + MT_WFDMA1_PCIE1_BUSY_ENA_TX_FIFO0 | + MT_WFDMA1_PCIE1_BUSY_ENA_TX_FIFO1 | + MT_WFDMA1_PCIE1_BUSY_ENA_RX_FIFO); + } + + mt76_poll(dev, MT_WFDMA_EXT_CSR_HIF_MISC, + MT_WFDMA_EXT_CSR_HIF_MISC_BUSY, 0, 1000); + + /* set WFDMA Tx/Rx */ + mt76_set(dev, MT_WFDMA0_GLO_CFG, + MT_WFDMA0_GLO_CFG_TX_DMA_EN | + MT_WFDMA0_GLO_CFG_RX_DMA_EN | + MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); + + if (is_mt7915(mdev)) + mt76_set(dev, MT_WFDMA1_GLO_CFG, + MT_WFDMA1_GLO_CFG_TX_DMA_EN | + MT_WFDMA1_GLO_CFG_RX_DMA_EN | MT_WFDMA1_GLO_CFG_OMIT_TX_INFO | MT_WFDMA1_GLO_CFG_OMIT_RX_INFO); - mt76_wr(dev, MT_WFDMA0_RST_DTX_PTR + hif1_ofs, ~0); - mt76_wr(dev, MT_WFDMA1_RST_DTX_PTR + hif1_ofs, ~0); + if (dev->hif2) { + mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs, + MT_WFDMA0_GLO_CFG_TX_DMA_EN | + MT_WFDMA0_GLO_CFG_RX_DMA_EN | + MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); + + if (is_mt7915(mdev)) + mt76_set(dev, MT_WFDMA1_GLO_CFG + hif1_ofs, + MT_WFDMA1_GLO_CFG_TX_DMA_EN | + MT_WFDMA1_GLO_CFG_RX_DMA_EN | + MT_WFDMA1_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA1_GLO_CFG_OMIT_RX_INFO); - mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG0 + hif1_ofs, 0); - mt76_wr(dev, MT_WFDMA1_PRI_DLY_INT_CFG0 + hif1_ofs, 0); + mt76_set(dev, MT_WFDMA_HOST_CONFIG, + MT_WFDMA_HOST_CONFIG_PDMA_BAND); } - /* configure perfetch settings */ - mt7915_dma_prefetch(dev); + /* enable interrupts for TX/RX rings */ + irq_mask = MT_INT_RX_DONE_MCU | + MT_INT_TX_DONE_MCU | + MT_INT_MCU_CMD | + MT_INT_BAND0_RX_DONE; + + if (dev->dbdc_support) + irq_mask |= MT_INT_BAND1_RX_DONE; + + mt7915_irq_enable(dev, irq_mask); + + return 0; +} + +int mt7915_dma_init(struct mt7915_dev *dev) +{ + struct mt76_dev *mdev = &dev->mt76; + u32 hif1_ofs = 0; + int ret; + + mt7915_dma_config(dev); + + mt76_dma_attach(&dev->mt76); + + if (dev->hif2) + hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0); + + mt7915_dma_disable(dev, true); /* init tx queue */ - ret = mt7915_init_tx_queues(&dev->phy, MT7915_TXQ_BAND0, - MT7915_TX_RING_SIZE); + ret = mt7915_init_tx_queues(&dev->phy, + MT_TXQ_ID(0), + MT7915_TX_RING_SIZE, + MT_TXQ_RING_BASE(0)); if (ret) return ret; /* command to WM */ - ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WM, MT7915_TXQ_MCU_WM, - MT7915_TX_MCU_RING_SIZE, MT_TX_RING_BASE); + ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WM, + MT_MCUQ_ID(MT_MCUQ_WM), + MT7915_TX_MCU_RING_SIZE, + MT_MCUQ_RING_BASE(MT_MCUQ_WM)); if (ret) return ret; /* command to WA */ - ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WA, MT7915_TXQ_MCU_WA, - MT7915_TX_MCU_RING_SIZE, MT_TX_RING_BASE); + ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_WA, + MT_MCUQ_ID(MT_MCUQ_WA), + MT7915_TX_MCU_RING_SIZE, + MT_MCUQ_RING_BASE(MT_MCUQ_WA)); if (ret) return ret; /* firmware download */ - ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_FWDL, MT7915_TXQ_FWDL, - MT7915_TX_FWDL_RING_SIZE, MT_TX_RING_BASE); + ret = mt76_init_mcu_queue(&dev->mt76, MT_MCUQ_FWDL, + MT_MCUQ_ID(MT_MCUQ_FWDL), + MT7915_TX_FWDL_RING_SIZE, + MT_MCUQ_RING_BASE(MT_MCUQ_FWDL)); if (ret) return ret; /* event from WM */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU], - MT7915_RXQ_MCU_WM, MT7915_RX_MCU_RING_SIZE, - MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE); + MT_RXQ_ID(MT_RXQ_MCU), + MT7915_RX_MCU_RING_SIZE, + MT_RX_BUF_SIZE, + MT_RXQ_RING_BASE(MT_RXQ_MCU)); if (ret) return ret; /* event from WA */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA], - MT7915_RXQ_MCU_WA, MT7915_RX_MCU_RING_SIZE, - MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE); + MT_RXQ_ID(MT_RXQ_MCU_WA), + MT7915_RX_MCU_RING_SIZE, + MT_RX_BUF_SIZE, + MT_RXQ_RING_BASE(MT_RXQ_MCU_WA)); if (ret) return ret; - /* rx data queue */ + /* rx data queue for band0 */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN], - MT7915_RXQ_BAND0, MT7915_RX_RING_SIZE, - MT_RX_BUF_SIZE, MT_RX_DATA_RING_BASE); + MT_RXQ_ID(MT_RXQ_MAIN), + MT7915_RX_RING_SIZE, + MT_RX_BUF_SIZE, + MT_RXQ_RING_BASE(MT_RXQ_MAIN)); if (ret) return ret; + /* tx free notify event from WA for band0 */ + if (!is_mt7915(mdev)) { + ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN_WA], + MT_RXQ_ID(MT_RXQ_MAIN_WA), + MT7915_RX_MCU_RING_SIZE, + MT_RX_BUF_SIZE, + MT_RXQ_RING_BASE(MT_RXQ_MAIN_WA)); + if (ret) + return ret; + } + if (dev->dbdc_support) { + /* rx data queue for band1 */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_EXT], - MT7915_RXQ_BAND1, MT7915_RX_RING_SIZE, + MT_RXQ_ID(MT_RXQ_EXT), + MT7915_RX_RING_SIZE, MT_RX_BUF_SIZE, - MT_RX_DATA_RING_BASE + hif1_ofs); + MT_RXQ_RING_BASE(MT_RXQ_EXT) + hif1_ofs); if (ret) return ret; - /* event from WA */ + /* tx free notify event from WA for band1 */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_EXT_WA], - MT7915_RXQ_MCU_WA_EXT, + MT_RXQ_ID(MT_RXQ_EXT_WA), MT7915_RX_MCU_RING_SIZE, MT_RX_BUF_SIZE, - MT_RX_EVENT_RING_BASE + hif1_ofs); + MT_RXQ_RING_BASE(MT_RXQ_EXT_WA) + hif1_ofs); if (ret) return ret; } @@ -186,80 +434,14 @@ int mt7915_dma_init(struct mt7915_dev *dev) mt7915_poll_tx, NAPI_POLL_WEIGHT); napi_enable(&dev->mt76.tx_napi); - /* hif wait WFDMA idle */ - mt76_set(dev, MT_WFDMA0_BUSY_ENA, - MT_WFDMA0_BUSY_ENA_TX_FIFO0 | - MT_WFDMA0_BUSY_ENA_TX_FIFO1 | - MT_WFDMA0_BUSY_ENA_RX_FIFO); - - mt76_set(dev, MT_WFDMA1_BUSY_ENA, - MT_WFDMA1_BUSY_ENA_TX_FIFO0 | - MT_WFDMA1_BUSY_ENA_TX_FIFO1 | - MT_WFDMA1_BUSY_ENA_RX_FIFO); - - mt76_set(dev, MT_WFDMA0_PCIE1_BUSY_ENA, - MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO0 | - MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO1 | - MT_WFDMA0_PCIE1_BUSY_ENA_RX_FIFO); - - mt76_set(dev, MT_WFDMA1_PCIE1_BUSY_ENA, - MT_WFDMA1_PCIE1_BUSY_ENA_TX_FIFO0 | - MT_WFDMA1_PCIE1_BUSY_ENA_TX_FIFO1 | - MT_WFDMA1_PCIE1_BUSY_ENA_RX_FIFO); - - mt76_poll(dev, MT_WFDMA_EXT_CSR_HIF_MISC, - MT_WFDMA_EXT_CSR_HIF_MISC_BUSY, 0, 1000); - - /* set WFDMA Tx/Rx */ - mt76_set(dev, MT_WFDMA0_GLO_CFG, - MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN); - mt76_set(dev, MT_WFDMA1_GLO_CFG, - MT_WFDMA1_GLO_CFG_TX_DMA_EN | MT_WFDMA1_GLO_CFG_RX_DMA_EN); - - if (dev->hif2) { - mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs, - (MT_WFDMA0_GLO_CFG_TX_DMA_EN | - MT_WFDMA0_GLO_CFG_RX_DMA_EN)); - mt76_set(dev, MT_WFDMA1_GLO_CFG + hif1_ofs, - (MT_WFDMA1_GLO_CFG_TX_DMA_EN | - MT_WFDMA1_GLO_CFG_RX_DMA_EN)); - mt76_set(dev, MT_WFDMA_HOST_CONFIG, - MT_WFDMA_HOST_CONFIG_PDMA_BAND); - } - - /* enable interrupts for TX/RX rings */ - mt7915_irq_enable(dev, MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_MCU | - MT_INT_MCU_CMD); + mt7915_dma_enable(dev); return 0; } void mt7915_dma_cleanup(struct mt7915_dev *dev) { - /* disable */ - mt76_clear(dev, MT_WFDMA0_GLO_CFG, - MT_WFDMA0_GLO_CFG_TX_DMA_EN | - MT_WFDMA0_GLO_CFG_RX_DMA_EN); - mt76_clear(dev, MT_WFDMA1_GLO_CFG, - MT_WFDMA1_GLO_CFG_TX_DMA_EN | - MT_WFDMA1_GLO_CFG_RX_DMA_EN); - - /* reset */ - mt76_clear(dev, MT_WFDMA1_RST, - MT_WFDMA1_RST_DMASHDL_ALL_RST | - MT_WFDMA1_RST_LOGIC_RST); - - mt76_set(dev, MT_WFDMA1_RST, - MT_WFDMA1_RST_DMASHDL_ALL_RST | - MT_WFDMA1_RST_LOGIC_RST); - - mt76_clear(dev, MT_WFDMA0_RST, - MT_WFDMA0_RST_DMASHDL_ALL_RST | - MT_WFDMA0_RST_LOGIC_RST); - - mt76_set(dev, MT_WFDMA0_RST, - MT_WFDMA0_RST_DMASHDL_ALL_RST | - MT_WFDMA0_RST_LOGIC_RST); + mt7915_dma_disable(dev, true); mt76_dma_cleanup(&dev->mt76); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c index edd74d0de157..6aa749b02cc3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c @@ -10,6 +10,7 @@ static int mt7915_eeprom_load_precal(struct mt7915_dev *dev) struct mt76_dev *mdev = &dev->mt76; u8 *eeprom = mdev->eeprom.data; u32 val = eeprom[MT_EE_DO_PRE_CAL]; + u32 offs; if (!dev->flash_mode) return 0; @@ -22,7 +23,9 @@ static int mt7915_eeprom_load_precal(struct mt7915_dev *dev) if (!dev->cal) return -ENOMEM; - return mt76_get_of_eeprom(mdev, dev->cal, MT_EE_PRECAL, val); + offs = is_mt7915(&dev->mt76) ? MT_EE_PRECAL : MT_EE_PRECAL_V2; + + return mt76_get_of_eeprom(mdev, dev->cal, offs, val); } static int mt7915_check_eeprom(struct mt7915_dev *dev) @@ -32,6 +35,7 @@ static int mt7915_check_eeprom(struct mt7915_dev *dev) switch (val) { case 0x7915: + case 0x7916: return 0; default: return -EINVAL; @@ -49,6 +53,9 @@ mt7915_eeprom_load_default(struct mt7915_dev *dev) if (dev->dbdc_support) default_bin = MT7915_EEPROM_DEFAULT_DBDC; + if (!is_mt7915(&dev->mt76)) + default_bin = MT7916_EEPROM_DEFAULT; + ret = request_firmware(&fw, default_bin, dev->mt76.dev); if (ret) return ret; @@ -59,7 +66,7 @@ mt7915_eeprom_load_default(struct mt7915_dev *dev) goto out; } - memcpy(eeprom, fw->data, MT7915_EEPROM_SIZE); + memcpy(eeprom, fw->data, mt7915_eeprom_size(dev)); dev->flash_mode = true; out: @@ -71,8 +78,9 @@ out: static int mt7915_eeprom_load(struct mt7915_dev *dev) { int ret; + u16 eeprom_size = mt7915_eeprom_size(dev); - ret = mt76_eeprom_init(&dev->mt76, MT7915_EEPROM_SIZE); + ret = mt76_eeprom_init(&dev->mt76, eeprom_size); if (ret < 0) return ret; @@ -88,7 +96,7 @@ static int mt7915_eeprom_load(struct mt7915_dev *dev) return -EINVAL; /* read eeprom data from efuse */ - block_num = DIV_ROUND_UP(MT7915_EEPROM_SIZE, + block_num = DIV_ROUND_UP(eeprom_size, MT7915_EEPROM_BLOCK_SIZE); for (i = 0; i < block_num; i++) mt7915_mcu_get_eeprom(dev, @@ -98,7 +106,7 @@ static int mt7915_eeprom_load(struct mt7915_dev *dev) return mt7915_check_eeprom(dev); } -void mt7915_eeprom_parse_band_config(struct mt7915_phy *phy) +static void mt7915_eeprom_parse_band_config(struct mt7915_phy *phy) { struct mt7915_dev *dev = phy->dev; bool ext_phy = phy != &dev->phy; @@ -124,32 +132,55 @@ void mt7915_eeprom_parse_band_config(struct mt7915_phy *phy) } } -static void mt7915_eeprom_parse_hw_cap(struct mt7915_dev *dev) +void mt7915_eeprom_parse_hw_cap(struct mt7915_dev *dev, + struct mt7915_phy *phy) { u8 nss, nss_band, *eeprom = dev->mt76.eeprom.data; + struct mt76_phy *mphy = phy->mt76; + bool ext_phy = phy != &dev->phy; - mt7915_eeprom_parse_band_config(&dev->phy); + mt7915_eeprom_parse_band_config(phy); + + /* read tx/rx mask from eeprom */ + if (is_mt7915(&dev->mt76)) { + nss = FIELD_GET(MT_EE_WIFI_CONF0_TX_PATH, + eeprom[MT_EE_WIFI_CONF]); + } else { + nss = FIELD_GET(MT_EE_WIFI_CONF0_TX_PATH, + eeprom[MT_EE_WIFI_CONF + ext_phy]); + } - /* read tx mask from eeprom */ - nss = FIELD_GET(MT_EE_WIFI_CONF0_TX_PATH, eeprom[MT_EE_WIFI_CONF]); if (!nss || nss > 4) nss = 4; + /* read tx/rx stream */ nss_band = nss; - if (dev->dbdc_support) { - nss_band = FIELD_GET(MT_EE_WIFI_CONF3_TX_PATH_B0, - eeprom[MT_EE_WIFI_CONF + 3]); + if (is_mt7915(&dev->mt76)) { + nss_band = FIELD_GET(MT_EE_WIFI_CONF3_TX_PATH_B0, + eeprom[MT_EE_WIFI_CONF + 3]); + if (ext_phy) + nss_band = FIELD_GET(MT_EE_WIFI_CONF3_TX_PATH_B1, + eeprom[MT_EE_WIFI_CONF + 3]); + } else { + nss_band = FIELD_GET(MT_EE_WIFI_CONF_STREAM_NUM, + eeprom[MT_EE_WIFI_CONF + 2 + ext_phy]); + } + if (!nss_band || nss_band > 2) nss_band = 2; + } - if (nss_band >= nss) - nss = 4; + if (nss_band > nss) { + dev_err(dev->mt76.dev, + "nss mismatch, nss(%d) nss_band(%d) ext_phy(%d)\n", + nss, nss_band, ext_phy); + nss = nss_band; } - dev->chainmask = BIT(nss) - 1; - dev->mphy.antenna_mask = BIT(nss_band) - 1; - dev->mphy.chainmask = dev->mphy.antenna_mask; + mphy->chainmask = ext_phy ? (BIT(nss_band) - 1) << 2 : (BIT(nss_band) - 1); + mphy->antenna_mask = BIT(hweight8(mphy->chainmask)) - 1; + dev->chainmask |= mphy->chainmask; } int mt7915_eeprom_init(struct mt7915_dev *dev) @@ -171,7 +202,7 @@ int mt7915_eeprom_init(struct mt7915_dev *dev) if (ret) return ret; - mt7915_eeprom_parse_hw_cap(dev); + mt7915_eeprom_parse_hw_cap(dev, &dev->phy); memcpy(dev->mphy.macaddr, dev->mt76.eeprom.data + MT_EE_MAC_ADDR, ETH_ALEN); @@ -194,15 +225,20 @@ int mt7915_eeprom_get_target_power(struct mt7915_dev *dev, tssi_on = mt7915_tssi_enabled(dev, chan->band); if (chan->band == NL80211_BAND_2GHZ) { - index = MT_EE_TX0_POWER_2G + chain_idx * 3; + u32 power = is_mt7915(&dev->mt76) ? + MT_EE_TX0_POWER_2G : MT_EE_TX0_POWER_2G_V2; + + index = power + chain_idx * 3; target_power = eeprom[index]; if (!tssi_on) target_power += eeprom[index + 1]; } else { int group = mt7915_get_channel_group(chan->hw_value); + u32 power = is_mt7915(&dev->mt76) ? + MT_EE_TX0_POWER_5G : MT_EE_TX0_POWER_5G_V2; - index = MT_EE_TX0_POWER_5G + chain_idx * 12; + index = power + chain_idx * 12; target_power = eeprom[index + group]; if (!tssi_on) @@ -217,11 +253,18 @@ s8 mt7915_eeprom_get_power_delta(struct mt7915_dev *dev, int band) u8 *eeprom = dev->mt76.eeprom.data; u32 val; s8 delta; + u32 rate_2g, rate_5g; + + rate_2g = is_mt7915(&dev->mt76) ? + MT_EE_RATE_DELTA_2G : MT_EE_RATE_DELTA_2G_V2; + + rate_5g = is_mt7915(&dev->mt76) ? + MT_EE_RATE_DELTA_5G : MT_EE_RATE_DELTA_5G_V2; if (band == NL80211_BAND_2GHZ) - val = eeprom[MT_EE_RATE_DELTA_2G]; + val = eeprom[rate_2g]; else - val = eeprom[MT_EE_RATE_DELTA_5G]; + val = eeprom[rate_5g]; if (!(val & MT_EE_RATE_DELTA_EN)) return 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h index a43389a41800..92d1a9401c74 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h @@ -23,11 +23,17 @@ enum mt7915_eeprom_field { MT_EE_RATE_DELTA_5G = 0x29d, MT_EE_TX0_POWER_2G = 0x2fc, MT_EE_TX0_POWER_5G = 0x34b, + MT_EE_RATE_DELTA_2G_V2 = 0x7d3, + MT_EE_RATE_DELTA_5G_V2 = 0x81e, + MT_EE_TX0_POWER_2G_V2 = 0x441, + MT_EE_TX0_POWER_5G_V2 = 0x445, MT_EE_ADIE_FT_VERSION = 0x9a0, __MT_EE_MAX = 0xe00, + __MT_EE_MAX_V2 = 0x1000, /* 0xe10 ~ 0x5780 used to save group cal data */ - MT_EE_PRECAL = 0xe10 + MT_EE_PRECAL = 0xe10, + MT_EE_PRECAL_V2 = 0x1010 }; #define MT_EE_WIFI_CAL_GROUP BIT(0) @@ -39,6 +45,7 @@ enum mt7915_eeprom_field { #define MT_EE_WIFI_CONF0_TX_PATH GENMASK(2, 0) #define MT_EE_WIFI_CONF0_BAND_SEL GENMASK(7, 6) #define MT_EE_WIFI_CONF1_BAND_SEL GENMASK(7, 6) +#define MT_EE_WIFI_CONF_STREAM_NUM GENMASK(7, 5) #define MT_EE_WIFI_CONF3_TX_PATH_B0 GENMASK(1, 0) #define MT_EE_WIFI_CONF3_TX_PATH_B1 GENMASK(5, 4) #define MT_EE_WIFI_CONF7_TSSI0_2G BIT(0) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c index d054cdecd5f7..705f362b8f7b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c @@ -288,17 +288,17 @@ mt7915_regd_notifier(struct wiphy *wiphy, struct mt7915_dev *dev = mt7915_hw_dev(hw); struct mt76_phy *mphy = hw->priv; struct mt7915_phy *phy = mphy->priv; - struct cfg80211_chan_def *chandef = &mphy->chandef; memcpy(dev->mt76.alpha2, request->alpha2, sizeof(dev->mt76.alpha2)); dev->mt76.region = request->dfs_region; + if (dev->mt76.region == NL80211_DFS_UNSET) + mt7915_mcu_rdd_background_enable(phy, NULL); + mt7915_init_txpower(dev, &mphy->sband_2g.sband); mt7915_init_txpower(dev, &mphy->sband_5g.sband); - if (!(chandef->chan->flags & IEEE80211_CHAN_RADAR)) - return; - + mphy->dfs_state = MT_DFS_STATE_UNKNOWN; mt7915_dfs_init_radar_detector(phy); } @@ -306,7 +306,9 @@ static void mt7915_init_wiphy(struct ieee80211_hw *hw) { struct mt7915_phy *phy = mt7915_hw_phy(hw); + struct mt76_dev *mdev = &phy->dev->mt76; struct wiphy *wiphy = hw->wiphy; + struct mt7915_dev *dev = phy->dev; hw->queues = 4; hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; @@ -333,6 +335,12 @@ mt7915_init_wiphy(struct ieee80211_hw *hw) wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_VHT); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_HE); + if (!mdev->dev->of_node || + !of_property_read_bool(mdev->dev->of_node, + "mediatek,disable-radar-background")) + wiphy_ext_feature_set(wiphy, + NL80211_EXT_FEATURE_RADAR_BACKGROUND); + ieee80211_hw_set(hw, HAS_RATE_CONTROL); ieee80211_hw_set(hw, SUPPORTS_TX_ENCAP_OFFLOAD); ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD); @@ -349,14 +357,34 @@ mt7915_init_wiphy(struct ieee80211_hw *hw) phy->mt76->sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING | IEEE80211_HT_CAP_MAX_AMSDU; - phy->mt76->sband_5g.sband.vht_cap.cap |= - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | - IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; + + if (is_mt7915(&dev->mt76)) { + phy->mt76->sband_5g.sband.vht_cap.cap |= + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | + IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; + + if (!dev->dbdc_support) + phy->mt76->sband_5g.sband.vht_cap.cap |= + IEEE80211_VHT_CAP_SHORT_GI_160 | + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ; + } else { + phy->mt76->sband_5g.sband.vht_cap.cap |= + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | + IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; + + /* mt7916 dbdc with 2g 2x2 bw40 and 5g 2x2 bw160c */ + phy->mt76->sband_5g.sband.vht_cap.cap |= + IEEE80211_VHT_CAP_SHORT_GI_160 | + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; + } } mt76_set_stream_caps(phy->mt76, true); mt7915_set_stream_vht_txbf_caps(phy); mt7915_set_stream_he_caps(phy); + + wiphy->available_antennas_rx = phy->mt76->antenna_mask; + wiphy->available_antennas_tx = phy->mt76->antenna_mask; } static void @@ -387,19 +415,27 @@ mt7915_mac_init_band(struct mt7915_dev *dev, u8 band) mt76_rmw(dev, MT_MDP_BNRCFR1(band), mask, set); mt76_rmw_field(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_MAX_RX_LEN, 0x680); - /* disable rx rate report by default due to hw issues */ + + /* mt7915: disable rx rate report by default due to hw issues */ mt76_clear(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_RXD_G5_EN); } static void mt7915_mac_init(struct mt7915_dev *dev) { int i; + u32 rx_len = is_mt7915(&dev->mt76) ? 0x400 : 0x680; + + /* config pse qid6 wfdma port selection */ + if (!is_mt7915(&dev->mt76) && dev->hif2) + mt76_rmw(dev, MT_WF_PP_TOP_RXQ_WFDMA_CF_5, 0, + MT_WF_PP_TOP_RXQ_QID6_WFDMA_HIF_SEL_MASK); + + mt76_rmw_field(dev, MT_MDP_DCR1, MT_MDP_DCR1_MAX_RX_LEN, rx_len); - mt76_rmw_field(dev, MT_MDP_DCR1, MT_MDP_DCR1_MAX_RX_LEN, 0x400); /* enable hardware de-agg */ mt76_set(dev, MT_MDP_DCR0, MT_MDP_DCR0_DAMSDU_EN); - for (i = 0; i < MT7915_WTBL_SIZE; i++) + for (i = 0; i < mt7915_wtbl_size(dev); i++) mt7915_mac_wtbl_update(dev, i, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); for (i = 0; i < 2; i++) @@ -449,20 +485,29 @@ static int mt7915_register_ext_phy(struct mt7915_dev *dev) phy = mphy->priv; phy->dev = dev; phy->mt76 = mphy; - mphy->chainmask = dev->chainmask & ~dev->mphy.chainmask; - mphy->antenna_mask = BIT(hweight8(mphy->chainmask)) - 1; INIT_DELAYED_WORK(&mphy->mac_work, mt7915_mac_work); - mt7915_eeprom_parse_band_config(phy); - mt7915_init_wiphy(mphy->hw); + mt7915_eeprom_parse_hw_cap(dev, phy); memcpy(mphy->macaddr, dev->mt76.eeprom.data + MT_EE_MAC_ADDR2, ETH_ALEN); + /* Make the secondary PHY MAC address local without overlapping with + * the usual MAC address allocation scheme on multiple virtual interfaces + */ + if (!is_valid_ether_addr(mphy->macaddr)) { + memcpy(mphy->macaddr, dev->mt76.eeprom.data + MT_EE_MAC_ADDR, + ETH_ALEN); + mphy->macaddr[0] |= 2; + mphy->macaddr[0] ^= BIT(7); + } mt76_eeprom_override(mphy); - ret = mt7915_init_tx_queues(phy, MT7915_TXQ_BAND1, - MT7915_TX_RING_SIZE); + /* init wiphy according to mphy and phy */ + mt7915_init_wiphy(mphy->hw); + ret = mt7915_init_tx_queues(phy, MT_TXQ_ID(1), + MT7915_TX_RING_SIZE, + MT_TXQ_RING_BASE(1)); if (ret) goto error; @@ -500,41 +545,50 @@ static void mt7915_init_work(struct work_struct *work) static void mt7915_wfsys_reset(struct mt7915_dev *dev) { - u32 val = MT_TOP_PWR_KEY | MT_TOP_PWR_SW_PWR_ON | MT_TOP_PWR_PWR_ON; - #define MT_MCU_DUMMY_RANDOM GENMASK(15, 0) #define MT_MCU_DUMMY_DEFAULT GENMASK(31, 16) - mt76_wr(dev, MT_MCU_WFDMA0_DUMMY_CR, MT_MCU_DUMMY_RANDOM); + if (is_mt7915(&dev->mt76)) { + u32 val = MT_TOP_PWR_KEY | MT_TOP_PWR_SW_PWR_ON | MT_TOP_PWR_PWR_ON; - /* change to software control */ - val |= MT_TOP_PWR_SW_RST; - mt76_wr(dev, MT_TOP_PWR_CTRL, val); + mt76_wr(dev, MT_MCU_WFDMA0_DUMMY_CR, MT_MCU_DUMMY_RANDOM); - /* reset wfsys */ - val &= ~MT_TOP_PWR_SW_RST; - mt76_wr(dev, MT_TOP_PWR_CTRL, val); + /* change to software control */ + val |= MT_TOP_PWR_SW_RST; + mt76_wr(dev, MT_TOP_PWR_CTRL, val); - /* release wfsys then mcu re-excutes romcode */ - val |= MT_TOP_PWR_SW_RST; - mt76_wr(dev, MT_TOP_PWR_CTRL, val); + /* reset wfsys */ + val &= ~MT_TOP_PWR_SW_RST; + mt76_wr(dev, MT_TOP_PWR_CTRL, val); - /* switch to hw control */ - val &= ~MT_TOP_PWR_SW_RST; - val |= MT_TOP_PWR_HW_CTRL; - mt76_wr(dev, MT_TOP_PWR_CTRL, val); + /* release wfsys then mcu re-excutes romcode */ + val |= MT_TOP_PWR_SW_RST; + mt76_wr(dev, MT_TOP_PWR_CTRL, val); - /* check whether mcu resets to default */ - if (!mt76_poll_msec(dev, MT_MCU_WFDMA0_DUMMY_CR, MT_MCU_DUMMY_DEFAULT, - MT_MCU_DUMMY_DEFAULT, 1000)) { - dev_err(dev->mt76.dev, "wifi subsystem reset failure\n"); - return; - } + /* switch to hw control */ + val &= ~MT_TOP_PWR_SW_RST; + val |= MT_TOP_PWR_HW_CTRL; + mt76_wr(dev, MT_TOP_PWR_CTRL, val); - /* wfsys reset won't clear host registers */ - mt76_clear(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE); + /* check whether mcu resets to default */ + if (!mt76_poll_msec(dev, MT_MCU_WFDMA0_DUMMY_CR, + MT_MCU_DUMMY_DEFAULT, MT_MCU_DUMMY_DEFAULT, + 1000)) { + dev_err(dev->mt76.dev, "wifi subsystem reset failure\n"); + return; + } + + /* wfsys reset won't clear host registers */ + mt76_clear(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE); - msleep(100); + msleep(100); + } else { + mt76_set(dev, MT_WF_SUBSYS_RST, 0x1); + msleep(20); + + mt76_clear(dev, MT_WF_SUBSYS_RST, 0x1); + msleep(20); + } } static int mt7915_init_hardware(struct mt7915_dev *dev) @@ -544,7 +598,9 @@ static int mt7915_init_hardware(struct mt7915_dev *dev) mt76_wr(dev, MT_INT_SOURCE_CSR, ~0); INIT_WORK(&dev->init_work, mt7915_init_work); - dev->dbdc_support = !!(mt76_rr(dev, MT_HW_BOUND) & BIT(5)); + + dev->dbdc_support = is_mt7915(&dev->mt76) ? + !!(mt76_rr(dev, MT_HW_BOUND) & BIT(5)) : true; /* If MCU was already running, it is likely in a bad state */ if (mt76_get_field(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE) > @@ -557,12 +613,6 @@ static int mt7915_init_hardware(struct mt7915_dev *dev) set_bit(MT76_STATE_INITIALIZED, &dev->mphy.state); - /* - * force firmware operation mode into normal state, - * which should be set before firmware download stage. - */ - mt76_wr(dev, MT_SWDEF_MODE, MT_SWDEF_NORMAL_MODE); - ret = mt7915_mcu_init(dev); if (ret) { /* Reset and try again */ @@ -577,7 +627,6 @@ static int mt7915_init_hardware(struct mt7915_dev *dev) if (ret < 0) return ret; - if (dev->flash_mode) { ret = mt7915_mcu_apply_group_cal(dev); if (ret) @@ -924,15 +973,6 @@ int mt7915_register_device(struct mt7915_dev *dev) mt7915_init_wiphy(hw); - if (!dev->dbdc_support) - dev->mphy.sband_5g.sband.vht_cap.cap |= - IEEE80211_VHT_CAP_SHORT_GI_160 | - IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ; - - dev->mphy.hw->wiphy->available_antennas_rx = dev->mphy.chainmask; - dev->mphy.hw->wiphy->available_antennas_tx = dev->mphy.chainmask; - dev->phy.dfs_state = -1; - #ifdef CONFIG_NL80211_TESTMODE dev->mt76.test_ops = &mt7915_testmode_ops; #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 48f115502282..08ee78f6309b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -165,7 +165,7 @@ static void mt7915_mac_sta_poll(struct mt7915_dev *dev) sta = container_of((void *)msta, struct ieee80211_sta, drv_priv); for (i = 0; i < IEEE80211_NUM_ACS; i++) { - u8 q = mt7915_lmac_mapping(dev, i); + u8 q = mt76_connac_lmac_mapping(i); u32 tx_cur = tx_time[q]; u32 rx_cur = rx_time[q]; u8 tid = ac_to_tid[i]; @@ -376,7 +376,8 @@ mt7915_mac_decode_he_radiotap(struct sk_buff *skb, __le32 *rxv, u32 mode) HE_BITS(DATA1_SPTL_REUSE3_KNOWN) | HE_BITS(DATA1_SPTL_REUSE4_KNOWN); - he->data4 |= HE_PREP(DATA4_TB_SPTL_REUSE2, SR1_MASK, rxv[11]) | + he->data4 |= HE_PREP(DATA4_TB_SPTL_REUSE1, SR_MASK, rxv[11]) | + HE_PREP(DATA4_TB_SPTL_REUSE2, SR1_MASK, rxv[11]) | HE_PREP(DATA4_TB_SPTL_REUSE3, SR2_MASK, rxv[11]) | HE_PREP(DATA4_TB_SPTL_REUSE4, SR3_MASK, rxv[11]); @@ -391,12 +392,12 @@ mt7915_mac_decode_he_radiotap(struct sk_buff *skb, __le32 *rxv, u32 mode) static int mt7915_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) { struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb; + struct ethhdr *eth_hdr = (struct ethhdr *)(skb->data + hdr_gap); struct mt7915_sta *msta = (struct mt7915_sta *)status->wcid; + __le32 *rxd = (__le32 *)skb->data; struct ieee80211_sta *sta; struct ieee80211_vif *vif; struct ieee80211_hdr hdr; - struct ethhdr eth_hdr; - __le32 *rxd = (__le32 *)skb->data; __le32 qos_ctrl, ht_ctrl; if (FIELD_GET(MT_RXD3_NORMAL_ADDR_TYPE, le32_to_cpu(rxd[3])) != @@ -413,7 +414,6 @@ static int mt7915_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv); /* store the info from RXD and ethhdr to avoid being overridden */ - memcpy(ð_hdr, skb->data + hdr_gap, sizeof(eth_hdr)); hdr.frame_control = FIELD_GET(MT_RXD6_FRAME_CONTROL, rxd[6]); hdr.seq_ctrl = FIELD_GET(MT_RXD8_SEQ_CTRL, rxd[8]); qos_ctrl = FIELD_GET(MT_RXD8_QOS_CTL, rxd[8]); @@ -428,24 +428,24 @@ static int mt7915_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) ether_addr_copy(hdr.addr3, vif->bss_conf.bssid); break; case IEEE80211_FCTL_FROMDS: - ether_addr_copy(hdr.addr3, eth_hdr.h_source); + ether_addr_copy(hdr.addr3, eth_hdr->h_source); break; case IEEE80211_FCTL_TODS: - ether_addr_copy(hdr.addr3, eth_hdr.h_dest); + ether_addr_copy(hdr.addr3, eth_hdr->h_dest); break; case IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS: - ether_addr_copy(hdr.addr3, eth_hdr.h_dest); - ether_addr_copy(hdr.addr4, eth_hdr.h_source); + ether_addr_copy(hdr.addr3, eth_hdr->h_dest); + ether_addr_copy(hdr.addr4, eth_hdr->h_source); break; default: break; } skb_pull(skb, hdr_gap + sizeof(struct ethhdr) - 2); - if (eth_hdr.h_proto == htons(ETH_P_AARP) || - eth_hdr.h_proto == htons(ETH_P_IPX)) + if (eth_hdr->h_proto == cpu_to_be16(ETH_P_AARP) || + eth_hdr->h_proto == cpu_to_be16(ETH_P_IPX)) ether_addr_copy(skb_push(skb, ETH_ALEN), bridge_tunnel_header); - else if (eth_hdr.h_proto >= htons(ETH_P_802_3_MIN)) + else if (eth_hdr->h_proto >= cpu_to_be16(ETH_P_802_3_MIN)) ether_addr_copy(skb_push(skb, ETH_ALEN), rfc1042_header); else skb_pull(skb, 2); @@ -463,6 +463,108 @@ static int mt7915_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) } static int +mt7915_mac_fill_rx_rate(struct mt7915_dev *dev, + struct mt76_rx_status *status, + struct ieee80211_supported_band *sband, + __le32 *rxv) +{ + u32 v0, v2; + u8 stbc, gi, bw, dcm, mode, nss; + int i, idx; + bool cck = false; + + v0 = le32_to_cpu(rxv[0]); + v2 = le32_to_cpu(rxv[2]); + + idx = i = FIELD_GET(MT_PRXV_TX_RATE, v0); + nss = FIELD_GET(MT_PRXV_NSTS, v0) + 1; + + if (!is_mt7915(&dev->mt76)) { + stbc = FIELD_GET(MT_PRXV_HT_STBC, v0); + gi = FIELD_GET(MT_PRXV_HT_SHORT_GI, v0); + mode = FIELD_GET(MT_PRXV_TX_MODE, v0); + dcm = FIELD_GET(MT_PRXV_DCM, v0); + bw = FIELD_GET(MT_PRXV_FRAME_MODE, v0); + } else { + stbc = FIELD_GET(MT_CRXV_HT_STBC, v2); + gi = FIELD_GET(MT_CRXV_HT_SHORT_GI, v2); + mode = FIELD_GET(MT_CRXV_TX_MODE, v2); + dcm = !!(idx & GENMASK(3, 0) & MT_PRXV_TX_DCM); + bw = FIELD_GET(MT_CRXV_FRAME_MODE, v2); + } + + switch (mode) { + case MT_PHY_TYPE_CCK: + cck = true; + fallthrough; + case MT_PHY_TYPE_OFDM: + i = mt76_get_rate(&dev->mt76, sband, i, cck); + break; + case MT_PHY_TYPE_HT_GF: + case MT_PHY_TYPE_HT: + status->encoding = RX_ENC_HT; + if (gi) + status->enc_flags |= RX_ENC_FLAG_SHORT_GI; + if (i > 31) + return -EINVAL; + break; + case MT_PHY_TYPE_VHT: + status->nss = nss; + status->encoding = RX_ENC_VHT; + if (gi) + status->enc_flags |= RX_ENC_FLAG_SHORT_GI; + if (i > 9) + return -EINVAL; + break; + case MT_PHY_TYPE_HE_MU: + case MT_PHY_TYPE_HE_SU: + case MT_PHY_TYPE_HE_EXT_SU: + case MT_PHY_TYPE_HE_TB: + status->nss = nss; + status->encoding = RX_ENC_HE; + i &= GENMASK(3, 0); + + if (gi <= NL80211_RATE_INFO_HE_GI_3_2) + status->he_gi = gi; + + status->he_dcm = dcm; + break; + default: + return -EINVAL; + } + status->rate_idx = i; + + switch (bw) { + case IEEE80211_STA_RX_BW_20: + break; + case IEEE80211_STA_RX_BW_40: + if (mode & MT_PHY_TYPE_HE_EXT_SU && + (idx & MT_PRXV_TX_ER_SU_106T)) { + status->bw = RATE_INFO_BW_HE_RU; + status->he_ru = + NL80211_RATE_INFO_HE_RU_ALLOC_106; + } else { + status->bw = RATE_INFO_BW_40; + } + break; + case IEEE80211_STA_RX_BW_80: + status->bw = RATE_INFO_BW_80; + break; + case IEEE80211_STA_RX_BW_160: + status->bw = RATE_INFO_BW_160; + break; + default: + return -EINVAL; + } + + status->enc_flags |= RX_ENC_FLAG_STBC_MASK * stbc; + if (mode < MT_PHY_TYPE_HE_SU && gi) + status->enc_flags |= RX_ENC_FLAG_SHORT_GI; + + return 0; +} + +static int mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) { struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb; @@ -626,7 +728,8 @@ mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) /* RXD Group 3 - P-RXV */ if (rxd1 & MT_RXD1_NORMAL_GROUP_3) { - u32 v0, v1, v2; + u32 v0, v1; + int ret; rxv = rxd; rxd += 2; @@ -635,7 +738,6 @@ mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) v0 = le32_to_cpu(rxv[0]); v1 = le32_to_cpu(rxv[1]); - v2 = le32_to_cpu(rxv[2]); if (v0 & MT_PRXV_HT_AD_CODE) status->enc_flags |= RX_ENC_FLAG_LDPC; @@ -657,82 +759,17 @@ mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) /* RXD Group 5 - C-RXV */ if (rxd1 & MT_RXD1_NORMAL_GROUP_5) { - u8 stbc = FIELD_GET(MT_CRXV_HT_STBC, v2); - u8 gi = FIELD_GET(MT_CRXV_HT_SHORT_GI, v2); - bool cck = false; - rxd += 18; if ((u8 *)rxd - skb->data >= skb->len) return -EINVAL; + } - idx = i = FIELD_GET(MT_PRXV_TX_RATE, v0); - mode = FIELD_GET(MT_CRXV_TX_MODE, v2); - - switch (mode) { - case MT_PHY_TYPE_CCK: - cck = true; - fallthrough; - case MT_PHY_TYPE_OFDM: - i = mt76_get_rate(&dev->mt76, sband, i, cck); - break; - case MT_PHY_TYPE_HT_GF: - case MT_PHY_TYPE_HT: - status->encoding = RX_ENC_HT; - if (i > 31) - return -EINVAL; - break; - case MT_PHY_TYPE_VHT: - status->nss = - FIELD_GET(MT_PRXV_NSTS, v0) + 1; - status->encoding = RX_ENC_VHT; - if (i > 9) - return -EINVAL; - break; - case MT_PHY_TYPE_HE_MU: - case MT_PHY_TYPE_HE_SU: - case MT_PHY_TYPE_HE_EXT_SU: - case MT_PHY_TYPE_HE_TB: - status->nss = - FIELD_GET(MT_PRXV_NSTS, v0) + 1; - status->encoding = RX_ENC_HE; - i &= GENMASK(3, 0); - - if (gi <= NL80211_RATE_INFO_HE_GI_3_2) - status->he_gi = gi; - - status->he_dcm = !!(idx & MT_PRXV_TX_DCM); - break; - default: - return -EINVAL; - } - status->rate_idx = i; - - switch (FIELD_GET(MT_CRXV_FRAME_MODE, v2)) { - case IEEE80211_STA_RX_BW_20: - break; - case IEEE80211_STA_RX_BW_40: - if (mode & MT_PHY_TYPE_HE_EXT_SU && - (idx & MT_PRXV_TX_ER_SU_106T)) { - status->bw = RATE_INFO_BW_HE_RU; - status->he_ru = - NL80211_RATE_INFO_HE_RU_ALLOC_106; - } else { - status->bw = RATE_INFO_BW_40; - } - break; - case IEEE80211_STA_RX_BW_80: - status->bw = RATE_INFO_BW_80; - break; - case IEEE80211_STA_RX_BW_160: - status->bw = RATE_INFO_BW_160; - break; - default: - return -EINVAL; - } - - status->enc_flags |= RX_ENC_FLAG_STBC_MASK * stbc; - if (mode < MT_PHY_TYPE_HE_SU && gi) - status->enc_flags |= RX_ENC_FLAG_SHORT_GI; + if (!is_mt7915(&dev->mt76) || + (is_mt7915(&dev->mt76) && + (rxd1 & MT_RXD1_NORMAL_GROUP_5))) { + ret = mt7915_mac_fill_rx_rate(dev, status, sband, rxv); + if (ret < 0) + return ret; } } @@ -801,6 +838,10 @@ mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) if (!status->wcid || !ieee80211_is_data_qos(fc)) return 0; + /* drop no data frame */ + if (fc & cpu_to_le16(IEEE80211_STYPE_NULLFUNC)) + return -EINVAL; + status->aggr = unicast && !ieee80211_is_qos_nullfunc(fc); status->qos_ctl = qos_ctl; @@ -1165,7 +1206,7 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi, } else { p_fmt = MT_TX_TYPE_CT; q_idx = wmm_idx * MT7915_MAX_WMM_SETS + - mt7915_lmac_mapping(dev, skb_get_queue_mapping(skb)); + mt76_connac_lmac_mapping(skb_get_queue_mapping(skb)); } val = FIELD_PREP(MT_TXD0_TX_BYTES, skb->len + MT_TXD_SIZE) | @@ -1383,8 +1424,10 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len) LIST_HEAD(free_list); struct sk_buff *skb, *tmp; void *end = data + len; - u8 i, count; - bool wake = false; + bool v3, wake = false; + u16 total, count = 0; + u32 txd = le32_to_cpu(free->txd); + u32 *cur_info; /* clean DMA queues and unmap buffers first */ mt76_queue_tx_cleanup(dev, dev->mphy.q_tx[MT_TXQ_PSD], false); @@ -1399,12 +1442,14 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len) * to the time ack is received or dropped by hw (air + hw queue time). * Should avoid accessing WTBL to get Tx airtime, and use it instead. */ - count = FIELD_GET(MT_TX_FREE_MSDU_CNT, le16_to_cpu(free->ctrl)); - if (WARN_ON_ONCE((void *)&free->info[count] > end)) + total = FIELD_GET(MT_TX_FREE_MSDU_CNT, le16_to_cpu(free->ctrl)); + v3 = (FIELD_GET(MT_TX_FREE_VER, txd) == 0x4); + if (WARN_ON_ONCE((void *)&free->info[total >> v3] > end)) return; - for (i = 0; i < count; i++) { - u32 msdu, info = le32_to_cpu(free->info[i]); + for (cur_info = &free->info[0]; count < total; cur_info++) { + u32 msdu, info = le32_to_cpu(*cur_info); + u8 i; /* * 1'b1: new wcid pair. @@ -1415,7 +1460,6 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len) struct mt76_wcid *wcid; u16 idx; - count++; idx = FIELD_GET(MT_TX_FREE_WLAN_ID, info); wcid = rcu_dereference(dev->mt76.wcid[idx]); sta = wcid_to_sta(wcid); @@ -1430,12 +1474,24 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len) continue; } - msdu = FIELD_GET(MT_TX_FREE_MSDU_ID, info); - txwi = mt76_token_release(mdev, msdu, &wake); - if (!txwi) + if (v3 && (info & MT_TX_FREE_MPDU_HEADER)) continue; - mt7915_txwi_free(dev, txwi, sta, &free_list); + for (i = 0; i < 1 + v3; i++) { + if (v3) { + msdu = (info >> (15 * i)) & MT_TX_FREE_MSDU_ID_V3; + if (msdu == MT_TX_FREE_MSDU_ID_V3) + continue; + } else { + msdu = FIELD_GET(MT_TX_FREE_MSDU_ID, info); + } + count++; + txwi = mt76_token_release(mdev, msdu, &wake); + if (!txwi) + continue; + + mt7915_txwi_free(dev, txwi, sta, &free_list); + } } mt7915_mac_sta_poll(dev); @@ -1512,7 +1568,6 @@ mt7915_mac_add_txs_skb(struct mt7915_dev *dev, struct mt76_wcid *wcid, int pid, break; case MT_PHY_TYPE_HT: case MT_PHY_TYPE_HT_GF: - rate.mcs += (rate.nss - 1) * 8; if (rate.mcs > 31) goto out; @@ -1594,7 +1649,7 @@ static void mt7915_mac_add_txs(struct mt7915_dev *dev, void *data) if (pid < MT_PACKET_ID_FIRST) return; - if (wcidx >= MT7915_WTBL_SIZE) + if (wcidx >= mt7915_wtbl_size(dev)) return; rcu_read_lock(); @@ -1635,6 +1690,9 @@ bool mt7915_rx_check(struct mt76_dev *mdev, void *data, int len) for (rxd += 2; rxd + 8 <= end; rxd += 8) mt7915_mac_add_txs(dev, rxd); return false; + case PKT_TYPE_RX_FW_MONITOR: + mt7915_debugfs_rx_fw_monitor(dev, data, len); + return false; default: return true; } @@ -1666,6 +1724,9 @@ void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, mt7915_mac_add_txs(dev, rxd); dev_kfree_skb(skb); break; + case PKT_TYPE_RX_FW_MONITOR: + mt7915_debugfs_rx_fw_monitor(dev, skb->data, skb->len); + break; case PKT_TYPE_NORMAL: if (!mt7915_mac_fill_rx(dev, skb)) { mt76_rx(&dev->mt76, q, skb); @@ -1891,7 +1952,7 @@ static void mt7915_dma_reset(struct mt7915_dev *dev) { struct mt76_phy *mphy_ext = dev->mt76.phy2; - u32 hif1_ofs = MT_WFDMA1_PCIE1_BASE - MT_WFDMA1_BASE; + u32 hif1_ofs = MT_WFDMA0_PCIE1(0) - MT_WFDMA0(0); int i; mt76_clear(dev, MT_WFDMA0_GLO_CFG, @@ -2052,9 +2113,11 @@ void mt7915_mac_update_stats(struct mt7915_phy *phy) struct mib_stats *mib = &phy->mib; bool ext_phy = phy != &dev->phy; int i, aggr0, aggr1, cnt; + u32 val; - mib->fcs_err_cnt += mt76_get_field(dev, MT_MIB_SDR3(ext_phy), - MT_MIB_SDR3_FCS_ERR_MASK); + cnt = mt76_rr(dev, MT_MIB_SDR3(ext_phy)); + mib->fcs_err_cnt += is_mt7915(&dev->mt76) ? FIELD_GET(MT_MIB_SDR3_FCS_ERR_MASK, cnt) : + FIELD_GET(MT_MIB_SDR3_FCS_ERR_MASK_MT7916, cnt); cnt = mt76_rr(dev, MT_MIB_SDR4(ext_phy)); mib->rx_fifo_full_cnt += FIELD_GET(MT_MIB_SDR4_RX_FIFO_FULL_MASK, cnt); @@ -2081,10 +2144,14 @@ void mt7915_mac_update_stats(struct mt7915_phy *phy) mib->tx_stop_q_empty_cnt += FIELD_GET(MT_MIB_SDR13_TX_STOP_Q_EMPTY_CNT_MASK, cnt); cnt = mt76_rr(dev, MT_MIB_SDR14(ext_phy)); - mib->tx_mpdu_attempts_cnt += FIELD_GET(MT_MIB_SDR14_TX_MPDU_ATTEMPTS_CNT_MASK, cnt); + mib->tx_mpdu_attempts_cnt += is_mt7915(&dev->mt76) ? + FIELD_GET(MT_MIB_SDR14_TX_MPDU_ATTEMPTS_CNT_MASK, cnt) : + FIELD_GET(MT_MIB_SDR14_TX_MPDU_ATTEMPTS_CNT_MASK_MT7916, cnt); cnt = mt76_rr(dev, MT_MIB_SDR15(ext_phy)); - mib->tx_mpdu_success_cnt += FIELD_GET(MT_MIB_SDR15_TX_MPDU_SUCCESS_CNT_MASK, cnt); + mib->tx_mpdu_success_cnt += is_mt7915(&dev->mt76) ? + FIELD_GET(MT_MIB_SDR15_TX_MPDU_SUCCESS_CNT_MASK, cnt) : + FIELD_GET(MT_MIB_SDR15_TX_MPDU_SUCCESS_CNT_MASK_MT7916, cnt); cnt = mt76_rr(dev, MT_MIB_SDR22(ext_phy)); mib->rx_ampdu_cnt += cnt; @@ -2093,7 +2160,9 @@ void mt7915_mac_update_stats(struct mt7915_phy *phy) mib->rx_ampdu_bytes_cnt += cnt; cnt = mt76_rr(dev, MT_MIB_SDR24(ext_phy)); - mib->rx_ampdu_valid_subframe_cnt += FIELD_GET(MT_MIB_SDR24_RX_AMPDU_SF_CNT_MASK, cnt); + mib->rx_ampdu_valid_subframe_cnt += is_mt7915(&dev->mt76) ? + FIELD_GET(MT_MIB_SDR24_RX_AMPDU_SF_CNT_MASK, cnt) : + FIELD_GET(MT_MIB_SDR24_RX_AMPDU_SF_CNT_MASK_MT7916, cnt); cnt = mt76_rr(dev, MT_MIB_SDR25(ext_phy)); mib->rx_ampdu_valid_subframe_bytes_cnt += cnt; @@ -2105,11 +2174,14 @@ void mt7915_mac_update_stats(struct mt7915_phy *phy) mib->tx_rwp_need_cnt += FIELD_GET(MT_MIB_SDR28_TX_RWP_NEED_CNT_MASK, cnt); cnt = mt76_rr(dev, MT_MIB_SDR29(ext_phy)); - mib->rx_pfdrop_cnt += FIELD_GET(MT_MIB_SDR29_RX_PFDROP_CNT_MASK, cnt); + mib->rx_pfdrop_cnt += is_mt7915(&dev->mt76) ? + FIELD_GET(MT_MIB_SDR29_RX_PFDROP_CNT_MASK, cnt) : + FIELD_GET(MT_MIB_SDR29_RX_PFDROP_CNT_MASK_MT7916, cnt); - cnt = mt76_rr(dev, MT_MIB_SDR30(ext_phy)); - mib->rx_vec_queue_overflow_drop_cnt += - FIELD_GET(MT_MIB_SDR30_RX_VEC_QUEUE_OVERFLOW_DROP_CNT_MASK, cnt); + cnt = mt76_rr(dev, MT_MIB_SDRVEC(ext_phy)); + mib->rx_vec_queue_overflow_drop_cnt += is_mt7915(&dev->mt76) ? + FIELD_GET(MT_MIB_SDR30_RX_VEC_QUEUE_OVERFLOW_DROP_CNT_MASK, cnt) : + FIELD_GET(MT_MIB_SDR30_RX_VEC_QUEUE_OVERFLOW_DROP_CNT_MASK_MT7916, cnt); cnt = mt76_rr(dev, MT_MIB_SDR31(ext_phy)); mib->rx_ba_cnt += cnt; @@ -2117,10 +2189,13 @@ void mt7915_mac_update_stats(struct mt7915_phy *phy) cnt = mt76_rr(dev, MT_MIB_SDR32(ext_phy)); mib->tx_pkt_ebf_cnt += FIELD_GET(MT_MIB_SDR32_TX_PKT_EBF_CNT_MASK, cnt); - cnt = mt76_rr(dev, MT_MIB_SDR33(ext_phy)); - mib->tx_pkt_ibf_cnt += FIELD_GET(MT_MIB_SDR33_TX_PKT_IBF_CNT_MASK, cnt); + if (is_mt7915(&dev->mt76)) + cnt = mt76_rr(dev, MT_MIB_SDR33(ext_phy)); + mib->tx_pkt_ibf_cnt += is_mt7915(&dev->mt76) ? + FIELD_GET(MT_MIB_SDR32_TX_PKT_IBF_CNT_MASK, cnt) : + FIELD_GET(MT_MIB_SDR32_TX_PKT_IBF_CNT_MASK_MT7916, cnt); - cnt = mt76_rr(dev, MT_MIB_SDR34(ext_phy)); + cnt = mt76_rr(dev, MT_MIB_SDRMUBF(ext_phy)); mib->tx_bf_cnt += FIELD_GET(MT_MIB_MU_BF_TX_CNT, cnt); cnt = mt76_rr(dev, MT_MIB_DR8(ext_phy)); @@ -2158,26 +2233,54 @@ void mt7915_mac_update_stats(struct mt7915_phy *phy) } aggr0 = ext_phy ? ARRAY_SIZE(dev->mt76.aggr_stats) / 2 : 0; - for (i = 0, aggr1 = aggr0 + 4; i < 4; i++) { - u32 val; - - val = mt76_rr(dev, MT_MIB_MB_SDR1(ext_phy, i)); - mib->ba_miss_cnt += FIELD_GET(MT_MIB_BA_MISS_COUNT_MASK, val); - mib->ack_fail_cnt += - FIELD_GET(MT_MIB_ACK_FAIL_COUNT_MASK, val); - - val = mt76_rr(dev, MT_MIB_MB_SDR0(ext_phy, i)); - mib->rts_cnt += FIELD_GET(MT_MIB_RTS_COUNT_MASK, val); - mib->rts_retries_cnt += - FIELD_GET(MT_MIB_RTS_RETRIES_COUNT_MASK, val); - - val = mt76_rr(dev, MT_TX_AGG_CNT(ext_phy, i)); - dev->mt76.aggr_stats[aggr0++] += val & 0xffff; - dev->mt76.aggr_stats[aggr0++] += val >> 16; + if (is_mt7915(&dev->mt76)) { + for (i = 0, aggr1 = aggr0 + 4; i < 4; i++) { + val = mt76_rr(dev, MT_MIB_MB_SDR1(ext_phy, (i << 4))); + mib->ba_miss_cnt += FIELD_GET(MT_MIB_BA_MISS_COUNT_MASK, val); + mib->ack_fail_cnt += + FIELD_GET(MT_MIB_ACK_FAIL_COUNT_MASK, val); + + val = mt76_rr(dev, MT_MIB_MB_SDR0(ext_phy, (i << 4))); + mib->rts_cnt += FIELD_GET(MT_MIB_RTS_COUNT_MASK, val); + mib->rts_retries_cnt += + FIELD_GET(MT_MIB_RTS_RETRIES_COUNT_MASK, val); + + val = mt76_rr(dev, MT_TX_AGG_CNT(ext_phy, i)); + dev->mt76.aggr_stats[aggr0++] += val & 0xffff; + dev->mt76.aggr_stats[aggr0++] += val >> 16; + + val = mt76_rr(dev, MT_TX_AGG_CNT2(ext_phy, i)); + dev->mt76.aggr_stats[aggr1++] += val & 0xffff; + dev->mt76.aggr_stats[aggr1++] += val >> 16; + } + } else { + for (i = 0; i < 2; i++) { + /* rts count */ + val = mt76_rr(dev, MT_MIB_MB_SDR0(ext_phy, (i << 2))); + mib->rts_cnt += FIELD_GET(GENMASK(15, 0), val); + mib->rts_cnt += FIELD_GET(GENMASK(31, 16), val); + + /* rts retry count */ + val = mt76_rr(dev, MT_MIB_MB_SDR1(ext_phy, (i << 2))); + mib->rts_retries_cnt += FIELD_GET(GENMASK(15, 0), val); + mib->rts_retries_cnt += FIELD_GET(GENMASK(31, 16), val); + + /* ba miss count */ + val = mt76_rr(dev, MT_MIB_MB_SDR2(ext_phy, (i << 2))); + mib->ba_miss_cnt += FIELD_GET(GENMASK(15, 0), val); + mib->ba_miss_cnt += FIELD_GET(GENMASK(31, 16), val); + + /* ack fail count */ + val = mt76_rr(dev, MT_MIB_MB_BFTF(ext_phy, (i << 2))); + mib->ack_fail_cnt += FIELD_GET(GENMASK(15, 0), val); + mib->ack_fail_cnt += FIELD_GET(GENMASK(31, 16), val); + } - val = mt76_rr(dev, MT_TX_AGG_CNT2(ext_phy, i)); - dev->mt76.aggr_stats[aggr1++] += val & 0xffff; - dev->mt76.aggr_stats[aggr1++] += val >> 16; + for (i = 0; i < 8; i++) { + val = mt76_rr(dev, MT_TX_AGG_CNT(ext_phy, i)); + dev->mt76.aggr_stats[aggr0++] += FIELD_GET(GENMASK(15, 0), val); + dev->mt76.aggr_stats[aggr0++] += FIELD_GET(GENMASK(31, 16), val); + } } } @@ -2248,20 +2351,24 @@ static void mt7915_dfs_stop_radar_detector(struct mt7915_phy *phy) struct mt7915_dev *dev = phy->dev; if (phy->rdd_state & BIT(0)) - mt7915_mcu_rdd_cmd(dev, RDD_STOP, 0, MT_RX_SEL0, 0); + mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, 0, + MT_RX_SEL0, 0); if (phy->rdd_state & BIT(1)) - mt7915_mcu_rdd_cmd(dev, RDD_STOP, 1, MT_RX_SEL0, 0); + mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, 1, + MT_RX_SEL0, 0); } static int mt7915_dfs_start_rdd(struct mt7915_dev *dev, int chain) { int err; - err = mt7915_mcu_rdd_cmd(dev, RDD_START, chain, MT_RX_SEL0, 0); + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_START, chain, + MT_RX_SEL0, 0); if (err < 0) return err; - return mt7915_mcu_rdd_cmd(dev, RDD_DET_MODE, chain, MT_RX_SEL0, 1); + return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_DET_MODE, chain, + MT_RX_SEL0, 1); } static int mt7915_dfs_start_radar_detector(struct mt7915_phy *phy) @@ -2272,7 +2379,8 @@ static int mt7915_dfs_start_radar_detector(struct mt7915_phy *phy) int err; /* start CAC */ - err = mt7915_mcu_rdd_cmd(dev, RDD_CAC_START, ext_phy, MT_RX_SEL0, 0); + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_START, ext_phy, + MT_RX_SEL0, 0); if (err < 0) return err; @@ -2330,48 +2438,57 @@ mt7915_dfs_init_radar_specs(struct mt7915_phy *phy) int mt7915_dfs_init_radar_detector(struct mt7915_phy *phy) { - struct cfg80211_chan_def *chandef = &phy->mt76->chandef; struct mt7915_dev *dev = phy->dev; bool ext_phy = phy != &dev->phy; + enum mt76_dfs_state dfs_state, prev_state; int err; - if (dev->mt76.region == NL80211_DFS_UNSET) { - phy->dfs_state = -1; - if (phy->rdd_state) - goto stop; + prev_state = phy->mt76->dfs_state; + dfs_state = mt76_phy_dfs_state(phy->mt76); + if (prev_state == dfs_state) return 0; - } - if (test_bit(MT76_SCANNING, &phy->mt76->state)) - return 0; + if (prev_state == MT_DFS_STATE_UNKNOWN) + mt7915_dfs_stop_radar_detector(phy); - if (phy->dfs_state == chandef->chan->dfs_state) - return 0; - - err = mt7915_dfs_init_radar_specs(phy); - if (err < 0) { - phy->dfs_state = -1; + if (dfs_state == MT_DFS_STATE_DISABLED) goto stop; - } - phy->dfs_state = chandef->chan->dfs_state; + if (prev_state <= MT_DFS_STATE_DISABLED) { + err = mt7915_dfs_init_radar_specs(phy); + if (err < 0) + return err; - if (chandef->chan->flags & IEEE80211_CHAN_RADAR) { - if (chandef->chan->dfs_state != NL80211_DFS_AVAILABLE) - return mt7915_dfs_start_radar_detector(phy); + err = mt7915_dfs_start_radar_detector(phy); + if (err < 0) + return err; - return mt7915_mcu_rdd_cmd(dev, RDD_CAC_END, ext_phy, - MT_RX_SEL0, 0); + phy->mt76->dfs_state = MT_DFS_STATE_CAC; } + if (dfs_state == MT_DFS_STATE_CAC) + return 0; + + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_CAC_END, + ext_phy, MT_RX_SEL0, 0); + if (err < 0) { + phy->mt76->dfs_state = MT_DFS_STATE_UNKNOWN; + return err; + } + + phy->mt76->dfs_state = MT_DFS_STATE_ACTIVE; + return 0; + stop: - err = mt7915_mcu_rdd_cmd(dev, RDD_NORMAL_START, ext_phy, - MT_RX_SEL0, 0); + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_NORMAL_START, ext_phy, + MT_RX_SEL0, 0); if (err < 0) return err; mt7915_dfs_stop_radar_detector(phy); + phy->mt76->dfs_state = MT_DFS_STATE_DISABLED; + return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.h b/drivers/net/wireless/mediatek/mt76/mt7915/mac.h index 7a2c740d1464..5add1dd36dbe 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.h @@ -23,6 +23,7 @@ enum rx_pkt_type { PKT_TYPE_RETRIEVE, PKT_TYPE_TXRX_NOTIFY, PKT_TYPE_RX_EVENT, + PKT_TYPE_RX_FW_MONITOR = 0x0c, }; /* RXD DW1 */ @@ -125,6 +126,12 @@ enum rx_pkt_type { #define MT_PRXV_RCPI2 GENMASK(23, 16) #define MT_PRXV_RCPI1 GENMASK(15, 8) #define MT_PRXV_RCPI0 GENMASK(7, 0) +#define MT_PRXV_HT_SHORT_GI GENMASK(16, 15) +#define MT_PRXV_HT_STBC GENMASK(23, 22) +#define MT_PRXV_TX_MODE GENMASK(27, 24) +#define MT_PRXV_FRAME_MODE GENMASK(14, 12) +#define MT_PRXV_DCM BIT(17) +#define MT_PRXV_NUM_RX BIT(20, 18) /* C-RXV */ #define MT_CRXV_HT_STBC GENMASK(1, 0) @@ -298,18 +305,20 @@ struct mt7915_txp { struct mt7915_tx_free { __le16 rx_byte_cnt; __le16 ctrl; - u8 txd_cnt; - u8 rsv[3]; + __le32 txd; __le32 info[]; } __packed __aligned(4); +#define MT_TX_FREE_VER GENMASK(18, 16) #define MT_TX_FREE_MSDU_CNT GENMASK(9, 0) #define MT_TX_FREE_WLAN_ID GENMASK(23, 14) #define MT_TX_FREE_LATENCY GENMASK(12, 0) /* 0: success, others: dropped */ -#define MT_TX_FREE_STATUS GENMASK(14, 13) #define MT_TX_FREE_MSDU_ID GENMASK(30, 16) #define MT_TX_FREE_PAIR BIT(31) +#define MT_TX_FREE_MPDU_HEADER BIT(30) +#define MT_TX_FREE_MSDU_ID_V3 GENMASK(14, 0) + /* will support this field in further revision */ #define MT_TX_FREE_RATE GENMASK(13, 0) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index 8ac6f59af174..dee7fc011cdf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -34,7 +34,7 @@ static int mt7915_start(struct ieee80211_hw *hw) running = mt7915_dev_running(dev); if (!running) { - ret = mt7915_mcu_set_pm(dev, 0, 0); + ret = mt76_connac_mcu_set_pm(&dev->mt76, 0, 0); if (ret) goto out; @@ -50,7 +50,7 @@ static int mt7915_start(struct ieee80211_hw *hw) } if (phy != &dev->phy) { - ret = mt7915_mcu_set_pm(dev, 1, 0); + ret = mt76_connac_mcu_set_pm(&dev->mt76, 1, 0); if (ret) goto out; @@ -65,7 +65,8 @@ static int mt7915_start(struct ieee80211_hw *hw) mt7915_mac_enable_nf(dev, 1); } - ret = mt7915_mcu_set_rts_thresh(phy, 0x92b); + ret = mt76_connac_mcu_set_rts_thresh(&dev->mt76, 0x92b, + phy != &dev->phy); if (ret) goto out; @@ -106,12 +107,12 @@ static void mt7915_stop(struct ieee80211_hw *hw) clear_bit(MT76_STATE_RUNNING, &phy->mt76->state); if (phy != &dev->phy) { - mt7915_mcu_set_pm(dev, 1, 1); + mt76_connac_mcu_set_pm(&dev->mt76, 1, 1); mt7915_mcu_set_mac(dev, 1, false, false); } if (!mt7915_dev_running(dev)) { - mt7915_mcu_set_pm(dev, 0, 1); + mt76_connac_mcu_set_pm(&dev->mt76, 0, 1); mt7915_mcu_set_mac(dev, 0, false, false); } @@ -256,6 +257,9 @@ static int mt7915_add_interface(struct ieee80211_hw *hw, mt7915_init_bitrate_mask(vif); memset(&mvif->cap, -1, sizeof(mvif->cap)); + mt7915_mcu_add_bss_info(phy, vif, true); + mt7915_mcu_add_sta(dev, vif, NULL, true); + out: mutex_unlock(&dev->mt76.mutex); @@ -298,25 +302,6 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw, mt76_packet_id_flush(&dev->mt76, &msta->wcid); } -static void mt7915_init_dfs_state(struct mt7915_phy *phy) -{ - struct mt76_phy *mphy = phy->mt76; - struct ieee80211_hw *hw = mphy->hw; - struct cfg80211_chan_def *chandef = &hw->conf.chandef; - - if (hw->conf.flags & IEEE80211_CONF_OFFCHANNEL) - return; - - if (!(chandef->chan->flags & IEEE80211_CHAN_RADAR)) - return; - - if (mphy->chandef.chan->center_freq == chandef->chan->center_freq && - mphy->chandef.width == chandef->width) - return; - - phy->dfs_state = -1; -} - int mt7915_set_channel(struct mt7915_phy *phy) { struct mt7915_dev *dev = phy->dev; @@ -327,7 +312,6 @@ int mt7915_set_channel(struct mt7915_phy *phy) mutex_lock(&dev->mt76.mutex); set_bit(MT76_RESET, &phy->mt76->state); - mt7915_init_dfs_state(phy); mt76_set_channel(phy->mt76); if (dev->flash_mode) { @@ -366,6 +350,7 @@ static int mt7915_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ieee80211_key_conf *key) { struct mt7915_dev *dev = mt7915_hw_dev(hw); + struct mt7915_phy *phy = mt7915_hw_phy(hw); struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; struct mt7915_sta *msta = sta ? (struct mt7915_sta *)sta->drv_priv : &mvif->sta; @@ -405,6 +390,11 @@ static int mt7915_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, mutex_lock(&dev->mt76.mutex); + if (cmd == SET_KEY && !sta && !mvif->mt76.cipher) { + mvif->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher); + mt7915_mcu_add_bss_info(phy, vif, true); + } + if (cmd == SET_KEY) *wcid_keyidx = idx; else if (idx == *wcid_keyidx) @@ -415,8 +405,9 @@ static int mt7915_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, mt76_wcid_key_setup(&dev->mt76, wcid, cmd == SET_KEY ? key : NULL); - err = mt7915_mcu_add_key(dev, vif, msta, key, cmd); - + err = mt76_connac_mcu_add_key(&dev->mt76, vif, &msta->bip, + key, MCU_EXT_CMD(STA_REC_UPDATE), + &msta->wcid, cmd); out: mutex_unlock(&dev->mt76.mutex); @@ -498,11 +489,10 @@ static int mt7915_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 queue, const struct ieee80211_tx_queue_params *params) { - struct mt7915_dev *dev = mt7915_hw_dev(hw); struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; /* no need to update right away, we'll get BSS_CHANGED_QOS */ - queue = mt7915_lmac_mapping(dev, queue); + queue = mt76_connac_lmac_mapping(queue); mvif->queue_params[queue] = *params; return 0; @@ -746,7 +736,7 @@ static int mt7915_set_rts_threshold(struct ieee80211_hw *hw, u32 val) int ret; mutex_lock(&dev->mt76.mutex); - ret = mt7915_mcu_set_rts_thresh(phy, val); + ret = mt76_connac_mcu_set_rts_thresh(&dev->mt76, val, phy != &dev->phy); mutex_unlock(&dev->mt76.mutex); return ret; @@ -861,8 +851,12 @@ u64 __mt7915_get_tsf(struct ieee80211_hw *hw, struct mt7915_vif *mvif) n = mvif->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : mvif->mt76.omac_idx; /* TSF software read */ - mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, - MT_LPON_TCR_SW_READ); + if (is_mt7915(&dev->mt76)) + mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_READ); + else + mt76_rmw(dev, MT_LPON_TCR_MT7916(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_READ); tsf.t32[0] = mt76_rr(dev, MT_LPON_UTTR0(band)); tsf.t32[1] = mt76_rr(dev, MT_LPON_UTTR1(band)); @@ -904,8 +898,12 @@ mt7915_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mt76_wr(dev, MT_LPON_UTTR0(band), tsf.t32[0]); mt76_wr(dev, MT_LPON_UTTR1(band), tsf.t32[1]); /* TSF software overwrite */ - mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, - MT_LPON_TCR_SW_WRITE); + if (is_mt7915(&dev->mt76)) + mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_WRITE); + else + mt76_rmw(dev, MT_LPON_TCR_MT7916(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_WRITE); mutex_unlock(&dev->mt76.mutex); } @@ -931,8 +929,12 @@ mt7915_offset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mt76_wr(dev, MT_LPON_UTTR0(band), tsf.t32[0]); mt76_wr(dev, MT_LPON_UTTR1(band), tsf.t32[1]); /* TSF software adjust*/ - mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, - MT_LPON_TCR_SW_ADJUST); + if (is_mt7915(&dev->mt76)) + mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_ADJUST); + else + mt76_rmw(dev, MT_LPON_TCR_MT7916(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_ADJUST); mutex_unlock(&dev->mt76.mutex); } @@ -994,7 +996,8 @@ static void mt7915_sta_statistics(struct ieee80211_hw *hw, struct rate_info *txrate = &msta->wcid.rate; struct rate_info rxrate = {}; - if (!mt7915_mcu_get_rx_rate(phy, vif, sta, &rxrate)) { + if (is_mt7915(&phy->dev->mt76) && + !mt7915_mcu_get_rx_rate(phy, vif, sta, &rxrate)) { sinfo->rxrate = rxrate; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE); } @@ -1079,7 +1082,7 @@ static void mt7915_sta_set_4addr(struct ieee80211_hw *hw, else clear_bit(MT_WCID_FLAG_4ADDR, &msta->wcid.flags); - mt7915_mcu_sta_update_hdr_trans(dev, vif, sta); + mt76_connac_mcu_wtbl_update_hdr_trans(&dev->mt76, vif, sta); } static void mt7915_sta_set_decap_offload(struct ieee80211_hw *hw, @@ -1095,7 +1098,7 @@ static void mt7915_sta_set_decap_offload(struct ieee80211_hw *hw, else clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags); - mt7915_mcu_sta_update_hdr_trans(dev, vif, sta); + mt76_connac_mcu_wtbl_update_hdr_trans(&dev->mt76, vif, sta); } static const char mt7915_gstrings_stats[][ETH_GSTRING_LEN] = { @@ -1332,6 +1335,55 @@ mt7915_twt_teardown_request(struct ieee80211_hw *hw, mutex_unlock(&dev->mt76.mutex); } +static int +mt7915_set_radar_background(struct ieee80211_hw *hw, + struct cfg80211_chan_def *chandef) +{ + struct mt7915_phy *phy = mt7915_hw_phy(hw); + struct mt7915_dev *dev = phy->dev; + int ret = -EINVAL; + bool running; + + mutex_lock(&dev->mt76.mutex); + + if (dev->mt76.region == NL80211_DFS_UNSET) + goto out; + + if (dev->rdd2_phy && dev->rdd2_phy != phy) { + /* rdd2 is already locked */ + ret = -EBUSY; + goto out; + } + + /* rdd2 already configured on a radar channel */ + running = dev->rdd2_phy && + cfg80211_chandef_valid(&dev->rdd2_chandef) && + !!(dev->rdd2_chandef.chan->flags & IEEE80211_CHAN_RADAR); + + if (!chandef || running || + !(chandef->chan->flags & IEEE80211_CHAN_RADAR)) { + ret = mt7915_mcu_rdd_background_enable(phy, NULL); + if (ret) + goto out; + + if (!running) + goto update_phy; + } + + ret = mt7915_mcu_rdd_background_enable(phy, chandef); + if (ret) + goto out; + +update_phy: + dev->rdd2_phy = chandef ? phy : NULL; + if (chandef) + dev->rdd2_chandef = *chandef; +out: + mutex_unlock(&dev->mt76.mutex); + + return ret; +} + const struct ieee80211_ops mt7915_ops = { .tx = mt7915_tx, .start = mt7915_start, @@ -1378,4 +1430,5 @@ const struct ieee80211_ops mt7915_ops = { #ifdef CONFIG_MAC80211_DEBUGFS .sta_add_debugfs = mt7915_sta_add_debugfs, #endif + .set_radar_background = mt7915_set_radar_background, }; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index 0911b6f973b5..462c7da93b60 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -66,134 +66,9 @@ struct mt7915_fw_region { #define MCU_PATCH_ADDRESS 0x200000 -#define FW_FEATURE_SET_ENCRYPT BIT(0) -#define FW_FEATURE_SET_KEY_IDX GENMASK(2, 1) -#define FW_FEATURE_OVERRIDE_ADDR BIT(5) - -#define DL_MODE_ENCRYPT BIT(0) -#define DL_MODE_KEY_IDX GENMASK(2, 1) -#define DL_MODE_RESET_SEC_IV BIT(3) -#define DL_MODE_WORKING_PDA_CR4 BIT(4) -#define DL_MODE_NEED_RSP BIT(31) - -#define FW_START_OVERRIDE BIT(0) -#define FW_START_WORKING_PDA_CR4 BIT(2) - -#define PATCH_SEC_TYPE_MASK GENMASK(15, 0) -#define PATCH_SEC_TYPE_INFO 0x2 - -#define to_wcid_lo(id) FIELD_GET(GENMASK(7, 0), (u16)id) -#define to_wcid_hi(id) FIELD_GET(GENMASK(9, 8), (u16)id) - #define HE_PHY(p, c) u8_get_bits(c, IEEE80211_HE_PHY_##p) #define HE_MAC(m, c) u8_get_bits(c, IEEE80211_HE_MAC_##m) -static enum mcu_cipher_type -mt7915_mcu_get_cipher(int cipher) -{ - switch (cipher) { - case WLAN_CIPHER_SUITE_WEP40: - return MCU_CIPHER_WEP40; - case WLAN_CIPHER_SUITE_WEP104: - return MCU_CIPHER_WEP104; - case WLAN_CIPHER_SUITE_TKIP: - return MCU_CIPHER_TKIP; - case WLAN_CIPHER_SUITE_AES_CMAC: - return MCU_CIPHER_BIP_CMAC_128; - case WLAN_CIPHER_SUITE_CCMP: - return MCU_CIPHER_AES_CCMP; - case WLAN_CIPHER_SUITE_CCMP_256: - return MCU_CIPHER_CCMP_256; - case WLAN_CIPHER_SUITE_GCMP: - return MCU_CIPHER_GCMP; - case WLAN_CIPHER_SUITE_GCMP_256: - return MCU_CIPHER_GCMP_256; - case WLAN_CIPHER_SUITE_SMS4: - return MCU_CIPHER_WAPI; - default: - return MCU_CIPHER_NONE; - } -} - -static u8 mt7915_mcu_chan_bw(struct cfg80211_chan_def *chandef) -{ - static const u8 width_to_bw[] = { - [NL80211_CHAN_WIDTH_40] = CMD_CBW_40MHZ, - [NL80211_CHAN_WIDTH_80] = CMD_CBW_80MHZ, - [NL80211_CHAN_WIDTH_80P80] = CMD_CBW_8080MHZ, - [NL80211_CHAN_WIDTH_160] = CMD_CBW_160MHZ, - [NL80211_CHAN_WIDTH_5] = CMD_CBW_5MHZ, - [NL80211_CHAN_WIDTH_10] = CMD_CBW_10MHZ, - [NL80211_CHAN_WIDTH_20] = CMD_CBW_20MHZ, - [NL80211_CHAN_WIDTH_20_NOHT] = CMD_CBW_20MHZ, - }; - - if (chandef->width >= ARRAY_SIZE(width_to_bw)) - return 0; - - return width_to_bw[chandef->width]; -} - -static const struct ieee80211_sta_he_cap * -mt7915_get_he_phy_cap(struct mt7915_phy *phy, struct ieee80211_vif *vif) -{ - struct ieee80211_supported_band *sband; - enum nl80211_band band; - - band = phy->mt76->chandef.chan->band; - sband = phy->mt76->hw->wiphy->bands[band]; - - return ieee80211_get_he_iftype_cap(sband, vif->type); -} - -static u8 -mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta) -{ - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - enum nl80211_band band = mvif->phy->mt76->chandef.chan->band; - struct ieee80211_sta_ht_cap *ht_cap; - struct ieee80211_sta_vht_cap *vht_cap; - const struct ieee80211_sta_he_cap *he_cap; - u8 mode = 0; - - if (sta) { - ht_cap = &sta->ht_cap; - vht_cap = &sta->vht_cap; - he_cap = &sta->he_cap; - } else { - struct ieee80211_supported_band *sband; - - sband = mvif->phy->mt76->hw->wiphy->bands[band]; - - ht_cap = &sband->ht_cap; - vht_cap = &sband->vht_cap; - he_cap = ieee80211_get_he_iftype_cap(sband, vif->type); - } - - if (band == NL80211_BAND_2GHZ) { - mode |= PHY_MODE_B | PHY_MODE_G; - - if (ht_cap->ht_supported) - mode |= PHY_MODE_GN; - - if (he_cap && he_cap->has_he) - mode |= PHY_MODE_AX_24G; - } else if (band == NL80211_BAND_5GHZ) { - mode |= PHY_MODE_A; - - if (ht_cap->ht_supported) - mode |= PHY_MODE_AN; - - if (vht_cap->vht_supported) - mode |= PHY_MODE_AC; - - if (he_cap && he_cap->has_he) - mode |= PHY_MODE_AX_5G; - } - - return mode; -} - static u8 mt7915_mcu_get_sta_nss(u16 mcs_map) { @@ -211,24 +86,12 @@ mt7915_mcu_get_sta_nss(u16 mcs_map) static void mt7915_mcu_set_sta_he_mcs(struct ieee80211_sta *sta, __le16 *he_mcs, - const u16 *mask) + u16 mcs_map) { struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; - struct cfg80211_chan_def *chandef = &msta->vif->phy->mt76->chandef; + enum nl80211_band band = msta->vif->phy->mt76->chandef.chan->band; + const u16 *mask = msta->vif->bitrate_mask.control[band].he_mcs; int nss, max_nss = sta->rx_nss > 3 ? 4 : sta->rx_nss; - u16 mcs_map; - - switch (chandef->width) { - case NL80211_CHAN_WIDTH_80P80: - mcs_map = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_80p80); - break; - case NL80211_CHAN_WIDTH_160: - mcs_map = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_160); - break; - default: - mcs_map = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_80); - break; - } for (nss = 0; nss < max_nss; nss++) { int mcs; @@ -483,7 +346,12 @@ mt7915_mcu_rx_radar_detected(struct mt7915_dev *dev, struct sk_buff *skb) if (r->band_idx && dev->mt76.phy2) mphy = dev->mt76.phy2; - ieee80211_radar_detected(mphy->hw); + if (r->band_idx == MT_RX_SEL2) + cfg80211_background_radar_event(mphy->hw->wiphy, + &dev->rdd2_chandef, + GFP_ATOMIC); + else + ieee80211_radar_detected(mphy->hw); dev->hw_pattern++; } @@ -493,9 +361,13 @@ mt7915_mcu_rx_log_message(struct mt7915_dev *dev, struct sk_buff *skb) struct mt7915_mcu_rxd *rxd = (struct mt7915_mcu_rxd *)skb->data; const char *data = (char *)&rxd[1]; const char *type; + int len = skb->len - sizeof(*rxd); switch (rxd->s2d_index) { case 0: + if (mt7915_debugfs_rx_log(dev, data, len)) + return; + type = "WM"; break; case 2: @@ -506,8 +378,7 @@ mt7915_mcu_rx_log_message(struct mt7915_dev *dev, struct sk_buff *skb) break; } - wiphy_info(mt76_hw(dev)->wiphy, "%s: %.*s", type, - (int)(skb->len - sizeof(*rxd)), data); + wiphy_info(mt76_hw(dev)->wiphy, "%s: %.*s", type, len, data); } static void @@ -577,88 +448,6 @@ void mt7915_mcu_rx_event(struct mt7915_dev *dev, struct sk_buff *skb) mt76_mcu_rx_event(&dev->mt76, skb); } -static struct sk_buff * -mt7915_mcu_alloc_sta_req(struct mt7915_dev *dev, struct mt7915_vif *mvif, - struct mt7915_sta *msta, int len) -{ - struct sta_req_hdr hdr = { - .bss_idx = mvif->mt76.idx, - .wlan_idx_lo = msta ? to_wcid_lo(msta->wcid.idx) : 0, - .wlan_idx_hi = msta ? to_wcid_hi(msta->wcid.idx) : 0, - .muar_idx = msta && msta->wcid.sta ? mvif->mt76.omac_idx : 0xe, - .is_tlv_append = 1, - }; - struct sk_buff *skb; - - skb = mt76_mcu_msg_alloc(&dev->mt76, NULL, len); - if (!skb) - return ERR_PTR(-ENOMEM); - - skb_put_data(skb, &hdr, sizeof(hdr)); - - return skb; -} - -static struct wtbl_req_hdr * -mt7915_mcu_alloc_wtbl_req(struct mt7915_dev *dev, struct mt7915_sta *msta, - int cmd, void *sta_wtbl, struct sk_buff **skb) -{ - struct tlv *sta_hdr = sta_wtbl; - struct wtbl_req_hdr hdr = { - .wlan_idx_lo = to_wcid_lo(msta->wcid.idx), - .wlan_idx_hi = to_wcid_hi(msta->wcid.idx), - .operation = cmd, - }; - struct sk_buff *nskb = *skb; - - if (!nskb) { - nskb = mt76_mcu_msg_alloc(&dev->mt76, NULL, - MT76_CONNAC_WTBL_UPDATE_MAX_SIZE); - if (!nskb) - return ERR_PTR(-ENOMEM); - - *skb = nskb; - } - - if (sta_hdr) - le16_add_cpu(&sta_hdr->len, sizeof(hdr)); - - return skb_put_data(nskb, &hdr, sizeof(hdr)); -} - -static struct tlv * -mt7915_mcu_add_nested_tlv(struct sk_buff *skb, int tag, int len, - void *sta_ntlv, void *sta_wtbl) -{ - struct sta_ntlv_hdr *ntlv_hdr = sta_ntlv; - struct tlv *sta_hdr = sta_wtbl; - struct tlv *ptlv, tlv = { - .tag = cpu_to_le16(tag), - .len = cpu_to_le16(len), - }; - u16 ntlv; - - ptlv = skb_put(skb, len); - memcpy(ptlv, &tlv, sizeof(tlv)); - - ntlv = le16_to_cpu(ntlv_hdr->tlv_num); - ntlv_hdr->tlv_num = cpu_to_le16(ntlv + 1); - - if (sta_hdr) { - u16 size = le16_to_cpu(sta_hdr->len); - - sta_hdr->len = cpu_to_le16(size + len); - } - - return ptlv; -} - -static struct tlv * -mt7915_mcu_add_tlv(struct sk_buff *skb, int tag, int len) -{ - return mt7915_mcu_add_nested_tlv(skb, tag, len, skb->data, NULL); -} - static struct tlv * mt7915_mcu_add_nested_subtlv(struct sk_buff *skb, int sub_tag, int sub_len, __le16 *sub_ntlv, __le16 *len) @@ -678,105 +467,6 @@ mt7915_mcu_add_nested_subtlv(struct sk_buff *skb, int sub_tag, int sub_len, } /** bss info **/ -static int -mt7915_mcu_bss_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct mt7915_phy *phy, bool enable) -{ - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - struct bss_info_basic *bss; - u16 wlan_idx = mvif->sta.wcid.idx; - u32 type = NETWORK_INFRA; - struct tlv *tlv; - - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_BASIC, sizeof(*bss)); - - switch (vif->type) { - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_MONITOR: - break; - case NL80211_IFTYPE_STATION: - /* TODO: enable BSS_INFO_UAPSD & BSS_INFO_PM */ - if (enable) { - struct ieee80211_sta *sta; - struct mt7915_sta *msta; - - rcu_read_lock(); - sta = ieee80211_find_sta(vif, vif->bss_conf.bssid); - if (!sta) { - rcu_read_unlock(); - return -EINVAL; - } - - msta = (struct mt7915_sta *)sta->drv_priv; - wlan_idx = msta->wcid.idx; - rcu_read_unlock(); - } - break; - case NL80211_IFTYPE_ADHOC: - type = NETWORK_IBSS; - break; - default: - WARN_ON(1); - break; - } - - bss = (struct bss_info_basic *)tlv; - bss->network_type = cpu_to_le32(type); - bss->bmc_wcid_lo = to_wcid_lo(wlan_idx); - bss->bmc_wcid_hi = to_wcid_hi(wlan_idx); - bss->wmm_idx = mvif->mt76.wmm_idx; - bss->active = enable; - - if (vif->type != NL80211_IFTYPE_MONITOR) { - memcpy(bss->bssid, vif->bss_conf.bssid, ETH_ALEN); - bss->bcn_interval = cpu_to_le16(vif->bss_conf.beacon_int); - bss->dtim_period = vif->bss_conf.dtim_period; - bss->phy_mode = mt7915_get_phy_mode(vif, NULL); - } else { - memcpy(bss->bssid, phy->mt76->macaddr, ETH_ALEN); - } - - return 0; -} - -static void -mt7915_mcu_bss_omac_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) -{ - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - struct bss_info_omac *omac; - struct tlv *tlv; - u32 type = 0; - u8 idx; - - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_OMAC, sizeof(*omac)); - - switch (vif->type) { - case NL80211_IFTYPE_MONITOR: - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_AP: - type = CONNECTION_INFRA_AP; - break; - case NL80211_IFTYPE_STATION: - type = CONNECTION_INFRA_STA; - break; - case NL80211_IFTYPE_ADHOC: - type = CONNECTION_IBSS_ADHOC; - break; - default: - WARN_ON(1); - break; - } - - omac = (struct bss_info_omac *)tlv; - idx = mvif->mt76.omac_idx > EXT_BSSID_START ? HW_BSSID_0 - : mvif->mt76.omac_idx; - omac->conn_type = cpu_to_le32(type); - omac->omac_idx = mvif->mt76.omac_idx; - omac->band_idx = mvif->mt76.band_idx; - omac->hw_bss_idx = idx; -} - struct mt7915_he_obss_narrow_bw_ru_data { bool tolerated; }; @@ -829,12 +519,12 @@ mt7915_mcu_bss_rfch_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct tlv *tlv; int freq1 = chandef->center_freq1; - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_RF_CH, sizeof(*ch)); + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_RF_CH, sizeof(*ch)); ch = (struct bss_info_rf_ch *)tlv; ch->pri_ch = chandef->chan->hw_value; ch->center_ch0 = ieee80211_frequency_to_channel(freq1); - ch->bw = mt7915_mcu_chan_bw(chandef); + ch->bw = mt76_connac_chan_bw(chandef); if (chandef->width == NL80211_CHAN_WIDTH_80P80) { int freq2 = chandef->center_freq2; @@ -866,7 +556,7 @@ mt7915_mcu_bss_ra_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct bss_info_ra *ra; struct tlv *tlv; - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_RA, sizeof(*ra)); + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_RA, sizeof(*ra)); ra = (struct bss_info_ra *)tlv; ra->op_mode = vif->type == NL80211_IFTYPE_AP; @@ -894,9 +584,9 @@ mt7915_mcu_bss_he_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct bss_info_he *he; struct tlv *tlv; - cap = mt7915_get_he_phy_cap(phy, vif); + cap = mt76_connac_get_he_phy_cap(phy->mt76, vif); - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_HE_BASIC, sizeof(*he)); + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_HE_BASIC, sizeof(*he)); he = (struct bss_info_he *)tlv; he->he_pe_duration = vif->bss_conf.htc_trig_based_pkt_ext; @@ -920,7 +610,7 @@ mt7915_mcu_bss_hw_amsdu_tlv(struct sk_buff *skb) struct bss_info_hw_amsdu *amsdu; struct tlv *tlv; - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_HW_AMSDU, sizeof(*amsdu)); + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_HW_AMSDU, sizeof(*amsdu)); amsdu = (struct bss_info_hw_amsdu *)tlv; amsdu->cmp_bitmap_0 = cpu_to_le32(TXD_CMP_MAP1); @@ -930,26 +620,6 @@ mt7915_mcu_bss_hw_amsdu_tlv(struct sk_buff *skb) } static void -mt7915_mcu_bss_ext_tlv(struct sk_buff *skb, struct mt7915_vif *mvif) -{ -/* SIFS 20us + 512 byte beacon tranmitted by 1Mbps (3906us) */ -#define BCN_TX_ESTIMATE_TIME (4096 + 20) - struct bss_info_ext_bss *ext; - int ext_bss_idx, tsf_offset; - struct tlv *tlv; - - ext_bss_idx = mvif->mt76.omac_idx - EXT_BSSID_START; - if (ext_bss_idx < 0) - return; - - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_EXT_BSS, sizeof(*ext)); - - ext = (struct bss_info_ext_bss *)tlv; - tsf_offset = ext_bss_idx * BCN_TX_ESTIMATE_TIME; - ext->mbss_tsf_offset = cpu_to_le32(tsf_offset); -} - -static void mt7915_mcu_bss_bmc_tlv(struct sk_buff *skb, struct mt7915_phy *phy) { struct bss_info_bmc_rate *bmc; @@ -957,7 +627,7 @@ mt7915_mcu_bss_bmc_tlv(struct sk_buff *skb, struct mt7915_phy *phy) enum nl80211_band band = chandef->chan->band; struct tlv *tlv; - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_BMC_RATE, sizeof(*bmc)); + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_BMC_RATE, sizeof(*bmc)); bmc = (struct bss_info_bmc_rate *)tlv; if (band == NL80211_BAND_2GHZ) { @@ -1010,6 +680,7 @@ int mt7915_mcu_add_bss_info(struct mt7915_phy *phy, struct ieee80211_vif *vif, int enable) { struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + struct mt7915_dev *dev = phy->dev; struct sk_buff *skb; if (mvif->mt76.omac_idx >= REPEATER_BSSID_START) { @@ -1017,16 +688,17 @@ int mt7915_mcu_add_bss_info(struct mt7915_phy *phy, mt7915_mcu_muar_config(phy, vif, true, enable); } - skb = mt7915_mcu_alloc_sta_req(phy->dev, mvif, NULL, - MT7915_BSS_UPDATE_MAX_SIZE); + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, NULL, + MT7915_BSS_UPDATE_MAX_SIZE); if (IS_ERR(skb)) return PTR_ERR(skb); /* bss_omac must be first */ if (enable) - mt7915_mcu_bss_omac_tlv(skb, vif); + mt76_connac_mcu_bss_omac_tlv(skb, vif); - mt7915_mcu_bss_basic_tlv(skb, vif, phy, enable); + mt76_connac_mcu_bss_basic_tlv(skb, vif, NULL, phy->mt76, + mvif->sta.wcid.idx, enable); if (vif->type == NL80211_IFTYPE_MONITOR) goto out; @@ -1042,309 +714,48 @@ int mt7915_mcu_add_bss_info(struct mt7915_phy *phy, if (mvif->mt76.omac_idx >= EXT_BSSID_START && mvif->mt76.omac_idx < REPEATER_BSSID_START) - mt7915_mcu_bss_ext_tlv(skb, mvif); + mt76_connac_mcu_bss_ext_tlv(skb, &mvif->mt76); } out: - return mt76_mcu_skb_send_msg(&phy->dev->mt76, skb, + return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD(BSS_INFO_UPDATE), true); } /** starec & wtbl **/ -static int -mt7915_mcu_sta_key_tlv(struct mt7915_sta *msta, struct sk_buff *skb, - struct ieee80211_key_conf *key, enum set_key_cmd cmd) -{ - struct mt7915_sta_key_conf *bip = &msta->bip; - struct sta_rec_sec *sec; - struct tlv *tlv; - u32 len = sizeof(*sec); - - tlv = mt7915_mcu_add_tlv(skb, STA_REC_KEY_V2, sizeof(*sec)); - - sec = (struct sta_rec_sec *)tlv; - sec->add = cmd; - - if (cmd == SET_KEY) { - struct sec_key *sec_key; - u8 cipher; - - cipher = mt7915_mcu_get_cipher(key->cipher); - if (cipher == MCU_CIPHER_NONE) - return -EOPNOTSUPP; - - sec_key = &sec->key[0]; - sec_key->cipher_len = sizeof(*sec_key); - - if (cipher == MCU_CIPHER_BIP_CMAC_128) { - sec_key->cipher_id = MCU_CIPHER_AES_CCMP; - sec_key->key_id = bip->keyidx; - sec_key->key_len = 16; - memcpy(sec_key->key, bip->key, 16); - - sec_key = &sec->key[1]; - sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128; - sec_key->cipher_len = sizeof(*sec_key); - sec_key->key_len = 16; - memcpy(sec_key->key, key->key, 16); - - sec->n_cipher = 2; - } else { - sec_key->cipher_id = cipher; - sec_key->key_id = key->keyidx; - sec_key->key_len = key->keylen; - memcpy(sec_key->key, key->key, key->keylen); - - if (cipher == MCU_CIPHER_TKIP) { - /* Rx/Tx MIC keys are swapped */ - memcpy(sec_key->key + 16, key->key + 24, 8); - memcpy(sec_key->key + 24, key->key + 16, 8); - } - - /* store key_conf for BIP batch update */ - if (cipher == MCU_CIPHER_AES_CCMP) { - memcpy(bip->key, key->key, key->keylen); - bip->keyidx = key->keyidx; - } - - len -= sizeof(*sec_key); - sec->n_cipher = 1; - } - } else { - len -= sizeof(sec->key); - sec->n_cipher = 0; - } - sec->len = cpu_to_le16(len); - - return 0; -} - -int mt7915_mcu_add_key(struct mt7915_dev *dev, struct ieee80211_vif *vif, - struct mt7915_sta *msta, struct ieee80211_key_conf *key, - enum set_key_cmd cmd) -{ - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - struct sk_buff *skb; - int len = sizeof(struct sta_req_hdr) + sizeof(struct sta_rec_sec); - int ret; - - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, len); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - ret = mt7915_mcu_sta_key_tlv(msta, skb, key, cmd); - if (ret) - return ret; - - return mt76_mcu_skb_send_msg(&dev->mt76, skb, - MCU_EXT_CMD(STA_REC_UPDATE), true); -} - -static void -mt7915_mcu_sta_ba_tlv(struct sk_buff *skb, - struct ieee80211_ampdu_params *params, - bool enable, bool tx) -{ - struct sta_rec_ba *ba; - struct tlv *tlv; - - tlv = mt7915_mcu_add_tlv(skb, STA_REC_BA, sizeof(*ba)); - - ba = (struct sta_rec_ba *)tlv; - ba->ba_type = tx ? MT_BA_TYPE_ORIGINATOR : MT_BA_TYPE_RECIPIENT; - ba->winsize = cpu_to_le16(params->buf_size); - ba->ssn = cpu_to_le16(params->ssn); - ba->ba_en = enable << params->tid; - ba->amsdu = params->amsdu; - ba->tid = params->tid; -} - -static void -mt7915_mcu_wtbl_ba_tlv(struct sk_buff *skb, - struct ieee80211_ampdu_params *params, - bool enable, bool tx, void *sta_wtbl, - void *wtbl_tlv) -{ - struct wtbl_ba *ba; - struct tlv *tlv; - - tlv = mt7915_mcu_add_nested_tlv(skb, WTBL_BA, sizeof(*ba), - wtbl_tlv, sta_wtbl); - - ba = (struct wtbl_ba *)tlv; - ba->tid = params->tid; - - if (tx) { - ba->ba_type = MT_BA_TYPE_ORIGINATOR; - ba->sn = enable ? cpu_to_le16(params->ssn) : 0; - ba->ba_en = enable; - } else { - memcpy(ba->peer_addr, params->sta->addr, ETH_ALEN); - ba->ba_type = MT_BA_TYPE_RECIPIENT; - ba->rst_ba_tid = params->tid; - ba->rst_ba_sel = RST_BA_MAC_TID_MATCH; - ba->rst_ba_sb = 1; - } - - if (enable) - ba->ba_winsize = cpu_to_le16(params->buf_size); -} - -static int -mt7915_mcu_sta_ba(struct mt7915_dev *dev, - struct ieee80211_ampdu_params *params, - bool enable, bool tx) +int mt7915_mcu_add_tx_ba(struct mt7915_dev *dev, + struct ieee80211_ampdu_params *params, + bool enable) { struct mt7915_sta *msta = (struct mt7915_sta *)params->sta->drv_priv; struct mt7915_vif *mvif = msta->vif; - struct wtbl_req_hdr *wtbl_hdr; - struct tlv *sta_wtbl; - struct sk_buff *skb; - int ret; - if (enable && tx && !params->amsdu) + if (enable && !params->amsdu) msta->wcid.amsdu = false; - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, - MT76_CONNAC_STA_UPDATE_MAX_SIZE); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - sta_wtbl = mt7915_mcu_add_tlv(skb, STA_REC_WTBL, sizeof(struct tlv)); - - wtbl_hdr = mt7915_mcu_alloc_wtbl_req(dev, msta, WTBL_SET, sta_wtbl, - &skb); - if (IS_ERR(wtbl_hdr)) - return PTR_ERR(wtbl_hdr); - - mt7915_mcu_wtbl_ba_tlv(skb, params, enable, tx, sta_wtbl, wtbl_hdr); - - ret = mt76_mcu_skb_send_msg(&dev->mt76, skb, - MCU_EXT_CMD(STA_REC_UPDATE), true); - if (ret) - return ret; - - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, - MT76_CONNAC_STA_UPDATE_MAX_SIZE); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - mt7915_mcu_sta_ba_tlv(skb, params, enable, tx); - - return mt76_mcu_skb_send_msg(&dev->mt76, skb, - MCU_EXT_CMD(STA_REC_UPDATE), true); -} - -int mt7915_mcu_add_tx_ba(struct mt7915_dev *dev, - struct ieee80211_ampdu_params *params, - bool enable) -{ - return mt7915_mcu_sta_ba(dev, params, enable, true); + return mt76_connac_mcu_sta_ba(&dev->mt76, &mvif->mt76, params, + MCU_EXT_CMD(STA_REC_UPDATE), + enable, true); } int mt7915_mcu_add_rx_ba(struct mt7915_dev *dev, struct ieee80211_ampdu_params *params, bool enable) { - return mt7915_mcu_sta_ba(dev, params, enable, false); -} - -static void -mt7915_mcu_wtbl_generic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, void *sta_wtbl, - void *wtbl_tlv) -{ - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - struct wtbl_generic *generic; - struct wtbl_rx *rx; - struct tlv *tlv; - - tlv = mt7915_mcu_add_nested_tlv(skb, WTBL_GENERIC, sizeof(*generic), - wtbl_tlv, sta_wtbl); - - generic = (struct wtbl_generic *)tlv; - - if (sta) { - memcpy(generic->peer_addr, sta->addr, ETH_ALEN); - generic->partial_aid = cpu_to_le16(sta->aid); - generic->muar_idx = mvif->mt76.omac_idx; - generic->qos = sta->wme; - } else { - /* use BSSID in station mode */ - if (vif->type == NL80211_IFTYPE_STATION) - memcpy(generic->peer_addr, vif->bss_conf.bssid, - ETH_ALEN); - else - eth_broadcast_addr(generic->peer_addr); - - generic->muar_idx = 0xe; - } - - tlv = mt7915_mcu_add_nested_tlv(skb, WTBL_RX, sizeof(*rx), - wtbl_tlv, sta_wtbl); - - rx = (struct wtbl_rx *)tlv; - rx->rca1 = sta ? vif->type != NL80211_IFTYPE_AP : 1; - rx->rca2 = 1; - rx->rv = 1; -} - -static void -mt7915_mcu_sta_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, bool enable) -{ -#define EXTRA_INFO_VER BIT(0) -#define EXTRA_INFO_NEW BIT(1) - struct sta_rec_basic *basic; - struct tlv *tlv; - - tlv = mt7915_mcu_add_tlv(skb, STA_REC_BASIC, sizeof(*basic)); - - basic = (struct sta_rec_basic *)tlv; - basic->extra_info = cpu_to_le16(EXTRA_INFO_VER); - - if (enable) { - basic->extra_info |= cpu_to_le16(EXTRA_INFO_NEW); - basic->conn_state = CONN_STATE_PORT_SECURE; - } else { - basic->conn_state = CONN_STATE_DISCONNECT; - } - - if (!sta) { - basic->conn_type = cpu_to_le32(CONNECTION_INFRA_BC); - eth_broadcast_addr(basic->peer_addr); - return; - } - - switch (vif->type) { - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_AP: - basic->conn_type = cpu_to_le32(CONNECTION_INFRA_STA); - break; - case NL80211_IFTYPE_STATION: - basic->conn_type = cpu_to_le32(CONNECTION_INFRA_AP); - break; - case NL80211_IFTYPE_ADHOC: - basic->conn_type = cpu_to_le32(CONNECTION_IBSS_ADHOC); - break; - default: - WARN_ON(1); - break; - } + struct mt7915_sta *msta = (struct mt7915_sta *)params->sta->drv_priv; + struct mt7915_vif *mvif = msta->vif; - memcpy(basic->peer_addr, sta->addr, ETH_ALEN); - basic->aid = cpu_to_le16(sta->aid); - basic->qos = sta->wme; + return mt76_connac_mcu_sta_ba(&dev->mt76, &mvif->mt76, params, + MCU_EXT_CMD(STA_REC_UPDATE), + enable, false); } static void mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, struct ieee80211_vif *vif) { - struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; struct ieee80211_he_cap_elem *elem = &sta->he_cap.he_cap_elem; - enum nl80211_band band = msta->vif->phy->mt76->chandef.chan->band; - const u16 *mcs_mask = msta->vif->bitrate_mask.control[band].he_mcs; + struct ieee80211_he_mcs_nss_supp mcs_map; struct sta_rec_he *he; struct tlv *tlv; u32 cap = 0; @@ -1352,7 +763,7 @@ mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, if (!sta->he_cap.has_he) return; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_HE, sizeof(*he)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HE, sizeof(*he)); he = (struct sta_rec_he *)tlv; @@ -1434,22 +845,23 @@ mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, he->he_cap = cpu_to_le32(cap); + mcs_map = sta->he_cap.he_mcs_nss_supp; switch (sta->bandwidth) { case IEEE80211_STA_RX_BW_160: if (elem->phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) mt7915_mcu_set_sta_he_mcs(sta, &he->max_nss_mcs[CMD_HE_MCS_BW8080], - mcs_mask); + le16_to_cpu(mcs_map.rx_mcs_80p80)); mt7915_mcu_set_sta_he_mcs(sta, &he->max_nss_mcs[CMD_HE_MCS_BW160], - mcs_mask); + le16_to_cpu(mcs_map.rx_mcs_160)); fallthrough; default: mt7915_mcu_set_sta_he_mcs(sta, &he->max_nss_mcs[CMD_HE_MCS_BW80], - mcs_mask); + le16_to_cpu(mcs_map.rx_mcs_80)); break; } @@ -1480,38 +892,6 @@ mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, } static void -mt7915_mcu_sta_uapsd_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, - struct ieee80211_vif *vif) -{ - struct sta_rec_uapsd *uapsd; - struct tlv *tlv; - - if (vif->type != NL80211_IFTYPE_AP || !sta->wme) - return; - - tlv = mt7915_mcu_add_tlv(skb, STA_REC_APPS, sizeof(*uapsd)); - uapsd = (struct sta_rec_uapsd *)tlv; - - if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO) { - uapsd->dac_map |= BIT(3); - uapsd->tac_map |= BIT(3); - } - if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI) { - uapsd->dac_map |= BIT(2); - uapsd->tac_map |= BIT(2); - } - if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE) { - uapsd->dac_map |= BIT(1); - uapsd->tac_map |= BIT(1); - } - if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK) { - uapsd->dac_map |= BIT(0); - uapsd->tac_map |= BIT(0); - } - uapsd->max_sp = sta->max_sp; -} - -static void mt7915_mcu_sta_muru_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, struct ieee80211_vif *vif) { @@ -1527,7 +907,7 @@ mt7915_mcu_sta_muru_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, if (!sta->vht_cap.vht_supported) return; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_MURU, sizeof(*muru)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_MURU, sizeof(*muru)); muru = (struct sta_rec_muru *)tlv; @@ -1574,7 +954,7 @@ mt7915_mcu_sta_ht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) struct sta_rec_ht *ht; struct tlv *tlv; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_HT, sizeof(*ht)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HT, sizeof(*ht)); ht = (struct sta_rec_ht *)tlv; ht->ht_cap = cpu_to_le16(sta->ht_cap.cap); @@ -1589,7 +969,7 @@ mt7915_mcu_sta_vht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) if (!sta->vht_cap.vht_supported) return; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_VHT, sizeof(*vht)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_VHT, sizeof(*vht)); vht = (struct sta_rec_vht *)tlv; vht->vht_cap = cpu_to_le32(sta->vht_cap.cap); @@ -1598,8 +978,8 @@ mt7915_mcu_sta_vht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) } static void -mt7915_mcu_sta_amsdu_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) +mt7915_mcu_sta_amsdu_tlv(struct mt7915_dev *dev, struct sk_buff *skb, + struct ieee80211_vif *vif, struct ieee80211_sta *sta) { struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; struct sta_rec_amsdu *amsdu; @@ -1612,96 +992,27 @@ mt7915_mcu_sta_amsdu_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, if (!sta->max_amsdu_len) return; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_HW_AMSDU, sizeof(*amsdu)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HW_AMSDU, sizeof(*amsdu)); amsdu = (struct sta_rec_amsdu *)tlv; amsdu->max_amsdu_num = 8; amsdu->amsdu_en = true; - amsdu->max_mpdu_size = sta->max_amsdu_len >= - IEEE80211_MAX_MPDU_LEN_VHT_7991; msta->wcid.amsdu = true; -} - -static void -mt7915_mcu_wtbl_smps_tlv(struct sk_buff *skb, struct ieee80211_sta *sta, - void *sta_wtbl, void *wtbl_tlv) -{ - struct wtbl_smps *smps; - struct tlv *tlv; - - tlv = mt7915_mcu_add_nested_tlv(skb, WTBL_SMPS, sizeof(*smps), - wtbl_tlv, sta_wtbl); - smps = (struct wtbl_smps *)tlv; - smps->smps = (sta->smps_mode == IEEE80211_SMPS_DYNAMIC); -} - -static void -mt7915_mcu_wtbl_ht_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, void *sta_wtbl, - void *wtbl_tlv) -{ - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - struct wtbl_ht *ht = NULL; - struct tlv *tlv; - /* wtbl ht */ - if (sta->ht_cap.ht_supported) { - tlv = mt7915_mcu_add_nested_tlv(skb, WTBL_HT, sizeof(*ht), - wtbl_tlv, sta_wtbl); - ht = (struct wtbl_ht *)tlv; - ht->ldpc = mvif->cap.ldpc && - (sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING); - ht->af = sta->ht_cap.ampdu_factor; - ht->mm = sta->ht_cap.ampdu_density; - ht->ht = true; - } - - /* wtbl vht */ - if (sta->vht_cap.vht_supported) { - struct wtbl_vht *vht; - u8 af; - - tlv = mt7915_mcu_add_nested_tlv(skb, WTBL_VHT, sizeof(*vht), - wtbl_tlv, sta_wtbl); - vht = (struct wtbl_vht *)tlv; - vht->ldpc = mvif->cap.ldpc && - (sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC); - vht->vht = true; - - af = FIELD_GET(IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK, - sta->vht_cap.cap); - if (ht) - ht->af = max_t(u8, ht->af, af); - } - - mt7915_mcu_wtbl_smps_tlv(skb, sta, sta_wtbl, wtbl_tlv); -} - -static void -mt7915_mcu_wtbl_hdr_trans_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - void *sta_wtbl, void *wtbl_tlv) -{ - struct mt7915_sta *msta; - struct wtbl_hdr_trans *htr = NULL; - struct tlv *tlv; - - tlv = mt7915_mcu_add_nested_tlv(skb, WTBL_HDR_TRANS, sizeof(*htr), - wtbl_tlv, sta_wtbl); - htr = (struct wtbl_hdr_trans *)tlv; - htr->no_rx_trans = true; - if (vif->type == NL80211_IFTYPE_STATION) - htr->to_ds = true; - else - htr->from_ds = true; - - if (!sta) + switch (sta->max_amsdu_len) { + case IEEE80211_MAX_MPDU_LEN_VHT_11454: + if (!is_mt7915(&dev->mt76)) { + amsdu->max_mpdu_size = + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454; + return; + } + fallthrough; + case IEEE80211_MAX_MPDU_LEN_HT_7935: + case IEEE80211_MAX_MPDU_LEN_VHT_7991: + amsdu->max_mpdu_size = IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991; + return; + default: + amsdu->max_mpdu_size = IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895; return; - - msta = (struct mt7915_sta *)sta->drv_priv; - htr->no_rx_trans = !test_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags); - if (test_bit(MT_WCID_FLAG_4ADDR, &msta->wcid.flags)) { - htr->to_ds = true; - htr->from_ds = true; } } @@ -1712,48 +1023,29 @@ mt7915_mcu_sta_wtbl_tlv(struct mt7915_dev *dev, struct sk_buff *skb, struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; struct mt7915_sta *msta; struct wtbl_req_hdr *wtbl_hdr; + struct mt76_wcid *wcid; struct tlv *tlv; msta = sta ? (struct mt7915_sta *)sta->drv_priv : &mvif->sta; + wcid = sta ? &msta->wcid : NULL; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_WTBL, sizeof(struct tlv)); - wtbl_hdr = mt7915_mcu_alloc_wtbl_req(dev, msta, WTBL_RESET_AND_SET, - tlv, &skb); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_WTBL, sizeof(struct tlv)); + wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(&dev->mt76, &msta->wcid, + WTBL_RESET_AND_SET, tlv, + &skb); if (IS_ERR(wtbl_hdr)) return PTR_ERR(wtbl_hdr); - mt7915_mcu_wtbl_generic_tlv(skb, vif, sta, tlv, wtbl_hdr); - mt7915_mcu_wtbl_hdr_trans_tlv(skb, vif, sta, tlv, wtbl_hdr); - + mt76_connac_mcu_wtbl_generic_tlv(&dev->mt76, skb, vif, sta, tlv, + wtbl_hdr); + mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, vif, wcid, tlv, wtbl_hdr); if (sta) - mt7915_mcu_wtbl_ht_tlv(skb, vif, sta, tlv, wtbl_hdr); + mt76_connac_mcu_wtbl_ht_tlv(&dev->mt76, skb, sta, tlv, + wtbl_hdr, mvif->cap.ldpc); return 0; } -int mt7915_mcu_sta_update_hdr_trans(struct mt7915_dev *dev, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta) -{ - struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; - struct wtbl_req_hdr *wtbl_hdr; - struct sk_buff *skb; - - skb = mt76_mcu_msg_alloc(&dev->mt76, NULL, - MT76_CONNAC_WTBL_UPDATE_MAX_SIZE); - if (!skb) - return -ENOMEM; - - wtbl_hdr = mt7915_mcu_alloc_wtbl_req(dev, msta, WTBL_SET, NULL, &skb); - if (IS_ERR(wtbl_hdr)) - return PTR_ERR(wtbl_hdr); - - mt7915_mcu_wtbl_hdr_trans_tlv(skb, vif, sta, NULL, wtbl_hdr); - - return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD(WTBL_UPDATE), - true); -} - static inline bool mt7915_is_ebf_supported(struct mt7915_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool bfee) @@ -1870,7 +1162,8 @@ mt7915_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif, { struct ieee80211_sta_he_cap *pc = &sta->he_cap; struct ieee80211_he_cap_elem *pe = &pc->he_cap_elem; - const struct ieee80211_sta_he_cap *vc = mt7915_get_he_phy_cap(phy, vif); + const struct ieee80211_sta_he_cap *vc = + mt76_connac_get_he_phy_cap(phy->mt76, vif); const struct ieee80211_he_cap_elem *ve = &vc->he_cap_elem; u16 mcs_map = le16_to_cpu(pc->he_mcs_nss_supp.rx_mcs_80); u8 nss_mcs = mt7915_mcu_get_sta_nss(mcs_map); @@ -1945,7 +1238,7 @@ mt7915_mcu_sta_bfer_tlv(struct mt7915_dev *dev, struct sk_buff *skb, if (!ebf && !dev->ibf) return; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_BF, sizeof(*bf)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_BF, sizeof(*bf)); bf = (struct sta_rec_bf *)tlv; /* he: eBF only, in accordance with spec @@ -2005,7 +1298,7 @@ mt7915_mcu_sta_bfee_tlv(struct mt7915_dev *dev, struct sk_buff *skb, if (!mt7915_is_ebf_supported(phy, vif, sta, true)) return; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_BFEE, sizeof(*bfee)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_BFEE, sizeof(*bfee)); bfee = (struct sta_rec_bfee *)tlv; if (sta->he_cap.has_he) { @@ -2050,13 +1343,13 @@ int mt7915_mcu_set_fixed_rate_ctrl(struct mt7915_dev *dev, struct sta_rec_ra_fixed *ra; struct sk_buff *skb; struct tlv *tlv; - int len = sizeof(struct sta_req_hdr) + sizeof(*ra); - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, len); + skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + &msta->wcid); if (IS_ERR(skb)) return PTR_ERR(skb); - tlv = mt7915_mcu_add_tlv(skb, STA_REC_RA_UPDATE, sizeof(*ra)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA_UPDATE, sizeof(*ra)); ra = (struct sta_rec_ra_fixed *)tlv; switch (field) { @@ -2091,19 +1384,19 @@ int mt7915_mcu_add_smps(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct sk_buff *skb; int ret; - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, - MT76_CONNAC_STA_UPDATE_MAX_SIZE); + skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + &msta->wcid); if (IS_ERR(skb)) return PTR_ERR(skb); - sta_wtbl = mt7915_mcu_add_tlv(skb, STA_REC_WTBL, sizeof(struct tlv)); - - wtbl_hdr = mt7915_mcu_alloc_wtbl_req(dev, msta, WTBL_SET, sta_wtbl, - &skb); + sta_wtbl = mt76_connac_mcu_add_tlv(skb, STA_REC_WTBL, + sizeof(struct tlv)); + wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(&dev->mt76, &msta->wcid, + WTBL_SET, sta_wtbl, &skb); if (IS_ERR(wtbl_hdr)) return PTR_ERR(wtbl_hdr); - mt7915_mcu_wtbl_smps_tlv(skb, sta, sta_wtbl, wtbl_hdr); + mt76_connac_mcu_wtbl_smps_tlv(skb, sta, sta_wtbl, wtbl_hdr); ret = mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD(STA_REC_UPDATE), true); @@ -2134,9 +1427,12 @@ mt7915_mcu_add_rate_ctrl_fixed(struct mt7915_dev *dev, phy.sgi |= gi << (i << (_he)); \ phy.he_ltf |= mask->control[band].he_ltf << (i << (_he));\ } \ - for (i = 0; i < ARRAY_SIZE(mask->control[band]._mcs); i++) \ - nrates += hweight16(mask->control[band]._mcs[i]); \ - phy.mcs = ffs(mask->control[band]._mcs[0]) - 1; \ + for (i = 0; i < ARRAY_SIZE(mask->control[band]._mcs); i++) { \ + if (!mask->control[band]._mcs[i]) \ + continue; \ + nrates += hweight16(mask->control[band]._mcs[i]); \ + phy.mcs = ffs(mask->control[band]._mcs[i]) - 1; \ + } \ } while (0) if (sta->he_cap.has_he) { @@ -2204,7 +1500,8 @@ mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - struct cfg80211_chan_def *chandef = &mvif->phy->mt76->chandef; + struct mt76_phy *mphy = mvif->phy->mt76; + struct cfg80211_chan_def *chandef = &mphy->chandef; struct cfg80211_bitrate_mask *mask = &mvif->bitrate_mask; enum nl80211_band band = chandef->chan->band; struct sta_rec_ra *ra; @@ -2212,12 +1509,12 @@ mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev, u32 supp_rate = sta->supp_rates[band]; u32 cap = sta->wme ? STA_CAP_WMM : 0; - tlv = mt7915_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra)); + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra)); ra = (struct sta_rec_ra *)tlv; ra->valid = true; ra->auto_rate = true; - ra->phy_mode = mt7915_get_phy_mode(vif, sta); + ra->phy_mode = mt76_connac_get_phy_mode(mphy, vif, band, sta); ra->channel = chandef->chan->hw_value; ra->bw = sta->bandwidth; ra->phy.bw = sta->bandwidth; @@ -2304,8 +1601,8 @@ int mt7915_mcu_add_rate_ctrl(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct sk_buff *skb; int ret; - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, - MT76_CONNAC_STA_UPDATE_MAX_SIZE); + skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + &msta->wcid); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -2371,13 +1668,13 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, msta = sta ? (struct mt7915_sta *)sta->drv_priv : &mvif->sta; - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, - MT76_CONNAC_STA_UPDATE_MAX_SIZE); + skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + &msta->wcid); if (IS_ERR(skb)) return PTR_ERR(skb); /* starec basic */ - mt7915_mcu_sta_basic_tlv(skb, vif, sta, enable); + mt76_connac_mcu_sta_basic_tlv(skb, vif, sta, enable, true); if (!enable) goto out; @@ -2390,16 +1687,18 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, /* starec vht */ mt7915_mcu_sta_vht_tlv(skb, sta); /* starec uapsd */ - mt7915_mcu_sta_uapsd_tlv(skb, sta, vif); + mt76_connac_mcu_sta_uapsd(skb, vif, sta); } ret = mt7915_mcu_sta_wtbl_tlv(dev, skb, vif, sta); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } if (sta && sta->ht_cap.ht_supported) { /* starec amsdu */ - mt7915_mcu_sta_amsdu_tlv(skb, vif, sta); + mt7915_mcu_sta_amsdu_tlv(dev, skb, vif, sta); /* starec he */ mt7915_mcu_sta_he_tlv(skb, sta, vif); /* starec muru */ @@ -2409,8 +1708,10 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, } ret = mt7915_mcu_add_group(dev, vif, sta); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } out: return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD(STA_REC_UPDATE), true); @@ -2571,7 +1872,7 @@ mt7915_mcu_beacon_check_caps(struct mt7915_phy *phy, struct ieee80211_vif *vif, mgmt->u.beacon.variable, len); if (ie && ie[1] >= sizeof(*he) + 1) { const struct ieee80211_sta_he_cap *pc = - mt7915_get_he_phy_cap(phy, vif); + mt76_connac_get_he_phy_cap(phy->mt76, vif); const struct ieee80211_he_cap_elem *pe = &pc->he_cap_elem; he = (void *)(ie + 3); @@ -2602,11 +1903,12 @@ int mt7915_mcu_add_beacon(struct ieee80211_hw *hw, struct bss_info_bcn *bcn; int len = MT7915_BEACON_UPDATE_SIZE + MAX_BEACON_SIZE; - rskb = mt7915_mcu_alloc_sta_req(dev, mvif, NULL, len); + rskb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + NULL, len); if (IS_ERR(rskb)) return PTR_ERR(rskb); - tlv = mt7915_mcu_add_tlv(rskb, BSS_INFO_OFFLOAD, sizeof(*bcn)); + tlv = mt76_connac_mcu_add_tlv(rskb, BSS_INFO_OFFLOAD, sizeof(*bcn)); bcn = (struct bss_info_bcn *)tlv; bcn->enable = en; @@ -2640,100 +1942,30 @@ out: MCU_EXT_CMD(BSS_INFO_UPDATE), true); } -static int mt7915_mcu_start_firmware(struct mt7915_dev *dev, u32 addr, - u32 option) -{ - struct { - __le32 option; - __le32 addr; - } req = { - .option = cpu_to_le32(option), - .addr = cpu_to_le32(addr), - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_CMD(FW_START_REQ), &req, - sizeof(req), true); -} - -static int mt7915_mcu_restart(struct mt76_dev *dev) -{ - struct { - u8 power_mode; - u8 rsv[3]; - } req = { - .power_mode = 1, - }; - - return mt76_mcu_send_msg(dev, MCU_CMD(NIC_POWER_CTRL), &req, - sizeof(req), false); -} - -static int mt7915_mcu_patch_sem_ctrl(struct mt7915_dev *dev, bool get) +static int mt7915_driver_own(struct mt7915_dev *dev, u8 band) { - struct { - __le32 op; - } req = { - .op = cpu_to_le32(get ? PATCH_SEM_GET : PATCH_SEM_RELEASE), - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_CMD(PATCH_SEM_CONTROL), &req, - sizeof(req), true); -} - -static int mt7915_mcu_start_patch(struct mt7915_dev *dev) -{ - struct { - u8 check_crc; - u8 reserved[3]; - } req = { - .check_crc = 0, - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_CMD(PATCH_FINISH_REQ), &req, - sizeof(req), true); -} - -static int mt7915_driver_own(struct mt7915_dev *dev) -{ - mt76_wr(dev, MT_TOP_LPCR_HOST_BAND0, MT_TOP_LPCR_HOST_DRV_OWN); - if (!mt76_poll_msec(dev, MT_TOP_LPCR_HOST_BAND0, - MT_TOP_LPCR_HOST_FW_OWN, 0, 500)) { + mt76_wr(dev, MT_TOP_LPCR_HOST_BAND(band), MT_TOP_LPCR_HOST_DRV_OWN); + if (!mt76_poll_msec(dev, MT_TOP_LPCR_HOST_BAND(band), + MT_TOP_LPCR_HOST_FW_OWN_STAT, 0, 500)) { dev_err(dev->mt76.dev, "Timeout for driver own\n"); return -EIO; } - return 0; -} - -static int mt7915_mcu_init_download(struct mt7915_dev *dev, u32 addr, - u32 len, u32 mode) -{ - struct { - __le32 addr; - __le32 len; - __le32 mode; - } req = { - .addr = cpu_to_le32(addr), - .len = cpu_to_le32(len), - .mode = cpu_to_le32(mode), - }; - int attr; - - if (req.addr == cpu_to_le32(MCU_PATCH_ADDRESS)) - attr = MCU_CMD(PATCH_START_REQ); - else - attr = MCU_CMD(TARGET_ADDRESS_LEN_REQ); + /* clear irq when the driver own success */ + mt76_wr(dev, MT_TOP_LPCR_HOST_BAND_IRQ_STAT(band), + MT_TOP_LPCR_HOST_BAND_STAT); - return mt76_mcu_send_msg(&dev->mt76, attr, &req, sizeof(req), true); + return 0; } static int mt7915_load_patch(struct mt7915_dev *dev) { const struct mt7915_patch_hdr *hdr; const struct firmware *fw = NULL; + const char *patch; int i, ret, sem; - sem = mt7915_mcu_patch_sem_ctrl(dev, 1); + sem = mt76_connac_mcu_patch_sem_ctrl(&dev->mt76, 1); switch (sem) { case PATCH_IS_DL: return 0; @@ -2744,7 +1976,8 @@ static int mt7915_load_patch(struct mt7915_dev *dev) return -EAGAIN; } - ret = request_firmware(&fw, MT7915_ROM_PATCH, dev->mt76.dev); + patch = is_mt7915(&dev->mt76) ? MT7915_ROM_PATCH : MT7916_ROM_PATCH; + ret = request_firmware(&fw, patch, dev->mt76.dev); if (ret) goto out; @@ -2776,8 +2009,8 @@ static int mt7915_load_patch(struct mt7915_dev *dev) len = be32_to_cpu(sec->info.len); dl = fw->data + be32_to_cpu(sec->offs); - ret = mt7915_mcu_init_download(dev, addr, len, - DL_MODE_NEED_RSP); + ret = mt76_connac_mcu_init_download(&dev->mt76, addr, len, + DL_MODE_NEED_RSP); if (ret) { dev_err(dev->mt76.dev, "Download request failed\n"); goto out; @@ -2791,12 +2024,12 @@ static int mt7915_load_patch(struct mt7915_dev *dev) } } - ret = mt7915_mcu_start_patch(dev); + ret = mt76_connac_mcu_start_patch(&dev->mt76); if (ret) dev_err(dev->mt76.dev, "Failed to start patch\n"); out: - sem = mt7915_mcu_patch_sem_ctrl(dev, 0); + sem = mt76_connac_mcu_patch_sem_ctrl(&dev->mt76, 0); switch (sem) { case PATCH_REL_SEM_SUCCESS: break; @@ -2810,20 +2043,6 @@ out: return ret; } -static u32 mt7915_mcu_gen_dl_mode(u8 feature_set, bool is_wa) -{ - u32 ret = 0; - - ret |= (feature_set & FW_FEATURE_SET_ENCRYPT) ? - (DL_MODE_ENCRYPT | DL_MODE_RESET_SEC_IV) : 0; - ret |= FIELD_PREP(DL_MODE_KEY_IDX, - FIELD_GET(FW_FEATURE_SET_KEY_IDX, feature_set)); - ret |= DL_MODE_NEED_RSP; - ret |= is_wa ? DL_MODE_WORKING_PDA_CR4 : 0; - - return ret; -} - static int mt7915_mcu_send_ram_firmware(struct mt7915_dev *dev, const struct mt7915_fw_trailer *hdr, @@ -2839,14 +2058,16 @@ mt7915_mcu_send_ram_firmware(struct mt7915_dev *dev, region = (const struct mt7915_fw_region *)((const u8 *)hdr - (hdr->n_region - i) * sizeof(*region)); - mode = mt7915_mcu_gen_dl_mode(region->feature_set, is_wa); + mode = mt76_connac_mcu_gen_dl_mode(&dev->mt76, + region->feature_set, is_wa); len = le32_to_cpu(region->len); addr = le32_to_cpu(region->addr); if (region->feature_set & FW_FEATURE_OVERRIDE_ADDR) override = addr; - err = mt7915_mcu_init_download(dev, addr, len, mode); + err = mt76_connac_mcu_init_download(&dev->mt76, addr, len, + mode); if (err) { dev_err(dev->mt76.dev, "Download request failed\n"); return err; @@ -2868,16 +2089,18 @@ mt7915_mcu_send_ram_firmware(struct mt7915_dev *dev, if (is_wa) option |= FW_START_WORKING_PDA_CR4; - return mt7915_mcu_start_firmware(dev, override, option); + return mt76_connac_mcu_start_firmware(&dev->mt76, override, option); } static int mt7915_load_ram(struct mt7915_dev *dev) { const struct mt7915_fw_trailer *hdr; const struct firmware *fw; + const char *mcu; int ret; - ret = request_firmware(&fw, MT7915_FIRMWARE_WM, dev->mt76.dev); + mcu = is_mt7915(&dev->mt76) ? MT7915_FIRMWARE_WM : MT7916_FIRMWARE_WM; + ret = request_firmware(&fw, mcu, dev->mt76.dev); if (ret) return ret; @@ -2901,7 +2124,8 @@ static int mt7915_load_ram(struct mt7915_dev *dev) release_firmware(fw); - ret = request_firmware(&fw, MT7915_FIRMWARE_WA, dev->mt76.dev); + mcu = is_mt7915(&dev->mt76) ? MT7915_FIRMWARE_WA : MT7916_FIRMWARE_WA; + ret = request_firmware(&fw, mcu, dev->mt76.dev); if (ret) return ret; @@ -2933,10 +2157,36 @@ out: return ret; } +static int +mt7915_firmware_state(struct mt7915_dev *dev, bool wa) +{ + u32 state = FIELD_PREP(MT_TOP_MISC_FW_STATE, + wa ? FW_STATE_RDY : FW_STATE_FW_DOWNLOAD); + + if (!mt76_poll_msec(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE, + state, 1000)) { + dev_err(dev->mt76.dev, "Timeout for initializing firmware\n"); + return -EIO; + } + return 0; +} + static int mt7915_load_firmware(struct mt7915_dev *dev) { int ret; + /* make sure fw is download state */ + if (mt7915_firmware_state(dev, false)) { + /* restart firmware once */ + __mt76_mcu_restart(&dev->mt76); + ret = mt7915_firmware_state(dev, false); + if (ret) { + dev_err(dev->mt76.dev, + "Firmware is not ready for download\n"); + return ret; + } + } + ret = mt7915_load_patch(dev); if (ret) return ret; @@ -2945,12 +2195,9 @@ static int mt7915_load_firmware(struct mt7915_dev *dev) if (ret) return ret; - if (!mt76_poll_msec(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE, - FIELD_PREP(MT_TOP_MISC_FW_STATE, - FW_STATE_RDY), 1000)) { - dev_err(dev->mt76.dev, "Timeout for initializing firmware\n"); - return -EIO; - } + ret = mt7915_firmware_state(dev, true); + if (ret) + return ret; mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_FWDL], false); @@ -3110,15 +2357,29 @@ int mt7915_mcu_init(struct mt7915_dev *dev) .headroom = sizeof(struct mt7915_mcu_txd), .mcu_skb_send_msg = mt7915_mcu_send_message, .mcu_parse_response = mt7915_mcu_parse_response, - .mcu_restart = mt7915_mcu_restart, + .mcu_restart = mt76_connac_mcu_restart, }; int ret; dev->mt76.mcu_ops = &mt7915_mcu_ops; - ret = mt7915_driver_own(dev); + /* force firmware operation mode into normal state, + * which should be set before firmware download stage. + */ + if (is_mt7915(&dev->mt76)) + mt76_wr(dev, MT_SWDEF_MODE, MT_SWDEF_NORMAL_MODE); + else + mt76_wr(dev, MT_SWDEF_MODE_MT7916, MT_SWDEF_NORMAL_MODE); + + ret = mt7915_driver_own(dev, 0); if (ret) return ret; + /* set driver own for band1 when two hif exist */ + if (dev->hif2) { + ret = mt7915_driver_own(dev, 1); + if (ret) + return ret; + } ret = mt7915_load_firmware(dev); if (ret) @@ -3153,14 +2414,15 @@ int mt7915_mcu_init(struct mt7915_dev *dev) void mt7915_mcu_exit(struct mt7915_dev *dev) { __mt76_mcu_restart(&dev->mt76); - if (!mt76_poll_msec(dev, MT_TOP_MISC, MT_TOP_MISC_FW_STATE, - FIELD_PREP(MT_TOP_MISC_FW_STATE, - FW_STATE_FW_DOWNLOAD), 1000)) { + if (mt7915_firmware_state(dev, false)) { dev_err(dev->mt76.dev, "Failed to exit mcu\n"); return; } - mt76_wr(dev, MT_TOP_LPCR_HOST_BAND0, MT_TOP_LPCR_HOST_FW_OWN); + mt76_wr(dev, MT_TOP_LPCR_HOST_BAND(0), MT_TOP_LPCR_HOST_FW_OWN); + if (dev->hif2) + mt76_wr(dev, MT_TOP_LPCR_HOST_BAND(1), + MT_TOP_LPCR_HOST_FW_OWN); skb_queue_purge(&dev->mt76.mcu.res_q); } @@ -3238,26 +2500,6 @@ int mt7915_mcu_set_scs(struct mt7915_dev *dev, u8 band, bool enable) sizeof(req), false); } -int mt7915_mcu_set_rts_thresh(struct mt7915_phy *phy, u32 val) -{ - struct mt7915_dev *dev = phy->dev; - struct { - u8 prot_idx; - u8 band; - u8 rsv[2]; - __le32 len_thresh; - __le32 pkt_thresh; - } __packed req = { - .prot_idx = 1, - .band = phy != &dev->phy, - .len_thresh = cpu_to_le32(val), - .pkt_thresh = cpu_to_le32(0x2), - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(PROTECT_CTRL), &req, - sizeof(req), true); -} - int mt7915_mcu_update_edca(struct mt7915_dev *dev, void *param) { struct mt7915_mcu_tx *req = (struct mt7915_mcu_tx *)param; @@ -3303,58 +2545,6 @@ int mt7915_mcu_set_tx(struct mt7915_dev *dev, struct ieee80211_vif *vif) return mt7915_mcu_update_edca(dev, &req); } -int mt7915_mcu_set_pm(struct mt7915_dev *dev, int band, int enter) -{ -#define ENTER_PM_STATE 1 -#define EXIT_PM_STATE 2 - struct { - u8 pm_number; - u8 pm_state; - u8 bssid[ETH_ALEN]; - u8 dtim_period; - u8 wlan_idx_lo; - __le16 bcn_interval; - __le32 aid; - __le32 rx_filter; - u8 band_idx; - u8 wlan_idx_hi; - u8 rsv[2]; - __le32 feature; - u8 omac_idx; - u8 wmm_idx; - u8 bcn_loss_cnt; - u8 bcn_sp_duration; - } __packed req = { - .pm_number = 5, - .pm_state = (enter) ? ENTER_PM_STATE : EXIT_PM_STATE, - .band_idx = band, - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(PM_STATE_CTRL), &req, - sizeof(req), true); -} - -int mt7915_mcu_rdd_cmd(struct mt7915_dev *dev, - enum mt7915_rdd_cmd cmd, u8 index, - u8 rx_sel, u8 val) -{ - struct { - u8 ctrl; - u8 rdd_idx; - u8 rdd_rx_sel; - u8 val; - u8 rsv[4]; - } __packed req = { - .ctrl = cmd, - .rdd_idx = index, - .rdd_rx_sel = rx_sel, - .val = val, - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(SET_RDD_CTRL), &req, - sizeof(req), true); -} - int mt7915_mcu_set_fcc5_lpn(struct mt7915_dev *dev, int val) { struct { @@ -3453,6 +2643,99 @@ int mt7915_mcu_set_radar_th(struct mt7915_dev *dev, int index, sizeof(req), true); } +static int +mt7915_mcu_background_chain_ctrl(struct mt7915_phy *phy, + struct cfg80211_chan_def *chandef, + int cmd) +{ + struct mt7915_dev *dev = phy->dev; + struct mt76_phy *mphy = phy->mt76; + struct ieee80211_channel *chan = mphy->chandef.chan; + int freq = mphy->chandef.center_freq1; + struct mt7915_mcu_background_chain_ctrl req = { + .monitor_scan_type = 2, /* simple rx */ + }; + + if (!chandef && cmd != CH_SWITCH_BACKGROUND_SCAN_STOP) + return -EINVAL; + + if (!cfg80211_chandef_valid(&mphy->chandef)) + return -EINVAL; + + switch (cmd) { + case CH_SWITCH_BACKGROUND_SCAN_START: { + req.chan = chan->hw_value; + req.central_chan = ieee80211_frequency_to_channel(freq); + req.bw = mt76_connac_chan_bw(&mphy->chandef); + req.monitor_chan = chandef->chan->hw_value; + req.monitor_central_chan = + ieee80211_frequency_to_channel(chandef->center_freq1); + req.monitor_bw = mt76_connac_chan_bw(chandef); + req.band_idx = phy != &dev->phy; + req.scan_mode = 1; + break; + } + case CH_SWITCH_BACKGROUND_SCAN_RUNNING: + req.monitor_chan = chandef->chan->hw_value; + req.monitor_central_chan = + ieee80211_frequency_to_channel(chandef->center_freq1); + req.band_idx = phy != &dev->phy; + req.scan_mode = 2; + break; + case CH_SWITCH_BACKGROUND_SCAN_STOP: + req.chan = chan->hw_value; + req.central_chan = ieee80211_frequency_to_channel(freq); + req.bw = mt76_connac_chan_bw(&mphy->chandef); + req.tx_stream = hweight8(mphy->antenna_mask); + req.rx_stream = mphy->antenna_mask; + break; + default: + return -EINVAL; + } + req.band = chandef ? chandef->chan->band == NL80211_BAND_5GHZ : 1; + + return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(OFFCH_SCAN_CTRL), + &req, sizeof(req), false); +} + +int mt7915_mcu_rdd_background_enable(struct mt7915_phy *phy, + struct cfg80211_chan_def *chandef) +{ + struct mt7915_dev *dev = phy->dev; + int err, region; + + if (!chandef) { /* disable offchain */ + err = mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_STOP, MT_RX_SEL2, + 0, 0); + if (err) + return err; + + return mt7915_mcu_background_chain_ctrl(phy, NULL, + CH_SWITCH_BACKGROUND_SCAN_STOP); + } + + err = mt7915_mcu_background_chain_ctrl(phy, chandef, + CH_SWITCH_BACKGROUND_SCAN_START); + if (err) + return err; + + switch (dev->mt76.region) { + case NL80211_DFS_ETSI: + region = 0; + break; + case NL80211_DFS_JP: + region = 2; + break; + case NL80211_DFS_FCC: + default: + region = 1; + break; + } + + return mt76_connac_mcu_rdd_cmd(&dev->mt76, RDD_START, MT_RX_SEL2, + 0, region); +} + int mt7915_mcu_set_chan_info(struct mt7915_phy *phy, int cmd) { struct mt7915_dev *dev = phy->dev; @@ -3479,7 +2762,7 @@ int mt7915_mcu_set_chan_info(struct mt7915_phy *phy, int cmd) } __packed req = { .control_ch = chandef->chan->hw_value, .center_ch = ieee80211_frequency_to_channel(freq1), - .bw = mt7915_mcu_chan_bw(chandef), + .bw = mt76_connac_chan_bw(chandef), .tx_streams_num = hweight8(phy->mt76->antenna_mask), .rx_streams = phy->mt76->antenna_mask, .band_idx = ext_phy, @@ -3503,7 +2786,7 @@ int mt7915_mcu_set_chan_info(struct mt7915_phy *phy, int cmd) if (phy->mt76->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL) req.switch_reason = CH_SWITCH_SCAN_BYPASS_DPD; - else if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) && + else if (phy->mt76->hw->conf.radar_enabled && chandef->chan->dfs_state != NL80211_DFS_AVAILABLE) req.switch_reason = CH_SWITCH_DFS; else @@ -3527,7 +2810,8 @@ static int mt7915_mcu_set_eeprom_flash(struct mt7915_dev *dev) #define PAGE_IDX_MASK GENMASK(4, 2) #define PER_PAGE_SIZE 0x400 struct mt7915_mcu_eeprom req = { .buffer_mode = EE_MODE_BUFFER }; - u8 total = DIV_ROUND_UP(MT7915_EEPROM_SIZE, PER_PAGE_SIZE); + u16 eeprom_size = mt7915_eeprom_size(dev); + u8 total = DIV_ROUND_UP(eeprom_size, PER_PAGE_SIZE); u8 *eep = (u8 *)dev->mt76.eeprom.data; int eep_len; int i; @@ -3536,8 +2820,8 @@ static int mt7915_mcu_set_eeprom_flash(struct mt7915_dev *dev) struct sk_buff *skb; int ret; - if (i == total - 1 && !!(MT7915_EEPROM_SIZE % PER_PAGE_SIZE)) - eep_len = MT7915_EEPROM_SIZE % PER_PAGE_SIZE; + if (i == total - 1 && !!(eeprom_size % PER_PAGE_SIZE)) + eep_len = eeprom_size % PER_PAGE_SIZE; else eep_len = PER_PAGE_SIZE; @@ -3770,19 +3054,24 @@ int mt7915_mcu_apply_tx_dpd(struct mt7915_phy *phy) int mt7915_mcu_get_chan_mib_info(struct mt7915_phy *phy, bool chan_switch) { /* strict order */ - static const enum mt7915_chan_mib_offs offs[] = { - MIB_BUSY_TIME, MIB_TX_TIME, MIB_RX_TIME, MIB_OBSS_AIRTIME + static const u32 offs[] = { + MIB_BUSY_TIME, MIB_TX_TIME, MIB_RX_TIME, MIB_OBSS_AIRTIME, + MIB_BUSY_TIME_V2, MIB_TX_TIME_V2, MIB_RX_TIME_V2, + MIB_OBSS_AIRTIME_V2 }; struct mt76_channel_state *state = phy->mt76->chan_state; struct mt76_channel_state *state_ts = &phy->state_ts; struct mt7915_dev *dev = phy->dev; struct mt7915_mcu_mib *res, req[4]; struct sk_buff *skb; - int i, ret; + int i, ret, start = 0; + + if (!is_mt7915(&dev->mt76)) + start = 4; for (i = 0; i < 4; i++) { req[i].band = cpu_to_le32(phy != &dev->phy); - req[i].offs = cpu_to_le32(offs[i]); + req[i].offs = cpu_to_le32(offs[i + start]); } ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_EXT_CMD(GET_MIB_INFO), @@ -4210,11 +3499,13 @@ int mt7915_mcu_update_bss_color(struct mt7915_dev *dev, struct ieee80211_vif *vi struct sk_buff *skb; struct tlv *tlv; - skb = mt7915_mcu_alloc_sta_req(dev, mvif, NULL, len); + skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, + NULL, len); if (IS_ERR(skb)) return PTR_ERR(skb); - tlv = mt7915_mcu_add_tlv(skb, BSS_INFO_BSS_COLOR, sizeof(*bss_color)); + tlv = mt76_connac_mcu_add_tlv(skb, BSS_INFO_BSS_COLOR, + sizeof(*bss_color)); bss_color = (struct bss_info_color *)tlv; bss_color->disable = !he_bss_color->enabled; bss_color->color = he_bss_color->color; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h index 92268e696931..9417f7bc807a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h @@ -131,6 +131,29 @@ struct mt7915_mcu_rdd_report { } hw_pulse[32]; } __packed; +struct mt7915_mcu_background_chain_ctrl { + u8 chan; /* primary channel */ + u8 central_chan; /* central channel */ + u8 bw; + u8 tx_stream; + u8 rx_stream; + + u8 monitor_chan; /* monitor channel */ + u8 monitor_central_chan;/* monitor central channel */ + u8 monitor_bw; + u8 monitor_tx_stream; + u8 monitor_rx_stream; + + u8 scan_mode; /* 0: ScanStop + * 1: ScanStart + * 2: ScanRunning + */ + u8 band_idx; /* DBDC */ + u8 monitor_scan_type; + u8 band; /* 0: 2.4GHz, 1: 5GHz */ + u8 rsv[2]; +} __packed; + struct mt7915_mcu_eeprom { u8 buffer_mode; u8 format; @@ -161,10 +184,16 @@ struct mt7915_mcu_mib { } __packed; enum mt7915_chan_mib_offs { + /* mt7915 */ MIB_BUSY_TIME = 14, MIB_TX_TIME = 81, MIB_RX_TIME, - MIB_OBSS_AIRTIME = 86 + MIB_OBSS_AIRTIME = 86, + /* mt7916 */ + MIB_BUSY_TIME_V2 = 0, + MIB_TX_TIME_V2 = 6, + MIB_RX_TIME_V2 = 8, + MIB_OBSS_AIRTIME_V2 = 490 }; struct edca { @@ -266,29 +295,6 @@ enum mcu_mmps_mode { MCU_MMPS_DISABLE, }; -#define STA_TYPE_STA BIT(0) -#define STA_TYPE_AP BIT(1) -#define STA_TYPE_ADHOC BIT(2) -#define STA_TYPE_WDS BIT(4) -#define STA_TYPE_BC BIT(5) - -#define NETWORK_INFRA BIT(16) -#define NETWORK_P2P BIT(17) -#define NETWORK_IBSS BIT(18) -#define NETWORK_WDS BIT(21) - -#define CONNECTION_INFRA_STA (STA_TYPE_STA | NETWORK_INFRA) -#define CONNECTION_INFRA_AP (STA_TYPE_AP | NETWORK_INFRA) -#define CONNECTION_P2P_GC (STA_TYPE_STA | NETWORK_P2P) -#define CONNECTION_P2P_GO (STA_TYPE_AP | NETWORK_P2P) -#define CONNECTION_IBSS_ADHOC (STA_TYPE_ADHOC | NETWORK_IBSS) -#define CONNECTION_WDS (STA_TYPE_WDS | NETWORK_WDS) -#define CONNECTION_INFRA_BC (STA_TYPE_BC | NETWORK_INFRA) - -#define CONN_STATE_DISCONNECT 0 -#define CONN_STATE_CONNECT 1 -#define CONN_STATE_PORT_SECURE 2 - enum { SCS_SEND_DATA, SCS_SET_MANUAL_PD_TH, diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c index 1f6ba306c850..e8ff686bd3f3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c @@ -1,101 +1,346 @@ // SPDX-License-Identifier: ISC /* Copyright (C) 2020 MediaTek Inc. */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pci.h> + #include "mt7915.h" +#include "mac.h" +#include "../trace.h" + +static const u32 mt7915_reg[] = { + [INT_SOURCE_CSR] = 0xd7010, + [INT_MASK_CSR] = 0xd7014, + [INT1_SOURCE_CSR] = 0xd7088, + [INT1_MASK_CSR] = 0xd708c, + [INT_MCU_CMD_SOURCE] = 0xd51f0, + [INT_MCU_CMD_EVENT] = 0x3108, +}; + +static const u32 mt7916_reg[] = { + [INT_SOURCE_CSR] = 0xd4200, + [INT_MASK_CSR] = 0xd4204, + [INT1_SOURCE_CSR] = 0xd8200, + [INT1_MASK_CSR] = 0xd8204, + [INT_MCU_CMD_SOURCE] = 0xd41f0, + [INT_MCU_CMD_EVENT] = 0x2108, +}; + +static const u32 mt7915_offs[] = { + [TMAC_CDTR] = 0x090, + [TMAC_ODTR] = 0x094, + [TMAC_ATCR] = 0x098, + [TMAC_TRCR0] = 0x09c, + [TMAC_ICR0] = 0x0a4, + [TMAC_ICR1] = 0x0b4, + [TMAC_CTCR0] = 0x0f4, + [TMAC_TFCR0] = 0x1e0, + [MDP_BNRCFR0] = 0x070, + [MDP_BNRCFR1] = 0x074, + [ARB_DRNGR0] = 0x194, + [ARB_SCR] = 0x080, + [RMAC_MIB_AIRTIME14] = 0x3b8, + [AGG_AWSCR0] = 0x05c, + [AGG_PCR0] = 0x06c, + [AGG_ACR0] = 0x084, + [AGG_MRCR] = 0x098, + [AGG_ATCR1] = 0x0f0, + [AGG_ATCR3] = 0x0f4, + [LPON_UTTR0] = 0x080, + [LPON_UTTR1] = 0x084, + [LPON_FRCR] = 0x314, + [MIB_SDR3] = 0x014, + [MIB_SDR4] = 0x018, + [MIB_SDR5] = 0x01c, + [MIB_SDR7] = 0x024, + [MIB_SDR8] = 0x028, + [MIB_SDR9] = 0x02c, + [MIB_SDR10] = 0x030, + [MIB_SDR11] = 0x034, + [MIB_SDR12] = 0x038, + [MIB_SDR13] = 0x03c, + [MIB_SDR14] = 0x040, + [MIB_SDR15] = 0x044, + [MIB_SDR16] = 0x048, + [MIB_SDR17] = 0x04c, + [MIB_SDR18] = 0x050, + [MIB_SDR19] = 0x054, + [MIB_SDR20] = 0x058, + [MIB_SDR21] = 0x05c, + [MIB_SDR22] = 0x060, + [MIB_SDR23] = 0x064, + [MIB_SDR24] = 0x068, + [MIB_SDR25] = 0x06c, + [MIB_SDR27] = 0x074, + [MIB_SDR28] = 0x078, + [MIB_SDR29] = 0x07c, + [MIB_SDRVEC] = 0x080, + [MIB_SDR31] = 0x084, + [MIB_SDR32] = 0x088, + [MIB_SDRMUBF] = 0x090, + [MIB_DR8] = 0x0c0, + [MIB_DR9] = 0x0c4, + [MIB_DR11] = 0x0cc, + [MIB_MB_SDR0] = 0x100, + [MIB_MB_SDR1] = 0x104, + [TX_AGG_CNT] = 0x0a8, + [TX_AGG_CNT2] = 0x164, + [MIB_ARNG] = 0x4b8, + [WTBLON_TOP_WDUCR] = 0x0, + [WTBL_UPDATE] = 0x030, + [PLE_FL_Q_EMPTY] = 0x0b0, + [PLE_FL_Q_CTRL] = 0x1b0, + [PLE_AC_QEMPTY] = 0x500, + [PLE_FREEPG_CNT] = 0x100, + [PLE_FREEPG_HEAD_TAIL] = 0x104, + [PLE_PG_HIF_GROUP] = 0x110, + [PLE_HIF_PG_INFO] = 0x114, + [AC_OFFSET] = 0x040, +}; + +static const u32 mt7916_offs[] = { + [TMAC_CDTR] = 0x0c8, + [TMAC_ODTR] = 0x0cc, + [TMAC_ATCR] = 0x00c, + [TMAC_TRCR0] = 0x010, + [TMAC_ICR0] = 0x014, + [TMAC_ICR1] = 0x018, + [TMAC_CTCR0] = 0x114, + [TMAC_TFCR0] = 0x0e4, + [MDP_BNRCFR0] = 0x090, + [MDP_BNRCFR1] = 0x094, + [ARB_DRNGR0] = 0x1e0, + [ARB_SCR] = 0x000, + [RMAC_MIB_AIRTIME14] = 0x0398, + [AGG_AWSCR0] = 0x030, + [AGG_PCR0] = 0x040, + [AGG_ACR0] = 0x054, + [AGG_MRCR] = 0x068, + [AGG_ATCR1] = 0x1a8, + [AGG_ATCR3] = 0x080, + [LPON_UTTR0] = 0x360, + [LPON_UTTR1] = 0x364, + [LPON_FRCR] = 0x37c, + [MIB_SDR3] = 0x698, + [MIB_SDR4] = 0x788, + [MIB_SDR5] = 0x780, + [MIB_SDR7] = 0x5a8, + [MIB_SDR8] = 0x78c, + [MIB_SDR9] = 0x024, + [MIB_SDR10] = 0x76c, + [MIB_SDR11] = 0x790, + [MIB_SDR12] = 0x558, + [MIB_SDR13] = 0x560, + [MIB_SDR14] = 0x564, + [MIB_SDR15] = 0x568, + [MIB_SDR16] = 0x7fc, + [MIB_SDR17] = 0x800, + [MIB_SDR18] = 0x030, + [MIB_SDR19] = 0x5ac, + [MIB_SDR20] = 0x5b0, + [MIB_SDR21] = 0x5b4, + [MIB_SDR22] = 0x770, + [MIB_SDR23] = 0x774, + [MIB_SDR24] = 0x778, + [MIB_SDR25] = 0x77c, + [MIB_SDR27] = 0x080, + [MIB_SDR28] = 0x084, + [MIB_SDR29] = 0x650, + [MIB_SDRVEC] = 0x5a8, + [MIB_SDR31] = 0x55c, + [MIB_SDR32] = 0x7a8, + [MIB_SDRMUBF] = 0x7ac, + [MIB_DR8] = 0x56c, + [MIB_DR9] = 0x570, + [MIB_DR11] = 0x574, + [MIB_MB_SDR0] = 0x688, + [MIB_MB_SDR1] = 0x690, + [TX_AGG_CNT] = 0x7dc, + [TX_AGG_CNT2] = 0x7ec, + [MIB_ARNG] = 0x0b0, + [WTBLON_TOP_WDUCR] = 0x200, + [WTBL_UPDATE] = 0x230, + [PLE_FL_Q_EMPTY] = 0x360, + [PLE_FL_Q_CTRL] = 0x3e0, + [PLE_AC_QEMPTY] = 0x600, + [PLE_FREEPG_CNT] = 0x380, + [PLE_FREEPG_HEAD_TAIL] = 0x384, + [PLE_PG_HIF_GROUP] = 0x00c, + [PLE_HIF_PG_INFO] = 0x388, + [AC_OFFSET] = 0x080, +}; + +static const struct __map mt7915_reg_map[] = { + { 0x00400000, 0x80000, 0x10000 }, /* WF_MCU_SYSRAM */ + { 0x00410000, 0x90000, 0x10000 }, /* WF_MCU_SYSRAM (configure regs) */ + { 0x40000000, 0x70000, 0x10000 }, /* WF_UMAC_SYSRAM */ + { 0x54000000, 0x02000, 0x1000 }, /* WFDMA PCIE0 MCU DMA0 */ + { 0x55000000, 0x03000, 0x1000 }, /* WFDMA PCIE0 MCU DMA1 */ + { 0x58000000, 0x06000, 0x1000 }, /* WFDMA PCIE1 MCU DMA0 (MEM_DMA) */ + { 0x59000000, 0x07000, 0x1000 }, /* WFDMA PCIE1 MCU DMA1 */ + { 0x7c000000, 0xf0000, 0x10000 }, /* CONN_INFRA */ + { 0x7c020000, 0xd0000, 0x10000 }, /* CONN_INFRA, WFDMA */ + { 0x80020000, 0xb0000, 0x10000 }, /* WF_TOP_MISC_OFF */ + { 0x81020000, 0xc0000, 0x10000 }, /* WF_TOP_MISC_ON */ + { 0x820c0000, 0x08000, 0x4000 }, /* WF_UMAC_TOP (PLE) */ + { 0x820c8000, 0x0c000, 0x2000 }, /* WF_UMAC_TOP (PSE) */ + { 0x820cc000, 0x0e000, 0x2000 }, /* WF_UMAC_TOP (PP) */ + { 0x820ce000, 0x21c00, 0x0200 }, /* WF_LMAC_TOP (WF_SEC) */ + { 0x820cf000, 0x22000, 0x1000 }, /* WF_LMAC_TOP (WF_PF) */ + { 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */ + { 0x820e0000, 0x20000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_CFG) */ + { 0x820e1000, 0x20400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_TRB) */ + { 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */ + { 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */ + { 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */ + { 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */ + { 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */ + { 0x820e9000, 0x23400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */ + { 0x820ea000, 0x24000, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_ETBF) */ + { 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */ + { 0x820ec000, 0x24600, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_INT) */ + { 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */ + { 0x820f0000, 0xa0000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_CFG) */ + { 0x820f1000, 0xa0600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_TRB) */ + { 0x820f2000, 0xa0800, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_AGG) */ + { 0x820f3000, 0xa0c00, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_ARB) */ + { 0x820f4000, 0xa1000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_TMAC) */ + { 0x820f5000, 0xa1400, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_RMAC) */ + { 0x820f7000, 0xa1e00, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_DMA) */ + { 0x820f9000, 0xa3400, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_WTBLOFF) */ + { 0x820fa000, 0xa4000, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_ETBF) */ + { 0x820fb000, 0xa4200, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_LPON) */ + { 0x820fc000, 0xa4600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_INT) */ + { 0x820fd000, 0xa4800, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_MIB) */ + { 0x0, 0x0, 0x0 }, /* imply end of search */ +}; + +static const struct __map mt7916_reg_map[] = { + { 0x54000000, 0x02000, 0x1000 }, /* WFDMA_0 (PCIE0 MCU DMA0) */ + { 0x55000000, 0x03000, 0x1000 }, /* WFDMA_1 (PCIE0 MCU DMA1) */ + { 0x56000000, 0x04000, 0x1000 }, /* WFDMA_2 (Reserved) */ + { 0x57000000, 0x05000, 0x1000 }, /* WFDMA_3 (MCU wrap CR) */ + { 0x58000000, 0x06000, 0x1000 }, /* WFDMA_4 (PCIE1 MCU DMA0) */ + { 0x59000000, 0x07000, 0x1000 }, /* WFDMA_5 (PCIE1 MCU DMA1) */ + { 0x820c0000, 0x08000, 0x4000 }, /* WF_UMAC_TOP (PLE) */ + { 0x820c8000, 0x0c000, 0x2000 }, /* WF_UMAC_TOP (PSE) */ + { 0x820cc000, 0x0e000, 0x2000 }, /* WF_UMAC_TOP (PP) */ + { 0x820e0000, 0x20000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_CFG) */ + { 0x820e1000, 0x20400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_TRB) */ + { 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */ + { 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */ + { 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */ + { 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */ + { 0x820ce000, 0x21c00, 0x0200 }, /* WF_LMAC_TOP (WF_SEC) */ + { 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */ + { 0x820cf000, 0x22000, 0x1000 }, /* WF_LMAC_TOP (WF_PF) */ + { 0x820e9000, 0x23400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */ + { 0x820ea000, 0x24000, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_ETBF) */ + { 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */ + { 0x820ec000, 0x24600, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_INT) */ + { 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */ + { 0x820ca000, 0x26000, 0x2000 }, /* WF_LMAC_TOP BN0 (WF_MUCOP) */ + { 0x820d0000, 0x30000, 0x10000}, /* WF_LMAC_TOP (WF_WTBLON) */ + { 0x00400000, 0x80000, 0x10000}, /* WF_MCU_SYSRAM */ + { 0x00410000, 0x90000, 0x10000}, /* WF_MCU_SYSRAM (configure cr) */ + { 0x820f0000, 0xa0000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_CFG) */ + { 0x820f1000, 0xa0600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_TRB) */ + { 0x820f2000, 0xa0800, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_AGG) */ + { 0x820f3000, 0xa0c00, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_ARB) */ + { 0x820f4000, 0xa1000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_TMAC) */ + { 0x820f5000, 0xa1400, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_RMAC) */ + { 0x820f7000, 0xa1e00, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_DMA) */ + { 0x820f9000, 0xa3400, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_WTBLOFF) */ + { 0x820fa000, 0xa4000, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_ETBF) */ + { 0x820fb000, 0xa4200, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_LPON) */ + { 0x820fc000, 0xa4600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_INT) */ + { 0x820fd000, 0xa4800, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_MIB) */ + { 0x820c4000, 0xa8000, 0x1000 }, /* WF_LMAC_TOP (WF_UWTBL ) */ + { 0x820b0000, 0xae000, 0x1000 }, /* [APB2] WFSYS_ON */ + { 0x80020000, 0xb0000, 0x10000}, /* WF_TOP_MISC_OFF */ + { 0x81020000, 0xc0000, 0x10000}, /* WF_TOP_MISC_ON */ + { 0x0, 0x0, 0x0 }, /* imply end of search */ +}; static u32 mt7915_reg_map_l1(struct mt7915_dev *dev, u32 addr) { u32 offset = FIELD_GET(MT_HIF_REMAP_L1_OFFSET, addr); u32 base = FIELD_GET(MT_HIF_REMAP_L1_BASE, addr); + u32 l1_remap = is_mt7915(&dev->mt76) ? + MT_HIF_REMAP_L1 : MT_HIF_REMAP_L1_MT7916; - mt76_rmw_field(dev, MT_HIF_REMAP_L1, MT_HIF_REMAP_L1_MASK, base); + dev->bus_ops->rmw(&dev->mt76, l1_remap, + MT_HIF_REMAP_L1_MASK, + FIELD_PREP(MT_HIF_REMAP_L1_MASK, base)); /* use read to push write */ - mt76_rr(dev, MT_HIF_REMAP_L1); + dev->bus_ops->rr(&dev->mt76, l1_remap); return MT_HIF_REMAP_BASE_L1 + offset; } static u32 mt7915_reg_map_l2(struct mt7915_dev *dev, u32 addr) { - u32 offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET, addr); - u32 base = FIELD_GET(MT_HIF_REMAP_L2_BASE, addr); + u32 offset, base; - mt76_rmw_field(dev, MT_HIF_REMAP_L2, MT_HIF_REMAP_L2_MASK, base); - /* use read to push write */ - mt76_rr(dev, MT_HIF_REMAP_L2); + if (is_mt7915(&dev->mt76)) { + offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET, addr); + base = FIELD_GET(MT_HIF_REMAP_L2_BASE, addr); + + dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L2, + MT_HIF_REMAP_L2_MASK, + FIELD_PREP(MT_HIF_REMAP_L2_MASK, base)); + + /* use read to push write */ + dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L2); + } else { + offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET_MT7916, addr); + base = FIELD_GET(MT_HIF_REMAP_L2_BASE_MT7916, addr); + + dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L2_MT7916, + MT_HIF_REMAP_L2_MASK_MT7916, + FIELD_PREP(MT_HIF_REMAP_L2_MASK_MT7916, base)); + + /* use read to push write */ + dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L2_MT7916); - return MT_HIF_REMAP_BASE_L2 + offset; + offset += MT_HIF_REMAP_BASE_L2_MT7916; + } + + return offset; } static u32 __mt7915_reg_addr(struct mt7915_dev *dev, u32 addr) { - static const struct { - u32 phys; - u32 mapped; - u32 size; - } fixed_map[] = { - { 0x00400000, 0x80000, 0x10000 }, /* WF_MCU_SYSRAM */ - { 0x00410000, 0x90000, 0x10000 }, /* WF_MCU_SYSRAM (configure regs) */ - { 0x40000000, 0x70000, 0x10000 }, /* WF_UMAC_SYSRAM */ - { 0x54000000, 0x02000, 0x1000 }, /* WFDMA PCIE0 MCU DMA0 */ - { 0x55000000, 0x03000, 0x1000 }, /* WFDMA PCIE0 MCU DMA1 */ - { 0x58000000, 0x06000, 0x1000 }, /* WFDMA PCIE1 MCU DMA0 (MEM_DMA) */ - { 0x59000000, 0x07000, 0x1000 }, /* WFDMA PCIE1 MCU DMA1 */ - { 0x7c000000, 0xf0000, 0x10000 }, /* CONN_INFRA */ - { 0x7c020000, 0xd0000, 0x10000 }, /* CONN_INFRA, WFDMA */ - { 0x80020000, 0xb0000, 0x10000 }, /* WF_TOP_MISC_OFF */ - { 0x81020000, 0xc0000, 0x10000 }, /* WF_TOP_MISC_ON */ - { 0x820c0000, 0x08000, 0x4000 }, /* WF_UMAC_TOP (PLE) */ - { 0x820c8000, 0x0c000, 0x2000 }, /* WF_UMAC_TOP (PSE) */ - { 0x820cc000, 0x0e000, 0x2000 }, /* WF_UMAC_TOP (PP) */ - { 0x820ce000, 0x21c00, 0x0200 }, /* WF_LMAC_TOP (WF_SEC) */ - { 0x820cf000, 0x22000, 0x1000 }, /* WF_LMAC_TOP (WF_PF) */ - { 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */ - { 0x820e0000, 0x20000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_CFG) */ - { 0x820e1000, 0x20400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_TRB) */ - { 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */ - { 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */ - { 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */ - { 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */ - { 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */ - { 0x820e9000, 0x23400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */ - { 0x820ea000, 0x24000, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_ETBF) */ - { 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */ - { 0x820ec000, 0x24600, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_INT) */ - { 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */ - { 0x820f0000, 0xa0000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_CFG) */ - { 0x820f1000, 0xa0600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_TRB) */ - { 0x820f2000, 0xa0800, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_AGG) */ - { 0x820f3000, 0xa0c00, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_ARB) */ - { 0x820f4000, 0xa1000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_TMAC) */ - { 0x820f5000, 0xa1400, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_RMAC) */ - { 0x820f7000, 0xa1e00, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_DMA) */ - { 0x820f9000, 0xa3400, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_WTBLOFF) */ - { 0x820fa000, 0xa4000, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_ETBF) */ - { 0x820fb000, 0xa4200, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_LPON) */ - { 0x820fc000, 0xa4600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_INT) */ - { 0x820fd000, 0xa4800, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_MIB) */ - }; int i; if (addr < 0x100000) return addr; - for (i = 0; i < ARRAY_SIZE(fixed_map); i++) { + if (!dev->reg.map) { + dev_err(dev->mt76.dev, "err: reg_map is null\n"); + return addr; + } + + for (i = 0; i < dev->reg.map_size; i++) { u32 ofs; - if (addr < fixed_map[i].phys) + if (addr < dev->reg.map[i].phys) continue; - ofs = addr - fixed_map[i].phys; - if (ofs > fixed_map[i].size) + ofs = addr - dev->reg.map[i].phys; + if (ofs > dev->reg.map[i].size) continue; - return fixed_map[i].mapped + ofs; + return dev->reg.map[i].maps + ofs; } - if ((addr >= 0x18000000 && addr < 0x18c00000) || - (addr >= 0x70000000 && addr < 0x78000000)) + if ((addr >= MT_INFRA_BASE && addr < MT_WFSYS0_PHY_START) || + (addr >= MT_WFSYS0_PHY_START && addr < MT_WFSYS1_PHY_START) || + (addr >= MT_WFSYS1_PHY_START && addr <= MT_WFSYS1_PHY_END) || + (addr >= MT_CBTOP1_PHY_START && addr <= MT_CBTOP1_PHY_END) || + (addr >= MT_CBTOP2_PHY_START && addr <= MT_CBTOP2_PHY_END)) return mt7915_reg_map_l1(dev, addr); return mt7915_reg_map_l2(dev, addr); @@ -125,7 +370,9 @@ static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) return dev->bus_ops->rmw(mdev, addr, mask, val); } -int mt7915_mmio_init(struct mt76_dev *mdev, void __iomem *mem_base, int irq) +static int mt7915_mmio_init(struct mt76_dev *mdev, + void __iomem *mem_base, + u32 device_id) { struct mt76_bus_ops *bus_ops; struct mt7915_dev *dev; @@ -133,6 +380,23 @@ int mt7915_mmio_init(struct mt76_dev *mdev, void __iomem *mem_base, int irq) dev = container_of(mdev, struct mt7915_dev, mt76); mt76_mmio_init(&dev->mt76, mem_base); + switch (device_id) { + case 0x7915: + dev->reg.reg_rev = mt7915_reg; + dev->reg.offs_rev = mt7915_offs; + dev->reg.map = mt7915_reg_map; + dev->reg.map_size = ARRAY_SIZE(mt7915_reg_map); + break; + case 0x7906: + dev->reg.reg_rev = mt7916_reg; + dev->reg.offs_rev = mt7916_offs; + dev->reg.map = mt7916_reg_map; + dev->reg.map_size = ARRAY_SIZE(mt7916_reg_map); + break; + default: + return -EINVAL; + } + dev->bus_ops = dev->mt76.bus; bus_ops = devm_kmemdup(dev->mt76.dev, dev->bus_ops, sizeof(*bus_ops), GFP_KERNEL); @@ -144,11 +408,194 @@ int mt7915_mmio_init(struct mt76_dev *mdev, void __iomem *mem_base, int irq) bus_ops->rmw = mt7915_rmw; dev->mt76.bus = bus_ops; - mdev->rev = (mt76_rr(dev, MT_HW_CHIPID) << 16) | + mdev->rev = (device_id << 16) | (mt76_rr(dev, MT_HW_REV) & 0xff); dev_dbg(mdev->dev, "ASIC revision: %04x\n", mdev->rev); + return 0; +} + +void mt7915_dual_hif_set_irq_mask(struct mt7915_dev *dev, + bool write_reg, + u32 clear, u32 set) +{ + struct mt76_dev *mdev = &dev->mt76; + unsigned long flags; + + spin_lock_irqsave(&mdev->mmio.irq_lock, flags); + + mdev->mmio.irqmask &= ~clear; + mdev->mmio.irqmask |= set; + + if (write_reg) { + mt76_wr(dev, MT_INT_MASK_CSR, mdev->mmio.irqmask); + mt76_wr(dev, MT_INT1_MASK_CSR, mdev->mmio.irqmask); + } + + spin_unlock_irqrestore(&mdev->mmio.irq_lock, flags); +} + +static void mt7915_rx_poll_complete(struct mt76_dev *mdev, + enum mt76_rxq_id q) +{ + struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); + + mt7915_irq_enable(dev, MT_INT_RX(q)); +} + +/* TODO: support 2/4/6/8 MSI-X vectors */ +static void mt7915_irq_tasklet(struct tasklet_struct *t) +{ + struct mt7915_dev *dev = from_tasklet(dev, t, irq_tasklet); + u32 intr, intr1, mask; + mt76_wr(dev, MT_INT_MASK_CSR, 0); + if (dev->hif2) + mt76_wr(dev, MT_INT1_MASK_CSR, 0); - return 0; + intr = mt76_rr(dev, MT_INT_SOURCE_CSR); + intr &= dev->mt76.mmio.irqmask; + mt76_wr(dev, MT_INT_SOURCE_CSR, intr); + + if (dev->hif2) { + intr1 = mt76_rr(dev, MT_INT1_SOURCE_CSR); + intr1 &= dev->mt76.mmio.irqmask; + mt76_wr(dev, MT_INT1_SOURCE_CSR, intr1); + + intr |= intr1; + } + + trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask); + + mask = intr & MT_INT_RX_DONE_ALL; + if (intr & MT_INT_TX_DONE_MCU) + mask |= MT_INT_TX_DONE_MCU; + + mt7915_irq_disable(dev, mask); + + if (intr & MT_INT_TX_DONE_MCU) + napi_schedule(&dev->mt76.tx_napi); + + if (intr & MT_INT_RX(MT_RXQ_MAIN)) + napi_schedule(&dev->mt76.napi[MT_RXQ_MAIN]); + + if (intr & MT_INT_RX(MT_RXQ_EXT)) + napi_schedule(&dev->mt76.napi[MT_RXQ_EXT]); + + if (intr & MT_INT_RX(MT_RXQ_MCU)) + napi_schedule(&dev->mt76.napi[MT_RXQ_MCU]); + + if (intr & MT_INT_RX(MT_RXQ_MCU_WA)) + napi_schedule(&dev->mt76.napi[MT_RXQ_MCU_WA]); + + if (!is_mt7915(&dev->mt76) && + (intr & MT_INT_RX(MT_RXQ_MAIN_WA))) + napi_schedule(&dev->mt76.napi[MT_RXQ_MAIN_WA]); + + if (intr & MT_INT_RX(MT_RXQ_EXT_WA)) + napi_schedule(&dev->mt76.napi[MT_RXQ_EXT_WA]); + + if (intr & MT_INT_MCU_CMD) { + u32 val = mt76_rr(dev, MT_MCU_CMD); + + mt76_wr(dev, MT_MCU_CMD, val); + if (val & MT_MCU_CMD_ERROR_MASK) { + dev->reset_state = val; + ieee80211_queue_work(mt76_hw(dev), &dev->reset_work); + wake_up(&dev->reset_wait); + } + } +} + +irqreturn_t mt7915_irq_handler(int irq, void *dev_instance) +{ + struct mt7915_dev *dev = dev_instance; + + mt76_wr(dev, MT_INT_MASK_CSR, 0); + if (dev->hif2) + mt76_wr(dev, MT_INT1_MASK_CSR, 0); + + if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state)) + return IRQ_NONE; + + tasklet_schedule(&dev->irq_tasklet); + + return IRQ_HANDLED; +} + +struct mt7915_dev *mt7915_mmio_probe(struct device *pdev, + void __iomem *mem_base, u32 device_id) +{ + static const struct mt76_driver_ops drv_ops = { + /* txwi_size = txd size + txp size */ + .txwi_size = MT_TXD_SIZE + sizeof(struct mt7915_txp), + .drv_flags = MT_DRV_TXWI_NO_FREE | MT_DRV_HW_MGMT_TXQ, + .survey_flags = SURVEY_INFO_TIME_TX | + SURVEY_INFO_TIME_RX | + SURVEY_INFO_TIME_BSS_RX, + .token_size = MT7915_TOKEN_SIZE, + .tx_prepare_skb = mt7915_tx_prepare_skb, + .tx_complete_skb = mt7915_tx_complete_skb, + .rx_skb = mt7915_queue_rx_skb, + .rx_check = mt7915_rx_check, + .rx_poll_complete = mt7915_rx_poll_complete, + .sta_ps = mt7915_sta_ps, + .sta_add = mt7915_mac_sta_add, + .sta_remove = mt7915_mac_sta_remove, + .update_survey = mt7915_update_channel, + }; + struct ieee80211_ops *ops; + struct mt7915_dev *dev; + struct mt76_dev *mdev; + int ret; + + ops = devm_kmemdup(pdev, &mt7915_ops, sizeof(mt7915_ops), GFP_KERNEL); + if (!ops) + return ERR_PTR(-ENOMEM); + + mdev = mt76_alloc_device(pdev, sizeof(*dev), ops, &drv_ops); + if (!mdev) + return ERR_PTR(-ENOMEM); + + dev = container_of(mdev, struct mt7915_dev, mt76); + + ret = mt7915_mmio_init(mdev, mem_base, device_id); + if (ret) + goto error; + + tasklet_setup(&dev->irq_tasklet, mt7915_irq_tasklet); + + mt76_wr(dev, MT_INT_MASK_CSR, 0); + + return dev; + +error: + mt76_free_device(&dev->mt76); + + return ERR_PTR(ret); } + +static int __init mt7915_init(void) +{ + int ret; + + ret = pci_register_driver(&mt7915_hif_driver); + if (ret) + return ret; + + ret = pci_register_driver(&mt7915_pci_driver); + if (ret) + pci_unregister_driver(&mt7915_hif_driver); + + return ret; +} + +static void __exit mt7915_exit(void) +{ + pci_unregister_driver(&mt7915_pci_driver); + pci_unregister_driver(&mt7915_hif_driver); +} + +module_init(mt7915_init); +module_exit(mt7915_exit); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h index 42d887383e8d..96653d64d161 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h @@ -6,13 +6,14 @@ #include <linux/interrupt.h> #include <linux/ktime.h> -#include "../mt76.h" +#include "../mt76_connac.h" #include "regs.h" #define MT7915_MAX_INTERFACES 19 #define MT7915_MAX_WMM_SETS 4 #define MT7915_WTBL_SIZE 288 -#define MT7915_WTBL_RESERVED (MT7915_WTBL_SIZE - 1) +#define MT7916_WTBL_SIZE 544 +#define MT7915_WTBL_RESERVED (mt7915_wtbl_size(dev) - 1) #define MT7915_WTBL_STA (MT7915_WTBL_RESERVED - \ MT7915_MAX_INTERFACES) @@ -30,10 +31,17 @@ #define MT7915_FIRMWARE_WM "mediatek/mt7915_wm.bin" #define MT7915_ROM_PATCH "mediatek/mt7915_rom_patch.bin" +#define MT7916_FIRMWARE_WA "mediatek/mt7916_wa.bin" +#define MT7916_FIRMWARE_WM "mediatek/mt7916_wm.bin" +#define MT7916_ROM_PATCH "mediatek/mt7916_rom_patch.bin" + #define MT7915_EEPROM_DEFAULT "mediatek/mt7915_eeprom.bin" #define MT7915_EEPROM_DEFAULT_DBDC "mediatek/mt7915_eeprom_dbdc.bin" +#define MT7916_EEPROM_DEFAULT "mediatek/mt7916_eeprom.bin" #define MT7915_EEPROM_SIZE 3584 +#define MT7916_EEPROM_SIZE 4096 + #define MT7915_EEPROM_BLOCK_SIZE 16 #define MT7915_TOKEN_SIZE 8192 @@ -46,6 +54,7 @@ #define MT7915_MAX_TWT_AGRT 16 #define MT7915_MAX_STA_TWT_AGRT 8 +#define MT7915_MAX_QUEUE (__MT_RXQ_MAX + __MT_MCUQ_MAX + 2) struct mt7915_vif; struct mt7915_sta; @@ -68,9 +77,13 @@ enum mt7915_rxq_id { MT7915_RXQ_MCU_WA_EXT, }; -struct mt7915_sta_key_conf { - s8 keyidx; - u8 key[16]; +enum mt7916_rxq_id { + MT7916_RXQ_MCU_WM = 0, + MT7916_RXQ_MCU_WA, + MT7916_RXQ_MCU_WA_MAIN, + MT7916_RXQ_MCU_WA_EXT, + MT7916_RXQ_BAND0, + MT7916_RXQ_BAND1, }; struct mt7915_twt_flow { @@ -104,7 +117,7 @@ struct mt7915_sta { struct mt76_sta_stats stats; - struct mt7915_sta_key_conf bip; + struct mt76_connac_sta_key_conf bip; struct { u8 flowid_mask; @@ -217,7 +230,6 @@ struct mt7915_phy { u8 slottime; u8 rdd_state; - int dfs_state; u32 rx_ampdu_ts; u32 ampdu_ref; @@ -247,11 +259,19 @@ struct mt7915_dev { }; struct mt7915_hif *hif2; + struct mt7915_reg_desc reg; + u8 q_id[MT7915_MAX_QUEUE]; + u32 q_int_mask[MT7915_MAX_QUEUE]; + u32 wfdma_mask; const struct mt76_bus_ops *bus_ops; struct tasklet_struct irq_tasklet; struct mt7915_phy phy; + /* monitor rx chain configured channel */ + struct cfg80211_chan_def rdd2_chandef; + struct mt7915_phy *rdd2_phy; + u16 chainmask; u32 hif_idx; @@ -274,6 +294,10 @@ struct mt7915_dev { bool ibf; u8 fw_debug_wm; u8 fw_debug_wa; + u8 fw_debug_bin; + + struct dentry *debugfs_dir; + struct rchan *relay_fwlog; void *cal; @@ -284,6 +308,13 @@ struct mt7915_dev { }; enum { + WFDMA0 = 0x0, + WFDMA1, + WFDMA_EXT, + __MT_WFDMA_MAX, +}; + +enum { MT_CTX0, MT_HIF0 = 0x0, @@ -300,6 +331,7 @@ enum { enum { MT_RX_SEL0, MT_RX_SEL1, + MT_RX_SEL2, /* monitor chain */ }; enum mt7915_rdd_cmd { @@ -345,21 +377,20 @@ mt7915_ext_phy(struct mt7915_dev *dev) return phy->priv; } -static inline u8 mt7915_lmac_mapping(struct mt7915_dev *dev, u8 ac) -{ - /* LMAC uses the reverse order of mac80211 AC indexes */ - return 3 - ac; -} - extern const struct ieee80211_ops mt7915_ops; extern const struct mt76_testmode_ops mt7915_testmode_ops; +extern struct pci_driver mt7915_pci_driver; +extern struct pci_driver mt7915_hif_driver; -u32 mt7915_reg_map(struct mt7915_dev *dev, u32 addr); +struct mt7915_dev *mt7915_mmio_probe(struct device *pdev, + void __iomem *mem_base, u32 device_id); +irqreturn_t mt7915_irq_handler(int irq, void *dev_instance); u64 __mt7915_get_tsf(struct ieee80211_hw *hw, struct mt7915_vif *mvif); int mt7915_register_device(struct mt7915_dev *dev); void mt7915_unregister_device(struct mt7915_dev *dev); int mt7915_eeprom_init(struct mt7915_dev *dev); -void mt7915_eeprom_parse_band_config(struct mt7915_phy *phy); +void mt7915_eeprom_parse_hw_cap(struct mt7915_dev *dev, + struct mt7915_phy *phy); int mt7915_eeprom_get_target_power(struct mt7915_dev *dev, struct ieee80211_channel *chan, u8 chain_idx); @@ -378,18 +409,12 @@ int mt7915_mcu_add_bss_info(struct mt7915_phy *phy, struct ieee80211_vif *vif, int enable); int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enable); -int mt7915_mcu_sta_update_hdr_trans(struct mt7915_dev *dev, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta); int mt7915_mcu_add_tx_ba(struct mt7915_dev *dev, struct ieee80211_ampdu_params *params, bool add); int mt7915_mcu_add_rx_ba(struct mt7915_dev *dev, struct ieee80211_ampdu_params *params, bool add); -int mt7915_mcu_add_key(struct mt7915_dev *dev, struct ieee80211_vif *vif, - struct mt7915_sta *msta, struct ieee80211_key_conf *key, - enum set_key_cmd cmd); int mt7915_mcu_update_bss_color(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct cfg80211_he_bss_color *he_bss_color); int mt7915_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -417,8 +442,6 @@ int mt7915_mcu_set_test_param(struct mt7915_dev *dev, u8 param, bool test_mode, u8 en); int mt7915_mcu_set_scs(struct mt7915_dev *dev, u8 band, bool enable); int mt7915_mcu_set_ser(struct mt7915_dev *dev, u8 action, u8 set, u8 band); -int mt7915_mcu_set_rts_thresh(struct mt7915_phy *phy, u32 val); -int mt7915_mcu_set_pm(struct mt7915_dev *dev, int band, int enter); int mt7915_mcu_set_sku_en(struct mt7915_phy *phy, bool enable); int mt7915_mcu_set_txpower_sku(struct mt7915_phy *phy); int mt7915_mcu_get_txpower_sku(struct mt7915_phy *phy, s8 *txpower, int len); @@ -436,17 +459,22 @@ int mt7915_mcu_get_temperature(struct mt7915_phy *phy); int mt7915_mcu_set_thermal_throttling(struct mt7915_phy *phy, u8 state); int mt7915_mcu_get_rx_rate(struct mt7915_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct rate_info *rate); -int mt7915_mcu_rdd_cmd(struct mt7915_dev *dev, enum mt7915_rdd_cmd cmd, - u8 index, u8 rx_sel, u8 val); +int mt7915_mcu_rdd_background_enable(struct mt7915_phy *phy, + struct cfg80211_chan_def *chandef); int mt7915_mcu_wa_cmd(struct mt7915_dev *dev, int cmd, u32 a1, u32 a2, u32 a3); int mt7915_mcu_fw_log_2_host(struct mt7915_dev *dev, u8 type, u8 ctrl); int mt7915_mcu_fw_dbg_ctrl(struct mt7915_dev *dev, u32 module, u8 level); void mt7915_mcu_rx_event(struct mt7915_dev *dev, struct sk_buff *skb); void mt7915_mcu_exit(struct mt7915_dev *dev); -static inline bool is_mt7915(struct mt76_dev *dev) +static inline u16 mt7915_wtbl_size(struct mt7915_dev *dev) +{ + return is_mt7915(&dev->mt76) ? MT7915_WTBL_SIZE : MT7916_WTBL_SIZE; +} + +static inline u16 mt7915_eeprom_size(struct mt7915_dev *dev) { - return mt76_chip(dev) == 0x7915; + return is_mt7915(&dev->mt76) ? MT7915_EEPROM_SIZE : MT7916_EEPROM_SIZE; } void mt7915_dual_hif_set_irq_mask(struct mt7915_dev *dev, bool write_reg, @@ -487,7 +515,6 @@ void mt7915_mac_work(struct work_struct *work); void mt7915_mac_reset_work(struct work_struct *work); void mt7915_mac_sta_rc_work(struct work_struct *work); void mt7915_mac_update_stats(struct mt7915_phy *phy); -int mt7915_mmio_init(struct mt76_dev *mdev, void __iomem *mem_base, int irq); void mt7915_mac_twt_teardown_flow(struct mt7915_dev *dev, struct mt7915_sta *msta, u8 flowid); @@ -500,7 +527,7 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, struct mt76_tx_info *tx_info); void mt7915_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e); void mt7915_tx_token_put(struct mt7915_dev *dev); -int mt7915_init_tx_queues(struct mt7915_phy *phy, int idx, int n_desc); +int mt7915_init_tx_queues(struct mt7915_phy *phy, int idx, int n_desc, int ring_base); void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb); bool mt7915_rx_check(struct mt76_dev *mdev, void *data, int len); @@ -514,6 +541,8 @@ void mt7915_update_channel(struct mt76_phy *mphy); int mt7915_mcu_muru_debug_set(struct mt7915_dev *dev, bool enable); int mt7915_mcu_muru_debug_get(struct mt7915_phy *phy, void *ms); int mt7915_init_debugfs(struct mt7915_phy *phy); +void mt7915_debugfs_rx_fw_monitor(struct mt7915_dev *dev, const void *data, int len); +bool mt7915_debugfs_rx_log(struct mt7915_dev *dev, const void *data, int len); #ifdef CONFIG_MAC80211_DEBUGFS void mt7915_sta_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct dentry *dir); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c index 8130ea43971f..6f819c41a4c4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c @@ -18,35 +18,17 @@ static u32 hif_idx; static const struct pci_device_id mt7915_pci_device_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7915) }, + { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7906) }, { }, }; static const struct pci_device_id mt7915_hif_device_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7916) }, + { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x790a) }, { }, }; -void mt7915_dual_hif_set_irq_mask(struct mt7915_dev *dev, bool write_reg, - u32 clear, u32 set) -{ - struct mt76_dev *mdev = &dev->mt76; - unsigned long flags; - - spin_lock_irqsave(&mdev->mmio.irq_lock, flags); - - mdev->mmio.irqmask &= ~clear; - mdev->mmio.irqmask |= set; - - if (write_reg) { - mt76_wr(dev, MT_INT_MASK_CSR, mdev->mmio.irqmask); - mt76_wr(dev, MT_INT1_MASK_CSR, mdev->mmio.irqmask); - } - - spin_unlock_irqrestore(&mdev->mmio.irq_lock, flags); -} - -static struct mt7915_hif * -mt7915_pci_get_hif2(struct mt7915_dev *dev) +static struct mt7915_hif *mt7915_pci_get_hif2(u32 idx) { struct mt7915_hif *hif; u32 val; @@ -56,7 +38,7 @@ mt7915_pci_get_hif2(struct mt7915_dev *dev) list_for_each_entry(hif, &hif_list, list) { val = readl(hif->regs + MT_PCIE_RECOG_ID); val &= MT_PCIE_RECOG_ID_MASK; - if (val != dev->hif_idx) + if (val != idx) continue; get_device(hif->dev); @@ -78,123 +60,17 @@ static void mt7915_put_hif2(struct mt7915_hif *hif) put_device(hif->dev); } -static void -mt7915_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q) -{ - struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); - static const u32 rx_irq_mask[] = { - [MT_RXQ_MAIN] = MT_INT_RX_DONE_DATA0, - [MT_RXQ_EXT] = MT_INT_RX_DONE_DATA1, - [MT_RXQ_MCU] = MT_INT_RX_DONE_WM, - [MT_RXQ_MCU_WA] = MT_INT_RX_DONE_WA, - [MT_RXQ_EXT_WA] = MT_INT_RX_DONE_WA_EXT, - }; - - mt7915_irq_enable(dev, rx_irq_mask[q]); -} - -/* TODO: support 2/4/6/8 MSI-X vectors */ -static void mt7915_irq_tasklet(struct tasklet_struct *t) +static struct mt7915_hif *mt7915_pci_init_hif2(struct pci_dev *pdev) { - struct mt7915_dev *dev = from_tasklet(dev, t, irq_tasklet); - u32 intr, intr1, mask; - - mt76_wr(dev, MT_INT_MASK_CSR, 0); - if (dev->hif2) - mt76_wr(dev, MT_INT1_MASK_CSR, 0); - - intr = mt76_rr(dev, MT_INT_SOURCE_CSR); - intr &= dev->mt76.mmio.irqmask; - mt76_wr(dev, MT_INT_SOURCE_CSR, intr); - - if (dev->hif2) { - intr1 = mt76_rr(dev, MT_INT1_SOURCE_CSR); - intr1 &= dev->mt76.mmio.irqmask; - mt76_wr(dev, MT_INT1_SOURCE_CSR, intr1); - - intr |= intr1; - } - - trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask); - - mask = intr & MT_INT_RX_DONE_ALL; - if (intr & MT_INT_TX_DONE_MCU) - mask |= MT_INT_TX_DONE_MCU; + hif_idx++; + if (!pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x7916, NULL) && + !pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x790a, NULL)) + return NULL; - mt7915_irq_disable(dev, mask); + writel(hif_idx | MT_PCIE_RECOG_ID_SEM, + pcim_iomap_table(pdev)[0] + MT_PCIE_RECOG_ID); - if (intr & MT_INT_TX_DONE_MCU) - napi_schedule(&dev->mt76.tx_napi); - - if (intr & MT_INT_RX_DONE_DATA0) - napi_schedule(&dev->mt76.napi[MT_RXQ_MAIN]); - - if (intr & MT_INT_RX_DONE_DATA1) - napi_schedule(&dev->mt76.napi[MT_RXQ_EXT]); - - if (intr & MT_INT_RX_DONE_WM) - napi_schedule(&dev->mt76.napi[MT_RXQ_MCU]); - - if (intr & MT_INT_RX_DONE_WA) - napi_schedule(&dev->mt76.napi[MT_RXQ_MCU_WA]); - - if (intr & MT_INT_RX_DONE_WA_EXT) - napi_schedule(&dev->mt76.napi[MT_RXQ_EXT_WA]); - - if (intr & MT_INT_MCU_CMD) { - u32 val = mt76_rr(dev, MT_MCU_CMD); - - mt76_wr(dev, MT_MCU_CMD, val); - if (val & MT_MCU_CMD_ERROR_MASK) { - dev->reset_state = val; - ieee80211_queue_work(mt76_hw(dev), &dev->reset_work); - wake_up(&dev->reset_wait); - } - } -} - -static irqreturn_t mt7915_irq_handler(int irq, void *dev_instance) -{ - struct mt7915_dev *dev = dev_instance; - - mt76_wr(dev, MT_INT_MASK_CSR, 0); - if (dev->hif2) - mt76_wr(dev, MT_INT1_MASK_CSR, 0); - - if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state)) - return IRQ_NONE; - - tasklet_schedule(&dev->irq_tasklet); - - return IRQ_HANDLED; -} - -static void mt7915_pci_init_hif2(struct mt7915_dev *dev) -{ - struct mt7915_hif *hif; - - dev->hif_idx = ++hif_idx; - if (!pci_get_device(PCI_VENDOR_ID_MEDIATEK, 0x7916, NULL)) - return; - - mt76_wr(dev, MT_PCIE_RECOG_ID, dev->hif_idx | MT_PCIE_RECOG_ID_SEM); - - hif = mt7915_pci_get_hif2(dev); - if (!hif) - return; - - dev->hif2 = hif; - - mt76_wr(dev, MT_INT1_MASK_CSR, 0); - - if (devm_request_irq(dev->mt76.dev, hif->irq, mt7915_irq_handler, - IRQF_SHARED, KBUILD_MODNAME "-hif", dev)) { - mt7915_put_hif2(hif); - hif = NULL; - } - - /* master switch of PCIe tnterrupt enable */ - mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0xff); + return mt7915_pci_get_hif2(hif_idx); } static int mt7915_pci_hif2_probe(struct pci_dev *pdev) @@ -219,26 +95,10 @@ static int mt7915_pci_hif2_probe(struct pci_dev *pdev) static int mt7915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - static const struct mt76_driver_ops drv_ops = { - /* txwi_size = txd size + txp size */ - .txwi_size = MT_TXD_SIZE + sizeof(struct mt7915_txp), - .drv_flags = MT_DRV_TXWI_NO_FREE | MT_DRV_HW_MGMT_TXQ, - .survey_flags = SURVEY_INFO_TIME_TX | - SURVEY_INFO_TIME_RX | - SURVEY_INFO_TIME_BSS_RX, - .token_size = MT7915_TOKEN_SIZE, - .tx_prepare_skb = mt7915_tx_prepare_skb, - .tx_complete_skb = mt7915_tx_complete_skb, - .rx_skb = mt7915_queue_rx_skb, - .rx_check = mt7915_rx_check, - .rx_poll_complete = mt7915_rx_poll_complete, - .sta_ps = mt7915_sta_ps, - .sta_add = mt7915_mac_sta_add, - .sta_remove = mt7915_mac_sta_remove, - .update_survey = mt7915_update_channel, - }; struct mt7915_dev *dev; struct mt76_dev *mdev; + struct mt7915_hif *hif2; + int irq; int ret; ret = pcim_enable_device(pdev); @@ -257,48 +117,65 @@ static int mt7915_pci_probe(struct pci_dev *pdev, mt76_pci_disable_aspm(pdev); - if (id->device == 0x7916) + if (id->device == 0x7916 || id->device == 0x790a) return mt7915_pci_hif2_probe(pdev); - mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt7915_ops, - &drv_ops); - if (!mdev) - return -ENOMEM; + dev = mt7915_mmio_probe(&pdev->dev, pcim_iomap_table(pdev)[0], + id->device); + if (IS_ERR(dev)) + return PTR_ERR(dev); - dev = container_of(mdev, struct mt7915_dev, mt76); + mdev = &dev->mt76; + hif2 = mt7915_pci_init_hif2(pdev); ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) - goto free; + goto free_device; - ret = mt7915_mmio_init(mdev, pcim_iomap_table(pdev)[0], pdev->irq); + irq = pdev->irq; + ret = devm_request_irq(mdev->dev, irq, mt7915_irq_handler, + IRQF_SHARED, KBUILD_MODNAME, dev); if (ret) - goto error; - - tasklet_setup(&dev->irq_tasklet, mt7915_irq_tasklet); + goto free_irq_vector; mt76_wr(dev, MT_INT_MASK_CSR, 0); /* master switch of PCIe tnterrupt enable */ mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff); - ret = devm_request_irq(mdev->dev, pdev->irq, mt7915_irq_handler, - IRQF_SHARED, KBUILD_MODNAME, dev); - if (ret) - goto error; + if (hif2) { + dev->hif2 = hif2; - mt7915_pci_init_hif2(dev); + mt76_wr(dev, MT_INT1_MASK_CSR, 0); + /* master switch of PCIe tnterrupt enable */ + if (is_mt7915(mdev)) + mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE, 0xff); + else + mt76_wr(dev, MT_PCIE1_MAC_INT_ENABLE_MT7916, 0xff); + + ret = devm_request_irq(mdev->dev, dev->hif2->irq, + mt7915_irq_handler, IRQF_SHARED, + KBUILD_MODNAME "-hif", dev); + if (ret) + goto free_hif2; + } ret = mt7915_register_device(dev); if (ret) - goto free_irq; + goto free_hif2_irq; return 0; -free_irq: - devm_free_irq(mdev->dev, pdev->irq, dev); -error: + +free_hif2_irq: + if (dev->hif2) + devm_free_irq(mdev->dev, dev->hif2->irq, dev); +free_hif2: + if (dev->hif2) + put_device(dev->hif2->dev); + devm_free_irq(mdev->dev, irq, dev); +free_irq_vector: pci_free_irq_vectors(pdev); -free: +free_device: mt76_free_device(&dev->mt76); return ret; @@ -322,47 +199,25 @@ static void mt7915_pci_remove(struct pci_dev *pdev) mt7915_unregister_device(dev); } -static struct pci_driver mt7915_hif_driver = { +struct pci_driver mt7915_hif_driver = { .name = KBUILD_MODNAME "_hif", .id_table = mt7915_hif_device_table, .probe = mt7915_pci_probe, .remove = mt7915_hif_remove, }; -static struct pci_driver mt7915_pci_driver = { +struct pci_driver mt7915_pci_driver = { .name = KBUILD_MODNAME, .id_table = mt7915_pci_device_table, .probe = mt7915_pci_probe, .remove = mt7915_pci_remove, }; -static int __init mt7915_init(void) -{ - int ret; - - ret = pci_register_driver(&mt7915_hif_driver); - if (ret) - return ret; - - ret = pci_register_driver(&mt7915_pci_driver); - if (ret) - pci_unregister_driver(&mt7915_hif_driver); - - return ret; -} - -static void __exit mt7915_exit(void) -{ - pci_unregister_driver(&mt7915_pci_driver); - pci_unregister_driver(&mt7915_hif_driver); -} - -module_init(mt7915_init); -module_exit(mt7915_exit); - MODULE_DEVICE_TABLE(pci, mt7915_pci_device_table); MODULE_DEVICE_TABLE(pci, mt7915_hif_device_table); MODULE_FIRMWARE(MT7915_FIRMWARE_WA); MODULE_FIRMWARE(MT7915_FIRMWARE_WM); MODULE_FIRMWARE(MT7915_ROM_PATCH); -MODULE_LICENSE("Dual BSD/GPL"); +MODULE_FIRMWARE(MT7916_FIRMWARE_WA); +MODULE_FIRMWARE(MT7916_FIRMWARE_WM); +MODULE_FIRMWARE(MT7916_ROM_PATCH); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h index 59693535b098..6a0f68180396 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h @@ -4,41 +4,146 @@ #ifndef __MT7915_REGS_H #define __MT7915_REGS_H +struct __map { + u32 phys; + u32 maps; + u32 size; +}; + +/* used to differentiate between generations */ +struct mt7915_reg_desc { + const u32 *reg_rev; + const u32 *offs_rev; + const struct __map *map; + u32 map_size; +}; + +enum reg_rev { + INT_SOURCE_CSR, + INT_MASK_CSR, + INT1_SOURCE_CSR, + INT1_MASK_CSR, + INT_MCU_CMD_SOURCE, + INT_MCU_CMD_EVENT, + __MT_REG_MAX, +}; + +enum offs_rev { + TMAC_CDTR, + TMAC_ODTR, + TMAC_ATCR, + TMAC_TRCR0, + TMAC_ICR0, + TMAC_ICR1, + TMAC_CTCR0, + TMAC_TFCR0, + MDP_BNRCFR0, + MDP_BNRCFR1, + ARB_DRNGR0, + ARB_SCR, + RMAC_MIB_AIRTIME14, + AGG_AWSCR0, + AGG_PCR0, + AGG_ACR0, + AGG_MRCR, + AGG_ATCR1, + AGG_ATCR3, + LPON_UTTR0, + LPON_UTTR1, + LPON_FRCR, + MIB_SDR3, + MIB_SDR4, + MIB_SDR5, + MIB_SDR7, + MIB_SDR8, + MIB_SDR9, + MIB_SDR10, + MIB_SDR11, + MIB_SDR12, + MIB_SDR13, + MIB_SDR14, + MIB_SDR15, + MIB_SDR16, + MIB_SDR17, + MIB_SDR18, + MIB_SDR19, + MIB_SDR20, + MIB_SDR21, + MIB_SDR22, + MIB_SDR23, + MIB_SDR24, + MIB_SDR25, + MIB_SDR27, + MIB_SDR28, + MIB_SDR29, + MIB_SDRVEC, + MIB_SDR31, + MIB_SDR32, + MIB_SDRMUBF, + MIB_DR8, + MIB_DR9, + MIB_DR11, + MIB_MB_SDR0, + MIB_MB_SDR1, + TX_AGG_CNT, + TX_AGG_CNT2, + MIB_ARNG, + WTBLON_TOP_WDUCR, + WTBL_UPDATE, + PLE_FL_Q_EMPTY, + PLE_FL_Q_CTRL, + PLE_AC_QEMPTY, + PLE_FREEPG_CNT, + PLE_FREEPG_HEAD_TAIL, + PLE_PG_HIF_GROUP, + PLE_HIF_PG_INFO, + AC_OFFSET, + __MT_OFFS_MAX, +}; + +#define __REG(id) (dev->reg.reg_rev[(id)]) +#define __OFFS(id) (dev->reg.offs_rev[(id)]) + /* MCU WFDMA0 */ #define MT_MCU_WFDMA0_BASE 0x2000 #define MT_MCU_WFDMA0(ofs) (MT_MCU_WFDMA0_BASE + (ofs)) + #define MT_MCU_WFDMA0_DUMMY_CR MT_MCU_WFDMA0(0x120) /* MCU WFDMA1 */ #define MT_MCU_WFDMA1_BASE 0x3000 #define MT_MCU_WFDMA1(ofs) (MT_MCU_WFDMA1_BASE + (ofs)) -#define MT_MCU_INT_EVENT MT_MCU_WFDMA1(0x108) +#define MT_MCU_INT_EVENT __REG(INT_MCU_CMD_EVENT) #define MT_MCU_INT_EVENT_DMA_STOPPED BIT(0) #define MT_MCU_INT_EVENT_DMA_INIT BIT(1) #define MT_MCU_INT_EVENT_SER_TRIGGER BIT(2) #define MT_MCU_INT_EVENT_RESET_DONE BIT(3) -#define MT_PLE_BASE 0x8000 +/* PLE */ +#define MT_PLE_BASE 0x820c0000 #define MT_PLE(ofs) (MT_PLE_BASE + (ofs)) -#define MT_FL_Q_EMPTY 0x0b0 -#define MT_FL_Q0_CTRL 0x1b0 -#define MT_FL_Q2_CTRL 0x1b8 -#define MT_FL_Q3_CTRL 0x1bc - -#define MT_PLE_FREEPG_CNT MT_PLE(0x100) -#define MT_PLE_FREEPG_HEAD_TAIL MT_PLE(0x104) -#define MT_PLE_PG_HIF_GROUP MT_PLE(0x110) -#define MT_PLE_HIF_PG_INFO MT_PLE(0x114) -#define MT_PLE_AC_QEMPTY(ac, n) MT_PLE(0x500 + 0x40 * (ac) + \ - ((n) << 2)) +#define MT_FL_Q_EMPTY MT_PLE(__OFFS(PLE_FL_Q_EMPTY)) +#define MT_FL_Q0_CTRL MT_PLE(__OFFS(PLE_FL_Q_CTRL)) +#define MT_FL_Q2_CTRL MT_PLE(__OFFS(PLE_FL_Q_CTRL) + 0x8) +#define MT_FL_Q3_CTRL MT_PLE(__OFFS(PLE_FL_Q_CTRL) + 0xc) + +#define MT_PLE_FREEPG_CNT MT_PLE(__OFFS(PLE_FREEPG_CNT)) +#define MT_PLE_FREEPG_HEAD_TAIL MT_PLE(__OFFS(PLE_FREEPG_HEAD_TAIL)) +#define MT_PLE_PG_HIF_GROUP MT_PLE(__OFFS(PLE_PG_HIF_GROUP)) +#define MT_PLE_HIF_PG_INFO MT_PLE(__OFFS(PLE_HIF_PG_INFO)) + +#define MT_PLE_AC_QEMPTY(ac, n) MT_PLE(__OFFS(PLE_AC_QEMPTY) + \ + __OFFS(AC_OFFSET) * \ + (ac) + ((n) << 2)) #define MT_PLE_AMSDU_PACK_MSDU_CNT(n) MT_PLE(0x10e0 + ((n) << 2)) -#define MT_PSE_BASE 0xc000 +#define MT_PSE_BASE 0x820c8000 #define MT_PSE(ofs) (MT_PSE_BASE + (ofs)) -#define MT_MDP_BASE 0xf000 +/* WF MDP TOP */ +#define MT_MDP_BASE 0x820cd000 #define MT_MDP(ofs) (MT_MDP_BASE + (ofs)) #define MT_MDP_DCR0 MT_MDP(0x000) @@ -47,63 +152,66 @@ #define MT_MDP_DCR1 MT_MDP(0x004) #define MT_MDP_DCR1_MAX_RX_LEN GENMASK(15, 3) -#define MT_MDP_BNRCFR0(_band) MT_MDP(0x070 + ((_band) << 8)) +#define MT_MDP_BNRCFR0(_band) MT_MDP(__OFFS(MDP_BNRCFR0) + \ + ((_band) << 8)) #define MT_MDP_RCFR0_MCU_RX_MGMT GENMASK(5, 4) #define MT_MDP_RCFR0_MCU_RX_CTL_NON_BAR GENMASK(7, 6) #define MT_MDP_RCFR0_MCU_RX_CTL_BAR GENMASK(9, 8) -#define MT_MDP_BNRCFR1(_band) MT_MDP(0x074 + ((_band) << 8)) +#define MT_MDP_BNRCFR1(_band) MT_MDP(__OFFS(MDP_BNRCFR1) + \ + ((_band) << 8)) #define MT_MDP_RCFR1_MCU_RX_BYPASS GENMASK(23, 22) #define MT_MDP_RCFR1_RX_DROPPED_UCAST GENMASK(28, 27) #define MT_MDP_RCFR1_RX_DROPPED_MCAST GENMASK(30, 29) #define MT_MDP_TO_HIF 0 #define MT_MDP_TO_WM 1 -/* TMAC: band 0(0x21000), band 1(0xa1000) */ -#define MT_WF_TMAC_BASE(_band) ((_band) ? 0xa1000 : 0x21000) +/* TMAC: band 0(0x820e4000), band 1(0x820f4000) */ +#define MT_WF_TMAC_BASE(_band) ((_band) ? 0x820f4000 : 0x820e4000) #define MT_WF_TMAC(_band, ofs) (MT_WF_TMAC_BASE(_band) + (ofs)) #define MT_TMAC_TCR0(_band) MT_WF_TMAC(_band, 0) #define MT_TMAC_TCR0_TX_BLINK GENMASK(7, 6) #define MT_TMAC_TCR0_TBTT_STOP_CTRL BIT(25) -#define MT_TMAC_CDTR(_band) MT_WF_TMAC(_band, 0x090) -#define MT_TMAC_ODTR(_band) MT_WF_TMAC(_band, 0x094) +#define MT_TMAC_CDTR(_band) MT_WF_TMAC(_band, __OFFS(TMAC_CDTR)) + #define MT_TMAC_ODTR(_band) MT_WF_TMAC(_band, __OFFS(TMAC_ODTR)) #define MT_TIMEOUT_VAL_PLCP GENMASK(15, 0) #define MT_TIMEOUT_VAL_CCA GENMASK(31, 16) -#define MT_TMAC_ATCR(_band) MT_WF_TMAC(_band, 0x098) +#define MT_TMAC_ATCR(_band) MT_WF_TMAC(_band, __OFFS(TMAC_ATCR)) #define MT_TMAC_ATCR_TXV_TOUT GENMASK(7, 0) -#define MT_TMAC_TRCR0(_band) MT_WF_TMAC(_band, 0x09c) +#define MT_TMAC_TRCR0(_band) MT_WF_TMAC(_band, __OFFS(TMAC_TRCR0)) #define MT_TMAC_TRCR0_TR2T_CHK GENMASK(8, 0) #define MT_TMAC_TRCR0_I2T_CHK GENMASK(24, 16) -#define MT_TMAC_ICR0(_band) MT_WF_TMAC(_band, 0x0a4) -#define MT_IFS_EIFS_OFDM GENMASK(8, 0) +#define MT_TMAC_ICR0(_band) MT_WF_TMAC(_band, __OFFS(TMAC_ICR0)) +#define MT_IFS_EIFS_OFDM GENMASK(8, 0) #define MT_IFS_RIFS GENMASK(14, 10) #define MT_IFS_SIFS GENMASK(22, 16) #define MT_IFS_SLOT GENMASK(30, 24) -#define MT_TMAC_ICR1(_band) MT_WF_TMAC(_band, 0x0b4) +#define MT_TMAC_ICR1(_band) MT_WF_TMAC(_band, __OFFS(TMAC_ICR1)) #define MT_IFS_EIFS_CCK GENMASK(8, 0) -#define MT_TMAC_CTCR0(_band) MT_WF_TMAC(_band, 0x0f4) +#define MT_TMAC_CTCR0(_band) MT_WF_TMAC(_band, __OFFS(TMAC_CTCR0)) #define MT_TMAC_CTCR0_INS_DDLMT_REFTIME GENMASK(5, 0) #define MT_TMAC_CTCR0_INS_DDLMT_EN BIT(17) #define MT_TMAC_CTCR0_INS_DDLMT_VHT_SMPDU_EN BIT(18) -#define MT_TMAC_TFCR0(_band) MT_WF_TMAC(_band, 0x1e0) +#define MT_TMAC_TFCR0(_band) MT_WF_TMAC(_band, __OFFS(TMAC_TFCR0)) -#define MT_WF_DMA_BASE(_band) ((_band) ? 0xa1e00 : 0x21e00) +/* WF DMA TOP: band 0(0x820e7000),band 1(0x820f7000) */ +#define MT_WF_DMA_BASE(_band) ((_band) ? 0x820f7000 : 0x820e7000) #define MT_WF_DMA(_band, ofs) (MT_WF_DMA_BASE(_band) + (ofs)) #define MT_DMA_DCR0(_band) MT_WF_DMA(_band, 0x000) #define MT_DMA_DCR0_MAX_RX_LEN GENMASK(15, 3) #define MT_DMA_DCR0_RXD_G5_EN BIT(23) -/* ETBF: band 0(0x24000), band 1(0xa4000) */ -#define MT_WF_ETBF_BASE(_band) ((_band) ? 0xa4000 : 0x24000) +/* ETBF: band 0(0x820ea000), band 1(0x820fa000) */ +#define MT_WF_ETBF_BASE(_band) ((_band) ? 0x820fa000 : 0x820ea000) #define MT_WF_ETBF(_band, ofs) (MT_WF_ETBF_BASE(_band) + (ofs)) #define MT_ETBF_TX_NDP_BFRP(_band) MT_WF_ETBF(_band, 0x040) @@ -125,174 +233,196 @@ #define MT_ETBF_RX_FB_VHT GENMASK(15, 8) #define MT_ETBF_RX_FB_HT GENMASK(7, 0) -/* LPON: band 0(0x24200), band 1(0xa4200) */ -#define MT_WF_LPON_BASE(_band) ((_band) ? 0xa4200 : 0x24200) +/* LPON: band 0(0x820eb000), band 1(0x820fb000) */ +#define MT_WF_LPON_BASE(_band) ((_band) ? 0x820fb000 : 0x820eb000) #define MT_WF_LPON(_band, ofs) (MT_WF_LPON_BASE(_band) + (ofs)) -#define MT_LPON_UTTR0(_band) MT_WF_LPON(_band, 0x080) -#define MT_LPON_UTTR1(_band) MT_WF_LPON(_band, 0x084) +#define MT_LPON_UTTR0(_band) MT_WF_LPON(_band, __OFFS(LPON_UTTR0)) +#define MT_LPON_UTTR1(_band) MT_WF_LPON(_band, __OFFS(LPON_UTTR1)) +#define MT_LPON_FRCR(_band) MT_WF_LPON(_band, __OFFS(LPON_FRCR)) -#define MT_LPON_TCR(_band, n) MT_WF_LPON(_band, 0x0a8 + (n) * 4) +#define MT_LPON_TCR(_band, n) MT_WF_LPON(_band, 0x0a8 + \ + (((n) * 4) << 1)) +#define MT_LPON_TCR_MT7916(_band, n) MT_WF_LPON(_band, 0x0a8 + \ + (((n) * 4) << 4)) #define MT_LPON_TCR_SW_MODE GENMASK(1, 0) #define MT_LPON_TCR_SW_WRITE BIT(0) #define MT_LPON_TCR_SW_ADJUST BIT(1) #define MT_LPON_TCR_SW_READ GENMASK(1, 0) -/* MIB: band 0(0x24800), band 1(0xa4800) */ +/* MIB: band 0(0x820ed000), band 1(0x820fd000) */ /* These counters are (mostly?) clear-on-read. So, some should not * be read at all in case firmware is already reading them. These * are commented with 'DNR' below. The DNR stats will be read by querying * the firmware API for the appropriate message. For counters the driver * does read, the driver should accumulate the counters. */ -#define MT_WF_MIB_BASE(_band) ((_band) ? 0xa4800 : 0x24800) +#define MT_WF_MIB_BASE(_band) ((_band) ? 0x820fd000 : 0x820ed000) #define MT_WF_MIB(_band, ofs) (MT_WF_MIB_BASE(_band) + (ofs)) #define MT_MIB_SDR0(_band) MT_WF_MIB(_band, 0x010) #define MT_MIB_SDR0_BERACON_TX_CNT_MASK GENMASK(15, 0) -#define MT_MIB_SDR3(_band) MT_WF_MIB(_band, 0x014) +#define MT_MIB_SDR3(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR3)) #define MT_MIB_SDR3_FCS_ERR_MASK GENMASK(15, 0) +#define MT_MIB_SDR3_FCS_ERR_MASK_MT7916 GENMASK(31, 16) -#define MT_MIB_SDR4(_band) MT_WF_MIB(_band, 0x018) +#define MT_MIB_SDR4(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR4)) #define MT_MIB_SDR4_RX_FIFO_FULL_MASK GENMASK(15, 0) /* rx mpdu counter, full 32 bits */ -#define MT_MIB_SDR5(_band) MT_WF_MIB(_band, 0x01c) +#define MT_MIB_SDR5(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR5)) #define MT_MIB_SDR6(_band) MT_WF_MIB(_band, 0x020) #define MT_MIB_SDR6_CHANNEL_IDL_CNT_MASK GENMASK(15, 0) -#define MT_MIB_SDR7(_band) MT_WF_MIB(_band, 0x024) +#define MT_MIB_SDR7(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR7)) #define MT_MIB_SDR7_RX_VECTOR_MISMATCH_CNT_MASK GENMASK(15, 0) -#define MT_MIB_SDR8(_band) MT_WF_MIB(_band, 0x028) +#define MT_MIB_SDR8(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR8)) #define MT_MIB_SDR8_RX_DELIMITER_FAIL_CNT_MASK GENMASK(15, 0) /* aka CCA_NAV_TX_TIME */ -#define MT_MIB_SDR9_DNR(_band) MT_WF_MIB(_band, 0x02c) -#define MT_MIB_SDR9_CCA_BUSY_TIME_MASK GENMASK(23, 0) +#define MT_MIB_SDR9_DNR(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR9)) +#define MT_MIB_SDR9_CCA_BUSY_TIME_MASK GENMASK(23, 0) -#define MT_MIB_SDR10_DNR(_band) MT_WF_MIB(_band, 0x030) -#define MT_MIB_SDR10_MRDY_COUNT_MASK GENMASK(25, 0) +#define MT_MIB_SDR10_DNR(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR10)) +#define MT_MIB_SDR10_MRDY_COUNT_MASK GENMASK(25, 0) +#define MT_MIB_SDR10_MRDY_COUNT_MASK_MT7916 GENMASK(31, 0) -#define MT_MIB_SDR11(_band) MT_WF_MIB(_band, 0x034) +#define MT_MIB_SDR11(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR11)) #define MT_MIB_SDR11_RX_LEN_MISMATCH_CNT_MASK GENMASK(15, 0) /* tx ampdu cnt, full 32 bits */ -#define MT_MIB_SDR12(_band) MT_WF_MIB(_band, 0x038) +#define MT_MIB_SDR12(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR12)) -#define MT_MIB_SDR13(_band) MT_WF_MIB(_band, 0x03c) +#define MT_MIB_SDR13(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR13)) #define MT_MIB_SDR13_TX_STOP_Q_EMPTY_CNT_MASK GENMASK(15, 0) /* counts all mpdus in ampdu, regardless of success */ -#define MT_MIB_SDR14(_band) MT_WF_MIB(_band, 0x040) +#define MT_MIB_SDR14(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR14)) #define MT_MIB_SDR14_TX_MPDU_ATTEMPTS_CNT_MASK GENMASK(23, 0) +#define MT_MIB_SDR14_TX_MPDU_ATTEMPTS_CNT_MASK_MT7916 GENMASK(31, 0) /* counts all successfully tx'd mpdus in ampdu */ -#define MT_MIB_SDR15(_band) MT_WF_MIB(_band, 0x044) +#define MT_MIB_SDR15(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR15)) #define MT_MIB_SDR15_TX_MPDU_SUCCESS_CNT_MASK GENMASK(23, 0) +#define MT_MIB_SDR15_TX_MPDU_SUCCESS_CNT_MASK_MT7916 GENMASK(31, 0) /* in units of 'us' */ -#define MT_MIB_SDR16_DNR(_band) MT_WF_MIB(_band, 0x048) +#define MT_MIB_SDR16_DNR(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR16)) #define MT_MIB_SDR16_PRIMARY_CCA_BUSY_TIME_MASK GENMASK(23, 0) -#define MT_MIB_SDR17_DNR(_band) MT_WF_MIB(_band, 0x04c) +#define MT_MIB_SDR17_DNR(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR17)) #define MT_MIB_SDR17_SECONDARY_CCA_BUSY_TIME_MASK GENMASK(23, 0) -#define MT_MIB_SDR18(_band) MT_WF_MIB(_band, 0x050) +#define MT_MIB_SDR18(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR18)) #define MT_MIB_SDR18_PRIMARY_ENERGY_DETECT_TIME_MASK GENMASK(23, 0) /* units are us */ -#define MT_MIB_SDR19_DNR(_band) MT_WF_MIB(_band, 0x054) +#define MT_MIB_SDR19_DNR(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR19)) #define MT_MIB_SDR19_CCK_MDRDY_TIME_MASK GENMASK(23, 0) -#define MT_MIB_SDR20_DNR(_band) MT_WF_MIB(_band, 0x058) +#define MT_MIB_SDR20_DNR(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR20)) #define MT_MIB_SDR20_OFDM_VHT_MDRDY_TIME_MASK GENMASK(23, 0) -#define MT_MIB_SDR21_DNR(_band) MT_WF_MIB(_band, 0x05c) +#define MT_MIB_SDR21_DNR(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR21)) #define MT_MIB_SDR20_GREEN_MDRDY_TIME_MASK GENMASK(23, 0) /* rx ampdu count, 32-bit */ -#define MT_MIB_SDR22(_band) MT_WF_MIB(_band, 0x060) +#define MT_MIB_SDR22(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR22)) /* rx ampdu bytes count, 32-bit */ -#define MT_MIB_SDR23(_band) MT_WF_MIB(_band, 0x064) +#define MT_MIB_SDR23(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR23)) /* rx ampdu valid subframe count */ -#define MT_MIB_SDR24(_band) MT_WF_MIB(_band, 0x068) +#define MT_MIB_SDR24(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR24)) #define MT_MIB_SDR24_RX_AMPDU_SF_CNT_MASK GENMASK(23, 0) +#define MT_MIB_SDR24_RX_AMPDU_SF_CNT_MASK_MT7916 GENMASK(31, 0) /* rx ampdu valid subframe bytes count, 32bits */ -#define MT_MIB_SDR25(_band) MT_WF_MIB(_band, 0x06c) +#define MT_MIB_SDR25(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR25)) /* remaining windows protected stats */ -#define MT_MIB_SDR27(_band) MT_WF_MIB(_band, 0x074) +#define MT_MIB_SDR27(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR27)) #define MT_MIB_SDR27_TX_RWP_FAIL_CNT_MASK GENMASK(15, 0) -#define MT_MIB_SDR28(_band) MT_WF_MIB(_band, 0x078) +#define MT_MIB_SDR28(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR28)) #define MT_MIB_SDR28_TX_RWP_NEED_CNT_MASK GENMASK(15, 0) -#define MT_MIB_SDR29(_band) MT_WF_MIB(_band, 0x07c) -#define MT_MIB_SDR29_RX_PFDROP_CNT_MASK GENMASK(7, 0) +#define MT_MIB_SDR29(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR29)) +#define MT_MIB_SDR29_RX_PFDROP_CNT_MASK GENMASK(7, 0) +#define MT_MIB_SDR29_RX_PFDROP_CNT_MASK_MT7916 GENMASK(15, 0) -#define MT_MIB_SDR30(_band) MT_WF_MIB(_band, 0x080) +#define MT_MIB_SDRVEC(_band) MT_WF_MIB(_band, __OFFS(MIB_SDRVEC)) #define MT_MIB_SDR30_RX_VEC_QUEUE_OVERFLOW_DROP_CNT_MASK GENMASK(15, 0) +#define MT_MIB_SDR30_RX_VEC_QUEUE_OVERFLOW_DROP_CNT_MASK_MT7916 GENMASK(31, 16) /* rx blockack count, 32 bits */ -#define MT_MIB_SDR31(_band) MT_WF_MIB(_band, 0x084) +#define MT_MIB_SDR31(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR31)) -#define MT_MIB_SDR32(_band) MT_WF_MIB(_band, 0x088) +#define MT_MIB_SDR32(_band) MT_WF_MIB(_band, __OFFS(MIB_SDR32)) #define MT_MIB_SDR32_TX_PKT_EBF_CNT_MASK GENMASK(15, 0) -#define MT_MIB_SDR33(_band) MT_WF_MIB(_band, 0x08c) -#define MT_MIB_SDR33_TX_PKT_IBF_CNT_MASK GENMASK(15, 0) +#define MT_MIB_SDR33(_band) MT_WF_MIB(_band, 0x088) +#define MT_MIB_SDR32_TX_PKT_IBF_CNT_MASK GENMASK(15, 0) +#define MT_MIB_SDR32_TX_PKT_IBF_CNT_MASK_MT7916 GENMASK(31, 16) -#define MT_MIB_SDR34(_band) MT_WF_MIB(_band, 0x090) +#define MT_MIB_SDRMUBF(_band) MT_WF_MIB(_band, __OFFS(MIB_SDRMUBF)) #define MT_MIB_MU_BF_TX_CNT GENMASK(15, 0) /* 36, 37 both DNR */ -#define MT_MIB_DR8(_band) MT_WF_MIB(_band, 0x0c0) -#define MT_MIB_DR9(_band) MT_WF_MIB(_band, 0x0c4) -#define MT_MIB_DR11(_band) MT_WF_MIB(_band, 0x0cc) +#define MT_MIB_DR8(_band) MT_WF_MIB(_band, __OFFS(MIB_DR8)) +#define MT_MIB_DR9(_band) MT_WF_MIB(_band, __OFFS(MIB_DR9)) +#define MT_MIB_DR11(_band) MT_WF_MIB(_band, __OFFS(MIB_DR11)) -#define MT_MIB_MB_SDR0(_band, n) MT_WF_MIB(_band, 0x100 + ((n) << 4)) +#define MT_MIB_MB_SDR0(_band, n) MT_WF_MIB(_band, __OFFS(MIB_MB_SDR0) + (n)) #define MT_MIB_RTS_RETRIES_COUNT_MASK GENMASK(31, 16) #define MT_MIB_RTS_COUNT_MASK GENMASK(15, 0) -#define MT_MIB_MB_SDR1(_band, n) MT_WF_MIB(_band, 0x104 + ((n) << 4)) +#define MT_MIB_MB_SDR1(_band, n) MT_WF_MIB(_band, __OFFS(MIB_MB_SDR1) + (n)) #define MT_MIB_BA_MISS_COUNT_MASK GENMASK(15, 0) #define MT_MIB_ACK_FAIL_COUNT_MASK GENMASK(31, 16) -#define MT_TX_AGG_CNT(_band, n) MT_WF_MIB(_band, 0x0a8 + ((n) << 2)) -#define MT_TX_AGG_CNT2(_band, n) MT_WF_MIB(_band, 0x164 + ((n) << 2)) -#define MT_MIB_ARNG(_band, n) MT_WF_MIB(_band, 0x4b8 + ((n) << 2)) +#define MT_MIB_MB_SDR2(_band, n) MT_WF_MIB(_band, 0x518 + (n)) +#define MT_MIB_MB_BFTF(_band, n) MT_WF_MIB(_band, 0x510 + (n)) + +#define MT_TX_AGG_CNT(_band, n) MT_WF_MIB(_band, __OFFS(TX_AGG_CNT) + \ + ((n) << 2)) +#define MT_TX_AGG_CNT2(_band, n) MT_WF_MIB(_band, __OFFS(TX_AGG_CNT2) + \ + ((n) << 2)) +#define MT_MIB_ARNG(_band, n) MT_WF_MIB(_band, __OFFS(MIB_ARNG) + \ + ((n) << 2)) #define MT_MIB_ARNCR_RANGE(val, n) (((val) >> ((n) << 3)) & GENMASK(7, 0)) -#define MT_WTBLON_TOP_BASE 0x34000 +/* WTBLON TOP */ +#define MT_WTBLON_TOP_BASE 0x820d4000 #define MT_WTBLON_TOP(ofs) (MT_WTBLON_TOP_BASE + (ofs)) -#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(0x0) +#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(__OFFS(WTBLON_TOP_WDUCR)) #define MT_WTBLON_TOP_WDUCR_GROUP GENMASK(2, 0) -#define MT_WTBL_UPDATE MT_WTBLON_TOP(0x030) +#define MT_WTBL_UPDATE MT_WTBLON_TOP(__OFFS(WTBL_UPDATE)) #define MT_WTBL_UPDATE_WLAN_IDX GENMASK(9, 0) #define MT_WTBL_UPDATE_ADM_COUNT_CLEAR BIT(12) #define MT_WTBL_UPDATE_BUSY BIT(31) -#define MT_WTBL_BASE 0x38000 +/* WTBL */ +#define MT_WTBL_BASE 0x820d8000 #define MT_WTBL_LMAC_ID GENMASK(14, 8) #define MT_WTBL_LMAC_DW GENMASK(7, 2) #define MT_WTBL_LMAC_OFFS(_id, _dw) (MT_WTBL_BASE | \ - FIELD_PREP(MT_WTBL_LMAC_ID, _id) | \ - FIELD_PREP(MT_WTBL_LMAC_DW, _dw)) + FIELD_PREP(MT_WTBL_LMAC_ID, _id) | \ + FIELD_PREP(MT_WTBL_LMAC_DW, _dw)) -/* AGG: band 0(0x20800), band 1(0xa0800) */ -#define MT_WF_AGG_BASE(_band) ((_band) ? 0xa0800 : 0x20800) +/* AGG: band 0(0x820e2000), band 1(0x820f2000) */ +#define MT_WF_AGG_BASE(_band) ((_band) ? 0x820f2000 : 0x820e2000) #define MT_WF_AGG(_band, ofs) (MT_WF_AGG_BASE(_band) + (ofs)) -#define MT_AGG_AWSCR0(_band, _n) MT_WF_AGG(_band, 0x05c + (_n) * 4) -#define MT_AGG_PCR0(_band, _n) MT_WF_AGG(_band, 0x06c + (_n) * 4) +#define MT_AGG_AWSCR0(_band, _n) MT_WF_AGG(_band, (__OFFS(AGG_AWSCR0) + \ + (_n) * 4)) +#define MT_AGG_PCR0(_band, _n) MT_WF_AGG(_band, (__OFFS(AGG_PCR0) + \ + (_n) * 4)) #define MT_AGG_PCR0_MM_PROT BIT(0) #define MT_AGG_PCR0_GF_PROT BIT(1) #define MT_AGG_PCR0_BW20_PROT BIT(2) @@ -305,31 +435,32 @@ #define MT_AGG_PCR1_RTS0_NUM_THRES GENMASK(31, 23) #define MT_AGG_PCR1_RTS0_LEN_THRES GENMASK(19, 0) -#define MT_AGG_ACR0(_band) MT_WF_AGG(_band, 0x084) +#define MT_AGG_ACR0(_band) MT_WF_AGG(_band, __OFFS(AGG_ACR0)) #define MT_AGG_ACR_CFEND_RATE GENMASK(13, 0) #define MT_AGG_ACR_BAR_RATE GENMASK(29, 16) -#define MT_AGG_MRCR(_band) MT_WF_AGG(_band, 0x098) -#define MT_AGG_MRCR_BAR_CNT_LIMIT GENMASK(15, 12) -#define MT_AGG_MRCR_LAST_RTS_CTS_RN BIT(6) -#define MT_AGG_MRCR_RTS_FAIL_LIMIT GENMASK(11, 7) +#define MT_AGG_MRCR(_band) MT_WF_AGG(_band, __OFFS(AGG_MRCR)) +#define MT_AGG_MRCR_BAR_CNT_LIMIT GENMASK(15, 12) +#define MT_AGG_MRCR_LAST_RTS_CTS_RN BIT(6) +#define MT_AGG_MRCR_RTS_FAIL_LIMIT GENMASK(11, 7) #define MT_AGG_MRCR_TXCMD_RTS_FAIL_LIMIT GENMASK(28, 24) -#define MT_AGG_ATCR1(_band) MT_WF_AGG(_band, 0x0f0) -#define MT_AGG_ATCR3(_band) MT_WF_AGG(_band, 0x0f4) +#define MT_AGG_ATCR1(_band) MT_WF_AGG(_band, __OFFS(AGG_ATCR1)) +#define MT_AGG_ATCR3(_band) MT_WF_AGG(_band, __OFFS(AGG_ATCR3)) -/* ARB: band 0(0x20c00), band 1(0xa0c00) */ -#define MT_WF_ARB_BASE(_band) ((_band) ? 0xa0c00 : 0x20c00) +/* ARB: band 0(0x820e3000), band 1(0x820f3000) */ +#define MT_WF_ARB_BASE(_band) ((_band) ? 0x820f3000 : 0x820e3000) #define MT_WF_ARB(_band, ofs) (MT_WF_ARB_BASE(_band) + (ofs)) -#define MT_ARB_SCR(_band) MT_WF_ARB(_band, 0x080) +#define MT_ARB_SCR(_band) MT_WF_ARB(_band, __OFFS(ARB_SCR)) #define MT_ARB_SCR_TX_DISABLE BIT(8) #define MT_ARB_SCR_RX_DISABLE BIT(9) -#define MT_ARB_DRNGR0(_band, _n) MT_WF_ARB(_band, 0x194 + (_n) * 4) +#define MT_ARB_DRNGR0(_band, _n) MT_WF_ARB(_band, (__OFFS(ARB_DRNGR0) + \ + (_n) * 4)) -/* RMAC: band 0(0x21400), band 1(0xa1400) */ -#define MT_WF_RMAC_BASE(_band) ((_band) ? 0xa1400 : 0x21400) +/* RMAC: band 0(0x820e5000), band 1(0x820f5000) */ +#define MT_WF_RMAC_BASE(_band) ((_band) ? 0x820f5000 : 0x820e5000) #define MT_WF_RMAC(_band, ofs) (MT_WF_RMAC_BASE(_band) + (ofs)) #define MT_WF_RFCR(_band) MT_WF_RMAC(_band, 0x000) @@ -381,15 +512,14 @@ #define MT_WFDMA0_GLO_CFG MT_WFDMA0(0x208) #define MT_WFDMA0_GLO_CFG_TX_DMA_EN BIT(0) #define MT_WFDMA0_GLO_CFG_RX_DMA_EN BIT(2) +#define MT_WFDMA0_GLO_CFG_OMIT_TX_INFO BIT(28) +#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO BIT(27) +#define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2 BIT(21) #define MT_WFDMA0_RST_DTX_PTR MT_WFDMA0(0x20c) #define MT_WFDMA0_PRI_DLY_INT_CFG0 MT_WFDMA0(0x2f0) - -#define MT_RX_DATA_RING_BASE MT_WFDMA0(0x500) - -#define MT_WFDMA0_RX_RING0_EXT_CTRL MT_WFDMA0(0x680) -#define MT_WFDMA0_RX_RING1_EXT_CTRL MT_WFDMA0(0x684) -#define MT_WFDMA0_RX_RING2_EXT_CTRL MT_WFDMA0(0x688) +#define MT_WFDMA0_PRI_DLY_INT_CFG1 MT_WFDMA0(0x2f4) +#define MT_WFDMA0_PRI_DLY_INT_CFG2 MT_WFDMA0(0x2f8) /* WFDMA1 */ #define MT_WFDMA1_BASE 0xd5000 @@ -404,129 +534,167 @@ #define MT_WFDMA1_BUSY_ENA_TX_FIFO1 BIT(1) #define MT_WFDMA1_BUSY_ENA_RX_FIFO BIT(2) -#define MT_MCU_CMD MT_WFDMA1(0x1f0) -#define MT_MCU_CMD_STOP_DMA_FW_RELOAD BIT(1) -#define MT_MCU_CMD_STOP_DMA BIT(2) -#define MT_MCU_CMD_RESET_DONE BIT(3) -#define MT_MCU_CMD_RECOVERY_DONE BIT(4) -#define MT_MCU_CMD_NORMAL_STATE BIT(5) -#define MT_MCU_CMD_ERROR_MASK GENMASK(5, 1) - #define MT_WFDMA1_GLO_CFG MT_WFDMA1(0x208) #define MT_WFDMA1_GLO_CFG_TX_DMA_EN BIT(0) #define MT_WFDMA1_GLO_CFG_RX_DMA_EN BIT(2) #define MT_WFDMA1_GLO_CFG_OMIT_TX_INFO BIT(28) #define MT_WFDMA1_GLO_CFG_OMIT_RX_INFO BIT(27) +#define MT_WFDMA1_GLO_CFG_OMIT_RX_INFO_PFET2 BIT(21) #define MT_WFDMA1_RST_DTX_PTR MT_WFDMA1(0x20c) #define MT_WFDMA1_PRI_DLY_INT_CFG0 MT_WFDMA1(0x2f0) -#define MT_TX_RING_BASE MT_WFDMA1(0x300) -#define MT_RX_EVENT_RING_BASE MT_WFDMA1(0x500) - -#define MT_WFDMA1_TX_RING0_EXT_CTRL MT_WFDMA1(0x600) -#define MT_WFDMA1_TX_RING1_EXT_CTRL MT_WFDMA1(0x604) -#define MT_WFDMA1_TX_RING2_EXT_CTRL MT_WFDMA1(0x608) -#define MT_WFDMA1_TX_RING3_EXT_CTRL MT_WFDMA1(0x60c) -#define MT_WFDMA1_TX_RING4_EXT_CTRL MT_WFDMA1(0x610) -#define MT_WFDMA1_TX_RING5_EXT_CTRL MT_WFDMA1(0x614) -#define MT_WFDMA1_TX_RING6_EXT_CTRL MT_WFDMA1(0x618) -#define MT_WFDMA1_TX_RING7_EXT_CTRL MT_WFDMA1(0x61c) - -#define MT_WFDMA1_TX_RING16_EXT_CTRL MT_WFDMA1(0x640) -#define MT_WFDMA1_TX_RING17_EXT_CTRL MT_WFDMA1(0x644) -#define MT_WFDMA1_TX_RING18_EXT_CTRL MT_WFDMA1(0x648) -#define MT_WFDMA1_TX_RING19_EXT_CTRL MT_WFDMA1(0x64c) -#define MT_WFDMA1_TX_RING20_EXT_CTRL MT_WFDMA1(0x650) -#define MT_WFDMA1_TX_RING21_EXT_CTRL MT_WFDMA1(0x654) -#define MT_WFDMA1_TX_RING22_EXT_CTRL MT_WFDMA1(0x658) -#define MT_WFDMA1_TX_RING23_EXT_CTRL MT_WFDMA1(0x65c) - -#define MT_WFDMA1_RX_RING0_EXT_CTRL MT_WFDMA1(0x680) -#define MT_WFDMA1_RX_RING1_EXT_CTRL MT_WFDMA1(0x684) -#define MT_WFDMA1_RX_RING2_EXT_CTRL MT_WFDMA1(0x688) -#define MT_WFDMA1_RX_RING3_EXT_CTRL MT_WFDMA1(0x68c) - /* WFDMA CSR */ #define MT_WFDMA_EXT_CSR_BASE 0xd7000 #define MT_WFDMA_EXT_CSR(ofs) (MT_WFDMA_EXT_CSR_BASE + (ofs)) -#define MT_INT_SOURCE_CSR MT_WFDMA_EXT_CSR(0x10) -#define MT_INT_MASK_CSR MT_WFDMA_EXT_CSR(0x14) -#define MT_INT_RX_DONE_DATA0 BIT(16) -#define MT_INT_RX_DONE_DATA1 BIT(17) -#define MT_INT_RX_DONE_WM BIT(0) -#define MT_INT_RX_DONE_WA BIT(1) -#define MT_INT_RX_DONE_WA_EXT BIT(2) -#define MT_INT_RX_DONE_ALL (GENMASK(2, 0) | GENMASK(17, 16)) -#define MT_INT_TX_DONE_MCU_WA BIT(15) -#define MT_INT_TX_DONE_FWDL BIT(26) -#define MT_INT_TX_DONE_MCU_WM BIT(27) -#define MT_INT_TX_DONE_BAND0 BIT(30) -#define MT_INT_TX_DONE_BAND1 BIT(31) - -#define MT_INT_BAND1_MASK (MT_INT_RX_DONE_WA_EXT | \ - MT_INT_TX_DONE_BAND1) - -#define MT_INT_MCU_CMD BIT(29) - -#define MT_INT_TX_DONE_MCU (MT_INT_TX_DONE_MCU_WA | \ - MT_INT_TX_DONE_MCU_WM | \ - MT_INT_TX_DONE_FWDL) - #define MT_WFDMA_HOST_CONFIG MT_WFDMA_EXT_CSR(0x30) #define MT_WFDMA_HOST_CONFIG_PDMA_BAND BIT(0) #define MT_WFDMA_EXT_CSR_HIF_MISC MT_WFDMA_EXT_CSR(0x44) #define MT_WFDMA_EXT_CSR_HIF_MISC_BUSY BIT(0) -#define MT_INT1_SOURCE_CSR MT_WFDMA_EXT_CSR(0x88) -#define MT_INT1_MASK_CSR MT_WFDMA_EXT_CSR(0x8c) - -#define MT_PCIE_RECOG_ID MT_WFDMA_EXT_CSR(0x90) +#define MT_PCIE_RECOG_ID 0xd7090 #define MT_PCIE_RECOG_ID_MASK GENMASK(30, 0) #define MT_PCIE_RECOG_ID_SEM BIT(31) /* WFDMA0 PCIE1 */ -#define MT_WFDMA0_PCIE1_BASE 0xd8000 -#define MT_WFDMA0_PCIE1(ofs) (MT_WFDMA0_PCIE1_BASE + (ofs)) +#define MT_WFDMA0_PCIE1_BASE 0xd8000 +#define MT_WFDMA0_PCIE1(ofs) (MT_WFDMA0_PCIE1_BASE + (ofs)) -#define MT_WFDMA0_PCIE1_BUSY_ENA MT_WFDMA0_PCIE1(0x13c) +#define MT_WFDMA0_PCIE1_BUSY_ENA MT_WFDMA0_PCIE1(0x13c) #define MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO0 BIT(0) #define MT_WFDMA0_PCIE1_BUSY_ENA_TX_FIFO1 BIT(1) #define MT_WFDMA0_PCIE1_BUSY_ENA_RX_FIFO BIT(2) /* WFDMA1 PCIE1 */ -#define MT_WFDMA1_PCIE1_BASE 0xd9000 -#define MT_WFDMA1_PCIE1(ofs) (MT_WFDMA0_PCIE1_BASE + (ofs)) +#define MT_WFDMA1_PCIE1_BASE 0xd9000 +#define MT_WFDMA1_PCIE1(ofs) (MT_WFDMA1_PCIE1_BASE + (ofs)) -#define MT_WFDMA1_PCIE1_BUSY_ENA MT_WFDMA1_PCIE1(0x13c) +#define MT_WFDMA1_PCIE1_BUSY_ENA MT_WFDMA1_PCIE1(0x13c) #define MT_WFDMA1_PCIE1_BUSY_ENA_TX_FIFO0 BIT(0) #define MT_WFDMA1_PCIE1_BUSY_ENA_TX_FIFO1 BIT(1) #define MT_WFDMA1_PCIE1_BUSY_ENA_RX_FIFO BIT(2) -#define MT_TOP_RGU_BASE 0xf0000 -#define MT_TOP_PWR_CTRL (MT_TOP_RGU_BASE + (0x0)) -#define MT_TOP_PWR_KEY (0x5746 << 16) -#define MT_TOP_PWR_SW_RST BIT(0) -#define MT_TOP_PWR_SW_PWR_ON GENMASK(3, 2) -#define MT_TOP_PWR_HW_CTRL BIT(4) -#define MT_TOP_PWR_PWR_ON BIT(7) +/* WFDMA COMMON */ +#define __RXQ(q) ((q) + __MT_MCUQ_MAX) +#define __TXQ(q) (__RXQ(q) + __MT_RXQ_MAX) + +#define MT_Q_ID(q) (dev->q_id[(q)]) +#define MT_Q_BASE(q) ((dev->wfdma_mask >> (q)) & 0x1 ? \ + MT_WFDMA1_BASE : MT_WFDMA0_BASE) + +#define MT_MCUQ_ID(q) MT_Q_ID(q) +#define MT_TXQ_ID(q) MT_Q_ID(__TXQ(q)) +#define MT_RXQ_ID(q) MT_Q_ID(__RXQ(q)) + +#define MT_MCUQ_RING_BASE(q) (MT_Q_BASE(q) + 0x300) +#define MT_TXQ_RING_BASE(q) (MT_Q_BASE(__TXQ(q)) + 0x300) +#define MT_RXQ_RING_BASE(q) (MT_Q_BASE(__RXQ(q)) + 0x500) + +#define MT_MCUQ_EXT_CTRL(q) (MT_Q_BASE(q) + 0x600 + \ + MT_MCUQ_ID(q)* 0x4) +#define MT_RXQ_EXT_CTRL(q) (MT_Q_BASE(__RXQ(q)) + 0x680 + \ + MT_RXQ_ID(q)* 0x4) +#define MT_TXQ_EXT_CTRL(q) (MT_Q_BASE(__TXQ(q)) + 0x600 + \ + MT_TXQ_ID(q)* 0x4) + +#define MT_INT_SOURCE_CSR __REG(INT_SOURCE_CSR) +#define MT_INT_MASK_CSR __REG(INT_MASK_CSR) + +#define MT_INT1_SOURCE_CSR __REG(INT1_SOURCE_CSR) +#define MT_INT1_MASK_CSR __REG(INT1_MASK_CSR) + +#define MT_INT_RX_DONE_BAND0 BIT(16) +#define MT_INT_RX_DONE_BAND1 BIT(17) +#define MT_INT_RX_DONE_WM BIT(0) +#define MT_INT_RX_DONE_WA BIT(1) +#define MT_INT_RX_DONE_WA_MAIN BIT(1) +#define MT_INT_RX_DONE_WA_EXT BIT(2) +#define MT_INT_MCU_CMD BIT(29) +#define MT_INT_RX_DONE_BAND0_MT7916 BIT(22) +#define MT_INT_RX_DONE_BAND1_MT7916 BIT(23) +#define MT_INT_RX_DONE_WA_MAIN_MT7916 BIT(2) +#define MT_INT_RX_DONE_WA_EXT_MT7916 BIT(3) + +#define MT_INT_RX(q) (dev->q_int_mask[__RXQ(q)]) +#define MT_INT_TX_MCU(q) (dev->q_int_mask[(q)]) + +#define MT_INT_RX_DONE_MCU (MT_INT_RX(MT_RXQ_MCU) | \ + MT_INT_RX(MT_RXQ_MCU_WA)) + +#define MT_INT_BAND0_RX_DONE (MT_INT_RX(MT_RXQ_MAIN) | \ + MT_INT_RX(MT_RXQ_MAIN_WA)) + +#define MT_INT_BAND1_RX_DONE (MT_INT_RX(MT_RXQ_EXT) | \ + MT_INT_RX(MT_RXQ_EXT_WA) | \ + MT_INT_RX(MT_RXQ_MAIN_WA)) + +#define MT_INT_RX_DONE_ALL (MT_INT_RX_DONE_MCU | \ + MT_INT_BAND0_RX_DONE | \ + MT_INT_BAND1_RX_DONE) + +#define MT_INT_TX_DONE_FWDL BIT(26) +#define MT_INT_TX_DONE_MCU_WM BIT(27) +#define MT_INT_TX_DONE_MCU_WA BIT(15) +#define MT_INT_TX_DONE_BAND0 BIT(30) +#define MT_INT_TX_DONE_BAND1 BIT(31) +#define MT_INT_TX_DONE_MCU_WA_MT7916 BIT(25) + +#define MT_INT_TX_DONE_MCU (MT_INT_TX_MCU(MT_MCUQ_WA) | \ + MT_INT_TX_MCU(MT_MCUQ_WM) | \ + MT_INT_TX_MCU(MT_MCUQ_FWDL)) -#define MT_INFRA_CFG_BASE 0xf1000 -#define MT_INFRA(ofs) (MT_INFRA_CFG_BASE + (ofs)) +#define MT_MCU_CMD __REG(INT_MCU_CMD_SOURCE) +#define MT_MCU_CMD_STOP_DMA_FW_RELOAD BIT(1) +#define MT_MCU_CMD_STOP_DMA BIT(2) +#define MT_MCU_CMD_RESET_DONE BIT(3) +#define MT_MCU_CMD_RECOVERY_DONE BIT(4) +#define MT_MCU_CMD_NORMAL_STATE BIT(5) +#define MT_MCU_CMD_ERROR_MASK GENMASK(5, 1) -#define MT_HIF_REMAP_L1 MT_INFRA(0x1ac) +/* TOP RGU */ +#define MT_TOP_RGU_BASE 0x18000000 +#define MT_TOP_PWR_CTRL (MT_TOP_RGU_BASE + (0x0)) +#define MT_TOP_PWR_KEY (0x5746 << 16) +#define MT_TOP_PWR_SW_RST BIT(0) +#define MT_TOP_PWR_SW_PWR_ON GENMASK(3, 2) +#define MT_TOP_PWR_HW_CTRL BIT(4) +#define MT_TOP_PWR_PWR_ON BIT(7) + +/* l1/l2 remap */ +#define MT_HIF_REMAP_L1 0xf11ac +#define MT_HIF_REMAP_L1_MT7916 0xfe260 #define MT_HIF_REMAP_L1_MASK GENMASK(15, 0) #define MT_HIF_REMAP_L1_OFFSET GENMASK(15, 0) #define MT_HIF_REMAP_L1_BASE GENMASK(31, 16) #define MT_HIF_REMAP_BASE_L1 0xe0000 -#define MT_HIF_REMAP_L2 MT_INFRA(0x1b0) +#define MT_HIF_REMAP_L2 0xf11b0 #define MT_HIF_REMAP_L2_MASK GENMASK(19, 0) #define MT_HIF_REMAP_L2_OFFSET GENMASK(11, 0) #define MT_HIF_REMAP_L2_BASE GENMASK(31, 12) -#define MT_HIF_REMAP_BASE_L2 0x00000 +#define MT_HIF_REMAP_L2_MT7916 0x1b8 +#define MT_HIF_REMAP_L2_MASK_MT7916 GENMASK(31, 16) +#define MT_HIF_REMAP_L2_OFFSET_MT7916 GENMASK(15, 0) +#define MT_HIF_REMAP_L2_BASE_MT7916 GENMASK(31, 16) +#define MT_HIF_REMAP_BASE_L2_MT7916 0x40000 + +#define MT_INFRA_BASE 0x18000000 +#define MT_WFSYS0_PHY_START 0x18400000 +#define MT_WFSYS1_PHY_START 0x18800000 +#define MT_WFSYS1_PHY_END 0x18bfffff +#define MT_CBTOP1_PHY_START 0x70000000 +#define MT_CBTOP1_PHY_END 0x7fffffff +#define MT_CBTOP2_PHY_START 0xf0000000 +#define MT_CBTOP2_PHY_END 0xffffffff + +/* FW MODE SYNC */ +#define MT_SWDEF_MODE 0x41f23c +#define MT_SWDEF_MODE_MT7916 0x41143c +#define MT_SWDEF_NORMAL_MODE 0 +#define MT_SWDEF_ICAP_MODE 1 +#define MT_SWDEF_SPECTRUM_MODE 2 #define MT_DIC_CMD_REG_BASE 0x41f000 #define MT_DIC_CMD_REG(ofs) (MT_DIC_CMD_REG_BASE + (ofs)) @@ -540,13 +708,7 @@ #define MT_CPU_UTIL_PEAK_IDLE_CNT MT_CPU_UTIL(0x0c) #define MT_CPU_UTIL_CTRL MT_CPU_UTIL(0x1c) -#define MT_SWDEF_BASE 0x41f200 -#define MT_SWDEF(ofs) (MT_SWDEF_BASE + (ofs)) -#define MT_SWDEF_MODE MT_SWDEF(0x3c) -#define MT_SWDEF_NORMAL_MODE 0 -#define MT_SWDEF_ICAP_MODE 1 -#define MT_SWDEF_SPECTRUM_MODE 2 - +/* LED */ #define MT_LED_TOP_BASE 0x18013000 #define MT_LED_PHYS(_n) (MT_LED_TOP_BASE + (_n)) @@ -561,32 +723,44 @@ #define MT_LED_EN(_n) MT_LED_PHYS(0x40 + ((_n) * 4)) +#define MT_LED_GPIO_MUX2 0x70005058 /* GPIO 18 */ +#define MT_LED_GPIO_MUX3 0x7000505C /* GPIO 26 */ +#define MT_LED_GPIO_SEL_MASK GENMASK(11, 8) + +/* MT TOP */ #define MT_TOP_BASE 0x18060000 #define MT_TOP(ofs) (MT_TOP_BASE + (ofs)) -#define MT_TOP_LPCR_HOST_BAND0 MT_TOP(0x10) +#define MT_TOP_LPCR_HOST_BAND(_band) MT_TOP(0x10 + ((_band) * 0x10)) #define MT_TOP_LPCR_HOST_FW_OWN BIT(0) #define MT_TOP_LPCR_HOST_DRV_OWN BIT(1) +#define MT_TOP_LPCR_HOST_FW_OWN_STAT BIT(2) + +#define MT_TOP_LPCR_HOST_BAND_IRQ_STAT(_band) MT_TOP(0x14 + ((_band) * 0x10)) +#define MT_TOP_LPCR_HOST_BAND_STAT BIT(0) #define MT_TOP_MISC MT_TOP(0xf0) #define MT_TOP_MISC_FW_STATE GENMASK(2, 0) -#define MT_LED_GPIO_MUX2 0x70005058 /* GPIO 18 */ -#define MT_LED_GPIO_MUX3 0x7000505C /* GPIO 26 */ -#define MT_LED_GPIO_SEL_MASK GENMASK(11, 8) - #define MT_HW_BOUND 0x70010020 -#define MT_HW_CHIPID 0x70010200 #define MT_HW_REV 0x70010204 +#define MT_WF_SUBSYS_RST 0x70002600 -#define MT_PCIE1_MAC_BASE 0x74020000 -#define MT_PCIE1_MAC(ofs) (MT_PCIE1_MAC_BASE + (ofs)) -#define MT_PCIE1_MAC_INT_ENABLE MT_PCIE1_MAC(0x188) - +/* PCIE MAC */ #define MT_PCIE_MAC_BASE 0x74030000 #define MT_PCIE_MAC(ofs) (MT_PCIE_MAC_BASE + (ofs)) #define MT_PCIE_MAC_INT_ENABLE MT_PCIE_MAC(0x188) +#define MT_PCIE1_MAC_INT_ENABLE 0x74020188 +#define MT_PCIE1_MAC_INT_ENABLE_MT7916 0x74090188 + +/* PP TOP */ +#define MT_WF_PP_TOP_BASE 0x820cc000 +#define MT_WF_PP_TOP(ofs) (MT_WF_PP_TOP_BASE + (ofs)) + +#define MT_WF_PP_TOP_RXQ_WFDMA_CF_5 MT_WF_PP_TOP(0x0e8) +#define MT_WF_PP_TOP_RXQ_QID6_WFDMA_HIF_SEL_MASK BIT(6) + #define MT_WF_IRPI_BASE 0x83006000 #define MT_WF_IRPI(ofs) (MT_WF_IRPI_BASE + ((ofs) << 16)) @@ -600,7 +774,7 @@ #define MT_WF_PHY_RXTD12(_phy) MT_WF_PHY(0x8230 + ((_phy) << 16)) #define MT_WF_PHY_RXTD12_IRPI_SW_CLR_ONLY BIT(18) -#define MT_WF_PHY_RXTD12_IRPI_SW_CLR BIT(29) +#define MT_WF_PHY_RXTD12_IRPI_SW_CLR BIT(29) #define MT_MCU_WM_CIRQ_BASE 0x89010000 #define MT_MCU_WM_CIRQ(ofs) (MT_MCU_WM_CIRQ_BASE + (ofs)) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c index af80c2cf8c83..83da21d15ddd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c @@ -23,30 +23,16 @@ struct reg_band { u32 band[2]; }; -#define REG_BAND(_reg) \ - { .band[0] = MT_##_reg(0), .band[1] = MT_##_reg(1) } -#define REG_BAND_IDX(_reg, _idx) \ - { .band[0] = MT_##_reg(0, _idx), .band[1] = MT_##_reg(1, _idx) } - -static const struct reg_band reg_backup_list[] = { - REG_BAND_IDX(AGG_PCR0, 0), - REG_BAND_IDX(AGG_PCR0, 1), - REG_BAND_IDX(AGG_AWSCR0, 0), - REG_BAND_IDX(AGG_AWSCR0, 1), - REG_BAND_IDX(AGG_AWSCR0, 2), - REG_BAND_IDX(AGG_AWSCR0, 3), - REG_BAND(AGG_MRCR), - REG_BAND(TMAC_TFCR0), - REG_BAND(TMAC_TCR0), - REG_BAND(AGG_ATCR1), - REG_BAND(AGG_ATCR3), - REG_BAND(TMAC_TRCR0), - REG_BAND(TMAC_ICR0), - REG_BAND_IDX(ARB_DRNGR0, 0), - REG_BAND_IDX(ARB_DRNGR0, 1), - REG_BAND(WF_RFCR), - REG_BAND(WF_RFCR1), -}; +#define REG_BAND(_list, _reg) \ + { _list.band[0] = MT_##_reg(0); \ + _list.band[1] = MT_##_reg(1); } +#define REG_BAND_IDX(_list, _reg, _idx) \ + { _list.band[0] = MT_##_reg(0, _idx); \ + _list.band[1] = MT_##_reg(1, _idx); } + +#define TM_REG_MAX_ID 17 +static struct reg_band reg_backup_list[TM_REG_MAX_ID]; + static int mt7915_tm_set_tx_power(struct mt7915_phy *phy) @@ -264,7 +250,7 @@ done: mt7915_tm_set_slot_time(phy, slot_time, sifs); return mt7915_tm_set_wmm_qid(dev, - mt7915_lmac_mapping(dev, IEEE80211_AC_BE), + mt76_connac_lmac_mapping(IEEE80211_AC_BE), aifsn, cw, cw, 0); } @@ -355,6 +341,24 @@ mt7915_tm_reg_backup_restore(struct mt7915_phy *phy) u32 *b = phy->test.reg_backup; int i; + REG_BAND_IDX(reg_backup_list[0], AGG_PCR0, 0); + REG_BAND_IDX(reg_backup_list[1], AGG_PCR0, 1); + REG_BAND_IDX(reg_backup_list[2], AGG_AWSCR0, 0); + REG_BAND_IDX(reg_backup_list[3], AGG_AWSCR0, 1); + REG_BAND_IDX(reg_backup_list[4], AGG_AWSCR0, 2); + REG_BAND_IDX(reg_backup_list[5], AGG_AWSCR0, 3); + REG_BAND(reg_backup_list[6], AGG_MRCR); + REG_BAND(reg_backup_list[7], TMAC_TFCR0); + REG_BAND(reg_backup_list[8], TMAC_TCR0); + REG_BAND(reg_backup_list[9], AGG_ATCR1); + REG_BAND(reg_backup_list[10], AGG_ATCR3); + REG_BAND(reg_backup_list[11], TMAC_TRCR0); + REG_BAND(reg_backup_list[12], TMAC_ICR0); + REG_BAND_IDX(reg_backup_list[13], ARB_DRNGR0, 0); + REG_BAND_IDX(reg_backup_list[14], ARB_DRNGR0, 1); + REG_BAND(reg_backup_list[15], WF_RFCR); + REG_BAND(reg_backup_list[16], WF_RFCR1); + if (phy->mt76->test.state == MT76_TM_STATE_OFF) { for (i = 0; i < n_regs; i++) mt76_wr(dev, reg_backup_list[i].band[ext_phy], b[i]); @@ -725,6 +729,7 @@ mt7915_tm_dump_stats(struct mt76_phy *mphy, struct sk_buff *msg) void *rx, *rssi; u16 fcs_err; int i; + u32 cnt; rx = nla_nest_start(msg, MT76_TM_STATS_ATTR_LAST_RX); if (!rx) @@ -768,8 +773,10 @@ mt7915_tm_dump_stats(struct mt76_phy *mphy, struct sk_buff *msg) nla_nest_end(msg, rx); - fcs_err = mt76_get_field(dev, MT_MIB_SDR3(ext_phy), - MT_MIB_SDR3_FCS_ERR_MASK); + cnt = mt76_rr(dev, MT_MIB_SDR3(ext_phy)); + fcs_err = is_mt7915(&dev->mt76) ? FIELD_GET(MT_MIB_SDR3_FCS_ERR_MASK, cnt) : + FIELD_GET(MT_MIB_SDR3_FCS_ERR_MASK_MT7916, cnt); + q = ext_phy ? MT_RXQ_EXT : MT_RXQ_MAIN; mphy->test.rx_stats.packets[q] += fcs_err; mphy->test.rx_stats.fcs_error[q] += fcs_err; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c index 86fd7292b229..dd04909d980a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c @@ -262,14 +262,6 @@ mt7921_txpwr(struct seq_file *s, void *data) return 0; } -static void -mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) -{ - struct mt7921_dev *dev = priv; - - mt7921_mcu_set_beacon_filter(dev, vif, dev->pm.enable); -} - static int mt7921_pm_set(void *data, u64 val) { @@ -278,10 +270,10 @@ mt7921_pm_set(void *data, u64 val) mutex_lock(&dev->mt76.mutex); - if (val == pm->enable) + if (val == pm->enable_user) goto out; - if (!pm->enable) { + if (!pm->enable_user) { pm->stats.last_wake_event = jiffies; pm->stats.last_doze_event = jiffies; } @@ -291,13 +283,8 @@ mt7921_pm_set(void *data, u64 val) pm->enable = false; mt76_connac_pm_wake(&dev->mphy, pm); - ieee80211_iterate_active_interfaces(mt76_hw(dev), - IEEE80211_IFACE_ITER_RESUME_ALL, - mt7921_pm_interface_iter, dev); - - mt76_connac_mcu_set_deep_sleep(&dev->mt76, pm->ds_enable); - - pm->enable = val; + pm->enable_user = val; + mt7921_set_runtime_pm(dev); mt76_connac_power_save_sched(&dev->mphy, pm); out: mutex_unlock(&dev->mt76.mutex); @@ -310,7 +297,7 @@ mt7921_pm_get(void *data, u64 *val) { struct mt7921_dev *dev = data; - *val = dev->pm.enable; + *val = dev->pm.enable_user; return 0; } @@ -322,13 +309,17 @@ mt7921_deep_sleep_set(void *data, u64 val) { struct mt7921_dev *dev = data; struct mt76_connac_pm *pm = &dev->pm; + bool monitor = !!(dev->mphy.hw->conf.flags & IEEE80211_CONF_MONITOR); bool enable = !!val; mt7921_mutex_acquire(dev); - if (pm->ds_enable != enable) { - mt76_connac_mcu_set_deep_sleep(&dev->mt76, enable); - pm->ds_enable = enable; - } + if (pm->ds_enable_user == enable) + goto out; + + pm->ds_enable_user = enable; + pm->ds_enable = enable && !monitor; + mt76_connac_mcu_set_deep_sleep(&dev->mt76, pm->ds_enable); +out: mt7921_mutex_release(dev); return 0; @@ -339,7 +330,7 @@ mt7921_deep_sleep_get(void *data, u64 *val) { struct mt7921_dev *dev = data; - *val = dev->pm.ds_enable; + *val = dev->pm.ds_enable_user; return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c index cdff1fd52d93..39d6ce4ecddd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c @@ -78,110 +78,6 @@ static void mt7921_dma_prefetch(struct mt7921_dev *dev) mt76_wr(dev, MT_WFDMA0_TX_RING17_EXT_CTRL, PREFETCH(0x380, 0x4)); } -static u32 __mt7921_reg_addr(struct mt7921_dev *dev, u32 addr) -{ - static const struct { - u32 phys; - u32 mapped; - u32 size; - } fixed_map[] = { - { 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */ - { 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */ - { 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */ - { 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */ - { 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */ - { 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */ - { 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */ - { 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */ - { 0x00400000, 0x80000, 0x10000 }, /* WF_MCU_SYSRAM */ - { 0x00410000, 0x90000, 0x10000 }, /* WF_MCU_SYSRAM (configure register) */ - { 0x40000000, 0x70000, 0x10000 }, /* WF_UMAC_SYSRAM */ - { 0x54000000, 0x02000, 0x1000 }, /* WFDMA PCIE0 MCU DMA0 */ - { 0x55000000, 0x03000, 0x1000 }, /* WFDMA PCIE0 MCU DMA1 */ - { 0x58000000, 0x06000, 0x1000 }, /* WFDMA PCIE1 MCU DMA0 (MEM_DMA) */ - { 0x59000000, 0x07000, 0x1000 }, /* WFDMA PCIE1 MCU DMA1 */ - { 0x7c000000, 0xf0000, 0x10000 }, /* CONN_INFRA */ - { 0x7c020000, 0xd0000, 0x10000 }, /* CONN_INFRA, WFDMA */ - { 0x7c060000, 0xe0000, 0x10000 }, /* CONN_INFRA, conn_host_csr_top */ - { 0x80020000, 0xb0000, 0x10000 }, /* WF_TOP_MISC_OFF */ - { 0x81020000, 0xc0000, 0x10000 }, /* WF_TOP_MISC_ON */ - { 0x820c0000, 0x08000, 0x4000 }, /* WF_UMAC_TOP (PLE) */ - { 0x820c8000, 0x0c000, 0x2000 }, /* WF_UMAC_TOP (PSE) */ - { 0x820cc000, 0x0e000, 0x1000 }, /* WF_UMAC_TOP (PP) */ - { 0x820cd000, 0x0f000, 0x1000 }, /* WF_MDP_TOP */ - { 0x820ce000, 0x21c00, 0x0200 }, /* WF_LMAC_TOP (WF_SEC) */ - { 0x820cf000, 0x22000, 0x1000 }, /* WF_LMAC_TOP (WF_PF) */ - { 0x820e0000, 0x20000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_CFG) */ - { 0x820e1000, 0x20400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_TRB) */ - { 0x820e9000, 0x23400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */ - { 0x820ea000, 0x24000, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_ETBF) */ - { 0x820ec000, 0x24600, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_INT) */ - { 0x820f0000, 0xa0000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_CFG) */ - { 0x820f1000, 0xa0600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_TRB) */ - { 0x820f2000, 0xa0800, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_AGG) */ - { 0x820f3000, 0xa0c00, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_ARB) */ - { 0x820f4000, 0xa1000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_TMAC) */ - { 0x820f5000, 0xa1400, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_RMAC) */ - { 0x820f7000, 0xa1e00, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_DMA) */ - { 0x820f9000, 0xa3400, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_WTBLOFF) */ - { 0x820fa000, 0xa4000, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_ETBF) */ - { 0x820fb000, 0xa4200, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_LPON) */ - { 0x820fc000, 0xa4600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_INT) */ - { 0x820fd000, 0xa4800, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_MIB) */ - }; - int i; - - if (addr < 0x100000) - return addr; - - for (i = 0; i < ARRAY_SIZE(fixed_map); i++) { - u32 ofs; - - if (addr < fixed_map[i].phys) - continue; - - ofs = addr - fixed_map[i].phys; - if (ofs > fixed_map[i].size) - continue; - - return fixed_map[i].mapped + ofs; - } - - if ((addr >= 0x18000000 && addr < 0x18c00000) || - (addr >= 0x70000000 && addr < 0x78000000) || - (addr >= 0x7c000000 && addr < 0x7c400000)) - return mt7921_reg_map_l1(dev, addr); - - dev_err(dev->mt76.dev, "Access currently unsupported address %08x\n", - addr); - - return 0; -} - -static u32 mt7921_rr(struct mt76_dev *mdev, u32 offset) -{ - struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); - u32 addr = __mt7921_reg_addr(dev, offset); - - return dev->bus_ops->rr(mdev, addr); -} - -static void mt7921_wr(struct mt76_dev *mdev, u32 offset, u32 val) -{ - struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); - u32 addr = __mt7921_reg_addr(dev, offset); - - dev->bus_ops->wr(mdev, addr, val); -} - -static u32 mt7921_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) -{ - struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); - u32 addr = __mt7921_reg_addr(dev, offset); - - return dev->bus_ops->rmw(mdev, addr, mask, val); -} - static int mt7921_dma_disable(struct mt7921_dev *dev, bool force) { if (force) { @@ -341,23 +237,8 @@ int mt7921_wpdma_reinit_cond(struct mt7921_dev *dev) int mt7921_dma_init(struct mt7921_dev *dev) { - struct mt76_bus_ops *bus_ops; int ret; - dev->phy.dev = dev; - dev->phy.mt76 = &dev->mt76.phy; - dev->mt76.phy.priv = &dev->phy; - dev->bus_ops = dev->mt76.bus; - bus_ops = devm_kmemdup(dev->mt76.dev, dev->bus_ops, sizeof(*bus_ops), - GFP_KERNEL); - if (!bus_ops) - return -ENOMEM; - - bus_ops->rr = mt7921_rr; - bus_ops->wr = mt7921_wr; - bus_ops->rmw = mt7921_rmw; - dev->mt76.bus = bus_ops; - mt76_dma_attach(&dev->mt76); ret = mt7921_dma_disable(dev, true); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c index ad59ef9839dc..fa6af85bba7b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c @@ -226,12 +226,10 @@ int mt7921_register_device(struct mt7921_dev *dev) dev->pm.idle_timeout = MT7921_PM_TIMEOUT; dev->pm.stats.last_wake_event = jiffies; dev->pm.stats.last_doze_event = jiffies; - - /* TODO: mt7921s run sleep mode on default */ - if (mt76_is_mmio(&dev->mt76)) { - dev->pm.enable = true; - dev->pm.ds_enable = true; - } + dev->pm.enable_user = true; + dev->pm.enable = true; + dev->pm.ds_enable_user = true; + dev->pm.ds_enable = true; if (mt76_is_sdio(&dev->mt76)) hw->extra_tx_headroom += MT_SDIO_TXD_SIZE + MT_SDIO_HDR_SIZE; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index ec10f95a4649..d17558349a17 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -116,7 +116,7 @@ void mt7921_mac_sta_poll(struct mt7921_dev *dev) sta = container_of((void *)msta, struct ieee80211_sta, drv_priv); for (i = 0; i < IEEE80211_NUM_ACS; i++) { - u8 q = mt7921_lmac_mapping(dev, i); + u8 q = mt76_connac_lmac_mapping(i); u32 tx_cur = tx_time[q]; u32 rx_cur = rx_time[q]; u8 tid = ac_to_tid[i]; @@ -308,7 +308,6 @@ mt7921_mac_decode_he_radiotap(struct sk_buff *skb, __le32 *rxv, u32 mode) he->data3 |= HE_PREP(DATA3_BEAM_CHANGE, BEAM_CHNG, rxv[14]) | HE_PREP(DATA3_UL_DL, UPLINK, rxv[2]); - he->data4 |= HE_PREP(DATA4_SU_MU_SPTL_REUSE, SR_MASK, rxv[11]); break; case MT_PHY_TYPE_HE_EXT_SU: he->data1 |= HE_BITS(DATA1_FORMAT_EXT_SU) | @@ -402,12 +401,12 @@ mt7921_mac_assoc_rssi(struct mt7921_dev *dev, struct sk_buff *skb) static int mt7921_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) { struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb; + struct ethhdr *eth_hdr = (struct ethhdr *)(skb->data + hdr_gap); struct mt7921_sta *msta = (struct mt7921_sta *)status->wcid; + __le32 *rxd = (__le32 *)skb->data; struct ieee80211_sta *sta; struct ieee80211_vif *vif; struct ieee80211_hdr hdr; - struct ethhdr eth_hdr; - __le32 *rxd = (__le32 *)skb->data; __le32 qos_ctrl, ht_ctrl; if (FIELD_GET(MT_RXD3_NORMAL_ADDR_TYPE, le32_to_cpu(rxd[3])) != @@ -424,7 +423,6 @@ static int mt7921_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv); /* store the info from RXD and ethhdr to avoid being overridden */ - memcpy(ð_hdr, skb->data + hdr_gap, sizeof(eth_hdr)); hdr.frame_control = FIELD_GET(MT_RXD6_FRAME_CONTROL, rxd[6]); hdr.seq_ctrl = FIELD_GET(MT_RXD8_SEQ_CTRL, rxd[8]); qos_ctrl = FIELD_GET(MT_RXD8_QOS_CTL, rxd[8]); @@ -439,24 +437,24 @@ static int mt7921_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap) ether_addr_copy(hdr.addr3, vif->bss_conf.bssid); break; case IEEE80211_FCTL_FROMDS: - ether_addr_copy(hdr.addr3, eth_hdr.h_source); + ether_addr_copy(hdr.addr3, eth_hdr->h_source); break; case IEEE80211_FCTL_TODS: - ether_addr_copy(hdr.addr3, eth_hdr.h_dest); + ether_addr_copy(hdr.addr3, eth_hdr->h_dest); break; case IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS: - ether_addr_copy(hdr.addr3, eth_hdr.h_dest); - ether_addr_copy(hdr.addr4, eth_hdr.h_source); + ether_addr_copy(hdr.addr3, eth_hdr->h_dest); + ether_addr_copy(hdr.addr4, eth_hdr->h_source); break; default: break; } skb_pull(skb, hdr_gap + sizeof(struct ethhdr) - 2); - if (eth_hdr.h_proto == htons(ETH_P_AARP) || - eth_hdr.h_proto == htons(ETH_P_IPX)) + if (eth_hdr->h_proto == cpu_to_be16(ETH_P_AARP) || + eth_hdr->h_proto == cpu_to_be16(ETH_P_IPX)) ether_addr_copy(skb_push(skb, ETH_ALEN), bridge_tunnel_header); - else if (eth_hdr.h_proto >= htons(ETH_P_802_3_MIN)) + else if (eth_hdr->h_proto >= cpu_to_be16(ETH_P_802_3_MIN)) ether_addr_copy(skb_push(skb, ETH_ALEN), rfc1042_header); else skb_pull(skb, 2); @@ -950,7 +948,7 @@ void mt7921_mac_write_txwi(struct mt7921_dev *dev, __le32 *txwi, } else { p_fmt = is_mmio ? MT_TX_TYPE_CT : MT_TX_TYPE_SF; q_idx = wmm_idx * MT7921_MAX_WMM_SETS + - mt7921_lmac_mapping(dev, skb_get_queue_mapping(skb)); + mt76_connac_lmac_mapping(skb_get_queue_mapping(skb)); } val = FIELD_PREP(MT_TXD0_TX_BYTES, skb->len + sz_txd) | @@ -1092,7 +1090,6 @@ mt7921_mac_add_txs_skb(struct mt7921_dev *dev, struct mt76_wcid *wcid, int pid, break; case MT_PHY_TYPE_HT: case MT_PHY_TYPE_HT_GF: - rate.mcs += (rate.nss - 1) * 8; if (rate.mcs > 31) goto out; @@ -1195,6 +1192,7 @@ void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data) out: rcu_read_unlock(); } +EXPORT_SYMBOL_GPL(mt7921_mac_add_txs); void mt7921_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb) @@ -1548,7 +1546,16 @@ void mt7921_pm_power_save_work(struct work_struct *work) delta = dev->pm.idle_timeout; if (test_bit(MT76_HW_SCANNING, &mphy->state) || - test_bit(MT76_HW_SCHED_SCANNING, &mphy->state)) + test_bit(MT76_HW_SCHED_SCANNING, &mphy->state) || + dev->fw_assert) + goto out; + + if (mutex_is_locked(&dev->mt76.mutex)) + /* if mt76 mutex is held we should not put the device + * to sleep since we are currently accessing device + * register map. We need to wait for the next power_save + * trigger. + */ goto out; if (time_is_after_jiffies(dev->pm.last_activity + delta)) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 7a8d2596c226..b6e836a4fad7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -273,6 +273,7 @@ static void mt7921_stop(struct ieee80211_hw *hw) cancel_delayed_work_sync(&dev->pm.ps_work); cancel_work_sync(&dev->pm.wake_work); + cancel_work_sync(&dev->reset_work); mt76_connac_free_pending_tx_skbs(&dev->pm, NULL); mt7921_mutex_acquire(dev); @@ -452,19 +453,46 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, mt76_wcid_key_setup(&dev->mt76, wcid, cmd == SET_KEY ? key : NULL); - err = mt7921_mcu_add_key(dev, vif, msta, key, cmd); + err = mt76_connac_mcu_add_key(&dev->mt76, vif, &msta->bip, + key, MCU_UNI_CMD(STA_REC_UPDATE), + &msta->wcid, cmd); if (err) goto out; if (key->cipher == WLAN_CIPHER_SUITE_WEP104 || key->cipher == WLAN_CIPHER_SUITE_WEP40) - err = mt7921_mcu_add_key(dev, vif, mvif->wep_sta, key, cmd); + err = mt76_connac_mcu_add_key(&dev->mt76, vif, + &mvif->wep_sta->bip, + key, MCU_UNI_CMD(STA_REC_UPDATE), + &mvif->wep_sta->wcid, cmd); out: mt7921_mutex_release(dev); return err; } +static void +mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) +{ + struct mt7921_dev *dev = priv; + + mt7921_mcu_set_beacon_filter(dev, vif, dev->pm.enable); +} + +void mt7921_set_runtime_pm(struct mt7921_dev *dev) +{ + struct ieee80211_hw *hw = dev->mphy.hw; + struct mt76_connac_pm *pm = &dev->pm; + bool monitor = !!(hw->conf.flags & IEEE80211_CONF_MONITOR); + + pm->enable = pm->enable_user && !monitor; + ieee80211_iterate_active_interfaces(hw, + IEEE80211_IFACE_ITER_RESUME_ALL, + mt7921_pm_interface_iter, dev); + pm->ds_enable = pm->ds_enable_user && !monitor; + mt76_connac_mcu_set_deep_sleep(&dev->mt76, pm->ds_enable); +} + static int mt7921_config(struct ieee80211_hw *hw, u32 changed) { struct mt7921_dev *dev = mt7921_hw_dev(hw); @@ -498,6 +526,7 @@ static int mt7921_config(struct ieee80211_hw *hw, u32 changed) mt76_rmw_field(dev, MT_DMA_DCR0(0), MT_DMA_DCR0_RXD_G5_EN, enabled); mt76_wr(dev, MT_WF_RFCR(0), phy->rxfilter); + mt7921_set_runtime_pm(dev); } out: @@ -510,11 +539,10 @@ static int mt7921_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 queue, const struct ieee80211_tx_queue_params *params) { - struct mt7921_dev *dev = mt7921_hw_dev(hw); struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; /* no need to update right away, we'll get BSS_CHANGED_QOS */ - queue = mt7921_lmac_mapping(dev, queue); + queue = mt76_connac_lmac_mapping(queue); mvif->queue_params[queue] = *params; return 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index ef1e1ef91611..33a836825cca 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -67,25 +67,6 @@ struct mt7921_fw_region { #define MT_STA_BFER BIT(0) #define MT_STA_BFEE BIT(1) -#define FW_FEATURE_SET_ENCRYPT BIT(0) -#define FW_FEATURE_SET_KEY_IDX GENMASK(2, 1) -#define FW_FEATURE_ENCRY_MODE BIT(4) -#define FW_FEATURE_OVERRIDE_ADDR BIT(5) - -#define DL_MODE_ENCRYPT BIT(0) -#define DL_MODE_KEY_IDX GENMASK(2, 1) -#define DL_MODE_RESET_SEC_IV BIT(3) -#define DL_MODE_WORKING_PDA_CR4 BIT(4) -#define DL_CONFIG_ENCRY_MODE_SEL BIT(6) -#define DL_MODE_NEED_RSP BIT(31) - -#define FW_START_OVERRIDE BIT(0) -#define FW_START_WORKING_PDA_CR4 BIT(2) - -#define PATCH_SEC_NOT_SUPPORT GENMASK(31, 0) -#define PATCH_SEC_TYPE_MASK GENMASK(15, 0) -#define PATCH_SEC_TYPE_INFO 0x2 - #define PATCH_SEC_ENC_TYPE_MASK GENMASK(31, 24) #define PATCH_SEC_ENC_TYPE_PLAIN 0x00 #define PATCH_SEC_ENC_TYPE_AES 0x01 @@ -93,52 +74,6 @@ struct mt7921_fw_region { #define PATCH_SEC_ENC_SCRAMBLE_INFO_MASK GENMASK(15, 0) #define PATCH_SEC_ENC_AES_KEY_MASK GENMASK(7, 0) -static enum mcu_cipher_type -mt7921_mcu_get_cipher(int cipher) -{ - switch (cipher) { - case WLAN_CIPHER_SUITE_WEP40: - return MCU_CIPHER_WEP40; - case WLAN_CIPHER_SUITE_WEP104: - return MCU_CIPHER_WEP104; - case WLAN_CIPHER_SUITE_TKIP: - return MCU_CIPHER_TKIP; - case WLAN_CIPHER_SUITE_AES_CMAC: - return MCU_CIPHER_BIP_CMAC_128; - case WLAN_CIPHER_SUITE_CCMP: - return MCU_CIPHER_AES_CCMP; - case WLAN_CIPHER_SUITE_CCMP_256: - return MCU_CIPHER_CCMP_256; - case WLAN_CIPHER_SUITE_GCMP: - return MCU_CIPHER_GCMP; - case WLAN_CIPHER_SUITE_GCMP_256: - return MCU_CIPHER_GCMP_256; - case WLAN_CIPHER_SUITE_SMS4: - return MCU_CIPHER_WAPI; - default: - return MCU_CIPHER_NONE; - } -} - -static u8 mt7921_mcu_chan_bw(struct cfg80211_chan_def *chandef) -{ - static const u8 width_to_bw[] = { - [NL80211_CHAN_WIDTH_40] = CMD_CBW_40MHZ, - [NL80211_CHAN_WIDTH_80] = CMD_CBW_80MHZ, - [NL80211_CHAN_WIDTH_80P80] = CMD_CBW_8080MHZ, - [NL80211_CHAN_WIDTH_160] = CMD_CBW_160MHZ, - [NL80211_CHAN_WIDTH_5] = CMD_CBW_5MHZ, - [NL80211_CHAN_WIDTH_10] = CMD_CBW_10MHZ, - [NL80211_CHAN_WIDTH_20] = CMD_CBW_20MHZ, - [NL80211_CHAN_WIDTH_20_NOHT] = CMD_CBW_20MHZ, - }; - - if (chandef->width >= ARRAY_SIZE(width_to_bw)) - return 0; - - return width_to_bw[chandef->width]; -} - static int mt7921_mcu_parse_eeprom(struct mt76_dev *dev, struct sk_buff *skb) { @@ -465,95 +400,6 @@ void mt7921_mcu_rx_event(struct mt7921_dev *dev, struct sk_buff *skb) } /** starec & wtbl **/ -static int -mt7921_mcu_sta_key_tlv(struct mt7921_sta *msta, struct sk_buff *skb, - struct ieee80211_key_conf *key, enum set_key_cmd cmd) -{ - struct mt7921_sta_key_conf *bip = &msta->bip; - struct sta_rec_sec *sec; - struct tlv *tlv; - u32 len = sizeof(*sec); - - tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_KEY_V2, sizeof(*sec)); - - sec = (struct sta_rec_sec *)tlv; - sec->add = cmd; - - if (cmd == SET_KEY) { - struct sec_key *sec_key; - u8 cipher; - - cipher = mt7921_mcu_get_cipher(key->cipher); - if (cipher == MCU_CIPHER_NONE) - return -EOPNOTSUPP; - - sec_key = &sec->key[0]; - sec_key->cipher_len = sizeof(*sec_key); - - if (cipher == MCU_CIPHER_BIP_CMAC_128) { - sec_key->cipher_id = MCU_CIPHER_AES_CCMP; - sec_key->key_id = bip->keyidx; - sec_key->key_len = 16; - memcpy(sec_key->key, bip->key, 16); - - sec_key = &sec->key[1]; - sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128; - sec_key->cipher_len = sizeof(*sec_key); - sec_key->key_len = 16; - memcpy(sec_key->key, key->key, 16); - - sec->n_cipher = 2; - } else { - sec_key->cipher_id = cipher; - sec_key->key_id = key->keyidx; - sec_key->key_len = key->keylen; - memcpy(sec_key->key, key->key, key->keylen); - - if (cipher == MCU_CIPHER_TKIP) { - /* Rx/Tx MIC keys are swapped */ - memcpy(sec_key->key + 16, key->key + 24, 8); - memcpy(sec_key->key + 24, key->key + 16, 8); - } - - /* store key_conf for BIP batch update */ - if (cipher == MCU_CIPHER_AES_CCMP) { - memcpy(bip->key, key->key, key->keylen); - bip->keyidx = key->keyidx; - } - - len -= sizeof(*sec_key); - sec->n_cipher = 1; - } - } else { - len -= sizeof(sec->key); - sec->n_cipher = 0; - } - sec->len = cpu_to_le16(len); - - return 0; -} - -int mt7921_mcu_add_key(struct mt7921_dev *dev, struct ieee80211_vif *vif, - struct mt7921_sta *msta, struct ieee80211_key_conf *key, - enum set_key_cmd cmd) -{ - struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; - struct sk_buff *skb; - int ret; - - skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->mt76, - &msta->wcid); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - ret = mt7921_mcu_sta_key_tlv(msta, skb, key, cmd); - if (ret) - return ret; - - return mt76_mcu_skb_send_msg(&dev->mt76, skb, - MCU_UNI_CMD(STA_REC_UPDATE), true); -} - int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev, struct ieee80211_ampdu_params *params, bool enable) @@ -564,6 +410,7 @@ int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev, msta->wcid.amsdu = false; return mt76_connac_mcu_sta_ba(&dev->mt76, &msta->vif->mt76, params, + MCU_UNI_CMD(STA_REC_UPDATE), enable, true); } @@ -574,23 +421,10 @@ int mt7921_mcu_uni_rx_ba(struct mt7921_dev *dev, struct mt7921_sta *msta = (struct mt7921_sta *)params->sta->drv_priv; return mt76_connac_mcu_sta_ba(&dev->mt76, &msta->vif->mt76, params, + MCU_UNI_CMD(STA_REC_UPDATE), enable, false); } -int mt7921_mcu_restart(struct mt76_dev *dev) -{ - struct { - u8 power_mode; - u8 rsv[3]; - } req = { - .power_mode = 1, - }; - - return mt76_mcu_send_msg(dev, MCU_CMD(NIC_POWER_CTRL), &req, - sizeof(req), false); -} -EXPORT_SYMBOL_GPL(mt7921_mcu_restart); - static u32 mt7921_get_data_mode(struct mt7921_dev *dev, u32 info) { u32 mode = DL_MODE_NEED_RSP; @@ -707,12 +541,8 @@ static int mt7921_load_patch(struct mt7921_dev *dev) if (mt76_is_sdio(&dev->mt76)) { /* activate again */ ret = __mt7921_mcu_fw_pmctrl(dev); - if (ret) - return ret; - - ret = __mt7921_mcu_drv_pmctrl(dev); - if (ret) - return ret; + if (!ret) + ret = __mt7921_mcu_drv_pmctrl(dev); } out: @@ -730,22 +560,6 @@ out: return ret; } -static u32 mt7921_mcu_gen_dl_mode(u8 feature_set, bool is_wa) -{ - u32 ret = 0; - - ret |= (feature_set & FW_FEATURE_SET_ENCRYPT) ? - (DL_MODE_ENCRYPT | DL_MODE_RESET_SEC_IV) : 0; - ret |= (feature_set & FW_FEATURE_ENCRY_MODE) ? - DL_CONFIG_ENCRY_MODE_SEL : 0; - ret |= FIELD_PREP(DL_MODE_KEY_IDX, - FIELD_GET(FW_FEATURE_SET_KEY_IDX, feature_set)); - ret |= DL_MODE_NEED_RSP; - ret |= is_wa ? DL_MODE_WORKING_PDA_CR4 : 0; - - return ret; -} - static int mt7921_mcu_send_ram_firmware(struct mt7921_dev *dev, const struct mt7921_fw_trailer *hdr, @@ -763,7 +577,8 @@ mt7921_mcu_send_ram_firmware(struct mt7921_dev *dev, region = (const struct mt7921_fw_region *)((const u8 *)hdr - (hdr->n_region - i) * sizeof(*region)); - mode = mt7921_mcu_gen_dl_mode(region->feature_set, is_wa); + mode = mt76_connac_mcu_gen_dl_mode(&dev->mt76, + region->feature_set, is_wa); len = le32_to_cpu(region->len); addr = le32_to_cpu(region->addr); @@ -920,33 +735,26 @@ EXPORT_SYMBOL_GPL(mt7921_mcu_exit); int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif) { -#define WMM_AIFS_SET BIT(0) -#define WMM_CW_MIN_SET BIT(1) -#define WMM_CW_MAX_SET BIT(2) -#define WMM_TXOP_SET BIT(3) -#define WMM_PARAM_SET GENMASK(3, 0) -#define TX_CMD_MODE 1 + struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; struct edca { - u8 queue; - u8 set; - u8 aifs; - u8 cw_min; + __le16 cw_min; __le16 cw_max; __le16 txop; - }; + __le16 aifs; + u8 guardtime; + u8 acm; + } __packed; struct mt7921_mcu_tx { - u8 total; - u8 action; - u8 valid; - u8 mode; - struct edca edca[IEEE80211_NUM_ACS]; + u8 bss_idx; + u8 qos; + u8 wmm_idx; + u8 pad; } __packed req = { - .valid = true, - .mode = TX_CMD_MODE, - .total = IEEE80211_NUM_ACS, + .bss_idx = mvif->mt76.idx, + .qos = vif->bss_conf.qos, + .wmm_idx = mvif->mt76.wmm_idx, }; - struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; struct mu_edca { u8 cw_min; u8 cw_max; @@ -970,30 +778,29 @@ int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif) .qos = vif->bss_conf.qos, .wmm_idx = mvif->mt76.wmm_idx, }; + static const int to_aci[] = { 1, 0, 2, 3 }; int ac, ret; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { struct ieee80211_tx_queue_params *q = &mvif->queue_params[ac]; - struct edca *e = &req.edca[ac]; + struct edca *e = &req.edca[to_aci[ac]]; - e->set = WMM_PARAM_SET; - e->queue = ac + mvif->mt76.wmm_idx * MT7921_MAX_WMM_SETS; - e->aifs = q->aifs; + e->aifs = cpu_to_le16(q->aifs); e->txop = cpu_to_le16(q->txop); if (q->cw_min) - e->cw_min = fls(q->cw_min); + e->cw_min = cpu_to_le16(q->cw_min); else - e->cw_min = 5; + e->cw_min = cpu_to_le16(5); if (q->cw_max) - e->cw_max = cpu_to_le16(fls(q->cw_max)); + e->cw_max = cpu_to_le16(q->cw_max); else e->cw_max = cpu_to_le16(10); } - ret = mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(EDCA_UPDATE), - &req, sizeof(req), true); + ret = mt76_mcu_send_msg(&dev->mt76, MCU_CE_CMD(SET_EDCA_PARMS), &req, + sizeof(req), false); if (ret) return ret; @@ -1003,7 +810,6 @@ int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif) for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { struct ieee80211_he_mu_edca_param_ac_rec *q; struct mu_edca *e; - int to_aci[] = {1, 0, 2, 3}; if (!mvif->queue_params[ac].mu_edca) break; @@ -1046,7 +852,7 @@ int mt7921_mcu_set_chan_info(struct mt7921_phy *phy, int cmd) } __packed req = { .control_ch = chandef->chan->hw_value, .center_ch = ieee80211_frequency_to_channel(freq1), - .bw = mt7921_mcu_chan_bw(chandef), + .bw = mt76_connac_chan_bw(chandef), .tx_streams_num = hweight8(phy->mt76->antenna_mask), .rx_streams = phy->mt76->antenna_mask, .band_idx = phy != &dev->phy, @@ -1093,30 +899,6 @@ int mt7921_mcu_set_eeprom(struct mt7921_dev *dev) } EXPORT_SYMBOL_GPL(mt7921_mcu_set_eeprom); -int mt7921_mcu_get_eeprom(struct mt7921_dev *dev, u32 offset) -{ - struct mt7921_mcu_eeprom_info req = { - .addr = cpu_to_le32(round_down(offset, 16)), - }; - struct mt7921_mcu_eeprom_info *res; - struct sk_buff *skb; - int ret; - u8 *buf; - - ret = mt76_mcu_send_and_get_msg(&dev->mt76, - MCU_EXT_QUERY(EFUSE_ACCESS), - &req, sizeof(req), true, &skb); - if (ret) - return ret; - - res = (struct mt7921_mcu_eeprom_info *)skb->data; - buf = dev->mt76.eeprom.data + le32_to_cpu(res->addr); - memcpy(buf, res->data, 16); - dev_kfree_skb(skb); - - return 0; -} - int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif) { struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h index 96647801850a..9edc83f06139 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h @@ -89,11 +89,6 @@ enum mt7921_rxq_id { MT7921_RXQ_MCU_WM = 0, }; -struct mt7921_sta_key_conf { - s8 keyidx; - u8 key[16]; -}; - struct mt7921_sta { struct mt76_wcid wcid; /* must be first */ @@ -106,7 +101,7 @@ struct mt7921_sta { unsigned long ampdu_state; struct mt76_sta_stats stats; - struct mt7921_sta_key_conf bip; + struct mt76_connac_sta_key_conf bip; }; DECLARE_EWMA(rssi, 10, 8); @@ -277,12 +272,6 @@ mt7921_hw_dev(struct ieee80211_hw *hw) #define mt7921_mutex_release(dev) \ mt76_connac_mutex_release(&(dev)->mt76, &(dev)->pm) -static inline u8 mt7921_lmac_mapping(struct mt7921_dev *dev, u8 ac) -{ - /* LMAC uses the reverse order of mac80211 AC indexes */ - return 3 - ac; -} - extern const struct ieee80211_ops mt7921_ops; extern struct pci_driver mt7921_pci_driver; @@ -296,16 +285,12 @@ int mt7921_wpdma_reset(struct mt7921_dev *dev, bool force); int mt7921_wpdma_reinit_cond(struct mt7921_dev *dev); void mt7921_dma_cleanup(struct mt7921_dev *dev); int mt7921_run_firmware(struct mt7921_dev *dev); -int mt7921_mcu_add_key(struct mt7921_dev *dev, struct ieee80211_vif *vif, - struct mt7921_sta *msta, struct ieee80211_key_conf *key, - enum set_key_cmd cmd); int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta, struct ieee80211_vif *vif, bool enable, enum mt76_sta_info_state state); int mt7921_mcu_set_chan_info(struct mt7921_phy *phy, int cmd); int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif); int mt7921_mcu_set_eeprom(struct mt7921_dev *dev); -int mt7921_mcu_get_eeprom(struct mt7921_dev *dev, u32 offset); int mt7921_mcu_get_rx_rate(struct mt7921_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct rate_info *rate); int mt7921_mcu_fw_log_2_host(struct mt7921_dev *dev, u8 ctrl); @@ -442,8 +427,8 @@ int mt7921_mcu_fill_message(struct mt76_dev *mdev, struct sk_buff *skb, int cmd, int *wait_seq); int mt7921_mcu_parse_response(struct mt76_dev *mdev, int cmd, struct sk_buff *skb, int seq); -int mt7921_mcu_restart(struct mt76_dev *dev); +bool mt7921e_rx_check(struct mt76_dev *mdev, void *data, int len); void mt7921e_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb); int mt7921e_driver_own(struct mt7921_dev *dev); @@ -452,6 +437,7 @@ int mt7921e_mcu_init(struct mt7921_dev *dev); int mt7921s_wfsys_reset(struct mt7921_dev *dev); int mt7921s_mac_reset(struct mt7921_dev *dev); int mt7921s_init_reset(struct mt7921_dev *dev); +int __mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev); int mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev); int mt7921e_mcu_fw_pmctrl(struct mt7921_dev *dev); @@ -465,4 +451,5 @@ int mt7921s_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, void mt7921s_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e); bool mt7921s_tx_status_data(struct mt76_dev *mdev, u8 *update); void mt7921_mac_add_txs(struct mt7921_dev *dev, void *data); +void mt7921_set_runtime_pm(struct mt7921_dev *dev); #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index 9dae2f5972bf..a0c82d19c4d9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -121,6 +121,110 @@ static void mt7921e_unregister_device(struct mt7921_dev *dev) mt76_free_device(&dev->mt76); } +static u32 __mt7921_reg_addr(struct mt7921_dev *dev, u32 addr) +{ + static const struct { + u32 phys; + u32 mapped; + u32 size; + } fixed_map[] = { + { 0x820d0000, 0x30000, 0x10000 }, /* WF_LMAC_TOP (WF_WTBLON) */ + { 0x820ed000, 0x24800, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_MIB) */ + { 0x820e4000, 0x21000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_TMAC) */ + { 0x820e7000, 0x21e00, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_DMA) */ + { 0x820eb000, 0x24200, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_LPON) */ + { 0x820e2000, 0x20800, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_AGG) */ + { 0x820e3000, 0x20c00, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_ARB) */ + { 0x820e5000, 0x21400, 0x0800 }, /* WF_LMAC_TOP BN0 (WF_RMAC) */ + { 0x00400000, 0x80000, 0x10000 }, /* WF_MCU_SYSRAM */ + { 0x00410000, 0x90000, 0x10000 }, /* WF_MCU_SYSRAM (configure register) */ + { 0x40000000, 0x70000, 0x10000 }, /* WF_UMAC_SYSRAM */ + { 0x54000000, 0x02000, 0x1000 }, /* WFDMA PCIE0 MCU DMA0 */ + { 0x55000000, 0x03000, 0x1000 }, /* WFDMA PCIE0 MCU DMA1 */ + { 0x58000000, 0x06000, 0x1000 }, /* WFDMA PCIE1 MCU DMA0 (MEM_DMA) */ + { 0x59000000, 0x07000, 0x1000 }, /* WFDMA PCIE1 MCU DMA1 */ + { 0x7c000000, 0xf0000, 0x10000 }, /* CONN_INFRA */ + { 0x7c020000, 0xd0000, 0x10000 }, /* CONN_INFRA, WFDMA */ + { 0x7c060000, 0xe0000, 0x10000 }, /* CONN_INFRA, conn_host_csr_top */ + { 0x80020000, 0xb0000, 0x10000 }, /* WF_TOP_MISC_OFF */ + { 0x81020000, 0xc0000, 0x10000 }, /* WF_TOP_MISC_ON */ + { 0x820c0000, 0x08000, 0x4000 }, /* WF_UMAC_TOP (PLE) */ + { 0x820c8000, 0x0c000, 0x2000 }, /* WF_UMAC_TOP (PSE) */ + { 0x820cc000, 0x0e000, 0x1000 }, /* WF_UMAC_TOP (PP) */ + { 0x820cd000, 0x0f000, 0x1000 }, /* WF_MDP_TOP */ + { 0x820ce000, 0x21c00, 0x0200 }, /* WF_LMAC_TOP (WF_SEC) */ + { 0x820cf000, 0x22000, 0x1000 }, /* WF_LMAC_TOP (WF_PF) */ + { 0x820e0000, 0x20000, 0x0400 }, /* WF_LMAC_TOP BN0 (WF_CFG) */ + { 0x820e1000, 0x20400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_TRB) */ + { 0x820e9000, 0x23400, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_WTBLOFF) */ + { 0x820ea000, 0x24000, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_ETBF) */ + { 0x820ec000, 0x24600, 0x0200 }, /* WF_LMAC_TOP BN0 (WF_INT) */ + { 0x820f0000, 0xa0000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_CFG) */ + { 0x820f1000, 0xa0600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_TRB) */ + { 0x820f2000, 0xa0800, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_AGG) */ + { 0x820f3000, 0xa0c00, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_ARB) */ + { 0x820f4000, 0xa1000, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_TMAC) */ + { 0x820f5000, 0xa1400, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_RMAC) */ + { 0x820f7000, 0xa1e00, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_DMA) */ + { 0x820f9000, 0xa3400, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_WTBLOFF) */ + { 0x820fa000, 0xa4000, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_ETBF) */ + { 0x820fb000, 0xa4200, 0x0400 }, /* WF_LMAC_TOP BN1 (WF_LPON) */ + { 0x820fc000, 0xa4600, 0x0200 }, /* WF_LMAC_TOP BN1 (WF_INT) */ + { 0x820fd000, 0xa4800, 0x0800 }, /* WF_LMAC_TOP BN1 (WF_MIB) */ + }; + int i; + + if (addr < 0x100000) + return addr; + + for (i = 0; i < ARRAY_SIZE(fixed_map); i++) { + u32 ofs; + + if (addr < fixed_map[i].phys) + continue; + + ofs = addr - fixed_map[i].phys; + if (ofs > fixed_map[i].size) + continue; + + return fixed_map[i].mapped + ofs; + } + + if ((addr >= 0x18000000 && addr < 0x18c00000) || + (addr >= 0x70000000 && addr < 0x78000000) || + (addr >= 0x7c000000 && addr < 0x7c400000)) + return mt7921_reg_map_l1(dev, addr); + + dev_err(dev->mt76.dev, "Access currently unsupported address %08x\n", + addr); + + return 0; +} + +static u32 mt7921_rr(struct mt76_dev *mdev, u32 offset) +{ + struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + u32 addr = __mt7921_reg_addr(dev, offset); + + return dev->bus_ops->rr(mdev, addr); +} + +static void mt7921_wr(struct mt76_dev *mdev, u32 offset, u32 val) +{ + struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + u32 addr = __mt7921_reg_addr(dev, offset); + + dev->bus_ops->wr(mdev, addr, val); +} + +static u32 mt7921_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) +{ + struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + u32 addr = __mt7921_reg_addr(dev, offset); + + return dev->bus_ops->rmw(mdev, addr, mask, val); +} + static int mt7921_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -134,6 +238,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev, .token_size = MT7921_TOKEN_SIZE, .tx_prepare_skb = mt7921e_tx_prepare_skb, .tx_complete_skb = mt7921e_tx_complete_skb, + .rx_check = mt7921e_rx_check, .rx_skb = mt7921e_queue_rx_skb, .rx_poll_complete = mt7921_rx_poll_complete, .sta_ps = mt7921_sta_ps, @@ -151,6 +256,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev, .fw_own = mt7921e_mcu_fw_pmctrl, }; + struct mt76_bus_ops *bus_ops; struct mt7921_dev *dev; struct mt76_dev *mdev; int ret; @@ -188,6 +294,25 @@ static int mt7921_pci_probe(struct pci_dev *pdev, mt76_mmio_init(&dev->mt76, pcim_iomap_table(pdev)[0]); tasklet_init(&dev->irq_tasklet, mt7921_irq_tasklet, (unsigned long)dev); + + dev->phy.dev = dev; + dev->phy.mt76 = &dev->mt76.phy; + dev->mt76.phy.priv = &dev->phy; + dev->bus_ops = dev->mt76.bus; + bus_ops = devm_kmemdup(dev->mt76.dev, dev->bus_ops, sizeof(*bus_ops), + GFP_KERNEL); + if (!bus_ops) + return -ENOMEM; + + bus_ops->rr = mt7921_rr; + bus_ops->wr = mt7921_wr; + bus_ops->rmw = mt7921_rmw; + dev->mt76.bus = bus_ops; + + ret = __mt7921e_mcu_drv_pmctrl(dev); + if (ret) + return ret; + mdev->rev = (mt7921_l1_rr(dev, MT_HW_CHIPID) << 16) | (mt7921_l1_rr(dev, MT_HW_REV) & 0xff); dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c index 85286cc9add1..8ca58293ddf1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c @@ -148,14 +148,15 @@ out: } static void -mt7921_mac_tx_free(struct mt7921_dev *dev, struct sk_buff *skb) +mt7921e_mac_tx_free(struct mt7921_dev *dev, void *data, int len) { - struct mt7921_tx_free *free = (struct mt7921_tx_free *)skb->data; + struct mt7921_tx_free *free = (struct mt7921_tx_free *)data; struct mt76_dev *mdev = &dev->mt76; struct mt76_txwi_cache *txwi; struct ieee80211_sta *sta = NULL; + struct sk_buff *skb, *tmp; + void *end = data + len; LIST_HEAD(free_list); - struct sk_buff *tmp; bool wake = false; u8 i, count; @@ -168,6 +169,9 @@ mt7921_mac_tx_free(struct mt7921_dev *dev, struct sk_buff *skb) * Should avoid accessing WTBL to get Tx airtime, and use it instead. */ count = FIELD_GET(MT_TX_FREE_MSDU_CNT, le16_to_cpu(free->ctrl)); + if (WARN_ON_ONCE((void *)&free->info[count] > end)) + return; + for (i = 0; i < count; i++) { u32 msdu, info = le32_to_cpu(free->info[i]); u8 stat; @@ -208,8 +212,6 @@ mt7921_mac_tx_free(struct mt7921_dev *dev, struct sk_buff *skb) if (wake) mt76_set_tx_blocked(&dev->mt76, false); - napi_consume_skb(skb, 1); - list_for_each_entry_safe(skb, tmp, &free_list, list) { skb_list_del_init(skb); napi_consume_skb(skb, 1); @@ -222,6 +224,27 @@ mt7921_mac_tx_free(struct mt7921_dev *dev, struct sk_buff *skb) mt76_worker_schedule(&dev->mt76.tx_worker); } +bool mt7921e_rx_check(struct mt76_dev *mdev, void *data, int len) +{ + struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + __le32 *rxd = (__le32 *)data; + __le32 *end = (__le32 *)&rxd[len / 4]; + enum rx_pkt_type type; + + type = FIELD_GET(MT_RXD0_PKT_TYPE, le32_to_cpu(rxd[0])); + switch (type) { + case PKT_TYPE_TXRX_NOTIFY: + mt7921e_mac_tx_free(dev, data, len); + return false; + case PKT_TYPE_TXS: + for (rxd += 2; rxd + 8 <= end; rxd += 8) + mt7921_mac_add_txs(dev, rxd); + return false; + default: + return true; + } +} + void mt7921e_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb) { @@ -233,7 +256,8 @@ void mt7921e_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, switch (type) { case PKT_TYPE_TXRX_NOTIFY: - mt7921_mac_tx_free(dev, skb); + mt7921e_mac_tx_free(dev, skb->data, skb->len); + napi_consume_skb(skb, 1); break; default: mt7921_queue_rx_skb(mdev, q, skb); @@ -314,6 +338,7 @@ int mt7921e_mac_reset(struct mt7921_dev *dev) } local_bh_enable(); + dev->fw_assert = false; clear_bit(MT76_MCU_RESET, &dev->mphy.state); mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c index a020352122a1..36669e5aeef3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mcu.c @@ -42,7 +42,7 @@ int mt7921e_mcu_init(struct mt7921_dev *dev) .headroom = sizeof(struct mt7921_mcu_txd), .mcu_skb_send_msg = mt7921_mcu_send_message, .mcu_parse_response = mt7921_mcu_parse_response, - .mcu_restart = mt7921_mcu_restart, + .mcu_restart = mt76_connac_mcu_restart, }; int err; @@ -59,10 +59,8 @@ int mt7921e_mcu_init(struct mt7921_dev *dev) return err; } -int mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev) +int __mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev) { - struct mt76_phy *mphy = &dev->mt76.phy; - struct mt76_connac_pm *pm = &dev->pm; int i, err = 0; for (i = 0; i < MT7921_DRV_OWN_RETRY_COUNT; i++) { @@ -75,9 +73,21 @@ int mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev) if (i == MT7921_DRV_OWN_RETRY_COUNT) { dev_err(dev->mt76.dev, "driver own failed\n"); err = -EIO; - goto out; } + return err; +} + +int mt7921e_mcu_drv_pmctrl(struct mt7921_dev *dev) +{ + struct mt76_phy *mphy = &dev->mt76.phy; + struct mt76_connac_pm *pm = &dev->pm; + int err; + + err = __mt7921e_mcu_drv_pmctrl(dev); + if (err < 0) + goto out; + mt7921_wpdma_reinit_cond(dev); clear_bit(MT76_STATE_PM, &mphy->state); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h index cbd38122c510..411695f273cd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h @@ -454,6 +454,9 @@ #define MT_DMASHDL_SCHED_SET(_n) MT_DMA_SHDL(0x070 + ((_n) << 2)) +#define MT_CONN_STATUS 0x7c053c10 +#define MT_WIFI_PATCH_DL_STATE BIT(0) + #define MT_CONN_ON_LPCTL 0x7c060010 #define PCIE_LPCR_HOST_OWN_SYNC BIT(2) #define PCIE_LPCR_HOST_CLR_OWN BIT(1) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c index 65d693902c22..a6ae29c97e0e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c @@ -58,7 +58,10 @@ static int mt7921s_parse_intr(struct mt76_dev *dev, struct mt76s_intr *intr) struct mt7921_sdio_intr *irq_data = sdio->intr_data; int i, err; + sdio_claim_host(sdio->func); err = sdio_readsb(sdio->func, irq_data, MCR_WHISR, sizeof(*irq_data)); + sdio_release_host(sdio->func); + if (err < 0) return err; @@ -118,7 +121,7 @@ static int mt7921s_probe(struct sdio_func *func, struct mt7921_dev *dev; struct mt76_dev *mdev; - int ret, i; + int ret; mdev = mt76_alloc_device(&func->dev, sizeof(*dev), &mt7921_ops, &drv_ops); @@ -151,16 +154,6 @@ static int mt7921s_probe(struct sdio_func *func, goto error; } - for (i = 0; i < ARRAY_SIZE(mdev->sdio.xmit_buf); i++) { - mdev->sdio.xmit_buf[i] = devm_kmalloc(mdev->dev, - MT76S_XMIT_BUF_SZ, - GFP_KERNEL); - if (!mdev->sdio.xmit_buf[i]) { - ret = -ENOMEM; - goto error; - } - } - ret = mt76s_alloc_rx_queue(mdev, MT_RXQ_MAIN); if (ret) goto error; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c index ccaf8134cec7..4fd1d4765b04 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c @@ -60,7 +60,11 @@ int mt7921s_wfsys_reset(struct mt7921_dev *dev) sdio_release_host(sdio->func); + clear_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); + /* activate mt7921s again */ + mt7921s_mcu_drv_pmctrl(dev); + mt76_clear(dev, MT_CONN_STATUS, MT_WIFI_PATCH_DL_STATE); mt7921s_mcu_fw_pmctrl(dev); mt7921s_mcu_drv_pmctrl(dev); @@ -81,7 +85,6 @@ int mt7921s_init_reset(struct mt7921_dev *dev) mt7921s_wfsys_reset(dev); mt76_worker_enable(&dev->mt76.sdio.txrx_worker); - clear_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); clear_bit(MT76_MCU_RESET, &dev->mphy.state); mt7921s_enable_irq(&dev->mt76); @@ -114,7 +117,6 @@ int mt7921s_mac_reset(struct mt7921_dev *dev) mt76_worker_enable(&dev->mt76.sdio.net_worker); dev->fw_assert = false; - clear_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); clear_bit(MT76_MCU_RESET, &dev->mphy.state); mt7921s_enable_irq(&dev->mt76); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c index d20f2ff01be1..5d8af18c7026 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mcu.c @@ -49,6 +49,26 @@ mt7921s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb, return ret; } +static u32 mt7921s_read_rm3r(struct mt7921_dev *dev) +{ + struct mt76_sdio *sdio = &dev->mt76.sdio; + + return sdio_readl(sdio->func, MCR_D2HRM3R, NULL); +} + +static u32 mt7921s_clear_rm3r_drv_own(struct mt7921_dev *dev) +{ + struct mt76_sdio *sdio = &dev->mt76.sdio; + u32 val; + + val = sdio_readl(sdio->func, MCR_D2HRM3R, NULL); + if (val) + sdio_writel(sdio->func, H2D_SW_INT_CLEAR_MAILBOX_ACK, + MCR_WSICR, NULL); + + return val; +} + int mt7921s_mcu_init(struct mt7921_dev *dev) { static const struct mt76_mcu_ops mt7921s_mcu_ops = { @@ -88,6 +108,12 @@ int mt7921s_mcu_drv_pmctrl(struct mt7921_dev *dev) err = readx_poll_timeout(mt76s_read_pcr, &dev->mt76, status, status & WHLPCR_IS_DRIVER_OWN, 2000, 1000000); + + if (!err && test_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state)) + err = readx_poll_timeout(mt7921s_read_rm3r, dev, status, + status & D2HRM3R_IS_DRIVER_OWN, + 2000, 1000000); + sdio_release_host(func); if (err < 0) { @@ -115,12 +141,24 @@ int mt7921s_mcu_fw_pmctrl(struct mt7921_dev *dev) sdio_claim_host(func); + if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state)) { + err = readx_poll_timeout(mt7921s_clear_rm3r_drv_own, + dev, status, + !(status & D2HRM3R_IS_DRIVER_OWN), + 2000, 1000000); + if (err < 0) { + dev_err(dev->mt76.dev, "mailbox ACK not cleared\n"); + goto err; + } + } + sdio_writel(func, WHLPCR_FW_OWN_REQ_SET, MCR_WHLPCR, NULL); err = readx_poll_timeout(mt76s_read_pcr, &dev->mt76, status, !(status & WHLPCR_IS_DRIVER_OWN), 2000, 1000000); sdio_release_host(func); +err: if (err < 0) { dev_err(dev->mt76.dev, "firmware own failed\n"); clear_bit(MT76_STATE_PM, &mphy->state); diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c index 54f72d215948..def7f325f5c5 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/sdio.c @@ -12,6 +12,8 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mmc/sdio_func.h> +#include <linux/mmc/card.h> +#include <linux/mmc/host.h> #include <linux/sched.h> #include <linux/kthread.h> @@ -627,6 +629,7 @@ int mt76s_init(struct mt76_dev *dev, struct sdio_func *func, const struct mt76_bus_ops *bus_ops) { struct mt76_sdio *sdio = &dev->sdio; + u32 host_max_cap; int err; err = mt76_worker_setup(dev->hw, &sdio->status_worker, @@ -648,7 +651,16 @@ int mt76s_init(struct mt76_dev *dev, struct sdio_func *func, dev->bus = bus_ops; dev->sdio.func = func; - return 0; + host_max_cap = min_t(u32, func->card->host->max_req_size, + func->cur_blksize * + func->card->host->max_blk_count); + dev->sdio.xmit_buf_sz = min_t(u32, host_max_cap, MT76S_XMIT_BUF_SZ); + dev->sdio.xmit_buf = devm_kmalloc(dev->dev, dev->sdio.xmit_buf_sz, + GFP_KERNEL); + if (!dev->sdio.xmit_buf) + err = -ENOMEM; + + return err; } EXPORT_SYMBOL_GPL(mt76s_init); diff --git a/drivers/net/wireless/mediatek/mt76/sdio.h b/drivers/net/wireless/mediatek/mt76/sdio.h index 99db4ad93b7c..27d5d2077eba 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio.h +++ b/drivers/net/wireless/mediatek/mt76/sdio.h @@ -65,6 +65,7 @@ #define MCR_H2DSM0R 0x0070 #define H2D_SW_INT_READ BIT(16) #define H2D_SW_INT_WRITE BIT(17) +#define H2D_SW_INT_CLEAR_MAILBOX_ACK BIT(22) #define MCR_H2DSM1R 0x0074 #define MCR_D2HRM0R 0x0078 @@ -109,6 +110,7 @@ #define MCR_H2DSM2R 0x0160 /* supported in CONNAC2 */ #define MCR_H2DSM3R 0x0164 /* supported in CONNAC2 */ #define MCR_D2HRM3R 0x0174 /* supported in CONNAC2 */ +#define D2HRM3R_IS_DRIVER_OWN BIT(0) #define MCR_WTQCR8 0x0190 /* supported in CONNAC2 */ #define MCR_WTQCR9 0x0194 /* supported in CONNAC2 */ #define MCR_WTQCR10 0x0198 /* supported in CONNAC2 */ diff --git a/drivers/net/wireless/mediatek/mt76/sdio_txrx.c b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c index 801590a0a334..9fcf507e09bd 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio_txrx.c +++ b/drivers/net/wireless/mediatek/mt76/sdio_txrx.c @@ -102,7 +102,10 @@ mt76s_rx_run_queue(struct mt76_dev *dev, enum mt76_rxq_id qid, buf = page_address(page); + sdio_claim_host(sdio->func); err = sdio_readsb(sdio->func, buf, MCR_WRDR(qid), len); + sdio_release_host(sdio->func); + if (err < 0) { dev_err(dev->dev, "sdio read data failed:%d\n", err); put_page(page); @@ -214,7 +217,10 @@ static int __mt76s_xmit_queue(struct mt76_dev *dev, u8 *data, int len) if (len > sdio->func->cur_blksize) len = roundup(len, sdio->func->cur_blksize); + sdio_claim_host(sdio->func); err = sdio_writesb(sdio->func, MCR_WTDR1, data, len); + sdio_release_host(sdio->func); + if (err) dev_err(dev->dev, "sdio write failed: %d\n", err); @@ -223,12 +229,11 @@ static int __mt76s_xmit_queue(struct mt76_dev *dev, u8 *data, int len) static int mt76s_tx_run_queue(struct mt76_dev *dev, struct mt76_queue *q) { - int qid, err, nframes = 0, len = 0, pse_sz = 0, ple_sz = 0; + int err, nframes = 0, len = 0, pse_sz = 0, ple_sz = 0; bool mcu = q == dev->q_mcu[MT_MCUQ_WM]; struct mt76_sdio *sdio = &dev->sdio; u8 pad; - qid = mcu ? ARRAY_SIZE(sdio->xmit_buf) - 1 : q->qid; while (q->first != q->head) { struct mt76_queue_entry *e = &q->entry[q->first]; struct sk_buff *iter; @@ -249,27 +254,25 @@ static int mt76s_tx_run_queue(struct mt76_dev *dev, struct mt76_queue *q) } pad = roundup(e->skb->len, 4) - e->skb->len; - if (len + e->skb->len + pad + 4 > MT76S_XMIT_BUF_SZ) + if (len + e->skb->len + pad + 4 > dev->sdio.xmit_buf_sz) break; if (mt76s_tx_pick_quota(sdio, mcu, e->buf_sz, &pse_sz, &ple_sz)) break; - memcpy(sdio->xmit_buf[qid] + len, e->skb->data, - skb_headlen(e->skb)); + memcpy(sdio->xmit_buf + len, e->skb->data, skb_headlen(e->skb)); len += skb_headlen(e->skb); nframes++; skb_walk_frags(e->skb, iter) { - memcpy(sdio->xmit_buf[qid] + len, iter->data, - iter->len); + memcpy(sdio->xmit_buf + len, iter->data, iter->len); len += iter->len; nframes++; } if (unlikely(pad)) { - memset(sdio->xmit_buf[qid] + len, 0, pad); + memset(sdio->xmit_buf + len, 0, pad); len += pad; } next: @@ -278,8 +281,8 @@ next: } if (nframes) { - memset(sdio->xmit_buf[qid] + len, 0, 4); - err = __mt76s_xmit_queue(dev, sdio->xmit_buf[qid], len + 4); + memset(sdio->xmit_buf + len, 0, 4); + err = __mt76s_xmit_queue(dev, sdio->xmit_buf, len + 4); if (err) return err; } @@ -298,6 +301,7 @@ void mt76s_txrx_worker(struct mt76_sdio *sdio) /* disable interrupt */ sdio_claim_host(sdio->func); sdio_writel(sdio->func, WHLPCR_INT_EN_CLR, MCR_WHLPCR, NULL); + sdio_release_host(sdio->func); do { nframes = 0; @@ -327,6 +331,7 @@ void mt76s_txrx_worker(struct mt76_sdio *sdio) } while (nframes > 0); /* enable interrupt */ + sdio_claim_host(sdio->func); sdio_writel(sdio->func, WHLPCR_INT_EN_SET, MCR_WHLPCR, NULL); sdio_release_host(sdio->func); } @@ -341,6 +346,7 @@ void mt76s_sdio_irq(struct sdio_func *func) test_bit(MT76_MCU_RESET, &dev->phy.state)) return; + sdio_writel(sdio->func, WHLPCR_INT_EN_CLR, MCR_WHLPCR, NULL); mt76_worker_schedule(&sdio->txrx_worker); } EXPORT_SYMBOL_GPL(mt76s_sdio_irq); diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c index 2c2ed4b09efd..217477f34c21 100644 --- a/drivers/net/wireless/microchip/wilc1000/spi.c +++ b/drivers/net/wireless/microchip/wilc1000/spi.c @@ -727,10 +727,7 @@ static int wilc_spi_dma_rw(struct wilc *wilc, u8 cmd, u32 adr, u8 *b, u32 sz) int nbytes; u8 rsp; - if (sz <= DATA_PKT_SZ) - nbytes = sz; - else - nbytes = DATA_PKT_SZ; + nbytes = min_t(u32, sz, DATA_PKT_SZ); /* * Data Response header diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 2987ad9271f6..87e98ab068ed 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -382,6 +382,8 @@ static int ray_config(struct pcmcia_device *link) goto failed; local->sram = ioremap(link->resource[2]->start, resource_size(link->resource[2])); + if (!local->sram) + goto failed; /*** Set up 16k window for shared memory (receive buffer) ***************/ link->resource[3]->flags |= @@ -396,6 +398,8 @@ static int ray_config(struct pcmcia_device *link) goto failed; local->rmem = ioremap(link->resource[3]->start, resource_size(link->resource[3])); + if (!local->rmem) + goto failed; /*** Set up window for attribute memory ***********************************/ link->resource[4]->flags |= @@ -410,6 +414,8 @@ static int ray_config(struct pcmcia_device *link) goto failed; local->amem = ioremap(link->resource[4]->start, resource_size(link->resource[4])); + if (!local->amem) + goto failed; dev_dbg(&link->dev, "ray_config sram=%p\n", local->sram); dev_dbg(&link->dev, "ray_config rmem=%p\n", local->rmem); diff --git a/drivers/net/wireless/realtek/rtlwifi/cam.c b/drivers/net/wireless/realtek/rtlwifi/cam.c index 7a0355dc6bab..32970ea4b4e7 100644 --- a/drivers/net/wireless/realtek/rtlwifi/cam.c +++ b/drivers/net/wireless/realtek/rtlwifi/cam.c @@ -208,7 +208,7 @@ void rtl_cam_empty_entry(struct ieee80211_hw *hw, u8 uc_index) u32 ul_command; u32 ul_content; - u32 ul_encalgo = rtlpriv->cfg->maps[SEC_CAM_AES]; + u32 ul_encalgo; u8 entry_i; switch (rtlpriv->sec.pairwise_enc_algorithm) { diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c index 2f7c036f9022..4c8e5ea5d069 100644 --- a/drivers/net/wireless/realtek/rtw88/fw.c +++ b/drivers/net/wireless/realtek/rtw88/fw.c @@ -1784,9 +1784,9 @@ void rtw_fw_scan_notify(struct rtw_dev *rtwdev, bool start) rtw_fw_send_h2c_command(rtwdev, h2c_pkt); } -static void rtw_append_probe_req_ie(struct rtw_dev *rtwdev, struct sk_buff *skb, - struct sk_buff_head *list, - struct rtw_vif *rtwvif) +static int rtw_append_probe_req_ie(struct rtw_dev *rtwdev, struct sk_buff *skb, + struct sk_buff_head *list, u8 *bands, + struct rtw_vif *rtwvif) { struct ieee80211_scan_ies *ies = rtwvif->scan_ies; struct rtw_chip_info *chip = rtwdev->chip; @@ -1797,19 +1797,24 @@ static void rtw_append_probe_req_ie(struct rtw_dev *rtwdev, struct sk_buff *skb, if (!(BIT(idx) & chip->band)) continue; new = skb_copy(skb, GFP_KERNEL); + if (!new) + return -ENOMEM; skb_put_data(new, ies->ies[idx], ies->len[idx]); skb_put_data(new, ies->common_ies, ies->common_ie_len); skb_queue_tail(list, new); + (*bands)++; } + + return 0; } -static int _rtw_hw_scan_update_probe_req(struct rtw_dev *rtwdev, u8 num_ssids, +static int _rtw_hw_scan_update_probe_req(struct rtw_dev *rtwdev, u8 num_probes, struct sk_buff_head *probe_req_list) { struct rtw_chip_info *chip = rtwdev->chip; struct sk_buff *skb, *tmp; u8 page_offset = 1, *buf, page_size = chip->page_size; - u8 pages = page_offset + num_ssids * RTW_PROBE_PG_CNT; + u8 pages = page_offset + num_probes * RTW_PROBE_PG_CNT; u16 pg_addr = rtwdev->fifo.rsvd_h2c_info_addr, loc; u16 buf_offset = page_size * page_offset; u8 tx_desc_sz = chip->tx_pkt_desc_sz; @@ -1848,6 +1853,8 @@ static int _rtw_hw_scan_update_probe_req(struct rtw_dev *rtwdev, u8 num_ssids, rtwdev->scan_info.probe_pg_size = page_offset; out: kfree(buf); + skb_queue_walk_safe(probe_req_list, skb, tmp) + kfree_skb(skb); return ret; } @@ -1857,8 +1864,9 @@ static int rtw_hw_scan_update_probe_req(struct rtw_dev *rtwdev, { struct cfg80211_scan_request *req = rtwvif->scan_req; struct sk_buff_head list; - struct sk_buff *skb; - u8 num = req->n_ssids, i; + struct sk_buff *skb, *tmp; + u8 num = req->n_ssids, i, bands = 0; + int ret; skb_queue_head_init(&list); for (i = 0; i < num; i++) { @@ -1866,11 +1874,25 @@ static int rtw_hw_scan_update_probe_req(struct rtw_dev *rtwdev, req->ssids[i].ssid, req->ssids[i].ssid_len, req->ie_len); - rtw_append_probe_req_ie(rtwdev, skb, &list, rtwvif); + if (!skb) { + ret = -ENOMEM; + goto out; + } + ret = rtw_append_probe_req_ie(rtwdev, skb, &list, &bands, + rtwvif); + if (ret) + goto out; + kfree_skb(skb); } - return _rtw_hw_scan_update_probe_req(rtwdev, num, &list); + return _rtw_hw_scan_update_probe_req(rtwdev, num * bands, &list); + +out: + skb_queue_walk_safe(&list, skb, tmp) + kfree_skb(skb); + + return ret; } static int rtw_add_chan_info(struct rtw_dev *rtwdev, struct rtw_chan_info *info, @@ -2022,7 +2044,7 @@ void rtw_hw_scan_complete(struct rtw_dev *rtwdev, struct ieee80211_vif *vif, rtwdev->hal.rcr |= BIT_CBSSID_BCN; rtw_write32(rtwdev, REG_RCR, rtwdev->hal.rcr); - rtw_core_scan_complete(rtwdev, vif); + rtw_core_scan_complete(rtwdev, vif, true); ieee80211_wake_queues(rtwdev->hw); ieee80211_scan_completed(rtwdev->hw, &info); diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c index ae7d97de5fdf..647d2662955b 100644 --- a/drivers/net/wireless/realtek/rtw88/mac80211.c +++ b/drivers/net/wireless/realtek/rtw88/mac80211.c @@ -72,6 +72,9 @@ static int rtw_ops_config(struct ieee80211_hw *hw, u32 changed) struct rtw_dev *rtwdev = hw->priv; int ret = 0; + /* let previous ips work finish to ensure we don't leave ips twice */ + cancel_work_sync(&rtwdev->ips_work); + mutex_lock(&rtwdev->mutex); rtw_leave_lps_deep(rtwdev); @@ -614,7 +617,7 @@ static void rtw_ops_sw_scan_complete(struct ieee80211_hw *hw, struct rtw_dev *rtwdev = hw->priv; mutex_lock(&rtwdev->mutex); - rtw_core_scan_complete(rtwdev, vif); + rtw_core_scan_complete(rtwdev, vif, false); mutex_unlock(&rtwdev->mutex); } diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 38252113c4a8..2757aa0dc586 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -272,6 +272,15 @@ static void rtw_c2h_work(struct work_struct *work) } } +static void rtw_ips_work(struct work_struct *work) +{ + struct rtw_dev *rtwdev = container_of(work, struct rtw_dev, ips_work); + + mutex_lock(&rtwdev->mutex); + rtw_enter_ips(rtwdev); + mutex_unlock(&rtwdev->mutex); +} + static u8 rtw_acquire_macid(struct rtw_dev *rtwdev) { unsigned long mac_id; @@ -1011,37 +1020,52 @@ static u8 get_rate_id(u8 wireless_set, enum rtw_bandwidth bw_mode, u8 tx_num) #define RA_MASK_VHT_RATES (RA_MASK_VHT_RATES_1SS | \ RA_MASK_VHT_RATES_2SS | \ RA_MASK_VHT_RATES_3SS) +#define RA_MASK_CCK_IN_BG 0x00005 #define RA_MASK_CCK_IN_HT 0x00005 #define RA_MASK_CCK_IN_VHT 0x00005 #define RA_MASK_OFDM_IN_VHT 0x00010 #define RA_MASK_OFDM_IN_HT_2G 0x00010 #define RA_MASK_OFDM_IN_HT_5G 0x00030 -static u64 rtw_update_rate_mask(struct rtw_dev *rtwdev, - struct rtw_sta_info *si, - u64 ra_mask, bool is_vht_enable, - u8 wireless_set) +static u64 rtw_rate_mask_rssi(struct rtw_sta_info *si, u8 wireless_set) +{ + u8 rssi_level = si->rssi_level; + + if (wireless_set == WIRELESS_CCK) + return 0xffffffffffffffffULL; + + if (rssi_level == 0) + return 0xffffffffffffffffULL; + else if (rssi_level == 1) + return 0xfffffffffffffff0ULL; + else if (rssi_level == 2) + return 0xffffffffffffefe0ULL; + else if (rssi_level == 3) + return 0xffffffffffffcfc0ULL; + else if (rssi_level == 4) + return 0xffffffffffff8f80ULL; + else + return 0xffffffffffff0f00ULL; +} + +static u64 rtw_rate_mask_recover(u64 ra_mask, u64 ra_mask_bak) +{ + if ((ra_mask & ~(RA_MASK_CCK_RATES | RA_MASK_OFDM_RATES)) == 0) + ra_mask |= (ra_mask_bak & ~(RA_MASK_CCK_RATES | RA_MASK_OFDM_RATES)); + + if (ra_mask == 0) + ra_mask |= (ra_mask_bak & (RA_MASK_CCK_RATES | RA_MASK_OFDM_RATES)); + + return ra_mask; +} + +static u64 rtw_rate_mask_cfg(struct rtw_dev *rtwdev, struct rtw_sta_info *si, + u64 ra_mask, bool is_vht_enable) { struct rtw_hal *hal = &rtwdev->hal; const struct cfg80211_bitrate_mask *mask = si->mask; u64 cfg_mask = GENMASK_ULL(63, 0); - u8 rssi_level, band; - - if (wireless_set != WIRELESS_CCK) { - rssi_level = si->rssi_level; - if (rssi_level == 0) - ra_mask &= 0xffffffffffffffffULL; - else if (rssi_level == 1) - ra_mask &= 0xfffffffffffffff0ULL; - else if (rssi_level == 2) - ra_mask &= 0xffffffffffffefe0ULL; - else if (rssi_level == 3) - ra_mask &= 0xffffffffffffcfc0ULL; - else if (rssi_level == 4) - ra_mask &= 0xffffffffffff8f80ULL; - else if (rssi_level >= 5) - ra_mask &= 0xffffffffffff0f00ULL; - } + u8 band; if (!si->use_cfg_mask) return ra_mask; @@ -1091,6 +1115,7 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) u8 ldpc_en = 0; u8 tx_num = 1; u64 ra_mask = 0; + u64 ra_mask_bak = 0; bool is_vht_enable = false; bool is_support_sgi = false; @@ -1115,6 +1140,7 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) if (hal->current_band_type == RTW_BAND_5G) { ra_mask |= (u64)sta->supp_rates[NL80211_BAND_5GHZ] << 4; + ra_mask_bak = ra_mask; if (sta->vht_cap.vht_supported) { ra_mask &= RA_MASK_VHT_RATES | RA_MASK_OFDM_IN_VHT; wireless_set = WIRELESS_OFDM | WIRELESS_VHT; @@ -1127,6 +1153,7 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) dm_info->rrsr_val_init = RRSR_INIT_5G; } else if (hal->current_band_type == RTW_BAND_2G) { ra_mask |= sta->supp_rates[NL80211_BAND_2GHZ]; + ra_mask_bak = ra_mask; if (sta->vht_cap.vht_supported) { ra_mask &= RA_MASK_VHT_RATES | RA_MASK_CCK_IN_VHT | RA_MASK_OFDM_IN_VHT; @@ -1140,11 +1167,13 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) } else if (sta->supp_rates[0] <= 0xf) { wireless_set = WIRELESS_CCK; } else { + ra_mask &= RA_MASK_OFDM_RATES | RA_MASK_CCK_IN_BG; wireless_set = WIRELESS_CCK | WIRELESS_OFDM; } dm_info->rrsr_val_init = RRSR_INIT_2G; } else { rtw_err(rtwdev, "Unknown band type\n"); + ra_mask_bak = ra_mask; wireless_set = 0; } @@ -1176,8 +1205,9 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si) rate_id = get_rate_id(wireless_set, bw_mode, tx_num); - ra_mask = rtw_update_rate_mask(rtwdev, si, ra_mask, is_vht_enable, - wireless_set); + ra_mask &= rtw_rate_mask_rssi(si, wireless_set); + ra_mask = rtw_rate_mask_recover(ra_mask, ra_mask_bak); + ra_mask = rtw_rate_mask_cfg(rtwdev, si, ra_mask, is_vht_enable); si->bw_mode = bw_mode; si->stbc_en = stbc_en; @@ -1339,7 +1369,8 @@ void rtw_core_scan_start(struct rtw_dev *rtwdev, struct rtw_vif *rtwvif, set_bit(RTW_FLAG_SCANNING, rtwdev->flags); } -void rtw_core_scan_complete(struct rtw_dev *rtwdev, struct ieee80211_vif *vif) +void rtw_core_scan_complete(struct rtw_dev *rtwdev, struct ieee80211_vif *vif, + bool hw_scan) { struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv; u32 config = 0; @@ -1354,6 +1385,9 @@ void rtw_core_scan_complete(struct rtw_dev *rtwdev, struct ieee80211_vif *vif) rtw_vif_port_config(rtwdev, rtwvif, config); rtw_coex_scan_notify(rtwdev, COEX_SCAN_FINISH); + + if (rtwvif->net_type == RTW_NET_NO_LINK && hw_scan) + ieee80211_queue_work(rtwdev->hw, &rtwdev->ips_work); } int rtw_core_start(struct rtw_dev *rtwdev) @@ -1919,6 +1953,7 @@ int rtw_core_init(struct rtw_dev *rtwdev) INIT_DELAYED_WORK(&coex->wl_ccklock_work, rtw_coex_wl_ccklock_work); INIT_WORK(&rtwdev->tx_work, rtw_tx_work); INIT_WORK(&rtwdev->c2h_work, rtw_c2h_work); + INIT_WORK(&rtwdev->ips_work, rtw_ips_work); INIT_WORK(&rtwdev->fw_recovery_work, rtw_fw_recovery_work); INIT_WORK(&rtwdev->ba_work, rtw_txq_ba_work); skb_queue_head_init(&rtwdev->c2h_queue); diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h index dc1cd9bd4b8a..36e1e408933d 100644 --- a/drivers/net/wireless/realtek/rtw88/main.h +++ b/drivers/net/wireless/realtek/rtw88/main.h @@ -1960,6 +1960,7 @@ struct rtw_dev { /* c2h cmd queue & handler work */ struct sk_buff_head c2h_queue; struct work_struct c2h_work; + struct work_struct ips_work; struct work_struct fw_recovery_work; /* used to protect txqs list */ @@ -2101,7 +2102,8 @@ void rtw_tx_report_purge_timer(struct timer_list *t); void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si); void rtw_core_scan_start(struct rtw_dev *rtwdev, struct rtw_vif *rtwvif, const u8 *mac_addr, bool hw_scan); -void rtw_core_scan_complete(struct rtw_dev *rtwdev, struct ieee80211_vif *vif); +void rtw_core_scan_complete(struct rtw_dev *rtwdev, struct ieee80211_vif *vif, + bool hw_scan); int rtw_core_start(struct rtw_dev *rtwdev); void rtw_core_stop(struct rtw_dev *rtwdev); int rtw_chip_info_setup(struct rtw_dev *rtwdev); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index db078df63f85..b1f4afb50830 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -1514,6 +1514,7 @@ static const struct rtw_rfe_def rtw8821c_rfe_defs[] = { [0] = RTW_DEF_RFE(8821c, 0, 0), [2] = RTW_DEF_RFE_EXT(8821c, 0, 0, 2), [4] = RTW_DEF_RFE_EXT(8821c, 0, 0, 2), + [6] = RTW_DEF_RFE(8821c, 0, 0), }; static struct rtw_hw_reg rtw8821c_dig[] = { diff --git a/drivers/net/wireless/realtek/rtw89/Kconfig b/drivers/net/wireless/realtek/rtw89/Kconfig index 37e5def24d9f..dd02b6a6790e 100644 --- a/drivers/net/wireless/realtek/rtw89/Kconfig +++ b/drivers/net/wireless/realtek/rtw89/Kconfig @@ -16,11 +16,15 @@ config RTW89_CORE config RTW89_PCI tristate +config RTW89_8852A + tristate + config RTW89_8852AE tristate "Realtek 8852AE PCI wireless network adapter" depends on PCI select RTW89_CORE select RTW89_PCI + select RTW89_8852A help Select this option will enable support for 8852AE chipset diff --git a/drivers/net/wireless/realtek/rtw89/Makefile b/drivers/net/wireless/realtek/rtw89/Makefile index 077e8fe23f60..012ae60c0b81 100644 --- a/drivers/net/wireless/realtek/rtw89/Makefile +++ b/drivers/net/wireless/realtek/rtw89/Makefile @@ -6,10 +6,6 @@ rtw89_core-y += core.o \ mac.o \ phy.o \ fw.o \ - rtw8852a.o \ - rtw8852a_table.o \ - rtw8852a_rfk.o \ - rtw8852a_rfk_table.o \ cam.o \ efuse.o \ regd.o \ @@ -18,6 +14,15 @@ rtw89_core-y += core.o \ ps.o \ ser.o +obj-$(CONFIG_RTW89_8852A) += rtw89_8852a.o +rtw89_8852a-objs := rtw8852a.o \ + rtw8852a_table.o \ + rtw8852a_rfk.o \ + rtw8852a_rfk_table.o + +obj-$(CONFIG_RTW89_8852AE) += rtw89_8852ae.o +rtw89_8852ae-objs := rtw8852ae.o + rtw89_core-$(CONFIG_RTW89_DEBUG) += debug.o obj-$(CONFIG_RTW89_PCI) += rtw89_pci.o diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c index bd34e4bbe107..305dbbebff6b 100644 --- a/drivers/net/wireless/realtek/rtw89/cam.c +++ b/drivers/net/wireless/realtek/rtw89/cam.c @@ -231,7 +231,7 @@ static int rtw89_cam_attach_sec_cam(struct rtw89_dev *rtwdev, } rtwvif = (struct rtw89_vif *)vif->drv_priv; - addr_cam = &rtwvif->addr_cam; + addr_cam = rtw89_get_addr_cam_of(rtwvif, rtwsta); ret = rtw89_cam_get_addr_cam_key_idx(addr_cam, sec_cam, key, &key_idx); if (ret) { rtw89_err(rtwdev, "failed to get addr cam key idx %d, %d\n", @@ -387,7 +387,7 @@ int rtw89_cam_sec_key_del(struct rtw89_dev *rtwdev, } rtwvif = (struct rtw89_vif *)vif->drv_priv; - addr_cam = &rtwvif->addr_cam; + addr_cam = rtw89_get_addr_cam_of(rtwvif, rtwsta); sec_cam = addr_cam->sec_entries[key_idx]; if (!sec_cam) return -EINVAL; @@ -427,15 +427,23 @@ static void rtw89_cam_reset_key_iter(struct ieee80211_hw *hw, rtw89_cam_deinit(rtwdev, rtwvif); } +void rtw89_cam_deinit_addr_cam(struct rtw89_dev *rtwdev, + struct rtw89_addr_cam_entry *addr_cam) +{ + struct rtw89_cam_info *cam_info = &rtwdev->cam_info; + + addr_cam->valid = false; + clear_bit(addr_cam->addr_cam_idx, cam_info->addr_cam_map); +} + void rtw89_cam_deinit(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) { struct rtw89_cam_info *cam_info = &rtwdev->cam_info; struct rtw89_addr_cam_entry *addr_cam = &rtwvif->addr_cam; struct rtw89_bssid_cam_entry *bssid_cam = &rtwvif->bssid_cam; - addr_cam->valid = false; + rtw89_cam_deinit_addr_cam(rtwdev, addr_cam); bssid_cam->valid = false; - clear_bit(addr_cam->addr_cam_idx, cam_info->addr_cam_map); clear_bit(bssid_cam->bssid_cam_idx, cam_info->bssid_cam_map); } @@ -464,10 +472,10 @@ static int rtw89_cam_get_avail_addr_cam(struct rtw89_dev *rtwdev, return 0; } -static int rtw89_cam_init_addr_cam(struct rtw89_dev *rtwdev, - struct rtw89_vif *rtwvif) +int rtw89_cam_init_addr_cam(struct rtw89_dev *rtwdev, + struct rtw89_addr_cam_entry *addr_cam, + const struct rtw89_bssid_cam_entry *bssid_cam) { - struct rtw89_addr_cam_entry *addr_cam = &rtwvif->addr_cam; u8 addr_cam_idx; int i; int ret; @@ -484,14 +492,17 @@ static int rtw89_cam_init_addr_cam(struct rtw89_dev *rtwdev, addr_cam->valid = true; addr_cam->addr_mask = 0; addr_cam->mask_sel = RTW89_NO_MSK; + addr_cam->sec_ent_mode = RTW89_ADDR_CAM_SEC_NORMAL; bitmap_zero(addr_cam->sec_cam_map, RTW89_SEC_CAM_IN_ADDR_CAM); - ether_addr_copy(addr_cam->sma, rtwvif->mac_addr); for (i = 0; i < RTW89_SEC_CAM_IN_ADDR_CAM; i++) { addr_cam->sec_ent_keyid[i] = 0; addr_cam->sec_ent[i] = 0; } + /* associate addr cam with bssid cam */ + addr_cam->bssid_cam_idx = bssid_cam->bssid_cam_idx; + return 0; } @@ -549,21 +560,18 @@ int rtw89_cam_init(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) struct rtw89_bssid_cam_entry *bssid_cam = &rtwvif->bssid_cam; int ret; - ret = rtw89_cam_init_addr_cam(rtwdev, rtwvif); + ret = rtw89_cam_init_bssid_cam(rtwdev, rtwvif); if (ret) { - rtw89_err(rtwdev, "failed to init addr cam\n"); + rtw89_err(rtwdev, "failed to init bssid cam\n"); return ret; } - ret = rtw89_cam_init_bssid_cam(rtwdev, rtwvif); + ret = rtw89_cam_init_addr_cam(rtwdev, addr_cam, bssid_cam); if (ret) { - rtw89_err(rtwdev, "failed to init bssid cam\n"); + rtw89_err(rtwdev, "failed to init addr cam\n"); return ret; } - /* associate addr cam with bssid cam */ - addr_cam->bssid_cam_idx = bssid_cam->bssid_cam_idx; - return 0; } @@ -609,7 +617,7 @@ void rtw89_cam_fill_addr_cam_info(struct rtw89_dev *rtwdev, u8 *cmd) { struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif); - struct rtw89_addr_cam_entry *addr_cam = &rtwvif->addr_cam; + struct rtw89_addr_cam_entry *addr_cam = rtw89_get_addr_cam_of(rtwvif, rtwsta); struct ieee80211_sta *sta = rtwsta_to_sta_safe(rtwsta); const u8 *sma = scan_mac_addr ? scan_mac_addr : rtwvif->mac_addr; u8 sma_hash, tma_hash, addr_msk_start; diff --git a/drivers/net/wireless/realtek/rtw89/cam.h b/drivers/net/wireless/realtek/rtw89/cam.h index 33a3ad582b81..3a6a786530d1 100644 --- a/drivers/net/wireless/realtek/rtw89/cam.h +++ b/drivers/net/wireless/realtek/rtw89/cam.h @@ -346,6 +346,11 @@ static inline void FWCMD_SET_ADDR_BSSID_BSSID5(void *cmd, u32 value) int rtw89_cam_init(struct rtw89_dev *rtwdev, struct rtw89_vif *vif); void rtw89_cam_deinit(struct rtw89_dev *rtwdev, struct rtw89_vif *vif); +int rtw89_cam_init_addr_cam(struct rtw89_dev *rtwdev, + struct rtw89_addr_cam_entry *addr_cam, + const struct rtw89_bssid_cam_entry *bssid_cam); +void rtw89_cam_deinit_addr_cam(struct rtw89_dev *rtwdev, + struct rtw89_addr_cam_entry *addr_cam); void rtw89_cam_fill_addr_cam_info(struct rtw89_dev *rtwdev, struct rtw89_vif *vif, struct rtw89_sta *rtwsta, diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c index 9f7d4f8d0c56..07f26718b66f 100644 --- a/drivers/net/wireless/realtek/rtw89/coex.c +++ b/drivers/net/wireless/realtek/rtw89/coex.c @@ -594,7 +594,7 @@ static void _reset_btc_var(struct rtw89_dev *rtwdev, u8 type) memset(&btc->dm, 0, sizeof(btc->dm)); memset(bt_linfo->rssi_state, 0, sizeof(bt_linfo->rssi_state)); - for (i = 0; i < RTW89_MAX_HW_PORT_NUM; i++) + for (i = 0; i < RTW89_PORT_NUM; i++) memset(wl_linfo[i].rssi_state, 0, sizeof(wl_linfo[i].rssi_state)); @@ -1698,7 +1698,7 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev) wl_rinfo->link_mode == BTC_WLINK_2G_SCC) { en = true; /* get p2p channel */ - for (i = 0; i < RTW89_MAX_HW_PORT_NUM; i++) { + for (i = 0; i < RTW89_PORT_NUM; i++) { if (wl_rinfo->active_role[i].role == RTW89_WIFI_ROLE_P2P_GO || wl_rinfo->active_role[i].role == @@ -1711,7 +1711,7 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev) } else { en = true; /* get 2g channel */ - for (i = 0; i < RTW89_MAX_HW_PORT_NUM; i++) { + for (i = 0; i < RTW89_PORT_NUM; i++) { if (wl_rinfo->active_role[i].connected && wl_rinfo->active_role[i].band == RTW89_BAND_2G) { ch = wl_rinfo->active_role[i].ch; @@ -3287,7 +3287,7 @@ static void _update_wl_info(struct rtw89_dev *rtwdev) memset(wl_rinfo, 0, sizeof(*wl_rinfo)); - for (i = 0; i < RTW89_MAX_HW_PORT_NUM; i++) { + for (i = 0; i < RTW89_PORT_NUM; i++) { /* check if role active? */ if (!wl_linfo[i].active) continue; @@ -4370,6 +4370,7 @@ void rtw89_btc_ntfy_wl_rfk(struct rtw89_dev *rtwdev, u8 phy_map, rtwdev->is_bt_iqk_timeout = true; } } +EXPORT_SYMBOL(rtw89_btc_ntfy_wl_rfk); struct rtw89_btc_wl_sta_iter_data { struct rtw89_dev *rtwdev; @@ -4676,7 +4677,7 @@ static void _show_wl_role_info(struct rtw89_dev *rtwdev, struct seq_file *m) wl_dinfo->real_band[RTW89_PHY_1]); } - for (i = 0; i < RTW89_MAX_HW_PORT_NUM; i++) { + for (i = 0; i < RTW89_PORT_NUM; i++) { plink = &btc->cx.wl.link_info[i]; if (!plink->active) diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index a0737eea9f81..a9544b006f0b 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -4,6 +4,7 @@ #include <linux/ip.h> #include <linux/udp.h> +#include "cam.h" #include "coex.h" #include "core.h" #include "efuse.h" @@ -21,50 +22,122 @@ static bool rtw89_disable_ps_mode; module_param_named(disable_ps_mode, rtw89_disable_ps_mode, bool, 0644); MODULE_PARM_DESC(disable_ps_mode, "Set Y to disable low power mode"); +#define RTW89_DEF_CHAN(_freq, _hw_val, _flags, _band) \ + { .center_freq = _freq, .hw_value = _hw_val, .flags = _flags, .band = _band, } +#define RTW89_DEF_CHAN_2G(_freq, _hw_val) \ + RTW89_DEF_CHAN(_freq, _hw_val, 0, NL80211_BAND_2GHZ) +#define RTW89_DEF_CHAN_5G(_freq, _hw_val) \ + RTW89_DEF_CHAN(_freq, _hw_val, 0, NL80211_BAND_5GHZ) +#define RTW89_DEF_CHAN_5G_NO_HT40MINUS(_freq, _hw_val) \ + RTW89_DEF_CHAN(_freq, _hw_val, IEEE80211_CHAN_NO_HT40MINUS, NL80211_BAND_5GHZ) +#define RTW89_DEF_CHAN_6G(_freq, _hw_val) \ + RTW89_DEF_CHAN(_freq, _hw_val, 0, NL80211_BAND_6GHZ) + static struct ieee80211_channel rtw89_channels_2ghz[] = { - { .center_freq = 2412, .hw_value = 1, }, - { .center_freq = 2417, .hw_value = 2, }, - { .center_freq = 2422, .hw_value = 3, }, - { .center_freq = 2427, .hw_value = 4, }, - { .center_freq = 2432, .hw_value = 5, }, - { .center_freq = 2437, .hw_value = 6, }, - { .center_freq = 2442, .hw_value = 7, }, - { .center_freq = 2447, .hw_value = 8, }, - { .center_freq = 2452, .hw_value = 9, }, - { .center_freq = 2457, .hw_value = 10, }, - { .center_freq = 2462, .hw_value = 11, }, - { .center_freq = 2467, .hw_value = 12, }, - { .center_freq = 2472, .hw_value = 13, }, - { .center_freq = 2484, .hw_value = 14, }, + RTW89_DEF_CHAN_2G(2412, 1), + RTW89_DEF_CHAN_2G(2417, 2), + RTW89_DEF_CHAN_2G(2422, 3), + RTW89_DEF_CHAN_2G(2427, 4), + RTW89_DEF_CHAN_2G(2432, 5), + RTW89_DEF_CHAN_2G(2437, 6), + RTW89_DEF_CHAN_2G(2442, 7), + RTW89_DEF_CHAN_2G(2447, 8), + RTW89_DEF_CHAN_2G(2452, 9), + RTW89_DEF_CHAN_2G(2457, 10), + RTW89_DEF_CHAN_2G(2462, 11), + RTW89_DEF_CHAN_2G(2467, 12), + RTW89_DEF_CHAN_2G(2472, 13), + RTW89_DEF_CHAN_2G(2484, 14), }; static struct ieee80211_channel rtw89_channels_5ghz[] = { - {.center_freq = 5180, .hw_value = 36,}, - {.center_freq = 5200, .hw_value = 40,}, - {.center_freq = 5220, .hw_value = 44,}, - {.center_freq = 5240, .hw_value = 48,}, - {.center_freq = 5260, .hw_value = 52,}, - {.center_freq = 5280, .hw_value = 56,}, - {.center_freq = 5300, .hw_value = 60,}, - {.center_freq = 5320, .hw_value = 64,}, - {.center_freq = 5500, .hw_value = 100,}, - {.center_freq = 5520, .hw_value = 104,}, - {.center_freq = 5540, .hw_value = 108,}, - {.center_freq = 5560, .hw_value = 112,}, - {.center_freq = 5580, .hw_value = 116,}, - {.center_freq = 5600, .hw_value = 120,}, - {.center_freq = 5620, .hw_value = 124,}, - {.center_freq = 5640, .hw_value = 128,}, - {.center_freq = 5660, .hw_value = 132,}, - {.center_freq = 5680, .hw_value = 136,}, - {.center_freq = 5700, .hw_value = 140,}, - {.center_freq = 5720, .hw_value = 144,}, - {.center_freq = 5745, .hw_value = 149,}, - {.center_freq = 5765, .hw_value = 153,}, - {.center_freq = 5785, .hw_value = 157,}, - {.center_freq = 5805, .hw_value = 161,}, - {.center_freq = 5825, .hw_value = 165, - .flags = IEEE80211_CHAN_NO_HT40MINUS}, + RTW89_DEF_CHAN_5G(5180, 36), + RTW89_DEF_CHAN_5G(5200, 40), + RTW89_DEF_CHAN_5G(5220, 44), + RTW89_DEF_CHAN_5G(5240, 48), + RTW89_DEF_CHAN_5G(5260, 52), + RTW89_DEF_CHAN_5G(5280, 56), + RTW89_DEF_CHAN_5G(5300, 60), + RTW89_DEF_CHAN_5G(5320, 64), + RTW89_DEF_CHAN_5G(5500, 100), + RTW89_DEF_CHAN_5G(5520, 104), + RTW89_DEF_CHAN_5G(5540, 108), + RTW89_DEF_CHAN_5G(5560, 112), + RTW89_DEF_CHAN_5G(5580, 116), + RTW89_DEF_CHAN_5G(5600, 120), + RTW89_DEF_CHAN_5G(5620, 124), + RTW89_DEF_CHAN_5G(5640, 128), + RTW89_DEF_CHAN_5G(5660, 132), + RTW89_DEF_CHAN_5G(5680, 136), + RTW89_DEF_CHAN_5G(5700, 140), + RTW89_DEF_CHAN_5G(5720, 144), + RTW89_DEF_CHAN_5G(5745, 149), + RTW89_DEF_CHAN_5G(5765, 153), + RTW89_DEF_CHAN_5G(5785, 157), + RTW89_DEF_CHAN_5G(5805, 161), + RTW89_DEF_CHAN_5G_NO_HT40MINUS(5825, 165), +}; + +static struct ieee80211_channel rtw89_channels_6ghz[] = { + RTW89_DEF_CHAN_6G(5955, 1), + RTW89_DEF_CHAN_6G(5975, 5), + RTW89_DEF_CHAN_6G(5995, 9), + RTW89_DEF_CHAN_6G(6015, 13), + RTW89_DEF_CHAN_6G(6035, 17), + RTW89_DEF_CHAN_6G(6055, 21), + RTW89_DEF_CHAN_6G(6075, 25), + RTW89_DEF_CHAN_6G(6095, 29), + RTW89_DEF_CHAN_6G(6115, 33), + RTW89_DEF_CHAN_6G(6135, 37), + RTW89_DEF_CHAN_6G(6155, 41), + RTW89_DEF_CHAN_6G(6175, 45), + RTW89_DEF_CHAN_6G(6195, 49), + RTW89_DEF_CHAN_6G(6215, 53), + RTW89_DEF_CHAN_6G(6235, 57), + RTW89_DEF_CHAN_6G(6255, 61), + RTW89_DEF_CHAN_6G(6275, 65), + RTW89_DEF_CHAN_6G(6295, 69), + RTW89_DEF_CHAN_6G(6315, 73), + RTW89_DEF_CHAN_6G(6335, 77), + RTW89_DEF_CHAN_6G(6355, 81), + RTW89_DEF_CHAN_6G(6375, 85), + RTW89_DEF_CHAN_6G(6395, 89), + RTW89_DEF_CHAN_6G(6415, 93), + RTW89_DEF_CHAN_6G(6435, 97), + RTW89_DEF_CHAN_6G(6455, 101), + RTW89_DEF_CHAN_6G(6475, 105), + RTW89_DEF_CHAN_6G(6495, 109), + RTW89_DEF_CHAN_6G(6515, 113), + RTW89_DEF_CHAN_6G(6535, 117), + RTW89_DEF_CHAN_6G(6555, 121), + RTW89_DEF_CHAN_6G(6575, 125), + RTW89_DEF_CHAN_6G(6595, 129), + RTW89_DEF_CHAN_6G(6615, 133), + RTW89_DEF_CHAN_6G(6635, 137), + RTW89_DEF_CHAN_6G(6655, 141), + RTW89_DEF_CHAN_6G(6675, 145), + RTW89_DEF_CHAN_6G(6695, 149), + RTW89_DEF_CHAN_6G(6715, 153), + RTW89_DEF_CHAN_6G(6735, 157), + RTW89_DEF_CHAN_6G(6755, 161), + RTW89_DEF_CHAN_6G(6775, 165), + RTW89_DEF_CHAN_6G(6795, 169), + RTW89_DEF_CHAN_6G(6815, 173), + RTW89_DEF_CHAN_6G(6835, 177), + RTW89_DEF_CHAN_6G(6855, 181), + RTW89_DEF_CHAN_6G(6875, 185), + RTW89_DEF_CHAN_6G(6895, 189), + RTW89_DEF_CHAN_6G(6915, 193), + RTW89_DEF_CHAN_6G(6935, 197), + RTW89_DEF_CHAN_6G(6955, 201), + RTW89_DEF_CHAN_6G(6975, 205), + RTW89_DEF_CHAN_6G(6995, 209), + RTW89_DEF_CHAN_6G(7015, 213), + RTW89_DEF_CHAN_6G(7035, 217), + RTW89_DEF_CHAN_6G(7055, 221), + RTW89_DEF_CHAN_6G(7075, 225), + RTW89_DEF_CHAN_6G(7095, 229), + RTW89_DEF_CHAN_6G(7115, 233), }; static struct ieee80211_rate rtw89_bitrates[] = { @@ -118,6 +191,16 @@ static struct ieee80211_supported_band rtw89_sband_5ghz = { .vht_cap = {0}, }; +static struct ieee80211_supported_band rtw89_sband_6ghz = { + .band = NL80211_BAND_6GHZ, + .channels = rtw89_channels_6ghz, + .n_channels = ARRAY_SIZE(rtw89_channels_6ghz), + + /* 6G has no CCK rates, 1M/2M/5.5M/11M */ + .bitrates = rtw89_bitrates + 4, + .n_bitrates = ARRAY_SIZE(rtw89_bitrates) - 4, +}; + static void rtw89_traffic_stats_accu(struct rtw89_dev *rtwdev, struct rtw89_traffic_stats *stats, struct sk_buff *skb, bool tx) @@ -149,6 +232,8 @@ static void rtw89_get_channel_params(struct cfg80211_chan_def *chandef, u8 center_chan; u8 bandwidth = RTW89_CHANNEL_WIDTH_20; u8 primary_chan_idx = 0; + u8 band; + u8 subband; center_chan = channel->hw_value; primary_freq = channel->center_freq; @@ -195,10 +280,41 @@ static void rtw89_get_channel_params(struct cfg80211_chan_def *chandef, break; } + switch (channel->band) { + default: + case NL80211_BAND_2GHZ: + band = RTW89_BAND_2G; + break; + case NL80211_BAND_5GHZ: + band = RTW89_BAND_5G; + break; + case NL80211_BAND_6GHZ: + band = RTW89_BAND_6G; + break; + } + + switch (center_chan) { + default: + case 1 ... 14: + subband = RTW89_CH_2G; + break; + case 36 ... 64: + subband = RTW89_CH_5G_BAND_1; + break; + case 100 ... 144: + subband = RTW89_CH_5G_BAND_3; + break; + case 149 ... 177: + subband = RTW89_CH_5G_BAND_4; + break; + } + chan_param->center_chan = center_chan; chan_param->primary_chan = channel->hw_value; chan_param->bandwidth = bandwidth; chan_param->pri_ch_idx = primary_chan_idx; + chan_param->band_type = band; + chan_param->subband_type = subband; } void rtw89_set_channel(struct rtw89_dev *rtwdev) @@ -209,7 +325,6 @@ void rtw89_set_channel(struct rtw89_dev *rtwdev) struct rtw89_channel_params ch_param; struct rtw89_channel_help_params bak; u8 center_chan, bandwidth; - u8 band_type; bool band_changed; rtw89_get_channel_params(&hw->conf.chandef, &ch_param); @@ -218,30 +333,15 @@ void rtw89_set_channel(struct rtw89_dev *rtwdev) center_chan = ch_param.center_chan; bandwidth = ch_param.bandwidth; - band_type = center_chan > 14 ? RTW89_BAND_5G : RTW89_BAND_2G; - band_changed = hal->current_band_type != band_type || + band_changed = hal->current_band_type != ch_param.band_type || hal->current_channel == 0; hal->current_band_width = bandwidth; hal->current_channel = center_chan; hal->prev_primary_channel = hal->current_primary_channel; hal->current_primary_channel = ch_param.primary_chan; - hal->current_band_type = band_type; - - switch (center_chan) { - case 1 ... 14: - hal->current_subband = RTW89_CH_2G; - break; - case 36 ... 64: - hal->current_subband = RTW89_CH_5G_BAND_1; - break; - case 100 ... 144: - hal->current_subband = RTW89_CH_5G_BAND_3; - break; - case 149 ... 177: - hal->current_subband = RTW89_CH_5G_BAND_4; - break; - } + hal->current_band_type = ch_param.band_type; + hal->current_subband = ch_param.subband_type; rtw89_chip_set_channel_prepare(rtwdev, &bak); @@ -300,9 +400,11 @@ rtw89_core_tx_update_sec_key(struct rtw89_dev *rtwdev, struct rtw89_core_tx_request *tx_req) { struct ieee80211_vif *vif = tx_req->vif; + struct ieee80211_sta *sta = tx_req->sta; struct ieee80211_tx_info *info; struct ieee80211_key_conf *key; struct rtw89_vif *rtwvif; + struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta); struct rtw89_addr_cam_entry *addr_cam; struct rtw89_sec_cam_entry *sec_cam; struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info; @@ -315,7 +417,7 @@ rtw89_core_tx_update_sec_key(struct rtw89_dev *rtwdev, } rtwvif = (struct rtw89_vif *)vif->drv_priv; - addr_cam = &rtwvif->addr_cam; + addr_cam = rtw89_get_addr_cam_of(rtwvif, rtwsta); info = IEEE80211_SKB_CB(skb); key = info->control.hw_key; @@ -377,14 +479,19 @@ static void rtw89_core_tx_update_mgmt_info(struct rtw89_dev *rtwdev, struct rtw89_core_tx_request *tx_req) { + struct ieee80211_vif *vif = tx_req->vif; + struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info; u8 qsel, ch_dma; - qsel = RTW89_TX_QSEL_B0_MGMT; + qsel = desc_info->hiq ? RTW89_TX_QSEL_B0_HI : RTW89_TX_QSEL_B0_MGMT; ch_dma = rtw89_core_get_ch_dma(rtwdev, qsel); - desc_info->qsel = RTW89_TX_QSEL_B0_MGMT; + desc_info->qsel = qsel; desc_info->ch_dma = ch_dma; + desc_info->port = desc_info->hiq ? rtwvif->port : 0; + desc_info->hw_ssn_sel = RTW89_MGMT_HW_SSN_SEL; + desc_info->hw_seq_mode = RTW89_MGMT_HW_SEQ_MODE; /* fixed data rate for mgmt frames */ desc_info->en_wd_info = true; @@ -520,6 +627,21 @@ desc_bk: desc_info->bk = true; } +static u8 rtw89_core_tx_get_mac_id(struct rtw89_dev *rtwdev, + struct rtw89_core_tx_request *tx_req) +{ + struct ieee80211_vif *vif = tx_req->vif; + struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; + struct ieee80211_sta *sta = tx_req->sta; + struct rtw89_sta *rtwsta; + + if (!sta) + return rtwvif->mac_id; + + rtwsta = (struct rtw89_sta *)sta->drv_priv; + return rtwsta->mac_id; +} + static void rtw89_core_tx_update_data_info(struct rtw89_dev *rtwdev, struct rtw89_core_tx_request *tx_req) @@ -535,12 +657,14 @@ rtw89_core_tx_update_data_info(struct rtw89_dev *rtwdev, tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; tid_indicate = rtw89_core_get_tid_indicate(rtwdev, tid); - qsel = rtw89_core_get_qsel(rtwdev, tid); + qsel = desc_info->hiq ? RTW89_TX_QSEL_B0_HI : rtw89_core_get_qsel(rtwdev, tid); ch_dma = rtw89_core_get_ch_dma(rtwdev, qsel); desc_info->ch_dma = ch_dma; desc_info->tid_indicate = tid_indicate; desc_info->qsel = qsel; + desc_info->mac_id = rtw89_core_tx_get_mac_id(rtwdev, tx_req); + desc_info->port = desc_info->hiq ? rtwvif->port : 0; /* enable wd_info for AMPDU */ desc_info->en_wd_info = true; @@ -601,6 +725,7 @@ rtw89_core_tx_update_desc_info(struct rtw89_dev *rtwdev, { struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info; struct sk_buff *skb = tx_req->skb; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; enum rtw89_core_tx_type tx_type; enum btc_pkt_type pkt_type; @@ -619,6 +744,7 @@ rtw89_core_tx_update_desc_info(struct rtw89_dev *rtwdev, desc_info->pkt_size = skb->len; desc_info->is_bmc = is_bmc; desc_info->wd_page = true; + desc_info->hiq = info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM; switch (tx_req->tx_type) { case RTW89_CORE_TX_TYPE_MGMT: @@ -710,7 +836,9 @@ static __le32 rtw89_build_txwd_body0(struct rtw89_tx_desc_info *desc_info) FIELD_PREP(RTW89_TXWD_BODY0_CHANNEL_DMA, desc_info->ch_dma) | FIELD_PREP(RTW89_TXWD_BODY0_HDR_LLC_LEN, desc_info->hdr_llc_len) | FIELD_PREP(RTW89_TXWD_BODY0_WD_PAGE, desc_info->wd_page) | - FIELD_PREP(RTW89_TXWD_BODY0_FW_DL, desc_info->fw_dl); + FIELD_PREP(RTW89_TXWD_BODY0_FW_DL, desc_info->fw_dl) | + FIELD_PREP(RTW89_TXWD_BODY0_HW_SSN_SEL, desc_info->hw_ssn_sel) | + FIELD_PREP(RTW89_TXWD_BODY0_HW_SSN_MODE, desc_info->hw_seq_mode); return cpu_to_le32(dword); } @@ -719,7 +847,8 @@ static __le32 rtw89_build_txwd_body2(struct rtw89_tx_desc_info *desc_info) { u32 dword = FIELD_PREP(RTW89_TXWD_BODY2_TID_INDICATE, desc_info->tid_indicate) | FIELD_PREP(RTW89_TXWD_BODY2_QSEL, desc_info->qsel) | - FIELD_PREP(RTW89_TXWD_BODY2_TXPKT_SIZE, desc_info->pkt_size); + FIELD_PREP(RTW89_TXWD_BODY2_TXPKT_SIZE, desc_info->pkt_size) | + FIELD_PREP(RTW89_TXWD_BODY2_MACID, desc_info->mac_id); return cpu_to_le32(dword); } @@ -737,7 +866,8 @@ static __le32 rtw89_build_txwd_info0(struct rtw89_tx_desc_info *desc_info) { u32 dword = FIELD_PREP(RTW89_TXWD_INFO0_USE_RATE, desc_info->use_rate) | FIELD_PREP(RTW89_TXWD_INFO0_DATA_RATE, desc_info->data_rate) | - FIELD_PREP(RTW89_TXWD_INFO0_DISDATAFB, desc_info->dis_data_fb); + FIELD_PREP(RTW89_TXWD_INFO0_DISDATAFB, desc_info->dis_data_fb) | + FIELD_PREP(RTW89_TXWD_INFO0_MULTIPORT_ID, desc_info->port); return cpu_to_le32(dword); } @@ -1087,6 +1217,18 @@ static void rtw89_core_hw_to_sband_rate(struct ieee80211_rx_status *rx_status) rx_status->rate_idx -= 4; } +static void rtw89_core_rx_to_mac80211(struct rtw89_dev *rtwdev, + struct rtw89_rx_phy_ppdu *phy_ppdu, + struct rtw89_rx_desc_info *desc_info, + struct sk_buff *skb_ppdu, + struct ieee80211_rx_status *rx_status) +{ + rtw89_core_hw_to_sband_rate(rx_status); + rtw89_core_rx_stats(rtwdev, phy_ppdu, desc_info, skb_ppdu); + ieee80211_rx_napi(rtwdev->hw, NULL, skb_ppdu, &rtwdev->napi); + rtwdev->napi_budget_countdown--; +} + static void rtw89_core_rx_pending_skb(struct rtw89_dev *rtwdev, struct rtw89_rx_phy_ppdu *phy_ppdu, struct rtw89_rx_desc_info *desc_info, @@ -1106,10 +1248,7 @@ static void rtw89_core_rx_pending_skb(struct rtw89_dev *rtwdev, if (rtw89_core_rx_ppdu_match(rtwdev, desc_info, rx_status)) rtw89_chip_query_ppdu(rtwdev, phy_ppdu, rx_status); rtw89_correct_cck_chan(rtwdev, rx_status); - rtw89_core_hw_to_sband_rate(rx_status); - rtw89_core_rx_stats(rtwdev, phy_ppdu, desc_info, skb_ppdu); - ieee80211_rx_napi(rtwdev->hw, NULL, skb_ppdu, &rtwdev->napi); - rtwdev->napi_budget_countdown--; + rtw89_core_rx_to_mac80211(rtwdev, phy_ppdu, desc_info, skb_ppdu, rx_status); } } @@ -1334,10 +1473,7 @@ static void rtw89_core_flush_ppdu_rx_queue(struct rtw89_dev *rtwdev, skb_queue_walk_safe(&ppdu_sts->rx_queue[band], skb_ppdu, tmp) { skb_unlink(skb_ppdu, &ppdu_sts->rx_queue[band]); rx_status = IEEE80211_SKB_RXCB(skb_ppdu); - rtw89_core_hw_to_sband_rate(rx_status); - rtw89_core_rx_stats(rtwdev, NULL, desc_info, skb_ppdu); - ieee80211_rx_napi(rtwdev->hw, NULL, skb_ppdu, &rtwdev->napi); - rtwdev->napi_budget_countdown--; + rtw89_core_rx_to_mac80211(rtwdev, NULL, desc_info, skb_ppdu, rx_status); } } @@ -1364,14 +1500,10 @@ void rtw89_core_rx(struct rtw89_dev *rtwdev, memset(rx_status, 0, sizeof(*rx_status)); rtw89_core_update_rx_status(rtwdev, desc_info, rx_status); if (desc_info->long_rxdesc && - BIT(desc_info->frame_type) & PPDU_FILTER_BITMAP) { + BIT(desc_info->frame_type) & PPDU_FILTER_BITMAP) skb_queue_tail(&ppdu_sts->rx_queue[band], skb); - } else { - rtw89_core_hw_to_sband_rate(rx_status); - rtw89_core_rx_stats(rtwdev, NULL, desc_info, skb); - ieee80211_rx_napi(rtwdev->hw, NULL, skb, &rtwdev->napi); - rtwdev->napi_budget_countdown--; - } + else + rtw89_core_rx_to_mac80211(rtwdev, NULL, desc_info, skb, rx_status); } EXPORT_SYMBOL(rtw89_core_rx); @@ -1770,6 +1902,51 @@ void rtw89_core_release_all_bits_map(unsigned long *addr, unsigned int nbits) bitmap_zero(addr, nbits); } +int rtw89_core_acquire_sta_ba_entry(struct rtw89_sta *rtwsta, u8 tid, u8 *cam_idx) +{ + struct rtw89_ba_cam_entry *entry; + u8 idx; + + idx = rtw89_core_acquire_bit_map(rtwsta->ba_cam_map, RTW89_BA_CAM_NUM); + if (idx == RTW89_BA_CAM_NUM) { + /* allocate a static BA CAM to tid=0, so replace the existing + * one if BA CAM is full. Hardware will process the original tid + * automatically. + */ + if (tid != 0) + return -ENOSPC; + + idx = 0; + } + + entry = &rtwsta->ba_cam_entry[idx]; + entry->tid = tid; + *cam_idx = idx; + + return 0; +} + +int rtw89_core_release_sta_ba_entry(struct rtw89_sta *rtwsta, u8 tid, u8 *cam_idx) +{ + struct rtw89_ba_cam_entry *entry; + int i; + + for (i = 0; i < RTW89_BA_CAM_NUM; i++) { + if (!test_bit(i, rtwsta->ba_cam_map)) + continue; + + entry = &rtwsta->ba_cam_entry[i]; + if (entry->tid != tid) + continue; + + rtw89_core_release_bit_map(rtwsta->ba_cam_map, i); + *cam_idx = i; + return 0; + } + + return -ENOENT; +} + #define RTW89_TYPE_MAPPING(_type) \ case NL80211_IFTYPE_ ## _type: \ rtwvif->wifi_role = RTW89_WIFI_ROLE_ ## _type; \ @@ -1838,6 +2015,9 @@ int rtw89_core_sta_add(struct rtw89_dev *rtwdev, rtw89_btc_ntfy_role_info(rtwdev, rtwvif, rtwsta, BTC_ROLE_MSTS_STA_CONN_START); rtw89_chip_rfk_channel(rtwdev); + } else if (vif->type == NL80211_IFTYPE_AP) { + rtwsta->mac_id = rtw89_core_acquire_bit_map(rtwdev->mac_id_map, + RTW89_MAX_MAC_ID_NUM); } return 0; @@ -1866,8 +2046,11 @@ int rtw89_core_sta_disconnect(struct rtw89_dev *rtwdev, rtw89_mac_bf_monitor_calc(rtwdev, sta, true); rtw89_mac_bf_disassoc(rtwdev, vif, sta); rtw89_core_free_sta_pending_ba(rtwdev, sta); + if (vif->type == NL80211_IFTYPE_AP) + rtw89_cam_deinit_addr_cam(rtwdev, &rtwsta->addr_cam); - rtw89_vif_type_mapping(vif, false); + if (vif->type == NL80211_IFTYPE_STATION) + rtw89_vif_type_mapping(vif, false); ret = rtw89_fw_h2c_assoc_cmac_tbl(rtwdev, vif, sta); if (ret) { @@ -1875,14 +2058,22 @@ int rtw89_core_sta_disconnect(struct rtw89_dev *rtwdev, return ret; } - ret = rtw89_fw_h2c_join_info(rtwdev, rtwvif, 1); + ret = rtw89_fw_h2c_join_info(rtwdev, rtwvif, rtwsta, true); if (ret) { rtw89_warn(rtwdev, "failed to send h2c join info\n"); return ret; } + if (vif->type == NL80211_IFTYPE_AP) { + ret = rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, rtwsta, RTW89_ROLE_REMOVE); + if (ret) { + rtw89_warn(rtwdev, "failed to send h2c role info\n"); + return ret; + } + } + /* update cam aid mac_id net_type */ - rtw89_fw_h2c_cam(rtwdev, rtwvif, rtwsta, NULL); + ret = rtw89_fw_h2c_cam(rtwdev, rtwvif, rtwsta, NULL); if (ret) { rtw89_warn(rtwdev, "failed to send h2c cam\n"); return ret; @@ -1899,7 +2090,25 @@ int rtw89_core_sta_assoc(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv; int ret; - rtw89_vif_type_mapping(vif, true); + if (vif->type == NL80211_IFTYPE_AP) { + ret = rtw89_mac_set_macid_pause(rtwdev, rtwsta->mac_id, false); + if (ret) { + rtw89_warn(rtwdev, "failed to send h2c macid pause\n"); + return ret; + } + + ret = rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, rtwsta, RTW89_ROLE_CREATE); + if (ret) { + rtw89_warn(rtwdev, "failed to send h2c role info\n"); + return ret; + } + + ret = rtw89_cam_init_addr_cam(rtwdev, &rtwsta->addr_cam, &rtwvif->bssid_cam); + if (ret) { + rtw89_warn(rtwdev, "failed to send h2c init addr cam\n"); + return ret; + } + } ret = rtw89_fw_h2c_assoc_cmac_tbl(rtwdev, vif, sta); if (ret) { @@ -1907,7 +2116,7 @@ int rtw89_core_sta_assoc(struct rtw89_dev *rtwdev, return ret; } - ret = rtw89_fw_h2c_join_info(rtwdev, rtwvif, 0); + ret = rtw89_fw_h2c_join_info(rtwdev, rtwvif, rtwsta, false); if (ret) { rtw89_warn(rtwdev, "failed to send h2c join info\n"); return ret; @@ -1950,6 +2159,8 @@ int rtw89_core_sta_remove(struct rtw89_dev *rtwdev, if (vif->type == NL80211_IFTYPE_STATION) rtw89_btc_ntfy_role_info(rtwdev, rtwvif, rtwsta, BTC_ROLE_MSTS_STA_DIS_CONN); + else if (vif->type == NL80211_IFTYPE_AP) + rtw89_core_release_bit_map(rtwdev->mac_id_map, rtwsta->mac_id); return 0; } @@ -2139,34 +2350,52 @@ static int rtw89_core_set_supported_band(struct rtw89_dev *rtwdev) { struct ieee80211_hw *hw = rtwdev->hw; struct ieee80211_supported_band *sband_2ghz = NULL, *sband_5ghz = NULL; + struct ieee80211_supported_band *sband_6ghz = NULL; u32 size = sizeof(struct ieee80211_supported_band); + u8 support_bands = rtwdev->chip->support_bands; - sband_2ghz = kmemdup(&rtw89_sband_2ghz, size, GFP_KERNEL); - if (!sband_2ghz) - goto err; - rtw89_init_ht_cap(rtwdev, &sband_2ghz->ht_cap); - rtw89_init_he_cap(rtwdev, NL80211_BAND_2GHZ, sband_2ghz); - hw->wiphy->bands[NL80211_BAND_2GHZ] = sband_2ghz; + if (support_bands & BIT(NL80211_BAND_2GHZ)) { + sband_2ghz = kmemdup(&rtw89_sband_2ghz, size, GFP_KERNEL); + if (!sband_2ghz) + goto err; + rtw89_init_ht_cap(rtwdev, &sband_2ghz->ht_cap); + rtw89_init_he_cap(rtwdev, NL80211_BAND_2GHZ, sband_2ghz); + hw->wiphy->bands[NL80211_BAND_2GHZ] = sband_2ghz; + } - sband_5ghz = kmemdup(&rtw89_sband_5ghz, size, GFP_KERNEL); - if (!sband_5ghz) - goto err; - rtw89_init_ht_cap(rtwdev, &sband_5ghz->ht_cap); - rtw89_init_vht_cap(rtwdev, &sband_5ghz->vht_cap); - rtw89_init_he_cap(rtwdev, NL80211_BAND_5GHZ, sband_5ghz); - hw->wiphy->bands[NL80211_BAND_5GHZ] = sband_5ghz; + if (support_bands & BIT(NL80211_BAND_5GHZ)) { + sband_5ghz = kmemdup(&rtw89_sband_5ghz, size, GFP_KERNEL); + if (!sband_5ghz) + goto err; + rtw89_init_ht_cap(rtwdev, &sband_5ghz->ht_cap); + rtw89_init_vht_cap(rtwdev, &sband_5ghz->vht_cap); + rtw89_init_he_cap(rtwdev, NL80211_BAND_5GHZ, sband_5ghz); + hw->wiphy->bands[NL80211_BAND_5GHZ] = sband_5ghz; + } + + if (support_bands & BIT(NL80211_BAND_6GHZ)) { + sband_6ghz = kmemdup(&rtw89_sband_6ghz, size, GFP_KERNEL); + if (!sband_6ghz) + goto err; + rtw89_init_he_cap(rtwdev, NL80211_BAND_6GHZ, sband_6ghz); + hw->wiphy->bands[NL80211_BAND_6GHZ] = sband_6ghz; + } return 0; err: hw->wiphy->bands[NL80211_BAND_2GHZ] = NULL; hw->wiphy->bands[NL80211_BAND_5GHZ] = NULL; + hw->wiphy->bands[NL80211_BAND_6GHZ] = NULL; if (sband_2ghz) kfree(sband_2ghz->iftype_data); if (sband_5ghz) kfree(sband_5ghz->iftype_data); + if (sband_6ghz) + kfree(sband_6ghz->iftype_data); kfree(sband_2ghz); kfree(sband_5ghz); + kfree(sband_6ghz); return -ENOMEM; } @@ -2176,10 +2405,14 @@ static void rtw89_core_clr_supported_band(struct rtw89_dev *rtwdev) kfree(hw->wiphy->bands[NL80211_BAND_2GHZ]->iftype_data); kfree(hw->wiphy->bands[NL80211_BAND_5GHZ]->iftype_data); + if (hw->wiphy->bands[NL80211_BAND_6GHZ]) + kfree(hw->wiphy->bands[NL80211_BAND_6GHZ]->iftype_data); kfree(hw->wiphy->bands[NL80211_BAND_2GHZ]); kfree(hw->wiphy->bands[NL80211_BAND_5GHZ]); + kfree(hw->wiphy->bands[NL80211_BAND_6GHZ]); hw->wiphy->bands[NL80211_BAND_2GHZ] = NULL; hw->wiphy->bands[NL80211_BAND_5GHZ] = NULL; + hw->wiphy->bands[NL80211_BAND_6GHZ] = NULL; } static void rtw89_core_ppdu_sts_init(struct rtw89_dev *rtwdev) @@ -2192,6 +2425,21 @@ static void rtw89_core_ppdu_sts_init(struct rtw89_dev *rtwdev) rtwdev->ppdu_sts.curr_rx_ppdu_cnt[i] = U8_MAX; } +void rtw89_core_update_beacon_work(struct work_struct *work) +{ + struct rtw89_dev *rtwdev; + struct rtw89_vif *rtwvif = container_of(work, struct rtw89_vif, + update_beacon_work); + + if (rtwvif->net_type != RTW89_NET_TYPE_AP_MODE) + return; + + rtwdev = rtwvif->rtwdev; + mutex_lock(&rtwdev->mutex); + rtw89_fw_h2c_update_beacon(rtwdev, rtwvif); + mutex_unlock(&rtwdev->mutex); +} + int rtw89_core_start(struct rtw89_dev *rtwdev) { int ret; @@ -2347,6 +2595,13 @@ static void rtw89_read_chip_ver(struct rtw89_dev *rtwdev) rtwdev->hal.cv = cv; } +static void rtw89_core_setup_phycap(struct rtw89_dev *rtwdev) +{ + rtwdev->hal.support_cckpd = + !(rtwdev->chip->chip_id == RTL8852A && rtwdev->hal.cv <= CHIP_CBV) && + !(rtwdev->chip->chip_id == RTL8852B && rtwdev->hal.cv <= CHIP_CAV); +} + static int rtw89_chip_efuse_info_setup(struct rtw89_dev *rtwdev) { int ret; @@ -2367,6 +2622,8 @@ static int rtw89_chip_efuse_info_setup(struct rtw89_dev *rtwdev) if (ret) return ret; + rtw89_core_setup_phycap(rtwdev); + rtw89_mac_pwr_off(rtwdev); return 0; @@ -2439,7 +2696,8 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev) ieee80211_hw_set(hw, SUPPORTS_PS); ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); - hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); + hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_AP); hw->wiphy->available_antennas_tx = BIT(rtwdev->chip->rf_path_num) - 1; hw->wiphy->available_antennas_rx = BIT(rtwdev->chip->rf_path_num) - 1; diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h index 7c84556ec4ad..deb91f6b6737 100644 --- a/drivers/net/wireless/realtek/rtw89/core.h +++ b/drivers/net/wireless/realtek/rtw89/core.h @@ -15,7 +15,6 @@ struct rtw89_dev; extern const struct ieee80211_ops rtw89_ops; -extern const struct rtw89_chip_info rtw8852a_chip_info; #define MASKBYTE0 0xff #define MASKBYTE1 0xff00 @@ -33,7 +32,6 @@ extern const struct rtw89_chip_info rtw8852a_chip_info; #define MAX_RSSI 110 #define RSSI_FACTOR 1 #define RTW89_RSSI_RAW_TO_DBM(rssi) ((s8)((rssi) >> RSSI_FACTOR) - MAX_RSSI) -#define RTW89_MAX_HW_PORT_NUM 5 #define RTW89_HTC_MASK_VARIANT GENMASK(1, 0) #define RTW89_HTC_VARIANT_HE 3 @@ -140,11 +138,11 @@ enum rtw89_wifi_role { }; enum rtw89_upd_mode { - RTW89_VIF_CREATE, - RTW89_VIF_REMOVE, - RTW89_VIF_TYPE_CHANGE, - RTW89_VIF_INFO_CHANGE, - RTW89_VIF_CON_DISCONN + RTW89_ROLE_CREATE, + RTW89_ROLE_REMOVE, + RTW89_ROLE_TYPE_CHANGE, + RTW89_ROLE_INFO_CHANGE, + RTW89_ROLE_CON_DISCONN }; enum rtw89_self_role { @@ -205,6 +203,7 @@ enum rtw89_port { enum rtw89_band { RTW89_BAND_2G = 0, RTW89_BAND_5G = 1, + RTW89_BAND_6G = 2, RTW89_BAND_MAX, }; @@ -421,9 +420,6 @@ enum rtw89_regulation_type { RTW89_REGD_NUM, }; -extern const u8 rtw89_rs_idx_max[RTW89_RS_MAX]; -extern const u8 rtw89_rs_nss_max[RTW89_RS_MAX]; - struct rtw89_txpwr_byrate { s8 cck[RTW89_RATE_CCK_MAX]; s8 ofdm[RTW89_RATE_OFDM_MAX]; @@ -573,6 +569,8 @@ struct rtw89_channel_params { u8 primary_chan; u8 bandwidth; u8 pri_ch_idx; + u8 band_type; + u8 subband_type; }; struct rtw89_channel_help_params { @@ -670,6 +668,7 @@ struct rtw89_rxdesc_long { struct rtw89_tx_desc_info { u16 pkt_size; u8 wp_offset; + u8 mac_id; u8 qsel; u8 ch_dma; u8 hdr_llc_len; @@ -691,6 +690,12 @@ struct rtw89_tx_desc_info { bool fw_dl; u16 seq; bool a_ctrl_bsr; + u8 hw_ssn_sel; +#define RTW89_MGMT_HW_SSN_SEL 1 + u8 hw_seq_mode; +#define RTW89_MGMT_HW_SEQ_MODE 1 + bool hiq; + u8 port; }; struct rtw89_core_tx_request { @@ -1048,7 +1053,7 @@ struct rtw89_btc_wl_role_info { /* struct size must be n*4 bytes */ u8 connect_cnt; u8 link_mode; union rtw89_btc_wl_role_info_map role_map; - struct rtw89_btc_wl_active_role active_role[RTW89_MAX_HW_PORT_NUM]; + struct rtw89_btc_wl_active_role active_role[RTW89_PORT_NUM]; }; struct rtw89_btc_wl_ver_info { @@ -1151,7 +1156,7 @@ struct rtw89_btc_rf_para { }; struct rtw89_btc_wl_info { - struct rtw89_btc_wl_link_info link_info[RTW89_MAX_HW_PORT_NUM]; + struct rtw89_btc_wl_link_info link_info[RTW89_PORT_NUM]; struct rtw89_btc_wl_rfk_info rfk_info; struct rtw89_btc_wl_ver_info ver_info; struct rtw89_btc_wl_afh_info afh_info; @@ -1831,27 +1836,10 @@ struct rtw89_ra_report { DECLARE_EWMA(rssi, 10, 16); -struct rtw89_sta { - u8 mac_id; - bool disassoc; - struct rtw89_vif *rtwvif; - struct rtw89_ra_info ra; - struct rtw89_ra_report ra_report; - int max_agg_wait; - u8 prev_rssi; - struct ewma_rssi avg_rssi; - struct rtw89_ampdu_params ampdu_params[IEEE80211_NUM_TIDS]; - struct ieee80211_rx_status rx_status; - u16 rx_hw_rate; - __le32 htc_template; - - bool use_cfg_mask; - struct cfg80211_bitrate_mask mask; +#define RTW89_BA_CAM_NUM 2 - bool cctl_tx_time; - u32 ampdu_max_time:4; - bool cctl_tx_retry_limit; - u32 data_tx_cnt_lmt:6; +struct rtw89_ba_cam_entry { + u8 tid; }; #define RTW89_MAX_ADDR_CAM_NUM 128 @@ -1868,7 +1856,6 @@ struct rtw89_addr_cam_entry { u8 wapi : 1; u8 mask_sel : 2; u8 bssid_cam_idx: 6; - u8 sma[ETH_ALEN]; u8 sec_ent_mode; DECLARE_BITMAP(sec_cam_map, RTW89_SEC_CAM_IN_ADDR_CAM); @@ -1898,6 +1885,33 @@ struct rtw89_sec_cam_entry { u8 key[32]; }; +struct rtw89_sta { + u8 mac_id; + bool disassoc; + struct rtw89_vif *rtwvif; + struct rtw89_ra_info ra; + struct rtw89_ra_report ra_report; + int max_agg_wait; + u8 prev_rssi; + struct ewma_rssi avg_rssi; + struct rtw89_ampdu_params ampdu_params[IEEE80211_NUM_TIDS]; + struct ieee80211_rx_status rx_status; + u16 rx_hw_rate; + __le32 htc_template; + struct rtw89_addr_cam_entry addr_cam; /* AP mode only */ + + bool use_cfg_mask; + struct cfg80211_bitrate_mask mask; + + bool cctl_tx_time; + u32 ampdu_max_time:4; + bool cctl_tx_retry_limit; + u32 data_tx_cnt_lmt:6; + + DECLARE_BITMAP(ba_cam_map, RTW89_BA_CAM_NUM); + struct rtw89_ba_cam_entry ba_cam_entry[RTW89_BA_CAM_NUM]; +}; + struct rtw89_efuse { bool valid; u8 xtal_cap; @@ -1915,6 +1929,7 @@ struct rtw89_phy_rate_pattern { struct rtw89_vif { struct list_head list; + struct rtw89_dev *rtwdev; u8 mac_id; u8 port; u8 mac_addr[ETH_ALEN]; @@ -1936,6 +1951,7 @@ struct rtw89_vif { bool wowlan_magic; bool is_hesta; bool last_a_ctrl; + struct work_struct update_beacon_work; struct rtw89_addr_cam_entry addr_cam; struct rtw89_bssid_cam_entry bssid_cam; struct ieee80211_tx_queue_params tx_params[IEEE80211_NUM_ACS]; @@ -2192,6 +2208,7 @@ struct rtw89_chip_info { const struct rtw89_hfc_param_ini *hfc_param_ini; const struct rtw89_dle_mem *dle_mem; u32 rf_base_addr[2]; + u8 support_bands; u8 rf_path_num; u8 tx_nss; u8 rx_nss; @@ -2247,6 +2264,10 @@ struct rtw89_chip_info { u8 ps_mode_supported; }; +struct rtw89_driver_info { + const struct rtw89_chip_info *chip; +}; + enum rtw89_hcifc_mode { RTW89_HCIFC_POH = 0, RTW89_HCIFC_STF = 1, @@ -2358,6 +2379,7 @@ struct rtw89_hal { u32 antenna_rx; u8 tx_nss; u8 rx_nss; + bool support_cckpd; }; #define RTW89_MAX_MAC_ID_NUM 128 @@ -2805,7 +2827,7 @@ struct rtw89_dev { struct rtw89_ser ser; - DECLARE_BITMAP(hw_port, RTW89_MAX_HW_PORT_NUM); + DECLARE_BITMAP(hw_port, RTW89_PORT_NUM); DECLARE_BITMAP(mac_id_map, RTW89_MAX_MAC_ID_NUM); DECLARE_BITMAP(flags, NUM_OF_RTW89_FLAGS); @@ -3129,6 +3151,15 @@ static inline struct rtw89_sta *sta_to_rtwsta_safe(struct ieee80211_sta *sta) } static inline +struct rtw89_addr_cam_entry *rtw89_get_addr_cam_of(struct rtw89_vif *rtwvif, + struct rtw89_sta *rtwsta) +{ + if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE && rtwsta) + return &rtwsta->addr_cam; + return &rtwvif->addr_cam; +} + +static inline void rtw89_chip_set_channel_prepare(struct rtw89_dev *rtwdev, struct rtw89_channel_help_params *p) { @@ -3371,6 +3402,8 @@ void rtw89_set_channel(struct rtw89_dev *rtwdev); u8 rtw89_core_acquire_bit_map(unsigned long *addr, unsigned long size); void rtw89_core_release_bit_map(unsigned long *addr, u8 bit); void rtw89_core_release_all_bits_map(unsigned long *addr, unsigned int nbits); +int rtw89_core_acquire_sta_ba_entry(struct rtw89_sta *rtwsta, u8 tid, u8 *cam_idx); +int rtw89_core_release_sta_ba_entry(struct rtw89_sta *rtwsta, u8 tid, u8 *cam_idx); void rtw89_vif_type_mapping(struct ieee80211_vif *vif, bool assoc); int rtw89_chip_info_setup(struct rtw89_dev *rtwdev); u16 rtw89_ra_report_to_bitrate(struct rtw89_dev *rtwdev, u8 rpt_rate); @@ -3381,5 +3414,6 @@ void rtw89_traffic_stats_init(struct rtw89_dev *rtwdev, struct rtw89_traffic_stats *stats); int rtw89_core_start(struct rtw89_dev *rtwdev); void rtw89_core_stop(struct rtw89_dev *rtwdev); +void rtw89_core_update_beacon_work(struct work_struct *work); #endif diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index 22bd1d03e722..b73cc03cecfd 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -2324,16 +2324,17 @@ rtw89_debug_append_rx_rate(struct seq_file *m, struct rtw89_pkt_stat *pkt_stat, static const struct rtw89_rx_rate_cnt_info { enum rtw89_hw_rate first_rate; int len; + int ext; const char *rate_mode; } rtw89_rx_rate_cnt_infos[] = { - {RTW89_HW_RATE_CCK1, 4, "Legacy:"}, - {RTW89_HW_RATE_OFDM6, 8, "OFDM:"}, - {RTW89_HW_RATE_MCS0, 8, "HT 0:"}, - {RTW89_HW_RATE_MCS8, 8, "HT 1:"}, - {RTW89_HW_RATE_VHT_NSS1_MCS0, 10, "VHT 1SS:"}, - {RTW89_HW_RATE_VHT_NSS2_MCS0, 10, "VHT 2SS:"}, - {RTW89_HW_RATE_HE_NSS1_MCS0, 12, "HE 1SS:"}, - {RTW89_HW_RATE_HE_NSS2_MCS0, 12, "HE 2ss:"}, + {RTW89_HW_RATE_CCK1, 4, 0, "Legacy:"}, + {RTW89_HW_RATE_OFDM6, 8, 0, "OFDM:"}, + {RTW89_HW_RATE_MCS0, 8, 0, "HT 0:"}, + {RTW89_HW_RATE_MCS8, 8, 0, "HT 1:"}, + {RTW89_HW_RATE_VHT_NSS1_MCS0, 10, 2, "VHT 1SS:"}, + {RTW89_HW_RATE_VHT_NSS2_MCS0, 10, 2, "VHT 2SS:"}, + {RTW89_HW_RATE_HE_NSS1_MCS0, 12, 0, "HE 1SS:"}, + {RTW89_HW_RATE_HE_NSS2_MCS0, 12, 0, "HE 2ss:"}, }; static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v) @@ -2358,6 +2359,11 @@ static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v) seq_printf(m, "%10s [", info->rate_mode); rtw89_debug_append_rx_rate(m, pkt_stat, info->first_rate, info->len); + if (info->ext) { + seq_puts(m, "]["); + rtw89_debug_append_rx_rate(m, pkt_stat, + info->first_rate + info->len, info->ext); + } seq_puts(m, "]\n"); } @@ -2366,6 +2372,72 @@ static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v) return 0; } +static void rtw89_dump_addr_cam(struct seq_file *m, + struct rtw89_addr_cam_entry *addr_cam) +{ + struct rtw89_sec_cam_entry *sec_entry; + int i; + + seq_printf(m, "\taddr_cam_idx=%u\n", addr_cam->addr_cam_idx); + seq_printf(m, "\t-> bssid_cam_idx=%u\n", addr_cam->bssid_cam_idx); + seq_printf(m, "\tsec_cam_bitmap=%*ph\n", (int)sizeof(addr_cam->sec_cam_map), + addr_cam->sec_cam_map); + for (i = 0; i < RTW89_SEC_CAM_IN_ADDR_CAM; i++) { + sec_entry = addr_cam->sec_entries[i]; + if (!sec_entry) + continue; + seq_printf(m, "\tsec[%d]: sec_cam_idx %u", i, sec_entry->sec_cam_idx); + if (sec_entry->ext_key) + seq_printf(m, ", %u", sec_entry->sec_cam_idx + 1); + seq_puts(m, "\n"); + } +} + +static +void rtw89_vif_ids_get_iter(void *data, u8 *mac, struct ieee80211_vif *vif) +{ + struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; + struct seq_file *m = (struct seq_file *)data; + struct rtw89_bssid_cam_entry *bssid_cam = &rtwvif->bssid_cam; + + seq_printf(m, "VIF [%d] %pM\n", rtwvif->mac_id, rtwvif->mac_addr); + seq_printf(m, "\tbssid_cam_idx=%u\n", bssid_cam->bssid_cam_idx); + rtw89_dump_addr_cam(m, &rtwvif->addr_cam); +} + +static void rtw89_sta_ids_get_iter(void *data, struct ieee80211_sta *sta) +{ + struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv; + struct seq_file *m = (struct seq_file *)data; + + seq_printf(m, "STA [%d] %pM\n", rtwsta->mac_id, sta->addr); + rtw89_dump_addr_cam(m, &rtwsta->addr_cam); +} + +static int rtw89_debug_priv_stations_get(struct seq_file *m, void *v) +{ + struct rtw89_debugfs_priv *debugfs_priv = m->private; + struct rtw89_dev *rtwdev = debugfs_priv->rtwdev; + struct rtw89_cam_info *cam_info = &rtwdev->cam_info; + + seq_puts(m, "map:\n"); + seq_printf(m, "\tmac_id: %*ph\n", (int)sizeof(rtwdev->mac_id_map), + rtwdev->mac_id_map); + seq_printf(m, "\taddr_cam: %*ph\n", (int)sizeof(cam_info->addr_cam_map), + cam_info->addr_cam_map); + seq_printf(m, "\tbssid_cam: %*ph\n", (int)sizeof(cam_info->bssid_cam_map), + cam_info->bssid_cam_map); + seq_printf(m, "\tsec_cam: %*ph\n", (int)sizeof(cam_info->sec_cam_map), + cam_info->sec_cam_map); + + ieee80211_iterate_active_interfaces_atomic(rtwdev->hw, + IEEE80211_IFACE_ITER_NORMAL, rtw89_vif_ids_get_iter, m); + + ieee80211_iterate_stations_atomic(rtwdev->hw, rtw89_sta_ids_get_iter, m); + + return 0; +} + static struct rtw89_debugfs_priv rtw89_debug_priv_read_reg = { .cb_read = rtw89_debug_priv_read_reg_get, .cb_write = rtw89_debug_priv_read_reg_select, @@ -2432,6 +2504,10 @@ static struct rtw89_debugfs_priv rtw89_debug_priv_phy_info = { .cb_read = rtw89_debug_priv_phy_info_get, }; +static struct rtw89_debugfs_priv rtw89_debug_priv_stations = { + .cb_read = rtw89_debug_priv_stations_get, +}; + #define rtw89_debugfs_add(name, mode, fopname, parent) \ do { \ rtw89_debug_priv_ ##name.rtwdev = rtwdev; \ @@ -2470,6 +2546,7 @@ void rtw89_debugfs_init(struct rtw89_dev *rtwdev) rtw89_debugfs_add_w(btc_manual); rtw89_debugfs_add_w(fw_log_manual); rtw89_debugfs_add_r(phy_info); + rtw89_debugfs_add_r(stations); } #endif diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 8a57b75b07c0..7fa60fd00143 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -555,11 +555,27 @@ fail: return -EBUSY; } -#define H2C_BA_CAM_LEN 4 -int rtw89_fw_h2c_ba_cam(struct rtw89_dev *rtwdev, bool valid, u8 macid, - struct ieee80211_ampdu_params *params) +#define H2C_BA_CAM_LEN 8 +int rtw89_fw_h2c_ba_cam(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta, + bool valid, struct ieee80211_ampdu_params *params) { + u8 macid = rtwsta->mac_id; struct sk_buff *skb; + u8 entry_idx; + int ret; + + ret = valid ? + rtw89_core_acquire_sta_ba_entry(rtwsta, params->tid, &entry_idx) : + rtw89_core_release_sta_ba_entry(rtwsta, params->tid, &entry_idx); + if (ret) { + /* it still works even if we don't have static BA CAM, because + * hardware can create dynamic BA CAM automatically. + */ + rtw89_debug(rtwdev, RTW89_DBG_TXRX, + "failed to %s entry tid=%d for h2c ba cam\n", + valid ? "alloc" : "free", params->tid); + return 0; + } skb = rtw89_fw_h2c_alloc_skb_with_hdr(H2C_BA_CAM_LEN); if (!skb) { @@ -568,6 +584,7 @@ int rtw89_fw_h2c_ba_cam(struct rtw89_dev *rtwdev, bool valid, u8 macid, } skb_put(skb, H2C_BA_CAM_LEN); SET_BA_CAM_MACID(skb->data, macid); + SET_BA_CAM_ENTRY_IDX(skb->data, entry_idx); if (!valid) goto end; SET_BA_CAM_VALID(skb->data, valid); @@ -577,7 +594,7 @@ int rtw89_fw_h2c_ba_cam(struct rtw89_dev *rtwdev, bool valid, u8 macid, else SET_BA_CAM_BMAP_SIZE(skb->data, 0); /* If init req is set, hw will set the ssn */ - SET_BA_CAM_INIT_REQ(skb->data, 0); + SET_BA_CAM_INIT_REQ(skb->data, 1); SET_BA_CAM_SSN(skb->data, params->ssn); end: @@ -716,12 +733,14 @@ fail: } #define H2C_CMC_TBL_LEN 68 -int rtw89_fw_h2c_default_cmac_tbl(struct rtw89_dev *rtwdev, u8 macid) +int rtw89_fw_h2c_default_cmac_tbl(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif) { struct rtw89_hal *hal = &rtwdev->hal; struct sk_buff *skb; u8 ntx_path = hal->antenna_tx ? hal->antenna_tx : RF_B; u8 map_b = hal->antenna_tx == RF_AB ? 1 : 0; + u8 macid = rtwvif->mac_id; skb = rtw89_fw_h2c_alloc_skb_with_hdr(H2C_CMC_TBL_LEN); if (!skb) { @@ -743,6 +762,8 @@ int rtw89_fw_h2c_default_cmac_tbl(struct rtw89_dev *rtwdev, u8 macid) SET_CMC_TBL_ANTSEL_D(skb->data, 0); SET_CMC_TBL_DOPPLER_CTRL(skb->data, 0); SET_CMC_TBL_TXPWR_TOLERENCE(skb->data, 0); + if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE) + SET_CMC_TBL_DATA_DCM(skb->data, 0); rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, H2C_CAT_MAC, H2C_CL_MAC_FR_EXCHG, @@ -821,13 +842,15 @@ int rtw89_fw_h2c_assoc_cmac_tbl(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta) { struct rtw89_hal *hal = &rtwdev->hal; - struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv; + struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta); struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; struct sk_buff *skb; u8 pads[RTW89_PPE_BW_NUM]; + u8 mac_id = rtwsta ? rtwsta->mac_id : rtwvif->mac_id; memset(pads, 0, sizeof(pads)); - __get_sta_he_pkt_padding(rtwdev, sta, pads); + if (sta) + __get_sta_he_pkt_padding(rtwdev, sta, pads); skb = rtw89_fw_h2c_alloc_skb_with_hdr(H2C_CMC_TBL_LEN); if (!skb) { @@ -835,7 +858,7 @@ int rtw89_fw_h2c_assoc_cmac_tbl(struct rtw89_dev *rtwdev, return -ENOMEM; } skb_put(skb, H2C_CMC_TBL_LEN); - SET_CTRL_INFO_MACID(skb->data, rtwsta->mac_id); + SET_CTRL_INFO_MACID(skb->data, mac_id); SET_CTRL_INFO_OPERATION(skb->data, 1); SET_CMC_TBL_DISRTSFB(skb->data, 1); SET_CMC_TBL_DISDATAFB(skb->data, 1); @@ -853,7 +876,10 @@ int rtw89_fw_h2c_assoc_cmac_tbl(struct rtw89_dev *rtwdev, SET_CMC_TBL_NOMINAL_PKT_PADDING(skb->data, pads[RTW89_CHANNEL_WIDTH_20]); SET_CMC_TBL_NOMINAL_PKT_PADDING40(skb->data, pads[RTW89_CHANNEL_WIDTH_40]); SET_CMC_TBL_NOMINAL_PKT_PADDING80(skb->data, pads[RTW89_CHANNEL_WIDTH_80]); - SET_CMC_TBL_BSR_QUEUE_SIZE_FORMAT(skb->data, sta->he_cap.has_he); + if (sta) + SET_CMC_TBL_BSR_QUEUE_SIZE_FORMAT(skb->data, sta->he_cap.has_he); + if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE) + SET_CMC_TBL_DATA_DCM(skb->data, 0); rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, H2C_CAT_MAC, H2C_CL_MAC_FR_EXCHG, @@ -911,28 +937,93 @@ fail: return -EBUSY; } -#define H2C_VIF_MAINTAIN_LEN 4 -int rtw89_fw_h2c_vif_maintain(struct rtw89_dev *rtwdev, - struct rtw89_vif *rtwvif, - enum rtw89_upd_mode upd_mode) +#define H2C_BCN_BASE_LEN 12 +int rtw89_fw_h2c_update_beacon(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif) +{ + struct rtw89_hal *hal = &rtwdev->hal; + struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif); + struct sk_buff *skb; + struct sk_buff *skb_beacon; + u16 tim_offset; + int bcn_total_len; + + skb_beacon = ieee80211_beacon_get_tim(rtwdev->hw, vif, &tim_offset, NULL); + if (!skb_beacon) { + rtw89_err(rtwdev, "failed to get beacon skb\n"); + return -ENOMEM; + } + + bcn_total_len = H2C_BCN_BASE_LEN + skb_beacon->len; + skb = rtw89_fw_h2c_alloc_skb_with_hdr(bcn_total_len); + if (!skb) { + rtw89_err(rtwdev, "failed to alloc skb for fw dl\n"); + dev_kfree_skb_any(skb_beacon); + return -ENOMEM; + } + skb_put(skb, H2C_BCN_BASE_LEN); + + SET_BCN_UPD_PORT(skb->data, rtwvif->port); + SET_BCN_UPD_MBSSID(skb->data, 0); + SET_BCN_UPD_BAND(skb->data, rtwvif->mac_idx); + SET_BCN_UPD_GRP_IE_OFST(skb->data, tim_offset); + SET_BCN_UPD_MACID(skb->data, rtwvif->mac_id); + SET_BCN_UPD_SSN_SEL(skb->data, RTW89_MGMT_HW_SSN_SEL); + SET_BCN_UPD_SSN_MODE(skb->data, RTW89_MGMT_HW_SEQ_MODE); + SET_BCN_UPD_RATE(skb->data, hal->current_band_type == RTW89_BAND_2G ? + RTW89_HW_RATE_CCK1 : RTW89_HW_RATE_OFDM6); + + skb_put_data(skb, skb_beacon->data, skb_beacon->len); + dev_kfree_skb_any(skb_beacon); + + rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, + H2C_CAT_MAC, H2C_CL_MAC_FR_EXCHG, + H2C_FUNC_MAC_BCN_UPD, 0, 1, + bcn_total_len); + + if (rtw89_h2c_tx(rtwdev, skb, false)) { + rtw89_err(rtwdev, "failed to send h2c\n"); + dev_kfree_skb_any(skb); + return -EBUSY; + } + + return 0; +} + +#define H2C_ROLE_MAINTAIN_LEN 4 +int rtw89_fw_h2c_role_maintain(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif, + struct rtw89_sta *rtwsta, + enum rtw89_upd_mode upd_mode) { struct sk_buff *skb; + u8 mac_id = rtwsta ? rtwsta->mac_id : rtwvif->mac_id; + u8 self_role; - skb = rtw89_fw_h2c_alloc_skb_with_hdr(H2C_VIF_MAINTAIN_LEN); + if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE) { + if (rtwsta) + self_role = RTW89_SELF_ROLE_AP_CLIENT; + else + self_role = rtwvif->self_role; + } else { + self_role = rtwvif->self_role; + } + + skb = rtw89_fw_h2c_alloc_skb_with_hdr(H2C_ROLE_MAINTAIN_LEN); if (!skb) { rtw89_err(rtwdev, "failed to alloc skb for h2c join\n"); return -ENOMEM; } - skb_put(skb, H2C_VIF_MAINTAIN_LEN); - SET_FWROLE_MAINTAIN_MACID(skb->data, rtwvif->mac_id); - SET_FWROLE_MAINTAIN_SELF_ROLE(skb->data, rtwvif->self_role); + skb_put(skb, H2C_ROLE_MAINTAIN_LEN); + SET_FWROLE_MAINTAIN_MACID(skb->data, mac_id); + SET_FWROLE_MAINTAIN_SELF_ROLE(skb->data, self_role); SET_FWROLE_MAINTAIN_UPD_MODE(skb->data, upd_mode); SET_FWROLE_MAINTAIN_WIFI_ROLE(skb->data, rtwvif->wifi_role); rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, H2C_CAT_MAC, H2C_CL_MAC_MEDIA_RPT, H2C_FUNC_MAC_FWROLE_MAINTAIN, 0, 1, - H2C_VIF_MAINTAIN_LEN); + H2C_ROLE_MAINTAIN_LEN); if (rtw89_h2c_tx(rtwdev, skb, false)) { rtw89_err(rtwdev, "failed to send h2c\n"); @@ -948,9 +1039,17 @@ fail: #define H2C_JOIN_INFO_LEN 4 int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, - u8 dis_conn) + struct rtw89_sta *rtwsta, bool dis_conn) { struct sk_buff *skb; + u8 mac_id = rtwsta ? rtwsta->mac_id : rtwvif->mac_id; + u8 self_role = rtwvif->self_role; + u8 net_type = rtwvif->net_type; + + if (net_type == RTW89_NET_TYPE_AP_MODE && rtwsta) { + self_role = RTW89_SELF_ROLE_AP_CLIENT; + net_type = dis_conn ? RTW89_NET_TYPE_NO_LINK : net_type; + } skb = rtw89_fw_h2c_alloc_skb_with_hdr(H2C_JOIN_INFO_LEN); if (!skb) { @@ -958,7 +1057,7 @@ int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, return -ENOMEM; } skb_put(skb, H2C_JOIN_INFO_LEN); - SET_JOININFO_MACID(skb->data, rtwvif->mac_id); + SET_JOININFO_MACID(skb->data, mac_id); SET_JOININFO_OP(skb->data, dis_conn); SET_JOININFO_BAND(skb->data, rtwvif->mac_idx); SET_JOININFO_WMM(skb->data, rtwvif->wmm); @@ -968,9 +1067,9 @@ int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, SET_JOININFO_TF_MAC_PAD(skb->data, 0); SET_JOININFO_DL_T_PE(skb->data, 0); SET_JOININFO_PORT_ID(skb->data, rtwvif->port); - SET_JOININFO_NET_TYPE(skb->data, rtwvif->net_type); + SET_JOININFO_NET_TYPE(skb->data, net_type); SET_JOININFO_WIFI_ROLE(skb->data, rtwvif->wifi_role); - SET_JOININFO_SELF_ROLE(skb->data, rtwvif->self_role); + SET_JOININFO_SELF_ROLE(skb->data, self_role); rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, H2C_CAT_MAC, H2C_CL_MAC_MEDIA_RPT, @@ -1212,7 +1311,7 @@ fail: return -EBUSY; } -#define H2C_LEN_CXDRVINFO_ROLE (4 + 12 * RTW89_MAX_HW_PORT_NUM + H2C_LEN_CXDRVHDR) +#define H2C_LEN_CXDRVINFO_ROLE (4 + 12 * RTW89_PORT_NUM + H2C_LEN_CXDRVHDR) int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev) { struct rtw89_btc *btc = &rtwdev->btc; @@ -1251,7 +1350,7 @@ int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev) RTW89_SET_FWCMD_CXROLE_ROLE_P2P_GO(cmd, bpos->p2p_go); RTW89_SET_FWCMD_CXROLE_ROLE_NAN(cmd, bpos->nan); - for (i = 0; i < RTW89_MAX_HW_PORT_NUM; i++, active++) { + for (i = 0; i < RTW89_PORT_NUM; i++, active++) { RTW89_SET_FWCMD_CXROLE_ACT_CONNECTED(cmd, active->connected, i); RTW89_SET_FWCMD_CXROLE_ACT_PID(cmd, active->pid, i); RTW89_SET_FWCMD_CXROLE_ACT_PHY(cmd, active->phy, i); diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h index 2d36dc27222f..83f4eaaf90f3 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.h +++ b/drivers/net/wireless/realtek/rtw89/fw.h @@ -1056,6 +1056,106 @@ static inline void SET_CMC_TBL_CSI_BW(void *table, u32 val) GENMASK(31, 30)); } +static inline void SET_BCN_UPD_PORT(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c, val, GENMASK(7, 0)); +} + +static inline void SET_BCN_UPD_MBSSID(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c, val, GENMASK(15, 8)); +} + +static inline void SET_BCN_UPD_BAND(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c, val, GENMASK(23, 16)); +} + +static inline void SET_BCN_UPD_GRP_IE_OFST(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c, (val - 24) | BIT(7), GENMASK(31, 24)); +} + +static inline void SET_BCN_UPD_MACID(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 1, val, GENMASK(7, 0)); +} + +static inline void SET_BCN_UPD_SSN_SEL(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 1, val, GENMASK(9, 8)); +} + +static inline void SET_BCN_UPD_SSN_MODE(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 1, val, GENMASK(11, 10)); +} + +static inline void SET_BCN_UPD_RATE(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 1, val, GENMASK(20, 12)); +} + +static inline void SET_BCN_UPD_TXPWR(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 1, val, GENMASK(23, 21)); +} + +static inline void SET_BCN_UPD_TXINFO_CTRL_EN(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, BIT(0)); +} + +static inline void SET_BCN_UPD_NTX_PATH_EN(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, GENMASK(4, 1)); +} + +static inline void SET_BCN_UPD_PATH_MAP_A(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, GENMASK(6, 5)); +} + +static inline void SET_BCN_UPD_PATH_MAP_B(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, GENMASK(8, 7)); +} + +static inline void SET_BCN_UPD_PATH_MAP_C(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, GENMASK(10, 9)); +} + +static inline void SET_BCN_UPD_PATH_MAP_D(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, GENMASK(12, 11)); +} + +static inline void SET_BCN_UPD_PATH_ANTSEL_A(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, BIT(13)); +} + +static inline void SET_BCN_UPD_PATH_ANTSEL_B(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, BIT(14)); +} + +static inline void SET_BCN_UPD_PATH_ANTSEL_C(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, BIT(15)); +} + +static inline void SET_BCN_UPD_PATH_ANTSEL_D(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, BIT(16)); +} + +static inline void SET_BCN_UPD_CSA_OFST(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)(h2c) + 2, val, GENMASK(31, 17)); +} + static inline void SET_FWROLE_MAINTAIN_MACID(void *h2c, u32 val) { le32p_replace_bits((__le32 *)h2c, val, GENMASK(7, 0)); @@ -1226,6 +1326,26 @@ static inline void SET_BA_CAM_SSN(void *h2c, u32 val) le32p_replace_bits((__le32 *)h2c, val, GENMASK(31, 20)); } +static inline void SET_BA_CAM_UID(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c + 1, val, GENMASK(7, 0)); +} + +static inline void SET_BA_CAM_STD_EN(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c + 1, val, BIT(8)); +} + +static inline void SET_BA_CAM_BAND(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c + 1, val, BIT(9)); +} + +static inline void SET_BA_CAM_ENTRY_IDX_V1(void *h2c, u32 val) +{ + le32p_replace_bits((__le32 *)h2c + 1, val, GENMASK(31, 28)); +} + static inline void SET_LPS_PARM_MACID(void *h2c, u32 val) { le32p_replace_bits((__le32 *)h2c, val, GENMASK(7, 0)); @@ -1709,6 +1829,7 @@ struct rtw89_fw_h2c_rf_reg_info { /* CLASS 5 - Frame Exchange */ #define H2C_CL_MAC_FR_EXCHG 0x5 #define H2C_FUNC_MAC_CCTLINFO_UD 0x2 +#define H2C_FUNC_MAC_BCN_UPD 0x5 /* CLASS 6 - Address CAM */ #define H2C_CL_MAC_ADDR_CAM_UPDATE 0x6 @@ -1750,21 +1871,25 @@ int rtw89_wait_firmware_completion(struct rtw89_dev *rtwdev); void rtw89_h2c_pkt_set_hdr(struct rtw89_dev *rtwdev, struct sk_buff *skb, u8 type, u8 cat, u8 class, u8 func, bool rack, bool dack, u32 len); -int rtw89_fw_h2c_default_cmac_tbl(struct rtw89_dev *rtwdev, u8 macid); +int rtw89_fw_h2c_default_cmac_tbl(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif); int rtw89_fw_h2c_assoc_cmac_tbl(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); int rtw89_fw_h2c_txtime_cmac_tbl(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta); +int rtw89_fw_h2c_update_beacon(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif); int rtw89_fw_h2c_cam(struct rtw89_dev *rtwdev, struct rtw89_vif *vif, struct rtw89_sta *rtwsta, const u8 *scan_mac_addr); void rtw89_fw_c2h_irqsafe(struct rtw89_dev *rtwdev, struct sk_buff *c2h); void rtw89_fw_c2h_work(struct work_struct *work); -int rtw89_fw_h2c_vif_maintain(struct rtw89_dev *rtwdev, - struct rtw89_vif *rtwvif, - enum rtw89_upd_mode upd_mode); +int rtw89_fw_h2c_role_maintain(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif, + struct rtw89_sta *rtwsta, + enum rtw89_upd_mode upd_mode); int rtw89_fw_h2c_join_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, - u8 dis_conn); + struct rtw89_sta *rtwsta, bool dis_conn); int rtw89_fw_h2c_macid_pause(struct rtw89_dev *rtwdev, u8 sh, u8 grp, bool pause); int rtw89_fw_h2c_set_edca(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, @@ -1785,8 +1910,9 @@ int rtw89_fw_h2c_raw(struct rtw89_dev *rtwdev, const u8 *buf, u16 len); void rtw89_fw_send_all_early_h2c(struct rtw89_dev *rtwdev); void rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev); int rtw89_fw_h2c_general_pkt(struct rtw89_dev *rtwdev, u8 macid); -int rtw89_fw_h2c_ba_cam(struct rtw89_dev *rtwdev, bool valid, u8 macid, - struct ieee80211_ampdu_params *params); +int rtw89_fw_h2c_ba_cam(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta, + bool valid, struct ieee80211_ampdu_params *params); + int rtw89_fw_h2c_lps_parm(struct rtw89_dev *rtwdev, struct rtw89_lps_parm *lps_param); struct sk_buff *rtw89_fw_h2c_alloc_skb_with_hdr(u32 len); diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index b98c47e9ecfe..031e6e99d4be 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -172,6 +172,7 @@ static void rtw89_mac_dump_qta_lost(struct rtw89_dev *rtwdev) qempty.dle_type = DLE_CTRL_TYPE_PLE; qempty.grpsel = 0; + qempty.qempty = ~(u32)0; ret = dle_dfi_qempty(rtwdev, &qempty); if (ret) rtw89_warn(rtwdev, "%s: query DLE fail\n", __func__); @@ -481,9 +482,10 @@ int rtw89_mac_set_err_status(struct rtw89_dev *rtwdev, u32 err) } EXPORT_SYMBOL(rtw89_mac_set_err_status); -const struct rtw89_hfc_prec_cfg rtw_hfc_preccfg_pcie = { +const struct rtw89_hfc_prec_cfg rtw89_hfc_preccfg_pcie = { 2, 40, 0, 0, 1, 0, 0, 0 }; +EXPORT_SYMBOL(rtw89_hfc_preccfg_pcie); static int hfc_reset_param(struct rtw89_dev *rtwdev) { @@ -1136,49 +1138,58 @@ static int rtw89_mac_sys_init(struct rtw89_dev *rtwdev) } /* PCIE 64 */ -const struct rtw89_dle_size wde_size0 = { +const struct rtw89_dle_size rtw89_wde_size0 = { RTW89_WDE_PG_64, 4095, 1, }; +EXPORT_SYMBOL(rtw89_wde_size0); /* DLFW */ -const struct rtw89_dle_size wde_size4 = { +const struct rtw89_dle_size rtw89_wde_size4 = { RTW89_WDE_PG_64, 0, 4096, }; +EXPORT_SYMBOL(rtw89_wde_size4); /* PCIE */ -const struct rtw89_dle_size ple_size0 = { +const struct rtw89_dle_size rtw89_ple_size0 = { RTW89_PLE_PG_128, 1520, 16, }; +EXPORT_SYMBOL(rtw89_ple_size0); /* DLFW */ -const struct rtw89_dle_size ple_size4 = { +const struct rtw89_dle_size rtw89_ple_size4 = { RTW89_PLE_PG_128, 64, 1472, }; +EXPORT_SYMBOL(rtw89_ple_size4); /* PCIE 64 */ -const struct rtw89_wde_quota wde_qt0 = { +const struct rtw89_wde_quota rtw89_wde_qt0 = { 3792, 196, 0, 107, }; +EXPORT_SYMBOL(rtw89_wde_qt0); /* DLFW */ -const struct rtw89_wde_quota wde_qt4 = { +const struct rtw89_wde_quota rtw89_wde_qt4 = { 0, 0, 0, 0, }; +EXPORT_SYMBOL(rtw89_wde_qt4); /* PCIE SCC */ -const struct rtw89_ple_quota ple_qt4 = { +const struct rtw89_ple_quota rtw89_ple_qt4 = { 264, 0, 16, 20, 26, 13, 356, 0, 32, 40, 8, }; +EXPORT_SYMBOL(rtw89_ple_qt4); /* PCIE SCC */ -const struct rtw89_ple_quota ple_qt5 = { +const struct rtw89_ple_quota rtw89_ple_qt5 = { 264, 0, 32, 20, 64, 13, 1101, 0, 64, 128, 120, }; +EXPORT_SYMBOL(rtw89_ple_qt5); /* DLFW */ -const struct rtw89_ple_quota ple_qt13 = { +const struct rtw89_ple_quota rtw89_ple_qt13 = { 0, 0, 16, 48, 0, 0, 0, 0, 0, 0, 0 }; +EXPORT_SYMBOL(rtw89_ple_qt13); static const struct rtw89_dle_mem *get_dle_mem_cfg(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode) @@ -2116,6 +2127,7 @@ int rtw89_mac_stop_sch_tx(struct rtw89_dev *rtwdev, u8 mac_idx, return 0; } +EXPORT_SYMBOL(rtw89_mac_stop_sch_tx); int rtw89_mac_resume_sch_tx(struct rtw89_dev *rtwdev, u8 mac_idx, u16 tx_en) { @@ -2127,6 +2139,7 @@ int rtw89_mac_resume_sch_tx(struct rtw89_dev *rtwdev, u8 mac_idx, u16 tx_en) return 0; } +EXPORT_SYMBOL(rtw89_mac_resume_sch_tx); static u16 rtw89_mac_dle_buf_req(struct rtw89_dev *rtwdev, u16 buf_len, bool wd) @@ -2705,7 +2718,7 @@ static void rtw89_mac_cmac_tbl_init(struct rtw89_dev *rtwdev, u8 macid) rtw89_write32(rtwdev, R_AX_INDIR_ACCESS_ENTRY + 28, 0xB8109); } -static int rtw89_set_macid_pause(struct rtw89_dev *rtwdev, u8 macid, bool pause) +int rtw89_mac_set_macid_pause(struct rtw89_dev *rtwdev, u8 macid, bool pause) { u8 sh = FIELD_GET(GENMASK(4, 0), macid); u8 grp = macid >> 5; @@ -2864,6 +2877,36 @@ static void rtw89_mac_port_cfg_bcn_intv(struct rtw89_dev *rtwdev, bcn_int); } +static void rtw89_mac_port_cfg_hiq_win(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif) +{ + static const u32 hiq_win_addr[RTW89_PORT_NUM] = { + R_AX_P0MB_HGQ_WINDOW_CFG_0, R_AX_PORT_HGQ_WINDOW_CFG, + R_AX_PORT_HGQ_WINDOW_CFG + 1, R_AX_PORT_HGQ_WINDOW_CFG + 2, + R_AX_PORT_HGQ_WINDOW_CFG + 3, + }; + u8 win = rtwvif->net_type == RTW89_NET_TYPE_AP_MODE ? 16 : 0; + u8 port = rtwvif->port; + u32 reg; + + reg = rtw89_mac_reg_by_idx(hiq_win_addr[port], rtwvif->mac_idx); + rtw89_write8(rtwdev, reg, win); +} + +static void rtw89_mac_port_cfg_hiq_dtim(struct rtw89_dev *rtwdev, + struct rtw89_vif *rtwvif) +{ + struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif); + const struct rtw89_port_reg *p = &rtw_port_base; + u32 addr; + + addr = rtw89_mac_reg_by_idx(R_AX_MD_TSFT_STMP_CTL, rtwvif->mac_idx); + rtw89_write8_set(rtwdev, addr, B_AX_UPD_HGQMD | B_AX_UPD_TIMIE); + + rtw89_write16_port_mask(rtwdev, rtwvif, p->dtim_ctrl, B_AX_DTIM_NUM_MASK, + vif->bss_conf.dtim_period); +} + static void rtw89_mac_port_cfg_bcn_setup_time(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) { @@ -2978,11 +3021,11 @@ int rtw89_mac_vif_init(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) rtw89_mac_dmac_tbl_init(rtwdev, rtwvif->mac_id); rtw89_mac_cmac_tbl_init(rtwdev, rtwvif->mac_id); - ret = rtw89_set_macid_pause(rtwdev, rtwvif->mac_id, false); + ret = rtw89_mac_set_macid_pause(rtwdev, rtwvif->mac_id, false); if (ret) return ret; - ret = rtw89_fw_h2c_vif_maintain(rtwdev, rtwvif, RTW89_VIF_CREATE); + ret = rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, NULL, RTW89_ROLE_CREATE); if (ret) return ret; @@ -2994,7 +3037,7 @@ int rtw89_mac_vif_init(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) if (ret) return ret; - ret = rtw89_fw_h2c_default_cmac_tbl(rtwdev, rtwvif->mac_id); + ret = rtw89_fw_h2c_default_cmac_tbl(rtwdev, rtwvif); if (ret) return ret; @@ -3005,7 +3048,7 @@ int rtw89_mac_vif_deinit(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) { int ret; - ret = rtw89_fw_h2c_vif_maintain(rtwdev, rtwvif, RTW89_VIF_REMOVE); + ret = rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, NULL, RTW89_ROLE_REMOVE); if (ret) return ret; @@ -3034,13 +3077,15 @@ int rtw89_mac_port_update(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif) rtw89_mac_port_cfg_rx_sync(rtwdev, rtwvif); rtw89_mac_port_cfg_tx_sw(rtwdev, rtwvif); rtw89_mac_port_cfg_bcn_intv(rtwdev, rtwvif); + rtw89_mac_port_cfg_hiq_win(rtwdev, rtwvif); + rtw89_mac_port_cfg_hiq_dtim(rtwdev, rtwvif); + rtw89_mac_port_cfg_hiq_drop(rtwdev, rtwvif); rtw89_mac_port_cfg_bcn_setup_time(rtwdev, rtwvif); rtw89_mac_port_cfg_bcn_hold_time(rtwdev, rtwvif); rtw89_mac_port_cfg_bcn_mask_area(rtwdev, rtwvif); rtw89_mac_port_cfg_tbtt_early(rtwdev, rtwvif); rtw89_mac_port_cfg_bss_color(rtwdev, rtwvif); rtw89_mac_port_cfg_mbssid(rtwdev, rtwvif); - rtw89_mac_port_cfg_hiq_drop(rtwdev, rtwvif); rtw89_mac_port_cfg_func_en(rtwdev, rtwvif); fsleep(BCN_ERLY_SET_DLY); rtw89_mac_port_cfg_bcn_early(rtwdev, rtwvif); @@ -3114,6 +3159,11 @@ rtw89_mac_c2h_log(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len) RTW89_GET_C2H_LOG_SRT_PRT(c2h->data)); } +static void +rtw89_mac_c2h_bcn_cnt(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len) +{ +} + static void (* const rtw89_mac_c2h_ofld_handler[])(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len) = { @@ -3130,6 +3180,7 @@ void (* const rtw89_mac_c2h_info_handler[])(struct rtw89_dev *rtwdev, [RTW89_MAC_C2H_FUNC_REC_ACK] = rtw89_mac_c2h_rec_ack, [RTW89_MAC_C2H_FUNC_DONE_ACK] = rtw89_mac_c2h_done_ack, [RTW89_MAC_C2H_FUNC_C2H_LOG] = rtw89_mac_c2h_log, + [RTW89_MAC_C2H_FUNC_BCN_CNT] = rtw89_mac_c2h_bcn_cnt, }; void rtw89_mac_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb, @@ -3192,6 +3243,7 @@ error: return false; } +EXPORT_SYMBOL(rtw89_mac_get_txpwr_cr); int rtw89_mac_cfg_ppdu_status(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable) { @@ -3216,6 +3268,7 @@ int rtw89_mac_cfg_ppdu_status(struct rtw89_dev *rtwdev, u8 mac_idx, bool enable) return ret; } +EXPORT_SYMBOL(rtw89_mac_cfg_ppdu_status); void rtw89_mac_update_rts_threshold(struct rtw89_dev *rtwdev, u8 mac_idx) { @@ -3349,6 +3402,7 @@ int rtw89_mac_coex_init(struct rtw89_dev *rtwdev, const struct rtw89_mac_ax_coex return 0; } +EXPORT_SYMBOL(rtw89_mac_coex_init); int rtw89_mac_cfg_gnt(struct rtw89_dev *rtwdev, const struct rtw89_mac_ax_coex_gnt *gnt_cfg) @@ -3388,7 +3442,7 @@ int rtw89_mac_cfg_gnt(struct rtw89_dev *rtwdev, int rtw89_mac_cfg_plt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt) { u32 reg; - u8 val; + u16 val; int ret; ret = rtw89_mac_check_mac_en(rtwdev, plt->band, RTW89_CMAC_SEL); @@ -3403,8 +3457,9 @@ int rtw89_mac_cfg_plt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt) (plt->rx & RTW89_MAC_AX_PLT_LTE_RX ? B_AX_RX_PLT_GNT_LTE_RX : 0) | (plt->rx & RTW89_MAC_AX_PLT_GNT_BT_TX ? B_AX_RX_PLT_GNT_BT_TX : 0) | (plt->rx & RTW89_MAC_AX_PLT_GNT_BT_RX ? B_AX_RX_PLT_GNT_BT_RX : 0) | - (plt->rx & RTW89_MAC_AX_PLT_GNT_WL ? B_AX_RX_PLT_GNT_WL : 0); - rtw89_write8(rtwdev, reg, val); + (plt->rx & RTW89_MAC_AX_PLT_GNT_WL ? B_AX_RX_PLT_GNT_WL : 0) | + B_AX_PLT_EN; + rtw89_write16(rtwdev, reg, val); return 0; } diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h index b7d13edf7dd1..e5db0a2eb9c2 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.h +++ b/drivers/net/wireless/realtek/rtw89/mac.h @@ -308,6 +308,7 @@ enum rtw89_mac_c2h_info_func { RTW89_MAC_C2H_FUNC_REC_ACK, RTW89_MAC_C2H_FUNC_DONE_ACK, RTW89_MAC_C2H_FUNC_C2H_LOG, + RTW89_MAC_C2H_FUNC_BCN_CNT, RTW89_MAC_C2H_FUNC_INFO_MAX, }; @@ -670,16 +671,16 @@ enum mac_ax_err_info { MAC_AX_SET_ERR_MAX, }; -extern const struct rtw89_hfc_prec_cfg rtw_hfc_preccfg_pcie; -extern const struct rtw89_dle_size wde_size0; -extern const struct rtw89_dle_size wde_size4; -extern const struct rtw89_dle_size ple_size0; -extern const struct rtw89_dle_size ple_size4; -extern const struct rtw89_wde_quota wde_qt0; -extern const struct rtw89_wde_quota wde_qt4; -extern const struct rtw89_ple_quota ple_qt4; -extern const struct rtw89_ple_quota ple_qt5; -extern const struct rtw89_ple_quota ple_qt13; +extern const struct rtw89_hfc_prec_cfg rtw89_hfc_preccfg_pcie; +extern const struct rtw89_dle_size rtw89_wde_size0; +extern const struct rtw89_dle_size rtw89_wde_size4; +extern const struct rtw89_dle_size rtw89_ple_size0; +extern const struct rtw89_dle_size rtw89_ple_size4; +extern const struct rtw89_wde_quota rtw89_wde_qt0; +extern const struct rtw89_wde_quota rtw89_wde_qt4; +extern const struct rtw89_ple_quota rtw89_ple_qt4; +extern const struct rtw89_ple_quota rtw89_ple_qt5; +extern const struct rtw89_ple_quota rtw89_ple_qt13; static inline u32 rtw89_mac_reg_by_idx(u32 reg_base, u8 band) { @@ -810,6 +811,7 @@ int rtw89_mac_vif_init(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif); int rtw89_mac_vif_deinit(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif); int rtw89_mac_set_hw_muedca_ctrl(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, bool en); +int rtw89_mac_set_macid_pause(struct rtw89_dev *rtwdev, u8 macid, bool pause); static inline void rtw89_mac_bf_monitor_track(struct rtw89_dev *rtwdev) { diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c index a322259f4cc4..5df7aceabdf5 100644 --- a/drivers/net/wireless/realtek/rtw89/mac80211.c +++ b/drivers/net/wireless/realtek/rtw89/mac80211.c @@ -102,14 +102,16 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw, int ret = 0; mutex_lock(&rtwdev->mutex); + rtwvif->rtwdev = rtwdev; list_add_tail(&rtwvif->list, &rtwdev->rtwvifs_list); + INIT_WORK(&rtwvif->update_beacon_work, rtw89_core_update_beacon_work); rtw89_leave_ps_mode(rtwdev); rtw89_traffic_stats_init(rtwdev, &rtwvif->stats); rtw89_vif_type_mapping(vif, false); rtwvif->port = rtw89_core_acquire_bit_map(rtwdev->hw_port, - RTW89_MAX_HW_PORT_NUM); - if (rtwvif->port == RTW89_MAX_HW_PORT_NUM) { + RTW89_PORT_NUM); + if (rtwvif->port == RTW89_PORT_NUM) { ret = -ENOSPC; goto out; } @@ -141,6 +143,8 @@ static void rtw89_ops_remove_interface(struct ieee80211_hw *hw, struct rtw89_dev *rtwdev = hw->priv; struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; + cancel_work_sync(&rtwvif->update_beacon_work); + mutex_lock(&rtwdev->mutex); rtw89_leave_ps_mode(rtwdev); rtw89_btc_ntfy_role_info(rtwdev, rtwvif, NULL, BTC_ROLE_STOP); @@ -161,7 +165,7 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw, rtw89_leave_ps_mode(rtwdev); *new_flags &= FIF_ALLMULTI | FIF_OTHER_BSS | FIF_FCSFAIL | - FIF_BCN_PRBRESP_PROMISC; + FIF_BCN_PRBRESP_PROMISC | FIF_PROBE_REQ; if (changed_flags & FIF_ALLMULTI) { if (*new_flags & FIF_ALLMULTI) @@ -192,6 +196,15 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw, rtwdev->hal.rx_fltr |= B_AX_A_A1_MATCH; } } + if (changed_flags & FIF_PROBE_REQ) { + if (*new_flags & FIF_PROBE_REQ) { + rtwdev->hal.rx_fltr &= ~B_AX_A_BC_CAM_MATCH; + rtwdev->hal.rx_fltr &= ~B_AX_A_UC_CAM_MATCH; + } else { + rtwdev->hal.rx_fltr |= B_AX_A_BC_CAM_MATCH; + rtwdev->hal.rx_fltr |= B_AX_A_UC_CAM_MATCH; + } + } rtw89_write32_mask(rtwdev, rtw89_mac_reg_by_idx(R_AX_RX_FLTR_OPT, RTW89_MAC_0), @@ -311,6 +324,9 @@ static void rtw89_station_mode_sta_assoc(struct rtw89_dev *rtwdev, rtw89_err(rtwdev, "can't find sta to set sta_assoc state\n"); return; } + + rtw89_vif_type_mapping(vif, true); + rtw89_core_sta_assoc(rtwdev, vif, sta); } @@ -340,6 +356,9 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw, rtw89_fw_h2c_cam(rtwdev, rtwvif, NULL, NULL); } + if (changed & BSS_CHANGED_BEACON) + rtw89_fw_h2c_update_beacon(rtwdev, rtwvif); + if (changed & BSS_CHANGED_ERP_SLOT) rtw89_conf_tx(rtwdev, rtwvif); @@ -352,6 +371,49 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw, mutex_unlock(&rtwdev->mutex); } +static int rtw89_ops_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif) +{ + struct rtw89_dev *rtwdev = hw->priv; + struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; + + mutex_lock(&rtwdev->mutex); + ether_addr_copy(rtwvif->bssid, vif->bss_conf.bssid); + rtw89_cam_bssid_changed(rtwdev, rtwvif); + rtw89_mac_port_update(rtwdev, rtwvif); + rtw89_fw_h2c_assoc_cmac_tbl(rtwdev, vif, NULL); + rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, NULL, RTW89_ROLE_TYPE_CHANGE); + rtw89_fw_h2c_join_info(rtwdev, rtwvif, NULL, true); + rtw89_fw_h2c_cam(rtwdev, rtwvif, NULL, NULL); + rtw89_chip_rfk_channel(rtwdev); + mutex_unlock(&rtwdev->mutex); + + return 0; +} + +static +void rtw89_ops_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif) +{ + struct rtw89_dev *rtwdev = hw->priv; + struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; + + mutex_lock(&rtwdev->mutex); + rtw89_fw_h2c_assoc_cmac_tbl(rtwdev, vif, NULL); + rtw89_fw_h2c_join_info(rtwdev, rtwvif, NULL, true); + mutex_unlock(&rtwdev->mutex); +} + +static int rtw89_ops_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta, + bool set) +{ + struct rtw89_dev *rtwdev = hw->priv; + struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv; + struct rtw89_vif *rtwvif = rtwsta->rtwvif; + + ieee80211_queue_work(rtwdev->hw, &rtwvif->update_beacon_work); + + return 0; +} + static int rtw89_ops_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 ac, const struct ieee80211_tx_queue_params *params) @@ -476,7 +538,6 @@ static int rtw89_ops_ampdu_action(struct ieee80211_hw *hw, case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT: mutex_lock(&rtwdev->mutex); clear_bit(RTW89_TXQ_F_AMPDU, &rtwtxq->flags); - rtw89_fw_h2c_ba_cam(rtwdev, false, rtwsta->mac_id, params); mutex_unlock(&rtwdev->mutex); ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; @@ -486,11 +547,17 @@ static int rtw89_ops_ampdu_action(struct ieee80211_hw *hw, rtwsta->ampdu_params[tid].agg_num = params->buf_size; rtwsta->ampdu_params[tid].amsdu = params->amsdu; rtw89_leave_ps_mode(rtwdev); - rtw89_fw_h2c_ba_cam(rtwdev, true, rtwsta->mac_id, params); mutex_unlock(&rtwdev->mutex); break; case IEEE80211_AMPDU_RX_START: + mutex_lock(&rtwdev->mutex); + rtw89_fw_h2c_ba_cam(rtwdev, rtwsta, true, params); + mutex_unlock(&rtwdev->mutex); + break; case IEEE80211_AMPDU_RX_STOP: + mutex_lock(&rtwdev->mutex); + rtw89_fw_h2c_ba_cam(rtwdev, rtwsta, false, params); + mutex_unlock(&rtwdev->mutex); break; default: WARN_ON(1); @@ -663,6 +730,9 @@ const struct ieee80211_ops rtw89_ops = { .remove_interface = rtw89_ops_remove_interface, .configure_filter = rtw89_ops_configure_filter, .bss_info_changed = rtw89_ops_bss_info_changed, + .start_ap = rtw89_ops_start_ap, + .stop_ap = rtw89_ops_stop_ap, + .set_tim = rtw89_ops_set_tim, .conf_tx = rtw89_ops_conf_tx, .sta_state = rtw89_ops_sta_state, .set_key = rtw89_ops_set_key, diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c index 2c94762e4f93..6481085b958e 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.c +++ b/drivers/net/wireless/realtek/rtw89/pci.c @@ -1413,79 +1413,52 @@ static int rtw89_write16_mdio_clr(struct rtw89_dev *rtwdev, u8 addr, u16 mask, u return 0; } -static int rtw89_dbi_write8(struct rtw89_dev *rtwdev, u16 addr, u8 data) +static int rtw89_pci_write_config_byte(struct rtw89_dev *rtwdev, u16 addr, + u8 data) { - u16 write_addr; - u16 remainder = addr & ~(B_AX_DBI_ADDR_MSK | B_AX_DBI_WREN_MSK); - u8 flag; - int ret; - - write_addr = addr & B_AX_DBI_ADDR_MSK; - write_addr |= u16_encode_bits(BIT(remainder), B_AX_DBI_WREN_MSK); - rtw89_write8(rtwdev, R_AX_DBI_WDATA + remainder, data); - rtw89_write16(rtwdev, R_AX_DBI_FLAG, write_addr); - rtw89_write8(rtwdev, R_AX_DBI_FLAG + 2, B_AX_DBI_WFLAG >> 16); - - ret = read_poll_timeout_atomic(rtw89_read8, flag, !flag, 10, - 10 * RTW89_PCI_WR_RETRY_CNT, false, - rtwdev, R_AX_DBI_FLAG + 2); - if (ret) - WARN(flag, "failed to write to DBI register, addr=0x%04x\n", - addr); + struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; + struct pci_dev *pdev = rtwpci->pdev; - return ret; + return pci_write_config_byte(pdev, addr, data); } -static int rtw89_dbi_read8(struct rtw89_dev *rtwdev, u16 addr, u8 *value) +static int rtw89_pci_read_config_byte(struct rtw89_dev *rtwdev, u16 addr, + u8 *value) { - u16 read_addr = addr & B_AX_DBI_ADDR_MSK; - u8 flag; - int ret; - - rtw89_write16(rtwdev, R_AX_DBI_FLAG, read_addr); - rtw89_write8(rtwdev, R_AX_DBI_FLAG + 2, B_AX_DBI_RFLAG >> 16); - - ret = read_poll_timeout_atomic(rtw89_read8, flag, !flag, 10, - 10 * RTW89_PCI_WR_RETRY_CNT, false, - rtwdev, R_AX_DBI_FLAG + 2); - - if (!ret) { - read_addr = R_AX_DBI_RDATA + (addr & 3); - *value = rtw89_read8(rtwdev, read_addr); - } else { - WARN(1, "failed to read DBI register, addr=0x%04x\n", addr); - ret = -EIO; - } + struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; + struct pci_dev *pdev = rtwpci->pdev; - return ret; + return pci_read_config_byte(pdev, addr, value); } -static int rtw89_dbi_write8_set(struct rtw89_dev *rtwdev, u16 addr, u8 bit) +static int rtw89_pci_config_byte_set(struct rtw89_dev *rtwdev, u16 addr, + u8 bit) { u8 value; int ret; - ret = rtw89_dbi_read8(rtwdev, addr, &value); + ret = rtw89_pci_read_config_byte(rtwdev, addr, &value); if (ret) return ret; value |= bit; - ret = rtw89_dbi_write8(rtwdev, addr, value); + ret = rtw89_pci_write_config_byte(rtwdev, addr, value); return ret; } -static int rtw89_dbi_write8_clr(struct rtw89_dev *rtwdev, u16 addr, u8 bit) +static int rtw89_pci_config_byte_clr(struct rtw89_dev *rtwdev, u16 addr, + u8 bit) { u8 value; int ret; - ret = rtw89_dbi_read8(rtwdev, addr, &value); + ret = rtw89_pci_read_config_byte(rtwdev, addr, &value); if (ret) return ret; value &= ~bit; - ret = rtw89_dbi_write8(rtwdev, addr, value); + ret = rtw89_pci_write_config_byte(rtwdev, addr, value); return ret; } @@ -1542,9 +1515,10 @@ static int rtw89_pci_auto_refclk_cal(struct rtw89_dev *rtwdev, bool autook_en) rtwdev->chip->chip_id == RTL8852C) return 0; - ret = rtw89_dbi_read8(rtwdev, RTW89_PCIE_PHY_RATE, &val8); + ret = rtw89_pci_read_config_byte(rtwdev, RTW89_PCIE_PHY_RATE, &val8); if (ret) { - rtw89_err(rtwdev, "[ERR]dbi_r8_pcie %X\n", RTW89_PCIE_PHY_RATE); + rtw89_err(rtwdev, "[ERR]pci config read %X\n", + RTW89_PCIE_PHY_RATE); return ret; } @@ -1557,17 +1531,18 @@ static int rtw89_pci_auto_refclk_cal(struct rtw89_dev *rtwdev, bool autook_en) return -EOPNOTSUPP; } /* Disable L1BD */ - ret = rtw89_dbi_read8(rtwdev, RTW89_PCIE_L1_CTRL, &bdr_ori); + ret = rtw89_pci_read_config_byte(rtwdev, RTW89_PCIE_L1_CTRL, &bdr_ori); if (ret) { - rtw89_err(rtwdev, "[ERR]dbi_r8_pcie %X\n", RTW89_PCIE_L1_CTRL); + rtw89_err(rtwdev, "[ERR]pci config read %X\n", RTW89_PCIE_L1_CTRL); return ret; } if (bdr_ori & RTW89_PCIE_BIT_L1) { - ret = rtw89_dbi_write8(rtwdev, RTW89_PCIE_L1_CTRL, - bdr_ori & ~RTW89_PCIE_BIT_L1); + ret = rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_L1_CTRL, + bdr_ori & ~RTW89_PCIE_BIT_L1); if (ret) { - rtw89_err(rtwdev, "[ERR]dbi_w8_pcie %X\n", RTW89_PCIE_L1_CTRL); + rtw89_err(rtwdev, "[ERR]pci config write %X\n", + RTW89_PCIE_L1_CTRL); return ret; } l1_flag = true; @@ -1662,14 +1637,17 @@ static int rtw89_pci_auto_refclk_cal(struct rtw89_dev *rtwdev, bool autook_en) } /* CLK delay = 0 */ - ret = rtw89_dbi_write8(rtwdev, RTW89_PCIE_CLK_CTRL, PCIE_CLKDLY_HW_0); + ret = rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_CLK_CTRL, + PCIE_CLKDLY_HW_0); end: /* Set L1BD to ori */ if (l1_flag) { - ret = rtw89_dbi_write8(rtwdev, RTW89_PCIE_L1_CTRL, bdr_ori); + ret = rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_L1_CTRL, + bdr_ori); if (ret) { - rtw89_err(rtwdev, "[ERR]dbi_w8_pcie %X\n", RTW89_PCIE_L1_CTRL); + rtw89_err(rtwdev, "[ERR]pci config write %X\n", + RTW89_PCIE_L1_CTRL); return ret; } } @@ -2552,17 +2530,17 @@ static void rtw89_pci_clkreq_set(struct rtw89_dev *rtwdev, bool enable) if (rtw89_pci_disable_clkreq) return; - ret = rtw89_dbi_write8(rtwdev, RTW89_PCIE_CLK_CTRL, - PCIE_CLKDLY_HW_30US); + ret = rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_CLK_CTRL, + PCIE_CLKDLY_HW_30US); if (ret) rtw89_err(rtwdev, "failed to set CLKREQ Delay\n"); if (enable) - ret = rtw89_dbi_write8_set(rtwdev, RTW89_PCIE_L1_CTRL, - RTW89_PCIE_BIT_CLK); + ret = rtw89_pci_config_byte_set(rtwdev, RTW89_PCIE_L1_CTRL, + RTW89_PCIE_BIT_CLK); else - ret = rtw89_dbi_write8_clr(rtwdev, RTW89_PCIE_L1_CTRL, - RTW89_PCIE_BIT_CLK); + ret = rtw89_pci_config_byte_clr(rtwdev, RTW89_PCIE_L1_CTRL, + RTW89_PCIE_BIT_CLK); if (ret) rtw89_err(rtwdev, "failed to %s CLKREQ_L1, ret=%d", enable ? "set" : "unset", ret); @@ -2576,7 +2554,7 @@ static void rtw89_pci_aspm_set(struct rtw89_dev *rtwdev, bool enable) if (rtw89_pci_disable_aspm_l1) return; - ret = rtw89_dbi_read8(rtwdev, RTW89_PCIE_ASPM_CTRL, &value); + ret = rtw89_pci_read_config_byte(rtwdev, RTW89_PCIE_ASPM_CTRL, &value); if (ret) rtw89_err(rtwdev, "failed to read ASPM Delay\n"); @@ -2584,16 +2562,16 @@ static void rtw89_pci_aspm_set(struct rtw89_dev *rtwdev, bool enable) value |= FIELD_PREP(RTW89_L1DLY_MASK, PCIE_L1DLY_16US) | FIELD_PREP(RTW89_L0DLY_MASK, PCIE_L0SDLY_4US); - ret = rtw89_dbi_write8(rtwdev, RTW89_PCIE_ASPM_CTRL, value); + ret = rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_ASPM_CTRL, value); if (ret) rtw89_err(rtwdev, "failed to read ASPM Delay\n"); if (enable) - ret = rtw89_dbi_write8_set(rtwdev, RTW89_PCIE_L1_CTRL, - RTW89_PCIE_BIT_L1); + ret = rtw89_pci_config_byte_set(rtwdev, RTW89_PCIE_L1_CTRL, + RTW89_PCIE_BIT_L1); else - ret = rtw89_dbi_write8_clr(rtwdev, RTW89_PCIE_L1_CTRL, - RTW89_PCIE_BIT_L1); + ret = rtw89_pci_config_byte_clr(rtwdev, RTW89_PCIE_L1_CTRL, + RTW89_PCIE_BIT_L1); if (ret) rtw89_err(rtwdev, "failed to %s ASPM L1, ret=%d", enable ? "set" : "unset", ret); @@ -2657,11 +2635,11 @@ static void rtw89_pci_l1ss_set(struct rtw89_dev *rtwdev, bool enable) int ret; if (enable) - ret = rtw89_dbi_write8_set(rtwdev, RTW89_PCIE_TIMER_CTRL, - RTW89_PCIE_BIT_L1SUB); + ret = rtw89_pci_config_byte_set(rtwdev, RTW89_PCIE_TIMER_CTRL, + RTW89_PCIE_BIT_L1SUB); else - ret = rtw89_dbi_write8_clr(rtwdev, RTW89_PCIE_TIMER_CTRL, - RTW89_PCIE_BIT_L1SUB); + ret = rtw89_pci_config_byte_clr(rtwdev, RTW89_PCIE_TIMER_CTRL, + RTW89_PCIE_BIT_L1SUB); if (ret) rtw89_err(rtwdev, "failed to %s L1SS, ret=%d", enable ? "set" : "unset", ret); @@ -2878,10 +2856,10 @@ static void rtw89_pci_l2_hci_ldo(struct rtw89_dev *rtwdev) return; /* Hardware need write the reg twice to ensure the setting work */ - rtw89_dbi_write8_set(rtwdev, RTW89_PCIE_RST_MSTATE, - RTW89_PCIE_BIT_CFG_RST_MSTATE); - rtw89_dbi_write8_set(rtwdev, RTW89_PCIE_RST_MSTATE, - RTW89_PCIE_BIT_CFG_RST_MSTATE); + rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_RST_MSTATE, + RTW89_PCIE_BIT_CFG_RST_MSTATE); + rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_RST_MSTATE, + RTW89_PCIE_BIT_CFG_RST_MSTATE); } static int __maybe_unused rtw89_pci_resume(struct device *dev) @@ -2932,11 +2910,11 @@ static const struct rtw89_hci_ops rtw89_pci_ops = { .napi_poll = rtw89_pci_napi_poll, }; -static int rtw89_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *id) +int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct ieee80211_hw *hw; struct rtw89_dev *rtwdev; + const struct rtw89_driver_info *info; int driver_data_size; int ret; @@ -2957,13 +2935,8 @@ static int rtw89_pci_probe(struct pci_dev *pdev, SET_IEEE80211_DEV(rtwdev->hw, &pdev->dev); - switch (id->driver_data) { - case RTL8852A: - rtwdev->chip = &rtw8852a_chip_info; - break; - default: - return -ENOENT; - } + info = (const struct rtw89_driver_info *)id->driver_data; + rtwdev->chip = info->chip; ret = rtw89_core_init(rtwdev); if (ret) { @@ -3022,8 +2995,9 @@ err_release_hw: return ret; } +EXPORT_SYMBOL(rtw89_pci_probe); -static void rtw89_pci_remove(struct pci_dev *pdev) +void rtw89_pci_remove(struct pci_dev *pdev) { struct ieee80211_hw *hw = pci_get_drvdata(pdev); struct rtw89_dev *rtwdev; @@ -3038,22 +3012,7 @@ static void rtw89_pci_remove(struct pci_dev *pdev) rtw89_core_deinit(rtwdev); ieee80211_free_hw(hw); } - -static const struct pci_device_id rtw89_pci_id_table[] = { - { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8852), .driver_data = RTL8852A }, - { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0xa85a), .driver_data = RTL8852A }, - {}, -}; -MODULE_DEVICE_TABLE(pci, rtw89_pci_id_table); - -static struct pci_driver rtw89_pci_driver = { - .name = "rtw89_pci", - .id_table = rtw89_pci_id_table, - .probe = rtw89_pci_probe, - .remove = rtw89_pci_remove, - .driver.pm = &rtw89_pm_ops, -}; -module_pci_driver(rtw89_pci_driver); +EXPORT_SYMBOL(rtw89_pci_remove); MODULE_AUTHOR("Realtek Corporation"); MODULE_DESCRIPTION("Realtek 802.11ax wireless PCI driver"); diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h index 20e6767ea5c4..7f1ee1544688 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.h +++ b/drivers/net/wireless/realtek/rtw89/pci.h @@ -627,4 +627,9 @@ static inline bool rtw89_pci_ltr_is_err_reg_val(u32 val) extern const struct dev_pm_ops rtw89_pm_ops; +struct pci_device_id; + +int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id); +void rtw89_pci_remove(struct pci_dev *pdev); + #endif diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c index 147009888de0..130db2f46f49 100644 --- a/drivers/net/wireless/realtek/rtw89/phy.c +++ b/drivers/net/wireless/realtek/rtw89/phy.c @@ -117,17 +117,28 @@ static u64 rtw89_phy_ra_mask_rssi(struct rtw89_dev *rtwdev, u8 rssi, else if (rssi_lv == 1) return 0xfffffffffffffff0ULL; else if (rssi_lv == 2) - return 0xffffffffffffffe0ULL; + return 0xffffffffffffefe0ULL; else if (rssi_lv == 3) - return 0xffffffffffffffc0ULL; + return 0xffffffffffffcfc0ULL; else if (rssi_lv == 4) - return 0xffffffffffffff80ULL; + return 0xffffffffffff8f80ULL; else if (rssi_lv >= 5) - return 0xffffffffffffff00ULL; + return 0xffffffffffff0f00ULL; return 0xffffffffffffffffULL; } +static u64 rtw89_phy_ra_mask_recover(u64 ra_mask, u64 ra_mask_bak) +{ + if ((ra_mask & ~(RA_MASK_CCK_RATES | RA_MASK_OFDM_RATES)) == 0) + ra_mask |= (ra_mask_bak & ~(RA_MASK_CCK_RATES | RA_MASK_OFDM_RATES)); + + if (ra_mask == 0) + ra_mask |= (ra_mask_bak & (RA_MASK_CCK_RATES | RA_MASK_OFDM_RATES)); + + return ra_mask; +} + static u64 rtw89_phy_ra_mask_cfg(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta) { struct rtw89_hal *hal = &rtwdev->hal; @@ -194,8 +205,8 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev, struct rtw89_ra_info *ra = &rtwsta->ra; const u64 *high_rate_masks = rtw89_ra_mask_ht_rates; u8 rssi = ewma_rssi_read(&rtwsta->avg_rssi); - u64 high_rate_mask = 0; u64 ra_mask = 0; + u64 ra_mask_bak; u8 mode = 0; u8 csi_mode = RTW89_RA_RPT_MODE_LEGACY; u8 bw_mode = 0; @@ -244,34 +255,36 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev, } if (rtwdev->hal.current_band_type == RTW89_BAND_2G) { + ra_mask |= sta->supp_rates[NL80211_BAND_2GHZ]; if (sta->supp_rates[NL80211_BAND_2GHZ] <= 0xf) mode |= RTW89_RA_MODE_CCK; else mode |= RTW89_RA_MODE_CCK | RTW89_RA_MODE_OFDM; } else { + ra_mask |= (u64)sta->supp_rates[NL80211_BAND_5GHZ] << 4; mode |= RTW89_RA_MODE_OFDM; } + ra_mask_bak = ra_mask; + if (mode >= RTW89_RA_MODE_HT) { + u64 mask = 0; for (i = 0; i < rtwdev->hal.tx_nss; i++) - high_rate_mask |= high_rate_masks[i]; - ra_mask &= high_rate_mask; + mask |= high_rate_masks[i]; if (mode & RTW89_RA_MODE_OFDM) - ra_mask |= RA_MASK_SUBOFDM_RATES; + mask |= RA_MASK_SUBOFDM_RATES; if (mode & RTW89_RA_MODE_CCK) - ra_mask |= RA_MASK_SUBCCK_RATES; + mask |= RA_MASK_SUBCCK_RATES; + ra_mask &= mask; } else if (mode & RTW89_RA_MODE_OFDM) { - if (mode & RTW89_RA_MODE_CCK) - ra_mask |= RA_MASK_SUBCCK_RATES; - ra_mask |= RA_MASK_OFDM_RATES; - } else { - ra_mask = RA_MASK_CCK_RATES; + ra_mask &= (RA_MASK_OFDM_RATES | RA_MASK_SUBCCK_RATES); } - if (mode != RTW89_RA_MODE_CCK) { + if (mode != RTW89_RA_MODE_CCK) ra_mask &= rtw89_phy_ra_mask_rssi(rtwdev, rssi, 0); - ra_mask &= rtw89_phy_ra_mask_cfg(rtwdev, rtwsta); - } + + ra_mask = rtw89_phy_ra_mask_recover(ra_mask, ra_mask_bak); + ra_mask &= rtw89_phy_ra_mask_cfg(rtwdev, rtwsta); switch (sta->bandwidth) { case IEEE80211_STA_RX_BW_80: @@ -568,6 +581,7 @@ u8 rtw89_phy_get_txsc(struct rtw89_dev *rtwdev, return txsc_idx; } +EXPORT_SYMBOL(rtw89_phy_get_txsc); u32 rtw89_phy_read_rf(struct rtw89_dev *rtwdev, enum rtw89_rf_path rf_path, u32 addr, u32 mask) @@ -972,6 +986,7 @@ void rtw89_phy_write32_idx(struct rtw89_dev *rtwdev, u32 addr, u32 mask, addr += rtw89_phy0_phy1_offset(rtwdev, addr); rtw89_phy_write32_mask(rtwdev, addr, mask, data); } +EXPORT_SYMBOL(rtw89_phy_write32_idx); void rtw89_phy_set_phy_regs(struct rtw89_dev *rtwdev, u32 addr, u32 mask, u32 val) @@ -995,6 +1010,7 @@ void rtw89_phy_write_reg3_tbl(struct rtw89_dev *rtwdev, rtw89_phy_write32_mask(rtwdev, reg3->addr, reg3->mask, reg3->data); } } +EXPORT_SYMBOL(rtw89_phy_write_reg3_tbl); const u8 rtw89_rs_idx_max[] = { [RTW89_RS_CCK] = RTW89_RATE_CCK_MAX, @@ -1003,6 +1019,7 @@ const u8 rtw89_rs_idx_max[] = { [RTW89_RS_HEDCM] = RTW89_RATE_HEDCM_MAX, [RTW89_RS_OFFSET] = RTW89_RATE_OFFSET_MAX, }; +EXPORT_SYMBOL(rtw89_rs_idx_max); const u8 rtw89_rs_nss_max[] = { [RTW89_RS_CCK] = 1, @@ -1011,6 +1028,7 @@ const u8 rtw89_rs_nss_max[] = { [RTW89_RS_HEDCM] = RTW89_NSS_HEDCM_MAX, [RTW89_RS_OFFSET] = 1, }; +EXPORT_SYMBOL(rtw89_rs_nss_max); static const u8 _byr_of_rs[] = { [RTW89_RS_CCK] = offsetof(struct rtw89_txpwr_byrate, cck), @@ -1044,6 +1062,7 @@ void rtw89_phy_load_txpwr_byrate(struct rtw89_dev *rtwdev, } } } +EXPORT_SYMBOL(rtw89_phy_load_txpwr_byrate); #define _phy_txpwr_rf_to_mac(rtwdev, txpwr_rf) \ ({ \ @@ -1074,6 +1093,7 @@ s8 rtw89_phy_read_txpwr_byrate(struct rtw89_dev *rtwdev, return _phy_txpwr_rf_to_mac(rtwdev, byr[idx]); } +EXPORT_SYMBOL(rtw89_phy_read_txpwr_byrate); static u8 rtw89_channel_to_idx(struct rtw89_dev *rtwdev, u8 channel) { @@ -1124,6 +1144,7 @@ s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, return min(lmt, sar); } +EXPORT_SYMBOL(rtw89_phy_read_txpwr_limit); #define __fill_txpwr_limit_nonbf_bf(ptr, bw, ntx, rs, ch) \ do { \ @@ -1222,6 +1243,7 @@ void rtw89_phy_fill_txpwr_limit(struct rtw89_dev *rtwdev, break; } } +EXPORT_SYMBOL(rtw89_phy_fill_txpwr_limit); static s8 rtw89_phy_read_txpwr_limit_ru(struct rtw89_dev *rtwdev, u8 ru, u8 ntx, u8 ch) @@ -1340,6 +1362,7 @@ void rtw89_phy_fill_txpwr_limit_ru(struct rtw89_dev *rtwdev, break; } } +EXPORT_SYMBOL(rtw89_phy_fill_txpwr_limit_ru); struct rtw89_phy_iter_ra_data { struct rtw89_dev *rtwdev; @@ -2845,7 +2868,9 @@ static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi, enum rtw89_bandwidth cbw = rtwdev->hal.current_band_width; struct rtw89_dig_info *dig = &rtwdev->dig; u8 final_rssi = 0, under_region = dig->pd_low_th_ofst; - u32 val = 0; + u8 ofdm_cca_th; + s8 cck_cca_th; + u32 pd_val = 0; under_region += PD_TH_SB_FLTR_CMP_VAL; @@ -2856,6 +2881,9 @@ static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi, case RTW89_CHANNEL_WIDTH_80: under_region += PD_TH_BW80_CMP_VAL; break; + case RTW89_CHANNEL_WIDTH_160: + under_region += PD_TH_BW160_CMP_VAL; + break; case RTW89_CHANNEL_WIDTH_20: fallthrough; default: @@ -2866,23 +2894,38 @@ static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi, dig->dyn_pd_th_max = dig->igi_rssi; final_rssi = min_t(u8, rssi, dig->igi_rssi); - final_rssi = clamp_t(u8, final_rssi, PD_TH_MIN_RSSI + under_region, - PD_TH_MAX_RSSI + under_region); + ofdm_cca_th = clamp_t(u8, final_rssi, PD_TH_MIN_RSSI + under_region, + PD_TH_MAX_RSSI + under_region); if (enable) { - val = (final_rssi - under_region - PD_TH_MIN_RSSI) >> 1; + pd_val = (ofdm_cca_th - under_region - PD_TH_MIN_RSSI) >> 1; rtw89_debug(rtwdev, RTW89_DBG_DIG, - "dyn_max=%d, final_rssi=%d, total=%d, PD_low=%d\n", - dig->igi_rssi, final_rssi, under_region, val); + "igi=%d, ofdm_ccaTH=%d, backoff=%d, PD_low=%d\n", + final_rssi, ofdm_cca_th, under_region, pd_val); } else { rtw89_debug(rtwdev, RTW89_DBG_DIG, "Dynamic PD th disabled, Set PD_low_bd=0\n"); } rtw89_phy_write32_mask(rtwdev, R_SEG0R_PD, B_SEG0R_PD_LOWER_BOUND_MSK, - val); + pd_val); rtw89_phy_write32_mask(rtwdev, R_SEG0R_PD, B_SEG0R_PD_SPATIAL_REUSE_EN_MSK, enable); + + if (!rtwdev->hal.support_cckpd) + return; + + cck_cca_th = max_t(s8, final_rssi - under_region, CCKPD_TH_MIN_RSSI); + pd_val = (u32)(cck_cca_th - IGI_RSSI_MAX); + + rtw89_debug(rtwdev, RTW89_DBG_DIG, + "igi=%d, cck_ccaTH=%d, backoff=%d, cck_PD_low=((%d))dB\n", + final_rssi, cck_cca_th, under_region, pd_val); + + rtw89_phy_write32_mask(rtwdev, R_BMODE_PDTH_EN_V1, + B_BMODE_PDTH_LIMIT_EN_MSK_V1, enable); + rtw89_phy_write32_mask(rtwdev, R_BMODE_PDTH_V1, + B_BMODE_PDTH_LOWER_BOUND_MSK_V1, pd_val); } void rtw89_phy_dig_reset(struct rtw89_dev *rtwdev) diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h index b1f059b725a1..2cb68f49b4d6 100644 --- a/drivers/net/wireless/realtek/rtw89/phy.h +++ b/drivers/net/wireless/realtek/rtw89/phy.h @@ -87,8 +87,11 @@ #define RXB_IDX_MAX 31 #define RXB_IDX_MIN 0 +#define IGI_RSSI_MAX 110 #define PD_TH_MAX_RSSI 70 #define PD_TH_MIN_RSSI 8 +#define CCKPD_TH_MIN_RSSI (-18) +#define PD_TH_BW160_CMP_VAL 9 #define PD_TH_BW80_CMP_VAL 6 #define PD_TH_BW40_CMP_VAL 3 #define PD_TH_BW20_CMP_VAL 0 @@ -265,6 +268,9 @@ const struct rtw89_phy_reg3_tbl _name ## _tbl = { \ .size = ARRAY_SIZE(_name), \ } +extern const u8 rtw89_rs_idx_max[RTW89_RS_MAX]; +extern const u8 rtw89_rs_nss_max[RTW89_RS_MAX]; + static inline void rtw89_phy_write8(struct rtw89_dev *rtwdev, u32 addr, u8 data) { diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h index e0a416d37d0e..b39e531df2d7 100644 --- a/drivers/net/wireless/realtek/rtw89/reg.h +++ b/drivers/net/wireless/realtek/rtw89/reg.h @@ -913,7 +913,7 @@ #define R_AX_DTIM_CTRL_P2 0xC4A6 #define R_AX_DTIM_CTRL_P3 0xC4E6 #define R_AX_DTIM_CTRL_P4 0xC526 -#define B_AX_DTIM_NUM_MASK GENMASK(15, 0) +#define B_AX_DTIM_NUM_MASK GENMASK(15, 8) #define B_AX_DTIM_CURRCNT_MASK GENMASK(7, 0) #define R_AX_TBTT_SHIFT_P0 0xC428 @@ -964,6 +964,11 @@ #define B_AX_P0MB2_EN BIT(2) #define B_AX_P0MB1_EN BIT(1) +#define R_AX_P0MB_HGQ_WINDOW_CFG_0 0xC590 +#define R_AX_P0MB_HGQ_WINDOW_CFG_0_C1 0xE590 +#define R_AX_PORT_HGQ_WINDOW_CFG 0xC5A0 +#define R_AX_PORT_HGQ_WINDOW_CFG_C1 0xE5A0 + #define R_AX_AMPDU_AGG_LIMIT 0xC610 #define B_AX_AMPDU_MAX_TIME_MASK GENMASK(31, 24) #define B_AX_RA_TRY_RATE_AGG_LMT_MASK GENMASK(23, 16) @@ -1080,6 +1085,13 @@ #define B_AX_TCR_ZLD_USTIME_AFTERPHYTXON GENMASK(11, 8) #define B_AX_TCR_TXTIMEOUT GENMASK(7, 0) +#define R_AX_MD_TSFT_STMP_CTL 0xCA08 +#define R_AX_MD_TSFT_STMP_CTL_C1 0xEA08 +#define B_AX_TSFT_OFS_MASK GENMASK(31, 16) +#define B_AX_STMP_THSD_MASK GENMASK(15, 8) +#define B_AX_UPD_HGQMD BIT(1) +#define B_AX_UPD_TIMIE BIT(0) + #define R_AX_PPWRBIT_SETTING 0xCA0C #define R_AX_PPWRBIT_SETTING_C1 0xEA0C @@ -1959,6 +1971,10 @@ #define R_CHBW_MOD 0x4978 #define B_CHBW_MOD_PRICH GENMASK(11, 8) #define B_CHBW_MOD_SBW GENMASK(13, 12) +#define R_BMODE_PDTH_V1 0x4B64 +#define B_BMODE_PDTH_LOWER_BOUND_MSK_V1 GENMASK(31, 24) +#define R_BMODE_PDTH_EN_V1 0x4B74 +#define B_BMODE_PDTH_LIMIT_EN_MSK_V1 BIT(30) #define R_CFO_COMP_SEG1_L 0x5384 #define R_CFO_COMP_SEG1_H 0x5388 #define R_CFO_COMP_SEG1_CTRL 0x538C diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c index 6b75e4bc7352..c39635a27399 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c @@ -36,16 +36,19 @@ static const struct rtw89_hfc_pub_cfg rtw8852a_hfc_pubcfg_pcie = { static const struct rtw89_hfc_param_ini rtw8852a_hfc_param_ini_pcie[] = { [RTW89_QTA_SCC] = {rtw8852a_hfc_chcfg_pcie, &rtw8852a_hfc_pubcfg_pcie, - &rtw_hfc_preccfg_pcie, RTW89_HCIFC_POH}, - [RTW89_QTA_DLFW] = {NULL, NULL, &rtw_hfc_preccfg_pcie, RTW89_HCIFC_POH}, + &rtw89_hfc_preccfg_pcie, RTW89_HCIFC_POH}, + [RTW89_QTA_DLFW] = {NULL, NULL, &rtw89_hfc_preccfg_pcie, + RTW89_HCIFC_POH}, [RTW89_QTA_INVALID] = {NULL}, }; static const struct rtw89_dle_mem rtw8852a_dle_mem_pcie[] = { - [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &wde_size0, &ple_size0, &wde_qt0, - &wde_qt0, &ple_qt4, &ple_qt5}, - [RTW89_QTA_DLFW] = {RTW89_QTA_DLFW, &wde_size4, &ple_size4, - &wde_qt4, &wde_qt4, &ple_qt13, &ple_qt13}, + [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_wde_size0, &rtw89_ple_size0, + &rtw89_wde_qt0, &rtw89_wde_qt0, &rtw89_ple_qt4, + &rtw89_ple_qt5}, + [RTW89_QTA_DLFW] = {RTW89_QTA_DLFW, &rtw89_wde_size4, &rtw89_ple_size4, + &rtw89_wde_qt4, &rtw89_wde_qt4, &rtw89_ple_qt13, + &rtw89_ple_qt13}, [RTW89_QTA_INVALID] = {RTW89_QTA_INVALID, NULL, NULL, NULL, NULL, NULL, NULL}, }; @@ -2019,6 +2022,8 @@ const struct rtw89_chip_info rtw8852a_chip_info = { .txpwr_factor_rf = 2, .txpwr_factor_mac = 1, .dig_table = &rtw89_8852a_phy_dig_table, + .support_bands = BIT(NL80211_BAND_2GHZ) | + BIT(NL80211_BAND_5GHZ), .rf_path_num = 2, .tx_nss = 2, .rx_nss = 2, @@ -2053,3 +2058,6 @@ const struct rtw89_chip_info rtw8852a_chip_info = { EXPORT_SYMBOL(rtw8852a_chip_info); MODULE_FIRMWARE("rtw89/rtw8852a_fw.bin"); +MODULE_AUTHOR("Realtek Corporation"); +MODULE_DESCRIPTION("Realtek 802.11ax wireless 8852A driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.h b/drivers/net/wireless/realtek/rtw89/rtw8852a.h index 633384374de0..fcff1194c009 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852a.h +++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.h @@ -93,6 +93,8 @@ struct rtw8852a_bb_pmac_info { u8 duty_cycle; }; +extern const struct rtw89_chip_info rtw8852a_chip_info; + void rtw8852a_bb_set_plcp_tx(struct rtw89_dev *rtwdev); void rtw8852a_bb_set_pmac_tx(struct rtw89_dev *rtwdev, struct rtw8852a_bb_pmac_info *tx_info, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852ae.c b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c new file mode 100644 index 000000000000..de93280e0f69 --- /dev/null +++ b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* Copyright(c) 2020-2021 Realtek Corporation + */ + +#include <linux/module.h> +#include <linux/pci.h> + +#include "pci.h" +#include "rtw8852a.h" + +static const struct rtw89_driver_info rtw89_8852ae_info = { + .chip = &rtw8852a_chip_info, +}; + +static const struct pci_device_id rtw89_8852ae_id_table[] = { + { + PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8852), + .driver_data = (kernel_ulong_t)&rtw89_8852ae_info, + }, + { + PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0xa85a), + .driver_data = (kernel_ulong_t)&rtw89_8852ae_info, + }, + {}, +}; +MODULE_DEVICE_TABLE(pci, rtw89_8852ae_id_table); + +static struct pci_driver rtw89_8852ae_driver = { + .name = "rtw89_8852ae", + .id_table = rtw89_8852ae_id_table, + .probe = rtw89_pci_probe, + .remove = rtw89_pci_remove, + .driver.pm = &rtw89_pm_ops, +}; +module_pci_driver(rtw89_8852ae_driver); + +MODULE_AUTHOR("Realtek Corporation"); +MODULE_DESCRIPTION("Realtek 802.11ax wireless 8852AE driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h index 75b11249f306..86e3d8b400d6 100644 --- a/drivers/net/wireless/realtek/rtw89/txrx.h +++ b/drivers/net/wireless/realtek/rtw89/txrx.h @@ -31,6 +31,8 @@ #define RTW89_TXWD_BODY0_HDR_LLC_LEN GENMASK(15, 11) #define RTW89_TXWD_BODY0_WD_PAGE BIT(7) #define RTW89_TXWD_BODY0_HW_AMSDU BIT(5) +#define RTW89_TXWD_BODY0_HW_SSN_SEL GENMASK(3, 2) +#define RTW89_TXWD_BODY0_HW_SSN_MODE GENMASK(1, 0) /* TX WD BODY DWORD 1 */ #define RTW89_TXWD_BODY1_PAYLOAD_ID GENMASK(31, 16) @@ -56,6 +58,7 @@ #define RTW89_TXWD_INFO0_GI_LTF GENMASK(27, 25) #define RTW89_TXWD_INFO0_DATA_RATE GENMASK(24, 16) #define RTW89_TXWD_INFO0_DISDATAFB BIT(10) +#define RTW89_TXWD_INFO0_MULTIPORT_ID GENMASK(6, 4) /* TX WD INFO DWORD 1 */ #define RTW89_TXWD_INFO1_DATA_RTY_LOWEST_RATE GENMASK(24, 16) diff --git a/drivers/net/wireless/st/cw1200/wsm.c b/drivers/net/wireless/st/cw1200/wsm.c index 99624dd34886..5a3e7a626702 100644 --- a/drivers/net/wireless/st/cw1200/wsm.c +++ b/drivers/net/wireless/st/cw1200/wsm.c @@ -537,7 +537,7 @@ int wsm_set_tx_queue_params(struct cw1200_common *priv, { int ret; struct wsm_buf *buf = &priv->wsm_cmd_buf; - u8 queue_id_to_wmm_aci[] = {3, 2, 0, 1}; + static const u8 queue_id_to_wmm_aci[] = { 3, 2, 0, 1 }; wsm_cmd_lock(priv); diff --git a/drivers/net/wwan/iosm/iosm_ipc_debugfs.c b/drivers/net/wwan/iosm/iosm_ipc_debugfs.c index f2f57751a7d2..e916139b8cd4 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_debugfs.c +++ b/drivers/net/wwan/iosm/iosm_ipc_debugfs.c @@ -12,10 +12,10 @@ void ipc_debugfs_init(struct iosm_imem *ipc_imem) { - struct dentry *debugfs_pdev = wwan_get_debugfs_dir(ipc_imem->dev); + ipc_imem->debugfs_wwan_dir = wwan_get_debugfs_dir(ipc_imem->dev); ipc_imem->debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, - debugfs_pdev); + ipc_imem->debugfs_wwan_dir); ipc_imem->trace = ipc_trace_init(ipc_imem); if (!ipc_imem->trace) @@ -26,4 +26,5 @@ void ipc_debugfs_deinit(struct iosm_imem *ipc_imem) { ipc_trace_deinit(ipc_imem->trace); debugfs_remove_recursive(ipc_imem->debugfs_dir); + wwan_put_debugfs_dir(ipc_imem->debugfs_wwan_dir); } diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index f9e8e0ee4de3..1e6a47976642 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -114,17 +114,35 @@ ipc_imem_fast_update_timer_cb(struct hrtimer *hr_timer) return HRTIMER_NORESTART; } +static int ipc_imem_tq_adb_timer_cb(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + ipc_mux_ul_adb_finish(ipc_imem->mux); + return 0; +} + +static enum hrtimer_restart +ipc_imem_adb_timer_cb(struct hrtimer *hr_timer) +{ + struct iosm_imem *ipc_imem = + container_of(hr_timer, struct iosm_imem, adb_timer); + + ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_adb_timer_cb, 0, + NULL, 0, false); + return HRTIMER_NORESTART; +} + static int ipc_imem_setup_cp_mux_cap_init(struct iosm_imem *ipc_imem, struct ipc_mux_config *cfg) { ipc_mmio_update_cp_capability(ipc_imem->mmio); - if (!ipc_imem->mmio->has_mux_lite) { + if (ipc_imem->mmio->mux_protocol == MUX_UNKNOWN) { dev_err(ipc_imem->dev, "Failed to get Mux capability."); return -EINVAL; } - cfg->protocol = MUX_LITE; + cfg->protocol = ipc_imem->mmio->mux_protocol; cfg->ul_flow = (ipc_imem->mmio->has_ul_flow_credit == 1) ? MUX_UL_ON_CREDITS : @@ -153,6 +171,10 @@ void ipc_imem_msg_send_feature_set(struct iosm_imem *ipc_imem, IPC_MSG_PREP_FEATURE_SET, &prep_args); } +/** + * ipc_imem_td_update_timer_start - Starts the TD Update Timer if not started. + * @ipc_imem: Pointer to imem data-struct + */ void ipc_imem_td_update_timer_start(struct iosm_imem *ipc_imem) { /* Use the TD update timer only in the runtime phase */ @@ -179,6 +201,21 @@ void ipc_imem_hrtimer_stop(struct hrtimer *hr_timer) hrtimer_cancel(hr_timer); } +/** + * ipc_imem_adb_timer_start - Starts the adb Timer if not starting. + * @ipc_imem: Pointer to imem data-struct + */ +void ipc_imem_adb_timer_start(struct iosm_imem *ipc_imem) +{ + if (!hrtimer_active(&ipc_imem->adb_timer)) { + ipc_imem->hrtimer_period = + ktime_set(0, IOSM_AGGR_MUX_ADB_FINISH_TIMEOUT_NSEC); + hrtimer_start(&ipc_imem->adb_timer, + ipc_imem->hrtimer_period, + HRTIMER_MODE_REL); + } +} + bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem) { struct ipc_mem_channel *channel; @@ -550,6 +587,11 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) while (ctrl_chl_idx < IPC_MEM_MAX_CHANNELS) { if (!ipc_chnl_cfg_get(&chnl_cfg_port, ctrl_chl_idx)) { ipc_imem->ipc_port[ctrl_chl_idx] = NULL; + if (ipc_imem->pcie->pci->device == INTEL_CP_DEVICE_7360_ID && + chnl_cfg_port.wwan_port_type == WWAN_PORT_MBIM) { + ctrl_chl_idx++; + continue; + } if (chnl_cfg_port.wwan_port_type != WWAN_PORT_UNKNOWN) { ipc_imem_channel_init(ipc_imem, IPC_CTYPE_CTRL, chnl_cfg_port, @@ -680,8 +722,11 @@ static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) } /* Try to generate new ADB or ADGH. */ - if (ipc_mux_ul_data_encode(ipc_imem->mux)) + if (ipc_mux_ul_data_encode(ipc_imem->mux)) { ipc_imem_td_update_timer_start(ipc_imem); + if (ipc_imem->mux->protocol == MUX_AGGREGATION) + ipc_imem_adb_timer_start(ipc_imem); + } /* Continue the send procedure with accumulated SIO or NETIF packets. * Reset the debounce flags. @@ -1330,6 +1375,9 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, HRTIMER_MODE_REL); ipc_imem->td_alloc_timer.function = ipc_imem_td_alloc_timer_cb; + hrtimer_init(&ipc_imem->adb_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + ipc_imem->adb_timer.function = ipc_imem_adb_timer_cb; + if (ipc_imem_config(ipc_imem)) { dev_err(ipc_imem->dev, "failed to initialize the imem"); goto imem_config_fail; diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h index 98554e9beb01..e700dc8bfe0a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h @@ -317,6 +317,7 @@ enum ipc_phase { * @tdupdate_timer: Delay the TD update doorbell. * @fast_update_timer: forced head pointer update delay timer. * @td_alloc_timer: Timer for DL pipe TD allocation retry + * @adb_timer: Timer for finishing the ADB. * @rom_exit_code: Mapped boot rom exit code. * @enter_runtime: 1 means the transition to runtime phase was * executed. @@ -340,6 +341,7 @@ enum ipc_phase { * @ev_mux_net_transmit_pending:0 means inform the IPC tasklet to pass * @reset_det_n: Reset detect flag * @pcie_wake_n: Pcie wake flag + * @debugfs_wwan_dir: WWAN Debug FS directory entry * @debugfs_dir: Debug FS directory for driver-specific entries */ struct iosm_imem { @@ -364,6 +366,7 @@ struct iosm_imem { struct hrtimer tdupdate_timer; struct hrtimer fast_update_timer; struct hrtimer td_alloc_timer; + struct hrtimer adb_timer; enum rom_exit_code rom_exit_code; u32 enter_runtime; struct completion ul_pend_sem; @@ -382,6 +385,7 @@ struct iosm_imem { reset_det_n:1, pcie_wake_n:1; #ifdef CONFIG_WWAN_DEBUGFS + struct dentry *debugfs_wwan_dir; struct dentry *debugfs_dir; #endif }; @@ -593,4 +597,7 @@ void ipc_imem_channel_init(struct iosm_imem *ipc_imem, enum ipc_ctype ctype, * Returns: 0 on success, -1 on failure */ int ipc_imem_devlink_trigger_chip_info(struct iosm_imem *ipc_imem); + +void ipc_imem_adb_timer_start(struct iosm_imem *ipc_imem); + #endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.c b/drivers/net/wwan/iosm/iosm_ipc_mmio.c index f09e5e77a2a5..63eb08c43c05 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mmio.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include "iosm_ipc_mmio.h" +#include "iosm_ipc_mux.h" /* Definition of MMIO offsets * note that MMIO_CI offsets are relative to end of chip info structure @@ -71,8 +72,9 @@ void ipc_mmio_update_cp_capability(struct iosm_mmio *ipc_mmio) ver = ipc_mmio_get_cp_version(ipc_mmio); cp_cap = ioread32(ipc_mmio->base + ipc_mmio->offset.cp_capability); - ipc_mmio->has_mux_lite = (ver >= IOSM_CP_VERSION) && - !(cp_cap & DL_AGGR) && !(cp_cap & UL_AGGR); + ipc_mmio->mux_protocol = ((ver >= IOSM_CP_VERSION) && (cp_cap & + (UL_AGGR | DL_AGGR))) ? MUX_AGGREGATION + : MUX_LITE; ipc_mmio->has_ul_flow_credit = (ver >= IOSM_CP_VERSION) && (cp_cap & UL_FLOW_CREDIT); diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.h b/drivers/net/wwan/iosm/iosm_ipc_mmio.h index f861994a6d90..193d7ba2478a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mmio.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.h @@ -72,7 +72,7 @@ struct mmio_offset { * @context_info_addr: Physical base address of context info structure * @chip_info_version: Version of chip info structure * @chip_info_size: Size of chip info structure - * @has_mux_lite: It doesn't support mux aggergation + * @mux_protocol: mux protocol * @has_ul_flow_credit: Ul flow credit support * @has_slp_no_prot: Device sleep no protocol support * @has_mcr_support: Usage of mcr support @@ -84,8 +84,8 @@ struct iosm_mmio { phys_addr_t context_info_addr; unsigned int chip_info_version; unsigned int chip_info_size; - u8 has_mux_lite:1, - has_ul_flow_credit:1, + u32 mux_protocol; + u8 has_ul_flow_credit:1, has_slp_no_prot:1, has_mcr_support:1; }; diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c index 8e66ffe92055..9c7a9a2a1f25 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c @@ -279,9 +279,10 @@ struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg, struct iosm_imem *imem) { struct iosm_mux *ipc_mux = kzalloc(sizeof(*ipc_mux), GFP_KERNEL); - int i, ul_tds, ul_td_size; + int i, j, ul_tds, ul_td_size; struct sk_buff_head *free_list; struct sk_buff *skb; + int qlt_size; if (!ipc_mux) return NULL; @@ -321,6 +322,24 @@ struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg, ipc_mux->channel_id = -1; ipc_mux->channel = NULL; + if (ipc_mux->protocol != MUX_LITE) { + qlt_size = offsetof(struct mux_qlth, ql) + + MUX_QUEUE_LEVEL * sizeof(struct mux_qlth_ql); + + for (i = 0; i < IPC_MEM_MUX_IP_SESSION_ENTRIES; i++) { + ipc_mux->ul_adb.pp_qlt[i] = kzalloc(qlt_size, + GFP_ATOMIC); + if (!ipc_mux->ul_adb.pp_qlt[i]) { + for (j = i - 1; j >= 0; j--) + kfree(ipc_mux->ul_adb.pp_qlt[j]); + return NULL; + } + } + + ul_td_size = IPC_MEM_MAX_UL_ADB_BUF_SIZE; + ul_tds = IPC_MEM_MAX_TDS_MUX_AGGR_UL; + } + /* Allocate the list of UL ADB. */ for (i = 0; i < ul_tds; i++) { dma_addr_t mapping; diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.h b/drivers/net/wwan/iosm/iosm_ipc_mux.h index 88debaa1ed31..cd9d74cc097f 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.h @@ -8,9 +8,12 @@ #include "iosm_ipc_protocol.h" -/* Size of the buffer for the IP MUX data buffer. */ -#define IPC_MEM_MAX_DL_MUX_BUF_SIZE (16 * 1024) -#define IPC_MEM_MAX_UL_ADB_BUF_SIZE IPC_MEM_MAX_DL_MUX_BUF_SIZE +#define IPC_MEM_MAX_UL_DG_ENTRIES 100 +#define IPC_MEM_MAX_TDS_MUX_AGGR_UL 60 + +#define IPC_MEM_MAX_ADB_BUF_SIZE (16 * 1024) +#define IPC_MEM_MAX_UL_ADB_BUF_SIZE IPC_MEM_MAX_ADB_BUF_SIZE +#define IPC_MEM_MAX_DL_ADB_BUF_SIZE IPC_MEM_MAX_ADB_BUF_SIZE /* Size of the buffer for the IP MUX Lite data buffer. */ #define IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE (2 * 1024) @@ -167,6 +170,7 @@ enum mux_state { enum ipc_mux_protocol { MUX_UNKNOWN, MUX_LITE, + MUX_AGGREGATION, }; /* Supported UL data transfer methods. */ @@ -192,24 +196,111 @@ struct mux_session { flush:1; /* flush net interface ? */ }; -/* State of a single UL data block. */ +/** + * struct mux_adth_dg - Structure of the datagram in the Aggregated Datagram + * Table Header. + * @datagram_index : Index (in bytes) to the k-th datagram in the table. + * Index shall count from the start of the block including + * the 16-byte header. This value shall be non-zero. + * @datagram_length: Length of the k-th datagram including the head padding. + * This value shall be non-zero. + * @service_class: Service class identifier for the datagram. + * @reserved: Reserved bytes. Set to zero + */ +struct mux_adth_dg { + __le32 datagram_index; + __le16 datagram_length; + u8 service_class; + u8 reserved; +}; + +/** + * struct mux_qlth_ql - Structure of the queue level in the Aggregated + * Datagram Queue Level Table Header. + * @nr_of_bytes: Number of bytes available to transmit in the queue. + */ +struct mux_qlth_ql { + __le32 nr_of_bytes; +}; + +/** + * struct mux_qlth - Structure of Aggregated Datagram Queue Level Table + * Header. + * @signature: Signature of the Queue Level Table Header + * Value: 0x48544C51 (ASCII characters: 'Q' 'L' 'T' 'H') + * @table_length: Length (in bytes) of the datagram table. This length + * shall include the queue level table header size. + * Minimum value:0x10 + * @if_id: ID of the interface the queue levels in the table + * belong to. + * @reserved: Reserved byte. Set to zero. + * @next_table_index: Index (in bytes) to the next table in the buffer. Index + * shall count from the start of the block including the + * 16-byte header. Value of zero indicates end of the list. + * @reserved2: Reserved bytes. Set to zero + * @ql: Queue level table with variable length + */ +struct mux_qlth { + __le32 signature; + __le16 table_length; + u8 if_id; + u8 reserved; + __le32 next_table_index; + __le32 reserved2; + struct mux_qlth_ql ql; +}; + +/** + * struct mux_adb - Structure of State of a single UL data block. + * @dest_skb: Current UL skb for the data block. + * @buf: ADB memory + * @adgh: ADGH pointer + * @qlth_skb: QLTH pointer + * @next_table_index: Pointer to next table index. + * @free_list: List of alloc. ADB for the UL sess. + * @size: Size of the ADB memory. + * @if_cnt: Statistic counter + * @dg_cnt_total: Datagram count total + * @payload_size: Payload Size + * @dg: Datagram table. + * @pp_qlt: Pointers to hold Queue Level Tables of session + * @adbh: ADBH pointer + * @qlt_updated: Queue level table updated + * @dg_count: Datagram count + */ struct mux_adb { - struct sk_buff *dest_skb; /* Current UL skb for the data block. */ - u8 *buf; /* ADB memory. */ - struct mux_adgh *adgh; /* ADGH pointer */ - struct sk_buff *qlth_skb; /* QLTH pointer */ - u32 *next_table_index; /* Pointer to next table index. */ - struct sk_buff_head free_list; /* List of alloc. ADB for the UL sess.*/ - int size; /* Size of the ADB memory. */ - u32 if_cnt; /* Statistic counter */ + struct sk_buff *dest_skb; + u8 *buf; + struct mux_adgh *adgh; + struct sk_buff *qlth_skb; + u32 *next_table_index; + struct sk_buff_head free_list; + int size; + u32 if_cnt; u32 dg_cnt_total; u32 payload_size; + struct mux_adth_dg + dg[IPC_MEM_MUX_IP_SESSION_ENTRIES][IPC_MEM_MAX_UL_DG_ENTRIES]; + struct mux_qlth *pp_qlt[IPC_MEM_MUX_IP_SESSION_ENTRIES]; + struct mux_adbh *adbh; + u32 qlt_updated[IPC_MEM_MUX_IP_SESSION_ENTRIES]; + u32 dg_count[IPC_MEM_MUX_IP_SESSION_ENTRIES]; }; -/* Temporary ACB state. */ +/** + * struct mux_acb - Structure of Temporary ACB state. + * @skb: Used UL skb. + * @if_id: Session id. + * @buf_p: Command buffer. + * @wanted_response: Wanted Response + * @got_response: Got response + * @cmd: command + * @got_param: Received command/response parameter + */ struct mux_acb { struct sk_buff *skb; /* Used UL skb. */ int if_id; /* Session id. */ + u8 *buf_p; u32 wanted_response; u32 got_response; u32 cmd; @@ -241,6 +332,12 @@ struct mux_acb { * @wwan_q_offset: This will hold the offset of the given instance * Useful while passing or receiving packets from * wwan/imem layer. + * @adb_finish_timer: Timer for forcefully finishing the ADB + * @acb_tx_sequence_nr: Sequence number for the ACB header. + * @params: user configurable parameters + * @adb_tx_sequence_nr: Sequence number for ADB header + * @acc_adb_size: Statistic data for logging + * @acc_payload_size: Statistic data for logging * @initialized: MUX object is initialized * @ev_mux_net_transmit_pending: * 0 means inform the IPC tasklet to pass the @@ -269,10 +366,16 @@ struct iosm_mux { long long ul_data_pend_bytes; struct mux_acb acb; int wwan_q_offset; + struct hrtimer adb_finish_timer; + u16 acb_tx_sequence_nr; + struct ipc_params *params; + u16 adb_tx_sequence_nr; + unsigned long long acc_adb_size; + unsigned long long acc_payload_size; u8 initialized:1, ev_mux_net_transmit_pending:1, - adb_prep_ongoing:1; -}; + adb_prep_ongoing; +} __packed; /* MUX configuration structure */ struct ipc_mux_config { diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index 40fb54a0513e..d41e373f9c0a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -54,6 +54,49 @@ static int ipc_mux_acb_send(struct iosm_mux *ipc_mux, bool blocking) return 0; } +/* Initialize the command header. */ +static void ipc_mux_acb_init(struct iosm_mux *ipc_mux) +{ + struct mux_acb *acb = &ipc_mux->acb; + struct mux_acbh *header; + + header = (struct mux_acbh *)(acb->skb)->data; + header->block_length = cpu_to_le32(sizeof(struct mux_acbh)); + header->first_cmd_index = header->block_length; + header->signature = cpu_to_le32(IOSM_AGGR_MUX_SIG_ACBH); + header->sequence_nr = cpu_to_le16(ipc_mux->acb_tx_sequence_nr++); +} + +/* Add a command to the ACB. */ +static struct mux_cmdh *ipc_mux_acb_add_cmd(struct iosm_mux *ipc_mux, u32 cmd, + void *param, u32 param_size) +{ + struct mux_acbh *header; + struct mux_cmdh *cmdh; + struct mux_acb *acb; + + acb = &ipc_mux->acb; + header = (struct mux_acbh *)(acb->skb)->data; + cmdh = (struct mux_cmdh *) + ((acb->skb)->data + le32_to_cpu(header->block_length)); + + cmdh->signature = cpu_to_le32(MUX_SIG_CMDH); + cmdh->command_type = cpu_to_le32(cmd); + cmdh->if_id = acb->if_id; + + acb->cmd = cmd; + cmdh->cmd_len = cpu_to_le16(offsetof(struct mux_cmdh, param) + + param_size); + cmdh->transaction_id = cpu_to_le32(ipc_mux->tx_transaction_id++); + if (param) + memcpy(&cmdh->param, param, param_size); + + skb_put(acb->skb, le32_to_cpu(header->block_length) + + le16_to_cpu(cmdh->cmd_len)); + + return cmdh; +} + /* Prepare mux Command */ static struct mux_lite_cmdh *ipc_mux_lite_add_cmd(struct iosm_mux *ipc_mux, u32 cmd, struct mux_acb *acb, @@ -104,7 +147,7 @@ int ipc_mux_dl_acb_send_cmds(struct iosm_mux *ipc_mux, u32 cmd_type, u8 if_id, size_t res_size, bool blocking, bool respond) { struct mux_acb *acb = &ipc_mux->acb; - struct mux_lite_cmdh *ack_lite; + union mux_type_cmdh cmdh; int ret = 0; acb->if_id = if_id; @@ -112,11 +155,23 @@ int ipc_mux_dl_acb_send_cmds(struct iosm_mux *ipc_mux, u32 cmd_type, u8 if_id, if (ret) return ret; - ack_lite = ipc_mux_lite_add_cmd(ipc_mux, cmd_type, acb, param, - res_size); - if (respond) - ack_lite->transaction_id = cpu_to_le32(transaction_id); + if (ipc_mux->protocol == MUX_LITE) { + cmdh.ack_lite = ipc_mux_lite_add_cmd(ipc_mux, cmd_type, acb, + param, res_size); + if (respond) + cmdh.ack_lite->transaction_id = + cpu_to_le32(transaction_id); + } else { + /* Initialize the ACB header. */ + ipc_mux_acb_init(ipc_mux); + cmdh.ack_aggr = ipc_mux_acb_add_cmd(ipc_mux, cmd_type, param, + res_size); + + if (respond) + cmdh.ack_aggr->transaction_id = + cpu_to_le32(transaction_id); + } ret = ipc_mux_acb_send(ipc_mux, blocking); return ret; @@ -129,15 +184,17 @@ void ipc_mux_netif_tx_flowctrl(struct mux_session *session, int idx, bool on) } static int ipc_mux_dl_cmdresps_decode_process(struct iosm_mux *ipc_mux, - struct mux_lite_cmdh *cmdh) + union mux_cmd_param param, + __le32 command_type, u8 if_id, + __le32 transaction_id) { struct mux_acb *acb = &ipc_mux->acb; - switch (le32_to_cpu(cmdh->command_type)) { + switch (le32_to_cpu(command_type)) { case MUX_CMD_OPEN_SESSION_RESP: case MUX_CMD_CLOSE_SESSION_RESP: /* Resume the control application. */ - acb->got_param = cmdh->param; + acb->got_param = param; break; case MUX_LITE_CMD_FLOW_CTL_ACK: @@ -147,8 +204,16 @@ static int ipc_mux_dl_cmdresps_decode_process(struct iosm_mux *ipc_mux, if (ipc_mux->protocol != MUX_LITE) return -EINVAL; - dev_dbg(ipc_mux->dev, "if %u FLOW_CTL_ACK %u received", - cmdh->if_id, le32_to_cpu(cmdh->transaction_id)); + dev_dbg(ipc_mux->dev, "if_id %u FLOW_CTL_ACK %u received", + if_id, le32_to_cpu(transaction_id)); + break; + + case IOSM_AGGR_MUX_CMD_FLOW_CTL_ACK: + /* This command type is not expected as response for + * Lite version of the protocol. So return non-zero. + */ + if (ipc_mux->protocol == MUX_LITE) + return -EINVAL; break; default: @@ -156,38 +221,39 @@ static int ipc_mux_dl_cmdresps_decode_process(struct iosm_mux *ipc_mux, } acb->wanted_response = MUX_CMD_INVALID; - acb->got_response = le32_to_cpu(cmdh->command_type); + acb->got_response = le32_to_cpu(command_type); complete(&ipc_mux->channel->ul_sem); return 0; } -static int ipc_mux_dl_dlcmds_decode_process(struct iosm_mux *ipc_mux, - struct mux_lite_cmdh *cmdh) +static int ipc_mux_dl_cmds_decode_process(struct iosm_mux *ipc_mux, + union mux_cmd_param *param, + __le32 command_type, u8 if_id, + __le16 cmd_len, int size) { - union mux_cmd_param *param = &cmdh->param; struct mux_session *session; - int new_size; + struct hrtimer *adb_timer; dev_dbg(ipc_mux->dev, "if_id[%d]: dlcmds decode process %d", - cmdh->if_id, le32_to_cpu(cmdh->command_type)); + if_id, le32_to_cpu(command_type)); - switch (le32_to_cpu(cmdh->command_type)) { + switch (le32_to_cpu(command_type)) { case MUX_LITE_CMD_FLOW_CTL: + case IOSM_AGGR_MUX_CMD_FLOW_CTL_DISABLE: - if (cmdh->if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) { + if (if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) { dev_err(ipc_mux->dev, "if_id [%d] not valid", - cmdh->if_id); + if_id); return -EINVAL; /* No session interface id. */ } - session = &ipc_mux->session[cmdh->if_id]; + session = &ipc_mux->session[if_id]; + adb_timer = &ipc_mux->imem->adb_timer; - new_size = offsetof(struct mux_lite_cmdh, param) + - sizeof(param->flow_ctl); if (param->flow_ctl.mask == cpu_to_le32(0xFFFFFFFF)) { /* Backward Compatibility */ - if (cmdh->cmd_len == cpu_to_le16(new_size)) + if (cmd_len == cpu_to_le16(size)) session->flow_ctl_mask = le32_to_cpu(param->flow_ctl.mask); else @@ -197,6 +263,16 @@ static int ipc_mux_dl_dlcmds_decode_process(struct iosm_mux *ipc_mux, * to limit uplink session queueing */ session->net_tx_stop = true; + + /* We have to call Finish ADB here. + * Otherwise any already queued data + * will be sent to CP when ADB is full + * for some other sessions. + */ + if (ipc_mux->protocol == MUX_AGGREGATION) { + ipc_mux_ul_adb_finish(ipc_mux); + ipc_imem_hrtimer_stop(adb_timer); + } /* Update the stats */ session->flow_ctl_en_cnt++; } else if (param->flow_ctl.mask == 0) { @@ -205,8 +281,10 @@ static int ipc_mux_dl_dlcmds_decode_process(struct iosm_mux *ipc_mux, * our internal Tx flag and enabling kernel * flow control */ + dev_dbg(ipc_mux->dev, "if_id[%u] flow_ctl mask 0x%08X", + if_id, le32_to_cpu(param->flow_ctl.mask)); /* Backward Compatibility */ - if (cmdh->cmd_len == cpu_to_le16(new_size)) + if (cmd_len == cpu_to_le16(size)) session->flow_ctl_mask = le32_to_cpu(param->flow_ctl.mask); else @@ -217,7 +295,10 @@ static int ipc_mux_dl_dlcmds_decode_process(struct iosm_mux *ipc_mux, break; } - dev_dbg(ipc_mux->dev, "if[%u] FLOW CTRL 0x%08X", cmdh->if_id, + ipc_mux->acc_adb_size = 0; + ipc_mux->acc_payload_size = 0; + + dev_dbg(ipc_mux->dev, "if_id[%u] FLOW CTRL 0x%08X", if_id, le32_to_cpu(param->flow_ctl.mask)); break; @@ -235,12 +316,20 @@ static void ipc_mux_dl_cmd_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) { struct mux_lite_cmdh *cmdh = (struct mux_lite_cmdh *)skb->data; __le32 trans_id = cmdh->transaction_id; + int size; - if (ipc_mux_dl_cmdresps_decode_process(ipc_mux, cmdh)) { + if (ipc_mux_dl_cmdresps_decode_process(ipc_mux, cmdh->param, + cmdh->command_type, cmdh->if_id, + cmdh->transaction_id)) { /* Unable to decode command response indicates the cmd_type * may be a command instead of response. So try to decoding it. */ - if (!ipc_mux_dl_dlcmds_decode_process(ipc_mux, cmdh)) { + size = offsetof(struct mux_lite_cmdh, param) + + sizeof(cmdh->param.flow_ctl); + if (!ipc_mux_dl_cmds_decode_process(ipc_mux, &cmdh->param, + cmdh->command_type, + cmdh->if_id, + cmdh->cmd_len, size)) { /* Decoded command may need a response. Give the * response according to the command type. */ @@ -349,7 +438,7 @@ static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, adgh = (struct mux_adgh *)block; - if (adgh->signature != cpu_to_le32(MUX_SIG_ADGH)) { + if (adgh->signature != cpu_to_le32(IOSM_AGGR_MUX_SIG_ADGH)) { dev_err(ipc_mux->dev, "invalid ADGH signature received"); return; } @@ -392,6 +481,192 @@ static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, ipc_mux->session[if_id].flush = 1; } +static void ipc_mux_dl_acbcmd_decode(struct iosm_mux *ipc_mux, + struct mux_cmdh *cmdh, int size) +{ + u32 link_st = IOSM_AGGR_MUX_CMD_LINK_STATUS_REPORT_RESP; + u32 fctl_dis = IOSM_AGGR_MUX_CMD_FLOW_CTL_DISABLE; + u32 fctl_ena = IOSM_AGGR_MUX_CMD_FLOW_CTL_ENABLE; + u32 fctl_ack = IOSM_AGGR_MUX_CMD_FLOW_CTL_ACK; + union mux_cmd_param *cmd_p = NULL; + u32 cmd = link_st; + u32 trans_id; + + if (!ipc_mux_dl_cmds_decode_process(ipc_mux, &cmdh->param, + cmdh->command_type, cmdh->if_id, + cmdh->cmd_len, size)) { + size = 0; + if (cmdh->command_type == cpu_to_le32(link_st)) { + cmd_p = &cmdh->param; + cmd_p->link_status_resp.response = MUX_CMD_RESP_SUCCESS; + } else if ((cmdh->command_type == cpu_to_le32(fctl_ena)) || + (cmdh->command_type == cpu_to_le32(fctl_dis))) { + cmd = fctl_ack; + } else { + return; + } + trans_id = le32_to_cpu(cmdh->transaction_id); + ipc_mux_dl_acb_send_cmds(ipc_mux, cmd, cmdh->if_id, + trans_id, cmd_p, size, false, true); + } +} + +/* Decode an aggregated command block. */ +static void ipc_mux_dl_acb_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) +{ + struct mux_acbh *acbh; + struct mux_cmdh *cmdh; + u32 next_cmd_index; + u8 *block; + int size; + + acbh = (struct mux_acbh *)(skb->data); + block = (u8 *)(skb->data); + + next_cmd_index = le32_to_cpu(acbh->first_cmd_index); + next_cmd_index = array_index_nospec(next_cmd_index, + sizeof(struct mux_cmdh)); + + while (next_cmd_index != 0) { + cmdh = (struct mux_cmdh *)&block[next_cmd_index]; + next_cmd_index = le32_to_cpu(cmdh->next_cmd_index); + if (ipc_mux_dl_cmdresps_decode_process(ipc_mux, cmdh->param, + cmdh->command_type, + cmdh->if_id, + cmdh->transaction_id)) { + size = offsetof(struct mux_cmdh, param) + + sizeof(cmdh->param.flow_ctl); + ipc_mux_dl_acbcmd_decode(ipc_mux, cmdh, size); + } + } +} + +/* process datagram */ +static int mux_dl_process_dg(struct iosm_mux *ipc_mux, struct mux_adbh *adbh, + struct mux_adth_dg *dg, struct sk_buff *skb, + int if_id, int nr_of_dg) +{ + u32 dl_head_pad_len = ipc_mux->session[if_id].dl_head_pad_len; + u32 packet_offset, i, rc; + + for (i = 0; i < nr_of_dg; i++, dg++) { + if (le32_to_cpu(dg->datagram_index) + < sizeof(struct mux_adbh)) + goto dg_error; + + /* Is the packet inside of the ADB */ + if (le32_to_cpu(dg->datagram_index) >= + le32_to_cpu(adbh->block_length)) { + goto dg_error; + } else { + packet_offset = + le32_to_cpu(dg->datagram_index) + + dl_head_pad_len; + /* Pass the packet to the netif layer. */ + rc = ipc_mux_net_receive(ipc_mux, if_id, ipc_mux->wwan, + packet_offset, + dg->service_class, + skb); + if (rc) + goto dg_error; + } + } + return 0; +dg_error: + return -1; +} + +/* Decode an aggregated data block. */ +static void mux_dl_adb_decode(struct iosm_mux *ipc_mux, + struct sk_buff *skb) +{ + struct mux_adth_dg *dg; + struct iosm_wwan *wwan; + struct mux_adbh *adbh; + struct mux_adth *adth; + int nr_of_dg, if_id; + u32 adth_index; + u8 *block; + + block = skb->data; + adbh = (struct mux_adbh *)block; + + /* Process the aggregated datagram tables. */ + adth_index = le32_to_cpu(adbh->first_table_index); + + /* Has CP sent an empty ADB ? */ + if (adth_index < 1) { + dev_err(ipc_mux->dev, "unexpected empty ADB"); + goto adb_decode_err; + } + + /* Loop through mixed session tables. */ + while (adth_index) { + /* Get the reference to the table header. */ + adth = (struct mux_adth *)(block + adth_index); + + /* Get the interface id and map it to the netif id. */ + if_id = adth->if_id; + if (if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) + goto adb_decode_err; + + if_id = array_index_nospec(if_id, + IPC_MEM_MUX_IP_SESSION_ENTRIES); + + /* Is the session active ? */ + wwan = ipc_mux->session[if_id].wwan; + if (!wwan) + goto adb_decode_err; + + /* Consistency checks for aggregated datagram table. */ + if (adth->signature != cpu_to_le32(IOSM_AGGR_MUX_SIG_ADTH)) + goto adb_decode_err; + + if (le16_to_cpu(adth->table_length) < (sizeof(struct mux_adth) - + sizeof(struct mux_adth_dg))) + goto adb_decode_err; + + /* Calculate the number of datagrams. */ + nr_of_dg = (le16_to_cpu(adth->table_length) - + sizeof(struct mux_adth) + + sizeof(struct mux_adth_dg)) / + sizeof(struct mux_adth_dg); + + /* Is the datagram table empty ? */ + if (nr_of_dg < 1) { + dev_err(ipc_mux->dev, + "adthidx=%u,nr_of_dg=%d,next_tblidx=%u", + adth_index, nr_of_dg, + le32_to_cpu(adth->next_table_index)); + + /* Move to the next aggregated datagram table. */ + adth_index = le32_to_cpu(adth->next_table_index); + continue; + } + + /* New aggregated datagram table. */ + dg = &adth->dg; + if (mux_dl_process_dg(ipc_mux, adbh, dg, skb, if_id, + nr_of_dg) < 0) + goto adb_decode_err; + + /* mark session for final flush */ + ipc_mux->session[if_id].flush = 1; + + /* Move to the next aggregated datagram table. */ + adth_index = le32_to_cpu(adth->next_table_index); + } + +adb_decode_err: + return; +} + +/** + * ipc_mux_dl_decode - Route the DL packet through the IP MUX layer + * depending on Header. + * @ipc_mux: Pointer to MUX data-struct + * @skb: Pointer to ipc_skb. + */ void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) { u32 signature; @@ -403,14 +678,18 @@ void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) signature = le32_to_cpup((__le32 *)skb->data); switch (signature) { - case MUX_SIG_ADGH: + case IOSM_AGGR_MUX_SIG_ADBH: /* Aggregated Data Block Header */ + mux_dl_adb_decode(ipc_mux, skb); + break; + case IOSM_AGGR_MUX_SIG_ADGH: ipc_mux_dl_adgh_decode(ipc_mux, skb); break; - case MUX_SIG_FCTH: ipc_mux_dl_fcth_decode(ipc_mux, skb->data); break; - + case IOSM_AGGR_MUX_SIG_ACBH: /* Aggregated Command Block Header */ + ipc_mux_dl_acb_decode(ipc_mux, skb); + break; case MUX_SIG_CMDH: ipc_mux_dl_cmd_decode(ipc_mux, skb); break; @@ -427,7 +706,10 @@ static int ipc_mux_ul_skb_alloc(struct iosm_mux *ipc_mux, { /* Take the first element of the free list. */ struct sk_buff *skb = skb_dequeue(&ul_adb->free_list); + u32 no_if = IPC_MEM_MUX_IP_SESSION_ENTRIES; + u32 *next_tb_id; int qlt_size; + u32 if_id; if (!skb) return -EBUSY; /* Wait for a free ADB skb. */ @@ -436,7 +718,37 @@ static int ipc_mux_ul_skb_alloc(struct iosm_mux *ipc_mux, IPC_CB(skb)->op_type = (u8)UL_MUX_OP_ADB; switch (type) { - case MUX_SIG_ADGH: + case IOSM_AGGR_MUX_SIG_ADBH: + /* Save the ADB memory settings. */ + ul_adb->dest_skb = skb; + ul_adb->buf = skb->data; + ul_adb->size = IPC_MEM_MAX_ADB_BUF_SIZE; + + /* reset statistic counter */ + ul_adb->if_cnt = 0; + ul_adb->payload_size = 0; + ul_adb->dg_cnt_total = 0; + + /* Initialize the ADBH. */ + ul_adb->adbh = (struct mux_adbh *)ul_adb->buf; + memset(ul_adb->adbh, 0, sizeof(struct mux_adbh)); + ul_adb->adbh->signature = cpu_to_le32(IOSM_AGGR_MUX_SIG_ADBH); + ul_adb->adbh->block_length = + cpu_to_le32(sizeof(struct mux_adbh)); + next_tb_id = (unsigned int *)&ul_adb->adbh->first_table_index; + ul_adb->next_table_index = next_tb_id; + + /* Clear the local copy of DGs for new ADB */ + memset(ul_adb->dg, 0, sizeof(ul_adb->dg)); + + /* Clear the DG count and QLT updated status for new ADB */ + for (if_id = 0; if_id < no_if; if_id++) { + ul_adb->dg_count[if_id] = 0; + ul_adb->qlt_updated[if_id] = 0; + } + break; + + case IOSM_AGGR_MUX_SIG_ADGH: /* Save the ADB memory settings. */ ul_adb->dest_skb = skb; ul_adb->buf = skb->data; @@ -506,6 +818,94 @@ static void ipc_mux_ul_adgh_finish(struct iosm_mux *ipc_mux) str, bytes); } +static void ipc_mux_ul_encode_adth(struct iosm_mux *ipc_mux, + struct mux_adb *ul_adb, int *out_offset) +{ + int i, qlt_size, offset = *out_offset; + struct mux_qlth *p_adb_qlt; + struct mux_adth_dg *dg; + struct mux_adth *adth; + u16 adth_dg_size; + u32 *next_tb_id; + + qlt_size = offsetof(struct mux_qlth, ql) + + MUX_QUEUE_LEVEL * sizeof(struct mux_qlth_ql); + + for (i = 0; i < ipc_mux->nr_sessions; i++) { + if (ul_adb->dg_count[i] > 0) { + adth_dg_size = offsetof(struct mux_adth, dg) + + ul_adb->dg_count[i] * sizeof(*dg); + + *ul_adb->next_table_index = offset; + adth = (struct mux_adth *)&ul_adb->buf[offset]; + next_tb_id = (unsigned int *)&adth->next_table_index; + ul_adb->next_table_index = next_tb_id; + offset += adth_dg_size; + adth->signature = cpu_to_le32(IOSM_AGGR_MUX_SIG_ADTH); + adth->if_id = i; + adth->table_length = cpu_to_le16(adth_dg_size); + adth_dg_size -= offsetof(struct mux_adth, dg); + memcpy(&adth->dg, ul_adb->dg[i], adth_dg_size); + ul_adb->if_cnt++; + } + + if (ul_adb->qlt_updated[i]) { + *ul_adb->next_table_index = offset; + p_adb_qlt = (struct mux_qlth *)&ul_adb->buf[offset]; + ul_adb->next_table_index = + (u32 *)&p_adb_qlt->next_table_index; + memcpy(p_adb_qlt, ul_adb->pp_qlt[i], qlt_size); + offset += qlt_size; + } + } + *out_offset = offset; +} + +/** + * ipc_mux_ul_adb_finish - Add the TD of the aggregated session packets to TDR. + * @ipc_mux: Pointer to MUX data-struct. + */ +void ipc_mux_ul_adb_finish(struct iosm_mux *ipc_mux) +{ + bool ul_data_pend = false; + struct mux_adb *ul_adb; + unsigned long flags; + int offset; + + ul_adb = &ipc_mux->ul_adb; + if (!ul_adb->dest_skb) + return; + + offset = *ul_adb->next_table_index; + ipc_mux_ul_encode_adth(ipc_mux, ul_adb, &offset); + ul_adb->adbh->block_length = cpu_to_le32(offset); + + if (le32_to_cpu(ul_adb->adbh->block_length) > ul_adb->size) { + ul_adb->dest_skb = NULL; + return; + } + + *ul_adb->next_table_index = 0; + ul_adb->adbh->sequence_nr = cpu_to_le16(ipc_mux->adb_tx_sequence_nr++); + skb_put(ul_adb->dest_skb, le32_to_cpu(ul_adb->adbh->block_length)); + + spin_lock_irqsave(&(&ipc_mux->channel->ul_list)->lock, flags); + __skb_queue_tail(&ipc_mux->channel->ul_list, ul_adb->dest_skb); + spin_unlock_irqrestore(&(&ipc_mux->channel->ul_list)->lock, flags); + + ul_adb->dest_skb = NULL; + /* Updates the TDs with ul_list */ + ul_data_pend = ipc_imem_ul_write_td(ipc_mux->imem); + + /* Delay the doorbell irq */ + if (ul_data_pend) + ipc_imem_td_update_timer_start(ipc_mux->imem); + + ipc_mux->acc_adb_size += le32_to_cpu(ul_adb->adbh->block_length); + ipc_mux->acc_payload_size += ul_adb->payload_size; + ipc_mux->ul_data_pend_bytes += ul_adb->payload_size; +} + /* Allocates an ADB from the free list and initializes it with ADBH */ static bool ipc_mux_ul_adb_allocate(struct iosm_mux *ipc_mux, struct mux_adb *adb, int *size_needed, @@ -688,7 +1088,7 @@ static int ipc_mux_ul_adgh_encode(struct iosm_mux *ipc_mux, int session_id, while (nr_of_pkts > 0) { /* get destination skb allocated */ if (ipc_mux_ul_adb_allocate(ipc_mux, adb, &ipc_mux->size_needed, - MUX_SIG_ADGH)) { + IOSM_AGGR_MUX_SIG_ADGH)) { dev_err(ipc_mux->dev, "no reserved memory for ADGH"); return -ENOMEM; } @@ -720,7 +1120,7 @@ static int ipc_mux_ul_adgh_encode(struct iosm_mux *ipc_mux, int session_id, memcpy(adb->buf + offset + pad_len, src_skb->data, src_skb->len); - adb->adgh->signature = cpu_to_le32(MUX_SIG_ADGH); + adb->adgh->signature = cpu_to_le32(IOSM_AGGR_MUX_SIG_ADGH); adb->adgh->if_id = session_id; adb->adgh->length = cpu_to_le16(sizeof(struct mux_adgh) + pad_len + @@ -762,6 +1162,187 @@ static int ipc_mux_ul_adgh_encode(struct iosm_mux *ipc_mux, int session_id, return adb_updated; } +/** + * ipc_mux_ul_adb_update_ql - Adds Queue Level Table and Queue Level to ADB + * @ipc_mux: pointer to MUX instance data + * @p_adb: pointer to UL aggegated data block + * @session_id: session id + * @qlth_n_ql_size: Length (in bytes) of the datagram table + * @ul_list: pointer to skb buffer head + */ +void ipc_mux_ul_adb_update_ql(struct iosm_mux *ipc_mux, struct mux_adb *p_adb, + int session_id, int qlth_n_ql_size, + struct sk_buff_head *ul_list) +{ + int qlevel = ul_list->qlen; + struct mux_qlth *p_qlt; + + p_qlt = (struct mux_qlth *)p_adb->pp_qlt[session_id]; + + /* Initialize QLTH if not been done */ + if (p_adb->qlt_updated[session_id] == 0) { + p_qlt->signature = cpu_to_le32(MUX_SIG_QLTH); + p_qlt->if_id = session_id; + p_qlt->table_length = cpu_to_le16(qlth_n_ql_size); + p_qlt->reserved = 0; + p_qlt->reserved2 = 0; + } + + /* Update Queue Level information always */ + p_qlt->ql.nr_of_bytes = cpu_to_le32(qlevel); + p_adb->qlt_updated[session_id] = 1; +} + +/* Update the next table index. */ +static int mux_ul_dg_update_tbl_index(struct iosm_mux *ipc_mux, + int session_id, + struct sk_buff_head *ul_list, + struct mux_adth_dg *dg, + int aligned_size, + u32 qlth_n_ql_size, + struct mux_adb *adb, + struct sk_buff *src_skb) +{ + ipc_mux_ul_adb_update_ql(ipc_mux, adb, session_id, + qlth_n_ql_size, ul_list); + ipc_mux_ul_adb_finish(ipc_mux); + if (ipc_mux_ul_adb_allocate(ipc_mux, adb, &ipc_mux->size_needed, + IOSM_AGGR_MUX_SIG_ADBH)) { + dev_kfree_skb(src_skb); + return -ENOMEM; + } + ipc_mux->size_needed = le32_to_cpu(adb->adbh->block_length); + + ipc_mux->size_needed += offsetof(struct mux_adth, dg); + ipc_mux->size_needed += qlth_n_ql_size; + ipc_mux->size_needed += sizeof(*dg) + aligned_size; + return 0; +} + +/* Process encode session UL data. */ +static int mux_ul_dg_encode(struct iosm_mux *ipc_mux, struct mux_adb *adb, + struct mux_adth_dg *dg, + struct sk_buff_head *ul_list, + struct sk_buff *src_skb, int session_id, + int pkt_to_send, u32 qlth_n_ql_size, + int *out_offset, int head_pad_len) +{ + int aligned_size; + int offset = *out_offset; + unsigned long flags; + int nr_of_skb = 0; + + while (pkt_to_send > 0) { + /* Peek at the head of the list. */ + src_skb = skb_peek(ul_list); + if (!src_skb) { + dev_err(ipc_mux->dev, + "skb peek return NULL with count : %d", + pkt_to_send); + return -1; + } + aligned_size = ALIGN((head_pad_len + src_skb->len), 4); + ipc_mux->size_needed += sizeof(*dg) + aligned_size; + + if (ipc_mux->size_needed > adb->size || + ((ipc_mux->size_needed + ipc_mux->ul_data_pend_bytes) >= + IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B)) { + *adb->next_table_index = offset; + if (mux_ul_dg_update_tbl_index(ipc_mux, session_id, + ul_list, dg, + aligned_size, + qlth_n_ql_size, adb, + src_skb) < 0) + return -ENOMEM; + nr_of_skb = 0; + offset = le32_to_cpu(adb->adbh->block_length); + /* Load pointer to next available datagram entry */ + dg = adb->dg[session_id] + adb->dg_count[session_id]; + } + /* Add buffer without head padding to next pending transfer. */ + memcpy(adb->buf + offset + head_pad_len, + src_skb->data, src_skb->len); + /* Setup datagram entry. */ + dg->datagram_index = cpu_to_le32(offset); + dg->datagram_length = cpu_to_le16(src_skb->len + head_pad_len); + dg->service_class = (((struct sk_buff *)src_skb)->priority); + dg->reserved = 0; + adb->dg_cnt_total++; + adb->payload_size += le16_to_cpu(dg->datagram_length); + dg++; + adb->dg_count[session_id]++; + offset += aligned_size; + /* Remove the processed elements and free it. */ + spin_lock_irqsave(&ul_list->lock, flags); + src_skb = __skb_dequeue(ul_list); + spin_unlock_irqrestore(&ul_list->lock, flags); + + dev_kfree_skb(src_skb); + nr_of_skb++; + pkt_to_send--; + } + *out_offset = offset; + return nr_of_skb; +} + +/* Process encode session UL data to ADB. */ +static int mux_ul_adb_encode(struct iosm_mux *ipc_mux, int session_id, + struct mux_session *session, + struct sk_buff_head *ul_list, struct mux_adb *adb, + int pkt_to_send) +{ + int adb_updated = -EINVAL; + int head_pad_len, offset; + struct sk_buff *src_skb = NULL; + struct mux_adth_dg *dg; + u32 qlth_n_ql_size; + + /* If any of the opened session has set Flow Control ON then limit the + * UL data to mux_flow_ctrl_high_thresh_b bytes + */ + if (ipc_mux->ul_data_pend_bytes >= + IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B) { + ipc_mux_stop_tx_for_all_sessions(ipc_mux); + return adb_updated; + } + + qlth_n_ql_size = offsetof(struct mux_qlth, ql) + + MUX_QUEUE_LEVEL * sizeof(struct mux_qlth_ql); + head_pad_len = session->ul_head_pad_len; + + if (session->ul_head_pad_len > IPC_MEM_DL_ETH_OFFSET) + head_pad_len = session->ul_head_pad_len - IPC_MEM_DL_ETH_OFFSET; + + if (ipc_mux_ul_adb_allocate(ipc_mux, adb, &ipc_mux->size_needed, + IOSM_AGGR_MUX_SIG_ADBH)) + return -ENOMEM; + + offset = le32_to_cpu(adb->adbh->block_length); + + if (ipc_mux->size_needed == 0) + ipc_mux->size_needed = offset; + + /* Calculate the size needed for ADTH, QLTH and QL*/ + if (adb->dg_count[session_id] == 0) { + ipc_mux->size_needed += offsetof(struct mux_adth, dg); + ipc_mux->size_needed += qlth_n_ql_size; + } + + dg = adb->dg[session_id] + adb->dg_count[session_id]; + + if (mux_ul_dg_encode(ipc_mux, adb, dg, ul_list, src_skb, + session_id, pkt_to_send, qlth_n_ql_size, &offset, + head_pad_len) > 0) { + adb_updated = 1; + *adb->next_table_index = offset; + ipc_mux_ul_adb_update_ql(ipc_mux, adb, session_id, + qlth_n_ql_size, ul_list); + adb->adbh->block_length = cpu_to_le32(offset); + } + + return adb_updated; +} + bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux) { struct sk_buff_head *ul_list; @@ -802,28 +1383,88 @@ bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux) * -> try next session id. */ continue; - - updated = ipc_mux_ul_adgh_encode(ipc_mux, session_id, session, - ul_list, &ipc_mux->ul_adb, - dg_n); + if (ipc_mux->protocol == MUX_LITE) + updated = ipc_mux_ul_adgh_encode(ipc_mux, session_id, + session, ul_list, + &ipc_mux->ul_adb, + dg_n); + else + updated = mux_ul_adb_encode(ipc_mux, session_id, + session, ul_list, + &ipc_mux->ul_adb, + dg_n); } ipc_mux->adb_prep_ongoing = false; return updated == 1; } -void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb) +/* Calculates the Payload from any given ADB. */ +static int ipc_mux_get_payload_from_adb(struct iosm_mux *ipc_mux, + struct mux_adbh *p_adbh) { - struct mux_adgh *adgh; - u16 adgh_len; + struct mux_adth_dg *dg; + struct mux_adth *adth; + u32 payload_size = 0; + u32 next_table_idx; + int nr_of_dg, i; + + /* Process the aggregated datagram tables. */ + next_table_idx = le32_to_cpu(p_adbh->first_table_index); + + if (next_table_idx < sizeof(struct mux_adbh)) { + dev_err(ipc_mux->dev, "unexpected empty ADB"); + return payload_size; + } - adgh = (struct mux_adgh *)skb->data; - adgh_len = le16_to_cpu(adgh->length); + while (next_table_idx != 0) { + /* Get the reference to the table header. */ + adth = (struct mux_adth *)((u8 *)p_adbh + next_table_idx); - if (adgh->signature == cpu_to_le32(MUX_SIG_ADGH) && - ipc_mux->ul_flow == MUX_UL) - ipc_mux->ul_data_pend_bytes = ipc_mux->ul_data_pend_bytes - - adgh_len; + if (adth->signature == cpu_to_le32(IOSM_AGGR_MUX_SIG_ADTH)) { + nr_of_dg = (le16_to_cpu(adth->table_length) - + sizeof(struct mux_adth) + + sizeof(struct mux_adth_dg)) / + sizeof(struct mux_adth_dg); + + if (nr_of_dg <= 0) + return payload_size; + + dg = &adth->dg; + + for (i = 0; i < nr_of_dg; i++, dg++) { + if (le32_to_cpu(dg->datagram_index) < + sizeof(struct mux_adbh)) { + return payload_size; + } + payload_size += + le16_to_cpu(dg->datagram_length); + } + } + next_table_idx = le32_to_cpu(adth->next_table_index); + } + + return payload_size; +} + +void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb) +{ + union mux_type_header hr; + u16 adgh_len; + int payload; + + if (ipc_mux->protocol == MUX_LITE) { + hr.adgh = (struct mux_adgh *)skb->data; + adgh_len = le16_to_cpu(hr.adgh->length); + if (hr.adgh->signature == cpu_to_le32(IOSM_AGGR_MUX_SIG_ADGH) && + ipc_mux->ul_flow == MUX_UL) + ipc_mux->ul_data_pend_bytes = + ipc_mux->ul_data_pend_bytes - adgh_len; + } else { + hr.adbh = (struct mux_adbh *)(skb->data); + payload = ipc_mux_get_payload_from_adb(ipc_mux, hr.adbh); + ipc_mux->ul_data_pend_bytes -= payload; + } if (ipc_mux->ul_flow == MUX_UL) dev_dbg(ipc_mux->dev, "ul_data_pend_bytes: %lld", @@ -846,10 +1487,13 @@ static int ipc_mux_tq_ul_trigger_encode(struct iosm_imem *ipc_imem, int arg, /* Add session UL data to a ADB and ADGH */ ul_data_pend = ipc_mux_ul_data_encode(ipc_mux); - if (ul_data_pend) + if (ul_data_pend) { + if (ipc_mux->protocol == MUX_AGGREGATION) + ipc_imem_adb_timer_start(ipc_mux->imem); + /* Delay the doorbell irq */ ipc_imem_td_update_timer_start(ipc_mux->imem); - + } /* reset the debounce flag */ ipc_mux->ev_mux_net_transmit_pending = false; diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h index aae83db5cbb8..5d4e3b89542c 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h @@ -13,6 +13,39 @@ */ #define MUX_QUEUE_LEVEL 1 +/* ADB finish timer value */ +#define IOSM_AGGR_MUX_ADB_FINISH_TIMEOUT_NSEC (500 * 1000) + +/* Enables the flow control (Flow is not allowed) */ +#define IOSM_AGGR_MUX_CMD_FLOW_CTL_ENABLE 5 + +/* Disables the flow control (Flow is allowed) */ +#define IOSM_AGGR_MUX_CMD_FLOW_CTL_DISABLE 6 + +/* ACK the flow control command. Shall have the same Transaction ID as the + * matching FLOW_CTL command + */ +#define IOSM_AGGR_MUX_CMD_FLOW_CTL_ACK 7 + +/* Aggregation Protocol Command for report packet indicating link quality + */ +#define IOSM_AGGR_MUX_CMD_LINK_STATUS_REPORT 8 + +/* Response to a report packet */ +#define IOSM_AGGR_MUX_CMD_LINK_STATUS_REPORT_RESP 9 + +/* ACBH: Signature of the Aggregated Command Block Header. */ +#define IOSM_AGGR_MUX_SIG_ACBH 0x48424341 + +/* ADTH: Signature of the Aggregated Datagram Table Header. */ +#define IOSM_AGGR_MUX_SIG_ADTH 0x48544441 + +/* ADBH: Signature of the Aggregated Data Block Header. */ +#define IOSM_AGGR_MUX_SIG_ADBH 0x48424441 + +/* ADGH: Signature of the Datagram Header. */ +#define IOSM_AGGR_MUX_SIG_ADGH 0x48474441 + /* Size of the buffer for the IP MUX commands. */ #define MUX_MAX_UL_ACB_BUF_SIZE 256 @@ -53,6 +86,85 @@ #define IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B (110 * 1024) /** + * struct mux_cmdh - Structure of Command Header. + * @signature: Signature of the Command Header. + * @cmd_len: Length (in bytes) of the Aggregated Command Block. + * @if_id: ID of the interface the commands in the table belong to. + * @reserved: Reserved. Set to zero. + * @next_cmd_index: Index (in bytes) to the next command in the buffer. + * @command_type: Command Enum. See table Session Management chapter for + * details. + * @transaction_id: The Transaction ID shall be unique to the command + * @param: Optional parameters used with the command. + */ +struct mux_cmdh { + __le32 signature; + __le16 cmd_len; + u8 if_id; + u8 reserved; + __le32 next_cmd_index; + __le32 command_type; + __le32 transaction_id; + union mux_cmd_param param; +}; + +/** + * struct mux_acbh - Structure of the Aggregated Command Block Header. + * @signature: Signature of the Aggregated Command Block Header. + * @reserved: Reserved bytes. Set to zero. + * @sequence_nr: Block sequence number. + * @block_length: Length (in bytes) of the Aggregated Command Block. + * @first_cmd_index: Index (in bytes) to the first command in the buffer. + */ +struct mux_acbh { + __le32 signature; + __le16 reserved; + __le16 sequence_nr; + __le32 block_length; + __le32 first_cmd_index; +}; + +/** + * struct mux_adbh - Structure of the Aggregated Data Block Header. + * @signature: Signature of the Aggregated Data Block Header. + * @reserved: Reserved bytes. Set to zero. + * @sequence_nr: Block sequence number. + * @block_length: Length (in bytes) of the Aggregated Data Block. + * @first_table_index: Index (in bytes) to the first Datagram Table in + * the buffer. + */ +struct mux_adbh { + __le32 signature; + __le16 reserved; + __le16 sequence_nr; + __le32 block_length; + __le32 first_table_index; +}; + +/** + * struct mux_adth - Structure of the Aggregated Datagram Table Header. + * @signature: Signature of the Aggregated Datagram Table Header. + * @table_length: Length (in bytes) of the datagram table. + * @if_id: ID of the interface the datagrams in the table + * belong to. + * @opt_ipv4v6: Indicates IPv4(=0)/IPv6(=1) hint. + * @reserved: Reserved bits. Set to zero. + * @next_table_index: Index (in bytes) to the next Datagram Table in + * the buffer. + * @reserved2: Reserved bytes. Set to zero + * @dg: datagramm table with variable length + */ +struct mux_adth { + __le32 signature; + __le16 table_length; + u8 if_id; + u8 opt_ipv4v6; + __le32 next_table_index; + __le32 reserved2; + struct mux_adth_dg dg; +}; + +/** * struct mux_adgh - Aggregated Datagram Header. * @signature: Signature of the Aggregated Datagram Header(0x48474441) * @length: Length (in bytes) of the datagram header. This length @@ -129,11 +241,25 @@ struct ipc_mem_lite_gen_tbl { }; /** - * ipc_mux_dl_decode -Route the DL packet through the IP MUX layer - * depending on Header. - * @ipc_mux: Pointer to MUX data-struct - * @skb: Pointer to ipc_skb. + * struct mux_type_cmdh - Structure of command header for mux lite and aggr + * @ack_lite: MUX Lite Command Header pointer + * @ack_aggr: Command Header pointer */ +union mux_type_cmdh { + struct mux_lite_cmdh *ack_lite; + struct mux_cmdh *ack_aggr; +}; + +/** + * struct mux_type_header - Structure of mux header type + * @adgh: Aggregated Datagram Header pointer + * @adbh: Aggregated Data Block Header pointer + */ +union mux_type_header { + struct mux_adgh *adgh; + struct mux_adbh *adbh; +}; + void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb); /** @@ -147,7 +273,7 @@ void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb); * @blocking: True for blocking send * @respond: If true return transaction ID * - * Returns: 0 in success and failure value on error + * Returns: 0 in success and failure value on error */ int ipc_mux_dl_acb_send_cmds(struct iosm_mux *ipc_mux, u32 cmd_type, u8 if_id, u32 transaction_id, union mux_cmd_param *param, @@ -190,4 +316,10 @@ bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux); */ void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb); +void ipc_mux_ul_adb_finish(struct iosm_mux *ipc_mux); + +void ipc_mux_ul_adb_update_ql(struct iosm_mux *ipc_mux, struct mux_adb *p_adb, + int session_id, int qlth_n_ql_size, + struct sk_buff_head *ul_list); + #endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index d73894e2a84e..31f57b986df2 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -320,6 +320,7 @@ ret_fail: static const struct pci_device_id iosm_ipc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, INTEL_CP_DEVICE_7560_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, INTEL_CP_DEVICE_7360_ID) }, {} }; MODULE_DEVICE_TABLE(pci, iosm_ipc_ids); diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.h b/drivers/net/wwan/iosm/iosm_ipc_pcie.h index 7d1f0cd7364c..844cf1fed994 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.h +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.h @@ -14,6 +14,7 @@ /* Device ID */ #define INTEL_CP_DEVICE_7560_ID 0x7560 +#define INTEL_CP_DEVICE_7360_ID 0x7360 /* Define for BAR area usage */ #define IPC_DOORBELL_BAR0 0 diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 1508dc2a497b..b8c7843730ed 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -160,6 +160,42 @@ struct dentry *wwan_get_debugfs_dir(struct device *parent) return wwandev->debugfs_dir; } EXPORT_SYMBOL_GPL(wwan_get_debugfs_dir); + +static int wwan_dev_debugfs_match(struct device *dev, const void *dir) +{ + struct wwan_device *wwandev; + + if (dev->type != &wwan_dev_type) + return 0; + + wwandev = to_wwan_dev(dev); + + return wwandev->debugfs_dir == dir; +} + +static struct wwan_device *wwan_dev_get_by_debugfs(struct dentry *dir) +{ + struct device *dev; + + dev = class_find_device(wwan_class, NULL, dir, wwan_dev_debugfs_match); + if (!dev) + return ERR_PTR(-ENODEV); + + return to_wwan_dev(dev); +} + +void wwan_put_debugfs_dir(struct dentry *dir) +{ + struct wwan_device *wwandev = wwan_dev_get_by_debugfs(dir); + + if (WARN_ON(IS_ERR(wwandev))) + return; + + /* wwan_dev_get_by_debugfs() also got a reference */ + put_device(&wwandev->dev); + put_device(&wwandev->dev); +} +EXPORT_SYMBOL_GPL(wwan_put_debugfs_dir); #endif /* This function allocates and registers a new WWAN device OR if a WWAN device diff --git a/drivers/nfc/st-nci/vendor_cmds.c b/drivers/nfc/st-nci/vendor_cmds.c index 30d2912d1a05..6335d7afca24 100644 --- a/drivers/nfc/st-nci/vendor_cmds.c +++ b/drivers/nfc/st-nci/vendor_cmds.c @@ -456,7 +456,7 @@ static const struct nfc_vendor_cmd st_nci_vendor_cmds[] = { int st_nci_vendor_cmds_init(struct nci_dev *ndev) { - return nfc_set_vendor_cmds(ndev->nfc_dev, st_nci_vendor_cmds, + return nci_set_vendor_cmds(ndev, st_nci_vendor_cmds, sizeof(st_nci_vendor_cmds)); } EXPORT_SYMBOL(st_nci_vendor_cmds_init); diff --git a/drivers/nfc/st21nfca/vendor_cmds.c b/drivers/nfc/st21nfca/vendor_cmds.c index 74882866dbaf..bfa418d4c6b0 100644 --- a/drivers/nfc/st21nfca/vendor_cmds.c +++ b/drivers/nfc/st21nfca/vendor_cmds.c @@ -358,7 +358,7 @@ int st21nfca_vendor_cmds_init(struct nfc_hci_dev *hdev) struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev); init_completion(&info->vendor_info.req_completion); - return nfc_set_vendor_cmds(hdev->ndev, st21nfca_vendor_cmds, - sizeof(st21nfca_vendor_cmds)); + return nfc_hci_set_vendor_cmds(hdev, st21nfca_vendor_cmds, + sizeof(st21nfca_vendor_cmds)); } EXPORT_SYMBOL(st21nfca_vendor_cmds_init); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 0e4bc8b9329d..b6f2cfd15dd2 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -317,11 +317,18 @@ no_memory: } EXPORT_SYMBOL(ptp_clock_register); +static int unregister_vclock(struct device *dev, void *data) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + + ptp_vclock_unregister(info_to_vclock(ptp->info)); + return 0; +} + int ptp_clock_unregister(struct ptp_clock *ptp) { if (ptp_vclock_in_use(ptp)) { - pr_err("ptp: virtual clock in use\n"); - return -EBUSY; + device_for_each_child(&ptp->dev, NULL, unregister_vclock); } ptp->defunct = 1; diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c index 8070f3fd98f0..7d4da9e605ef 100644 --- a/drivers/ptp/ptp_pch.c +++ b/drivers/ptp/ptp_pch.c @@ -10,9 +10,10 @@ #include <linux/device.h> #include <linux/err.h> -#include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/io-64-nonatomic-hi-lo.h> #include <linux/irq.h> #include <linux/kernel.h> #include <linux/module.h> @@ -100,7 +101,6 @@ struct pch_ts_regs { #define PCH_ECS_ETH (1 << 0) #define PCH_ECS_CAN (1 << 1) -#define PCH_STATION_BYTES 6 #define PCH_IEEE1588_ETH (1 << 0) #define PCH_IEEE1588_CAN (1 << 1) @@ -115,8 +115,6 @@ struct pch_dev { int exts0_enabled; int exts1_enabled; - u32 mem_base; - u32 mem_size; u32 irq; struct pci_dev *pdev; spinlock_t register_lock; @@ -148,28 +146,15 @@ static inline void pch_eth_enable_set(struct pch_dev *chip) static u64 pch_systime_read(struct pch_ts_regs __iomem *regs) { u64 ns; - u32 lo, hi; - lo = ioread32(®s->systime_lo); - hi = ioread32(®s->systime_hi); + ns = ioread64_lo_hi(®s->systime_lo); - ns = ((u64) hi) << 32; - ns |= lo; - ns <<= TICKS_NS_SHIFT; - - return ns; + return ns << TICKS_NS_SHIFT; } static void pch_systime_write(struct pch_ts_regs __iomem *regs, u64 ns) { - u32 hi, lo; - - ns >>= TICKS_NS_SHIFT; - hi = ns >> 32; - lo = ns & 0xffffffff; - - iowrite32(lo, ®s->systime_lo); - iowrite32(hi, ®s->systime_hi); + iowrite64_lo_hi(ns >> TICKS_NS_SHIFT, ®s->systime_lo); } static inline void pch_block_reset(struct pch_dev *chip) @@ -235,16 +220,10 @@ u64 pch_rx_snap_read(struct pci_dev *pdev) { struct pch_dev *chip = pci_get_drvdata(pdev); u64 ns; - u32 lo, hi; - lo = ioread32(&chip->regs->rx_snap_lo); - hi = ioread32(&chip->regs->rx_snap_hi); + ns = ioread64_lo_hi(&chip->regs->rx_snap_lo); - ns = ((u64) hi) << 32; - ns |= lo; - ns <<= TICKS_NS_SHIFT; - - return ns; + return ns << TICKS_NS_SHIFT; } EXPORT_SYMBOL(pch_rx_snap_read); @@ -252,16 +231,10 @@ u64 pch_tx_snap_read(struct pci_dev *pdev) { struct pch_dev *chip = pci_get_drvdata(pdev); u64 ns; - u32 lo, hi; - - lo = ioread32(&chip->regs->tx_snap_lo); - hi = ioread32(&chip->regs->tx_snap_hi); - ns = ((u64) hi) << 32; - ns |= lo; - ns <<= TICKS_NS_SHIFT; + ns = ioread64_lo_hi(&chip->regs->tx_snap_lo); - return ns; + return ns << TICKS_NS_SHIFT; } EXPORT_SYMBOL(pch_tx_snap_read); @@ -292,8 +265,9 @@ static void pch_reset(struct pch_dev *chip) */ int pch_set_station_address(u8 *addr, struct pci_dev *pdev) { - s32 i; struct pch_dev *chip = pci_get_drvdata(pdev); + bool valid; + u64 mac; /* Verify the parameter */ if ((chip->regs == NULL) || addr == (u8 *)NULL) { @@ -301,37 +275,15 @@ int pch_set_station_address(u8 *addr, struct pci_dev *pdev) "invalid params returning PCH_INVALIDPARAM\n"); return PCH_INVALIDPARAM; } - /* For all station address bytes */ - for (i = 0; i < PCH_STATION_BYTES; i++) { - u32 val; - s32 tmp; - - tmp = hex_to_bin(addr[i * 3]); - if (tmp < 0) { - dev_err(&pdev->dev, - "invalid params returning PCH_INVALIDPARAM\n"); - return PCH_INVALIDPARAM; - } - val = tmp * 16; - tmp = hex_to_bin(addr[(i * 3) + 1]); - if (tmp < 0) { - dev_err(&pdev->dev, - "invalid params returning PCH_INVALIDPARAM\n"); - return PCH_INVALIDPARAM; - } - val += tmp; - /* Expects ':' separated addresses */ - if ((i < 5) && (addr[(i * 3) + 2] != ':')) { - dev_err(&pdev->dev, - "invalid params returning PCH_INVALIDPARAM\n"); - return PCH_INVALIDPARAM; - } - /* Ideally we should set the address only after validating - entire string */ - dev_dbg(&pdev->dev, "invoking pch_station_set\n"); - iowrite32(val, &chip->regs->ts_st[i]); + valid = mac_pton(addr, (u8 *)&mac); + if (!valid) { + dev_err(&pdev->dev, "invalid params returning PCH_INVALIDPARAM\n"); + return PCH_INVALIDPARAM; } + + dev_dbg(&pdev->dev, "invoking pch_station_set\n"); + iowrite64_lo_hi(mac, &chip->regs->ts_st); return 0; } EXPORT_SYMBOL(pch_set_station_address); @@ -344,19 +296,16 @@ static irqreturn_t isr(int irq, void *priv) struct pch_dev *pch_dev = priv; struct pch_ts_regs __iomem *regs = pch_dev->regs; struct ptp_clock_event event; - u32 ack = 0, lo, hi, val; + u32 ack = 0, val; val = ioread32(®s->event); if (val & PCH_TSE_SNS) { ack |= PCH_TSE_SNS; if (pch_dev->exts0_enabled) { - hi = ioread32(®s->asms_hi); - lo = ioread32(®s->asms_lo); event.type = PTP_CLOCK_EXTTS; event.index = 0; - event.timestamp = ((u64) hi) << 32; - event.timestamp |= lo; + event.timestamp = ioread64_hi_lo(®s->asms_hi); event.timestamp <<= TICKS_NS_SHIFT; ptp_clock_event(pch_dev->ptp_clock, &event); } @@ -365,12 +314,9 @@ static irqreturn_t isr(int irq, void *priv) if (val & PCH_TSE_SNM) { ack |= PCH_TSE_SNM; if (pch_dev->exts1_enabled) { - hi = ioread32(®s->amms_hi); - lo = ioread32(®s->amms_lo); event.type = PTP_CLOCK_EXTTS; event.index = 1; - event.timestamp = ((u64) hi) << 32; - event.timestamp |= lo; + event.timestamp = ioread64_hi_lo(®s->asms_hi); event.timestamp <<= TICKS_NS_SHIFT; ptp_clock_event(pch_dev->ptp_clock, &event); } @@ -501,31 +447,12 @@ static const struct ptp_clock_info ptp_pch_caps = { .enable = ptp_pch_enable, }; -#define pch_suspend NULL -#define pch_resume NULL - static void pch_remove(struct pci_dev *pdev) { struct pch_dev *chip = pci_get_drvdata(pdev); + free_irq(pdev->irq, chip); ptp_clock_unregister(chip->ptp_clock); - /* free the interrupt */ - if (pdev->irq != 0) - free_irq(pdev->irq, chip); - - /* unmap the virtual IO memory space */ - if (chip->regs != NULL) { - iounmap(chip->regs); - chip->regs = NULL; - } - /* release the reserved IO memory space */ - if (chip->mem_base != 0) { - release_mem_region(chip->mem_base, chip->mem_size); - chip->mem_base = 0; - } - pci_disable_device(pdev); - kfree(chip); - dev_info(&pdev->dev, "complete\n"); } static s32 @@ -535,50 +462,29 @@ pch_probe(struct pci_dev *pdev, const struct pci_device_id *id) unsigned long flags; struct pch_dev *chip; - chip = kzalloc(sizeof(struct pch_dev), GFP_KERNEL); + chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL); if (chip == NULL) return -ENOMEM; /* enable the 1588 pci device */ - ret = pci_enable_device(pdev); + ret = pcim_enable_device(pdev); if (ret != 0) { dev_err(&pdev->dev, "could not enable the pci device\n"); - goto err_pci_en; + return ret; } - chip->mem_base = pci_resource_start(pdev, IO_MEM_BAR); - if (!chip->mem_base) { + ret = pcim_iomap_regions(pdev, BIT(IO_MEM_BAR), "1588_regs"); + if (ret) { dev_err(&pdev->dev, "could not locate IO memory address\n"); - ret = -ENODEV; - goto err_pci_start; - } - - /* retrieve the available length of the IO memory space */ - chip->mem_size = pci_resource_len(pdev, IO_MEM_BAR); - - /* allocate the memory for the device registers */ - if (!request_mem_region(chip->mem_base, chip->mem_size, "1588_regs")) { - dev_err(&pdev->dev, - "could not allocate register memory space\n"); - ret = -EBUSY; - goto err_req_mem_region; + return ret; } /* get the virtual address to the 1588 registers */ - chip->regs = ioremap(chip->mem_base, chip->mem_size); - - if (!chip->regs) { - dev_err(&pdev->dev, "Could not get virtual address\n"); - ret = -ENOMEM; - goto err_ioremap; - } - + chip->regs = pcim_iomap_table(pdev)[IO_MEM_BAR]; chip->caps = ptp_pch_caps; chip->ptp_clock = ptp_clock_register(&chip->caps, &pdev->dev); - if (IS_ERR(chip->ptp_clock)) { - ret = PTR_ERR(chip->ptp_clock); - goto err_ptp_clock_reg; - } + if (IS_ERR(chip->ptp_clock)) + return PTR_ERR(chip->ptp_clock); spin_lock_init(&chip->register_lock); @@ -598,8 +504,7 @@ pch_probe(struct pci_dev *pdev, const struct pci_device_id *id) pch_reset(chip); iowrite32(DEFAULT_ADDEND, &chip->regs->addend); - iowrite32(1, &chip->regs->trgt_lo); - iowrite32(0, &chip->regs->trgt_hi); + iowrite64_lo_hi(1, &chip->regs->trgt_lo); iowrite32(PCH_TSE_TTIPEND, &chip->regs->event); pch_eth_enable_set(chip); @@ -617,21 +522,7 @@ pch_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_req_irq: ptp_clock_unregister(chip->ptp_clock); -err_ptp_clock_reg: - iounmap(chip->regs); - chip->regs = NULL; -err_ioremap: - release_mem_region(chip->mem_base, chip->mem_size); - -err_req_mem_region: - chip->mem_base = 0; - -err_pci_start: - pci_disable_device(pdev); - -err_pci_en: - kfree(chip); dev_err(&pdev->dev, "probe failed(ret=0x%x)\n", ret); return ret; @@ -646,33 +537,13 @@ static const struct pci_device_id pch_ieee1588_pcidev_id[] = { }; MODULE_DEVICE_TABLE(pci, pch_ieee1588_pcidev_id); -static SIMPLE_DEV_PM_OPS(pch_pm_ops, pch_suspend, pch_resume); - static struct pci_driver pch_driver = { .name = KBUILD_MODNAME, .id_table = pch_ieee1588_pcidev_id, .probe = pch_probe, .remove = pch_remove, - .driver.pm = &pch_pm_ops, }; - -static void __exit ptp_pch_exit(void) -{ - pci_unregister_driver(&pch_driver); -} - -static s32 __init ptp_pch_init(void) -{ - s32 ret; - - /* register the driver with the pci core */ - ret = pci_register_driver(&pch_driver); - - return ret; -} - -module_init(ptp_pch_init); -module_exit(ptp_pch_exit); +module_pci_driver(pch_driver); module_param_string(station, pch_param.station, sizeof(pch_param.station), 0444); diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 41b92dc2f011..9233bfedeb17 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -14,7 +14,7 @@ static ssize_t clock_name_show(struct device *dev, struct device_attribute *attr, char *page) { struct ptp_clock *ptp = dev_get_drvdata(dev); - return snprintf(page, PAGE_SIZE-1, "%s\n", ptp->info->name); + return sysfs_emit(page, "%s\n", ptp->info->name); } static DEVICE_ATTR_RO(clock_name); @@ -387,7 +387,7 @@ static ssize_t ptp_pin_show(struct device *dev, struct device_attribute *attr, mutex_unlock(&ptp->pincfg_mux); - return snprintf(page, PAGE_SIZE, "%u %u\n", func, chan); + return sysfs_emit(page, "%u %u\n", func, chan); } static ssize_t ptp_pin_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index ab1d233173e1..cb179a3ea508 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -57,6 +57,30 @@ static int ptp_vclock_gettime(struct ptp_clock_info *ptp, return 0; } +static int ptp_vclock_gettimex(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + struct ptp_clock *pptp = vclock->pclock; + struct timespec64 pts; + unsigned long flags; + int err; + u64 ns; + + err = pptp->info->gettimex64(pptp->info, &pts, sts); + if (err) + return err; + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_cyc2time(&vclock->tc, timespec64_to_ns(&pts)); + spin_unlock_irqrestore(&vclock->lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + static int ptp_vclock_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts) { @@ -71,6 +95,28 @@ static int ptp_vclock_settime(struct ptp_clock_info *ptp, return 0; } +static int ptp_vclock_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *xtstamp) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + struct ptp_clock *pptp = vclock->pclock; + unsigned long flags; + int err; + u64 ns; + + err = pptp->info->getcrosststamp(pptp->info, xtstamp); + if (err) + return err; + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_cyc2time(&vclock->tc, ktime_to_ns(xtstamp->device)); + spin_unlock_irqrestore(&vclock->lock, flags); + + xtstamp->device = ns_to_ktime(ns); + + return 0; +} + static long ptp_vclock_refresh(struct ptp_clock_info *ptp) { struct ptp_vclock *vclock = info_to_vclock(ptp); @@ -84,11 +130,9 @@ static long ptp_vclock_refresh(struct ptp_clock_info *ptp) static const struct ptp_clock_info ptp_vclock_info = { .owner = THIS_MODULE, .name = "ptp virtual clock", - /* The maximum ppb value that long scaled_ppm can support */ - .max_adj = 32767999, + .max_adj = 500000000, .adjfine = ptp_vclock_adjfine, .adjtime = ptp_vclock_adjtime, - .gettime64 = ptp_vclock_gettime, .settime64 = ptp_vclock_settime, .do_aux_work = ptp_vclock_refresh, }; @@ -124,6 +168,12 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) vclock->pclock = pclock; vclock->info = ptp_vclock_info; + if (pclock->info->gettimex64) + vclock->info.gettimex64 = ptp_vclock_gettimex; + else + vclock->info.gettime64 = ptp_vclock_gettime; + if (pclock->info->getcrosststamp) + vclock->info.getcrosststamp = ptp_vclock_getcrosststamp; vclock->cc = ptp_vclock_cc; snprintf(vclock->info.name, PTP_CLOCK_NAME_LEN, "ptp%d_virt", diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c index 058b78fac5e3..0a3fb6c115f4 100644 --- a/drivers/soc/fsl/dpio/qbman-portal.c +++ b/drivers/soc/fsl/dpio/qbman-portal.c @@ -743,8 +743,8 @@ int qbman_swp_enqueue_multiple_mem_back(struct qbman_swp *s, full_mask = s->eqcr.pi_ci_mask; if (!s->eqcr.available) { eqcr_ci = s->eqcr.ci; - p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK; - s->eqcr.ci = *p & full_mask; + s->eqcr.ci = qbman_read_register(s, QBMAN_CINH_SWP_EQCR_CI); + s->eqcr.ci &= full_mask; s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size, eqcr_ci, s->eqcr.ci); if (!s->eqcr.available) { @@ -887,8 +887,8 @@ int qbman_swp_enqueue_multiple_desc_mem_back(struct qbman_swp *s, full_mask = s->eqcr.pi_ci_mask; if (!s->eqcr.available) { eqcr_ci = s->eqcr.ci; - p = s->addr_cena + QBMAN_CENA_SWP_EQCR_CI_MEMBACK; - s->eqcr.ci = *p & full_mask; + s->eqcr.ci = qbman_read_register(s, QBMAN_CINH_SWP_EQCR_CI); + s->eqcr.ci &= full_mask; s->eqcr.available = qm_cyc_diff(s->eqcr.pi_ring_size, eqcr_ci, s->eqcr.ci); if (!s->eqcr.available) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index b525d8cdc25b..88a51b242adc 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -8,6 +8,7 @@ #include <linux/jump_label.h> #include <linux/percpu.h> #include <linux/rbtree.h> +#include <net/sock.h> #include <uapi/linux/bpf.h> struct sock; @@ -165,11 +166,23 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags); +/* Opportunistic check to see whether we have any BPF program attached*/ +static inline bool cgroup_bpf_sock_enabled(struct sock *sk, + enum cgroup_bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog_array *array; + + array = rcu_access_pointer(cgrp->bpf.effective[type]); + return array != &bpf_empty_prog_array.hdr; +} + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_INET_INGRESS)) \ + if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) && \ + cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ CGROUP_INET_INGRESS); \ \ @@ -181,7 +194,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk)) \ + if (sk_fullsock(__sk) && \ + cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ } \ @@ -347,7 +361,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -367,7 +382,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fa517ae604ad..2fc7e5c5ef41 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -194,6 +194,17 @@ struct bpf_map { struct work_struct work; struct mutex freeze_mutex; atomic64_t writecnt; + /* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + } owner; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -321,7 +332,10 @@ enum bpf_type_flag { */ MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_ALLOC, + /* MEM is in user address space. */ + MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_USER, }; /* Max number of base types. */ @@ -577,8 +591,7 @@ struct bpf_verifier_ops { const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); + u32 *next_btf_id, enum bpf_type_flag *flag); }; struct bpf_prog_offload_ops { @@ -833,8 +846,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); -int bpf_jit_charge_modmem(u32 pages); -void bpf_jit_uncharge_modmem(u32 pages); +int bpf_jit_charge_modmem(u32 size); +void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, @@ -939,6 +952,8 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; + bool xdp_has_frags; + bool use_bpf_prog_pack; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; @@ -999,16 +1014,6 @@ struct bpf_prog_aux { }; struct bpf_array_aux { - /* 'Ownership' of prog array is claimed by the first program that - * is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have - * the same prog type and JITed flag. - */ - struct { - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; @@ -1183,7 +1188,14 @@ struct bpf_event_entry { struct rcu_head rcu; }; -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +static inline bool map_type_contains_progs(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_CPUMAP; +} + +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -1225,6 +1237,19 @@ struct bpf_prog_array { struct bpf_prog_array_item items[]; }; +struct bpf_empty_prog_array { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +}; + +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'bpf_empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +extern struct bpf_empty_prog_array bpf_empty_prog_array; + struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); @@ -1251,6 +1276,7 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; + int retval; }; struct bpf_trace_run_ctx { @@ -1283,19 +1309,19 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, - u32 *ret_flags) + int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; u32 func_ret; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1304,27 +1330,29 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - ret &= (func_ret & 1); + if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) + const void *ctx, bpf_prog_run_fn run_prog, + int retval) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1332,13 +1360,14 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - ret &= run_prog(prog, ctx); + if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline u32 @@ -1391,19 +1420,21 @@ out: * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped + * 3: -err skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ - if (_ret) \ + if (_ret && !IS_ERR_VALUE((long)_ret)) \ + _ret = -EFAULT; \ + if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret = (_cn ? NET_XMIT_DROP : _ret); \ _ret; \ }) @@ -1724,7 +1755,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1754,7 +1784,7 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); + u32 *next_btf_id, enum bpf_type_flag *flag); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id); @@ -1862,11 +1892,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } -static inline bool dev_map_can_have_prog(struct bpf_map *map) -{ - return false; -} - static inline void __dev_flush(void) { } @@ -1930,11 +1955,6 @@ static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, return -EOPNOTSUPP; } -static inline bool cpu_map_prog_allowed(struct bpf_map *map) -{ - return false; -} - static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { @@ -1976,12 +1996,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, - struct module *owner) -{ - return false; -} - static inline void bpf_map_put(struct bpf_map *map) { } @@ -2076,6 +2090,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -2129,6 +2146,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } + +static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ @@ -2227,6 +2250,7 @@ extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_strncmp_proto; +extern const struct bpf_func_proto bpf_copy_from_user_task_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2339,6 +2363,8 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void *bpf_arch_text_copy(void *dst, void *src, size_t len); + struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e9993172f892..7a7be8c057f2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -521,6 +521,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); @@ -564,4 +566,9 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 0c74348cbc9d..36bc09b8e890 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -12,11 +12,33 @@ #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) +enum btf_kfunc_type { + BTF_KFUNC_TYPE_CHECK, + BTF_KFUNC_TYPE_ACQUIRE, + BTF_KFUNC_TYPE_RELEASE, + BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_MAX, +}; + struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; +struct btf_id_set; + +struct btf_kfunc_id_set { + struct module *owner; + union { + struct { + struct btf_id_set *check_set; + struct btf_id_set *acquire_set; + struct btf_id_set *release_set; + struct btf_id_set *ret_null_set; + }; + struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; + }; +}; extern const struct file_operations btf_fops; @@ -216,6 +238,11 @@ static inline bool btf_type_is_var(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; } +static inline bool btf_type_is_type_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG; +} + /* union is only a special case of struct: * all its offsetof(member) == 0 */ @@ -300,6 +327,11 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo( return (const struct btf_var_secinfo *)(t + 1); } +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + #ifdef CONFIG_BPF_SYSCALL struct bpf_prog; @@ -307,6 +339,11 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id); +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -318,50 +355,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf, { return NULL; } -#endif - -struct kfunc_btf_id_set { - struct list_head list; - struct btf_id_set *set; - struct module *owner; -}; - -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner); - -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; -#else -static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static inline bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, + u32 kfunc_btf_id) { + return false; } -static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, - u32 kfunc_id, struct module *owner) +static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s) { - return false; + return 0; } - -static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; -static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; #endif -#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ - struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ - THIS_MODULE } - #endif diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 919c0fde1c51..bc5d9cc34e4c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -11,6 +11,7 @@ struct btf_id_set { #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ +#include <linux/compiler_attributes.h> /* for __maybe_unused */ /* * Following macros help to define lists of BTF IDs placed @@ -146,14 +147,14 @@ extern struct btf_id_set name; #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3c1795fdb568..3f31ff400432 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -31,6 +31,9 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __kernel # ifdef STRUCTLEAK_PLUGIN # define __user __attribute__((user)) +# elif defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ + __has_attribute(btf_type_tag) +# define __user __attribute__((btf_type_tag("user"))) # else # define __user # endif diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h new file mode 100644 index 000000000000..4359fb0221cf --- /dev/null +++ b/include/linux/dsa/tag_qca.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __TAG_QCA_H +#define __TAG_QCA_H + +#define QCA_HDR_LEN 2 +#define QCA_HDR_VERSION 0x2 + +#define QCA_HDR_RECV_VERSION GENMASK(15, 14) +#define QCA_HDR_RECV_PRIORITY GENMASK(13, 11) +#define QCA_HDR_RECV_TYPE GENMASK(10, 6) +#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) +#define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0) + +/* Packet type for recv */ +#define QCA_HDR_RECV_TYPE_NORMAL 0x0 +#define QCA_HDR_RECV_TYPE_MIB 0x1 +#define QCA_HDR_RECV_TYPE_RW_REG_ACK 0x2 + +#define QCA_HDR_XMIT_VERSION GENMASK(15, 14) +#define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11) +#define QCA_HDR_XMIT_CONTROL GENMASK(10, 8) +#define QCA_HDR_XMIT_FROM_CPU BIT(7) +#define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0) + +/* Packet type for xmit */ +#define QCA_HDR_XMIT_TYPE_NORMAL 0x0 +#define QCA_HDR_XMIT_TYPE_RW_REG 0x1 + +/* Check code for a valid mgmt packet. Switch will ignore the packet + * with this wrong. + */ +#define QCA_HDR_MGMT_CHECK_CODE_VAL 0x5 + +/* Specific define for in-band MDIO read/write with Ethernet packet */ +#define QCA_HDR_MGMT_SEQ_LEN 4 /* 4 byte for the seq */ +#define QCA_HDR_MGMT_COMMAND_LEN 4 /* 4 byte for the command */ +#define QCA_HDR_MGMT_DATA1_LEN 4 /* First 4 byte for the mdio data */ +#define QCA_HDR_MGMT_HEADER_LEN (QCA_HDR_MGMT_SEQ_LEN + \ + QCA_HDR_MGMT_COMMAND_LEN + \ + QCA_HDR_MGMT_DATA1_LEN) + +#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */ +#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */ + +#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \ + QCA_HDR_LEN + \ + QCA_HDR_MGMT_DATA2_LEN + \ + QCA_HDR_MGMT_PADDING_LEN) + +#define QCA_HDR_MGMT_SEQ_NUM GENMASK(31, 0) /* 63, 32 */ +#define QCA_HDR_MGMT_CHECK_CODE GENMASK(31, 29) /* 31, 29 */ +#define QCA_HDR_MGMT_CMD BIT(28) /* 28 */ +#define QCA_HDR_MGMT_LENGTH GENMASK(23, 20) /* 23, 20 */ +#define QCA_HDR_MGMT_ADDR GENMASK(18, 0) /* 18, 0 */ + +/* Special struct emulating a Ethernet header */ +struct qca_mgmt_ethhdr { + u32 command; /* command bit 31:0 */ + u32 seq; /* seq 63:32 */ + u32 mdio_data; /* first 4byte mdio */ + __be16 hdr; /* qca hdr */ +} __packed; + +enum mdio_cmd { + MDIO_WRITE = 0x0, + MDIO_READ +}; + +struct mib_ethhdr { + u32 data[3]; /* first 3 mib counter */ + __be16 hdr; /* qca hdr */ +} __packed; + +struct qca_tagger_data { + void (*rw_reg_ack_handler)(struct dsa_switch *ds, + struct sk_buff *skb); + void (*mib_autocast_handler)(struct dsa_switch *ds, + struct sk_buff *skb); +}; + +#endif /* __TAG_QCA_H */ diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad71cc90b37..92b10e67d5f8 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -134,7 +134,7 @@ static inline bool is_multicast_ether_addr(const u8 *addr) #endif } -static inline bool is_multicast_ether_addr_64bits(const u8 addr[6+2]) +static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN @@ -372,8 +372,7 @@ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ -static inline bool ether_addr_equal_64bits(const u8 addr1[6+2], - const u8 addr2[6+2]) +static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 11efc45de66a..e0853f48b75e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -70,9 +70,11 @@ enum { /** * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. + * @tcp_data_split: Scatter packet headers and data to separate buffers */ struct kernel_ethtool_ringparam { u32 rx_buf_len; + u8 tcp_data_split; }; /** diff --git a/include/linux/filter.h b/include/linux/filter.h index 71fa57b88bfc..1cb1af917617 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,7 +548,7 @@ struct sock_fprog_kern { #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { - u32 pages; + u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; @@ -886,17 +886,8 @@ static inline void bpf_prog_lock_ro(struct bpf_prog *fp) static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_ro((unsigned long)hdr, hdr->pages); - set_memory_x((unsigned long)hdr, hdr->pages); -} - -static inline struct bpf_binary_header * -bpf_jit_binary_hdr(const struct bpf_prog *fp) -{ - unsigned long real_start = (unsigned long)fp->bpf_func; - unsigned long addr = real_start & PAGE_MASK; - - return (void *)addr; + set_memory_ro((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + set_memory_x((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -1068,6 +1059,18 @@ void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); +struct bpf_binary_header * +bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, + unsigned int alignment, + struct bpf_binary_header **rw_hdr, + u8 **rw_image, + bpf_jit_fill_hole_t bpf_fill_ill_insns); +int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, + struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); +void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); + int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); @@ -1356,7 +1359,10 @@ struct bpf_sockopt_kern { s32 level; s32 optname; s32 optlen; - s32 retval; + /* for retval in struct bpf_cg_run_ctx */ + struct task_struct *current_task; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 559b6c644938..60ee7b3f58e7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2427,7 +2427,7 @@ struct ieee80211_tx_pwr_env { static inline u8 ieee80211_he_oper_size(const u8 *he_oper_ie) { - struct ieee80211_he_operation *he_oper = (void *)he_oper_ie; + const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; u8 oper_len = sizeof(struct ieee80211_he_operation); u32 he_oper_params; @@ -2460,7 +2460,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { - const u8 *ret = (void *)&he_oper->optional; + const u8 *ret = (const void *)&he_oper->optional; u32 he_oper_params; if (!he_oper) @@ -2475,7 +2475,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) ret++; - return (void *)ret; + return (const void *)ret; } /* HE Spatial Reuse defines */ @@ -2496,7 +2496,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) static inline u8 ieee80211_he_spr_size(const u8 *he_spr_ie) { - struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; + const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; u8 spr_len = sizeof(struct ieee80211_he_spr); u8 he_spr_params; diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a59d25f19385..16870f86c74d 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -51,7 +51,7 @@ struct ipv6_devconf { __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - __s32 mc_forwarding; + atomic_t mc_forwarding; #endif __s32 disable_ipv6; __s32 drop_unicast_in_l2_multicast; @@ -371,19 +371,12 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) return NULL; } -static inline struct inet6_request_sock * - inet6_rsk(const struct request_sock *rsk) -{ - return NULL; -} - static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL -#define tcp_twsk_ipv6only(__sk) 0 #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index f8397f300fcd..15e0e0209da4 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -66,11 +66,6 @@ static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, linkmode_clear_bit(nr, addr); } -static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) -{ - __change_bit(nr, addr); -} - static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); diff --git a/include/linux/mii.h b/include/linux/mii.h index 12ea29e04293..5ee13083cec7 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -355,56 +355,6 @@ static inline u32 mii_adv_to_ethtool_adv_x(u32 adv) } /** - * mii_lpa_mod_linkmode_adv_sgmii - * @lp_advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_LPA bits to - * linkmode advertisement settings for SGMII. - * Leaves other bits unchanged. - */ -static inline void -mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) -{ - u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10FULL); -} - -/** - * mii_lpa_to_linkmode_adv_sgmii - * @advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings when in SGMII mode. - * Clears the old value of advertising. - */ -static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising, - u32 lpa) -{ - linkmode_zero(lp_advertising); - - mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa); -} - -/** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. * @adv: value of the MII_ADVERTISE register diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..27145c4d6820 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -64,13 +64,6 @@ enum { }; enum { - MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, - MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, - MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, - MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 -}; - -enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 6b3267b49755..ed42bd5f639f 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -26,11 +26,6 @@ struct i40e_client_version { u8 rsvd; }; -enum i40e_client_state { - __I40E_CLIENT_NULL, - __I40E_CLIENT_REGISTERED -}; - enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_NONE, __I40E_CLIENT_INSTANCE_OPENED, @@ -190,11 +185,6 @@ struct i40e_client { const struct i40e_client_ops *ops; /* client ops provided by the client */ }; -static inline bool i40e_client_is_registered(struct i40e_client *client) -{ - return test_bit(__I40E_CLIENT_REGISTERED, &client->state); -} - void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); void i40e_client_device_unregister(struct i40e_info *ldev); diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h index 1289593411d3..1c1332e4df26 100644 --- a/include/linux/net/intel/iidc.h +++ b/include/linux/net/intel/iidc.h @@ -32,6 +32,8 @@ enum iidc_rdma_protocol { }; #define IIDC_MAX_USER_PRIORITY 8 +#define IIDC_MAX_DSCP_MAPPING 64 +#define IIDC_DSCP_PFC_MODE 0x1 /* Struct to hold per RDMA Qset info */ struct iidc_rdma_qset_params { @@ -60,6 +62,8 @@ struct iidc_qos_params { u8 vport_relative_bw; u8 vport_priority_type; u8 num_tc; + u8 pfc_mode; + u8 dscp_map[IIDC_MAX_DSCP_MAPPING]; }; struct iidc_event { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8b5a314db167..93fc680b658f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1948,6 +1948,8 @@ enum netdev_ml_priv_type { * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. * @watchdog_dev_tracker: refcount tracker used by watchdog. + * @dev_registered_tracker: tracker for reference held while + * registered * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2282,6 +2284,7 @@ struct net_device { u8 dev_addr_shadow[MAX_ADDR_LEN]; netdevice_tracker linkwatch_dev_tracker; netdevice_tracker watchdog_dev_tracker; + netdevice_tracker dev_registered_tracker; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -3669,8 +3672,18 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); -int netif_rx_ni(struct sk_buff *skb); -int netif_rx_any_context(struct sk_buff *skb); +int __netif_rx(struct sk_buff *skb); + +static inline int netif_rx_ni(struct sk_buff *skb) +{ + return netif_rx(skb); +} + +static inline int netif_rx_any_context(struct sk_buff *skb) +{ + return netif_rx(skb); +} + int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list_internal(struct list_head *head); @@ -3817,14 +3830,7 @@ extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); -/** - * dev_put - release reference to device - * @dev: network device - * - * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. - */ -static inline void dev_put(struct net_device *dev) +static inline void __dev_put(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3835,14 +3841,7 @@ static inline void dev_put(struct net_device *dev) } } -/** - * dev_hold - get reference to device - * @dev: network device - * - * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. - */ -static inline void dev_hold(struct net_device *dev) +static inline void __dev_hold(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3853,11 +3852,24 @@ static inline void dev_hold(struct net_device *dev) } } +static inline void __netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, + gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +/* netdev_tracker_alloc() can upgrade a prior untracked reference + * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. + */ static inline void netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER - ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); + refcount_dec(&dev->refcnt_tracker.no_tracker); + __netdev_tracker_alloc(dev, tracker, gfp); #endif } @@ -3873,8 +3885,8 @@ static inline void dev_hold_track(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { if (dev) { - dev_hold(dev); - netdev_tracker_alloc(dev, tracker, gfp); + __dev_hold(dev); + __netdev_tracker_alloc(dev, tracker, gfp); } } @@ -3883,10 +3895,34 @@ static inline void dev_put_track(struct net_device *dev, { if (dev) { netdev_tracker_free(dev, tracker); - dev_put(dev); + __dev_put(dev); } } +/** + * dev_hold - get reference to device + * @dev: network device + * + * Hold reference to device to keep it from being freed. + * Try using dev_hold_track() instead. + */ +static inline void dev_hold(struct net_device *dev) +{ + dev_hold_track(dev, NULL, GFP_ATOMIC); +} + +/** + * dev_put - release reference to device + * @dev: network device + * + * Release reference to device to allow it to be freed. + * Try using dev_put_track() instead. + */ +static inline void dev_put(struct net_device *dev) +{ + dev_put_track(dev, NULL); +} + static inline void dev_replace_track(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, @@ -3895,11 +3931,11 @@ static inline void dev_replace_track(struct net_device *odev, if (odev) netdev_tracker_free(odev, tracker); - dev_hold(ndev); - dev_put(odev); + __dev_hold(ndev); + __dev_put(odev); if (ndev) - netdev_tracker_alloc(ndev, tracker, gfp); + __netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 15e71bfff726..c2c6f332fb90 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -379,6 +379,7 @@ struct nf_nat_hook { unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir); + void (*remove_nat_bysrc)(struct nf_conn *ct); }; extern const struct nf_nat_hook __rcu *nf_nat_hook; diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index a28aa289afdc..c3bdb4370938 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -300,26 +300,22 @@ union pptp_ctrl_union { struct PptpSetLinkInfo setlink; }; -extern int -(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern int -(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern void -(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *exp_orig, - struct nf_conntrack_expect *exp_reply); - -extern void -(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, - struct nf_conntrack_expect *exp); +struct nf_nat_pptp_hook { + int (*outbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + int (*inbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + void (*exp_gre)(struct nf_conntrack_expect *exp_orig, + struct nf_conntrack_expect *exp_reply); + void (*expectfn)(struct nf_conn *ct, + struct nf_conntrack_expect *exp); +}; +extern const struct nf_nat_pptp_hook __rcu *nf_nat_pptp_hook; #endif /* _NF_CONNTRACK_PPTP_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1ec631838af9..bda1c385cffb 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -135,15 +135,6 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, extack->cookie_len = sizeof(cookie); } -static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, - u32 cookie) -{ - if (!extack) - return; - memcpy(extack->cookie, &cookie, sizeof(cookie)); - extack->cookie_len = sizeof(cookie); -} - void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index add077a81b21..266eb26fb029 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -31,8 +31,7 @@ void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, unsigned int mode); -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state); +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, diff --git a/include/linux/phy.h b/include/linux/phy.h index 6de8d7a90d78..cd08cf1a8b0d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1661,7 +1661,7 @@ int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 713a0c928b7c..cca149f78d35 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -582,7 +582,6 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); -void phylink_set_10g_modes(unsigned long *mask); void phylink_helper_basex_speed(struct phylink_link_state *state); void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index 60f3453be23e..9ca353ab712b 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -13,6 +13,8 @@ struct ref_tracker_dir { spinlock_t lock; unsigned int quarantine_avail; refcount_t untracked; + refcount_t no_tracker; + bool dead; struct list_head list; /* List of active trackers */ struct list_head quarantine; /* List of dead trackers */ #endif @@ -26,7 +28,9 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, INIT_LIST_HEAD(&dir->quarantine); spin_lock_init(&dir->lock); dir->quarantine_avail = quarantine_count; + dir->dead = false; refcount_set(&dir->untracked, 1); + refcount_set(&dir->no_tracker, 1); stack_depot_init(); } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8a636e678902..a5adbf6b51e8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,12 +314,38 @@ struct sk_buff; * used to translate the reason to string. */ enum skb_drop_reason { - SKB_DROP_REASON_NOT_SPECIFIED, - SKB_DROP_REASON_NO_SOCKET, - SKB_DROP_REASON_PKT_TOO_SMALL, - SKB_DROP_REASON_TCP_CSUM, - SKB_DROP_REASON_SOCKET_FILTER, - SKB_DROP_REASON_UDP_CSUM, + SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ + SKB_DROP_REASON_NO_SOCKET, /* socket not found */ + SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ + SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ + SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ + SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ + SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ + SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current + * host (interface is in promisc + * mode) + */ + SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ + SKB_DROP_REASON_IP_INHDR, /* there is something wrong with + * IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ + SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. + * see the document for rp_filter + * in ip-sysctl.rst for more + * information + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 + * is multicast, but L3 is + * unicast. + */ + SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ + SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ + SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ + SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as + * udp packet drop out of + * udp_memory_allocated. + */ SKB_DROP_REASON_MAX, }; @@ -557,6 +583,7 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; + unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ @@ -3898,11 +3925,6 @@ static inline ktime_t net_timedelta(ktime_t t) return ktime_sub(ktime_get_real(), t); } -static inline ktime_t net_invalid_timestamp(void) -{ - return 0; -} - static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 18a717fe62eb..fdb5375f0562 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,7 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - unsigned long copy; + DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the @@ -38,7 +38,6 @@ struct sk_msg_sg { */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; -static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -171,11 +170,6 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) -static inline void sk_msg_clear_meta(struct sk_msg *msg) -{ - memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); -} - static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); @@ -234,7 +228,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (test_bit(msg->sg.start, &msg->sg.copy)) { + if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -253,7 +247,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - __set_bit(msg->sg.end, &msg->sg.copy); + __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -262,9 +256,9 @@ static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) - __set_bit(i, &msg->sg.copy); + __set_bit(i, msg->sg.copy); else - __clear_bit(i, &msg->sg.copy); + __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; diff --git a/include/linux/socket.h b/include/linux/socket.h index 8ef26d89ef49..6f85f5d957ef 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -366,6 +366,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 15ba0df1ee0d..28c145a51e57 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -95,7 +95,7 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) struct ssb_gige *dev = pdev_to_ssb_gige(pdev); if (dev) return (dev->dev->bus->chip_id == 0x4785); - return 0; + return false; } /* Get the device MAC address */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 571f605bc91e..382af90320ac 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -88,6 +88,7 @@ struct svc_xprt { struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; + netns_tracker ns_tracker; const struct cred *xpt_cred; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..3cdc8d878d81 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -284,6 +284,7 @@ struct rpc_xprt { } stat; struct net *xprt_net; + netns_tracker ns_tracker; const char *servername; const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 78b91bb92f0d..1168302b7927 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -394,6 +394,7 @@ struct tcp_sock { bool is_mptcp; #endif #if IS_ENABLED(CONFIG_SMC) + bool (*smc_hs_congested)(const struct sock *sk); bool syn_smc; /* SYN includes SMC */ #endif diff --git a/include/linux/udp.h b/include/linux/udp.h index ae66dadd8543..254a2654400f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,11 +23,6 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } -static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) -{ - return (struct udphdr *)skb_inner_transport_header(skb); -} - #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) diff --git a/include/linux/uio.h b/include/linux/uio.h index 1198a2bfc9bf..739285fe5a2f 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -273,6 +273,23 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) i->count = count; } +static inline int +iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) +{ + size_t shorted = 0; + int npages; + + if (iov_iter_count(i) > max_bytes) { + shorted = iov_iter_count(i) - max_bytes; + iov_iter_truncate(i, max_bytes); + } + npages = iov_iter_npages(i, INT_MAX); + if (shorted) + iov_iter_reexpand(i, iov_iter_count(i) + shorted); + + return npages; +} + struct csum_state { __wsum csum; size_t off; diff --git a/include/linux/wwan.h b/include/linux/wwan.h index afb3334ec8c5..5ce2acf444fb 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -174,11 +174,13 @@ void wwan_unregister_ops(struct device *parent); #ifdef CONFIG_WWAN_DEBUGFS struct dentry *wwan_get_debugfs_dir(struct device *parent); +void wwan_put_debugfs_dir(struct dentry *dir); #else static inline struct dentry *wwan_get_debugfs_dir(struct device *parent) { return ERR_PTR(-ENODEV); } +static inline void wwan_put_debugfs_dir(struct dentry *dir) {} #endif #endif /* __WWAN_H */ diff --git a/include/net/ax25.h b/include/net/ax25.h index 8221af1811df..0f9790c455bb 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -187,18 +187,12 @@ typedef struct { typedef struct ax25_route { struct ax25_route *next; - refcount_t refcount; ax25_address callsign; struct net_device *dev; ax25_digi *digipeat; char ip_mode; } ax25_route; -static inline void ax25_hold_route(ax25_route *ax25_rt) -{ - refcount_inc(&ax25_rt->refcount); -} - void __ax25_put_route(ax25_route *ax25_rt); extern rwlock_t ax25_route_lock; @@ -213,12 +207,6 @@ static inline void ax25_route_lock_unuse(void) read_unlock(&ax25_route_lock); } -static inline void ax25_put_route(ax25_route *ax25_rt) -{ - if (refcount_dec_and_test(&ax25_rt->refcount)) - __ax25_put_route(ax25_rt); -} - typedef struct { char slave; /* slave_mode? */ struct timer_list slave_timer; /* timeout timer */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 586f69d084a2..f5caff1ddb29 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -258,6 +258,15 @@ struct adv_info { #define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F +struct monitored_device { + struct list_head list; + + bdaddr_t bdaddr; + __u8 addr_type; + __u16 handle; + bool notified; +}; + struct adv_pattern { struct list_head list; __u8 ad_type; @@ -294,6 +303,9 @@ struct adv_monitor { #define HCI_MAX_SHORT_NAME_LENGTH 10 +#define HCI_CONN_HANDLE_UNSET 0xffff +#define HCI_CONN_HANDLE_MAX 0x0eff + /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 @@ -591,6 +603,9 @@ struct hci_dev { struct delayed_work interleave_scan; + struct list_head monitored_devices; + bool advmon_pend_notify; + #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif @@ -1847,6 +1862,8 @@ void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status); +void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 107b25deae68..99266f7aebdc 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1104,3 +1104,19 @@ struct mgmt_ev_controller_resume { #define MGMT_WAKE_REASON_NON_BT_WAKE 0x0 #define MGMT_WAKE_REASON_UNEXPECTED 0x1 #define MGMT_WAKE_REASON_REMOTE_WAKE 0x2 + +#define MGMT_EV_ADV_MONITOR_DEVICE_FOUND 0x002f +struct mgmt_ev_adv_monitor_device_found { + __le16 monitor_handle; + struct mgmt_addr_info addr; + __s8 rssi; + __le32 flags; + __le16 eir_len; + __u8 eir[0]; +} __packed; + +#define MGMT_EV_ADV_MONITOR_DEVICE_LOST 0x0030 +struct mgmt_ev_adv_monitor_device_lost { + __le16 monitor_handle; + struct mgmt_addr_info addr; +} __packed; diff --git a/include/net/bonding.h b/include/net/bonding.h index 83cfd2d70247..7dead855a72d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -699,20 +699,6 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond, } /* Caller must hold rcu_read_lock() for read */ -static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond, - const u8 *mac) -{ - struct list_head *iter; - struct slave *tmp; - - bond_for_each_slave_rcu(bond, tmp, iter) - if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) - return tmp; - - return NULL; -} - -/* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) { struct list_head *iter; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d19e48f9fdc6..f6db085ff3df 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2604,7 +2604,7 @@ const struct element *ieee80211_bss_get_elem(struct cfg80211_bss *bss, u8 id); */ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) { - return (void *)ieee80211_bss_get_elem(bss, id); + return (const void *)ieee80211_bss_get_elem(bss, id); } @@ -5970,9 +5970,9 @@ cfg80211_find_ie_match(u8 eid, const u8 *ies, unsigned int len, (!match_len && match_offset))) return NULL; - return (void *)cfg80211_find_elem_match(eid, ies, len, - match, match_len, - match_offset ? + return (const void *)cfg80211_find_elem_match(eid, ies, len, + match, match_len, + match_offset ? match_offset - 2 : 0); } @@ -6099,7 +6099,7 @@ static inline const u8 * cfg80211_find_vendor_ie(unsigned int oui, int oui_type, const u8 *ies, unsigned int len) { - return (void *)cfg80211_find_vendor_elem(oui, oui_type, ies, len); + return (const void *)cfg80211_find_vendor_elem(oui, oui_type, ies, len); } /** diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 6ed07844eb24..833672d6fbe4 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -227,6 +227,16 @@ static inline void wpan_phy_net_set(struct wpan_phy *wpan_phy, struct net *net) write_pnet(&wpan_phy->_net, net); } +/** + * struct ieee802154_addr - IEEE802.15.4 device address + * @mode: Address mode from frame header. Can be one of: + * - @IEEE802154_ADDR_NONE + * - @IEEE802154_ADDR_SHORT + * - @IEEE802154_ADDR_LONG + * @pan_id: The PAN ID this address belongs to + * @short_addr: address if @mode is @IEEE802154_ADDR_SHORT + * @extended_addr: address if @mode is @IEEE802154_ADDR_LONG + */ struct ieee802154_addr { u8 mode; __le16 pan_id; diff --git a/include/net/dsa.h b/include/net/dsa.h index 85a5ba3772f5..1456313a1faa 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -278,6 +278,10 @@ struct dsa_port { u8 devlink_port_setup:1; + /* Master state bits, valid only on CPU ports */ + u8 master_admin_up:1; + u8 master_oper_up:1; + u8 setup:1; struct device_node *dn; @@ -308,6 +312,10 @@ struct dsa_port { struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; + + /* List of VLANs that CPU and DSA ports are members of. */ + struct mutex vlans_lock; + struct list_head vlans; }; /* TODO: ideally DSA ports would have a single dp->link_dp member, @@ -328,6 +336,12 @@ struct dsa_mac_addr { struct list_head list; }; +struct dsa_vlan { + u16 vid; + refcount_t refcount; + struct list_head list; +}; + struct dsa_switch { struct device *dev; @@ -478,6 +492,12 @@ static inline bool dsa_port_is_unused(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_UNUSED; } +static inline bool dsa_port_master_is_operational(struct dsa_port *dp) +{ + return dsa_port_is_cpu(dp) && dp->master_admin_up && + dp->master_oper_up; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; @@ -581,6 +601,24 @@ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) return port == dsa_upstream_port(ds, port); } +/* Return true if this is a DSA port leading away from the CPU */ +static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) +{ + return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); +} + +/* Return the local port used to reach the CPU port */ +static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) +{ + struct dsa_port *dp; + + dsa_switch_for_each_available_port(dp, ds) { + return dsa_upstream_port(ds, dp->index); + } + + return ds->num_ports; +} + /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. @@ -1036,6 +1074,13 @@ struct dsa_switch_ops { int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); + + /* + * DSA master tracking operations + */ + void (*master_state_change)(struct dsa_switch *ds, + const struct net_device *master, + bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ @@ -1247,7 +1292,7 @@ module_exit(dsa_tag_driver_module_exit) /** * module_dsa_tag_drivers() - Helper macro for registering DSA tag * drivers - * @__ops_array: Array of tag driver strucutres + * @__ops_array: Array of tag driver structures * * Helper macro for DSA tag drivers which do not do anything special * in module init/exit. Each module may only use this macro once, and diff --git a/include/net/gro.h b/include/net/gro.h index 8f75802d50fd..a765fedda5c4 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -29,46 +29,50 @@ struct napi_gro_cb { /* Number of segments aggregated. */ u16 count; - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; /* jiffies when first packet was created/queued */ unsigned long age; - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; + /* portion of the cb set to zero at every gro iteration */ + struct_group(zeroed, + + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; - /* Used in tunnel GRO receive */ - u8 encap_mark:1; + /* Used in tunnel GRO receive */ + u8 encap_mark:1; - /* GRO checksum is valid */ - u8 csum_valid:1; + /* GRO checksum is valid */ + u8 csum_valid:1; - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; - /* Free the skb? */ - u8 free:2; + /* Free the skb? */ + u8 free:2; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; + ); /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 11630351c978..598f53d2a3a0 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -1,6 +1,6 @@ /* * Copyright (c) 2017 Intel Deutschland GmbH - * Copyright (c) 2018-2019 Intel Corporation + * Copyright (c) 2018-2019, 2021 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -365,7 +365,7 @@ enum ieee80211_radiotap_zero_len_psdu_type { */ static inline u16 ieee80211_get_radiotap_len(const char *data) { - struct ieee80211_radiotap_header *hdr = (void *)data; + const struct ieee80211_radiotap_header *hdr = (const void *)data; return get_unaligned_le16(&hdr->it_len); } diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 4ad47d9f9d27..3908296d103f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -285,6 +285,14 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); +static inline unsigned long +reqsk_timeout(struct request_sock *req, unsigned long max_timeout) +{ + u64 timeout = (u64)req->timeout << req->num_timeout; + + return (unsigned long)min_t(u64, timeout, max_timeout); +} + static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ diff --git a/include/net/inet_dscp.h b/include/net/inet_dscp.h new file mode 100644 index 000000000000..72f250dffada --- /dev/null +++ b/include/net/inet_dscp.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * inet_dscp.h: helpers for handling differentiated services codepoints (DSCP) + * + * DSCP is defined in RFC 2474: + * + * 0 1 2 3 4 5 6 7 + * +---+---+---+---+---+---+---+---+ + * | DSCP | CU | + * +---+---+---+---+---+---+---+---+ + * + * DSCP: differentiated services codepoint + * CU: currently unused + * + * The whole DSCP + CU bits form the DS field. + * The DS field is also commonly called TOS or Traffic Class (for IPv6). + * + * Note: the CU bits are now used for Explicit Congestion Notification + * (RFC 3168). + */ + +#ifndef _INET_DSCP_H +#define _INET_DSCP_H + +#include <linux/types.h> + +/* Special type for storing DSCP values. + * + * A dscp_t variable stores a DS field with the CU (ECN) bits cleared. + * Using dscp_t allows to strictly separate DSCP and ECN bits, thus avoiding + * bugs where ECN bits are erroneously taken into account during FIB lookups + * or policy routing. + * + * Note: to get the real DSCP value contained in a dscp_t variable one would + * have to do a bit shift after calling inet_dscp_to_dsfield(). We could have + * a helper for that, but there's currently no users. + */ +typedef u8 __bitwise dscp_t; + +#define INET_DSCP_MASK 0xfc + +static inline dscp_t inet_dsfield_to_dscp(__u8 dsfield) +{ + return (__force dscp_t)(dsfield & INET_DSCP_MASK); +} + +static inline __u8 inet_dscp_to_dsfield(dscp_t dscp) +{ + return (__force __u8)dscp; +} + +static inline bool inet_validate_dscp(__u8 val) +{ + return !(val & ~INET_DSCP_MASK); +} + +#endif /* _INET_DSCP_H */ diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index dfd919b3119e..463ae5d33eb0 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -65,13 +65,13 @@ struct inet_timewait_sock { /* these three are in inet_sock */ __be16 tw_sport; /* And these are ours. */ - unsigned int tw_kill : 1, - tw_transparent : 1, + unsigned int tw_transparent : 1, tw_flowlabel : 20, - tw_pad : 2, /* 2 bits hole */ + tw_pad : 3, /* 3 bits hole */ tw_tos : 8; u32 tw_txhash; u32 tw_priority; + u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,8 +110,6 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); - static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { diff --git a/include/net/ip.h b/include/net/ip.h index b51bae43b0dd..3984f2c39c4b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -517,7 +517,6 @@ void ip_dst_metrics_put(struct dst_entry *dst) kfree(p); } -u32 ip_idents_reserve(u32 hash, int segs); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, @@ -712,7 +711,7 @@ int ip_forward(struct sk_buff *skb); */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, - __be32 daddr, struct rtable *rt, int is_frag); + __be32 daddr, struct rtable *rt); int __ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb, const struct ip_options *sopt); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 2048bc8748cb..6268963d9599 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -369,9 +369,8 @@ struct rt6_statistics { __u32 fib_rt_cache; /* cached rt entries in exception table */ __u32 fib_discarded_routes; /* total number of routes delete */ - /* The following stats are not protected by any lock */ + /* The following stat is not protected by any lock */ atomic_t fib_rt_alloc; /* total number of routes alloced */ - atomic_t fib_rt_uncache; /* rt entries in uncached list */ }; #define RTN_TL_ROOT 0x0001 diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index c4297704bbcb..6a82bcb8813b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -17,6 +17,7 @@ #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> +#include <net/inet_dscp.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> @@ -24,7 +25,7 @@ struct fib_config { u8 fc_dst_len; - u8 fc_tos; + dscp_t fc_dscp; u8 fc_protocol; u8 fc_scope; u8 fc_type; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 92eec13d1693..213612f1680c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -15,9 +15,9 @@ #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> -#include <net/ndisc.h> #include <net/flow.h> #include <net/flow_dissector.h> +#include <net/inet_dscp.h> #include <net/snmp.h> #include <net/netns/hash.h> @@ -440,8 +440,16 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); -struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, - struct ipv6_txoptions *opt); +struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, + struct ipv6_txoptions *opt); + +static inline struct ipv6_txoptions * +ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) +{ + if (!opt) + return NULL; + return __ipv6_fixup_options(opt_space, opt); +} bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); @@ -970,6 +978,11 @@ static inline u8 ip6_tclass(__be32 flowinfo) return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } +static inline dscp_t ip6_dscp(__be32 flowinfo) +{ + return inet_dsfield_to_dscp(ip6_tclass(flowinfo)); +} + static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; @@ -1023,7 +1036,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm6_cookie *ipc6, struct flowi6 *fl6, + struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 0a4779175a52..5052c66e22d2 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_FRAG_H #define _IPV6_FRAG_H +#include <linux/icmpv6.h> #include <linux/kernel.h> #include <net/addrconf.h> #include <net/ipv6.h> diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c50221d7e82c..bd6912d0292b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7,7 +7,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2021 Intel Corporation + * Copyright (C) 2018 - 2022 Intel Corporation */ #ifndef MAC80211_H @@ -883,6 +883,17 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), }; +/** + * enum mac80211_tx_status_flags - flags to describe transmit status + * + * @IEEE80211_TX_STATUS_ACK_SIGNAL_VALID: ACK signal is valid + * + * These flags are used in tx_info->status.flags. + */ +enum mac80211_tx_status_flags { + IEEE80211_TX_STATUS_ACK_SIGNAL_VALID = BIT(0), +}; + /* * This definition is used as a mask to clear all temporary flags, which are * set by the tx handlers for each transmission attempt by the mac80211 stack. @@ -1046,7 +1057,7 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @status.antenna: (legacy, kept only for iwlegacy) * @status.tx_time: airtime consumed for transmission; note this is only * used for WMM AC, not for airtime fairness - * @status.is_valid_ack_signal: ACK signal is valid + * @status.flags: status flags, see &enum mac80211_tx_status_flags * @status.status_driver_data: driver use area * @ack: union part for pure ACK data * @ack.cookie: cookie for the ACK @@ -1099,8 +1110,8 @@ struct ieee80211_tx_info { u8 ampdu_len; u8 antenna; u16 tx_time; - bool is_valid_ack_signal; - void *status_driver_data[19 / sizeof(void *)]; + u8 flags; + void *status_driver_data[18 / sizeof(void *)]; } status; struct { struct ieee80211_tx_rate driver_rates[ diff --git a/include/net/mac802154.h b/include/net/mac802154.h index d524ffb9eb25..2c3bbc6645ba 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -464,6 +464,12 @@ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, * ieee802154_wake_queue - wake ieee802154 queue * @hw: pointer as obtained from ieee802154_alloc_hw(). * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we had to stop the queue to + * avoid new skb to come during the transmission. The queue then needs to be + * woken up after the operation. + * * Drivers should use this function instead of netif_wake_queue. */ void ieee802154_wake_queue(struct ieee802154_hw *hw); @@ -472,6 +478,12 @@ void ieee802154_wake_queue(struct ieee802154_hw *hw); * ieee802154_stop_queue - stop ieee802154 queue * @hw: pointer as obtained from ieee802154_alloc_hw(). * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we need to tell upper layers to + * stop giving us new skbs while we are busy with the transmitted one. The queue + * must then be stopped before transmitting. + * * Drivers should use this function instead of netif_stop_queue. */ void ieee802154_stop_queue(struct ieee802154_hw *hw); diff --git a/include/net/mctp.h b/include/net/mctp.h index 7e35ec79b909..e80a4baf8379 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -45,6 +45,11 @@ static inline bool mctp_address_ok(mctp_eid_t eid) return eid >= 8 && eid < 255; } +static inline bool mctp_address_matches(mctp_eid_t match, mctp_eid_t eid) +{ + return match == eid || match == MCTP_ADDR_ANY; +} + static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb) { return (struct mctp_hdr *)skb_network_header(skb); @@ -121,7 +126,7 @@ struct mctp_sock { */ struct mctp_sk_key { mctp_eid_t peer_addr; - mctp_eid_t local_addr; + mctp_eid_t local_addr; /* MCTP_ADDR_ANY for local owned tags */ __u8 tag; /* incoming tag match; invert TO for local */ /* we hold a ref to sk when set */ @@ -158,6 +163,12 @@ struct mctp_sk_key { */ unsigned long dev_flow_state; struct mctp_dev *dev; + + /* a tag allocated with SIOCMCTPALLOCTAG ioctl will not expire + * automatically on timeout or response, instead SIOCMCTPDROPTAG + * is used. + */ + bool manual_alloc; }; struct mctp_skb_cb { @@ -234,6 +245,9 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); void mctp_key_unref(struct mctp_sk_key *key); +struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, + mctp_eid_t daddr, mctp_eid_t saddr, + bool manual, u8 *tagp); /* routing <--> device interface */ unsigned int mctp_default_net(struct net *net); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index a925349b4b89..0a3b0fb04a3b 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -217,12 +217,6 @@ static inline bool rsk_drop_req(const struct request_sock *req) return false; } -static inline void mptcp_parse_option(const struct sk_buff *skb, - const unsigned char *ptr, int opsize, - struct tcp_options_received *opt_rx) -{ -} - static inline bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 5b61c462e534..c4f5601f6e32 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -63,7 +63,7 @@ struct net { */ spinlock_t rules_mod_lock; - unsigned int dev_unreg_count; + atomic_t dev_unreg_count; unsigned int dev_base_seq; /* protected by rtnl_mutex */ int ifindex; @@ -513,4 +513,10 @@ static inline void fnhe_genid_bump(struct net *net) atomic_inc(&net->fnhe_genid); } +#ifdef CONFIG_NET +void net_ns_init(void); +#else +static inline void net_ns_init(void) {} +#endif + #endif /* __NET_NET_NAMESPACE_H */ diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h index 7f44a771530e..4b2b7f8914ea 100644 --- a/include/net/netfilter/nf_conntrack_acct.h +++ b/include/net/netfilter/nf_conntrack_acct.h @@ -78,7 +78,6 @@ static inline void nf_ct_acct_update(struct nf_conn *ct, u32 dir, void nf_conntrack_acct_pernet_init(struct net *net); -int nf_conntrack_acct_init(void); void nf_conntrack_acct_fini(void); #endif /* _NF_CONNTRACK_ACCT_H */ diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h new file mode 100644 index 000000000000..a473b56842c5 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _NF_CONNTRACK_BPF_H +#define _NF_CONNTRACK_BPF_H + +#include <linux/btf.h> +#include <linux/kconfig.h> + +#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +extern int register_nf_conntrack_bpf(void); + +#else + +static inline int register_nf_conntrack_bpf(void) +{ + return 0; +} + +#endif + +#endif /* _NF_CONNTRACK_BPF_H */ diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index d932e22edcb4..6c4c490a3e34 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -21,10 +21,10 @@ enum nf_ct_ecache_state { struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ - u16 missed; /* missed events */ u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ enum nf_ct_ecache_state state:8;/* ecache state */ + u32 missed; /* missed events */ u32 portid; /* netlink portid of destroyer */ }; @@ -166,9 +166,6 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state); void nf_conntrack_ecache_pernet_init(struct net *net); void nf_conntrack_ecache_pernet_fini(struct net *net); -int nf_conntrack_ecache_init(void); -void nf_conntrack_ecache_fini(void); - static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return net->ct.ecache_dwork_pending; @@ -194,16 +191,6 @@ static inline void nf_conntrack_ecache_pernet_init(struct net *net) static inline void nf_conntrack_ecache_pernet_fini(struct net *net) { } - -static inline int nf_conntrack_ecache_init(void) -{ - return 0; -} - -static inline void nf_conntrack_ecache_fini(void) -{ -} - static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return false; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ #endif /*_NF_CONNTRACK_ECACHE_H*/ diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index c7515d82ab06..96635ad2acc7 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -49,7 +49,7 @@ enum nf_ct_ext_id { struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; - char data[]; + char data[] __aligned(8); }; static inline bool __nf_ct_ext_exist(const struct nf_ct_ext *ext, u8 id) @@ -72,23 +72,7 @@ static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id) #define nf_ct_ext_find(ext, id) \ ((id##_TYPE *)__nf_ct_ext_find((ext), (id))) -/* Destroy all relationships */ -void nf_ct_ext_destroy(struct nf_conn *ct); - /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); -struct nf_ct_ext_type { - /* Destroys relationships (can be NULL). */ - void (*destroy)(struct nf_conn *ct); - - enum nf_ct_ext_id id; - - /* Length and min alignment. */ - u8 len; - u8 align; -}; - -int nf_ct_extend_register(const struct nf_ct_ext_type *type); -void nf_ct_extend_unregister(const struct nf_ct_ext_type *type); #endif /* _NF_CONNTRACK_EXTEND_H */ diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index ba916411c4e1..3c23298e68ca 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -45,12 +45,9 @@ int nf_connlabels_replace(struct nf_conn *ct, #ifdef CONFIG_NF_CONNTRACK_LABELS int nf_conntrack_labels_init(void); -void nf_conntrack_labels_fini(void); int nf_connlabels_get(struct net *net, unsigned int bit); void nf_connlabels_put(struct net *net); #else -static inline int nf_conntrack_labels_init(void) { return 0; } -static inline void nf_conntrack_labels_fini(void) {} static inline int nf_connlabels_get(struct net *net, unsigned int bit) { return 0; } static inline void nf_connlabels_put(struct net *net) {} #endif diff --git a/include/net/netfilter/nf_conntrack_seqadj.h b/include/net/netfilter/nf_conntrack_seqadj.h index 0a10b50537ae..883c414b768e 100644 --- a/include/net/netfilter/nf_conntrack_seqadj.h +++ b/include/net/netfilter/nf_conntrack_seqadj.h @@ -42,7 +42,4 @@ int nf_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int protoff); s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir, u32 seq); -int nf_conntrack_seqadj_init(void); -void nf_conntrack_seqadj_fini(void); - #endif /* _NF_CONNTRACK_SEQADJ_H */ diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 659b0ea25b4d..3ea94f6f3844 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -89,23 +89,11 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -int nf_conntrack_timeout_init(void); -void nf_conntrack_timeout_fini(void); void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout); int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, const char *timeout_name); void nf_ct_destroy_timeout(struct nf_conn *ct); #else -static inline int nf_conntrack_timeout_init(void) -{ - return 0; -} - -static inline void nf_conntrack_timeout_fini(void) -{ - return; -} - static inline int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, const char *timeout_name) @@ -120,8 +108,12 @@ static inline void nf_ct_destroy_timeout(struct nf_conn *ct) #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -extern struct nf_ct_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name); -extern void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout); +struct nf_ct_timeout_hooks { + struct nf_ct_timeout *(*timeout_find_get)(struct net *net, const char *name); + void (*timeout_put)(struct nf_ct_timeout *timeout); +}; + +extern const struct nf_ct_timeout_hooks *nf_ct_timeout_hook; #endif #endif /* _NF_CONNTRACK_TIMEOUT_H */ diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h index 820ea34b6029..57138d974a9f 100644 --- a/include/net/netfilter/nf_conntrack_timestamp.h +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -40,21 +40,8 @@ struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP void nf_conntrack_tstamp_pernet_init(struct net *net); - -int nf_conntrack_tstamp_init(void); -void nf_conntrack_tstamp_fini(void); #else static inline void nf_conntrack_tstamp_pernet_init(struct net *net) {} - -static inline int nf_conntrack_tstamp_init(void) -{ - return 0; -} - -static inline void nf_conntrack_tstamp_fini(void) -{ - return; -} #endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ #endif /* _NF_CONNTRACK_TSTAMP_H */ diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index b6fb1fdff9b2..0ea7c55cea4d 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -42,6 +42,14 @@ struct nft_cmp_fast_expr { bool inv; }; +struct nft_cmp16_fast_expr { + struct nft_data data; + struct nft_data mask; + u8 sreg; + u8 len; + bool inv; +}; + struct nft_immediate_expr { struct nft_data data; u8 dreg; @@ -59,6 +67,7 @@ static inline u32 nft_cmp_fast_mask(unsigned int len) } extern const struct nft_expr_ops nft_cmp_fast_ops; +extern const struct nft_expr_ops nft_cmp16_fast_ops; struct nft_payload { enum nft_payload_bases base:8; diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 552bc25b1933..388244e315e7 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -10,6 +10,7 @@ struct netns_core { struct ctl_table_header *sysctl_hdr; int sysctl_somaxconn; + u8 sysctl_txrehash; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 78557643526e..f0687867b5cd 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -31,18 +31,16 @@ struct ping_group_range { struct inet_hashinfo; struct inet_timewait_death_row { - atomic_t tw_count; - char tw_pad[L1_CACHE_BYTES - sizeof(atomic_t)]; + refcount_t tw_refcount; - struct inet_hashinfo *hashinfo; + struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; int sysctl_max_tw_buckets; }; struct tcp_fastopen_context; struct netns_ipv4 { - /* Please keep tcp_death_row at first field in netns_ipv4 */ - struct inet_timewait_death_row tcp_death_row ____cacheline_aligned_in_smp; + struct inet_timewait_death_row *tcp_death_row; #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; @@ -70,11 +68,9 @@ struct netns_ipv4 { struct hlist_head *fib_table_hash; struct sock *fibnl; - struct sock * __percpu *icmp_sk; struct sock *mc_autojoin_sk; struct inet_peer_base *peers; - struct sock * __percpu *tcp_sk; struct fqdir *fqdir; u8 sysctl_icmp_echo_ignore_all; @@ -87,6 +83,7 @@ struct netns_ipv4 { u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; + int ip_rt_min_advmss; struct local_ports ip_local_ports; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 6bd7e5a85ce7..3d83b64471d3 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -89,11 +89,15 @@ struct netns_ipv6 { struct fib6_table *fib6_local_tbl; struct fib_rules_ops *fib6_rules_ops; #endif - struct sock * __percpu *icmp_sk; struct sock *ndisc_sk; struct sock *tcp_sk; struct sock *igmp_sk; struct sock *mc_autojoin_sk; + + struct hlist_head *inet6_addr_lst; + spinlock_t addrconf_hash_lock; + struct delayed_work addr_chk_work; + #ifdef CONFIG_IPV6_MROUTE #ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES struct mr_table *mrt6; diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index ea8a9cf2619b..47b166684fd8 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -12,5 +12,7 @@ struct netns_smc { /* protect fback_rsn */ struct mutex mutex_fback_rsn; struct smc_stats_rsn *fback_rsn; + + bool limit_smc_hs; /* constraint on handshake */ }; #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 79a805542d0f..97c3c19872ff 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -201,21 +201,67 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, } #endif -void page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct); +void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, + bool allow_direct); -/* Same as above but will try to sync the entire area pool->max_len */ -static inline void page_pool_put_full_page(struct page_pool *pool, - struct page *page, bool allow_direct) +static inline void page_pool_fragment_page(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_defrag_page(struct page *page, long nr) +{ + long ret; + + /* If nr == pp_frag_count then we have cleared all remaining + * references to the page. No need to actually overwrite it, instead + * we can leave this to be overwritten by the calling function. + * + * The main advantage to doing this is that an atomic_read is + * generally a much cheaper operation than an atomic update, + * especially when dealing with a page that may be partitioned + * into only 2 or 3 pieces. + */ + if (atomic_long_read(&page->pp_frag_count) == nr) + return 0; + + ret = atomic_long_sub_return(nr, &page->pp_frag_count); + WARN_ON(ret < 0); + return ret; +} + +static inline bool page_pool_is_last_frag(struct page_pool *pool, + struct page *page) +{ + /* If fragments aren't enabled or count is 0 we were the last user */ + return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || + (page_pool_defrag_page(page, 1) == 0); +} + +static inline void page_pool_put_page(struct page_pool *pool, + struct page *page, + unsigned int dma_sync_size, + bool allow_direct) { /* When page_pool isn't compiled-in, net/core/xdp.c doesn't * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - page_pool_put_page(pool, page, -1, allow_direct); + if (!page_pool_is_last_frag(pool, page)) + return; + + page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); #endif } +/* Same as above but will try to sync the entire area pool->max_len */ +static inline void page_pool_put_full_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + page_pool_put_page(pool, page, -1, allow_direct); +} + /* Same as above but the caller must guarantee safe context. e.g NAPI */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) @@ -243,30 +289,6 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) page->dma_addr_upper = upper_32_bits(addr); } -static inline void page_pool_set_frag_count(struct page *page, long nr) -{ - atomic_long_set(&page->pp_frag_count, nr); -} - -static inline long page_pool_atomic_sub_frag_count_return(struct page *page, - long nr) -{ - long ret; - - /* As suggested by Alexander, atomic_long_read() may cover up the - * reference count errors, so avoid calling atomic_long_read() in - * the cases of freeing or draining the page_frags, where we would - * not expect it to match or that are slowpath anyway. - */ - if (__builtin_constant_p(nr) && - atomic_long_read(&page->pp_frag_count) == nr) - return 0; - - ret = atomic_long_sub_return(nr, &page->pp_frag_count); - WARN_ON(ret < 0); - return ret; -} - static inline bool is_page_pool_compiled_in(void) { #ifdef CONFIG_PAGE_POOL diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 676cb8ea9e15..a3b57a93228a 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -1028,4 +1028,15 @@ struct tc_fifo_qopt_offload { }; }; +#ifdef CONFIG_NET_CLS_ACT +DECLARE_STATIC_KEY_FALSE(tc_skb_ext_tc); +void tc_skb_ext_tc_enable(void); +void tc_skb_ext_tc_disable(void); +#define tc_skb_ext_tc_enabled() static_branch_unlikely(&tc_skb_ext_tc) +#else /* CONFIG_NET_CLS_ACT */ +static inline void tc_skb_ext_tc_enable(void) { } +static inline void tc_skb_ext_tc_disable(void) { } +#define tc_skb_ext_tc_enabled() false +#endif + #endif diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9e7b21c0b3a6..44a35531952e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -63,12 +63,6 @@ static inline psched_time_t psched_get_time(void) return PSCHED_NS2TICKS(ktime_get_ns()); } -static inline psched_tdiff_t -psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound) -{ - return min(tv1 - tv2, bound); -} - struct qdisc_watchdog { u64 last_expires; struct hrtimer timer; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 29e41ff3ec93..144c39db9898 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -70,6 +70,7 @@ struct request_sock { struct saved_syn *saved_syn; u32 secid; u32 peer_secid; + u32 timeout; }; static inline struct request_sock *inet_reqsk(const struct sock *sk) @@ -104,6 +105,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; + req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 472843eedbae..9bab396c1f3b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -518,11 +518,6 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) BUILD_BUG_ON(sizeof(qcb->data) < sz); } -static inline int qdisc_qlen_cpu(const struct Qdisc *q) -{ - return this_cpu_ptr(q->cpu_qstats)->qlen; -} - static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; diff --git a/include/net/sock.h b/include/net/sock.h index ff9b508d9c5f..d6c13f0fba40 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -316,6 +316,7 @@ struct sk_filter; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit + * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received @@ -491,6 +492,7 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; + u8 sk_txrehash; #ifdef CONFIG_NET_RX_BUSY_POLL u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; @@ -587,6 +589,18 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk) __tmp | SK_USER_DATA_NOCOPY); \ }) +static inline +struct net *sock_net(const struct sock *sk) +{ + return read_pnet(&sk->sk_net); +} + +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ + write_pnet(&sk->sk_net, net); +} + /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE @@ -2054,7 +2068,7 @@ static inline void sk_set_txhash(struct sock *sk) static inline bool sk_rethink_txhash(struct sock *sk) { - if (sk->sk_txhash) { + if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } @@ -2704,18 +2718,6 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static inline -struct net *sock_net(const struct sock *sk) -{ - return read_pnet(&sk->sk_net); -} - -static inline -void sock_net_set(struct sock *sk, struct net *net) -{ - write_pnet(&sk->sk_net, net); -} - static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d353793dfeb5..c32e1c8f79ec 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -81,6 +81,13 @@ struct switchdev_obj_port_vlan { struct switchdev_obj obj; u16 flags; u16 vid; + /* If set, the notifier signifies a change of one of the following + * flags for a VLAN that already exists: + * - BRIDGE_VLAN_INFO_PVID + * - BRIDGE_VLAN_INFO_UNTAGGED + * Entries with BRIDGE_VLAN_INFO_BRENTRY unset are not notified at all. + */ + bool changed; }; #define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \ @@ -317,11 +324,26 @@ int switchdev_handle_port_obj_add(struct net_device *dev, int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)); +int switchdev_handle_port_obj_add_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack)); int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)); +int switchdev_handle_port_obj_del_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj)); int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, @@ -440,6 +462,18 @@ switchdev_handle_port_obj_add(struct net_device *dev, return 0; } +static inline int switchdev_handle_port_obj_add_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack)) +{ + return 0; +} + static inline int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, @@ -451,6 +485,18 @@ switchdev_handle_port_obj_del(struct net_device *dev, } static inline int +switchdev_handle_port_obj_del_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj)) +{ + return 0; +} + +static inline int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), diff --git a/include/net/tcp.h b/include/net/tcp.h index b9fc978fb2ca..eff2487d972d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2358,7 +2358,7 @@ static inline u32 tcp_timeout_init(struct sock *sk) if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; - return timeout; + return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) diff --git a/include/net/udplite.h b/include/net/udplite.h index 9185e45b997f..a3c53110d30b 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -70,49 +70,6 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) return 0; } -/* Slow-path computation of checksum. Socket is locked. */ -static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) -{ - const struct udp_sock *up = udp_sk(skb->sk); - int cscov = up->len; - __wsum csum = 0; - - if (up->pcflag & UDPLITE_SEND_CC) { - /* - * Sender has set `partial coverage' option on UDP-Lite socket. - * The special case "up->pcslen == 0" signifies full coverage. - */ - if (up->pcslen < up->len) { - if (0 < up->pcslen) - cscov = up->pcslen; - udp_hdr(skb)->len = htons(up->pcslen); - } - /* - * NOTE: Causes for the error case `up->pcslen > up->len': - * (i) Application error (will not be penalized). - * (ii) Payload too big for send buffer: data is split - * into several packets, each with its own header. - * In this case (e.g. last segment), coverage may - * exceed packet length. - * Since packets with coverage length > packet length are - * illegal, we fall back to the defaults here. - */ - } - - skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ - - skb_queue_walk(&sk->sk_write_queue, skb) { - const int off = skb_transport_offset(skb); - const int len = skb->len - off; - - csum = skb_checksum(skb, off, (cscov > len)? len : cscov, csum); - - if ((cscov -= len) <= 0) - break; - } - return csum; -} - /* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { diff --git a/include/net/xdp.h b/include/net/xdp.h index 8f0812e4996d..b7721c3e4d1f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -60,12 +60,20 @@ struct xdp_rxq_info { u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; + u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; +enum xdp_buff_flags { + XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ + XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under + * pressure + */ +}; + struct xdp_buff { void *data; void *data_end; @@ -74,13 +82,40 @@ struct xdp_buff { struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + +static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; +} + static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; + xdp->flags = 0; } static __always_inline void @@ -111,6 +146,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp) return (struct skb_shared_info *)xdp_data_hard_end(xdp); } +static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +{ + unsigned int len = xdp->data_end - xdp->data; + struct skb_shared_info *sinfo; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + len += sinfo->xdp_frags_size; +out: + return len; +} + struct xdp_frame { void *data; u16 len; @@ -122,8 +171,19 @@ struct xdp_frame { */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; @@ -159,6 +219,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +static inline void +xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, + unsigned int size, unsigned int truesize, + bool pfmemalloc) +{ + skb_shinfo(skb)->nr_frags = nr_frags; + + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; + skb->pfmemalloc |= pfmemalloc; +} + /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) @@ -180,6 +253,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; + xdp->flags = frame->flags; } static inline @@ -206,6 +280,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp, xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; + xdp_frame->flags = xdp->flags; return 0; } @@ -230,6 +305,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) return xdp_frame; } +void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); @@ -246,14 +323,37 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; + struct skb_shared_info *sinfo; + int i; /* Curr only page_pool needs this */ - if (mem->type == MEM_TYPE_PAGE_POOL) - __xdp_release_frame(xdpf->data, mem); + if (mem->type != MEM_TYPE_PAGE_POOL) + return; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_release_frame(page_address(page), mem); + } +out: + __xdp_release_frame(xdpf->data, mem); +} + +int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id, u32 frag_size); +static inline int +xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id) +{ + return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } -int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index, unsigned int napi_id); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 443d45951564..4aa031849668 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -13,7 +13,7 @@ void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); -u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, u32 max); +u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max); void xsk_tx_release(struct xsk_buff_pool *pool); struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id); @@ -142,8 +142,7 @@ static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, return false; } -static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, - u32 max) +static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max) { return 0; } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index ddeefc4a1040..5554ee75e7da 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -60,6 +60,7 @@ struct xsk_buff_pool { */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; + struct xdp_desc *tx_descs; u64 chunk_mask; u64 addrs_cnt; u32 free_list_cnt; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 5c3a3597f1d2..78f56502bc09 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -105,8 +105,6 @@ #define REG_RESERVED_ADDR 0xffffffff #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) -#define OCELOT_MRP_CPUQ 7 - enum ocelot_target { ANA = 1, QS, @@ -540,6 +538,13 @@ struct ocelot_stat_layout { char name[ETH_GSTRING_LEN]; }; +struct ocelot_stats_region { + struct list_head node; + u32 offset; + int count; + u32 *buf; +}; + enum ocelot_tag_prefix { OCELOT_TAG_PREFIX_DISABLED = 0, OCELOT_TAG_PREFIX_NONE, @@ -671,6 +676,7 @@ struct ocelot { struct regmap_field *regfields[REGFIELD_MAX]; const u32 *const *map; const struct ocelot_stat_layout *stats_layout; + struct list_head stats_regions; unsigned int num_stats; u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; @@ -683,6 +689,7 @@ struct ocelot { u8 base_mac[ETH_ALEN]; struct list_head vlans; + struct list_head traps; /* Switches like VSC9959 have flooding per traffic class */ int num_flooding_pgids; @@ -742,25 +749,42 @@ struct ocelot_policer { u32 burst; /* bytes */ }; -#define ocelot_read_ix(ocelot, reg, gi, ri) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) -#define ocelot_read_gix(ocelot, reg, gi) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi)) -#define ocelot_read_rix(ocelot, reg, ri) __ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri)) -#define ocelot_read(ocelot, reg) __ocelot_read_ix(ocelot, reg, 0) - -#define ocelot_write_ix(ocelot, val, reg, gi, ri) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) -#define ocelot_write_gix(ocelot, val, reg, gi) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi)) -#define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri)) +#define ocelot_bulk_read_rix(ocelot, reg, ri, buf, count) \ + __ocelot_bulk_read_ix(ocelot, reg, reg##_RSZ * (ri), buf, count) + +#define ocelot_read_ix(ocelot, reg, gi, ri) \ + __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_read_gix(ocelot, reg, gi) \ + __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi)) +#define ocelot_read_rix(ocelot, reg, ri) \ + __ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri)) +#define ocelot_read(ocelot, reg) \ + __ocelot_read_ix(ocelot, reg, 0) + +#define ocelot_write_ix(ocelot, val, reg, gi, ri) \ + __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_write_gix(ocelot, val, reg, gi) \ + __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi)) +#define ocelot_write_rix(ocelot, val, reg, ri) \ + __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri)) #define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0) -#define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) -#define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi)) -#define ocelot_rmw_rix(ocelot, val, m, reg, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri)) +#define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) \ + __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_rmw_gix(ocelot, val, m, reg, gi) \ + __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi)) +#define ocelot_rmw_rix(ocelot, val, m, reg, ri) \ + __ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri)) #define ocelot_rmw(ocelot, val, m, reg) __ocelot_rmw_ix(ocelot, val, m, reg, 0) -#define ocelot_field_write(ocelot, reg, val) regmap_field_write((ocelot)->regfields[(reg)], (val)) -#define ocelot_field_read(ocelot, reg, val) regmap_field_read((ocelot)->regfields[(reg)], (val)) -#define ocelot_fields_write(ocelot, id, reg, val) regmap_fields_write((ocelot)->regfields[(reg)], (id), (val)) -#define ocelot_fields_read(ocelot, id, reg, val) regmap_fields_read((ocelot)->regfields[(reg)], (id), (val)) +#define ocelot_field_write(ocelot, reg, val) \ + regmap_field_write((ocelot)->regfields[(reg)], (val)) +#define ocelot_field_read(ocelot, reg, val) \ + regmap_field_read((ocelot)->regfields[(reg)], (val)) +#define ocelot_fields_write(ocelot, id, reg, val) \ + regmap_fields_write((ocelot)->regfields[(reg)], (id), (val)) +#define ocelot_fields_read(ocelot, id, reg, val) \ + regmap_fields_read((ocelot)->regfields[(reg)], (id), (val)) #define ocelot_target_read_ix(ocelot, target, reg, gi, ri) \ __ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) @@ -784,6 +808,8 @@ struct ocelot_policer { u32 ocelot_port_readl(struct ocelot_port *port, u32 reg); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg); void ocelot_port_rmwl(struct ocelot_port *port, u32 val, u32 mask, u32 reg); +int __ocelot_bulk_read_ix(struct ocelot *ocelot, u32 reg, u32 offset, void *buf, + int count); u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset); void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset); void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 709cbc198fd2..deb2ad9eb0a5 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -8,6 +8,20 @@ #include <soc/mscc/ocelot.h> +/* Cookie definitions for private VCAP filters installed by the driver. + * Must be unique per VCAP block. + */ +#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) +#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2) +#define OCELOT_VCAP_IS2_L2_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 1) +#define OCELOT_VCAP_IS2_IPV4_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 2) +#define OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 3) +#define OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 4) +#define OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 5) + /* ================================================================= * VCAP Common * ================================================================= @@ -666,6 +680,7 @@ struct ocelot_vcap_id { struct ocelot_vcap_filter { struct list_head list; + struct list_head trap_list; enum ocelot_vcap_filter_type type; int block_id; @@ -678,6 +693,7 @@ struct ocelot_vcap_filter { struct ocelot_vcap_action action; struct ocelot_vcap_stats stats; /* For VCAP IS1 and IS2 */ + bool take_ts; unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; diff --git a/include/trace/events/mctp.h b/include/trace/events/mctp.h index 175b057c507f..165cf25f77a7 100644 --- a/include/trace/events/mctp.h +++ b/include/trace/events/mctp.h @@ -15,6 +15,7 @@ enum { MCTP_TRACE_KEY_REPLIED, MCTP_TRACE_KEY_INVALIDATED, MCTP_TRACE_KEY_CLOSED, + MCTP_TRACE_KEY_DROPPED, }; #endif /* __TRACE_MCTP_ENUMS */ @@ -22,6 +23,7 @@ TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_TIMEOUT); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_REPLIED); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_INVALIDATED); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_CLOSED); +TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_DROPPED); TRACE_EVENT(mctp_key_acquire, TP_PROTO(const struct mctp_sk_key *key), @@ -66,7 +68,8 @@ TRACE_EVENT(mctp_key_release, { MCTP_TRACE_KEY_TIMEOUT, "timeout" }, { MCTP_TRACE_KEY_REPLIED, "replied" }, { MCTP_TRACE_KEY_INVALIDATED, "invalidated" }, - { MCTP_TRACE_KEY_CLOSED, "closed" }) + { MCTP_TRACE_KEY_CLOSED, "closed" }, + { MCTP_TRACE_KEY_DROPPED, "dropped" }) ) ); diff --git a/include/trace/events/net.h b/include/trace/events/net.h index 78c448c6ab4c..032b431b987b 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -260,13 +260,6 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_ARGS(skb) ); -DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry, - - TP_PROTO(const struct sk_buff *skb), - - TP_ARGS(skb) -); - DECLARE_EVENT_CLASS(net_dev_rx_exit_template, TP_PROTO(int ret), @@ -312,13 +305,6 @@ DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, TP_ARGS(ret) ); -DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit, - - TP_PROTO(int ret), - - TP_ARGS(ret) -); - DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, TP_PROTO(int ret), diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index a8a64b97504d..cfcfd26399f7 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -16,6 +16,17 @@ EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ + EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP) \ + EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST) \ + EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM) \ + EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR) \ + EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER) \ + EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, \ + UNICAST_IN_L2_MULTICAST) \ + EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY) \ + EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ + EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ + EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index c77a1313b3b0..467ca2f28760 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -128,6 +128,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b0383d371b9a..afe3d0d7f5f2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1111,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1775,6 +1782,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1791,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2267,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2382,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2481,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3257,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. @@ -5018,6 +5038,54 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5206,6 +5274,12 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ + FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5500,7 +5574,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; @@ -6378,7 +6453,8 @@ struct bpf_sk_lookup { __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index cca6e474a085..417d4280d7b5 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -319,6 +319,12 @@ enum { /* RINGS */ enum { + ETHTOOL_TCP_DATA_SPLIT_UNKNOWN = 0, + ETHTOOL_TCP_DATA_SPLIT_DISABLED, + ETHTOOL_TCP_DATA_SPLIT_ENABLED, +}; + +enum { ETHTOOL_A_RINGS_UNSPEC, ETHTOOL_A_RINGS_HEADER, /* nest - _A_HEADER_* */ ETHTOOL_A_RINGS_RX_MAX, /* u32 */ @@ -330,6 +336,7 @@ enum { ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ + ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index 829ffdfcacca..38f6a8fdfd34 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -41,6 +41,15 @@ enum { /* IOAM Trace Header */ IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + /* Insertion frequency: + * "k over n" packets (0 < k <= n) + * [0.0001% ... 100%] + */ +#define IOAM6_IPTUNNEL_FREQ_MIN 1 +#define IOAM6_IPTUNNEL_FREQ_MAX 1000000 + IOAM6_IPTUNNEL_FREQ_K, /* u32 */ + IOAM6_IPTUNNEL_FREQ_N, /* u32 */ + __IOAM6_IPTUNNEL_MAX, }; diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 07b0318716fc..154ab56651f1 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -44,7 +44,25 @@ struct sockaddr_mctp_ext { #define MCTP_TAG_MASK 0x07 #define MCTP_TAG_OWNER 0x08 +#define MCTP_TAG_PREALLOC 0x10 #define MCTP_OPT_ADDR_EXT 1 +#define SIOCMCTPALLOCTAG (SIOCPROTOPRIVATE + 0) +#define SIOCMCTPDROPTAG (SIOCPROTOPRIVATE + 1) + +struct mctp_ioc_tag_ctl { + mctp_eid_t peer_addr; + + /* For SIOCMCTPALLOCTAG: must be passed as zero, kernel will + * populate with the allocated tag value. Returned tag value will + * always have TO and PREALLOC set. + * + * For SIOCMCTPDROPTAG: userspace provides tag value to drop, from + * a prior SIOCMCTPALLOCTAG call (and so must have TO and PREALLOC set). + */ + __u8 tag; + __u16 flags; +}; + #endif /* __UAPI_MCTP_H */ diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 66048cc5d7b3..1bbea8f0681e 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -93,6 +93,7 @@ enum net_dm_attr { NET_DM_ATTR_SW_DROPS, /* flag */ NET_DM_ATTR_HW_DROPS, /* flag */ NET_DM_ATTR_FLOW_ACTION_COOKIE, /* binary */ + NET_DM_ATTR_REASON, /* string */ __NET_DM_ATTR_MAX, NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1 diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index aed90c4df0c8..ef7c97f21a15 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -61,6 +61,7 @@ enum nfqnl_attr_type { NFQA_SECCTX, /* security context string */ NFQA_VLAN, /* nested attribute: packet vlan info */ NFQA_L2HDR, /* full L2 header */ + NFQA_PRIORITY, /* skb->priority */ __NFQA_MAX }; diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 6c2874fd2c00..693f549f6966 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -59,6 +59,9 @@ enum { SMC_NETLINK_DUMP_SEID, SMC_NETLINK_ENABLE_SEID, SMC_NETLINK_DISABLE_SEID, + SMC_NETLINK_DUMP_HS_LIMITATION, + SMC_NETLINK_ENABLE_HS_LIMITATION, + SMC_NETLINK_DISABLE_HS_LIMITATION, }; /* SMC_GENL_FAMILY top level attributes */ @@ -284,4 +287,16 @@ enum { __SMC_NLA_SEID_TABLE_MAX, SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 }; + +/* SMC_NETLINK_HS_LIMITATION attributes */ +enum { + SMC_NLA_HS_LIMITATION_UNSPEC, + SMC_NLA_HS_LIMITATION_ENABLED, /* u8 */ + __SMC_NLA_HS_LIMITATION_MAX, + SMC_NLA_HS_LIMITATION_MAX = __SMC_NLA_HS_LIMITATION_MAX - 1 +}; + +/* SMC socket options */ +#define SMC_LIMIT_HS 1 /* constraint on smc handshake */ + #endif /* _UAPI_LINUX_SMC_H */ diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index eb0a9a5b6e71..51d6bb2f6765 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,4 +31,8 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) +#define SOCK_TXREHASH_DEFAULT ((u8)-1) +#define SOCK_TXREHASH_DISABLED 0 +#define SOCK_TXREHASH_ENABLED 1 + #endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/init/Kconfig b/init/Kconfig index e9119bf54b1f..7328d4f25370 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -86,6 +86,10 @@ config CC_HAS_ASM_INLINE config CC_HAS_NO_PROFILE_FN_ATTR def_bool $(success,echo '__attribute__((no_profile_instrument_function)) int x();' | $(CC) -x c - -c -o /dev/null -Werror) +config PAHOLE_VERSION + int + default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE)) + config CONSTRUCTORS bool diff --git a/init/main.c b/init/main.c index 65fa2e41a9c0..ada50f5a15e4 100644 --- a/init/main.c +++ b/init/main.c @@ -99,6 +99,7 @@ #include <linux/kcsan.h> #include <linux/init_syscalls.h> #include <linux/stackdepot.h> +#include <net/net_namespace.h> #include <asm/io.h> #include <asm/bugs.h> @@ -1116,6 +1117,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) key_init(); security_init(); dbg_late_init(); + net_ns_init(); vfs_caches_init(); pagecache_init(); signals_init(); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c7a5be3bf8be..7f145aefbff8 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -837,13 +837,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) static void *prog_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { - struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog = bpf_prog_get(fd); if (IS_ERR(prog)) return prog; - if (!bpf_prog_array_compatible(array, prog)) { + if (!bpf_prog_map_compatible(map, prog)) { bpf_prog_put(prog); return ERR_PTR(-EINVAL); } @@ -1071,7 +1070,6 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) INIT_WORK(&aux->work, prog_array_map_clear_deferred); INIT_LIST_HEAD(&aux->poke_progs); mutex_init(&aux->poke_mutex); - spin_lock_init(&aux->owner.lock); map = array_map_alloc(attr); if (IS_ERR(map)) { diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b7aef5b3416d..110029ede71e 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -5,6 +5,7 @@ #include <linux/anon_inodes.h> #include <linux/filter.h> #include <linux/bpf.h> +#include <linux/rcupdate_trace.h> struct bpf_iter_target_info { struct list_head list; @@ -684,11 +685,20 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) { int ret; - rcu_read_lock(); - migrate_disable(); - ret = bpf_prog_run(prog, ctx); - migrate_enable(); - rcu_read_unlock(); + if (prog->aux->sleepable) { + rcu_read_lock_trace(); + migrate_disable(); + might_fault(); + ret = bpf_prog_run(prog, ctx); + migrate_enable(); + rcu_read_unlock_trace(); + } else { + rcu_read_lock(); + migrate_disable(); + ret = bpf_prog_run(prog, ctx); + migrate_enable(); + rcu_read_unlock(); + } /* bpf program can only return 0 or 1: * 0 : okay diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e16dafeb2450..11740b300de9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -198,6 +198,21 @@ DEFINE_IDR(btf_idr); DEFINE_SPINLOCK(btf_idr_lock); +enum btf_kfunc_hook { + BTF_KFUNC_HOOK_XDP, + BTF_KFUNC_HOOK_TC, + BTF_KFUNC_HOOK_STRUCT_OPS, + BTF_KFUNC_HOOK_MAX, +}; + +enum { + BTF_KFUNC_SET_MAX_CNT = 32, +}; + +struct btf_kfunc_set_tab { + struct btf_id_set *sets[BTF_KFUNC_HOOK_MAX][BTF_KFUNC_TYPE_MAX]; +}; + struct btf { void *data; struct btf_type **types; @@ -212,6 +227,7 @@ struct btf { refcount_t refcnt; u32 id; struct rcu_head rcu; + struct btf_kfunc_set_tab *kfunc_set_tab; /* split BTF support */ struct btf *base_btf; @@ -403,6 +419,9 @@ static struct btf_type btf_void; static int btf_resolve(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id); +static int btf_func_check(struct btf_verifier_env *env, + const struct btf_type *t); + static bool btf_type_is_modifier(const struct btf_type *t) { /* Some of them is not strictly a C modifier @@ -579,6 +598,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || + btf_type_is_func(t) || btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -1531,8 +1551,30 @@ static void btf_free_id(struct btf *btf) spin_unlock_irqrestore(&btf_idr_lock, flags); } +static void btf_free_kfunc_set_tab(struct btf *btf) +{ + struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab; + int hook, type; + + if (!tab) + return; + /* For module BTF, we directly assign the sets being registered, so + * there is nothing to free except kfunc_set_tab. + */ + if (btf_is_module(btf)) + goto free_tab; + for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) { + for (type = 0; type < ARRAY_SIZE(tab->sets[0]); type++) + kfree(tab->sets[hook][type]); + } +free_tab: + kfree(tab); + btf->kfunc_set_tab = NULL; +} + static void btf_free(struct btf *btf) { + btf_free_kfunc_set_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); @@ -3533,9 +3575,24 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env, return 0; } +static int btf_func_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + int err; + + err = btf_func_check(env, t); + if (err) + return err; + + env_stack_pop_resolved(env, next_type_id, 0); + return 0; +} + static struct btf_kind_operations func_ops = { .check_meta = btf_func_check_meta, - .resolve = btf_df_resolve, + .resolve = btf_func_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_ref_type_log, @@ -4156,7 +4213,7 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); - if (btf_type_is_decl_tag(t)) + if (btf_type_is_decl_tag(t) || btf_type_is_func(t)) return btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); @@ -4246,12 +4303,6 @@ static int btf_check_all_types(struct btf_verifier_env *env) if (err) return err; } - - if (btf_type_is_func(t)) { - err = btf_func_check(env, t); - if (err) - return err; - } } return 0; @@ -4848,6 +4899,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; + const char *tag_value; u32 nr_args, arg; int i, ret; @@ -5000,6 +5052,13 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, info->btf = btf; info->btf_id = t->type; t = btf_type_by_id(btf, t->type); + + if (btf_type_is_type_tag(t)) { + tag_value = __btf_name_by_offset(btf, t->name_off); + if (strcmp(tag_value, "user") == 0) + info->reg_type |= MEM_USER; + } + /* skip modifiers */ while (btf_type_is_modifier(t)) { info->btf_id = t->type; @@ -5026,12 +5085,12 @@ enum bpf_struct_walk_result { static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, - u32 *next_btf_id) + u32 *next_btf_id, enum bpf_type_flag *flag) { u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; const struct btf_type *mtype, *elem_type = NULL; const struct btf_member *member; - const char *tname, *mname; + const char *tname, *mname, *tag_value; u32 vlen, elem_id, mid; again: @@ -5215,7 +5274,8 @@ error: } if (btf_type_is_ptr(mtype)) { - const struct btf_type *stype; + const struct btf_type *stype, *t; + enum bpf_type_flag tmp_flag = 0; u32 id; if (msize != size || off != moff) { @@ -5224,9 +5284,19 @@ error: mname, moff, tname, off, size); return -EACCES; } + + /* check __user tag */ + t = btf_type_by_id(btf, mtype->type); + if (btf_type_is_type_tag(t)) { + tag_value = __btf_name_by_offset(btf, t->name_off); + if (strcmp(tag_value, "user") == 0) + tmp_flag = MEM_USER; + } + stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; + *flag = tmp_flag; return WALK_PTR; } } @@ -5253,13 +5323,14 @@ error: int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype __maybe_unused, - u32 *next_btf_id) + u32 *next_btf_id, enum bpf_type_flag *flag) { + enum bpf_type_flag tmp_flag = 0; int err; u32 id; do { - err = btf_struct_walk(log, btf, t, off, size, &id); + err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); switch (err) { case WALK_PTR: @@ -5267,6 +5338,7 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, * we're done. */ *next_btf_id = id; + *flag = tmp_flag; return PTR_TO_BTF_ID; case WALK_SCALAR: return SCALAR_VALUE; @@ -5311,6 +5383,7 @@ bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *need_btf, u32 need_type_id) { const struct btf_type *type; + enum bpf_type_flag flag; int err; /* Are we already done? */ @@ -5321,7 +5394,7 @@ again: type = btf_type_by_id(btf, id); if (!type) return false; - err = btf_struct_walk(log, btf, type, off, 1, &id); + err = btf_struct_walk(log, btf, type, off, 1, &id, &flag); if (err != WALK_STRUCT) return false; @@ -5616,17 +5689,45 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log, return true; } +static bool is_kfunc_arg_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) +{ + int len, sfx_len = sizeof("__sz") - 1; + const struct btf_type *t; + const char *param_name; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len < sfx_len) + return false; + param_name += len - sfx_len; + if (strncmp(param_name, "__sz", sfx_len)) + return false; + + return true; +} + static int btf_check_func_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, bool ptr_to_mem_ok) { struct bpf_verifier_log *log = &env->log; + u32 i, nargs, ref_id, ref_obj_id = 0; bool is_kfunc = btf_is_kernel(btf); const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; - u32 i, nargs, ref_id; + int ref_regno = 0; + bool rel = false; t = btf_type_by_id(btf, func_id); if (!t || !btf_type_is_func(t)) { @@ -5704,6 +5805,16 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (reg->type == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; + /* Ensure only one argument is referenced PTR_TO_BTF_ID */ + if (reg->ref_obj_id) { + if (ref_obj_id) { + bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, ref_obj_id); + return -EFAULT; + } + ref_regno = regno; + ref_obj_id = reg->ref_obj_id; + } } else { reg_btf = btf_vmlinux; reg_ref_id = *reg2btf_ids[reg->type]; @@ -5727,17 +5838,33 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, u32 type_size; if (is_kfunc) { + bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], ®s[regno + 1]); + /* Permit pointer to mem, but only when argument * type is pointer to scalar, or struct composed * (recursively) of scalars. + * When arg_mem_size is true, the pointer can be + * void *. */ if (!btf_type_is_scalar(ref_t) && - !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) { + !__btf_type_is_scalar_struct(log, btf, ref_t, 0) && + (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { bpf_log(log, - "arg#%d pointer type %s %s must point to scalar or struct with scalar\n", - i, btf_type_str(ref_t), ref_tname); + "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", + i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); return -EINVAL; } + + /* Check for mem, len pair */ + if (arg_mem_size) { + if (check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1)) { + bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", + i, i + 1); + return -EINVAL; + } + i++; + continue; + } } resolve_ret = btf_resolve_size(btf, ref_t, &type_size); @@ -5758,7 +5885,23 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, } } - return 0; + /* Either both are set, or neither */ + WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno)); + if (is_kfunc) { + rel = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_RELEASE, func_id); + /* We already made sure ref_obj_id is set only for one argument */ + if (rel && !ref_obj_id) { + bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", + func_name); + return -EINVAL; + } + /* Allow (!rel && ref_obj_id), so that passing such referenced PTR_TO_BTF_ID to + * other kfuncs works + */ + } + /* returns argument register number > 0 in case of reference release kfunc */ + return rel ? ref_regno : 0; } /* Compare BTF of a function with given bpf_reg_state. @@ -6200,12 +6343,17 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id) return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; } +enum { + BTF_MODULE_F_LIVE = (1 << 0), +}; + #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module { struct list_head list; struct module *module; struct btf *btf; struct bin_attribute *sysfs_attr; + int flags; }; static LIST_HEAD(btf_modules); @@ -6233,7 +6381,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, int err = 0; if (mod->btf_data_size == 0 || - (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) + (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE && + op != MODULE_STATE_GOING)) goto out; switch (op) { @@ -6292,6 +6441,17 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, } break; + case MODULE_STATE_LIVE: + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + btf_mod->flags |= BTF_MODULE_F_LIVE; + break; + } + mutex_unlock(&btf_module_mutex); + break; case MODULE_STATE_GOING: mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { @@ -6338,7 +6498,12 @@ struct module *btf_try_get_module(const struct btf *btf) if (btf_mod->btf != btf) continue; - if (try_module_get(btf_mod->module)) + /* We must only consider module whose __init routine has + * finished, hence we must check for BTF_MODULE_F_LIVE flag, + * which is set from the notifier callback for + * MODULE_STATE_LIVE. + */ + if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module)) res = btf_mod->module; break; @@ -6349,6 +6514,36 @@ struct module *btf_try_get_module(const struct btf *btf) return res; } +/* Returns struct btf corresponding to the struct module + * + * This function can return NULL or ERR_PTR. Note that caller must + * release reference for struct btf iff btf_is_module is true. + */ +static struct btf *btf_get_module_btf(const struct module *module) +{ + struct btf *btf = NULL; +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + struct btf_module *btf_mod, *tmp; +#endif + + if (!module) + return bpf_get_btf_vmlinux(); +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + btf_get(btf_mod->btf); + btf = btf_mod->btf; + break; + } + mutex_unlock(&btf_module_mutex); +#endif + + return btf; +} + BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) { struct btf *btf; @@ -6416,58 +6611,300 @@ BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE -/* BTF ID set registration API for modules */ +/* Kernel Function (kfunc) BTF ID set registration API */ -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, + enum btf_kfunc_type type, + struct btf_id_set *add_set, bool vmlinux_set) +{ + struct btf_kfunc_set_tab *tab; + struct btf_id_set *set; + u32 set_cnt; + int ret; + + if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX) { + ret = -EINVAL; + goto end; + } + + if (!add_set->cnt) + return 0; + + tab = btf->kfunc_set_tab; + if (!tab) { + tab = kzalloc(sizeof(*tab), GFP_KERNEL | __GFP_NOWARN); + if (!tab) + return -ENOMEM; + btf->kfunc_set_tab = tab; + } + + set = tab->sets[hook][type]; + /* Warn when register_btf_kfunc_id_set is called twice for the same hook + * for module sets. + */ + if (WARN_ON_ONCE(set && !vmlinux_set)) { + ret = -EINVAL; + goto end; + } + + /* We don't need to allocate, concatenate, and sort module sets, because + * only one is allowed per hook. Hence, we can directly assign the + * pointer and return. + */ + if (!vmlinux_set) { + tab->sets[hook][type] = add_set; + return 0; + } + + /* In case of vmlinux sets, there may be more than one set being + * registered per hook. To create a unified set, we allocate a new set + * and concatenate all individual sets being registered. While each set + * is individually sorted, they may become unsorted when concatenated, + * hence re-sorting the final set again is required to make binary + * searching the set using btf_id_set_contains function work. + */ + set_cnt = set ? set->cnt : 0; + + if (set_cnt > U32_MAX - add_set->cnt) { + ret = -EOVERFLOW; + goto end; + } + + if (set_cnt + add_set->cnt > BTF_KFUNC_SET_MAX_CNT) { + ret = -E2BIG; + goto end; + } + + /* Grow set */ + set = krealloc(tab->sets[hook][type], + offsetof(struct btf_id_set, ids[set_cnt + add_set->cnt]), + GFP_KERNEL | __GFP_NOWARN); + if (!set) { + ret = -ENOMEM; + goto end; + } + + /* For newly allocated set, initialize set->cnt to 0 */ + if (!tab->sets[hook][type]) + set->cnt = 0; + tab->sets[hook][type] = set; + + /* Concatenate the two sets */ + memcpy(set->ids + set->cnt, add_set->ids, add_set->cnt * sizeof(set->ids[0])); + set->cnt += add_set->cnt; + + sort(set->ids, set->cnt, sizeof(set->ids[0]), btf_id_cmp_func, NULL); + + return 0; +end: + btf_free_kfunc_set_tab(btf); + return ret; +} + +static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, + const struct btf_kfunc_id_set *kset) +{ + bool vmlinux_set = !btf_is_module(btf); + int type, ret; + + for (type = 0; type < ARRAY_SIZE(kset->sets); type++) { + if (!kset->sets[type]) + continue; + + ret = __btf_populate_kfunc_set(btf, hook, type, kset->sets[type], vmlinux_set); + if (ret) + break; + } + return ret; +} + +static bool __btf_kfunc_id_set_contains(const struct btf *btf, + enum btf_kfunc_hook hook, + enum btf_kfunc_type type, + u32 kfunc_btf_id) +{ + struct btf_id_set *set; + + if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX) + return false; + if (!btf->kfunc_set_tab) + return false; + set = btf->kfunc_set_tab->sets[hook][type]; + if (!set) + return false; + return btf_id_set_contains(set, kfunc_btf_id); +} -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) { - mutex_lock(&l->mutex); - list_add(&s->list, &l->list); - mutex_unlock(&l->mutex); + switch (prog_type) { + case BPF_PROG_TYPE_XDP: + return BTF_KFUNC_HOOK_XDP; + case BPF_PROG_TYPE_SCHED_CLS: + return BTF_KFUNC_HOOK_TC; + case BPF_PROG_TYPE_STRUCT_OPS: + return BTF_KFUNC_HOOK_STRUCT_OPS; + default: + return BTF_KFUNC_HOOK_MAX; + } } -EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +/* Caution: + * Reference to the module (obtained using btf_try_get_module) corresponding to + * the struct btf *MUST* be held when calling this function from verifier + * context. This is usually true as we stash references in prog's kfunc_btf_tab; + * keeping the reference for the duration of the call provides the necessary + * protection for looking up a well-formed btf->kfunc_set_tab. + */ +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id) { - mutex_lock(&l->mutex); - list_del_init(&s->list); - mutex_unlock(&l->mutex); + enum btf_kfunc_hook hook; + + hook = bpf_prog_type_to_kfunc_hook(prog_type); + return __btf_kfunc_id_set_contains(btf, hook, type, kfunc_btf_id); } -EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner) +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *kset) { - struct kfunc_btf_id_set *s; + enum btf_kfunc_hook hook; + struct btf *btf; + int ret; - mutex_lock(&klist->mutex); - list_for_each_entry(s, &klist->list, list) { - if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { - mutex_unlock(&klist->mutex); - return true; + btf = btf_get_module_btf(kset->owner); + if (!btf) { + if (!kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + pr_err("missing vmlinux BTF, cannot register kfuncs\n"); + return -ENOENT; } + if (kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) { + pr_err("missing module BTF, cannot register kfuncs\n"); + return -ENOENT; + } + return 0; } - mutex_unlock(&klist->mutex); - return false; + if (IS_ERR(btf)) + return PTR_ERR(btf); + + hook = bpf_prog_type_to_kfunc_hook(prog_type); + ret = btf_populate_kfunc_set(btf, hook, kset); + /* reference is only taken for module BTF */ + if (btf_is_module(btf)) + btf_put(btf); + return ret; } +EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); -#define DEFINE_KFUNC_BTF_ID_LIST(name) \ - struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ - __MUTEX_INITIALIZER(name.mutex) }; \ - EXPORT_SYMBOL_GPL(name) +#define MAX_TYPES_ARE_COMPAT_DEPTH 2 -DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); -DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); +static +int __bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id, + int level) +{ + const struct btf_type *local_type, *targ_type; + int depth = 32; /* max recursion depth */ -#endif + /* caller made sure that names match (ignoring flavor suffix) */ + local_type = btf_type_by_id(local_btf, local_id); + targ_type = btf_type_by_id(targ_btf, targ_id); + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; +recur: + depth--; + if (depth < 0) + return -EINVAL; + + local_type = btf_type_skip_modifiers(local_btf, local_id, &local_id); + targ_type = btf_type_skip_modifiers(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + return 1; + case BTF_KIND_INT: + /* just reject deprecated bitfield-like integers; all other + * integers are by default compatible between each other + */ + return btf_int_offset(local_type) == 0 && btf_int_offset(targ_type) == 0; + case BTF_KIND_PTR: + local_id = local_type->type; + targ_id = targ_type->type; + goto recur; + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + case BTF_KIND_FUNC_PROTO: { + struct btf_param *local_p = btf_params(local_type); + struct btf_param *targ_p = btf_params(targ_type); + __u16 local_vlen = btf_vlen(local_type); + __u16 targ_vlen = btf_vlen(targ_type); + int i, err; + + if (local_vlen != targ_vlen) + return 0; + + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) { + if (level <= 0) + return -EINVAL; + + btf_type_skip_modifiers(local_btf, local_p->type, &local_id); + btf_type_skip_modifiers(targ_btf, targ_p->type, &targ_id); + err = __bpf_core_types_are_compat(local_btf, local_id, + targ_btf, targ_id, + level - 1); + if (err <= 0) + return err; + } + + /* tail recurse for return type check */ + btf_type_skip_modifiers(local_btf, local_type->type, &local_id); + btf_type_skip_modifiers(targ_btf, targ_type->type, &targ_id); + goto recur; + } + default: + return 0; + } +} + +/* Check local and target types for compatibility. This check is used for + * type-based CO-RE relocations and follow slightly different rules than + * field-based relocations. This function assumes that root types were already + * checked for name match. Beyond that initial root-level name check, names + * are completely ignored. Compatibility rules are as follows: + * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs are considered compatible, but + * kind should match for local and target types (i.e., STRUCT is not + * compatible with UNION); + * - for ENUMs, the size is ignored; + * - for INT, size and signedness are ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - CONST/VOLATILE/RESTRICT modifiers are ignored; + * - TYPEDEFs/PTRs are compatible if types they pointing to are compatible; + * - FUNC_PROTOs are compatible if they have compatible signature: same + * number of input args and compatible return and argument types. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id) { - return -EOPNOTSUPP; + return __bpf_core_types_are_compat(local_btf, local_id, + targ_btf, targ_id, + MAX_TYPES_ARE_COMPAT_DEPTH); } static bool bpf_core_is_flavor_sep(const char *s) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 514b4681a90a..098632fdbc45 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1044,7 +1044,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, * NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr * NET_XMIT_CN (2) - continue with packet output and notify TCP * to call cwr - * -EPERM - drop packet + * -err - drop packet * * For ingress packets, this function will return -EPERM if any * attached program was found and if it returned != 1 during execution. @@ -1079,8 +1079,9 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb); } else { ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb, - __bpf_prog_run_save_cb); - ret = (ret == 1 ? 0 : -EPERM); + __bpf_prog_run_save_cb, 0); + if (ret && !IS_ERR_VALUE((long)ret)) + ret = -EFAULT; } bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); @@ -1107,10 +1108,9 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - int ret; - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, bpf_prog_run); - return ret == 1 ? 0 : -EPERM; + return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, + bpf_prog_run, 0); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -1142,7 +1142,6 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, }; struct sockaddr_storage unspec; struct cgroup *cgrp; - int ret; /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). @@ -1156,10 +1155,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx, - bpf_prog_run, flags); - - return ret == 1 ? 0 : -EPERM; + return BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx, + bpf_prog_run, 0, flags); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); @@ -1184,11 +1181,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - int ret; - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops, - bpf_prog_run); - return ret == 1 ? 0 : -EPERM; + return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops, + bpf_prog_run, 0); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); @@ -1201,17 +1196,47 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, .major = major, .minor = minor, }; - int allow; + int ret; rcu_read_lock(); cgrp = task_dfl_cgroup(current); - allow = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, - bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, + bpf_prog_run, 0); rcu_read_unlock(); - return !allow; + return ret; +} + +BPF_CALL_0(bpf_get_retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + return ctx->retval; +} + +static const struct bpf_func_proto bpf_get_retval_proto = { + .func = bpf_get_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +BPF_CALL_1(bpf_set_retval, int, retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + ctx->retval = retval; + return 0; } +static const struct bpf_func_proto bpf_set_retval_proto = { + .func = bpf_set_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1224,6 +1249,10 @@ cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; + case BPF_FUNC_get_retval: + return &bpf_get_retval_proto; + case BPF_FUNC_set_retval: + return &bpf_set_retval_proto; default: return bpf_base_func_proto(func_id); } @@ -1337,7 +1366,8 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, + bpf_prog_run, 0); rcu_read_unlock(); kfree(ctx.cur_val); @@ -1350,24 +1380,10 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, kfree(ctx.new_val); } - return ret == 1 ? 0 : -EPERM; + return ret; } #ifdef CONFIG_NET -static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, - enum cgroup_bpf_attach_type attach_type) -{ - struct bpf_prog_array *prog_array; - bool empty; - - rcu_read_lock(); - prog_array = rcu_dereference(cgrp->bpf.effective[attach_type]); - empty = bpf_prog_array_is_empty(prog_array); - rcu_read_unlock(); - - return empty; -} - static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen, struct bpf_sockopt_buf *buf) { @@ -1426,19 +1442,11 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, }; 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 - * memory and locking the socket. - */ - if (__cgroup_bpf_prog_array_is_empty(cgrp, CGROUP_SETSOCKOPT)) - return 0; - /* 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); - max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; @@ -1452,13 +1460,11 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, lock_sock(sk); ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_SETSOCKOPT], - &ctx, bpf_prog_run); + &ctx, bpf_prog_run, 0); release_sock(sk); - if (!ret) { - ret = -EPERM; + if (ret) goto out; - } if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ @@ -1518,19 +1524,11 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, .sk = sk, .level = level, .optname = optname, - .retval = retval, + .current_task = current, }; int ret; - /* Opportunistic check to see whether we have any BPF program - * attached to the hook so we don't waste time allocating - * memory and locking the socket. - */ - if (__cgroup_bpf_prog_array_is_empty(cgrp, CGROUP_GETSOCKOPT)) - return retval; - ctx.optlen = max_optlen; - max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; @@ -1562,27 +1560,17 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, lock_sock(sk); ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run); + &ctx, bpf_prog_run, retval); release_sock(sk); - if (!ret) { - ret = -EPERM; + if (ret < 0) goto out; - } if (ctx.optlen > max_optlen || ctx.optlen < 0) { ret = -EFAULT; goto out; } - /* BPF programs only allowed to set retval to 0, not some - * arbitrary value. - */ - if (ctx.retval != 0 && ctx.retval != retval) { - ret = -EFAULT; - goto out; - } - if (ctx.optlen != 0) { if (copy_to_user(optval, ctx.optval, ctx.optlen) || put_user(ctx.optlen, optlen)) { @@ -1591,8 +1579,6 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, } } - ret = ctx.retval; - out: sockopt_free_buf(&ctx, &buf); return ret; @@ -1607,10 +1593,10 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, .sk = sk, .level = level, .optname = optname, - .retval = retval, .optlen = *optlen, .optval = optval, .optval_end = optval + *optlen, + .current_task = current, }; int ret; @@ -1623,25 +1609,19 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, */ ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run); - if (!ret) - return -EPERM; + &ctx, bpf_prog_run, retval); + if (ret < 0) + return ret; if (ctx.optlen > *optlen) return -EFAULT; - /* BPF programs only allowed to set retval to 0, not some - * arbitrary value. - */ - if (ctx.retval != 0 && ctx.retval != retval) - return -EFAULT; - /* BPF programs can shrink the buffer, export the modifications. */ if (ctx.optlen != 0) *optlen = ctx.optlen; - return ctx.retval; + return ret; } #endif @@ -2057,10 +2037,39 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen); break; case offsetof(struct bpf_sockopt, retval): - if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval); - else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval); + BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0); + + if (type == BPF_WRITE) { + int treg = BPF_REG_9; + + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg, + offsetof(struct bpf_sockopt_kern, tmp_reg)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), + treg, si->dst_reg, + offsetof(struct bpf_sockopt_kern, current_task)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), + treg, treg, + offsetof(struct task_struct, bpf_ctx)); + *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), + treg, si->src_reg, + offsetof(struct bpf_cg_run_ctx, retval)); + *insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg, + offsetof(struct bpf_sockopt_kern, tmp_reg)); + } else { + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sockopt_kern, current_task)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), + si->dst_reg, si->dst_reg, + offsetof(struct task_struct, bpf_ctx)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), + si->dst_reg, si->dst_reg, + offsetof(struct bpf_cg_run_ctx, retval)); + } break; case offsetof(struct bpf_sockopt, optval): *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index de3e5bc6781f..42d96549a804 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -537,13 +537,10 @@ long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) { - const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog); - unsigned long addr = (unsigned long)hdr; - WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); prog->aux->ksym.start = (unsigned long) prog->bpf_func; - prog->aux->ksym.end = addr + hdr->pages * PAGE_SIZE; + prog->aux->ksym.end = prog->aux->ksym.start + prog->jited_len; } static void @@ -808,6 +805,137 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, return slot; } +/* + * BPF program pack allocator. + * + * Most BPF programs are pretty small. Allocating a hole page for each + * program is sometime a waste. Many small bpf program also adds pressure + * to instruction TLB. To solve this issue, we introduce a BPF program pack + * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86) + * to host BPF programs. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define BPF_PROG_PACK_SIZE HPAGE_PMD_SIZE +#else +#define BPF_PROG_PACK_SIZE PAGE_SIZE +#endif +#define BPF_PROG_CHUNK_SHIFT 6 +#define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT) +#define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1)) +#define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE) + +struct bpf_prog_pack { + struct list_head list; + void *ptr; + unsigned long bitmap[BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)]; +}; + +#define BPF_PROG_MAX_PACK_PROG_SIZE BPF_PROG_PACK_SIZE +#define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE) + +static DEFINE_MUTEX(pack_mutex); +static LIST_HEAD(pack_list); + +static struct bpf_prog_pack *alloc_new_pack(void) +{ + struct bpf_prog_pack *pack; + + pack = kzalloc(sizeof(*pack), GFP_KERNEL); + if (!pack) + return NULL; + pack->ptr = module_alloc(BPF_PROG_PACK_SIZE); + if (!pack->ptr) { + kfree(pack); + return NULL; + } + bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); + list_add_tail(&pack->list, &pack_list); + + set_vm_flush_reset_perms(pack->ptr); + set_memory_ro((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); + set_memory_x((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); + return pack; +} + +static void *bpf_prog_pack_alloc(u32 size) +{ + unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); + struct bpf_prog_pack *pack; + unsigned long pos; + void *ptr = NULL; + + if (size > BPF_PROG_MAX_PACK_PROG_SIZE) { + size = round_up(size, PAGE_SIZE); + ptr = module_alloc(size); + if (ptr) { + set_vm_flush_reset_perms(ptr); + set_memory_ro((unsigned long)ptr, size / PAGE_SIZE); + set_memory_x((unsigned long)ptr, size / PAGE_SIZE); + } + return ptr; + } + mutex_lock(&pack_mutex); + list_for_each_entry(pack, &pack_list, list) { + pos = bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, + nbits, 0); + if (pos < BPF_PROG_CHUNK_COUNT) + goto found_free_area; + } + + pack = alloc_new_pack(); + if (!pack) + goto out; + + pos = 0; + +found_free_area: + bitmap_set(pack->bitmap, pos, nbits); + ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT); + +out: + mutex_unlock(&pack_mutex); + return ptr; +} + +static void bpf_prog_pack_free(struct bpf_binary_header *hdr) +{ + struct bpf_prog_pack *pack = NULL, *tmp; + unsigned int nbits; + unsigned long pos; + void *pack_ptr; + + if (hdr->size > BPF_PROG_MAX_PACK_PROG_SIZE) { + module_memfree(hdr); + return; + } + + pack_ptr = (void *)((unsigned long)hdr & ~(BPF_PROG_PACK_SIZE - 1)); + mutex_lock(&pack_mutex); + + list_for_each_entry(tmp, &pack_list, list) { + if (tmp->ptr == pack_ptr) { + pack = tmp; + break; + } + } + + if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) + goto out; + + nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); + pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT; + + bitmap_clear(pack->bitmap, pos, nbits); + if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, + BPF_PROG_CHUNK_COUNT, 0) == 0) { + list_del(&pack->list); + module_memfree(pack->ptr); + kfree(pack); + } +out: + mutex_unlock(&pack_mutex); +} + static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, @@ -833,12 +961,11 @@ static int __init bpf_jit_charge_init(void) } pure_initcall(bpf_jit_charge_init); -int bpf_jit_charge_modmem(u32 pages) +int bpf_jit_charge_modmem(u32 size) { - if (atomic_long_add_return(pages, &bpf_jit_current) > - (bpf_jit_limit >> PAGE_SHIFT)) { + if (atomic_long_add_return(size, &bpf_jit_current) > bpf_jit_limit) { if (!bpf_capable()) { - atomic_long_sub(pages, &bpf_jit_current); + atomic_long_sub(size, &bpf_jit_current); return -EPERM; } } @@ -846,9 +973,9 @@ int bpf_jit_charge_modmem(u32 pages) return 0; } -void bpf_jit_uncharge_modmem(u32 pages) +void bpf_jit_uncharge_modmem(u32 size) { - atomic_long_sub(pages, &bpf_jit_current); + atomic_long_sub(size, &bpf_jit_current); } void *__weak bpf_jit_alloc_exec(unsigned long size) @@ -867,7 +994,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; - u32 size, hole, start, pages; + u32 size, hole, start; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); @@ -877,20 +1004,19 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); - pages = size / PAGE_SIZE; - if (bpf_jit_charge_modmem(pages)) + if (bpf_jit_charge_modmem(size)) return NULL; hdr = bpf_jit_alloc_exec(size); if (!hdr) { - bpf_jit_uncharge_modmem(pages); + bpf_jit_uncharge_modmem(size); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); - hdr->pages = pages; + hdr->size = size; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); @@ -903,10 +1029,113 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr) { - u32 pages = hdr->pages; + u32 size = hdr->size; bpf_jit_free_exec(hdr); - bpf_jit_uncharge_modmem(pages); + bpf_jit_uncharge_modmem(size); +} + +/* Allocate jit binary from bpf_prog_pack allocator. + * Since the allocated memory is RO+X, the JIT engine cannot write directly + * to the memory. To solve this problem, a RW buffer is also allocated at + * as the same time. The JIT engine should calculate offsets based on the + * RO memory address, but write JITed program to the RW buffer. Once the + * JIT engine finishes, it calls bpf_jit_binary_pack_finalize, which copies + * the JITed program to the RO memory. + */ +struct bpf_binary_header * +bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, + unsigned int alignment, + struct bpf_binary_header **rw_header, + u8 **rw_image, + bpf_jit_fill_hole_t bpf_fill_ill_insns) +{ + struct bpf_binary_header *ro_header; + u32 size, hole, start; + + WARN_ON_ONCE(!is_power_of_2(alignment) || + alignment > BPF_IMAGE_ALIGNMENT); + + /* add 16 bytes for a random section of illegal instructions */ + size = round_up(proglen + sizeof(*ro_header) + 16, BPF_PROG_CHUNK_SIZE); + + if (bpf_jit_charge_modmem(size)) + return NULL; + ro_header = bpf_prog_pack_alloc(size); + if (!ro_header) { + bpf_jit_uncharge_modmem(size); + return NULL; + } + + *rw_header = kvmalloc(size, GFP_KERNEL); + if (!*rw_header) { + bpf_prog_pack_free(ro_header); + bpf_jit_uncharge_modmem(size); + return NULL; + } + + /* Fill space with illegal/arch-dep instructions. */ + bpf_fill_ill_insns(*rw_header, size); + (*rw_header)->size = size; + + hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)), + BPF_PROG_CHUNK_SIZE - sizeof(*ro_header)); + start = (get_random_int() % hole) & ~(alignment - 1); + + *image_ptr = &ro_header->image[start]; + *rw_image = &(*rw_header)->image[start]; + + return ro_header; +} + +/* Copy JITed text from rw_header to its final location, the ro_header. */ +int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, + struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header) +{ + void *ptr; + + ptr = bpf_arch_text_copy(ro_header, rw_header, rw_header->size); + + kvfree(rw_header); + + if (IS_ERR(ptr)) { + bpf_prog_pack_free(ro_header); + return PTR_ERR(ptr); + } + prog->aux->use_bpf_prog_pack = true; + return 0; +} + +/* bpf_jit_binary_pack_free is called in two different scenarios: + * 1) when the program is freed after; + * 2) when the JIT engine fails (before bpf_jit_binary_pack_finalize). + * For case 2), we need to free both the RO memory and the RW buffer. + * Also, ro_header->size in 2) is not properly set yet, so rw_header->size + * is used for uncharge. + */ +void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header) +{ + u32 size = rw_header ? rw_header->size : ro_header->size; + + bpf_prog_pack_free(ro_header); + kvfree(rw_header); + bpf_jit_uncharge_modmem(size); +} + +static inline struct bpf_binary_header * +bpf_jit_binary_hdr(const struct bpf_prog *fp) +{ + unsigned long real_start = (unsigned long)fp->bpf_func; + unsigned long addr; + + if (fp->aux->use_bpf_prog_pack) + addr = real_start & BPF_PROG_CHUNK_MASK; + else + addr = real_start & PAGE_MASK; + + return (void *)addr; } /* This symbol is only overridden by archs that have different @@ -918,7 +1147,10 @@ void __weak bpf_jit_free(struct bpf_prog *fp) if (fp->jited) { struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); - bpf_jit_binary_free(hdr); + if (fp->aux->use_bpf_prog_pack) + bpf_jit_binary_pack_free(hdr, NULL /* rw_buffer */); + else + bpf_jit_binary_free(hdr); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); } @@ -1829,28 +2061,30 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, } #endif -bool bpf_prog_array_compatible(struct bpf_array *array, - const struct bpf_prog *fp) +bool bpf_prog_map_compatible(struct bpf_map *map, + const struct bpf_prog *fp) { bool ret; if (fp->kprobe_override) return false; - spin_lock(&array->aux->owner.lock); - - if (!array->aux->owner.type) { + spin_lock(&map->owner.lock); + if (!map->owner.type) { /* There's no owner yet where we could check for * compatibility. */ - array->aux->owner.type = fp->type; - array->aux->owner.jited = fp->jited; + map->owner.type = fp->type; + map->owner.jited = fp->jited; + map->owner.xdp_has_frags = fp->aux->xdp_has_frags; ret = true; } else { - ret = array->aux->owner.type == fp->type && - array->aux->owner.jited == fp->jited; + ret = map->owner.type == fp->type && + map->owner.jited == fp->jited && + map->owner.xdp_has_frags == fp->aux->xdp_has_frags; } - spin_unlock(&array->aux->owner.lock); + spin_unlock(&map->owner.lock); + return ret; } @@ -1862,13 +2096,11 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) mutex_lock(&aux->used_maps_mutex); for (i = 0; i < aux->used_map_cnt; i++) { struct bpf_map *map = aux->used_maps[i]; - struct bpf_array *array; - if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) + if (!map_type_contains_progs(map)) continue; - array = container_of(map, struct bpf_array, map); - if (!bpf_prog_array_compatible(array, fp)) { + if (!bpf_prog_map_compatible(map, fp)) { ret = -EINVAL; goto out; } @@ -1968,18 +2200,10 @@ static struct bpf_prog_dummy { }, }; -/* to avoid allocating empty bpf_prog_array for cgroups that - * don't have bpf program attached use one global 'empty_prog_array' - * It will not be modified the caller of bpf_prog_array_alloc() - * (since caller requested prog_cnt == 0) - * that pointer should be 'freed' by bpf_prog_array_free() - */ -static struct { - struct bpf_prog_array hdr; - struct bpf_prog *null_prog; -} empty_prog_array = { +struct bpf_empty_prog_array bpf_empty_prog_array = { .null_prog = NULL, }; +EXPORT_SYMBOL(bpf_empty_prog_array); struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { @@ -1989,12 +2213,12 @@ struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) (prog_cnt + 1), flags); - return &empty_prog_array.hdr; + return &bpf_empty_prog_array.hdr; } void bpf_prog_array_free(struct bpf_prog_array *progs) { - if (!progs || progs == &empty_prog_array.hdr) + if (!progs || progs == &bpf_empty_prog_array.hdr) return; kfree_rcu(progs, rcu); } @@ -2453,6 +2677,11 @@ int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, return -ENOTSUPP; } +void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + return ERR_PTR(-ENOTSUPP); +} + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index b3e6b9422238..650e5d21f90d 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -397,7 +397,8 @@ static int cpu_map_kthread_run(void *data) return 0; } -static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) +static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, + struct bpf_map *map, int fd) { struct bpf_prog *prog; @@ -405,7 +406,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) if (IS_ERR(prog)) return PTR_ERR(prog); - if (prog->expected_attach_type != BPF_XDP_CPUMAP) { + if (prog->expected_attach_type != BPF_XDP_CPUMAP || + !bpf_prog_map_compatible(map, prog)) { bpf_prog_put(prog); return -EINVAL; } @@ -457,7 +459,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, rcpu->map_id = map->id; rcpu->value.qsize = value->qsize; - if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd)) + if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd)) goto free_ptr_ring; /* Setup kthread */ diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index fe019dbdb3f0..038f6d7a83e4 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -858,7 +858,8 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; - if (prog->expected_attach_type != BPF_XDP_DEVMAP) + if (prog->expected_attach_type != BPF_XDP_DEVMAP || + !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 01cfdf40c838..4e5969fde0b3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -16,6 +16,7 @@ #include <linux/pid_namespace.h> #include <linux/proc_ns.h> #include <linux/security.h> +#include <linux/btf_ids.h> #include "../../lib/kstrtox.h" @@ -671,6 +672,39 @@ const struct bpf_func_proto bpf_copy_from_user_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size, + const void __user *, user_ptr, struct task_struct *, tsk, u64, flags) +{ + int ret; + + /* flags is not used yet */ + if (unlikely(flags)) + return -EINVAL; + + if (unlikely(!size)) + return 0; + + ret = access_process_vm(tsk, (unsigned long)user_ptr, dst, size, 0); + if (ret == size) + return 0; + + memset(dst, 0, size); + /* Return -EFAULT for partial read */ + return ret < 0 ? ret : -EFAULT; +} + +const struct bpf_func_proto bpf_copy_from_user_task_proto = { + .func = bpf_copy_from_user_task, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_BTF_ID, + .arg4_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg5_type = ARG_ANYTHING +}; + BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu) { if (cpu >= nr_cpu_ids) diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile index 1400ac58178e..baf47d9c7557 100644 --- a/kernel/bpf/preload/Makefile +++ b/kernel/bpf/preload/Makefile @@ -1,40 +1,16 @@ # SPDX-License-Identifier: GPL-2.0 LIBBPF_SRCS = $(srctree)/tools/lib/bpf/ -LIBBPF_OUT = $(abspath $(obj))/libbpf -LIBBPF_A = $(LIBBPF_OUT)/libbpf.a -LIBBPF_DESTDIR = $(LIBBPF_OUT) -LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include - -# Although not in use by libbpf's Makefile, set $(O) so that the "dummy" test -# in tools/scripts/Makefile.include always succeeds when building the kernel -# with $(O) pointing to a relative path, as in "make O=build bindeb-pkg". -$(LIBBPF_A): | $(LIBBPF_OUT) - $(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= \ - $(LIBBPF_OUT)/libbpf.a install_headers - -libbpf_hdrs: $(LIBBPF_A) - -.PHONY: libbpf_hdrs - -$(LIBBPF_OUT): - $(call msg,MKDIR,$@) - $(Q)mkdir -p $@ +LIBBPF_INCLUDE = $(LIBBPF_SRCS)/.. userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \ -I $(LIBBPF_INCLUDE) -Wno-unused-result userprogs := bpf_preload_umd -clean-files := libbpf/ - -$(obj)/iterators/iterators.o: | libbpf_hdrs - bpf_preload_umd-objs := iterators/iterators.o -bpf_preload_umd-userldlibs := $(LIBBPF_A) -lelf -lz -$(obj)/bpf_preload_umd: $(LIBBPF_A) +$(obj)/bpf_preload_umd: $(obj)/bpf_preload_umd_blob.o: $(obj)/bpf_preload_umd diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile index b8bd60511227..bfe24f8c5a20 100644 --- a/kernel/bpf/preload/iterators/Makefile +++ b/kernel/bpf/preload/iterators/Makefile @@ -35,15 +35,15 @@ endif .PHONY: all clean -all: iterators.skel.h +all: iterators.lskel.h clean: $(call msg,CLEAN) $(Q)rm -rf $(OUTPUT) iterators -iterators.skel.h: $(OUTPUT)/iterators.bpf.o | $(BPFTOOL) +iterators.lskel.h: $(OUTPUT)/iterators.bpf.o | $(BPFTOOL) $(call msg,GEN-SKEL,$@) - $(Q)$(BPFTOOL) gen skeleton $< > $@ + $(Q)$(BPFTOOL) gen skeleton -L $< > $@ $(OUTPUT)/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) diff --git a/kernel/bpf/preload/iterators/iterators.c b/kernel/bpf/preload/iterators/iterators.c index 5d872a705470..4dafe0f4f2b2 100644 --- a/kernel/bpf/preload/iterators/iterators.c +++ b/kernel/bpf/preload/iterators/iterators.c @@ -10,20 +10,36 @@ #include <bpf/libbpf.h> #include <bpf/bpf.h> #include <sys/mount.h> -#include "iterators.skel.h" +#include "iterators.lskel.h" #include "bpf_preload_common.h" int to_kernel = -1; int from_kernel = 0; -static int send_link_to_kernel(struct bpf_link *link, const char *link_name) +static int __bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) +{ + union bpf_attr attr; + int err; + + memset(&attr, 0, sizeof(attr)); + attr.info.bpf_fd = bpf_fd; + attr.info.info_len = *info_len; + attr.info.info = (long) info; + + err = skel_sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr)); + if (!err) + *info_len = attr.info.info_len; + return err; +} + +static int send_link_to_kernel(int link_fd, const char *link_name) { struct bpf_preload_info obj = {}; struct bpf_link_info info = {}; __u32 info_len = sizeof(info); int err; - err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &info, &info_len); + err = __bpf_obj_get_info_by_fd(link_fd, &info, &info_len); if (err) return err; obj.link_id = info.id; @@ -37,7 +53,6 @@ static int send_link_to_kernel(struct bpf_link *link, const char *link_name) int main(int argc, char **argv) { - struct rlimit rlim = { RLIM_INFINITY, RLIM_INFINITY }; struct iterators_bpf *skel; int err, magic; int debug_fd; @@ -55,7 +70,6 @@ int main(int argc, char **argv) printf("bad start magic %d\n", magic); return 1; } - setrlimit(RLIMIT_MEMLOCK, &rlim); /* libbpf opens BPF object and loads it into the kernel */ skel = iterators_bpf__open_and_load(); if (!skel) { @@ -72,10 +86,10 @@ int main(int argc, char **argv) goto cleanup; /* send two bpf_link IDs with names to the kernel */ - err = send_link_to_kernel(skel->links.dump_bpf_map, "maps.debug"); + err = send_link_to_kernel(skel->links.dump_bpf_map_fd, "maps.debug"); if (err) goto cleanup; - err = send_link_to_kernel(skel->links.dump_bpf_prog, "progs.debug"); + err = send_link_to_kernel(skel->links.dump_bpf_prog_fd, "progs.debug"); if (err) goto cleanup; diff --git a/kernel/bpf/preload/iterators/iterators.lskel.h b/kernel/bpf/preload/iterators/iterators.lskel.h new file mode 100644 index 000000000000..d90562d672d2 --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.lskel.h @@ -0,0 +1,428 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* THIS FILE IS AUTOGENERATED! */ +#ifndef __ITERATORS_BPF_SKEL_H__ +#define __ITERATORS_BPF_SKEL_H__ + +#include <stdlib.h> +#include <bpf/bpf.h> +#include <bpf/skel_internal.h> + +struct iterators_bpf { + struct bpf_loader_ctx ctx; + struct { + struct bpf_map_desc rodata; + } maps; + struct { + struct bpf_prog_desc dump_bpf_map; + struct bpf_prog_desc dump_bpf_prog; + } progs; + struct { + int dump_bpf_map_fd; + int dump_bpf_prog_fd; + } links; + struct iterators_bpf__rodata { + } *rodata; +}; + +static inline int +iterators_bpf__dump_bpf_map__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_map.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_map_fd = fd; + return fd; +} + +static inline int +iterators_bpf__dump_bpf_prog__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_prog.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_prog_fd = fd; + return fd; +} + +static inline int +iterators_bpf__attach(struct iterators_bpf *skel) +{ + int ret = 0; + + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_map__attach(skel); + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_prog__attach(skel); + return ret < 0 ? ret : 0; +} + +static inline void +iterators_bpf__detach(struct iterators_bpf *skel) +{ + skel_closenz(skel->links.dump_bpf_map_fd); + skel_closenz(skel->links.dump_bpf_prog_fd); +} +static void +iterators_bpf__destroy(struct iterators_bpf *skel) +{ + if (!skel) + return; + iterators_bpf__detach(skel); + skel_closenz(skel->progs.dump_bpf_map.prog_fd); + skel_closenz(skel->progs.dump_bpf_prog.prog_fd); + munmap(skel->rodata, 4096); + skel_closenz(skel->maps.rodata.map_fd); + free(skel); +} +static inline struct iterators_bpf * +iterators_bpf__open(void) +{ + struct iterators_bpf *skel; + + skel = calloc(sizeof(*skel), 1); + if (!skel) + goto cleanup; + skel->ctx.sz = (void *)&skel->links - (void *)skel; + skel->rodata = + mmap(NULL, 4096, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (skel->rodata == (void *) -1) + goto cleanup; + memcpy(skel->rodata, (void *)"\ +\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\ +\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\ +\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0", 98); + skel->maps.rodata.initial_value = (__u64)(long)skel->rodata; + return skel; +cleanup: + iterators_bpf__destroy(skel); + return NULL; +} + +static inline int +iterators_bpf__load(struct iterators_bpf *skel) +{ + struct bpf_load_and_run_opts opts = {}; + int err; + + opts.ctx = (struct bpf_loader_ctx *)skel; + opts.data_sz = 6056; + opts.data = (void *)"\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x9f\xeb\x01\0\ +\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\xf9\x04\0\0\0\0\0\0\0\0\0\x02\x02\0\ +\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\0\x04\ +\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\0\0\0\0\0\ +\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\0\0\0\x20\ +\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\0\0\xb1\0\ +\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\0\0\x80\0\ +\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\0\0\0\0\ +\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x94\x01\0\0\x03\0\0\x04\ +\x18\0\0\0\x9c\x01\0\0\x0e\0\0\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xa4\ +\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb0\x01\0\0\0\0\0\x08\x0f\0\0\0\xb6\x01\0\0\0\0\0\ +\x01\x04\0\0\0\x20\0\0\0\xc3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\0\0\0\ +\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xc8\x01\0\0\0\0\0\x01\x04\0\0\0\ +\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x2c\x02\0\0\x02\0\0\x04\x10\0\0\0\x13\0\ +\0\0\x03\0\0\0\0\0\0\0\x3f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x18\0\ +\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x44\x02\0\0\x01\0\0\x0c\ +\x16\0\0\0\x90\x02\0\0\x01\0\0\x04\x08\0\0\0\x99\x02\0\0\x19\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x02\x1a\0\0\0\xea\x02\0\0\x06\0\0\x04\x38\0\0\0\x9c\x01\0\0\x0e\0\0\ +\0\0\0\0\0\x9f\x01\0\0\x11\0\0\0\x20\0\0\0\xf7\x02\0\0\x1b\0\0\0\xc0\0\0\0\x08\ +\x03\0\0\x15\0\0\0\0\x01\0\0\x11\x03\0\0\x1d\0\0\0\x40\x01\0\0\x1b\x03\0\0\x1e\ +\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\0\0\0\0\ +\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x65\x03\0\0\x02\0\0\x04\ +\x08\0\0\0\x73\x03\0\0\x0e\0\0\0\0\0\0\0\x7c\x03\0\0\x0e\0\0\0\x20\0\0\0\x1b\ +\x03\0\0\x03\0\0\x04\x18\0\0\0\x86\x03\0\0\x1b\0\0\0\0\0\0\0\x8e\x03\0\0\x21\0\ +\0\0\x40\0\0\0\x94\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\0\0\0\ +\0\0\0\0\0\x02\x24\0\0\0\x98\x03\0\0\x01\0\0\x04\x04\0\0\0\xa3\x03\0\0\x0e\0\0\ +\0\0\0\0\0\x0c\x04\0\0\x01\0\0\x04\x04\0\0\0\x15\x04\0\0\x0e\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x8b\x04\0\0\0\0\0\x0e\x25\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\x9f\x04\ +\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\ +\x20\0\0\0\xb5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\ +\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xca\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe1\x04\0\0\0\0\0\x0e\x2d\0\0\ +\0\x01\0\0\0\xe9\x04\0\0\x04\0\0\x0f\x62\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\0\x28\ +\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\0\0\ +\x11\0\0\0\xf1\x04\0\0\x01\0\0\x0f\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\x62\ +\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\ +\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\x70\ +\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x30\ +\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\x65\ +\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\ +\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\ +\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\ +\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\ +\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\ +\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\ +\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\x6e\ +\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\x74\ +\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\ +\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\ +\x29\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x20\x63\ +\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\x3b\0\x30\ +\x3a\x32\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\ +\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\ +\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\ +\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\ +\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\ +\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\ +\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\ +\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\ +\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\ +\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\ +\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\ +\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\ +\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\ +\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\ +\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\ +\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\ +\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\ +\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\ +\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\ +\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\ +\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\ +\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\ +\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\ +\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\ +\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\ +\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\ +\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\ +\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\ +\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\ +\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\ +\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\ +\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\ +\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\ +\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\ +\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\ +\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\ +\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\ +\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\ +\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\ +\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\ +\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\ +\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ +\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ +\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\ +\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\ +\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\ +\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2d\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\ +\0\x04\0\0\0\x62\0\0\0\x01\0\0\0\x80\x04\0\0\0\0\0\0\0\0\0\0\x69\x74\x65\x72\ +\x61\x74\x6f\x72\x2e\x72\x6f\x64\x61\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\x2f\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\ +\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\ +\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\ +\x25\x73\x20\x25\x73\x0a\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\ +\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\x1b\0\0\ +\0\0\0\x79\x11\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\ +\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x23\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\ +\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\ +\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\x7b\x2a\xf0\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\ +\x7b\x1a\xf8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\ +\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x23\0\0\0\xb7\x03\0\0\x0e\0\0\0\ +\xb7\x05\0\0\x18\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ +\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x3c\x01\0\x01\0\0\0\x42\0\0\ +\0\x7b\0\0\0\x24\x3c\x01\0\x02\0\0\0\x42\0\0\0\xee\0\0\0\x1d\x44\x01\0\x03\0\0\ +\0\x42\0\0\0\x0f\x01\0\0\x06\x4c\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\x40\ +\x01\0\x05\0\0\0\x42\0\0\0\x1a\x01\0\0\x1d\x40\x01\0\x06\0\0\0\x42\0\0\0\x43\ +\x01\0\0\x06\x58\x01\0\x08\0\0\0\x42\0\0\0\x56\x01\0\0\x03\x5c\x01\0\x0f\0\0\0\ +\x42\0\0\0\xdc\x01\0\0\x02\x64\x01\0\x1f\0\0\0\x42\0\0\0\x2a\x02\0\0\x01\x6c\ +\x01\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\ +\0\x10\0\0\0\x02\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\ +\x28\0\0\0\x08\0\0\0\x3f\x01\0\0\0\0\0\0\x78\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\ +\x88\0\0\0\x0d\0\0\0\xea\0\0\0\0\0\0\0\xa8\0\0\0\x0d\0\0\0\x3f\x01\0\0\0\0\0\0\ +\x1a\0\0\0\x21\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\ +\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\ +\0\0\0\0\0\x0a\0\0\0\x01\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\x10\0\0\0\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x6d\ +\x61\x70\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\ +\0\0\0\0\x79\x12\x08\0\0\0\0\0\x15\x02\x3c\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x79\ +\x27\0\0\0\0\0\0\x79\x11\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\ +\0\x07\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\ +\x31\0\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x7b\ +\x6a\xc8\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xb7\x03\0\0\ +\x04\0\0\0\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\x71\x28\0\0\0\0\0\x79\ +\x78\x30\0\0\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\ +\0\x61\x11\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\0\x03\0\0\0\x0f\x13\0\ +\0\0\0\0\0\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\ +\xb7\x02\0\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\ +\0\0\0\0\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\ +\xb7\x02\0\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\ +\xff\0\0\0\0\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\ +\xbf\x69\0\0\0\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\ +\xff\0\0\0\0\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\ +\x1a\xe8\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\x79\xa1\ +\xc8\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x51\0\0\0\xb7\x03\0\0\x11\0\0\0\ +\xb7\x05\0\0\x20\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ +\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x80\x01\0\x01\0\0\0\x42\0\0\ +\0\x7b\0\0\0\x24\x80\x01\0\x02\0\0\0\x42\0\0\0\x60\x02\0\0\x1f\x88\x01\0\x03\0\ +\0\0\x42\0\0\0\x84\x02\0\0\x06\x94\x01\0\x04\0\0\0\x42\0\0\0\x1a\x01\0\0\x17\ +\x84\x01\0\x05\0\0\0\x42\0\0\0\x9d\x02\0\0\x0e\xa0\x01\0\x06\0\0\0\x42\0\0\0\ +\x1a\x01\0\0\x1d\x84\x01\0\x07\0\0\0\x42\0\0\0\x43\x01\0\0\x06\xa4\x01\0\x09\0\ +\0\0\x42\0\0\0\xaf\x02\0\0\x03\xa8\x01\0\x11\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\ +\xb0\x01\0\x18\0\0\0\x42\0\0\0\x5a\x03\0\0\x06\x04\x01\0\x1b\0\0\0\x42\0\0\0\0\ +\0\0\0\0\0\0\0\x1c\0\0\0\x42\0\0\0\xab\x03\0\0\x0f\x10\x01\0\x1d\0\0\0\x42\0\0\ +\0\xc0\x03\0\0\x2d\x14\x01\0\x1f\0\0\0\x42\0\0\0\xf7\x03\0\0\x0d\x0c\x01\0\x21\ +\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x22\0\0\0\x42\0\0\0\xc0\x03\0\0\x02\x14\x01\0\ +\x25\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x28\0\0\0\x42\0\0\0\0\0\0\0\0\0\ +\0\0\x29\0\0\0\x42\0\0\0\x1e\x04\0\0\x0d\x18\x01\0\x2c\0\0\0\x42\0\0\0\x1e\x04\ +\0\0\x0d\x18\x01\0\x2d\0\0\0\x42\0\0\0\x4c\x04\0\0\x1b\x1c\x01\0\x2e\0\0\0\x42\ +\0\0\0\x4c\x04\0\0\x06\x1c\x01\0\x2f\0\0\0\x42\0\0\0\x6f\x04\0\0\x0d\x24\x01\0\ +\x31\0\0\0\x42\0\0\0\x1f\x03\0\0\x02\xb0\x01\0\x40\0\0\0\x42\0\0\0\x2a\x02\0\0\ +\x01\xc0\x01\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\ +\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xea\0\0\0\0\0\0\0\x20\0\0\0\x14\0\0\0\x3e\0\0\0\ +\0\0\0\0\x28\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x30\0\0\0\x08\0\0\0\x3f\x01\0\0\ +\0\0\0\0\x88\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x98\0\0\0\x1a\0\0\0\xea\0\0\0\0\ +\0\0\0\xb0\0\0\0\x1a\0\0\0\x52\x03\0\0\0\0\0\0\xb8\0\0\0\x1a\0\0\0\x56\x03\0\0\ +\0\0\0\0\xc8\0\0\0\x1f\0\0\0\x84\x03\0\0\0\0\0\0\xe0\0\0\0\x20\0\0\0\xea\0\0\0\ +\0\0\0\0\xf8\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x20\x01\0\0\x24\0\0\0\x3e\0\0\0\ +\0\0\0\0\x58\x01\0\0\x1a\0\0\0\xea\0\0\0\0\0\0\0\x68\x01\0\0\x20\0\0\0\x46\x04\ +\0\0\0\0\0\0\x90\x01\0\0\x1a\0\0\0\x3f\x01\0\0\0\0\0\0\xa0\x01\0\0\x1a\0\0\0\ +\x87\x04\0\0\0\0\0\0\xa8\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x42\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0\x1c\0\0\ +\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x1a\0\ +\0\0\x01\0\0\0\0\0\0\0\x13\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\0\ +\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\0\0\ +\0\0\0\0"; + opts.insns_sz = 2184; + opts.insns = (void *)"\ +\xbf\x16\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\x78\xff\xff\xff\xb7\x02\0\ +\0\x88\0\0\0\xb7\x03\0\0\0\0\0\0\x85\0\0\0\x71\0\0\0\x05\0\x14\0\0\0\0\0\x61\ +\xa1\x78\xff\0\0\0\0\xd5\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x7c\xff\ +\0\0\0\0\xd5\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x80\xff\0\0\0\0\xd5\ +\x01\x01\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa1\x84\xff\0\0\0\0\xd5\x01\x01\0\0\ +\0\0\0\x85\0\0\0\xa8\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\ +\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xbf\x70\0\0\ +\0\0\0\0\x95\0\0\0\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ +\x48\x0e\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\ +\0\0\x44\x0e\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\ +\0\0\0\0\x38\x0e\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x05\0\0\ +\x18\x61\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x12\0\ +\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x30\x0e\0\0\xb7\x03\0\0\x1c\0\0\0\x85\0\0\0\ +\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\xd4\xff\0\0\0\0\x63\x7a\x78\xff\0\0\0\0\ +\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x80\x0e\0\0\x63\x01\0\0\0\ +\0\0\0\x61\x60\x20\0\0\0\0\0\x15\0\x03\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ +\x5c\x0e\0\0\x63\x01\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\ +\0\x50\x0e\0\0\xb7\x03\0\0\x48\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\ +\xc5\x07\xc3\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x71\0\0\0\0\0\ +\0\x79\x63\x18\0\0\0\0\0\x15\x03\x04\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x98\ +\x0e\0\0\xb7\x02\0\0\x62\0\0\0\x85\0\0\0\x94\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\x63\x01\0\ +\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ +\x10\x0f\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x98\x0e\0\0\x18\ +\x61\0\0\0\0\0\0\0\0\0\0\x18\x0f\0\0\x7b\x01\0\0\0\0\0\0\xb7\x01\0\0\x02\0\0\0\ +\x18\x62\0\0\0\0\0\0\0\0\0\0\x08\x0f\0\0\xb7\x03\0\0\x20\0\0\0\x85\0\0\0\xa6\0\ +\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\xa3\xff\0\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\x61\x20\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\x63\x01\0\0\ +\0\0\0\0\xb7\x01\0\0\x16\0\0\0\x18\x62\0\0\0\0\0\0\0\0\0\0\x28\x0f\0\0\xb7\x03\ +\0\0\x04\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x96\xff\0\0\0\0\ +\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x0f\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x78\x11\0\ +\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x38\x0f\0\0\x18\x61\0\0\0\0\ +\0\0\0\0\0\0\x70\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x40\ +\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb8\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\ +\0\0\0\0\0\0\0\0\0\x48\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xc8\x11\0\0\x7b\x01\ +\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xe8\x10\0\0\x18\x61\0\0\0\0\0\0\0\0\0\ +\0\xe8\x11\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x18\x61\ +\0\0\0\0\0\0\0\0\0\0\xe0\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\x60\x08\0\0\0\0\0\x18\ +\x61\0\0\0\0\0\0\0\0\0\0\x80\x11\0\0\x63\x01\0\0\0\0\0\0\x61\x60\x0c\0\0\0\0\0\ +\x18\x61\0\0\0\0\0\0\0\0\0\0\x84\x11\0\0\x63\x01\0\0\0\0\0\0\x79\x60\x10\0\0\0\ +\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x88\x11\0\0\x7b\x01\0\0\0\0\0\0\x61\xa0\x78\ +\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\xb0\x11\0\0\x63\x01\0\0\0\0\0\0\x18\ +\x61\0\0\0\0\0\0\0\0\0\0\xf8\x11\0\0\xb7\x02\0\0\x11\0\0\0\xb7\x03\0\0\x0c\0\0\ +\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\0\0\xc5\x07\x60\xff\ +\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x68\x11\0\0\x63\x70\x6c\0\0\0\0\0\x77\x07\ +\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\0\0\0\x18\x62\0\0\0\0\0\0\ +\0\0\0\0\x68\x11\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\0\xbf\x07\0\0\0\0\ +\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd8\x11\0\0\x61\x01\0\0\0\0\0\0\xd5\x01\x02\0\ +\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x4e\xff\0\0\0\0\x63\ +\x7a\x80\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x10\x12\0\0\x18\x61\0\0\0\0\0\ +\0\0\0\0\0\x10\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x18\x12\ +\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x08\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\ +\0\0\0\0\0\0\0\x28\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x50\x17\0\0\x7b\x01\0\0\ +\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x30\x14\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\ +\x60\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\xd0\x15\0\0\x18\ +\x61\0\0\0\0\0\0\0\0\0\0\x80\x17\0\0\x7b\x01\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x78\x17\0\0\x7b\x01\0\0\0\0\0\0\x61\ +\x60\x08\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x18\x17\0\0\x63\x01\0\0\0\0\0\0\ +\x61\x60\x0c\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x1c\x17\0\0\x63\x01\0\0\0\0\ +\0\0\x79\x60\x10\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\x7b\x01\0\0\ +\0\0\0\0\x61\xa0\x78\xff\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x48\x17\0\0\x63\ +\x01\0\0\0\0\0\0\x18\x61\0\0\0\0\0\0\0\0\0\0\x90\x17\0\0\xb7\x02\0\0\x12\0\0\0\ +\xb7\x03\0\0\x0c\0\0\0\xb7\x04\0\0\0\0\0\0\x85\0\0\0\xa7\0\0\0\xbf\x07\0\0\0\0\ +\0\0\xc5\x07\x17\xff\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\x63\x70\x6c\ +\0\0\0\0\0\x77\x07\0\0\x20\0\0\0\x63\x70\x70\0\0\0\0\0\xb7\x01\0\0\x05\0\0\0\ +\x18\x62\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\xb7\x03\0\0\x8c\0\0\0\x85\0\0\0\xa6\0\0\ +\0\xbf\x07\0\0\0\0\0\0\x18\x60\0\0\0\0\0\0\0\0\0\0\x70\x17\0\0\x61\x01\0\0\0\0\ +\0\0\xd5\x01\x02\0\0\0\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\xc5\x07\x05\ +\xff\0\0\0\0\x63\x7a\x84\xff\0\0\0\0\x61\xa1\x78\xff\0\0\0\0\xd5\x01\x02\0\0\0\ +\0\0\xbf\x19\0\0\0\0\0\0\x85\0\0\0\xa8\0\0\0\x61\xa0\x80\xff\0\0\0\0\x63\x06\ +\x28\0\0\0\0\0\x61\xa0\x84\xff\0\0\0\0\x63\x06\x2c\0\0\0\0\0\x18\x61\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\0\0\x63\x06\x18\0\0\0\0\0\xb7\0\0\0\0\0\0\0\ +\x95\0\0\0\0\0\0\0"; + err = bpf_load_and_run(&opts); + if (err < 0) + return err; + skel->rodata = + mmap(skel->rodata, 4096, PROT_READ, MAP_SHARED | MAP_FIXED, + skel->maps.rodata.map_fd, 0); + return 0; +} + +static inline struct iterators_bpf * +iterators_bpf__open_and_load(void) +{ + struct iterators_bpf *skel; + + skel = iterators_bpf__open(); + if (!skel) + return NULL; + if (iterators_bpf__load(skel)) { + iterators_bpf__destroy(skel); + return NULL; + } + return skel; +} + +#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/preload/iterators/iterators.skel.h b/kernel/bpf/preload/iterators/iterators.skel.h deleted file mode 100644 index cf9a6a94b3a4..000000000000 --- a/kernel/bpf/preload/iterators/iterators.skel.h +++ /dev/null @@ -1,412 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ - -/* THIS FILE IS AUTOGENERATED! */ -#ifndef __ITERATORS_BPF_SKEL_H__ -#define __ITERATORS_BPF_SKEL_H__ - -#include <stdlib.h> -#include <bpf/libbpf.h> - -struct iterators_bpf { - struct bpf_object_skeleton *skeleton; - struct bpf_object *obj; - struct { - struct bpf_map *rodata; - } maps; - struct { - struct bpf_program *dump_bpf_map; - struct bpf_program *dump_bpf_prog; - } progs; - struct { - struct bpf_link *dump_bpf_map; - struct bpf_link *dump_bpf_prog; - } links; - struct iterators_bpf__rodata { - char dump_bpf_map____fmt[35]; - char dump_bpf_map____fmt_1[14]; - char dump_bpf_prog____fmt[32]; - char dump_bpf_prog____fmt_2[17]; - } *rodata; -}; - -static void -iterators_bpf__destroy(struct iterators_bpf *obj) -{ - if (!obj) - return; - if (obj->skeleton) - bpf_object__destroy_skeleton(obj->skeleton); - free(obj); -} - -static inline int -iterators_bpf__create_skeleton(struct iterators_bpf *obj); - -static inline struct iterators_bpf * -iterators_bpf__open_opts(const struct bpf_object_open_opts *opts) -{ - struct iterators_bpf *obj; - - obj = (struct iterators_bpf *)calloc(1, sizeof(*obj)); - if (!obj) - return NULL; - if (iterators_bpf__create_skeleton(obj)) - goto err; - if (bpf_object__open_skeleton(obj->skeleton, opts)) - goto err; - - return obj; -err: - iterators_bpf__destroy(obj); - return NULL; -} - -static inline struct iterators_bpf * -iterators_bpf__open(void) -{ - return iterators_bpf__open_opts(NULL); -} - -static inline int -iterators_bpf__load(struct iterators_bpf *obj) -{ - return bpf_object__load_skeleton(obj->skeleton); -} - -static inline struct iterators_bpf * -iterators_bpf__open_and_load(void) -{ - struct iterators_bpf *obj; - - obj = iterators_bpf__open(); - if (!obj) - return NULL; - if (iterators_bpf__load(obj)) { - iterators_bpf__destroy(obj); - return NULL; - } - return obj; -} - -static inline int -iterators_bpf__attach(struct iterators_bpf *obj) -{ - return bpf_object__attach_skeleton(obj->skeleton); -} - -static inline void -iterators_bpf__detach(struct iterators_bpf *obj) -{ - return bpf_object__detach_skeleton(obj->skeleton); -} - -static inline int -iterators_bpf__create_skeleton(struct iterators_bpf *obj) -{ - struct bpf_object_skeleton *s; - - s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s)); - if (!s) - return -1; - obj->skeleton = s; - - s->sz = sizeof(*s); - s->name = "iterators_bpf"; - s->obj = &obj->obj; - - /* maps */ - s->map_cnt = 1; - s->map_skel_sz = sizeof(*s->maps); - s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz); - if (!s->maps) - goto err; - - s->maps[0].name = "iterator.rodata"; - s->maps[0].map = &obj->maps.rodata; - s->maps[0].mmaped = (void **)&obj->rodata; - - /* programs */ - s->prog_cnt = 2; - s->prog_skel_sz = sizeof(*s->progs); - s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz); - if (!s->progs) - goto err; - - s->progs[0].name = "dump_bpf_map"; - s->progs[0].prog = &obj->progs.dump_bpf_map; - s->progs[0].link = &obj->links.dump_bpf_map; - - s->progs[1].name = "dump_bpf_prog"; - s->progs[1].prog = &obj->progs.dump_bpf_prog; - s->progs[1].link = &obj->links.dump_bpf_prog; - - s->data_sz = 7176; - s->data = (void *)"\ -\x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\x48\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\ -\x0e\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\ -\x1a\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\ -\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\xb7\x03\0\0\x23\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x61\x71\0\ -\0\0\0\0\0\x7b\x1a\xe8\xff\0\0\0\0\xb7\x01\0\0\x04\0\0\0\xbf\x72\0\0\0\0\0\0\ -\x0f\x12\0\0\0\0\0\0\x7b\x2a\xf0\xff\0\0\0\0\x61\x71\x14\0\0\0\0\0\x7b\x1a\xf8\ -\xff\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\ -\0\x18\x02\0\0\x23\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x0e\0\0\0\xb7\x05\0\0\x18\ -\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\x79\x12\0\0\0\0\ -\0\0\x79\x26\0\0\0\0\0\0\x79\x11\x08\0\0\0\0\0\x15\x01\x3b\0\0\0\0\0\x79\x17\0\ -\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\ -\x04\0\0\xd0\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x02\0\0\x31\0\0\0\0\0\0\0\0\0\ -\0\0\xb7\x03\0\0\x20\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x7e\0\0\0\x7b\x6a\xc8\ -\xff\0\0\0\0\x61\x71\0\0\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xb7\x03\0\0\x04\0\0\0\ -\xbf\x79\0\0\0\0\0\0\x0f\x39\0\0\0\0\0\0\x79\x71\x28\0\0\0\0\0\x79\x78\x30\0\0\ -\0\0\0\x15\x08\x18\0\0\0\0\0\xb7\x02\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\0\x61\x11\ -\x04\0\0\0\0\0\x79\x83\x08\0\0\0\0\0\x67\x01\0\0\x03\0\0\0\x0f\x13\0\0\0\0\0\0\ -\x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\ -\0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\ -\x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\ -\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\ -\x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\ -\0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\ -\x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\ -\0\0\0\0\xbf\xa4\0\0\0\0\0\0\x07\x04\0\0\xd0\xff\xff\xff\x79\xa1\xc8\xff\0\0\0\ -\0\x18\x02\0\0\x51\0\0\0\0\0\0\0\0\0\0\0\xb7\x03\0\0\x11\0\0\0\xb7\x05\0\0\x20\ -\0\0\0\x85\0\0\0\x7e\0\0\0\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\x20\x20\x69\x64\ -\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\ -\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\ -\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\ -\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\ -\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\x47\x50\x4c\0\x9f\ -\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\x09\x05\0\0\0\0\0\0\0\0\0\ -\x02\x02\0\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\ -\0\0\0\x04\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\ -\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\ -\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xaf\0\0\0\x03\0\0\x04\x18\0\ -\0\0\xbd\0\0\0\x09\0\0\0\0\0\0\0\xc1\0\0\0\x0b\0\0\0\x40\0\0\0\xcc\0\0\0\x0b\0\ -\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd4\0\0\0\0\0\0\x07\0\0\0\0\xdd\0\0\ -\0\0\0\0\x08\x0c\0\0\0\xe3\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xa4\x01\0\0\x03\ -\0\0\x04\x18\0\0\0\xac\x01\0\0\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\ -\0\xb4\x01\0\0\x0e\0\0\0\xa0\0\0\0\xc0\x01\0\0\0\0\0\x08\x0f\0\0\0\xc6\x01\0\0\ -\0\0\0\x01\x04\0\0\0\x20\0\0\0\xd3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\ -\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xd8\x01\0\0\0\0\0\x01\x04\ -\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x3c\x02\0\0\x02\0\0\x04\x10\0\0\0\ -\x13\0\0\0\x03\0\0\0\0\0\0\0\x4f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\ -\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x54\x02\0\0\x01\0\ -\0\x0c\x16\0\0\0\xa0\x02\0\0\x01\0\0\x04\x08\0\0\0\xa9\x02\0\0\x19\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xfa\x02\0\0\x06\0\0\x04\x38\0\0\0\xac\x01\0\0\ -\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\0\x07\x03\0\0\x1b\0\0\0\xc0\0\ -\0\0\x18\x03\0\0\x15\0\0\0\0\x01\0\0\x21\x03\0\0\x1d\0\0\0\x40\x01\0\0\x2b\x03\ -\0\0\x1e\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\ -\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x75\x03\0\0\x02\0\ -\0\x04\x08\0\0\0\x83\x03\0\0\x0e\0\0\0\0\0\0\0\x8c\x03\0\0\x0e\0\0\0\x20\0\0\0\ -\x2b\x03\0\0\x03\0\0\x04\x18\0\0\0\x96\x03\0\0\x1b\0\0\0\0\0\0\0\x9e\x03\0\0\ -\x21\0\0\0\x40\0\0\0\xa4\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\ -\0\0\0\0\0\0\0\0\x02\x24\0\0\0\xa8\x03\0\0\x01\0\0\x04\x04\0\0\0\xb3\x03\0\0\ -\x0e\0\0\0\0\0\0\0\x1c\x04\0\0\x01\0\0\x04\x04\0\0\0\x25\x04\0\0\x0e\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x9b\x04\0\0\0\0\0\ -\x0e\x25\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\ -\xaf\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\ -\x12\0\0\0\x20\0\0\0\xc5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\ -\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xda\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xf1\x04\0\0\0\0\0\x0e\ -\x2d\0\0\0\x01\0\0\0\xf9\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\ -\0\x28\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\ -\0\0\x11\0\0\0\x01\x05\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\ -\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\ -\x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\ -\x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\ -\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x6c\x72\x75\x61\x2f\x62\x75\x69\x6c\ -\x64\x2f\x6c\x69\x6e\x75\x78\x2f\x6b\x65\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\ -\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\ -\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\ -\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\ -\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\ -\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\ -\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\ -\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\x20\x75\x6e\ -\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\x31\0\x09\x73\x74\x72\x75\ -\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\x20\x63\ -\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\x29\0\ -\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\ -\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\ -\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\x29\ -\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\ -\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\ -\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\ -\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\ -\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\ -\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\ -\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\ -\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\ -\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\ -\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\ -\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\ -\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\ -\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\ -\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\ -\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\ -\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\ -\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\ -\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\ -\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\ -\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\ -\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\ -\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\ -\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\ -\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\ -\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\ -\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\ -\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\ -\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\ -\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\ -\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\ -\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\ -\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\ -\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\ -\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\ -\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\ -\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\ -\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\ -\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\ -\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\ -\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\ -\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\ -\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ -\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\ -\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\ -\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\ -\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\ -\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\ -\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\ -\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\0\x62\x02\0\0\x01\0\0\0\ -\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\ -\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x87\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\ -\xfe\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\0\0\0\x1f\x01\0\0\x06\x50\x01\0\x20\0\0\ -\0\x42\0\0\0\x2e\x01\0\0\x1d\x44\x01\0\x28\0\0\0\x42\0\0\0\x53\x01\0\0\x06\x5c\ -\x01\0\x38\0\0\0\x42\0\0\0\x66\x01\0\0\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xec\ -\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\0\x3a\x02\0\0\x01\x70\x01\0\x62\x02\0\ -\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x87\ -\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\x70\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\ -\x42\0\0\0\x94\x02\0\0\x06\x98\x01\0\x20\0\0\0\x42\0\0\0\xad\x02\0\0\x0e\xa4\ -\x01\0\x28\0\0\0\x42\0\0\0\x2e\x01\0\0\x1d\x88\x01\0\x30\0\0\0\x42\0\0\0\x53\ -\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\xbf\x02\0\0\x03\xac\x01\0\x80\0\0\0\ -\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xb8\0\0\0\x42\0\0\0\x6a\x03\0\0\x06\x08\ -\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\x42\0\0\0\xbb\x03\0\0\x0f\ -\x14\x01\0\xe0\0\0\0\x42\0\0\0\xd0\x03\0\0\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\ -\x07\x04\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\ -\0\0\0\xd0\x03\0\0\x02\x18\x01\0\x20\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\ -\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\ -\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\ -\0\x5c\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\0\0\0\x5c\x04\0\0\x06\x20\x01\0\ -\x70\x01\0\0\x42\0\0\0\x7f\x04\0\0\x0d\x28\x01\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\ -\0\0\0\0\x80\x01\0\0\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\ -\x3a\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\ -\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x02\0\0\0\xfa\0\ -\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\ -\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xfa\0\0\0\0\0\0\0\xa0\0\0\0\x0d\0\0\0\x2a\x01\ -\0\0\0\0\0\0\x62\x02\0\0\x12\0\0\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\ -\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xfa\0\0\0\0\0\0\0\x20\0\0\0\ -\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x80\0\0\0\ -\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\xa8\0\0\0\ -\x1a\0\0\0\x62\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\0\x66\x03\0\0\0\0\0\0\xc0\0\0\ -\0\x1f\0\0\0\x94\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\0\0\xfa\0\0\0\0\0\0\0\xf0\0\0\ -\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\ -\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\x60\x01\0\0\x20\0\0\0\x56\x04\0\0\0\0\0\0\x88\ -\x01\0\0\x1a\0\0\0\x2a\x01\0\0\0\0\0\0\x98\x01\0\0\x1a\0\0\0\x97\x04\0\0\0\0\0\ -\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\x91\0\0\0\x04\0\xf1\xff\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xe6\0\0\ -\0\0\0\x02\0\x70\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\0\0\x02\0\xf0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\xdf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\xd1\0\0\0\0\0\x03\0\x80\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xca\0\0\0\0\0\x03\0\ -\xf8\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\ -\0\0\0\0\0\0\0\x04\x01\0\0\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\ -\0\0\0\x01\0\x04\0\x31\0\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\xed\0\0\0\x01\0\x04\0\ -\x51\0\0\0\0\0\0\0\x11\0\0\0\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\x03\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\ -\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\ -\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\ -\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\ -\0\0\x0d\0\0\0\xc8\0\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\ -\0\x0d\0\0\0\xd0\x01\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\ -\0\0\x0d\0\0\0\xfc\x03\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x08\x04\0\0\0\0\0\0\x0a\ -\0\0\0\x0d\0\0\0\x14\x04\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x2c\x04\0\0\0\0\0\0\0\ -\0\0\0\x0e\0\0\0\x2c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x50\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0b\0\ -\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\ -\x90\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xb0\0\ -\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xd0\0\0\0\0\ -\0\0\0\0\0\0\0\x0b\0\0\0\xe8\0\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\0\0\0\0\0\0\0\ -\0\0\0\0\x0c\0\0\0\x08\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x01\0\0\0\0\0\0\0\ -\0\0\0\x0c\0\0\0\x28\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x01\0\0\0\0\0\0\0\0\ -\0\0\x0c\0\0\0\x48\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\ -\0\x0c\0\0\0\x68\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x88\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\xa8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\ -\x0b\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\ -\x0b\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\ -\x0b\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\ -\x0c\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4d\x4e\x40\x41\x42\x43\x4c\0\ -\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\ -\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\ -\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\ -\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\ -\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\ -\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\ -\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\ -\x6e\x73\x65\0\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\ -\x2e\x73\x74\x72\x74\x61\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\ -\x61\x74\x61\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\ -\x4c\x42\x42\x31\x5f\x37\0\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\ -\x4c\x42\x42\x31\x5f\x33\0\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\ -\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\ -\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\ -\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\x40\x01\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\xb1\0\0\0\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\ -\0\0\0\0\0\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\x89\0\0\0\x01\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xbd\0\0\0\x01\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x3d\x09\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\0\0\0\0\xeb\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa9\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\0\0\0\0\x18\x11\0\0\0\0\0\0\x98\x01\0\0\0\0\0\0\x0e\0\0\0\x0e\0\0\0\x08\0\0\ -\0\0\0\0\0\x18\0\0\0\0\0\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ -\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\ -\x10\0\0\0\0\0\0\0\x69\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\ -\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\ -\0\0\0\0\xb9\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xf0\x12\0\0\0\0\0\ -\0\x50\0\0\0\0\0\0\0\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\ -\x07\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x13\0\0\0\0\0\0\xe0\ -\x03\0\0\0\0\0\0\x08\0\0\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\ -\0\0\x03\x4c\xff\x6f\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\0\0\0\0\x07\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\x03\ -\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x27\x17\0\0\0\0\0\0\x1a\x01\0\0\0\0\0\0\ -\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"; - - return 0; -err: - bpf_object__destroy_skeleton(s); - return -1; -} - -#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fa4505f9b611..72ce1edde950 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -556,16 +556,14 @@ static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { - const struct bpf_map *map = filp->private_data; - const struct bpf_array *array; + struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; - if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { - array = container_of(map, struct bpf_array, map); - spin_lock(&array->aux->owner.lock); - type = array->aux->owner.type; - jited = array->aux->owner.jited; - spin_unlock(&array->aux->owner.lock); + if (map_type_contains_progs(map)) { + spin_lock(&map->owner.lock); + type = map->owner.type; + jited = map->owner.jited; + spin_unlock(&map->owner.lock); } seq_printf(m, @@ -874,6 +872,7 @@ static int map_create(union bpf_attr *attr) atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); + spin_lock_init(&map->owner.lock); map->spin_lock_off = -EINVAL; map->timer_off = -EINVAL; @@ -2217,7 +2216,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | - BPF_F_TEST_RND_HI32)) + BPF_F_TEST_RND_HI32 | + BPF_F_XDP_HAS_FRAGS)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -2303,6 +2303,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; + prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; err = security_bpf_prog_alloc(prog->aux); if (err) @@ -3318,6 +3319,11 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_FLOW_DISSECTOR: case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); + case BPF_SK_SKB_STREAM_PARSER: + case BPF_SK_SKB_STREAM_VERDICT: + case BPF_SK_MSG_VERDICT: + case BPF_SK_SKB_VERDICT: + return sock_map_bpf_prog_query(attr, uattr); default: return -EINVAL; } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 5e7edf913060..7224691df2ec 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -213,7 +213,7 @@ static void __bpf_tramp_image_put_deferred(struct work_struct *work) im = container_of(work, struct bpf_tramp_image, work); bpf_image_ksym_del(&im->ksym); bpf_jit_free_exec(im->image); - bpf_jit_uncharge_modmem(1); + bpf_jit_uncharge_modmem(PAGE_SIZE); percpu_ref_exit(&im->pcref); kfree_rcu(im, rcu); } @@ -310,7 +310,7 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) if (!im) goto out; - err = bpf_jit_charge_modmem(1); + err = bpf_jit_charge_modmem(PAGE_SIZE); if (err) goto out_free_im; @@ -332,7 +332,7 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) out_free_image: bpf_jit_free_exec(im->image); out_uncharge: - bpf_jit_uncharge_modmem(1); + bpf_jit_uncharge_modmem(PAGE_SIZE); out_free_im: kfree(im); out: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a39eedecc93a..bbef86cb4e72 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -452,7 +452,8 @@ static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { return base_type(type) == PTR_TO_SOCKET || base_type(type) == PTR_TO_TCP_SOCK || - base_type(type) == PTR_TO_MEM; + base_type(type) == PTR_TO_MEM || + base_type(type) == PTR_TO_BTF_ID; } static bool type_is_rdonly_mem(u32 type) @@ -535,7 +536,7 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) static const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) { - char postfix[16] = {0}, prefix[16] = {0}; + char postfix[16] = {0}, prefix[32] = {0}; static const char * const str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "inv", @@ -569,9 +570,11 @@ static const char *reg_type_str(struct bpf_verifier_env *env, } if (type & MEM_RDONLY) - strncpy(prefix, "rdonly_", 16); + strncpy(prefix, "rdonly_", 32); if (type & MEM_ALLOC) - strncpy(prefix, "alloc_", 16); + strncpy(prefix, "alloc_", 32); + if (type & MEM_USER) + strncpy(prefix, "user_", 32); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); @@ -1546,14 +1549,15 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, static void mark_btf_ld_reg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, enum bpf_reg_type reg_type, - struct btf *btf, u32 btf_id) + struct btf *btf, u32 btf_id, + enum bpf_type_flag flag) { if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, regno); return; } mark_reg_known_zero(env, regs, regno); - regs[regno].type = PTR_TO_BTF_ID; + regs[regno].type = PTR_TO_BTF_ID | flag; regs[regno].btf = btf; regs[regno].btf_id = btf_id; } @@ -1743,7 +1747,7 @@ find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) } static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, - s16 offset, struct module **btf_modp) + s16 offset) { struct bpf_kfunc_btf kf_btf = { .offset = offset }; struct bpf_kfunc_btf_tab *tab; @@ -1797,8 +1801,6 @@ static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); } - if (btf_modp) - *btf_modp = b->module; return b->btf; } @@ -1815,8 +1817,7 @@ void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) } static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, - u32 func_id, s16 offset, - struct module **btf_modp) + u32 func_id, s16 offset) { if (offset) { if (offset < 0) { @@ -1827,7 +1828,7 @@ static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, return ERR_PTR(-EINVAL); } - return __find_kfunc_desc_btf(env, offset, btf_modp); + return __find_kfunc_desc_btf(env, offset); } return btf_vmlinux ?: ERR_PTR(-ENOENT); } @@ -1890,7 +1891,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) prog_aux->kfunc_btf_tab = btf_tab; } - desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL); + desc_btf = find_kfunc_desc_btf(env, func_id, offset); if (IS_ERR(desc_btf)) { verbose(env, "failed to find BTF for kernel function\n"); return PTR_ERR(desc_btf); @@ -2351,7 +2352,7 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; - desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL); + desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off); if (IS_ERR(desc_btf)) return "<error>"; @@ -3498,11 +3499,6 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, #define MAX_PACKET_OFF 0xffff -static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) -{ - return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; -} - static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) @@ -4159,6 +4155,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg = regs + regno; const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); const char *tname = btf_name_by_offset(reg->btf, t->name_off); + enum bpf_type_flag flag = 0; u32 btf_id; int ret; @@ -4178,9 +4175,16 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } + if (reg->type & MEM_USER) { + verbose(env, + "R%d is ptr_%s access user memory: off=%d\n", + regno, tname, off); + return -EACCES; + } + if (env->ops->btf_struct_access) { ret = env->ops->btf_struct_access(&env->log, reg->btf, t, - off, size, atype, &btf_id); + off, size, atype, &btf_id, &flag); } else { if (atype != BPF_READ) { verbose(env, "only read is supported\n"); @@ -4188,14 +4192,14 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, } ret = btf_struct_access(&env->log, reg->btf, t, off, size, - atype, &btf_id); + atype, &btf_id, &flag); } if (ret < 0) return ret; if (atype == BPF_READ && value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id); + mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); return 0; } @@ -4208,6 +4212,7 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, { struct bpf_reg_state *reg = regs + regno; struct bpf_map *map = reg->map_ptr; + enum bpf_type_flag flag = 0; const struct btf_type *t; const char *tname; u32 btf_id; @@ -4245,12 +4250,12 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, return -EACCES; } - ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id); + ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id, &flag); if (ret < 0) return ret; if (value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id); + mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag); return 0; } @@ -4451,7 +4456,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, &btf_id); + err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, + &btf_id); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { @@ -4877,6 +4883,62 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +static int check_mem_size_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + bool zero_size_allowed, + struct bpf_call_arg_meta *meta) +{ + int err; + + /* This is used to refine r0 return value bounds for helpers + * that enforce this value as an upper bound on return values. + * See do_refine_retval_range() for helpers that can refine + * the return value. C type of helper is u32 so we pull register + * bound from umax_value however, if negative verifier errors + * out. Only upper bounds can be learned because retval is an + * int type and negative retvals are allowed. + */ + if (meta) + meta->msize_max_value = reg->umax_value; + + /* The register is SCALAR_VALUE; the access check + * happens using its boundaries. + */ + if (!tnum_is_const(reg->var_off)) + /* For unprivileged variable accesses, disable raw + * mode so that the program is required to + * initialize all the memory that the helper could + * just partially fill up. + */ + meta = NULL; + + if (reg->smin_value < 0) { + verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", + regno); + return -EACCES; + } + + if (reg->umin_value == 0) { + err = check_helper_mem_access(env, regno - 1, 0, + zero_size_allowed, + meta); + if (err) + return err; + } + + if (reg->umax_value >= BPF_MAX_VAR_SIZ) { + verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", + regno); + return -EACCES; + } + err = check_helper_mem_access(env, regno - 1, + reg->umax_value, + zero_size_allowed, meta); + if (!err) + err = mark_chain_precision(env, regno); + return err; +} + int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size) { @@ -4900,6 +4962,28 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return check_helper_mem_access(env, regno, mem_size, true, NULL); } +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno) +{ + struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; + bool may_be_null = type_may_be_null(mem_reg->type); + struct bpf_reg_state saved_reg; + int err; + + WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); + + if (may_be_null) { + saved_reg = *mem_reg; + mark_ptr_not_null_reg(mem_reg); + } + + err = check_mem_size_reg(env, reg, regno, true, NULL); + + if (may_be_null) + *mem_reg = saved_reg; + return err; +} + /* Implementation details: * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL * Two bpf_map_lookups (even with the same key) will have different reg->id. @@ -5439,51 +5523,7 @@ skip_type_check: } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); - /* This is used to refine r0 return value bounds for helpers - * that enforce this value as an upper bound on return values. - * See do_refine_retval_range() for helpers that can refine - * the return value. C type of helper is u32 so we pull register - * bound from umax_value however, if negative verifier errors - * out. Only upper bounds can be learned because retval is an - * int type and negative retvals are allowed. - */ - meta->msize_max_value = reg->umax_value; - - /* The register is SCALAR_VALUE; the access check - * happens using its boundaries. - */ - if (!tnum_is_const(reg->var_off)) - /* For unprivileged variable accesses, disable raw - * mode so that the program is required to - * initialize all the memory that the helper could - * just partially fill up. - */ - meta = NULL; - - if (reg->smin_value < 0) { - verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", - regno); - return -EACCES; - } - - if (reg->umin_value == 0) { - err = check_helper_mem_access(env, regno - 1, 0, - zero_size_allowed, - meta); - if (err) - return err; - } - - if (reg->umax_value >= BPF_MAX_VAR_SIZ) { - verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", - regno); - return -EACCES; - } - err = check_helper_mem_access(env, regno - 1, - reg->umax_value, - zero_size_allowed, meta); - if (!err) - err = mark_chain_precision(env, regno); + err = check_mem_size_reg(env, reg, regno, zero_size_allowed, meta); } else if (arg_type_is_alloc_size(arg_type)) { if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a known constant'\n", @@ -6842,22 +6882,23 @@ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, } } -static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) +static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx_p) { const struct btf_type *t, *func, *func_proto, *ptr_type; struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; u32 i, nargs, func_id, ptr_type_id; - struct module *btf_mod = NULL; + int err, insn_idx = *insn_idx_p; const struct btf_param *args; struct btf *desc_btf; - int err; + bool acq; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) return 0; - desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod); + desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off); if (IS_ERR(desc_btf)) return PTR_ERR(desc_btf); @@ -6866,23 +6907,43 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) func_name = btf_name_by_offset(desc_btf, func->name_off); func_proto = btf_type_by_id(desc_btf, func->type); - if (!env->ops->check_kfunc_call || - !env->ops->check_kfunc_call(func_id, btf_mod)) { + if (!btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_CHECK, func_id)) { verbose(env, "calling kernel function %s is not allowed\n", func_name); return -EACCES; } + acq = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_ACQUIRE, func_id); + /* Check the arguments */ err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs); - if (err) + if (err < 0) return err; + /* In case of release function, we get register number of refcounted + * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now + */ + if (err) { + err = release_reference(env, regs[err].ref_obj_id); + if (err) { + verbose(env, "kfunc %s#%d reference has not been acquired before\n", + func_name, func_id); + return err; + } + } for (i = 0; i < CALLER_SAVED_REGS; i++) mark_reg_not_init(env, regs, caller_saved[i]); /* Check return type */ t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); + + if (acq && !btf_type_is_ptr(t)) { + verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); + return -EINVAL; + } + if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); @@ -6901,7 +6962,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; + if (btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_RET_NULL, func_id)) { + regs[BPF_REG_0].type |= PTR_MAYBE_NULL; + /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ + regs[BPF_REG_0].id = ++env->id_gen; + } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); + if (acq) { + int id = acquire_reference_state(env, insn_idx); + + if (id < 0) + return id; + regs[BPF_REG_0].id = id; + regs[BPF_REG_0].ref_obj_id = id; + } } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ nargs = btf_type_vlen(func_proto); @@ -11549,7 +11624,7 @@ static int do_check(struct bpf_verifier_env *env) if (insn->src_reg == BPF_PSEUDO_CALL) err = check_func_call(env, insn, &env->insn_idx); else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) - err = check_kfunc_call(env, insn); + err = check_kfunc_call(env, insn, &env->insn_idx); else err = check_helper_call(env, insn, &env->insn_idx); if (err) @@ -12992,6 +13067,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) prog->jited = 1; prog->bpf_func = func[0]->bpf_func; + prog->jited_len = func[0]->jited_len; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt; bpf_prog_jit_attempt_done(prog); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 21aa30644219..a2024ba32a20 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1235,6 +1235,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_task_stack_proto; case BPF_FUNC_copy_from_user: return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; + case BPF_FUNC_copy_from_user_task: + return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_per_cpu_ptr: @@ -1562,6 +1564,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { extern const struct bpf_func_proto bpf_skb_output_proto; extern const struct bpf_func_proto bpf_xdp_output_proto; +extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) @@ -1661,6 +1664,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_from_file_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_trace_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 14b89aa37c5c..1555da672275 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -296,7 +296,7 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_DWARF5 bool "Generate DWARF Version 5 debuginfo" depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) - depends on !DEBUG_INFO_BTF + depends on !DEBUG_INFO_BTF || PAHOLE_VERSION >= 121 help Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc 5.0+ accepts the -gdwarf-5 flag but only had partial support for some @@ -323,7 +323,15 @@ config DEBUG_INFO_BTF DWARF type info into equivalent deduplicated BTF type info. config PAHOLE_HAS_SPLIT_BTF - def_bool $(success, test `$(PAHOLE) --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/'` -ge "119") + def_bool PAHOLE_VERSION >= 119 + +config PAHOLE_HAS_BTF_TAG + def_bool PAHOLE_VERSION >= 123 + depends on CC_IS_CLANG + help + Decide whether pahole emits btf_tag attributes (btf_type_tag and + btf_decl_tag) or not. Currently only clang compiler implements + these attributes, so make the config depend on CC_IS_CLANG. config DEBUG_INFO_BTF_MODULES def_bool y diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c index a6789c0c626b..dc7b14aa3431 100644 --- a/lib/ref_tracker.c +++ b/lib/ref_tracker.c @@ -20,6 +20,7 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir) unsigned long flags; bool leak = false; + dir->dead = true; spin_lock_irqsave(&dir->lock, flags); list_for_each_entry_safe(tracker, n, &dir->quarantine, head) { list_del(&tracker->head); @@ -37,6 +38,7 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir) spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(leak); WARN_ON_ONCE(refcount_read(&dir->untracked) != 1); + WARN_ON_ONCE(refcount_read(&dir->no_tracker) != 1); } EXPORT_SYMBOL(ref_tracker_dir_exit); @@ -72,6 +74,12 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir, gfp_t gfp_mask = gfp; unsigned long flags; + WARN_ON_ONCE(dir->dead); + + if (!trackerp) { + refcount_inc(&dir->no_tracker); + return 0; + } if (gfp & __GFP_DIRECT_RECLAIM) gfp_mask |= __GFP_NOFAIL; *trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask); @@ -81,7 +89,6 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir, return -ENOMEM; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); - nr_entries = filter_irq_stacks(entries, nr_entries); tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); spin_lock_irqsave(&dir->lock, flags); @@ -95,17 +102,23 @@ int ref_tracker_free(struct ref_tracker_dir *dir, struct ref_tracker **trackerp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; - struct ref_tracker *tracker = *trackerp; depot_stack_handle_t stack_handle; + struct ref_tracker *tracker; unsigned int nr_entries; unsigned long flags; + WARN_ON_ONCE(dir->dead); + + if (!trackerp) { + refcount_dec(&dir->no_tracker); + return 0; + } + tracker = *trackerp; if (!tracker) { refcount_dec(&dir->untracked); return -EEXIST; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); - nr_entries = filter_irq_stacks(entries, nr_entries); stack_handle = stack_depot_save(entries, nr_entries, GFP_ATOMIC); spin_lock_irqsave(&dir->lock, flags); diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c index a068757eabaf..7b3341cef926 100644 --- a/net/6lowpan/core.c +++ b/net/6lowpan/core.c @@ -5,6 +5,7 @@ * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> */ +#include <linux/if_arp.h> #include <linux/module.h> #include <net/6lowpan.h> diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index 9751207f7757..b7c4d656a94b 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -116,7 +116,6 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) return -ENOMEM; } - refcount_set(&ax25_rt->refcount, 1); ax25_rt->callsign = route->dest_addr; ax25_rt->dev = ax25_dev->dev; ax25_rt->digipeat = NULL; @@ -167,12 +166,12 @@ static int ax25_rt_del(struct ax25_routes_struct *route) ax25cmp(&route->dest_addr, &s->callsign) == 0) { if (ax25_route_list == s) { ax25_route_list = s->next; - ax25_put_route(s); + __ax25_put_route(s); } else { for (t = ax25_route_list; t != NULL; t = t->next) { if (t->next == s) { t->next = s->next; - ax25_put_route(s); + __ax25_put_route(s); break; } } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index f4004cf0ff6f..9f311fddfaf9 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -134,7 +134,7 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev) { struct inet6_dev *in6_dev = __in6_dev_get(dev); - if (in6_dev && in6_dev->cnf.mc_forwarding) + if (in6_dev && atomic_read(&in6_dev->cnf.mc_forwarding)) return BATADV_NO_FLAGS; else return BATADV_MCAST_WANT_NO_RTR6; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 04ebe901e86f..d10651108033 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -689,6 +689,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); + conn->handle = HCI_CONN_HANDLE_UNSET; conn->hdev = hdev; conn->type = type; conn->role = role; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2b7bd3655b07..5bde0ec41177 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2503,6 +2503,7 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_LIST_HEAD(&hdev->adv_instances); INIT_LIST_HEAD(&hdev->blocked_keys); + INIT_LIST_HEAD(&hdev->monitored_devices); INIT_LIST_HEAD(&hdev->local_codecs); INIT_WORK(&hdev->rx_work, hci_rx_work); @@ -3666,8 +3667,8 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) sco_recv_scodata(conn, skb); return; } else { - bt_dev_err(hdev, "SCO packet for unknown connection handle %d", - handle); + bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d", + handle); } kfree_skb(skb); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index fc30f4c03d29..63b925921c87 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3068,6 +3068,11 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, struct hci_ev_conn_complete *ev = data; struct hci_conn *conn; + if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle"); + return; + } + bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); @@ -3106,6 +3111,17 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, } } + /* The HCI_Connection_Complete event is only sent once per connection. + * Processing it more than once per connection can corrupt kernel memory. + * + * As the connection handle is set here for the first time, it indicates + * whether the connection is already set up. + */ + if (conn->handle != HCI_CONN_HANDLE_UNSET) { + bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); + goto unlock; + } + if (!ev->status) { conn->handle = __le16_to_cpu(ev->handle); @@ -4534,7 +4550,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, void *edata, if (!info) { bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); - return; + goto unlock; } bacpy(&data.bdaddr, &info->bdaddr); @@ -4565,7 +4581,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, void *edata, if (!info) { bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); - return; + goto unlock; } bacpy(&data.bdaddr, &info->bdaddr); @@ -4587,7 +4603,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, void *edata, bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); } - +unlock: hci_dev_unlock(hdev); } @@ -4661,6 +4677,24 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, struct hci_ev_sync_conn_complete *ev = data; struct hci_conn *conn; + switch (ev->link_type) { + case SCO_LINK: + case ESCO_LINK: + break; + default: + /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type + * for HCI_Synchronous_Connection_Complete is limited to + * either SCO or eSCO + */ + bt_dev_err(hdev, "Ignoring connect complete event for invalid link type"); + return; + } + + if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle"); + return; + } + bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); @@ -4684,23 +4718,19 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } + /* The HCI_Synchronous_Connection_Complete event is only sent once per connection. + * Processing it more than once per connection can corrupt kernel memory. + * + * As the connection handle is set here for the first time, it indicates + * whether the connection is already set up. + */ + if (conn->handle != HCI_CONN_HANDLE_UNSET) { + bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection"); + goto unlock; + } + switch (ev->status) { case 0x00: - /* The synchronous connection complete event should only be - * sent once per new connection. Receiving a successful - * complete event when the connection status is already - * BT_CONNECTED means that the device is misbehaving and sent - * multiple complete event packets for the same new connection. - * - * Registering the device more than once can corrupt kernel - * memory, hence upon detecting this invalid event, we report - * an error and ignore the packet. - */ - if (conn->state == BT_CONNECTED) { - bt_dev_err(hdev, "Ignoring connect complete event for existing connection"); - goto unlock; - } - conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -5496,6 +5526,11 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, struct smp_irk *irk; u8 addr_type; + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle"); + return; + } + hci_dev_lock(hdev); /* All controllers implicitly stop advertising in the event of a @@ -5537,6 +5572,17 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, cancel_delayed_work(&conn->le_conn_timeout); } + /* The HCI_LE_Connection_Complete event is only sent once per connection. + * Processing it more than once per connection can corrupt kernel memory. + * + * As the connection handle is set here for the first time, it indicates + * whether the connection is already set up. + */ + if (conn->handle != HCI_CONN_HANDLE_UNSET) { + bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); + goto unlock; + } + le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa); /* Lookup the identity address from the stored connection @@ -6798,7 +6844,7 @@ static const struct hci_ev { HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt, sizeof(struct hci_ev_num_comp_blocks)), /* [0xff = HCI_EV_VENDOR] */ - HCI_EV(HCI_EV_VENDOR, msft_vendor_evt, 0), + HCI_EV_VL(HCI_EV_VENDOR, msft_vendor_evt, 0, HCI_MAX_EVENT_SIZE), }; static void hci_event_func(struct hci_dev *hdev, u8 event, struct sk_buff *skb, @@ -6823,8 +6869,9 @@ static void hci_event_func(struct hci_dev *hdev, u8 event, struct sk_buff *skb, * decide if that is acceptable. */ if (skb->len > ev->max_len) - bt_dev_warn(hdev, "unexpected event 0x%2.2x length: %u > %u", - event, skb->len, ev->max_len); + bt_dev_warn_ratelimited(hdev, + "unexpected event 0x%2.2x length: %u > %u", + event, skb->len, ev->max_len); data = hci_ev_skb_pull(hdev, skb, event, ev->min_len); if (!data) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 0feb68f12545..6e71aa6b6fea 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -382,6 +382,9 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, { struct hci_cmd_sync_work_entry *entry; + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return -ENODEV; + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; @@ -5140,8 +5143,8 @@ static void set_ext_conn_params(struct hci_conn *conn, p->max_ce_len = cpu_to_le16(0x0000); } -int hci_le_ext_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, - u8 own_addr_type) +static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn, u8 own_addr_type) { struct hci_cp_le_ext_create_conn *cp; struct hci_cp_le_ext_conn_param *p; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 37087cf7dc5a..5dd684e0b259 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -42,7 +42,7 @@ #include "aosp.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 21 +#define MGMT_REVISION 22 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -174,6 +174,8 @@ static const u16 mgmt_events[] = { MGMT_EV_ADV_MONITOR_REMOVED, MGMT_EV_CONTROLLER_SUSPEND, MGMT_EV_CONTROLLER_RESUME, + MGMT_EV_ADV_MONITOR_DEVICE_FOUND, + MGMT_EV_ADV_MONITOR_DEVICE_LOST, }; static const u16 mgmt_untrusted_commands[] = { @@ -9589,12 +9591,116 @@ static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir, return true; } +void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type) +{ + struct mgmt_ev_adv_monitor_device_lost ev; + + ev.monitor_handle = cpu_to_le16(handle); + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = addr_type; + + mgmt_event(MGMT_EV_ADV_MONITOR_DEVICE_LOST, hdev, &ev, sizeof(ev), + NULL); +} + +static void mgmt_adv_monitor_device_found(struct hci_dev *hdev, + bdaddr_t *bdaddr, bool report_device, + struct sk_buff *skb, + struct sock *skip_sk) +{ + struct sk_buff *advmon_skb; + size_t advmon_skb_len; + __le16 *monitor_handle; + struct monitored_device *dev, *tmp; + bool matched = false; + bool notify = false; + + /* We have received the Advertisement Report because: + * 1. the kernel has initiated active discovery + * 2. if not, we have pend_le_reports > 0 in which case we are doing + * passive scanning + * 3. if none of the above is true, we have one or more active + * Advertisement Monitor + * + * For case 1 and 2, report all advertisements via MGMT_EV_DEVICE_FOUND + * and report ONLY one advertisement per device for the matched Monitor + * via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event. + * + * For case 3, since we are not active scanning and all advertisements + * received are due to a matched Advertisement Monitor, report all + * advertisements ONLY via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event. + */ + if (report_device && !hdev->advmon_pend_notify) { + mgmt_event_skb(skb, skip_sk); + return; + } + + advmon_skb_len = (sizeof(struct mgmt_ev_adv_monitor_device_found) - + sizeof(struct mgmt_ev_device_found)) + skb->len; + advmon_skb = mgmt_alloc_skb(hdev, MGMT_EV_ADV_MONITOR_DEVICE_FOUND, + advmon_skb_len); + if (!advmon_skb) { + if (report_device) + mgmt_event_skb(skb, skip_sk); + else + kfree_skb(skb); + return; + } + + /* ADV_MONITOR_DEVICE_FOUND is similar to DEVICE_FOUND event except + * that it also has 'monitor_handle'. Make a copy of DEVICE_FOUND and + * store monitor_handle of the matched monitor. + */ + monitor_handle = skb_put(advmon_skb, sizeof(*monitor_handle)); + skb_put_data(advmon_skb, skb->data, skb->len); + + hdev->advmon_pend_notify = false; + + list_for_each_entry_safe(dev, tmp, &hdev->monitored_devices, list) { + if (!bacmp(&dev->bdaddr, bdaddr)) { + matched = true; + + if (!dev->notified) { + *monitor_handle = cpu_to_le16(dev->handle); + notify = true; + dev->notified = true; + } + } + + if (!dev->notified) + hdev->advmon_pend_notify = true; + } + + if (!report_device && + ((matched && !notify) || !msft_monitor_supported(hdev))) { + /* Handle 0 indicates that we are not active scanning and this + * is a subsequent advertisement report for an already matched + * Advertisement Monitor or the controller offloading support + * is not available. + */ + *monitor_handle = 0; + notify = true; + } + + if (report_device) + mgmt_event_skb(skb, skip_sk); + else + kfree_skb(skb); + + if (notify) + mgmt_event_skb(advmon_skb, skip_sk); + else + kfree_skb(advmon_skb); +} + void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len) { struct sk_buff *skb; struct mgmt_ev_device_found *ev; + bool report_device = hci_discovery_active(hdev); /* Don't send events for a non-kernel initiated discovery. With * LE one exception is if we have pend_le_reports > 0 in which @@ -9603,11 +9709,10 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, if (!hci_discovery_active(hdev)) { if (link_type == ACL_LINK) return; - if (link_type == LE_LINK && - list_empty(&hdev->pend_le_reports) && - !hci_is_adv_monitoring(hdev)) { + if (link_type == LE_LINK && !list_empty(&hdev->pend_le_reports)) + report_device = true; + else if (!hci_is_adv_monitoring(hdev)) return; - } } if (hdev->discovery.result_filtering) { @@ -9672,7 +9777,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len); - mgmt_event_skb(skb, NULL); + mgmt_adv_monitor_device_found(hdev, bdaddr, report_device, skb, NULL); } void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 6a943634b31a..9a3d77d3ca86 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -80,6 +80,14 @@ struct msft_rp_le_set_advertisement_filter_enable { __u8 sub_opcode; } __packed; +#define MSFT_EV_LE_MONITOR_DEVICE 0x02 +struct msft_ev_le_monitor_device { + __u8 addr_type; + bdaddr_t bdaddr; + __u8 monitor_handle; + __u8 monitor_state; +} __packed; + struct msft_monitor_advertisement_handle_data { __u8 msft_handle; __u16 mgmt_handle; @@ -204,6 +212,37 @@ static struct msft_monitor_advertisement_handle_data *msft_find_handle_data return NULL; } +/* This function requires the caller holds hdev->lock */ +static int msft_monitor_device_del(struct hci_dev *hdev, __u16 mgmt_handle, + bdaddr_t *bdaddr, __u8 addr_type, + bool notify) +{ + struct monitored_device *dev, *tmp; + int count = 0; + + list_for_each_entry_safe(dev, tmp, &hdev->monitored_devices, list) { + /* mgmt_handle == 0 indicates remove all devices, whereas, + * bdaddr == NULL indicates remove all devices matching the + * mgmt_handle. + */ + if ((!mgmt_handle || dev->handle == mgmt_handle) && + (!bdaddr || (!bacmp(bdaddr, &dev->bdaddr) && + addr_type == dev->addr_type))) { + if (notify && dev->notified) { + mgmt_adv_monitor_device_lost(hdev, dev->handle, + &dev->bdaddr, + dev->addr_type); + } + + list_del(&dev->list); + kfree(dev); + count++; + } + } + + return count; +} + static void msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) @@ -294,6 +333,10 @@ static void msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, if (monitor && !msft->suspending) hci_free_adv_monitor(hdev, monitor); + /* Clear any monitored devices by this Adv Monitor */ + msft_monitor_device_del(hdev, handle_data->mgmt_handle, NULL, + 0, false); + list_del(&handle_data->list); kfree(handle_data); } @@ -557,6 +600,14 @@ void msft_do_close(struct hci_dev *hdev) list_del(&handle_data->list); kfree(handle_data); } + + hci_dev_lock(hdev); + + /* Clear any devices that are being monitored and notify device lost */ + hdev->advmon_pend_notify = false; + msft_monitor_device_del(hdev, 0, NULL, 0, true); + + hci_dev_unlock(hdev); } void msft_register(struct hci_dev *hdev) @@ -590,10 +641,101 @@ void msft_unregister(struct hci_dev *hdev) kfree(msft); } +/* This function requires the caller holds hdev->lock */ +static void msft_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, + __u8 addr_type, __u16 mgmt_handle) +{ + struct monitored_device *dev; + + dev = kmalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) { + bt_dev_err(hdev, "MSFT vendor event %u: no memory", + MSFT_EV_LE_MONITOR_DEVICE); + return; + } + + bacpy(&dev->bdaddr, bdaddr); + dev->addr_type = addr_type; + dev->handle = mgmt_handle; + dev->notified = false; + + INIT_LIST_HEAD(&dev->list); + list_add(&dev->list, &hdev->monitored_devices); + hdev->advmon_pend_notify = true; +} + +/* This function requires the caller holds hdev->lock */ +static void msft_device_lost(struct hci_dev *hdev, bdaddr_t *bdaddr, + __u8 addr_type, __u16 mgmt_handle) +{ + if (!msft_monitor_device_del(hdev, mgmt_handle, bdaddr, addr_type, + true)) { + bt_dev_err(hdev, "MSFT vendor event %u: dev %pMR not in list", + MSFT_EV_LE_MONITOR_DEVICE, bdaddr); + } +} + +static void *msft_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, + u8 ev, size_t len) +{ + void *data; + + data = skb_pull_data(skb, len); + if (!data) + bt_dev_err(hdev, "Malformed MSFT vendor event: 0x%02x", ev); + + return data; +} + +/* This function requires the caller holds hdev->lock */ +static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct msft_ev_le_monitor_device *ev; + struct msft_monitor_advertisement_handle_data *handle_data; + u8 addr_type; + + ev = msft_skb_pull(hdev, skb, MSFT_EV_LE_MONITOR_DEVICE, sizeof(*ev)); + if (!ev) + return; + + bt_dev_dbg(hdev, + "MSFT vendor event 0x%02x: handle 0x%04x state %d addr %pMR", + MSFT_EV_LE_MONITOR_DEVICE, ev->monitor_handle, + ev->monitor_state, &ev->bdaddr); + + handle_data = msft_find_handle_data(hdev, ev->monitor_handle, false); + if (!handle_data) + return; + + switch (ev->addr_type) { + case ADDR_LE_DEV_PUBLIC: + addr_type = BDADDR_LE_PUBLIC; + break; + + case ADDR_LE_DEV_RANDOM: + addr_type = BDADDR_LE_RANDOM; + break; + + default: + bt_dev_err(hdev, + "MSFT vendor event 0x%02x: unknown addr type 0x%02x", + MSFT_EV_LE_MONITOR_DEVICE, ev->addr_type); + return; + } + + if (ev->monitor_state) + msft_device_found(hdev, &ev->bdaddr, addr_type, + handle_data->mgmt_handle); + else + msft_device_lost(hdev, &ev->bdaddr, addr_type, + handle_data->mgmt_handle); +} + void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct msft_data *msft = hdev->msft_data; - u8 event; + u8 *evt_prefix; + u8 *evt; if (!msft) return; @@ -602,13 +744,12 @@ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) * matches, and otherwise just return. */ if (msft->evt_prefix_len > 0) { - if (skb->len < msft->evt_prefix_len) + evt_prefix = msft_skb_pull(hdev, skb, 0, msft->evt_prefix_len); + if (!evt_prefix) return; - if (memcmp(skb->data, msft->evt_prefix, msft->evt_prefix_len)) + if (memcmp(evt_prefix, msft->evt_prefix, msft->evt_prefix_len)) return; - - skb_pull(skb, msft->evt_prefix_len); } /* Every event starts at least with an event code and the rest of @@ -617,10 +758,23 @@ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) if (skb->len < 1) return; - event = *skb->data; - skb_pull(skb, 1); + evt = msft_skb_pull(hdev, skb, 0, sizeof(*evt)); + if (!evt) + return; + + hci_dev_lock(hdev); + + switch (*evt) { + case MSFT_EV_LE_MONITOR_DEVICE: + msft_monitor_device_evt(hdev, skb); + break; - bt_dev_dbg(hdev, "MSFT vendor event %u", event); + default: + bt_dev_dbg(hdev, "MSFT vendor event 0x%02x", *evt); + break; + } + + hci_dev_unlock(hdev); } __u64 msft_get_features(struct hci_dev *hdev) diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index fbc896323bec..d0e54e30658a 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -145,7 +145,8 @@ static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id) + u32 *next_btf_id, + enum bpf_type_flag *flag) { const struct btf_type *state; s32 type_id; @@ -162,7 +163,8 @@ static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, return -EACCES; } - err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id); + err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id, + flag); if (err < 0) return err; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 46dd95755967..f08034500813 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -5,6 +5,7 @@ #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/slab.h> +#include <linux/init.h> #include <linux/vmalloc.h> #include <linux/etherdevice.h> #include <linux/filter.h> @@ -130,7 +131,8 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, static int bpf_test_finish(const union bpf_attr *kattr, union bpf_attr __user *uattr, const void *data, - u32 size, u32 retval, u32 duration) + struct skb_shared_info *sinfo, u32 size, + u32 retval, u32 duration) { void __user *data_out = u64_to_user_ptr(kattr->test.data_out); int err = -EFAULT; @@ -145,8 +147,37 @@ static int bpf_test_finish(const union bpf_attr *kattr, err = -ENOSPC; } - if (data_out && copy_to_user(data_out, data, copy_size)) - goto out; + if (data_out) { + int len = sinfo ? copy_size - sinfo->xdp_frags_size : copy_size; + + if (copy_to_user(data_out, data, len)) + goto out; + + if (sinfo) { + int i, offset = len; + u32 data_len; + + for (i = 0; i < sinfo->nr_frags; i++) { + skb_frag_t *frag = &sinfo->frags[i]; + + if (offset >= copy_size) { + err = -ENOSPC; + break; + } + + data_len = min_t(u32, copy_size - offset, + skb_frag_size(frag)); + + if (copy_to_user(data_out + offset, + skb_frag_address(frag), + data_len)) + goto out; + + offset += data_len; + } + } + } + if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size))) goto out; if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) @@ -171,6 +202,8 @@ int noinline bpf_fentry_test1(int a) { return a + 1; } +EXPORT_SYMBOL_GPL(bpf_fentry_test1); +ALLOW_ERROR_INJECTION(bpf_fentry_test1, ERRNO); int noinline bpf_fentry_test2(int a, u64 b) { @@ -232,28 +265,142 @@ struct sock * noinline bpf_kfunc_call_test3(struct sock *sk) return sk; } +struct prog_test_ref_kfunc { + int a; + int b; + struct prog_test_ref_kfunc *next; +}; + +static struct prog_test_ref_kfunc prog_test_struct = { + .a = 42, + .b = 108, + .next = &prog_test_struct, +}; + +noinline struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) +{ + /* randomly return NULL */ + if (get_jiffies_64() % 2) + return NULL; + return &prog_test_struct; +} + +noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) +{ +} + +struct prog_test_pass1 { + int x0; + struct { + int x1; + struct { + int x2; + struct { + int x3; + }; + }; + }; +}; + +struct prog_test_pass2 { + int len; + short arr1[4]; + struct { + char arr2[4]; + unsigned long arr3[8]; + } x; +}; + +struct prog_test_fail1 { + void *p; + int x; +}; + +struct prog_test_fail2 { + int x8; + struct prog_test_pass1 x; +}; + +struct prog_test_fail3 { + int len; + char arr1[2]; + char arr2[]; +}; + +noinline void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +noinline void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +{ +} + +noinline void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +{ +} + +noinline void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +{ +} + +noinline void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +{ +} + +noinline void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +{ +} + +noinline void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +{ +} + +noinline void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +{ +} + +noinline void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +{ +} + __diag_pop(); ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); -BTF_SET_START(test_sk_kfunc_ids) +BTF_SET_START(test_sk_check_kfunc_ids) BTF_ID(func, bpf_kfunc_call_test1) BTF_ID(func, bpf_kfunc_call_test2) BTF_ID(func, bpf_kfunc_call_test3) -BTF_SET_END(test_sk_kfunc_ids) - -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner) -{ - if (btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id)) - return true; - return bpf_check_mod_kfunc_call(&prog_test_kfunc_list, kfunc_id, owner); -} - -static void *bpf_test_init(const union bpf_attr *kattr, u32 size, - u32 headroom, u32 tailroom) +BTF_ID(func, bpf_kfunc_call_test_acquire) +BTF_ID(func, bpf_kfunc_call_test_release) +BTF_ID(func, bpf_kfunc_call_test_pass_ctx) +BTF_ID(func, bpf_kfunc_call_test_pass1) +BTF_ID(func, bpf_kfunc_call_test_pass2) +BTF_ID(func, bpf_kfunc_call_test_fail1) +BTF_ID(func, bpf_kfunc_call_test_fail2) +BTF_ID(func, bpf_kfunc_call_test_fail3) +BTF_ID(func, bpf_kfunc_call_test_mem_len_pass1) +BTF_ID(func, bpf_kfunc_call_test_mem_len_fail1) +BTF_ID(func, bpf_kfunc_call_test_mem_len_fail2) +BTF_SET_END(test_sk_check_kfunc_ids) + +BTF_SET_START(test_sk_acquire_kfunc_ids) +BTF_ID(func, bpf_kfunc_call_test_acquire) +BTF_SET_END(test_sk_acquire_kfunc_ids) + +BTF_SET_START(test_sk_release_kfunc_ids) +BTF_ID(func, bpf_kfunc_call_test_release) +BTF_SET_END(test_sk_release_kfunc_ids) + +BTF_SET_START(test_sk_ret_null_kfunc_ids) +BTF_ID(func, bpf_kfunc_call_test_acquire) +BTF_SET_END(test_sk_ret_null_kfunc_ids) + +static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, + u32 size, u32 headroom, u32 tailroom) { void __user *data_in = u64_to_user_ptr(kattr->test.data_in); - u32 user_size = kattr->test.data_size_in; void *data; if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) @@ -581,7 +728,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, if (kattr->test.flags || kattr->test.cpu) return -EINVAL; - data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, + data = bpf_test_init(kattr, kattr->test.data_size_in, + size, NET_SKB_PAD + NET_IP_ALIGN, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (IS_ERR(data)) return PTR_ERR(data); @@ -683,7 +831,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) size = skb_headlen(skb); - ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration); + ret = bpf_test_finish(kattr, uattr, skb->data, NULL, size, retval, + duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct __sk_buff)); @@ -758,16 +907,16 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - u32 headroom = XDP_PACKET_HEADROOM; u32 size = kattr->test.data_size_in; + u32 headroom = XDP_PACKET_HEADROOM; + u32 retval, duration, max_data_sz; u32 repeat = kattr->test.repeat; struct netdev_rx_queue *rxqueue; + struct skb_shared_info *sinfo; struct xdp_buff xdp = {}; - u32 retval, duration; + int i, ret = -EINVAL; struct xdp_md *ctx; - u32 max_data_sz; void *data; - int ret = -EINVAL; if (prog->expected_attach_type == BPF_XDP_DEVMAP || prog->expected_attach_type == BPF_XDP_CPUMAP) @@ -787,26 +936,65 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, headroom -= ctx->data; } - /* XDP have extra tailroom as (most) drivers use full page */ max_data_sz = 4096 - headroom - tailroom; + size = min_t(u32, size, max_data_sz); - data = bpf_test_init(kattr, max_data_sz, headroom, tailroom); + data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom); if (IS_ERR(data)) { ret = PTR_ERR(data); goto free_ctx; } rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); - xdp_init_buff(&xdp, headroom + max_data_sz + tailroom, - &rxqueue->xdp_rxq); + rxqueue->xdp_rxq.frag_size = headroom + max_data_sz + tailroom; + xdp_init_buff(&xdp, rxqueue->xdp_rxq.frag_size, &rxqueue->xdp_rxq); xdp_prepare_buff(&xdp, data, headroom, size, true); + sinfo = xdp_get_shared_info_from_buff(&xdp); ret = xdp_convert_md_to_buff(ctx, &xdp); if (ret) goto free_data; + if (unlikely(kattr->test.data_size_in > size)) { + void __user *data_in = u64_to_user_ptr(kattr->test.data_in); + + while (size < kattr->test.data_size_in) { + struct page *page; + skb_frag_t *frag; + u32 data_len; + + if (sinfo->nr_frags == MAX_SKB_FRAGS) { + ret = -ENOMEM; + goto out; + } + + page = alloc_page(GFP_KERNEL); + if (!page) { + ret = -ENOMEM; + goto out; + } + + frag = &sinfo->frags[sinfo->nr_frags++]; + __skb_frag_set_page(frag, page); + + data_len = min_t(u32, kattr->test.data_size_in - size, + PAGE_SIZE); + skb_frag_size_set(frag, data_len); + + if (copy_from_user(page_address(page), data_in + size, + data_len)) { + ret = -EFAULT; + goto out; + } + sinfo->xdp_frags_size += data_len; + size += data_len; + } + xdp_buff_set_frags_flag(&xdp); + } + if (repeat > 1) bpf_prog_change_xdp(NULL, prog); + ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented @@ -816,12 +1004,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (ret) goto out; - if (xdp.data_meta != data + headroom || - xdp.data_end != xdp.data_meta + size) - size = xdp.data_end - xdp.data_meta; - - ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval, - duration); + size = xdp.data_end - xdp.data_meta + sinfo->xdp_frags_size; + ret = bpf_test_finish(kattr, uattr, xdp.data_meta, sinfo, size, + retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct xdp_md)); @@ -830,6 +1015,8 @@ out: if (repeat > 1) bpf_prog_change_xdp(prog, NULL); free_data: + for (i = 0; i < sinfo->nr_frags; i++) + __free_page(skb_frag_page(&sinfo->frags[i])); kfree(data); free_ctx: kfree(ctx); @@ -876,7 +1063,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (size < ETH_HLEN) return -EINVAL; - data = bpf_test_init(kattr, size, 0, 0); + data = bpf_test_init(kattr, kattr->test.data_size_in, size, 0, 0); if (IS_ERR(data)) return PTR_ERR(data); @@ -911,8 +1098,8 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (ret < 0) goto out; - ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), - retval, duration); + ret = bpf_test_finish(kattr, uattr, &flow_keys, NULL, + sizeof(flow_keys), retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(struct bpf_flow_keys)); @@ -960,7 +1147,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx))) goto out; - if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) { + if (user_ctx->local_port > U16_MAX) { ret = -ERANGE; goto out; } @@ -968,7 +1155,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat ctx.family = (u16)user_ctx->family; ctx.protocol = (u16)user_ctx->protocol; ctx.dport = (u16)user_ctx->local_port; - ctx.sport = (__force __be16)user_ctx->remote_port; + ctx.sport = user_ctx->remote_port; switch (ctx.family) { case AF_INET: @@ -1016,7 +1203,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat user_ctx->cookie = sock_gen_cookie(ctx.selected_sk); } - ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration); + ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx)); @@ -1067,3 +1254,17 @@ out: kfree(ctx); return err; } + +static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &test_sk_check_kfunc_ids, + .acquire_set = &test_sk_acquire_kfunc_ids, + .release_set = &test_sk_release_kfunc_ids, + .ret_null_set = &test_sk_ret_null_kfunc_ids, +}; + +static int __init bpf_prog_test_run_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set); +} +late_initcall(bpf_prog_test_run_init); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2661dda1a92b..48bc61ebc211 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1985,7 +1985,7 @@ void br_switchdev_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, int type); int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, - struct netlink_ext_ack *extack); + bool changed, struct netlink_ext_ack *extack); int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid); void br_switchdev_init(struct net_bridge *br); @@ -2052,8 +2052,8 @@ static inline int br_switchdev_set_port_flag(struct net_bridge_port *p, return 0; } -static inline int br_switchdev_port_vlan_add(struct net_device *dev, - u16 vid, u16 flags, +static inline int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, + u16 flags, bool changed, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index f8fbaaa7c501..59fcabd08ef1 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -160,13 +160,14 @@ br_switchdev_fdb_notify(struct net_bridge *br, } int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, - struct netlink_ext_ack *extack) + bool changed, struct netlink_ext_ack *extack) { struct switchdev_obj_port_vlan v = { .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .flags = flags, .vid = vid, + .changed = changed, }; return switchdev_port_obj_add(dev, &v.obj, extack); @@ -351,51 +352,19 @@ br_switchdev_vlan_replay_one(struct notifier_block *nb, return notifier_to_errno(err); } -static int br_switchdev_vlan_replay(struct net_device *br_dev, - struct net_device *dev, - const void *ctx, bool adding, - struct notifier_block *nb, - struct netlink_ext_ack *extack) +static int br_switchdev_vlan_replay_group(struct notifier_block *nb, + struct net_device *dev, + struct net_bridge_vlan_group *vg, + const void *ctx, unsigned long action, + struct netlink_ext_ack *extack) { - struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; - struct net_bridge_port *p; - struct net_bridge *br; - unsigned long action; int err = 0; u16 pvid; - ASSERT_RTNL(); - - if (!nb) - return 0; - - if (!netif_is_bridge_master(br_dev)) - return -EINVAL; - - if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) - return -EINVAL; - - if (netif_is_bridge_master(dev)) { - br = netdev_priv(dev); - vg = br_vlan_group(br); - p = NULL; - } else { - p = br_port_get_rtnl(dev); - if (WARN_ON(!p)) - return -EINVAL; - vg = nbp_vlan_group(p); - br = p->br; - } - if (!vg) return 0; - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; - pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { @@ -415,7 +384,48 @@ static int br_switchdev_vlan_replay(struct net_device *br_dev, return err; } - return err; + return 0; +} + +static int br_switchdev_vlan_replay(struct net_device *br_dev, + const void *ctx, bool adding, + struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + struct net_bridge *br = netdev_priv(br_dev); + struct net_bridge_port *p; + unsigned long action; + int err; + + ASSERT_RTNL(); + + if (!nb) + return 0; + + if (!netif_is_bridge_master(br_dev)) + return -EINVAL; + + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + err = br_switchdev_vlan_replay_group(nb, br_dev, br_vlan_group(br), + ctx, action, extack); + if (err) + return err; + + list_for_each_entry(p, &br->port_list, list) { + struct net_device *dev = p->dev; + + err = br_switchdev_vlan_replay_group(nb, dev, + nbp_vlan_group(p), + ctx, action, extack); + if (err) + return err; + } + + return 0; } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING @@ -681,8 +691,7 @@ static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, struct net_device *dev = p->dev; int err; - err = br_switchdev_vlan_replay(br_dev, dev, ctx, true, blocking_nb, - extack); + err = br_switchdev_vlan_replay(br_dev, ctx, true, blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; @@ -706,11 +715,11 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, struct net_device *br_dev = p->br->dev; struct net_device *dev = p->dev; - br_switchdev_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL); + br_switchdev_fdb_replay(br_dev, ctx, false, atomic_nb); br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); - br_switchdev_fdb_replay(br_dev, ctx, false, atomic_nb); + br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL); } /* Let the bridge know that this port is offloaded, so that it can assign a diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 1402d5ca242d..7557e90b60e1 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -34,53 +34,70 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } -static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, +static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, const struct net_bridge_vlan *v) { if (vg->pvid == v->vid) - return false; + return; smp_wmb(); br_vlan_set_pvid_state(vg, v->state); vg->pvid = v->vid; - - return true; } -static bool __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) +static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid != vid) - return false; + return; smp_wmb(); vg->pvid = 0; - - return true; } -/* return true if anything changed, false otherwise */ -static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) +/* Update the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED flags of @v. + * If @commit is false, return just whether the BRIDGE_VLAN_INFO_PVID and + * BRIDGE_VLAN_INFO_UNTAGGED bits of @flags would produce any change onto @v. + */ +static bool __vlan_flags_update(struct net_bridge_vlan *v, u16 flags, + bool commit) { struct net_bridge_vlan_group *vg; - u16 old_flags = v->flags; - bool ret; + bool change; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); + /* check if anything would be changed on commit */ + change = !!(flags & BRIDGE_VLAN_INFO_PVID) == !!(vg->pvid != v->vid) || + ((flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED); + + if (!commit) + goto out; + if (flags & BRIDGE_VLAN_INFO_PVID) - ret = __vlan_add_pvid(vg, v); + __vlan_add_pvid(vg, v); else - ret = __vlan_delete_pvid(vg, v->vid); + __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; - return ret || !!(old_flags ^ v->flags); +out: + return change; +} + +static bool __vlan_flags_would_change(struct net_bridge_vlan *v, u16 flags) +{ + return __vlan_flags_update(v, flags, false); +} + +static void __vlan_flags_commit(struct net_bridge_vlan *v, u16 flags) +{ + __vlan_flags_update(v, flags, true); } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, @@ -92,7 +109,7 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ - err = br_switchdev_port_vlan_add(dev, v->vid, flags, extack); + err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err == -EOPNOTSUPP) return vlan_vid_add(dev, br->vlan_proto, v->vid); v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV; @@ -284,9 +301,12 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, } br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx); } else { - err = br_switchdev_port_vlan_add(dev, v->vid, flags, extack); - if (err && err != -EOPNOTSUPP) - goto out; + if (br_vlan_should_use(v)) { + err = br_switchdev_port_vlan_add(dev, v->vid, flags, + false, extack); + if (err && err != -EOPNOTSUPP) + goto out; + } br_multicast_ctx_init(br, v, &v->br_mcast_ctx); v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED; } @@ -310,7 +330,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, goto out_fdb_insert; __vlan_add_list(v); - __vlan_add_flags(v, flags); + __vlan_flags_commit(v, flags); br_multicast_toggle_one_vlan(v, true); if (p) @@ -404,6 +424,7 @@ static void __vlan_flush(const struct net_bridge *br, { struct net_bridge_vlan *vlan, *tmp; u16 v_start = 0, v_end = 0; + int err; __vlan_delete_pvid(vg, vg->pvid); list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { @@ -417,7 +438,13 @@ static void __vlan_flush(const struct net_bridge *br, } v_end = vlan->vid; - __vlan_del(vlan); + err = __vlan_del(vlan); + if (err) { + br_err(br, + "port %u(%s) failed to delete vlan %d: %pe\n", + (unsigned int) p->port_no, p->dev->name, + vlan->vid, ERR_PTR(err)); + } } /* notify about the last/whole vlan range */ @@ -670,18 +697,29 @@ static int br_vlan_add_existing(struct net_bridge *br, u16 flags, bool *changed, struct netlink_ext_ack *extack) { + bool would_change = __vlan_flags_would_change(vlan, flags); + bool becomes_brentry = false; int err; - err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, extack); - if (err && err != -EOPNOTSUPP) - return err; - if (!br_vlan_is_brentry(vlan)) { /* Trying to change flags of non-existent bridge vlan */ - if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) { - err = -EINVAL; - goto err_flags; - } + if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) + return -EINVAL; + + becomes_brentry = true; + } + + /* Master VLANs that aren't brentries weren't notified before, + * time to notify them now. + */ + if (becomes_brentry || would_change) { + err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, + would_change, extack); + if (err && err != -EOPNOTSUPP) + return err; + } + + if (becomes_brentry) { /* It was only kept for port vlans, now make it real */ err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid); if (err) { @@ -696,13 +734,13 @@ static int br_vlan_add_existing(struct net_bridge *br, br_multicast_toggle_one_vlan(vlan, true); } - if (__vlan_add_flags(vlan, flags)) + __vlan_flags_commit(vlan, flags); + if (would_change) *changed = true; return 0; err_fdb_insert: -err_flags: br_switchdev_port_vlan_del(br->dev, vlan->vid); return err; } @@ -1247,11 +1285,18 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, *changed = false; vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { - /* Pass the flags to the hardware bridge */ - ret = br_switchdev_port_vlan_add(port->dev, vid, flags, extack); - if (ret && ret != -EOPNOTSUPP) - return ret; - *changed = __vlan_add_flags(vlan, flags); + bool would_change = __vlan_flags_would_change(vlan, flags); + + if (would_change) { + /* Pass the flags to the hardware bridge */ + ret = br_switchdev_port_vlan_add(port->dev, vid, flags, + true, extack); + if (ret && ret != -EOPNOTSUPP) + return ret; + } + + __vlan_flags_commit(vlan, flags); + *changed = would_change; return 0; } diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 440139706130..52dd0b6835bc 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -268,7 +268,7 @@ static int receive(struct sk_buff *skb, struct net_device *dev, err = caifd->layer.up->receive(caifd->layer.up, pkt); - /* For -EILSEQ the packet is not freed so so it now */ + /* For -EILSEQ the packet is not freed so free it now */ if (err == -EILSEQ) cfpkt_destroy(pkt); diff --git a/net/can/gw.c b/net/can/gw.c index d8861e862f15..24221352e059 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1239,16 +1239,19 @@ static int __net_init cangw_pernet_init(struct net *net) return 0; } -static void __net_exit cangw_pernet_exit(struct net *net) +static void __net_exit cangw_pernet_exit_batch(struct list_head *net_list) { + struct net *net; + rtnl_lock(); - cgw_remove_all_jobs(net); + list_for_each_entry(net, net_list, exit_list) + cgw_remove_all_jobs(net); rtnl_unlock(); } static struct pernet_operations cangw_pernet_ops = { .init = cangw_pernet_init, - .exit = cangw_pernet_exit, + .exit_batch = cangw_pernet_exit_batch, }; static __init int cgw_module_init(void) diff --git a/net/core/dev.c b/net/core/dev.c index 1baab07820f6..05fa867f1878 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -216,18 +216,38 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } -static inline void rps_lock(struct softnet_data *sd) +static inline void rps_lock_irqsave(struct softnet_data *sd, + unsigned long *flags) { -#ifdef CONFIG_RPS - spin_lock(&sd->input_pkt_queue.lock); -#endif + if (IS_ENABLED(CONFIG_RPS)) + spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_save(*flags); } -static inline void rps_unlock(struct softnet_data *sd) +static inline void rps_lock_irq_disable(struct softnet_data *sd) { -#ifdef CONFIG_RPS - spin_unlock(&sd->input_pkt_queue.lock); -#endif + if (IS_ENABLED(CONFIG_RPS)) + spin_lock_irq(&sd->input_pkt_queue.lock); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); +} + +static inline void rps_unlock_irq_restore(struct softnet_data *sd, + unsigned long *flags) +{ + if (IS_ENABLED(CONFIG_RPS)) + spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_restore(*flags); +} + +static inline void rps_unlock_irq_enable(struct softnet_data *sd) +{ + if (IS_ENABLED(CONFIG_RPS)) + spin_unlock_irq(&sd->input_pkt_queue.lock); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, @@ -1037,7 +1057,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) - set_bit(i, inuse); + __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; @@ -1047,7 +1067,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) - set_bit(i, inuse); + __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); @@ -4456,11 +4476,11 @@ static void rps_trigger_softirq(void *data) * If yes, queue it to our IPI list and return 1 * If no, return 0 */ -static int rps_ipi_queued(struct softnet_data *sd) +static int napi_schedule_rps(struct softnet_data *sd) { -#ifdef CONFIG_RPS struct softnet_data *mysd = this_cpu_ptr(&softnet_data); +#ifdef CONFIG_RPS if (sd != mysd) { sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; @@ -4469,6 +4489,7 @@ static int rps_ipi_queued(struct softnet_data *sd) return 1; } #endif /* CONFIG_RPS */ + __napi_schedule_irqoff(&mysd->backlog); return 0; } @@ -4525,9 +4546,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, sd = &per_cpu(softnet_data, cpu); - local_irq_save(flags); - - rps_lock(sd); + rps_lock_irqsave(sd, &flags); if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); @@ -4536,26 +4555,21 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); input_queue_tail_incr_save(sd, qtail); - rps_unlock(sd); - local_irq_restore(flags); + rps_unlock_irq_restore(sd, &flags); return NET_RX_SUCCESS; } /* Schedule NAPI for backlog device * We can use non atomic operation since we own the queue lock */ - if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) { - if (!rps_ipi_queued(sd)) - ____napi_schedule(sd, &sd->backlog); - } + if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) + napi_schedule_rps(sd); goto enqueue; } drop: sd->dropped++; - rps_unlock(sd); - - local_irq_restore(flags); + rps_unlock_irq_restore(sd, &flags); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -4796,7 +4810,6 @@ static int netif_rx_internal(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -4806,78 +4819,67 @@ static int netif_rx_internal(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - preempt_enable(); } else #endif { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu(), &qtail); - put_cpu(); + ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** + * __netif_rx - Slightly optimized version of netif_rx + * @skb: buffer to post + * + * This behaves as netif_rx except that it does not disable bottom halves. + * As a result this function may only be invoked from the interrupt context + * (either hard or soft interrupt). + */ +int __netif_rx(struct sk_buff *skb) +{ + int ret; + + lockdep_assert_once(hardirq_count() | softirq_count()); + + trace_netif_rx_entry(skb); + ret = netif_rx_internal(skb); + trace_netif_rx_exit(ret); + return ret; +} +EXPORT_SYMBOL(__netif_rx); + +/** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. + * the upper (protocol) levels to process via the backlog NAPI device. It + * always succeeds. The buffer may be dropped during processing for + * congestion control or by the protocol layers. + * The network buffer is passed via the backlog NAPI device. Modern NIC + * driver should use NAPI and GRO. + * This function can used from any context. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ - int netif_rx(struct sk_buff *skb) { int ret; + local_bh_disable(); trace_netif_rx_entry(skb); - ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); - + local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); -int netif_rx_ni(struct sk_buff *skb) -{ - int err; - - trace_netif_rx_ni_entry(skb); - - preempt_disable(); - err = netif_rx_internal(skb); - if (local_softirq_pending()) - do_softirq(); - preempt_enable(); - trace_netif_rx_ni_exit(err); - - return err; -} -EXPORT_SYMBOL(netif_rx_ni); - -int netif_rx_any_context(struct sk_buff *skb) -{ - /* - * If invoked from contexts which do not invoke bottom half - * processing either at return from interrupt or when softrqs are - * reenabled, use netif_rx_ni() which invokes bottomhalf processing - * directly. - */ - if (in_interrupt()) - return netif_rx(skb); - else - return netif_rx_ni(skb); -} -EXPORT_SYMBOL(netif_rx_any_context); - static __latent_entropy void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -5650,8 +5652,7 @@ static void flush_backlog(struct work_struct *work) local_bh_disable(); sd = this_cpu_ptr(&softnet_data); - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); @@ -5659,8 +5660,7 @@ static void flush_backlog(struct work_struct *work) input_queue_head_incr(sd); } } - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { @@ -5678,16 +5678,14 @@ static bool flush_required(int cpu) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); return do_flush; #endif @@ -5802,8 +5800,7 @@ static int process_backlog(struct napi_struct *napi, int quota) } - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). @@ -5819,8 +5816,7 @@ static int process_backlog(struct napi_struct *napi, int quota) skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); } - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); } return work; @@ -9143,7 +9139,7 @@ DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); - dev_net(dev)->dev_unreg_count++; + atomic_inc(&dev_net(dev)->dev_unreg_count); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, @@ -9683,8 +9679,10 @@ int register_netdevice(struct net_device *dev) linkwatch_init_dev(dev); dev_init_scheduler(dev); - dev_hold(dev); + + dev_hold_track(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should @@ -9813,8 +9811,8 @@ int netdev_unregister_timeout_secs __read_mostly = 10; #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** - * netdev_wait_allrefs - wait until all references are gone. - * @dev: target net_device + * netdev_wait_allrefs_any - wait until all references are gone. + * @list: list of net_devices to wait on * * This is called when unregistering network devices. * @@ -9824,37 +9822,45 @@ int netdev_unregister_timeout_secs __read_mostly = 10; * We can get stuck here if buggy protocols don't correctly * call dev_put. */ -static void netdev_wait_allrefs(struct net_device *dev) +static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; - int wait = 0, refcnt; + struct net_device *dev; + int wait = 0; - linkwatch_forget_dev(dev); + list_for_each_entry(dev, list, todo_list) + linkwatch_forget_dev(dev); rebroadcast_time = warning_time = jiffies; - refcnt = netdev_refcnt_read(dev); - while (refcnt != 1) { + list_for_each_entry(dev, list, todo_list) + if (netdev_refcnt_read(dev) == 1) + return dev; + + while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + list_for_each_entry(dev, list, todo_list) + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); - if (test_bit(__LINK_STATE_LINKWATCH_PENDING, - &dev->state)) { - /* We must not have linkwatch events - * pending on unregister. If this - * happens, we simply run the queue - * unscheduled, resulting in a noop - * for this device. - */ - linkwatch_run_queue(); - } + list_for_each_entry(dev, list, todo_list) + if (test_bit(__LINK_STATE_LINKWATCH_PENDING, + &dev->state)) { + /* We must not have linkwatch events + * pending on unregister. If this + * happens, we simply run the queue + * unscheduled, resulting in a noop + * for this device. + */ + linkwatch_run_queue(); + break; + } __rtnl_unlock(); @@ -9869,14 +9875,18 @@ static void netdev_wait_allrefs(struct net_device *dev) wait = min(wait << 1, WAIT_REFS_MAX_MSECS); } - refcnt = netdev_refcnt_read(dev); + list_for_each_entry(dev, list, todo_list) + if (netdev_refcnt_read(dev) == 1) + return dev; - if (refcnt != 1 && - time_after(jiffies, warning_time + + if (time_after(jiffies, warning_time + netdev_unregister_timeout_secs * HZ)) { - pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", - dev->name, refcnt); - ref_tracker_dir_print(&dev->refcnt_tracker, 10); + list_for_each_entry(dev, list, todo_list) { + pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", + dev->name, netdev_refcnt_read(dev)); + ref_tracker_dir_print(&dev->refcnt_tracker, 10); + } + warning_time = jiffies; } } @@ -9908,6 +9918,7 @@ static void netdev_wait_allrefs(struct net_device *dev) */ void netdev_run_todo(void) { + struct net_device *dev, *tmp; struct list_head list; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; @@ -9928,26 +9939,23 @@ void netdev_run_todo(void) __rtnl_unlock(); - /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); - while (!list_empty(&list)) { - struct net_device *dev - = list_first_entry(&list, struct net_device, todo_list); - list_del(&dev->todo_list); - + list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { - pr_err("network todo '%s' but state %d\n", - dev->name, dev->reg_state); - dump_stack(); + netdev_WARN(dev, "run_todo but not unregistering\n"); + list_del(&dev->todo_list); continue; } dev->reg_state = NETREG_UNREGISTERED; + } - netdev_wait_allrefs(dev); + while (!list_empty(&list)) { + dev = netdev_wait_allrefs_any(&list); + list_del(&dev->todo_list); /* paranoia */ BUG_ON(netdev_refcnt_read(dev) != 1); @@ -9963,11 +9971,8 @@ void netdev_run_todo(void) if (dev->needs_free_netdev) free_netdev(dev); - /* Report a network device has been unregistered */ - rtnl_lock(); - dev_net(dev)->dev_unreg_count--; - __rtnl_unlock(); - wake_up(&netdev_unregistering_wq); + if (atomic_dec_and_test(&dev_net(dev)->dev_unreg_count)) + wake_up(&netdev_unregistering_wq); /* Free network device */ kobject_put(&dev->dev.kobj); @@ -10172,7 +10177,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; - dev_hold(dev); + __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif @@ -10449,7 +10454,7 @@ void unregister_netdevice_many(struct list_head *head) synchronize_net(); list_for_each_entry(dev, head, unreg_list) { - dev_put(dev); + dev_put_track(dev, &dev->dev_registered_tracker); net_set_todo(dev); } @@ -10732,8 +10737,7 @@ static int __net_init netdev_init(struct net *net) BUILD_BUG_ON(GRO_HASH_BUCKETS > 8 * sizeof_field(struct napi_struct, gro_bitmask)); - if (net != &init_net) - INIT_LIST_HEAD(&net->dev_base_head); + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) @@ -10849,14 +10853,14 @@ static struct pernet_operations __net_initdata netdev_net_ops = { .exit = netdev_exit, }; -static void __net_exit default_device_exit(struct net *net) +static void __net_exit default_device_exit_net(struct net *net) { struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ - rtnl_lock(); + ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -10880,24 +10884,24 @@ static void __net_exit default_device_exit(struct net *net) BUG(); } } - rtnl_unlock(); } static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) { - /* Return with the rtnl_lock held when there are no network + /* Return (with the rtnl_lock held) when there are no network * devices unregistering in any network namespace in net_list. */ - struct net *net; - bool unregistering; DEFINE_WAIT_FUNC(wait, woken_wake_function); + bool unregistering; + struct net *net; + ASSERT_RTNL(); add_wait_queue(&netdev_unregistering_wq, &wait); for (;;) { unregistering = false; - rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { - if (net->dev_unreg_count > 0) { + if (atomic_read(&net->dev_unreg_count) > 0) { unregistering = true; break; } @@ -10907,6 +10911,7 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) __rtnl_unlock(); wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); + rtnl_lock(); } remove_wait_queue(&netdev_unregistering_wq, &wait); } @@ -10922,6 +10927,11 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + default_device_exit_net(net); + cond_resched(); + } /* To prevent network device cleanup code from dereferencing * loopback devices or network devices that have been freed * wait here for all pending unregistrations to complete, @@ -10934,6 +10944,7 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) * default_device_exit_batch. */ rtnl_lock_unregistering(net_list); + list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) @@ -10947,7 +10958,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } static struct pernet_operations __net_initdata default_device_ops = { - .exit = default_device_exit, .exit_batch = default_device_exit_batch, }; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index d5dc6be2522c..d7d177f75d43 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -48,6 +48,19 @@ static int trace_state = TRACE_OFF; static bool monitor_hw; +#undef EM +#undef EMe + +#define EM(a, b) [a] = #b, +#define EMe(a, b) [a] = #b + +/* drop_reasons is used to translate 'enum skb_drop_reason' to string, + * which is reported to user space. + */ +static const char * const drop_reasons[] = { + TRACE_SKB_DROP_REASON +}; + /* net_dm_mutex * * An overall lock guarding every operation coming from userspace. @@ -126,6 +139,7 @@ struct net_dm_skb_cb { struct devlink_trap_metadata *hw_metadata; void *pc; }; + enum skb_drop_reason reason; }; #define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) @@ -502,6 +516,7 @@ static void net_dm_packet_trace_kfree_skb_hit(void *ignore, { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; + struct net_dm_skb_cb *cb; struct sk_buff *nskb; unsigned long flags; @@ -512,7 +527,11 @@ static void net_dm_packet_trace_kfree_skb_hit(void *ignore, if (!nskb) return; - NET_DM_SKB_CB(nskb)->pc = location; + if ((unsigned int)reason >= SKB_DROP_REASON_MAX) + reason = SKB_DROP_REASON_NOT_SPECIFIED; + cb = NET_DM_SKB_CB(nskb); + cb->reason = reason; + cb->pc = location; /* Override the timestamp because we care about the time when the * packet was dropped. */ @@ -557,7 +576,8 @@ static size_t net_dm_in_port_size(void) #define NET_DM_MAX_SYMBOL_LEN 40 -static size_t net_dm_packet_report_size(size_t payload_len) +static size_t net_dm_packet_report_size(size_t payload_len, + enum skb_drop_reason reason) { size_t size; @@ -578,6 +598,8 @@ static size_t net_dm_packet_report_size(size_t payload_len) nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_REASON */ + nla_total_size(strlen(drop_reasons[reason]) + 1) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } @@ -610,7 +632,7 @@ nla_put_failure: 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; + struct net_dm_skb_cb *cb = NET_DM_SKB_CB(skb); char buf[NET_DM_MAX_SYMBOL_LEN]; struct nlattr *attr; void *hdr; @@ -624,10 +646,15 @@ static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, 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)) + if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, (u64)(uintptr_t)cb->pc, + NET_DM_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_string(msg, NET_DM_ATTR_REASON, + drop_reasons[cb->reason])) goto nla_put_failure; - snprintf(buf, sizeof(buf), "%pS", NET_DM_SKB_CB(skb)->pc); + snprintf(buf, sizeof(buf), "%pS", cb->pc); if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) goto nla_put_failure; @@ -683,7 +710,9 @@ static void net_dm_packet_report(struct sk_buff *skb) 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); + msg = nlmsg_new(net_dm_packet_report_size(payload_len, + NET_DM_SKB_CB(skb)->reason), + GFP_KERNEL); if (!msg) goto out; diff --git a/net/core/filter.c b/net/core/filter.c index 4603b7cd3cd1..818244068c2d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2603,7 +2603,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) + if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist @@ -2809,7 +2809,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; - __clear_bit(new, &msg->sg.copy); + __clear_bit(new, msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); @@ -3783,6 +3783,28 @@ static const struct bpf_func_proto sk_skb_change_head_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; + +BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) +{ + return xdp_get_buff_len(xdp); +} + +static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) + +const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], +}; + static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -3817,11 +3839,208 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, + void *buf, unsigned long len, bool flush) +{ + unsigned long ptr_len, ptr_off = 0; + skb_frag_t *next_frag, *end_frag; + struct skb_shared_info *sinfo; + void *src, *dst; + u8 *ptr_buf; + + if (likely(xdp->data_end - xdp->data >= off + len)) { + src = flush ? buf : xdp->data + off; + dst = flush ? xdp->data + off : buf; + memcpy(dst, src, len); + return; + } + + sinfo = xdp_get_shared_info_from_buff(xdp); + end_frag = &sinfo->frags[sinfo->nr_frags]; + next_frag = &sinfo->frags[0]; + + ptr_len = xdp->data_end - xdp->data; + ptr_buf = xdp->data; + + while (true) { + if (off < ptr_off + ptr_len) { + unsigned long copy_off = off - ptr_off; + unsigned long copy_len = min(len, ptr_len - copy_off); + + src = flush ? buf : ptr_buf + copy_off; + dst = flush ? ptr_buf + copy_off : buf; + memcpy(dst, src, copy_len); + + off += copy_len; + len -= copy_len; + buf += copy_len; + } + + if (!len || next_frag == end_frag) + break; + + ptr_off += ptr_len; + ptr_buf = skb_frag_address(next_frag); + ptr_len = skb_frag_size(next_frag); + next_frag++; + } +} + +static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + u32 size = xdp->data_end - xdp->data; + void *addr = xdp->data; + int i; + + if (unlikely(offset > 0xffff || len > 0xffff)) + return ERR_PTR(-EFAULT); + + if (offset + len > xdp_get_buff_len(xdp)) + return ERR_PTR(-EINVAL); + + if (offset < size) /* linear area */ + goto out; + + offset -= size; + for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ + u32 frag_size = skb_frag_size(&sinfo->frags[i]); + + if (offset < frag_size) { + addr = skb_frag_address(&sinfo->frags[i]); + size = frag_size; + break; + } + offset -= frag_size; + } +out: + return offset + len < size ? addr + offset : NULL; +} + +BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, false); + else + memcpy(buf, ptr, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { + .func = bpf_xdp_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, true); + else + memcpy(ptr, buf, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { + .func = bpf_xdp_store_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; + struct xdp_rxq_info *rxq = xdp->rxq; + unsigned int tailroom; + + if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) + return -EOPNOTSUPP; + + tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); + if (unlikely(offset > tailroom)) + return -EINVAL; + + memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); + skb_frag_size_add(frag, offset); + sinfo->xdp_frags_size += offset; + + return 0; +} + +static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + int i, n_frags_free = 0, len_free = 0; + + if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) + return -EINVAL; + + for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { + skb_frag_t *frag = &sinfo->frags[i]; + int shrink = min_t(int, offset, skb_frag_size(frag)); + + len_free += shrink; + offset -= shrink; + + if (skb_frag_size(frag) == shrink) { + struct page *page = skb_frag_page(frag); + + __xdp_return(page_address(page), &xdp->rxq->mem, + false, NULL); + n_frags_free++; + } else { + skb_frag_size_sub(frag, shrink); + break; + } + } + sinfo->nr_frags -= n_frags_free; + sinfo->xdp_frags_size -= len_free; + + if (unlikely(!sinfo->nr_frags)) { + xdp_buff_clear_frags_flag(xdp); + xdp->data_end -= offset; + } + + return 0; +} + BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; + if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */ + if (offset < 0) + return bpf_xdp_frags_shrink_tail(xdp, -offset); + + return bpf_xdp_frags_increase_tail(xdp, offset); + } + /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; @@ -4047,6 +4266,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); enum bpf_map_type map_type = ri->map_type; + /* XDP_REDIRECT is not fully supported yet for xdp frags since + * not all XDP capable drivers can map non-linear xdp_frame in + * ndo_xdp_xmit. + */ + if (unlikely(xdp_buff_has_frags(xdp) && + map_type != BPF_MAP_TYPE_CPUMAP)) + return -EOPNOTSUPP; + if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); @@ -4590,10 +4817,12 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { }; #endif -static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, +static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { - memcpy(dst_buff, src_buff + off, len); + struct xdp_buff *xdp = (struct xdp_buff *)ctx; + + bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } @@ -4604,11 +4833,11 @@ BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; - if (unlikely(!xdp || - xdp_size > (unsigned long)(xdp->data_end - xdp->data))) + + if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp))) return -EFAULT; - return bpf_event_output(map, flags, meta, meta_size, xdp->data, + return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } @@ -4862,6 +5091,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, case SO_REUSEPORT: sk->sk_reuseport = valbool; break; + case SO_TXREHASH: + if (val < -1 || val > 1) { + ret = -EINVAL; + break; + } + sk->sk_txrehash = (u8)val; + break; default: ret = -EINVAL; } @@ -5040,6 +5276,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, case SO_REUSEPORT: *((int *)optval) = sk->sk_reuseport; break; + case SO_TXREHASH: + *((int *)optval) = sk->sk_txrehash; + break; default: goto err_clear; } @@ -7533,6 +7772,12 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_proto; + case BPF_FUNC_xdp_load_bytes: + return &bpf_xdp_load_bytes_proto; + case BPF_FUNC_xdp_store_bytes: + return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: @@ -8030,6 +8275,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); + int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; @@ -8041,7 +8287,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): - case offsetof(struct bpf_sock, dst_port): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): @@ -8050,6 +8295,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case bpf_ctx_range(struct bpf_sock, dst_port): + field_size = size == size_default ? + size_default : sizeof_field(struct bpf_sock, dst_port); + bpf_ctx_record_field_size(info, field_size); + return bpf_ctx_narrow_access_ok(off, size, field_size); + case offsetofend(struct bpf_sock, dst_port) ... + offsetof(struct bpf_sock, dst_ip4) - 1: + return false; } return size == size_default; @@ -10062,7 +10315,6 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, - .check_kfunc_call = bpf_prog_test_check_kfunc_call, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { @@ -10601,7 +10853,8 @@ static bool sk_lookup_is_valid_access(int off, int size, case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): - case bpf_ctx_range(struct bpf_sk_lookup, remote_port): + case offsetof(struct bpf_sk_lookup, remote_port) ... + offsetof(struct bpf_sk_lookup, local_ip4) - 1: case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); diff --git a/net/core/gro.c b/net/core/gro.c index a11b286d1495..ee5e7e889d8b 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -459,29 +459,22 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff skb_set_network_header(skb, skb_gro_offset(skb)); skb_reset_mac_len(skb); - NAPI_GRO_CB(skb)->same_flow = 0; + BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed), + sizeof(u32))); /* Avoid slow unaligned acc */ + *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->encap_mark = 0; - NAPI_GRO_CB(skb)->recursion_counter = 0; - NAPI_GRO_CB(skb)->is_fou = 0; NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ switch (skb->ip_summed) { case CHECKSUM_COMPLETE: NAPI_GRO_CB(skb)->csum = skb->csum; NAPI_GRO_CB(skb)->csum_valid = 1; - NAPI_GRO_CB(skb)->csum_cnt = 0; break; case CHECKSUM_UNNECESSARY: NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - NAPI_GRO_CB(skb)->csum_valid = 0; break; - default: - NAPI_GRO_CB(skb)->csum_cnt = 0; - NAPI_GRO_CB(skb)->csum_valid = 0; } pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, @@ -634,7 +627,6 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; - skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (unlikely(skb->slow_gro)) { skb_orphan(skb); skb_ext_reset(skb); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index b0f5344d1185..95098d1a49bd 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -166,10 +166,10 @@ static void linkwatch_do_dev(struct net_device *dev) netdev_state_change(dev); } - /* Note: our callers are responsible for - * calling netdev_tracker_free(). + /* Note: our callers are responsible for calling netdev_tracker_free(). + * This is the reason we use __dev_put() instead of dev_put(). */ - dev_put(dev); + __dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a5b5bb99c644..0ec2f5906a27 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -44,13 +44,7 @@ EXPORT_SYMBOL_GPL(net_rwsem); static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; #endif -struct net init_net = { - .ns.count = REFCOUNT_INIT(1), - .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), -#ifdef CONFIG_KEYS - .key_domain = &init_net_key_domain, -#endif -}; +struct net init_net; EXPORT_SYMBOL(init_net); static bool init_net_initialized; @@ -301,6 +295,7 @@ struct net *get_net_ns_by_id(const struct net *net, int id) return peer; } +EXPORT_SYMBOL_GPL(get_net_ns_by_id); /* * setup_net runs the initializers for the network namespace object. @@ -363,6 +358,8 @@ out_undo: static int __net_init net_defaults_init_net(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; + net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; + return 0; } @@ -1084,7 +1081,7 @@ out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } -static int __init net_ns_init(void) +void __init net_ns_init(void) { struct net_generic *ng; @@ -1105,6 +1102,9 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); +#ifdef CONFIG_KEYS + init_net.key_domain = &init_net_key_domain; +#endif down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); @@ -1119,12 +1119,8 @@ static int __init net_ns_init(void) RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, RTNL_FLAG_DOIT_UNLOCKED); - - return 0; } -pure_initcall(net_ns_init); - static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) { ops_pre_exit_list(ops, net_exit_list); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index bd62c01a2ec3..e25d359d84d9 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -423,11 +423,6 @@ static __always_inline struct page * __page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct) { - /* It is not the last user for the page frag case */ - if (pool->p.flags & PP_FLAG_PAGE_FRAG && - page_pool_atomic_sub_frag_count_return(page, 1)) - return NULL; - /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the * regular page allocator APIs. @@ -471,8 +466,8 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, return NULL; } -void page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct) +void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) { page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct); if (page && !page_pool_recycle_in_ring(pool, page)) { @@ -480,7 +475,7 @@ void page_pool_put_page(struct page_pool *pool, struct page *page, page_pool_return_page(pool, page); } } -EXPORT_SYMBOL(page_pool_put_page); +EXPORT_SYMBOL(page_pool_put_defragged_page); /* Caller must not use data area after call, as this function overwrites it */ void page_pool_put_page_bulk(struct page_pool *pool, void **data, @@ -491,6 +486,10 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); + /* It is not the last user for the page frag case */ + if (!page_pool_is_last_frag(pool, page)) + continue; + page = __page_pool_put_page(pool, page, -1, false); /* Approved for bulk recycling in ptr_ring cache */ if (page) @@ -526,8 +525,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool, long drain_count = BIAS_MAX - pool->frag_users; /* Some user is still using the page frag */ - if (likely(page_pool_atomic_sub_frag_count_return(page, - drain_count))) + if (likely(page_pool_defrag_page(page, drain_count))) return NULL; if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) { @@ -548,8 +546,7 @@ static void page_pool_free_frag(struct page_pool *pool) pool->frag_page = NULL; - if (!page || - page_pool_atomic_sub_frag_count_return(page, drain_count)) + if (!page || page_pool_defrag_page(page, drain_count)) return; page_pool_return_page(pool, page); @@ -588,7 +585,7 @@ frag_reset: pool->frag_users = 1; *offset = 0; pool->frag_offset = size; - page_pool_set_frag_count(page, BIAS_MAX); + page_pool_fragment_page(page, BIAS_MAX); return page; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2fb8eb6791e8..20a9e1686453 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -459,7 +459,7 @@ static void rtnl_lock_unregistering_all(void) * setup_net() and cleanup_net() are not possible. */ for_each_net(net) { - if (net->dev_unreg_count > 0) { + if (atomic_read(&net->dev_unreg_count) > 0) { unregistering = true; break; } @@ -5407,8 +5407,10 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENODEV; filter_mask = ifsm->filter_mask; - if (!filter_mask) + if (!filter_mask) { + NL_SET_ERR_MSG(extack, "Filter mask must be set for stats get"); return -EINVAL; + } nskb = nlmsg_new(if_nlmsg_stats_size(dev, filter_mask), GFP_KERNEL); if (!nskb) diff --git a/net/core/sock.c b/net/core/sock.c index 4ff806d71921..09d31a7dc68f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1447,6 +1447,15 @@ set_sndbuf: break; } + case SO_TXREHASH: + if (val < -1 || val > 1) { + ret = -EINVAL; + break; + } + /* Paired with READ_ONCE() in tcp_rtx_synack() */ + WRITE_ONCE(sk->sk_txrehash, (u8)val); + break; + default: ret = -ENOPROTOOPT; break; @@ -1834,6 +1843,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reserved_mem; break; + case SO_TXREHASH: + v.val = sk->sk_txrehash; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -2266,6 +2279,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; /* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */ sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size); + sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1); /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); } @@ -2611,7 +2625,8 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, switch (cmsg->cmsg_type) { case SO_MARK: - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; @@ -3278,6 +3293,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; + sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 1827669eedd6..2d213c4011db 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1416,38 +1416,50 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) return NULL; } -static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which) +static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog, + u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); - struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - pprog = &progs->msg_parser; + *pprog = &progs->msg_parser; break; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: - pprog = &progs->stream_parser; + *pprog = &progs->stream_parser; break; #endif case BPF_SK_SKB_STREAM_VERDICT: if (progs->skb_verdict) return -EBUSY; - pprog = &progs->stream_verdict; + *pprog = &progs->stream_verdict; break; case BPF_SK_SKB_VERDICT: if (progs->stream_verdict) return -EBUSY; - pprog = &progs->skb_verdict; + *pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + return 0; +} + +static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which) +{ + struct bpf_prog **pprog; + int ret; + + ret = sock_map_prog_lookup(map, &pprog, which); + if (ret) + return ret; + if (old) return psock_replace_prog(pprog, prog, old); @@ -1455,6 +1467,57 @@ static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, return 0; } +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd; + struct bpf_prog **pprog; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + u32 id = 0; + int ret; + + if (attr->query.query_flags) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + rcu_read_lock(); + + ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type); + if (ret) + goto end; + + prog = *pprog; + prog_cnt = !prog ? 0 : 1; + + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + goto end; + + /* we do not hold the refcnt, the bpf prog may be released + * asynchronously and the id would be set to 0. + */ + id = data_race(prog->aux->id); + if (id == 0) + prog_cnt = 0; + +end: + rcu_read_unlock(); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)) || + (id != 0 && copy_to_user(prog_ids, &id, sizeof(u32))) || + copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + ret = -EFAULT; + + fdput(f); + return ret; +} + static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link) { switch (link->map->map_type) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7b4d485aac7a..dbeb8ecbcd98 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -593,6 +593,15 @@ static struct ctl_table netns_core_table[] = { .extra1 = SYSCTL_ZERO, .proc_handler = proc_dointvec_minmax }, + { + .procname = "txrehash", + .data = &init_net.core.sysctl_txrehash, + .maxlen = sizeof(u8), + .mode = 0644, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + .proc_handler = proc_dou8vec_minmax, + }, { } }; @@ -611,7 +620,7 @@ __setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); static __net_init int sysctl_core_net_init(struct net *net) { - struct ctl_table *tbl; + struct ctl_table *tbl, *tmp; tbl = netns_core_table; if (!net_eq(net, &init_net)) { @@ -619,7 +628,8 @@ static __net_init int sysctl_core_net_init(struct net *net) if (tbl == NULL) goto err_dup; - tbl[0].data = &net->core.sysctl_somaxconn; + for (tmp = tbl; tmp->procname; tmp++) + tmp->data += (char *)net - (char *)&init_net; /* Don't export any sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 7aba35504986..361df312ee7f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -162,8 +162,9 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) } /* Returns 0 on success, negative on failure */ -int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index, unsigned int napi_id) +int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id, u32 frag_size) { if (!dev) { WARN(1, "Missing net_device from driver"); @@ -185,11 +186,12 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->napi_id = napi_id; + xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } -EXPORT_SYMBOL_GPL(xdp_rxq_info_reg); +EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { @@ -369,8 +371,8 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ -static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, - struct xdp_buff *xdp) +void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp) { struct xdp_mem_allocator *xa; struct page *page; @@ -406,12 +408,38 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, void xdp_return_frame(struct xdp_frame *xdpf) { + struct skb_shared_info *sinfo; + int i; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_return(page_address(page), &xdpf->mem, false, NULL); + } +out: __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { + struct skb_shared_info *sinfo; + int i; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_return(page_address(page), &xdpf->mem, true, NULL); + } +out: __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); @@ -447,7 +475,7 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_mem_allocator *xa; if (mem->type != MEM_TYPE_PAGE_POOL) { - __xdp_return(xdpf->data, &xdpf->mem, false, NULL); + xdp_return_frame(xdpf); return; } @@ -466,12 +494,38 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); } + if (unlikely(xdp_frame_has_frags(xdpf))) { + struct skb_shared_info *sinfo; + int i; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + skb_frag_t *frag = &sinfo->frags[i]; + + bq->q[bq->count++] = skb_frag_address(frag); + if (bq->count == XDP_BULK_QUEUE_SIZE) + xdp_flush_frame_bulk(bq); + } + } bq->q[bq->count++] = xdpf->data; } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); void xdp_return_buff(struct xdp_buff *xdp) { + struct skb_shared_info *sinfo; + int i; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_return(page_address(page), &xdp->rxq->mem, true, xdp); + } +out: __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } @@ -561,8 +615,14 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); unsigned int headroom, frame_size; void *hard_start; + u8 nr_frags; + + /* xdp frags frame */ + if (unlikely(xdp_frame_has_frags(xdpf))) + nr_frags = sinfo->nr_frags; /* Part of headroom was reserved to xdpf */ headroom = sizeof(*xdpf) + xdpf->headroom; @@ -582,6 +642,12 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); + if (unlikely(xdp_frame_has_frags(xdpf))) + xdp_update_skb_shared_info(skb, nr_frags, + sinfo->xdp_frags_size, + nr_frags * xdpf->frame_sz, + xdp_frame_is_frag_pfmemalloc(xdpf)); + /* Essential SKB info: protocol and skb->dev */ skb->protocol = eth_type_trans(skb, dev); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 5183e627468d..671c377f0889 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -136,11 +136,6 @@ static inline int between48(const u64 seq1, const u64 seq2, const u64 seq3) return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16); } -static inline u64 max48(const u64 seq1, const u64 seq2) -{ - return after48(seq1, seq2) ? seq1 : seq2; -} - /** * dccp_loss_count - Approximate the number of lost data packets in a burst loss * @s1: last known sequence number before the loss ('hole') diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 0ea29270d7e5..ae662567a6cb 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1030,15 +1030,9 @@ static void __net_exit dccp_v4_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v4_ctl_sk); } -static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&dccp_hashinfo, AF_INET); -} - static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, - .exit_batch = dccp_v4_exit_batch, .id = &dccp_v4_pernet_id, .size = sizeof(struct dccp_v4_pernet), }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index fa663518fa0e..eab3bd1ee9a0 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1115,15 +1115,9 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } -static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&dccp_hashinfo, AF_INET6); -} - static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, - .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 91e7a2202697..64d805b27add 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -22,6 +22,7 @@ #include "feat.h" struct inet_timewait_death_row dccp_death_row = { + .tw_refcount = REFCOUNT_INIT(1), .sysctl_max_tw_buckets = NR_FILE * 2, .hashinfo = &dccp_hashinfo, }; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index dcad3100b164..408b79a28cd4 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -15,6 +15,7 @@ #include <linux/of.h> #include <linux/of_net.h> #include <net/devlink.h> +#include <net/sch_generic.h> #include "dsa_priv.h" @@ -452,8 +453,10 @@ static int dsa_port_setup(struct dsa_port *dp) return 0; mutex_init(&dp->addr_lists_lock); + mutex_init(&dp->vlans_lock); INIT_LIST_HEAD(&dp->fdbs); INIT_LIST_HEAD(&dp->mdbs); + INIT_LIST_HEAD(&dp->vlans); if (ds->ops->port_setup) { err = ds->ops->port_setup(ds, dp->index); @@ -562,6 +565,7 @@ static void dsa_port_teardown(struct dsa_port *dp) struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a, *tmp; struct net_device *slave; + struct dsa_vlan *v, *n; if (!dp->setup) return; @@ -602,6 +606,11 @@ static void dsa_port_teardown(struct dsa_port *dp) kfree(a); } + list_for_each_entry_safe(v, n, &dp->vlans, list) { + list_del(&v->list); + kfree(v); + } + dp->setup = false; } @@ -1064,9 +1073,18 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) list_for_each_entry(dp, &dst->ports, list) { if (dsa_port_is_cpu(dp)) { - err = dsa_master_setup(dp->master, dp); + struct net_device *master = dp->master; + bool admin_up = (master->flags & IFF_UP) && + !qdisc_tx_is_noop(master); + + err = dsa_master_setup(master, dp); if (err) return err; + + /* Replay master state event */ + dsa_tree_master_admin_state_change(dst, master, admin_up); + dsa_tree_master_oper_state_change(dst, master, + netif_oper_up(master)); } } @@ -1081,9 +1099,19 @@ static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) rtnl_lock(); - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_cpu(dp)) - dsa_master_teardown(dp->master); + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_cpu(dp)) { + struct net_device *master = dp->master; + + /* Synthesizing an "admin down" state is sufficient for + * the switches to get a notification if the master is + * currently up and running. + */ + dsa_tree_master_admin_state_change(dst, master, false); + + dsa_master_teardown(master); + } + } rtnl_unlock(); } @@ -1279,6 +1307,52 @@ out_unlock: return err; } +static void dsa_tree_master_state_change(struct dsa_switch_tree *dst, + struct net_device *master) +{ + struct dsa_notifier_master_state_info info; + struct dsa_port *cpu_dp = master->dsa_ptr; + + info.master = master; + info.operational = dsa_port_master_is_operational(cpu_dp); + + dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info); +} + +void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (up && cpu_dp->master_oper_up)) + notify = true; + + cpu_dp->master_admin_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + +void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (cpu_dp->master_admin_up && up)) + notify = true; + + cpu_dp->master_oper_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) { struct dsa_switch_tree *dst = ds->dst; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 23c79e91ac67..a37f0883676a 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -34,12 +34,15 @@ enum { DSA_NOTIFIER_HOST_MDB_DEL, DSA_NOTIFIER_VLAN_ADD, DSA_NOTIFIER_VLAN_DEL, + DSA_NOTIFIER_HOST_VLAN_ADD, + DSA_NOTIFIER_HOST_VLAN_DEL, DSA_NOTIFIER_MTU, DSA_NOTIFIER_TAG_PROTO, DSA_NOTIFIER_TAG_PROTO_CONNECT, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, + DSA_NOTIFIER_MASTER_STATE_CHANGE, }; /* DSA_NOTIFIER_AGEING_TIME */ @@ -109,6 +112,12 @@ struct dsa_notifier_tag_8021q_vlan_info { u16 vid; }; +/* DSA_NOTIFIER_MASTER_STATE_CHANGE */ +struct dsa_notifier_master_state_info { + const struct net_device *master; + bool operational; +}; + struct dsa_switchdev_event_work { struct dsa_switch *ds; int port; @@ -226,6 +235,11 @@ int dsa_port_vlan_add(struct dsa_port *dp, struct netlink_ext_ack *extack); int dsa_port_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan); +int dsa_port_host_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack); +int dsa_port_host_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan); int dsa_port_mrp_add(const struct dsa_port *dp, const struct switchdev_obj_mrp *mrp); int dsa_port_mrp_del(const struct dsa_port *dp, @@ -481,6 +495,12 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, struct net_device *master, const struct dsa_device_ops *tag_ops, const struct dsa_device_ops *old_tag_ops); +void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up); +void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up); unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); void dsa_bridge_num_put(const struct net_device *bridge_dev, unsigned int bridge_num); diff --git a/net/dsa/master.c b/net/dsa/master.c index 2199104ca7df..6ac393cc6ea7 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -330,8 +330,6 @@ static const struct attribute_group dsa_group = { .attrs = dsa_slave_attrs, }; -static struct lock_class_key dsa_master_addr_list_lock_key; - int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { struct dsa_switch *ds = cpu_dp->ds; @@ -353,8 +351,6 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; - lockdep_set_class(&dev->addr_list_lock, - &dsa_master_addr_list_lock_key); dsa_master_set_promiscuity(dev, 1); diff --git a/net/dsa/port.c b/net/dsa/port.c index bd78192e0e47..cca5cf686f74 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -904,6 +904,48 @@ int dsa_port_vlan_del(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); } +int dsa_port_host_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + struct dsa_notifier_vlan_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .vlan = vlan, + .extack = extack, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dsa_port_notify(dp, DSA_NOTIFIER_HOST_VLAN_ADD, &info); + if (err && err != -EOPNOTSUPP) + return err; + + vlan_vid_add(cpu_dp->master, htons(ETH_P_8021Q), vlan->vid); + + return err; +} + +int dsa_port_host_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan) +{ + struct dsa_notifier_vlan_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .vlan = vlan, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dsa_port_notify(dp, DSA_NOTIFIER_HOST_VLAN_DEL, &info); + if (err && err != -EOPNOTSUPP) + return err; + + vlan_vid_del(cpu_dp->master, htons(ETH_P_8021Q), vlan->vid); + + return err; +} + int dsa_port_mrp_add(const struct dsa_port *dp, const struct switchdev_obj_mrp *mrp) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 22241afcac81..f61e6b72ffbb 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -348,9 +348,8 @@ static int dsa_slave_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { - struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - struct switchdev_obj_port_vlan vlan; + struct switchdev_obj_port_vlan *vlan; int err; if (dsa_port_skip_vlan_configuration(dp)) { @@ -358,14 +357,14 @@ static int dsa_slave_vlan_add(struct net_device *dev, return 0; } - vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); - err = dsa_slave_vlan_check_for_8021q_uppers(dev, &vlan); + err = dsa_slave_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, @@ -374,21 +373,36 @@ static int dsa_slave_vlan_add(struct net_device *dev, } } - err = dsa_port_vlan_add(dp, &vlan, extack); - if (err) - return err; + return dsa_port_vlan_add(dp, vlan, extack); +} + +/* Offload a VLAN installed on the bridge or on a foreign interface by + * installing it as a VLAN towards the CPU port. + */ +static int dsa_slave_host_vlan_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct switchdev_obj_port_vlan vlan; + + /* Do nothing if this is a software bridge */ + if (!dp->bridge) + return -EOPNOTSUPP; + + if (dsa_port_skip_vlan_configuration(dp)) { + NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); + return 0; + } + + vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); - /* We need the dedicated CPU port to be a member of the VLAN as well. - * Even though drivers often handle CPU membership in special ways, + /* Even though drivers often handle CPU membership in special ways, * it doesn't make sense to program a PVID, so clear this flag. */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; - err = dsa_port_vlan_add(dp->cpu_dp, &vlan, extack); - if (err) - return err; - - return vlan_vid_add(master, htons(ETH_P_8021Q), vlan.vid); + return dsa_port_host_vlan_add(dp, &vlan, extack); } static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, @@ -415,10 +429,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, err = dsa_port_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) - return -EOPNOTSUPP; - - err = dsa_slave_vlan_add(dev, obj, extack); + if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + err = dsa_slave_vlan_add(dev, obj, extack); + else + err = dsa_slave_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) @@ -444,26 +458,33 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, static int dsa_slave_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { - struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan *vlan; - int err; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); - /* Do not deprogram the CPU port as it may be shared with other user - * ports which can be members of this VLAN as well. - */ - err = dsa_port_vlan_del(dp, vlan); - if (err) - return err; + return dsa_port_vlan_del(dp, vlan); +} - vlan_vid_del(master, htons(ETH_P_8021Q), vlan->vid); +static int dsa_slave_host_vlan_del(struct net_device *dev, + const struct switchdev_obj *obj) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct switchdev_obj_port_vlan *vlan; - return 0; + /* Do nothing if this is a software bridge */ + if (!dp->bridge) + return -EOPNOTSUPP; + + if (dsa_port_skip_vlan_configuration(dp)) + return 0; + + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + + return dsa_port_host_vlan_del(dp, vlan); } static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, @@ -489,10 +510,10 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, err = dsa_port_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) - return -EOPNOTSUPP; - - err = dsa_slave_vlan_del(dev, obj); + if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + err = dsa_slave_vlan_del(dev, obj); + else + err = dsa_slave_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) @@ -515,26 +536,6 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, return err; } -static int dsa_slave_get_port_parent_id(struct net_device *dev, - struct netdev_phys_item_id *ppid) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst = ds->dst; - - /* For non-legacy ports, devlink is used and it takes - * care of the name generation. This ndo implementation - * should be removed with legacy support. - */ - if (dp->ds->devlink) - return -EOPNOTSUPP; - - ppid->id_len = sizeof(dst->index); - memcpy(&ppid->id, &dst->index, ppid->id_len); - - return 0; -} - static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, struct sk_buff *skb) { @@ -973,24 +974,6 @@ static void dsa_slave_poll_controller(struct net_device *dev) } #endif -static int dsa_slave_get_phys_port_name(struct net_device *dev, - char *name, size_t len) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - /* For non-legacy ports, devlink is used and it takes - * care of the name generation. This ndo implementation - * should be removed with legacy support. - */ - if (dp->ds->devlink) - return -EOPNOTSUPP; - - if (snprintf(name, len, "p%d", dp->index) >= len) - return -EINVAL; - - return 0; -} - static struct dsa_mall_tc_entry * dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { @@ -1385,7 +1368,6 @@ static int dsa_slave_get_ts_info(struct net_device *dev, static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { - struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, @@ -1405,7 +1387,7 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, } /* And CPU port... */ - ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &extack); + ret = dsa_port_host_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, @@ -1413,13 +1395,12 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, return ret; } - return vlan_vid_add(master, proto, vid); + return 0; } static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { - struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, @@ -1428,16 +1409,11 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, }; int err; - /* Do not deprogram the CPU port as it may be shared with other user - * ports which can be members of this VLAN as well. - */ err = dsa_port_vlan_del(dp, &vlan); if (err) return err; - vlan_vid_del(master, proto, vid); - - return 0; + return dsa_port_host_vlan_del(dp, &vlan); } static int dsa_slave_restore_vlan(struct net_device *vdev, int vid, void *arg) @@ -1747,7 +1723,7 @@ static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - return dp->ds->devlink ? &dp->devlink_port : NULL; + return &dp->devlink_port; } static void dsa_slave_get_stats64(struct net_device *dev, @@ -1792,10 +1768,8 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_netpoll_cleanup = dsa_slave_netpoll_cleanup, .ndo_poll_controller = dsa_slave_poll_controller, #endif - .ndo_get_phys_port_name = dsa_slave_get_phys_port_name, .ndo_setup_tc = dsa_slave_setup_tc, .ndo_get_stats64 = dsa_slave_get_stats64, - .ndo_get_port_parent_id = dsa_slave_get_port_parent_id, .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, .ndo_get_devlink_port = dsa_slave_get_devlink_port, @@ -1917,15 +1891,6 @@ void dsa_slave_setup_tagger(struct net_device *slave) slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } -static struct lock_class_key dsa_slave_netdev_xmit_lock_key; -static void dsa_slave_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &dsa_slave_netdev_xmit_lock_key); -} - int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); @@ -1988,9 +1953,6 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); - netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, - NULL); - SET_NETDEV_DEV(slave_dev, port->ds->dev); slave_dev->dev.of_node = port->dn; slave_dev->vlan_features = master->vlan_features; @@ -2346,6 +2308,36 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, err = dsa_port_lag_change(dp, info->lower_state_info); return notifier_from_errno(err); } + case NETDEV_CHANGE: + case NETDEV_UP: { + /* Track state of master port. + * DSA driver may require the master port (and indirectly + * the tagger) to be available for some special operation. + */ + if (netdev_uses_dsa(dev)) { + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->ds->dst; + + /* Track when the master port is UP */ + dsa_tree_master_oper_state_change(dst, dev, + netif_oper_up(dev)); + + /* Track when the master port is ready and can accept + * packet. + * NETDEV_UP event is not enough to flag a port as ready. + * We also have to wait for linkwatch_do_dev to dev_activate + * and emit a NETDEV_CHANGE event. + * We check if a master port is ready by checking if the dev + * have a qdisc assigned and is not noop. + */ + dsa_tree_master_admin_state_change(dst, dev, + !qdisc_tx_is_noop(dev)); + + return NOTIFY_OK; + } + + return NOTIFY_DONE; + } case NETDEV_GOING_DOWN: { struct dsa_port *dp, *cpu_dp; struct dsa_switch_tree *dst; @@ -2357,6 +2349,8 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; + dsa_tree_master_admin_state_change(dst, dev, false); + list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) continue; @@ -2550,14 +2544,16 @@ static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_PORT_OBJ_ADD: - err = switchdev_handle_port_obj_add(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_obj_add); + err = switchdev_handle_port_obj_add_foreign(dev, ptr, + dsa_slave_dev_check, + dsa_foreign_dev_check, + dsa_slave_port_obj_add); return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: - err = switchdev_handle_port_obj_del(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_obj_del); + err = switchdev_handle_port_obj_del_foreign(dev, ptr, + dsa_slave_dev_check, + dsa_foreign_dev_check, + dsa_slave_port_obj_del); return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, diff --git a/net/dsa/switch.c b/net/dsa/switch.c index e3c7d2627a61..0bb3987bd4e6 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -113,26 +113,15 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, return dsa_tag_8021q_bridge_join(ds, info); } -static int dsa_switch_bridge_leave(struct dsa_switch *ds, - struct dsa_notifier_bridge_info *info) +static int dsa_switch_sync_vlan_filtering(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info) { - struct dsa_switch_tree *dst = ds->dst; struct netlink_ext_ack extack = {0}; bool change_vlan_filtering = false; bool vlan_filtering; struct dsa_port *dp; int err; - if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_leave) - ds->ops->port_bridge_leave(ds, info->port, info->bridge); - - if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_leave) - ds->ops->crosschip_bridge_leave(ds, info->tree_index, - info->sw_index, info->port, - info->bridge); - if (ds->needs_standalone_vlan_filtering && !br_vlan_enabled(info->bridge.dev)) { change_vlan_filtering = true; @@ -172,6 +161,31 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, return err; } + return 0; +} + +static int dsa_switch_bridge_leave(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info) +{ + struct dsa_switch_tree *dst = ds->dst; + int err; + + if (dst->index == info->tree_index && ds->index == info->sw_index && + ds->ops->port_bridge_leave) + ds->ops->port_bridge_leave(ds, info->port, info->bridge); + + if ((dst->index != info->tree_index || ds->index != info->sw_index) && + ds->ops->crosschip_bridge_leave) + ds->ops->crosschip_bridge_leave(ds, info->tree_index, + info->sw_index, info->port, + info->bridge); + + if (ds->dst->index == info->tree_index && ds->index == info->sw_index) { + err = dsa_switch_sync_vlan_filtering(ds, info); + if (err) + return err; + } + return dsa_tag_8021q_bridge_leave(ds, info); } @@ -544,6 +558,7 @@ static int dsa_switch_host_mdb_del(struct dsa_switch *ds, return err; } +/* Port VLANs match on the targeted port and on all DSA ports */ static bool dsa_port_vlan_match(struct dsa_port *dp, struct dsa_notifier_vlan_info *info) { @@ -556,6 +571,126 @@ static bool dsa_port_vlan_match(struct dsa_port *dp, return false; } +/* Host VLANs match on the targeted port's CPU port, and on all DSA ports + * (upstream and downstream) of that switch and its upstream switches. + */ +static bool dsa_port_host_vlan_match(struct dsa_port *dp, + struct dsa_notifier_vlan_info *info) +{ + struct dsa_port *targeted_dp, *cpu_dp; + struct dsa_switch *targeted_ds; + + targeted_ds = dsa_switch_find(dp->ds->dst->index, info->sw_index); + targeted_dp = dsa_to_port(targeted_ds, info->port); + cpu_dp = targeted_dp->cpu_dp; + + if (dsa_switch_is_upstream_of(dp->ds, targeted_ds)) + return dsa_port_is_dsa(dp) || dp == cpu_dp; + + return false; +} + +static struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, + const struct switchdev_obj_port_vlan *vlan) +{ + struct dsa_vlan *v; + + list_for_each_entry(v, vlan_list, list) + if (v->vid == vlan->vid) + return v; + + return NULL; +} + +static int dsa_port_do_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dp->ds; + int port = dp->index; + struct dsa_vlan *v; + int err = 0; + + /* No need to bother with refcounting for user ports. */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_vlan_add(ds, port, vlan, extack); + + /* No need to propagate on shared ports the existing VLANs that were + * re-notified after just the flags have changed. This would cause a + * refcount bump which we need to avoid, since it unbalances the + * additions with the deletions. + */ + if (vlan->changed) + return 0; + + mutex_lock(&dp->vlans_lock); + + v = dsa_vlan_find(&dp->vlans, vlan); + if (v) { + refcount_inc(&v->refcount); + goto out; + } + + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) { + err = -ENOMEM; + goto out; + } + + err = ds->ops->port_vlan_add(ds, port, vlan, extack); + if (err) { + kfree(v); + goto out; + } + + v->vid = vlan->vid; + refcount_set(&v->refcount, 1); + list_add_tail(&v->list, &dp->vlans); + +out: + mutex_unlock(&dp->vlans_lock); + + return err; +} + +static int dsa_port_do_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan) +{ + struct dsa_switch *ds = dp->ds; + int port = dp->index; + struct dsa_vlan *v; + int err = 0; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_vlan_del(ds, port, vlan); + + mutex_lock(&dp->vlans_lock); + + v = dsa_vlan_find(&dp->vlans, vlan); + if (!v) { + err = -ENOENT; + goto out; + } + + if (!refcount_dec_and_test(&v->refcount)) + goto out; + + err = ds->ops->port_vlan_del(ds, port, vlan); + if (err) { + refcount_set(&v->refcount, 1); + goto out; + } + + list_del(&v->list); + kfree(v); + +out: + mutex_unlock(&dp->vlans_lock); + + return err; +} + static int dsa_switch_vlan_add(struct dsa_switch *ds, struct dsa_notifier_vlan_info *info) { @@ -567,8 +702,8 @@ static int dsa_switch_vlan_add(struct dsa_switch *ds, dsa_switch_for_each_port(dp, ds) { if (dsa_port_vlan_match(dp, info)) { - err = ds->ops->port_vlan_add(ds, dp->index, info->vlan, - info->extack); + err = dsa_port_do_vlan_add(dp, info->vlan, + info->extack); if (err) return err; } @@ -580,15 +715,61 @@ static int dsa_switch_vlan_add(struct dsa_switch *ds, static int dsa_switch_vlan_del(struct dsa_switch *ds, struct dsa_notifier_vlan_info *info) { + struct dsa_port *dp; + int err; + if (!ds->ops->port_vlan_del) return -EOPNOTSUPP; - if (ds->index == info->sw_index) - return ds->ops->port_vlan_del(ds, info->port, info->vlan); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_vlan_match(dp, info)) { + err = dsa_port_do_vlan_del(dp, info->vlan); + if (err) + return err; + } + } + + return 0; +} + +static int dsa_switch_host_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) +{ + struct dsa_port *dp; + int err; + + if (!ds->ops->port_vlan_add) + return -EOPNOTSUPP; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_vlan_match(dp, info)) { + err = dsa_port_do_vlan_add(dp, info->vlan, + info->extack); + if (err) + return err; + } + } + + return 0; +} + +static int dsa_switch_host_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) +{ + struct dsa_port *dp; + int err; + + if (!ds->ops->port_vlan_del) + return -EOPNOTSUPP; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_vlan_match(dp, info)) { + err = dsa_port_do_vlan_del(dp, info->vlan); + if (err) + return err; + } + } - /* Do not deprogram the DSA links as they may be used as conduit - * for other VLAN members in the fabric. - */ return 0; } @@ -683,6 +864,18 @@ dsa_switch_disconnect_tag_proto(struct dsa_switch *ds, return 0; } +static int +dsa_switch_master_state_change(struct dsa_switch *ds, + struct dsa_notifier_master_state_info *info) +{ + if (!ds->ops->master_state_change) + return 0; + + ds->ops->master_state_change(ds, info->master, info->operational); + + return 0; +} + static int dsa_switch_event(struct notifier_block *nb, unsigned long event, void *info) { @@ -738,6 +931,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_VLAN_DEL: err = dsa_switch_vlan_del(ds, info); break; + case DSA_NOTIFIER_HOST_VLAN_ADD: + err = dsa_switch_host_vlan_add(ds, info); + break; + case DSA_NOTIFIER_HOST_VLAN_DEL: + err = dsa_switch_host_vlan_del(ds, info); + break; case DSA_NOTIFIER_MTU: err = dsa_switch_mtu(ds, info); break; @@ -756,6 +955,9 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL: err = dsa_switch_tag_8021q_vlan_del(ds, info); break; + case DSA_NOTIFIER_MASTER_STATE_CHANGE: + err = dsa_switch_master_state_change(ds, info); + break; default: err = -EOPNOTSUPP; break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 27712a81c967..114f663332d0 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -577,14 +577,14 @@ void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id) { u16 vid, tci; - skb_push_rcsum(skb, ETH_HLEN); if (skb_vlan_tag_present(skb)) { tci = skb_vlan_tag_get(skb); __vlan_hwaccel_clear_tag(skb); } else { + skb_push_rcsum(skb, ETH_HLEN); __skb_vlan_pop(skb, &tci); + skb_pull_rcsum(skb, ETH_HLEN); } - skb_pull_rcsum(skb, ETH_HLEN); vid = tci & VLAN_VID_MASK; diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 68982b2789a5..bd6f1d0e5372 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -32,6 +32,13 @@ static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, if (!xmit_work_fn || !xmit_worker) return NULL; + /* PTP over IP packets need UDP checksumming. We may have inherited + * NETIF_F_HW_CSUM from the DSA master, but these packets are not sent + * through the DSA master, so calculate the checksum here. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); if (!xmit_work) return NULL; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 1ea9401b8ace..57d2e00f1e5d 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -4,30 +4,12 @@ */ #include <linux/etherdevice.h> +#include <linux/bitfield.h> +#include <net/dsa.h> +#include <linux/dsa/tag_qca.h> #include "dsa_priv.h" -#define QCA_HDR_LEN 2 -#define QCA_HDR_VERSION 0x2 - -#define QCA_HDR_RECV_VERSION_MASK GENMASK(15, 14) -#define QCA_HDR_RECV_VERSION_S 14 -#define QCA_HDR_RECV_PRIORITY_MASK GENMASK(13, 11) -#define QCA_HDR_RECV_PRIORITY_S 11 -#define QCA_HDR_RECV_TYPE_MASK GENMASK(10, 6) -#define QCA_HDR_RECV_TYPE_S 6 -#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) -#define QCA_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) - -#define QCA_HDR_XMIT_VERSION_MASK GENMASK(15, 14) -#define QCA_HDR_XMIT_VERSION_S 14 -#define QCA_HDR_XMIT_PRIORITY_MASK GENMASK(13, 11) -#define QCA_HDR_XMIT_PRIORITY_S 11 -#define QCA_HDR_XMIT_CONTROL_MASK GENMASK(10, 8) -#define QCA_HDR_XMIT_CONTROL_S 8 -#define QCA_HDR_XMIT_FROM_CPU BIT(7) -#define QCA_HDR_XMIT_DP_BIT_MASK GENMASK(6, 0) - static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -40,8 +22,9 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) phdr = dsa_etype_header_pos_tx(skb); /* Set the version field, and set destination port information */ - hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | - QCA_HDR_XMIT_FROM_CPU | BIT(dp->index); + hdr = FIELD_PREP(QCA_HDR_XMIT_VERSION, QCA_HDR_VERSION); + hdr |= QCA_HDR_XMIT_FROM_CPU; + hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(dp->index)); *phdr = htons(hdr); @@ -50,10 +33,17 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) { - u8 ver; - u16 hdr; - int port; + struct qca_tagger_data *tagger_data; + struct dsa_port *dp = dev->dsa_ptr; + struct dsa_switch *ds = dp->ds; + u8 ver, pk_type; __be16 *phdr; + int port; + u16 hdr; + + BUILD_BUG_ON(sizeof(struct qca_mgmt_ethhdr) != QCA_HDR_MGMT_HEADER_LEN + QCA_HDR_LEN); + + tagger_data = ds->tagger_data; if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN))) return NULL; @@ -62,16 +52,33 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) hdr = ntohs(*phdr); /* Make sure the version is correct */ - ver = (hdr & QCA_HDR_RECV_VERSION_MASK) >> QCA_HDR_RECV_VERSION_S; + ver = FIELD_GET(QCA_HDR_RECV_VERSION, hdr); if (unlikely(ver != QCA_HDR_VERSION)) return NULL; + /* Get pk type */ + pk_type = FIELD_GET(QCA_HDR_RECV_TYPE, hdr); + + /* Ethernet mgmt read/write packet */ + if (pk_type == QCA_HDR_RECV_TYPE_RW_REG_ACK) { + if (likely(tagger_data->rw_reg_ack_handler)) + tagger_data->rw_reg_ack_handler(ds, skb); + return NULL; + } + + /* Ethernet MIB counter packet */ + if (pk_type == QCA_HDR_RECV_TYPE_MIB) { + if (likely(tagger_data->mib_autocast_handler)) + tagger_data->mib_autocast_handler(ds, skb); + return NULL; + } + /* Remove QCA tag and recalculate checksum */ skb_pull_rcsum(skb, QCA_HDR_LEN); dsa_strip_etype_header(skb, QCA_HDR_LEN); /* Get source port information */ - port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); + port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, hdr); skb->dev = dsa_master_find_slave(dev, 0, port); if (!skb->dev) @@ -80,12 +87,34 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) return skb; } +static int qca_tag_connect(struct dsa_switch *ds) +{ + struct qca_tagger_data *tagger_data; + + tagger_data = kzalloc(sizeof(*tagger_data), GFP_KERNEL); + if (!tagger_data) + return -ENOMEM; + + ds->tagger_data = tagger_data; + + return 0; +} + +static void qca_tag_disconnect(struct dsa_switch *ds) +{ + kfree(ds->tagger_data); + ds->tagger_data = NULL; +} + static const struct dsa_device_ops qca_netdev_ops = { .name = "qca", .proto = DSA_TAG_PROTO_QCA, + .connect = qca_tag_connect, + .disconnect = qca_tag_disconnect, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, .needed_headroom = QCA_HDR_LEN, + .promisc_on_master = true, }; MODULE_LICENSE("GPL"); diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index c1d5f5e0fdc9..18a5035d3bee 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -53,7 +53,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ nla_total_size(sizeof(u32)) + /* _RINGS_TX */ - nla_total_size(sizeof(u32)); /* _RINGS_RX_BUF_LEN */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX_BUF_LEN */ + nla_total_size(sizeof(u8)); /* _RINGS_TCP_DATA_SPLIT */ } static int rings_fill_reply(struct sk_buff *skb, @@ -61,9 +62,11 @@ static int rings_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct rings_reply_data *data = RINGS_REPDATA(reply_base); - const struct kernel_ethtool_ringparam *kernel_ringparam = &data->kernel_ringparam; + const struct kernel_ethtool_ringparam *kr = &data->kernel_ringparam; const struct ethtool_ringparam *ringparam = &data->ringparam; + WARN_ON(kr->tcp_data_split > ETHTOOL_TCP_DATA_SPLIT_ENABLED); + if ((ringparam->rx_max_pending && (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_MAX, ringparam->rx_max_pending) || @@ -84,9 +87,11 @@ static int rings_fill_reply(struct sk_buff *skb, ringparam->tx_max_pending) || nla_put_u32(skb, ETHTOOL_A_RINGS_TX, ringparam->tx_pending))) || - (kernel_ringparam->rx_buf_len && - (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, - kernel_ringparam->rx_buf_len)))) + (kr->rx_buf_len && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, kr->rx_buf_len))) || + (kr->tcp_data_split && + (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT, + kr->tcp_data_split)))) return -EMSGSIZE; return 0; diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 99f3af1a9d4d..fe6094e9a2db 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/debugfs.h> +#include <linux/jhash.h> #include "hsr_main.h" #include "hsr_framereg.h" @@ -28,6 +29,7 @@ hsr_node_table_show(struct seq_file *sfp, void *data) { struct hsr_priv *priv = (struct hsr_priv *)sfp->private; struct hsr_node *node; + int i; seq_printf(sfp, "Node Table entries for (%s) device\n", (priv->prot_version == PRP_V1 ? "PRP" : "HSR")); @@ -39,22 +41,28 @@ hsr_node_table_show(struct seq_file *sfp, void *data) seq_puts(sfp, "DAN-H\n"); rcu_read_lock(); - list_for_each_entry_rcu(node, &priv->node_db, mac_list) { - /* skip self node */ - if (hsr_addr_is_self(priv, node->macaddress_A)) - continue; - seq_printf(sfp, "%pM ", &node->macaddress_A[0]); - seq_printf(sfp, "%pM ", &node->macaddress_B[0]); - seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_A]); - seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_B]); - seq_printf(sfp, "%14x, ", node->addr_B_port); - - if (priv->prot_version == PRP_V1) - seq_printf(sfp, "%5x, %5x, %5x\n", - node->san_a, node->san_b, - (node->san_a == 0 && node->san_b == 0)); - else - seq_printf(sfp, "%5x\n", 1); + + for (i = 0 ; i < priv->hash_buckets; i++) { + hlist_for_each_entry_rcu(node, &priv->node_db[i], mac_list) { + /* skip self node */ + if (hsr_addr_is_self(priv, node->macaddress_A)) + continue; + seq_printf(sfp, "%pM ", &node->macaddress_A[0]); + seq_printf(sfp, "%pM ", &node->macaddress_B[0]); + seq_printf(sfp, "%10lx, ", + node->time_in[HSR_PT_SLAVE_A]); + seq_printf(sfp, "%10lx, ", + node->time_in[HSR_PT_SLAVE_B]); + seq_printf(sfp, "%14x, ", node->addr_B_port); + + if (priv->prot_version == PRP_V1) + seq_printf(sfp, "%5x, %5x, %5x\n", + node->san_a, node->san_b, + (node->san_a == 0 && + node->san_b == 0)); + else + seq_printf(sfp, "%5x\n", 1); + } } rcu_read_unlock(); return 0; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e57fdad9ef94..7f250216433d 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -485,12 +485,16 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], { bool unregister = false; struct hsr_priv *hsr; - int res; + int res, i; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); - INIT_LIST_HEAD(&hsr->node_db); - INIT_LIST_HEAD(&hsr->self_node_db); + INIT_HLIST_HEAD(&hsr->self_node_db); + hsr->hash_buckets = HSR_HSIZE; + get_random_bytes(&hsr->hash_seed, sizeof(hsr->hash_seed)); + for (i = 0; i < hsr->hash_buckets; i++) + INIT_HLIST_HEAD(&hsr->node_db[i]); + spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index e59cbb4f0cd1..5bf357734b11 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -570,20 +570,23 @@ static int fill_frame_info(struct hsr_frame_info *frame, struct ethhdr *ethhdr; __be16 proto; int ret; + u32 hash; /* Check if skb contains ethhdr */ if (skb->mac_len < sizeof(struct ethhdr)) return -EINVAL; memset(frame, 0, sizeof(*frame)); + + ethhdr = (struct ethhdr *)skb_mac_header(skb); + hash = hsr_mac_hash(port->hsr, ethhdr->h_source); frame->is_supervision = is_supervision_frame(port->hsr, skb); - frame->node_src = hsr_get_node(port, &hsr->node_db, skb, + frame->node_src = hsr_get_node(port, &hsr->node_db[hash], skb, frame->is_supervision, port->type); if (!frame->node_src) return -1; /* Unknown node and !is_supervision, or no mem */ - ethhdr = (struct ethhdr *)skb_mac_header(skb); frame->is_vlan = false; proto = ethhdr->h_proto; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 0775f0f95dbf..b3c6ffa1894d 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -15,11 +15,28 @@ #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/rculist.h> +#include <linux/jhash.h> #include "hsr_main.h" #include "hsr_framereg.h" #include "hsr_netlink.h" -/* TODO: use hash lists for mac addresses (linux/jhash.h)? */ +u32 hsr_mac_hash(struct hsr_priv *hsr, const unsigned char *addr) +{ + u32 hash = jhash(addr, ETH_ALEN, hsr->hash_seed); + + return reciprocal_scale(hash, hsr->hash_buckets); +} + +struct hsr_node *hsr_node_get_first(struct hlist_head *head) +{ + struct hlist_node *first; + + first = rcu_dereference(hlist_first_rcu(head)); + if (first) + return hlist_entry(first, struct hsr_node, mac_list); + + return NULL; +} /* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b, * false otherwise. @@ -42,8 +59,7 @@ bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) { struct hsr_node *node; - node = list_first_or_null_rcu(&hsr->self_node_db, struct hsr_node, - mac_list); + node = hsr_node_get_first(&hsr->self_node_db); if (!node) { WARN_ONCE(1, "HSR: No self node\n"); return false; @@ -59,12 +75,12 @@ bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) /* Search for mac entry. Caller must hold rcu read lock. */ -static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, +static struct hsr_node *find_node_by_addr_A(struct hlist_head *node_db, const unsigned char addr[ETH_ALEN]) { struct hsr_node *node; - list_for_each_entry_rcu(node, node_db, mac_list) { + hlist_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, addr)) return node; } @@ -79,7 +95,7 @@ int hsr_create_self_node(struct hsr_priv *hsr, const unsigned char addr_a[ETH_ALEN], const unsigned char addr_b[ETH_ALEN]) { - struct list_head *self_node_db = &hsr->self_node_db; + struct hlist_head *self_node_db = &hsr->self_node_db; struct hsr_node *node, *oldnode; node = kmalloc(sizeof(*node), GFP_KERNEL); @@ -90,14 +106,13 @@ int hsr_create_self_node(struct hsr_priv *hsr, ether_addr_copy(node->macaddress_B, addr_b); spin_lock_bh(&hsr->list_lock); - oldnode = list_first_or_null_rcu(self_node_db, - struct hsr_node, mac_list); + oldnode = hsr_node_get_first(self_node_db); if (oldnode) { - list_replace_rcu(&oldnode->mac_list, &node->mac_list); + hlist_replace_rcu(&oldnode->mac_list, &node->mac_list); spin_unlock_bh(&hsr->list_lock); kfree_rcu(oldnode, rcu_head); } else { - list_add_tail_rcu(&node->mac_list, self_node_db); + hlist_add_tail_rcu(&node->mac_list, self_node_db); spin_unlock_bh(&hsr->list_lock); } @@ -106,25 +121,25 @@ int hsr_create_self_node(struct hsr_priv *hsr, void hsr_del_self_node(struct hsr_priv *hsr) { - struct list_head *self_node_db = &hsr->self_node_db; + struct hlist_head *self_node_db = &hsr->self_node_db; struct hsr_node *node; spin_lock_bh(&hsr->list_lock); - node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); + node = hsr_node_get_first(self_node_db); if (node) { - list_del_rcu(&node->mac_list); + hlist_del_rcu(&node->mac_list); kfree_rcu(node, rcu_head); } spin_unlock_bh(&hsr->list_lock); } -void hsr_del_nodes(struct list_head *node_db) +void hsr_del_nodes(struct hlist_head *node_db) { struct hsr_node *node; - struct hsr_node *tmp; + struct hlist_node *tmp; - list_for_each_entry_safe(node, tmp, node_db, mac_list) - kfree(node); + hlist_for_each_entry_safe(node, tmp, node_db, mac_list) + kfree_rcu(node, rcu_head); } void prp_handle_san_frame(bool san, enum hsr_port_type port, @@ -145,7 +160,7 @@ void prp_handle_san_frame(bool san, enum hsr_port_type port, * originating from the newly added node. */ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, - struct list_head *node_db, + struct hlist_head *node_db, unsigned char addr[], u16 seq_out, bool san, enum hsr_port_type rx_port) @@ -175,14 +190,14 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, hsr->proto_ops->handle_san_frame(san, rx_port, new_node); spin_lock_bh(&hsr->list_lock); - list_for_each_entry_rcu(node, node_db, mac_list, - lockdep_is_held(&hsr->list_lock)) { + hlist_for_each_entry_rcu(node, node_db, mac_list, + lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) goto out; } - list_add_tail_rcu(&new_node->mac_list, node_db); + hlist_add_tail_rcu(&new_node->mac_list, node_db); spin_unlock_bh(&hsr->list_lock); return new_node; out: @@ -202,7 +217,7 @@ void prp_update_san_info(struct hsr_node *node, bool is_sup) /* Get the hsr_node from which 'skb' was sent. */ -struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, +struct hsr_node *hsr_get_node(struct hsr_port *port, struct hlist_head *node_db, struct sk_buff *skb, bool is_sup, enum hsr_port_type rx_port) { @@ -218,7 +233,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, ethhdr = (struct ethhdr *)skb_mac_header(skb); - list_for_each_entry_rcu(node, node_db, mac_list) { + hlist_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { if (hsr->proto_ops->update_san_info) hsr->proto_ops->update_san_info(node, is_sup); @@ -268,11 +283,12 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) struct hsr_sup_tlv *hsr_sup_tlv; struct hsr_node *node_real; struct sk_buff *skb = NULL; - struct list_head *node_db; + struct hlist_head *node_db; struct ethhdr *ethhdr; int i; unsigned int pull_size = 0; unsigned int total_pull_size = 0; + u32 hash; /* Here either frame->skb_hsr or frame->skb_prp should be * valid as supervision frame always will have protocol @@ -310,11 +326,13 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) hsr_sp = (struct hsr_sup_payload *)skb->data; /* Merge node_curr (registered on macaddress_B) into node_real */ - node_db = &port_rcv->hsr->node_db; - node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); + node_db = port_rcv->hsr->node_db; + hash = hsr_mac_hash(hsr, hsr_sp->macaddress_A); + node_real = find_node_by_addr_A(&node_db[hash], hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ - node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, + node_real = hsr_add_node(hsr, &node_db[hash], + hsr_sp->macaddress_A, HSR_SEQNR_START - 1, true, port_rcv->type); if (!node_real) @@ -348,7 +366,8 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) hsr_sp = (struct hsr_sup_payload *)skb->data; /* Check if redbox mac and node mac are equal. */ - if (!ether_addr_equal(node_real->macaddress_A, hsr_sp->macaddress_A)) { + if (!ether_addr_equal(node_real->macaddress_A, + hsr_sp->macaddress_A)) { /* This is a redbox supervision frame for a VDAN! */ goto done; } @@ -368,7 +387,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); - list_del_rcu(&node_curr->mac_list); + hlist_del_rcu(&node_curr->mac_list); spin_unlock_bh(&hsr->list_lock); kfree_rcu(node_curr, rcu_head); @@ -406,6 +425,7 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, struct hsr_port *port) { struct hsr_node *node_dst; + u32 hash; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: Mac header not set\n", __func__); @@ -415,7 +435,8 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, if (!is_unicast_ether_addr(eth_hdr(skb)->h_dest)) return; - node_dst = find_node_by_addr_A(&port->hsr->node_db, + hash = hsr_mac_hash(port->hsr, eth_hdr(skb)->h_dest); + node_dst = find_node_by_addr_A(&port->hsr->node_db[hash], eth_hdr(skb)->h_dest); if (!node_dst) { if (net_ratelimit()) @@ -491,59 +512,73 @@ static struct hsr_port *get_late_port(struct hsr_priv *hsr, void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); + struct hlist_node *tmp; struct hsr_node *node; - struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; + int i; spin_lock_bh(&hsr->list_lock); - list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { - /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] - * nor time_in[HSR_PT_SLAVE_B], will ever be updated for - * the master port. Thus the master node will be repeatedly - * pruned leading to packet loss. - */ - if (hsr_addr_is_self(hsr, node->macaddress_A)) - continue; - - /* Shorthand */ - time_a = node->time_in[HSR_PT_SLAVE_A]; - time_b = node->time_in[HSR_PT_SLAVE_B]; - - /* Check for timestamps old enough to risk wrap-around */ - if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET / 2)) - node->time_in_stale[HSR_PT_SLAVE_A] = true; - if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET / 2)) - node->time_in_stale[HSR_PT_SLAVE_B] = true; - - /* Get age of newest frame from node. - * At least one time_in is OK here; nodes get pruned long - * before both time_ins can get stale - */ - timestamp = time_a; - if (node->time_in_stale[HSR_PT_SLAVE_A] || - (!node->time_in_stale[HSR_PT_SLAVE_B] && - time_after(time_b, time_a))) - timestamp = time_b; - - /* Warn of ring error only as long as we get frames at all */ - if (time_is_after_jiffies(timestamp + - msecs_to_jiffies(1.5 * MAX_SLAVE_DIFF))) { - rcu_read_lock(); - port = get_late_port(hsr, node); - if (port) - hsr_nl_ringerror(hsr, node->macaddress_A, port); - rcu_read_unlock(); - } - /* Prune old entries */ - if (time_is_before_jiffies(timestamp + - msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { - hsr_nl_nodedown(hsr, node->macaddress_A); - list_del_rcu(&node->mac_list); - /* Note that we need to free this entry later: */ - kfree_rcu(node, rcu_head); + for (i = 0; i < hsr->hash_buckets; i++) { + hlist_for_each_entry_safe(node, tmp, &hsr->node_db[i], + mac_list) { + /* Don't prune own node. + * Neither time_in[HSR_PT_SLAVE_A] + * nor time_in[HSR_PT_SLAVE_B], will ever be updated + * for the master port. Thus the master node will be + * repeatedly pruned leading to packet loss. + */ + if (hsr_addr_is_self(hsr, node->macaddress_A)) + continue; + + /* Shorthand */ + time_a = node->time_in[HSR_PT_SLAVE_A]; + time_b = node->time_in[HSR_PT_SLAVE_B]; + + /* Check for timestamps old enough to + * risk wrap-around + */ + if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET / 2)) + node->time_in_stale[HSR_PT_SLAVE_A] = true; + if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET / 2)) + node->time_in_stale[HSR_PT_SLAVE_B] = true; + + /* Get age of newest frame from node. + * At least one time_in is OK here; nodes get pruned + * long before both time_ins can get stale + */ + timestamp = time_a; + if (node->time_in_stale[HSR_PT_SLAVE_A] || + (!node->time_in_stale[HSR_PT_SLAVE_B] && + time_after(time_b, time_a))) + timestamp = time_b; + + /* Warn of ring error only as long as we get + * frames at all + */ + if (time_is_after_jiffies(timestamp + + msecs_to_jiffies(1.5 * MAX_SLAVE_DIFF))) { + rcu_read_lock(); + port = get_late_port(hsr, node); + if (port) + hsr_nl_ringerror(hsr, + node->macaddress_A, + port); + rcu_read_unlock(); + } + + /* Prune old entries */ + if (time_is_before_jiffies(timestamp + + msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { + hsr_nl_nodedown(hsr, node->macaddress_A); + hlist_del_rcu(&node->mac_list); + /* Note that we need to free this + * entry later: + */ + kfree_rcu(node, rcu_head); + } } } spin_unlock_bh(&hsr->list_lock); @@ -557,17 +592,19 @@ void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]) { struct hsr_node *node; + u32 hash; + + hash = hsr_mac_hash(hsr, addr); if (!_pos) { - node = list_first_or_null_rcu(&hsr->node_db, - struct hsr_node, mac_list); + node = hsr_node_get_first(&hsr->node_db[hash]); if (node) ether_addr_copy(addr, node->macaddress_A); return node; } node = _pos; - list_for_each_entry_continue_rcu(node, &hsr->node_db, mac_list) { + hlist_for_each_entry_continue_rcu(node, mac_list) { ether_addr_copy(addr, node->macaddress_A); return node; } @@ -587,8 +624,11 @@ int hsr_get_node_data(struct hsr_priv *hsr, struct hsr_node *node; struct hsr_port *port; unsigned long tdiff; + u32 hash; + + hash = hsr_mac_hash(hsr, addr); - node = find_node_by_addr_A(&hsr->node_db, addr); + node = find_node_by_addr_A(&hsr->node_db[hash], addr); if (!node) return -ENOENT; diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index bdbb8c822ba1..d7cce6b161e3 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -28,9 +28,11 @@ struct hsr_frame_info { bool is_from_san; }; +u32 hsr_mac_hash(struct hsr_priv *hsr, const unsigned char *addr); +struct hsr_node *hsr_node_get_first(struct hlist_head *head); void hsr_del_self_node(struct hsr_priv *hsr); -void hsr_del_nodes(struct list_head *node_db); -struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, +void hsr_del_nodes(struct hlist_head *node_db); +struct hsr_node *hsr_get_node(struct hsr_port *port, struct hlist_head *node_db, struct sk_buff *skb, bool is_sup, enum hsr_port_type rx_port); void hsr_handle_sup_frame(struct hsr_frame_info *frame); @@ -68,7 +70,7 @@ void prp_handle_san_frame(bool san, enum hsr_port_type port, void prp_update_san_info(struct hsr_node *node, bool is_sup); struct hsr_node { - struct list_head mac_list; + struct hlist_node mac_list; unsigned char macaddress_A[ETH_ALEN]; unsigned char macaddress_B[ETH_ALEN]; /* Local slave through which AddrB frames are received from this node */ diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 043e4e9a1694..ca556bda3467 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -63,6 +63,9 @@ struct hsr_tag { #define HSR_V1_SUP_LSDUSIZE 52 +#define HSR_HSIZE_SHIFT 8 +#define HSR_HSIZE BIT(HSR_HSIZE_SHIFT) + /* The helper functions below assumes that 'path' occupies the 4 most * significant bits of the 16-bit field shared by 'path' and 'LSDU_size' (or * equivalently, the 4 most significant bits of HSR tag byte 14). @@ -201,8 +204,8 @@ struct hsr_proto_ops { struct hsr_priv { struct rcu_head rcu_head; struct list_head ports; - struct list_head node_db; /* Known HSR nodes */ - struct list_head self_node_db; /* MACs of slaves */ + struct hlist_head node_db[HSR_HSIZE]; /* Known HSR nodes */ + struct hlist_head self_node_db; /* MACs of slaves */ struct timer_list announce_timer; /* Supervision frame dispatch */ struct timer_list prune_timer; int announce_count; @@ -212,6 +215,8 @@ struct hsr_priv { spinlock_t seqnr_lock; /* locking for sequence_nr */ spinlock_t list_lock; /* locking for node list */ struct hsr_proto_ops *proto_ops; + u32 hash_buckets; + u32 hash_seed; #define PRP_LAN_ID 0x5 /* 0x1010 for A and 0x1011 for B. Bit 0 is set * based on SLAVE_A or SLAVE_B */ @@ -259,11 +264,6 @@ static inline u16 prp_get_skb_sequence_nr(struct prp_rct *rct) return ntohs(rct->sequence_nr); } -static inline u16 get_prp_lan_id(struct prp_rct *rct) -{ - return ntohs(rct->lan_id_and_LSDU_size) >> 12; -} - /* assume there is a valid rct */ static inline bool prp_check_lsdu_size(struct sk_buff *skb, struct prp_rct *rct, diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index f3c8f91dbe2c..1405c037cf7a 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -105,6 +105,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, static void hsr_dellink(struct net_device *dev, struct list_head *head) { struct hsr_priv *hsr = netdev_priv(dev); + int i; del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->announce_timer); @@ -113,7 +114,8 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) hsr_del_ports(hsr); hsr_del_self_node(hsr); - hsr_del_nodes(&hsr->node_db); + for (i = 0; i < hsr->hash_buckets; i++) + hsr_del_nodes(&hsr->node_db[i]); unregister_netdevice_queue(dev, head); } diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 2cf62718a282..2c087b7f17c5 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -47,6 +47,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> +#include <linux/if_arp.h> #include <net/ipv6.h> diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index dd5a45f8a78a..359249ab77bf 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -30,7 +30,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, { void *hdr; int i, pages = 0; - uint32_t *buf = kcalloc(32, sizeof(uint32_t), GFP_KERNEL); + u32 *buf = kcalloc(IEEE802154_MAX_PAGE + 1, sizeof(u32), GFP_KERNEL); pr_debug("%s\n", __func__); @@ -47,7 +47,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) || nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel)) goto nla_put_failure; - for (i = 0; i < 32; i++) { + for (i = 0; i <= IEEE802154_MAX_PAGE; i++) { if (phy->supported.channels[i]) buf[pages++] = phy->supported.channels[i] | (i << 27); } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index de610cb83694..f79ab942f03b 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#include <linux/init.h> #include <linux/types.h> #include <linux/bpf_verifier.h> #include <linux/bpf.h> @@ -95,12 +96,14 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id) + u32 *next_btf_id, + enum bpf_type_flag *flag) { size_t end; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id); + return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, + flag); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); @@ -212,26 +215,23 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, } } -BTF_SET_START(bpf_tcp_ca_kfunc_ids) +BTF_SET_START(bpf_tcp_ca_check_kfunc_ids) BTF_ID(func, tcp_reno_ssthresh) BTF_ID(func, tcp_reno_cong_avoid) BTF_ID(func, tcp_reno_undo_cwnd) BTF_ID(func, tcp_slow_start) BTF_ID(func, tcp_cong_avoid_ai) -BTF_SET_END(bpf_tcp_ca_kfunc_ids) +BTF_SET_END(bpf_tcp_ca_check_kfunc_ids) -static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id, struct module *owner) -{ - if (btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id)) - return true; - return bpf_check_mod_kfunc_call(&bpf_tcp_ca_kfunc_list, kfunc_btf_id, owner); -} +static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &bpf_tcp_ca_check_kfunc_ids, +}; static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = { .get_func_proto = bpf_tcp_ca_get_func_proto, .is_valid_access = bpf_tcp_ca_is_valid_access, .btf_struct_access = bpf_tcp_ca_btf_struct_access, - .check_kfunc_call = bpf_tcp_ca_check_kfunc_call, }; static int bpf_tcp_ca_init_member(const struct btf_type *t, @@ -300,3 +300,9 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .init = bpf_tcp_ca_init, .name = "tcp_congestion_ops", }; + +static int __init bpf_tcp_ca_kfunc_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); +} +late_initcall(bpf_tcp_ca_kfunc_init); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 85117b45216d..e0730c4d07d6 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -32,6 +32,7 @@ #include <linux/list.h> #include <linux/slab.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> @@ -738,8 +739,16 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); + + if (!inet_validate_dscp(rtm->rtm_tos)) { + NL_SET_ERR_MSG(extack, + "Invalid dsfield (tos): ECN bits must be 0"); + err = -EINVAL; + goto errout; + } + cfg->fc_dscp = inet_dsfield_to_dscp(rtm->rtm_tos); + cfg->fc_dst_len = rtm->rtm_dst_len; - cfg->fc_tos = rtm->rtm_tos; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; cfg->fc_scope = rtm->rtm_scope; @@ -1550,7 +1559,7 @@ static void ip_fib_net_exit(struct net *net) { int i; - rtnl_lock(); + ASSERT_RTNL(); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); @@ -1575,7 +1584,7 @@ static void ip_fib_net_exit(struct net *net) #ifdef CONFIG_IP_MULTIPLE_TABLES fib4_rules_exit(net); #endif - rtnl_unlock(); + kfree(net->ipv4.fib_table_hash); fib4_notifier_exit(net); } @@ -1602,7 +1611,9 @@ out: out_proc: nl_fib_lookup_exit(net); out_nlfl: + rtnl_lock(); ip_fib_net_exit(net); + rtnl_unlock(); goto out; } @@ -1610,12 +1621,23 @@ static void __net_exit fib_net_exit(struct net *net) { fib_proc_exit(net); nl_fib_lookup_exit(net); - ip_fib_net_exit(net); +} + +static void __net_exit fib_net_exit_batch(struct list_head *net_list) +{ + struct net *net; + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) + ip_fib_net_exit(net); + + rtnl_unlock(); } static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, + .exit_batch = fib_net_exit_batch, }; void __init ip_fib_init(void) diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 78e40ea42e58..f9b9e26c32c1 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -4,13 +4,14 @@ #include <linux/types.h> #include <linux/list.h> +#include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/nexthop.h> struct fib_alias { struct hlist_node fa_list; struct fib_info *fa_info; - u8 fa_tos; + dscp_t fa_dscp; u8 fa_type; u8 fa_state; u8 fa_slen; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index e0b6c8b6de57..001fea394bde 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/export.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/tcp.h> @@ -35,7 +36,7 @@ struct fib4_rule { struct fib_rule common; u8 dst_len; u8 src_len; - u8 tos; + dscp_t dscp; __be32 src; __be32 srcmask; __be32 dst; @@ -49,7 +50,7 @@ static bool fib4_rule_matchall(const struct fib_rule *rule) { struct fib4_rule *r = container_of(rule, struct fib4_rule, common); - if (r->dst_len || r->src_len || r->tos) + if (r->dst_len || r->src_len || r->dscp) return false; return fib_rule_matchall(rule); } @@ -185,7 +186,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, ((daddr ^ r->dst) & r->dstmask)) return 0; - if (r->tos && (r->tos != fl4->flowi4_tos)) + if (r->dscp && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos)) return 0; if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) @@ -225,10 +226,17 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, int err = -EINVAL; struct fib4_rule *rule4 = (struct fib4_rule *) rule; + if (!inet_validate_dscp(frh->tos)) { + NL_SET_ERR_MSG(extack, + "Invalid dsfield (tos): ECN bits must be 0"); + goto errout; + } + /* IPv4 currently doesn't handle high order DSCP bits correctly */ if (frh->tos & ~IPTOS_TOS_MASK) { NL_SET_ERR_MSG(extack, "Invalid tos"); goto errout; } + rule4->dscp = inet_dsfield_to_dscp(frh->tos); /* split local/main if they are not already split */ err = fib_unmerge(net); @@ -270,7 +278,6 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->srcmask = inet_make_mask(rule4->src_len); rule4->dst_len = frh->dst_len; rule4->dstmask = inet_make_mask(rule4->dst_len); - rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; @@ -313,7 +320,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->dst_len && (rule4->dst_len != frh->dst_len)) return 0; - if (frh->tos && (rule4->tos != frh->tos)) + if (frh->tos && inet_dscp_to_dsfield(rule4->dscp) != frh->tos) return 0; #ifdef CONFIG_IP_ROUTE_CLASSID @@ -337,7 +344,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->dst_len = rule4->dst_len; frh->src_len = rule4->src_len; - frh->tos = rule4->tos; + frh->tos = inet_dscp_to_dsfield(rule4->dscp); if ((rule4->dst_len && nla_put_in_addr(skb, FRA_DST, rule4->dst)) || diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2dd375f7407b..c5a29703185a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -32,6 +32,7 @@ #include <linux/hash.h> #include <net/arp.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> @@ -523,7 +524,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, fri.tb_id = tb_id; fri.dst = key; fri.dst_len = dst_len; - fri.tos = fa->fa_tos; + fri.tos = inet_dscp_to_dsfield(fa->fa_dscp); fri.type = fa->fa_type; fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); @@ -1257,34 +1258,13 @@ fib_info_laddrhash_bucket(const struct net *net, __be32 val) return &fib_info_laddrhash[slot]; } -static struct hlist_head *fib_info_hash_alloc(int bytes) -{ - if (bytes <= PAGE_SIZE) - return kzalloc(bytes, GFP_KERNEL); - else - return (struct hlist_head *) - __get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(bytes)); -} - -static void fib_info_hash_free(struct hlist_head *hash, int bytes) -{ - if (!hash) - return; - - if (bytes <= PAGE_SIZE) - kfree(hash); - else - free_pages((unsigned long) hash, get_order(bytes)); -} - static void fib_info_hash_move(struct hlist_head *new_info_hash, struct hlist_head *new_laddrhash, unsigned int new_size) { struct hlist_head *old_info_hash, *old_laddrhash; unsigned int old_size = fib_info_hash_size; - unsigned int i, bytes; + unsigned int i; spin_lock_bh(&fib_info_lock); old_info_hash = fib_info_hash; @@ -1325,9 +1305,8 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, spin_unlock_bh(&fib_info_lock); - bytes = old_size * sizeof(struct hlist_head *); - fib_info_hash_free(old_info_hash, bytes); - fib_info_hash_free(old_laddrhash, bytes); + kvfree(old_info_hash); + kvfree(old_laddrhash); } __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, @@ -1444,19 +1423,19 @@ struct fib_info *fib_create_info(struct fib_config *cfg, unsigned int new_size = fib_info_hash_size << 1; struct hlist_head *new_info_hash; struct hlist_head *new_laddrhash; - unsigned int bytes; + size_t bytes; if (!new_size) new_size = 16; - bytes = new_size * sizeof(struct hlist_head *); - new_info_hash = fib_info_hash_alloc(bytes); - new_laddrhash = fib_info_hash_alloc(bytes); + bytes = (size_t)new_size * sizeof(struct hlist_head *); + new_info_hash = kvzalloc(bytes, GFP_KERNEL); + new_laddrhash = kvzalloc(bytes, GFP_KERNEL); if (!new_info_hash || !new_laddrhash) { - fib_info_hash_free(new_info_hash, bytes); - fib_info_hash_free(new_laddrhash, bytes); - } else + kvfree(new_info_hash); + kvfree(new_laddrhash); + } else { fib_info_hash_move(new_info_hash, new_laddrhash, new_size); - + } if (!fib_info_hash_size) goto failure; } @@ -2061,7 +2040,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) int order = -1, last_idx = -1; struct fib_alias *fa, *fa1 = NULL; u32 last_prio = res->fi->fib_priority; - u8 last_tos = 0; + dscp_t last_dscp = 0; hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; @@ -2069,19 +2048,20 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) if (fa->fa_slen != slen) continue; - if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + if (fa->fa_dscp && + fa->fa_dscp != inet_dsfield_to_dscp(flp->flowi4_tos)) continue; if (fa->tb_id != tb->tb_id) continue; if (next_fi->fib_priority > last_prio && - fa->fa_tos == last_tos) { - if (last_tos) + fa->fa_dscp == last_dscp) { + if (last_dscp) continue; break; } if (next_fi->fib_flags & RTNH_F_DEAD) continue; - last_tos = fa->fa_tos; + last_dscp = fa->fa_dscp; last_prio = next_fi->fib_priority; if (next_fi->fib_scope != res->scope || diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index f7f74d5c14da..2af2b99e0bea 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -61,6 +61,7 @@ #include <linux/vmalloc.h> #include <linux/notifier.h> #include <net/net_namespace.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> @@ -81,7 +82,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, - .tos = fa->fa_tos, + .tos = inet_dscp_to_dsfield(fa->fa_dscp), .type = fa->fa_type, .tb_id = fa->tb_id, }; @@ -98,7 +99,7 @@ static int call_fib_entry_notifiers(struct net *net, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, - .tos = fa->fa_tos, + .tos = inet_dscp_to_dsfield(fa->fa_dscp), .type = fa->fa_type, .tb_id = fa->tb_id, }; @@ -973,13 +974,13 @@ static struct key_vector *fib_find_node(struct trie *t, return n; } -/* Return the first fib alias matching TOS with +/* Return the first fib alias matching DSCP with * priority less than or equal to PRIO. * If 'find_first' is set, return the first matching - * fib alias, regardless of TOS and priority. + * fib alias, regardless of DSCP and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, - u8 tos, u32 prio, u32 tb_id, + dscp_t dscp, u32 prio, u32 tb_id, bool find_first) { struct fib_alias *fa; @@ -988,6 +989,10 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, return NULL; hlist_for_each_entry(fa, fah, fa_list) { + /* Avoid Sparse warning when using dscp_t in inequalities */ + u8 __fa_dscp = inet_dscp_to_dsfield(fa->fa_dscp); + u8 __dscp = inet_dscp_to_dsfield(dscp); + if (fa->fa_slen < slen) continue; if (fa->fa_slen != slen) @@ -998,9 +1003,9 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, break; if (find_first) return fa; - if (fa->fa_tos > tos) + if (__fa_dscp > __dscp) continue; - if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos) + if (fa->fa_info->fib_priority >= prio || __fa_dscp < __dscp) return fa; } @@ -1027,8 +1032,8 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && - fa->fa_tos == fri->tos && fa->fa_info == fri->fi && - fa->fa_type == fri->type) + fa->fa_dscp == inet_dsfield_to_dscp(fri->tos) && + fa->fa_info == fri->fi && fa->fa_type == fri->type) return fa; } @@ -1214,7 +1219,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; - u8 tos = cfg->fc_tos; + dscp_t dscp; u32 key; int err; @@ -1231,12 +1236,13 @@ int fib_table_insert(struct net *net, struct fib_table *tb, goto err; } + dscp = cfg->fc_dscp; l = fib_find_node(t, &tp, key); - fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority, + fa = l ? fib_find_alias(&l->leaf, slen, dscp, fi->fib_priority, tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias - * with the same keys [prefix,tos,priority], if such key already + * with the same keys [prefix,dscp,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and @@ -1244,7 +1250,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, * of the new alias. */ - if (fa && fa->fa_tos == tos && + if (fa && fa->fa_dscp == dscp && fa->fa_info->fib_priority == fi->fib_priority) { struct fib_alias *fa_first, *fa_match; @@ -1264,7 +1270,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, hlist_for_each_entry_from(fa, fa_list) { if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || - (fa->fa_tos != tos)) + (fa->fa_dscp != dscp)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; @@ -1292,7 +1298,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, goto out; fi_drop = fa->fa_info; - new_fa->fa_tos = fa->fa_tos; + new_fa->fa_dscp = fa->fa_dscp; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; state = fa->fa_state; @@ -1355,7 +1361,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, goto out; new_fa->fa_info = fi; - new_fa->fa_tos = tos; + new_fa->fa_dscp = dscp; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; new_fa->fa_slen = slen; @@ -1571,7 +1577,8 @@ found: if (index >= (1ul << fa->fa_slen)) continue; } - if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + if (fa->fa_dscp && + inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) continue; if (fi->fib_dead) continue; @@ -1707,7 +1714,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, struct key_vector *l, *tp; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; - u8 tos = cfg->fc_tos; + dscp_t dscp; u32 key; key = ntohl(cfg->fc_dst); @@ -1719,11 +1726,13 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!l) return -ESRCH; - fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false); + dscp = cfg->fc_dscp; + fa = fib_find_alias(&l->leaf, slen, dscp, 0, tb->tb_id, false); if (!fa) return -ESRCH; - pr_debug("Deleting %08x/%d tos=%d t=%p\n", key, plen, tos, t); + pr_debug("Deleting %08x/%d dsfield=0x%02x t=%p\n", key, plen, + inet_dscp_to_dsfield(dscp), t); fa_to_delete = NULL; hlist_for_each_entry_from(fa, fa_list) { @@ -1731,7 +1740,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || - (fa->fa_tos != tos)) + (fa->fa_dscp != dscp)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && @@ -2299,7 +2308,7 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, fri.tb_id = tb->tb_id; fri.dst = xkey; fri.dst_len = KEYLENGTH - fa->fa_slen; - fri.tos = fa->fa_tos; + fri.tos = inet_dscp_to_dsfield(fa->fa_dscp); fri.type = fa->fa_type; fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); @@ -2811,8 +2820,9 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); - if (fa->fa_tos) - seq_printf(seq, " tos=%d", fa->fa_tos); + if (fa->fa_dscp) + seq_printf(seq, " tos=%d", + inet_dscp_to_dsfield(fa->fa_dscp)); seq_putc(seq, '\n'); } } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index b7e277d8a84d..72a375c7f417 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -192,24 +192,14 @@ struct icmp_control { static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; -/* - * The ICMP socket(s). This is the most convenient way to flow control - * our ICMP output as well as maintain a clean interface throughout - * all layers. All Socketless IP sends will soon be gone. - * - * On SMP we have one ICMP socket per-cpu. - */ -static struct sock *icmp_sk(struct net *net) -{ - return this_cpu_read(*net->ipv4.icmp_sk); -} +static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk); /* Called with BH disabled */ static inline struct sock *icmp_xmit_lock(struct net *net) { struct sock *sk; - sk = icmp_sk(net); + sk = this_cpu_read(ipv4_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a @@ -217,11 +207,13 @@ static inline struct sock *icmp_xmit_lock(struct net *net) */ return NULL; } + sock_net_set(sk, net); return sk; } static inline void icmp_xmit_unlock(struct sock *sk) { + sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } @@ -363,14 +355,13 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, return 0; } -static void icmp_push_reply(struct icmp_bxm *icmp_param, +static void icmp_push_reply(struct sock *sk, + struct icmp_bxm *icmp_param, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt) { - struct sock *sk; struct sk_buff *skb; - sk = icmp_sk(dev_net((*rt)->dst.dev)); if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, @@ -452,7 +443,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) if (IS_ERR(rt)) goto out_unlock; if (icmpv4_xrlim_allow(net, rt, &fl4, type, code)) - icmp_push_reply(icmp_param, &fl4, &ipc, &rt); + icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); @@ -766,7 +757,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (!fl4.saddr) fl4.saddr = htonl(INADDR_DUMMY); - icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); + icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); out_unlock: @@ -1434,46 +1425,8 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = { }, }; -static void __net_exit icmp_sk_exit(struct net *net) -{ - int i; - - for_each_possible_cpu(i) - inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i)); - free_percpu(net->ipv4.icmp_sk); - net->ipv4.icmp_sk = NULL; -} - static int __net_init icmp_sk_init(struct net *net) { - int i, err; - - net->ipv4.icmp_sk = alloc_percpu(struct sock *); - if (!net->ipv4.icmp_sk) - return -ENOMEM; - - for_each_possible_cpu(i) { - struct sock *sk; - - err = inet_ctl_sock_create(&sk, PF_INET, - SOCK_RAW, IPPROTO_ICMP, net); - if (err < 0) - goto fail; - - *per_cpu_ptr(net->ipv4.icmp_sk, i) = sk; - - /* Enough space for 2 64K ICMP packets, including - * sk_buff/skb_shared_info struct overhead. - */ - sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); - - /* - * Speedup sock_wfree() - */ - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); - inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; - } - /* Control parameters for ECHO replies. */ net->ipv4.sysctl_icmp_echo_ignore_all = 0; net->ipv4.sysctl_icmp_echo_enable_probe = 0; @@ -1499,18 +1452,36 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; return 0; - -fail: - icmp_sk_exit(net); - return err; } static struct pernet_operations __net_initdata icmp_sk_ops = { .init = icmp_sk_init, - .exit = icmp_sk_exit, }; int __init icmp_init(void) { + int err, i; + + for_each_possible_cpu(i) { + struct sock *sk; + + err = inet_ctl_sock_create(&sk, PF_INET, + SOCK_RAW, IPPROTO_ICMP, &init_net); + if (err < 0) + return err; + + per_cpu(ipv4_icmp_sk, i) = sk; + + /* Enough space for 2 64K ICMP packets, including + * sk_buff/skb_shared_info struct overhead. + */ + sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); + + /* + * Speedup sock_wfree() + */ + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; + } return register_pernet_subsys(&icmp_sk_ops); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fc2a985f6064..1e5b53c2bb26 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -866,12 +866,9 @@ static void reqsk_timer_handler(struct timer_list *t) (!resend || !inet_rtx_syn_ack(sk_listener, req) || inet_rsk(req)->acked)) { - unsigned long timeo; - if (req->num_timeout++ == 0) atomic_dec(&queue->young); - timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); - mod_timer(&req->rsk_timer, jiffies + timeo); + mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX)); if (!nreq) return; @@ -1046,6 +1043,9 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); + if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) + sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); + /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 30ab717ff1b8..17440840a791 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -637,7 +637,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) int err = 0; if (sk->sk_state != TCP_LISTEN) { + local_bh_disable(); inet_ehash_nolisten(sk, osk, NULL); + local_bh_enable(); return 0; } WARN_ON(!sk_unhashed(sk)); @@ -669,45 +671,54 @@ int inet_hash(struct sock *sk) { int err = 0; - if (sk->sk_state != TCP_CLOSE) { - local_bh_disable(); + if (sk->sk_state != TCP_CLOSE) err = __inet_hash(sk, NULL); - local_bh_enable(); - } return err; } EXPORT_SYMBOL_GPL(inet_hash); -void inet_unhash(struct sock *sk) +static void __inet_unhash(struct sock *sk, struct inet_listen_hashbucket *ilb) { - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - struct inet_listen_hashbucket *ilb = NULL; - spinlock_t *lock; - if (sk_unhashed(sk)) return; - if (sk->sk_state == TCP_LISTEN) { - ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &ilb->lock; - } else { - lock = inet_ehash_lockp(hashinfo, sk->sk_hash); - } - spin_lock_bh(lock); - if (sk_unhashed(sk)) - goto unlock; - if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_stop_listen_sock(sk); if (ilb) { + struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + inet_unhash2(hashinfo, sk); ilb->count--; } __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); -unlock: - spin_unlock_bh(lock); +} + +void inet_unhash(struct sock *sk) +{ + struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + + if (sk_unhashed(sk)) + return; + + if (sk->sk_state == TCP_LISTEN) { + struct inet_listen_hashbucket *ilb; + + ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + /* Don't disable bottom halves while acquiring the lock to + * avoid circular locking dependency on PREEMPT_RT. + */ + spin_lock(&ilb->lock); + __inet_unhash(sk, ilb); + spin_unlock(&ilb->lock); + } else { + spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); + + spin_lock_bh(lock); + __inet_unhash(sk, NULL); + spin_unlock_bh(lock); + } } EXPORT_SYMBOL_GPL(inet_unhash); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 437afe392e66..9e0bbd026560 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -52,14 +52,15 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) spin_unlock(lock); /* Disassociate with bind bucket. */ - bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, - hashinfo->bhash_size)]; + bhead = &hashinfo->bhash[tw->tw_bslot]; spin_lock(&bhead->lock); inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); - atomic_dec(&tw->tw_dr->tw_count); + if (refcount_dec_and_test(&tw->tw_dr->tw_refcount)) + kfree(tw->tw_dr); + inet_twsk_put(tw); } @@ -110,8 +111,12 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, - hashinfo->bhash_size)]; + /* Cache inet_bhashfn(), because 'struct net' might be no longer + * available later in inet_twsk_kill(). + */ + tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num, + hashinfo->bhash_size); + bhead = &hashinfo->bhash[tw->tw_bslot]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); @@ -145,10 +150,6 @@ static void tw_timer_handler(struct timer_list *t) { struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); - if (tw->tw_kill) - __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); - else - __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITED); inet_twsk_kill(tw); } @@ -158,7 +159,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, { struct inet_timewait_sock *tw; - if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets) + if (refcount_read(&dr->tw_refcount) - 1 >= dr->sysctl_max_tw_buckets) return NULL; tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, @@ -244,59 +245,15 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) * of PAWS. */ - tw->tw_kill = timeo <= 4*HZ; if (!rearm) { + bool kill = timeo <= 4*HZ; + + __NET_INC_STATS(twsk_net(tw), kill ? LINUX_MIB_TIMEWAITKILLED : + LINUX_MIB_TIMEWAITED); BUG_ON(mod_timer(&tw->tw_timer, jiffies + timeo)); - atomic_inc(&tw->tw_dr->tw_count); + refcount_inc(&tw->tw_dr->tw_refcount); } else { mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); - -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) -{ - struct inet_timewait_sock *tw; - struct sock *sk; - struct hlist_nulls_node *node; - unsigned int slot; - - for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { - struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; -restart_rcu: - cond_resched(); - rcu_read_lock(); -restart: - sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) - continue; - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count)) - continue; - - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) - continue; - - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count))) { - inet_twsk_put(tw); - goto restart; - } - - rcu_read_unlock(); - local_bh_disable(); - inet_twsk_deschedule_put(tw); - local_bh_enable(); - goto restart_rcu; - } - /* If the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot) - goto restart; - rcu_read_unlock(); - } -} -EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3a025c011971..d94f9f7e60c3 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -196,7 +196,8 @@ resubmit: if (ipprot) { if (!ipprot->no_policy) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); + kfree_skb_reason(skb, + SKB_DROP_REASON_XFRM_POLICY); return; } nf_reset_ct(skb); @@ -215,7 +216,7 @@ resubmit: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); } - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_IP_NOPROTO); } else { __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS); consume_skb(skb); @@ -318,8 +319,10 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, { const struct iphdr *iph = ip_hdr(skb); int (*edemux)(struct sk_buff *skb); + int err, drop_reason; struct rtable *rt; - int err; + + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (ip_can_use_hint(skb, iph, hint)) { err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos, @@ -396,19 +399,23 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, * so-called "hole-196" attack) so do it for both. */ if (in_dev && - IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) + IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) { + drop_reason = SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST; goto drop; + } } return NET_RX_SUCCESS; drop: - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return NET_RX_DROP; drop_error: - if (err == -EXDEV) + if (err == -EXDEV) { + drop_reason = SKB_DROP_REASON_IP_RPFILTER; __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); + } goto drop; } @@ -436,13 +443,16 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) { const struct iphdr *iph; + int drop_reason; u32 len; /* When the interface is in promisc. mode, drop all the crap * that it receives, do not try to analyse it. */ - if (skb->pkt_type == PACKET_OTHERHOST) + if (skb->pkt_type == PACKET_OTHERHOST) { + drop_reason = SKB_DROP_REASON_OTHERHOST; goto drop; + } __IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len); @@ -452,6 +462,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) goto out; } + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto inhdr_error; @@ -488,6 +499,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) len = ntohs(iph->tot_len); if (skb->len < len) { + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; __IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) @@ -516,11 +528,14 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) return skb; csum_error: + drop_reason = SKB_DROP_REASON_IP_CSUM; __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: + if (drop_reason == SKB_DROP_REASON_NOT_SPECIFIED) + drop_reason = SKB_DROP_REASON_IP_INHDR; __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); out: return NULL; } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index da1b5038bdfd..a9e22a098872 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -42,7 +42,7 @@ */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, - __be32 daddr, struct rtable *rt, int is_frag) + __be32 daddr, struct rtable *rt) { unsigned char *iph = skb_network_header(skb); @@ -53,28 +53,15 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, if (opt->srr) memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4); - if (!is_frag) { - if (opt->rr_needaddr) - ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); - if (opt->ts_needaddr) - ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); - if (opt->ts_needtime) { - __be32 midtime; + if (opt->rr_needaddr) + ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); + if (opt->ts_needaddr) + ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); + if (opt->ts_needtime) { + __be32 midtime; - midtime = inet_current_timestamp(); - memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); - } - return; - } - if (opt->rr) { - memset(iph + opt->rr, IPOPT_NOP, iph[opt->rr + 1]); - opt->rr = 0; - opt->rr_needaddr = 0; - } - if (opt->ts) { - memset(iph + opt->ts, IPOPT_NOP, iph[opt->ts + 1]); - opt->ts = 0; - opt->ts_needaddr = opt->ts_needtime = 0; + midtime = inet_current_timestamp(); + memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 139cec29ed06..0c0574eb5f5b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -179,7 +179,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; - ip_options_build(skb, &opt->opt, daddr, rt, 0); + ip_options_build(skb, &opt->opt, daddr, rt); } skb->priority = sk->sk_priority; @@ -519,7 +519,7 @@ packet_routed: if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; - ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); + ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt); } ip_select_ident_segs(net, skb, sk, @@ -1541,7 +1541,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, if (opt) { iph->ihl += opt->optlen >> 2; - ip_options_build(skb, opt, cork->addr, rt, 0); + ip_options_build(skb, opt, cork->addr, rt); } skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 29bbe2b08ae9..c860519d57ee 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -268,13 +268,12 @@ static void __net_exit ipmr_rules_exit(struct net *net) { struct mr_table *mrt, *next; - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) { list_del(&mrt->list); ipmr_free_table(mrt); } fib_rules_unregister(net->ipv4.mr_rules_ops); - rtnl_unlock(); } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, @@ -330,10 +329,9 @@ static int __net_init ipmr_rules_init(struct net *net) static void __net_exit ipmr_rules_exit(struct net *net) { - rtnl_lock(); + ASSERT_RTNL(); ipmr_free_table(net->ipv4.mrt); net->ipv4.mrt = NULL; - rtnl_unlock(); } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, @@ -3077,7 +3075,9 @@ static int __net_init ipmr_net_init(struct net *net) proc_cache_fail: remove_proc_entry("ip_mr_vif", net->proc_net); proc_vif_fail: + rtnl_lock(); ipmr_rules_exit(net); + rtnl_unlock(); #endif ipmr_rules_fail: ipmr_notifier_exit(net); @@ -3092,12 +3092,22 @@ static void __net_exit ipmr_net_exit(struct net *net) remove_proc_entry("ip_mr_vif", net->proc_net); #endif ipmr_notifier_exit(net); - ipmr_rules_exit(net); +} + +static void __net_exit ipmr_net_exit_batch(struct list_head *net_list) +{ + struct net *net; + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) + ipmr_rules_exit(net); + rtnl_unlock(); } static struct pernet_operations ipmr_net_ops = { .init = ipmr_net_init, .exit = ipmr_net_exit, + .exit_batch = ipmr_net_exit_batch, }; int __init ip_mr_init(void) diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 3f248a19faa3..fab357cc8559 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -295,28 +295,24 @@ pptp_inbound_pkt(struct sk_buff *skb, return NF_ACCEPT; } +static const struct nf_nat_pptp_hook pptp_hooks = { + .outbound = pptp_outbound_pkt, + .inbound = pptp_inbound_pkt, + .exp_gre = pptp_exp_gre, + .expectfn = pptp_nat_expected, +}; + static int __init nf_nat_helper_pptp_init(void) { - BUG_ON(nf_nat_pptp_hook_outbound != NULL); - RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, pptp_outbound_pkt); - - BUG_ON(nf_nat_pptp_hook_inbound != NULL); - RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, pptp_inbound_pkt); - - BUG_ON(nf_nat_pptp_hook_exp_gre != NULL); - RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, pptp_exp_gre); + WARN_ON(nf_nat_pptp_hook != NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook, &pptp_hooks); - BUG_ON(nf_nat_pptp_hook_expectfn != NULL); - RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, pptp_nat_expected); return 0; } static void __exit nf_nat_helper_pptp_fini(void) { - RCU_INIT_POINTER(nf_nat_pptp_hook_expectfn, NULL); - RCU_INIT_POINTER(nf_nat_pptp_hook_exp_gre, NULL); - RCU_INIT_POINTER(nf_nat_pptp_hook_inbound, NULL); - RCU_INIT_POINTER(nf_nat_pptp_hook_outbound, NULL); + RCU_INIT_POINTER(nf_nat_pptp_hook, NULL); synchronize_rcu(); } diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index eeafeccebb8d..e459a391e607 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3733,12 +3733,16 @@ out: } EXPORT_SYMBOL(nexthop_res_grp_activity_update); -static void __net_exit nexthop_net_exit(struct net *net) +static void __net_exit nexthop_net_exit_batch(struct list_head *net_list) { + struct net *net; + rtnl_lock(); - flush_all_nexthops(net); + list_for_each_entry(net, net_list, exit_list) { + flush_all_nexthops(net); + kfree(net->nexthop.devhash); + } rtnl_unlock(); - kfree(net->nexthop.devhash); } static int __net_init nexthop_net_init(struct net *net) @@ -3756,7 +3760,7 @@ static int __net_init nexthop_net_init(struct net *net) static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, - .exit = nexthop_net_exit, + .exit_batch = nexthop_net_exit_batch, }; static int __init nexthop_init(void) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index f30273afb539..28836071f0a6 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -59,8 +59,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, - atomic_read(&net->ipv4.tcp_death_row.tw_count), sockets, - proto_memory_allocated(&tcp_prot)); + refcount_read(&net->ipv4.tcp_death_row->tw_refcount) - 1, + sockets, proto_memory_allocated(&tcp_prot)); seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), proto_memory_allocated(&udp_prot)); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f33ad1f383b6..f444f5983405 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -84,6 +84,7 @@ #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> +#include <net/inet_dscp.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/route.h> @@ -112,14 +113,13 @@ #define DEFAULT_MIN_PMTU (512 + 20 + 20) #define DEFAULT_MTU_EXPIRES (10 * 60 * HZ) - +#define DEFAULT_MIN_ADVMSS 256 static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; -static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; @@ -458,7 +458,7 @@ static u32 *ip_tstamps __read_mostly; * if one generator is seldom used. This makes hard for an attacker * to infer how many packets were sent between two points in time. */ -u32 ip_idents_reserve(u32 hash, int segs) +static u32 ip_idents_reserve(u32 hash, int segs) { u32 bucket, old, now = (u32)jiffies; atomic_t *p_id; @@ -479,7 +479,6 @@ u32 ip_idents_reserve(u32 hash, int segs) */ return atomic_add_return(segs + delta, p_id) - segs; } -EXPORT_SYMBOL(ip_idents_reserve); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { @@ -1298,9 +1297,10 @@ static void set_class_tag(struct rtable *rt, u32 tag) static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { + struct net *net = dev_net(dst->dev); unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, - ip_rt_min_advmss); + net->ipv4.ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); } @@ -1485,6 +1485,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) struct uncached_list { spinlock_t lock; struct list_head head; + struct list_head quarantine; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); @@ -1506,7 +1507,7 @@ void rt_del_uncached_list(struct rtable *rt) struct uncached_list *ul = rt->rt_uncached_list; spin_lock_bh(&ul->lock); - list_del(&rt->rt_uncached); + list_del_init(&rt->rt_uncached); spin_unlock_bh(&ul->lock); } } @@ -1521,20 +1522,24 @@ static void ipv4_dst_destroy(struct dst_entry *dst) void rt_flush_dev(struct net_device *dev) { - struct rtable *rt; + struct rtable *rt, *safe; int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); + if (list_empty(&ul->head)) + continue; + spin_lock_bh(&ul->lock); - list_for_each_entry(rt, &ul->head, rt_uncached) { + list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; dev_replace_track(dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); + list_move(&rt->rt_uncached, &ul->quarantine); } spin_unlock_bh(&ul->lock); } @@ -3392,7 +3397,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (fa->fa_slen == slen && fa->tb_id == fri.tb_id && - fa->fa_tos == fri.tos && + fa->fa_dscp == inet_dsfield_to_dscp(fri.tos) && fa->fa_info == res.fi && fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); @@ -3535,13 +3540,6 @@ static struct ctl_table ipv4_route_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "min_adv_mss", - .data = &ip_rt_min_advmss, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { } }; @@ -3569,6 +3567,13 @@ static struct ctl_table ipv4_route_netns_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "min_adv_mss", + .data = &init_net.ipv4.ip_rt_min_advmss, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { }, }; @@ -3631,6 +3636,7 @@ static __net_init int netns_ip_rt_init(struct net *net) /* Set default value for namespaceified sysctls */ net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU; net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES; + net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS; return 0; } @@ -3705,6 +3711,7 @@ int __init ip_rt_init(void) struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); + INIT_LIST_HEAD(&ul->quarantine); spin_lock_init(&ul->lock); } #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 97eb54774924..1cae27b5dcd8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -589,6 +589,14 @@ static struct ctl_table ipv4_table[] = { }; static struct ctl_table ipv4_net_table[] = { + /* tcp_max_tw_buckets must be first in this table. */ + { + .procname = "tcp_max_tw_buckets", +/* .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, */ + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "icmp_echo_ignore_all", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, @@ -1001,13 +1009,6 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &two, }, { - .procname = "tcp_max_tw_buckets", - .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, .maxlen = sizeof(int), @@ -1400,7 +1401,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!table) goto err_alloc; - for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { + /* skip first entry (sysctl_max_tw_buckets) */ + for (i = 1; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { if (table[i].data) { /* Update the variables to point into * the current struct net @@ -1415,6 +1417,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) } } + table[0].data = &net->ipv4.tcp_death_row->sysctl_max_tw_buckets; + net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (!net->ipv4.ipv4_hdr) goto err_reg; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 02cb275e5487..760e8221d321 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -894,8 +894,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ - new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER; - new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal); + new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size); /* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index ec5550089b4d..02e8626ccb27 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1154,7 +1154,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .set_state = bbr_set_state, }; -BTF_SET_START(tcp_bbr_kfunc_ids) +BTF_SET_START(tcp_bbr_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID(func, bbr_init) @@ -1167,25 +1167,27 @@ BTF_ID(func, bbr_min_tso_segs) BTF_ID(func, bbr_set_state) #endif #endif -BTF_SET_END(tcp_bbr_kfunc_ids) +BTF_SET_END(tcp_bbr_check_kfunc_ids) -static DEFINE_KFUNC_BTF_ID_SET(&tcp_bbr_kfunc_ids, tcp_bbr_kfunc_btf_set); +static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &tcp_bbr_check_kfunc_ids, +}; static int __init bbr_register(void) { int ret; BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); - ret = tcp_register_congestion_control(&tcp_bbr_cong_ops); - if (ret) + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_bbr_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); - return 0; + return tcp_register_congestion_control(&tcp_bbr_cong_ops); } static void __exit bbr_unregister(void) { - unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); tcp_unregister_congestion_control(&tcp_bbr_cong_ops); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index e07837e23b3f..24d562dd6225 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -485,7 +485,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .name = "cubic", }; -BTF_SET_START(tcp_cubic_kfunc_ids) +BTF_SET_START(tcp_cubic_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID(func, cubictcp_init) @@ -496,9 +496,12 @@ BTF_ID(func, cubictcp_cwnd_event) BTF_ID(func, cubictcp_acked) #endif #endif -BTF_SET_END(tcp_cubic_kfunc_ids) +BTF_SET_END(tcp_cubic_check_kfunc_ids) -static DEFINE_KFUNC_BTF_ID_SET(&tcp_cubic_kfunc_ids, tcp_cubic_kfunc_btf_set); +static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &tcp_cubic_check_kfunc_ids, +}; static int __init cubictcp_register(void) { @@ -534,16 +537,14 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - ret = tcp_register_congestion_control(&cubictcp); - if (ret) + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_cubic_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); - return 0; + return tcp_register_congestion_control(&cubictcp); } static void __exit cubictcp_unregister(void) { - unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); tcp_unregister_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 0d7ab3cc7b61..1943a6630341 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -238,7 +238,7 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { .name = "dctcp-reno", }; -BTF_SET_START(tcp_dctcp_kfunc_ids) +BTF_SET_START(tcp_dctcp_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID(func, dctcp_init) @@ -249,25 +249,27 @@ BTF_ID(func, dctcp_cwnd_undo) BTF_ID(func, dctcp_state) #endif #endif -BTF_SET_END(tcp_dctcp_kfunc_ids) +BTF_SET_END(tcp_dctcp_check_kfunc_ids) -static DEFINE_KFUNC_BTF_ID_SET(&tcp_dctcp_kfunc_ids, tcp_dctcp_kfunc_btf_set); +static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &tcp_dctcp_check_kfunc_ids, +}; static int __init dctcp_register(void) { int ret; BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE); - ret = tcp_register_congestion_control(&dctcp); - if (ret) + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_dctcp_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); - return 0; + return tcp_register_congestion_control(&dctcp); } static void __exit dctcp_unregister(void) { - unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); tcp_unregister_congestion_control(&dctcp); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bfe4112e000c..92e65d56dc2c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6703,7 +6703,8 @@ static void tcp_openreq_init(struct request_sock *req, ireq->ir_num = ntohs(tcp_hdr(skb)->dest); ireq->ir_mark = inet_request_mark(sk, skb); #if IS_ENABLED(CONFIG_SMC) - ireq->smc_ok = rx_opt->smc_ok; + ireq->smc_ok = rx_opt->smc_ok && !(tcp_sk(sk)->smc_hs_congested && + tcp_sk(sk)->smc_hs_congested(sk)); #endif } @@ -6725,6 +6726,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); ireq->ireq_family = sk_listener->sk_family; + req->timeout = TCP_TIMEOUT_INIT; } return req; @@ -6941,9 +6943,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); } else { tcp_rsk(req)->tfo_listener = false; - if (!want_cookie) - inet_csk_reqsk_queue_hash_add(sk, req, - tcp_timeout_init((struct sock *)req)); + if (!want_cookie) { + req->timeout = tcp_timeout_init((struct sock *)req); + inet_csk_reqsk_queue_hash_add(sk, req, req->timeout); + } af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : TCP_SYNACK_COOKIE, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fec656f5a39e..6873f46fc8ba 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -91,6 +91,8 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); +static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -206,7 +208,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct rtable *rt; int err; struct ip_options_rcu *inet_opt; - struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; + struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; @@ -810,7 +812,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; @@ -825,6 +828,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) transmit_time); ctl_sk->sk_mark = 0; + sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); @@ -908,7 +912,8 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? @@ -921,6 +926,7 @@ static void tcp_v4_send_ack(const struct sock *sk, transmit_time); ctl_sk->sk_mark = 0; + sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } @@ -3111,41 +3117,18 @@ EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { - int cpu; + struct inet_timewait_death_row *tcp_death_row = net->ipv4.tcp_death_row; if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); - - for_each_possible_cpu(cpu) - inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); - free_percpu(net->ipv4.tcp_sk); + if (refcount_dec_and_test(&tcp_death_row->tw_refcount)) + kfree(tcp_death_row); } static int __net_init tcp_sk_init(struct net *net) { - int res, cpu, cnt; - - net->ipv4.tcp_sk = alloc_percpu(struct sock *); - if (!net->ipv4.tcp_sk) - return -ENOMEM; - - for_each_possible_cpu(cpu) { - struct sock *sk; - - res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, - IPPROTO_TCP, net); - if (res) - goto fail; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); - - /* Please enforce IP_DF and IPID==0 for RST and - * ACK sent in SYN-RECV and TIME-WAIT state. - */ - inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; - - *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; - } + int cnt; net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; @@ -3172,9 +3155,13 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 2; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; + net->ipv4.tcp_death_row = kzalloc(sizeof(struct inet_timewait_death_row), GFP_KERNEL); + if (!net->ipv4.tcp_death_row) + return -ENOMEM; + refcount_set(&net->ipv4.tcp_death_row->tw_refcount, 1); cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; - net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; + net->ipv4.tcp_death_row->sysctl_max_tw_buckets = cnt / 2; + net->ipv4.tcp_death_row->hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; @@ -3229,18 +3216,12 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_congestion_control = &tcp_reno; return 0; -fail: - tcp_sk_exit(net); - - return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; - inet_twsk_purge(&tcp_hashinfo, AF_INET); - list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } @@ -3326,6 +3307,24 @@ static void __init bpf_iter_register(void) void __init tcp_v4_init(void) { + int cpu, res; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, &init_net); + if (res) + panic("Failed to create the TCP control socket.\n"); + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + + per_cpu(ipv4_tcp_sk, cpu) = sk; + } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7c2d3ac2363a..6366df7aaf2a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -248,7 +248,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct inet_timewait_sock *tw; - struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; + struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; tw = inet_twsk_alloc(sk, tcp_death_row, state); @@ -583,7 +583,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout); + tmp_opt.ts_recent_stamp = ktime_get_seconds() - reqsk_timeout(req, TCP_RTO_MAX) / HZ; paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } @@ -622,8 +622,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, !inet_rtx_syn_ack(sk, req)) { unsigned long expires = jiffies; - expires += min(TCP_TIMEOUT_INIT << req->num_timeout, - TCP_RTO_MAX); + expires += reqsk_timeout(req, TCP_RTO_MAX); if (!fastopen) mod_timer_pending(&req->rsk_timer, expires); else diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5079832af5c1..e76bf1e9251e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1960,7 +1960,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, bytes = min_t(unsigned long, sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), - sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); + sk->sk_gso_max_size); /* Goal is to send at least one packet per ms, * not one big TSO packet every 100 ms. @@ -4092,7 +4092,9 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) struct flowi fl; int res; - tcp_rsk(req)->txhash = net_tx_rndhash(); + /* Paired with WRITE_ONCE() in sock_setsockopt() */ + if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) + tcp_rsk(req)->txhash = net_tx_rndhash(); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 090360939401..6b4d8361560f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2093,16 +2093,20 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); + int drop_reason; /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) + if (rc == -ENOMEM) { UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - else + drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; + } else { UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, is_udplite); + drop_reason = SKB_DROP_REASON_PROTO_MEM; + } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -2120,14 +2124,17 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { + int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); /* * Charge it to the socket, dropping if the queue is full. */ - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; + } nf_reset_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { @@ -2204,8 +2211,10 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto drop; + } udp_csum_pull_header(skb); @@ -2213,11 +2222,12 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) return __udp_queue_rcv_skb(sk, skb); csum_error: + drop_reason = SKB_DROP_REASON_UDP_CSUM; __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return -1; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3f23da8c0b10..2f307da17f21 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -146,18 +146,11 @@ static int ipv6_generate_stable_address(struct in6_addr *addr, #define IN6_ADDR_HSIZE_SHIFT 8 #define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) -/* - * Configured unicast address hash table - */ -static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; -static DEFINE_SPINLOCK(addrconf_hash_lock); -static void addrconf_verify(void); -static void addrconf_verify_rtnl(void); -static void addrconf_verify_work(struct work_struct *); +static void addrconf_verify(struct net *net); +static void addrconf_verify_rtnl(struct net *net); static struct workqueue_struct *addrconf_wq; -static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work); static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); @@ -379,7 +372,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ASSERT_RTNL(); - if (dev->mtu < IPV6_MIN_MTU) + if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev) return ERR_PTR(-EINVAL); ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL); @@ -416,12 +409,13 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) return ERR_PTR(err); } - if (snmp6_register_dev(ndev) < 0) { - netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n", - __func__, dev->name); - goto err_release; + if (dev != blackhole_netdev) { + if (snmp6_register_dev(ndev) < 0) { + netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n", + __func__, dev->name); + goto err_release; + } } - /* One reference from device. */ refcount_set(&ndev->refcnt, 1); @@ -452,25 +446,28 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; - err = addrconf_sysctl_register(ndev); - if (err) { - ipv6_mc_destroy_dev(ndev); - snmp6_unregister_dev(ndev); - goto err_release; + if (dev != blackhole_netdev) { + err = addrconf_sysctl_register(ndev); + if (err) { + ipv6_mc_destroy_dev(ndev); + snmp6_unregister_dev(ndev); + goto err_release; + } } /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev); - /* Join interface-local all-node multicast group */ - ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes); - - /* Join all-node multicast group */ - ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); + if (dev != blackhole_netdev) { + /* Join interface-local all-node multicast group */ + ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes); - /* Join all-router multicast group if forwarding is set */ - if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST)) - ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + /* Join all-node multicast group */ + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); + /* Join all-router multicast group if forwarding is set */ + if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST)) + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + } return ndev; err_release: @@ -554,7 +551,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, #ifdef CONFIG_IPV6_MROUTE if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, - devconf->mc_forwarding) < 0) + atomic_read(&devconf->mc_forwarding)) < 0) goto nla_put_failure; #endif if ((all || type == NETCONFA_PROXY_NEIGH) && @@ -1011,9 +1008,7 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, { struct inet6_ifaddr *ifp; - hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev) return true; @@ -1024,20 +1019,21 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) { - unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr); + struct net *net = dev_net(dev); + unsigned int hash = inet6_addr_hash(net, &ifa->addr); int err = 0; - spin_lock(&addrconf_hash_lock); + spin_lock(&net->ipv6.addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ - if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) { + if (ipv6_chk_same_addr(net, &ifa->addr, dev, hash)) { netdev_dbg(dev, "ipv6_add_addr: already assigned\n"); err = -EEXIST; } else { - hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); + hlist_add_head_rcu(&ifa->addr_lst, &net->ipv6.inet6_addr_lst[hash]); } - spin_unlock(&addrconf_hash_lock); + spin_unlock(&net->ipv6.addrconf_hash_lock); return err; } @@ -1261,9 +1257,10 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, static void ipv6_del_addr(struct inet6_ifaddr *ifp) { - int state; enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; + struct net *net = dev_net(ifp->idev->dev); unsigned long expires; + int state; ASSERT_RTNL(); @@ -1275,9 +1272,9 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (state == INET6_IFADDR_STATE_DEAD) goto out; - spin_lock_bh(&addrconf_hash_lock); + spin_lock_bh(&net->ipv6.addrconf_hash_lock); hlist_del_init_rcu(&ifp->addr_lst); - spin_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&net->ipv6.addrconf_hash_lock); write_lock_bh(&ifp->idev->lock); @@ -1920,10 +1917,8 @@ __ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, if (skip_dev_check) dev = NULL; - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { ndev = ifp->idev->dev; - if (!net_eq(dev_net(ndev), net)) - continue; if (l3mdev_master_dev_rcu(ndev) != l3mdev) continue; @@ -2027,9 +2022,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add struct inet6_ifaddr *ifp, *result = NULL; rcu_read_lock(); - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { @@ -2096,7 +2089,7 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; - struct net *net = dev_net(ifp->idev->dev); + struct net *net = dev_net(idev->dev); if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); @@ -2675,7 +2668,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, create, now); in6_ifa_put(ifp); - addrconf_verify(); + addrconf_verify(net); } return 0; @@ -2987,7 +2980,7 @@ static int inet6_addr_add(struct net *net, int ifindex, manage_tempaddrs(idev, ifp, cfg->valid_lft, cfg->preferred_lft, true, jiffies); in6_ifa_put(ifp); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(net); return 0; } else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, @@ -3027,7 +3020,7 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, manage_tempaddrs(idev, ifp, 0, 0, false, jiffies); ipv6_del_addr(ifp); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(net); if (ipv6_addr_is_multicast(pfx)) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, pfx, dev->ifindex); @@ -3772,9 +3765,9 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister) /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { - struct hlist_head *h = &inet6_addr_lst[i]; + struct hlist_head *h = &net->ipv6.inet6_addr_lst[i]; - spin_lock_bh(&addrconf_hash_lock); + spin_lock_bh(&net->ipv6.addrconf_hash_lock); restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { @@ -3790,7 +3783,7 @@ restart: } } } - spin_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&net->ipv6.addrconf_hash_lock); } write_lock_bh(&idev->lock); @@ -4246,7 +4239,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, * before this temporary address becomes deprecated. */ if (ifp->flags & IFA_F_TEMPORARY) - addrconf_verify_rtnl(); + addrconf_verify_rtnl(dev_net(dev)); } static void addrconf_dad_run(struct inet6_dev *idev, bool restart) @@ -4288,10 +4281,8 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) } for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], + hlist_for_each_entry_rcu(ifa, &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { - if (!net_eq(dev_net(ifa->idev->dev), net)) - continue; /* sync with offset */ if (p < state->offset) { p++; @@ -4314,8 +4305,6 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); hlist_for_each_entry_continue_rcu(ifa, addr_lst) { - if (!net_eq(dev_net(ifa->idev->dev), net)) - continue; state->offset++; return ifa; } @@ -4323,9 +4312,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, state->offset = 0; while (++state->bucket < IN6_ADDR_HSIZE) { hlist_for_each_entry_rcu(ifa, - &inet6_addr_lst[state->bucket], addr_lst) { - if (!net_eq(dev_net(ifa->idev->dev), net)) - continue; + &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { return ifa; } } @@ -4413,9 +4400,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) int ret = 0; rcu_read_lock(); - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr) && (ifp->flags & IFA_F_HOMEADDRESS)) { ret = 1; @@ -4453,9 +4438,7 @@ int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, hash = inet6_addr_hash(net, addr); hash_found = false; - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { hash_found = true; @@ -4484,7 +4467,7 @@ int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, * Periodic address status verification */ -static void addrconf_verify_rtnl(void) +static void addrconf_verify_rtnl(struct net *net) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; @@ -4496,11 +4479,11 @@ static void addrconf_verify_rtnl(void) now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); - cancel_delayed_work(&addr_chk_work); + cancel_delayed_work(&net->ipv6.addr_chk_work); for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &net->ipv6.inet6_addr_lst[i], addr_lst) { unsigned long age; /* When setting preferred_lft to a value not zero or @@ -4599,20 +4582,23 @@ restart: pr_debug("now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", now, next, next_sec, next_sched); - mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now); + mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, next_sched - now); rcu_read_unlock_bh(); } static void addrconf_verify_work(struct work_struct *w) { + struct net *net = container_of(to_delayed_work(w), struct net, + ipv6.addr_chk_work); + rtnl_lock(); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(net); rtnl_unlock(); } -static void addrconf_verify(void) +static void addrconf_verify(struct net *net) { - mod_delayed_work(addrconf_wq, &addr_chk_work, 0); + mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, 0); } static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, @@ -4708,7 +4694,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, return 0; } -static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) +static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, + struct ifa6_config *cfg) { u32 flags; clock_t expires; @@ -4822,7 +4809,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) jiffies); } - addrconf_verify_rtnl(); + addrconf_verify_rtnl(net); return 0; } @@ -4909,7 +4896,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, !(nlh->nlmsg_flags & NLM_F_REPLACE)) err = -EEXIST; else - err = inet6_addr_modify(ifa, &cfg); + err = inet6_addr_modify(net, ifa, &cfg); in6_ifa_put(ifa); @@ -5533,7 +5520,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding; + array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding); #endif array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; @@ -5794,7 +5781,7 @@ update_lft: write_unlock_bh(&idev->lock); inet6_ifinfo_notify(RTM_NEWLINK, idev); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(dev_net(dev)); return 0; } @@ -7111,6 +7098,14 @@ static int __net_init addrconf_init_net(struct net *net) int err = -ENOMEM; struct ipv6_devconf *all, *dflt; + spin_lock_init(&net->ipv6.addrconf_hash_lock); + INIT_DEFERRABLE_WORK(&net->ipv6.addr_chk_work, addrconf_verify_work); + net->ipv6.inet6_addr_lst = kcalloc(IN6_ADDR_HSIZE, + sizeof(struct hlist_head), + GFP_KERNEL); + if (!net->ipv6.inet6_addr_lst) + goto err_alloc_addr; + all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; @@ -7172,11 +7167,15 @@ err_reg_all: err_alloc_dflt: kfree(all); err_alloc_all: + kfree(net->ipv6.inet6_addr_lst); +err_alloc_addr: return err; } static void __net_exit addrconf_exit_net(struct net *net) { + int i; + #ifdef CONFIG_SYSCTL __addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); @@ -7184,7 +7183,19 @@ static void __net_exit addrconf_exit_net(struct net *net) NETCONFA_IFINDEX_ALL); #endif kfree(net->ipv6.devconf_dflt); + net->ipv6.devconf_dflt = NULL; kfree(net->ipv6.devconf_all); + net->ipv6.devconf_all = NULL; + + cancel_delayed_work_sync(&net->ipv6.addr_chk_work); + /* + * Check hash table, then free it. + */ + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON_ONCE(!hlist_empty(&net->ipv6.inet6_addr_lst[i])); + + kfree(net->ipv6.inet6_addr_lst); + net->ipv6.inet6_addr_lst = NULL; } static struct pernet_operations addrconf_ops = { @@ -7207,7 +7218,7 @@ static struct rtnl_af_ops inet6_ops __read_mostly = { int __init addrconf_init(void) { struct inet6_dev *idev; - int i, err; + int err; err = ipv6_addr_label_init(); if (err < 0) { @@ -7226,26 +7237,8 @@ int __init addrconf_init(void) goto out_nowq; } - /* The addrconf netdev notifier requires that loopback_dev - * has it's ipv6 private information allocated and setup - * before it can bring up and give link-local addresses - * to other devices which are up. - * - * Unfortunately, loopback_dev is not necessarily the first - * entry in the global dev_base list of net devices. In fact, - * it is likely to be the very last entry on that list. - * So this causes the notifier registry below to try and - * give link-local addresses to all devices besides loopback_dev - * first, then loopback_dev, which cases all the non-loopback_dev - * devices to fail to get a link-local address. - * - * So, as a temporary fix, allocate the ipv6 structure for - * loopback_dev first by hand. - * Longer term, all of the dependencies ipv6 has upon the loopback - * device and it being up should be removed. - */ rtnl_lock(); - idev = ipv6_add_dev(init_net.loopback_dev); + idev = ipv6_add_dev(blackhole_netdev); rtnl_unlock(); if (IS_ERR(idev)) { err = PTR_ERR(idev); @@ -7254,12 +7247,9 @@ int __init addrconf_init(void) ip6_route_init_special_entries(); - for (i = 0; i < IN6_ADDR_HSIZE; i++) - INIT_HLIST_HEAD(&inet6_addr_lst[i]); - register_netdevice_notifier(&ipv6_dev_notf); - addrconf_verify(); + addrconf_verify(&init_net); rtnl_af_register(&inet6_ops); @@ -7317,7 +7307,6 @@ out: void addrconf_cleanup(void) { struct net_device *dev; - int i; unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); @@ -7335,14 +7324,6 @@ void addrconf_cleanup(void) } addrconf_ifdown(init_net.loopback_dev, true); - /* - * Check hash table. - */ - spin_lock_bh(&addrconf_hash_lock); - for (i = 0; i < IN6_ADDR_HSIZE; i++) - WARN_ON(!hlist_empty(&inet6_addr_lst[i])); - spin_unlock_bh(&addrconf_hash_lock); - cancel_delayed_work(&addr_chk_work); rtnl_unlock(); destroy_workqueue(addrconf_wq); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 77e34aec7e82..658d5eabaf7e 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -1344,14 +1344,14 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return opt2; } -struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, - struct ipv6_txoptions *opt) +struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, + struct ipv6_txoptions *opt) { /* * ignore the dest before srcrt unless srcrt is being included. * --yoshfuji */ - if (opt && opt->dst0opt && !opt->srcrt) { + if (opt->dst0opt && !opt->srcrt) { if (opt_space != opt) { memcpy(opt_space, opt, sizeof(*opt_space)); opt = opt_space; @@ -1362,7 +1362,7 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, return opt; } -EXPORT_SYMBOL_GPL(ipv6_fixup_options); +EXPORT_SYMBOL_GPL(__ipv6_fixup_options); /** * fl6_update_dst - update flowi destination address with info given diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index ec029c86ae06..7c2003833010 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -16,6 +16,7 @@ #include <linux/indirect_call_wrapper.h> #include <net/fib_rules.h> +#include <net/inet_dscp.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/ip6_route.h> @@ -25,14 +26,14 @@ struct fib6_rule { struct fib_rule common; struct rt6key src; struct rt6key dst; - u8 tclass; + dscp_t dscp; }; static bool fib6_rule_matchall(const struct fib_rule *rule) { struct fib6_rule *r = container_of(rule, struct fib6_rule, common); - if (r->dst.plen || r->src.plen || r->tclass) + if (r->dst.plen || r->src.plen || r->dscp) return false; return fib_rule_matchall(rule); } @@ -323,7 +324,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, return 0; } - if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel)) + if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel)) return 0; if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) @@ -349,6 +350,13 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct net *net = sock_net(skb->sk); struct fib6_rule *rule6 = (struct fib6_rule *) rule; + if (!inet_validate_dscp(frh->tos)) { + NL_SET_ERR_MSG(extack, + "Invalid dsfield (tos): ECN bits must be 0"); + goto errout; + } + rule6->dscp = inet_dsfield_to_dscp(frh->tos); + if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { if (rule->table == RT6_TABLE_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid table"); @@ -369,7 +377,6 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule6->src.plen = frh->src_len; rule6->dst.plen = frh->dst_len; - rule6->tclass = frh->tos; if (fib_rule_requires_fldissect(rule)) net->ipv6.fib6_rules_require_fldissect++; @@ -402,7 +409,7 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) return 0; - if (frh->tos && (rule6->tclass != frh->tos)) + if (frh->tos && inet_dscp_to_dsfield(rule6->dscp) != frh->tos) return 0; if (frh->src_len && @@ -423,7 +430,7 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->dst_len = rule6->dst.plen; frh->src_len = rule6->src.plen; - frh->tos = rule6->tclass; + frh->tos = inet_dscp_to_dsfield(rule6->dscp); if ((rule6->dst.plen && nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) || @@ -486,16 +493,21 @@ out_fib6_rules_ops: goto out; } -static void __net_exit fib6_rules_net_exit(struct net *net) +static void __net_exit fib6_rules_net_exit_batch(struct list_head *net_list) { + struct net *net; + rtnl_lock(); - fib_rules_unregister(net->ipv6.fib6_rules_ops); + list_for_each_entry(net, net_list, exit_list) { + fib_rules_unregister(net->ipv6.fib6_rules_ops); + cond_resched(); + } rtnl_unlock(); } static struct pernet_operations fib6_rules_net_ops = { .init = fib6_rules_net_init, - .exit = fib6_rules_net_exit, + .exit_batch = fib6_rules_net_exit_batch, }; int __init fib6_rules_init(void) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 96c5cc0f30ce..e6b978ea0e87 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -69,17 +69,7 @@ #include <linux/uaccess.h> -/* - * The ICMP socket(s). This is the most convenient way to flow control - * our ICMP output as well as maintain a clean interface throughout - * all layers. All Socketless IP sends will soon be gone. - * - * On SMP we have one ICMP socket per-cpu. - */ -static struct sock *icmpv6_sk(struct net *net) -{ - return this_cpu_read(*net->ipv6.icmp_sk); -} +static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk); static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) @@ -110,11 +100,11 @@ static const struct inet6_protocol icmpv6_protocol = { }; /* Called with BH disabled */ -static __inline__ struct sock *icmpv6_xmit_lock(struct net *net) +static struct sock *icmpv6_xmit_lock(struct net *net) { struct sock *sk; - sk = icmpv6_sk(net); + sk = this_cpu_read(ipv6_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path (f.e. SIT or * ip6ip6 tunnel) signals dst_link_failure() for an @@ -122,11 +112,13 @@ static __inline__ struct sock *icmpv6_xmit_lock(struct net *net) */ return NULL; } + sock_net_set(sk, net); return sk; } -static __inline__ void icmpv6_xmit_unlock(struct sock *sk) +static void icmpv6_xmit_unlock(struct sock *sk) { + sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } @@ -1034,59 +1026,27 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } -static void __net_exit icmpv6_sk_exit(struct net *net) -{ - int i; - - for_each_possible_cpu(i) - inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv6.icmp_sk, i)); - free_percpu(net->ipv6.icmp_sk); -} - -static int __net_init icmpv6_sk_init(struct net *net) +int __init icmpv6_init(void) { struct sock *sk; int err, i; - net->ipv6.icmp_sk = alloc_percpu(struct sock *); - if (!net->ipv6.icmp_sk) - return -ENOMEM; - for_each_possible_cpu(i) { err = inet_ctl_sock_create(&sk, PF_INET6, - SOCK_RAW, IPPROTO_ICMPV6, net); + SOCK_RAW, IPPROTO_ICMPV6, &init_net); if (err < 0) { pr_err("Failed to initialize the ICMP6 control socket (err %d)\n", err); - goto fail; + return err; } - *per_cpu_ptr(net->ipv6.icmp_sk, i) = sk; + per_cpu(ipv6_icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); } - return 0; - - fail: - icmpv6_sk_exit(net); - return err; -} - -static struct pernet_operations icmpv6_sk_ops = { - .init = icmpv6_sk_init, - .exit = icmpv6_sk_exit, -}; - -int __init icmpv6_init(void) -{ - int err; - - err = register_pernet_subsys(&icmpv6_sk_ops); - if (err < 0) - return err; err = -EAGAIN; if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) @@ -1101,14 +1061,12 @@ sender_reg_err: inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); fail: pr_err("Failed to register ICMP6 protocol\n"); - unregister_pernet_subsys(&icmpv6_sk_ops); return err; } void icmpv6_cleanup(void) { inet6_unregister_icmp_sender(icmp6_send); - unregister_pernet_subsys(&icmpv6_sk_ops); inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 4514444e96c8..4740afecf7c6 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -333,11 +333,8 @@ int inet6_hash(struct sock *sk) { int err = 0; - if (sk->sk_state != TCP_CLOSE) { - local_bh_disable(); + if (sk->sk_state != TCP_CLOSE) err = __inet_hash(sk, NULL); - local_bh_enable(); - } return err; } diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index f90a87389fcc..f6f5b83dd954 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -32,13 +32,25 @@ struct ioam6_lwt_encap { struct ioam6_trace_hdr traceh; } __packed; +struct ioam6_lwt_freq { + u32 k; + u32 n; +}; + struct ioam6_lwt { struct dst_cache cache; + struct ioam6_lwt_freq freq; + atomic_t pkt_cnt; u8 mode; struct in6_addr tundst; struct ioam6_lwt_encap tuninfo; }; +static struct netlink_range_validation freq_range = { + .min = IOAM6_IPTUNNEL_FREQ_MIN, + .max = IOAM6_IPTUNNEL_FREQ_MAX, +}; + static struct ioam6_lwt *ioam6_lwt_state(struct lwtunnel_state *lwt) { return (struct ioam6_lwt *)lwt->data; @@ -55,6 +67,8 @@ static struct ioam6_trace_hdr *ioam6_lwt_trace(struct lwtunnel_state *lwt) } static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { + [IOAM6_IPTUNNEL_FREQ_K] = NLA_POLICY_FULL_RANGE(NLA_U32, &freq_range), + [IOAM6_IPTUNNEL_FREQ_N] = NLA_POLICY_FULL_RANGE(NLA_U32, &freq_range), [IOAM6_IPTUNNEL_MODE] = NLA_POLICY_RANGE(NLA_U8, IOAM6_IPTUNNEL_MODE_MIN, IOAM6_IPTUNNEL_MODE_MAX), @@ -96,6 +110,7 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, struct lwtunnel_state *lwt; struct ioam6_lwt *ilwt; int len_aligned, err; + u32 freq_k, freq_n; u8 mode; if (family != AF_INET6) @@ -106,6 +121,23 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, if (err < 0) return err; + if ((!tb[IOAM6_IPTUNNEL_FREQ_K] && tb[IOAM6_IPTUNNEL_FREQ_N]) || + (tb[IOAM6_IPTUNNEL_FREQ_K] && !tb[IOAM6_IPTUNNEL_FREQ_N])) { + NL_SET_ERR_MSG(extack, "freq: missing parameter"); + return -EINVAL; + } else if (!tb[IOAM6_IPTUNNEL_FREQ_K] && !tb[IOAM6_IPTUNNEL_FREQ_N]) { + freq_k = IOAM6_IPTUNNEL_FREQ_MIN; + freq_n = IOAM6_IPTUNNEL_FREQ_MIN; + } else { + freq_k = nla_get_u32(tb[IOAM6_IPTUNNEL_FREQ_K]); + freq_n = nla_get_u32(tb[IOAM6_IPTUNNEL_FREQ_N]); + + if (freq_k > freq_n) { + NL_SET_ERR_MSG(extack, "freq: k > n is forbidden"); + return -EINVAL; + } + } + if (!tb[IOAM6_IPTUNNEL_MODE]) mode = IOAM6_IPTUNNEL_MODE_INLINE; else @@ -140,6 +172,10 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, return err; } + atomic_set(&ilwt->pkt_cnt, 0); + ilwt->freq.k = freq_k; + ilwt->freq.n = freq_n; + ilwt->mode = mode; if (tb[IOAM6_IPTUNNEL_DST]) ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]); @@ -263,11 +299,18 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct in6_addr orig_daddr; struct ioam6_lwt *ilwt; int err = -EINVAL; + u32 pkt_cnt; if (skb->protocol != htons(ETH_P_IPV6)) goto drop; ilwt = ioam6_lwt_state(dst->lwtstate); + + /* Check for insertion frequency (i.e., "k over n" insertions) */ + pkt_cnt = atomic_fetch_inc(&ilwt->pkt_cnt); + if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k) + goto out; + orig_daddr = ipv6_hdr(skb)->daddr; switch (ilwt->mode) { @@ -358,6 +401,14 @@ static int ioam6_fill_encap_info(struct sk_buff *skb, struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); int err; + err = nla_put_u32(skb, IOAM6_IPTUNNEL_FREQ_K, ilwt->freq.k); + if (err) + goto ret; + + err = nla_put_u32(skb, IOAM6_IPTUNNEL_FREQ_N, ilwt->freq.n); + if (err) + goto ret; + err = nla_put_u8(skb, IOAM6_IPTUNNEL_MODE, ilwt->mode); if (err) goto ret; @@ -379,7 +430,9 @@ static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); int nlsize; - nlsize = nla_total_size(sizeof(ilwt->mode)) + + nlsize = nla_total_size(sizeof(ilwt->freq.k)) + + nla_total_size(sizeof(ilwt->freq.n)) + + nla_total_size(sizeof(ilwt->mode)) + nla_total_size(sizeof(ilwt->tuninfo.traceh)); if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) @@ -395,7 +448,9 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) struct ioam6_lwt *ilwt_a = ioam6_lwt_state(a); struct ioam6_lwt *ilwt_b = ioam6_lwt_state(b); - return (ilwt_a->mode != ilwt_b->mode || + return (ilwt_a->freq.k != ilwt_b->freq.k || + ilwt_a->freq.n != ilwt_b->freq.n || + ilwt_a->mode != ilwt_b->mode || (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) || trace_a->namespace_id != trace_b->namespace_id); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 80256717868e..d4b1e2c5aa76 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -508,7 +508,7 @@ int ip6_mc_input(struct sk_buff *skb) /* * IPv6 multicast router mode is now supported ;) */ - if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && + if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) && !(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index b29e9ba5e113..d37a79a8554e 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -249,7 +249,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, if ((first_word & htonl(0xF00FFFFF)) || !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || - *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) { + iph->nexthdr != iph2->nexthdr) { not_same_flow: NAPI_GRO_CB(p)->same_flow = 0; continue; @@ -260,7 +260,8 @@ not_same_flow: goto not_same_flow; } /* flush if Traffic Class fields are different */ - NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); + NAPI_GRO_CB(p)->flush |= !!((first_word & htonl(0x0FF00000)) | + (__force __be32)(iph->hop_limit ^ iph2->hop_limit)); NAPI_GRO_CB(p)->flush |= flush; /* If the previous IP ID value was based on an atomic diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2995f8d89e7e..3286b64ec03d 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1350,11 +1350,16 @@ static void ip6_append_data_mtu(unsigned int *mtu, static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, - struct rt6_info *rt, struct flowi6 *fl6) + struct rt6_info *rt) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu; - struct ipv6_txoptions *opt = ipc6->opt; + struct ipv6_txoptions *nopt, *opt = ipc6->opt; + + /* callers pass dst together with a reference, set it first so + * ip6_cork_release() can put it down even in case of an error. + */ + cork->base.dst = &rt->dst; /* * setup for corking @@ -1363,39 +1368,32 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (WARN_ON(v6_cork->opt)) return -EINVAL; - v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); - if (unlikely(!v6_cork->opt)) + nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); + if (unlikely(!nopt)) return -ENOBUFS; - v6_cork->opt->tot_len = sizeof(*opt); - v6_cork->opt->opt_flen = opt->opt_flen; - v6_cork->opt->opt_nflen = opt->opt_nflen; + nopt->tot_len = sizeof(*opt); + nopt->opt_flen = opt->opt_flen; + nopt->opt_nflen = opt->opt_nflen; - v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt, - sk->sk_allocation); - if (opt->dst0opt && !v6_cork->opt->dst0opt) + nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); + if (opt->dst0opt && !nopt->dst0opt) return -ENOBUFS; - v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt, - sk->sk_allocation); - if (opt->dst1opt && !v6_cork->opt->dst1opt) + nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); + if (opt->dst1opt && !nopt->dst1opt) return -ENOBUFS; - v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt, - sk->sk_allocation); - if (opt->hopopt && !v6_cork->opt->hopopt) + nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); + if (opt->hopopt && !nopt->hopopt) return -ENOBUFS; - v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt, - sk->sk_allocation); - if (opt->srcrt && !v6_cork->opt->srcrt) + nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); + if (opt->srcrt && !nopt->srcrt) return -ENOBUFS; /* need source address above miyazawa*/ } - dst_hold(&rt->dst); - cork->base.dst = &rt->dst; - cork->fl.u.ip6 = *fl6; v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) @@ -1426,9 +1424,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, } static int __ip6_append_data(struct sock *sk, - struct flowi6 *fl6, struct sk_buff_head *queue, - struct inet_cork *cork, + struct inet_cork_full *cork_full, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, @@ -1437,6 +1434,8 @@ static int __ip6_append_data(struct sock *sk, unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; + struct inet_cork *cork = &cork_full->base; + struct flowi6 *fl6 = &cork_full->fl.u.ip6; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; struct ubuf_info *uarg = NULL; int exthdrlen = 0; @@ -1488,6 +1487,7 @@ static int __ip6_append_data(struct sock *sk, if (cork->length + length > mtu - headersize && ipc6->dontfrag && (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_ICMPV6 || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); @@ -1788,34 +1788,46 @@ int ip6_append_data(struct sock *sk, /* * setup for corking */ + dst_hold(&rt->dst); err = ip6_setup_cork(sk, &inet->cork, &np->cork, - ipc6, rt, fl6); + ipc6, rt); if (err) return err; + inet->cork.fl.u.ip6 = *fl6; exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { - fl6 = &inet->cork.fl.u.ip6; transhdrlen = 0; } - return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base, + return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags, ipc6); } EXPORT_SYMBOL_GPL(ip6_append_data); +static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) +{ + struct dst_entry *dst = cork->base.dst; + + cork->base.dst = NULL; + cork->base.flags &= ~IPCORK_ALLFRAG; + skb_dst_set(skb, dst); +} + static void ip6_cork_release(struct inet_cork_full *cork, struct inet6_cork *v6_cork) { if (v6_cork->opt) { - kfree(v6_cork->opt->dst0opt); - kfree(v6_cork->opt->dst1opt); - kfree(v6_cork->opt->hopopt); - kfree(v6_cork->opt->srcrt); - kfree(v6_cork->opt); + struct ipv6_txoptions *opt = v6_cork->opt; + + kfree(opt->dst0opt); + kfree(opt->dst1opt); + kfree(opt->hopopt); + kfree(opt->srcrt); + kfree(opt); v6_cork->opt = NULL; } @@ -1824,7 +1836,6 @@ static void ip6_cork_release(struct inet_cork_full *cork, cork->base.dst = NULL; cork->base.flags &= ~IPCORK_ALLFRAG; } - memset(&cork->fl, 0, sizeof(cork->fl)); } struct sk_buff *__ip6_make_skb(struct sock *sk, @@ -1834,7 +1845,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; - struct in6_addr final_dst_buf, *final_dst = &final_dst_buf; + struct in6_addr *final_dst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *hdr; @@ -1864,9 +1875,9 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, /* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); - - *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); + + final_dst = &fl6->daddr; if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) @@ -1886,10 +1897,9 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = sk->sk_priority; skb->mark = cork->base.mark; - skb->tstamp = cork->base.transmit_time; - skb_dst_set(skb, dst_clone(&rt->dst)); + ip6_cork_steal_dst(skb, cork); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@ -1961,26 +1971,26 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm6_cookie *ipc6, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, - struct inet_cork_full *cork) + struct ipcm6_cookie *ipc6, struct rt6_info *rt, + unsigned int flags, struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); int err; - if (flags & MSG_PROBE) + if (flags & MSG_PROBE) { + dst_release(&rt->dst); return NULL; + } __skb_queue_head_init(&queue); cork->base.flags = 0; cork->base.addr = 0; cork->base.opt = NULL; - cork->base.dst = NULL; v6_cork.opt = NULL; - err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6); + err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); @@ -1988,7 +1998,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_sk(sk)->dontfrag; - err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork, + err = __ip6_append_data(sk, &queue, cork, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 97ade833f58c..53f632a560ec 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1121,6 +1121,14 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); + } else if (skb->protocol == htons(ETH_P_IP)) { + const struct rtable *rt = skb_rtable(skb); + + if (!rt) + goto tx_err_link_failure; + + if (rt->rt_gw_family == AF_INET6) + memcpy(&fl6->daddr, &rt->rt_gw6, sizeof(fl6->daddr)); } } else if (t->parms.proto != 0 && !(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8a2db926b5eb..0ebaaec3faf9 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -255,13 +255,12 @@ static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr_table *mrt, *next; - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } fib_rules_unregister(net->ipv6.mr6_rules_ops); - rtnl_unlock(); } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, @@ -318,10 +317,9 @@ static int __net_init ip6mr_rules_init(struct net *net) static void __net_exit ip6mr_rules_exit(struct net *net) { - rtnl_lock(); + ASSERT_RTNL(); ip6mr_free_table(net->ipv6.mrt6); net->ipv6.mrt6 = NULL; - rtnl_unlock(); } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, @@ -734,7 +732,7 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, in6_dev = __in6_dev_get(dev); if (in6_dev) { - in6_dev->cnf.mc_forwarding--; + atomic_dec(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); @@ -902,7 +900,7 @@ static int mif6_add(struct net *net, struct mr_table *mrt, in6_dev = __in6_dev_get(dev); if (in6_dev) { - in6_dev->cnf.mc_forwarding++; + atomic_inc(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); @@ -1325,7 +1323,9 @@ static int __net_init ip6mr_net_init(struct net *net) proc_cache_fail: remove_proc_entry("ip6_mr_vif", net->proc_net); proc_vif_fail: + rtnl_lock(); ip6mr_rules_exit(net); + rtnl_unlock(); #endif ip6mr_rules_fail: ip6mr_notifier_exit(net); @@ -1338,13 +1338,23 @@ static void __net_exit ip6mr_net_exit(struct net *net) remove_proc_entry("ip6_mr_cache", net->proc_net); remove_proc_entry("ip6_mr_vif", net->proc_net); #endif - ip6mr_rules_exit(net); ip6mr_notifier_exit(net); } +static void __net_exit ip6mr_net_exit_batch(struct list_head *net_list) +{ + struct net *net; + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) + ip6mr_rules_exit(net); + rtnl_unlock(); +} + static struct pernet_operations ip6mr_net_ops = { .init = ip6mr_net_init, .exit = ip6mr_net_exit, + .exit_batch = ip6mr_net_exit_batch, }; int __init ip6_mr_init(void) @@ -1553,7 +1563,7 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) } else { rcu_assign_pointer(mrt->mroute_sk, sk); sock_set_flag(sk, SOCK_RCU_FREE); - net->ipv6.devconf_all->mc_forwarding++; + atomic_inc(&net->ipv6.devconf_all->mc_forwarding); } write_unlock_bh(&mrt_lock); @@ -1569,14 +1579,19 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) int ip6mr_sk_done(struct sock *sk) { - int err = -EACCES; struct net *net = sock_net(sk); + struct ipv6_devconf *devconf; struct mr_table *mrt; + int err = -EACCES; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return err; + devconf = net->ipv6.devconf_all; + if (!devconf || !atomic_read(&devconf->mc_forwarding)) + return err; + rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { @@ -1586,7 +1601,7 @@ int ip6mr_sk_done(struct sock *sk) * so the RCU grace period before sk freeing * is guaranteed by sk_destruct() */ - net->ipv6.devconf_all->mc_forwarding--; + atomic_dec(&devconf->mc_forwarding); write_unlock_bh(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f03b597e4121..1c06d0cd02f7 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1337,8 +1337,12 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } neigh->flags |= NTF_ROUTER; - } else if (rt) { + } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) { + struct nl_info nlinfo = { + .nl_net = net, + }; rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } if (rt) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 9256f6ba87ef..ff033d16549e 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -59,8 +59,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct pingfakehdr pfh; struct ipcm6_cookie ipc6; - pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); - err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph, sizeof(user_icmph)); if (err) @@ -99,7 +97,25 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) return -EINVAL; - /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ + ipcm6_init_sk(&ipc6, np); + ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.mark = sk->sk_mark; + + if (msg->msg_controllen) { + struct ipv6_txoptions opt = {}; + + opt.tot_len = sizeof(opt); + ipc6.opt = &opt; + + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); + if (err < 0) + return err; + + /* Changes to txoptions and flow info are not implemented, yet. + * Drop the options, fl6 is wiped below. + */ + ipc6.opt = NULL; + } memset(&fl6, 0, sizeof(fl6)); @@ -107,14 +123,12 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.saddr = np->saddr; fl6.daddr = *daddr; fl6.flowi6_oif = oif; - fl6.flowi6_mark = sk->sk_mark; + fl6.flowi6_mark = ipc6.sockc.mark; fl6.flowi6_uid = sk->sk_uid; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); - ipcm6_init_sk(&ipc6, np); - ipc6.sockc.mark = sk->sk_mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); @@ -136,7 +150,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) pfh.wcheck = 0; pfh.family = AF_INET6; - ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + if (ipc6.hlimit < 0) + ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); lock_sock(sk); err = ip6_append_data(sk, ping_getfrag, &pfh, len, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ea1cf414a92e..6188712f24b0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -130,6 +130,7 @@ static struct fib6_info *rt6_get_route_info(struct net *net, struct uncached_list { spinlock_t lock; struct list_head head; + struct list_head quarantine; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); @@ -149,35 +150,34 @@ void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; - struct net *net = dev_net(rt->dst.dev); spin_lock_bh(&ul->lock); - list_del(&rt->rt6i_uncached); - atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache); + list_del_init(&rt->rt6i_uncached); spin_unlock_bh(&ul->lock); } } -static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) +static void rt6_uncached_list_flush_dev(struct net_device *dev) { - struct net_device *loopback_dev = net->loopback_dev; int cpu; - if (dev == loopback_dev) - return; - for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); - struct rt6_info *rt; + struct rt6_info *rt, *safe; + + if (list_empty(&ul->head)) + continue; spin_lock_bh(&ul->lock); - list_for_each_entry(rt, &ul->head, rt6i_uncached) { + list_for_each_entry_safe(rt, safe, &ul->head, rt6i_uncached) { struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; + bool handled = false; if (rt_idev->dev == dev) { - rt->rt6i_idev = in6_dev_get(loopback_dev); + rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); + handled = true; } if (rt_dev == dev) { @@ -185,7 +185,11 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) dev_replace_track(rt_dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); + handled = true; } + if (handled) + list_move(&rt->rt6i_uncached, + &ul->quarantine); } spin_unlock_bh(&ul->lock); } @@ -373,13 +377,12 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - struct net_device *loopback_dev = - dev_net(dev)->loopback_dev; - if (idev && idev->dev != loopback_dev) { - struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev); - if (loopback_idev) { - rt->rt6i_idev = loopback_idev; + if (idev && idev->dev != blackhole_netdev) { + struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev); + + if (blackhole_idev) { + rt->rt6i_idev = blackhole_idev; in6_dev_put(idev); } } @@ -2244,7 +2247,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, * if caller sets RT6_LOOKUP_F_DST_NOREF flag. */ rt6_uncached_list_add(rt); - atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); rcu_read_unlock(); return rt; @@ -3287,7 +3289,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, * do proper release of the net_device */ rt6_uncached_list_add(rt); - atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); @@ -4896,7 +4897,7 @@ void rt6_sync_down_dev(struct net_device *dev, unsigned long event) void rt6_disable_ip(struct net_device *dev, unsigned long event) { rt6_sync_down_dev(dev, event); - rt6_uncached_list_flush_dev(dev_net(dev), dev); + rt6_uncached_list_flush_dev(dev); neigh_ifdown(&nd_tbl, dev); } @@ -5009,6 +5010,12 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, err = -EINVAL; rtm = nlmsg_data(nlh); + if (rtm->rtm_tos) { + NL_SET_ERR_MSG(extack, + "Invalid dsfield (tos): option not available for IPv6"); + goto errout; + } + *cfg = (struct fib6_config){ .fc_table = rtm->rtm_table, .fc_dst_len = rtm->rtm_dst_len, @@ -6731,6 +6738,7 @@ int __init ip6_route_init(void) struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); + INIT_LIST_HEAD(&ul->quarantine); spin_lock_init(&ul->lock); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 075ee8a2df3b..0c648bf07f39 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -148,6 +148,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_timewait_death_row *tcp_death_row; struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; @@ -156,7 +157,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct dst_entry *dst; int addr_type; int err; - struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; @@ -308,6 +308,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); + tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; err = inet6_hash_connect(tcp_death_row, sk); if (err) goto late_failure; @@ -2237,15 +2238,9 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } -static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&tcp_hashinfo, AF_INET6); -} - static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, - .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 528b81ef19c9..7f0fa9bd9ffe 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -912,6 +912,7 @@ static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; const struct in6_addr *saddr, *daddr; struct net *net = dev_net(skb->dev); struct udphdr *uh; @@ -988,6 +989,8 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, return udp6_unicast_rcv_skb(sk, skb, uh); } + reason = SKB_DROP_REASON_NO_SOCKET; + if (!uh->check) goto report_csum_error; @@ -1000,10 +1003,12 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, __UDP6_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); - kfree_skb(skb); + kfree_skb_reason(skb, reason); return 0; short_packet: + if (reason == SKB_DROP_REASON_NOT_SPECIFIED) + reason = SKB_DROP_REASON_PKT_TOO_SMALL; net_dbg_ratelimited("UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n", proto == IPPROTO_UDPLITE ? "-Lite" : "", saddr, ntohs(uh->source), @@ -1014,10 +1019,12 @@ short_packet: report_csum_error: udp6_csum_zero_error(skb); csum_error: + if (reason == SKB_DROP_REASON_NOT_SPECIFIED) + reason = SKB_DROP_REASON_UDP_CSUM; __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: __UDP6_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb(skb); + kfree_skb_reason(skb, reason); return 0; } @@ -1266,23 +1273,17 @@ static int udp_v6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; struct udp_sock *up = udp_sk(sk); - struct flowi6 fl6; int err = 0; if (up->pending == AF_INET) return udp_push_pending_frames(sk); - /* ip6_finish_skb will release the cork, so make a copy of - * fl6 here. - */ - fl6 = inet_sk(sk)->cork.fl.u.ip6; - skb = ip6_finish_skb(sk); if (!skb) goto out; - err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base); - + err = udp_v6_send_skb(skb, &inet_sk(sk)->cork.fl.u.ip6, + &inet_sk(sk)->cork.base); out: up->len = 0; up->pending = 0; @@ -1300,7 +1301,8 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipv6_txoptions *opt = NULL; struct ipv6_txoptions *opt_to_free = NULL; struct ip6_flowlabel *flowlabel = NULL; - struct flowi6 fl6; + struct inet_cork_full cork; + struct flowi6 *fl6 = &cork.fl.u.ip6; struct dst_entry *dst; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; @@ -1363,9 +1365,6 @@ do_udp_sendmsg: } } - if (up->pending == AF_INET) - return udp_sendmsg(sk, msg, len); - /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ @@ -1374,6 +1373,8 @@ do_udp_sendmsg: getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; if (up->pending) { + if (up->pending == AF_INET) + return udp_sendmsg(sk, msg, len); /* * There are pending frames. * The socket lock must be held while it's corked. @@ -1391,19 +1392,19 @@ do_udp_sendmsg: } ulen += sizeof(struct udphdr); - memset(&fl6, 0, sizeof(fl6)); + memset(fl6, 0, sizeof(*fl6)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; - fl6.fl6_dport = sin6->sin6_port; + fl6->fl6_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; if (np->sndflow) { - fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); + fl6->flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } @@ -1420,24 +1421,24 @@ do_udp_sendmsg: if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) - fl6.flowi6_oif = sin6->sin6_scope_id; + fl6->flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl6.fl6_dport = inet->inet_dport; + fl6->fl6_dport = inet->inet_dport; daddr = &sk->sk_v6_daddr; - fl6.flowlabel = np->flow_label; + fl6->flowlabel = np->flow_label; connected = true; } - if (!fl6.flowi6_oif) - fl6.flowi6_oif = sk->sk_bound_dev_if; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = sk->sk_bound_dev_if; - if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; - fl6.flowi6_uid = sk->sk_uid; + fl6->flowi6_uid = sk->sk_uid; if (msg->msg_controllen) { opt = &opt_space; @@ -1447,14 +1448,14 @@ do_udp_sendmsg: err = udp_cmsg_send(sk, msg, &ipc6.gso_size); if (err > 0) - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } - if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); + if ((fl6->flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } @@ -1471,16 +1472,17 @@ do_udp_sendmsg: opt = ipv6_fixup_options(&opt_space, opt); ipc6.opt = opt; - fl6.flowi6_proto = sk->sk_protocol; - fl6.flowi6_mark = ipc6.sockc.mark; - fl6.daddr = *daddr; - if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - fl6.saddr = np->saddr; - fl6.fl6_sport = inet->inet_sport; + fl6->flowi6_proto = sk->sk_protocol; + fl6->flowi6_mark = ipc6.sockc.mark; + fl6->daddr = *daddr; + if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr)) + fl6->saddr = np->saddr; + fl6->fl6_sport = inet->inet_sport; if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, - (struct sockaddr *)sin6, &fl6.saddr); + (struct sockaddr *)sin6, + &fl6->saddr); if (err) goto out_no_dst; if (sin6) { @@ -1496,32 +1498,32 @@ do_udp_sendmsg: err = -EINVAL; goto out_no_dst; } - fl6.fl6_dport = sin6->sin6_port; - fl6.daddr = sin6->sin6_addr; + fl6->fl6_dport = sin6->sin6_port; + fl6->daddr = sin6->sin6_addr; } } - if (ipv6_addr_any(&fl6.daddr)) - fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + if (ipv6_addr_any(&fl6->daddr)) + fl6->daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ - final_p = fl6_update_dst(&fl6, opt, &final); + final_p = fl6_update_dst(fl6, opt, &final); if (final_p) connected = false; - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { - fl6.flowi6_oif = np->mcast_oif; + if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) { + fl6->flowi6_oif = np->mcast_oif; connected = false; - } else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + } else if (!fl6->flowi6_oif) + fl6->flowi6_oif = np->ucast_oif; - security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); + security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); if (ipc6.tclass < 0) ipc6.tclass = np->tclass; - fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); + fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, connected); + dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -1529,7 +1531,7 @@ do_udp_sendmsg: } if (ipc6.hlimit < 0) - ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst); if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; @@ -1537,17 +1539,17 @@ back_from_confirm: /* Lockless fast path for the non-corking case */ if (!corkreq) { - struct inet_cork_full cork; struct sk_buff *skb; skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, - &fl6, (struct rt6_info *)dst, + (struct rt6_info *)dst, msg->msg_flags, &cork); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) - err = udp_v6_send_skb(skb, &fl6, &cork.base); - goto out; + err = udp_v6_send_skb(skb, fl6, &cork.base); + /* ip6_make_skb steals dst reference */ + goto out_no_dst; } lock_sock(sk); @@ -1568,7 +1570,7 @@ do_append_data: ipc6.dontfrag = np->dontfrag; up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), - &ipc6, &fl6, (struct rt6_info *)dst, + &ipc6, fl6, (struct rt6_info *)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); @@ -1603,7 +1605,7 @@ out_no_dst: do_confirm: if (msg->msg_flags & MSG_PROBE) - dst_confirm_neigh(dst, &fl6.daddr); + dst_confirm_neigh(dst, &fl6->daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index fad687ee6dd8..55bb2cbae13d 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -92,7 +92,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_src = rt->rt6i_src; INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); rt6_uncached_list_add(&xdst->u.rt6); - atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 26d2f8ba7029..64e8ce9760b9 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: ISC /* * Copyright (C) 2019 Felix Fietkau <nbd@nbd.name> + * Copyright (C) 2021 Intel Corporation */ #include <net/mac80211.h> @@ -67,17 +68,11 @@ #define IEEE80211_VHT_STREAM_GROUPS 8 /* BW(=4) * SGI(=2) */ #define IEEE80211_HE_MAX_STREAMS 8 -#define IEEE80211_HE_STREAM_GROUPS 12 /* BW(=4) * GI(=3) */ #define IEEE80211_HT_GROUPS_NB (IEEE80211_MAX_STREAMS * \ IEEE80211_HT_STREAM_GROUPS) #define IEEE80211_VHT_GROUPS_NB (IEEE80211_MAX_STREAMS * \ IEEE80211_VHT_STREAM_GROUPS) -#define IEEE80211_HE_GROUPS_NB (IEEE80211_HE_MAX_STREAMS * \ - IEEE80211_HE_STREAM_GROUPS) -#define IEEE80211_GROUPS_NB (IEEE80211_HT_GROUPS_NB + \ - IEEE80211_VHT_GROUPS_NB + \ - IEEE80211_HE_GROUPS_NB) #define IEEE80211_HT_GROUP_0 0 #define IEEE80211_VHT_GROUP_0 (IEEE80211_HT_GROUP_0 + IEEE80211_HT_GROUPS_NB) @@ -650,12 +645,12 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_rx_status stat; - struct ieee80211_tx_rate *rate = &sta->tx_stats.last_rate; + struct ieee80211_tx_rate *tx_rate = &sta->tx_stats.last_rate; struct rate_info *ri = &sta->tx_stats.last_rate_info; u32 duration, overhead; u8 agg_shift; - if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + if (ieee80211_fill_rx_status(&stat, hw, tx_rate, ri, band, len)) return 0; if (stat.encoding == RX_ENC_LEGACY || !ampdu) diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 8dbfe325ee66..f4c9a92f50f9 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -634,8 +634,10 @@ static const struct file_operations stats_ ##name## _ops = { \ .llseek = generic_file_llseek, \ }; +#ifdef CONFIG_MAC80211_DEBUG_COUNTERS #define DEBUGFS_STATS_ADD(name) \ debugfs_create_u32(#name, 0400, statsd, &local->name); +#endif #define DEBUGFS_DEVSTATS_ADD(name) \ debugfs_create_file(#name, 0400, statsd, local, &stats_ ##name## _ops); diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index f53dec8a3d5c..edc7792e1361 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -4,6 +4,7 @@ * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2015 Intel Deutschland GmbH + * Copyright (C) 2021 Intel Corporation */ #include <linux/kobject.h> @@ -22,7 +23,6 @@ static ssize_t key_##name##_read(struct file *file, \ return mac80211_format_buffer(userbuf, count, ppos, \ format_string, key->prop); \ } -#define KEY_READ_D(name) KEY_READ(name, name, "%d\n") #define KEY_READ_X(name) KEY_READ(name, name, "0x%x\n") #define KEY_OPS(name) \ diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index db724fc10a5f..e490c3da3aca 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2020 Intel Corporation + * Copyright (C) 2020-2021 Intel Corporation */ #include <linux/kernel.h> @@ -77,8 +77,6 @@ static ssize_t ieee80211_if_fmt_##name( \ IEEE80211_IF_FMT(name, field, "%#x\n") #define IEEE80211_IF_FMT_LHEX(name, field) \ IEEE80211_IF_FMT(name, field, "%#lx\n") -#define IEEE80211_IF_FMT_SIZE(name, field) \ - IEEE80211_IF_FMT(name, field, "%zd\n") #define IEEE80211_IF_FMT_HEXARRAY(name, field) \ static ssize_t ieee80211_if_fmt_##name( \ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 330ea62231fa..da35791b8378 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2380,7 +2380,7 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_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, +u8 *ieee80211_ie_build_he_cap(u32 disable_flags, u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end); void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 15ac08d111ea..6847fdf93439 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -580,7 +580,7 @@ int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, return -ENOMEM; pos = skb_put(skb, ie_len); - ieee80211_ie_build_he_cap(pos, he_cap, pos + ie_len); + ieee80211_ie_build_he_cap(0, pos, he_cap, pos + ie_len); return 0; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e5ccf17618ab..20b57ddf149c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -635,7 +635,7 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct ieee80211_supported_band *sband) { - u8 *pos; + u8 *pos, *pre_he_pos; const struct ieee80211_sta_he_cap *he_cap = NULL; struct ieee80211_chanctx_conf *chanctx_conf; u8 he_cap_size; @@ -652,16 +652,21 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, he_cap = ieee80211_get_he_iftype_cap(sband, ieee80211_vif_type_p2p(&sdata->vif)); - if (!he_cap || !reg_cap) + if (!he_cap || !chanctx_conf || !reg_cap) return; + /* get a max size estimate */ he_cap_size = 2 + 1 + sizeof(he_cap->he_cap_elem) + ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) + ieee80211_he_ppe_size(he_cap->ppe_thres[0], he_cap->he_cap_elem.phy_cap_info); pos = skb_put(skb, he_cap_size); - ieee80211_ie_build_he_cap(pos, he_cap, pos + he_cap_size); + pre_he_pos = pos; + pos = ieee80211_ie_build_he_cap(sdata->u.mgd.flags, + pos, he_cap, pos + he_cap_size); + /* trim excess if any */ + skb_trim(skb, skb->len - (pre_he_pos + he_cap_size - pos)); ieee80211_ie_build_he_6ghz_cap(sdata, skb); } @@ -4915,13 +4920,20 @@ void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) rcu_read_unlock(); } -static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, - struct cfg80211_bss *cbss) +static u8 ieee80211_max_rx_chains(struct ieee80211_sub_if_data *sdata, + struct cfg80211_bss *cbss) { + struct ieee80211_he_mcs_nss_supp *he_mcs_nss_supp; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; const struct element *ht_cap_elem, *vht_cap_elem; + const struct cfg80211_bss_ies *ies; const struct ieee80211_ht_cap *ht_cap; const struct ieee80211_vht_cap *vht_cap; + const struct ieee80211_he_cap_elem *he_cap; + const struct element *he_cap_elem; + u16 mcs_80_map, mcs_160_map; + int i, mcs_nss_size; + bool support_160; u8 chains = 1; if (ifmgd->flags & IEEE80211_STA_DISABLE_HT) @@ -4956,10 +4968,156 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, chains = max(chains, nss); } + if (ifmgd->flags & IEEE80211_STA_DISABLE_HE) + return chains; + + ies = rcu_dereference(cbss->ies); + he_cap_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, + ies->data, ies->len); + + if (!he_cap_elem || he_cap_elem->datalen < sizeof(*he_cap)) + return chains; + + /* skip one byte ext_tag_id */ + he_cap = (void *)(he_cap_elem->data + 1); + mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap); + + /* invalid HE IE */ + if (he_cap_elem->datalen < 1 + mcs_nss_size + sizeof(*he_cap)) + return chains; + + /* mcs_nss is right after he_cap info */ + he_mcs_nss_supp = (void *)(he_cap + 1); + + mcs_80_map = le16_to_cpu(he_mcs_nss_supp->tx_mcs_80); + + for (i = 7; i >= 0; i--) { + u8 mcs_80 = mcs_80_map >> (2 * i) & 3; + + if (mcs_80 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + chains = max_t(u8, chains, i + 1); + break; + } + } + + support_160 = he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + + if (!support_160) + return chains; + + mcs_160_map = le16_to_cpu(he_mcs_nss_supp->tx_mcs_160); + for (i = 7; i >= 0; i--) { + u8 mcs_160 = mcs_160_map >> (2 * i) & 3; + + if (mcs_160 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + chains = max_t(u8, chains, i + 1); + break; + } + } + return chains; } static bool +ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata, + const struct cfg80211_bss_ies *ies, + const struct ieee80211_he_operation *he_op) +{ + const struct element *he_cap_elem; + const struct ieee80211_he_cap_elem *he_cap; + struct ieee80211_he_mcs_nss_supp *he_mcs_nss_supp; + u16 mcs_80_map_tx, mcs_80_map_rx; + u16 ap_min_req_set; + int mcs_nss_size; + int nss; + + he_cap_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, + ies->data, ies->len); + + /* invalid HE IE */ + if (!he_cap_elem || he_cap_elem->datalen < 1 + sizeof(*he_cap)) { + sdata_info(sdata, + "Invalid HE elem, Disable HE\n"); + return false; + } + + /* skip one byte ext_tag_id */ + he_cap = (void *)(he_cap_elem->data + 1); + mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap); + + /* invalid HE IE */ + if (he_cap_elem->datalen < 1 + sizeof(*he_cap) + mcs_nss_size) { + sdata_info(sdata, + "Invalid HE elem with nss size, Disable HE\n"); + return false; + } + + /* mcs_nss is right after he_cap info */ + he_mcs_nss_supp = (void *)(he_cap + 1); + + mcs_80_map_tx = le16_to_cpu(he_mcs_nss_supp->tx_mcs_80); + mcs_80_map_rx = le16_to_cpu(he_mcs_nss_supp->rx_mcs_80); + + /* P802.11-REVme/D0.3 + * 27.1.1 Introduction to the HE PHY + * ... + * An HE STA shall support the following features: + * ... + * Single spatial stream HE-MCSs 0 to 7 (transmit and receive) in all + * supported channel widths for HE SU PPDUs + */ + if ((mcs_80_map_tx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED || + (mcs_80_map_rx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED) { + sdata_info(sdata, + "Missing mandatory rates for 1 Nss, rx 0x%x, tx 0x%x, disable HE\n", + mcs_80_map_tx, mcs_80_map_rx); + return false; + } + + if (!he_op) + return true; + + ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); + + /* make sure the AP is consistent with itself + * + * P802.11-REVme/D0.3 + * 26.17.1 Basic HE BSS operation + * + * A STA that is operating in an HE BSS shall be able to receive and + * transmit at each of the <HE-MCS, NSS> tuple values indicated by the + * Basic HE-MCS And NSS Set field of the HE Operation parameter of the + * MLME-START.request primitive and shall be able to receive at each of + * the <HE-MCS, NSS> tuple values indicated by the Supported HE-MCS and + * NSS Set field in the HE Capabilities parameter of the MLMESTART.request + * primitive + */ + for (nss = 8; nss > 0; nss--) { + u8 ap_op_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; + u8 ap_rx_val; + u8 ap_tx_val; + + if (ap_op_val == IEEE80211_HE_MCS_NOT_SUPPORTED) + continue; + + ap_rx_val = (mcs_80_map_rx >> (2 * (nss - 1))) & 3; + ap_tx_val = (mcs_80_map_tx >> (2 * (nss - 1))) & 3; + + if (ap_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + ap_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + ap_rx_val < ap_op_val || ap_tx_val < ap_op_val) { + sdata_info(sdata, + "Invalid rates for %d Nss, rx %d, tx %d oper %d, disable HE\n", + nss, ap_rx_val, ap_rx_val, ap_op_val); + return false; + } + } + + return true; +} + +static bool ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_he_operation *he_op) @@ -5005,7 +5163,15 @@ ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata, /* * Make sure the HE AP doesn't require MCSs that aren't - * supported by the client + * supported by the client as required by spec + * + * P802.11-REVme/D0.3 + * 26.17.1 Basic HE BSS operation + * + * An HE STA shall not attempt to join * (MLME-JOIN.request primitive) + * a BSS, unless it supports (i.e., is able to both transmit and + * receive using) all of the <HE-MCS, NSS> tuples in the basic + * HE-MCS and NSS set. */ if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || @@ -5136,7 +5302,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } - if (!ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) + if (!ieee80211_verify_peer_he_mcs_support(sdata, ies, he_oper) || + !ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } @@ -5170,7 +5337,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, s1g_oper, &chandef, false); - sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), + sdata->needed_rx_chains = min(ieee80211_max_rx_chains(sdata, cbss), local->rx_chains); rcu_read_unlock(); diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 9c3b7fc377c1..9c6ace858107 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010-2013 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2019-2020 Intel Corporation + * Copyright (C) 2019-2021 Intel Corporation */ #include <linux/netdevice.h> #include <linux/types.h> diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 93680af62c47..d54a4d98c648 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4629,6 +4629,8 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, /* do the header conversion - first grab the addresses */ ether_addr_copy(addrs.da, skb->data + fast_rx->da_offs); ether_addr_copy(addrs.sa, skb->data + fast_rx->sa_offs); + skb_postpull_rcsum(skb, skb->data + snap_offs, + sizeof(rfc1042_header) + 2); /* remove the SNAP but leave the ethertype */ skb_pull(skb, snap_offs + sizeof(rfc1042_header)); /* push the addresses in front */ diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 537535a88990..91fbb1ee5c38 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -364,8 +364,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, goto free; sta->mesh->plink_sta = sta; spin_lock_init(&sta->mesh->plink_lock); - if (ieee80211_vif_is_mesh(&sdata->vif) && - !sdata->u.mesh.user_mpm) + if (!sdata->u.mesh.user_mpm) timer_setup(&sta->mesh->plink_timer, mesh_plink_timer, 0); sta->mesh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index f6f63a0b1b72..e81e8a5bb774 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -5,6 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2008-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2021-2022 Intel Corporation */ #include <linux/export.h> @@ -628,6 +629,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr = (void *)skb->data; + bool is_valid_ack_signal = + !!(info->status.flags & IEEE80211_TX_STATUS_ACK_SIGNAL_VALID); rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); @@ -644,7 +647,7 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, info->status.ack_signal, - info->status.is_valid_ack_signal, + is_valid_ack_signal, GFP_ATOMIC); else if (ieee80211_is_mgmt(hdr->frame_control)) cfg80211_mgmt_tx_status(&sdata->wdev, cookie, @@ -754,7 +757,6 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, */ #define STA_LOST_PKT_THRESHOLD 50 #define STA_LOST_PKT_TIME HZ /* 1 sec since last ACK */ -#define STA_LOST_TDLS_PKT_THRESHOLD 10 #define STA_LOST_TDLS_PKT_TIME (10*HZ) /* 10secs since last ACK */ static void ieee80211_lost_packet(struct sta_info *sta, @@ -781,7 +783,7 @@ static void ieee80211_lost_packet(struct sta_info *sta, } /* - * If we're in TDLS mode, make sure that all STA_LOST_TDLS_PKT_THRESHOLD + * If we're in TDLS mode, make sure that all STA_LOST_PKT_THRESHOLD * of the last packets were lost, and that no ACK was received in the * last STA_LOST_TDLS_PKT_TIME ms, before triggering the CQM packet-loss * mechanism. @@ -1102,7 +1104,7 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_supported_band *sband; struct sta_info *sta = NULL; int rates_idx, retry_count; - bool acked, noack_success; + bool acked, noack_success, ack_signal_valid; u16 tx_time_est; if (pubsta) { @@ -1133,6 +1135,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, acked = !!(info->flags & IEEE80211_TX_STAT_ACK); noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); + ack_signal_valid = + !!(info->status.flags & IEEE80211_TX_STATUS_ACK_SIGNAL_VALID); if (pubsta) { struct ieee80211_sub_if_data *sdata = sta->sdata; @@ -1161,7 +1165,7 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, unlikely(sdata->u.mgd.probe_send_count > 0)) sdata->u.mgd.probe_send_count = 0; - if (info->status.is_valid_ack_signal) { + if (ack_signal_valid) { sta->status_stats.last_ack_signal = (s8)info->status.ack_signal; sta->status_stats.ack_signal_filled = true; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index f71b042a5c8b..abc29df6834c 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1974,7 +1974,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, if (he_cap && cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), IEEE80211_CHAN_NO_HE)) { - pos = ieee80211_ie_build_he_cap(pos, he_cap, end); + pos = ieee80211_ie_build_he_cap(0, pos, he_cap, end); if (!pos) goto out_err; } @@ -2918,10 +2918,11 @@ u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) he_cap->he_cap_elem.phy_cap_info); } -u8 *ieee80211_ie_build_he_cap(u8 *pos, +u8 *ieee80211_ie_build_he_cap(u32 disable_flags, u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end) { + struct ieee80211_he_cap_elem elem; u8 n; u8 ie_len; u8 *orig_pos = pos; @@ -2934,7 +2935,23 @@ u8 *ieee80211_ie_build_he_cap(u8 *pos, if (!he_cap) return orig_pos; - n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem); + /* modify on stack first to calculate 'n' and 'ie_len' correctly */ + elem = he_cap->he_cap_elem; + + if (disable_flags & IEEE80211_STA_DISABLE_40MHZ) + elem.phy_cap_info[0] &= + ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G); + + if (disable_flags & IEEE80211_STA_DISABLE_160MHZ) + elem.phy_cap_info[0] &= + ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + + if (disable_flags & IEEE80211_STA_DISABLE_80P80MHZ) + elem.phy_cap_info[0] &= + ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; + + n = ieee80211_he_mcs_nss_size(&elem); ie_len = 2 + 1 + sizeof(he_cap->he_cap_elem) + n + ieee80211_he_ppe_size(he_cap->ppe_thres[0], @@ -2948,8 +2965,8 @@ u8 *ieee80211_ie_build_he_cap(u8 *pos, *pos++ = WLAN_EID_EXT_HE_CAPABILITY; /* Fixed data */ - memcpy(pos, &he_cap->he_cap_elem, sizeof(he_cap->he_cap_elem)); - pos += sizeof(he_cap->he_cap_elem); + memcpy(pos, &elem, sizeof(elem)); + pos += sizeof(elem); memcpy(pos, &he_cap->he_mcs_nss_supp, n); pos += n; @@ -3262,7 +3279,6 @@ bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, channel_type = NL80211_CHAN_HT40MINUS; break; default: - channel_type = NL80211_CHAN_NO_HT; return false; } diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index e856f9092137..a45dacde96f7 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -501,7 +501,7 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) for (i = 7; i >= 0; i--) { u8 mcs_160 = (mcs_160_map >> (2 * i)) & 3; - if (mcs_160 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + if (mcs_160 != IEEE80211_HE_MCS_NOT_SUPPORTED) { rx_mcs_160 = i + 1; break; } @@ -509,7 +509,7 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) for (i = 7; i >= 0; i--) { u8 mcs_80 = (mcs_80_map >> (2 * i)) & 3; - if (mcs_80 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + if (mcs_80 != IEEE80211_HE_MCS_NOT_SUPPORTED) { rx_mcs_80 = i + 1; break; } diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index c921de63b494..f0702d920d8d 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -6,6 +6,7 @@ * Copyright (c) 2021 Google */ +#include <linux/compat.h> #include <linux/if_arp.h> #include <linux/net.h> #include <linux/mctp.h> @@ -21,6 +22,8 @@ /* socket implementation */ +static void mctp_sk_expire_keys(struct timer_list *timer); + static int mctp_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -99,13 +102,20 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sk_buff *skb; if (addr) { + const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER | + MCTP_TAG_PREALLOC; + if (addrlen < sizeof(struct sockaddr_mctp)) return -EINVAL; if (addr->smctp_family != AF_MCTP) return -EINVAL; if (!mctp_sockaddr_is_ok(addr)) return -EINVAL; - if (addr->smctp_tag & ~(MCTP_TAG_MASK | MCTP_TAG_OWNER)) + if (addr->smctp_tag & ~tagbits) + return -EINVAL; + /* can't preallocate a non-owned tag */ + if (addr->smctp_tag & MCTP_TAG_PREALLOC && + !(addr->smctp_tag & MCTP_TAG_OWNER)) return -EINVAL; } else { @@ -248,6 +258,32 @@ out_free: return rc; } +/* We're done with the key; invalidate, stop reassembly, and remove from lists. + */ +static void __mctp_key_remove(struct mctp_sk_key *key, struct net *net, + unsigned long flags, unsigned long reason) +__releases(&key->lock) +__must_hold(&net->mctp.keys_lock) +{ + struct sk_buff *skb; + + trace_mctp_key_release(key, reason); + skb = key->reasm_head; + key->reasm_head = NULL; + key->reasm_dead = true; + key->valid = false; + mctp_dev_release_key(key->dev, key); + spin_unlock_irqrestore(&key->lock, flags); + + hlist_del(&key->hlist); + hlist_del(&key->sklist); + + /* unref for the lists */ + mctp_key_unref(key); + + kfree_skb(skb); +} + static int mctp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -293,6 +329,115 @@ static int mctp_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; } +static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg) +{ + struct net *net = sock_net(&msk->sk); + struct mctp_sk_key *key = NULL; + struct mctp_ioc_tag_ctl ctl; + unsigned long flags; + u8 tag; + + if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) + return -EFAULT; + + if (ctl.tag) + return -EINVAL; + + if (ctl.flags) + return -EINVAL; + + key = mctp_alloc_local_tag(msk, ctl.peer_addr, MCTP_ADDR_ANY, + true, &tag); + if (IS_ERR(key)) + return PTR_ERR(key); + + ctl.tag = tag | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC; + if (copy_to_user((void __user *)arg, &ctl, sizeof(ctl))) { + spin_lock_irqsave(&key->lock, flags); + __mctp_key_remove(key, net, flags, MCTP_TRACE_KEY_DROPPED); + mctp_key_unref(key); + return -EFAULT; + } + + mctp_key_unref(key); + return 0; +} + +static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) +{ + struct net *net = sock_net(&msk->sk); + struct mctp_ioc_tag_ctl ctl; + unsigned long flags, fl2; + struct mctp_sk_key *key; + struct hlist_node *tmp; + int rc; + u8 tag; + + if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) + return -EFAULT; + + if (ctl.flags) + return -EINVAL; + + /* Must be a local tag, TO set, preallocated */ + if ((ctl.tag & ~MCTP_TAG_MASK) != (MCTP_TAG_OWNER | MCTP_TAG_PREALLOC)) + return -EINVAL; + + tag = ctl.tag & MCTP_TAG_MASK; + rc = -EINVAL; + + spin_lock_irqsave(&net->mctp.keys_lock, flags); + hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { + /* we do an irqsave here, even though we know the irq state, + * so we have the flags to pass to __mctp_key_remove + */ + spin_lock_irqsave(&key->lock, fl2); + if (key->manual_alloc && + ctl.peer_addr == key->peer_addr && + tag == key->tag) { + __mctp_key_remove(key, net, fl2, + MCTP_TRACE_KEY_DROPPED); + rc = 0; + } else { + spin_unlock_irqrestore(&key->lock, fl2); + } + } + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + + return rc; +} + +static int mctp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + + switch (cmd) { + case SIOCMCTPALLOCTAG: + return mctp_ioctl_alloctag(msk, arg); + case SIOCMCTPDROPTAG: + return mctp_ioctl_droptag(msk, arg); + } + + return -EINVAL; +} + +#ifdef CONFIG_COMPAT +static int mctp_compat_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + void __user *argp = compat_ptr(arg); + + switch (cmd) { + /* These have compatible ptr layouts */ + case SIOCMCTPALLOCTAG: + case SIOCMCTPDROPTAG: + return mctp_ioctl(sock, cmd, (unsigned long)argp); + } + + return -ENOIOCTLCMD; +} +#endif + static const struct proto_ops mctp_dgram_ops = { .family = PF_MCTP, .release = mctp_release, @@ -302,7 +447,7 @@ static const struct proto_ops mctp_dgram_ops = { .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, - .ioctl = sock_no_ioctl, + .ioctl = mctp_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, @@ -312,6 +457,9 @@ static const struct proto_ops mctp_dgram_ops = { .recvmsg = mctp_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_ioctl = mctp_compat_ioctl, +#endif }; static void mctp_sk_expire_keys(struct timer_list *timer) @@ -319,7 +467,7 @@ static void mctp_sk_expire_keys(struct timer_list *timer) struct mctp_sock *msk = container_of(timer, struct mctp_sock, key_expiry); struct net *net = sock_net(&msk->sk); - unsigned long next_expiry, flags; + unsigned long next_expiry, flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; bool next_expiry_valid = false; @@ -327,15 +475,16 @@ static void mctp_sk_expire_keys(struct timer_list *timer) spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { - spin_lock(&key->lock); + /* don't expire. manual_alloc is immutable, no locking + * required. + */ + if (key->manual_alloc) + continue; + spin_lock_irqsave(&key->lock, fl2); if (!time_after_eq(key->expiry, jiffies)) { - trace_mctp_key_release(key, MCTP_TRACE_KEY_TIMEOUT); - key->valid = false; - hlist_del_rcu(&key->hlist); - hlist_del_rcu(&key->sklist); - spin_unlock(&key->lock); - mctp_key_unref(key); + __mctp_key_remove(key, net, fl2, + MCTP_TRACE_KEY_TIMEOUT); continue; } @@ -346,7 +495,7 @@ static void mctp_sk_expire_keys(struct timer_list *timer) next_expiry = key->expiry; next_expiry_valid = true; } - spin_unlock(&key->lock); + spin_unlock_irqrestore(&key->lock, fl2); } spin_unlock_irqrestore(&net->mctp.keys_lock, flags); @@ -387,9 +536,9 @@ static void mctp_sk_unhash(struct sock *sk) { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct net *net = sock_net(sk); + unsigned long flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; - unsigned long flags; /* remove from any type-based binds */ mutex_lock(&net->mctp.bind_lock); @@ -399,20 +548,8 @@ static void mctp_sk_unhash(struct sock *sk) /* remove tag allocations */ spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { - hlist_del(&key->sklist); - hlist_del(&key->hlist); - - trace_mctp_key_release(key, MCTP_TRACE_KEY_CLOSED); - - spin_lock(&key->lock); - kfree_skb(key->reasm_head); - key->reasm_head = NULL; - key->reasm_dead = true; - key->valid = false; - spin_unlock(&key->lock); - - /* key is no longer on the lookup lists, unref */ - mctp_key_unref(key); + spin_lock_irqsave(&key->lock, fl2); + __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED); } spin_unlock_irqrestore(&net->mctp.keys_lock, flags); } diff --git a/net/mctp/device.c b/net/mctp/device.c index ef2755f82f87..02ddc0f1bd3e 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -6,6 +6,7 @@ * Copyright (c) 2021 Google */ +#include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/mctp.h> #include <linux/netdevice.h> diff --git a/net/mctp/route.c b/net/mctp/route.c index e52cef750500..0c4c56e1bd6e 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -64,8 +64,7 @@ static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb) if (msk->bind_type != type) continue; - if (msk->bind_addr != MCTP_ADDR_ANY && - msk->bind_addr != mh->dest) + if (!mctp_address_matches(msk->bind_addr, mh->dest)) continue; return msk; @@ -77,7 +76,7 @@ static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb) static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local, mctp_eid_t peer, u8 tag) { - if (key->local_addr != local) + if (!mctp_address_matches(key->local_addr, local)) return false; if (key->peer_addr != peer) @@ -204,29 +203,38 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) return rc; } -/* We're done with the key; unset valid and remove from lists. There may still - * be outstanding refs on the key though... +/* Helper for mctp_route_input(). + * We're done with the key; unlock and unref the key. + * For the usual case of automatic expiry we remove the key from lists. + * In the case that manual allocation is set on a key we release the lock + * and local ref, reset reassembly, but don't remove from lists. */ -static void __mctp_key_unlock_drop(struct mctp_sk_key *key, struct net *net, - unsigned long flags) - __releases(&key->lock) +static void __mctp_key_done_in(struct mctp_sk_key *key, struct net *net, + unsigned long flags, unsigned long reason) +__releases(&key->lock) { struct sk_buff *skb; + trace_mctp_key_release(key, reason); skb = key->reasm_head; key->reasm_head = NULL; - key->reasm_dead = true; - key->valid = false; - mctp_dev_release_key(key->dev, key); + + if (!key->manual_alloc) { + key->reasm_dead = true; + key->valid = false; + mctp_dev_release_key(key->dev, key); + } spin_unlock_irqrestore(&key->lock, flags); - spin_lock_irqsave(&net->mctp.keys_lock, flags); - hlist_del(&key->hlist); - hlist_del(&key->sklist); - spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + if (!key->manual_alloc) { + spin_lock_irqsave(&net->mctp.keys_lock, flags); + hlist_del(&key->hlist); + hlist_del(&key->sklist); + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); - /* one unref for the lists */ - mctp_key_unref(key); + /* unref for the lists */ + mctp_key_unref(key); + } /* and one for the local reference */ mctp_key_unref(key); @@ -380,9 +388,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) /* we've hit a pending reassembly; not much we * can do but drop it */ - trace_mctp_key_release(key, - MCTP_TRACE_KEY_REPLIED); - __mctp_key_unlock_drop(key, net, f); + __mctp_key_done_in(key, net, f, + MCTP_TRACE_KEY_REPLIED); key = NULL; } rc = 0; @@ -425,9 +432,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) } else { if (key->reasm_head || key->reasm_dead) { /* duplicate start? drop everything */ - trace_mctp_key_release(key, - MCTP_TRACE_KEY_INVALIDATED); - __mctp_key_unlock_drop(key, net, f); + __mctp_key_done_in(key, net, f, + MCTP_TRACE_KEY_INVALIDATED); rc = -EEXIST; key = NULL; } else { @@ -450,10 +456,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * the reassembly/response key */ if (!rc && flags & MCTP_HDR_FLAG_EOM) { + msk = container_of(key->sk, struct mctp_sock, sk); sock_queue_rcv_skb(key->sk, key->reasm_head); key->reasm_head = NULL; - trace_mctp_key_release(key, MCTP_TRACE_KEY_REPLIED); - __mctp_key_unlock_drop(key, net, f); + __mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED); key = NULL; } @@ -581,9 +587,9 @@ static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key, /* Allocate a locally-owned tag value for (saddr, daddr), and reserve * it for the socket msk */ -static struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, - mctp_eid_t saddr, - mctp_eid_t daddr, u8 *tagp) +struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, + mctp_eid_t daddr, mctp_eid_t saddr, + bool manual, u8 *tagp) { struct net *net = sock_net(&msk->sk); struct netns_mctp *mns = &net->mctp; @@ -617,9 +623,8 @@ static struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, if (tmp->tag & MCTP_HDR_FLAG_TO) continue; - if (!((tmp->peer_addr == daddr || - tmp->peer_addr == MCTP_ADDR_ANY) && - tmp->local_addr == saddr)) + if (!(mctp_address_matches(tmp->peer_addr, daddr) && + mctp_address_matches(tmp->local_addr, saddr))) continue; spin_lock(&tmp->lock); @@ -639,6 +644,7 @@ static struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, mctp_reserve_tag(net, key, msk); trace_mctp_key_acquire(key); + key->manual_alloc = manual; *tagp = key->tag; } @@ -652,6 +658,50 @@ static struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, return key; } +static struct mctp_sk_key *mctp_lookup_prealloc_tag(struct mctp_sock *msk, + mctp_eid_t daddr, + u8 req_tag, u8 *tagp) +{ + struct net *net = sock_net(&msk->sk); + struct netns_mctp *mns = &net->mctp; + struct mctp_sk_key *key, *tmp; + unsigned long flags; + + req_tag &= ~(MCTP_TAG_PREALLOC | MCTP_TAG_OWNER); + key = NULL; + + spin_lock_irqsave(&mns->keys_lock, flags); + + hlist_for_each_entry(tmp, &mns->keys, hlist) { + if (tmp->tag != req_tag) + continue; + + if (!mctp_address_matches(tmp->peer_addr, daddr)) + continue; + + if (!tmp->manual_alloc) + continue; + + spin_lock(&tmp->lock); + if (tmp->valid) { + key = tmp; + refcount_inc(&key->refs); + spin_unlock(&tmp->lock); + break; + } + spin_unlock(&tmp->lock); + } + spin_unlock_irqrestore(&mns->keys_lock, flags); + + if (!key) + return ERR_PTR(-ENOENT); + + if (tagp) + *tagp = key->tag; + + return key; +} + /* routing lookups */ static bool mctp_rt_match_eid(struct mctp_route *rt, unsigned int net, mctp_eid_t eid) @@ -846,8 +896,14 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, if (rc) goto out_release; - if (req_tag & MCTP_HDR_FLAG_TO) { - key = mctp_alloc_local_tag(msk, saddr, daddr, &tag); + if (req_tag & MCTP_TAG_OWNER) { + if (req_tag & MCTP_TAG_PREALLOC) + key = mctp_lookup_prealloc_tag(msk, daddr, + req_tag, &tag); + else + key = mctp_alloc_local_tag(msk, daddr, saddr, + false, &tag); + if (IS_ERR(key)) { rc = PTR_ERR(key); goto out_release; @@ -858,7 +914,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, tag |= MCTP_HDR_FLAG_TO; } else { key = NULL; - tag = req_tag; + tag = req_tag & MCTP_TAG_MASK; } skb->protocol = htons(ETH_P_MCTP); diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 750f9f9b4daf..61205cf40074 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -369,14 +369,15 @@ static void mctp_test_route_input_sk(struct kunit *test) #define FL_S (MCTP_HDR_FLAG_SOM) #define FL_E (MCTP_HDR_FLAG_EOM) -#define FL_T (MCTP_HDR_FLAG_TO) +#define FL_TO (MCTP_HDR_FLAG_TO) +#define FL_T(t) ((t) & MCTP_HDR_TAG_MASK) static const struct mctp_route_input_sk_test mctp_route_input_sk_tests[] = { - { .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_T), .type = 0, .deliver = true }, - { .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_T), .type = 1, .deliver = false }, + { .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 0, .deliver = true }, + { .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 1, .deliver = false }, { .hdr = RX_HDR(1, 10, 8, FL_S | FL_E), .type = 0, .deliver = false }, - { .hdr = RX_HDR(1, 10, 8, FL_E | FL_T), .type = 0, .deliver = false }, - { .hdr = RX_HDR(1, 10, 8, FL_T), .type = 0, .deliver = false }, + { .hdr = RX_HDR(1, 10, 8, FL_E | FL_TO), .type = 0, .deliver = false }, + { .hdr = RX_HDR(1, 10, 8, FL_TO), .type = 0, .deliver = false }, { .hdr = RX_HDR(1, 10, 8, 0), .type = 0, .deliver = false }, }; @@ -436,7 +437,7 @@ static void mctp_test_route_input_sk_reasm(struct kunit *test) __mctp_route_test_fini(test, dev, rt, sock); } -#define RX_FRAG(f, s) RX_HDR(1, 10, 8, FL_T | (f) | ((s) << MCTP_HDR_SEQ_SHIFT)) +#define RX_FRAG(f, s) RX_HDR(1, 10, 8, FL_TO | (f) | ((s) << MCTP_HDR_SEQ_SHIFT)) static const struct mctp_route_input_sk_reasm_test mctp_route_input_sk_reasm_tests[] = { { @@ -522,12 +523,156 @@ static void mctp_route_input_sk_reasm_to_desc( KUNIT_ARRAY_PARAM(mctp_route_input_sk_reasm, mctp_route_input_sk_reasm_tests, mctp_route_input_sk_reasm_to_desc); +struct mctp_route_input_sk_keys_test { + const char *name; + mctp_eid_t key_peer_addr; + mctp_eid_t key_local_addr; + u8 key_tag; + struct mctp_hdr hdr; + bool deliver; +}; + +/* test packet rx in the presence of various key configurations */ +static void mctp_test_route_input_sk_keys(struct kunit *test) +{ + const struct mctp_route_input_sk_keys_test *params; + struct mctp_test_route *rt; + struct sk_buff *skb, *skb2; + struct mctp_test_dev *dev; + struct mctp_sk_key *key; + struct netns_mctp *mns; + struct mctp_sock *msk; + struct socket *sock; + unsigned long flags; + int rc; + u8 c; + + params = test->param_value; + + dev = mctp_test_create_dev(); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + + rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt); + + rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock); + KUNIT_ASSERT_EQ(test, rc, 0); + + msk = container_of(sock->sk, struct mctp_sock, sk); + mns = &sock_net(sock->sk)->mctp; + + /* set the incoming tag according to test params */ + key = mctp_key_alloc(msk, params->key_local_addr, params->key_peer_addr, + params->key_tag, GFP_KERNEL); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, key); + + spin_lock_irqsave(&mns->keys_lock, flags); + mctp_reserve_tag(&init_net, key, msk); + spin_unlock_irqrestore(&mns->keys_lock, flags); + + /* create packet and route */ + c = 0; + skb = mctp_test_create_skb_data(¶ms->hdr, &c); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); + + skb->dev = dev->ndev; + __mctp_cb(skb); + + rc = mctp_route_input(&rt->rt, skb); + + /* (potentially) receive message */ + skb2 = skb_recv_datagram(sock->sk, 0, 1, &rc); + + if (params->deliver) + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2); + else + KUNIT_EXPECT_PTR_EQ(test, skb2, NULL); + + if (skb2) + skb_free_datagram(sock->sk, skb2); + + mctp_key_unref(key); + __mctp_route_test_fini(test, dev, rt, sock); +} + +static const struct mctp_route_input_sk_keys_test mctp_route_input_sk_keys_tests[] = { + { + .name = "direct match", + .key_peer_addr = 9, + .key_local_addr = 8, + .key_tag = 1, + .hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)), + .deliver = true, + }, + { + .name = "flipped src/dest", + .key_peer_addr = 8, + .key_local_addr = 9, + .key_tag = 1, + .hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)), + .deliver = false, + }, + { + .name = "peer addr mismatch", + .key_peer_addr = 9, + .key_local_addr = 8, + .key_tag = 1, + .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_T(1)), + .deliver = false, + }, + { + .name = "tag value mismatch", + .key_peer_addr = 9, + .key_local_addr = 8, + .key_tag = 1, + .hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(2)), + .deliver = false, + }, + { + .name = "TO mismatch", + .key_peer_addr = 9, + .key_local_addr = 8, + .key_tag = 1, + .hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1) | FL_TO), + .deliver = false, + }, + { + .name = "broadcast response", + .key_peer_addr = MCTP_ADDR_ANY, + .key_local_addr = 8, + .key_tag = 1, + .hdr = RX_HDR(1, 11, 8, FL_S | FL_E | FL_T(1)), + .deliver = true, + }, + { + .name = "any local match", + .key_peer_addr = 12, + .key_local_addr = MCTP_ADDR_ANY, + .key_tag = 1, + .hdr = RX_HDR(1, 12, 8, FL_S | FL_E | FL_T(1)), + .deliver = true, + }, +}; + +static void mctp_route_input_sk_keys_to_desc( + const struct mctp_route_input_sk_keys_test *t, + char *desc) +{ + sprintf(desc, "%s", t->name); +} + +KUNIT_ARRAY_PARAM(mctp_route_input_sk_keys, mctp_route_input_sk_keys_tests, + mctp_route_input_sk_keys_to_desc); + static struct kunit_case mctp_test_cases[] = { KUNIT_CASE_PARAM(mctp_test_fragment, mctp_frag_gen_params), KUNIT_CASE_PARAM(mctp_test_rx_input, mctp_rx_input_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk, mctp_route_input_sk_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk_reasm, mctp_route_input_sk_reasm_gen_params), + KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys, + mctp_route_input_sk_keys_gen_params), {} }; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 645dd984fef0..ac10a04ccd7c 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -336,6 +336,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; + pr_debug("MP_RST: transient=%u reason=%u", + mp_opt->reset_transient, mp_opt->reset_reason); break; case MPTCPOPT_MP_FAIL: @@ -353,8 +355,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } -void mptcp_get_options(const struct sock *sk, - const struct sk_buff *skb, +void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { const struct tcphdr *th = tcp_hdr(skb); @@ -651,7 +652,6 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * bool drop_other_suboptions = false; unsigned int opt_size = *size; bool echo; - bool port; int len; /* add addr will strip the existing options, be sure to avoid breaking @@ -660,12 +660,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * if (!mptcp_pm_should_add_signal(msk) || (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) || !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr, - &echo, &port, &drop_other_suboptions)) + &echo, &drop_other_suboptions)) return false; if (drop_other_suboptions) remaining += opt_size; - len = mptcp_add_addr_len(opts->addr.family, echo, port); + len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false; @@ -1084,8 +1084,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, &mp_opt->addr); pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n", - msk, (unsigned long long)hmac, - (unsigned long long)mp_opt->ahmac); + msk, hmac, mp_opt->ahmac); return hmac == mp_opt->ahmac; } @@ -1112,7 +1111,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return true; } - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); /* The subflow can be in close state only if check_fully_established() * just sent a reset. If so, tell the caller to ignore the current packet. @@ -1264,22 +1263,30 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { - if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - - subflow = mptcp_subflow_ctx(ssk); - subflow->send_mp_fail = 0; - - *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, - TCPOLEN_MPTCP_FAIL, - 0, 0); - put_unaligned_be64(opts->fail_seq, ptr); - ptr += 2; - } - - /* DSS, MPC, MPJ, ADD_ADDR, FASTCLOSE and RST are mutually exclusive, - * see mptcp_established_options*() + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + /* Which options can be used together? + * + * X: mutually exclusive + * O: often used together + * C: can be used together in some cases + * P: could be used together but we prefer not to (optimisations) + * + * Opt: | MPC | MPJ | DSS | ADD | RM | PRIO | FAIL | FC | + * ------|------|------|------|------|------|------|------|------| + * MPC |------|------|------|------|------|------|------|------| + * MPJ | X |------|------|------|------|------|------|------| + * DSS | X | X |------|------|------|------|------|------| + * ADD | X | X | P |------|------|------|------|------| + * RM | C | C | C | P |------|------|------|------| + * PRIO | X | C | C | C | C |------|------|------| + * FAIL | X | X | C | X | X | X |------|------| + * FC | X | X | X | X | X | X | X |------| + * RST | X | X | X | X | X | X | O | O | + * ------|------|------|------|------|------|------|------|------| + * + * The same applies in mptcp_established_options() function. */ if (likely(OPTION_MPTCP_DSS & opts->suboptions)) { struct mptcp_ext *mpext = &opts->ext_copy; @@ -1336,6 +1343,10 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, } ptr += 1; } + + /* We might need to add MP_FAIL options in rare cases */ + if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) + goto mp_fail; } else if (OPTIONS_MPTCP_MPC & opts->suboptions) { u8 len, flag = MPTCP_CAP_HMAC_SHA256; @@ -1479,6 +1490,21 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, if (OPTION_MPTCP_RST & opts->suboptions) goto mp_rst; return; + } else if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { +mp_fail: + /* MP_FAIL is mutually exclusive with others except RST */ + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_fail = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, + TCPOLEN_MPTCP_FAIL, + 0, 0); + put_unaligned_be64(opts->fail_seq, ptr); + ptr += 2; + + if (OPTION_MPTCP_RST & opts->suboptions) + goto mp_rst; + return; } else if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) { mp_rst: *ptr++ = mptcp_option(MPTCPOPT_RST, @@ -1489,9 +1515,6 @@ mp_rst: } if (OPTION_MPTCP_PRIO & opts->suboptions) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - subflow = mptcp_subflow_ctx(ssk); subflow->send_mp_prio = 0; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 696b2c4613a7..8755b81896de 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -219,7 +219,7 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, } void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) + const struct mptcp_addr_info *addr) { struct mptcp_pm_data *pm = &msk->pm; @@ -275,14 +275,15 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) /* path manager helpers */ -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, unsigned int opt_size, unsigned int remaining, struct mptcp_addr_info *addr, bool *echo, - bool *port, bool *drop_other_suboptions) + bool *drop_other_suboptions) { int ret = false; u8 add_addr; u8 family; + bool port; spin_lock_bh(&msk->pm.lock); @@ -300,10 +301,10 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, } *echo = mptcp_pm_should_add_signal_echo(msk); - *port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); + port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); family = *echo ? msk->pm.remote.family : msk->pm.local.family; - if (remaining < mptcp_add_addr_len(family, *echo, *port)) + if (remaining < mptcp_add_addr_len(family, *echo, port)) goto out_unlock; if (*echo) { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 356f596e2032..9aeee30e50ba 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -120,7 +120,7 @@ static void remote_address(const struct sock_common *skc, } static bool lookup_subflow_by_saddr(const struct list_head *list, - struct mptcp_addr_info *saddr) + const struct mptcp_addr_info *saddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; @@ -138,7 +138,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list, } static bool lookup_subflow_by_daddr(const struct list_head *list, - struct mptcp_addr_info *daddr) + const struct mptcp_addr_info *daddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; @@ -157,10 +157,10 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, static struct mptcp_pm_addr_entry * select_local_address(const struct pm_nl_pernet *pernet, - struct mptcp_sock *msk) + const struct mptcp_sock *msk) { + const struct sock *sk = (const struct sock *)msk; struct mptcp_pm_addr_entry *entry, *ret = NULL; - struct sock *sk = (struct sock *)msk; msk_owned_by_me(msk); @@ -190,7 +190,7 @@ select_local_address(const struct pm_nl_pernet *pernet, } static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, struct mptcp_sock *msk) +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) { struct mptcp_pm_addr_entry *entry, *ret = NULL; @@ -214,16 +214,16 @@ select_signal_address(struct pm_nl_pernet *pernet, struct mptcp_sock *msk) return ret; } -unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) { - struct pm_nl_pernet *pernet; + const struct pm_nl_pernet *pernet; - pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + pernet = net_generic(sock_net((const struct sock *)msk), pm_nl_pernet_id); return READ_ONCE(pernet->add_addr_signal_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max); -unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet; @@ -232,7 +232,7 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk) } EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max); -unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet; @@ -241,7 +241,7 @@ unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk) } EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max); -unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk) +unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet; @@ -264,8 +264,8 @@ bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk) } struct mptcp_pm_add_entry * -mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) +mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; @@ -346,7 +346,7 @@ out: struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, bool check_id) + const struct mptcp_addr_info *addr, bool check_id) { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; @@ -364,7 +364,7 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, } static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) + const struct mptcp_pm_addr_entry *entry) { struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; @@ -410,8 +410,8 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } -static bool lookup_address_in_vec(struct mptcp_addr_info *addrs, unsigned int nr, - struct mptcp_addr_info *addr) +static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, + const struct mptcp_addr_info *addr) { int i; @@ -493,9 +493,9 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info, } static int -lookup_id_by_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *addr) +lookup_id_by_addr(const struct pm_nl_pernet *pernet, const struct mptcp_addr_info *addr) { - struct mptcp_pm_addr_entry *entry; + const struct mptcp_pm_addr_entry *entry; int ret = -1; rcu_read_lock(); @@ -1178,14 +1178,8 @@ skip_family: if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); - if (tb[MPTCP_PM_ADDR_ATTR_PORT]) { - if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - NL_SET_ERR_MSG_ATTR(info->extack, attr, - "flags must have signal when using port"); - return -EINVAL; - } + if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); - } return 0; } @@ -1231,6 +1225,11 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; + if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + GENL_SET_ERR_MSG(info, "flags must have signal when using port"); + return -EINVAL; + } + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { GENL_SET_ERR_MSG(info, "can't allocate addr"); @@ -1282,7 +1281,7 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id, } static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr) + const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; @@ -1297,7 +1296,7 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, } static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, + const struct mptcp_addr_info *addr, bool force) { struct mptcp_rm_list list = { .nr = 0 }; @@ -1732,9 +1731,20 @@ fail: return -EMSGSIZE; } -static int mptcp_nl_addr_backup(struct net *net, - struct mptcp_addr_info *addr, - u8 bkup) +static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, + struct mptcp_addr_info *addr) +{ + struct mptcp_rm_list list = { .nr = 0 }; + + list.ids[list.nr++] = addr->id; + + mptcp_pm_nl_rm_subflow_received(msk, &list); + mptcp_pm_create_subflow_or_signal_addr(msk); +} + +static int mptcp_nl_set_flags(struct net *net, + struct mptcp_addr_info *addr, + u8 bkup, u8 changed) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; @@ -1748,7 +1758,10 @@ static int mptcp_nl_addr_backup(struct net *net, lock_sock(sk); spin_lock_bh(&msk->pm.lock); - ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) + ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) + mptcp_pm_nl_fullmesh(msk, addr); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1765,6 +1778,8 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); + u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | + MPTCP_PM_ADDR_FLAG_FULLMESH; struct net *net = sock_net(skb->sk); u8 bkup = 0, lookup_by_id = 0; int ret; @@ -1787,15 +1802,18 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); return -EINVAL; } + if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && + (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + spin_unlock_bh(&pernet->lock); + return -EINVAL; + } - if (bkup) - entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else - entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; + changed = (addr.flags ^ entry->flags) & mask; + entry->flags = (entry->flags & ~mask) | (addr.flags & mask); addr = *entry; spin_unlock_bh(&pernet->lock); - mptcp_nl_addr_backup(net, &addr.addr, bkup); + mptcp_nl_set_flags(net, &addr.addr, bkup, changed); return 0; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 85317ce38e3f..9d0ee6cee07f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -468,9 +468,7 @@ struct mptcp_subflow_context { struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ const struct inet_connection_sock_af_ops *icsk_af_ops; - void (*tcp_data_ready)(struct sock *sk); void (*tcp_state_change)(struct sock *sk); - void (*tcp_write_space)(struct sock *sk); void (*tcp_error_report)(struct sock *sk); struct rcu_head rcu; @@ -614,9 +612,9 @@ bool mptcp_subflow_active(struct mptcp_subflow_context *subflow); static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) { - sk->sk_data_ready = ctx->tcp_data_ready; + sk->sk_data_ready = sock_def_readable; sk->sk_state_change = ctx->tcp_state_change; - sk->sk_write_space = ctx->tcp_write_space; + sk->sk_write_space = sk_stream_write_space; sk->sk_error_report = ctx->tcp_error_report; inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops; @@ -643,8 +641,7 @@ int __init mptcp_proto_v6_init(void); struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req); -void mptcp_get_options(const struct sock *sk, - const struct sk_buff *skb, +void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); @@ -743,7 +740,7 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, void mptcp_pm_add_addr_received(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, - struct mptcp_addr_info *addr); + const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, @@ -754,10 +751,10 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, bool check_id); + const struct mptcp_addr_info *addr, bool check_id); struct mptcp_pm_add_entry * -mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, - struct mptcp_addr_info *addr); +mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, + const struct mptcp_addr_info *addr); int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id, u8 *flags, int *ifindex); @@ -816,10 +813,10 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list) return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1; } -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, unsigned int opt_size, unsigned int remaining, struct mptcp_addr_info *addr, bool *echo, - bool *port, bool *drop_other_suboptions); + bool *drop_other_suboptions); bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); @@ -830,10 +827,10 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); -unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk); -unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); -unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); -unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); +unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); +unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); +unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk); void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index dacf3cee0027..f949d22f52bd 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -343,6 +343,8 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_RCVLOWAT: case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: + case SO_SNDTIMEO_OLD: + case SO_SNDTIMEO_NEW: case SO_BUSY_POLL: case SO_PREFER_BUSY_POLL: case SO_BUSY_POLL_BUDGET: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index bea47a1180dc..45c004f87f5a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -153,7 +153,7 @@ static int subflow_check_req(struct request_sock *req, return -EINVAL; #endif - mptcp_get_options(sk_listener, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); @@ -250,7 +250,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, int err; subflow_init_req(req, sk_listener); - mptcp_get_options(sk_listener, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); @@ -344,9 +344,7 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow) thmac = get_unaligned_be64(hmac); pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n", - subflow, subflow->token, - (unsigned long long)thmac, - (unsigned long long)subflow->thmac); + subflow, subflow->token, thmac, subflow->thmac); return thmac == subflow->thmac; } @@ -410,7 +408,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->ssn_offset = TCP_SKB_CB(skb)->seq; pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { MPTCP_INC_STATS(sock_net(sk), @@ -484,8 +482,7 @@ do_reset: } struct request_sock_ops mptcp_subflow_request_sock_ops; -EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops); -static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops; +static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -506,9 +503,9 @@ drop: } #if IS_ENABLED(CONFIG_MPTCP_IPV6) -static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops; -static struct inet_connection_sock_af_ops subflow_v6_specific; -static struct inet_connection_sock_af_ops subflow_v6m_specific; +static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; +static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; +static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; static struct proto tcpv6_prot_override; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) @@ -663,7 +660,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * reordered MPC will cause fallback, but we don't have other * options. */ - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { fallback = true; goto create_child; @@ -673,7 +670,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - mptcp_get_options(sk, skb, &mp_opt); + mptcp_get_options(skb, &mp_opt); if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { @@ -790,7 +787,7 @@ dispose_child: return child; } -static struct inet_connection_sock_af_ops subflow_specific; +static struct inet_connection_sock_af_ops subflow_specific __ro_after_init; static struct proto tcp_prot_override; enum mapping_status { @@ -1311,7 +1308,7 @@ static void subflow_write_space(struct sock *ssk) mptcp_write_space(sk); } -static struct inet_connection_sock_af_ops * +static const struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1326,7 +1323,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_connection_sock_af_ops *target; + const struct inet_connection_sock_af_ops *target; target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); @@ -1657,10 +1654,12 @@ static int subflow_ulp_init(struct sock *sk) tp->is_mptcp = 1; ctx->icsk_af_ops = icsk->icsk_af_ops; icsk->icsk_af_ops = subflow_default_af_ops(sk); - ctx->tcp_data_ready = sk->sk_data_ready; ctx->tcp_state_change = sk->sk_state_change; - ctx->tcp_write_space = sk->sk_write_space; ctx->tcp_error_report = sk->sk_error_report; + + WARN_ON_ONCE(sk->sk_data_ready != sock_def_readable); + WARN_ON_ONCE(sk->sk_write_space != sk_stream_write_space); + sk->sk_data_ready = subflow_data_ready; sk->sk_write_space = subflow_write_space; sk->sk_state_change = subflow_state_change; @@ -1715,9 +1714,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->conn_finished = 1; new_ctx->icsk_af_ops = old_ctx->icsk_af_ops; - new_ctx->tcp_data_ready = old_ctx->tcp_data_ready; new_ctx->tcp_state_change = old_ctx->tcp_state_change; - new_ctx->tcp_write_space = old_ctx->tcp_write_space; new_ctx->tcp_error_report = old_ctx->tcp_error_report; new_ctx->rel_write_seq = 1; new_ctx->tcp_sock = newsk; diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a135b1a46014..238b6a620e88 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -14,6 +14,11 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o +ifeq ($(CONFIG_NF_CONNTRACK),m) +nf_conntrack-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_conntrack_bpf.o +else ifeq ($(CONFIG_NF_CONNTRACK),y) +nf_conntrack-$(CONFIG_DEBUG_INFO_BTF) += nf_conntrack_bpf.o +endif obj-$(CONFIG_NETFILTER) = netfilter.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 354cb472f386..d1c9dfbb11fa 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -621,7 +621,8 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, case NF_ACCEPT: break; case NF_DROP: - kfree_skb(skb); + kfree_skb_reason(skb, + SKB_DROP_REASON_NETFILTER_DROP); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index 91bc8df3e4b0..385a5f458aba 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -22,26 +22,7 @@ static bool nf_ct_acct __read_mostly; module_param_named(acct, nf_ct_acct, bool, 0644); MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting."); -static const struct nf_ct_ext_type acct_extend = { - .len = sizeof(struct nf_conn_acct), - .align = __alignof__(struct nf_conn_acct), - .id = NF_CT_EXT_ACCT, -}; - void nf_conntrack_acct_pernet_init(struct net *net) { net->ct.sysctl_acct = nf_ct_acct; } - -int nf_conntrack_acct_init(void) -{ - int ret = nf_ct_extend_register(&acct_extend); - if (ret < 0) - pr_err("Unable to register extension\n"); - return ret; -} - -void nf_conntrack_acct_fini(void) -{ - nf_ct_extend_unregister(&acct_extend); -} diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c new file mode 100644 index 000000000000..8ad3f52579f3 --- /dev/null +++ b/net/netfilter/nf_conntrack_bpf.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Unstable Conntrack Helpers for XDP and TC-BPF hook + * + * These are called from the XDP and SCHED_CLS BPF programs. Note that it is + * allowed to break compatibility for these functions since the interface they + * are exposed through to BPF programs is explicitly unstable. + */ + +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/types.h> +#include <linux/btf_ids.h> +#include <linux/net_namespace.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> + +/* bpf_ct_opts - Options for CT lookup helpers + * + * Members: + * @netns_id - Specify the network namespace for lookup + * Values: + * BPF_F_CURRENT_NETNS (-1) + * Use namespace associated with ctx (xdp_md, __sk_buff) + * [0, S32_MAX] + * Network Namespace ID + * @error - Out parameter, set for any errors encountered + * Values: + * -EINVAL - Passed NULL for bpf_tuple pointer + * -EINVAL - opts->reserved is not 0 + * -EINVAL - netns_id is less than -1 + * -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (12) + * -EPROTO - l4proto isn't one of IPPROTO_TCP or IPPROTO_UDP + * -ENONET - No network namespace found for netns_id + * -ENOENT - Conntrack lookup could not find entry for tuple + * -EAFNOSUPPORT - tuple__sz isn't one of sizeof(tuple->ipv4) + * or sizeof(tuple->ipv6) + * @l4proto - Layer 4 protocol + * Values: + * IPPROTO_TCP, IPPROTO_UDP + * @reserved - Reserved member, will be reused for more options in future + * Values: + * 0 + */ +struct bpf_ct_opts { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +}; + +enum { + NF_BPF_CT_OPTS_SZ = 12, +}; + +static struct nf_conn *__bpf_nf_ct_lookup(struct net *net, + struct bpf_sock_tuple *bpf_tuple, + u32 tuple_len, u8 protonum, + s32 netns_id) +{ + struct nf_conntrack_tuple_hash *hash; + struct nf_conntrack_tuple tuple; + + if (unlikely(protonum != IPPROTO_TCP && protonum != IPPROTO_UDP)) + return ERR_PTR(-EPROTO); + if (unlikely(netns_id < BPF_F_CURRENT_NETNS)) + return ERR_PTR(-EINVAL); + + memset(&tuple, 0, sizeof(tuple)); + switch (tuple_len) { + case sizeof(bpf_tuple->ipv4): + tuple.src.l3num = AF_INET; + tuple.src.u3.ip = bpf_tuple->ipv4.saddr; + tuple.src.u.tcp.port = bpf_tuple->ipv4.sport; + tuple.dst.u3.ip = bpf_tuple->ipv4.daddr; + tuple.dst.u.tcp.port = bpf_tuple->ipv4.dport; + break; + case sizeof(bpf_tuple->ipv6): + tuple.src.l3num = AF_INET6; + memcpy(tuple.src.u3.ip6, bpf_tuple->ipv6.saddr, sizeof(bpf_tuple->ipv6.saddr)); + tuple.src.u.tcp.port = bpf_tuple->ipv6.sport; + memcpy(tuple.dst.u3.ip6, bpf_tuple->ipv6.daddr, sizeof(bpf_tuple->ipv6.daddr)); + tuple.dst.u.tcp.port = bpf_tuple->ipv6.dport; + break; + default: + return ERR_PTR(-EAFNOSUPPORT); + } + + tuple.dst.protonum = protonum; + + if (netns_id >= 0) { + net = get_net_ns_by_id(net, netns_id); + if (unlikely(!net)) + return ERR_PTR(-ENONET); + } + + hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple); + if (netns_id >= 0) + put_net(net); + if (!hash) + return ERR_PTR(-ENOENT); + return nf_ct_tuplehash_to_ctrack(hash); +} + +__diag_push(); +__diag_ignore(GCC, 8, "-Wmissing-prototypes", + "Global functions as their definitions will be in nf_conntrack BTF"); + +/* bpf_xdp_ct_lookup - Lookup CT entry for the given tuple, and acquire a + * reference to it + * + * Parameters: + * @xdp_ctx - Pointer to ctx (xdp_md) in XDP program + * Cannot be NULL + * @bpf_tuple - Pointer to memory representing the tuple to look up + * Cannot be NULL + * @tuple__sz - Length of the tuple structure + * Must be one of sizeof(bpf_tuple->ipv4) or + * sizeof(bpf_tuple->ipv6) + * @opts - Additional options for lookup (documented above) + * Cannot be NULL + * @opts__sz - Length of the bpf_ct_opts structure + * Must be NF_BPF_CT_OPTS_SZ (12) + */ +struct nf_conn * +bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, + u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) +{ + struct xdp_buff *ctx = (struct xdp_buff *)xdp_ctx; + struct net *caller_net; + struct nf_conn *nfct; + + BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ); + + if (!opts) + return NULL; + if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] || + opts->reserved[2] || opts__sz != NF_BPF_CT_OPTS_SZ) { + opts->error = -EINVAL; + return NULL; + } + caller_net = dev_net(ctx->rxq->dev); + nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto, + opts->netns_id); + if (IS_ERR(nfct)) { + opts->error = PTR_ERR(nfct); + return NULL; + } + return nfct; +} + +/* bpf_skb_ct_lookup - Lookup CT entry for the given tuple, and acquire a + * reference to it + * + * Parameters: + * @skb_ctx - Pointer to ctx (__sk_buff) in TC program + * Cannot be NULL + * @bpf_tuple - Pointer to memory representing the tuple to look up + * Cannot be NULL + * @tuple__sz - Length of the tuple structure + * Must be one of sizeof(bpf_tuple->ipv4) or + * sizeof(bpf_tuple->ipv6) + * @opts - Additional options for lookup (documented above) + * Cannot be NULL + * @opts__sz - Length of the bpf_ct_opts structure + * Must be NF_BPF_CT_OPTS_SZ (12) + */ +struct nf_conn * +bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, + u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) +{ + struct sk_buff *skb = (struct sk_buff *)skb_ctx; + struct net *caller_net; + struct nf_conn *nfct; + + BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ); + + if (!opts) + return NULL; + if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] || + opts->reserved[2] || opts__sz != NF_BPF_CT_OPTS_SZ) { + opts->error = -EINVAL; + return NULL; + } + caller_net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk); + nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto, + opts->netns_id); + if (IS_ERR(nfct)) { + opts->error = PTR_ERR(nfct); + return NULL; + } + return nfct; +} + +/* bpf_ct_release - Release acquired nf_conn object + * + * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects + * the program if any references remain in the program in all of the explored + * states. + * + * Parameters: + * @nf_conn - Pointer to referenced nf_conn object, obtained using + * bpf_xdp_ct_lookup or bpf_skb_ct_lookup. + */ +void bpf_ct_release(struct nf_conn *nfct) +{ + if (!nfct) + return; + nf_ct_put(nfct); +} + +__diag_pop() + +BTF_SET_START(nf_ct_xdp_check_kfunc_ids) +BTF_ID(func, bpf_xdp_ct_lookup) +BTF_ID(func, bpf_ct_release) +BTF_SET_END(nf_ct_xdp_check_kfunc_ids) + +BTF_SET_START(nf_ct_tc_check_kfunc_ids) +BTF_ID(func, bpf_skb_ct_lookup) +BTF_ID(func, bpf_ct_release) +BTF_SET_END(nf_ct_tc_check_kfunc_ids) + +BTF_SET_START(nf_ct_acquire_kfunc_ids) +BTF_ID(func, bpf_xdp_ct_lookup) +BTF_ID(func, bpf_skb_ct_lookup) +BTF_SET_END(nf_ct_acquire_kfunc_ids) + +BTF_SET_START(nf_ct_release_kfunc_ids) +BTF_ID(func, bpf_ct_release) +BTF_SET_END(nf_ct_release_kfunc_ids) + +/* Both sets are identical */ +#define nf_ct_ret_null_kfunc_ids nf_ct_acquire_kfunc_ids + +static const struct btf_kfunc_id_set nf_conntrack_xdp_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &nf_ct_xdp_check_kfunc_ids, + .acquire_set = &nf_ct_acquire_kfunc_ids, + .release_set = &nf_ct_release_kfunc_ids, + .ret_null_set = &nf_ct_ret_null_kfunc_ids, +}; + +static const struct btf_kfunc_id_set nf_conntrack_tc_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &nf_ct_tc_check_kfunc_ids, + .acquire_set = &nf_ct_acquire_kfunc_ids, + .release_set = &nf_ct_release_kfunc_ids, + .ret_null_set = &nf_ct_ret_null_kfunc_ids, +}; + +int register_nf_conntrack_bpf(void) +{ + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &nf_conntrack_xdp_kfunc_set); + return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_tc_kfunc_set); +} diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d6aa5b47031e..9b7f9c966f73 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -34,10 +34,10 @@ #include <linux/rculist_nulls.h> #include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_bpf.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> -#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_acct.h> @@ -47,7 +47,6 @@ #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_synproxy.h> -#include <net/netfilter/nf_conntrack_act_ct.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #include <net/netns/hash.h> @@ -594,7 +593,7 @@ EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); void nf_ct_tmpl_free(struct nf_conn *tmpl) { - nf_ct_ext_destroy(tmpl); + kfree(tmpl->ext); if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK) kfree((char *)tmpl - tmpl->proto.tmpl_padto); @@ -1597,7 +1596,17 @@ void nf_conntrack_free(struct nf_conn *ct) */ WARN_ON(refcount_read(&ct->ct_general.use) != 0); - nf_ct_ext_destroy(ct); + if (ct->status & IPS_SRC_NAT_DONE) { + const struct nf_nat_hook *nat_hook; + + rcu_read_lock(); + nat_hook = rcu_dereference(nf_nat_hook); + if (nat_hook) + nat_hook->remove_nat_bysrc(ct); + rcu_read_unlock(); + } + + kfree(ct->ext); kmem_cache_free(nf_conntrack_cachep, ct); cnet = nf_ct_pernet(net); @@ -2467,13 +2476,7 @@ void nf_conntrack_cleanup_end(void) kvfree(nf_conntrack_hash); nf_conntrack_proto_fini(); - nf_conntrack_seqadj_fini(); - nf_conntrack_labels_fini(); nf_conntrack_helper_fini(); - nf_conntrack_timeout_fini(); - nf_conntrack_ecache_fini(); - nf_conntrack_tstamp_fini(); - nf_conntrack_acct_fini(); nf_conntrack_expect_fini(); kmem_cache_destroy(nf_conntrack_cachep); @@ -2628,39 +2631,6 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) return nf_conntrack_hash_resize(hashsize); } -static __always_inline unsigned int total_extension_size(void) -{ - /* remember to add new extensions below */ - BUILD_BUG_ON(NF_CT_EXT_NUM > 10); - - return sizeof(struct nf_ct_ext) + - sizeof(struct nf_conn_help) -#if IS_ENABLED(CONFIG_NF_NAT) - + sizeof(struct nf_conn_nat) -#endif - + sizeof(struct nf_conn_seqadj) - + sizeof(struct nf_conn_acct) -#ifdef CONFIG_NF_CONNTRACK_EVENTS - + sizeof(struct nf_conntrack_ecache) -#endif -#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP - + sizeof(struct nf_conn_tstamp) -#endif -#ifdef CONFIG_NF_CONNTRACK_TIMEOUT - + sizeof(struct nf_conn_timeout) -#endif -#ifdef CONFIG_NF_CONNTRACK_LABELS - + sizeof(struct nf_conn_labels) -#endif -#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) - + sizeof(struct nf_conn_synproxy) -#endif -#if IS_ENABLED(CONFIG_NET_ACT_CT) - + sizeof(struct nf_conn_act_ct_ext) -#endif - ; -}; - int nf_conntrack_init_start(void) { unsigned long nr_pages = totalram_pages(); @@ -2668,9 +2638,6 @@ int nf_conntrack_init_start(void) int ret = -ENOMEM; int i; - /* struct nf_ct_ext uses u8 to store offsets/size */ - BUILD_BUG_ON(total_extension_size() > 255u); - seqcount_spinlock_init(&nf_conntrack_generation, &nf_conntrack_locks_all_lock); @@ -2715,34 +2682,10 @@ int nf_conntrack_init_start(void) if (ret < 0) goto err_expect; - ret = nf_conntrack_acct_init(); - if (ret < 0) - goto err_acct; - - ret = nf_conntrack_tstamp_init(); - if (ret < 0) - goto err_tstamp; - - ret = nf_conntrack_ecache_init(); - if (ret < 0) - goto err_ecache; - - ret = nf_conntrack_timeout_init(); - if (ret < 0) - goto err_timeout; - ret = nf_conntrack_helper_init(); if (ret < 0) goto err_helper; - ret = nf_conntrack_labels_init(); - if (ret < 0) - goto err_labels; - - ret = nf_conntrack_seqadj_init(); - if (ret < 0) - goto err_seqadj; - ret = nf_conntrack_proto_init(); if (ret < 0) goto err_proto; @@ -2750,23 +2693,18 @@ int nf_conntrack_init_start(void) conntrack_gc_work_init(&conntrack_gc_work); queue_delayed_work(system_power_efficient_wq, &conntrack_gc_work.dwork, HZ); + ret = register_nf_conntrack_bpf(); + if (ret < 0) + goto err_kfunc; + return 0; +err_kfunc: + cancel_delayed_work_sync(&conntrack_gc_work.dwork); + nf_conntrack_proto_fini(); err_proto: - nf_conntrack_seqadj_fini(); -err_seqadj: - nf_conntrack_labels_fini(); -err_labels: nf_conntrack_helper_fini(); err_helper: - nf_conntrack_timeout_fini(); -err_timeout: - nf_conntrack_ecache_fini(); -err_ecache: - nf_conntrack_tstamp_fini(); -err_tstamp: - nf_conntrack_acct_fini(); -err_acct: nf_conntrack_expect_fini(); err_expect: kmem_cache_destroy(nf_conntrack_cachep); diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 41768ff19464..07e65b4e92f8 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -131,13 +131,13 @@ static void ecache_work(struct work_struct *work) } static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e, - const unsigned int events, - const unsigned long missed, + const u32 events, + const u32 missed, const struct nf_ct_event *item) { - struct nf_conn *ct = item->ct; struct net *net = nf_ct_net(item->ct); struct nf_ct_event_notifier *notify; + u32 old, want; int ret; if (!((events | missed) & e->ctmask)) @@ -157,12 +157,13 @@ static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e, if (likely(ret >= 0 && missed == 0)) return 0; - spin_lock_bh(&ct->lock); - if (ret < 0) - e->missed |= events; - else - e->missed &= ~missed; - spin_unlock_bh(&ct->lock); + do { + old = READ_ONCE(e->missed); + if (ret < 0) + want = old | events; + else + want = old & ~missed; + } while (cmpxchg(&e->missed, old, want) != old); return ret; } @@ -172,7 +173,7 @@ int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct, { struct nf_conntrack_ecache *e; struct nf_ct_event item; - unsigned long missed; + unsigned int missed; int ret; if (!nf_ct_is_confirmed(ct)) @@ -211,7 +212,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct) { struct nf_conntrack_ecache *e; struct nf_ct_event item; - unsigned long events; + unsigned int events; if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct)) return; @@ -304,12 +305,6 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) #define NF_CT_EVENTS_DEFAULT 1 static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT; -static const struct nf_ct_ext_type event_extend = { - .len = sizeof(struct nf_conntrack_ecache), - .align = __alignof__(struct nf_conntrack_ecache), - .id = NF_CT_EXT_ECACHE, -}; - void nf_conntrack_ecache_pernet_init(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); @@ -317,6 +312,8 @@ void nf_conntrack_ecache_pernet_init(struct net *net) net->ct.sysctl_events = nf_ct_events; cnet->ct_net = &net->ct; INIT_DELAYED_WORK(&cnet->ecache_dwork, ecache_work); + + BUILD_BUG_ON(__IPCT_MAX >= 16); /* e->ctmask is u16 */ } void nf_conntrack_ecache_pernet_fini(struct net *net) @@ -325,19 +322,3 @@ void nf_conntrack_ecache_pernet_fini(struct net *net) cancel_delayed_work_sync(&cnet->ecache_dwork); } - -int nf_conntrack_ecache_init(void) -{ - int ret = nf_ct_extend_register(&event_extend); - if (ret < 0) - pr_err("Unable to register event extension\n"); - - BUILD_BUG_ON(__IPCT_MAX >= 16); /* ctmask, missed use u16 */ - - return ret; -} - -void nf_conntrack_ecache_fini(void) -{ - nf_ct_extend_unregister(&event_extend); -} diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 3dbe2329c3f1..1296fda54ac6 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -13,40 +13,90 @@ #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack_extend.h> -static struct nf_ct_ext_type __rcu *nf_ct_ext_types[NF_CT_EXT_NUM]; -static DEFINE_MUTEX(nf_ct_ext_type_mutex); +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_acct.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_timestamp.h> +#include <net/netfilter/nf_conntrack_timeout.h> +#include <net/netfilter/nf_conntrack_labels.h> +#include <net/netfilter/nf_conntrack_synproxy.h> +#include <net/netfilter/nf_conntrack_act_ct.h> +#include <net/netfilter/nf_nat.h> + #define NF_CT_EXT_PREALLOC 128u /* conntrack events are on by default */ -void nf_ct_ext_destroy(struct nf_conn *ct) +static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = { + [NF_CT_EXT_HELPER] = sizeof(struct nf_conn_help), +#if IS_ENABLED(CONFIG_NF_NAT) + [NF_CT_EXT_NAT] = sizeof(struct nf_conn_nat), +#endif + [NF_CT_EXT_SEQADJ] = sizeof(struct nf_conn_seqadj), + [NF_CT_EXT_ACCT] = sizeof(struct nf_conn_acct), +#ifdef CONFIG_NF_CONNTRACK_EVENTS + [NF_CT_EXT_ECACHE] = sizeof(struct nf_conntrack_ecache), +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_acct), +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_tstamp), +#endif +#ifdef CONFIG_NF_CONNTRACK_LABELS + [NF_CT_EXT_LABELS] = sizeof(struct nf_conn_labels), +#endif +#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) + [NF_CT_EXT_SYNPROXY] = sizeof(struct nf_conn_synproxy), +#endif +#if IS_ENABLED(CONFIG_NET_ACT_CT) + [NF_CT_EXT_ACT_CT] = sizeof(struct nf_conn_act_ct_ext), +#endif +}; + +static __always_inline unsigned int total_extension_size(void) { - unsigned int i; - struct nf_ct_ext_type *t; - - for (i = 0; i < NF_CT_EXT_NUM; i++) { - rcu_read_lock(); - t = rcu_dereference(nf_ct_ext_types[i]); - - /* Here the nf_ct_ext_type might have been unregisterd. - * I.e., it has responsible to cleanup private - * area in all conntracks when it is unregisterd. - */ - if (t && t->destroy) - t->destroy(ct); - rcu_read_unlock(); - } - - kfree(ct->ext); + /* remember to add new extensions below */ + BUILD_BUG_ON(NF_CT_EXT_NUM > 10); + + return sizeof(struct nf_ct_ext) + + sizeof(struct nf_conn_help) +#if IS_ENABLED(CONFIG_NF_NAT) + + sizeof(struct nf_conn_nat) +#endif + + sizeof(struct nf_conn_seqadj) + + sizeof(struct nf_conn_acct) +#ifdef CONFIG_NF_CONNTRACK_EVENTS + + sizeof(struct nf_conntrack_ecache) +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + + sizeof(struct nf_conn_tstamp) +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT + + sizeof(struct nf_conn_timeout) +#endif +#ifdef CONFIG_NF_CONNTRACK_LABELS + + sizeof(struct nf_conn_labels) +#endif +#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) + + sizeof(struct nf_conn_synproxy) +#endif +#if IS_ENABLED(CONFIG_NET_ACT_CT) + + sizeof(struct nf_conn_act_ct_ext) +#endif + ; } void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) { unsigned int newlen, newoff, oldlen, alloc; - struct nf_ct_ext_type *t; struct nf_ct_ext *new; /* Conntrack must not be confirmed to avoid races on reallocation. */ WARN_ON(nf_ct_is_confirmed(ct)); + /* struct nf_ct_ext uses u8 to store offsets/size */ + BUILD_BUG_ON(total_extension_size() > 255u); if (ct->ext) { const struct nf_ct_ext *old = ct->ext; @@ -58,16 +108,8 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) oldlen = sizeof(*new); } - rcu_read_lock(); - t = rcu_dereference(nf_ct_ext_types[id]); - if (!t) { - rcu_read_unlock(); - return NULL; - } - - newoff = ALIGN(oldlen, t->align); - newlen = newoff + t->len; - rcu_read_unlock(); + newoff = ALIGN(oldlen, __alignof__(struct nf_ct_ext)); + newlen = newoff + nf_ct_ext_type_len[id]; alloc = max(newlen, NF_CT_EXT_PREALLOC); new = krealloc(ct->ext, alloc, gfp); @@ -85,31 +127,3 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) return (void *)new + newoff; } EXPORT_SYMBOL(nf_ct_ext_add); - -/* This MUST be called in process context. */ -int nf_ct_extend_register(const struct nf_ct_ext_type *type) -{ - int ret = 0; - - mutex_lock(&nf_ct_ext_type_mutex); - if (nf_ct_ext_types[type->id]) { - ret = -EBUSY; - goto out; - } - - rcu_assign_pointer(nf_ct_ext_types[type->id], type); -out: - mutex_unlock(&nf_ct_ext_type_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_extend_register); - -/* This MUST be called in process context. */ -void nf_ct_extend_unregister(const struct nf_ct_ext_type *type) -{ - mutex_lock(&nf_ct_ext_type_mutex); - RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL); - mutex_unlock(&nf_ct_ext_type_mutex); - synchronize_rcu(); -} -EXPORT_SYMBOL_GPL(nf_ct_extend_unregister); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ae4488a13c70..a97ddb1497aa 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -550,12 +550,6 @@ void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat) } EXPORT_SYMBOL_GPL(nf_nat_helper_unregister); -static const struct nf_ct_ext_type helper_extend = { - .len = sizeof(struct nf_conn_help), - .align = __alignof__(struct nf_conn_help), - .id = NF_CT_EXT_HELPER, -}; - void nf_conntrack_helper_pernet_init(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); @@ -565,28 +559,17 @@ void nf_conntrack_helper_pernet_init(struct net *net) int nf_conntrack_helper_init(void) { - int ret; nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); if (!nf_ct_helper_hash) return -ENOMEM; - ret = nf_ct_extend_register(&helper_extend); - if (ret < 0) { - pr_err("nf_ct_helper: Unable to register helper extension.\n"); - goto out_extend; - } - INIT_LIST_HEAD(&nf_ct_nat_helpers); return 0; -out_extend: - kvfree(nf_ct_helper_hash); - return ret; } void nf_conntrack_helper_fini(void) { - nf_ct_extend_unregister(&helper_extend); kvfree(nf_ct_helper_hash); } diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 522792556632..6e70e137a0a6 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -67,6 +67,8 @@ int nf_connlabels_get(struct net *net, unsigned int bits) net->ct.labels_used++; spin_unlock(&nf_connlabels_lock); + BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX); + return 0; } EXPORT_SYMBOL_GPL(nf_connlabels_get); @@ -78,21 +80,3 @@ void nf_connlabels_put(struct net *net) spin_unlock(&nf_connlabels_lock); } EXPORT_SYMBOL_GPL(nf_connlabels_put); - -static const struct nf_ct_ext_type labels_extend = { - .len = sizeof(struct nf_conn_labels), - .align = __alignof__(struct nf_conn_labels), - .id = NF_CT_EXT_LABELS, -}; - -int nf_conntrack_labels_init(void) -{ - BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX); - - return nf_ct_extend_register(&labels_extend); -} - -void nf_conntrack_labels_fini(void) -{ - nf_ct_extend_unregister(&labels_extend); -} diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7032402ffd33..1ea2ad732d57 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -58,6 +58,12 @@ MODULE_LICENSE("GPL"); +struct ctnetlink_list_dump_ctx { + struct nf_conn *last; + unsigned int cpu; + bool done; +}; + static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *l4proto) @@ -1694,14 +1700,18 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, static int ctnetlink_done_list(struct netlink_callback *cb) { - if (cb->args[1]) - nf_ct_put((struct nf_conn *)cb->args[1]); + struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx; + + if (ctx->last) + nf_ct_put(ctx->last); + return 0; } static int ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying) { + struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx; struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; @@ -1712,12 +1722,12 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying struct hlist_nulls_head *list; struct net *net = sock_net(skb->sk); - if (cb->args[2]) + if (ctx->done) return 0; - last = (struct nf_conn *)cb->args[1]; + last = ctx->last; - for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { + for (cpu = ctx->cpu; cpu < nr_cpu_ids; cpu++) { struct ct_pcpu *pcpu; if (!cpu_possible(cpu)) @@ -1731,10 +1741,10 @@ restart: ct = nf_ct_tuplehash_to_ctrack(h); if (l3proto && nf_ct_l3num(ct) != l3proto) continue; - if (cb->args[1]) { + if (ctx->last) { if (ct != last) continue; - cb->args[1] = 0; + ctx->last = NULL; } /* We can't dump extension info for the unconfirmed @@ -1751,19 +1761,19 @@ restart: if (res < 0) { if (!refcount_inc_not_zero(&ct->ct_general.use)) continue; - cb->args[0] = cpu; - cb->args[1] = (unsigned long)ct; + ctx->cpu = cpu; + ctx->last = ct; spin_unlock_bh(&pcpu->lock); goto out; } } - if (cb->args[1]) { - cb->args[1] = 0; + if (ctx->last) { + ctx->last = NULL; goto restart; } spin_unlock_bh(&pcpu->lock); } - cb->args[2] = 1; + ctx->done = true; out: if (last) nf_ct_put(last); @@ -3878,6 +3888,8 @@ static int __init ctnetlink_init(void) { int ret; + BUILD_BUG_ON(sizeof(struct ctnetlink_list_dump_ctx) > sizeof_field(struct netlink_callback, ctx)); + ret = nfnetlink_subsys_register(&ctnl_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register with nfnetlink.\n"); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 7d5708b92138..f3fa367b455f 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -45,30 +45,8 @@ MODULE_ALIAS_NFCT_HELPER("pptp"); static DEFINE_SPINLOCK(nf_pptp_lock); -int -(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq) __read_mostly; -EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_outbound); - -int -(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq) __read_mostly; -EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_inbound); - -void -(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *expect_orig, - struct nf_conntrack_expect *expect_reply) - __read_mostly; -EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_exp_gre); - -void -(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, - struct nf_conntrack_expect *exp) __read_mostly; -EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn); +const struct nf_nat_pptp_hook *nf_nat_pptp_hook; +EXPORT_SYMBOL_GPL(nf_nat_pptp_hook); #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) /* PptpControlMessageType names */ @@ -111,8 +89,8 @@ EXPORT_SYMBOL(pptp_msg_name); static void pptp_expectfn(struct nf_conn *ct, struct nf_conntrack_expect *exp) { + const struct nf_nat_pptp_hook *hook; struct net *net = nf_ct_net(ct); - typeof(nf_nat_pptp_hook_expectfn) nf_nat_pptp_expectfn; pr_debug("increasing timeouts\n"); /* increase timeout of GRE data channel conntrack entry */ @@ -122,9 +100,9 @@ static void pptp_expectfn(struct nf_conn *ct, /* Can you see how rusty this code is, compared with the pre-2.6.11 * one? That's what happened to my shiny newnat of 2002 ;( -HW */ - nf_nat_pptp_expectfn = rcu_dereference(nf_nat_pptp_hook_expectfn); - if (nf_nat_pptp_expectfn && ct->master->status & IPS_NAT_MASK) - nf_nat_pptp_expectfn(ct, exp); + hook = rcu_dereference(nf_nat_pptp_hook); + if (hook && ct->master->status & IPS_NAT_MASK) + hook->expectfn(ct, exp); else { struct nf_conntrack_tuple inv_t; struct nf_conntrack_expect *exp_other; @@ -209,9 +187,9 @@ static void pptp_destroy_siblings(struct nf_conn *ct) static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid) { struct nf_conntrack_expect *exp_orig, *exp_reply; + const struct nf_nat_pptp_hook *hook; enum ip_conntrack_dir dir; int ret = 1; - typeof(nf_nat_pptp_hook_exp_gre) nf_nat_pptp_exp_gre; exp_orig = nf_ct_expect_alloc(ct); if (exp_orig == NULL) @@ -239,9 +217,9 @@ static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid) IPPROTO_GRE, &callid, &peer_callid); exp_reply->expectfn = pptp_expectfn; - nf_nat_pptp_exp_gre = rcu_dereference(nf_nat_pptp_hook_exp_gre); - if (nf_nat_pptp_exp_gre && ct->status & IPS_NAT_MASK) - nf_nat_pptp_exp_gre(exp_orig, exp_reply); + hook = rcu_dereference(nf_nat_pptp_hook); + if (hook && ct->status & IPS_NAT_MASK) + hook->exp_gre(exp_orig, exp_reply); if (nf_ct_expect_related(exp_orig, 0) != 0) goto out_put_both; if (nf_ct_expect_related(exp_reply, 0) != 0) @@ -279,9 +257,9 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo) { struct nf_ct_pptp_master *info = nfct_help_data(ct); + const struct nf_nat_pptp_hook *hook; u_int16_t msg; __be16 cid = 0, pcid = 0; - typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound; msg = ntohs(ctlh->messageType); pr_debug("inbound control message %s\n", pptp_msg_name(msg)); @@ -383,10 +361,9 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, goto invalid; } - nf_nat_pptp_inbound = rcu_dereference(nf_nat_pptp_hook_inbound); - if (nf_nat_pptp_inbound && ct->status & IPS_NAT_MASK) - return nf_nat_pptp_inbound(skb, ct, ctinfo, - protoff, ctlh, pptpReq); + hook = rcu_dereference(nf_nat_pptp_hook); + if (hook && ct->status & IPS_NAT_MASK) + return hook->inbound(skb, ct, ctinfo, protoff, ctlh, pptpReq); return NF_ACCEPT; invalid: @@ -407,9 +384,9 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo) { struct nf_ct_pptp_master *info = nfct_help_data(ct); + const struct nf_nat_pptp_hook *hook; u_int16_t msg; __be16 cid = 0, pcid = 0; - typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound; msg = ntohs(ctlh->messageType); pr_debug("outbound control message %s\n", pptp_msg_name(msg)); @@ -479,10 +456,9 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, goto invalid; } - nf_nat_pptp_outbound = rcu_dereference(nf_nat_pptp_hook_outbound); - if (nf_nat_pptp_outbound && ct->status & IPS_NAT_MASK) - return nf_nat_pptp_outbound(skb, ct, ctinfo, - protoff, ctlh, pptpReq); + hook = rcu_dereference(nf_nat_pptp_hook); + if (hook && ct->status & IPS_NAT_MASK) + return hook->outbound(skb, ct, ctinfo, protoff, ctlh, pptpReq); return NF_ACCEPT; invalid: diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 3b516cffc779..12f793d8fe0c 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -63,8 +63,10 @@ static bool udp_error(struct sk_buff *skb, } /* Packet with no checksum */ - if (!hdr->check) + if (!hdr->check) { + skb->ip_summed = CHECKSUM_UNNECESSARY; return false; + } /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index 3066449f8bd8..7ab2b25b57bc 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -232,19 +232,3 @@ s32 nf_ct_seq_offset(const struct nf_conn *ct, this_way->offset_after : this_way->offset_before; } EXPORT_SYMBOL_GPL(nf_ct_seq_offset); - -static const struct nf_ct_ext_type nf_ct_seqadj_extend = { - .len = sizeof(struct nf_conn_seqadj), - .align = __alignof__(struct nf_conn_seqadj), - .id = NF_CT_EXT_SEQADJ, -}; - -int nf_conntrack_seqadj_init(void) -{ - return nf_ct_extend_register(&nf_ct_seqadj_extend); -} - -void nf_conntrack_seqadj_fini(void) -{ - nf_ct_extend_unregister(&nf_ct_seqadj_extend); -} diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index 14387e0b8008..cec166ecba77 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -22,12 +22,8 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_timeout.h> -struct nf_ct_timeout * -(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name) __read_mostly; -EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook); - -void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout) __read_mostly; -EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook); +const struct nf_ct_timeout_hooks *nf_ct_timeout_hook __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_timeout_hook); static int untimeout(struct nf_conn *ct, void *timeout) { @@ -48,31 +44,30 @@ EXPORT_SYMBOL_GPL(nf_ct_untimeout); static void __nf_ct_timeout_put(struct nf_ct_timeout *timeout) { - typeof(nf_ct_timeout_put_hook) timeout_put; + const struct nf_ct_timeout_hooks *h = rcu_dereference(nf_ct_timeout_hook); - timeout_put = rcu_dereference(nf_ct_timeout_put_hook); - if (timeout_put) - timeout_put(timeout); + if (h) + h->timeout_put(timeout); } int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, const char *timeout_name) { - typeof(nf_ct_timeout_find_get_hook) timeout_find_get; + const struct nf_ct_timeout_hooks *h; struct nf_ct_timeout *timeout; struct nf_conn_timeout *timeout_ext; const char *errmsg = NULL; int ret = 0; rcu_read_lock(); - timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook); - if (!timeout_find_get) { + h = rcu_dereference(nf_ct_timeout_hook); + if (!h) { ret = -ENOENT; errmsg = "Timeout policy base is empty"; goto out; } - timeout = timeout_find_get(net, timeout_name); + timeout = h->timeout_find_get(net, timeout_name); if (!timeout) { ret = -ENOENT; pr_info_ratelimited("No such timeout policy \"%s\"\n", @@ -119,37 +114,18 @@ EXPORT_SYMBOL_GPL(nf_ct_set_timeout); void nf_ct_destroy_timeout(struct nf_conn *ct) { struct nf_conn_timeout *timeout_ext; - typeof(nf_ct_timeout_put_hook) timeout_put; + const struct nf_ct_timeout_hooks *h; rcu_read_lock(); - timeout_put = rcu_dereference(nf_ct_timeout_put_hook); + h = rcu_dereference(nf_ct_timeout_hook); - if (timeout_put) { + if (h) { timeout_ext = nf_ct_timeout_find(ct); if (timeout_ext) { - timeout_put(timeout_ext->timeout); + h->timeout_put(timeout_ext->timeout); RCU_INIT_POINTER(timeout_ext->timeout, NULL); } } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_ct_destroy_timeout); - -static const struct nf_ct_ext_type timeout_extend = { - .len = sizeof(struct nf_conn_timeout), - .align = __alignof__(struct nf_conn_timeout), - .id = NF_CT_EXT_TIMEOUT, -}; - -int nf_conntrack_timeout_init(void) -{ - int ret = nf_ct_extend_register(&timeout_extend); - if (ret < 0) - pr_err("nf_ct_timeout: Unable to register timeout extension.\n"); - return ret; -} - -void nf_conntrack_timeout_fini(void) -{ - nf_ct_extend_unregister(&timeout_extend); -} diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c index f656d393fa92..9e43a0a59e73 100644 --- a/net/netfilter/nf_conntrack_timestamp.c +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -19,27 +19,7 @@ static bool nf_ct_tstamp __read_mostly; module_param_named(tstamp, nf_ct_tstamp, bool, 0644); MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping."); -static const struct nf_ct_ext_type tstamp_extend = { - .len = sizeof(struct nf_conn_tstamp), - .align = __alignof__(struct nf_conn_tstamp), - .id = NF_CT_EXT_TSTAMP, -}; - void nf_conntrack_tstamp_pernet_init(struct net *net) { net->ct.sysctl_tstamp = nf_ct_tstamp; } - -int nf_conntrack_tstamp_init(void) -{ - int ret; - ret = nf_ct_extend_register(&tstamp_extend); - if (ret < 0) - pr_err("Unable to register extension\n"); - return ret; -} - -void nf_conntrack_tstamp_fini(void) -{ - nf_ct_extend_unregister(&tstamp_extend); -} diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 2d06a66899b2..58c06ac10179 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -838,7 +838,7 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data) return i->status & IPS_NAT_MASK ? 1 : 0; } -static void __nf_nat_cleanup_conntrack(struct nf_conn *ct) +static void nf_nat_cleanup_conntrack(struct nf_conn *ct) { unsigned int h; @@ -860,7 +860,7 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * will delete entry from already-freed table. */ if (test_and_clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status)) - __nf_nat_cleanup_conntrack(ct); + nf_nat_cleanup_conntrack(ct); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. @@ -868,20 +868,6 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) return 0; } -/* No one using conntrack by the time this called. */ -static void nf_nat_cleanup_conntrack(struct nf_conn *ct) -{ - if (ct->status & IPS_SRC_NAT_DONE) - __nf_nat_cleanup_conntrack(ct); -} - -static struct nf_ct_ext_type nat_extend __read_mostly = { - .len = sizeof(struct nf_conn_nat), - .align = __alignof__(struct nf_conn_nat), - .destroy = nf_nat_cleanup_conntrack, - .id = NF_CT_EXT_NAT, -}; - #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> @@ -1173,6 +1159,7 @@ static const struct nf_nat_hook nat_hook = { .decode_session = __nf_nat_decode_session, #endif .manip_pkt = nf_nat_manip_pkt, + .remove_nat_bysrc = nf_nat_cleanup_conntrack, }; static int __init nf_nat_init(void) @@ -1188,19 +1175,11 @@ static int __init nf_nat_init(void) if (!nf_nat_bysource) return -ENOMEM; - ret = nf_ct_extend_register(&nat_extend); - if (ret < 0) { - kvfree(nf_nat_bysource); - pr_err("Unable to register extension\n"); - return ret; - } - for (i = 0; i < CONNTRACK_LOCKS; i++) spin_lock_init(&nf_nat_locks[i]); ret = register_pernet_subsys(&nat_net_ops); if (ret < 0) { - nf_ct_extend_unregister(&nat_extend); kvfree(nf_nat_bysource); return ret; } @@ -1219,7 +1198,6 @@ static void __exit nf_nat_cleanup(void) nf_ct_iterate_destroy(nf_nat_proto_clean, &clean); - nf_ct_extend_unregister(&nat_extend); nf_ct_helper_expectfn_unregister(&follow_master_nat); RCU_INIT_POINTER(nf_nat_hook, NULL); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 2dfc5dae0656..e479dd0561c5 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -236,12 +236,6 @@ synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff, return 1; } -static struct nf_ct_ext_type nf_ct_synproxy_extend __read_mostly = { - .len = sizeof(struct nf_conn_synproxy), - .align = __alignof__(struct nf_conn_synproxy), - .id = NF_CT_EXT_SYNPROXY, -}; - #ifdef CONFIG_PROC_FS static void *synproxy_cpu_seq_start(struct seq_file *seq, loff_t *pos) { @@ -387,28 +381,12 @@ static struct pernet_operations synproxy_net_ops = { static int __init synproxy_core_init(void) { - int err; - - err = nf_ct_extend_register(&nf_ct_synproxy_extend); - if (err < 0) - goto err1; - - err = register_pernet_subsys(&synproxy_net_ops); - if (err < 0) - goto err2; - - return 0; - -err2: - nf_ct_extend_unregister(&nf_ct_synproxy_extend); -err1: - return err; + return register_pernet_subsys(&synproxy_net_ops); } static void __exit synproxy_core_exit(void) { unregister_pernet_subsys(&synproxy_net_ops); - nf_ct_extend_unregister(&nf_ct_synproxy_extend); } module_init(synproxy_core_init); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 36e73f9828c5..c6c05b2412c4 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -67,6 +67,20 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr, regs->verdict.code = NFT_BREAK; } +static void nft_cmp16_fast_eval(const struct nft_expr *expr, + struct nft_regs *regs) +{ + const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); + const u64 *reg_data = (const u64 *)®s->data[priv->sreg]; + const u64 *mask = (const u64 *)&priv->mask; + const u64 *data = (const u64 *)&priv->data; + + if (((reg_data[0] & mask[0]) == data[0] && + ((reg_data[1] & mask[1]) == data[1])) ^ priv->inv) + return; + regs->verdict.code = NFT_BREAK; +} + static noinline void __nft_trace_verdict(struct nft_traceinfo *info, const struct nft_chain *chain, const struct nft_regs *regs) @@ -225,6 +239,8 @@ next_rule: nft_rule_dp_for_each_expr(expr, last, rule) { if (expr->ops == &nft_cmp_fast_ops) nft_cmp_fast_eval(expr, ®s); + else if (expr->ops == &nft_cmp16_fast_ops) + nft_cmp16_fast_eval(expr, ®s); else if (expr->ops == &nft_bitwise_fast_ops) nft_bitwise_fast_eval(expr, ®s); else if (expr->ops != &nft_payload_fast_ops || diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index c57673d499be..b0d8888a539b 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -605,6 +605,11 @@ static struct pernet_operations cttimeout_ops = { .size = sizeof(struct nfct_timeout_pernet), }; +static const struct nf_ct_timeout_hooks hooks = { + .timeout_find_get = ctnl_timeout_find_get, + .timeout_put = ctnl_timeout_put, +}; + static int __init cttimeout_init(void) { int ret; @@ -619,8 +624,7 @@ static int __init cttimeout_init(void) "nfnetlink.\n"); goto err_out; } - RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, ctnl_timeout_find_get); - RCU_INIT_POINTER(nf_ct_timeout_put_hook, ctnl_timeout_put); + RCU_INIT_POINTER(nf_ct_timeout_hook, &hooks); return 0; err_out: @@ -633,8 +637,7 @@ static void __exit cttimeout_exit(void) nfnetlink_subsys_unregister(&cttimeout_subsys); unregister_pernet_subsys(&cttimeout_ops); - RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL); - RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL); + RCU_INIT_POINTER(nf_ct_timeout_hook, NULL); synchronize_rcu(); } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea2d9c2a44cf..8c15978d9258 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -402,6 +402,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + + nla_total_size(sizeof(u_int32_t)) /* priority */ + nla_total_size(sizeof(struct nfqnl_msg_packet_hw)) + nla_total_size(sizeof(u_int32_t)) /* skbinfo */ + nla_total_size(sizeof(u_int32_t)); /* cap_len */ @@ -559,6 +560,10 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark))) goto nla_put_failure; + if (entskb->priority && + nla_put_be32(skb, NFQA_PRIORITY, htonl(entskb->priority))) + goto nla_put_failure; + if (indev && entskb->dev && skb_mac_header_was_set(entskb) && skb_mac_header_len(entskb) != 0) { @@ -1014,11 +1019,13 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_CT] = { .type = NLA_UNSPEC }, [NFQA_EXP] = { .type = NLA_UNSPEC }, [NFQA_VLAN] = { .type = NLA_NESTED }, + [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, + [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static struct nfqnl_instance * @@ -1099,6 +1106,9 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb, if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); + if (nfqa[NFQA_PRIORITY]) + entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); + nfqnl_reinject(entry, verdict); } return 0; @@ -1225,6 +1235,9 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); + if (nfqa[NFQA_PRIORITY]) + entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); + nfqnl_reinject(entry, verdict); return 0; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 47b6d05f1ae6..917072af09df 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -272,12 +272,103 @@ const struct nft_expr_ops nft_cmp_fast_ops = { .offload = nft_cmp_fast_offload, }; +static u32 nft_cmp_mask(u32 bitlen) +{ + return (__force u32)cpu_to_le32(~0U >> (sizeof(u32) * BITS_PER_BYTE - bitlen)); +} + +static void nft_cmp16_fast_mask(struct nft_data *data, unsigned int bitlen) +{ + int len = bitlen / BITS_PER_BYTE; + int i, words = len / sizeof(u32); + + for (i = 0; i < words; i++) { + data->data[i] = 0xffffffff; + bitlen -= sizeof(u32) * BITS_PER_BYTE; + } + + if (len % sizeof(u32)) + data->data[i++] = nft_cmp_mask(bitlen); + + for (; i < 4; i++) + data->data[i] = 0; +} + +static int nft_cmp16_fast_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); + struct nft_data_desc desc; + int err; + + err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &desc, + tb[NFTA_CMP_DATA]); + if (err < 0) + return err; + + err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + if (err < 0) + return err; + + nft_cmp16_fast_mask(&priv->mask, desc.len * BITS_PER_BYTE); + priv->inv = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ; + priv->len = desc.len; + + return 0; +} + +static int nft_cmp16_fast_offload(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_expr *expr) +{ + const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); + struct nft_cmp_expr cmp = { + .data = priv->data, + .sreg = priv->sreg, + .len = priv->len, + .op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ, + }; + + return __nft_cmp_offload(ctx, flow, &cmp); +} + +static int nft_cmp16_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); + enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ; + + if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg)) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op))) + goto nla_put_failure; + + if (nft_data_dump(skb, NFTA_CMP_DATA, &priv->data, + NFT_DATA_VALUE, priv->len) < 0) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + + +const struct nft_expr_ops nft_cmp16_fast_ops = { + .type = &nft_cmp_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_cmp16_fast_expr)), + .eval = NULL, /* inlined */ + .init = nft_cmp16_fast_init, + .dump = nft_cmp16_fast_dump, + .offload = nft_cmp16_fast_offload, +}; + static const struct nft_expr_ops * nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_data_desc desc; struct nft_data data; enum nft_cmp_ops op; + u8 sreg; int err; if (tb[NFTA_CMP_SREG] == NULL || @@ -306,9 +397,16 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) if (desc.type != NFT_DATA_VALUE) goto err1; - if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ)) - return &nft_cmp_fast_ops; + sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG])); + if (op == NFT_CMP_EQ || op == NFT_CMP_NEQ) { + if (desc.len <= sizeof(u32)) + return &nft_cmp_fast_ops; + else if (desc.len <= sizeof(data) && + ((sreg >= NFT_REG_1 && sreg <= NFT_REG_4) || + (sreg >= NFT_REG32_00 && sreg <= NFT_REG32_12 && sreg % 2 == 0))) + return &nft_cmp16_fast_ops; + } return &nft_cmp_ops; err1: nft_data_release(&data, desc.type); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index f69cc73c5813..5a46d8289d1d 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -731,6 +731,14 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { static struct nft_expr_type nft_match_type; +static bool nft_match_reduce(struct nft_regs_track *track, + const struct nft_expr *expr) +{ + const struct xt_match *match = expr->ops->data; + + return strcmp(match->name, "comment") == 0; +} + static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -773,6 +781,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, ops->dump = nft_match_dump; ops->validate = nft_match_validate; ops->data = match; + ops->reduce = nft_match_reduce; matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); if (matchsize > NFT_MATCH_LARGE_THRESH) { diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 9e927ab4df15..d2b9378164bb 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -308,6 +308,63 @@ err: regs->verdict.code = NFT_BREAK; } +static void nft_exthdr_tcp_strip_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + u8 buff[sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE]; + struct nft_exthdr *priv = nft_expr_priv(expr); + unsigned int i, tcphdr_len, optl; + struct tcphdr *tcph; + u8 *opt; + + tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); + if (!tcph) + goto err; + + if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + tcphdr_len)) + goto drop; + + opt = (u8 *)nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); + if (!opt) + goto err; + for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { + unsigned int j; + + optl = optlen(opt, i); + if (priv->type != opt[i]) + continue; + + if (i + optl > tcphdr_len) + goto drop; + + for (j = 0; j < optl; ++j) { + u16 n = TCPOPT_NOP; + u16 o = opt[i+j]; + + if ((i + j) % 2 == 0) { + o <<= 8; + n <<= 8; + } + inet_proto_csum_replace2(&tcph->check, pkt->skb, htons(o), + htons(n), false); + } + memset(opt + i, TCPOPT_NOP, optl); + return; + } + + /* option not found, continue. This allows to do multiple + * option removals per rule. + */ + return; +err: + regs->verdict.code = NFT_BREAK; + return; +drop: + /* can't remove, no choice but to drop */ + regs->verdict.code = NF_DROP; +} + static void nft_exthdr_sctp_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -457,6 +514,28 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, priv->len); } +static int nft_exthdr_tcp_strip_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + + if (tb[NFTA_EXTHDR_SREG] || + tb[NFTA_EXTHDR_DREG] || + tb[NFTA_EXTHDR_FLAGS] || + tb[NFTA_EXTHDR_OFFSET] || + tb[NFTA_EXTHDR_LEN]) + return -EINVAL; + + if (!tb[NFTA_EXTHDR_TYPE]) + return -EINVAL; + + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); + priv->op = NFT_EXTHDR_OP_TCPOPT; + + return 0; +} + static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -517,6 +596,13 @@ static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } +static int nft_exthdr_dump_strip(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_exthdr *priv = nft_expr_priv(expr); + + return nft_exthdr_dump_common(skb, priv); +} + static const struct nft_expr_ops nft_exthdr_ipv6_ops = { .type = &nft_exthdr_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), @@ -549,6 +635,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_set_ops = { .dump = nft_exthdr_dump_set, }; +static const struct nft_expr_ops nft_exthdr_tcp_strip_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_tcp_strip_eval, + .init = nft_exthdr_tcp_strip_init, + .dump = nft_exthdr_dump_strip, +}; + static const struct nft_expr_ops nft_exthdr_sctp_ops = { .type = &nft_exthdr_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), @@ -576,7 +670,7 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, return &nft_exthdr_tcp_set_ops; if (tb[NFTA_EXTHDR_DREG]) return &nft_exthdr_tcp_ops; - break; + return &nft_exthdr_tcp_strip_ops; case NFT_EXTHDR_OP_IPV6: if (tb[NFTA_EXTHDR_DREG]) return &nft_exthdr_ipv6_ops; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 67ad08320886..7e8a39a35627 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -37,6 +37,7 @@ #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/pkt_cls.h> #include "datapath.h" #include "flow.h" @@ -1601,8 +1602,6 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, dp->user_features = 0; } -DEFINE_STATIC_KEY_FALSE(tc_recirc_sharing_support); - static int ovs_dp_set_upcall_portids(struct datapath *dp, const struct nlattr *ids) { @@ -1657,7 +1656,7 @@ u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id) static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) { - u32 user_features = 0; + u32 user_features = 0, old_features = dp->user_features; int err; if (a[OVS_DP_ATTR_USER_FEATURES]) { @@ -1696,10 +1695,12 @@ static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) return err; } - if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) - static_branch_enable(&tc_recirc_sharing_support); - else - static_branch_disable(&tc_recirc_sharing_support); + if ((dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) && + !(old_features & OVS_DP_F_TC_RECIRC_SHARING)) + tc_skb_ext_tc_enable(); + else if (!(dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) && + (old_features & OVS_DP_F_TC_RECIRC_SHARING)) + tc_skb_ext_tc_disable(); return 0; } @@ -1839,6 +1840,9 @@ static void __dp_destroy(struct datapath *dp) struct flow_table *table = &dp->table; int i; + if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) + tc_skb_ext_tc_disable(); + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; struct hlist_node *n; diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index fcfe6cb46441..0cd29971a907 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -253,8 +253,6 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex) extern struct notifier_block ovs_dp_device_notifier; extern struct genl_family dp_vport_genl_family; -DECLARE_STATIC_KEY_FALSE(tc_recirc_sharing_support); - void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key); void ovs_dp_detach_port(struct vport *); int ovs_dp_upcall(struct datapath *, struct sk_buff *, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 02096f2ec678..f6cd24fd530c 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -34,6 +34,7 @@ #include <net/mpls.h> #include <net/ndisc.h> #include <net/nsh.h> +#include <net/pkt_cls.h> #include <net/netfilter/nf_conntrack_zones.h> #include "conntrack.h" @@ -895,7 +896,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->mac_proto = res; #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - if (static_branch_unlikely(&tc_recirc_sharing_support)) { + if (tc_skb_ext_tc_enabled()) { tc_ext = skb_ext_find(skb, TC_SKB_EXT); key->recirc_id = tc_ext ? tc_ext->chain : 0; OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f99247fc6468..7108e71ce4db 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -57,12 +57,6 @@ static const struct rhashtable_params zones_params = { .automatic_shrinking = true, }; -static struct nf_ct_ext_type act_ct_extend __read_mostly = { - .len = sizeof(struct nf_conn_act_ct_ext), - .align = __alignof__(struct nf_conn_act_ct_ext), - .id = NF_CT_EXT_ACT_CT, -}; - static struct flow_action_entry * tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action) { @@ -1608,16 +1602,10 @@ static int __init ct_init_module(void) if (err) goto err_register; - err = nf_ct_extend_register(&act_ct_extend); - if (err) - goto err_register_extend; - static_branch_inc(&tcf_frag_xmit_count); return 0; -err_register_extend: - tcf_unregister_action(&act_ct_ops, &ct_net_ops); err_register: tcf_ct_flow_tables_uninit(); err_tbl_init: @@ -1628,7 +1616,6 @@ err_tbl_init: static void __exit ct_cleanup_module(void) { static_branch_dec(&tcf_frag_xmit_count); - nf_ct_extend_unregister(&act_ct_extend); tcf_unregister_action(&act_ct_ops, &ct_net_ops); tcf_ct_flow_tables_uninit(); destroy_workqueue(act_ct_wq); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 0923aa2b8f8a..899fe025df77 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -239,6 +239,20 @@ release_idr: return err; } +static bool tcf_police_mtu_check(struct sk_buff *skb, u32 limit) +{ + u32 len; + + if (skb_is_gso(skb)) + return skb_gso_validate_mac_len(skb, limit); + + len = qdisc_pkt_len(skb); + if (skb_at_tc_ingress(skb)) + len += skb->mac_len; + + return len <= limit; +} + static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -261,7 +275,7 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, goto inc_overlimits; } - if (qdisc_pkt_len(skb) <= p->tcfp_mtu) { + if (tcf_police_mtu_check(skb, p->tcfp_mtu)) { if (!p->rate_present && !p->pps_present) { ret = p->tcfp_result; goto end; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 5ce1208a6ea3..2957f8f5cea7 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -49,6 +49,23 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +#ifdef CONFIG_NET_CLS_ACT +DEFINE_STATIC_KEY_FALSE(tc_skb_ext_tc); +EXPORT_SYMBOL(tc_skb_ext_tc); + +void tc_skb_ext_tc_enable(void) +{ + static_branch_inc(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_enable); + +void tc_skb_ext_tc_disable(void) +{ + static_branch_dec(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_disable); +#endif + static u32 destroy_obj_hashfn(const struct tcf_proto *tp) { return jhash_3words(tp->chain->index, tp->prio, @@ -1615,19 +1632,21 @@ int tcf_classify(struct sk_buff *skb, ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, &last_executed_chain); - /* If we missed on some chain */ - if (ret == TC_ACT_UNSPEC && last_executed_chain) { - struct tc_skb_cb *cb = tc_skb_cb(skb); - - ext = tc_skb_ext_alloc(skb); - if (WARN_ON_ONCE(!ext)) - return TC_ACT_SHOT; - ext->chain = last_executed_chain; - ext->mru = cb->mru; - ext->post_ct = cb->post_ct; - ext->post_ct_snat = cb->post_ct_snat; - ext->post_ct_dnat = cb->post_ct_dnat; - ext->zone = cb->zone; + if (tc_skb_ext_tc_enabled()) { + /* If we missed on some chain */ + if (ret == TC_ACT_UNSPEC && last_executed_chain) { + struct tc_skb_cb *cb = tc_skb_cb(skb); + + ext = tc_skb_ext_alloc(skb); + if (WARN_ON_ONCE(!ext)) + return TC_ACT_SHOT; + ext->chain = last_executed_chain; + ext->mru = cb->mru; + ext->post_ct = cb->post_ct; + ext->post_ct_snat = cb->post_ct_snat; + ext->post_ct_dnat = cb->post_ct_dnat; + ext->zone = cb->zone; + } } return ret; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 306d9e8cd1dd..b40ae4d28cbf 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -59,12 +59,52 @@ static DEFINE_MUTEX(smc_client_lgr_pending); /* serialize link group * creation on client */ +static struct workqueue_struct *smc_tcp_ls_wq; /* wq for tcp listen work */ struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ struct workqueue_struct *smc_close_wq; /* wq for close work */ static void smc_tcp_listen_work(struct work_struct *); static void smc_connect_work(struct work_struct *); +int smc_nl_dump_hs_limitation(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + void *hdr; + + if (cb_ctx->pos[0]) + goto out; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_DUMP_HS_LIMITATION); + if (!hdr) + return -ENOMEM; + + if (nla_put_u8(skb, SMC_NLA_HS_LIMITATION_ENABLED, + sock_net(skb->sk)->smc.limit_smc_hs)) + goto err; + + genlmsg_end(skb, hdr); + cb_ctx->pos[0] = 1; +out: + return skb->len; +err: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info) +{ + sock_net(skb->sk)->smc.limit_smc_hs = true; + return 0; +} + +int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info) +{ + sock_net(skb->sk)->smc.limit_smc_hs = false; + return 0; +} + static void smc_set_keepalive(struct sock *sk, int val) { struct smc_sock *smc = smc_sk(sk); @@ -72,6 +112,51 @@ static void smc_set_keepalive(struct sock *sk, int val) smc->clcsock->sk->sk_prot->keepalive(smc->clcsock->sk, val); } +static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, + struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req) +{ + struct smc_sock *smc; + + smc = smc_clcsock_user_data(sk); + + if (READ_ONCE(sk->sk_ack_backlog) + atomic_read(&smc->queued_smc_hs) > + sk->sk_max_ack_backlog) + goto drop; + + if (sk_acceptq_is_full(&smc->sk)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + goto drop; + } + + /* passthrough to original syn recv sock fct */ + return smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, + own_req); + +drop: + dst_release(dst); + tcp_listendrop(sk); + return NULL; +} + +static bool smc_hs_congested(const struct sock *sk) +{ + const struct smc_sock *smc; + + smc = smc_clcsock_user_data(sk); + + if (!smc) + return true; + + if (workqueue_congested(WORK_CPU_UNBOUND, smc_hs_wq)) + return true; + + return false; +} + static struct smc_hashinfo smc_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), }; @@ -1291,8 +1376,14 @@ static int __smc_connect(struct smc_sock *smc) /* perform CLC handshake */ rc = smc_connect_clc(smc, aclc2, ini); - if (rc) + if (rc) { + /* -EAGAIN on timeout, see tcp_recvmsg() */ + if (rc == -EAGAIN) { + rc = -ETIMEDOUT; + smc->sk.sk_err = ETIMEDOUT; + } goto vlan_cleanup; + } /* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); @@ -1598,6 +1689,9 @@ static void smc_listen_out(struct smc_sock *new_smc) struct smc_sock *lsmc = new_smc->listen_smc; struct sock *newsmcsk = &new_smc->sk; + if (tcp_sk(new_smc->clcsock->sk)->syn_smc) + atomic_dec(&lsmc->queued_smc_hs); + if (lsmc->sk.sk_state == SMC_LISTEN) { lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); @@ -2203,6 +2297,9 @@ static void smc_tcp_listen_work(struct work_struct *work) if (!new_smc) continue; + if (tcp_sk(new_smc->clcsock->sk)->syn_smc) + atomic_inc(&lsmc->queued_smc_hs); + new_smc->listen_smc = lsmc; new_smc->use_fallback = lsmc->use_fallback; new_smc->fallback_rsn = lsmc->fallback_rsn; @@ -2231,7 +2328,7 @@ static void smc_clcsock_data_ready(struct sock *listen_clcsock) lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ - if (!queue_work(smc_hs_wq, &lsmc->tcp_listen_work)) + if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } } @@ -2269,6 +2366,18 @@ static int smc_listen(struct socket *sock, int backlog) smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + + /* save original ops */ + smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; + + smc->af_ops = *smc->ori_af_ops; + smc->af_ops.syn_recv_sock = smc_tcp_syn_recv_sock; + + inet_csk(smc->clcsock->sk)->icsk_af_ops = &smc->af_ops; + + if (smc->limit_smc_hs) + tcp_sk(smc->clcsock->sk)->smc_hs_congested = smc_hs_congested; + rc = kernel_listen(smc->clcsock, backlog); if (rc) { smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; @@ -2562,6 +2671,67 @@ out: return rc ? rc : rc1; } +static int __smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct smc_sock *smc; + int val, len; + + smc = smc_sk(sock->sk); + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(int, len, sizeof(int)); + + if (len < 0) + return -EINVAL; + + switch (optname) { + case SMC_LIMIT_HS: + val = smc->limit_smc_hs; + break; + default: + return -EOPNOTSUPP; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + +static int __smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct smc_sock *smc; + int val, rc; + + smc = smc_sk(sk); + + lock_sock(sk); + switch (optname) { + case SMC_LIMIT_HS: + if (optlen < sizeof(int)) + return -EINVAL; + if (copy_from_sockptr(&val, optval, sizeof(int))) + return -EFAULT; + + smc->limit_smc_hs = !!val; + rc = 0; + break; + default: + rc = -EOPNOTSUPP; + break; + } + release_sock(sk); + + return rc; +} + static int smc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -2571,6 +2741,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (level == SOL_TCP && optname == TCP_ULP) return -EOPNOTSUPP; + else if (level == SOL_SMC) + return __smc_setsockopt(sock, level, optname, optval, optlen); smc = smc_sk(sk); @@ -2630,8 +2802,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_state != SMC_CLOSED) { if (!val) { SMC_STAT_INC(smc, cork_cnt); - mod_delayed_work(smc->conn.lgr->tx_wq, - &smc->conn.tx_work, 0); + smc_tx_pending(&smc->conn); + cancel_delayed_work(&smc->conn.tx_work); } } break; @@ -2653,6 +2825,9 @@ static int smc_getsockopt(struct socket *sock, int level, int optname, struct smc_sock *smc; int rc; + if (level == SOL_SMC) + return __smc_getsockopt(sock, level, optname, optval, optlen); + smc = smc_sk(sock->sk); mutex_lock(&smc->clcsock_release_lock); if (!smc->clcsock) { @@ -2769,8 +2944,10 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); } else { + lock_sock(sk); + rc = smc_tx_sendpage(smc, page, offset, size, flags); + release_sock(sk); SMC_STAT_INC(smc, sendpage_cnt); - rc = sock_no_sendpage(sock, page, offset, size, flags); } out: @@ -2879,6 +3056,9 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, smc->use_fallback = false; /* assume rdma capability first */ smc->fallback_rsn = 0; + /* default behavior from limit_smc_hs in every net namespace */ + smc->limit_smc_hs = net->smc.limit_smc_hs; + rc = 0; if (!clcsock) { rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, @@ -3026,9 +3206,14 @@ static int __init smc_init(void) goto out_nl; rc = -ENOMEM; + + smc_tcp_ls_wq = alloc_workqueue("smc_tcp_ls_wq", 0, 0); + if (!smc_tcp_ls_wq) + goto out_pnet; + smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0); if (!smc_hs_wq) - goto out_pnet; + goto out_alloc_tcp_ls_wq; smc_close_wq = alloc_workqueue("smc_close_wq", 0, 0); if (!smc_close_wq) @@ -3099,6 +3284,8 @@ out_alloc_wqs: destroy_workqueue(smc_close_wq); out_alloc_hs_wq: destroy_workqueue(smc_hs_wq); +out_alloc_tcp_ls_wq: + destroy_workqueue(smc_tcp_ls_wq); out_pnet: smc_pnet_exit(); out_nl: @@ -3117,6 +3304,7 @@ static void __exit smc_exit(void) smc_core_exit(); smc_ib_unregister_client(); destroy_workqueue(smc_close_wq); + destroy_workqueue(smc_tcp_ls_wq); destroy_workqueue(smc_hs_wq); proto_unregister(&smc_proto6); proto_unregister(&smc_proto); diff --git a/net/smc/smc.h b/net/smc/smc.h index 37b2001a0255..a096d8af21a0 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -14,6 +14,7 @@ #include <linux/socket.h> #include <linux/types.h> #include <linux/compiler.h> /* __aligned */ +#include <net/genetlink.h> #include <net/sock.h> #include "smc_ib.h" @@ -249,9 +250,14 @@ struct smc_sock { /* smc sock container */ struct work_struct smc_listen_work;/* prepare new accept socket */ struct list_head accept_q; /* sockets to be accepted */ spinlock_t accept_q_lock; /* protects accept_q */ + bool limit_smc_hs; /* put constraint on handshake */ bool use_fallback; /* fallback to tcp */ int fallback_rsn; /* reason for fallback */ u32 peer_diagnosis; /* decline reason from peer */ + atomic_t queued_smc_hs; /* queued smc handshakes */ + struct inet_connection_sock_af_ops af_ops; + const struct inet_connection_sock_af_ops *ori_af_ops; + /* original af ops */ int sockopt_defer_accept; /* sockopt TCP_DEFER_ACCEPT * value @@ -276,7 +282,7 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } -static inline struct smc_sock *smc_clcsock_user_data(struct sock *clcsk) +static inline struct smc_sock *smc_clcsock_user_data(const struct sock *clcsk) { return (struct smc_sock *) ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); @@ -331,4 +337,9 @@ void smc_fill_gid_list(struct smc_link_group *lgr, struct smc_gidlist *gidlist, struct smc_ib_device *known_dev, u8 *known_gid); +/* smc handshake limitation interface for netlink */ +int smc_nl_dump_hs_limitation(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info); +int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info); + #endif /* __SMC_H */ diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index f13ab0661ed5..c5a62f6f52ba 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -111,6 +111,21 @@ static const struct genl_ops smc_gen_nl_ops[] = { .flags = GENL_ADMIN_PERM, .doit = smc_nl_disable_seid, }, + { + .cmd = SMC_NETLINK_DUMP_HS_LIMITATION, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_hs_limitation, + }, + { + .cmd = SMC_NETLINK_ENABLE_HS_LIMITATION, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_enable_hs_limitation, + }, + { + .cmd = SMC_NETLINK_DISABLE_HS_LIMITATION, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_disable_hs_limitation, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 0599246c0376..ff61b7b95875 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -870,6 +870,9 @@ int smc_pnet_net_init(struct net *net) smc_pnet_create_pnetids_list(net); + /* disable handshake limitation by default */ + net->smc.limit_smc_hs = 0; + return 0; } diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index be241d53020f..5df3940d4543 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -31,7 +31,6 @@ #include "smc_tracepoint.h" #define SMC_TX_WORK_DELAY 0 -#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ /***************************** sndbuf producer *******************************/ @@ -236,16 +235,15 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) */ if ((msg->msg_flags & MSG_OOB) && !send_remaining) conn->urg_tx_pend = true; - if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) && - (atomic_read(&conn->sndbuf_space) > - (conn->sndbuf_desc->len >> 1))) - /* for a corked socket defer the RDMA writes if there - * is still sufficient sndbuf_space available + if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc) || + msg->msg_flags & MSG_SENDPAGE_NOTLAST) && + (atomic_read(&conn->sndbuf_space))) + /* for a corked socket defer the RDMA writes if + * sndbuf_space is still available. The applications + * should known how/when to uncork it. */ - queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, - SMC_TX_CORK_DELAY); - else - smc_tx_sndbuf_nonempty(conn); + continue; + smc_tx_sndbuf_nonempty(conn); trace_smc_tx_sendmsg(smc, copylen); } /* while (msg_data_left(msg)) */ @@ -260,6 +258,22 @@ out_err: return rc; } +int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset, + size_t size, int flags) +{ + struct msghdr msg = {.msg_flags = flags}; + char *kaddr = kmap(page); + struct kvec iov; + int rc; + + iov.iov_base = kaddr + offset; + iov.iov_len = size; + iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size); + rc = smc_tx_sendmsg(smc, &msg, size); + kunmap(page); + return rc; +} + /***************************** sndbuf consumer *******************************/ /* sndbuf consumer: actual data transfer of one target chunk with ISM write */ @@ -598,26 +612,36 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) } /* Wakeup sndbuf consumers from process context - * since there is more data to transmit + * since there is more data to transmit. The caller + * must hold sock lock. */ -void smc_tx_work(struct work_struct *work) +void smc_tx_pending(struct smc_connection *conn) { - struct smc_connection *conn = container_of(to_delayed_work(work), - struct smc_connection, - tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc; - lock_sock(&smc->sk); if (smc->sk.sk_err) - goto out; + return; rc = smc_tx_sndbuf_nonempty(conn); if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; +} + +/* Wakeup sndbuf consumers from process context + * since there is more data to transmit in locked + * sock. + */ +void smc_tx_work(struct work_struct *work) +{ + struct smc_connection *conn = container_of(to_delayed_work(work), + struct smc_connection, + tx_work); + struct smc_sock *smc = container_of(conn, struct smc_sock, conn); -out: + lock_sock(&smc->sk); + smc_tx_pending(conn); release_sock(&smc->sk); } diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h index 07e6ad76224a..34b578498b1f 100644 --- a/net/smc/smc_tx.h +++ b/net/smc/smc_tx.h @@ -27,9 +27,12 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn) return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); } +void smc_tx_pending(struct smc_connection *conn); void smc_tx_work(struct work_struct *work); void smc_tx_init(struct smc_sock *smc); int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len); +int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset, + size_t size, int flags); int smc_tx_sndbuf_nonempty(struct smc_connection *conn); void smc_tx_sndbuf_nonfull(struct smc_sock *smc); void smc_tx_consumer_update(struct smc_connection *conn, bool force); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 5f42aa5fc612..8eb7e8544815 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -72,7 +72,8 @@ struct gss_auth { struct gss_api_mech *mech; enum rpc_gss_svc service; struct rpc_clnt *client; - struct net *net; + struct net *net; + netns_tracker ns_tracker; /* * There are two upcall pipes; dentry[1], named "gssd", is used * for the new text-based upcall; dentry[0] is named after the @@ -1013,7 +1014,8 @@ gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) goto err_free; } gss_auth->client = clnt; - gss_auth->net = get_net(rpc_net_ns(clnt)); + gss_auth->net = get_net_track(rpc_net_ns(clnt), &gss_auth->ns_tracker, + GFP_KERNEL); err = -EINVAL; gss_auth->mech = gss_mech_get_by_pseudoflavor(flavor); if (!gss_auth->mech) @@ -1068,7 +1070,7 @@ err_destroy_credcache: err_put_mech: gss_mech_put(gss_auth->mech); err_put_net: - put_net(gss_auth->net); + put_net_track(gss_auth->net, &gss_auth->ns_tracker); err_free: kfree(gss_auth->target_name); kfree(gss_auth); @@ -1084,7 +1086,7 @@ gss_free(struct gss_auth *gss_auth) gss_pipe_free(gss_auth->gss_pipe[0]); gss_pipe_free(gss_auth->gss_pipe[1]); gss_mech_put(gss_auth->mech); - put_net(gss_auth->net); + put_net_track(gss_auth->net, &gss_auth->ns_tracker); kfree(gss_auth->target_name); kfree(gss_auth); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b21ad7994147..db878e833b67 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -162,7 +162,7 @@ static void svc_xprt_free(struct kref *kref) if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) svcauth_unix_info_release(xprt); put_cred(xprt->xpt_cred); - put_net(xprt->xpt_net); + put_net_track(xprt->xpt_net, &xprt->ns_tracker); /* See comment on corresponding get in xs_setup_bc_tcp(): */ if (xprt->xpt_bc_xprt) xprt_put(xprt->xpt_bc_xprt); @@ -198,7 +198,7 @@ void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl, mutex_init(&xprt->xpt_mutex); spin_lock_init(&xprt->xpt_lock); set_bit(XPT_BUSY, &xprt->xpt_flags); - xprt->xpt_net = get_net(net); + xprt->xpt_net = get_net_track(net, &xprt->ns_tracker, GFP_ATOMIC); strcpy(xprt->xpt_remotebuf, "uninitialized"); } EXPORT_SYMBOL_GPL(svc_xprt_init); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index a02de2bddb28..5af484d6ba5e 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1835,7 +1835,7 @@ EXPORT_SYMBOL_GPL(xprt_alloc); void xprt_free(struct rpc_xprt *xprt) { - put_net(xprt->xprt_net); + put_net_track(xprt->xprt_net, &xprt->ns_tracker); xprt_free_all_slots(xprt); xprt_free_id(xprt); rpc_sysfs_xprt_destroy(xprt); @@ -2027,7 +2027,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) xprt_init_xid(xprt); - xprt->xprt_net = get_net(net); + xprt->xprt_net = get_net_track(net, &xprt->ns_tracker, GFP_KERNEL); } /** diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index b62565278fac..6a00c390547b 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -85,7 +85,7 @@ static int switchdev_deferred_enqueue(struct net_device *dev, { struct switchdev_deferred_item *dfitem; - dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC); + dfitem = kmalloc(struct_size(dfitem, data, data_len), GFP_ATOMIC); if (!dfitem) return -ENOMEM; dfitem->dev = dev; @@ -409,6 +409,27 @@ static int switchdev_lower_dev_walk(struct net_device *lower_dev, } static struct net_device * +switchdev_lower_dev_find_rcu(struct net_device *dev, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev)) +{ + struct switchdev_nested_priv switchdev_priv = { + .check_cb = check_cb, + .foreign_dev_check_cb = foreign_dev_check_cb, + .dev = dev, + .lower_dev = NULL, + }; + struct netdev_nested_priv priv = { + .data = &switchdev_priv, + }; + + netdev_walk_all_lower_dev_rcu(dev, switchdev_lower_dev_walk, &priv); + + return switchdev_priv.lower_dev; +} + +static struct net_device * switchdev_lower_dev_find(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), bool (*foreign_dev_check_cb)(const struct net_device *dev, @@ -424,7 +445,7 @@ switchdev_lower_dev_find(struct net_device *dev, .data = &switchdev_priv, }; - netdev_walk_all_lower_dev_rcu(dev, switchdev_lower_dev_walk, &priv); + netdev_walk_all_lower_dev(dev, switchdev_lower_dev_walk, &priv); return switchdev_priv.lower_dev; } @@ -451,7 +472,7 @@ static int __switchdev_handle_fdb_event_to_device(struct net_device *dev, return mod_cb(dev, orig_dev, event, info->ctx, fdb_info); if (netif_is_lag_master(dev)) { - if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb)) + if (!switchdev_lower_dev_find_rcu(dev, check_cb, foreign_dev_check_cb)) goto maybe_bridged_with_us; /* This is a LAG interface that we offload */ @@ -465,7 +486,7 @@ static int __switchdev_handle_fdb_event_to_device(struct net_device *dev, * towards a bridge device. */ if (netif_is_bridge_master(dev)) { - if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb)) + if (!switchdev_lower_dev_find_rcu(dev, check_cb, foreign_dev_check_cb)) return 0; /* This is a bridge interface that we offload */ @@ -478,8 +499,8 @@ static int __switchdev_handle_fdb_event_to_device(struct net_device *dev, * that we offload. */ if (!check_cb(lower_dev) && - !switchdev_lower_dev_find(lower_dev, check_cb, - foreign_dev_check_cb)) + !switchdev_lower_dev_find_rcu(lower_dev, check_cb, + foreign_dev_check_cb)) continue; err = __switchdev_handle_fdb_event_to_device(lower_dev, orig_dev, @@ -501,7 +522,7 @@ maybe_bridged_with_us: if (!br || !netif_is_bridge_master(br)) return 0; - if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb)) + if (!switchdev_lower_dev_find_rcu(br, check_cb, foreign_dev_check_cb)) return 0; return __switchdev_handle_fdb_event_to_device(br, orig_dev, event, fdb_info, @@ -536,13 +557,15 @@ EXPORT_SYMBOL_GPL(switchdev_handle_fdb_event_to_device); static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { struct switchdev_notifier_info *info = &port_obj_info->info; + struct net_device *br, *lower_dev; struct netlink_ext_ack *extack; - struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; @@ -566,15 +589,42 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, if (netif_is_bridge_master(lower_dev)) continue; + /* When searching for switchdev interfaces that are neighbors + * of foreign ones, and @dev is a bridge, do not recurse on the + * foreign interface again, it was already visited. + */ + if (foreign_dev_check_cb && !check_cb(lower_dev) && + !switchdev_lower_dev_find(lower_dev, check_cb, foreign_dev_check_cb)) + continue; + err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info, - check_cb, add_cb); + check_cb, foreign_dev_check_cb, + add_cb); if (err && err != -EOPNOTSUPP) return err; } - return err; + /* Event is neither on a bridge nor a LAG. Check whether it is on an + * interface that is in a bridge with us. + */ + if (!foreign_dev_check_cb) + return err; + + br = netdev_master_upper_dev_get(dev); + if (!br || !netif_is_bridge_master(br)) + return err; + + if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb)) + return err; + + return __switchdev_handle_port_obj_add(br, port_obj_info, check_cb, + foreign_dev_check_cb, add_cb); } +/* Pass through a port object addition, if @dev passes @check_cb, or replicate + * it towards all lower interfaces of @dev that pass @check_cb, if @dev is a + * bridge or a LAG. + */ int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), @@ -585,21 +635,46 @@ int switchdev_handle_port_obj_add(struct net_device *dev, int err; err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb, - add_cb); + NULL, add_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add); +/* Same as switchdev_handle_port_obj_add(), except if object is notified on a + * @dev that passes @foreign_dev_check_cb, it is replicated towards all devices + * that pass @check_cb and are in the same bridge as @dev. + */ +int switchdev_handle_port_obj_add_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack)) +{ + int err; + + err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb, + foreign_dev_check_cb, add_cb); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} +EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add_foreign); + static int __switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { struct switchdev_notifier_info *info = &port_obj_info->info; - struct net_device *lower_dev; + struct net_device *br, *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; @@ -621,15 +696,42 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, if (netif_is_bridge_master(lower_dev)) continue; + /* When searching for switchdev interfaces that are neighbors + * of foreign ones, and @dev is a bridge, do not recurse on the + * foreign interface again, it was already visited. + */ + if (foreign_dev_check_cb && !check_cb(lower_dev) && + !switchdev_lower_dev_find(lower_dev, check_cb, foreign_dev_check_cb)) + continue; + err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info, - check_cb, del_cb); + check_cb, foreign_dev_check_cb, + del_cb); if (err && err != -EOPNOTSUPP) return err; } - return err; + /* Event is neither on a bridge nor a LAG. Check whether it is on an + * interface that is in a bridge with us. + */ + if (!foreign_dev_check_cb) + return err; + + br = netdev_master_upper_dev_get(dev); + if (!br || !netif_is_bridge_master(br)) + return err; + + if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb)) + return err; + + return __switchdev_handle_port_obj_del(br, port_obj_info, check_cb, + foreign_dev_check_cb, del_cb); } +/* Pass through a port object deletion, if @dev passes @check_cb, or replicate + * it towards all lower interfaces of @dev that pass @check_cb, if @dev is a + * bridge or a LAG. + */ int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), @@ -639,13 +741,35 @@ int switchdev_handle_port_obj_del(struct net_device *dev, int err; err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb, - del_cb); + NULL, del_cb); if (err == -EOPNOTSUPP) err = 0; return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del); +/* Same as switchdev_handle_port_obj_del(), except if object is notified on a + * @dev that passes @foreign_dev_check_cb, it is replicated towards all devices + * that pass @check_cb and are in the same bridge as @dev. + */ +int switchdev_handle_port_obj_del_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj)) +{ + int err; + + err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb, + foreign_dev_check_cb, del_cb); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} +EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del_foreign); + static int __switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 64ae4c4c44f8..c5eec16213d7 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -226,14 +226,6 @@ static inline void msg_set_bits(struct tipc_msg *m, u32 w, m->hdr[w] |= htonl(val); } -static inline void msg_swap_words(struct tipc_msg *msg, u32 a, u32 b) -{ - u32 temp = msg->hdr[a]; - - msg->hdr[a] = msg->hdr[b]; - msg->hdr[b] = temp; -} - /* * Word 0 */ @@ -480,11 +472,6 @@ static inline void msg_incr_reroute_cnt(struct tipc_msg *m) msg_set_bits(m, 1, 21, 0xf, msg_reroute_cnt(m) + 1); } -static inline void msg_reset_reroute_cnt(struct tipc_msg *m) -{ - msg_set_bits(m, 1, 21, 0xf, 0); -} - static inline u32 msg_lookup_scope(struct tipc_msg *m) { return msg_bits(m, 1, 19, 0x3); @@ -800,11 +787,6 @@ static inline void msg_set_dest_domain(struct tipc_msg *m, u32 n) msg_set_word(m, 2, n); } -static inline u32 msg_bcgap_after(struct tipc_msg *m) -{ - return msg_bits(m, 2, 16, 0xffff); -} - static inline void msg_set_bcgap_after(struct tipc_msg *m, u32 n) { msg_set_bits(m, 2, 16, 0xffff, n); @@ -868,11 +850,6 @@ static inline void msg_set_next_sent(struct tipc_msg *m, u16 n) msg_set_bits(m, 4, 0, 0xffff, n); } -static inline void msg_set_long_msgno(struct tipc_msg *m, u32 n) -{ - msg_set_bits(m, 4, 0, 0xffff, n); -} - static inline u32 msg_bc_netid(struct tipc_msg *m) { return msg_word(m, 4); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index efc84845bb6b..0024a692f0f8 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1433,7 +1433,8 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (*zc && (out_iov || out_sg)) { if (out_iov) - n_sgout = iov_iter_npages(out_iov, INT_MAX) + 1; + n_sgout = 1 + + iov_iter_npages_cap(out_iov, INT_MAX, data_len); else n_sgout = sg_nents(out_sg); n_sgin = skb_nsg(skb, rxm->offset + prot->prepend_size, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c19569819866..3e0d6281fd1e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3240,49 +3240,58 @@ static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos) return sk; } -static struct sock *unix_next_socket(struct seq_file *seq, - struct sock *sk, - loff_t *pos) +static struct sock *unix_get_first(struct seq_file *seq, loff_t *pos) { unsigned long bucket = get_bucket(*pos); + struct sock *sk; - while (sk > (struct sock *)SEQ_START_TOKEN) { - sk = sk_next(sk); - if (!sk) - goto next_bucket; - if (sock_net(sk) == seq_file_net(seq)) - return sk; - } - - do { + while (bucket < ARRAY_SIZE(unix_socket_table)) { spin_lock(&unix_table_locks[bucket]); + sk = unix_from_bucket(seq, pos); if (sk) return sk; -next_bucket: - spin_unlock(&unix_table_locks[bucket++]); - *pos = set_bucket_offset(bucket, 1); - } while (bucket < ARRAY_SIZE(unix_socket_table)); + spin_unlock(&unix_table_locks[bucket]); + + *pos = set_bucket_offset(++bucket, 1); + } return NULL; } +static struct sock *unix_get_next(struct seq_file *seq, struct sock *sk, + loff_t *pos) +{ + unsigned long bucket = get_bucket(*pos); + + for (sk = sk_next(sk); sk; sk = sk_next(sk)) + if (sock_net(sk) == seq_file_net(seq)) + return sk; + + spin_unlock(&unix_table_locks[bucket]); + + *pos = set_bucket_offset(++bucket, 1); + + return unix_get_first(seq, pos); +} + static void *unix_seq_start(struct seq_file *seq, loff_t *pos) { if (!*pos) return SEQ_START_TOKEN; - if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table)) - return NULL; - - return unix_next_socket(seq, NULL, pos); + return unix_get_first(seq, pos); } static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; - return unix_next_socket(seq, v, pos); + + if (v == SEQ_START_TOKEN) + return unix_get_first(seq, pos); + + return unix_get_next(seq, v, pos); } static void unix_seq_stop(struct seq_file *seq, void *v) @@ -3347,6 +3356,15 @@ static const struct seq_operations unix_seq_ops = { }; #if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) +struct bpf_unix_iter_state { + struct seq_net_private p; + unsigned int cur_sk; + unsigned int end_sk; + unsigned int max_sk; + struct sock **batch; + bool st_bucket_done; +}; + struct bpf_iter__unix { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct unix_sock *, unix_sk); @@ -3365,24 +3383,156 @@ static int unix_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, return bpf_iter_run_prog(prog, &ctx); } +static int bpf_iter_unix_hold_batch(struct seq_file *seq, struct sock *start_sk) + +{ + struct bpf_unix_iter_state *iter = seq->private; + unsigned int expected = 1; + struct sock *sk; + + sock_hold(start_sk); + iter->batch[iter->end_sk++] = start_sk; + + for (sk = sk_next(start_sk); sk; sk = sk_next(sk)) { + if (sock_net(sk) != seq_file_net(seq)) + continue; + + if (iter->end_sk < iter->max_sk) { + sock_hold(sk); + iter->batch[iter->end_sk++] = sk; + } + + expected++; + } + + spin_unlock(&unix_table_locks[start_sk->sk_hash]); + + return expected; +} + +static void bpf_iter_unix_put_batch(struct bpf_unix_iter_state *iter) +{ + while (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); +} + +static int bpf_iter_unix_realloc_batch(struct bpf_unix_iter_state *iter, + unsigned int new_batch_sz) +{ + struct sock **new_batch; + + new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, + GFP_USER | __GFP_NOWARN); + if (!new_batch) + return -ENOMEM; + + bpf_iter_unix_put_batch(iter); + kvfree(iter->batch); + iter->batch = new_batch; + iter->max_sk = new_batch_sz; + + return 0; +} + +static struct sock *bpf_iter_unix_batch(struct seq_file *seq, + loff_t *pos) +{ + struct bpf_unix_iter_state *iter = seq->private; + unsigned int expected; + bool resized = false; + struct sock *sk; + + if (iter->st_bucket_done) + *pos = set_bucket_offset(get_bucket(*pos) + 1, 1); + +again: + /* Get a new batch */ + iter->cur_sk = 0; + iter->end_sk = 0; + + sk = unix_get_first(seq, pos); + if (!sk) + return NULL; /* Done */ + + expected = bpf_iter_unix_hold_batch(seq, sk); + + if (iter->end_sk == expected) { + iter->st_bucket_done = true; + return sk; + } + + if (!resized && !bpf_iter_unix_realloc_batch(iter, expected * 3 / 2)) { + resized = true; + goto again; + } + + return sk; +} + +static void *bpf_iter_unix_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (!*pos) + return SEQ_START_TOKEN; + + /* bpf iter does not support lseek, so it always + * continue from where it was stop()-ped. + */ + return bpf_iter_unix_batch(seq, pos); +} + +static void *bpf_iter_unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_unix_iter_state *iter = seq->private; + struct sock *sk; + + /* Whenever seq_next() is called, the iter->cur_sk is + * done with seq_show(), so advance to the next sk in + * the batch. + */ + if (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); + + ++*pos; + + if (iter->cur_sk < iter->end_sk) + sk = iter->batch[iter->cur_sk]; + else + sk = bpf_iter_unix_batch(seq, pos); + + return sk; +} + static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; + bool slow; + int ret; if (v == SEQ_START_TOKEN) return 0; + slow = lock_sock_fast(sk); + + if (unlikely(sk_unhashed(sk))) { + ret = SEQ_SKIP; + goto unlock; + } + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); meta.seq = seq; prog = bpf_iter_get_info(&meta, false); - return unix_prog_seq_show(prog, &meta, v, uid); + ret = unix_prog_seq_show(prog, &meta, v, uid); +unlock: + unlock_sock_fast(sk, slow); + return ret; } static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) { + struct bpf_unix_iter_state *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; @@ -3393,12 +3543,13 @@ static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) (void)unix_prog_seq_show(prog, &meta, v, 0); } - unix_seq_stop(seq, v); + if (iter->cur_sk < iter->end_sk) + bpf_iter_unix_put_batch(iter); } static const struct seq_operations bpf_iter_unix_seq_ops = { - .start = unix_seq_start, - .next = unix_seq_next, + .start = bpf_iter_unix_seq_start, + .next = bpf_iter_unix_seq_next, .stop = bpf_iter_unix_seq_stop, .show = bpf_iter_unix_seq_show, }; @@ -3447,13 +3598,55 @@ static struct pernet_operations unix_net_ops = { DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta, struct unix_sock *unix_sk, uid_t uid) +#define INIT_BATCH_SZ 16 + +static int bpf_iter_init_unix(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct bpf_unix_iter_state *iter = priv_data; + int err; + + err = bpf_iter_init_seq_net(priv_data, aux); + if (err) + return err; + + err = bpf_iter_unix_realloc_batch(iter, INIT_BATCH_SZ); + if (err) { + bpf_iter_fini_seq_net(priv_data); + return err; + } + + return 0; +} + +static void bpf_iter_fini_unix(void *priv_data) +{ + struct bpf_unix_iter_state *iter = priv_data; + + bpf_iter_fini_seq_net(priv_data); + kvfree(iter->batch); +} + static const struct bpf_iter_seq_info unix_seq_info = { .seq_ops = &bpf_iter_unix_seq_ops, - .init_seq_private = bpf_iter_init_seq_net, - .fini_seq_private = bpf_iter_fini_seq_net, - .seq_priv_size = sizeof(struct seq_net_private), + .init_seq_private = bpf_iter_init_unix, + .fini_seq_private = bpf_iter_fini_unix, + .seq_priv_size = sizeof(struct bpf_unix_iter_state), }; +static const struct bpf_func_proto * +bpf_iter_unix_get_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_setsockopt: + return &bpf_sk_setsockopt_proto; + case BPF_FUNC_getsockopt: + return &bpf_sk_getsockopt_proto; + default: + return NULL; + } +} + static struct bpf_iter_reg unix_reg_info = { .target = "unix", .ctx_arg_info_size = 1, @@ -3461,6 +3654,7 @@ static struct bpf_iter_reg unix_reg_info = { { offsetof(struct bpf_iter__unix, unix_sk), PTR_TO_BTF_ID_OR_NULL }, }, + .get_func_proto = bpf_iter_unix_get_func_proto, .seq_info = &unix_seq_info, }; diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 328cf54bda82..2bc647720cda 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -2,8 +2,6 @@ /* * Copyright (C) 2018 - 2021 Intel Corporation */ -#ifndef __PMSR_H -#define __PMSR_H #include <net/cfg80211.h> #include "core.h" #include "nl80211.h" @@ -661,5 +659,3 @@ void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid) } spin_unlock_bh(&wdev->pmsr_lock); } - -#endif /* __PMSR_H */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b888522f133b..b2fdac96bab0 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -700,8 +700,12 @@ static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap, for (i = 0; i < request->n_ssids; i++) { /* wildcard ssid in the scan request */ - if (!request->ssids[i].ssid_len) + if (!request->ssids[i].ssid_len) { + if (ap->multi_bss && !ap->transmitted_bssid) + continue; + return true; + } if (ap->ssid_len && ap->ssid_len == request->ssids[i].ssid_len) { @@ -827,6 +831,9 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) !cfg80211_find_ssid_match(ap, request)) continue; + if (!request->n_ssids && ap->multi_bss && !ap->transmitted_bssid) + continue; + cfg80211_scan_req_add_chan(request, chan, true); memcpy(scan_6ghz_params->bssid, ap->bssid, ETH_ALEN); scan_6ghz_params->short_ssid = ap->short_ssid; diff --git a/net/wireless/util.c b/net/wireless/util.c index 41ea65deb6e1..e02f1702806e 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> @@ -634,12 +634,14 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, if (likely((!is_amsdu && ether_addr_equal(payload.hdr, rfc1042_header) && tmp.h_proto != htons(ETH_P_AARP) && tmp.h_proto != htons(ETH_P_IPX)) || - ether_addr_equal(payload.hdr, bridge_tunnel_header))) + ether_addr_equal(payload.hdr, bridge_tunnel_header))) { /* remove RFC1042 or Bridge-Tunnel encapsulation and * replace EtherType */ hdrlen += ETH_ALEN + 2; - else + skb_postpull_rcsum(skb, &payload, ETH_ALEN + 2); + } else { tmp.h_proto = htons(skb->len - hdrlen); + } pskb_pull(skb, hdrlen); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 28ef3f4465ae..2abd64e4d589 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -343,9 +343,9 @@ out: } EXPORT_SYMBOL(xsk_tx_peek_desc); -static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, struct xdp_desc *descs, - u32 max_entries) +static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, u32 max_entries) { + struct xdp_desc *descs = pool->tx_descs; u32 nb_pkts = 0; while (nb_pkts < max_entries && xsk_tx_peek_desc(pool, &descs[nb_pkts])) @@ -355,8 +355,7 @@ static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, struct xdp_d return nb_pkts; } -u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *descs, - u32 max_entries) +u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries) { struct xdp_sock *xs; u32 nb_pkts; @@ -365,7 +364,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc * if (!list_is_singular(&pool->xsk_tx_list)) { /* Fallback to the non-batched version */ rcu_read_unlock(); - return xsk_tx_peek_release_fallback(pool, descs, max_entries); + return xsk_tx_peek_release_fallback(pool, max_entries); } xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list); @@ -374,7 +373,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc * goto out; } - nb_pkts = xskq_cons_peek_desc_batch(xs->tx, descs, pool, max_entries); + nb_pkts = xskq_cons_peek_desc_batch(xs->tx, pool, max_entries); if (!nb_pkts) { xs->tx->queue_empty_descs++; goto out; @@ -386,7 +385,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc * * packets. This avoids having to implement any buffering in * the Tx path. */ - nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, descs, nb_pkts); + nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, pool->tx_descs, nb_pkts); if (!nb_pkts) goto out; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index fd39bb660ebc..b34fca6ada86 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -37,6 +37,7 @@ void xp_destroy(struct xsk_buff_pool *pool) if (!pool) return; + kvfree(pool->tx_descs); kvfree(pool->heads); kvfree(pool); } @@ -58,6 +59,12 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, if (!pool->heads) goto out; + if (xs->tx) { + pool->tx_descs = kcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL); + if (!pool->tx_descs) + goto out; + } + pool->chunk_mask = ~((u64)umem->chunk_size - 1); pool->addrs_cnt = umem->size; pool->heads_cnt = umem->chunks; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index e9aa2c236356..801cda5d1938 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -205,11 +205,11 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q, return false; } -static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, - struct xdp_desc *descs, - struct xsk_buff_pool *pool, u32 max) +static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, + u32 max) { u32 cached_cons = q->cached_cons, nb_entries = 0; + struct xdp_desc *descs = pool->tx_descs; while (cached_cons != q->cached_prod && nb_entries < max) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; @@ -282,12 +282,12 @@ static inline bool xskq_cons_peek_desc(struct xsk_queue *q, return xskq_cons_read_desc(q, desc, pool); } -static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xdp_desc *descs, - struct xsk_buff_pool *pool, u32 max) +static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, + u32 max) { u32 entries = xskq_cons_nb_entries(q, max); - return xskq_cons_read_desc_batch(q, descs, pool, entries); + return xskq_cons_read_desc_batch(q, pool, entries); } /* To improve performance in the xskq_cons_release functions, only update local state here. @@ -304,13 +304,6 @@ static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt) q->cached_cons += cnt; } -static inline bool xskq_cons_is_full(struct xsk_queue *q) -{ - /* No barriers needed since data is not accessed */ - return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer) == - q->nentries; -} - static inline u32 xskq_cons_present_entries(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index 319fd31522f3..e69651a6902f 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -413,7 +413,7 @@ static void fixup_map(struct bpf_object *obj) for (i = 0; i < NR_TESTS; i++) { if (!strcmp(test_map_names[i], name) && (check_test_flags(i))) { - bpf_map__resize(map, num_map_entries); + bpf_map__set_max_entries(map, num_map_entries); continue; } } diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index 8675fa5273df..631f0cabe139 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -26,12 +26,12 @@ static void int_exit(int sig) { __u32 curr_prog_id = 0; - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given interface\n"); else @@ -79,13 +79,11 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); const char *optstr = "FSN"; int prog_fd, map_fd, opt; + struct bpf_program *prog; struct bpf_object *obj; struct bpf_map *map; char filename[256]; @@ -123,11 +121,19 @@ int main(int argc, char **argv) } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) + return 1; + + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + err = bpf_object__load(obj); + if (err) return 1; + prog_fd = bpf_program__fd(prog); + map = bpf_object__next_map(obj, NULL); if (!map) { printf("finding a map in obj file failed\n"); @@ -143,7 +149,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { printf("link set xdp fd failed\n"); return 1; } diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index a70b094c8ec5..b3f6e49676ed 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -34,12 +34,12 @@ static void int_exit(int sig) __u32 curr_prog_id = 0; if (ifindex > -1) { - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given iface\n"); else @@ -82,15 +82,13 @@ static void usage(const char *cmd) int main(int argc, char **argv) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; unsigned char opt_flags[256] = {}; const char *optstr = "i:T:P:SNFh"; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); unsigned int kill_after_s = 0; int i, prog_fd, map_fd, opt; + struct bpf_program *prog; struct bpf_object *obj; __u32 max_pckt_size = 0; __u32 key = 0; @@ -148,11 +146,20 @@ int main(int argc, char **argv) } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) return 1; + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); + + err = bpf_object__load(obj); + if (err) + return 1; + + prog_fd = bpf_program__fd(prog); + /* static global var 'max_pcktsz' is accessible from .data section */ if (max_pckt_size) { map_fd = bpf_object__find_map_fd_by_name(obj, "xdp_adju.data"); @@ -173,7 +180,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { printf("link set xdp fd failed\n"); return 1; } diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c index 4ad896782f77..1828487bae9a 100644 --- a/samples/bpf/xdp_fwd_user.c +++ b/samples/bpf/xdp_fwd_user.c @@ -33,7 +33,7 @@ static int do_attach(int idx, int prog_fd, int map_fd, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, prog_fd, xdp_flags); + err = bpf_xdp_attach(idx, prog_fd, xdp_flags, NULL); if (err < 0) { printf("ERROR: failed to attach program to %s\n", name); return err; @@ -51,7 +51,7 @@ static int do_detach(int idx, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, -1, xdp_flags); + err = bpf_xdp_detach(idx, xdp_flags, NULL); if (err < 0) printf("ERROR: failed to detach program from %s\n", name); @@ -75,14 +75,11 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; const char *prog_name = "xdp_fwd"; struct bpf_program *prog = NULL; struct bpf_program *pos; const char *sec_name; - int prog_fd, map_fd = -1; + int prog_fd = -1, map_fd = -1; char filename[PATH_MAX]; struct bpf_object *obj; int opt, i, idx, err; @@ -119,7 +116,6 @@ int main(int argc, char **argv) if (attach) { snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; if (access(filename, O_RDONLY) < 0) { printf("error accessing file %s: %s\n", @@ -127,7 +123,14 @@ int main(int argc, char **argv) return 1; } - err = bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) + return 1; + + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); + + err = bpf_object__load(obj); if (err) { printf("Does kernel support devmap lookup?\n"); /* If not, the error message will be: diff --git a/samples/bpf/xdp_redirect_cpu.bpf.c b/samples/bpf/xdp_redirect_cpu.bpf.c index 25e3a405375f..87c54bfdbb70 100644 --- a/samples/bpf/xdp_redirect_cpu.bpf.c +++ b/samples/bpf/xdp_redirect_cpu.bpf.c @@ -491,7 +491,7 @@ int xdp_prognum5_lb_hash_ip_pairs(struct xdp_md *ctx) return bpf_redirect_map(&cpu_map, cpu_dest, 0); } -SEC("xdp_cpumap/redirect") +SEC("xdp/cpumap") int xdp_redirect_cpu_devmap(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -507,19 +507,19 @@ int xdp_redirect_cpu_devmap(struct xdp_md *ctx) return bpf_redirect_map(&tx_port, 0, 0); } -SEC("xdp_cpumap/pass") +SEC("xdp/cpumap") int xdp_redirect_cpu_pass(struct xdp_md *ctx) { return XDP_PASS; } -SEC("xdp_cpumap/drop") +SEC("xdp/cpumap") int xdp_redirect_cpu_drop(struct xdp_md *ctx) { return XDP_DROP; } -SEC("xdp_devmap/egress") +SEC("xdp/devmap") int xdp_redirect_egress_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index a81704d3317b..5f74a70a9021 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -70,7 +70,7 @@ static void print_avail_progs(struct bpf_object *obj) printf(" Programs to be used for -p/--progname:\n"); bpf_object__for_each_program(pos, obj) { - if (bpf_program__is_xdp(pos)) { + if (bpf_program__type(pos) == BPF_PROG_TYPE_XDP) { if (!strncmp(bpf_program__name(pos), "xdp_prognum", sizeof("xdp_prognum") - 1)) printf(" %s\n", bpf_program__name(pos)); diff --git a/samples/bpf/xdp_redirect_map.bpf.c b/samples/bpf/xdp_redirect_map.bpf.c index 59efd656e1b2..415bac1758e3 100644 --- a/samples/bpf/xdp_redirect_map.bpf.c +++ b/samples/bpf/xdp_redirect_map.bpf.c @@ -68,7 +68,7 @@ int xdp_redirect_map_native(struct xdp_md *ctx) return xdp_redirect_map(ctx, &tx_port_native); } -SEC("xdp_devmap/egress") +SEC("xdp/devmap") int xdp_redirect_map_egress(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/samples/bpf/xdp_redirect_map_multi.bpf.c b/samples/bpf/xdp_redirect_map_multi.bpf.c index bb0a5a3bfcf0..8b2fd4ec2c76 100644 --- a/samples/bpf/xdp_redirect_map_multi.bpf.c +++ b/samples/bpf/xdp_redirect_map_multi.bpf.c @@ -53,7 +53,7 @@ int xdp_redirect_map_native(struct xdp_md *ctx) return xdp_redirect_map(ctx, &forward_map_native); } -SEC("xdp_devmap/egress") +SEC("xdp/devmap") int xdp_devmap_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index cfaf7e50e431..6dae87d83e1c 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -43,13 +43,13 @@ static void int_exit(int sig) int i = 0; for (i = 0; i < total_ifindex; i++) { - if (bpf_get_link_xdp_id(ifindex_list[i], &prog_id, flags)) { - printf("bpf_get_link_xdp_id on iface %d failed\n", + if (bpf_xdp_query_id(ifindex_list[i], flags, &prog_id)) { + printf("bpf_xdp_query_id on iface %d failed\n", ifindex_list[i]); exit(1); } if (prog_id_list[i] == prog_id) - bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_xdp_detach(ifindex_list[i], flags, NULL); else if (!prog_id) printf("couldn't find a prog id on iface %d\n", ifindex_list[i]); @@ -640,12 +640,10 @@ static void usage(const char *prog) int main(int ac, char **argv) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); const char *optstr = "SF"; + struct bpf_program *prog; struct bpf_object *obj; char filename[256]; char **ifname_list; @@ -653,7 +651,6 @@ int main(int ac, char **argv) int err, i = 1; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; total_ifindex = ac - 1; ifname_list = (argv + 1); @@ -684,14 +681,20 @@ int main(int ac, char **argv) return 1; } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) return 1; + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); + printf("\n******************loading bpf file*********************\n"); - if (!prog_fd) { - printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + err = bpf_object__load(obj); + if (err) { + printf("bpf_object__load(): %s\n", strerror(errno)); return 1; } + prog_fd = bpf_program__fd(prog); lpm_map_fd = bpf_object__find_map_fd_by_name(obj, "lpm_map"); rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); @@ -716,12 +719,12 @@ int main(int ac, char **argv) } prog_id_list = (__u32 *)calloc(total_ifindex, sizeof(__u32 *)); for (i = 0; i < total_ifindex; i++) { - if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd, flags) < 0) { + if (bpf_xdp_attach(ifindex_list[i], prog_fd, flags, NULL) < 0) { printf("link set xdp fd failed\n"); int recovery_index = i; for (i = 0; i < recovery_index; i++) - bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_xdp_detach(ifindex_list[i], flags, NULL); return 1; } diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 74a2926eba08..f2d90cba5164 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -62,15 +62,15 @@ static void int_exit(int sig) __u32 curr_prog_id = 0; if (ifindex > -1) { - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(EXIT_FAIL); } if (prog_id == curr_prog_id) { fprintf(stderr, "Interrupted: Removing XDP program on ifindex:%d device:%s\n", ifindex, ifname); - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); } else if (!curr_prog_id) { printf("couldn't find a prog id on a given iface\n"); } else { @@ -209,7 +209,7 @@ static struct datarec *alloc_record_per_cpu(void) static struct record *alloc_record_per_rxq(void) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); struct record *array; array = calloc(nr_rxqs, sizeof(struct record)); @@ -222,7 +222,7 @@ static struct record *alloc_record_per_rxq(void) static struct stats_record *alloc_stats_record(void) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); struct stats_record *rec; int i; @@ -241,7 +241,7 @@ static struct stats_record *alloc_stats_record(void) static void free_stats_record(struct stats_record *r) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); int i; for (i = 0; i < nr_rxqs; i++) @@ -289,7 +289,7 @@ static void stats_collect(struct stats_record *rec) map_collect_percpu(fd, 0, &rec->stats); fd = bpf_map__fd(rx_queue_index_map); - max_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + max_rxqs = bpf_map__max_entries(rx_queue_index_map); for (i = 0; i < max_rxqs; i++) map_collect_percpu(fd, i, &rec->rxq[i]); } @@ -335,7 +335,7 @@ static void stats_print(struct stats_record *stats_rec, struct stats_record *stats_prev, int action, __u32 cfg_opt) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); unsigned int nr_cpus = bpf_num_possible_cpus(); double pps = 0, err = 0; struct record *rec, *prev; @@ -450,14 +450,12 @@ static void stats_poll(int interval, int action, __u32 cfg_opt) int main(int argc, char **argv) { __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */ - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); int prog_fd, map_fd, opt, err; bool use_separators = true; struct config cfg = { 0 }; + struct bpf_program *prog; struct bpf_object *obj; struct bpf_map *map; char filename[256]; @@ -471,11 +469,19 @@ int main(int argc, char **argv) char *action_str = NULL; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) return EXIT_FAIL; + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); + + err = bpf_object__load(obj); + if (err) + return EXIT_FAIL; + prog_fd = bpf_program__fd(prog); + map = bpf_object__find_map_by_name(obj, "config_map"); stats_global_map = bpf_object__find_map_by_name(obj, "stats_global_map"); rx_queue_index_map = bpf_object__find_map_by_name(obj, "rx_queue_index_map"); @@ -582,7 +588,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { fprintf(stderr, "link set xdp fd failed\n"); return EXIT_FAIL_XDP; } diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index 587eacb49103..0a2b3e997aed 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -30,7 +30,7 @@ static int do_attach(int idx, int fd, const char *name) __u32 info_len = sizeof(info); int err; - err = bpf_set_link_xdp_fd(idx, fd, xdp_flags); + err = bpf_xdp_attach(idx, fd, xdp_flags, NULL); if (err < 0) { printf("ERROR: failed to attach program to %s\n", name); return err; @@ -51,13 +51,13 @@ static int do_detach(int idx, const char *name) __u32 curr_prog_id = 0; int err = 0; - err = bpf_get_link_xdp_id(idx, &curr_prog_id, xdp_flags); + err = bpf_xdp_query_id(idx, xdp_flags, &curr_prog_id); if (err) { - printf("bpf_get_link_xdp_id failed\n"); + printf("bpf_xdp_query_id failed\n"); return err; } if (prog_id == curr_prog_id) { - err = bpf_set_link_xdp_fd(idx, -1, xdp_flags); + err = bpf_xdp_detach(idx, xdp_flags, NULL); if (err < 0) printf("ERROR: failed to detach prog from %s\n", name); } else if (!curr_prog_id) { diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c index 8740838e7767..c4332d068b91 100644 --- a/samples/bpf/xdp_sample_user.c +++ b/samples/bpf/xdp_sample_user.c @@ -1218,7 +1218,7 @@ int sample_setup_maps(struct bpf_map **maps) default: return -EINVAL; } - if (bpf_map__resize(sample_map[i], sample_map_count[i]) < 0) + if (bpf_map__set_max_entries(sample_map[i], sample_map_count[i]) < 0) return -errno; } sample_map[MAP_DEVMAP_XMIT_MULTI] = maps[MAP_DEVMAP_XMIT_MULTI]; @@ -1265,7 +1265,7 @@ static int __sample_remove_xdp(int ifindex, __u32 prog_id, int xdp_flags) int ret; if (prog_id) { - ret = bpf_get_link_xdp_id(ifindex, &cur_prog_id, xdp_flags); + ret = bpf_xdp_query_id(ifindex, xdp_flags, &cur_prog_id); if (ret < 0) return -errno; @@ -1278,7 +1278,7 @@ static int __sample_remove_xdp(int ifindex, __u32 prog_id, int xdp_flags) } } - return bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + return bpf_xdp_detach(ifindex, xdp_flags, NULL); } int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, @@ -1295,8 +1295,7 @@ int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, xdp_flags |= !force ? XDP_FLAGS_UPDATE_IF_NOEXIST : 0; xdp_flags |= generic ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; - ret = bpf_set_link_xdp_fd(ifindex, bpf_program__fd(xdp_prog), - xdp_flags); + ret = bpf_xdp_attach(ifindex, bpf_program__fd(xdp_prog), xdp_flags, NULL); if (ret < 0) { ret = -errno; fprintf(stderr, @@ -1308,7 +1307,7 @@ int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, return ret; } - ret = bpf_get_link_xdp_id(ifindex, &prog_id, xdp_flags); + ret = bpf_xdp_query_id(ifindex, xdp_flags, &prog_id); if (ret < 0) { ret = -errno; fprintf(stderr, diff --git a/samples/bpf/xdp_sample_user.h b/samples/bpf/xdp_sample_user.h index 5f44b877ecf5..f45051679977 100644 --- a/samples/bpf/xdp_sample_user.h +++ b/samples/bpf/xdp_sample_user.h @@ -61,7 +61,7 @@ static inline char *safe_strncpy(char *dst, const char *src, size_t size) #define __attach_tp(name) \ ({ \ - if (!bpf_program__is_tracing(skel->progs.name)) \ + if (bpf_program__type(skel->progs.name) != BPF_PROG_TYPE_TRACING)\ return -EINVAL; \ skel->links.name = bpf_program__attach(skel->progs.name); \ if (!skel->links.name) \ diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index 1d4f305d02aa..2e811e4331cc 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -32,12 +32,12 @@ static void int_exit(int sig) __u32 curr_prog_id = 0; if (ifindex > -1) { - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given iface\n"); else @@ -152,9 +152,6 @@ static int parse_ports(const char *port_str, int *min_port, int *max_port) int main(int argc, char **argv) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; int min_port = 0, max_port = 0, vip2tnl_map_fd; const char *optstr = "i:a:p:s:d:m:T:P:FSNh"; unsigned char opt_flags[256] = {}; @@ -162,6 +159,7 @@ int main(int argc, char **argv) __u32 info_len = sizeof(info); unsigned int kill_after_s = 0; struct iptnl_info tnl = {}; + struct bpf_program *prog; struct bpf_object *obj; struct vip vip = {}; char filename[256]; @@ -259,15 +257,20 @@ int main(int argc, char **argv) } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) return 1; - if (!prog_fd) { - printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); + + err = bpf_object__load(obj); + if (err) { + printf("bpf_object__load(): %s\n", strerror(errno)); return 1; } + prog_fd = bpf_program__fd(prog); rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); vip2tnl_map_fd = bpf_object__find_map_fd_by_name(obj, "vip2tnl"); @@ -288,7 +291,7 @@ int main(int argc, char **argv) } } - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { printf("link set xdp fd failed\n"); return 1; } @@ -302,7 +305,7 @@ int main(int argc, char **argv) poll_stats(kill_after_s); - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); return 0; } diff --git a/samples/bpf/xdpsock_ctrl_proc.c b/samples/bpf/xdpsock_ctrl_proc.c index cc4408797ab7..28b5f2a9fa08 100644 --- a/samples/bpf/xdpsock_ctrl_proc.c +++ b/samples/bpf/xdpsock_ctrl_proc.c @@ -173,7 +173,7 @@ main(int argc, char **argv) unlink(SOCKET_NAME); /* Unset fd for given ifindex */ - err = bpf_set_link_xdp_fd(ifindex, -1, 0); + err = bpf_xdp_detach(ifindex, 0, NULL); if (err) { fprintf(stderr, "Error when unsetting bpf prog_fd for ifindex(%d)\n", ifindex); return err; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index aa50864e4415..19288a2bbc75 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -571,13 +571,13 @@ static void remove_xdp_program(void) { u32 curr_prog_id = 0; - if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(opt_ifindex, opt_xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(EXIT_FAILURE); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + bpf_xdp_detach(opt_ifindex, opt_xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given interface\n"); else @@ -1027,7 +1027,7 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, if (ret) exit_with_error(-ret); - ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags); + ret = bpf_xdp_query_id(opt_ifindex, opt_xdp_flags, &prog_id); if (ret) exit_with_error(-ret); @@ -1760,7 +1760,7 @@ static void load_xdp_program(char **argv, struct bpf_object **obj) exit(EXIT_FAILURE); } - if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) { + if (bpf_xdp_attach(opt_ifindex, prog_fd, opt_xdp_flags, NULL) < 0) { fprintf(stderr, "ERROR: link set xdp fd failed\n"); exit(EXIT_FAILURE); } diff --git a/samples/bpf/xsk_fwd.c b/samples/bpf/xsk_fwd.c index 52e7c4ffd228..2220509588a0 100644 --- a/samples/bpf/xsk_fwd.c +++ b/samples/bpf/xsk_fwd.c @@ -974,8 +974,8 @@ static void remove_xdp_program(void) int i; for (i = 0 ; i < n_ports; i++) - bpf_set_link_xdp_fd(if_nametoindex(port_params[i].iface), -1, - port_params[i].xsk_cfg.xdp_flags); + bpf_xdp_detach(if_nametoindex(port_params[i].iface), + port_params[i].xsk_cfg.xdp_flags, NULL); } int main(int argc, char **argv) diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index a6403ddf5de7..096625242475 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -87,21 +87,25 @@ class HeaderParser(object): self.line = '' self.helpers = [] self.commands = [] + self.desc_unique_helpers = set() + self.define_unique_helpers = [] + self.desc_syscalls = [] + self.enum_syscalls = [] def parse_element(self): proto = self.parse_symbol() - desc = self.parse_desc() - ret = self.parse_ret() + desc = self.parse_desc(proto) + ret = self.parse_ret(proto) return APIElement(proto=proto, desc=desc, ret=ret) def parse_helper(self): proto = self.parse_proto() - desc = self.parse_desc() - ret = self.parse_ret() + desc = self.parse_desc(proto) + ret = self.parse_ret(proto) return Helper(proto=proto, desc=desc, ret=ret) def parse_symbol(self): - p = re.compile(' \* ?(.+)$') + p = re.compile(' \* ?(BPF\w+)$') capture = p.match(self.line) if not capture: raise NoSyscallCommandFound @@ -127,16 +131,15 @@ class HeaderParser(object): self.line = self.reader.readline() return capture.group(1) - def parse_desc(self): + def parse_desc(self, proto): p = re.compile(' \* ?(?:\t| {5,8})Description$') capture = p.match(self.line) if not capture: - # Helper can have empty description and we might be parsing another - # attribute: return but do not consume. - return '' + raise Exception("No description section found for " + proto) # Description can be several lines, some of them possibly empty, and it # stops when another subsection title is met. desc = '' + desc_present = False while True: self.line = self.reader.readline() if self.line == ' *\n': @@ -145,21 +148,24 @@ class HeaderParser(object): p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)') capture = p.match(self.line) if capture: + desc_present = True desc += capture.group(1) + '\n' else: break + + if not desc_present: + raise Exception("No description found for " + proto) return desc - def parse_ret(self): + def parse_ret(self, proto): p = re.compile(' \* ?(?:\t| {5,8})Return$') capture = p.match(self.line) if not capture: - # Helper can have empty retval and we might be parsing another - # attribute: return but do not consume. - return '' + raise Exception("No return section found for " + proto) # Return value description can be several lines, some of them possibly # empty, and it stops when another subsection title is met. ret = '' + ret_present = False while True: self.line = self.reader.readline() if self.line == ' *\n': @@ -168,44 +174,101 @@ class HeaderParser(object): p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)') capture = p.match(self.line) if capture: + ret_present = True ret += capture.group(1) + '\n' else: break + + if not ret_present: + raise Exception("No return found for " + proto) return ret - def seek_to(self, target, help_message): + def seek_to(self, target, help_message, discard_lines = 1): self.reader.seek(0) offset = self.reader.read().find(target) if offset == -1: raise Exception(help_message) self.reader.seek(offset) self.reader.readline() - self.reader.readline() + for _ in range(discard_lines): + self.reader.readline() self.line = self.reader.readline() - def parse_syscall(self): + def parse_desc_syscall(self): self.seek_to('* DOC: eBPF Syscall Commands', 'Could not find start of eBPF syscall descriptions list') while True: try: command = self.parse_element() self.commands.append(command) + self.desc_syscalls.append(command.proto) + except NoSyscallCommandFound: break - def parse_helpers(self): + def parse_enum_syscall(self): + self.seek_to('enum bpf_cmd {', + 'Could not find start of bpf_cmd enum', 0) + # Searches for either one or more BPF\w+ enums + bpf_p = re.compile('\s*(BPF\w+)+') + # Searches for an enum entry assigned to another entry, + # for e.g. BPF_PROG_RUN = BPF_PROG_TEST_RUN, which is + # not documented hence should be skipped in check to + # determine if the right number of syscalls are documented + assign_p = re.compile('\s*(BPF\w+)\s*=\s*(BPF\w+)') + bpf_cmd_str = '' + while True: + capture = assign_p.match(self.line) + if capture: + # Skip line if an enum entry is assigned to another entry + self.line = self.reader.readline() + continue + capture = bpf_p.match(self.line) + if capture: + bpf_cmd_str += self.line + else: + break + self.line = self.reader.readline() + # Find the number of occurences of BPF\w+ + self.enum_syscalls = re.findall('(BPF\w+)+', bpf_cmd_str) + + def parse_desc_helpers(self): self.seek_to('* Start of BPF helper function descriptions:', 'Could not find start of eBPF helper descriptions list') while True: try: helper = self.parse_helper() self.helpers.append(helper) + proto = helper.proto_break_down() + self.desc_unique_helpers.add(proto['name']) except NoHelperFound: break + def parse_define_helpers(self): + # Parse the number of FN(...) in #define __BPF_FUNC_MAPPER to compare + # later with the number of unique function names present in description. + # Note: seek_to(..) discards the first line below the target search text, + # resulting in FN(unspec) being skipped and not added to self.define_unique_helpers. + self.seek_to('#define __BPF_FUNC_MAPPER(FN)', + 'Could not find start of eBPF helper definition list') + # Searches for either one or more FN(\w+) defines or a backslash for newline + p = re.compile('\s*(FN\(\w+\))+|\\\\') + fn_defines_str = '' + while True: + capture = p.match(self.line) + if capture: + fn_defines_str += self.line + else: + break + self.line = self.reader.readline() + # Find the number of occurences of FN(\w+) + self.define_unique_helpers = re.findall('FN\(\w+\)', fn_defines_str) + def run(self): - self.parse_syscall() - self.parse_helpers() + self.parse_desc_syscall() + self.parse_enum_syscall() + self.parse_desc_helpers() + self.parse_define_helpers() self.reader.close() ############################################################################### @@ -235,6 +298,25 @@ class Printer(object): self.print_one(elem) self.print_footer() + def elem_number_check(self, desc_unique_elem, define_unique_elem, type, instance): + """ + Checks the number of helpers/syscalls documented within the header file + description with those defined as part of enum/macro and raise an + Exception if they don't match. + """ + nr_desc_unique_elem = len(desc_unique_elem) + nr_define_unique_elem = len(define_unique_elem) + if nr_desc_unique_elem != nr_define_unique_elem: + exception_msg = ''' +The number of unique %s in description (%d) doesn\'t match the number of unique %s defined in %s (%d) +''' % (type, nr_desc_unique_elem, type, instance, nr_define_unique_elem) + if nr_desc_unique_elem < nr_define_unique_elem: + # Function description is parsed until no helper is found (which can be due to + # misformatting). Hence, only print the first missing/misformatted helper/enum. + exception_msg += ''' +The description for %s is not present or formatted correctly. +''' % (define_unique_elem[nr_desc_unique_elem]) + raise Exception(exception_msg) class PrinterRST(Printer): """ @@ -295,7 +377,6 @@ class PrinterRST(Printer): print('') - class PrinterHelpersRST(PrinterRST): """ A printer for dumping collected information about helpers as a ReStructured @@ -305,6 +386,7 @@ class PrinterHelpersRST(PrinterRST): """ def __init__(self, parser): self.elements = parser.helpers + self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER') def print_header(self): header = '''\ @@ -478,6 +560,7 @@ class PrinterSyscallRST(PrinterRST): """ def __init__(self, parser): self.elements = parser.commands + self.elem_number_check(parser.desc_syscalls, parser.enum_syscalls, 'syscall', 'bpf_cmd') def print_header(self): header = '''\ @@ -509,6 +592,7 @@ class PrinterHelpers(Printer): """ def __init__(self, parser): self.elements = parser.helpers + self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER') type_fwds = [ 'struct bpf_fib_lookup', diff --git a/scripts/pahole-flags.sh b/scripts/pahole-flags.sh index e6093adf4c06..c293941612e7 100755 --- a/scripts/pahole-flags.sh +++ b/scripts/pahole-flags.sh @@ -7,7 +7,7 @@ if ! [ -x "$(command -v ${PAHOLE})" ]; then exit 0 fi -pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/') +pahole_ver=$($(dirname $0)/pahole-version.sh ${PAHOLE}) if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then # pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars diff --git a/scripts/pahole-version.sh b/scripts/pahole-version.sh new file mode 100755 index 000000000000..f8a32ab93ad1 --- /dev/null +++ b/scripts/pahole-version.sh @@ -0,0 +1,13 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Usage: $ ./pahole-version.sh pahole +# +# Prints pahole's version in a 3-digit form, such as 119 for v1.19. + +if [ ! -x "$(command -v "$@")" ]; then + echo 0 + exit 1 +fi + +"$@" --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/' diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 842889f3dcb7..a9f8c63a96d1 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -838,7 +838,7 @@ int devcgroup_check_permission(short type, u32 major, u32 minor, short access) int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); if (rc) - return -EPERM; + return rc; #ifdef CONFIG_CGROUP_DEVICE return devcgroup_legacy_check_permission(type, major, minor, access); diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 59833125ac0a..a2c665beda87 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -902,7 +902,7 @@ static int do_show(int argc, char **argv) equal_fn_for_key_as_id, NULL); btf_map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!btf_prog_table || !btf_map_table) { + if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) { hashmap__free(btf_prog_table); hashmap__free(btf_map_table); if (fd >= 0) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 3571a281c43f..effe136119d7 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -50,6 +50,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { + char prog_name[MAX_PROG_FULL_NAME]; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); int prog_fd; @@ -63,6 +64,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, return -1; } + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); @@ -73,7 +75,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, jsonw_uint_field(json_wtr, "attach_type", attach_type); jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); - jsonw_string_field(json_wtr, "name", info.name); + jsonw_string_field(json_wtr, "name", prog_name); jsonw_end_object(json_wtr); } else { printf("%s%-8u ", level ? " " : "", info.id); @@ -81,7 +83,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, printf("%-15s", attach_type_name[attach_type]); else printf("type %-10u", attach_type); - printf(" %-15s %-15s\n", attach_flags_str, info.name); + printf(" %-15s %-15s\n", attach_flags_str, prog_name); } close(prog_fd); diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index fa8eb8134344..606743c6db41 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -24,6 +24,7 @@ #include <bpf/bpf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/btf.h> #include "main.h" @@ -304,6 +305,49 @@ const char *get_fd_type_name(enum bpf_obj_type type) return names[type]; } +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len) +{ + const char *prog_name = prog_info->name; + const struct btf_type *func_type; + const struct bpf_func_info finfo = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct btf *prog_btf = NULL; + + if (buff_len <= BPF_OBJ_NAME_LEN || + strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1) + goto copy_name; + + if (!prog_info->btf_id || prog_info->nr_func_info == 0) + goto copy_name; + + info.nr_func_info = 1; + info.func_info_rec_size = prog_info->func_info_rec_size; + if (info.func_info_rec_size > sizeof(finfo)) + info.func_info_rec_size = sizeof(finfo); + info.func_info = ptr_to_u64(&finfo); + + if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) + goto copy_name; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (!prog_btf) + goto copy_name; + + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto copy_name; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +copy_name: + snprintf(name_buff, buff_len, "%s", prog_name); + + if (prog_btf) + btf__free(prog_btf); +} + int get_fd_type(int fd) { char path[PATH_MAX]; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index e999159fa28d..9c894b1447de 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -487,17 +487,12 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, size_t maxlen; bool res; - if (ifindex) - /* Only test offload-able program types */ - switch (prog_type) { - case BPF_PROG_TYPE_SCHED_CLS: - case BPF_PROG_TYPE_XDP: - break; - default: - return; - } + if (ifindex) { + p_info("BPF offload feature probing is not supported"); + return; + } - res = bpf_probe_prog_type(prog_type, ifindex); + res = libbpf_probe_bpf_prog_type(prog_type, NULL); #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for unprivileged users * check that we did not fail because of insufficient permissions @@ -535,7 +530,12 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, size_t maxlen; bool res; - res = bpf_probe_map_type(map_type, ifindex); + if (ifindex) { + p_info("BPF offload feature probing is not supported"); + return; + } + + res = libbpf_probe_bpf_map_type(map_type, NULL); /* Probe result depends on the success of map creation, no additional * check required for unprivileged users @@ -567,7 +567,12 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, bool res = false; if (supported_type) { - res = bpf_probe_helper(id, prog_type, ifindex); + if (ifindex) { + p_info("BPF offload feature probing is not supported"); + return; + } + + res = libbpf_probe_bpf_helper(prog_type, id, NULL); #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for * unprivileged users check that we did not fail because of diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index b4695df2ea3d..eacfc6a2060d 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -227,7 +227,7 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) /* only generate definitions for memory-mapped internal maps */ if (!bpf_map__is_internal(map)) continue; - if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + if (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) continue; if (!get_map_ident(map, map_ident, sizeof(map_ident))) @@ -378,13 +378,16 @@ static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) int prog_fd = skel->progs.%2$s.prog_fd; \n\ ", obj_name, bpf_program__name(prog)); - switch (bpf_program__get_type(prog)) { + switch (bpf_program__type(prog)) { case BPF_PROG_TYPE_RAW_TRACEPOINT: tp_name = strchr(bpf_program__section_name(prog), '/') + 1; - printf("\tint fd = bpf_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); + printf("\tint fd = skel_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); break; case BPF_PROG_TYPE_TRACING: - printf("\tint fd = bpf_raw_tracepoint_open(NULL, prog_fd);\n"); + if (bpf_program__expected_attach_type(prog) == BPF_TRACE_ITER) + printf("\tint fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER);\n"); + else + printf("\tint fd = skel_raw_tracepoint_open(NULL, prog_fd);\n"); break; default: printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n"); @@ -468,7 +471,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) if (!get_map_ident(map, ident, sizeof(ident))) continue; if (bpf_map__is_internal(map) && - (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) printf("\tmunmap(skel->%1$s, %2$zd);\n", ident, bpf_map_mmap_sz(map)); codegen("\ @@ -536,7 +539,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h continue; if (!bpf_map__is_internal(map) || - !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) continue; codegen("\ @@ -600,10 +603,10 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h continue; if (!bpf_map__is_internal(map) || - !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) continue; - if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG) + if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) mmap_flags = "PROT_READ"; else mmap_flags = "PROT_READ | PROT_WRITE"; @@ -927,7 +930,6 @@ static int do_skeleton(int argc, char **argv) s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ if (!s) \n\ goto err; \n\ - obj->skeleton = s; \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -962,7 +964,7 @@ static int do_skeleton(int argc, char **argv) i, bpf_map__name(map), i, ident); /* memory-mapped internal maps */ if (bpf_map__is_internal(map) && - (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { + (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) { printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", i, ident); } @@ -1000,6 +1002,7 @@ static int do_skeleton(int argc, char **argv) \n\ s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ \n\ + obj->skeleton = s; \n\ return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 2c258db0d352..97dec81950e5 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -2,6 +2,7 @@ /* Copyright (C) 2020 Facebook */ #include <errno.h> +#include <linux/err.h> #include <net/if.h> #include <stdio.h> #include <unistd.h> @@ -306,7 +307,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { link_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!link_table) { + if (IS_ERR(link_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 020e91a542d5..490f7bd54e4c 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -478,7 +478,11 @@ int main(int argc, char **argv) } if (!legacy_libbpf) { - ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + /* Allow legacy map definitions for skeleton generation. + * It will still be rejected if users use LIBBPF_STRICT_ALL + * mode for loading generated skeleton. + */ + ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); if (ret) p_err("failed to enable libbpf strict mode: %d", ret); } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 8d76d937a62b..0c3840596b5a 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -140,6 +140,10 @@ struct cmd { int cmd_select(const struct cmd *cmds, int argc, char **argv, int (*help)(int argc, char **argv)); +#define MAX_PROG_FULL_NAME 128 +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len); + int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index cc530a229812..c66a3c979b7a 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -699,7 +699,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!map_table) { + if (IS_ERR(map_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 649053704bd7..526a332c48e6 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -551,7 +551,7 @@ static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type, if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD) flags |= XDP_FLAGS_HW_MODE; - return bpf_set_link_xdp_fd(ifindex, progfd, flags); + return bpf_xdp_attach(ifindex, progfd, flags, NULL); } static int do_attach(int argc, char **argv) diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index 56b598eee043..7c384d10e95f 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2020 Facebook */ #include <errno.h> +#include <linux/err.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -101,7 +102,7 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) libbpf_print_fn_t default_print; *map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!*map) { + if (IS_ERR(*map)) { p_err("failed to create hashmap for PID references"); return -1; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2a21d50516bc..92a6f679ef7d 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -424,8 +424,10 @@ out_free: free(value); } -static void print_prog_header_json(struct bpf_prog_info *info) +static void print_prog_header_json(struct bpf_prog_info *info, int fd) { + char prog_name[MAX_PROG_FULL_NAME]; + jsonw_uint_field(json_wtr, "id", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) jsonw_string_field(json_wtr, "type", @@ -433,8 +435,10 @@ static void print_prog_header_json(struct bpf_prog_info *info) else jsonw_uint_field(json_wtr, "type", info->type); - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + jsonw_string_field(json_wtr, "name", prog_name); + } jsonw_name(json_wtr, "tag"); jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"", @@ -455,7 +459,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) char *memlock; jsonw_start_object(json_wtr); - print_prog_header_json(info); + print_prog_header_json(info, fd); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -507,16 +511,20 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_object(json_wtr); } -static void print_prog_header_plain(struct bpf_prog_info *info) +static void print_prog_header_plain(struct bpf_prog_info *info, int fd) { + char prog_name[MAX_PROG_FULL_NAME]; + printf("%u: ", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) printf("%s ", prog_type_name[info->type]); else printf("type %u ", info->type); - if (*info->name) - printf("name %s ", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + printf("name %s ", prog_name); + } printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); @@ -534,7 +542,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) { char *memlock; - print_prog_header_plain(info); + print_prog_header_plain(info, fd); if (info->load_time) { char buf[32]; @@ -641,7 +649,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { prog_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!prog_table) { + if (IS_ERR(prog_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } @@ -972,10 +980,10 @@ static int do_dump(int argc, char **argv) if (json_output && nb_fds > 1) { jsonw_start_object(json_wtr); /* prog object */ - print_prog_header_json(&info); + print_prog_header_json(&info, fds[i]); jsonw_name(json_wtr, "insns"); } else if (nb_fds > 1) { - print_prog_header_plain(&info); + print_prog_header_plain(&info, fds[i]); } err = prog_dump(&info, mode, filepath, opcodes, visual, linum); @@ -1264,12 +1272,12 @@ static int do_run(int argc, char **argv) { char *data_fname_in = NULL, *data_fname_out = NULL; char *ctx_fname_in = NULL, *ctx_fname_out = NULL; - struct bpf_prog_test_run_attr test_attr = {0}; const unsigned int default_size = SZ_32K; void *data_in = NULL, *data_out = NULL; void *ctx_in = NULL, *ctx_out = NULL; unsigned int repeat = 1; int fd, err; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); if (!REQ_ARGS(4)) return -1; @@ -1387,14 +1395,13 @@ static int do_run(int argc, char **argv) goto free_ctx_in; } - test_attr.prog_fd = fd; test_attr.repeat = repeat; test_attr.data_in = data_in; test_attr.data_out = data_out; test_attr.ctx_in = ctx_in; test_attr.ctx_out = ctx_out; - err = bpf_prog_test_run_xattr(&test_attr); + err = bpf_prog_test_run_opts(fd, &test_attr); if (err) { p_err("failed to run program: %s", strerror(errno)); goto free_ctx_out; @@ -2275,10 +2282,10 @@ static int do_profile(int argc, char **argv) profile_obj->rodata->num_metric = num_metric; /* adjust map sizes */ - bpf_map__resize(profile_obj->maps.events, num_metric * num_cpu); - bpf_map__resize(profile_obj->maps.fentry_readings, num_metric); - bpf_map__resize(profile_obj->maps.accum_readings, num_metric); - bpf_map__resize(profile_obj->maps.counts, 1); + bpf_map__set_max_entries(profile_obj->maps.events, num_metric * num_cpu); + bpf_map__set_max_entries(profile_obj->maps.fentry_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.accum_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.counts, 1); /* change target name */ profile_tgt_name = profile_target_name(profile_tgt_fd); diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 2f693b082bdb..e08a6ff2866c 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -480,7 +480,6 @@ static int do_unregister(int argc, char **argv) static int do_register(int argc, char **argv) { LIBBPF_OPTS(bpf_object_open_opts, open_opts); - const struct bpf_map_def *def; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); int nr_errs = 0, nr_maps = 0; @@ -510,8 +509,7 @@ static int do_register(int argc, char **argv) } bpf_object__for_each_map(map, obj) { - def = bpf_map__def(map); - if (def->type != BPF_MAP_TYPE_STRUCT_OPS) + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) continue; link = bpf_map__attach_struct_ops(map); diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 320a88ac28c9..19a3112e271a 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -24,6 +24,8 @@ LD = $(HOSTLD) ARCH = $(HOSTARCH) RM ?= rm CROSS_COMPILE = +CFLAGS := $(KBUILD_HOSTCFLAGS) +LDFLAGS := $(KBUILD_HOSTLDFLAGS) OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -51,10 +53,10 @@ $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \ $(abspath $@) install_headers -CFLAGS := -g \ +CFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b0383d371b9a..afe3d0d7f5f2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1111,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1775,6 +1782,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1791,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2267,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2382,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2481,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3257,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. @@ -5018,6 +5038,54 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5206,6 +5274,12 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ + FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5500,7 +5574,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; @@ -6378,7 +6453,8 @@ struct bpf_sk_lookup { __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index f947b61b2107..b8b37fe76006 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -131,7 +131,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ sed 's/\[.*\]//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) @@ -194,7 +194,7 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ sed 's/\[.*\]//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff -u $(OUTPUT)libbpf_global_syms.tmp \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 550b4cbb6c99..418b259166f8 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -754,10 +754,10 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, .flags = flags, ); - return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); + return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts); } -int bpf_prog_attach_xattr(int prog_fd, int target_fd, +int bpf_prog_attach_opts(int prog_fd, int target_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts) { @@ -778,6 +778,11 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd, return libbpf_err_errno(ret); } +__attribute__((alias("bpf_prog_attach_opts"))) +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); + int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 14e0d97ad2cf..16b21757b8bf 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -391,6 +391,10 @@ struct bpf_prog_attach_opts { LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead") LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts); @@ -449,12 +453,14 @@ struct bpf_prog_test_run_attr { * out: length of cxt_out */ }; +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); /* * bpf_prog_test_run does not check that data_out is large enough. Consider - * using bpf_prog_test_run_xattr instead. + * using bpf_prog_test_run_opts instead. */ +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 963b1060d944..44df982d2a5c 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -133,7 +133,7 @@ struct bpf_map_def { unsigned int value_size; unsigned int max_entries; unsigned int map_flags; -}; +} __attribute__((deprecated("use BTF-defined maps in .maps section"))); enum libbpf_pin_type { LIBBPF_PIN_NONE, diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 90f56b0f585f..e3a8c947e89f 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -76,6 +76,9 @@ #define __PT_RC_REG ax #define __PT_SP_REG sp #define __PT_IP_REG ip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #else @@ -105,6 +108,9 @@ #define __PT_RC_REG rax #define __PT_SP_REG rsp #define __PT_IP_REG rip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #endif /* __i386__ */ @@ -112,6 +118,10 @@ #elif defined(bpf_target_s390) +struct pt_regs___s390 { + unsigned long orig_gpr2; +}; + /* s390 provides user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) #define __PT_PARM1_REG gprs[2] @@ -124,6 +134,8 @@ #define __PT_RC_REG gprs[2] #define __PT_SP_REG gprs[15] #define __PT_IP_REG psw.addr +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) #elif defined(bpf_target_arm) @@ -140,6 +152,10 @@ #elif defined(bpf_target_arm64) +struct pt_regs___arm64 { + unsigned long orig_x0; +}; + /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) #define __PT_PARM1_REG regs[0] @@ -152,6 +168,8 @@ #define __PT_RC_REG regs[0] #define __PT_SP_REG sp #define __PT_IP_REG pc +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) #elif defined(bpf_target_mips) @@ -178,6 +196,8 @@ #define __PT_RC_REG gpr[3] #define __PT_SP_REG sp #define __PT_IP_REG nip +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx #elif defined(bpf_target_sparc) @@ -206,10 +226,12 @@ #define __PT_PARM4_REG a3 #define __PT_PARM5_REG a4 #define __PT_RET_REG ra -#define __PT_FP_REG fp +#define __PT_FP_REG s0 #define __PT_RC_REG a5 #define __PT_SP_REG sp -#define __PT_IP_REG epc +#define __PT_IP_REG pc +/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx #endif @@ -263,6 +285,26 @@ struct pt_regs; #endif +#ifndef PT_REGS_PARM1_SYSCALL +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x) +#endif +#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x) +#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x) +#ifndef PT_REGS_PARM4_SYSCALL +#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x) +#endif +#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x) + +#ifndef PT_REGS_PARM1_CORE_SYSCALL +#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x) +#endif +#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x) +#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x) +#ifndef PT_REGS_PARM4_CORE_SYSCALL +#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x) +#endif +#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x) + #else /* defined(bpf_target_defined) */ #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -290,8 +332,30 @@ struct pt_regs; #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + #endif /* defined(bpf_target_defined) */ +/* + * When invoked from a syscall handler kprobe, returns a pointer to a + * struct pt_regs containing syscall arguments and suitable for passing to + * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL(). + */ +#ifndef PT_REGS_SYSCALL_REGS +/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx)) +#endif + #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b #endif @@ -406,4 +470,39 @@ typeof(name(0)) name(struct pt_regs *ctx) \ } \ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) +#define ___bpf_syscall_args0() ctx +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) + +/* + * BPF_KPROBE_SYSCALL is a variant of BPF_KPROBE, which is intended for + * tracing syscall functions, like __x64_sys_close. It hides the underlying + * platform-specific low-level way of getting syscall input arguments from + * struct pt_regs, and provides a familiar typed and named function arguments + * syntax and semantics of accessing syscall input parameters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + * + * This macro relies on BPF CO-RE support. + */ +#define BPF_KPROBE_SYSCALL(name, args...) \ +name(struct pt_regs *ctx); \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + struct pt_regs *regs = PT_REGS_SYSCALL_REGS(ctx); \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_syscall_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 9aa19c89f758..1383e26c5d1f 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1620,20 +1620,37 @@ static int btf_commit_type(struct btf *btf, int data_sz) struct btf_pipe { const struct btf *src; struct btf *dst; + struct hashmap *str_off_map; /* map string offsets from src to dst */ }; static int btf_rewrite_str(__u32 *str_off, void *ctx) { struct btf_pipe *p = ctx; - int off; + void *mapped_off; + int off, err; if (!*str_off) /* nothing to do for empty strings */ return 0; + if (p->str_off_map && + hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) { + *str_off = (__u32)(long)mapped_off; + return 0; + } + off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off)); if (off < 0) return off; + /* Remember string mapping from src to dst. It avoids + * performing expensive string comparisons. + */ + if (p->str_off_map) { + err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off); + if (err) + return err; + } + *str_off = off; return 0; } @@ -1680,6 +1697,9 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) return 0; } +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx); +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx); + int btf__add_btf(struct btf *btf, const struct btf *src_btf) { struct btf_pipe p = { .src = src_btf, .dst = btf }; @@ -1713,6 +1733,11 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) if (!off) return libbpf_err(-ENOMEM); + /* Map the string offsets from src_btf to the offsets from btf to improve performance */ + p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(p.str_off_map)) + return libbpf_err(-ENOMEM); + /* bulk copy types data for all types from src_btf */ memcpy(t, src_btf->types_data, data_sz); @@ -1754,6 +1779,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) btf->hdr->str_off += data_sz; btf->nr_types += cnt; + hashmap__free(p.str_off_map); + /* return type ID of the first added BTF type */ return btf->start_id + btf->nr_types - cnt; err_out: @@ -1767,6 +1794,8 @@ err_out: * wasn't modified, so doesn't need restoring, see big comment above */ btf->hdr->str_len = old_strs_len; + hashmap__free(p.str_off_map); + return libbpf_err(err); } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 061839f04525..951ac7475794 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -147,11 +147,10 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API void btf__set_fd(struct btf *btf, int fd); -LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead") -LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); +LIBBPF_DEPRECATED_SINCE(0, 7, "this API is not necessary when BTF-defined maps are used") LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, __u32 expected_key_size, __u32 expected_value_size, @@ -159,8 +158,7 @@ LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); -LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, - __u32 *size); +LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions") int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ext, @@ -171,8 +169,10 @@ int btf_ext__reloc_line_info(const struct btf *btf, const struct btf_ext *btf_ext, const char *sec_name, __u32 insns_cnt, void **line_info, __u32 *cnt); -LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); -LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info is deprecated; write custom func_info parsing to fetch rec_size") +__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info is deprecated; write custom line_info parsing to fetch rec_size") +__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); @@ -375,8 +375,28 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id, const struct btf_dump_type_data_opts *opts); /* - * A set of helpers for easier BTF types handling + * A set of helpers for easier BTF types handling. + * + * The inline functions below rely on constants from the kernel headers which + * may not be available for applications including this header file. To avoid + * compilation errors, we define all the constants here that were added after + * the initial introduction of the BTF_KIND* constants. */ +#ifndef BTF_KIND_FUNC +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#endif +#ifndef BTF_KIND_VAR +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#endif +#ifndef BTF_KIND_FLOAT +#define BTF_KIND_FLOAT 16 /* Floating point */ +#endif +/* The kernel header switched to enums, so these two were never #defined */ +#define BTF_KIND_DECL_TAG 17 /* Decl Tag */ +#define BTF_KIND_TYPE_TAG 18 /* Type Tag */ + static inline __u16 btf_kind(const struct btf_type *t) { return BTF_INFO_KIND(t->info); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index b9a3260c83cb..07ebe70d3a30 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -1861,14 +1861,16 @@ static int btf_dump_array_data(struct btf_dump *d, { const struct btf_array *array = btf_array(t); const struct btf_type *elem_type; - __u32 i, elem_size = 0, elem_type_id; + __u32 i, elem_type_id; + __s64 elem_size; bool is_array_member; elem_type_id = array->type; elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL); elem_size = btf__resolve_size(d->btf, elem_type_id); if (elem_size <= 0) { - pr_warn("unexpected elem size %d for array type [%u]\n", elem_size, id); + pr_warn("unexpected elem size %zd for array type [%u]\n", + (ssize_t)elem_size, id); return -EINVAL; } diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 3c20b126d60d..aeb09c288716 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map) void hashmap__free(struct hashmap *map) { - if (!map) + if (IS_ERR_OR_NULL(map)) return; hashmap__clear(map); @@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key, return true; } - diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7f10dd501a52..2262bcdfee92 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -156,14 +156,6 @@ enum libbpf_strict_mode libbpf_mode = LIBBPF_STRICT_NONE; int libbpf_set_strict_mode(enum libbpf_strict_mode mode) { - /* __LIBBPF_STRICT_LAST is the last power-of-2 value used + 1, so to - * get all possible values we compensate last +1, and then (2*x - 1) - * to get the bit mask - */ - if (mode != LIBBPF_STRICT_ALL - && (mode & ~((__LIBBPF_STRICT_LAST - 1) * 2 - 1))) - return errno = EINVAL, -EINVAL; - libbpf_mode = mode; return 0; } @@ -235,6 +227,10 @@ enum sec_def_flags { SEC_SLEEPABLE = 8, /* allow non-strict prefix matching */ SEC_SLOPPY_PFX = 16, + /* BPF program support non-linear XDP buffer */ + SEC_XDP_FRAGS = 32, + /* deprecated sec definitions not supposed to be used */ + SEC_DEPRECATED = 64, }; struct bpf_sec_def { @@ -1937,6 +1933,11 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (obj->efile.maps_shndx < 0) return 0; + if (libbpf_mode & LIBBPF_STRICT_MAP_DEFINITIONS) { + pr_warn("legacy map definitions in SEC(\"maps\") are not supported\n"); + return -EOPNOTSUPP; + } + if (!symbols) return -EINVAL; @@ -1999,6 +2000,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } + pr_warn("map '%s' (legacy): legacy map definitions are deprecated, use BTF-defined maps instead\n", map_name); + if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; @@ -4190,9 +4193,13 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) return 0; if (!bpf_map__is_internal(map)) { + pr_warn("Use of BPF_ANNOTATE_KV_PAIR is deprecated, use BTF-defined maps in .maps section instead\n"); +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, def->value_size, &key_type_id, &value_type_id); +#pragma GCC diagnostic pop } else { /* * LLVM annotates global data differently in BTF, that is, @@ -6562,6 +6569,13 @@ static int libbpf_preload_prog(struct bpf_program *prog, if (def & SEC_SLEEPABLE) opts->prog_flags |= BPF_F_SLEEPABLE; + if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) + opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + + if (def & SEC_DEPRECATED) + pr_warn("SEC(\"%s\") is deprecated, please see https://github.com/libbpf/libbpf/wiki/Libbpf-1.0-migration-guide#bpf-program-sec-annotation-deprecations for details\n", + prog->sec_name); + if ((prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { @@ -7883,10 +7897,8 @@ int bpf_map__set_pin_path(struct bpf_map *map, const char *path) return 0; } -const char *bpf_map__get_pin_path(const struct bpf_map *map) -{ - return map->pin_path; -} +__alias(bpf_map__pin_path) +const char *bpf_map__get_pin_path(const struct bpf_map *map); const char *bpf_map__pin_path(const struct bpf_map *map) { @@ -8451,7 +8463,10 @@ static int bpf_program_nth_fd(const struct bpf_program *prog, int n) return fd; } -enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog) +__alias(bpf_program__type) +enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); + +enum bpf_prog_type bpf_program__type(const struct bpf_program *prog) { return prog->type; } @@ -8495,8 +8510,10 @@ BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS); BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT); BPF_PROG_TYPE_FNS(sk_lookup, BPF_PROG_TYPE_SK_LOOKUP); -enum bpf_attach_type -bpf_program__get_expected_attach_type(const struct bpf_program *prog) +__alias(bpf_program__expected_attach_type) +enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); + +enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program *prog) { return prog->expected_attach_type; } @@ -8580,7 +8597,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX | SEC_DEPRECATED), SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), @@ -8599,9 +8616,15 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("lsm/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("iter.s/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_iter), SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), - SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), - SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/devmap", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE | SEC_DEPRECATED), + SEC_DEF("xdp.frags/cpumap", XDP, BPF_XDP_CPUMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/cpumap", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE | SEC_DEPRECATED), + SEC_DEF("xdp.frags", XDP, BPF_XDP, SEC_XDP_FRAGS), SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -9443,7 +9466,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, open_attr.file = attr->file; open_attr.prog_type = attr->prog_type; - obj = bpf_object__open_xattr(&open_attr); + obj = __bpf_object__open_xattr(&open_attr, 0); err = libbpf_get_error(obj); if (err) return libbpf_err(-ENOENT); @@ -9460,7 +9483,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, bpf_program__set_expected_attach_type(prog, attach_type); } - if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) { + if (bpf_program__type(prog) == BPF_PROG_TYPE_UNSPEC) { /* * we haven't guessed from section name and user * didn't provide a fallback type, too bad... @@ -9477,7 +9500,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, } bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_offload_neutral(map)) + if (map->def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) map->map_ifindex = attr->ifindex; } @@ -10511,7 +10534,7 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; - attach_type = bpf_program__get_expected_attach_type(prog); + attach_type = bpf_program__expected_attach_type(prog); link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts); if (link_fd < 0) { link_fd = -errno; @@ -11795,6 +11818,9 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) { + if (!s) + return; + if (s->progs) bpf_object__detach_skeleton(s); if (s->obj) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8b9bc5e90c2b..c8d8daad212e 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -180,9 +180,11 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); /* deprecated bpf_object__open variants */ +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open_mem() instead") LIBBPF_API struct bpf_object * bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, const char *name); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open_file() instead") LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); @@ -244,8 +246,10 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev); (pos) = (tmp), (tmp) = bpf_object__next(tmp)) typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); LIBBPF_API int @@ -277,9 +281,10 @@ bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog) typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, bpf_program_clear_priv_t clear_priv); - +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); @@ -591,26 +596,39 @@ LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); /* * Adjust type of BPF program. Default is kprobe. */ +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sk_lookup(struct bpf_program *prog); -LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); +LIBBPF_API enum bpf_prog_type bpf_program__type(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); LIBBPF_API enum bpf_attach_type -bpf_program__get_expected_attach_type(const struct bpf_program *prog); +bpf_program__expected_attach_type(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); @@ -631,18 +649,31 @@ LIBBPF_API int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, const char *attach_func_name); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sk_lookup(const struct bpf_program *prog); /* @@ -706,7 +737,8 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); LIBBPF_API int bpf_map__fd(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); /* get map definition */ -LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use appropriate getters or setters instead") +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); /* get map name */ LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); /* get/set map type */ @@ -715,6 +747,7 @@ LIBBPF_API int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type); /* get/set map size (max_entries) */ LIBBPF_API __u32 bpf_map__max_entries(const struct bpf_map *map); LIBBPF_API int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__set_max_entries() instead") LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); /* get/set map flags */ LIBBPF_API __u32 bpf_map__map_flags(const struct bpf_map *map); @@ -739,8 +772,10 @@ LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map); LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); @@ -757,7 +792,6 @@ LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); -LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map); LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); @@ -832,13 +866,42 @@ struct bpf_xdp_set_link_opts { }; #define bpf_xdp_set_link_opts__last_field old_fd +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query_id() instead") LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query() instead") LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); +struct bpf_xdp_attach_opts { + size_t sz; + int old_prog_fd; + size_t :0; +}; +#define bpf_xdp_attach_opts__last_field old_prog_fd + +struct bpf_xdp_query_opts { + size_t sz; + __u32 prog_id; /* output */ + __u32 drv_prog_id; /* output */ + __u32 hw_prog_id; /* output */ + __u32 skb_prog_id; /* output */ + __u8 attach_mode; /* output */ + size_t :0; +}; +#define bpf_xdp_query_opts__last_field attach_mode + +LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts); +LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id); + /* TC related API */ enum bpf_tc_attach_point { BPF_TC_INGRESS = 1 << 0, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 529783967793..aef6253a90c8 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -247,6 +247,7 @@ LIBBPF_0.0.8 { bpf_link_create; bpf_link_update; bpf_map__set_initial_value; + bpf_prog_attach_opts; bpf_program__attach_cgroup; bpf_program__attach_lsm; bpf_program__is_lsm; @@ -423,10 +424,16 @@ LIBBPF_0.6.0 { LIBBPF_0.7.0 { global: bpf_btf_load; + bpf_program__expected_attach_type; bpf_program__log_buf; bpf_program__log_level; bpf_program__set_log_buf; bpf_program__set_log_level; + bpf_program__type; + bpf_xdp_attach; + bpf_xdp_detach; + bpf_xdp_query; + bpf_xdp_query_id; libbpf_probe_bpf_helper; libbpf_probe_bpf_map_type; libbpf_probe_bpf_prog_type; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 1565679eb432..bc86b82e90d1 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -92,6 +92,9 @@ # define offsetofend(TYPE, FIELD) \ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +#ifndef __alias +#define __alias(symbol) __attribute__((alias(#symbol))) +#endif /* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is * a string literal known at compilation time or char * pointer known only at diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 79131f761a27..a283cf031665 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -73,6 +73,11 @@ enum libbpf_strict_mode { * operation. */ LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10, + /* + * Error out on any SEC("maps") map definition, which are deprecated + * in favor of BTF-defined map definitions in SEC(".maps"). + */ + LIBBPF_STRICT_MAP_DEFINITIONS = 0x20, __LIBBPF_STRICT_LAST, }; @@ -81,6 +86,23 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); #define DECLARE_LIBBPF_OPTS LIBBPF_OPTS +/* "Discouraged" APIs which don't follow consistent libbpf naming patterns. + * They are normally a trivial aliases or wrappers for proper APIs and are + * left to minimize unnecessary disruption for users of libbpf. But they + * shouldn't be used going forward. + */ + +struct bpf_program; +struct bpf_map; +struct btf; +struct btf_ext; + +LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); +LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); +LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); +LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); +LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 39f25e09b51e..c39c37f99d5c 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -217,6 +217,28 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); } +int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + int old_prog_fd, err; + + if (!OPTS_VALID(opts, bpf_xdp_attach_opts)) + return libbpf_err(-EINVAL); + + old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (old_prog_fd) + flags |= XDP_FLAGS_REPLACE; + else + old_prog_fd = -1; + + err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags); + return libbpf_err(err); +} + +int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + return bpf_xdp_attach(ifindex, -1, flags, opts); +} + int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts) { @@ -303,69 +325,98 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } -int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, - size_t info_size, __u32 flags) +int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { - struct xdp_id_md xdp_id = {}; - __u32 mask; - int ret; struct libbpf_nla_req req = { .nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), .nh.nlmsg_type = RTM_GETLINK, .nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, .ifinfo.ifi_family = AF_PACKET, }; + struct xdp_id_md xdp_id = {}; + int err; - if (flags & ~XDP_FLAGS_MASK || !info_size) + if (!OPTS_VALID(opts, bpf_xdp_query_opts)) + return libbpf_err(-EINVAL); + + if (xdp_flags & ~XDP_FLAGS_MASK) return libbpf_err(-EINVAL); /* Check whether the single {HW,DRV,SKB} mode is set */ - flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE); - mask = flags - 1; - if (flags && flags & mask) + xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE; + if (xdp_flags & (xdp_flags - 1)) return libbpf_err(-EINVAL); xdp_id.ifindex = ifindex; - xdp_id.flags = flags; + xdp_id.flags = xdp_flags; - ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, get_xdp_info, &xdp_id); - if (!ret) { - size_t sz = min(info_size, sizeof(xdp_id.info)); + if (err) + return libbpf_err(err); - memcpy(info, &xdp_id.info, sz); - memset((void *) info + sz, 0, info_size - sz); - } + OPTS_SET(opts, prog_id, xdp_id.info.prog_id); + OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id); + OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id); + OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); + OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); - return libbpf_err(ret); + return 0; } -static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) +int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags) { - flags &= XDP_FLAGS_MODES; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + size_t sz; + int err; + + if (!info_size) + return libbpf_err(-EINVAL); - if (info->attach_mode != XDP_ATTACHED_MULTI && !flags) - return info->prog_id; - if (flags & XDP_FLAGS_DRV_MODE) - return info->drv_prog_id; - if (flags & XDP_FLAGS_HW_MODE) - return info->hw_prog_id; - if (flags & XDP_FLAGS_SKB_MODE) - return info->skb_prog_id; + err = bpf_xdp_query(ifindex, flags, &opts); + if (err) + return libbpf_err(err); + + /* struct xdp_link_info field layout matches struct bpf_xdp_query_opts + * layout after sz field + */ + sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode)); + memcpy(info, &opts.prog_id, sz); + memset((void *)info + sz, 0, info_size - sz); return 0; } -int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id) { - struct xdp_link_info info; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); int ret; - ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags); - if (!ret) - *prog_id = get_xdp_id(&info, flags); + ret = bpf_xdp_query(ifindex, flags, &opts); + if (ret) + return libbpf_err(ret); + + flags &= XDP_FLAGS_MODES; - return libbpf_err(ret); + if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags) + *prog_id = opts.prog_id; + else if (flags & XDP_FLAGS_DRV_MODE) + *prog_id = opts.drv_prog_id; + else if (flags & XDP_FLAGS_HW_MODE) + *prog_id = opts.hw_prog_id; + else if (flags & XDP_FLAGS_SKB_MODE) + *prog_id = opts.skb_prog_id; + else + *prog_id = 0; + + return 0; +} + + +int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +{ + return bpf_xdp_query_id(ifindex, flags, prog_id); } typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 0b84d8e6b72a..dcd3336512d4 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -70,19 +70,85 @@ static inline int skel_closenz(int fd) return -EINVAL; } +#ifndef offsetofend +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) +#endif + +static inline int skel_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + + attr.map_type = map_type; + strncpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + + return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz); +} + +static inline int skel_map_update_elem(int fd, const void *key, + const void *value, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = (long) key; + attr.value = (long) value; + attr.flags = flags; + + return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); +} + +static inline int skel_raw_tracepoint_open(const char *name, int prog_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.raw_tracepoint.name = (long) name; + attr.raw_tracepoint.prog_fd = prog_fd; + + return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); +} + +static inline int skel_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type) +{ + const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.link_create.prog_fd = prog_fd; + attr.link_create.target_fd = target_fd; + attr.link_create.attach_type = attach_type; + + return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz); +} + static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) { int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL); + map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1); if (map_fd < 0) { opts->errstr = "failed to create loader map"; err = -errno; goto out; } - err = bpf_map_update_elem(map_fd, &key, opts->data, 0); + err = skel_map_update_elem(map_fd, &key, opts->data, 0); if (err < 0) { opts->errstr = "failed to update loader map"; err = -errno; diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 8ac0a3a457ef..0bc25a56cfef 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) { struct bpf_object *obj; - obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL); + obj = bpf_object__open_mem(obj_buf, obj_buf_sz, NULL); if (libbpf_get_error(obj)) return TEST_FAIL; bpf_object__close(obj); diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 16ec605a9fe4..ec6d9e7b446d 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -54,6 +54,7 @@ static bool libbpf_initialized; struct bpf_object * bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) { + LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = name); struct bpf_object *obj; if (!libbpf_initialized) { @@ -61,7 +62,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) libbpf_initialized = true; } - obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name); + obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load buffer\n"); return ERR_PTR(-EINVAL); @@ -72,6 +73,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) struct bpf_object *bpf__prepare_load(const char *filename, bool source) { + LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = filename); struct bpf_object *obj; if (!libbpf_initialized) { @@ -94,7 +96,7 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE); } else pr_debug("bpf: successful builtin compilation\n"); - obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename); + obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj) llvm__dump_obj(filename, obj_buf, obj_buf_sz); @@ -654,11 +656,11 @@ int bpf__probe(struct bpf_object *obj) } if (priv->is_tp) { - bpf_program__set_tracepoint(prog); + bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); continue; } - bpf_program__set_kprobe(prog); + bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE); pev = &priv->pev; err = convert_perf_probe_events(pev, 1); @@ -1005,24 +1007,22 @@ __bpf_map__config_value(struct bpf_map *map, { struct bpf_map_op *op; const char *map_name = bpf_map__name(map); - const struct bpf_map_def *def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("Unable to get map definition from '%s'\n", - map_name); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; } - if (def->type != BPF_MAP_TYPE_ARRAY) { + if (bpf_map__type(map) != BPF_MAP_TYPE_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; } - if (def->key_size < sizeof(unsigned int)) { + if (bpf_map__key_size(map) < sizeof(unsigned int)) { pr_debug("Map %s has incorrect key size\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE; } - switch (def->value_size) { + switch (bpf_map__value_size(map)) { case 1: case 2: case 4: @@ -1064,7 +1064,6 @@ __bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, struct evlist *evlist) { - const struct bpf_map_def *def; struct bpf_map_op *op; const char *map_name = bpf_map__name(map); struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str); @@ -1075,18 +1074,16 @@ __bpf_map__config_event(struct bpf_map *map, return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("Unable to get map definition from '%s'\n", - map_name); - return PTR_ERR(def); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); + return PTR_ERR(map); } /* * No need to check key_size and value_size: * kernel has already checked them. */ - if (def->type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; @@ -1135,7 +1132,6 @@ config_map_indices_range_check(struct parse_events_term *term, const char *map_name) { struct parse_events_array *array = &term->array; - const struct bpf_map_def *def; unsigned int i; if (!array->nr_ranges) @@ -1146,10 +1142,8 @@ config_map_indices_range_check(struct parse_events_term *term, return -BPF_LOADER_ERRNO__INTERNAL; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("ERROR: Unable to get map definition from '%s'\n", - map_name); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; } @@ -1158,7 +1152,7 @@ config_map_indices_range_check(struct parse_events_term *term, size_t length = array->ranges[i].length; unsigned int idx = start + length - 1; - if (idx >= def->max_entries) { + if (idx >= bpf_map__max_entries(map)) { pr_debug("ERROR: index %d too large\n", idx); return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG; } @@ -1252,21 +1246,21 @@ out: } typedef int (*map_config_func_t)(const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op, void *pkey, void *arg); static int foreach_key_array_all(map_config_func_t func, void *arg, const char *name, - int map_fd, const struct bpf_map_def *pdef, + int map_fd, const struct bpf_map *map, struct bpf_map_op *op) { unsigned int i; int err; - for (i = 0; i < pdef->max_entries; i++) { - err = func(name, map_fd, pdef, op, &i, arg); + for (i = 0; i < bpf_map__max_entries(map); i++) { + err = func(name, map_fd, map, op, &i, arg); if (err) { pr_debug("ERROR: failed to insert value to %s[%u]\n", name, i); @@ -1279,7 +1273,7 @@ foreach_key_array_all(map_config_func_t func, static int foreach_key_array_ranges(map_config_func_t func, void *arg, const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op) { unsigned int i, j; @@ -1292,7 +1286,7 @@ foreach_key_array_ranges(map_config_func_t func, void *arg, for (j = 0; j < length; j++) { unsigned int idx = start + j; - err = func(name, map_fd, pdef, op, &idx, arg); + err = func(name, map_fd, map, op, &idx, arg); if (err) { pr_debug("ERROR: failed to insert value to %s[%u]\n", name, idx); @@ -1308,9 +1302,8 @@ bpf_map_config_foreach_key(struct bpf_map *map, map_config_func_t func, void *arg) { - int err, map_fd; + int err, map_fd, type; struct bpf_map_op *op; - const struct bpf_map_def *def; const char *name = bpf_map__name(map); struct bpf_map_priv *priv = bpf_map__priv(map); @@ -1323,9 +1316,8 @@ bpf_map_config_foreach_key(struct bpf_map *map, return 0; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("ERROR: failed to get definition from map %s\n", name); + if (!map) { + pr_debug("Map '%s' is invalid\n", name); return -BPF_LOADER_ERRNO__INTERNAL; } map_fd = bpf_map__fd(map); @@ -1334,19 +1326,19 @@ bpf_map_config_foreach_key(struct bpf_map *map, return map_fd; } + type = bpf_map__type(map); list_for_each_entry(op, &priv->ops_list, list) { - switch (def->type) { + switch (type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: switch (op->key_type) { case BPF_MAP_KEY_ALL: err = foreach_key_array_all(func, arg, name, - map_fd, def, op); + map_fd, map, op); break; case BPF_MAP_KEY_RANGES: err = foreach_key_array_ranges(func, arg, name, - map_fd, def, - op); + map_fd, map, op); break; default: pr_debug("ERROR: keytype for map '%s' invalid\n", @@ -1455,7 +1447,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, static int apply_obj_config_map_for_key(const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op, void *pkey, void *arg __maybe_unused) { @@ -1464,7 +1456,7 @@ apply_obj_config_map_for_key(const char *name, int map_fd, switch (op->op_type) { case BPF_MAP_OP_SET_VALUE: err = apply_config_value_for_key(map_fd, pkey, - pdef->value_size, + bpf_map__value_size(map), op->v.value); break; case BPF_MAP_OP_SET_EVSEL: diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c index eb853ca67cf4..c863ae0c5cb5 100644 --- a/tools/perf/util/bpf_map.c +++ b/tools/perf/util/bpf_map.c @@ -9,25 +9,25 @@ #include <stdlib.h> #include <unistd.h> -static bool bpf_map_def__is_per_cpu(const struct bpf_map_def *def) +static bool bpf_map__is_per_cpu(enum bpf_map_type type) { - return def->type == BPF_MAP_TYPE_PERCPU_HASH || - def->type == BPF_MAP_TYPE_PERCPU_ARRAY || - def->type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - def->type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; + return type == BPF_MAP_TYPE_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_ARRAY || + type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; } -static void *bpf_map_def__alloc_value(const struct bpf_map_def *def) +static void *bpf_map__alloc_value(const struct bpf_map *map) { - if (bpf_map_def__is_per_cpu(def)) - return malloc(round_up(def->value_size, 8) * sysconf(_SC_NPROCESSORS_CONF)); + if (bpf_map__is_per_cpu(bpf_map__type(map))) + return malloc(round_up(bpf_map__value_size(map), 8) * + sysconf(_SC_NPROCESSORS_CONF)); - return malloc(def->value_size); + return malloc(bpf_map__value_size(map)); } int bpf_map__fprintf(struct bpf_map *map, FILE *fp) { - const struct bpf_map_def *def = bpf_map__def(map); void *prev_key = NULL, *key, *value; int fd = bpf_map__fd(map), err; int printed = 0; @@ -35,15 +35,15 @@ int bpf_map__fprintf(struct bpf_map *map, FILE *fp) if (fd < 0) return fd; - if (IS_ERR(def)) - return PTR_ERR(def); + if (!map) + return PTR_ERR(map); err = -ENOMEM; - key = malloc(def->key_size); + key = malloc(bpf_map__key_size(map)); if (key == NULL) goto out; - value = bpf_map_def__alloc_value(def); + value = bpf_map__alloc_value(map); if (value == NULL) goto out_free_key; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 42ffc24e9e71..91ea729990da 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -21,7 +21,7 @@ endif BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= -CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \ +CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) LDFLAGS += $(SAN_CFLAGS) @@ -292,7 +292,7 @@ IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) -BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ +BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ -I$(abspath $(OUTPUT)/../usr/include) @@ -330,7 +330,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c \ - map_ptr_kern.c core_kern.c + map_ptr_kern.c core_kern.c core_kern_overflow.c # Generate both light skeleton and libbpf skeleton for these LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test_subprog.c SKEL_BLACKLIST += $$(LSKELS) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 42ef250c7acc..d099d91adc3b 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -206,6 +206,8 @@ btf_tag test and Clang version The btf_tag selftest requires LLVM support to recognize the btf_decl_tag and btf_type_tag attributes. They are introduced in `Clang 14` [0_, 1_]. +The subtests ``btf_type_tag_user_{mod1, mod2, vmlinux}`` also requires +pahole version ``1.23``. Without them, the btf_tag selftest will be skipped and you will observe: diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index da8593b3494a..c2554f9695ff 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -151,7 +151,7 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void) /* record data + header take 16 bytes */ skel->rodata->wakeup_data_size = args.sample_rate * 16; - bpf_map__resize(skel->maps.ringbuf, args.ringbuf_sz); + bpf_map__set_max_entries(skel->maps.ringbuf, args.ringbuf_sz); if (ringbuf_bench__load(skel)) { fprintf(stderr, "failed to load skeleton\n"); diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 7f957c55a3ca..0c481de2833d 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -154,7 +154,6 @@ static void *uprobe_producer_without_nop(void *input) static void usetup(bool use_retprobe, bool use_nop) { size_t uprobe_offset; - ssize_t base_addr; struct bpf_link *link; setup_libbpf(); @@ -165,11 +164,10 @@ static void usetup(bool use_retprobe, bool use_nop) exit(1); } - base_addr = get_base_addr(); if (use_nop) - uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop, base_addr); + uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop); else - uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop, base_addr); + uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop); link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe, use_retprobe, diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index df3b292a8ffe..27d63be47b95 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -13,6 +13,10 @@ #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" +typedef int (*func_proto_typedef)(long); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef); +typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); + DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; noinline void @@ -21,6 +25,27 @@ bpf_testmod_test_mod_kfunc(int i) *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; } +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 __user *p; +}; + +noinline int +bpf_testmod_test_btf_type_tag_user_1(struct bpf_testmod_btf_type_tag_1 __user *arg) { + BTF_TYPE_EMIT(func_proto_typedef); + BTF_TYPE_EMIT(func_proto_typedef_nested1); + BTF_TYPE_EMIT(func_proto_typedef_nested2); + return arg->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_user_2(struct bpf_testmod_btf_type_tag_2 *arg) { + return arg->p->a; +} + noinline int bpf_testmod_loop_test(int n) { int i, sum = 0; @@ -109,26 +134,31 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; -BTF_SET_START(bpf_testmod_kfunc_ids) +BTF_SET_START(bpf_testmod_check_kfunc_ids) BTF_ID(func, bpf_testmod_test_mod_kfunc) -BTF_SET_END(bpf_testmod_kfunc_ids) +BTF_SET_END(bpf_testmod_check_kfunc_ids) + +static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &bpf_testmod_check_kfunc_ids, +}; -static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set); +extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) { int ret; - ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); - if (ret) + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); - return 0; + if (bpf_fentry_test1(0) < 0) + return -EINVAL; + return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } static void bpf_testmod_exit(void) { - unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f6287132fa89..763db63a3890 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -48,3 +48,8 @@ CONFIG_IMA_READ_POLICY=y CONFIG_BLK_DEV_LOOP=y CONFIG_FUNCTION_TRACER=y CONFIG_DYNAMIC_FTRACE=y +CONFIG_NETFILTER=y +CONFIG_NF_DEFRAG_IPV4=y +CONFIG_NF_DEFRAG_IPV6=y +CONFIG_NF_CONNTRACK=y +CONFIG_USERFAULTFD=y diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 86b7d5d84eec..ab62aba10e2b 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -7,18 +7,18 @@ static void test_add(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; int link_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); link_fd = atomics_lskel__add__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(add)")) return; prog_fd = skel->progs.add.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) goto cleanup; ASSERT_EQ(skel->data->add64_value, 3, "add64_value"); @@ -39,19 +39,18 @@ cleanup: static void test_sub(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; int link_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); link_fd = atomics_lskel__sub__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(sub)")) return; prog_fd = skel->progs.sub.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run sub", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) goto cleanup; ASSERT_EQ(skel->data->sub64_value, -1, "sub64_value"); @@ -72,18 +71,18 @@ cleanup: static void test_and(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; int link_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); link_fd = atomics_lskel__and__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(and)")) return; prog_fd = skel->progs.and.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run and", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) goto cleanup; ASSERT_EQ(skel->data->and64_value, 0x010ull << 32, "and64_value"); @@ -100,19 +99,18 @@ cleanup: static void test_or(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; int link_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); link_fd = atomics_lskel__or__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(or)")) return; prog_fd = skel->progs.or.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run or", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) goto cleanup; ASSERT_EQ(skel->data->or64_value, 0x111ull << 32, "or64_value"); @@ -129,18 +127,18 @@ cleanup: static void test_xor(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; int link_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); link_fd = atomics_lskel__xor__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(xor)")) return; prog_fd = skel->progs.xor.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xor", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) goto cleanup; ASSERT_EQ(skel->data->xor64_value, 0x101ull << 32, "xor64_value"); @@ -157,18 +155,18 @@ cleanup: static void test_cmpxchg(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; int link_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); link_fd = atomics_lskel__cmpxchg__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)")) return; prog_fd = skel->progs.cmpxchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run cmpxchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) goto cleanup; ASSERT_EQ(skel->data->cmpxchg64_value, 2, "cmpxchg64_value"); @@ -186,18 +184,18 @@ cleanup: static void test_xchg(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; int link_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); link_fd = atomics_lskel__xchg__attach(skel); if (!ASSERT_GT(link_fd, 0, "attach(xchg)")) return; prog_fd = skel->progs.xchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + goto cleanup; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) goto cleanup; ASSERT_EQ(skel->data->xchg64_value, 2, "xchg64_value"); diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index d0bd51eb23c8..d48f6e533e1e 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -5,9 +5,10 @@ /* this is how USDT semaphore is actually defined, except volatile modifier */ volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes"))); -/* attach point */ -static void method(void) { - return ; +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); } void test_attach_probe(void) @@ -17,8 +18,7 @@ void test_attach_probe(void) struct bpf_link *kprobe_link, *kretprobe_link; struct bpf_link *uprobe_link, *uretprobe_link; struct test_attach_probe* skel; - size_t uprobe_offset; - ssize_t base_addr, ref_ctr_offset; + ssize_t uprobe_offset, ref_ctr_offset; bool legacy; /* Check if new-style kprobe/uprobe API is supported. @@ -34,11 +34,9 @@ void test_attach_probe(void) */ legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0; - base_addr = get_base_addr(); - if (CHECK(base_addr < 0, "get_base_addr", - "failed to find base addr: %zd", base_addr)) + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) return; - uprobe_offset = get_uprobe_offset(&method, base_addr); ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr); if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset")) @@ -103,7 +101,7 @@ void test_attach_probe(void) goto cleanup; /* trigger & validate uprobe & uretprobe */ - method(); + trigger_func(); if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res", "wrong uprobe res: %d\n", skel->bss->uprobe_res)) diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c index d0f06e40c16d..eac71fbb24ce 100644 --- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c +++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c @@ -1,13 +1,24 @@ // SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include "bind_perm.skel.h" - +#define _GNU_SOURCE +#include <sched.h> +#include <stdlib.h> #include <sys/types.h> #include <sys/socket.h> #include <sys/capability.h> +#include "test_progs.h" +#include "bind_perm.skel.h" + static int duration; +static int create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return -1; + + return 0; +} + void try_bind(int family, int port, int expected_errno) { struct sockaddr_storage addr = {}; @@ -75,6 +86,9 @@ void test_bind_perm(void) struct bind_perm *skel; int cgroup_fd; + if (create_netns()) + return; + cgroup_fd = test__join_cgroup("/bind_perm"); if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 5eea3c3a40fe..cd10df6cd0fc 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -8,6 +8,12 @@ #include <test_progs.h> #include "test_bpf_cookie.skel.h" +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); +} + static void kprobe_subtest(struct test_bpf_cookie *skel) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); @@ -62,11 +68,11 @@ static void uprobe_subtest(struct test_bpf_cookie *skel) DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); struct bpf_link *link1 = NULL, *link2 = NULL; struct bpf_link *retlink1 = NULL, *retlink2 = NULL; - size_t uprobe_offset; - ssize_t base_addr; + ssize_t uprobe_offset; - base_addr = get_base_addr(); - uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr); + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) + goto cleanup; /* attach two uprobes */ opts.bpf_cookie = 0x100; @@ -99,7 +105,7 @@ static void uprobe_subtest(struct test_bpf_cookie *skel) goto cleanup; /* trigger uprobe && uretprobe */ - get_base_addr(); + trigger_func(); ASSERT_EQ(skel->bss->uprobe_res, 0x100 | 0x200, "uprobe_res"); ASSERT_EQ(skel->bss->uretprobe_res, 0x1000 | 0x2000, "uretprobe_res"); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index b84f859b1267..5142a7d130b2 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -138,6 +138,24 @@ static void test_task(void) bpf_iter_task__destroy(skel); } +static void test_task_sleepable(void) +{ + struct bpf_iter_task *skel; + + skel = bpf_iter_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + return; + + do_dummy_read(skel->progs.dump_task_sleepable); + + ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0, + "num_expected_failure_copy_from_user_task"); + ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, + "num_success_copy_from_user_task"); + + bpf_iter_task__destroy(skel); +} + static void test_task_stack(void) { struct bpf_iter_task_stack *skel; @@ -1252,6 +1270,8 @@ void test_bpf_iter(void) test_bpf_map(); if (test__start_subtest("task")) test_task(); + if (test__start_subtest("task_sleepable")) + test_task_sleepable(); if (test__start_subtest("task_stack")) test_task_stack(); if (test__start_subtest("task_file")) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..ee725d4d98a5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include <sys/socket.h> +#include <sys/un.h> +#include <test_progs.h> +#include "bpf_iter_setsockopt_unix.skel.h" + +#define NR_CASES 5 + +static int create_unix_socket(struct bpf_iter_setsockopt_unix *skel) +{ + struct sockaddr_un addr = { + .sun_family = AF_UNIX, + .sun_path = "", + }; + socklen_t len; + int fd, err; + + fd = socket(AF_UNIX, SOCK_STREAM, 0); + if (!ASSERT_NEQ(fd, -1, "socket")) + return -1; + + len = offsetof(struct sockaddr_un, sun_path); + err = bind(fd, (struct sockaddr *)&addr, len); + if (!ASSERT_OK(err, "bind")) + return -1; + + len = sizeof(addr); + err = getsockname(fd, (struct sockaddr *)&addr, &len); + if (!ASSERT_OK(err, "getsockname")) + return -1; + + memcpy(&skel->bss->sun_path, &addr.sun_path, + len - offsetof(struct sockaddr_un, sun_path)); + + return fd; +} + +static void test_sndbuf(struct bpf_iter_setsockopt_unix *skel, int fd) +{ + socklen_t optlen; + int i, err; + + for (i = 0; i < NR_CASES; i++) { + if (!ASSERT_NEQ(skel->data->sndbuf_getsockopt[i], -1, + "bpf_(get|set)sockopt")) + return; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->data->sndbuf_setsockopt[i]), + sizeof(skel->data->sndbuf_setsockopt[i])); + if (!ASSERT_OK(err, "setsockopt")) + return; + + optlen = sizeof(skel->bss->sndbuf_getsockopt_expected[i]); + err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->bss->sndbuf_getsockopt_expected[i]), + &optlen); + if (!ASSERT_OK(err, "getsockopt")) + return; + + if (!ASSERT_EQ(skel->data->sndbuf_getsockopt[i], + skel->bss->sndbuf_getsockopt_expected[i], + "bpf_(get|set)sockopt")) + return; + } +} + +void test_bpf_iter_setsockopt_unix(void) +{ + struct bpf_iter_setsockopt_unix *skel; + int err, unix_fd, iter_fd; + char buf; + + skel = bpf_iter_setsockopt_unix__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + unix_fd = create_unix_socket(skel); + if (!ASSERT_NEQ(unix_fd, -1, "create_unix_server")) + goto destroy; + + skel->links.change_sndbuf = bpf_program__attach_iter(skel->progs.change_sndbuf, NULL); + if (!ASSERT_OK_PTR(skel->links.change_sndbuf, "bpf_program__attach_iter")) + goto destroy; + + iter_fd = bpf_iter_create(bpf_link__fd(skel->links.change_sndbuf)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto destroy; + + while ((err = read(iter_fd, &buf, sizeof(buf))) == -1 && + errno == EAGAIN) + ; + if (!ASSERT_OK(err, "read iter error")) + goto destroy; + + test_sndbuf(skel, unix_fd); +destroy: + bpf_iter_setsockopt_unix__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c new file mode 100644 index 000000000000..d43f548c572c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> +#include <pthread.h> +#include <sys/mman.h> +#include <stdatomic.h> +#include <test_progs.h> +#include <sys/syscall.h> +#include <linux/module.h> +#include <linux/userfaultfd.h> + +#include "ksym_race.skel.h" +#include "bpf_mod_race.skel.h" +#include "kfunc_call_race.skel.h" + +/* This test crafts a race between btf_try_get_module and do_init_module, and + * checks whether btf_try_get_module handles the invocation for a well-formed + * but uninitialized module correctly. Unless the module has completed its + * initcalls, the verifier should fail the program load and return ENXIO. + * + * userfaultfd is used to trigger a fault in an fmod_ret program, and make it + * sleep, then the BPF program is loaded and the return value from verifier is + * inspected. After this, the userfaultfd is closed so that the module loading + * thread makes forward progress, and fmod_ret injects an error so that the + * module load fails and it is freed. + * + * If the verifier succeeded in loading the supplied program, it will end up + * taking reference to freed module, and trigger a crash when the program fd + * is closed later. This is true for both kfuncs and ksyms. In both cases, + * the crash is triggered inside bpf_prog_free_deferred, when module reference + * is finally released. + */ + +struct test_config { + const char *str_open; + void *(*bpf_open_and_load)(); + void (*bpf_destroy)(void *); +}; + +enum test_state { + _TS_INVALID, + TS_MODULE_LOAD, + TS_MODULE_LOAD_FAIL, +}; + +static _Atomic enum test_state state = _TS_INVALID; + +static int sys_finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int sys_delete_module(const char *name, unsigned int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +static int load_module(const char *mod) +{ + int ret, fd; + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) + return fd; + + ret = sys_finit_module(fd, "", 0); + close(fd); + if (ret < 0) + return ret; + return 0; +} + +static void *load_module_thread(void *p) +{ + + if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + atomic_store(&state, TS_MODULE_LOAD); + else + atomic_store(&state, TS_MODULE_LOAD_FAIL); + return p; +} + +static int sys_userfaultfd(int flags) +{ + return syscall(__NR_userfaultfd, flags); +} + +static int test_setup_uffd(void *fault_addr) +{ + struct uffdio_register uffd_register = {}; + struct uffdio_api uffd_api = {}; + int uffd; + + uffd = sys_userfaultfd(O_CLOEXEC); + if (uffd < 0) + return -errno; + + uffd_api.api = UFFD_API; + uffd_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffd_api)) { + close(uffd); + return -1; + } + + uffd_register.range.start = (unsigned long)fault_addr; + uffd_register.range.len = 4096; + uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) { + close(uffd); + return -1; + } + return uffd; +} + +static void test_bpf_mod_race_config(const struct test_config *config) +{ + void *fault_addr, *skel_fail; + struct bpf_mod_race *skel; + struct uffd_msg uffd_msg; + pthread_t load_mod_thrd; + _Atomic int *blockingp; + int uffd, ret; + + fault_addr = mmap(0, 4096, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) + return; + + if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + goto end_mmap; + + skel = bpf_mod_race__open(); + if (!ASSERT_OK_PTR(skel, "bpf_mod_kfunc_race__open")) + goto end_module; + + skel->rodata->bpf_mod_race_config.tgid = getpid(); + skel->rodata->bpf_mod_race_config.inject_error = -4242; + skel->rodata->bpf_mod_race_config.fault_addr = fault_addr; + if (!ASSERT_OK(bpf_mod_race__load(skel), "bpf_mod___load")) + goto end_destroy; + blockingp = (_Atomic int *)&skel->bss->bpf_blocking; + + if (!ASSERT_OK(bpf_mod_race__attach(skel), "bpf_mod_kfunc_race__attach")) + goto end_destroy; + + uffd = test_setup_uffd(fault_addr); + if (!ASSERT_GE(uffd, 0, "userfaultfd open + register address")) + goto end_destroy; + + if (!ASSERT_OK(pthread_create(&load_mod_thrd, NULL, load_module_thread, NULL), + "load module thread")) + goto end_uffd; + + /* Now, we either fail loading module, or block in bpf prog, spin to find out */ + while (!atomic_load(&state) && !atomic_load(blockingp)) + ; + if (!ASSERT_EQ(state, _TS_INVALID, "module load should block")) + goto end_join; + if (!ASSERT_EQ(*blockingp, 1, "module load blocked")) { + pthread_kill(load_mod_thrd, SIGKILL); + goto end_uffd; + } + + /* We might have set bpf_blocking to 1, but may have not blocked in + * bpf_copy_from_user. Read userfaultfd descriptor to verify that. + */ + if (!ASSERT_EQ(read(uffd, &uffd_msg, sizeof(uffd_msg)), sizeof(uffd_msg), + "read uffd block event")) + goto end_join; + if (!ASSERT_EQ(uffd_msg.event, UFFD_EVENT_PAGEFAULT, "read uffd event is pagefault")) + goto end_join; + + /* We know that load_mod_thrd is blocked in the fmod_ret program, the + * module state is still MODULE_STATE_COMING because mod->init hasn't + * returned. This is the time we try to load a program calling kfunc and + * check if we get ENXIO from verifier. + */ + skel_fail = config->bpf_open_and_load(); + ret = errno; + if (!ASSERT_EQ(skel_fail, NULL, config->str_open)) { + /* Close uffd to unblock load_mod_thrd */ + close(uffd); + uffd = -1; + while (atomic_load(blockingp) != 2) + ; + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); + config->bpf_destroy(skel_fail); + goto end_join; + + } + ASSERT_EQ(ret, ENXIO, "verifier returns ENXIO"); + ASSERT_EQ(skel->data->res_try_get_module, false, "btf_try_get_module == false"); + + close(uffd); + uffd = -1; +end_join: + pthread_join(load_mod_thrd, NULL); + if (uffd < 0) + ASSERT_EQ(atomic_load(&state), TS_MODULE_LOAD_FAIL, "load_mod_thrd success"); +end_uffd: + if (uffd >= 0) + close(uffd); +end_destroy: + bpf_mod_race__destroy(skel); + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); +end_module: + sys_delete_module("bpf_testmod", 0); + ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); +end_mmap: + munmap(fault_addr, 4096); + atomic_store(&state, _TS_INVALID); +} + +static const struct test_config ksym_config = { + .str_open = "ksym_race__open_and_load", + .bpf_open_and_load = (void *)ksym_race__open_and_load, + .bpf_destroy = (void *)ksym_race__destroy, +}; + +static const struct test_config kfunc_config = { + .str_open = "kfunc_call_race__open_and_load", + .bpf_open_and_load = (void *)kfunc_call_race__open_and_load, + .bpf_destroy = (void *)kfunc_call_race__destroy, +}; + +void serial_test_bpf_mod_race(void) +{ + if (test__start_subtest("ksym (used_btfs UAF)")) + test_bpf_mod_race_config(&ksym_config); + if (test__start_subtest("kfunc (kfunc_btf_tab UAF)")) + test_bpf_mod_race_config(&kfunc_config); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c new file mode 100644 index 000000000000..dd30b1e3a67c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include "test_bpf_nf.skel.h" + +enum { + TEST_XDP, + TEST_TC_BPF, +}; + +void test_bpf_nf_ct(int mode) +{ + struct test_bpf_nf *skel; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + + skel = test_bpf_nf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load")) + return; + + if (mode == TEST_XDP) + prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test); + else + prog_fd = bpf_program__fd(skel->progs.nf_skb_ct_test); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto end; + + ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple"); + ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0"); + ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1"); + ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ"); + ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP"); + ASSERT_EQ(skel->bss->test_enonet_netns_id, -ENONET, "Test ENONET for bad but valid netns_id"); + ASSERT_EQ(skel->bss->test_enoent_lookup, -ENOENT, "Test ENOENT for failed lookup"); + ASSERT_EQ(skel->bss->test_eafnosupport, -EAFNOSUPPORT, "Test EAFNOSUPPORT for invalid len__tuple"); +end: + test_bpf_nf__destroy(skel); +} + +void test_bpf_nf(void) +{ + if (test__start_subtest("xdp-ct")) + test_bpf_nf_ct(TEST_XDP); + if (test__start_subtest("tc-bpf-ct")) + test_bpf_nf_ct(TEST_TC_BPF); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 8ba53acf9eb4..8b652f5ce423 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3939,6 +3939,25 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { + .descr = "decl_tag test #15, func, invalid func proto", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_DECL_TAG_ENC(NAME_TBD, 3, 0), /* [2] */ + BTF_FUNC_ENC(NAME_TBD, 8), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag\0func"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ .descr = "type_tag test #1", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ @@ -4560,6 +4579,8 @@ static void do_test_file(unsigned int test_num) has_btf_ext = btf_ext != NULL; btf_ext__free(btf_ext); + /* temporary disable LIBBPF_STRICT_MAP_DEFINITIONS to test legacy maps */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); obj = bpf_object__open(test->file); err = libbpf_get_error(obj); if (CHECK(err, "obj: %d", err)) @@ -4684,6 +4705,8 @@ skip: fprintf(stderr, "OK"); done: + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + btf__free(btf); free(func_info); bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c index 88d63e23e35f..f7560b54a6bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_tag.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c @@ -1,19 +1,21 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ #include <test_progs.h> -#include "btf_decl_tag.skel.h" +#include <bpf/btf.h> +#include "test_btf_decl_tag.skel.h" /* struct btf_type_tag_test is referenced in btf_type_tag.skel.h */ struct btf_type_tag_test { int **p; }; #include "btf_type_tag.skel.h" +#include "btf_type_tag_user.skel.h" static void test_btf_decl_tag(void) { - struct btf_decl_tag *skel; + struct test_btf_decl_tag *skel; - skel = btf_decl_tag__open_and_load(); + skel = test_btf_decl_tag__open_and_load(); if (!ASSERT_OK_PTR(skel, "btf_decl_tag")) return; @@ -22,7 +24,7 @@ static void test_btf_decl_tag(void) test__skip(); } - btf_decl_tag__destroy(skel); + test_btf_decl_tag__destroy(skel); } static void test_btf_type_tag(void) @@ -41,10 +43,101 @@ static void test_btf_type_tag(void) btf_type_tag__destroy(skel); } +static void test_btf_type_tag_mod_user(bool load_test_user1) +{ + const char *module_name = "bpf_testmod"; + struct btf *vmlinux_btf, *module_btf; + struct btf_type_tag_user *skel; + __s32 type_id; + int err; + + if (!env.has_testmod) { + test__skip(); + return; + } + + /* skip the test if the module does not have __user tags */ + vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(vmlinux_btf, "could not load vmlinux BTF")) + return; + + module_btf = btf__load_module_btf(module_name, vmlinux_btf); + if (!ASSERT_OK_PTR(module_btf, "could not load module BTF")) + goto free_vmlinux_btf; + + type_id = btf__find_by_name_kind(module_btf, "user", BTF_KIND_TYPE_TAG); + if (type_id <= 0) { + printf("%s:SKIP: btf_type_tag attribute not in %s", __func__, module_name); + test__skip(); + goto free_module_btf; + } + + skel = btf_type_tag_user__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) + goto free_module_btf; + + bpf_program__set_autoload(skel->progs.test_sys_getsockname, false); + if (load_test_user1) + bpf_program__set_autoload(skel->progs.test_user2, false); + else + bpf_program__set_autoload(skel->progs.test_user1, false); + + err = btf_type_tag_user__load(skel); + ASSERT_ERR(err, "btf_type_tag_user"); + + btf_type_tag_user__destroy(skel); + +free_module_btf: + btf__free(module_btf); +free_vmlinux_btf: + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_vmlinux_user(void) +{ + struct btf_type_tag_user *skel; + struct btf *vmlinux_btf; + __s32 type_id; + int err; + + /* skip the test if the vmlinux does not have __user tags */ + vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(vmlinux_btf, "could not load vmlinux BTF")) + return; + + type_id = btf__find_by_name_kind(vmlinux_btf, "user", BTF_KIND_TYPE_TAG); + if (type_id <= 0) { + printf("%s:SKIP: btf_type_tag attribute not in vmlinux btf", __func__); + test__skip(); + goto free_vmlinux_btf; + } + + skel = btf_type_tag_user__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) + goto free_vmlinux_btf; + + bpf_program__set_autoload(skel->progs.test_user2, false); + bpf_program__set_autoload(skel->progs.test_user1, false); + + err = btf_type_tag_user__load(skel); + ASSERT_ERR(err, "btf_type_tag_user"); + + btf_type_tag_user__destroy(skel); + +free_vmlinux_btf: + btf__free(vmlinux_btf); +} + void test_btf_tag(void) { if (test__start_subtest("btf_decl_tag")) test_btf_decl_tag(); if (test__start_subtest("btf_type_tag")) test_btf_type_tag(); + if (test__start_subtest("btf_type_tag_user_mod1")) + test_btf_type_tag_mod_user(true); + if (test__start_subtest("btf_type_tag_user_mod2")) + test_btf_type_tag_mod_user(false); + if (test__start_subtest("btf_type_tag_sys_user_vmlinux")) + test_btf_type_tag_vmlinux_user(); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index d3e8f729c623..38b3c47293da 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -194,14 +194,14 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE; attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_override", "unexpected success\n")) goto err; CHECK_FAIL(errno != EINVAL); attach_opts.flags = BPF_F_REPLACE; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_multi", "unexpected success\n")) goto err; @@ -209,7 +209,7 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE; attach_opts.replace_prog_fd = -1; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_bad_fd", "unexpected success\n")) goto err; @@ -217,7 +217,7 @@ void serial_test_cgroup_attach_multi(void) /* replacing a program that is not attached to cgroup should fail */ attach_opts.replace_prog_fd = allow_prog[3]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_ent", "unexpected success\n")) goto err; @@ -225,14 +225,14 @@ void serial_test_cgroup_attach_multi(void) /* replace 1st from the top program */ attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; /* replace program with itself */ attach_opts.replace_prog_fd = allow_prog[6]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c new file mode 100644 index 000000000000..0b47c3c000c7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <test_progs.h> +#include <cgroup_helpers.h> +#include <network_helpers.h> + +#include "cgroup_getset_retval_setsockopt.skel.h" +#include "cgroup_getset_retval_getsockopt.skel.h" + +#define SOL_CUSTOM 0xdeadbeef + +static int zero; + +static void test_setsockopt_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, assert that + * we actually get that error when we run setsockopt() + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, and one that gets the + * previously set errno. Assert that we get the same errno back. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno. + * Assert that, without anything setting one, we get 0. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL, *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno, and then + * one that sets the errno to EUNATCH. Assert that the get does not + * see EUNATCH set later, and does not prevent EUNATCH from being set. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_set_eisconn = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, + * and then one that gets the exported errno. Assert both the syscall + * and the helper sees the last set errno. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EISCONN, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_legacy_eperm = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that return a reject without setting errno + * (legacy reject), and one that gets the errno. Assert that for + * backward compatibility the syscall result in EPERM, and this + * is also visible to the helper. + */ + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EPERM, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EPERM, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_legacy_eperm = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that return a reject + * without setting errno, and then one that gets the exported errno. + * Assert both the syscall and the helper's errno are unaffected by + * the second prog (i.e. legacy rejects does not override the errno + * to EPERM). + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_getsockopt_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that gets previously set errno. Assert that the + * error from kernel is in both ctx_retval_value and retval_value. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EOPNOTSUPP, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EOPNOTSUPP, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, -EOPNOTSUPP, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN. Assert that this + * overrides the value from kernel. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL, *link_clear_retval = NULL; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN, and one that clears + * ctx retval. Assert that the clearing ctx retval is synced to helper + * and clears any errors both from kernel and BPF.. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_clear_retval = bpf_program__attach_cgroup(obj->progs.clear_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_clear_retval, "cg-attach-clear_retval")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, 0, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_clear_retval); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +void test_cgroup_getset_retval(void) +{ + int cgroup_fd = -1; + int sock_fd = -1; + + cgroup_fd = test__join_cgroup("/cgroup_getset_retval"); + if (!ASSERT_GE(cgroup_fd, 0, "cg-create")) + goto close_fd; + + sock_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(sock_fd, 0, "start-server")) + goto close_fd; + + if (test__start_subtest("setsockopt-set")) + test_setsockopt_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-set_and_get")) + test_setsockopt_set_and_get(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero")) + test_setsockopt_default_zero(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero_and_set")) + test_setsockopt_default_zero_and_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-override")) + test_setsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_eperm")) + test_setsockopt_legacy_eperm(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_no_override")) + test_setsockopt_legacy_no_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-get")) + test_getsockopt_get(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-override")) + test_getsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-retval_sync")) + test_getsockopt_retval_sync(cgroup_fd, sock_fd); + +close_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index f73e6e36b74d..12f4395f18b3 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -79,28 +79,21 @@ static void test_check_mtu_run_xdp(struct test_check_mtu *skel, struct bpf_program *prog, __u32 mtu_expect) { - const char *prog_name = bpf_program__name(prog); int retval_expect = XDP_PASS; __u32 mtu_result = 0; char buf[256] = {}; - int err; - struct bpf_prog_test_run_attr tattr = { + int err, prog_fd = bpf_program__fd(prog); + LIBBPF_OPTS(bpf_test_run_opts, topts, .repeat = 1, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .data_out = buf, .data_size_out = sizeof(buf), - .prog_fd = bpf_program__fd(prog), - }; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0, "bpf_prog_test_run", - "prog_name:%s (err %d errno %d retval %d)\n", - prog_name, err, errno, tattr.retval); + ); - CHECK(tattr.retval != retval_expect, "retval", - "progname:%s unexpected retval=%d expected=%d\n", - prog_name, tattr.retval, retval_expect); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, retval_expect, "retval"); /* Extract MTU that BPF-prog got */ mtu_result = skel->bss->global_bpf_mtu_xdp; @@ -139,28 +132,21 @@ static void test_check_mtu_run_tc(struct test_check_mtu *skel, struct bpf_program *prog, __u32 mtu_expect) { - const char *prog_name = bpf_program__name(prog); int retval_expect = BPF_OK; __u32 mtu_result = 0; char buf[256] = {}; - int err; - struct bpf_prog_test_run_attr tattr = { - .repeat = 1, + int err, prog_fd = bpf_program__fd(prog); + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .data_out = buf, .data_size_out = sizeof(buf), - .prog_fd = bpf_program__fd(prog), - }; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0, "bpf_prog_test_run", - "prog_name:%s (err %d errno %d retval %d)\n", - prog_name, err, errno, tattr.retval); + .repeat = 1, + ); - CHECK(tattr.retval != retval_expect, "retval", - "progname:%s unexpected retval=%d expected=%d\n", - prog_name, tattr.retval, retval_expect); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, retval_expect, "retval"); /* Extract MTU that BPF-prog got */ mtu_result = skel->bss->global_bpf_mtu_tc; diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c index e075d03ab630..224f016b0a53 100644 --- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -161,7 +161,7 @@ static socklen_t prepare_addr(struct sockaddr_storage *addr, int family) } } -static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr) +static bool was_decapsulated(struct bpf_test_run_opts *tattr) { return tattr->data_size_out < tattr->data_size_in; } @@ -367,12 +367,12 @@ static void close_fds(int *fds, int n) static void test_cls_redirect_common(struct bpf_program *prog) { - struct bpf_prog_test_run_attr tattr = {}; + LIBBPF_OPTS(bpf_test_run_opts, tattr); int families[] = { AF_INET, AF_INET6 }; struct sockaddr_storage ss; struct sockaddr *addr; socklen_t slen; - int i, j, err; + int i, j, err, prog_fd; int servers[__NR_KIND][ARRAY_SIZE(families)] = {}; int conns[__NR_KIND][ARRAY_SIZE(families)] = {}; struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)]; @@ -394,7 +394,7 @@ static void test_cls_redirect_common(struct bpf_program *prog) goto cleanup; } - tattr.prog_fd = bpf_program__fd(prog); + prog_fd = bpf_program__fd(prog); for (i = 0; i < ARRAY_SIZE(tests); i++) { struct test_cfg *test = &tests[i]; @@ -415,7 +415,7 @@ static void test_cls_redirect_common(struct bpf_program *prog) if (CHECK_FAIL(!tattr.data_size_in)) continue; - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); if (CHECK_FAIL(err)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern.c b/tools/testing/selftests/bpf/prog_tests/core_kern.c index 561c5185d886..6a5a1c019a5d 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_kern.c +++ b/tools/testing/selftests/bpf/prog_tests/core_kern.c @@ -7,8 +7,22 @@ void test_core_kern_lskel(void) { struct core_kern_lskel *skel; + int link_fd; skel = core_kern_lskel__open_and_load(); - ASSERT_OK_PTR(skel, "open_and_load"); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + link_fd = core_kern_lskel__core_relo_proto__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(core_relo_proto)")) + goto cleanup; + + /* trigger tracepoints */ + usleep(1); + ASSERT_TRUE(skel->bss->proto_out[0], "bpf_core_type_exists"); + ASSERT_FALSE(skel->bss->proto_out[1], "!bpf_core_type_exists"); + ASSERT_TRUE(skel->bss->proto_out[2], "bpf_core_type_exists. nested"); + +cleanup: core_kern_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c b/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c new file mode 100644 index 000000000000..04cc145bc26a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "test_progs.h" +#include "core_kern_overflow.lskel.h" + +void test_core_kern_overflow_lskel(void) +{ + struct core_kern_overflow_lskel *skel; + + skel = core_kern_overflow_lskel__open_and_load(); + if (!ASSERT_NULL(skel, "open_and_load")) + core_kern_overflow_lskel__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index cbaa44ffb8c6..5aa52cc31dc2 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -26,10 +26,10 @@ static void test_dummy_st_ops_attach(void) static void test_dummy_init_ret_value(void) { __u64 args[1] = {0}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; @@ -38,8 +38,7 @@ static void test_dummy_init_ret_value(void) return; fd = bpf_program__fd(skel->progs.test_1); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret"); @@ -53,10 +52,10 @@ static void test_dummy_init_ptr_arg(void) .val = exp_retval, }; __u64 args[1] = {(unsigned long)&in_state}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; @@ -65,8 +64,7 @@ static void test_dummy_init_ptr_arg(void) return; fd = bpf_program__fd(skel->progs.test_1); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret"); ASSERT_EQ(attr.retval, exp_retval, "test_ret"); @@ -77,10 +75,10 @@ static void test_dummy_init_ptr_arg(void) static void test_dummy_multiple_args(void) { __u64 args[5] = {0, -100, 0x8a5f, 'c', 0x1234567887654321ULL}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; size_t i; @@ -91,8 +89,7 @@ static void test_dummy_multiple_args(void) return; fd = bpf_program__fd(skel->progs.test_2); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); for (i = 0; i < ARRAY_SIZE(args); i++) { snprintf(name, sizeof(name), "arg %zu", i); diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 4374ac8a8a91..130f5b82d2e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -9,38 +9,34 @@ void test_fentry_fexit(void) struct fentry_test_lskel *fentry_skel = NULL; struct fexit_test_lskel *fexit_skel = NULL; __u64 *fentry_res, *fexit_res; - __u32 duration = 0, retval; int err, prog_fd, i; + LIBBPF_OPTS(bpf_test_run_opts, topts); fentry_skel = fentry_test_lskel__open_and_load(); - if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) + if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto close_prog; fexit_skel = fexit_test_lskel__open_and_load(); - if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) + if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto close_prog; err = fentry_test_lskel__attach(fentry_skel); - if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) + if (!ASSERT_OK(err, "fentry_attach")) goto close_prog; err = fexit_test_lskel__attach(fexit_skel); - if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) + if (!ASSERT_OK(err, "fexit_attach")) goto close_prog; prog_fd = fexit_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_OK(topts.retval, "ipv6 test retval"); fentry_res = (__u64 *)fentry_skel->bss; fexit_res = (__u64 *)fexit_skel->bss; printf("%lld\n", fentry_skel->bss->test1_result); for (i = 0; i < 8; i++) { - CHECK(fentry_res[i] != 1, "result", - "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); - CHECK(fexit_res[i] != 1, "result", - "fexit_test%d failed err %lld\n", i + 1, fexit_res[i]); + ASSERT_EQ(fentry_res[i], 1, "fentry result"); + ASSERT_EQ(fexit_res[i], 1, "fexit result"); } close_prog: diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 12921b3850d2..c0d1d61d5f66 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -6,9 +6,9 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel) { int err, prog_fd, i; - __u32 duration = 0, retval; int link_fd; __u64 *result; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = fentry_test_lskel__attach(fentry_skel); if (!ASSERT_OK(err, "fentry_attach")) @@ -20,10 +20,9 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel) return -1; prog_fd = fentry_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); result = (__u64 *)fentry_skel->bss; for (i = 0; i < sizeof(*fentry_skel->bss) / sizeof(__u64); i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index c52f99f6a909..d9aad15e0d24 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -58,12 +58,17 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, test_cb cb) { struct bpf_object *obj = NULL, *tgt_obj; - __u32 retval, tgt_prog_id, info_len; + __u32 tgt_prog_id, info_len; struct bpf_prog_info prog_info = {}; struct bpf_program **prog = NULL, *p; struct bpf_link **link = NULL; int err, tgt_fd, i; struct btf *btf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v6, + .data_size_in = sizeof(pkt_v6), + .repeat = 1, + ); err = bpf_prog_test_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); @@ -132,7 +137,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, &link_info, &info_len); ASSERT_OK(err, "link_fd_get_info"); ASSERT_EQ(link_info.tracing.attach_type, - bpf_program__get_expected_attach_type(prog[i]), + bpf_program__expected_attach_type(prog[i]), "link_attach_type"); ASSERT_EQ(link_info.tracing.target_obj_id, tgt_prog_id, "link_tgt_obj_id"); ASSERT_EQ(link_info.tracing.target_btf_id, btf_id, "link_tgt_btf_id"); @@ -147,10 +152,9 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, if (!run_prog) goto close_prog; - err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, NULL); + err = bpf_prog_test_run_opts(tgt_fd, &topts); ASSERT_OK(err, "prog_run"); - ASSERT_EQ(retval, 0, "prog_run_ret"); + ASSERT_EQ(topts.retval, 0, "prog_run_ret"); if (check_data_map(obj, prog_cnt, false)) goto close_prog; @@ -225,29 +229,31 @@ static int test_second_attach(struct bpf_object *obj) const char *tgt_obj_file = "./test_pkt_access.o"; struct bpf_program *prog = NULL; struct bpf_object *tgt_obj; - __u32 duration = 0, retval; struct bpf_link *link; int err = 0, tgt_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v6, + .data_size_in = sizeof(pkt_v6), + .repeat = 1, + ); prog = bpf_object__find_program_by_name(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog %s not found\n", prog_name)) + if (!ASSERT_OK_PTR(prog, "find_prog")) return -ENOENT; err = bpf_prog_test_load(tgt_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); - if (CHECK(err, "second_prog_load", "file %s err %d errno %d\n", - tgt_obj_file, err, errno)) + if (!ASSERT_OK(err, "second_prog_load")) return err; link = bpf_program__attach_freplace(prog, tgt_fd, tgt_name); if (!ASSERT_OK_PTR(link, "second_link")) goto out; - err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(tgt_fd, &topts); + if (!ASSERT_OK(err, "ipv6 test_run")) + goto out; + if (!ASSERT_OK(topts.retval, "ipv6 retval")) goto out; err = check_data_map(obj, 1, true); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index e4cede6b4b2d..3ee2107bbf7a 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -10,9 +10,7 @@ void test_fexit_stress(void) char test_skb[128] = {}; int fexit_fd[CNT] = {}; int link_fd[CNT] = {}; - __u32 duration = 0; char error[4096]; - __u32 prog_ret; int err, i, filter_fd; const struct bpf_insn trace_program[] = { @@ -36,9 +34,15 @@ void test_fexit_stress(void) .log_size = sizeof(error), ); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + .repeat = 1, + ); + err = libbpf_find_vmlinux_btf_id("bpf_fentry_test1", trace_opts.expected_attach_type); - if (CHECK(err <= 0, "find_vmlinux_btf_id", "failed: %d\n", err)) + if (!ASSERT_GT(err, 0, "find_vmlinux_btf_id")) goto out; trace_opts.attach_btf_id = err; @@ -47,24 +51,20 @@ void test_fexit_stress(void) trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), &trace_opts); - if (CHECK(fexit_fd[i] < 0, "fexit loaded", - "failed: %d errno %d\n", fexit_fd[i], errno)) + if (!ASSERT_GE(fexit_fd[i], 0, "fexit load")) goto out; link_fd[i] = bpf_raw_tracepoint_open(NULL, fexit_fd[i]); - if (CHECK(link_fd[i] < 0, "fexit attach failed", - "prog %d failed: %d err %d\n", i, link_fd[i], errno)) + if (!ASSERT_GE(link_fd[i], 0, "fexit attach")) goto out; } filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", skb_program, sizeof(skb_program) / sizeof(struct bpf_insn), &skb_opts); - if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", - filter_fd, errno)) + if (!ASSERT_GE(filter_fd, 0, "test_program_loaded")) goto out; - err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, - 0, &prog_ret, 0); + err = bpf_prog_test_run_opts(filter_fd, &topts); close(filter_fd); CHECK_FAIL(err); out: diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index d4887d8bb396..101b7343036b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -6,9 +6,9 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel) { int err, prog_fd, i; - __u32 duration = 0, retval; int link_fd; __u64 *result; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = fexit_test_lskel__attach(fexit_skel); if (!ASSERT_OK(err, "fexit_attach")) @@ -20,10 +20,9 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel) return -1; prog_fd = fexit_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); result = (__u64 *)fexit_skel->bss; for (i = 0; i < sizeof(*fexit_skel->bss) / sizeof(__u64); i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index ac54e3f91d42..0c1661ea996e 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -13,8 +13,9 @@ #endif #define CHECK_FLOW_KEYS(desc, got, expected) \ - CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ + _CHECK(memcmp(&got, &expected, sizeof(got)) != 0, \ desc, \ + topts.duration, \ "nhoff=%u/%u " \ "thoff=%u/%u " \ "addr_proto=0x%x/0x%x " \ @@ -457,7 +458,7 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) if (map_fd < 0) return -1; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -487,7 +488,7 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *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 = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts); struct bpf_flow_keys flow_keys = {}; __u32 key = (__u32)(tests[i].keys.sport) << 16 | tests[i].keys.dport; @@ -503,13 +504,12 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); - CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err); + ASSERT_OK(err, "bpf_map_lookup_elem"); - 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); + ASSERT_OK(err, "bpf_map_delete_elem"); } } @@ -573,27 +573,24 @@ void test_flow_dissector(void) for (i = 0; i < ARRAY_SIZE(tests); i++) { struct bpf_flow_keys flow_keys; - struct bpf_prog_test_run_attr tattr = { - .prog_fd = prog_fd, + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &tests[i].pkt, .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); + topts.ctx_in = &ctx; + topts.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) || - err || tattr.retval != 1, - tests[i].name, - "err %d errno %d retval %d duration %d size %u/%zu\n", - err, errno, tattr.retval, tattr.duration, - tattr.data_size_out, sizeof(flow_keys)); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 1, "test_run retval"); + ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), + "test_run data_size_out"); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c index 93ac3f28226c..36afb409c25f 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c @@ -5,7 +5,6 @@ void serial_test_flow_dissector_load_bytes(void) { struct bpf_flow_keys flow_keys; - __u32 duration = 0, retval, size; struct bpf_insn prog[] = { // BPF_REG_1 - 1st argument: context // BPF_REG_2 - 2nd argument: offset, start at first byte @@ -27,22 +26,25 @@ void serial_test_flow_dissector_load_bytes(void) BPF_EXIT_INSN(), }; int fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = &flow_keys, + .data_size_out = sizeof(flow_keys), + .repeat = 1, + ); /* make sure bpf_skb_load_bytes is not allowed from skb-less context */ fd = bpf_test_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); - CHECK(fd < 0, - "flow_dissector-bpf_skb_load_bytes-load", - "fd %d errno %d\n", - fd, errno); + ASSERT_GE(fd, 0, "bpf_test_load_program good fd"); - err = bpf_prog_test_run(fd, 1, &pkt_v4, sizeof(pkt_v4), - &flow_keys, &size, &retval, &duration); - CHECK(size != sizeof(flow_keys) || err || retval != 1, - "flow_dissector-bpf_skb_load_bytes", - "err %d errno %d retval %d duration %d size %u/%zu\n", - err, errno, retval, duration, size, sizeof(flow_keys)); + err = bpf_prog_test_run_opts(fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), + "test_run data_size_out"); + ASSERT_EQ(topts.retval, 1, "test_run retval"); if (fd >= -1) close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c index 68eb12a287d4..044df13ee069 100644 --- a/tools/testing/selftests/bpf/prog_tests/for_each.c +++ b/tools/testing/selftests/bpf/prog_tests/for_each.c @@ -12,8 +12,13 @@ static void test_hash_map(void) int i, err, hashmap_fd, max_entries, percpu_map_fd; struct for_each_hash_map_elem *skel; __u64 *percpu_valbuf = NULL; - __u32 key, num_cpus, retval; + __u32 key, num_cpus; __u64 val; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = for_each_hash_map_elem__open_and_load(); if (!ASSERT_OK_PTR(skel, "for_each_hash_map_elem__open_and_load")) @@ -42,11 +47,10 @@ static void test_hash_map(void) if (!ASSERT_OK(err, "percpu_map_update")) goto out; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access), - 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, - &retval, &duration); - if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n", - err, errno, retval)) + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts); + duration = topts.duration; + if (CHECK(err || topts.retval, "ipv4", "err %d errno %d retval %d\n", + err, errno, topts.retval)) goto out; ASSERT_EQ(skel->bss->hashmap_output, 4, "hashmap_output"); @@ -69,11 +73,16 @@ out: static void test_array_map(void) { - __u32 key, num_cpus, max_entries, retval; + __u32 key, num_cpus, max_entries; int i, arraymap_fd, percpu_map_fd, err; struct for_each_array_map_elem *skel; __u64 *percpu_valbuf = NULL; __u64 val, expected_total; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = for_each_array_map_elem__open_and_load(); if (!ASSERT_OK_PTR(skel, "for_each_array_map_elem__open_and_load")) @@ -106,11 +115,10 @@ static void test_array_map(void) if (!ASSERT_OK(err, "percpu_map_update")) goto out; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access), - 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, - &retval, &duration); - if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n", - err, errno, retval)) + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts); + duration = topts.duration; + if (CHECK(err || topts.retval, "ipv4", "err %d errno %d retval %d\n", + err, errno, topts.retval)) goto out; ASSERT_EQ(skel->bss->arraymap_output, expected_total, "array_output"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c index 85c427119fe9..28cf63963cb7 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c @@ -5,8 +5,8 @@ void test_get_func_args_test(void) { struct get_func_args_test *skel = NULL; - __u32 duration = 0, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = get_func_args_test__open_and_load(); if (!ASSERT_OK_PTR(skel, "get_func_args_test__open_and_load")) @@ -20,19 +20,17 @@ void test_get_func_args_test(void) * fentry/fexit programs. */ prog_fd = bpf_program__fd(skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); /* This runs bpf_modify_return_test function and triggers * fmod_ret_test and fexit_test programs. */ prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 1234, "test_run"); + ASSERT_EQ(topts.retval, 1234, "test_run"); ASSERT_EQ(skel->bss->test1_result, 1, "test1_result"); ASSERT_EQ(skel->bss->test2_result, 1, "test2_result"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c index 02a465f36d59..938dbd4d7c2f 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c @@ -5,8 +5,8 @@ void test_get_func_ip_test(void) { struct get_func_ip_test *skel = NULL; - __u32 duration = 0, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = get_func_ip_test__open(); if (!ASSERT_OK_PTR(skel, "get_func_ip_test__open")) @@ -29,14 +29,12 @@ void test_get_func_ip_test(void) goto cleanup; prog_fd = bpf_program__fd(skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); prog_fd = bpf_program__fd(skel->progs.test5); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c index 8d5a6023a1bb..5308de1ed478 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c @@ -27,7 +27,7 @@ void test_get_stackid_cannot_attach(void) return; /* override program type */ - bpf_program__set_perf_event(skel->progs.oncpu); + bpf_program__set_type(skel->progs.oncpu, BPF_PROG_TYPE_PERF_EVENT); err = test_stacktrace_build_id__load(skel); if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index 9da131b32e13..6fb3d3155c35 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -121,7 +121,7 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) if (CHECK_FAIL(map_fd < 0)) return; - buff = malloc(bpf_map__def(map)->value_size); + buff = malloc(bpf_map__value_size(map)); if (buff) err = bpf_map_update_elem(map_fd, &zero, buff, 0); free(buff); @@ -132,24 +132,26 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) void test_global_data(void) { const char *file = "./test_global_data.o"; - __u32 duration = 0, retval; struct bpf_object *obj; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (CHECK(err, "load program", "error %d loading %s\n", err, file)) + if (!ASSERT_OK(err, "load program")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "pass global data run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "pass global data run err"); + ASSERT_OK(topts.retval, "pass global data run retval"); - test_global_data_number(obj, duration); - test_global_data_string(obj, duration); - test_global_data_struct(obj, duration); - test_global_data_rdonly(obj, duration); + test_global_data_number(obj, topts.duration); + test_global_data_string(obj, topts.duration); + test_global_data_struct(obj, topts.duration); + test_global_data_rdonly(obj, topts.duration); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c index 1db86eab101b..57331c606964 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c @@ -20,7 +20,7 @@ void test_global_data_init(void) if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) goto out; - sz = bpf_map__def(map)->value_size; + sz = bpf_map__value_size(map); newval = malloc(sz); if (CHECK_FAIL(!newval)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_args.c b/tools/testing/selftests/bpf/prog_tests/global_func_args.c index 93a2439237b0..29039a36cce5 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_func_args.c +++ b/tools/testing/selftests/bpf/prog_tests/global_func_args.c @@ -40,19 +40,21 @@ static void test_global_func_args0(struct bpf_object *obj) void test_global_func_args(void) { const char *file = "./test_global_func_args.o"; - __u32 retval; struct bpf_object *obj; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); if (CHECK(err, "load program", "error %d loading %s\n", err, file)) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "pass global func args run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); test_global_func_args0(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index ce10d2fc3a6c..1cee6957285e 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -53,24 +53,24 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void serial_test_kfree_skb(void) { struct __sk_buff skb = {}; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v6, .data_size_in = sizeof(pkt_v6), .ctx_in = &skb, .ctx_size_in = sizeof(skb), - }; + ); struct kfree_skb *skel = NULL; struct bpf_link *link; struct bpf_object *obj; struct perf_buffer *pb = NULL; - int err; + int err, prog_fd; bool passed = false; __u32 duration = 0; const int zero = 0; bool test_ok[2]; err = bpf_prog_test_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &obj, &tattr.prog_fd); + &obj, &prog_fd); if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) return; @@ -100,11 +100,9 @@ void serial_test_kfree_skb(void) goto close_prog; memcpy(skb.cb, &cb, sizeof(cb)); - err = bpf_prog_test_run_xattr(&tattr); - duration = tattr.duration; - CHECK(err || tattr.retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, tattr.retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_OK(topts.retval, "ipv6 test_run retval"); /* read perf buffer */ err = perf_buffer__poll(pb, 100); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 7d7445ccc141..c00eb974eb85 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -9,23 +9,31 @@ static void test_main(void) { struct kfunc_call_test_lskel *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = skel->progs.kfunc_call_test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 12, "test1-retval"); + ASSERT_EQ(topts.retval, 12, "test1-retval"); prog_fd = skel->progs.kfunc_call_test2.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test2)"); - ASSERT_EQ(retval, 3, "test2-retval"); + ASSERT_EQ(topts.retval, 3, "test2-retval"); + + prog_fd = skel->progs.kfunc_call_test_ref_btf_id.prog_fd; + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "bpf_prog_test_run(test_ref_btf_id)"); + ASSERT_EQ(topts.retval, 0, "test_ref_btf_id-retval"); kfunc_call_test_lskel__destroy(skel); } @@ -33,17 +41,21 @@ static void test_main(void) static void test_subprog(void) { struct kfunc_call_test_subprog *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_subprog__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_EQ(topts.retval, 10, "test1-retval"); ASSERT_NEQ(skel->data->active_res, -1, "active_res"); ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); @@ -53,17 +65,21 @@ static void test_subprog(void) static void test_subprog_lskel(void) { struct kfunc_call_test_subprog_lskel *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_subprog_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = skel->progs.kfunc_call_test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_EQ(topts.retval, 10, "test1-retval"); ASSERT_NEQ(skel->data->active_res, -1, "active_res"); ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index d490ad80eccb..a1ebac70ec29 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -6,11 +6,15 @@ #include "test_ksyms_module.lskel.h" #include "test_ksyms_module.skel.h" -void test_ksyms_module_lskel(void) +static void test_ksyms_module_lskel(void) { struct test_ksyms_module_lskel *skel; - int retval; int err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); if (!env.has_testmod) { test__skip(); @@ -20,20 +24,24 @@ void test_ksyms_module_lskel(void) skel = test_ksyms_module_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_ksyms_module_lskel__open_and_load")) return; - err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(skel->progs.load.prog_fd, &topts); if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(topts.retval, 0, "retval"); ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module_lskel__destroy(skel); } -void test_ksyms_module_libbpf(void) +static void test_ksyms_module_libbpf(void) { struct test_ksyms_module *skel; - int retval, err; + int err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); if (!env.has_testmod) { test__skip(); @@ -43,11 +51,10 @@ void test_ksyms_module_libbpf(void) skel = test_ksyms_module__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open")) return; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4, - sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.load), &topts); if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(topts.retval, 0, "retval"); ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c index 540ef28fabff..55f733ff4109 100644 --- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c +++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c @@ -23,12 +23,16 @@ static void test_l4lb(const char *file) __u8 flags; } real_def = {.dst = MAGIC_VAL}; __u32 ch_key = 11, real_num = 3; - __u32 duration, retval, size; int err, i, prog_fd, map_fd; __u64 bytes = 0, pkts = 0; struct bpf_object *obj; char buf[128]; u32 *magic = (u32 *)buf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = NUM_ITER, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) @@ -49,19 +53,24 @@ static void test_l4lb(const char *file) goto out; bpf_map_update_elem(map_fd, &real_num, &real_def, 0); - err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 || - *magic != MAGIC_VAL, "ipv4", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + topts.data_in = &pkt_v4; + topts.data_size_in = sizeof(pkt_v4); - err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 || - *magic != MAGIC_VAL, "ipv6", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 7 /*TC_ACT_REDIRECT*/, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 54, "ipv4 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv4 magic"); + + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); /* reset out size */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 7 /*TC_ACT_REDIRECT*/, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv6 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv6 magic"); map_fd = bpf_find_map(__func__, obj, "stats"); if (map_fd < 0) diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index e469b023962b..1ef377a7e731 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -202,7 +202,7 @@ static void bpf_btf_load_log_buf(void) const void *raw_btf_data; __u32 raw_btf_size; struct btf *btf; - char *log_buf; + char *log_buf = NULL; int fd = -1; btf = btf__new_empty(); diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index 23d19e9cf26a..e4e99b37df64 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -4,14 +4,17 @@ static void *spin_lock_thread(void *arg) { - __u32 duration, retval; int err, prog_fd = *(u32 *) arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10000, + ); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); - err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); pthread_exit(arg); } diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c index 273725504f11..43e502acf050 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_ptr.c +++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c @@ -9,10 +9,16 @@ void test_map_ptr(void) { struct map_ptr_kern_lskel *skel; - __u32 duration = 0, retval; char buf[128]; int err; int page_size = getpagesize(); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); skel = map_ptr_kern_lskel__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -26,14 +32,12 @@ void test_map_ptr(void) skel->bss->page_size = page_size; - err = bpf_prog_test_run(skel->progs.cg_skb.prog_fd, 1, &pkt_v4, - sizeof(pkt_v4), buf, NULL, &retval, NULL); + err = bpf_prog_test_run_opts(skel->progs.cg_skb.prog_fd, &topts); - if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno)) + if (!ASSERT_OK(err, "test_run")) goto cleanup; - if (CHECK(!retval, "retval", "retval=%d map_type=%u line=%u\n", retval, - skel->bss->g_map_type, skel->bss->g_line)) + if (!ASSERT_NEQ(topts.retval, 0, "test_run retval")) goto cleanup; cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c index b772fe30ce9b..5d9955af6247 100644 --- a/tools/testing/selftests/bpf/prog_tests/modify_return.c +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -15,39 +15,31 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) { struct modify_return *skel = NULL; int err, prog_fd; - __u32 duration = 0, retval; __u16 side_effect; __s16 ret; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = modify_return__open_and_load(); - if (CHECK(!skel, "skel_load", "modify_return skeleton failed\n")) + if (!ASSERT_OK_PTR(skel, "skel_load")) goto cleanup; err = modify_return__attach(skel); - if (CHECK(err, "modify_return", "attach failed: %d\n", err)) + if (!ASSERT_OK(err, "modify_return__attach failed")) goto cleanup; skel->bss->input_retval = input_retval; prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, 0, - &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); - CHECK(err, "test_run", "err %d errno %d\n", err, errno); + side_effect = UPPER(topts.retval); + ret = LOWER(topts.retval); - side_effect = UPPER(retval); - ret = LOWER(retval); - - CHECK(ret != want_ret, "test_run", - "unexpected ret: %d, expected: %d\n", ret, want_ret); - CHECK(side_effect != want_side_effect, "modify_return", - "unexpected side_effect: %d\n", side_effect); - - CHECK(skel->bss->fentry_result != 1, "modify_return", - "fentry failed\n"); - CHECK(skel->bss->fexit_result != 1, "modify_return", - "fexit failed\n"); - CHECK(skel->bss->fmod_ret_result != 1, "modify_return", - "fmod_ret failed\n"); + ASSERT_EQ(ret, want_ret, "test_run ret"); + ASSERT_EQ(side_effect, want_side_effect, "modify_return side_effect"); + ASSERT_EQ(skel->bss->fentry_result, 1, "modify_return fentry_result"); + ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result"); + ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result"); cleanup: modify_return__destroy(skel); @@ -63,4 +55,3 @@ void serial_test_modify_return(void) 0 /* want_side_effect */, -EINVAL /* want_ret */); } - diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c index 6628710ec3c6..0bcccdc34fbc 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c @@ -6,23 +6,27 @@ void test_pkt_access(void) { const char *file = "./test_pkt_access.o"; struct bpf_object *obj; - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 100000, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv4", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4 test_run_opts err"); + ASSERT_OK(topts.retval, "ipv4 test_run_opts retval"); + + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = 0; /* reset from last call */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run_opts err"); + ASSERT_OK(topts.retval, "ipv6 test_run_opts retval"); - err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c index c9d2d6a1bfcc..00ee1dd792aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c @@ -6,18 +6,20 @@ void test_pkt_md_access(void) { const char *file = "./test_pkt_md_access.o"; struct bpf_object *obj; - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c new file mode 100644 index 000000000000..1ccd2bdf8fa8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +#include "test_pkt_access.skel.h" + +static const __u32 duration; + +static void check_run_cnt(int prog_fd, __u64 run_cnt) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) + return; + + CHECK(run_cnt != info.run_cnt, "run_cnt", + "incorrect number of repetitions, want %llu have %llu\n", run_cnt, info.run_cnt); +} + +void test_prog_run_opts(void) +{ + struct test_pkt_access *skel; + int err, stats_fd = -1, prog_fd; + char buf[10] = {}; + __u64 run_cnt = 0; + + LIBBPF_OPTS(bpf_test_run_opts, topts, + .repeat = 1, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = 5, + ); + + stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); + if (!ASSERT_GE(stats_fd, 0, "enable_stats good fd")) + return; + + skel = test_pkt_access__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.test_pkt_access); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_EQ(errno, ENOSPC, "test_run errno"); + ASSERT_ERR(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); + + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), "test_run data_size_out"); + ASSERT_EQ(buf[5], 0, "overflow, BPF_PROG_TEST_RUN ignored size hint"); + + run_cnt += topts.repeat; + check_run_cnt(prog_fd, run_cnt); + + topts.data_out = NULL; + topts.data_size_out = 0; + topts.repeat = 2; + errno = 0; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(errno, "run_no_output errno"); + ASSERT_OK(err, "run_no_output err"); + ASSERT_OK(topts.retval, "run_no_output retval"); + + run_cnt += topts.repeat; + check_run_cnt(prog_fd, run_cnt); + +cleanup: + if (skel) + test_pkt_access__destroy(skel); + if (stats_fd >= 0) + close(stats_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c deleted file mode 100644 index 89fc98faf19e..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ /dev/null @@ -1,83 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include <network_helpers.h> - -#include "test_pkt_access.skel.h" - -static const __u32 duration; - -static void check_run_cnt(int prog_fd, __u64 run_cnt) -{ - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - int err; - - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) - return; - - CHECK(run_cnt != info.run_cnt, "run_cnt", - "incorrect number of repetitions, want %llu have %llu\n", run_cnt, info.run_cnt); -} - -void test_prog_run_xattr(void) -{ - struct test_pkt_access *skel; - int err, stats_fd = -1; - char buf[10] = {}; - __u64 run_cnt = 0; - - struct bpf_prog_test_run_attr tattr = { - .repeat = 1, - .data_in = &pkt_v4, - .data_size_in = sizeof(pkt_v4), - .data_out = buf, - .data_size_out = 5, - }; - - stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); - if (CHECK_ATTR(stats_fd < 0, "enable_stats", "failed %d\n", errno)) - return; - - skel = test_pkt_access__open_and_load(); - if (CHECK_ATTR(!skel, "open_and_load", "failed\n")) - goto cleanup; - - tattr.prog_fd = bpf_program__fd(skel->progs.test_pkt_access); - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err >= 0 || errno != ENOSPC || tattr.retval, "run", - "err %d errno %d retval %d\n", err, errno, tattr.retval); - - CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out", - "incorrect output size, want %zu have %u\n", - sizeof(pkt_v4), tattr.data_size_out); - - CHECK_ATTR(buf[5] != 0, "overflow", - "BPF_PROG_TEST_RUN ignored size hint\n"); - - run_cnt += tattr.repeat; - check_run_cnt(tattr.prog_fd, run_cnt); - - tattr.data_out = NULL; - tattr.data_size_out = 0; - tattr.repeat = 2; - errno = 0; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err || errno || tattr.retval, "run_no_output", - "err %d errno %d retval %d\n", err, errno, tattr.retval); - - tattr.data_size_out = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != -EINVAL, "run_wrong_size_out", "err %d\n", err); - - run_cnt += tattr.repeat; - check_run_cnt(tattr.prog_fd, run_cnt); - -cleanup: - if (skel) - test_pkt_access__destroy(skel); - if (stats_fd >= 0) - close(stats_fd); -} diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index b9822f914eeb..d2743fc10032 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -10,11 +10,18 @@ enum { static void test_queue_stack_map_by_type(int type) { const int MAP_SIZE = 32; - __u32 vals[MAP_SIZE], duration, retval, size, val; + __u32 vals[MAP_SIZE], val; int i, err, prog_fd, map_in_fd, map_out_fd; char file[32], buf[128]; struct bpf_object *obj; struct iphdr iph; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); /* Fill test values to be used */ for (i = 0; i < MAP_SIZE; i++) @@ -58,38 +65,37 @@ static void test_queue_stack_map_by_type(int type) pkt_v4.iph.saddr = vals[MAP_SIZE - 1 - i] * 5; } - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - if (err || retval || size != sizeof(pkt_v4)) + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (err || topts.retval || + topts.data_size_out != sizeof(pkt_v4)) break; memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); if (iph.daddr != val) break; } - CHECK(err || retval || size != sizeof(pkt_v4) || iph.daddr != val, - "bpf_map_pop_elem", - "err %d errno %d retval %d size %d iph->daddr %u\n", - err, errno, retval, size, iph.daddr); + ASSERT_OK(err, "bpf_map_pop_elem"); + ASSERT_OK(topts.retval, "bpf_map_pop_elem test retval"); + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), + "bpf_map_pop_elem data_size_out"); + ASSERT_EQ(iph.daddr, val, "bpf_map_pop_elem iph.daddr"); /* Queue is empty, program should return TC_ACT_SHOT */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 2 /* TC_ACT_SHOT */|| size != sizeof(pkt_v4), - "check-queue-stack-map-empty", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "check-queue-stack-map-empty"); + ASSERT_EQ(topts.retval, 2 /* TC_ACT_SHOT */, + "check-queue-stack-map-empty test retval"); + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), + "check-queue-stack-map-empty data_size_out"); /* Check that the program pushed elements correctly */ for (i = 0; i < MAP_SIZE; i++) { err = bpf_map_lookup_and_delete_elem(map_out_fd, NULL, &val); - if (err || val != vals[i] * 5) - break; + ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"); + ASSERT_EQ(val, vals[i] * 5, "bpf_map_push_elem val"); } - - CHECK(i != MAP_SIZE && (err || val != vals[i] * 5), - "bpf_map_push_elem", "err %d value %u\n", err, val); - out: pkt_v4.iph.saddr = 0; bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c index 41720a62c4fa..fe5b8fae2c36 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c @@ -5,59 +5,54 @@ #include "bpf/libbpf_internal.h" #include "test_raw_tp_test_run.skel.h" -static int duration; - void test_raw_tp_test_run(void) { - struct bpf_prog_test_run_attr test_attr = {}; int comm_fd = -1, err, nr_online, i, prog_fd; __u64 args[2] = {0x1234ULL, 0x5678ULL}; int expected_retval = 0x1234 + 0x5678; struct test_raw_tp_test_run *skel; char buf[] = "new_name"; bool *online = NULL; - DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, - .ctx_in = args, - .ctx_size_in = sizeof(args), - .flags = BPF_F_TEST_RUN_ON_CPU, - ); + LIBBPF_OPTS(bpf_test_run_opts, opts, + .ctx_in = args, + .ctx_size_in = sizeof(args), + .flags = BPF_F_TEST_RUN_ON_CPU, + ); err = parse_cpu_mask_file("/sys/devices/system/cpu/online", &online, &nr_online); - if (CHECK(err, "parse_cpu_mask_file", "err %d\n", err)) + if (!ASSERT_OK(err, "parse_cpu_mask_file")) return; skel = test_raw_tp_test_run__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "skel_open")) goto cleanup; err = test_raw_tp_test_run__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "skel_attach")) goto cleanup; comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); - if (CHECK(comm_fd < 0, "open /proc/self/comm", "err %d\n", errno)) + if (!ASSERT_GE(comm_fd, 0, "open /proc/self/comm")) goto cleanup; err = write(comm_fd, buf, sizeof(buf)); - CHECK(err < 0, "task rename", "err %d", errno); + ASSERT_GE(err, 0, "task rename"); - CHECK(skel->bss->count == 0, "check_count", "didn't increase\n"); - CHECK(skel->data->on_cpu != 0xffffffff, "check_on_cpu", "got wrong value\n"); + ASSERT_NEQ(skel->bss->count, 0, "check_count"); + ASSERT_EQ(skel->data->on_cpu, 0xffffffff, "check_on_cpu"); prog_fd = bpf_program__fd(skel->progs.rename); - test_attr.prog_fd = prog_fd; - test_attr.ctx_in = args; - test_attr.ctx_size_in = sizeof(__u64); + opts.ctx_in = args; + opts.ctx_size_in = sizeof(__u64); - err = bpf_prog_test_run_xattr(&test_attr); - CHECK(err == 0, "test_run", "should fail for too small ctx\n"); + err = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_NEQ(err, 0, "test_run should fail for too small ctx"); - test_attr.ctx_size_in = sizeof(args); - err = bpf_prog_test_run_xattr(&test_attr); - CHECK(err < 0, "test_run", "err %d\n", errno); - CHECK(test_attr.retval != expected_retval, "check_retval", - "expect 0x%x, got 0x%x\n", expected_retval, test_attr.retval); + opts.ctx_size_in = sizeof(args); + err = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(opts.retval, expected_retval, "check_retval"); for (i = 0; i < nr_online; i++) { if (!online[i]) @@ -66,28 +61,23 @@ void test_raw_tp_test_run(void) opts.cpu = i; opts.retval = 0; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err < 0, "test_run_opts", "err %d\n", errno); - CHECK(skel->data->on_cpu != i, "check_on_cpu", - "expect %d got %d\n", i, skel->data->on_cpu); - CHECK(opts.retval != expected_retval, - "check_retval", "expect 0x%x, got 0x%x\n", - expected_retval, opts.retval); + ASSERT_OK(err, "test_run_opts"); + ASSERT_EQ(skel->data->on_cpu, i, "check_on_cpu"); + ASSERT_EQ(opts.retval, expected_retval, "check_retval"); } /* invalid cpu ID should fail with ENXIO */ opts.cpu = 0xffffffff; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err >= 0 || errno != ENXIO, - "test_run_opts_fail", - "should failed with ENXIO\n"); + ASSERT_EQ(errno, ENXIO, "test_run_opts should fail with ENXIO"); + ASSERT_ERR(err, "test_run_opts_fail"); /* non-zero cpu w/o BPF_F_TEST_RUN_ON_CPU should fail with EINVAL */ opts.cpu = 1; opts.flags = 0; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err >= 0 || errno != EINVAL, - "test_run_opts_fail", - "should failed with EINVAL\n"); + ASSERT_EQ(errno, EINVAL, "test_run_opts should fail with EINVAL"); + ASSERT_ERR(err, "test_run_opts_fail"); cleanup: close(comm_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c index 239baccabccb..f4aa7dab4766 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -56,21 +56,23 @@ void serial_test_raw_tp_writable_test_run(void) 0, }; - __u32 prog_ret; - int err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, - 0, &prog_ret, 0); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + .repeat = 1, + ); + int err = bpf_prog_test_run_opts(filter_fd, &topts); CHECK(err != 42, "test_run", "tracepoint did not modify return value\n"); - CHECK(prog_ret != 0, "test_run_ret", + CHECK(topts.retval != 0, "test_run_ret", "socket_filter did not return 0\n"); close(tp_fd); - err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, 0, - &prog_ret, 0); + err = bpf_prog_test_run_opts(filter_fd, &topts); CHECK(err != 0, "test_run_notrace", "test_run failed with %d errno %d\n", err, errno); - CHECK(prog_ret != 0, "test_run_ret_notrace", + CHECK(topts.retval != 0, "test_run_ret_notrace", "socket_filter did not return 0\n"); out_filterfd: diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c index aecfe662c070..70b49da5ca0a 100644 --- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c +++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c @@ -13,10 +13,14 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) struct itimerval timeo = { .it_value.tv_usec = 100000, /* 100ms */ }; - __u32 duration = 0, retval; int prog_fd; int err; int i; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 0xffffffff, + ); for (i = 0; i < ARRAY_SIZE(prog); i++) prog[i] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0); @@ -24,20 +28,17 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) prog_fd = bpf_test_load_program(prog_type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); - CHECK(prog_fd < 0, "test-run", "errno %d\n", errno); + ASSERT_GE(prog_fd, 0, "test-run load"); err = sigaction(SIGALRM, &sigalrm_action, NULL); - CHECK(err, "test-run-signal-sigaction", "errno %d\n", errno); + ASSERT_OK(err, "test-run-signal-sigaction"); err = setitimer(ITIMER_REAL, &timeo, NULL); - CHECK(err, "test-run-signal-timer", "errno %d\n", errno); - - err = bpf_prog_test_run(prog_fd, 0xffffffff, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(duration > 500000000, /* 500ms */ - "test-run-signal-duration", - "duration %dns > 500ms\n", - duration); + ASSERT_OK(err, "test-run-signal-timer"); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_LE(topts.duration, 500000000 /* 500ms */, + "test-run-signal-duration"); signal(SIGALRM, SIG_DFL); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index b5319ba2ee27..ce0e555b5e38 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -20,97 +20,72 @@ void test_skb_ctx(void) .gso_size = 10, .hwtstamp = 11, }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .ctx_in = &skb, .ctx_size_in = sizeof(skb), .ctx_out = &skb, .ctx_size_out = sizeof(skb), - }; + ); struct bpf_object *obj; - int err; - int i; + int err, prog_fd, i; - err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj, - &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, + &obj, &prog_fd); + if (!ASSERT_OK(err, "load")) return; /* ctx_in != NULL, ctx_size_in == 0 */ tattr.ctx_size_in = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "ctx_size_in", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "ctx_size_in"); tattr.ctx_size_in = sizeof(skb); /* ctx_out != NULL, ctx_size_out == 0 */ tattr.ctx_size_out = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "ctx_size_out", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "ctx_size_out"); tattr.ctx_size_out = sizeof(skb); /* non-zero [len, tc_index] fields should be rejected*/ skb.len = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "len", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "len"); skb.len = 0; skb.tc_index = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "tc_index", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "tc_index"); skb.tc_index = 0; /* non-zero [hash, sk] fields should be rejected */ skb.hash = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "hash", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "hash"); skb.hash = 0; skb.sk = (struct bpf_sock *)1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "sk", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "sk"); skb.sk = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0 || tattr.retval, - "run", - "err %d errno %d retval %d\n", - err, errno, tattr.retval); - - CHECK_ATTR(tattr.ctx_size_out != sizeof(skb), - "ctx_size_out", - "incorrect output size, want %zu have %u\n", - sizeof(skb), tattr.ctx_size_out); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_OK(err, "test_run"); + ASSERT_OK(tattr.retval, "test_run retval"); + ASSERT_EQ(tattr.ctx_size_out, sizeof(skb), "ctx_size_out"); for (i = 0; i < 5; i++) - CHECK_ATTR(skb.cb[i] != i + 2, - "ctx_out_cb", - "skb->cb[i] == %d, expected %d\n", - skb.cb[i], i + 2); - CHECK_ATTR(skb.priority != 7, - "ctx_out_priority", - "skb->priority == %d, expected %d\n", - skb.priority, 7); - CHECK_ATTR(skb.ifindex != 1, - "ctx_out_ifindex", - "skb->ifindex == %d, expected %d\n", - skb.ifindex, 1); - CHECK_ATTR(skb.ingress_ifindex != 11, - "ctx_out_ingress_ifindex", - "skb->ingress_ifindex == %d, expected %d\n", - skb.ingress_ifindex, 11); - CHECK_ATTR(skb.tstamp != 8, - "ctx_out_tstamp", - "skb->tstamp == %lld, expected %d\n", - skb.tstamp, 8); - CHECK_ATTR(skb.mark != 10, - "ctx_out_mark", - "skb->mark == %u, expected %d\n", - skb.mark, 10); + ASSERT_EQ(skb.cb[i], i + 2, "ctx_out_cb"); + ASSERT_EQ(skb.priority, 7, "ctx_out_priority"); + ASSERT_EQ(skb.ifindex, 1, "ctx_out_ifindex"); + ASSERT_EQ(skb.ingress_ifindex, 11, "ctx_out_ingress_ifindex"); + ASSERT_EQ(skb.tstamp, 8, "ctx_out_tstamp"); + ASSERT_EQ(skb.mark, 10, "ctx_out_mark"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c index 6f802a1c0800..97dc8b14be48 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c @@ -9,22 +9,22 @@ void test_skb_helpers(void) .gso_segs = 8, .gso_size = 10, }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .ctx_in = &skb, .ctx_size_in = sizeof(skb), .ctx_out = &skb, .ctx_size_out = sizeof(skb), - }; + ); struct bpf_object *obj; - int err; + int err, prog_fd; - err = bpf_prog_test_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj, - &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load("./test_skb_helpers.o", + BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (!ASSERT_OK(err, "load")) return; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err, "len", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c index 9fc040eaa482..9d211b5c22c4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#define _GNU_SOURCE #include <netinet/in.h> #include <arpa/inet.h> #include <unistd.h> +#include <sched.h> #include <stdlib.h> #include <string.h> #include <errno.h> @@ -20,6 +22,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -42,8 +45,16 @@ static __u64 child_cg_id; static int linum_map_fd; static __u32 duration; -static __u32 egress_linum_idx = EGRESS_LINUM_IDX; -static __u32 ingress_linum_idx = INGRESS_LINUM_IDX; +static bool create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return false; + + if (!ASSERT_OK(system("ip link set dev lo up"), "bring up lo")) + return false; + + return true; +} static void print_sk(const struct bpf_sock *sk, const char *prefix) { @@ -91,19 +102,24 @@ static void check_result(void) { struct bpf_tcp_sock srv_tp, cli_tp, listen_tp; struct bpf_sock srv_sk, cli_sk, listen_sk; - __u32 ingress_linum, egress_linum; + __u32 idx, ingress_linum, egress_linum, linum; int err; - err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx, - &egress_linum); + idx = EGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &egress_linum); CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); - err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx, - &ingress_linum); + idx = INGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &ingress_linum); CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); + idx = READ_SK_DST_PORT_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &linum); + ASSERT_OK(err, "bpf_map_lookup_elem(linum_map_fd, READ_SK_DST_PORT_IDX)"); + ASSERT_EQ(linum, 0, "failure in read_sk_dst_port on line"); + memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk)); memcpy(&srv_tp, &skel->bss->srv_tp, sizeof(srv_tp)); memcpy(&cli_sk, &skel->bss->cli_sk, sizeof(cli_sk)); @@ -262,7 +278,7 @@ static void test(void) char buf[DATA_LEN]; /* Prepare listen_fd */ - listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0xcafe, 0); /* start_server() has logged the error details */ if (CHECK_FAIL(listen_fd == -1)) goto done; @@ -330,8 +346,12 @@ done: void serial_test_sock_fields(void) { - struct bpf_link *egress_link = NULL, *ingress_link = NULL; int parent_cg_fd = -1, child_cg_fd = -1; + struct bpf_link *link; + + /* Use a dedicated netns to have a fixed listen port */ + if (!create_netns()) + return; /* Create a cgroup, get fd, and join it */ parent_cg_fd = test__join_cgroup(PARENT_CGROUP); @@ -352,15 +372,20 @@ void serial_test_sock_fields(void) if (CHECK(!skel, "test_sock_fields__open_and_load", "failed\n")) goto done; - egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, - child_cg_fd); - if (!ASSERT_OK_PTR(egress_link, "attach_cgroup(egress)")) + link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(egress_read_sock_fields)")) + goto done; + skel->links.egress_read_sock_fields = link; + + link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(ingress_read_sock_fields)")) goto done; + skel->links.ingress_read_sock_fields = link; - ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, - child_cg_fd); - if (!ASSERT_OK_PTR(ingress_link, "attach_cgroup(ingress)")) + link = bpf_program__attach_cgroup(skel->progs.read_sk_dst_port, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(read_sk_dst_port")) goto done; + skel->links.read_sk_dst_port = link; linum_map_fd = bpf_map__fd(skel->maps.linum_map); sk_pkt_out_cnt_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt); @@ -369,8 +394,7 @@ void serial_test_sock_fields(void) test(); done: - bpf_link__destroy(egress_link); - bpf_link__destroy(ingress_link); + test_sock_fields__detach(skel); test_sock_fields__destroy(skel); if (child_cg_fd >= 0) close(child_cg_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 85db0f4cdd95..cec5c0882372 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -8,6 +8,7 @@ #include "test_sockmap_update.skel.h" #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" +#include "test_sockmap_progs_query.skel.h" #include "bpf_iter_sockmap.skel.h" #define TCP_REPAIR 19 /* TCP sock is under repair right now */ @@ -139,12 +140,16 @@ out: static void test_sockmap_update(enum bpf_map_type map_type) { - struct bpf_prog_test_run_attr tattr; int err, prog, src, duration = 0; struct test_sockmap_update *skel; struct bpf_map *dst_map; const __u32 zero = 0; char dummy[14] = {0}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = dummy, + .data_size_in = sizeof(dummy), + .repeat = 1, + ); __s64 sk; sk = connected_socket_v4(); @@ -166,16 +171,10 @@ static void test_sockmap_update(enum bpf_map_type map_type) if (CHECK(err, "update_elem(src)", "errno=%u\n", errno)) goto out; - tattr = (struct bpf_prog_test_run_attr){ - .prog_fd = prog, - .repeat = 1, - .data_in = dummy, - .data_size_in = sizeof(dummy), - }; - - err = bpf_prog_test_run_xattr(&tattr); - if (CHECK_ATTR(err || !tattr.retval, "bpf_prog_test_run", - "errno=%u retval=%u\n", errno, tattr.retval)) + err = bpf_prog_test_run_opts(prog, &topts); + if (!ASSERT_OK(err, "test_run")) + goto out; + if (!ASSERT_NEQ(topts.retval, 0, "test_run retval")) goto out; compare_cookies(skel->maps.src, dst_map); @@ -315,6 +314,63 @@ out: test_sockmap_skb_verdict_attach__destroy(skel); } +static __u32 query_prog_id(int prog_fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd") || + !ASSERT_EQ(info_len, sizeof(info), "bpf_obj_get_info_by_fd")) + return 0; + + return info.id; +} + +static void test_sockmap_progs_query(enum bpf_attach_type attach_type) +{ + struct test_sockmap_progs_query *skel; + int err, map_fd, verdict_fd; + __u32 attach_flags = 0; + __u32 prog_ids[3] = {}; + __u32 prog_cnt = 3; + + skel = test_sockmap_progs_query__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_sockmap_progs_query__open_and_load")) + return; + + map_fd = bpf_map__fd(skel->maps.sock_map); + + if (attach_type == BPF_SK_MSG_VERDICT) + verdict_fd = bpf_program__fd(skel->progs.prog_skmsg_verdict); + else + verdict_fd = bpf_program__fd(skel->progs.prog_skb_verdict); + + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 0, "wrong program count on query"); + + err = bpf_prog_attach(verdict_fd, map_fd, attach_type, 0); + if (!ASSERT_OK(err, "bpf_prog_attach failed")) + goto out; + + prog_cnt = 1; + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 1, "wrong program count on query"); + ASSERT_EQ(prog_ids[0], query_prog_id(verdict_fd), + "wrong prog_ids on query"); + + bpf_prog_detach2(verdict_fd, map_fd, attach_type); +out: + test_sockmap_progs_query__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -341,4 +397,12 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT, BPF_SK_SKB_VERDICT); } + if (test__start_subtest("sockmap msg_verdict progs query")) + test_sockmap_progs_query(BPF_SK_MSG_VERDICT); + if (test__start_subtest("sockmap stream_parser progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_PARSER); + if (test__start_subtest("sockmap stream_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); + if (test__start_subtest("sockmap skb_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_VERDICT); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 7e21bfab6358..2cf0c7a3fe23 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1413,14 +1413,12 @@ close_srv1: static void test_ops_cleanup(const struct bpf_map *map) { - const struct bpf_map_def *def; int err, mapfd; u32 key; - def = bpf_map__def(map); mapfd = bpf_map__fd(map); - for (key = 0; key < def->max_entries; key++) { + for (key = 0; key < bpf_map__max_entries(map); key++) { err = bpf_map_delete_elem(mapfd, &key); if (err && errno != EINVAL && errno != ENOENT) FAIL_ERRNO("map_delete: expected EINVAL/ENOENT"); @@ -1443,13 +1441,13 @@ static const char *family_str(sa_family_t family) static const char *map_type_str(const struct bpf_map *map) { - const struct bpf_map_def *def; + int type; - def = bpf_map__def(map); - if (IS_ERR(def)) + if (!map) return "invalid"; + type = bpf_map__type(map); - switch (def->type) { + switch (type) { case BPF_MAP_TYPE_SOCKMAP: return "sockmap"; case BPF_MAP_TYPE_SOCKHASH: diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4b937e5dbaca..30a99d2ed5c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -173,11 +173,11 @@ static int getsetsockopt(void) } memset(&buf, 0, sizeof(buf)); - buf.zc.address = 12345; /* rejected by BPF */ + buf.zc.address = 12345; /* Not page aligned. Rejected by tcp_zerocopy_receive() */ optlen = sizeof(buf.zc); errno = 0; err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); - if (errno != EPERM) { + if (errno != EINVAL) { log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", err, errno); goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 6307f5d2b417..8e329eaee6d7 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -4,14 +4,16 @@ static void *spin_lock_thread(void *arg) { - __u32 duration, retval; int err, prog_fd = *(u32 *) arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10000, + ); - err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); pthread_exit(arg); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index 0a91d8d9954b..f45a1d7b0a28 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -42,7 +42,7 @@ retry: return; /* override program type */ - bpf_program__set_perf_event(skel->progs.oncpu); + bpf_program__set_type(skel->progs.oncpu, BPF_PROG_TYPE_PERF_EVENT); err = test_stacktrace_build_id__load(skel); if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c index 81e997a69f7a..f4d40001155a 100644 --- a/tools/testing/selftests/bpf/prog_tests/syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/syscall.c @@ -20,20 +20,20 @@ void test_syscall(void) .log_buf = (uintptr_t) verifier_log, .log_size = sizeof(verifier_log), }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .ctx_in = &ctx, .ctx_size_in = sizeof(ctx), - }; + ); struct syscall *skel = NULL; __u64 key = 12, value = 0; - int err; + int err, prog_fd; skel = syscall__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_load")) goto cleanup; - tattr.prog_fd = bpf_program__fd(skel->progs.bpf_prog); - err = bpf_prog_test_run_xattr(&tattr); + prog_fd = bpf_program__fd(skel->progs.bpf_prog); + err = bpf_prog_test_run_opts(prog_fd, &tattr); ASSERT_EQ(err, 0, "err"); ASSERT_EQ(tattr.retval, 1, "retval"); ASSERT_GT(ctx.map_fd, 0, "ctx.map_fd"); diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 5dc0f425bd11..c4da87ec3ba4 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -12,9 +12,13 @@ static void test_tailcall_1(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -37,7 +41,7 @@ static void test_tailcall_1(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -53,23 +57,21 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -85,13 +87,12 @@ static void test_tailcall_1(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -107,33 +108,30 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != j, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, j, "tailcall retval"); err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err >= 0 || errno != ENOENT)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: @@ -150,9 +148,13 @@ static void test_tailcall_2(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -175,7 +177,7 @@ static void test_tailcall_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -191,30 +193,27 @@ static void test_tailcall_2(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 2, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 2, "tailcall retval"); i = 2; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); out: bpf_object__close(obj); } @@ -225,8 +224,12 @@ static void test_tailcall_count(const char *which) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -262,10 +265,9 @@ static void test_tailcall_count(const char *which) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) @@ -277,18 +279,17 @@ static void test_tailcall_count(const char *which) i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val, 33, "tailcall count"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); out: bpf_object__close(obj); } @@ -319,10 +320,14 @@ static void test_tailcall_4(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; static const int zero = 0; char buff[128] = {}; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -353,7 +358,7 @@ static void test_tailcall_4(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -369,18 +374,17 @@ static void test_tailcall_4(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -389,10 +393,9 @@ static void test_tailcall_4(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: bpf_object__close(obj); @@ -407,10 +410,14 @@ static void test_tailcall_5(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; static const int zero = 0; char buff[128] = {}; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall5.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -441,7 +448,7 @@ static void test_tailcall_5(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -457,18 +464,17 @@ static void test_tailcall_5(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -477,10 +483,9 @@ static void test_tailcall_5(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: bpf_object__close(obj); @@ -495,8 +500,12 @@ static void test_tailcall_bpf2bpf_1(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -520,7 +529,7 @@ static void test_tailcall_bpf2bpf_1(void) goto out; /* nop -> jmp */ - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -536,10 +545,9 @@ static void test_tailcall_bpf2bpf_1(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != 1, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); /* jmp -> nop, call subprog that will do tailcall */ i = 1; @@ -547,10 +555,9 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); /* make sure that subprog can access ctx and entry prog that * called this subprog can properly return @@ -560,11 +567,9 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != sizeof(pkt_v4) * 2, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval"); out: bpf_object__close(obj); } @@ -579,8 +584,12 @@ static void test_tailcall_bpf2bpf_2(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -616,10 +625,9 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) @@ -631,18 +639,17 @@ static void test_tailcall_bpf2bpf_2(void) i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val, 33, "tailcall count"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); out: bpf_object__close(obj); } @@ -657,8 +664,12 @@ static void test_tailcall_bpf2bpf_3(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf3.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -681,7 +692,7 @@ static void test_tailcall_bpf2bpf_3(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -697,33 +708,27 @@ static void test_tailcall_bpf2bpf_3(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval"); i = 1; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4), - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4), "tailcall retval"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 2, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval"); out: bpf_object__close(obj); } @@ -754,8 +759,12 @@ static void test_tailcall_bpf2bpf_4(bool noise) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -778,7 +787,7 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -809,15 +818,14 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval"); i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n", - err, errno, val.count); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val.count, 31, "tailcall count"); out: bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c index 37c20b5ffa70..61935e7e056a 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c +++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c @@ -3,18 +3,22 @@ #include <test_progs.h> #include "test_task_pt_regs.skel.h" +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); +} + void test_task_pt_regs(void) { struct test_task_pt_regs *skel; struct bpf_link *uprobe_link; - size_t uprobe_offset; - ssize_t base_addr; + ssize_t uprobe_offset; bool match; - base_addr = get_base_addr(); - if (!ASSERT_GT(base_addr, 0, "get_base_addr")) + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) return; - uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr); skel = test_task_pt_regs__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -32,7 +36,7 @@ void test_task_pt_regs(void) skel->links.handle_uprobe = uprobe_link; /* trigger & validate uprobe */ - get_base_addr(); + trigger_func(); if (!ASSERT_EQ(skel->bss->uprobe_res, 1, "check_uprobe_res")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c new file mode 100644 index 000000000000..c381faaae741 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 Sony Group Corporation */ +#include <sys/prctl.h> +#include <test_progs.h> +#include "bpf_syscall_macro.skel.h" + +void test_bpf_syscall_macro(void) +{ + struct bpf_syscall_macro *skel = NULL; + int err; + int exp_arg1 = 1001; + unsigned long exp_arg2 = 12; + unsigned long exp_arg3 = 13; + unsigned long exp_arg4 = 14; + unsigned long exp_arg5 = 15; + + /* check whether it can open program */ + skel = bpf_syscall_macro__open(); + if (!ASSERT_OK_PTR(skel, "bpf_syscall_macro__open")) + return; + + skel->rodata->filter_pid = getpid(); + + /* check whether it can load program */ + err = bpf_syscall_macro__load(skel); + if (!ASSERT_OK(err, "bpf_syscall_macro__load")) + goto cleanup; + + /* check whether it can attach kprobe */ + err = bpf_syscall_macro__attach(skel); + if (!ASSERT_OK(err, "bpf_syscall_macro__attach")) + goto cleanup; + + /* check whether args of syscall are copied correctly */ + prctl(exp_arg1, exp_arg2, exp_arg3, exp_arg4, exp_arg5); +#if defined(__aarch64__) || defined(__s390__) + ASSERT_NEQ(skel->bss->arg1, exp_arg1, "syscall_arg1"); +#else + ASSERT_EQ(skel->bss->arg1, exp_arg1, "syscall_arg1"); +#endif + ASSERT_EQ(skel->bss->arg2, exp_arg2, "syscall_arg2"); + ASSERT_EQ(skel->bss->arg3, exp_arg3, "syscall_arg3"); + /* it cannot copy arg4 when uses PT_REGS_PARM4 on x86_64 */ +#ifdef __x86_64__ + ASSERT_NEQ(skel->bss->arg4_cx, exp_arg4, "syscall_arg4_from_cx"); +#else + ASSERT_EQ(skel->bss->arg4_cx, exp_arg4, "syscall_arg4_from_cx"); +#endif + ASSERT_EQ(skel->bss->arg4, exp_arg4, "syscall_arg4"); + ASSERT_EQ(skel->bss->arg5, exp_arg5, "syscall_arg5"); + + /* check whether args of syscall are copied correctly for CORE variants */ + ASSERT_EQ(skel->bss->arg1_core, exp_arg1, "syscall_arg1_core_variant"); + ASSERT_EQ(skel->bss->arg2_core, exp_arg2, "syscall_arg2_core_variant"); + ASSERT_EQ(skel->bss->arg3_core, exp_arg3, "syscall_arg3_core_variant"); + /* it cannot copy arg4 when uses PT_REGS_PARM4_CORE on x86_64 */ +#ifdef __x86_64__ + ASSERT_NEQ(skel->bss->arg4_core_cx, exp_arg4, "syscall_arg4_from_cx_core_variant"); +#else + ASSERT_EQ(skel->bss->arg4_core_cx, exp_arg4, "syscall_arg4_from_cx_core_variant"); +#endif + ASSERT_EQ(skel->bss->arg4_core, exp_arg4, "syscall_arg4_core_variant"); + ASSERT_EQ(skel->bss->arg5_core, exp_arg5, "syscall_arg5_core_variant"); + + ASSERT_EQ(skel->bss->option_syscall, exp_arg1, "BPF_KPROBE_SYSCALL_option"); + ASSERT_EQ(skel->bss->arg2_syscall, exp_arg2, "BPF_KPROBE_SYSCALL_arg2"); + ASSERT_EQ(skel->bss->arg3_syscall, exp_arg3, "BPF_KPROBE_SYSCALL_arg3"); + ASSERT_EQ(skel->bss->arg4_syscall, exp_arg4, "BPF_KPROBE_SYSCALL_arg4"); + ASSERT_EQ(skel->bss->arg5_syscall, exp_arg5, "BPF_KPROBE_SYSCALL_arg5"); + +cleanup: + bpf_syscall_macro__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_profiler.c b/tools/testing/selftests/bpf/prog_tests/test_profiler.c index 4ca275101ee0..de24e8f0e738 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_profiler.c +++ b/tools/testing/selftests/bpf/prog_tests/test_profiler.c @@ -8,20 +8,20 @@ static int sanity_run(struct bpf_program *prog) { - struct bpf_prog_test_run_attr test_attr = {}; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); __u64 args[] = {1, 2, 3}; - __u32 duration = 0; int err, prog_fd; prog_fd = bpf_program__fd(prog); - test_attr.prog_fd = prog_fd; test_attr.ctx_in = args; test_attr.ctx_size_in = sizeof(args); - err = bpf_prog_test_run_xattr(&test_attr); - if (CHECK(err || test_attr.retval, "test_run", - "err %d errno %d retval %d duration %d\n", - err, errno, test_attr.retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &test_attr); + if (!ASSERT_OK(err, "test_run")) + return -1; + + if (!ASSERT_OK(test_attr.retval, "test_run retval")) return -1; + return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c index cf1215531920..ae93411fd582 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c +++ b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c @@ -6,15 +6,18 @@ static int sanity_run(struct bpf_program *prog) { - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); prog_fd = bpf_program__fd(prog); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - if (CHECK(err || retval != 123, "test_run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run")) + return -1; + if (!ASSERT_EQ(topts.retval, 123, "test_run retval")) return -1; return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index 0f4e49e622cd..7eb049214859 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -6,7 +6,7 @@ static int timer(struct timer *timer_skel) { int err, prog_fd; - __u32 duration = 0, retval; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = timer__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) @@ -16,10 +16,9 @@ static int timer(struct timer *timer_skel) ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1"); prog_fd = bpf_program__fd(timer_skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); timer__detach(timer_skel); usleep(50); /* 10 usecs should be enough, but give it extra */ diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index 949a0617869d..2ee5f5ae11d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -6,19 +6,18 @@ static int timer_mim(struct timer_mim *timer_skel) { - __u32 duration = 0, retval; __u64 cnt1, cnt2; int err, prog_fd, key1 = 1; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = timer_mim__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) return err; prog_fd = bpf_program__fd(timer_skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); timer_mim__detach(timer_skel); /* check that timer_cb[12] are incrementing 'cnt' */ diff --git a/tools/testing/selftests/bpf/prog_tests/trace_ext.c b/tools/testing/selftests/bpf/prog_tests/trace_ext.c index 924441d4362d..aabdff7bea3e 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_ext.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_ext.c @@ -23,8 +23,12 @@ void test_trace_ext(void) int err, pkt_fd, ext_fd; struct bpf_program *prog; char buf[100]; - __u32 retval; __u64 len; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); /* open/load/attach test_pkt_md_access */ skel_pkt = test_pkt_md_access__open_and_load(); @@ -77,32 +81,32 @@ void test_trace_ext(void) /* load/attach tracing */ err = test_trace_ext_tracing__load(skel_trace); - if (CHECK(err, "setup", "tracing/test_pkt_md_access_new load failed\n")) { + if (!ASSERT_OK(err, "tracing/test_pkt_md_access_new load")) { libbpf_strerror(err, buf, sizeof(buf)); fprintf(stderr, "%s\n", buf); goto cleanup; } err = test_trace_ext_tracing__attach(skel_trace); - if (CHECK(err, "setup", "tracing/test_pkt_md_access_new attach failed: %d\n", err)) + if (!ASSERT_OK(err, "tracing/test_pkt_md_access_new attach")) goto cleanup; /* trigger the test */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "run", "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(pkt_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); bss_ext = skel_ext->bss; bss_trace = skel_trace->bss; len = bss_ext->ext_called; - CHECK(bss_ext->ext_called == 0, - "check", "failed to trigger freplace/test_pkt_md_access\n"); - CHECK(bss_trace->fentry_called != len, - "check", "failed to trigger fentry/test_pkt_md_access_new\n"); - CHECK(bss_trace->fexit_called != len, - "check", "failed to trigger fexit/test_pkt_md_access_new\n"); + ASSERT_NEQ(bss_ext->ext_called, 0, + "failed to trigger freplace/test_pkt_md_access"); + ASSERT_EQ(bss_trace->fentry_called, len, + "failed to trigger fentry/test_pkt_md_access_new"); + ASSERT_EQ(bss_trace->fexit_called, len, + "failed to trigger fexit/test_pkt_md_access_new"); cleanup: test_trace_ext_tracing__destroy(skel_trace); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c index ac65456b7ab8..ec21c53cb1da 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp.c @@ -13,8 +13,14 @@ void test_xdp(void) char buf[128]; struct ipv6hdr iph6; struct iphdr iph; - __u32 duration, retval, size; int err, prog_fd, map_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) @@ -26,21 +32,23 @@ void test_xdp(void) bpf_map_update_elem(map_fd, &key4, &value4, 0); bpf_map_update_elem(map_fd, &key6, &value6, 0); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); - CHECK(err || retval != XDP_TX || size != 74 || - iph.protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv4 test_run data_size_out"); + ASSERT_EQ(iph.protocol, IPPROTO_IPIP, "ipv4 test_run iph.protocol"); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); + + err = bpf_prog_test_run_opts(prog_fd, &topts); memcpy(&iph6, buf + sizeof(struct ethhdr), sizeof(iph6)); - CHECK(err || retval != XDP_TX || size != 114 || - iph6.nexthdr != IPPROTO_IPV6, "ipv6", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 114, "ipv6 test_run data_size_out"); + ASSERT_EQ(iph6.nexthdr, IPPROTO_IPV6, "ipv6 test_run iph6.nexthdr"); out: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c new file mode 100644 index 000000000000..d18e6f343c48 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +static void test_xdp_update_frags(void) +{ + const char *file = "./test_xdp_update_frags.o"; + struct bpf_program *prog; + struct bpf_object *obj; + int err, prog_fd; + __u32 *offset; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(128); + if (!ASSERT_OK_PTR(buf, "alloc buf 128b")) + goto out; + + memset(buf, 0, 128); + offset = (__u32 *)buf; + *offset = 16; + buf[*offset] = 0xaa; /* marker at offset 16 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 31 (head) */ + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 128; + topts.data_size_out = 128; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[16,31]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[16], 0xbb, "xdp_update_frag buf[16]"); + ASSERT_EQ(buf[31], 0xbb, "xdp_update_frag buf[31]"); + + free(buf); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 5000; + buf[*offset] = 0xaa; /* marker at offset 5000 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 5015 (frag0) */ + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 9000; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[5000,5015]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[5000], 0xbb, "xdp_update_frag buf[5000]"); + ASSERT_EQ(buf[5015], 0xbb, "xdp_update_frag buf[5015]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 3510; + buf[*offset] = 0xaa; /* marker at offset 3510 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 3525 (frag0) */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[3510,3525]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[3510], 0xbb, "xdp_update_frag buf[3510]"); + ASSERT_EQ(buf[3525], 0xbb, "xdp_update_frag buf[3525]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 7606; + buf[*offset] = 0xaa; /* marker at offset 7606 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 7621 (frag1) */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[7606,7621]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[7606], 0xbb, "xdp_update_frag buf[7606]"); + ASSERT_EQ(buf[7621], 0xbb, "xdp_update_frag buf[7621]"); + + free(buf); +out: + bpf_object__close(obj); +} + +void test_xdp_adjust_frags(void) +{ + if (test__start_subtest("xdp_adjust_frags")) + test_xdp_update_frags(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 3f5a17c38be5..21ceac24e174 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -5,28 +5,35 @@ static void test_xdp_adjust_tail_shrink(void) { const char *file = "./test_xdp_adjust_tail_shrink.o"; - __u32 duration, retval, size, expect_sz; + __u32 expect_sz; struct bpf_object *obj; int err, prog_fd; char buf[128]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_shrink")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) - 20; /* Test shrink with 20 bytes */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(topts.data_size_out, expect_sz, "ipv6 size"); + bpf_object__close(obj); } @@ -35,25 +42,31 @@ static void test_xdp_adjust_tail_grow(void) const char *file = "./test_xdp_adjust_tail_grow.o"; struct bpf_object *obj; char buf[4096]; /* avoid segfault: large buf to hold grow results */ - __u32 duration, retval, size, expect_sz; + __u32 expect_sz; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */, - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(topts.data_size_out, expect_sz, "ipv6 size"); bpf_object__close(obj); } @@ -65,18 +78,18 @@ static void test_xdp_adjust_tail_grow2(void) int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/; struct bpf_object *obj; int err, cnt, i; - int max_grow; + int max_grow, prog_fd; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .repeat = 1, .data_in = &buf, .data_out = &buf, .data_size_in = 0, /* Per test */ .data_size_out = 0, /* Per test */ - }; + ); - err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; /* Test case-64 */ @@ -84,49 +97,171 @@ static void test_xdp_adjust_tail_grow2(void) tattr.data_size_in = 64; /* Determine test case via pkt size */ tattr.data_size_out = 128; /* Limit copy_size */ /* Kernel side alloc packet memory area that is zero init */ - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); - CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */ - || tattr.retval != XDP_TX - || tattr.data_size_out != 192, /* Expected grow size */ - "case-64", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(errno, ENOSPC, "case-64 errno"); /* Due limit copy_size in bpf_test_finish */ + ASSERT_EQ(tattr.retval, XDP_TX, "case-64 retval"); + ASSERT_EQ(tattr.data_size_out, 192, "case-64 data_size_out"); /* Expected grow size */ /* Extra checks for data contents */ - CHECK_ATTR(tattr.data_size_out != 192 - || buf[0] != 1 || buf[63] != 1 /* 0-63 memset to 1 */ - || buf[64] != 0 || buf[127] != 0 /* 64-127 memset to 0 */ - || buf[128] != 1 || buf[191] != 1, /*128-191 memset to 1 */ - "case-64-data", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(buf[0], 1, "case-64-data buf[0]"); /* 0-63 memset to 1 */ + ASSERT_EQ(buf[63], 1, "case-64-data buf[63]"); + ASSERT_EQ(buf[64], 0, "case-64-data buf[64]"); /* 64-127 memset to 0 */ + ASSERT_EQ(buf[127], 0, "case-64-data buf[127]"); + ASSERT_EQ(buf[128], 1, "case-64-data buf[128]"); /* 128-191 memset to 1 */ + ASSERT_EQ(buf[191], 1, "case-64-data buf[191]"); /* Test case-128 */ memset(buf, 2, sizeof(buf)); tattr.data_size_in = 128; /* Determine test case via pkt size */ tattr.data_size_out = sizeof(buf); /* Copy everything */ - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); max_grow = 4096 - XDP_PACKET_HEADROOM - tailroom; /* 3520 */ - CHECK_ATTR(err - || tattr.retval != XDP_TX - || tattr.data_size_out != max_grow,/* Expect max grow size */ - "case-128", - "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, max_grow); + ASSERT_OK(err, "case-128"); + ASSERT_EQ(tattr.retval, XDP_TX, "case-128 retval"); + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128 data_size_out"); /* Expect max grow */ /* Extra checks for data content: Count grow size, will contain zeros */ for (i = 0, cnt = 0; i < sizeof(buf); i++) { if (buf[i] == 0) cnt++; } - CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */ - || tattr.data_size_out != max_grow, /* Total grow size */ - "case-128-data", - "err %d errno %d retval %d size %d grow-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, cnt); + ASSERT_EQ(cnt, max_grow - tattr.data_size_in, "case-128-data cnt"); /* Grow increase */ + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128-data data_size_out"); /* Total grow */ + + bpf_object__close(obj); +} + +static void test_xdp_adjust_frags_tail_shrink(void) +{ + const char *file = "./test_xdp_adjust_tail_shrink.o"; + __u32 exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, prog_fd; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + /* For the individual test cases, the first byte in the packet + * indicates which test will be run. + */ + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + + /* Test case removing 10 bytes from last frag, NOT freeing it */ + exp_size = 8990; /* 9000 - 10 */ + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 9000; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-10b"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-10b size"); + + /* Test case removing one of two pages, assuming 4K pages */ + buf[0] = 1; + exp_size = 4900; /* 9000 - 4100 */ + + topts.data_size_out = 9000; /* reset from previous invocation */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-4Kb"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-4Kb retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-4Kb size"); + + /* Test case removing two pages resulting in a linear xdp_buff */ + buf[0] = 2; + exp_size = 800; /* 9000 - 8200 */ + topts.data_size_out = 9000; /* reset from previous invocation */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-9Kb"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-9Kb retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-9Kb size"); + + free(buf); +out: + bpf_object__close(obj); +} + +static void test_xdp_adjust_frags_tail_grow(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.o"; + __u32 exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, i, prog_fd; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(16384); + if (!ASSERT_OK_PTR(buf, "alloc buf 16Kb")) + goto out; + + /* Test case add 10 bytes to last frag */ + memset(buf, 1, 16384); + exp_size = 9000 + 10; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 16384; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size"); + + for (i = 0; i < 9000; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-old"); + + for (i = 9000; i < 9010; i++) + ASSERT_EQ(buf[i], 0, "9Kb+10b-new"); + + for (i = 9010; i < 16384; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched"); + + /* Test a too large grow */ + memset(buf, 1, 16384); + exp_size = 9001; + + topts.data_in = topts.data_out = buf; + topts.data_size_in = 9001; + topts.data_size_out = 16384; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(topts.retval, XDP_DROP, "9Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size"); + free(buf); +out: bpf_object__close(obj); } @@ -138,4 +273,8 @@ void test_xdp_adjust_tail(void) test_xdp_adjust_tail_grow(); if (test__start_subtest("xdp_adjust_tail_grow2")) test_xdp_adjust_tail_grow2(); + if (test__start_subtest("xdp_adjust_frags_tail_shrink")) + test_xdp_adjust_frags_tail_shrink(); + if (test__start_subtest("xdp_adjust_frags_tail_grow")) + test_xdp_adjust_frags_tail_grow(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index c6fa390e3aa1..62aa3edda5e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -11,8 +11,7 @@ void serial_test_xdp_attach(void) const char *file = "./test_xdp.o"; struct bpf_prog_info info = {}; int err, fd1, fd2, fd3; - DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, - .old_fd = -1); + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); len = sizeof(info); @@ -38,49 +37,47 @@ void serial_test_xdp_attach(void) if (CHECK_FAIL(err)) goto out_2; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE, - &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE, &opts); if (CHECK(err, "load_ok", "initial load failed")) goto out_close; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != id1, "id1_check", "loaded prog id %u != id1 %u, err %d", id0, id1, err)) goto out_close; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, - &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, &opts); if (CHECK(!err, "load_fail", "load with expected id didn't fail")) goto out; - opts.old_fd = fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts); + opts.old_prog_fd = fd1; + err = bpf_xdp_attach(IFINDEX_LO, fd2, 0, &opts); if (CHECK(err, "replace_ok", "replace valid old_fd failed")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != id2, "id2_check", "loaded prog id %u != id2 %u, err %d", id0, id2, err)) goto out_close; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd3, 0, &opts); if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail")) goto out; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + err = bpf_xdp_detach(IFINDEX_LO, 0, &opts); if (CHECK(!err, "remove_fail", "remove invalid old_fd didn't fail")) goto out; - opts.old_fd = fd2; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + opts.old_prog_fd = fd2; + err = bpf_xdp_detach(IFINDEX_LO, 0, &opts); if (CHECK(err, "remove_ok", "remove valid old_fd failed")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != 0, "unload_check", "loaded prog id %u != 0, err %d", id0, err)) goto out_close; out: - bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: bpf_object__close(obj3); out_2: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index c98a897ad692..76967d8ace9c 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -10,40 +10,101 @@ struct meta { int pkt_len; }; +struct test_ctx_s { + bool passed; + int pkt_size; +}; + +struct test_ctx_s test_ctx; + static void on_sample(void *ctx, int cpu, void *data, __u32 size) { - int duration = 0; struct meta *meta = (struct meta *)data; struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta); + unsigned char *raw_pkt = data + sizeof(*meta); + struct test_ctx_s *tst_ctx = ctx; + + ASSERT_GE(size, sizeof(pkt_v4) + sizeof(*meta), "check_size"); + ASSERT_EQ(meta->ifindex, if_nametoindex("lo"), "check_meta_ifindex"); + ASSERT_EQ(meta->pkt_len, tst_ctx->pkt_size, "check_meta_pkt_len"); + ASSERT_EQ(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), 0, + "check_packet_content"); + + if (meta->pkt_len > sizeof(pkt_v4)) { + for (int i = 0; i < meta->pkt_len - sizeof(pkt_v4); i++) + ASSERT_EQ(raw_pkt[i + sizeof(pkt_v4)], (unsigned char)i, + "check_packet_content"); + } + + tst_ctx->passed = true; +} - if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta), - "check_size", "size %u < %zu\n", - size, sizeof(pkt_v4) + sizeof(*meta))) - return; +#define BUF_SZ 9000 - if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex", - "meta->ifindex = %d\n", meta->ifindex)) +static void run_xdp_bpf2bpf_pkt_size(int pkt_fd, struct perf_buffer *pb, + struct test_xdp_bpf2bpf *ftrace_skel, + int pkt_size) +{ + __u8 *buf, *buf_in; + int err; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + if (!ASSERT_LE(pkt_size, BUF_SZ, "pkt_size") || + !ASSERT_GE(pkt_size, sizeof(pkt_v4), "pkt_size")) return; - if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len", - "meta->pkt_len = %zd\n", sizeof(pkt_v4))) + buf_in = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf_in, "buf_in malloc()")) return; - if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), - "check_packet_content", "content not the same\n")) + buf = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf, "buf malloc()")) { + free(buf_in); return; + } + + test_ctx.passed = false; + test_ctx.pkt_size = pkt_size; + + memcpy(buf_in, &pkt_v4, sizeof(pkt_v4)); + if (pkt_size > sizeof(pkt_v4)) { + for (int i = 0; i < (pkt_size - sizeof(pkt_v4)); i++) + buf_in[i + sizeof(pkt_v4)] = i; + } + + /* Run test program */ + topts.data_in = buf_in; + topts.data_size_in = pkt_size; + topts.data_out = buf; + topts.data_size_out = BUF_SZ; + + err = bpf_prog_test_run_opts(pkt_fd, &topts); + + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_PASS, "ipv4 retval"); + ASSERT_EQ(topts.data_size_out, pkt_size, "ipv4 size"); + + /* Make sure bpf_xdp_output() was triggered and it sent the expected + * data to the perf ring buffer. + */ + err = perf_buffer__poll(pb, 100); + + ASSERT_GE(err, 0, "perf_buffer__poll"); + ASSERT_TRUE(test_ctx.passed, "test passed"); + /* Verify test results */ + ASSERT_EQ(ftrace_skel->bss->test_result_fentry, if_nametoindex("lo"), + "fentry result"); + ASSERT_EQ(ftrace_skel->bss->test_result_fexit, XDP_PASS, "fexit result"); - *(bool *)ctx = true; + free(buf); + free(buf_in); } void test_xdp_bpf2bpf(void) { - __u32 duration = 0, retval, size; - char buf[128]; int err, pkt_fd, map_fd; - bool passed = false; - struct iphdr iph; - struct iptnl_info value4 = {.family = AF_INET}; + int pkt_sizes[] = {sizeof(pkt_v4), 1024, 4100, 8200}; + struct iptnl_info value4 = {.family = AF_INET6}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; @@ -52,7 +113,7 @@ void test_xdp_bpf2bpf(void) /* Load XDP program to introspect */ pkt_skel = test_xdp__open_and_load(); - if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n")) + if (!ASSERT_OK_PTR(pkt_skel, "test_xdp__open_and_load")) return; pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel); @@ -62,7 +123,7 @@ void test_xdp_bpf2bpf(void) /* Load trace program */ ftrace_skel = test_xdp_bpf2bpf__open(); - if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n")) + if (!ASSERT_OK_PTR(ftrace_skel, "test_xdp_bpf2bpf__open")) goto out; /* Demonstrate the bpf_program__set_attach_target() API rather than @@ -77,50 +138,24 @@ void test_xdp_bpf2bpf(void) bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel"); err = test_xdp_bpf2bpf__load(ftrace_skel); - if (CHECK(err, "__load", "ftrace skeleton failed\n")) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__load")) goto out; err = test_xdp_bpf2bpf__attach(ftrace_skel); - if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err)) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__attach")) goto out; /* Set up perf buffer */ - pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 1, - on_sample, NULL, &passed, NULL); + pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 8, + on_sample, NULL, &test_ctx, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out; - /* Run test program */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); - if (CHECK(err || retval != XDP_TX || size != 74 || - iph.protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size)) - goto out; - - /* Make sure bpf_xdp_output() was triggered and it sent the expected - * data to the perf ring buffer. - */ - err = perf_buffer__poll(pb, 100); - if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) - goto out; - - CHECK_FAIL(!passed); - - /* Verify test results */ - if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), - "result", "fentry failed err %llu\n", - ftrace_skel->bss->test_result_fentry)) - goto out; - - CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result", - "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); - + for (int i = 0; i < ARRAY_SIZE(pkt_sizes); i++) + run_xdp_bpf2bpf_pkt_size(pkt_fd, pb, ftrace_skel, + pkt_sizes[i]); out: - if (pb) - perf_buffer__free(pb); + perf_buffer__free(pb); test_xdp__destroy(pkt_skel); test_xdp_bpf2bpf__destroy(ftrace_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index fd812bd43600..f775a1613833 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -3,11 +3,12 @@ #include <linux/if_link.h> #include <test_progs.h> +#include "test_xdp_with_cpumap_frags_helpers.skel.h" #include "test_xdp_with_cpumap_helpers.skel.h" #define IFINDEX_LO 1 -void serial_test_xdp_cpumap_attach(void) +static void test_xdp_with_cpumap_helpers(void) { struct test_xdp_with_cpumap_helpers *skel; struct bpf_prog_info info = {}; @@ -23,11 +24,11 @@ void serial_test_xdp_cpumap_attach(void) return; prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte CPUMAP")) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); ASSERT_OK(err, "XDP program detach"); prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm); @@ -45,15 +46,76 @@ void serial_test_xdp_cpumap_attach(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id"); /* can not attach BPF_XDP_CPUMAP program to a device */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_CPUMAP program")) - bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); val.qsize = 192; val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry"); + /* Try to attach BPF_XDP program with frags to cpumap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry"); + out_close: test_xdp_with_cpumap_helpers__destroy(skel); } + +static void test_xdp_with_cpumap_frags_helpers(void) +{ + struct test_xdp_with_cpumap_frags_helpers *skel; + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + struct bpf_cpumap_val val = { + .qsize = 192, + }; + int err, frags_prog_fd, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_cpumap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load")) + return; + + frags_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + map_fd = bpf_map__fd(skel->maps.cpu_map); + err = bpf_obj_get_info_by_fd(frags_prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = frags_prog_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add program to cpumap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read cpumap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to cpumap entry prog_id"); + + /* Try to attach BPF_XDP program to cpumap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to cpumap entry"); + +out_close: + test_xdp_with_cpumap_frags_helpers__destroy(skel); +} + +void serial_test_xdp_cpumap_attach(void) +{ + if (test__start_subtest("CPUMAP with programs in entries")) + test_xdp_with_cpumap_helpers(); + + if (test__start_subtest("CPUMAP with frags programs in entries")) + test_xdp_with_cpumap_frags_helpers(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 3079d5568f8f..ead40016c324 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include "test_xdp_devmap_helpers.skel.h" +#include "test_xdp_with_devmap_frags_helpers.skel.h" #include "test_xdp_with_devmap_helpers.skel.h" #define IFINDEX_LO 1 @@ -25,11 +26,11 @@ static void test_xdp_with_devmap_helpers(void) return; dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap")) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); ASSERT_OK(err, "XDP program detach"); dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); @@ -47,15 +48,24 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); /* can not attach BPF_XDP_DEVMAP program to a device */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program")) - bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); val.ifindex = 1; val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_DEVMAP program to devmap entry"); + /* Try to attach BPF_XDP program with frags to devmap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry"); + out_close: test_xdp_with_devmap_helpers__destroy(skel); } @@ -71,12 +81,57 @@ static void test_neg_xdp_devmap_helpers(void) } } +static void test_xdp_with_devmap_frags_helpers(void) +{ + struct test_xdp_with_devmap_frags_helpers *skel; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = { + .ifindex = IFINDEX_LO, + }; + __u32 len = sizeof(info); + int err, dm_fd_frags, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_devmap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) + return; + + dm_fd_frags = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_obj_get_info_by_fd(dm_fd_frags, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = dm_fd_frags; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add frags program to devmap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read devmap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to devmap entry prog_id"); + + /* Try to attach BPF_XDP program to devmap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to devmap entry"); + +out_close: + test_xdp_with_devmap_frags_helpers__destroy(skel); +} void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) test_xdp_with_devmap_helpers(); + if (test__start_subtest("DEVMAP with frags programs in entries")) + test_xdp_with_devmap_frags_helpers(); + if (test__start_subtest("Verifier check of DEVMAP programs")) test_neg_xdp_devmap_helpers(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c index abe48e82e1dc..0d01ff6cb91a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -14,13 +14,13 @@ void serial_test_xdp_info(void) /* Get prog_id for XDP_ATTACHED_NONE mode */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &prog_id); if (CHECK(err, "get_xdp_none", "errno=%d\n", errno)) return; if (CHECK(prog_id, "prog_id_none", "unexpected prog_id=%u\n", prog_id)) return; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_SKB_MODE, &prog_id); if (CHECK(err, "get_xdp_none_skb", "errno=%d\n", errno)) return; if (CHECK(prog_id, "prog_id_none_skb", "unexpected prog_id=%u\n", @@ -37,32 +37,32 @@ void serial_test_xdp_info(void) if (CHECK(err, "get_prog_info", "errno=%d\n", errno)) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (CHECK(err, "set_xdp_skb", "errno=%d\n", errno)) goto out_close; /* Get prog_id for single prog mode */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &prog_id); if (CHECK(err, "get_xdp", "errno=%d\n", errno)) goto out; if (CHECK(prog_id != info.id, "prog_id", "prog_id not available\n")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_SKB_MODE, &prog_id); if (CHECK(err, "get_xdp_skb", "errno=%d\n", errno)) goto out; if (CHECK(prog_id != info.id, "prog_id_skb", "prog_id not available\n")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_DRV_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &prog_id); if (CHECK(err, "get_xdp_drv", "errno=%d\n", errno)) goto out; if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) goto out; out: - bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c index b2b357f8c74c..3e9d5c5521f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -8,9 +8,9 @@ void serial_test_xdp_link(void) { - DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1); struct test_xdp_link *skel1 = NULL, *skel2 = NULL; __u32 id1, id2, id0 = 0, prog_fd1, prog_fd2; + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); struct bpf_link_info link_info; struct bpf_prog_info prog_info; struct bpf_link *link; @@ -41,12 +41,12 @@ void serial_test_xdp_link(void) id2 = prog_info.id; /* set initial prog attachment */ - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); if (!ASSERT_OK(err, "fd_attach")) goto cleanup; /* validate prog ID */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val")) goto cleanup; @@ -55,14 +55,14 @@ void serial_test_xdp_link(void) if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { bpf_link__destroy(link); /* best-effort detach prog */ - opts.old_fd = prog_fd1; - bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + opts.old_prog_fd = prog_fd1; + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_REPLACE, &opts); goto cleanup; } /* detach BPF program */ - opts.old_fd = prog_fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + opts.old_prog_fd = prog_fd1; + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_REPLACE, &opts); if (!ASSERT_OK(err, "prog_detach")) goto cleanup; @@ -73,23 +73,23 @@ void serial_test_xdp_link(void) skel1->links.xdp_handler = link; /* validate prog ID */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val")) goto cleanup; /* BPF prog attach is not allowed to replace BPF link */ - opts.old_fd = prog_fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); + opts.old_prog_fd = prog_fd1; + err = bpf_xdp_attach(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); if (!ASSERT_ERR(err, "prog_attach_fail")) goto cleanup; /* Can't force-update when BPF link is active */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd2, 0, NULL); if (!ASSERT_ERR(err, "prog_update_fail")) goto cleanup; /* Can't force-detach when BPF link is active */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + err = bpf_xdp_detach(IFINDEX_LO, 0, NULL); if (!ASSERT_ERR(err, "prog_detach_fail")) goto cleanup; @@ -109,7 +109,7 @@ void serial_test_xdp_link(void) goto cleanup; skel2->links.xdp_handler = link; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (!ASSERT_OK(err, "id2_check_err") || !ASSERT_EQ(id0, id2, "id2_check_val")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c index 0281095de266..92ef0aa50866 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c @@ -25,43 +25,49 @@ void test_xdp_noinline(void) __u8 flags; } real_def = {.dst = MAGIC_VAL}; __u32 ch_key = 11, real_num = 3; - __u32 duration = 0, retval, size; int err, i; __u64 bytes = 0, pkts = 0; char buf[128]; u32 *magic = (u32 *)buf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = NUM_ITER, + ); skel = test_xdp_noinline__open_and_load(); - if (CHECK(!skel, "skel_open_and_load", "failed\n")) + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) return; bpf_map_update_elem(bpf_map__fd(skel->maps.vip_map), &key, &value, 0); bpf_map_update_elem(bpf_map__fd(skel->maps.ch_rings), &ch_key, &real_num, 0); bpf_map_update_elem(bpf_map__fd(skel->maps.reals), &real_num, &real_def, 0); - err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v4), - NUM_ITER, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 1 || size != 54 || - *magic != MAGIC_VAL, "ipv4", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.balancer_ingress_v4), &topts); + ASSERT_OK(err, "ipv4 test_run"); + ASSERT_EQ(topts.retval, 1, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 54, "ipv4 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv4 test_run magic"); - err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v6), - NUM_ITER, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != 1 || size != 74 || - *magic != MAGIC_VAL, "ipv6", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_out = buf; + topts.data_size_out = sizeof(buf); + + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.balancer_ingress_v6), &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_EQ(topts.retval, 1, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv6 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv6 test_run magic"); bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats), &stats_key, stats); for (i = 0; i < nr_cpus; i++) { bytes += stats[i].bytes; pkts += stats[i].pkts; } - CHECK(bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2, - "stats", "bytes %lld pkts %lld\n", - (unsigned long long)bytes, (unsigned long long)pkts); + ASSERT_EQ(bytes, MAGIC_BYTES * NUM_ITER * 2, "stats bytes"); + ASSERT_EQ(pkts, NUM_ITER * 2, "stats pkts"); test_xdp_noinline__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c index 15a3900e4370..f543d1bd21b8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c @@ -4,22 +4,25 @@ void test_xdp_perf(void) { const char *file = "./xdp_dummy.o"; - __u32 duration, retval, size; struct bpf_object *obj; char in[128], out[128]; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = in, + .data_size_in = sizeof(in), + .data_out = out, + .data_size_out = sizeof(out), + .repeat = 1000000, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 1000000, &in[0], 128, - out, &size, &retval, &duration); - - CHECK(err || retval != XDP_PASS || size != 128, - "xdp-perf", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_PASS, "test_run retval"); + ASSERT_EQ(topts.data_size_out, 128, "test_run data_size_out"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c index d9a88dd1ea65..7efcbdbe772d 100644 --- a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c +++ b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c @@ -5,6 +5,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -87,7 +88,7 @@ bloom_callback(struct bpf_map *map, __u32 *key, void *val, return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_lookup(void *ctx) { struct callback_ctx data; @@ -100,7 +101,7 @@ int bloom_lookup(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_update(void *ctx) { struct callback_ctx data; @@ -113,7 +114,7 @@ int bloom_update(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_hashmap_lookup(void *ctx) { __u64 *result; diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_map.c b/tools/testing/selftests/bpf/progs/bloom_filter_map.c index 1316f3db79d9..f245fcfe0c61 100644 --- a/tools/testing/selftests/bpf/progs/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/progs/bloom_filter_map.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -51,7 +52,7 @@ check_elem(struct bpf_map *map, __u32 *key, __u32 *val, return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int inner_map(void *ctx) { struct bpf_map *inner_map; @@ -70,7 +71,7 @@ int inner_map(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int check_bloom(void *ctx) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..eafc877ea460 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <limits.h> + +#define AUTOBIND_LEN 6 +char sun_path[AUTOBIND_LEN]; + +#define NR_CASES 5 +int sndbuf_setsockopt[NR_CASES] = {-1, 0, 8192, INT_MAX / 2, INT_MAX}; +int sndbuf_getsockopt[NR_CASES] = {-1, -1, -1, -1, -1}; +int sndbuf_getsockopt_expected[NR_CASES]; + +static inline int cmpname(struct unix_sock *unix_sk) +{ + int i; + + for (i = 0; i < AUTOBIND_LEN; i++) { + if (unix_sk->addr->name->sun_path[i] != sun_path[i]) + return -1; + } + + return 0; +} + +SEC("iter/unix") +int change_sndbuf(struct bpf_iter__unix *ctx) +{ + struct unix_sock *unix_sk = ctx->unix_sk; + int i, err; + + if (!unix_sk || !unix_sk->addr) + return 0; + + if (unix_sk->addr->name->sun_path[0]) + return 0; + + if (cmpname(unix_sk)) + return 0; + + for (i = 0; i < NR_CASES; i++) { + err = bpf_setsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_setsockopt[i], + sizeof(sndbuf_setsockopt[i])); + if (err) + break; + + err = bpf_getsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_getsockopt[i], + sizeof(sndbuf_getsockopt[i])); + if (err) + break; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c index c86b93f33b32..d22741272692 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; @@ -23,3 +24,56 @@ int dump_task(struct bpf_iter__task *ctx) BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid); return 0; } + +int num_expected_failure_copy_from_user_task = 0; +int num_success_copy_from_user_task = 0; + +SEC("iter.s/task") +int dump_task_sleepable(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + static const char info[] = " === END ==="; + struct pt_regs *regs; + void *ptr; + uint32_t user_data = 0; + int ret; + + if (task == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Read an invalid pointer and ensure we get an error */ + ptr = NULL; + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + ++num_expected_failure_copy_from_user_task; + } else { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Try to read the contents of the task's instruction pointer from the + * remote task's address space. + */ + regs = (struct pt_regs *)bpf_task_pt_regs(task); + if (regs == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ptr = (void *)PT_REGS_IP(regs); + + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ++num_success_copy_from_user_task; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid data\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c index c21e3f545371..e6aefae38894 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -63,7 +63,7 @@ int dump_unix(struct bpf_iter__unix *ctx) BPF_SEQ_PRINTF(seq, " @"); for (i = 1; i < len; i++) { - /* unix_mkname() tests this upper bound. */ + /* unix_validate_addr() tests this upper bound. */ if (i >= sizeof(struct sockaddr_un)) break; diff --git a/tools/testing/selftests/bpf/progs/bpf_loop.c b/tools/testing/selftests/bpf/progs/bpf_loop.c index 12349e4601e8..e08565282759 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -53,7 +54,7 @@ static int nested_callback1(__u32 index, void *data) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int test_prog(void *ctx) { struct callback_ctx data = {}; @@ -71,7 +72,7 @@ int test_prog(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_null_ctx(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) @@ -82,7 +83,7 @@ int prog_null_ctx(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_invalid_flags(void *ctx) { struct callback_ctx data = {}; @@ -95,7 +96,7 @@ int prog_invalid_flags(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_nested_calls(void *ctx) { struct callback_ctx data = {}; diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c index 9dafdc244462..4ce76eb064c4 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -14,7 +15,7 @@ static int empty_callback(__u32 index, void *data) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int benchmark(void *ctx) { for (int i = 0; i < 1000; i++) { diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h new file mode 100644 index 000000000000..5bb11fe595a4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_MISC_H__ +#define __BPF_MISC_H__ + +#if defined(__TARGET_ARCH_x86) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__x64_" +#elif defined(__TARGET_ARCH_s390) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__s390x_" +#elif defined(__TARGET_ARCH_arm64) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__arm64_" +#else +#define SYSCALL_WRAPPER 0 +#define SYS_PREFIX "__se_" +#endif + +#endif diff --git a/tools/testing/selftests/bpf/progs/bpf_mod_race.c b/tools/testing/selftests/bpf/progs/bpf_mod_race.c new file mode 100644 index 000000000000..82a5c6c6ba83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_mod_race.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile struct { + /* thread to activate trace programs for */ + pid_t tgid; + /* return error from __init function */ + int inject_error; + /* uffd monitored range start address */ + void *fault_addr; +} bpf_mod_race_config = { -1 }; + +int bpf_blocking = 0; +int res_try_get_module = -1; + +static __always_inline bool check_thread_id(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + return task->tgid == bpf_mod_race_config.tgid; +} + +/* The trace of execution is something like this: + * + * finit_module() + * load_module() + * prepare_coming_module() + * notifier_call(MODULE_STATE_COMING) + * btf_parse_module() + * btf_alloc_id() // Visible to userspace at this point + * list_add(btf_mod->list, &btf_modules) + * do_init_module() + * freeinit = kmalloc() + * ret = mod->init() + * bpf_prog_widen_race() + * bpf_copy_from_user() + * ...<sleep>... + * if (ret < 0) + * ... + * free_module() + * return ret + * + * At this point, module loading thread is blocked, we now load the program: + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module_live == false + * return -ENXIO + * + * Without the fix (try_get_module_live in btf_try_get_module): + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module == true + * <store module reference in btf_kfunc_tab or used_btf array> + * ... + * return fd + * + * Now, if we inject an error in the blocked program, our module will be freed + * (going straight from MODULE_STATE_COMING to MODULE_STATE_GOING). + * Later, when bpf program is freed, it will try to module_put already freed + * module. This is why try_get_module_live returns false if mod->state is not + * MODULE_STATE_LIVE. + */ + +SEC("fmod_ret.s/bpf_fentry_test1") +int BPF_PROG(widen_race, int a, int ret) +{ + char dst; + + if (!check_thread_id()) + return 0; + /* Indicate that we will attempt to block */ + bpf_blocking = 1; + bpf_copy_from_user(&dst, 1, bpf_mod_race_config.fault_addr); + return bpf_mod_race_config.inject_error; +} + +SEC("fexit/do_init_module") +int BPF_PROG(fexit_init_module, struct module *mod, int ret) +{ + if (!check_thread_id()) + return 0; + /* Indicate that we finished blocking */ + bpf_blocking = 2; + return 0; +} + +SEC("fexit/btf_try_get_module") +int BPF_PROG(fexit_module_get, const struct btf *btf, struct module *mod) +{ + res_try_get_module = !!mod; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c new file mode 100644 index 000000000000..05838ed9b89c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 Sony Group Corporation */ +#include <vmlinux.h> + +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +int arg1 = 0; +unsigned long arg2 = 0; +unsigned long arg3 = 0; +unsigned long arg4_cx = 0; +unsigned long arg4 = 0; +unsigned long arg5 = 0; + +int arg1_core = 0; +unsigned long arg2_core = 0; +unsigned long arg3_core = 0; +unsigned long arg4_core_cx = 0; +unsigned long arg4_core = 0; +unsigned long arg5_core = 0; + +int option_syscall = 0; +unsigned long arg2_syscall = 0; +unsigned long arg3_syscall = 0; +unsigned long arg4_syscall = 0; +unsigned long arg5_syscall = 0; + +const volatile pid_t filter_pid = 0; + +SEC("kprobe/" SYS_PREFIX "sys_prctl") +int BPF_KPROBE(handle_sys_prctl) +{ + struct pt_regs *real_regs; + pid_t pid = bpf_get_current_pid_tgid() >> 32; + unsigned long tmp = 0; + + if (pid != filter_pid) + return 0; + + real_regs = PT_REGS_SYSCALL_REGS(ctx); + + /* test for PT_REGS_PARM */ + +#if !defined(bpf_target_arm64) && !defined(bpf_target_s390) + bpf_probe_read_kernel(&tmp, sizeof(tmp), &PT_REGS_PARM1_SYSCALL(real_regs)); +#endif + arg1 = tmp; + bpf_probe_read_kernel(&arg2, sizeof(arg2), &PT_REGS_PARM2_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg3, sizeof(arg3), &PT_REGS_PARM3_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg4_cx, sizeof(arg4_cx), &PT_REGS_PARM4(real_regs)); + bpf_probe_read_kernel(&arg4, sizeof(arg4), &PT_REGS_PARM4_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg5, sizeof(arg5), &PT_REGS_PARM5_SYSCALL(real_regs)); + + /* test for the CORE variant of PT_REGS_PARM */ + arg1_core = PT_REGS_PARM1_CORE_SYSCALL(real_regs); + arg2_core = PT_REGS_PARM2_CORE_SYSCALL(real_regs); + arg3_core = PT_REGS_PARM3_CORE_SYSCALL(real_regs); + arg4_core_cx = PT_REGS_PARM4_CORE(real_regs); + arg4_core = PT_REGS_PARM4_CORE_SYSCALL(real_regs); + arg5_core = PT_REGS_PARM5_CORE_SYSCALL(real_regs); + + return 0; +} + +SEC("kprobe/" SYS_PREFIX "sys_prctl") +int BPF_KPROBE_SYSCALL(prctl_enter, int option, unsigned long arg2, + unsigned long arg3, unsigned long arg4, unsigned long arg5) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != filter_pid) + return 0; + + option_syscall = option; + arg2_syscall = arg2; + arg3_syscall = arg3; + arg4_syscall = arg4; + arg5_syscall = arg5; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index e0f42601be9b..1c1289ba5fc5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -5,6 +5,8 @@ #define AF_INET 2 #define AF_INET6 10 +#define SOL_SOCKET 1 +#define SO_SNDBUF 7 #define __SO_ACCEPTCON (1 << 16) #define SOL_TCP 6 diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_user.c b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c new file mode 100644 index 000000000000..5523f77c5a44 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +int g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_1") +int BPF_PROG(test_user1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_2") +int BPF_PROG(test_user2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, + * int __user *usockaddr_len); + */ +SEC("fentry/__sys_getsockname") +int BPF_PROG(test_sys_getsockname, int fd, struct sockaddr *usockaddr, + int *usockaddr_len) +{ + g = usockaddr->sa_family; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c new file mode 100644 index 000000000000..b2a409e6382a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; +__u32 ctx_retval_value = 0; + +SEC("cgroup/getsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + ctx_retval_value = ctx->retval; + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/getsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 1; +} + +SEC("cgroup/getsockopt") +int clear_retval(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + ctx->retval = 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c new file mode 100644 index 000000000000..d6e5903e06ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; + +SEC("cgroup/setsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/setsockopt") +int set_eunatch(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EUNATCH)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int legacy_eperm(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/core_kern.c b/tools/testing/selftests/bpf/progs/core_kern.c index 13499cc15c7d..2715fe27d4cf 100644 --- a/tools/testing/selftests/bpf/progs/core_kern.c +++ b/tools/testing/selftests/bpf/progs/core_kern.c @@ -101,4 +101,20 @@ int balancer_ingress(struct __sk_buff *ctx) return 0; } +typedef int (*func_proto_typedef___match)(long); +typedef int (*func_proto_typedef___doesnt_match)(char *); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef___match); + +int proto_out[3]; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out[0] = bpf_core_type_exists(func_proto_typedef___match); + proto_out[1] = bpf_core_type_exists(func_proto_typedef___doesnt_match); + proto_out[2] = bpf_core_type_exists(func_proto_typedef_nested1); + + return 0; +} + char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/core_kern_overflow.c b/tools/testing/selftests/bpf/progs/core_kern_overflow.c new file mode 100644 index 000000000000..f0d5652256ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_kern_overflow.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +typedef int (*func_proto_typedef)(long); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef); +typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); + +int proto_out; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out = bpf_core_type_exists(func_proto_typedef_nested2); + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c index bca92c9bd29a..106dc75efcc4 100644 --- a/tools/testing/selftests/bpf/progs/fexit_sleep.c +++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char LICENSE[] SEC("license") = "GPL"; @@ -10,8 +11,8 @@ int pid = 0; int fentry_cnt = 0; int fexit_cnt = 0; -SEC("fentry/__x64_sys_nanosleep") -int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fentry(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; @@ -20,8 +21,8 @@ int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) return 0; } -SEC("fexit/__x64_sys_nanosleep") -int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret) +SEC("fexit/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fexit(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; diff --git a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c index 68a5a9db928a..7e94412d47a5 100644 --- a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c @@ -7,12 +7,12 @@ #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") sock_map = { - .type = BPF_MAP_TYPE_SOCKMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, int); + __uint(max_entries, 2); +} sock_map SEC(".maps"); SEC("freplace/cls_redirect") int freplace_cls_redirect_test(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c new file mode 100644 index 000000000000..4e8fed75a4e0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; + +SEC("tc") +int kfunc_call_fail(struct __sk_buff *ctx) +{ + bpf_testmod_test_mod_kfunc(0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 8a8cf59017aa..5aecbb9fdc68 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -1,13 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; +extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; +extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { @@ -44,4 +51,45 @@ int kfunc_call_test1(struct __sk_buff *skb) return ret; } +SEC("tc") +int kfunc_call_test_ref_btf_id(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + if (pt->a != 42 || pt->b != 108) + ret = -1; + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("tc") +int kfunc_call_test_pass(struct __sk_buff *skb) +{ + struct prog_test_pass1 p1 = {}; + struct prog_test_pass2 p2 = {}; + short a = 0; + __u64 b = 0; + long c = 0; + char d = 0; + int e = 0; + + bpf_kfunc_call_test_pass_ctx(skb); + bpf_kfunc_call_test_pass1(&p1); + bpf_kfunc_call_test_pass2(&p2); + + bpf_kfunc_call_test_mem_len_pass1(&a, sizeof(a)); + bpf_kfunc_call_test_mem_len_pass1(&b, sizeof(b)); + bpf_kfunc_call_test_mem_len_pass1(&c, sizeof(c)); + bpf_kfunc_call_test_mem_len_pass1(&d, sizeof(d)); + bpf_kfunc_call_test_mem_len_pass1(&e, sizeof(e)); + bpf_kfunc_call_test_mem_len_fail2(&b, -1); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/ksym_race.c b/tools/testing/selftests/bpf/progs/ksym_race.c new file mode 100644 index 000000000000..def97f2fed90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ksym_race.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern int bpf_testmod_ksym_percpu __ksym; + +SEC("tc") +int ksym_fail(struct __sk_buff *ctx) +{ + return *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c index e5ab4836a641..45204fe0c570 100644 --- a/tools/testing/selftests/bpf/progs/perfbuf_bench.c +++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <stdint.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -18,7 +19,7 @@ const volatile int batch_cnt = 0; long sample_val = 42; long dropped __attribute__((aligned(128))) = 0; -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_perfbuf(void *ctx) { __u64 *sample; diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c index 123607d314d6..6a468496f539 100644 --- a/tools/testing/selftests/bpf/progs/ringbuf_bench.c +++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <stdint.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -30,7 +31,7 @@ static __always_inline long get_flags() return sz >= wakeup_data_size ? BPF_RB_FORCE_WAKEUP : BPF_RB_NO_WAKEUP; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_ringbuf(void *ctx) { long *sample, flags; diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c index 1612a32007b6..495990d355ef 100644 --- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c @@ -2,19 +2,19 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") htab = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} htab SEC(".maps"); -struct bpf_map_def SEC("maps") array = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} array SEC(".maps"); /* Sample program which should always load for testing control paths. */ SEC(".text") int func() diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 95d5b941bc1f..c9abfe3a11af 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -7,8 +7,6 @@ int bpf_prog1(struct __sk_buff *skb) { void *data_end = (void *)(long) skb->data_end; void *data = (void *)(long) skb->data; - __u32 lport = skb->local_port; - __u32 rport = skb->remote_port; __u8 *d = data; int err; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 79c8139b63b8..c8d810010a94 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -72,18 +72,19 @@ int _getsockopt(struct bpf_sockopt *ctx) * reasons. */ - if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end) - return 0; /* EPERM, bounds check */ + /* Check that optval contains address (__u64) */ + if (optval + sizeof(__u64) > optval_end) + return 0; /* bounds check */ if (((struct tcp_zerocopy_receive *)optval)->address != 0) - return 0; /* EPERM, unexpected data */ + return 0; /* unexpected data */ return 1; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -96,24 +97,24 @@ int _getsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ if (!ctx->retval) - return 0; /* EPERM, kernel should not have handled + return 0; /* kernel should not have handled * SOL_CUSTOM, something is wrong! */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -152,7 +153,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Overwrite SO_SNDBUF value */ if (optval + sizeof(__u32) > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ *(__u32 *)optval = 0x55AA; ctx->optlen = 4; @@ -164,7 +165,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Always use cubic */ if (optval + 5 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ memcpy(optval, "cubic", 5); ctx->optlen = 5; @@ -175,10 +176,10 @@ int _setsockopt(struct bpf_sockopt *ctx) if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { /* Original optlen is larger than PAGE_SIZE. */ if (ctx->optlen != page_size * 2) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ /* Make sure we can trim the buffer. */ optval[0] = 0; @@ -189,21 +190,21 @@ int _setsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ storage->val = optval[0]; ctx->optlen = -1; /* BPF has consumed this option, don't call kernel diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c new file mode 100644 index 000000000000..f00a9731930e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define EAFNOSUPPORT 97 +#define EPROTO 71 +#define ENONET 64 +#define EINVAL 22 +#define ENOENT 2 + +int test_einval_bpf_tuple = 0; +int test_einval_reserved = 0; +int test_einval_netns_id = 0; +int test_einval_len_opts = 0; +int test_eproto_l4proto = 0; +int test_enonet_netns_id = 0; +int test_enoent_lookup = 0; +int test_eafnosupport = 0; + +struct nf_conn; + +struct bpf_ct_opts___local { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +} __attribute__((preserve_access_index)); + +struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +void bpf_ct_release(struct nf_conn *) __ksym; + +static __always_inline void +nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32), + void *ctx) +{ + struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 }; + struct bpf_sock_tuple bpf_tuple; + struct nf_conn *ct; + + __builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4)); + + ct = func(ctx, NULL, 0, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_einval_bpf_tuple = opts_def.error; + + opts_def.reserved[0] = 1; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.reserved[0] = 0; + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_einval_reserved = opts_def.error; + + opts_def.netns_id = -2; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_einval_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def) - 1); + if (ct) + bpf_ct_release(ct); + else + test_einval_len_opts = opts_def.error; + + opts_def.l4proto = IPPROTO_ICMP; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_eproto_l4proto = opts_def.error; + + opts_def.netns_id = 0xf00f; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_enonet_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_enoent_lookup = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_eafnosupport = opts_def.error; +} + +SEC("xdp") +int nf_xdp_ct_test(struct xdp_md *ctx) +{ + nf_ct_test((void *)bpf_xdp_ct_lookup, ctx); + return 0; +} + +SEC("tc") +int nf_skb_ct_test(struct __sk_buff *ctx) +{ + nf_ct_test((void *)bpf_skb_ct_lookup, ctx); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/btf_decl_tag.c b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c index c88ccc53529a..c88ccc53529a 100644 --- a/tools/testing/selftests/bpf/progs/btf_decl_tag.c +++ b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 160ead6c67b2..07c94df13660 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -9,12 +9,15 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" struct bpf_map_def SEC("maps") btf_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), .value_size = sizeof(struct ipv_counts), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index 1884a5bd10f5..762671a2e90c 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -9,6 +9,8 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" /* just to validate we can handle maps in multiple sections */ struct bpf_map_def SEC("maps") btf_map_legacy = { .type = BPF_MAP_TYPE_ARRAY, @@ -16,6 +18,7 @@ struct bpf_map_def SEC("maps") btf_map_legacy = { .value_size = sizeof(long long), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 15e0f9945fe4..1dabb88f8cb4 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -8,12 +8,12 @@ struct ipv_counts { unsigned int v6; }; -struct bpf_map_def SEC("maps") btf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct ipv_counts), - .max_entries = 4, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct ipv_counts)); + __uint(max_entries, 4); +} btf_map SEC(".maps"); __attribute__((noinline)) int test_long_fname_2(void) diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 8812a90da4eb..702578a5e496 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -7,20 +7,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> - -#if defined(__TARGET_ARCH_x86) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__x64_" -#elif defined(__TARGET_ARCH_s390) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__s390x_" -#elif defined(__TARGET_ARCH_arm64) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__arm64_" -#else -#define SYSCALL_WRAPPER 0 -#define SYS_PREFIX "" -#endif +#include "bpf_misc.h" static struct sockaddr_in old; diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c index eaa7d9dba0be..5bdc0d38efc0 100644 --- a/tools/testing/selftests/bpf/progs/test_ringbuf.c +++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -35,7 +36,7 @@ long prod_pos = 0; /* inner state */ long seq = 0; -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int test_ringbuf(void *ctx) { int cur_pid = bpf_get_current_pid_tgid() >> 32; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index 83b0aaa52ef7..bf5b7caefdd0 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -392,6 +392,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; int err, family; + __u32 val_u32; bool v4; v4 = (ctx->family == AF_INET); @@ -418,6 +419,11 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) if (LSW(ctx->remote_port, 0) != SRC_PORT) return SK_DROP; + /* Load from remote_port field with zero padding (backward compatibility) */ + val_u32 = *(__u32 *)&ctx->remote_port; + if (val_u32 != bpf_htonl(bpf_ntohs(SRC_PORT) << 16)) + return SK_DROP; + /* Narrow loads from local_port field. Expect DST_PORT. */ if (LSB(ctx->local_port, 0) != ((DST_PORT >> 0) & 0xff) || LSB(ctx->local_port, 1) != ((DST_PORT >> 8) & 0xff) || diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index c304cd5b8cad..37aacc66cd68 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -10,12 +10,12 @@ #define NUM_CGROUP_LEVELS 4 -struct bpf_map_def SEC("maps") cgroup_ids = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = NUM_CGROUP_LEVELS, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, NUM_CGROUP_LEVELS); +} cgroup_ids SEC(".maps"); static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level) { diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index 81b57b9aaaea..246f1f001813 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -12,6 +12,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -250,4 +251,44 @@ int ingress_read_sock_fields(struct __sk_buff *skb) return CG_OK; } +static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) +{ + __u32 *word = (__u32 *)&sk->dst_port; + return word[0] == bpf_htonl(0xcafe0000); +} + +static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) +{ + __u16 *half = (__u16 *)&sk->dst_port; + return half[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_byte(struct bpf_sock *sk) +{ + __u8 *byte = (__u8 *)&sk->dst_port; + return byte[0] == 0xca && byte[1] == 0xfe; +} + +SEC("cgroup_skb/egress") +int read_sk_dst_port(struct __sk_buff *skb) +{ + __u32 linum, linum_idx; + struct bpf_sock *sk; + + linum_idx = READ_SK_DST_PORT_LINUM_IDX; + + sk = skb->sk; + if (!sk) + RET_LOG(); + + if (!sk_dst_port__load_word(sk)) + RET_LOG(); + if (!sk_dst_port__load_half(sk)) + RET_LOG(); + if (!sk_dst_port__load_byte(sk)) + RET_LOG(); + + return CG_OK; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c new file mode 100644 index 000000000000..9d58d61c0dee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +SEC("sk_msg") +int prog_skmsg_verdict(struct sk_msg_md *msg) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index bf28814bfde5..950a70b61e74 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -17,12 +17,12 @@ #define THROTTLE_RATE_BPS (5 * 1000 * 1000) /* flow_key => last_tstamp timestamp used */ -struct bpf_map_def SEC("maps") flow_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(uint32_t), - .value_size = sizeof(uint64_t), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, uint32_t); + __type(value, uint64_t); + __uint(max_entries, 1); +} flow_map SEC(".maps"); static inline int throttle_flow(struct __sk_buff *skb) { 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 cd747cd93dbe..6edebce563b5 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 @@ -16,12 +16,12 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -struct bpf_map_def SEC("maps") results = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), - .max_entries = 3, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 3); +} results SEC(".maps"); static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, void *iph, __u32 ip_size, diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 199c61b7d062..53b64c999450 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -7,11 +7,10 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; void *data = (void *)(long)xdp->data; - unsigned int data_len; + int data_len = bpf_xdp_get_buff_len(xdp); int offset = 0; /* Data length determine test case */ - data_len = data_end - data; if (data_len == 54) { /* sizeof(pkt_v4) */ offset = 4096; /* test too large offset */ @@ -20,7 +19,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) } else if (data_len == 64) { offset = 128; } else if (data_len == 128) { - offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */ + /* Max tail grow 3520 */ + offset = 4096 - 256 - 320 - data_len; + } else if (data_len == 9000) { + offset = 10; + } else if (data_len == 9001) { + offset = 4096; } else { return XDP_ABORTED; /* No matching test */ } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index b7448253d135..ca68c038357c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -12,14 +12,38 @@ SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { - void *data_end = (void *)(long)xdp->data_end; - void *data = (void *)(long)xdp->data; + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; int offset = 0; - if (data_end - data == 54) /* sizeof(pkt_v4) */ + switch (bpf_xdp_get_buff_len(xdp)) { + case 54: + /* sizeof(pkt_v4) */ offset = 256; /* shrink too much */ - else + break; + case 9000: + /* non-linear buff test cases */ + if (data + 1 > data_end) + return XDP_DROP; + + switch (data[0]) { + case 0: + offset = 10; + break; + case 1: + offset = 4100; + break; + case 2: + offset = 8200; + break; + default: + return XDP_DROP; + } + break; + default: offset = 20; + break; + } if (bpf_xdp_adjust_tail(xdp, 0 - offset)) return XDP_DROP; return XDP_TX; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index 58cf4345f5cc..3379d303f41a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -49,7 +49,7 @@ int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) void *data = (void *)(long)xdp->data; meta.ifindex = xdp->rxq->dev->ifindex; - meta.pkt_len = data_end - data; + meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp); bpf_xdp_output(xdp, &perf_buf_map, ((__u64) meta.pkt_len << 32) | BPF_F_CURRENT_CPU, diff --git a/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c new file mode 100644 index 000000000000..2a3496d8e327 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <bpf/bpf_helpers.h> + +int _version SEC("version") = 1; + +SEC("xdp.frags") +int xdp_adjust_frags(struct xdp_md *xdp) +{ + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; + __u8 val[16] = {}; + __u32 offset; + int err; + + if (data + sizeof(__u32) > data_end) + return XDP_DROP; + + offset = *(__u32 *)data; + err = bpf_xdp_load_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + if (val[0] != 0xaa || val[15] != 0xaa) /* marker */ + return XDP_DROP; + + val[0] = 0xbb; /* update the marker */ + val[15] = 0xbb; + err = bpf_xdp_store_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c new file mode 100644 index 000000000000..97ed625bb70a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp/cpumap") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 532025057711..20ec6723df18 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -24,7 +24,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) return XDP_PASS; } -SEC("xdp_cpumap/dummy_cm") +SEC("xdp/cpumap") int xdp_dummy_cm(struct xdp_md *ctx) { if (ctx->ingress_ifindex == IFINDEX_LO) @@ -33,4 +33,10 @@ int xdp_dummy_cm(struct xdp_md *ctx) return XDP_PASS; } +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c new file mode 100644 index 000000000000..cdcf7de7ec8c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 4); +} dm_ports SEC(".maps"); + +/* valid program on DEVMAP entry via SEC name; + * has access to egress and ingress ifindex + */ +SEC("xdp/devmap") +int xdp_dummy_dm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 1e6b9c38ea6d..4139a14f9996 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -27,7 +27,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) /* valid program on DEVMAP entry via SEC name; * has access to egress and ingress ifindex */ -SEC("xdp_devmap/map_prog") +SEC("xdp/devmap") int xdp_dummy_dm(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; @@ -40,4 +40,11 @@ int xdp_dummy_dm(struct xdp_md *ctx) return XDP_PASS; } + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c index 119582aa105a..6695478c2b25 100644 --- a/tools/testing/selftests/bpf/progs/trace_printk.c +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -4,6 +4,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -12,7 +13,7 @@ int trace_printk_ran = 0; const char fmt[] = "Testing,testing %d\n"; -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int sys_enter(void *ctx) { trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c index d327241ba047..969306cd4f33 100644 --- a/tools/testing/selftests/bpf/progs/trace_vprintk.c +++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c @@ -4,6 +4,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -11,7 +12,7 @@ int null_data_vprintk_ret = 0; int trace_vprintk_ret = 0; int trace_vprintk_ran = 0; -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int sys_enter(void *ctx) { static const char one[] = "1"; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 2098f3f27f18..2ab049b54d6c 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -5,6 +5,7 @@ #include <asm/unistd.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -25,28 +26,28 @@ int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id) return 0; } -SEC("kprobe/__x64_sys_getpgid") +SEC("kprobe/" SYS_PREFIX "sys_getpgid") int bench_trigger_kprobe(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fentry.s/__x64_sys_getpgid") +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry_sleep(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fmod_ret/__x64_sys_getpgid") +SEC("fmod_ret/" SYS_PREFIX "sys_getpgid") int bench_trigger_fmodret(void *ctx) { __sync_add_and_fetch(&hits, 1); diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c index 8395782b6e0a..97b26a30b59a 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -70,7 +70,7 @@ int xdp_redirect_map_all_prog(struct xdp_md *ctx) BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); } -SEC("xdp_devmap/map_prog") +SEC("xdp/devmap") int xdp_devmap_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index b9f1bbbc8aba..6e6235185a86 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -61,7 +61,11 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, }; __u8 data[64] = {}; int mfd, pfd, ret, zero = 0; - __u32 retval = 0; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = data, + .data_size_in = sizeof(data), + .repeat = 1, + ); mfd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(__u64), 1, NULL); if (mfd < 0) @@ -75,9 +79,8 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, return -1; } - ret = bpf_prog_test_run(pfd, 1, data, sizeof(data), - NULL, NULL, &retval, NULL); - if (ret < 0 || retval != 42) { + ret = bpf_prog_test_run_opts(pfd, &topts); + if (ret < 0 || topts.retval != 42) { ret = -1; } else { assert(!bpf_map_lookup_elem(mfd, &zero, value)); diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 5620919fde9e..826f4423ce02 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -23,6 +23,12 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" +readonly NS3="ns3-$(mktemp -u XXXXXX)" +readonly NS4="ns4-$(mktemp -u XXXXXX)" +readonly NS5="ns5-$(mktemp -u XXXXXX)" +readonly NS6="ns6-$(mktemp -u XXXXXX)" msg="skip all tests:" if [ $UID != 0 ]; then @@ -41,23 +47,23 @@ cleanup() fi set +e - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null - ip netns del ns3 2> /dev/null - ip netns del ns4 2> /dev/null - ip netns del ns5 2> /dev/null - ip netns del ns6 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null + ip netns del ${NS3} 2> /dev/null + ip netns del ${NS4} 2> /dev/null + ip netns del ${NS5} 2> /dev/null + ip netns del ${NS6} 2> /dev/null rm -f $TMP_FILE } set -e -ip netns add ns1 -ip netns add ns2 -ip netns add ns3 -ip netns add ns4 -ip netns add ns5 -ip netns add ns6 +ip netns add ${NS1} +ip netns add ${NS2} +ip netns add ${NS3} +ip netns add ${NS4} +ip netns add ${NS5} +ip netns add ${NS6} trap cleanup 0 2 3 6 9 @@ -67,78 +73,78 @@ ip link add veth5 type veth peer name veth6 ip link add veth7 type veth peer name veth8 ip link add veth9 type veth peer name veth10 -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 -ip link set veth3 netns ns2 -ip link set veth4 netns ns3 -ip link set veth5 netns ns3 -ip link set veth6 netns ns4 -ip link set veth7 netns ns4 -ip link set veth8 netns ns5 -ip link set veth9 netns ns5 -ip link set veth10 netns ns6 - -ip netns exec ns1 ip link set dev veth1 up -ip netns exec ns2 ip link set dev veth2 up -ip netns exec ns2 ip link set dev veth3 up -ip netns exec ns3 ip link set dev veth4 up -ip netns exec ns3 ip link set dev veth5 up -ip netns exec ns4 ip link set dev veth6 up -ip netns exec ns4 ip link set dev veth7 up -ip netns exec ns5 ip link set dev veth8 up -ip netns exec ns5 ip link set dev veth9 up -ip netns exec ns6 ip link set dev veth10 up -ip netns exec ns6 ip link set dev lo up +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} +ip link set veth3 netns ${NS2} +ip link set veth4 netns ${NS3} +ip link set veth5 netns ${NS3} +ip link set veth6 netns ${NS4} +ip link set veth7 netns ${NS4} +ip link set veth8 netns ${NS5} +ip link set veth9 netns ${NS5} +ip link set veth10 netns ${NS6} + +ip netns exec ${NS1} ip link set dev veth1 up +ip netns exec ${NS2} ip link set dev veth2 up +ip netns exec ${NS2} ip link set dev veth3 up +ip netns exec ${NS3} ip link set dev veth4 up +ip netns exec ${NS3} ip link set dev veth5 up +ip netns exec ${NS4} ip link set dev veth6 up +ip netns exec ${NS4} ip link set dev veth7 up +ip netns exec ${NS5} ip link set dev veth8 up +ip netns exec ${NS5} ip link set dev veth9 up +ip netns exec ${NS6} ip link set dev veth10 up +ip netns exec ${NS6} ip link set dev lo up # All link scope addresses and routes required between veths -ip netns exec ns1 ip -6 addr add fb00::12/16 dev veth1 scope link -ip netns exec ns1 ip -6 route add fb00::21 dev veth1 scope link -ip netns exec ns2 ip -6 addr add fb00::21/16 dev veth2 scope link -ip netns exec ns2 ip -6 addr add fb00::34/16 dev veth3 scope link -ip netns exec ns2 ip -6 route add fb00::43 dev veth3 scope link -ip netns exec ns3 ip -6 route add fb00::65 dev veth5 scope link -ip netns exec ns3 ip -6 addr add fb00::43/16 dev veth4 scope link -ip netns exec ns3 ip -6 addr add fb00::56/16 dev veth5 scope link -ip netns exec ns4 ip -6 addr add fb00::65/16 dev veth6 scope link -ip netns exec ns4 ip -6 addr add fb00::78/16 dev veth7 scope link -ip netns exec ns4 ip -6 route add fb00::87 dev veth7 scope link -ip netns exec ns5 ip -6 addr add fb00::87/16 dev veth8 scope link -ip netns exec ns5 ip -6 addr add fb00::910/16 dev veth9 scope link -ip netns exec ns5 ip -6 route add fb00::109 dev veth9 scope link -ip netns exec ns5 ip -6 route add fb00::109 table 117 dev veth9 scope link -ip netns exec ns6 ip -6 addr add fb00::109/16 dev veth10 scope link - -ip netns exec ns1 ip -6 addr add fb00::1/16 dev lo -ip netns exec ns1 ip -6 route add fb00::6 dev veth1 via fb00::21 - -ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 -ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link - -ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 -ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 - -ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 -ip netns exec ns4 ip -6 addr add fc42::1 dev lo -ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 - -ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 -ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 - -ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo -ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo - -ip netns exec ns1 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns2 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns3 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns4 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns5 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - -ip netns exec ns6 sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null -ip netns exec ns6 sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null -ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null - -ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE & -ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" +ip netns exec ${NS1} ip -6 addr add fb00::12/16 dev veth1 scope link +ip netns exec ${NS1} ip -6 route add fb00::21 dev veth1 scope link +ip netns exec ${NS2} ip -6 addr add fb00::21/16 dev veth2 scope link +ip netns exec ${NS2} ip -6 addr add fb00::34/16 dev veth3 scope link +ip netns exec ${NS2} ip -6 route add fb00::43 dev veth3 scope link +ip netns exec ${NS3} ip -6 route add fb00::65 dev veth5 scope link +ip netns exec ${NS3} ip -6 addr add fb00::43/16 dev veth4 scope link +ip netns exec ${NS3} ip -6 addr add fb00::56/16 dev veth5 scope link +ip netns exec ${NS4} ip -6 addr add fb00::65/16 dev veth6 scope link +ip netns exec ${NS4} ip -6 addr add fb00::78/16 dev veth7 scope link +ip netns exec ${NS4} ip -6 route add fb00::87 dev veth7 scope link +ip netns exec ${NS5} ip -6 addr add fb00::87/16 dev veth8 scope link +ip netns exec ${NS5} ip -6 addr add fb00::910/16 dev veth9 scope link +ip netns exec ${NS5} ip -6 route add fb00::109 dev veth9 scope link +ip netns exec ${NS5} ip -6 route add fb00::109 table 117 dev veth9 scope link +ip netns exec ${NS6} ip -6 addr add fb00::109/16 dev veth10 scope link + +ip netns exec ${NS1} ip -6 addr add fb00::1/16 dev lo +ip netns exec ${NS1} ip -6 route add fb00::6 dev veth1 via fb00::21 + +ip netns exec ${NS2} ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 +ip netns exec ${NS2} ip -6 route add fd00::1 dev veth3 via fb00::43 scope link + +ip netns exec ${NS3} ip -6 route add fc42::1 dev veth5 via fb00::65 +ip netns exec ${NS3} ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 + +ip netns exec ${NS4} ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ${NS4} ip -6 addr add fc42::1 dev lo +ip netns exec ${NS4} ip -6 route add fd00::3 dev veth7 via fb00::87 + +ip netns exec ${NS5} ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 +ip netns exec ${NS5} ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 + +ip netns exec ${NS6} ip -6 addr add fb00::6/16 dev lo +ip netns exec ${NS6} ip -6 addr add fd00::4/16 dev lo + +ip netns exec ${NS1} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS2} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS3} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS4} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS5} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + +ip netns exec ${NS6} sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null +ip netns exec ${NS6} sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null +ip netns exec ${NS6} sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null + +ip netns exec ${NS6} nc -l -6 -u -d 7330 > $TMP_FILE & +ip netns exec ${NS1} bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment kill -TERM $! diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 50f7e74ca0b9..cbebfaa7c1e8 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -738,7 +738,7 @@ static void test_sockmap(unsigned int tasks, void *data) sizeof(key), sizeof(value), 6, NULL); if (fd < 0) { - if (!bpf_probe_map_type(BPF_MAP_TYPE_SOCKMAP, 0)) { + if (!libbpf_probe_bpf_map_type(BPF_MAP_TYPE_SOCKMAP, NULL)) { printf("%s SKIP (unsupported map type BPF_MAP_TYPE_SOCKMAP)\n", __func__); skips++; diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index 6413c1472554..102e6588e2fe 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -4,6 +4,7 @@ # Copyright (c) 2019 Cloudflare set -eu +readonly NS1="ns1-$(mktemp -u XXXXXX)" wait_for_ip() { @@ -28,12 +29,12 @@ get_prog_id() ns1_exec() { - ip netns exec ns1 "$@" + ip netns exec ${NS1} "$@" } setup() { - ip netns add ns1 + ip netns add ${NS1} ns1_exec ip link set lo up ns1_exec sysctl -w net.ipv4.tcp_syncookies=2 diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 76cd903117af..92e3465fbae8 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -31,6 +31,7 @@ #include <linux/if_ether.h> #include <linux/btf.h> +#include <bpf/btf.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -66,6 +67,11 @@ static bool unpriv_disabled = false; static int skips; static bool verbose = false; +struct kfunc_btf_id_pair { + const char *kfunc; + int insn_idx; +}; + struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -92,6 +98,7 @@ struct bpf_test { int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; int fixup_map_timer[MAX_FIXUPS]; + struct kfunc_btf_id_pair fixup_kfunc_btf_id[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -449,7 +456,7 @@ static int probe_filter_length(const struct bpf_insn *fp) static bool skip_unsupported_map(enum bpf_map_type map_type) { - if (!bpf_probe_map_type(map_type, 0)) { + if (!libbpf_probe_bpf_map_type(map_type, NULL)) { printf("SKIP (unsupported map type %d)\n", map_type); skips++; return true; @@ -744,6 +751,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; + struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -936,6 +944,26 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_timer++; } while (*fixup_map_timer); } + + /* Patch in kfunc BTF IDs */ + if (fixup_kfunc_btf_id->kfunc) { + struct btf *btf; + int btf_id; + + do { + btf_id = 0; + btf = btf__load_vmlinux_btf(); + if (btf) { + btf_id = btf__find_by_name_kind(btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + btf__free(btf); + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } while (fixup_kfunc_btf_id->kfunc); + } } struct libcap { @@ -993,13 +1021,18 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, { __u8 tmp[TEST_DATA_LEN << 2]; __u32 size_tmp = sizeof(tmp); - uint32_t retval; int err, saved_errno; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = data, + .data_size_in = size_data, + .data_out = tmp, + .data_size_out = size_tmp, + .repeat = 1, + ); if (unpriv) set_admin(true); - err = bpf_prog_test_run(fd_prog, 1, data, size_data, - tmp, &size_tmp, &retval, NULL); + err = bpf_prog_test_run_opts(fd_prog, &topts); saved_errno = errno; if (unpriv) @@ -1023,9 +1056,8 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, } } - if (retval != expected_val && - expected_val != POINTER_VALUE) { - printf("FAIL retval %d != %d ", retval, expected_val); + if (topts.retval != expected_val && expected_val != POINTER_VALUE) { + printf("FAIL retval %d != %d ", topts.retval, expected_val); return 1; } @@ -1148,7 +1180,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, * bpf_probe_prog_type won't give correct answer */ if (fd_prog < 0 && prog_type != BPF_PROG_TYPE_TRACING && - !bpf_probe_prog_type(prog_type, 0)) { + !libbpf_probe_bpf_prog_type(prog_type, NULL)) { printf("SKIP (unsupported program type %d)\n", prog_type); skips++; goto close_fds; diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index d10cefd6eb09..ea69370caae3 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -2,6 +2,8 @@ # Kselftest framework requirement - SKIP code is 4. readonly KSFT_SKIP=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" cleanup() { @@ -13,8 +15,8 @@ cleanup() set +e ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } ip link set dev lo xdp off 2>/dev/null > /dev/null @@ -24,32 +26,32 @@ if [ $? -ne 0 ];then fi set -e -ip netns add ns1 -ip netns add ns2 +ip netns add ${NS1} +ip netns add ${NS2} trap cleanup 0 2 3 6 9 ip link add veth1 type veth peer name veth2 -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} -ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1 -ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2 +ip netns exec ${NS1} ip addr add 10.1.1.11/24 dev veth1 +ip netns exec ${NS2} ip addr add 10.1.1.22/24 dev veth2 -ip netns exec ns1 tc qdisc add dev veth1 clsact -ip netns exec ns2 tc qdisc add dev veth2 clsact +ip netns exec ${NS1} tc qdisc add dev veth1 clsact +ip netns exec ${NS2} tc qdisc add dev veth2 clsact -ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t -ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ${NS1} tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ${NS2} tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t -ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x -ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x +ip netns exec ${NS1} ip link set dev veth1 xdp obj test_xdp_meta.o sec x +ip netns exec ${NS2} ip link set dev veth2 xdp obj test_xdp_meta.o sec x -ip netns exec ns1 ip link set dev veth1 up -ip netns exec ns2 ip link set dev veth2 up +ip netns exec ${NS1} ip link set dev veth1 up +ip netns exec ${NS2} ip link set dev veth2 up -ip netns exec ns1 ping -c 1 10.1.1.22 -ip netns exec ns2 ping -c 1 10.1.1.11 +ip netns exec ${NS1} ping -c 1 10.1.1.22 +ip netns exec ${NS2} ping -c 1 10.1.1.11 exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index 57c8db9972a6..1d79f31480ad 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -10,6 +10,8 @@ # | xdp forwarding | # ------------------ +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" ret=0 setup() @@ -17,27 +19,27 @@ setup() local xdpmode=$1 - ip netns add ns1 - ip netns add ns2 + ip netns add ${NS1} + ip netns add ${NS2} - ip link add veth1 index 111 type veth peer name veth11 netns ns1 - ip link add veth2 index 222 type veth peer name veth22 netns ns2 + ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} + ip link add veth2 index 222 type veth peer name veth22 netns ${NS2} ip link set veth1 up ip link set veth2 up - ip -n ns1 link set dev veth11 up - ip -n ns2 link set dev veth22 up + ip -n ${NS1} link set dev veth11 up + ip -n ${NS2} link set dev veth22 up - ip -n ns1 addr add 10.1.1.11/24 dev veth11 - ip -n ns2 addr add 10.1.1.22/24 dev veth22 + ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 + ip -n ${NS2} addr add 10.1.1.22/24 dev veth22 } cleanup() { ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } test_xdp_redirect() @@ -52,13 +54,13 @@ test_xdp_redirect() return 0 fi - ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null - ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ${NS1} link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ${NS2} link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null - if ip netns exec ns1 ping -c 1 10.1.1.22 &> /dev/null && - ip netns exec ns2 ping -c 1 10.1.1.11 &> /dev/null; then + if ip netns exec ${NS1} ping -c 1 10.1.1.22 &> /dev/null && + ip netns exec ${NS2} ping -c 1 10.1.1.11 &> /dev/null; then echo "selftests: test_xdp_redirect $xdpmode [PASS]"; else ret=1 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index 05f872740999..cc57cb87e65f 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -32,6 +32,11 @@ DRV_MODE="xdpgeneric xdpdrv xdpegress" PASS=0 FAIL=0 LOG_DIR=$(mktemp -d) +declare -a NS +NS[0]="ns0-$(mktemp -u XXXXXX)" +NS[1]="ns1-$(mktemp -u XXXXXX)" +NS[2]="ns2-$(mktemp -u XXXXXX)" +NS[3]="ns3-$(mktemp -u XXXXXX)" test_pass() { @@ -47,11 +52,9 @@ test_fail() clean_up() { - for i in $(seq $NUM); do - ip link del veth$i 2> /dev/null - ip netns del ns$i 2> /dev/null + for i in $(seq 0 $NUM); do + ip netns del ${NS[$i]} 2> /dev/null done - ip netns del ns0 2> /dev/null } # Kselftest framework requirement - SKIP code is 4. @@ -79,23 +82,22 @@ setup_ns() mode="xdpdrv" fi - ip netns add ns0 + ip netns add ${NS[0]} for i in $(seq $NUM); do - ip netns add ns$i - ip -n ns$i link add veth0 index 2 type veth \ - peer name veth$i netns ns0 index $((1 + $i)) - ip -n ns0 link set veth$i up - ip -n ns$i link set veth0 up - - ip -n ns$i addr add 192.0.2.$i/24 dev veth0 - ip -n ns$i addr add 2001:db8::$i/64 dev veth0 + ip netns add ${NS[$i]} + ip -n ${NS[$i]} link add veth0 type veth peer name veth$i netns ${NS[0]} + ip -n ${NS[$i]} link set veth0 up + ip -n ${NS[0]} link set veth$i up + + ip -n ${NS[$i]} addr add 192.0.2.$i/24 dev veth0 + ip -n ${NS[$i]} addr add 2001:db8::$i/64 dev veth0 # Add a neigh entry for IPv4 ping test - ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 - ip -n ns$i link set veth0 $mode obj \ + ip -n ${NS[$i]} neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 + ip -n ${NS[$i]} link set veth0 $mode obj \ xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" - veth_mac[$i]=$(ip -n ns0 link show veth$i | awk '/link\/ether/ {print $2}') + veth_mac[$i]=$(ip -n ${NS[0]} link show veth$i | awk '/link\/ether/ {print $2}') done } @@ -104,10 +106,10 @@ do_egress_tests() local mode=$1 # mac test - ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & + ip netns exec ${NS[2]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & + ip netns exec ${NS[3]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & sleep 0.5 - ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null + ip netns exec ${NS[1]} ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null sleep 0.5 pkill tcpdump @@ -123,18 +125,18 @@ do_ping_tests() local mode=$1 # ping6 test: echo request should be redirect back to itself, not others - ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 + ip netns exec ${NS[1]} ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 - ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & - ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & + ip netns exec ${NS[1]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & + ip netns exec ${NS[2]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & + ip netns exec ${NS[3]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & sleep 0.5 # ARP test - ip netns exec ns1 arping -q -c 2 -I veth0 192.0.2.254 + ip netns exec ${NS[1]} arping -q -c 2 -I veth0 192.0.2.254 # IPv4 test - ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null + ip netns exec ${NS[1]} ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null # IPv6 test - ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null + ip netns exec ${NS[1]} ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null sleep 0.5 pkill tcpdump @@ -180,7 +182,7 @@ do_tests() xdpgeneric) drv_p="-S";; esac - ip netns exec ns0 ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & + ip netns exec ${NS[0]} ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & xdp_pid=$! sleep 1 if ! ps -p $xdp_pid > /dev/null; then @@ -197,10 +199,10 @@ do_tests() kill $xdp_pid } -trap clean_up EXIT - check_env +trap clean_up EXIT + for mode in ${DRV_MODE}; do setup_ns $mode do_tests $mode diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh index a3a1eaee26ea..392d28cc4e58 100755 --- a/tools/testing/selftests/bpf/test_xdp_veth.sh +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -22,6 +22,9 @@ ksft_skip=4 TESTNAME=xdp_veth BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts) BPF_DIR=$BPF_FS/test_$TESTNAME +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" +readonly NS3="ns3-$(mktemp -u XXXXXX)" _cleanup() { @@ -29,9 +32,9 @@ _cleanup() ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null ip link del veth3 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null - ip netns del ns3 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null + ip netns del ${NS3} 2> /dev/null rm -rf $BPF_DIR 2> /dev/null } @@ -77,24 +80,24 @@ set -e trap cleanup_skip EXIT -ip netns add ns1 -ip netns add ns2 -ip netns add ns3 +ip netns add ${NS1} +ip netns add ${NS2} +ip netns add ${NS3} -ip link add veth1 index 111 type veth peer name veth11 netns ns1 -ip link add veth2 index 122 type veth peer name veth22 netns ns2 -ip link add veth3 index 133 type veth peer name veth33 netns ns3 +ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} +ip link add veth2 index 122 type veth peer name veth22 netns ${NS2} +ip link add veth3 index 133 type veth peer name veth33 netns ${NS3} ip link set veth1 up ip link set veth2 up ip link set veth3 up -ip -n ns1 addr add 10.1.1.11/24 dev veth11 -ip -n ns3 addr add 10.1.1.33/24 dev veth33 +ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 +ip -n ${NS3} addr add 10.1.1.33/24 dev veth33 -ip -n ns1 link set dev veth11 up -ip -n ns2 link set dev veth22 up -ip -n ns3 link set dev veth33 up +ip -n ${NS1} link set dev veth11 up +ip -n ${NS2} link set dev veth22 up +ip -n ${NS3} link set dev veth33 up mkdir $BPF_DIR bpftool prog loadall \ @@ -107,12 +110,12 @@ ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0 ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2 -ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp -ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp -ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp +ip -n ${NS1} link set dev veth11 xdp obj xdp_dummy.o sec xdp +ip -n ${NS2} link set dev veth22 xdp obj xdp_tx.o sec xdp +ip -n ${NS3} link set dev veth33 xdp obj xdp_dummy.o sec xdp trap cleanup EXIT -ip netns exec ns1 ping -c 1 -W 1 10.1.1.33 +ip netns exec ${NS1} ping -c 1 -W 1 10.1.1.33 exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index 0cbc7604a2f8..810c407e0286 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -4,6 +4,8 @@ # Kselftest framework requirement - SKIP code is 4. readonly KSFT_SKIP=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then @@ -49,15 +51,15 @@ cleanup() if [ -n "$INTERACTIVE" ]; then echo "Namespace setup still active explore with:" - echo " ip netns exec ns1 bash" - echo " ip netns exec ns2 bash" + echo " ip netns exec ${NS1} bash" + echo " ip netns exec ${NS2} bash" exit $status fi set +e ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } # Using external program "getopt" to get --long-options @@ -126,8 +128,8 @@ fi # Interactive mode likely require us to cleanup netns if [ -n "$INTERACTIVE" ]; then ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null fi # Exit on failure @@ -144,8 +146,8 @@ if [ -n "$VERBOSE" ]; then fi # Create two namespaces -ip netns add ns1 -ip netns add ns2 +ip netns add ${NS1} +ip netns add ${NS2} # Run cleanup if failing or on kill trap cleanup 0 2 3 6 9 @@ -154,44 +156,44 @@ trap cleanup 0 2 3 6 9 ip link add veth1 type veth peer name veth2 # Move veth1 and veth2 into the respective namespaces -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} # NOTICE: XDP require VLAN header inside packet payload # - Thus, disable VLAN offloading driver features # - For veth REMEMBER TX side VLAN-offload # # Disable rx-vlan-offload (mostly needed on ns1) -ip netns exec ns1 ethtool -K veth1 rxvlan off -ip netns exec ns2 ethtool -K veth2 rxvlan off +ip netns exec ${NS1} ethtool -K veth1 rxvlan off +ip netns exec ${NS2} ethtool -K veth2 rxvlan off # # Disable tx-vlan-offload (mostly needed on ns2) -ip netns exec ns2 ethtool -K veth2 txvlan off -ip netns exec ns1 ethtool -K veth1 txvlan off +ip netns exec ${NS2} ethtool -K veth2 txvlan off +ip netns exec ${NS1} ethtool -K veth1 txvlan off export IPADDR1=100.64.41.1 export IPADDR2=100.64.41.2 # In ns1/veth1 add IP-addr on plain net_device -ip netns exec ns1 ip addr add ${IPADDR1}/24 dev veth1 -ip netns exec ns1 ip link set veth1 up +ip netns exec ${NS1} ip addr add ${IPADDR1}/24 dev veth1 +ip netns exec ${NS1} ip link set veth1 up # In ns2/veth2 create VLAN device export VLAN=4011 export DEVNS2=veth2 -ip netns exec ns2 ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN -ip netns exec ns2 ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN -ip netns exec ns2 ip link set $DEVNS2 up -ip netns exec ns2 ip link set $DEVNS2.$VLAN up +ip netns exec ${NS2} ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN +ip netns exec ${NS2} ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN +ip netns exec ${NS2} ip link set $DEVNS2 up +ip netns exec ${NS2} ip link set $DEVNS2.$VLAN up # Bringup lo in netns (to avoids confusing people using --interactive) -ip netns exec ns1 ip link set lo up -ip netns exec ns2 ip link set lo up +ip netns exec ${NS1} ip link set lo up +ip netns exec ${NS2} ip link set lo up # At this point, the hosts cannot reach each-other, # because ns2 are using VLAN tags on the packets. -ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' +ip netns exec ${NS2} sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags @@ -202,19 +204,19 @@ export FILE=test_xdp_vlan.o # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" export XDP_PROG=xdp_vlan_change -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # In ns1: egress use TC to add back VLAN tag 4011 # (del cmd) # tc qdisc del dev $DEVNS1 clsact 2> /dev/null # -ip netns exec ns1 tc qdisc add dev $DEVNS1 clsact -ip netns exec ns1 tc filter add dev $DEVNS1 egress \ +ip netns exec ${NS1} tc qdisc add dev $DEVNS1 clsact +ip netns exec ${NS1} tc filter add dev $DEVNS1 egress \ prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push # Now the namespaces can reach each-other, test with ping: -ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 +ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 # Second test: Replace xdp prog, that fully remove vlan header # @@ -223,9 +225,9 @@ ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 # ETH_P_8021Q indication, and this cause overwriting of our changes. # export XDP_PROG=xdp_vlan_remove_outer2 -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE off +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # Now the namespaces should still be able reach each-other, test with ping: -ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 +ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 7b7f918eda77..ca6abae9b09c 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -138,6 +138,29 @@ void read_trace_pipe(void) } } +ssize_t get_uprobe_offset(const void *addr) +{ + size_t start, end, base; + char buf[256]; + bool found = false; + FILE *f; + + f = fopen("/proc/self/maps", "r"); + if (!f) + return -errno; + + while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) { + if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) { + found = true; + break; + } + } + + fclose(f); + + if (!found) + return -ESRCH; + #if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2 #define OP_RT_RA_MASK 0xffff0000UL @@ -145,10 +168,6 @@ void read_trace_pipe(void) #define ADDIS_R2_R12 0x3c4c0000UL #define ADDI_R2_R2 0x38420000UL -ssize_t get_uprobe_offset(const void *addr, ssize_t base) -{ - u32 *insn = (u32 *)(uintptr_t)addr; - /* * A PPC64 ABIv2 function may have a local and a global entry * point. We need to use the local entry point when patching @@ -165,43 +184,16 @@ ssize_t get_uprobe_offset(const void *addr, ssize_t base) * lis r2,XXXX * addi r2,r2,XXXX */ - if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || - ((*insn & OP_RT_RA_MASK) == LIS_R2)) && - ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2)) - return (ssize_t)(insn + 2) - base; - else - return (uintptr_t)addr - base; -} - -#else + { + const u32 *insn = (const u32 *)(uintptr_t)addr; -ssize_t get_uprobe_offset(const void *addr, ssize_t base) -{ - return (uintptr_t)addr - base; -} - -#endif - -ssize_t get_base_addr(void) -{ - size_t start, offset; - char buf[256]; - FILE *f; - - f = fopen("/proc/self/maps", "r"); - if (!f) - return -errno; - - while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n", - &start, buf, &offset) == 3) { - if (strcmp(buf, "r-xp") == 0) { - fclose(f); - return start - offset; - } + if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || + ((*insn & OP_RT_RA_MASK) == LIS_R2)) && + ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2)) + return (uintptr_t)(insn + 2) - start + base; } - - fclose(f); - return -EINVAL; +#endif + return (uintptr_t)addr - start + base; } ssize_t get_rel_offset(uintptr_t addr) diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index d907b445524d..238a9c98cde2 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -18,8 +18,7 @@ int kallsyms_find(const char *sym, unsigned long long *addr); void read_trace_pipe(void); -ssize_t get_uprobe_offset(const void *addr, ssize_t base); -ssize_t get_base_addr(void); +ssize_t get_uprobe_offset(const void *addr); ssize_t get_rel_offset(uintptr_t addr); #endif diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index d7b74eb28333..829be2b9e08e 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -22,6 +22,81 @@ .result = ACCEPT, }, { + "calls: invalid kfunc call: ptr_to_mem to struct with non-scalar", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail1 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail1", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with nesting depth > 4", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "max struct nesting depth exceeded\narg#0 pointer type STRUCT prog_test_fail2", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail2", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with FAM", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail3 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail3", 2 }, + }, +}, +{ + "calls: invalid kfunc call: reg->type != PTR_TO_CTX", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 expected pointer to ctx, but got PTR", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_pass_ctx", 2 }, + }, +}, +{ + "calls: invalid kfunc call: void * not allowed in func proto without mem size arg", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type UNKNOWN must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_mem_len_fail1", 2 }, + }, +}, +{ "calls: basic sanity", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index ce13ece08d51..8c224eac93df 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -121,7 +121,25 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [narrow load]", + "sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [half load]", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -139,7 +157,64 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]", + "sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -149,7 +224,7 @@ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c index 51c8224b4ccc..aaedbf4955c3 100644 --- a/tools/testing/selftests/bpf/xdp_redirect_multi.c +++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c @@ -32,12 +32,12 @@ static void int_exit(int sig) int i; for (i = 0; ifaces[i] > 0; i++) { - if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifaces[i], xdp_flags, &prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id) - bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags); + bpf_xdp_detach(ifaces[i], xdp_flags, NULL); } exit(0); @@ -210,7 +210,7 @@ int main(int argc, char **argv) } /* bind prog_fd to each interface */ - ret = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags); + ret = bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL); if (ret) { printf("Set xdp fd failed on %d\n", ifindex); goto err_out; diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index baa870a759a2..c567856fd1bc 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -29,7 +29,7 @@ static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static void cleanup(int sig) { - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); if (sig) exit(1); } @@ -203,7 +203,7 @@ int main(int argc, char **argv) printf("XDP setup disrupts network connectivity, hit Ctrl+C to quit\n"); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { fprintf(stderr, "Link set xdp fd failed for %s\n", ifname); goto done; } diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 0a5d23da486d..5f8296d29e77 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -266,22 +266,24 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size } static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, - struct ifobject *ifobject, u32 qid) + struct ifobject *ifobject, bool shared) { - struct xsk_socket_config cfg; + struct xsk_socket_config cfg = {}; struct xsk_ring_cons *rxr; struct xsk_ring_prod *txr; xsk->umem = umem; cfg.rx_size = xsk->rxqsize; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg.libbpf_flags = 0; + cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD; cfg.xdp_flags = ifobject->xdp_flags; cfg.bind_flags = ifobject->bind_flags; + if (shared) + cfg.bind_flags |= XDP_SHARED_UMEM; txr = ifobject->tx_on ? &xsk->tx : NULL; rxr = ifobject->rx_on ? &xsk->rx : NULL; - return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg); + return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg); } static struct option long_options[] = { @@ -387,7 +389,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, for (i = 0; i < MAX_INTERFACES; i++) { struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; - ifobj->umem = &ifobj->umem_arr[0]; ifobj->xsk = &ifobj->xsk_arr[0]; ifobj->use_poll = false; ifobj->pacing_on = true; @@ -401,11 +402,12 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, ifobj->tx_on = false; } + memset(ifobj->umem, 0, sizeof(*ifobj->umem)); + ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; + ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + for (j = 0; j < MAX_SOCKETS; j++) { - memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j])); memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); - ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS; - ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; } } @@ -906,7 +908,10 @@ static bool rx_stats_are_valid(struct ifobject *ifobject) return true; case STAT_TEST_RX_FULL: xsk_stat = stats.rx_ring_full; - expected_stat -= RX_FULL_RXQSIZE; + if (ifobject->umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + expected_stat = ifobject->umem->num_frames - RX_FULL_RXQSIZE; + else + expected_stat = XSK_RING_PROD__DEFAULT_NUM_DESCS - RX_FULL_RXQSIZE; break; case STAT_TEST_RX_FILL_EMPTY: xsk_stat = stats.rx_fill_ring_empty_descs; @@ -947,7 +952,10 @@ static void tx_stats_validate(struct ifobject *ifobject) static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) { + u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; + int ret, ifindex; + void *bufs; u32 i; ifobject->ns_fd = switch_namespace(ifobject->nsname); @@ -955,23 +963,20 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (ifobject->umem->unaligned_mode) mmap_flags |= MAP_HUGETLB; - for (i = 0; i < test->nb_sockets; i++) { - u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; - u32 ctr = 0; - void *bufs; - int ret; + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + exit_with_error(errno); - bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); + ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz); + if (ret) + exit_with_error(-ret); - ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); - if (ret) - exit_with_error(-ret); + for (i = 0; i < test->nb_sockets; i++) { + u32 ctr = 0; while (ctr++ < SOCK_RECONF_CTR) { - ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], - ifobject, i); + ret = xsk_configure_socket(&ifobject->xsk_arr[i], ifobject->umem, + ifobject, !!i); if (!ret) break; @@ -982,8 +987,22 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) } } - ifobject->umem = &ifobject->umem_arr[0]; ifobject->xsk = &ifobject->xsk_arr[0]; + + if (!ifobject->rx_on) + return; + + ifindex = if_nametoindex(ifobject->ifname); + if (!ifindex) + exit_with_error(errno); + + ret = xsk_setup_xdp_prog(ifindex, &ifobject->xsk_map_fd); + if (ret) + exit_with_error(-ret); + + ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd); + if (ret) + exit_with_error(-ret); } static void testapp_cleanup_xsk_res(struct ifobject *ifobj) @@ -1139,14 +1158,16 @@ static void testapp_bidi(struct test_spec *test) static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) { + int ret; + xsk_socket__delete(ifobj_tx->xsk->xsk); - xsk_umem__delete(ifobj_tx->umem->umem); xsk_socket__delete(ifobj_rx->xsk->xsk); - xsk_umem__delete(ifobj_rx->umem->umem); - ifobj_tx->umem = &ifobj_tx->umem_arr[1]; ifobj_tx->xsk = &ifobj_tx->xsk_arr[1]; - ifobj_rx->umem = &ifobj_rx->umem_arr[1]; ifobj_rx->xsk = &ifobj_rx->xsk_arr[1]; + + ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd); + if (ret) + exit_with_error(-ret); } static void testapp_bpf_res(struct test_spec *test) @@ -1405,13 +1426,13 @@ static struct ifobject *ifobject_create(void) if (!ifobj->xsk_arr) goto out_xsk_arr; - ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr)); - if (!ifobj->umem_arr) - goto out_umem_arr; + ifobj->umem = calloc(1, sizeof(*ifobj->umem)); + if (!ifobj->umem) + goto out_umem; return ifobj; -out_umem_arr: +out_umem: free(ifobj->xsk_arr); out_xsk_arr: free(ifobj); @@ -1420,7 +1441,7 @@ out_xsk_arr: static void ifobject_delete(struct ifobject *ifobj) { - free(ifobj->umem_arr); + free(ifobj->umem); free(ifobj->xsk_arr); free(ifobj); } diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 2f705f44b748..62a3e6388632 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -125,10 +125,10 @@ struct ifobject { struct xsk_socket_info *xsk; struct xsk_socket_info *xsk_arr; struct xsk_umem_info *umem; - struct xsk_umem_info *umem_arr; thread_func_t func_ptr; struct pkt_stream *pkt_stream; int ns_fd; + int xsk_map_fd; u32 dst_ip; u32 src_ip; u32 xdp_flags; diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 7581a7348e1b..21a411b04890 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -35,4 +35,4 @@ test_unix_oob gro ioam6_parser toeplitz -cmsg_so_mark +cmsg_sender diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 9897fa9ab953..3bfeaf06b960 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -30,6 +30,7 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh +TEST_PROGS += cmsg_time.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh @@ -52,7 +53,7 @@ TEST_GEN_FILES += gro TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls TEST_GEN_FILES += toeplitz -TEST_GEN_FILES += cmsg_so_mark +TEST_GEN_FILES += cmsg_sender TEST_FILES := settings diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh new file mode 100755 index 000000000000..2d89cb0ad288 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -0,0 +1,156 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ksft_skip=4 + +NS=ns +IP6=2001:db8:1::1/64 +TGT6=2001:db8:1::2 +TMPF=`mktemp` + +cleanup() +{ + rm -f $TMPF + ip netns del $NS +} + +trap cleanup EXIT + +NSEXE="ip netns exec $NS" + +tcpdump -h | grep immediate-mode >> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP - tcpdump with --immediate-mode option required" + exit $ksft_skip +fi + +# Namespaces +ip netns add $NS + +$NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + +# Connectivity +ip -netns $NS link add type dummy +ip -netns $NS link set dev dummy0 up +ip -netns $NS addr add $IP6 dev dummy0 + +# Test +BAD=0 +TOTAL=0 + +check_result() { + ((TOTAL++)) + if [ $1 -ne $2 ]; then + echo " Case $3 returned $1, expected $2" + ((BAD++)) + fi +} + +# IPV6_DONTFRAG +for ovr in setsock cmsg both diff; do + for df in 0 1; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-F $df" + [ $ovr == "cmsg" ] && m="-f $df" + [ $ovr == "both" ] && m="-F $df -f $df" + [ $ovr == "diff" ] && m="-F $((1 - df)) -f $df" + + $NSEXE ./cmsg_sender -s -S 2000 -6 -p $p $m $TGT6 1234 + check_result $? $df "DONTFRAG $prot $ovr" + done + done +done + +# IPV6_TCLASS +TOS=0x10 +TOS2=0x20 + +ip -6 -netns $NS rule add tos $TOS lookup 300 +ip -6 -netns $NS route add table 300 prohibit any + +for ovr in setsock cmsg both diff; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-C" + [ $ovr == "cmsg" ] && m="-c" + [ $ovr == "both" ] && m="-C $((TOS2)) -c" + [ $ovr == "diff" ] && m="-C $((TOS )) -c" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 + check_result $? 0 "TCLASS $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null + check_result $? 0 "TCLASS $prot $ovr - packet data" + rm $TMPF + + [ $ovr == "both" ] && m="-C $((TOS )) -c" + [ $ovr == "diff" ] && m="-C $((TOS2)) -c" + + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234 + check_result $? 1 "TCLASS $prot $ovr - rejection" + done +done + +# IPV6_HOPLIMIT +LIM=4 + +for ovr in setsock cmsg both diff; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-L" + [ $ovr == "cmsg" ] && m="-l" + [ $ovr == "both" ] && m="-L $LIM -l" + [ $ovr == "diff" ] && m="-L $((LIM + 1)) -l" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 + check_result $? 0 "HOPLIMIT $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null + check_result $? 0 "HOPLIMIT $prot $ovr - packet data" + rm $TMPF + done +done + +# IPV6 exthdr +for p in u i r; do + # Very basic "does it crash" test + for h in h d r; do + $NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234 + check_result $? 0 "ExtHdr $prot $ovr - pass" + done +done + +# Summary +if [ $BAD -ne 0 ]; then + echo "FAIL - $BAD/$TOTAL cases failed" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c new file mode 100644 index 000000000000..aed7845c08a8 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -0,0 +1,504 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <errno.h> +#include <error.h> +#include <netdb.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/errqueue.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/net_tstamp.h> +#include <linux/types.h> +#include <linux/udp.h> +#include <sys/socket.h> + +enum { + ERN_SUCCESS = 0, + /* Well defined errors, callers may depend on these */ + ERN_SEND = 1, + /* Informational, can reorder */ + ERN_HELP, + ERN_SEND_SHORT, + ERN_SOCK_CREATE, + ERN_RESOLVE, + ERN_CMSG_WR, + ERN_SOCKOPT, + ERN_GETTIME, + ERN_RECVERR, + ERN_CMSG_RD, + ERN_CMSG_RCV, +}; + +struct option_cmsg_u32 { + bool ena; + unsigned int val; +}; + +struct options { + bool silent_send; + const char *host; + const char *service; + unsigned int size; + struct { + unsigned int mark; + unsigned int dontfrag; + unsigned int tclass; + unsigned int hlimit; + } sockopt; + struct { + unsigned int family; + unsigned int type; + unsigned int proto; + } sock; + struct option_cmsg_u32 mark; + struct { + bool ena; + unsigned int delay; + } txtime; + struct { + bool ena; + } ts; + struct { + struct option_cmsg_u32 dontfrag; + struct option_cmsg_u32 tclass; + struct option_cmsg_u32 hlimit; + struct option_cmsg_u32 exthdr; + } v6; +} opt = { + .size = 13, + .sock = { + .family = AF_UNSPEC, + .type = SOCK_DGRAM, + .proto = IPPROTO_UDP, + }, +}; + +static struct timespec time_start_real; +static struct timespec time_start_mono; + +static void __attribute__((noreturn)) cs_usage(const char *bin) +{ + printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin); + printf("Options:\n" + "\t\t-s Silent send() failures\n" + "\t\t-S send() size\n" + "\t\t-4/-6 Force IPv4 / IPv6 only\n" + "\t\t-p prot Socket protocol\n" + "\t\t (u = UDP (default); i = ICMP; r = RAW)\n" + "\n" + "\t\t-m val Set SO_MARK with given value\n" + "\t\t-M val Set SO_MARK via setsockopt\n" + "\t\t-d val Set SO_TXTIME with given delay (usec)\n" + "\t\t-t Enable time stamp reporting\n" + "\t\t-f val Set don't fragment via cmsg\n" + "\t\t-F val Set don't fragment via setsockopt\n" + "\t\t-c val Set TCLASS via cmsg\n" + "\t\t-C val Set TCLASS via setsockopt\n" + "\t\t-l val Set HOPLIMIT via cmsg\n" + "\t\t-L val Set HOPLIMIT via setsockopt\n" + "\t\t-H type Add an IPv6 header option\n" + "\t\t (h = HOP; d = DST; r = RTDST)" + ""); + exit(ERN_HELP); +} + +static void cs_parse_args(int argc, char *argv[]) +{ + char o; + + while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) { + switch (o) { + case 's': + opt.silent_send = true; + break; + case 'S': + opt.size = atoi(optarg); + break; + case '4': + opt.sock.family = AF_INET; + break; + case '6': + opt.sock.family = AF_INET6; + break; + case 'p': + if (*optarg == 'u' || *optarg == 'U') { + opt.sock.proto = IPPROTO_UDP; + } else if (*optarg == 'i' || *optarg == 'I') { + opt.sock.proto = IPPROTO_ICMP; + } else if (*optarg == 'r') { + opt.sock.type = SOCK_RAW; + } else { + printf("Error: unknown protocol: %s\n", optarg); + cs_usage(argv[0]); + } + break; + + case 'm': + opt.mark.ena = true; + opt.mark.val = atoi(optarg); + break; + case 'M': + opt.sockopt.mark = atoi(optarg); + break; + case 'd': + opt.txtime.ena = true; + opt.txtime.delay = atoi(optarg); + break; + case 't': + opt.ts.ena = true; + break; + case 'f': + opt.v6.dontfrag.ena = true; + opt.v6.dontfrag.val = atoi(optarg); + break; + case 'F': + opt.sockopt.dontfrag = atoi(optarg); + break; + case 'c': + opt.v6.tclass.ena = true; + opt.v6.tclass.val = atoi(optarg); + break; + case 'C': + opt.sockopt.tclass = atoi(optarg); + break; + case 'l': + opt.v6.hlimit.ena = true; + opt.v6.hlimit.val = atoi(optarg); + break; + case 'L': + opt.sockopt.hlimit = atoi(optarg); + break; + case 'H': + opt.v6.exthdr.ena = true; + switch (optarg[0]) { + case 'h': + opt.v6.exthdr.val = IPV6_HOPOPTS; + break; + case 'd': + opt.v6.exthdr.val = IPV6_DSTOPTS; + break; + case 'r': + opt.v6.exthdr.val = IPV6_RTHDRDSTOPTS; + break; + default: + printf("Error: hdr type: %s\n", optarg); + break; + } + break; + } + } + + if (optind != argc - 2) + cs_usage(argv[0]); + + opt.host = argv[optind]; + opt.service = argv[optind + 1]; +} + +static void memrnd(void *s, size_t n) +{ + int *dword = s; + char *byte; + + for (; n >= 4; n -= 4) + *dword++ = rand(); + byte = (void *)dword; + while (n--) + *byte++ = rand(); +} + +static void +ca_write_cmsg_u32(char *cbuf, size_t cbuf_sz, size_t *cmsg_len, + int level, int optname, struct option_cmsg_u32 *uopt) +{ + struct cmsghdr *cmsg; + + if (!uopt->ena) + return; + + cmsg = (struct cmsghdr *)(cbuf + *cmsg_len); + *cmsg_len += CMSG_SPACE(sizeof(__u32)); + if (cbuf_sz < *cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = level; + cmsg->cmsg_type = optname; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + *(__u32 *)CMSG_DATA(cmsg) = uopt->val; +} + +static void +cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) +{ + struct cmsghdr *cmsg; + size_t cmsg_len; + + msg->msg_control = cbuf; + cmsg_len = 0; + + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_SOCKET, SO_MARK, &opt.mark); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_HOPLIMIT, &opt.v6.hlimit); + + if (opt.txtime.ena) { + struct sock_txtime so_txtime = { + .clockid = CLOCK_MONOTONIC, + }; + __u64 txtime; + + if (setsockopt(fd, SOL_SOCKET, SO_TXTIME, + &so_txtime, sizeof(so_txtime))) + error(ERN_SOCKOPT, errno, "setsockopt TXTIME"); + + txtime = time_start_mono.tv_sec * (1000ULL * 1000 * 1000) + + time_start_mono.tv_nsec + + opt.txtime.delay * 1000; + + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(sizeof(txtime)); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_TXTIME; + cmsg->cmsg_len = CMSG_LEN(sizeof(txtime)); + memcpy(CMSG_DATA(cmsg), &txtime, sizeof(txtime)); + } + if (opt.ts.ena) { + __u32 val = SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_TSONLY; + + if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, + &val, sizeof(val))) + error(ERN_SOCKOPT, errno, "setsockopt TIMESTAMPING"); + + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(sizeof(__u32)); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SO_TIMESTAMPING; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + *(__u32 *)CMSG_DATA(cmsg) = SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_TX_SOFTWARE; + } + if (opt.v6.exthdr.ena) { + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(8); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_IPV6; + cmsg->cmsg_type = opt.v6.exthdr.val; + cmsg->cmsg_len = CMSG_LEN(8); + *(__u64 *)CMSG_DATA(cmsg) = 0; + } + + if (cmsg_len) + msg->msg_controllen = cmsg_len; + else + msg->msg_control = NULL; +} + +static const char *cs_ts_info2str(unsigned int info) +{ + static const char *names[] = { + [SCM_TSTAMP_SND] = "SND", + [SCM_TSTAMP_SCHED] = "SCHED", + [SCM_TSTAMP_ACK] = "ACK", + }; + + if (info < sizeof(names) / sizeof(names[0])) + return names[info]; + return "unknown"; +} + +static void +cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) +{ + struct sock_extended_err *see; + struct scm_timestamping *ts; + struct cmsghdr *cmsg; + int i, err; + + if (!opt.ts.ena) + return; + msg->msg_control = cbuf; + msg->msg_controllen = cbuf_sz; + + while (true) { + ts = NULL; + see = NULL; + memset(cbuf, 0, cbuf_sz); + + err = recvmsg(fd, msg, MSG_ERRQUEUE); + if (err < 0) { + if (errno == EAGAIN) + break; + error(ERN_RECVERR, errno, "recvmsg ERRQ"); + } + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SO_TIMESTAMPING_OLD) { + if (cmsg->cmsg_len < sizeof(*ts)) + error(ERN_CMSG_RD, EINVAL, "TS cmsg"); + + ts = (void *)CMSG_DATA(cmsg); + } + if ((cmsg->cmsg_level == SOL_IP && + cmsg->cmsg_type == IP_RECVERR) || + (cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_RECVERR)) { + if (cmsg->cmsg_len < sizeof(*see)) + error(ERN_CMSG_RD, EINVAL, "sock_err cmsg"); + + see = (void *)CMSG_DATA(cmsg); + } + } + + if (!ts) + error(ERN_CMSG_RCV, ENOENT, "TS cmsg not found"); + if (!see) + error(ERN_CMSG_RCV, ENOENT, "sock_err cmsg not found"); + + for (i = 0; i < 3; i++) { + unsigned long long rel_time; + + if (!ts->ts[i].tv_sec && !ts->ts[i].tv_nsec) + continue; + + rel_time = (ts->ts[i].tv_sec - time_start_real.tv_sec) * + (1000ULL * 1000) + + (ts->ts[i].tv_nsec - time_start_real.tv_nsec) / + 1000; + printf(" %5s ts%d %lluus\n", + cs_ts_info2str(see->ee_info), + i, rel_time); + } + } +} + +static void ca_set_sockopts(int fd) +{ + if (opt.sockopt.mark && + setsockopt(fd, SOL_SOCKET, SO_MARK, + &opt.sockopt.mark, sizeof(opt.sockopt.mark))) + error(ERN_SOCKOPT, errno, "setsockopt SO_MARK"); + if (opt.sockopt.dontfrag && + setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG, + &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG"); + if (opt.sockopt.tclass && + setsockopt(fd, SOL_IPV6, IPV6_TCLASS, + &opt.sockopt.tclass, sizeof(opt.sockopt.tclass))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS"); + if (opt.sockopt.hlimit && + setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS, + &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT"); +} + +int main(int argc, char *argv[]) +{ + struct addrinfo hints, *ai; + struct iovec iov[1]; + struct msghdr msg; + char cbuf[1024]; + char *buf; + int err; + int fd; + + cs_parse_args(argc, argv); + + buf = malloc(opt.size); + memrnd(buf, opt.size); + + memset(&hints, 0, sizeof(hints)); + hints.ai_family = opt.sock.family; + + ai = NULL; + err = getaddrinfo(opt.host, opt.service, &hints, &ai); + if (err) { + fprintf(stderr, "Can't resolve address [%s]:%s\n", + opt.host, opt.service); + return ERN_SOCK_CREATE; + } + + if (ai->ai_family == AF_INET6 && opt.sock.proto == IPPROTO_ICMP) + opt.sock.proto = IPPROTO_ICMPV6; + + fd = socket(ai->ai_family, opt.sock.type, opt.sock.proto); + if (fd < 0) { + fprintf(stderr, "Can't open socket: %s\n", strerror(errno)); + freeaddrinfo(ai); + return ERN_RESOLVE; + } + + if (opt.sock.proto == IPPROTO_ICMP) { + buf[0] = ICMP_ECHO; + buf[1] = 0; + } else if (opt.sock.proto == IPPROTO_ICMPV6) { + buf[0] = ICMPV6_ECHO_REQUEST; + buf[1] = 0; + } else if (opt.sock.type == SOCK_RAW) { + struct udphdr hdr = { 1, 2, htons(opt.size), 0 }; + struct sockaddr_in6 *sin6 = (void *)ai->ai_addr;; + + memcpy(buf, &hdr, sizeof(hdr)); + sin6->sin6_port = htons(opt.sock.proto); + } + + ca_set_sockopts(fd); + + if (clock_gettime(CLOCK_REALTIME, &time_start_real)) + error(ERN_GETTIME, errno, "gettime REALTIME"); + if (clock_gettime(CLOCK_MONOTONIC, &time_start_mono)) + error(ERN_GETTIME, errno, "gettime MONOTONIC"); + + iov[0].iov_base = buf; + iov[0].iov_len = opt.size; + + memset(&msg, 0, sizeof(msg)); + msg.msg_name = ai->ai_addr; + msg.msg_namelen = ai->ai_addrlen; + msg.msg_iov = iov; + msg.msg_iovlen = 1; + + cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + + err = sendmsg(fd, &msg, 0); + if (err < 0) { + if (!opt.silent_send) + fprintf(stderr, "send failed: %s\n", strerror(errno)); + err = ERN_SEND; + goto err_out; + } else if (err != (int)opt.size) { + fprintf(stderr, "short send\n"); + err = ERN_SEND_SHORT; + goto err_out; + } else { + err = ERN_SUCCESS; + } + + /* Make sure all timestamps have time to loop back */ + usleep(opt.txtime.delay); + + cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + +err_out: + close(fd); + freeaddrinfo(ai); + return err; +} diff --git a/tools/testing/selftests/net/cmsg_so_mark.c b/tools/testing/selftests/net/cmsg_so_mark.c deleted file mode 100644 index 27f2804892a7..000000000000 --- a/tools/testing/selftests/net/cmsg_so_mark.c +++ /dev/null @@ -1,67 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -#include <errno.h> -#include <netdb.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> -#include <linux/types.h> -#include <sys/socket.h> - -int main(int argc, const char **argv) -{ - char cbuf[CMSG_SPACE(sizeof(__u32))]; - struct addrinfo hints, *ai; - struct cmsghdr *cmsg; - struct iovec iov[1]; - struct msghdr msg; - int mark; - int err; - int fd; - - if (argc != 4) { - fprintf(stderr, "Usage: %s <dst_ip> <port> <mark>\n", argv[0]); - return 1; - } - mark = atoi(argv[3]); - - memset(&hints, 0, sizeof(hints)); - hints.ai_family = AF_UNSPEC; - hints.ai_socktype = SOCK_DGRAM; - - ai = NULL; - err = getaddrinfo(argv[1], argv[2], &hints, &ai); - if (err) { - fprintf(stderr, "Can't resolve address: %s\n", strerror(errno)); - return 1; - } - - fd = socket(ai->ai_family, SOCK_DGRAM, IPPROTO_UDP); - if (fd < 0) { - fprintf(stderr, "Can't open socket: %s\n", strerror(errno)); - freeaddrinfo(ai); - return 1; - } - - iov[0].iov_base = "bla"; - iov[0].iov_len = 4; - - msg.msg_name = ai->ai_addr; - msg.msg_namelen = ai->ai_addrlen; - msg.msg_iov = iov; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_SOCKET; - cmsg->cmsg_type = SO_MARK; - cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); - *(__u32 *)CMSG_DATA(cmsg) = mark; - - err = sendmsg(fd, &msg, 0); - - close(fd); - freeaddrinfo(ai); - return err != 4; -} diff --git a/tools/testing/selftests/net/cmsg_so_mark.sh b/tools/testing/selftests/net/cmsg_so_mark.sh index 19c6aab8d0e9..1650b8622f2f 100755 --- a/tools/testing/selftests/net/cmsg_so_mark.sh +++ b/tools/testing/selftests/net/cmsg_so_mark.sh @@ -18,6 +18,8 @@ trap cleanup EXIT # Namespaces ip netns add $NS +ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + # Connectivity ip -netns $NS link add type dummy ip -netns $NS link set dev dummy0 up @@ -41,15 +43,29 @@ check_result() { fi } -ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $((MARK + 1)) -check_result $? 0 "IPv4 pass" -ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $((MARK + 1)) -check_result $? 0 "IPv6 pass" +for ovr in setsock cmsg both; do + for i in 4 6; do + [ $i == 4 ] && TGT=$TGT4 || TGT=$TGT6 + + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-M" + [ $ovr == "cmsg" ] && m="-m" + [ $ovr == "both" ] && m="-M $MARK -m" + + ip netns exec $NS ./cmsg_sender -$i -p $p $m $((MARK + 1)) $TGT 1234 + check_result $? 0 "$prot $ovr - pass" + + [ $ovr == "diff" ] && m="-M $((MARK + 1)) -m" -ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $MARK -check_result $? 1 "IPv4 rejection" -ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $MARK -check_result $? 1 "IPv6 rejection" + ip netns exec $NS ./cmsg_sender -$i -p $p $m $MARK -s $TGT 1234 + check_result $? 1 "$prot $ovr - rejection" + done + done +done # Summary if [ $BAD -ne 0 ]; then diff --git a/tools/testing/selftests/net/cmsg_time.sh b/tools/testing/selftests/net/cmsg_time.sh new file mode 100755 index 000000000000..91161e1da734 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_time.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NS=ns +IP4=172.16.0.1/24 +TGT4=172.16.0.2 +IP6=2001:db8:1::1/64 +TGT6=2001:db8:1::2 + +cleanup() +{ + ip netns del $NS +} + +trap cleanup EXIT + +# Namespaces +ip netns add $NS + +ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + +# Connectivity +ip -netns $NS link add type dummy +ip -netns $NS link set dev dummy0 up +ip -netns $NS addr add $IP4 dev dummy0 +ip -netns $NS addr add $IP6 dev dummy0 + +# Need FQ for TXTIME +ip netns exec $NS tc qdisc replace dev dummy0 root fq + +# Test +BAD=0 +TOTAL=0 + +check_result() { + ((TOTAL++)) + if [ $1 -ne 0 ]; then + echo " Case $4 returned $1, expected 0" + ((BAD++)) + elif [ "$2" != "$3" ]; then + echo " Case $4 returned '$2', expected '$3'" + ((BAD++)) + fi +} + +for i in "-4 $TGT4" "-6 $TGT6"; do + for p in u i r; do + [ $p == "u" ] && prot=UDPv${i:1:2} + [ $p == "i" ] && prot=ICMPv${i:1:2} + [ $p == "r" ] && prot=RAWv${i:1:2} + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234) + check_result $? "$ts" "" "$prot - no options" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | wc -l) + check_result $? "$ts" "2" "$prot - ts cnt" + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | + sed -n "s/.*SCHED ts0 [0-9].*/OK/p") + check_result $? "$ts" "OK" "$prot - ts0 SCHED" + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | + sed -n "s/.*SND ts0 [0-9].*/OK/p") + check_result $? "$ts" "OK" "$prot - ts0 SND" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | + awk '/SND/ { if ($3 > 1000) print "OK"; }') + check_result $? "$ts" "OK" "$prot - TXTIME abs" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | + awk '/SND/ {snd=$3} + /SCHED/ {sch=$3} + END { if (snd - sch > 500) print "OK"; }') + check_result $? "$ts" "OK" "$prot - TXTIME rel" + done +done + +# Summary +if [ $BAD -ne 0 ]; then + echo "FAIL - $BAD/$TOTAL cases failed" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 43ea8407a82e..4f70baad867d 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -96,7 +96,7 @@ fib_rule6_del() fib_rule6_del_by_pref() { - pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP -6 rule show $1 table $RTABLE | cut -d ":" -f 1) $IP -6 rule del pref $pref } @@ -104,17 +104,36 @@ fib_rule6_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP -6 rule add $match table $RTABLE $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule6 check: $1" + log_test $? 0 "rule6 check: $description" fib_rule6_del_by_pref "$match" - log_test $? 0 "rule6 del by pref: $match" + log_test $? 0 "rule6 del by pref: $description" +} + +fib_rule6_test_reject() +{ + local match="$1" + local rc + + $IP -6 rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule6 check: $match" + + if [ $rc -eq 0 ]; then + $IP -6 rule del $match table $RTABLE + fi } fib_rule6_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink @@ -124,8 +143,21 @@ fib_rule6_test() match="from $SRC_IP6 iif $DEV" fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule6_test_reject "$match" + done + + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" @@ -165,7 +197,7 @@ fib_rule4_del() fib_rule4_del_by_pref() { - pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP rule show $1 table $RTABLE | cut -d ":" -f 1) $IP rule del pref $pref } @@ -173,17 +205,36 @@ fib_rule4_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP rule add $match table $RTABLE $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule4 check: $1" + log_test $? 0 "rule4 check: $description" fib_rule4_del_by_pref "$match" - log_test $? 0 "rule4 del by pref: $match" + log_test $? 0 "rule4 del by pref: $description" +} + +fib_rule4_test_reject() +{ + local match="$1" + local rc + + $IP rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule4 check: $match" + + if [ $rc -eq 0 ]; then + $IP rule del $match table $RTABLE + fi } fib_rule4_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink @@ -192,14 +243,27 @@ fib_rule4_test() # need enable forwarding and disable rp_filter temporarily as all the # addresses are in the same subnet and egress device == ingress device. - ip netns exec testns sysctl -w net.ipv4.ip_forward=1 - ip netns exec testns sysctl -w net.ipv4.conf.$DEV.rp_filter=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=1 + ip netns exec testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" - ip netns exec testns sysctl -w net.ipv4.ip_forward=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=0 + + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule4_test_reject "$match" + done + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 996af1ae3d3d..e2690cc42da3 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -988,12 +988,25 @@ ipv6_rt_replace() ipv6_rt_replace_mpath } +ipv6_rt_dsfield() +{ + echo + echo "IPv6 route with dsfield tests" + + run_cmd "$IP -6 route flush 2001:db8:102::/64" + + # IPv6 doesn't support routing based on dsfield + run_cmd "$IP -6 route add 2001:db8:102::/64 dsfield 0x04 via 2001:db8:101::2" + log_test $? 2 "Reject route with dsfield" +} + ipv6_route_test() { route_setup ipv6_rt_add ipv6_rt_replace + ipv6_rt_dsfield route_cleanup } @@ -1447,6 +1460,81 @@ ipv4_local_rt_cache() log_test $? 0 "Cached route removed from VRF port device" } +ipv4_rt_dsfield() +{ + echo + echo "IPv4 route with dsfield tests" + + run_cmd "$IP route flush 172.16.102.0/24" + + # New routes should reject dsfield options that interfere with ECN + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x01 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x01" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x02 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x02" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x03 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x03" + + # A generic route that doesn't take DSCP into account + run_cmd "$IP route add 172.16.102.0/24 via 172.16.101.2" + + # A more specific route for DSCP 0x10 + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x10 via 172.16.103.2" + + # DSCP 0x10 should match the specific route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x10 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x11 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x12 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x13 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:CE" + + # Unknown DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x14 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x15 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x16 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x17 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:CE" + + # Null DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x00 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x01 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x02 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x03 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:CE" +} + ipv4_route_test() { route_setup @@ -1454,6 +1542,7 @@ ipv4_route_test() ipv4_rt_add ipv4_rt_replace ipv4_local_rt_cache + ipv4_rt_dsfield route_cleanup } diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index b90dff8d3a94..64bd00fe9a4f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -28,8 +28,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge vlan_filtering 1 ageing_time 1000 \ + ip link add dev br0 type bridge \ + vlan_filtering 1 \ + ageing_time $LOW_AGEING_TIME \ mcast_snooping 0 ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index c15c6c85c984..1c8a26046589 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -27,8 +27,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge ageing_time 1000 mcast_snooping 0 + ip link add dev br0 type bridge \ + ageing_time $LOW_AGEING_TIME \ + mcast_snooping 0 ip link set dev $swp1 master br0 ip link set dev $swp2 master br0 diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh index e134a5f529c9..1b3b46292179 100644 --- a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh +++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh @@ -99,15 +99,15 @@ fib_ipv4_tos_test() fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false check_err $? "Route not in hardware when should" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 8 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 8 metric 1024" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true check_err $? "Lowest TOS route still in hardware when should not" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4 metric 1024" true check_err $? "Middle TOS route in hardware when should not" log_test "IPv4 routes with TOS" @@ -277,11 +277,11 @@ fib_ipv4_replay_tos_test() ip -n $ns link set dev dummy1 up ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 devlink -N $ns dev reload $devlink_dev - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b0980a2efa31..4a546509de90 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -41,6 +41,8 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Minimum ageing_time (in centiseconds) supported by hardware +LOW_AGEING_TIME=1000 # Flag for tc match, supposed to be skip_sw/skip_hw which means do not process # filter by software/hardware TC_FLAG=skip_hw diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7da783d6f453..e7e434a4758b 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -24,6 +24,7 @@ PING_COUNT=${PING_COUNT:=10} PING_TIMEOUT=${PING_TIMEOUT:=5} WAIT_TIMEOUT=${WAIT_TIMEOUT:=20} INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600} +LOW_AGEING_TIME=${LOW_AGEING_TIME:=1000} REQUIRE_JQ=${REQUIRE_JQ:=yes} REQUIRE_MZ=${REQUIRE_MZ:=yes} diff --git a/tools/testing/selftests/net/forwarding/pedit_ip.sh b/tools/testing/selftests/net/forwarding/pedit_ip.sh new file mode 100755 index 000000000000..d14efb2d23b2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/pedit_ip.sh @@ -0,0 +1,201 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on +# egress of $swp2, the traffic is acted upon by a pedit action. An ingress +# filter installed on $h2 verifies that the packet looks like expected. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | +-|----------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +--------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_ip4_src + test_ip4_dst + test_ip6_src + test_ip6_dst +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge vlan_filtering 1 + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h2mac=$(mac_get $h2) + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +do_test_pedit_ip() +{ + local pedit_locus=$1; shift + local pedit_action=$1; shift + local match_prot=$1; shift + local match_flower=$1; shift + local mz_flags=$1; shift + + tc filter add $pedit_locus handle 101 pref 1 \ + flower action pedit ex munge $pedit_action + tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \ + flower skip_hw $match_flower action pass + + RET=0 + + $MZ $mz_flags $h1 -c 10 -d 20msec -p 100 -a own -b $h2mac -q -t ip + + local pkts + pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \ + tc_rule_handle_stats_get "dev $h2 ingress" 101) + check_err $? "Expected to get 10 packets, but got $pkts." + + pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101) + ((pkts >= 10)) + check_err $? "Expected to get 10 packets on pedit rule, but got $pkts." + + log_test "$pedit_locus pedit $pedit_action" + + tc filter del dev $h2 ingress pref 1 + tc filter del $pedit_locus pref 1 +} + +do_test_pedit_ip6() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 2001:db8:2::1" ipv6 \ + "$flower_addr 2001:db8:2::1" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" +} + +do_test_pedit_ip4() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 198.51.100.1" ip \ + "$flower_addr 198.51.100.1" \ + "-A 192.0.2.1 -B 192.0.2.2" +} + +test_ip4_src() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip src" src_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip src" src_ip +} + +test_ip4_dst() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip dst" dst_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip dst" dst_ip +} + +test_ip6_src() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 src" src_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 src" src_ip +} + +test_ip6_dst() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 dst" dst_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 dst" dst_ip +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh index 4f9f17cb45d6..0a51eef21b9e 100755 --- a/tools/testing/selftests/net/forwarding/tc_police.sh +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -37,6 +37,8 @@ ALL_TESTS=" police_tx_mirror_test police_pps_rx_test police_pps_tx_test + police_mtu_rx_test + police_mtu_tx_test " NUM_NETIFS=6 source tc_common.sh @@ -346,6 +348,56 @@ police_pps_tx_test() tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower } +police_mtu_common_test() { + RET=0 + + local test_name=$1; shift + local dev=$1; shift + local direction=$1; shift + + tc filter add dev $dev $direction protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police mtu 1042 conform-exceed drop/ok + + # to count "conform" packets + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1001 -c 10 -q + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1000 -c 3 -q + + tc_check_packets "dev $dev $direction" 101 13 + check_err $? "wrong packet counter" + + # "exceed" packets + local overlimits_t0=$(tc_rule_stats_get ${dev} 1 ${direction} .overlimits) + test ${overlimits_t0} = 10 + check_err $? "wrong overlimits, expected 10 got ${overlimits_t0}" + + # "conform" packets + tc_check_packets "dev $h2 ingress" 101 3 + check_err $? "forwarding error" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $dev $direction protocol ip pref 1 handle 101 flower + + log_test "$test_name" +} + +police_mtu_rx_test() +{ + police_mtu_common_test "police mtu (rx)" $rp1 ingress +} + +police_mtu_tx_test() +{ + police_mtu_common_test "police mtu (tx)" $rp2 egress +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c0801df15f54..18bb0d0cf4bd 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -15,6 +15,7 @@ timeout_test=$((timeout_poll * 2 + 1)) mptcp_connect="" capture=0 checksum=0 +ip_mptcp=0 do_all_tests=1 TEST_COUNT=0 @@ -239,6 +240,16 @@ is_v6() [ -z "${1##*:*}" ] } +is_addr() +{ + [ -z "${1##*[.:]*}" ] +} + +is_number() +{ + [[ $1 == ?(-)+([0-9]) ]] +} + # $1: ns, $2: port wait_local_port_listen() { @@ -278,6 +289,109 @@ wait_rm_addr() done } +pm_nl_set_limits() +{ + local ns=$1 + local addrs=$2 + local subflows=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp limits set add_addr_accepted $addrs subflows $subflows + else + ip netns exec $ns ./pm_nl_ctl limits $addrs $subflows + fi +} + +pm_nl_add_endpoint() +{ + local ns=$1 + local addr=$2 + local flags + local port + local dev + local id + local nr=2 + + for p in $@ + do + if [ $p = "flags" ]; then + eval _flags=\$"$nr" + [ ! -z $_flags ]; flags="flags $_flags" + fi + if [ $p = "dev" ]; then + eval _dev=\$"$nr" + [ ! -z $_dev ]; dev="dev $_dev" + fi + if [ $p = "id" ]; then + eval _id=\$"$nr" + [ ! -z $_id ]; id="id $_id" + fi + if [ $p = "port" ]; then + eval _port=\$"$nr" + [ ! -z $_port ]; port="port $_port" + fi + + let nr+=1 + done + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint add $addr ${_flags//","/" "} $dev $id $port + else + ip netns exec $ns ./pm_nl_ctl add $addr $flags $dev $id $port + fi +} + +pm_nl_del_endpoint() +{ + local ns=$1 + local id=$2 + local addr=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint delete id $id $addr + else + ip netns exec $ns ./pm_nl_ctl del $id $addr + fi +} + +pm_nl_flush_endpoint() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint flush + else + ip netns exec $ns ./pm_nl_ctl flush + fi +} + +pm_nl_show_endpoints() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint show + else + ip netns exec $ns ./pm_nl_ctl dump + fi +} + +pm_nl_change_endpoint() +{ + local ns=$1 + local flags=$2 + local id=$3 + local addr=$4 + local port="" + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint change id $id ${flags//","/" "} + else + if [ $5 -ne 0 ]; then port="port $5"; fi + ip netns exec $ns ./pm_nl_ctl set $addr flags $flags $port + fi +} + do_transfer() { listener_ns="$1" @@ -289,7 +403,7 @@ do_transfer() addr_nr_ns1="$7" addr_nr_ns2="$8" speed="$9" - bkup="${10}" + sflags="${10}" port=$((10000+$TEST_COUNT)) TEST_COUNT=$((TEST_COUNT+1)) @@ -378,31 +492,36 @@ do_transfer() else addr="10.0.$counter.1" fi - ip netns exec $ns1 ./pm_nl_ctl add $addr flags signal + pm_nl_add_endpoint $ns1 $addr flags signal let counter+=1 let add_nr_ns1-=1 done elif [ $addr_nr_ns1 -lt 0 ]; then let rm_nr_ns1=-addr_nr_ns1 if [ $rm_nr_ns1 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${listener_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns1 ] - do - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${connector_ns}) - ip netns exec ${listener_ns} ./pm_nl_ctl del $id - wait_rm_addr ${connector_ns} ${rm_addr} - let counter+=1 - let pos+=5 + counter=0 + pm_nl_show_endpoints ${listener_ns} | while read line; do + local arr=($line) + local nr=0 + + for i in ${arr[@]}; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns1 ]; then + break + fi + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${connector_ns}) + pm_nl_del_endpoint ${listener_ns} $id + wait_rm_addr ${connector_ns} ${rm_addr} + let counter+=1 + fi + let nr+=1 done - fi + done elif [ $rm_nr_ns1 -eq 8 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${listener_ns} elif [ $rm_nr_ns1 -eq 9 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl del 0 ${connect_addr} + pm_nl_del_endpoint ${listener_ns} 0 ${connect_addr} fi fi @@ -426,30 +545,36 @@ do_transfer() else addr="10.0.$counter.2" fi - ip netns exec $ns2 ./pm_nl_ctl add $addr flags $flags + pm_nl_add_endpoint $ns2 $addr flags $flags let counter+=1 let add_nr_ns2-=1 done elif [ $addr_nr_ns2 -lt 0 ]; then let rm_nr_ns2=-addr_nr_ns2 if [ $rm_nr_ns2 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${connector_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns2 ] - do - # rm_addr are serialized, allow the previous one to complete - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${listener_ns}) - ip netns exec ${connector_ns} ./pm_nl_ctl del $id - wait_rm_addr ${listener_ns} ${rm_addr} - let counter+=1 - let pos+=5 + counter=0 + pm_nl_show_endpoints ${connector_ns} | while read line; do + local arr=($line) + local nr=0 + + for i in ${arr[@]}; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns2 ]; then + break + fi + # rm_addr are serialized, allow the previous one to + # complete + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${listener_ns}) + pm_nl_del_endpoint ${connector_ns} $id + wait_rm_addr ${listener_ns} ${rm_addr} + let counter+=1 + fi + let nr+=1 done - fi + done elif [ $rm_nr_ns2 -eq 8 ]; then - ip netns exec ${connector_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${connector_ns} elif [ $rm_nr_ns2 -eq 9 ]; then local addr if is_v6 "${connect_addr}"; then @@ -457,19 +582,34 @@ do_transfer() else addr="10.0.1.2" fi - ip netns exec ${connector_ns} ./pm_nl_ctl del 0 $addr + pm_nl_del_endpoint ${connector_ns} 0 $addr fi fi - if [ ! -z $bkup ]; then + if [ ! -z $sflags ]; then sleep 1 for netns in "$ns1" "$ns2"; do - dump=(`ip netns exec $netns ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - addr=${dump[${#dump[@]} - 1]} - backup="ip netns exec $netns ./pm_nl_ctl set $addr flags $bkup" - $backup - fi + pm_nl_show_endpoints $netns | while read line; do + local arr=($line) + local addr + local port=0 + local id + + for i in ${arr[@]}; do + if is_addr $i; then + addr=$i + elif is_number $i; then + # The minimum expected port number is 10000 + if [ $i -gt 10000 ]; then + port=$i + # The maximum id number is 255 + elif [ $i -lt 255 ]; then + id=$i + fi + fi + done + pm_nl_change_endpoint $netns $sflags $id $addr $port + done done fi @@ -545,7 +685,7 @@ run_tests() addr_nr_ns1="${5:-0}" addr_nr_ns2="${6:-0}" speed="${7:-fast}" - bkup="${8:-""}" + sflags="${8:-""}" lret=0 oldin="" @@ -574,7 +714,7 @@ run_tests() fi do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup} + ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags} lret=$? } @@ -978,51 +1118,51 @@ subflows_tests() # subflow limited by client reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 0 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, limited by client" 0 0 0 # subflow limited by server reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, limited by server" 1 1 0 # subflow reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow" 1 1 1 # multiple subflows reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows" 2 2 2 # multiple subflows limited by server reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows, limited by server" 2 2 1 # single subflow, dev reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow dev ns2eth3 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow dev ns2eth3 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, dev" 1 1 1 } @@ -1032,28 +1172,28 @@ subflows_error_tests() # If a single subflow is configured, and matches the MPC src # address, no additional subflow should be created reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "no MPC reuse with single endpoint" 0 0 0 # multiple subflows, with subflow creation error reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "multi subflows, with failing subflow" 1 1 1 # multiple subflows, with subflow timeout on MPJ reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j DROP run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "multi subflows, with subflow timeout" 1 1 1 @@ -1062,9 +1202,9 @@ subflows_error_tests() # closed subflow (due to reset) is not reused if additional # subflows are added later reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & @@ -1074,7 +1214,7 @@ subflows_error_tests() # mpj subflow will be in TW after the reset wait_for_tw $ns2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow wait # additional subflow could be created only if the PM select @@ -1086,16 +1226,16 @@ signal_address_tests() { # add_address, unused reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "unused signal address" 0 0 0 chk_add_nr 1 1 # accept and use add_addr reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address" 1 1 1 chk_add_nr 1 1 @@ -1105,59 +1245,59 @@ signal_address_tests() # belong to different subnets or one of the listed local address could be # used for 'add_addr' subflow reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and signal" 2 2 2 chk_add_nr 1 1 # accept and use add_addr with additional subflows reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows and signal" 3 3 3 chk_add_nr 1 1 # signal addresses reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal addresses" 3 3 3 chk_add_nr 3 3 # signal invalid addresses reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal invalid addresses" 1 1 1 chk_add_nr 3 3 # signal addresses race test reset - ip netns exec $ns1 ./pm_nl_ctl limits 4 4 - ip netns exec $ns2 ./pm_nl_ctl limits 4 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags signal + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal + pm_nl_add_endpoint $ns2 10.0.4.2 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal addresses race test" 3 3 3 @@ -1178,11 +1318,11 @@ link_failure_tests() # active backup and link switch-over. # Let's set some arbitrary (low) virtual link limits. init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr "multiple flows, signal, link failure" 3 3 3 chk_add_nr 1 1 @@ -1192,11 +1332,11 @@ link_failure_tests() # for bidirectional transfer reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow run_tests $ns1 $ns2 10.0.1.1 2 chk_join_nr "multi flows, signal, bidi, link fail" 3 3 3 chk_add_nr 1 1 @@ -1206,11 +1346,11 @@ link_failure_tests() # will never be used reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 export FAILING_LINKS="1" - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr "backup subflow unused, link failure" 2 2 2 chk_add_nr 1 1 @@ -1220,10 +1360,10 @@ link_failure_tests() # the traffic reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup export FAILING_LINKS="1 2" run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr "backup flow used, multi links fail" 2 2 2 @@ -1235,10 +1375,10 @@ link_failure_tests() # for bidirectional transfer reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 2 chk_join_nr "backup flow used, bidi, link failure" 2 2 2 chk_add_nr 1 1 @@ -1250,38 +1390,38 @@ add_addr_timeout_tests() { # add_addr timeout reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1 chk_add_nr 4 0 # add_addr timeout IPv6 reset_with_add_addr_timeout 6 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1 chk_add_nr 4 0 # signal addresses timeout reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 0 0 0 least chk_join_nr "signal addresses, ADD_ADDR timeout" 2 2 2 chk_add_nr 8 0 # signal invalid addresses timeout reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 0 0 0 least chk_join_nr "invalid address, ADD_ADDR timeout" 1 1 1 chk_add_nr 8 0 @@ -1291,28 +1431,28 @@ remove_tests() { # single subflow, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow chk_join_nr "remove single subflow" 1 1 1 chk_rm_nr 1 1 # multiple subflows, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow chk_join_nr "remove multiple subflows" 2 2 2 chk_rm_nr 2 2 # single address, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow chk_join_nr "remove single address" 1 1 1 chk_add_nr 1 1 @@ -1320,10 +1460,10 @@ remove_tests() # subflow and signal, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow chk_join_nr "remove subflow and signal" 2 2 2 chk_add_nr 1 1 @@ -1331,11 +1471,11 @@ remove_tests() # subflows and signal, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow chk_join_nr "remove subflows and signal" 3 3 3 chk_add_nr 1 1 @@ -1343,11 +1483,11 @@ remove_tests() # addresses remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow chk_join_nr "remove addresses" 3 3 3 chk_add_nr 3 3 @@ -1355,11 +1495,11 @@ remove_tests() # invalid addresses remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow chk_join_nr "remove invalid addresses" 1 1 1 chk_add_nr 3 3 @@ -1367,11 +1507,11 @@ remove_tests() # subflows and signal, flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr "flush subflows and signal" 3 3 3 chk_add_nr 1 1 @@ -1379,22 +1519,22 @@ remove_tests() # subflows flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow id 150 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 3 3 + pm_nl_set_limits $ns2 3 3 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr "flush subflows" 3 3 3 chk_rm_nr 3 3 # addresses flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr "flush addresses" 3 3 3 chk_add_nr 3 3 @@ -1402,11 +1542,11 @@ remove_tests() # invalid addresses flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow chk_join_nr "flush invalid addresses" 1 1 1 chk_add_nr 3 3 @@ -1414,18 +1554,18 @@ remove_tests() # remove id 0 subflow reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow chk_join_nr "remove id 0 subflow" 1 1 1 chk_rm_nr 1 1 # remove id 0 address reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow chk_join_nr "remove id 0 address" 1 1 1 chk_add_nr 1 1 @@ -1436,37 +1576,37 @@ add_tests() { # add single subflow reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow chk_join_nr "add single subflow" 1 1 1 # add signal address reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow chk_join_nr "add signal address" 1 1 1 chk_add_nr 1 1 # add multiple subflows reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow chk_join_nr "add multiple subflows" 2 2 2 # add multiple subflows IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow chk_join_nr "add multiple subflows IPv6" 2 2 2 # add multiple addresses IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow chk_join_nr "add multiple addresses IPv6" 2 2 2 chk_add_nr 2 2 @@ -1476,33 +1616,33 @@ ipv6_tests() { # subflow IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "single subflow IPv6" 1 1 1 # add_address, unused IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "unused signal address IPv6" 0 0 0 chk_add_nr 1 1 # signal address IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "single address IPv6" 1 1 1 chk_add_nr 1 1 # single address IPv6, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow chk_join_nr "remove single address IPv6" 1 1 1 chk_add_nr 1 1 @@ -1510,10 +1650,10 @@ ipv6_tests() # subflow and signal IPv6, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow chk_join_nr "remove subflow and signal IPv6" 2 2 2 chk_add_nr 1 1 @@ -1524,76 +1664,76 @@ v4mapped_tests() { # subflow IPv4-mapped to IPv4-mapped reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "single subflow IPv4-mapped" 1 1 1 # signal address IPv4-mapped with IPv4-mapped sk reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "signal address IPv4-mapped" 1 1 1 chk_add_nr 1 1 # subflow v4-map-v6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "single subflow v4-map-v6" 1 1 1 # signal address v4-map-v6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "signal address v4-map-v6" 1 1 1 chk_add_nr 1 1 # subflow v6-map-v4 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow v6-map-v4" 1 1 1 # signal address v6-map-v4 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address v6-map-v4" 1 1 1 chk_add_nr 1 1 # no subflow IPv6 to v4 address reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "no JOIN with diff families v4-v6" 0 0 0 # no subflow IPv6 to v4 address even if v6 has a valid v4 at the end reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "no JOIN with diff families v4-v6-2" 0 0 0 # no subflow IPv4 to v6 address, no need to slow down too then reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr "no JOIN with diff families v6-v4" 0 0 0 } @@ -1602,50 +1742,60 @@ backup_tests() { # single subflow, backup reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,backup + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup chk_join_nr "single subflow, backup" 1 1 1 chk_prio_nr 0 1 # single address, backup reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup chk_join_nr "single address, backup" 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 0 + + # single address with port, backup + reset + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr "single address with port, backup" 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 0 } add_addr_ports_tests() { # signal address with port reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address with port" 1 1 1 chk_add_nr 1 1 1 # subflow and signal with port reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and signal with port" 2 2 2 chk_add_nr 1 1 1 # single address with port, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow chk_join_nr "remove single address with port" 1 1 1 chk_add_nr 1 1 1 @@ -1653,10 +1803,10 @@ add_addr_ports_tests() # subflow and signal with port, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow chk_join_nr "remove subflow and signal with port" 2 2 2 chk_add_nr 1 1 1 @@ -1664,11 +1814,11 @@ add_addr_ports_tests() # subflows and signal with port, flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow chk_join_nr "flush subflows and signal with port" 3 3 3 chk_add_nr 1 1 @@ -1676,20 +1826,20 @@ add_addr_ports_tests() # multiple addresses with port reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10100 + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple addresses with port" 2 2 2 chk_add_nr 2 2 2 # multiple addresses with ports reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10101 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10101 + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple addresses with ports" 2 2 2 chk_add_nr 2 2 2 @@ -1699,56 +1849,56 @@ syncookies_tests() { # single subflow, syncookies reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow with syn cookies" 1 1 1 # multiple subflows with syn cookies reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows with syn cookies" 2 2 2 # multiple subflows limited by server reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflows limited by server w cookies" 2 1 1 # test signal address with cookies reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address with syn cookies" 1 1 1 chk_add_nr 1 1 # test cookie with subflow and signal reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and signal w cookies" 2 2 2 chk_add_nr 1 1 # accept and use add_addr with additional subflows reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflows and signal w. cookies" 3 3 3 chk_add_nr 1 1 @@ -1758,29 +1908,29 @@ checksum_tests() { # checksum test 0 0 reset_with_checksum 0 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 0 0" # checksum test 1 1 reset_with_checksum 1 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 1 1" # checksum test 0 1 reset_with_checksum 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 0 1" # checksum test 1 0 reset_with_checksum 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 1 0" } @@ -1789,26 +1939,26 @@ deny_join_id0_tests() { # subflow allow join id0 ns1 reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow allow join id0 ns1" 1 1 1 # subflow allow join id0 ns2 reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow allow join id0 ns2" 0 0 0 # signal address allow join id0 ns1 # ADD_ADDRs are not affected by allow_join_id0 value. reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address allow join id0 ns1" 1 1 1 chk_add_nr 1 1 @@ -1816,28 +1966,28 @@ deny_join_id0_tests() # signal address allow join id0 ns2 # ADD_ADDRs are not affected by allow_join_id0 value. reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address allow join id0 ns2" 1 1 1 chk_add_nr 1 1 # subflow and address allow join id0 ns1 reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and address allow join id0 1" 2 2 2 # subflow and address allow join id0 ns2 reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and address allow join id0 2" 1 1 1 } @@ -1848,10 +1998,10 @@ fullmesh_tests() # 2 fullmesh addrs in ns2, added before the connection, # 1 non-fullmesh addr in ns1, added during the connection. reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow,fullmesh - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,fullmesh + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow chk_join_nr "fullmesh test 2x1" 4 4 4 chk_add_nr 1 1 @@ -1860,9 +2010,9 @@ fullmesh_tests() # 1 non-fullmesh addr in ns1, added before the connection, # 1 fullmesh addr in ns2, added during the connection. reset - ip netns exec $ns1 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 1 3 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow chk_join_nr "fullmesh test 1x1" 3 3 3 chk_add_nr 1 1 @@ -1871,9 +2021,9 @@ fullmesh_tests() # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection. reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 5 - ip netns exec $ns2 ./pm_nl_ctl limits 1 5 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 2 5 + pm_nl_set_limits $ns2 1 5 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow chk_join_nr "fullmesh test 1x2" 5 5 5 chk_add_nr 1 1 @@ -1883,12 +2033,50 @@ fullmesh_tests() # 2 fullmesh addrs in ns2, added during the connection, # limit max_subflows to 4. reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 2 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow chk_join_nr "fullmesh test 1x2, limited" 4 4 4 chk_add_nr 1 1 + + # set fullmesh flag + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + chk_join_nr "set fullmesh flag test" 2 2 2 + chk_rm_nr 0 1 + + # set nofullmesh flag + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + chk_join_nr "set nofullmesh flag test" 2 2 2 + chk_rm_nr 0 1 + + # set backup,fullmesh flags + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + chk_join_nr "set backup,fullmesh flags test" 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + + # set nobackup,nofullmesh flags + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + chk_join_nr "set nobackup,nofullmesh flags test" 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 } all_tests() @@ -1930,6 +2118,7 @@ usage() echo " -m fullmesh_tests" echo " -c capture pcap files" echo " -C enable data checksum" + echo " -i use ip mptcp" echo " -h help" } @@ -1951,9 +2140,12 @@ for arg in "$@"; do if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"C"[0-9a-zA-Z]*$ ]]; then checksum=1 fi + if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"i"[0-9a-zA-Z]*$ ]]; then + ip_mptcp=1 + fi - # exception for the capture/checksum options, the rest means: a part of the tests - if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ]; then + # exception for the capture/checksum/ip_mptcp options, the rest means: a part of the tests + if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ] && [ "${arg}" != "-i" ]; then do_all_tests=0 fi done @@ -1963,7 +2155,7 @@ if [ $do_all_tests -eq 1 ]; then exit $ret fi -while getopts 'fesltra64bpkdmchCS' opt; do +while getopts 'fesltra64bpkdmchCSi' opt; do case $opt in f) subflows_tests @@ -2014,6 +2206,8 @@ while getopts 'fesltra64bpkdmchCS' opt; do ;; C) ;; + i) + ;; h | *) usage ;; diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index cbacf9f6538b..89839d1ff9d8 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -164,4 +164,22 @@ id 253 flags 10.0.0.5 id 254 flags 10.0.0.2 id 255 flags 10.0.0.3" "wrap-around ids" +ip netns exec $ns1 ./pm_nl_ctl flush +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags subflow +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags backup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup 10.0.1.1" "set flags (backup)" +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nobackup)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,fullmesh 10.0.1.1" " (fullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nofullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" + exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 354784512748..22a5ec1e128e 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -28,7 +28,7 @@ static void syntax(char *argv[]) fprintf(stderr, "\tadd [flags signal|subflow|backup|fullmesh] [id <nr>] [dev <name>] <ip>\n"); fprintf(stderr, "\tdel <id> [<ip>]\n"); fprintf(stderr, "\tget <id>\n"); - fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n"); + fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>]\n"); fprintf(stderr, "\tflush\n"); fprintf(stderr, "\tdump\n"); fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n"); @@ -657,8 +657,10 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) u_int32_t flags = 0; u_int16_t family; int nest_start; + int use_id = 0; + u_int8_t id; int off = 0; - int arg; + int arg = 2; memset(data, 0, sizeof(data)); nh = (void *)data; @@ -674,29 +676,45 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) nest->rta_len = RTA_LENGTH(0); off += NLMSG_ALIGN(nest->rta_len); - /* addr data */ - rta = (void *)(data + off); - if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) { - family = AF_INET; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; - rta->rta_len = RTA_LENGTH(4); - } else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) { - family = AF_INET6; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; - rta->rta_len = RTA_LENGTH(16); + if (!strcmp(argv[arg], "id")) { + if (++arg >= argc) + error(1, 0, " missing id value"); + + use_id = 1; + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); } else { - error(1, errno, "can't parse ip %s", argv[2]); + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[arg], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[arg], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else { + error(1, errno, "can't parse ip %s", argv[arg]); + } + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); } - off += NLMSG_ALIGN(rta->rta_len); - /* family */ - rta = (void *)(data + off); - rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; - rta->rta_len = RTA_LENGTH(2); - memcpy(RTA_DATA(rta), &family, 2); - off += NLMSG_ALIGN(rta->rta_len); + if (++arg >= argc) + error(1, 0, " missing flags keyword"); - for (arg = 3; arg < argc; arg++) { + for (; arg < argc; arg++) { if (!strcmp(argv[arg], "flags")) { char *tok, *str; @@ -704,12 +722,14 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) if (++arg >= argc) error(1, 0, " missing flags value"); - /* do not support flag list yet */ for (str = argv[arg]; (tok = strtok(str, ",")); str = NULL) { if (!strcmp(tok, "backup")) flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else if (strcmp(tok, "nobackup")) + else if (!strcmp(tok, "fullmesh")) + flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else if (strcmp(tok, "nobackup") && + strcmp(tok, "nofullmesh")) error(1, errno, "unknown flag %s", argv[arg]); } @@ -719,6 +739,21 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) rta->rta_len = RTA_LENGTH(4); memcpy(RTA_DATA(rta), &flags, 4); off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + u_int16_t port; + + if (use_id) + error(1, 0, " port can't be used with id"); + + if (++arg >= argc) + error(1, 0, " missing port value"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); } else { error(1, 0, "unknown keyword %s", argv[arg]); } diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index c9ce3dfa42ee..0900c5438fbb 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -216,9 +216,9 @@ kci_test_route_get() check_err $? ip route get fe80::1 dev "$devdummy" > /dev/null check_err $? - ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x1 mark 0x1 > /dev/null + ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x10 mark 0x1 > /dev/null check_err $? - ip route get ::1 from ::1 iif lo oif lo tos 0x1 mark 0x1 > /dev/null + ip route get ::1 from ::1 iif lo oif lo tos 0x10 mark 0x1 > /dev/null check_err $? ip addr add dev "$devdummy" 10.23.7.11/24 check_err $? diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c index aee631c5284e..044bc0e9ed81 100644 --- a/tools/testing/selftests/net/timestamping.c +++ b/tools/testing/selftests/net/timestamping.c @@ -325,8 +325,8 @@ int main(int argc, char **argv) struct ifreq device; struct ifreq hwtstamp; struct hwtstamp_config hwconfig, hwconfig_requested; - struct so_timestamping so_timestamping_get = { 0, -1 }; - struct so_timestamping so_timestamping = { 0, -1 }; + struct so_timestamping so_timestamping_get = { 0, 0 }; + struct so_timestamping so_timestamping = { 0, 0 }; struct sockaddr_in addr; struct ip_mreq imr; struct in_addr iaddr; |