diff options
130 files changed, 2395 insertions, 734 deletions
diff --git a/Documentation/bpf/standardization/abi.rst b/Documentation/bpf/standardization/abi.rst index 0c2e10eeb89a..41514137cb7b 100644 --- a/Documentation/bpf/standardization/abi.rst +++ b/Documentation/bpf/standardization/abi.rst @@ -23,3 +23,6 @@ The BPF calling convention is defined as: R0 - R5 are scratch registers and BPF programs needs to spill/fill them if necessary across calls. + +The BPF program needs to store the return value into register R0 before doing an +``EXIT``. diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst index 00c93eb42613..8d19810504b8 100644 --- a/Documentation/bpf/standardization/instruction-set.rst +++ b/Documentation/bpf/standardization/instruction-set.rst @@ -14,6 +14,13 @@ set architecture (ISA). Documentation conventions ========================= +The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", +"SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and +"OPTIONAL" in this document are to be interpreted as described in +BCP 14 `<https://www.rfc-editor.org/info/rfc2119>`_ +`RFC8174 <https://www.rfc-editor.org/info/rfc8174>`_ +when, and only when, they appear in all capitals, as shown here. + For brevity and consistency, this document refers to families of types using a shorthand syntax and refers to several expository, mnemonic functions when describing the semantics of instructions. @@ -25,7 +32,7 @@ Types This document refers to integer types with the notation `SN` to specify a type's signedness (`S`) and bit width (`N`), respectively. -.. table:: Meaning of signedness notation. +.. table:: Meaning of signedness notation ==== ========= S Meaning @@ -34,7 +41,7 @@ a type's signedness (`S`) and bit width (`N`), respectively. s signed ==== ========= -.. table:: Meaning of bit-width notation. +.. table:: Meaning of bit-width notation ===== ========= N Bit width @@ -106,9 +113,9 @@ Conformance groups An implementation does not need to support all instructions specified in this document (e.g., deprecated instructions). Instead, a number of conformance -groups are specified. An implementation must support the base32 conformance -group and may support additional conformance groups, where supporting a -conformance group means it must support all instructions in that conformance +groups are specified. An implementation MUST support the base32 conformance +group and MAY support additional conformance groups, where supporting a +conformance group means it MUST support all instructions in that conformance group. The use of named conformance groups enables interoperability between a runtime @@ -209,7 +216,7 @@ For example:: 07 1 0 00 00 11 22 33 44 r1 += 0x11223344 // big Note that most instructions do not use all of the fields. -Unused fields shall be cleared to zero. +Unused fields SHALL be cleared to zero. Wide instruction encoding -------------------------- @@ -256,18 +263,20 @@ Instruction classes The three least significant bits of the 'opcode' field store the instruction class: -===== ===== =============================== =================================== -class value description reference -===== ===== =============================== =================================== -LD 0x0 non-standard load operations `Load and store instructions`_ -LDX 0x1 load into register operations `Load and store instructions`_ -ST 0x2 store from immediate operations `Load and store instructions`_ -STX 0x3 store from register operations `Load and store instructions`_ -ALU 0x4 32-bit arithmetic operations `Arithmetic and jump instructions`_ -JMP 0x5 64-bit jump operations `Arithmetic and jump instructions`_ -JMP32 0x6 32-bit jump operations `Arithmetic and jump instructions`_ -ALU64 0x7 64-bit arithmetic operations `Arithmetic and jump instructions`_ -===== ===== =============================== =================================== +.. table:: Instruction class + + ===== ===== =============================== =================================== + class value description reference + ===== ===== =============================== =================================== + LD 0x0 non-standard load operations `Load and store instructions`_ + LDX 0x1 load into register operations `Load and store instructions`_ + ST 0x2 store from immediate operations `Load and store instructions`_ + STX 0x3 store from register operations `Load and store instructions`_ + ALU 0x4 32-bit arithmetic operations `Arithmetic and jump instructions`_ + JMP 0x5 64-bit jump operations `Arithmetic and jump instructions`_ + JMP32 0x6 32-bit jump operations `Arithmetic and jump instructions`_ + ALU64 0x7 64-bit arithmetic operations `Arithmetic and jump instructions`_ + ===== ===== =============================== =================================== Arithmetic and jump instructions ================================ @@ -285,12 +294,14 @@ For arithmetic and jump instructions (``ALU``, ``ALU64``, ``JMP`` and **s (source)** the source operand location, which unless otherwise specified is one of: - ====== ===== ============================================== - source value description - ====== ===== ============================================== - K 0 use 32-bit 'imm' value as source operand - X 1 use 'src_reg' register value as source operand - ====== ===== ============================================== + .. table:: Source operand location + + ====== ===== ============================================== + source value description + ====== ===== ============================================== + K 0 use 32-bit 'imm' value as source operand + X 1 use 'src_reg' register value as source operand + ====== ===== ============================================== **instruction class** the instruction class (see `Instruction classes`_) @@ -305,27 +316,29 @@ The 'code' field encodes the operation as below, where 'src' refers to the the source operand and 'dst' refers to the value of the destination register. -===== ===== ======= ========================================================== -name code offset description -===== ===== ======= ========================================================== -ADD 0x0 0 dst += src -SUB 0x1 0 dst -= src -MUL 0x2 0 dst \*= src -DIV 0x3 0 dst = (src != 0) ? (dst / src) : 0 -SDIV 0x3 1 dst = (src != 0) ? (dst s/ src) : 0 -OR 0x4 0 dst \|= src -AND 0x5 0 dst &= src -LSH 0x6 0 dst <<= (src & mask) -RSH 0x7 0 dst >>= (src & mask) -NEG 0x8 0 dst = -dst -MOD 0x9 0 dst = (src != 0) ? (dst % src) : dst -SMOD 0x9 1 dst = (src != 0) ? (dst s% src) : dst -XOR 0xa 0 dst ^= src -MOV 0xb 0 dst = src -MOVSX 0xb 8/16/32 dst = (s8,s16,s32)src -ARSH 0xc 0 :term:`sign extending<Sign Extend>` dst >>= (src & mask) -END 0xd 0 byte swap operations (see `Byte swap instructions`_ below) -===== ===== ======= ========================================================== +.. table:: Arithmetic instructions + + ===== ===== ======= ========================================================== + name code offset description + ===== ===== ======= ========================================================== + ADD 0x0 0 dst += src + SUB 0x1 0 dst -= src + MUL 0x2 0 dst \*= src + DIV 0x3 0 dst = (src != 0) ? (dst / src) : 0 + SDIV 0x3 1 dst = (src != 0) ? (dst s/ src) : 0 + OR 0x4 0 dst \|= src + AND 0x5 0 dst &= src + LSH 0x6 0 dst <<= (src & mask) + RSH 0x7 0 dst >>= (src & mask) + NEG 0x8 0 dst = -dst + MOD 0x9 0 dst = (src != 0) ? (dst % src) : dst + SMOD 0x9 1 dst = (src != 0) ? (dst s% src) : dst + XOR 0xa 0 dst ^= src + MOV 0xb 0 dst = src + MOVSX 0xb 8/16/32 dst = (s8,s16,s32)src + ARSH 0xc 0 :term:`sign extending<Sign Extend>` dst >>= (src & mask) + END 0xd 0 byte swap operations (see `Byte swap instructions`_ below) + ===== ===== ======= ========================================================== Underflow and overflow are allowed during arithmetic operations, meaning the 64-bit or 32-bit value will wrap. If BPF program execution would @@ -374,7 +387,7 @@ interpreted as a 64-bit signed value. Note that there are varying definitions of the signed modulo operation when the dividend or divisor are negative, where implementations often vary by language such that Python, Ruby, etc. differ from C, Go, Java, -etc. This specification requires that signed modulo use truncated division +etc. This specification requires that signed modulo MUST use truncated division (where -13 % 3 == -1) as implemented in C, Go, etc.:: a % n = a - n * trunc(a / n) @@ -386,6 +399,19 @@ The ``MOVSX`` instruction does a move operation with sign extension. operands into 64-bit operands. Unlike other arithmetic instructions, ``MOVSX`` is only defined for register source operands (``X``). +``{MOV, K, ALU64}`` means:: + + dst = (s64)imm + +``{MOV, X, ALU}`` means:: + + dst = (u32)src + +``{MOVSX, X, ALU}`` with 'offset' 8 means:: + + dst = (u32)(s32)(s8)src + + The ``NEG`` instruction is only defined when the source bit is clear (``K``). @@ -404,15 +430,17 @@ only and do not use a separate source register or immediate value. For ``ALU``, the 1-bit source operand field in the opcode is used to select what byte order the operation converts from or to. For ``ALU64``, the 1-bit source operand field in the opcode is reserved -and must be set to 0. +and MUST be set to 0. -===== ======== ===== ================================================= -class source value description -===== ======== ===== ================================================= -ALU TO_LE 0 convert between host byte order and little endian -ALU TO_BE 1 convert between host byte order and big endian -ALU64 Reserved 0 do byte swap unconditionally -===== ======== ===== ================================================= +.. table:: Byte swap instructions + + ===== ======== ===== ================================================= + class source value description + ===== ======== ===== ================================================= + ALU TO_LE 0 convert between host byte order and little endian + ALU TO_BE 1 convert between host byte order and big endian + ALU64 Reserved 0 do byte swap unconditionally + ===== ======== ===== ================================================= The 'imm' field encodes the width of the swap operations. The following widths are supported: 16, 32 and 64. Width 64 operations belong to the base64 @@ -448,27 +476,29 @@ otherwise identical operations, and indicates the base64 conformance group unless otherwise specified. The 'code' field encodes the operation as below: -======== ===== ======= ================================= =================================================== -code value src_reg description notes -======== ===== ======= ================================= =================================================== -JA 0x0 0x0 PC += offset {JA, K, JMP} only -JA 0x0 0x0 PC += imm {JA, K, JMP32} only -JEQ 0x1 any PC += offset if dst == src -JGT 0x2 any PC += offset if dst > src unsigned -JGE 0x3 any PC += offset if dst >= src unsigned -JSET 0x4 any PC += offset if dst & src -JNE 0x5 any PC += offset if dst != src -JSGT 0x6 any PC += offset if dst > src signed -JSGE 0x7 any PC += offset if dst >= src signed -CALL 0x8 0x0 call helper function by static ID {CALL, K, JMP} only, see `Helper functions`_ -CALL 0x8 0x1 call PC += imm {CALL, K, JMP} only, see `Program-local functions`_ -CALL 0x8 0x2 call helper function by BTF ID {CALL, K, JMP} only, see `Helper functions`_ -EXIT 0x9 0x0 return {CALL, K, JMP} only -JLT 0xa any PC += offset if dst < src unsigned -JLE 0xb any PC += offset if dst <= src unsigned -JSLT 0xc any PC += offset if dst < src signed -JSLE 0xd any PC += offset if dst <= src signed -======== ===== ======= ================================= =================================================== +.. table:: Jump instructions + + ======== ===== ======= ================================= =================================================== + code value src_reg description notes + ======== ===== ======= ================================= =================================================== + JA 0x0 0x0 PC += offset {JA, K, JMP} only + JA 0x0 0x0 PC += imm {JA, K, JMP32} only + JEQ 0x1 any PC += offset if dst == src + JGT 0x2 any PC += offset if dst > src unsigned + JGE 0x3 any PC += offset if dst >= src unsigned + JSET 0x4 any PC += offset if dst & src + JNE 0x5 any PC += offset if dst != src + JSGT 0x6 any PC += offset if dst > src signed + JSGE 0x7 any PC += offset if dst >= src signed + CALL 0x8 0x0 call helper function by static ID {CALL, K, JMP} only, see `Helper functions`_ + CALL 0x8 0x1 call PC += imm {CALL, K, JMP} only, see `Program-local functions`_ + CALL 0x8 0x2 call helper function by BTF ID {CALL, K, JMP} only, see `Helper functions`_ + EXIT 0x9 0x0 return {CALL, K, JMP} only + JLT 0xa any PC += offset if dst < src unsigned + JLE 0xb any PC += offset if dst <= src unsigned + JSLT 0xc any PC += offset if dst < src signed + JSLE 0xd any PC += offset if dst <= src signed + ======== ===== ======= ================================= =================================================== where 'PC' denotes the program counter, and the offset to increment by is in units of 64-bit instructions relative to the instruction following @@ -476,9 +506,6 @@ the jump instruction. Thus 'PC += 1' skips execution of the next instruction if it's a basic instruction or results in undefined behavior if the next instruction is a 128-bit wide instruction. -The BPF program needs to store the return value into register R0 before doing an -``EXIT``. - Example: ``{JSGE, X, JMP32}`` means:: @@ -487,6 +514,10 @@ Example: where 's>=' indicates a signed '>=' comparison. +``{JLE, K, JMP}`` means:: + + if dst <= (u64)(s64)imm goto +offset + ``{JA, K, JMP32}`` means:: gotol +imm @@ -515,14 +546,16 @@ for each program type, but static IDs are unique across all program types. Platforms that support the BPF Type Format (BTF) support identifying a helper function by a BTF ID encoded in the 'imm' field, where the BTF ID -identifies the helper name and type. +identifies the helper name and type. Further documentation of BTF +is outside the scope of this document and is left for future work. Program-local functions ~~~~~~~~~~~~~~~~~~~~~~~ Program-local functions are functions exposed by the same BPF program as the -caller, and are referenced by offset from the call instruction, similar to -``JA``. The offset is encoded in the 'imm' field of the call instruction. -An ``EXIT`` within the program-local function will return to the caller. +caller, and are referenced by offset from the instruction following the call +instruction, similar to ``JA``. The offset is encoded in the 'imm' field of +the call instruction. An ``EXIT`` within the program-local function will +return to the caller. Load and store instructions =========================== @@ -537,6 +570,8 @@ For load and store instructions (``LD``, ``LDX``, ``ST``, and ``STX``), the **mode** The mode modifier is one of: + .. table:: Mode modifier + ============= ===== ==================================== ============= mode modifier value description reference ============= ===== ==================================== ============= @@ -551,6 +586,8 @@ For load and store instructions (``LD``, ``LDX``, ``ST``, and ``STX``), the **sz (size)** The size modifier is one of: + .. table:: Size modifier + ==== ===== ===================== size value description ==== ===== ===================== @@ -619,14 +656,16 @@ 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: -======== ===== =========== -imm value description -======== ===== =========== -ADD 0x00 atomic add -OR 0x40 atomic or -AND 0x50 atomic and -XOR 0xa0 atomic xor -======== ===== =========== +.. table:: Simple atomic operations + + ======== ===== =========== + imm value description + ======== ===== =========== + ADD 0x00 atomic add + OR 0x40 atomic or + AND 0x50 atomic and + XOR 0xa0 atomic xor + ======== ===== =========== ``{ATOMIC, W, STX}`` with 'imm' = ADD means:: @@ -640,13 +679,15 @@ XOR 0xa0 atomic xor In addition to the simple atomic operations, there also is a modifier and two complex atomic operations: -=========== ================ =========================== -imm value description -=========== ================ =========================== -FETCH 0x01 modifier: return old value -XCHG 0xe0 | FETCH atomic exchange -CMPXCHG 0xf0 | FETCH atomic compare and exchange -=========== ================ =========================== +.. table:: Complex atomic operations + + =========== ================ =========================== + imm value description + =========== ================ =========================== + FETCH 0x01 modifier: return old value + XCHG 0xe0 | FETCH atomic exchange + CMPXCHG 0xf0 | FETCH atomic compare and exchange + =========== ================ =========================== The ``FETCH`` modifier is optional for simple atomic operations, and always set for the complex atomic operations. If the ``FETCH`` flag @@ -673,17 +714,19 @@ The following table defines a set of ``{IMM, DW, LD}`` instructions with opcode subtypes in the 'src_reg' field, using new terms such as "map" defined further below: -======= ========================================= =========== ============== -src_reg pseudocode imm type dst type -======= ========================================= =========== ============== -0x0 dst = (next_imm << 32) | imm integer integer -0x1 dst = map_by_fd(imm) map fd map -0x2 dst = map_val(map_by_fd(imm)) + next_imm map fd data address -0x3 dst = var_addr(imm) variable id data address -0x4 dst = code_addr(imm) integer code address -0x5 dst = map_by_idx(imm) map index map -0x6 dst = map_val(map_by_idx(imm)) + next_imm map index data address -======= ========================================= =========== ============== +.. table:: 64-bit immediate instructions + + ======= ========================================= =========== ============== + src_reg pseudocode imm type dst type + ======= ========================================= =========== ============== + 0x0 dst = (next_imm << 32) | imm integer integer + 0x1 dst = map_by_fd(imm) map fd map + 0x2 dst = map_val(map_by_fd(imm)) + next_imm map fd data address + 0x3 dst = var_addr(imm) variable id data address + 0x4 dst = code_addr(imm) integer code address + 0x5 dst = map_by_idx(imm) map index map + 0x6 dst = map_val(map_by_idx(imm)) + next_imm map index data address + ======= ========================================= =========== ============== where @@ -725,5 +768,5 @@ carried over from classic BPF. These instructions used an instruction class of ``LD``, a size modifier of ``W``, ``H``, or ``B``, and a mode modifier of ``ABS`` or ``IND``. The 'dst_reg' and 'offset' fields were set to zero, and 'src_reg' was set to zero for ``ABS``. However, these -instructions are deprecated and should no longer be used. All legacy packet +instructions are deprecated and SHOULD no longer be used. All legacy packet access instructions belong to the "packet" conformance group. diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 21cc27e75f50..3bab4e1f3fbf 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -76,6 +76,7 @@ properties: - rockchip,rk3128-gmac - rockchip,rk3228-gmac - rockchip,rk3288-gmac + - rockchip,rk3308-gmac - rockchip,rk3328-gmac - rockchip,rk3366-gmac - rockchip,rk3368-gmac diff --git a/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml index e253fa786092..c296e5711848 100644 --- a/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml +++ b/Documentation/devicetree/bindings/net/ti,icssg-prueth.yaml @@ -55,6 +55,14 @@ properties: description: phandle to MII_RT module's syscon regmap + ti,pa-stats: + $ref: /schemas/types.yaml#/definitions/phandle + description: + phandle to PA_STATS module's syscon regmap. PA_STATS is a set of + registers where different statistics related to ICSSG, are dumped by + ICSSG firmware. PA_STATS module's syscon regmap will help the device to + access/read/write those statistics. + ti,iep: $ref: /schemas/types.yaml#/definitions/phandle-array maxItems: 2 @@ -194,6 +202,7 @@ examples: "tx1-0", "tx1-1", "tx1-2", "tx1-3", "rx0", "rx1"; ti,mii-g-rt = <&icssg2_mii_g_rt>; + ti,pa-stats = <&icssg2_pa_stats>; ti,iep = <&icssg2_iep0>, <&icssg2_iep1>; interrupt-parent = <&icssg2_intc>; interrupts = <24 0 2>, <25 1 3>; diff --git a/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml b/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml index 0f781dac6717..eb803ddd13e0 100644 --- a/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml +++ b/Documentation/devicetree/bindings/net/xlnx,gmii-to-rgmii.yaml @@ -31,6 +31,10 @@ properties: phy-handle: $ref: ethernet-controller.yaml#/properties/phy-handle + clocks: + items: + - description: 200/375 MHz free-running clock is used as input clock. + required: - compatible - reg @@ -51,5 +55,6 @@ examples: compatible = "xlnx,gmii-to-rgmii-1.0"; reg = <8>; phy-handle = <&phy>; + clocks = <&dummy>; }; }; diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 95b0eb1486bf..94132d30e0e0 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -479,6 +479,7 @@ operations: name: pin-get doc: | Get list of pins and its attributes. + - dump request without any attributes given - list all the pins in the system - dump request with target dpll - list all the pins registered with diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b94176e25be1..58d3dcfebea2 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -610,6 +610,18 @@ config TOOLCHAIN_HAS_VECTOR_CRYPTO def_bool $(as-instr, .option arch$(comma) +v$(comma) +zvkb) depends on AS_HAS_OPTION_ARCH +config RISCV_ISA_ZBA + bool "Zba extension support for bit manipulation instructions" + default y + help + Add support for enabling optimisations in the kernel when the Zba + extension is detected at boot. + + The Zba extension provides instructions to accelerate the generation + of addresses that index into arrays of basic data types. + + If you don't know what to do here, say Y. + config RISCV_ISA_ZBB bool "Zbb extension support for bit manipulation instructions" depends on TOOLCHAIN_HAS_ZBB diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index fdbf88ca8b70..97041b58237a 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -18,6 +18,11 @@ static inline bool rvc_enabled(void) return IS_ENABLED(CONFIG_RISCV_ISA_C); } +static inline bool rvzba_enabled(void) +{ + return IS_ENABLED(CONFIG_RISCV_ISA_ZBA) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBA); +} + static inline bool rvzbb_enabled(void) { return IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBB); @@ -939,6 +944,14 @@ static inline u16 rvc_sdsp(u32 imm9, u8 rs2) return rv_css_insn(0x7, imm, rs2, 0x2); } +/* RV64-only ZBA instructions. */ + +static inline u32 rvzba_zextw(u8 rd, u8 rs1) +{ + /* add.uw rd, rs1, ZERO */ + return rv_r_insn(0x04, RV_REG_ZERO, rs1, 0, rd, 0x3b); +} + #endif /* __riscv_xlen == 64 */ /* Helper functions that emit RVC instructions when possible. */ @@ -1161,6 +1174,11 @@ static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx) static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx) { + if (rvzba_enabled()) { + emit(rvzba_zextw(rd, rs), ctx); + return; + } + emit_slli(rd, rs, 32, ctx); emit_srli(rd, rd, 32, ctx); } diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 79a001d5533e..2bc4c14ea59a 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -537,8 +537,10 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, /* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */ case BPF_CMPXCHG: r0 = bpf_to_rv_reg(BPF_REG_0, ctx); - emit(is64 ? rv_addi(RV_REG_T2, r0, 0) : - rv_addiw(RV_REG_T2, r0, 0), ctx); + if (is64) + emit_mv(RV_REG_T2, r0, ctx); + else + emit_addiw(RV_REG_T2, r0, 0, ctx); emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) : rv_lr_w(r0, 0, rd, 0, 0), ctx); jmp_offset = ninsns_rvoff(8); @@ -868,7 +870,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, stack_size += 8; sreg_off = stack_size; - stack_size = round_up(stack_size, 16); + stack_size = round_up(stack_size, STACK_ALIGN); if (!is_struct_ops) { /* For the trampoline called from function entry, @@ -1960,7 +1962,7 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) { int i, stack_adjust = 0, store_offset, bpf_stack_adjust; - bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); + bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, STACK_ALIGN); if (bpf_stack_adjust) mark_fp(ctx); @@ -1982,7 +1984,7 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) if (ctx->arena_vm_start) stack_adjust += 8; - stack_adjust = round_up(stack_adjust, 16); + stack_adjust = round_up(stack_adjust, STACK_ALIGN); stack_adjust += bpf_stack_adjust; store_offset = stack_adjust - 8; diff --git a/drivers/isdn/mISDN/dsp_blowfish.c b/drivers/isdn/mISDN/dsp_blowfish.c index 0aa572f3858d..0e77c282c862 100644 --- a/drivers/isdn/mISDN/dsp_blowfish.c +++ b/drivers/isdn/mISDN/dsp_blowfish.c @@ -73,11 +73,6 @@ * crypto-api for faster implementation */ -struct bf_ctx { - u32 p[18]; - u32 s[1024]; -}; - static const u32 bf_pbox[16 + 2] = { 0x243f6a88, 0x85a308d3, 0x13198a2e, 0x03707344, 0xa4093822, 0x299f31d0, 0x082efa98, 0xec4e6c89, diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 3092b391031a..8508b5145bc1 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -102,6 +102,7 @@ config NET_DSA_SMSC_LAN9303 tristate select NET_DSA_TAG_LAN9303 select REGMAP + imply SMSC_PHY help This enables support for the Microchip LAN9303/LAN9354 3 port ethernet switch chips. diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 61e95487732d..3aa66bf9eafc 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1050,24 +1050,32 @@ static void felix_phylink_get_caps(struct dsa_switch *ds, int port, config->supported_interfaces); } -static void felix_phylink_mac_config(struct dsa_switch *ds, int port, +static void felix_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); + struct dsa_port *dp = dsa_phylink_to_port(config); + struct ocelot *ocelot = dp->ds->priv; + int port = dp->index; + struct felix *felix; + + felix = ocelot_to_felix(ocelot); if (felix->info->phylink_mac_config) felix->info->phylink_mac_config(ocelot, port, mode, state); } -static struct phylink_pcs *felix_phylink_mac_select_pcs(struct dsa_switch *ds, - int port, - phy_interface_t iface) +static struct phylink_pcs * +felix_phylink_mac_select_pcs(struct phylink_config *config, + phy_interface_t iface) { - struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); + struct dsa_port *dp = dsa_phylink_to_port(config); + struct ocelot *ocelot = dp->ds->priv; struct phylink_pcs *pcs = NULL; + int port = dp->index; + struct felix *felix; + + felix = ocelot_to_felix(ocelot); if (felix->pcs && felix->pcs[port]) pcs = felix->pcs[port]; @@ -1075,11 +1083,13 @@ static struct phylink_pcs *felix_phylink_mac_select_pcs(struct dsa_switch *ds, return pcs; } -static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, +static void felix_phylink_mac_link_down(struct phylink_config *config, unsigned int link_an_mode, phy_interface_t interface) { - struct ocelot *ocelot = ds->priv; + struct dsa_port *dp = dsa_phylink_to_port(config); + struct ocelot *ocelot = dp->ds->priv; + int port = dp->index; struct felix *felix; felix = ocelot_to_felix(ocelot); @@ -1088,15 +1098,19 @@ static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, felix->info->quirks); } -static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, +static void felix_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, unsigned int link_an_mode, phy_interface_t interface, - struct phy_device *phydev, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); + struct dsa_port *dp = dsa_phylink_to_port(config); + struct ocelot *ocelot = dp->ds->priv; + int port = dp->index; + struct felix *felix; + + felix = ocelot_to_felix(ocelot); ocelot_phylink_mac_link_up(ocelot, port, phydev, link_an_mode, interface, speed, duplex, tx_pause, rx_pause, @@ -2083,6 +2097,14 @@ static void felix_get_mm_stats(struct dsa_switch *ds, int port, ocelot_port_get_mm_stats(ocelot, port, stats); } +const struct phylink_mac_ops felix_phylink_mac_ops = { + .mac_select_pcs = felix_phylink_mac_select_pcs, + .mac_config = felix_phylink_mac_config, + .mac_link_down = felix_phylink_mac_link_down, + .mac_link_up = felix_phylink_mac_link_up, +}; +EXPORT_SYMBOL_GPL(felix_phylink_mac_ops); + const struct dsa_switch_ops felix_switch_ops = { .get_tag_protocol = felix_get_tag_protocol, .change_tag_protocol = felix_change_tag_protocol, @@ -2104,10 +2126,6 @@ const struct dsa_switch_ops felix_switch_ops = { .get_sset_count = felix_get_sset_count, .get_ts_info = felix_get_ts_info, .phylink_get_caps = felix_phylink_get_caps, - .phylink_mac_config = felix_phylink_mac_config, - .phylink_mac_select_pcs = felix_phylink_mac_select_pcs, - .phylink_mac_link_down = felix_phylink_mac_link_down, - .phylink_mac_link_up = felix_phylink_mac_link_up, .port_enable = felix_port_enable, .port_fast_age = felix_port_fast_age, .port_fdb_dump = felix_fdb_dump, diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index dbf5872fe367..4d3489aaa659 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -82,6 +82,7 @@ struct felix_tag_proto_ops { struct netlink_ext_ack *extack); }; +extern const struct phylink_mac_ops felix_phylink_mac_ops; extern const struct dsa_switch_ops felix_switch_ops; /* DSA glue / front-end for struct ocelot */ diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 85952d841f28..d4799a908abc 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -2717,6 +2717,7 @@ static int felix_pci_probe(struct pci_dev *pdev, ds->num_ports = felix->info->num_ports; ds->num_tx_queues = felix->info->num_tx_queues; ds->ops = &felix_switch_ops; + ds->phylink_mac_ops = &felix_phylink_mac_ops; ds->priv = ocelot; felix->ds = ds; felix->tag_proto = DSA_TAG_PROTO_OCELOT; diff --git a/drivers/net/dsa/ocelot/ocelot_ext.c b/drivers/net/dsa/ocelot/ocelot_ext.c index 22187d831c4b..a8927dc7aca4 100644 --- a/drivers/net/dsa/ocelot/ocelot_ext.c +++ b/drivers/net/dsa/ocelot/ocelot_ext.c @@ -96,6 +96,7 @@ static int ocelot_ext_probe(struct platform_device *pdev) ds->num_tx_queues = felix->info->num_tx_queues; ds->ops = &felix_switch_ops; + ds->phylink_mac_ops = &felix_phylink_mac_ops; ds->priv = ocelot; felix->ds = ds; felix->tag_proto = DSA_TAG_PROTO_OCELOT; diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 049930da0521..5ac8897e232b 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1009,6 +1009,7 @@ static int seville_probe(struct platform_device *pdev) ds->dev = &pdev->dev; ds->num_ports = felix->info->num_ports; ds->ops = &felix_switch_ops; + ds->phylink_mac_ops = &felix_phylink_mac_ops; ds->priv = ocelot; felix->ds = ds; felix->tag_proto = DSA_TAG_PROTO_SEVILLE; diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c index 65f56a98c0a0..1a34da07c0db 100644 --- a/drivers/net/ethernet/8390/ne2k-pci.c +++ b/drivers/net/ethernet/8390/ne2k-pci.c @@ -186,17 +186,6 @@ static void ne2k_pci_block_output(struct net_device *dev, const int count, static const struct ethtool_ops ne2k_pci_ethtool_ops; - -/* There is no room in the standard 8390 structure for extra info we need, - * so we build a meta/outer-wrapper structure.. - */ -struct ne2k_pci_card { - struct net_device *dev; - struct pci_dev *pci_dev; -}; - - - /* NEx000-clone boards have a Station Address (SA) PROM (SAPROM) in the packet * buffer memory space. By-the-spec NE2000 clones have 0x57,0x57 in bytes * 0x0e,0x0f of the SAPROM, while other supposed NE2000 clones must be diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 857361c74f5d..e1b8794b14c9 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -441,14 +441,6 @@ enum rx_desc_bits { }; /* Completion queue entry. */ -struct short_rx_done_desc { - __le32 status; /* Low 16 bits is length. */ -}; -struct basic_rx_done_desc { - __le32 status; /* Low 16 bits is length. */ - __le16 vlanid; - __le16 status2; -}; struct csum_rx_done_desc { __le32 status; /* Low 16 bits is length. */ __le16 csum; /* Partial checksum */ diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 34f02a8ec2ca..1d79f6eaa41f 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -92,12 +92,6 @@ static int octeon_console_debug_enabled(u32 console) /* time to wait for possible in-flight requests in milliseconds */ #define WAIT_INFLIGHT_REQUEST msecs_to_jiffies(1000) -struct oct_link_status_resp { - u64 rh; - struct oct_link_info link_info; - u64 status; -}; - struct oct_timestamp_resp { u64 rh; u64 timestamp; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index 0d6ee30affb9..eef12fdd246d 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -30,11 +30,6 @@ #include "cn23xx_pf_device.h" #include "cn23xx_vf_device.h" -struct niclist { - struct list_head list; - void *ptr; -}; - struct __dispatch { struct list_head list; struct octeon_recv_info *rinfo; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 5f0c9e1771db..7ebd61a3a49b 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -79,7 +79,8 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); #define GMAC0_IRQ4_8 (GMAC0_MIB_INT_BIT | GMAC0_RX_OVERRUN_INT_BIT) #define GMAC_OFFLOAD_FEATURES (NETIF_F_SG | NETIF_F_IP_CSUM | \ - NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM) + NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | \ + NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6) /** * struct gmac_queue_page - page buffer per-page info @@ -1148,13 +1149,25 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, skb_frag_t *skb_frag; dma_addr_t mapping; void *buffer; + u16 mss; int ret; - /* TODO: implement proper TSO using MTU in word3 */ word1 = skb->len; word3 = SOF_BIT; - if (skb->len >= ETH_FRAME_LEN) { + mss = skb_shinfo(skb)->gso_size; + if (mss) { + /* This means we are dealing with TCP and skb->len is the + * sum total of all the segments. The TSO will deal with + * chopping this up for us. + */ + /* The accelerator needs the full frame size here */ + mss += skb_tcp_all_headers(skb); + netdev_dbg(netdev, "segment offloading mss = %04x len=%04x\n", + mss, skb->len); + word1 |= TSS_MTU_ENABLE_BIT; + word3 |= mss; + } else if (skb->len >= ETH_FRAME_LEN) { /* Hardware offloaded checksumming isn't working on frames * bigger than 1514 bytes. A hypothesis about this is that the * checksum buffer is only 1518 bytes, so when the frames get @@ -1169,7 +1182,9 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, return ret; } word1 |= TSS_BYPASS_BIT; - } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) { int tcp = 0; /* We do not switch off the checksumming on non TCP/UDP diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 92b8f4ab26f1..796e6f4e583d 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -1066,7 +1066,6 @@ int memac_initialization(struct mac_device *mac_dev, struct fman_mac_params *params) { int err; - struct device_node *fixed; struct phylink_pcs *pcs; struct fman_mac *memac; unsigned long capabilities; @@ -1222,18 +1221,15 @@ int memac_initialization(struct mac_device *mac_dev, memac->rgmii_no_half_duplex = true; /* Most boards should use MLO_AN_INBAND, but existing boards don't have - * a managed property. Default to MLO_AN_INBAND if nothing else is - * specified. We need to be careful and not enable this if we have a - * fixed link or if we are using MII or RGMII, since those - * configurations modes don't use in-band autonegotiation. + * a managed property. Default to MLO_AN_INBAND rather than MLO_AN_PHY. + * Phylink will allow this to be overriden by a fixed link. We need to + * be careful and not enable this if we are using MII or RGMII, since + * those configurations modes don't use in-band autonegotiation. */ - fixed = of_get_child_by_name(mac_node, "fixed-link"); - if (!fixed && !of_property_read_bool(mac_node, "fixed-link") && - !of_property_read_bool(mac_node, "managed") && + if (!of_property_read_bool(mac_node, "managed") && mac_dev->phy_if != PHY_INTERFACE_MODE_MII && !phy_interface_mode_is_rgmii(mac_dev->phy_if)) - mac_dev->phylink_config.ovr_an_inband = true; - of_node_put(fixed); + mac_dev->phylink_config.default_an_inband = true; err = memac_init(mac_dev->fman_mac); if (err < 0) diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile index 8e9293e57bfd..e8af26da1fc1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/Makefile @@ -15,15 +15,14 @@ hns3-objs = hns3_enet.o hns3_ethtool.o hns3_debugfs.o hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o -obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o +obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o hclge-common.o -hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o \ - hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o +hclge-common-objs += hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o -obj-$(CONFIG_HNS3_HCLGE) += hclge.o +hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o + +obj-$(CONFIG_HNS3_HCLGE) += hclge.o hclge-common.o hclge-objs = hns3pf/hclge_main.o hns3pf/hclge_mdio.o hns3pf/hclge_tm.o hns3pf/hclge_regs.o \ hns3pf/hclge_mbx.o hns3pf/hclge_err.o hns3pf/hclge_debugfs.o hns3pf/hclge_ptp.o hns3pf/hclge_devlink.o \ - hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o - hclge-$(CONFIG_HNS3_DCB) += hns3pf/hclge_dcb.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c index ea40b594dbac..4ad4e8ab2f1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c @@ -48,6 +48,7 @@ void hclge_comm_cmd_reuse_desc(struct hclge_desc *desc, bool is_read) else desc->flag &= cpu_to_le16(~HCLGE_COMM_CMD_FLAG_WR); } +EXPORT_SYMBOL_GPL(hclge_comm_cmd_reuse_desc); static void hclge_comm_set_default_capability(struct hnae3_ae_dev *ae_dev, bool is_pf) @@ -72,6 +73,7 @@ void hclge_comm_cmd_setup_basic_desc(struct hclge_desc *desc, if (is_read) desc->flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_WR); } +EXPORT_SYMBOL_GPL(hclge_comm_cmd_setup_basic_desc); int hclge_comm_firmware_compat_config(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw, bool en) @@ -517,6 +519,7 @@ int hclge_comm_cmd_send(struct hclge_comm_hw *hw, struct hclge_desc *desc, return ret; } +EXPORT_SYMBOL_GPL(hclge_comm_cmd_send); static void hclge_comm_cmd_uninit_regs(struct hclge_comm_hw *hw) { @@ -553,6 +556,7 @@ void hclge_comm_cmd_uninit(struct hnae3_ae_dev *ae_dev, hclge_comm_free_cmd_desc(&cmdq->csq); hclge_comm_free_cmd_desc(&cmdq->crq); } +EXPORT_SYMBOL_GPL(hclge_comm_cmd_uninit); int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw) { @@ -591,6 +595,7 @@ err_csq: hclge_comm_free_cmd_desc(&hw->cmq.csq); return ret; } +EXPORT_SYMBOL_GPL(hclge_comm_cmd_queue_init); void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw, const struct hclge_comm_cmq_ops *ops) @@ -602,6 +607,7 @@ void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw, cmdq->ops.trace_cmd_get = ops->trace_cmd_get; } } +EXPORT_SYMBOL_GPL(hclge_comm_cmd_init_ops); int hclge_comm_cmd_init(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw, u32 *fw_version, bool is_pf, @@ -672,3 +678,8 @@ err_cmd_init: return ret; } +EXPORT_SYMBOL_GPL(hclge_comm_cmd_init); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("HNS3: Hisilicon Ethernet PF/VF Common Library"); +MODULE_AUTHOR("Huawei Tech. Co., Ltd."); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c index b4ae2160aff4..4e2bb6556b1c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c @@ -62,6 +62,7 @@ int hclge_comm_rss_init_cfg(struct hnae3_handle *nic, return 0; } +EXPORT_SYMBOL_GPL(hclge_comm_rss_init_cfg); void hclge_comm_get_rss_tc_info(u16 rss_size, u8 hw_tc_map, u16 *tc_offset, u16 *tc_valid, u16 *tc_size) @@ -78,6 +79,7 @@ void hclge_comm_get_rss_tc_info(u16 rss_size, u8 hw_tc_map, u16 *tc_offset, tc_offset[i] = (hw_tc_map & BIT(i)) ? rss_size * i : 0; } } +EXPORT_SYMBOL_GPL(hclge_comm_get_rss_tc_info); int hclge_comm_set_rss_tc_mode(struct hclge_comm_hw *hw, u16 *tc_offset, u16 *tc_valid, u16 *tc_size) @@ -113,6 +115,7 @@ int hclge_comm_set_rss_tc_mode(struct hclge_comm_hw *hw, u16 *tc_offset, return ret; } +EXPORT_SYMBOL_GPL(hclge_comm_set_rss_tc_mode); int hclge_comm_set_rss_hash_key(struct hclge_comm_rss_cfg *rss_cfg, struct hclge_comm_hw *hw, const u8 *key, @@ -143,6 +146,7 @@ int hclge_comm_set_rss_hash_key(struct hclge_comm_rss_cfg *rss_cfg, return 0; } +EXPORT_SYMBOL_GPL(hclge_comm_set_rss_hash_key); int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw, @@ -185,11 +189,13 @@ int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev, rss_cfg->rss_tuple_sets.ipv6_fragment_en = req->ipv6_fragment_en; return 0; } +EXPORT_SYMBOL_GPL(hclge_comm_set_rss_tuple); u32 hclge_comm_get_rss_key_size(struct hnae3_handle *handle) { return HCLGE_COMM_RSS_KEY_SIZE; } +EXPORT_SYMBOL_GPL(hclge_comm_get_rss_key_size); int hclge_comm_parse_rss_hfunc(struct hclge_comm_rss_cfg *rss_cfg, const u8 hfunc, u8 *hash_algo) @@ -217,6 +223,7 @@ void hclge_comm_rss_indir_init_cfg(struct hnae3_ae_dev *ae_dev, for (i = 0; i < ae_dev->dev_specs.rss_ind_tbl_size; i++) rss_cfg->rss_indirection_tbl[i] = i % rss_cfg->rss_size; } +EXPORT_SYMBOL_GPL(hclge_comm_rss_indir_init_cfg); int hclge_comm_get_rss_tuple(struct hclge_comm_rss_cfg *rss_cfg, int flow_type, u8 *tuple_sets) @@ -250,6 +257,7 @@ int hclge_comm_get_rss_tuple(struct hclge_comm_rss_cfg *rss_cfg, int flow_type, return 0; } +EXPORT_SYMBOL_GPL(hclge_comm_get_rss_tuple); static void hclge_comm_append_rss_msb_info(struct hclge_comm_rss_ind_tbl_cmd *req, @@ -304,6 +312,7 @@ int hclge_comm_set_rss_indir_table(struct hnae3_ae_dev *ae_dev, } return 0; } +EXPORT_SYMBOL_GPL(hclge_comm_set_rss_indir_table); int hclge_comm_set_rss_input_tuple(struct hclge_comm_hw *hw, struct hclge_comm_rss_cfg *rss_cfg) @@ -332,6 +341,7 @@ int hclge_comm_set_rss_input_tuple(struct hclge_comm_hw *hw, "failed to configure rss input, ret = %d.\n", ret); return ret; } +EXPORT_SYMBOL_GPL(hclge_comm_set_rss_input_tuple); void hclge_comm_get_rss_hash_info(struct hclge_comm_rss_cfg *rss_cfg, u8 *key, u8 *hfunc) @@ -355,6 +365,7 @@ void hclge_comm_get_rss_hash_info(struct hclge_comm_rss_cfg *rss_cfg, u8 *key, if (key) memcpy(key, rss_cfg->rss_hash_key, HCLGE_COMM_RSS_KEY_SIZE); } +EXPORT_SYMBOL_GPL(hclge_comm_get_rss_hash_info); void hclge_comm_get_rss_indir_tbl(struct hclge_comm_rss_cfg *rss_cfg, u32 *indir, u16 rss_ind_tbl_size) @@ -367,6 +378,7 @@ void hclge_comm_get_rss_indir_tbl(struct hclge_comm_rss_cfg *rss_cfg, for (i = 0; i < rss_ind_tbl_size; i++) indir[i] = rss_cfg->rss_indirection_tbl[i]; } +EXPORT_SYMBOL_GPL(hclge_comm_get_rss_indir_tbl); int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc, const u8 *key) @@ -408,6 +420,7 @@ int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc, return 0; } +EXPORT_SYMBOL_GPL(hclge_comm_set_rss_algo_key); static u8 hclge_comm_get_rss_hash_bits(struct ethtool_rxnfc *nfc) { @@ -502,3 +515,4 @@ u64 hclge_comm_convert_rss_tuple(u8 tuple_sets) return tuple_data; } +EXPORT_SYMBOL_GPL(hclge_comm_convert_rss_tuple); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index 618f66d9586b..2b31188ff555 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -26,6 +26,7 @@ u64 *hclge_comm_tqps_get_stats(struct hnae3_handle *handle, u64 *data) return buff; } +EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_stats); int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle) { @@ -33,6 +34,7 @@ int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle) return kinfo->num_tqps * HCLGE_COMM_QUEUE_PAIR_SIZE; } +EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_sset_count); u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data) { @@ -56,6 +58,7 @@ u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data) return buff; } +EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_strings); int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, struct hclge_comm_hw *hw) @@ -99,6 +102,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, return 0; } +EXPORT_SYMBOL_GPL(hclge_comm_tqps_update_stats); void hclge_comm_reset_tqp_stats(struct hnae3_handle *handle) { @@ -113,3 +117,4 @@ void hclge_comm_reset_tqp_stats(struct hnae3_handle *handle) memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats)); } } +EXPORT_SYMBOL_GPL(hclge_comm_reset_tqp_stats); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 5664f768cb0c..e4c5dc46dd42 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -3,16 +3,18 @@ # Makefile for Marvell's RVU Ethernet device drivers # -obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o -obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o +obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o otx2_devlink.o +obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o otx2_devlink.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ - otx2_devlink.o qos_sq.o qos.o -rvu_nicvf-y := otx2_vf.o otx2_devlink.o + qos_sq.o qos.o +rvu_nicvf-y := otx2_vf.o -rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o -rvu_nicvf-$(CONFIG_DCB) += otx2_dcbnl.o +ifdef CONFIG_DCB +obj-$(CONFIG_OCTEONTX2_PF) += otx2_dcbnl.o +obj-$(CONFIG_OCTEONTX2_VF) += otx2_dcbnl.o +endif rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index 28fb643d2917..0d7e611d9a05 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -54,6 +54,7 @@ int otx2_pfc_txschq_config(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL_GPL(otx2_pfc_txschq_config); static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio) { @@ -122,6 +123,7 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL_GPL(otx2_pfc_txschq_alloc); static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio) { @@ -260,6 +262,7 @@ update_sq_smq_map: return 0; } +EXPORT_SYMBOL_GPL(otx2_pfc_txschq_update); int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) { @@ -282,6 +285,7 @@ int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL_GPL(otx2_pfc_txschq_stop); int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf) { @@ -321,6 +325,7 @@ unlock: mutex_unlock(&pfvf->mbox.lock); return err; } +EXPORT_SYMBOL_GPL(otx2_config_priority_flow_ctrl); void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx, bool pfc_enable) @@ -385,6 +390,7 @@ out: "Updating BPIDs in CQ and Aura contexts of RQ%d failed with err %d\n", qidx, err); } +EXPORT_SYMBOL_GPL(otx2_update_bpid_in_rqctx); static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) { @@ -472,3 +478,8 @@ int otx2_dcbnl_set_ops(struct net_device *dev) return 0; } +EXPORT_SYMBOL_GPL(otx2_dcbnl_set_ops); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Marvell RVU dcbnl"); +MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>"); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 99ddf31269d9..440f574d1195 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -113,6 +113,7 @@ err_dl: devlink_free(dl); return err; } +EXPORT_SYMBOL_GPL(otx2_register_dl); void otx2_unregister_dl(struct otx2_nic *pfvf) { @@ -124,3 +125,8 @@ void otx2_unregister_dl(struct otx2_nic *pfvf) ARRAY_SIZE(otx2_dl_params)); devlink_free(dl); } +EXPORT_SYMBOL_GPL(otx2_unregister_dl); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Marvell RVU PF/VF Netdev Devlink"); +MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>"); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 1184ac5751e1..461cc2c79c71 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -126,6 +126,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, cq_idx = cq_idx % priv->rx_ring_num; rx_cq = priv->rx_cq[cq_idx]; cq->vector = rx_cq->vector; + irq = mlx4_eq_get_irq(mdev->dev, cq->vector); } if (cq->type == RX) @@ -142,18 +143,23 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, if (err) goto free_eq; + cq->cq_idx = cq_idx; cq->mcq.event = mlx4_en_cq_event; switch (cq->type) { case TX: cq->mcq.comp = mlx4_en_tx_irq; netif_napi_add_tx(cq->dev, &cq->napi, mlx4_en_poll_tx_cq); + netif_napi_set_irq(&cq->napi, irq); napi_enable(&cq->napi); + netif_queue_set_napi(cq->dev, cq_idx, NETDEV_QUEUE_TYPE_TX, &cq->napi); break; case RX: cq->mcq.comp = mlx4_en_rx_irq; netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq); + netif_napi_set_irq(&cq->napi, irq); napi_enable(&cq->napi); + netif_queue_set_napi(cq->dev, cq_idx, NETDEV_QUEUE_TYPE_RX, &cq->napi); break; case TX_XDP: /* nothing regarding napi, it's shared with rx ring */ @@ -189,6 +195,14 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq) void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) { if (cq->type != TX_XDP) { + enum netdev_queue_type qtype; + + if (cq->type == RX) + qtype = NETDEV_QUEUE_TYPE_RX; + else + qtype = NETDEV_QUEUE_TYPE_TX; + + netif_queue_set_napi(cq->dev, cq->cq_idx, qtype, NULL); napi_disable(&cq->napi); netif_napi_del(&cq->napi); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 4c089cfa027a..281b34af0bb4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -43,6 +43,7 @@ #include <net/vxlan.h> #include <net/devlink.h> #include <net/rps.h> +#include <net/netdev_queues.h> #include <linux/mlx4/driver.h> #include <linux/mlx4/device.h> @@ -2073,6 +2074,7 @@ static void mlx4_en_clear_stats(struct net_device *dev) priv->rx_ring[i]->csum_ok = 0; priv->rx_ring[i]->csum_none = 0; priv->rx_ring[i]->csum_complete = 0; + priv->rx_ring[i]->alloc_fail = 0; } } @@ -3099,6 +3101,77 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, last_i += NUM_PHY_STATS; } +static void mlx4_get_queue_stats_rx(struct net_device *dev, int i, + struct netdev_queue_stats_rx *stats) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + const struct mlx4_en_rx_ring *ring; + + spin_lock_bh(&priv->stats_lock); + + if (!priv->port_up || mlx4_is_master(priv->mdev->dev)) + goto out_unlock; + + ring = priv->rx_ring[i]; + stats->packets = READ_ONCE(ring->packets); + stats->bytes = READ_ONCE(ring->bytes); + stats->alloc_fail = READ_ONCE(ring->alloc_fail); + +out_unlock: + spin_unlock_bh(&priv->stats_lock); +} + +static void mlx4_get_queue_stats_tx(struct net_device *dev, int i, + struct netdev_queue_stats_tx *stats) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + const struct mlx4_en_tx_ring *ring; + + spin_lock_bh(&priv->stats_lock); + + if (!priv->port_up || mlx4_is_master(priv->mdev->dev)) + goto out_unlock; + + ring = priv->tx_ring[TX][i]; + stats->packets = READ_ONCE(ring->packets); + stats->bytes = READ_ONCE(ring->bytes); + +out_unlock: + spin_unlock_bh(&priv->stats_lock); +} + +static void mlx4_get_base_stats(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + + spin_lock_bh(&priv->stats_lock); + + if (!priv->port_up || mlx4_is_master(priv->mdev->dev)) + goto out_unlock; + + if (priv->rx_ring_num) { + rx->packets = 0; + rx->bytes = 0; + rx->alloc_fail = 0; + } + + if (priv->tx_ring_num[TX]) { + tx->packets = 0; + tx->bytes = 0; + } + +out_unlock: + spin_unlock_bh(&priv->stats_lock); +} + +static const struct netdev_stat_ops mlx4_stat_ops = { + .get_queue_stats_rx = mlx4_get_queue_stats_rx, + .get_queue_stats_tx = mlx4_get_queue_stats_tx, + .get_base_stats = mlx4_get_base_stats, +}; + int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, struct mlx4_en_port_profile *prof) { @@ -3262,6 +3335,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]); netif_set_real_num_rx_queues(dev, priv->rx_ring_num); + dev->stat_ops = &mlx4_stat_ops; dev->ethtool_ops = &mlx4_en_ethtool_ops; /* diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 8328df8645d5..15c57e9517e9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -82,8 +82,10 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, for (i = 0; i < priv->num_frags; i++, frags++) { if (!frags->page) { - if (mlx4_alloc_page(priv, frags, gfp)) + if (mlx4_alloc_page(priv, frags, gfp)) { + ring->alloc_fail++; return -ENOMEM; + } ring->rx_alloc_pages++; } rx_desc->data[i].addr = cpu_to_be64(frags->dma + diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 98688e4dbec5..febeadfdd5a5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -169,12 +169,6 @@ module_param_array(port_type_array, int, &arr_argc, 0444); MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default " "1 for IB, 2 for Ethernet"); -struct mlx4_port_config { - struct list_head list; - enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1]; - struct pci_dev *pdev; -}; - static atomic_t pf_loading = ATOMIC_INIT(0); static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id, diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index efe3f97b874f..28b70dcc652e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -355,6 +355,7 @@ struct mlx4_en_rx_ring { unsigned long xdp_tx; unsigned long xdp_tx_full; unsigned long dropped; + unsigned long alloc_fail; int hwtstamp_rx_filter; cpumask_var_t affinity_mask; struct xdp_rxq_info xdp_rxq; @@ -379,6 +380,7 @@ struct mlx4_en_cq { #define MLX4_EN_OPCODE_ERROR 0x1e const struct cpumask *aff_mask; + int cq_idx; }; struct mlx4_en_port_profile { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index c3ae11a48024..59e5a9f21105 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -220,7 +220,7 @@ static int netdev_show(struct seq_file *seq, void *v) { struct net_device *netdev = seq->private; - seq_printf(seq, "%s\n", netdev->name); + seq_printf(seq, "%s\n", netdev_name(netdev)); return 0; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h index 9a1825edf0d0..9c85c0706c6e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_if.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -71,7 +71,7 @@ enum ionic_cmd_opcode { IONIC_CMD_FW_CONTROL_V1 = 255, }; -/** +/* * enum ionic_status_code - Device command return codes */ enum ionic_status_code { @@ -112,6 +112,7 @@ enum ionic_notifyq_opcode { /** * struct ionic_admin_cmd - General admin command format * @opcode: Opcode for the command + * @rsvd: reserved byte(s) * @lif_index: LIF index * @cmd_data: Opcode-specific command bytes */ @@ -125,6 +126,7 @@ struct ionic_admin_cmd { /** * struct ionic_admin_comp - General admin command completion format * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion * @cmd_data: Command-specific bytes * @color: Color bit (Always 0 for commands issued to the @@ -147,6 +149,7 @@ static inline u8 color_match(u8 color, u8 done_color) /** * struct ionic_nop_cmd - NOP command * @opcode: opcode + * @rsvd: reserved byte(s) */ struct ionic_nop_cmd { u8 opcode; @@ -156,6 +159,7 @@ struct ionic_nop_cmd { /** * struct ionic_nop_comp - NOP command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) */ struct ionic_nop_comp { u8 status; @@ -166,6 +170,7 @@ struct ionic_nop_comp { * struct ionic_dev_init_cmd - Device init command * @opcode: opcode * @type: Device type + * @rsvd: reserved byte(s) */ struct ionic_dev_init_cmd { u8 opcode; @@ -176,6 +181,7 @@ struct ionic_dev_init_cmd { /** * struct ionic_dev_init_comp - Device init command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) */ struct ionic_dev_init_comp { u8 status; @@ -185,6 +191,7 @@ struct ionic_dev_init_comp { /** * struct ionic_dev_reset_cmd - Device reset command * @opcode: opcode + * @rsvd: reserved byte(s) */ struct ionic_dev_reset_cmd { u8 opcode; @@ -194,6 +201,7 @@ struct ionic_dev_reset_cmd { /** * struct ionic_dev_reset_comp - Reset command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) */ struct ionic_dev_reset_comp { u8 status; @@ -207,6 +215,7 @@ struct ionic_dev_reset_comp { * struct ionic_dev_identify_cmd - Driver/device identify command * @opcode: opcode * @ver: Highest version of identify supported by driver + * @rsvd: reserved byte(s) */ struct ionic_dev_identify_cmd { u8 opcode; @@ -218,6 +227,7 @@ struct ionic_dev_identify_cmd { * struct ionic_dev_identify_comp - Driver/device identify command completion * @status: Status of the command (enum ionic_status_code) * @ver: Version of identify returned by device + * @rsvd: reserved byte(s) */ struct ionic_dev_identify_comp { u8 status; @@ -242,6 +252,7 @@ enum ionic_os_type { * @kernel_ver: Kernel version, numeric format * @kernel_ver_str: Kernel version, string format * @driver_ver_str: Driver version, string format + * @words: word access to struct contents */ union ionic_drv_identity { struct { @@ -267,7 +278,9 @@ enum ionic_dev_capability { * union ionic_dev_identity - device identity information * @version: Version of device identify * @type: Identify type (0 for now) + * @rsvd: reserved byte(s) * @nports: Number of ports provisioned + * @rsvd2: reserved byte(s) * @nlifs: Number of LIFs provisioned * @nintrs: Number of interrupts provisioned * @ndbpgs_per_lif: Number of doorbell pages per LIF @@ -284,6 +297,7 @@ enum ionic_dev_capability { * @hwstamp_mult: Hardware tick to nanosecond multiplier. * @hwstamp_shift: Hardware tick to nanosecond divisor (power of two). * @capabilities: Device capabilities + * @words: word access to struct contents */ union ionic_dev_identity { struct { @@ -317,6 +331,7 @@ enum ionic_lif_type { * @opcode: opcode * @type: LIF type (enum ionic_lif_type) * @ver: Version of identify returned by device + * @rsvd: reserved byte(s) */ struct ionic_lif_identify_cmd { u8 opcode; @@ -329,6 +344,7 @@ struct ionic_lif_identify_cmd { * struct ionic_lif_identify_comp - LIF identify command completion * @status: Status of the command (enum ionic_status_code) * @ver: Version of identify returned by device + * @rsvd2: reserved byte(s) */ struct ionic_lif_identify_comp { u8 status; @@ -416,7 +432,7 @@ enum ionic_txq_feature { }; /** - * struct ionic_hwstamp_bits - Hardware timestamp decoding bits + * enum ionic_hwstamp_bits - Hardware timestamp decoding bits * @IONIC_HWSTAMP_INVALID: Invalid hardware timestamp value * @IONIC_HWSTAMP_CQ_NEGOFFSET: Timestamp field negative offset * from the base cq descriptor. @@ -429,6 +445,7 @@ enum ionic_hwstamp_bits { /** * struct ionic_lif_logical_qtype - Descriptor of logical to HW queue type * @qtype: Hardware Queue Type + * @rsvd: reserved byte(s) * @qid_count: Number of Queue IDs of the logical type * @qid_base: Minimum Queue ID of the logical type */ @@ -454,12 +471,14 @@ enum ionic_lif_state { /** * union ionic_lif_config - LIF configuration * @state: LIF state (enum ionic_lif_state) + * @rsvd: reserved byte(s) * @name: LIF name * @mtu: MTU * @mac: Station MAC address * @vlan: Default Vlan ID * @features: Features (enum ionic_eth_hw_features) * @queue_count: Queue counts per queue-type + * @words: word access to struct contents */ union ionic_lif_config { struct { @@ -481,33 +500,39 @@ union ionic_lif_config { * @capabilities: LIF capabilities * * @eth: Ethernet identify structure - * @version: Ethernet identify structure version - * @max_ucast_filters: Number of perfect unicast addresses supported - * @max_mcast_filters: Number of perfect multicast addresses supported - * @min_frame_size: Minimum size of frames to be sent - * @max_frame_size: Maximum size of frames to be sent - * @hwstamp_tx_modes: Bitmask of BIT_ULL(enum ionic_txstamp_mode) - * @hwstamp_rx_filters: Bitmask of enum ionic_pkt_class - * @config: LIF config struct with features, mtu, mac, q counts + * @eth.version: Ethernet identify structure version + * @eth.rsvd: reserved byte(s) + * @eth.max_ucast_filters: Number of perfect unicast addresses supported + * @eth.max_mcast_filters: Number of perfect multicast addresses supported + * @eth.min_frame_size: Minimum size of frames to be sent + * @eth.max_frame_size: Maximum size of frames to be sent + * @eth.rsvd2: reserved byte(s) + * @eth.hwstamp_tx_modes: Bitmask of BIT_ULL(enum ionic_txstamp_mode) + * @eth.hwstamp_rx_filters: Bitmask of enum ionic_pkt_class + * @eth.rsvd3: reserved byte(s) + * @eth.config: LIF config struct with features, mtu, mac, q counts * * @rdma: RDMA identify structure - * @version: RDMA version of opcodes and queue descriptors - * @qp_opcodes: Number of RDMA queue pair opcodes supported - * @admin_opcodes: Number of RDMA admin opcodes supported - * @npts_per_lif: Page table size per LIF - * @nmrs_per_lif: Number of memory regions per LIF - * @nahs_per_lif: Number of address handles per LIF - * @max_stride: Max work request stride - * @cl_stride: Cache line stride - * @pte_stride: Page table entry stride - * @rrq_stride: Remote RQ work request stride - * @rsq_stride: Remote SQ work request stride - * @dcqcn_profiles: Number of DCQCN profiles - * @aq_qtype: RDMA Admin Qtype - * @sq_qtype: RDMA Send Qtype - * @rq_qtype: RDMA Receive Qtype - * @cq_qtype: RDMA Completion Qtype - * @eq_qtype: RDMA Event Qtype + * @rdma.version: RDMA version of opcodes and queue descriptors + * @rdma.qp_opcodes: Number of RDMA queue pair opcodes supported + * @rdma.admin_opcodes: Number of RDMA admin opcodes supported + * @rdma.rsvd: reserved byte(s) + * @rdma.npts_per_lif: Page table size per LIF + * @rdma.nmrs_per_lif: Number of memory regions per LIF + * @rdma.nahs_per_lif: Number of address handles per LIF + * @rdma.max_stride: Max work request stride + * @rdma.cl_stride: Cache line stride + * @rdma.pte_stride: Page table entry stride + * @rdma.rrq_stride: Remote RQ work request stride + * @rdma.rsq_stride: Remote SQ work request stride + * @rdma.dcqcn_profiles: Number of DCQCN profiles + * @rdma.rsvd_dimensions: reserved byte(s) + * @rdma.aq_qtype: RDMA Admin Qtype + * @rdma.sq_qtype: RDMA Send Qtype + * @rdma.rq_qtype: RDMA Receive Qtype + * @rdma.cq_qtype: RDMA Completion Qtype + * @rdma.eq_qtype: RDMA Event Qtype + * @words: word access to struct contents */ union ionic_lif_identity { struct { @@ -558,7 +583,9 @@ union ionic_lif_identity { * @opcode: Opcode * @type: LIF type (enum ionic_lif_type) * @index: LIF index + * @rsvd: reserved byte(s) * @info_pa: Destination address for LIF info (struct ionic_lif_info) + * @rsvd2: reserved byte(s) */ struct ionic_lif_init_cmd { u8 opcode; @@ -572,7 +599,9 @@ struct ionic_lif_init_cmd { /** * struct ionic_lif_init_comp - LIF init command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @hw_index: Hardware index of the initialized LIF + * @rsvd2: reserved byte(s) */ struct ionic_lif_init_comp { u8 status; @@ -584,9 +613,11 @@ struct ionic_lif_init_comp { /** * struct ionic_q_identify_cmd - queue identify command * @opcode: opcode + * @rsvd: reserved byte(s) * @lif_type: LIF type (enum ionic_lif_type) * @type: Logical queue type (enum ionic_logical_qtype) * @ver: Highest queue type version that the driver supports + * @rsvd2: reserved byte(s) */ struct ionic_q_identify_cmd { u8 opcode; @@ -600,8 +631,10 @@ struct ionic_q_identify_cmd { /** * struct ionic_q_identify_comp - queue identify command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion * @ver: Queue type version that can be used with FW + * @rsvd2: reserved byte(s) */ struct ionic_q_identify_comp { u8 status; @@ -615,12 +648,14 @@ struct ionic_q_identify_comp { * union ionic_q_identity - queue identity information * @version: Queue type version that can be used with FW * @supported: Bitfield of queue versions, first bit = ver 0 + * @rsvd: reserved byte(s) * @features: Queue features (enum ionic_q_feature, etc) * @desc_sz: Descriptor size * @comp_sz: Completion descriptor size * @sg_desc_sz: Scatter/Gather descriptor size * @max_sg_elems: Maximum number of Scatter/Gather elements * @sg_desc_stride: Number of Scatter/Gather elements per descriptor + * @words: word access to struct contents */ union ionic_q_identity { struct { @@ -640,8 +675,10 @@ union ionic_q_identity { /** * struct ionic_q_init_cmd - Queue init command * @opcode: opcode + * @rsvd: reserved byte(s) * @type: Logical queue type * @ver: Queue type version + * @rsvd1: reserved byte(s) * @lif_index: LIF index * @index: (LIF, qtype) relative admin queue index * @intr_index: Interrupt control register index, or Event queue index @@ -667,6 +704,7 @@ union ionic_q_identity { * @ring_base: Queue ring base address * @cq_ring_base: Completion queue ring base address * @sg_ring_base: Scatter/Gather ring base address + * @rsvd2: reserved byte(s) * @features: Mask of queue features to enable, if not in the flags above. */ struct ionic_q_init_cmd { @@ -698,9 +736,11 @@ struct ionic_q_init_cmd { /** * struct ionic_q_init_comp - Queue init command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion * @hw_index: Hardware Queue ID * @hw_type: Hardware Queue type + * @rsvd2: reserved byte(s) * @color: Color */ struct ionic_q_init_comp { @@ -800,7 +840,7 @@ enum ionic_txq_desc_opcode { * will set CWR flag in the first segment if * CWR is set in the template header, and * clear CWR in remaining segments. - * @flags: + * flags: * vlan: * Insert an L2 VLAN header using @vlan_tci * encap: @@ -813,13 +853,14 @@ enum ionic_txq_desc_opcode { * TSO start * tso_eot: * TSO end - * @num_sg_elems: Number of scatter-gather elements in SG + * num_sg_elems: Number of scatter-gather elements in SG * descriptor - * @addr: First data buffer's DMA address + * addr: First data buffer's DMA address * (Subsequent data buffers are on txq_sg_desc) * @len: First data buffer's length, in bytes * @vlan_tci: VLAN tag to insert in the packet (if requested * by @V-bit). Includes .1p and .1q tags + * @hword0: half word padding * @hdr_len: Length of packet headers, including * encapsulating outer header, if applicable * Valid for opcodes IONIC_TXQ_DESC_OPCODE_CALC_CSUM and @@ -830,10 +871,12 @@ enum ionic_txq_desc_opcode { * IONIC_TXQ_DESC_OPCODE_TSO, @hdr_len is up to * inner-most L4 payload, so inclusive of * inner-most L4 header. + * @hword1: half word padding * @mss: Desired MSS value for TSO; only applicable for * IONIC_TXQ_DESC_OPCODE_TSO * @csum_start: Offset from packet to first byte checked in L4 checksum * @csum_offset: Offset from csum_start to L4 checksum field + * @hword2: half word padding */ struct ionic_txq_desc { __le64 cmd; @@ -901,6 +944,7 @@ static inline void decode_txq_desc_cmd(u64 cmd, u8 *opcode, u8 *flags, * struct ionic_txq_sg_elem - Transmit scatter-gather (SG) descriptor element * @addr: DMA address of SG element data buffer * @len: Length of SG element data buffer, in bytes + * @rsvd: reserved byte(s) */ struct ionic_txq_sg_elem { __le64 addr; @@ -927,7 +971,9 @@ struct ionic_txq_sg_desc_v1 { /** * struct ionic_txq_comp - Ethernet transmit queue completion descriptor * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion + * @rsvd2: reserved byte(s) * @color: Color bit */ struct ionic_txq_comp { @@ -953,6 +999,7 @@ enum ionic_rxq_desc_opcode { * receive, including actual bytes received, * are recorded in Rx completion descriptor. * + * @rsvd: reserved byte(s) * @len: Data buffer's length, in bytes * @addr: Data buffer's DMA address */ @@ -967,6 +1014,7 @@ struct ionic_rxq_desc { * struct ionic_rxq_sg_elem - Receive scatter-gather (SG) descriptor element * @addr: DMA address of SG element data buffer * @len: Length of SG element data buffer, in bytes + * @rsvd: reserved byte(s) */ struct ionic_rxq_sg_elem { __le64 addr; @@ -1170,6 +1218,7 @@ enum ionic_pkt_class { * @lif_index: LIF index * @index: Queue index * @oper: Operation (enum ionic_q_control_oper) + * @rsvd: reserved byte(s) */ struct ionic_q_control_cmd { u8 opcode; @@ -1182,7 +1231,7 @@ struct ionic_q_control_cmd { typedef struct ionic_admin_comp ionic_q_control_comp; -enum q_control_oper { +enum ionic_q_control_oper { IONIC_Q_DISABLE = 0, IONIC_Q_ENABLE = 1, IONIC_Q_HANG_RESET = 2, @@ -1216,7 +1265,7 @@ enum ionic_xcvr_state { IONIC_XCVR_STATE_SPROM_READ_ERR = 4, }; -/** +/* * enum ionic_xcvr_pid - Supported link modes */ enum ionic_xcvr_pid { @@ -1351,6 +1400,7 @@ struct ionic_xcvr_status { * @fec_type: fec type (enum ionic_port_fec_type) * @pause_type: pause type (enum ionic_port_pause_type) * @loopback_mode: loopback mode (enum ionic_port_loopback_mode) + * @words: word access to struct contents */ union ionic_port_config { struct { @@ -1382,6 +1432,7 @@ union ionic_port_config { * @speed: link speed (in Mbps) * @link_down_count: number of times link went from up to down * @fec_type: fec type (enum ionic_port_fec_type) + * @rsvd: reserved byte(s) * @xcvr: transceiver status */ struct ionic_port_status { @@ -1399,6 +1450,7 @@ struct ionic_port_status { * @opcode: opcode * @index: port index * @ver: Highest version of identify supported by driver + * @rsvd: reserved byte(s) */ struct ionic_port_identify_cmd { u8 opcode; @@ -1411,6 +1463,7 @@ struct ionic_port_identify_cmd { * struct ionic_port_identify_comp - Port identify command completion * @status: Status of the command (enum ionic_status_code) * @ver: Version of identify returned by device + * @rsvd: reserved byte(s) */ struct ionic_port_identify_comp { u8 status; @@ -1422,7 +1475,9 @@ struct ionic_port_identify_comp { * struct ionic_port_init_cmd - Port initialization command * @opcode: opcode * @index: port index + * @rsvd: reserved byte(s) * @info_pa: destination address for port info (struct ionic_port_info) + * @rsvd2: reserved byte(s) */ struct ionic_port_init_cmd { u8 opcode; @@ -1435,6 +1490,7 @@ struct ionic_port_init_cmd { /** * struct ionic_port_init_comp - Port initialization command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) */ struct ionic_port_init_comp { u8 status; @@ -1445,6 +1501,7 @@ struct ionic_port_init_comp { * struct ionic_port_reset_cmd - Port reset command * @opcode: opcode * @index: port index + * @rsvd: reserved byte(s) */ struct ionic_port_reset_cmd { u8 opcode; @@ -1455,6 +1512,7 @@ struct ionic_port_reset_cmd { /** * struct ionic_port_reset_comp - Port reset command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) */ struct ionic_port_reset_comp { u8 status; @@ -1510,6 +1568,7 @@ enum ionic_port_attr { * @opcode: Opcode * @index: Port index * @attr: Attribute type (enum ionic_port_attr) + * @rsvd: reserved byte(s) * @state: Port state * @speed: Port speed * @mtu: Port MTU @@ -1518,6 +1577,7 @@ enum ionic_port_attr { * @pause_type: Port pause type setting * @loopback_mode: Port loopback mode * @stats_ctl: Port stats setting + * @rsvd2: reserved byte(s) */ struct ionic_port_setattr_cmd { u8 opcode; @@ -1540,6 +1600,7 @@ struct ionic_port_setattr_cmd { /** * struct ionic_port_setattr_comp - Port set attr command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @color: Color bit */ struct ionic_port_setattr_comp { @@ -1553,6 +1614,7 @@ struct ionic_port_setattr_comp { * @opcode: Opcode * @index: port index * @attr: Attribute type (enum ionic_port_attr) + * @rsvd: reserved byte(s) */ struct ionic_port_getattr_cmd { u8 opcode; @@ -1564,6 +1626,7 @@ struct ionic_port_getattr_cmd { /** * struct ionic_port_getattr_comp - Port get attr command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @state: Port state * @speed: Port speed * @mtu: Port MTU @@ -1571,6 +1634,7 @@ struct ionic_port_getattr_cmd { * @fec_type: Port FEC type setting * @pause_type: Port pause type setting * @loopback_mode: Port loopback mode + * @rsvd2: reserved byte(s) * @color: Color bit */ struct ionic_port_getattr_comp { @@ -1593,9 +1657,11 @@ struct ionic_port_getattr_comp { * struct ionic_lif_status - LIF status register * @eid: most recent NotifyQ event id * @port_num: port the LIF is connected to + * @rsvd: reserved byte(s) * @link_status: port status (enum ionic_port_oper_status) * @link_speed: speed of link in Mbps * @link_down_count: number of times link went from up to down + * @rsvd2: reserved byte(s) */ struct ionic_lif_status { __le64 eid; @@ -1610,7 +1676,9 @@ struct ionic_lif_status { /** * struct ionic_lif_reset_cmd - LIF reset command * @opcode: opcode + * @rsvd: reserved byte(s) * @index: LIF index + * @rsvd2: reserved byte(s) */ struct ionic_lif_reset_cmd { u8 opcode; @@ -1643,9 +1711,11 @@ enum ionic_dev_attr { * struct ionic_dev_setattr_cmd - Set Device attributes on the NIC * @opcode: Opcode * @attr: Attribute type (enum ionic_dev_attr) + * @rsvd: reserved byte(s) * @state: Device state (enum ionic_dev_state) * @name: The bus info, e.g. PCI slot-device-function, 0 terminated * @features: Device features + * @rsvd2: reserved byte(s) */ struct ionic_dev_setattr_cmd { u8 opcode; @@ -1662,7 +1732,9 @@ struct ionic_dev_setattr_cmd { /** * struct ionic_dev_setattr_comp - Device set attr command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @features: Device features + * @rsvd2: reserved byte(s) * @color: Color bit */ struct ionic_dev_setattr_comp { @@ -1679,6 +1751,7 @@ struct ionic_dev_setattr_comp { * struct ionic_dev_getattr_cmd - Get Device attributes from the NIC * @opcode: opcode * @attr: Attribute type (enum ionic_dev_attr) + * @rsvd: reserved byte(s) */ struct ionic_dev_getattr_cmd { u8 opcode; @@ -1687,9 +1760,11 @@ struct ionic_dev_getattr_cmd { }; /** - * struct ionic_dev_setattr_comp - Device set attr command completion + * struct ionic_dev_getattr_comp - Device set attr command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @features: Device features + * @rsvd2: reserved byte(s) * @color: Color bit */ struct ionic_dev_getattr_comp { @@ -1702,7 +1777,7 @@ struct ionic_dev_getattr_comp { u8 color; }; -/** +/* * RSS parameters */ #define IONIC_RSS_HASH_KEY_SIZE 40 @@ -1726,6 +1801,7 @@ enum ionic_rss_hash_types { * @IONIC_LIF_ATTR_RSS: LIF RSS attribute * @IONIC_LIF_ATTR_STATS_CTRL: LIF statistics control attribute * @IONIC_LIF_ATTR_TXSTAMP: LIF TX timestamping mode + * @IONIC_LIF_ATTR_MAX: maximum attribute value */ enum ionic_lif_attr { IONIC_LIF_ATTR_STATE = 0, @@ -1736,6 +1812,7 @@ enum ionic_lif_attr { IONIC_LIF_ATTR_RSS = 5, IONIC_LIF_ATTR_STATS_CTRL = 6, IONIC_LIF_ATTR_TXSTAMP = 7, + IONIC_LIF_ATTR_MAX = 255, }; /** @@ -1749,11 +1826,13 @@ enum ionic_lif_attr { * @mac: Station mac * @features: Features (enum ionic_eth_hw_features) * @rss: RSS properties - * @types: The hash types to enable (see rss_hash_types) - * @key: The hash secret key - * @addr: Address for the indirection table shared memory + * @rss.types: The hash types to enable (see rss_hash_types) + * @rss.key: The hash secret key + * @rss.rsvd: reserved byte(s) + * @rss.addr: Address for the indirection table shared memory * @stats_ctl: stats control commands (enum ionic_stats_ctl_cmd) - * @txstamp: TX Timestamping Mode (enum ionic_txstamp_mode) + * @txstamp_mode: TX Timestamping Mode (enum ionic_txstamp_mode) + * @rsvd: reserved byte(s) */ struct ionic_lif_setattr_cmd { u8 opcode; @@ -1772,7 +1851,7 @@ struct ionic_lif_setattr_cmd { __le64 addr; } rss; u8 stats_ctl; - __le16 txstamp_mode; + __le16 txstamp_mode; u8 rsvd[60]; } __packed; }; @@ -1780,8 +1859,10 @@ struct ionic_lif_setattr_cmd { /** * struct ionic_lif_setattr_comp - LIF set attr command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion * @features: features (enum ionic_eth_hw_features) + * @rsvd2: reserved byte(s) * @color: Color bit */ struct ionic_lif_setattr_comp { @@ -1800,6 +1881,7 @@ struct ionic_lif_setattr_comp { * @opcode: Opcode * @attr: Attribute type (enum ionic_lif_attr) * @index: LIF index + * @rsvd: reserved byte(s) */ struct ionic_lif_getattr_cmd { u8 opcode; @@ -1811,13 +1893,14 @@ struct ionic_lif_getattr_cmd { /** * struct ionic_lif_getattr_comp - LIF get attr command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion * @state: LIF state (enum ionic_lif_state) - * @name: The netdev name string, 0 terminated * @mtu: Mtu * @mac: Station mac * @features: Features (enum ionic_eth_hw_features) - * @txstamp: TX Timestamping Mode (enum ionic_txstamp_mode) + * @txstamp_mode: TX Timestamping Mode (enum ionic_txstamp_mode) + * @rsvd2: reserved byte(s) * @color: Color bit */ struct ionic_lif_getattr_comp { @@ -1838,12 +1921,15 @@ struct ionic_lif_getattr_comp { /** * struct ionic_lif_setphc_cmd - Set LIF PTP Hardware Clock * @opcode: Opcode + * @rsvd1: reserved byte(s) * @lif_index: LIF index + * @rsvd2: reserved byte(s) * @tick: Hardware stamp tick of an instant in time. * @nsec: Nanosecond stamp of the same instant. * @frac: Fractional nanoseconds at the same instant. * @mult: Cycle to nanosecond multiplier. * @shift: Cycle to nanosecond divisor (power of two). + * @rsvd3: reserved byte(s) */ struct ionic_lif_setphc_cmd { u8 opcode; @@ -1870,6 +1956,7 @@ enum ionic_rx_mode { /** * struct ionic_rx_mode_set_cmd - Set LIF's Rx mode command * @opcode: opcode + * @rsvd: reserved byte(s) * @lif_index: LIF index * @rx_mode: Rx mode flags: * IONIC_RX_MODE_F_UNICAST: Accept known unicast packets @@ -1878,6 +1965,7 @@ enum ionic_rx_mode { * IONIC_RX_MODE_F_PROMISC: Accept any packets * IONIC_RX_MODE_F_ALLMULTI: Accept any multicast packets * IONIC_RX_MODE_F_RDMA_SNIFFER: Sniff RDMA packets + * @rsvd2: reserved byte(s) */ struct ionic_rx_mode_set_cmd { u8 opcode; @@ -1904,13 +1992,14 @@ enum ionic_rx_filter_match_type { * @qid: Queue ID * @match: Rx filter match type (see IONIC_RX_FILTER_MATCH_xxx) * @vlan: VLAN filter - * @vlan: VLAN ID + * @vlan.vlan: VLAN ID * @mac: MAC filter - * @addr: MAC address (network-byte order) + * @mac.addr: MAC address (network-byte order) * @mac_vlan: MACVLAN filter - * @vlan: VLAN ID - * @addr: MAC address (network-byte order) + * @mac_vlan.vlan: VLAN ID + * @mac_vlan.addr: MAC address (network-byte order) * @pkt_class: Packet classification filter + * @rsvd: reserved byte(s) */ struct ionic_rx_filter_add_cmd { u8 opcode; @@ -1937,8 +2026,10 @@ struct ionic_rx_filter_add_cmd { /** * struct ionic_rx_filter_add_comp - Add LIF Rx filter command completion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion * @filter_id: Filter ID + * @rsvd2: reserved byte(s) * @color: Color bit */ struct ionic_rx_filter_add_comp { @@ -1953,8 +2044,10 @@ struct ionic_rx_filter_add_comp { /** * struct ionic_rx_filter_del_cmd - Delete LIF Rx filter command * @opcode: opcode + * @rsvd: reserved byte(s) * @lif_index: LIF index * @filter_id: Filter ID + * @rsvd2: reserved byte(s) */ struct ionic_rx_filter_del_cmd { u8 opcode; @@ -2000,6 +2093,7 @@ enum ionic_vf_link_status { * @trust: enable VF trust * @linkstate: set link up or down * @stats_pa: set DMA address for VF stats + * @pad: reserved byte(s) */ struct ionic_vf_setattr_cmd { u8 opcode; @@ -2031,6 +2125,7 @@ struct ionic_vf_setattr_comp { * @opcode: Opcode * @attr: Attribute type (enum ionic_vf_attr) * @vf_index: VF index + * @rsvd: reserved byte(s) */ struct ionic_vf_getattr_cmd { u8 opcode; @@ -2064,8 +2159,8 @@ enum ionic_vf_ctrl_opcode { /** * struct ionic_vf_ctrl_cmd - VF control command * @opcode: Opcode for the command - * @vf_index: VF Index. It is unused if op START_ALL is used. * @ctrl_opcode: VF control operation type + * @vf_index: VF Index. It is unused if op START_ALL is used. */ struct ionic_vf_ctrl_cmd { u8 opcode; @@ -2089,7 +2184,7 @@ struct ionic_vf_ctrl_comp { * struct ionic_qos_identify_cmd - QoS identify command * @opcode: opcode * @ver: Highest version of identify supported by driver - * + * @rsvd: reserved byte(s) */ struct ionic_qos_identify_cmd { u8 opcode; @@ -2101,6 +2196,7 @@ struct ionic_qos_identify_cmd { * struct ionic_qos_identify_comp - QoS identify command completion * @status: Status of the command (enum ionic_status_code) * @ver: Version of identify returned by device + * @rsvd: reserved byte(s) */ struct ionic_qos_identify_comp { u8 status; @@ -2118,7 +2214,7 @@ struct ionic_qos_identify_comp { #define IONIC_QOS_ALL_PCP 0xFF #define IONIC_DSCP_BLOCK_SIZE 8 -/** +/* * enum ionic_qos_class */ enum ionic_qos_class { @@ -2174,6 +2270,7 @@ enum ionic_qos_sched_type { * @dot1q_pcp: Dot1q pcp value * @ndscp: Number of valid dscp values in the ip_dscp field * @ip_dscp: IP dscp values + * @words: word access to struct contents */ union ionic_qos_config { struct { @@ -2219,8 +2316,9 @@ union ionic_qos_config { * union ionic_qos_identity - QoS identity structure * @version: Version of the identify structure * @type: QoS system type - * @nclasses: Number of usable QoS classes + * @rsvd: reserved byte(s) * @config: Current configuration of classes + * @words: word access to struct contents */ union ionic_qos_identity { struct { @@ -2236,7 +2334,9 @@ union ionic_qos_identity { * struct ionic_qos_init_cmd - QoS config init command * @opcode: Opcode * @group: QoS class id + * @rsvd: reserved byte(s) * @info_pa: destination address for qos info + * @rsvd1: reserved byte(s) */ struct ionic_qos_init_cmd { u8 opcode; @@ -2252,6 +2352,7 @@ typedef struct ionic_admin_comp ionic_qos_init_comp; * struct ionic_qos_reset_cmd - QoS config reset command * @opcode: Opcode * @group: QoS class id + * @rsvd: reserved byte(s) */ struct ionic_qos_reset_cmd { u8 opcode; @@ -2260,8 +2361,10 @@ struct ionic_qos_reset_cmd { }; /** - * struct ionic_qos_clear_port_stats_cmd - Qos config reset command + * struct ionic_qos_clear_stats_cmd - Qos config reset command * @opcode: Opcode + * @group_bitmap: bitmap of groups to be cleared + * @rsvd: reserved byte(s) */ struct ionic_qos_clear_stats_cmd { u8 opcode; @@ -2274,6 +2377,7 @@ typedef struct ionic_admin_comp ionic_qos_reset_comp; /** * struct ionic_fw_download_cmd - Firmware download command * @opcode: opcode + * @rsvd: reserved byte(s) * @addr: dma address of the firmware buffer * @offset: offset of the firmware buffer within the full image * @length: number of valid bytes in the firmware buffer @@ -2297,6 +2401,7 @@ typedef struct ionic_admin_comp ionic_fw_download_comp; * @IONIC_FW_INSTALL_STATUS: Firmware installation status * @IONIC_FW_ACTIVATE_ASYNC: Activate firmware asynchronously * @IONIC_FW_ACTIVATE_STATUS: Firmware activate status + * @IONIC_FW_UPDATE_CLEANUP: Clean up after an interrupted fw update */ enum ionic_fw_control_oper { IONIC_FW_RESET = 0, @@ -2312,8 +2417,10 @@ enum ionic_fw_control_oper { /** * struct ionic_fw_control_cmd - Firmware control command * @opcode: opcode + * @rsvd: reserved byte(s) * @oper: firmware control operation (enum ionic_fw_control_oper) * @slot: slot to activate + * @rsvd1: reserved byte(s) */ struct ionic_fw_control_cmd { u8 opcode; @@ -2326,8 +2433,10 @@ struct ionic_fw_control_cmd { /** * struct ionic_fw_control_comp - Firmware control copletion * @status: Status of the command (enum ionic_status_code) + * @rsvd: reserved byte(s) * @comp_index: Index in the descriptor ring for which this is the completion * @slot: Slot where the firmware was installed + * @rsvd1: reserved byte(s) * @color: Color bit */ struct ionic_fw_control_comp { @@ -2346,7 +2455,9 @@ struct ionic_fw_control_comp { /** * struct ionic_rdma_reset_cmd - Reset RDMA LIF cmd * @opcode: opcode + * @rsvd: reserved byte(s) * @lif_index: LIF index + * @rsvd2: reserved byte(s) * * There is no RDMA specific dev command completion struct. Completion uses * the common struct ionic_admin_comp. Only the status is indicated. @@ -2362,6 +2473,7 @@ struct ionic_rdma_reset_cmd { /** * struct ionic_rdma_queue_cmd - Create RDMA Queue command * @opcode: opcode, 52, 53 + * @rsvd: reserved byte(s) * @lif_index: LIF index * @qid_ver: (qid | (RDMA version << 24)) * @cid: intr, eq_id, or cq_id @@ -2369,6 +2481,7 @@ struct ionic_rdma_reset_cmd { * @depth_log2: log base two of queue depth * @stride_log2: log base two of queue stride * @dma_addr: address of the queue memory + * @rsvd2: reserved byte(s) * * The same command struct is used to create an RDMA event queue, completion * queue, or RDMA admin queue. The cid is an interrupt number for an event @@ -2425,6 +2538,7 @@ struct ionic_notifyq_event { * @ecode: event code = IONIC_EVENT_LINK_CHANGE * @link_status: link up/down, with error bits (enum ionic_port_status) * @link_speed: speed of the network link + * @rsvd: reserved byte(s) * * Sent when the network link state changes between UP and DOWN */ @@ -2442,6 +2556,7 @@ struct ionic_link_change_event { * @ecode: event code = IONIC_EVENT_RESET * @reset_code: reset type * @state: 0=pending, 1=complete, 2=error + * @rsvd: reserved byte(s) * * Sent when the NIC or some subsystem is going to be or * has been reset. @@ -2458,6 +2573,7 @@ struct ionic_reset_event { * struct ionic_heartbeat_event - Sent periodically by NIC to indicate health * @eid: event number * @ecode: event code = IONIC_EVENT_HEARTBEAT + * @rsvd: reserved byte(s) */ struct ionic_heartbeat_event { __le64 eid; @@ -2481,6 +2597,7 @@ struct ionic_log_event { * struct ionic_xcvr_event - Transceiver change event * @eid: event number * @ecode: event code = IONIC_EVENT_XCVR + * @rsvd: reserved byte(s) */ struct ionic_xcvr_event { __le64 eid; @@ -2488,7 +2605,7 @@ struct ionic_xcvr_event { u8 rsvd[54]; }; -/** +/* * struct ionic_port_stats - Port statistics structure */ struct ionic_port_stats { @@ -2646,8 +2763,7 @@ enum ionic_oflow_drop_stats { IONIC_OFLOW_DROP_MAX, }; -/** - * struct port_pb_stats - packet buffers system stats +/* struct ionic_port_pb_stats - packet buffers system stats * uses ionic_pb_buffer_drop_stats for drop_counts[] */ struct ionic_port_pb_stats { @@ -2681,7 +2797,9 @@ struct ionic_port_pb_stats { * @pause_type: supported pause types * @loopback_mode: supported loopback mode * @speeds: supported speeds + * @rsvd2: reserved byte(s) * @config: current port configuration + * @words: word access to struct contents */ union ionic_port_identity { struct { @@ -2707,7 +2825,8 @@ union ionic_port_identity { * @status: Port status data * @stats: Port statistics data * @mgmt_stats: Port management statistics data - * @port_pb_drop_stats: uplink pb drop stats + * @rsvd: reserved byte(s) + * @pb_stats: uplink pb drop stats */ struct ionic_port_info { union ionic_port_config config; @@ -2721,7 +2840,7 @@ struct ionic_port_info { struct ionic_port_pb_stats pb_stats; }; -/** +/* * struct ionic_lif_stats - LIF statistics structure */ struct ionic_lif_stats { @@ -2983,8 +3102,10 @@ struct ionic_hwstamp_regs { * bit 4-7 - 4 bit generation number, changes on fw restart * @fw_heartbeat: Firmware heartbeat counter * @serial_num: Serial number + * @rsvd_pad1024: reserved byte(s) * @fw_version: Firmware version - * @hwstamp_regs: Hardware current timestamp registers + * @hwstamp: Hardware current timestamp registers + * @words: word access to struct contents */ union ionic_dev_info_regs { #define IONIC_DEVINFO_FWVERS_BUFLEN 32 @@ -3014,7 +3135,9 @@ union ionic_dev_info_regs { * @done: Done indicator, bit 0 == 1 when command is complete * @cmd: Opcode-specific command bytes * @comp: Opcode-specific response bytes + * @rsvd: reserved byte(s) * @data: Opcode-specific side-data + * @words: word access to struct contents */ union ionic_dev_cmd_regs { struct { @@ -3032,6 +3155,7 @@ union ionic_dev_cmd_regs { * union ionic_dev_regs - Device register format for bar 0 page 0 * @info: Device info registers * @devcmd: Device command registers + * @words: word access to struct contents */ union ionic_dev_regs { struct { @@ -3098,6 +3222,7 @@ union ionic_adminq_comp { * interrupts when armed. * @qid_lo: Queue destination for the producer index and flags (low bits) * @qid_hi: Queue destination for the producer index and flags (high bits) + * @rsvd2: reserved byte(s) */ struct ionic_doorbell { __le16 p_index; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 24870da3f484..23e1f6638b38 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -237,12 +237,12 @@ static int ionic_request_irq(struct ionic_lif *lif, struct ionic_qcq *qcq) const char *name; if (lif->registered) - name = lif->netdev->name; + name = netdev_name(lif->netdev); else name = dev_name(dev); snprintf(intr->name, sizeof(intr->name), - "%s-%s-%s", IONIC_DRV_NAME, name, q->name); + "%.5s-%.16s-%.8s", IONIC_DRV_NAME, name, q->name); return devm_request_irq(dev, intr->vector, ionic_isr, 0, intr->name, &qcq->napi); @@ -3388,6 +3388,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) * just need to reanimate it. */ ionic_init_devinfo(ionic); + ionic_reset(ionic); err = ionic_identify(ionic); if (err) goto err_out; @@ -3731,7 +3732,7 @@ static void ionic_lif_set_netdev_info(struct ionic_lif *lif) }, }; - strscpy(ctx.cmd.lif_setattr.name, lif->netdev->name, + strscpy(ctx.cmd.lif_setattr.name, netdev_name(lif->netdev), sizeof(ctx.cmd.lif_setattr.name)); ionic_adminq_post_wait(lif, &ctx); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 5dba6d2d633c..c3a6c4af52f1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -502,7 +502,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, XDP_PACKET_HEADROOM, frag_len, false); dma_sync_single_range_for_cpu(rxq->dev, ionic_rx_buf_pa(buf_info), - XDP_PACKET_HEADROOM, len, + XDP_PACKET_HEADROOM, frag_len, DMA_FROM_DEVICE); prefetchw(&xdp_buf.data_hard_start); @@ -582,7 +582,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, buf_info->page_offset, true); __netif_tx_unlock(nq); - if (err) { + if (unlikely(err)) { netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err); goto out_xdp_abort; } @@ -597,7 +597,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, IONIC_PAGE_SIZE, DMA_FROM_DEVICE); err = xdp_do_redirect(netdev, &xdp_buf, xdp_prog); - if (err) { + if (unlikely(err)) { netdev_dbg(netdev, "xdp_do_redirect err %d\n", err); goto out_xdp_abort; } @@ -1058,7 +1058,7 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, dma_addr_t dma_addr; dma_addr = dma_map_single(dev, data, len, DMA_TO_DEVICE); - if (dma_mapping_error(dev, dma_addr)) { + if (unlikely(dma_mapping_error(dev, dma_addr))) { net_warn_ratelimited("%s: DMA single map failed on %s!\n", dev_name(dev), q->name); q_to_tx_stats(q)->dma_map_err++; @@ -1075,7 +1075,7 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, dma_addr_t dma_addr; dma_addr = skb_frag_dma_map(dev, frag, offset, len, DMA_TO_DEVICE); - if (dma_mapping_error(dev, dma_addr)) { + if (unlikely(dma_mapping_error(dev, dma_addr))) { net_warn_ratelimited("%s: DMA frag map failed on %s!\n", dev_name(dev), q->name); q_to_tx_stats(q)->dma_map_err++; @@ -1316,7 +1316,7 @@ static int ionic_tx_tcp_inner_pseudo_csum(struct sk_buff *skb) int err; err = skb_cow_head(skb, 0); - if (err) + if (unlikely(err)) return err; if (skb->protocol == cpu_to_be16(ETH_P_IP)) { @@ -1340,7 +1340,7 @@ static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb) int err; err = skb_cow_head(skb, 0); - if (err) + if (unlikely(err)) return err; if (skb->protocol == cpu_to_be16(ETH_P_IP)) { @@ -1357,7 +1357,7 @@ static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb) } static void ionic_tx_tso_post(struct net_device *netdev, struct ionic_queue *q, - struct ionic_tx_desc_info *desc_info, + struct ionic_txq_desc *desc, struct sk_buff *skb, dma_addr_t addr, u8 nsge, u16 len, unsigned int hdrlen, unsigned int mss, @@ -1365,7 +1365,6 @@ static void ionic_tx_tso_post(struct net_device *netdev, struct ionic_queue *q, u16 vlan_tci, bool has_vlan, bool start, bool done) { - struct ionic_txq_desc *desc = &q->txq[q->head_idx]; u8 flags = 0; u64 cmd; @@ -1445,7 +1444,7 @@ static int ionic_tx_tso(struct net_device *netdev, struct ionic_queue *q, err = ionic_tx_tcp_inner_pseudo_csum(skb); else err = ionic_tx_tcp_pseudo_csum(skb); - if (err) { + if (unlikely(err)) { /* clean up mapping from ionic_tx_map_skb */ ionic_tx_desc_unmap_bufs(q, desc_info); return err; @@ -1503,10 +1502,9 @@ static int ionic_tx_tso(struct net_device *netdev, struct ionic_queue *q, seg_rem = min(tso_rem, mss); done = (tso_rem == 0); /* post descriptor */ - ionic_tx_tso_post(netdev, q, desc_info, skb, - desc_addr, desc_nsge, desc_len, - hdrlen, mss, outer_csum, vlan_tci, has_vlan, - start, done); + ionic_tx_tso_post(netdev, q, desc, skb, desc_addr, desc_nsge, + desc_len, hdrlen, mss, outer_csum, vlan_tci, + has_vlan, start, done); start = false; /* Buffer information is stored with the first tso descriptor */ desc_info = &q->tx_info[q->head_idx]; @@ -1731,7 +1729,7 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) linearize: if (too_many_frags) { err = skb_linearize(skb); - if (err) + if (unlikely(err)) return err; q_to_tx_stats(q)->linearize++; } @@ -1765,7 +1763,7 @@ static netdev_tx_t ionic_start_hwstamp_xmit(struct sk_buff *skb, else err = ionic_tx(netdev, q, skb); - if (err) + if (unlikely(err)) goto err_out_drop; return NETDEV_TX_OK; @@ -1811,7 +1809,7 @@ netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev) else err = ionic_tx(netdev, q, skb); - if (err) + if (unlikely(err)) goto err_out_drop; return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 7b9e04884575..9246ea2118ff 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2274,7 +2274,9 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) /* 8168B family. */ { 0x7c8, 0x380, RTL_GIGA_MAC_VER_17 }, - { 0x7c8, 0x300, RTL_GIGA_MAC_VER_11 }, + /* This one is very old and rare, let's see if anybody complains. + * { 0x7c8, 0x300, RTL_GIGA_MAC_VER_11 }, + */ /* 8101 family. */ { 0x7c8, 0x448, RTL_GIGA_MAC_VER_39 }, @@ -5086,12 +5088,10 @@ static void rtl_set_irq_mask(struct rtl8169_private *tp) tp->irq_mask = RxOK | RxErr | TxOK | TxErr | LinkChg; if (tp->mac_version <= RTL_GIGA_MAC_VER_06) - tp->irq_mask |= SYSErr | RxOverflow | RxFIFOOver; + tp->irq_mask |= SYSErr | RxFIFOOver; else if (tp->mac_version == RTL_GIGA_MAC_VER_11) /* special workaround needed */ tp->irq_mask |= RxFIFOOver; - else - tp->irq_mask |= RxOverflow; } static int rtl_alloc_irq(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 78ff3af7911a..907498848028 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -1574,12 +1574,8 @@ smc_ethtool_set_link_ksettings(struct net_device *dev, (cmd->base.port != PORT_TP && cmd->base.port != PORT_AUI)) return -EINVAL; -// lp->port = cmd->base.port; lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL; -// if (netif_running(dev)) -// smc_set_port(dev); - ret = 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 9cd62b2110a1..cd36ff4da68c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -271,8 +271,6 @@ struct stmmac_safety_stats { /* PCS defines */ #define STMMAC_PCS_RGMII (1 << 0) #define STMMAC_PCS_SGMII (1 << 1) -#define STMMAC_PCS_TBI (1 << 2) -#define STMMAC_PCS_RTBI (1 << 3) #define SF_DMA_MODE 1 /* DMA STORE-AND-FORWARD Operation Mode */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 60283543ffc8..56649edb18cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -248,7 +248,7 @@ static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data) dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n"); priv->plat->max_speed = 2500; priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX; - priv->plat->mdio_bus_data->xpcs_an_inband = false; + priv->plat->mdio_bus_data->default_an_inband = false; } else { priv->plat->max_speed = 1000; } @@ -586,18 +586,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, if (plat->phy_interface == PHY_INTERFACE_MODE_SGMII || plat->phy_interface == PHY_INTERFACE_MODE_1000BASEX) { plat->mdio_bus_data->has_xpcs = true; - plat->mdio_bus_data->xpcs_an_inband = true; - } - - /* For fixed-link setup, we clear xpcs_an_inband */ - if (fwnode) { - struct fwnode_handle *fixed_node; - - fixed_node = fwnode_get_named_child_node(fwnode, "fixed-link"); - if (fixed_node) - plat->mdio_bus_data->xpcs_an_inband = false; - - fwnode_handle_put(fixed_node); + plat->mdio_bus_data->default_an_inband = true; } /* Ensure mdio bus scan skips intel serdes and pcs-xpcs */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index e254b21fdb59..d9eed415b0b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -605,6 +605,14 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos) return 0; } +static void ethqos_set_serdes_speed(struct qcom_ethqos *ethqos, int speed) +{ + if (ethqos->serdes_speed != speed) { + phy_set_speed(ethqos->serdes_phy, speed); + ethqos->serdes_speed = speed; + } +} + /* On interface toggle MAC registers gets reset. * Configure MAC block for SGMII on ethernet phy link up */ @@ -622,9 +630,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); - if (ethqos->serdes_speed != SPEED_2500) - phy_set_speed(ethqos->serdes_phy, SPEED_2500); - ethqos->serdes_speed = SPEED_2500; + ethqos_set_serdes_speed(ethqos, SPEED_2500); stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 0, 0, 0); break; case SPEED_1000: @@ -632,16 +638,12 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); - if (ethqos->serdes_speed != SPEED_1000) - phy_set_speed(ethqos->serdes_phy, SPEED_1000); - ethqos->serdes_speed = SPEED_1000; + ethqos_set_serdes_speed(ethqos, SPEED_1000); stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0); break; case SPEED_100: val |= ETHQOS_MAC_CTRL_PORT_SEL | ETHQOS_MAC_CTRL_SPEED_MODE; - if (ethqos->serdes_speed != SPEED_1000) - phy_set_speed(ethqos->serdes_phy, SPEED_1000); - ethqos->serdes_speed = SPEED_1000; + ethqos_set_serdes_speed(ethqos, SPEED_1000); stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0); break; case SPEED_10: @@ -651,9 +653,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR, SGMII_10M_RX_CLK_DVDR), RGMII_IO_MACRO_CONFIG); - if (ethqos->serdes_speed != SPEED_1000) - phy_set_speed(ethqos->serdes_phy, ethqos->speed); - ethqos->serdes_speed = SPEED_1000; + ethqos_set_serdes_speed(ethqos, SPEED_1000); stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, 0, 0); break; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 8555299443f4..d413d76a8936 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -15,7 +15,7 @@ #include <linux/crc32.h> #include <linux/slab.h> #include <linux/ethtool.h> -#include <asm/io.h> +#include <linux/io.h> #include "stmmac.h" #include "stmmac_pcs.h" #include "dwmac1000.h" @@ -404,11 +404,6 @@ static void dwmac1000_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral, dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback); } -static void dwmac1000_rane(void __iomem *ioaddr, bool restart) -{ - dwmac_rane(ioaddr, GMAC_PCS_BASE, restart); -} - static void dwmac1000_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv) { dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv); @@ -519,7 +514,6 @@ const struct stmmac_ops dwmac1000_ops = { .set_eee_pls = dwmac1000_set_eee_pls, .debug = dwmac1000_debug, .pcs_ctrl_ane = dwmac1000_ctrl_ane, - .pcs_rane = dwmac1000_rane, .pcs_get_adv_lp = dwmac1000_get_adv_lp, .set_mac_loopback = dwmac1000_set_mac_loopback, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index daf79cdbd3ec..adccdd816ea9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -12,7 +12,7 @@ Author: Giuseppe Cavallaro <peppe.cavallaro@st.com> *******************************************************************************/ -#include <asm/io.h> +#include <linux/io.h> #include "dwmac1000.h" #include "dwmac_dma.h" diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index 7667d103cd0e..14e847c0e1a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -15,7 +15,7 @@ *******************************************************************************/ #include <linux/crc32.h> -#include <asm/io.h> +#include <linux/io.h> #include "stmmac.h" #include "dwmac100.h" diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c index dea270f60cc3..b402fb54f613 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c @@ -14,7 +14,7 @@ Author: Giuseppe Cavallaro <peppe.cavallaro@st.com> *******************************************************************************/ -#include <asm/io.h> +#include <linux/io.h> #include "dwmac100.h" #include "dwmac_dma.h" diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index b25774d69195..dbd9f93b2460 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -758,11 +758,6 @@ static void dwmac4_ctrl_ane(void __iomem *ioaddr, bool ane, bool srgmi_ral, dwmac_ctrl_ane(ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback); } -static void dwmac4_rane(void __iomem *ioaddr, bool restart) -{ - dwmac_rane(ioaddr, GMAC_PCS_BASE, restart); -} - static void dwmac4_get_adv_lp(void __iomem *ioaddr, struct rgmii_adv *adv) { dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv); @@ -1215,7 +1210,6 @@ const struct stmmac_ops dwmac4_ops = { .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, - .pcs_rane = dwmac4_rane, .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, @@ -1260,7 +1254,6 @@ const struct stmmac_ops dwmac410_ops = { .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, - .pcs_rane = dwmac4_rane, .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, @@ -1309,7 +1302,6 @@ const struct stmmac_ops dwmac510_ops = { .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, - .pcs_rane = dwmac4_rane, .pcs_get_adv_lp = dwmac4_get_adv_lp, .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index f8e7775bb633..6a987cf598e4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -1554,9 +1554,6 @@ const struct stmmac_ops dwxgmac210_ops = { .reset_eee_mode = dwxgmac2_reset_eee_mode, .set_eee_timer = dwxgmac2_set_eee_timer, .set_eee_pls = dwxgmac2_set_eee_pls, - .pcs_ctrl_ane = NULL, - .pcs_rane = NULL, - .pcs_get_adv_lp = NULL, .debug = NULL, .set_filter = dwxgmac2_set_filter, .safety_feat_config = dwxgmac3_safety_feat_config, @@ -1614,9 +1611,6 @@ const struct stmmac_ops dwxlgmac2_ops = { .reset_eee_mode = dwxgmac2_reset_eee_mode, .set_eee_timer = dwxgmac2_set_eee_timer, .set_eee_pls = dwxgmac2_set_eee_pls, - .pcs_ctrl_ane = NULL, - .pcs_rane = NULL, - .pcs_get_adv_lp = NULL, .debug = NULL, .set_filter = dwxgmac2_set_filter, .safety_feat_config = dwxgmac3_safety_feat_config, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 90384db228b5..97934ccba5b1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -370,7 +370,6 @@ struct stmmac_ops { /* PCS calls */ void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral, bool loopback); - void (*pcs_rane)(void __iomem *ioaddr, bool restart); void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv); /* Safety Features */ int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp, @@ -484,8 +483,6 @@ struct stmmac_ops { stmmac_do_void_callback(__priv, mac, debug, __priv, __args) #define stmmac_pcs_ctrl_ane(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, pcs_ctrl_ane, __args) -#define stmmac_pcs_rane(__priv, __args...) \ - stmmac_do_void_callback(__priv, mac, pcs_rane, __priv, __args) #define stmmac_pcs_get_adv_lp(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, pcs_get_adv_lp, __args) #define stmmac_safety_feat_config(__priv, __args...) \ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 542e2633a6f5..18468c0228f0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -11,10 +11,10 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/mii.h> #include <linux/phylink.h> #include <linux/net_tstamp.h> -#include <asm/io.h> #include "stmmac.h" #include "dwmac_dma.h" diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b3afc7cb7d72..bbedf2a8c60f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -471,13 +471,6 @@ bool stmmac_eee_init(struct stmmac_priv *priv) { int eee_tw_timer = priv->eee_tw_timer; - /* Using PCS we cannot dial with the phy registers at this stage - * so we do not support extra feature like EEE. - */ - if (priv->hw->pcs == STMMAC_PCS_TBI || - priv->hw->pcs == STMMAC_PCS_RTBI) - return false; - /* Check if MAC core supports the EEE feature. */ if (!priv->dma_cap.eee) return false; @@ -1228,8 +1221,8 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) mdio_bus_data = priv->plat->mdio_bus_data; if (mdio_bus_data) - priv->phylink_config.ovr_an_inband = - mdio_bus_data->xpcs_an_inband; + priv->phylink_config.default_an_inband = + mdio_bus_data->default_an_inband; /* Set the platform/firmware specified interface mode. Note, phylink * deals with the PHY interface mode, not the MAC interface mode. @@ -3953,9 +3946,7 @@ static int __stmmac_open(struct net_device *dev, if (ret < 0) return ret; - if (priv->hw->pcs != STMMAC_PCS_TBI && - priv->hw->pcs != STMMAC_PCS_RTBI && - (!priv->hw->xpcs || + if ((!priv->hw->xpcs || xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73)) { ret = stmmac_init_phy(dev); if (ret) { @@ -4097,8 +4088,6 @@ static int stmmac_release(struct net_device *dev) if (priv->plat->serdes_powerdown) priv->plat->serdes_powerdown(dev, priv->plat->bsp_priv); - netif_carrier_off(dev); - stmmac_release_ptp(priv); pm_runtime_put(priv->device); @@ -7739,16 +7728,12 @@ int stmmac_dvr_probe(struct device *device, if (!pm_runtime_enabled(device)) pm_runtime_enable(device); - if (priv->hw->pcs != STMMAC_PCS_TBI && - priv->hw->pcs != STMMAC_PCS_RTBI) { - /* MDIO bus Registration */ - ret = stmmac_mdio_register(ndev); - if (ret < 0) { - dev_err_probe(priv->device, ret, - "%s: MDIO bus (id: %d) registration failed\n", - __func__, priv->plat->bus_id); - goto error_mdio_register; - } + ret = stmmac_mdio_register(ndev); + if (ret < 0) { + dev_err_probe(priv->device, ret, + "MDIO bus (id: %d) registration failed\n", + priv->plat->bus_id); + goto error_mdio_register; } if (priv->plat->speed_mode_2500) @@ -7790,9 +7775,7 @@ error_netdev_register: error_phy_setup: stmmac_pcs_clean(ndev); error_pcs_setup: - if (priv->hw->pcs != STMMAC_PCS_TBI && - priv->hw->pcs != STMMAC_PCS_RTBI) - stmmac_mdio_unregister(ndev); + stmmac_mdio_unregister(ndev); error_mdio_register: stmmac_napi_del(ndev); error_hw_init: @@ -7821,7 +7804,6 @@ void stmmac_dvr_remove(struct device *dev) stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); - netif_carrier_off(ndev); unregister_netdev(ndev); #ifdef CONFIG_DEBUG_FS @@ -7833,10 +7815,8 @@ void stmmac_dvr_remove(struct device *dev) reset_control_assert(priv->plat->stmmac_ahb_rst); stmmac_pcs_clean(ndev); + stmmac_mdio_unregister(ndev); - if (priv->hw->pcs != STMMAC_PCS_TBI && - priv->hw->pcs != STMMAC_PCS_RTBI) - stmmac_mdio_unregister(ndev); destroy_workqueue(priv->wq); mutex_destroy(&priv->lock); bitmap_free(priv->af_xdp_zc_qps); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h index 13a30e6df4c1..1bdf87b237c4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h @@ -75,23 +75,6 @@ static inline void dwmac_pcs_isr(void __iomem *ioaddr, u32 reg, } /** - * dwmac_rane - To restart ANE - * @ioaddr: IO registers pointer - * @reg: Base address of the AN Control Register. - * @restart: to restart ANE - * Description: this is to just restart the Auto-Negotiation. - */ -static inline void dwmac_rane(void __iomem *ioaddr, u32 reg, bool restart) -{ - u32 value = readl(ioaddr + GMAC_AN_CTRL(reg)); - - if (restart) - value |= GMAC_AN_CTRL_RAN; - - writel(value, ioaddr + GMAC_AN_CTRL(reg)); -} - -/** * dwmac_ctrl_ane - To program the AN Control Register. * @ioaddr: IO registers pointer * @reg: Base address of the AN Control Register. diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 1729eb0e0b41..f160a3b71499 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -204,6 +204,7 @@ config TI_ICSSG_PRUETH_SR1 select TI_ICSS_IEP select TI_K3_CPPI_DESC_POOL depends on PRU_REMOTEPROC + depends on NET_SWITCHDEV depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER help Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem. diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index 6e086b4c0384..59cd20a38267 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -39,7 +39,8 @@ icssg-prueth-y := icssg/icssg_prueth.o \ icssg/icssg_config.o \ icssg/icssg_mii_cfg.o \ icssg/icssg_stats.o \ - icssg/icssg_ethtool.o + icssg/icssg_ethtool.o \ + icssg/icssg_switchdev.o obj-$(CONFIG_TI_ICSSG_PRUETH_SR1) += icssg-prueth-sr1.o icssg-prueth-sr1-y := icssg/icssg_prueth_sr1.o \ icssg/icssg_common.o \ diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 4e50b3792888..e6f87ac394fe 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -896,7 +896,7 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) /* mac_sl should be configured via phy-link interface */ am65_cpsw_sl_ctl_reset(port); - ret = phylink_of_phy_connect(port->slave.phylink, port->slave.phy_node, 0); + ret = phylink_of_phy_connect(port->slave.phylink, port->slave.port_np, 0); if (ret) goto error_cleanup; @@ -2611,7 +2611,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) of_property_read_bool(port_np, "ti,mac-only"); /* get phy/link info */ - port->slave.phy_node = port_np; + port->slave.port_np = port_np; ret = of_get_phy_mode(port_np, &port->slave.phy_if); if (ret) { dev_err(dev, "%pOF read phy-mode err %d\n", @@ -2703,6 +2703,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) mutex_init(&ndev_priv->mm_lock); port->qos.link_speed = SPEED_UNKNOWN; SET_NETDEV_DEV(port->ndev, dev); + port->ndev->dev.of_node = port->slave.port_np; eth_hw_addr_set(port->ndev, port->slave.mac_addr); @@ -2760,7 +2761,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) } phylink = phylink_create(&port->slave.phylink_config, - of_node_to_fwnode(port->slave.phy_node), + of_node_to_fwnode(port->slave.port_np), port->slave.phy_if, &am65_cpsw_phylink_mac_ops); if (IS_ERR(phylink)) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index d8ce88dc9c89..e2ce2be320bd 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -30,7 +30,7 @@ struct am65_cpts; struct am65_cpsw_slave_data { bool mac_only; struct cpsw_sl *mac_sl; - struct device_node *phy_node; + struct device_node *port_np; phy_interface_t phy_if; struct phy *ifphy; struct phy *serdes_phy; diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index 088ab8076db4..873126dfc173 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -581,6 +581,8 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id) } else { /* send the filled skb up the n/w stack */ skb_put(skb, pkt_len); + if (emac->prueth->is_switch_mode) + skb->offload_fwd_mark = emac->offload_fwd_mark; skb->protocol = eth_type_trans(skb, ndev); napi_gro_receive(&emac->napi_rx, skb); ndev->stats.rx_bytes += pkt_len; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index 15f2235bf90f..9444e56b7672 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -107,28 +107,49 @@ static const struct map hwq_map[2][ICSSG_NUM_OTHER_QUEUES] = { }, }; +static void icssg_config_mii_init_switch(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + int mii = prueth_emac_slice(emac); + u32 txcfg_reg, pcnt_reg, txcfg; + struct regmap *mii_rt; + + mii_rt = prueth->mii_rt; + + txcfg_reg = (mii == ICSS_MII0) ? PRUSS_MII_RT_TXCFG0 : + PRUSS_MII_RT_TXCFG1; + pcnt_reg = (mii == ICSS_MII0) ? PRUSS_MII_RT_RX_PCNT0 : + PRUSS_MII_RT_RX_PCNT1; + + txcfg = PRUSS_MII_RT_TXCFG_TX_ENABLE | + PRUSS_MII_RT_TXCFG_TX_AUTO_PREAMBLE | + PRUSS_MII_RT_TXCFG_TX_IPG_WIRE_CLK_EN; + + if (emac->phy_if == PHY_INTERFACE_MODE_MII && mii == ICSS_MII1) + txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL; + else if (emac->phy_if != PHY_INTERFACE_MODE_MII && mii == ICSS_MII0) + txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL; + + regmap_write(mii_rt, txcfg_reg, txcfg); + regmap_write(mii_rt, pcnt_reg, 0x1); +} + static void icssg_config_mii_init(struct prueth_emac *emac) { - u32 rxcfg, txcfg, rxcfg_reg, txcfg_reg, pcnt_reg; struct prueth *prueth = emac->prueth; int slice = prueth_emac_slice(emac); + u32 txcfg, txcfg_reg, pcnt_reg; struct regmap *mii_rt; mii_rt = prueth->mii_rt; - rxcfg_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_RXCFG0 : - PRUSS_MII_RT_RXCFG1; txcfg_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_TXCFG0 : PRUSS_MII_RT_TXCFG1; pcnt_reg = (slice == ICSS_MII0) ? PRUSS_MII_RT_RX_PCNT0 : PRUSS_MII_RT_RX_PCNT1; - rxcfg = MII_RXCFG_DEFAULT; txcfg = MII_TXCFG_DEFAULT; - if (slice == ICSS_MII1) - rxcfg |= PRUSS_MII_RT_RXCFG_RX_MUX_SEL; - /* In MII mode TX lines swapped inside ICSSG, so TX_MUX_SEL cfg need * to be swapped also comparing to RGMII mode. */ @@ -137,7 +158,6 @@ static void icssg_config_mii_init(struct prueth_emac *emac) else if (emac->phy_if != PHY_INTERFACE_MODE_MII && slice == ICSS_MII1) txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL; - regmap_write(mii_rt, rxcfg_reg, rxcfg); regmap_write(mii_rt, txcfg_reg, txcfg); regmap_write(mii_rt, pcnt_reg, 0x1); } @@ -257,6 +277,66 @@ static int emac_r30_is_done(struct prueth_emac *emac) return 1; } +static int prueth_switch_buffer_setup(struct prueth_emac *emac) +{ + struct icssg_buffer_pool_cfg __iomem *bpool_cfg; + struct icssg_rxq_ctx __iomem *rxq_ctx; + struct prueth *prueth = emac->prueth; + int slice = prueth_emac_slice(emac); + u32 addr; + int i; + + addr = lower_32_bits(prueth->msmcram.pa); + if (slice) + addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + + if (addr % SZ_64K) { + dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n"); + return -EINVAL; + } + + bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; + /* workaround for f/w bug. bpool 0 needs to be initialized */ + for (i = 0; i < PRUETH_NUM_BUF_POOLS; i++) { + writel(addr, &bpool_cfg[i].addr); + writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len); + addr += PRUETH_EMAC_BUF_POOL_SIZE; + } + + if (!slice) + addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + else + addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; + + for (i = PRUETH_NUM_BUF_POOLS; + i < 2 * PRUETH_SW_NUM_BUF_POOLS_HOST + PRUETH_NUM_BUF_POOLS; + i++) { + /* The driver only uses first 4 queues per PRU so only initialize them */ + if (i % PRUETH_SW_NUM_BUF_POOLS_HOST < PRUETH_SW_NUM_BUF_POOLS_PER_PRU) { + writel(addr, &bpool_cfg[i].addr); + writel(PRUETH_SW_BUF_POOL_SIZE_HOST, &bpool_cfg[i].len); + addr += PRUETH_SW_BUF_POOL_SIZE_HOST; + } else { + writel(0, &bpool_cfg[i].addr); + writel(0, &bpool_cfg[i].len); + } + } + + if (!slice) + addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; + else + addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + + rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; + for (i = 0; i < 3; i++) + writel(addr, &rxq_ctx->start[i]); + + addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + writel(addr - SZ_2K, &rxq_ctx->end); + + return 0; +} + static int prueth_emac_buffer_setup(struct prueth_emac *emac) { struct icssg_buffer_pool_cfg __iomem *bpool_cfg; @@ -321,25 +401,63 @@ static void icssg_init_emac_mode(struct prueth *prueth) /* When the device is configured as a bridge and it is being brought * back to the emac mode, the host mac address has to be set as 0. */ + u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET; + int i; u8 mac[ETH_ALEN] = { 0 }; if (prueth->emacs_initialized) return; - regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, - SMEM_VLAN_OFFSET_MASK, 0); - regmap_write(prueth->miig_rt, FDB_GEN_CFG2, 0); + /* Set VLAN TABLE address base */ + regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, + addr << SMEM_VLAN_OFFSET); + /* Set enable VLAN aware mode, and FDBs for all PRUs */ + regmap_write(prueth->miig_rt, FDB_GEN_CFG2, (FDB_PRU0_EN | FDB_PRU1_EN | FDB_HOST_EN)); + prueth->vlan_tbl = (struct prueth_vlan_tbl __force *)(prueth->shram.va + + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET); + for (i = 0; i < SZ_4K - 1; i++) { + prueth->vlan_tbl[i].fid = i; + prueth->vlan_tbl[i].fid_c1 = 0; + } /* Clear host MAC address */ icssg_class_set_host_mac_addr(prueth->miig_rt, mac); } +static void icssg_init_switch_mode(struct prueth *prueth) +{ + u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET; + int i; + + if (prueth->emacs_initialized) + return; + + /* Set VLAN TABLE address base */ + regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, + addr << SMEM_VLAN_OFFSET); + /* Set enable VLAN aware mode, and FDBs for all PRUs */ + regmap_write(prueth->miig_rt, FDB_GEN_CFG2, FDB_EN_ALL); + prueth->vlan_tbl = (struct prueth_vlan_tbl __force *)(prueth->shram.va + + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET); + for (i = 0; i < SZ_4K - 1; i++) { + prueth->vlan_tbl[i].fid = i; + prueth->vlan_tbl[i].fid_c1 = 0; + } + + if (prueth->hw_bridge_dev) + icssg_class_set_host_mac_addr(prueth->miig_rt, prueth->hw_bridge_dev->dev_addr); + icssg_set_pvid(prueth, prueth->default_vlan, PRUETH_PORT_HOST); +} + int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) { void __iomem *config = emac->dram.va + ICSSG_CONFIG_OFFSET; struct icssg_flow_cfg __iomem *flow_cfg; int ret; - icssg_init_emac_mode(prueth); + if (prueth->is_switch_mode) + icssg_init_switch_mode(prueth); + else + icssg_init_emac_mode(prueth); memset_io(config, 0, TAS_GATE_MASK_LIST0); icssg_miig_queues_init(prueth, slice); @@ -353,7 +471,10 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) regmap_update_bits(prueth->miig_rt, ICSSG_CFG_OFFSET, ICSSG_CFG_DEFAULT, ICSSG_CFG_DEFAULT); icssg_miig_set_interface_mode(prueth->miig_rt, slice, emac->phy_if); - icssg_config_mii_init(emac); + if (prueth->is_switch_mode) + icssg_config_mii_init_switch(emac); + else + icssg_config_mii_init(emac); icssg_config_ipg(emac); icssg_update_rgmii_cfg(prueth->miig_rt, emac); @@ -376,7 +497,10 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) writeb(0, config + SPL_PKT_DEFAULT_PRIORITY); writeb(0, config + QUEUE_NUM_UNTAGGED); - ret = prueth_emac_buffer_setup(emac); + if (prueth->is_switch_mode) + ret = prueth_switch_buffer_setup(emac); + else + ret = prueth_emac_buffer_setup(emac); if (ret) return ret; @@ -477,3 +601,173 @@ void icssg_config_set_speed(struct prueth_emac *emac) writeb(fw_speed, emac->dram.va + PORT_LINK_SPEED_OFFSET); } + +int icssg_send_fdb_msg(struct prueth_emac *emac, struct mgmt_cmd *cmd, + struct mgmt_cmd_rsp *rsp) +{ + struct prueth *prueth = emac->prueth; + int slice = prueth_emac_slice(emac); + int addr, ret; + + addr = icssg_queue_pop(prueth, slice == 0 ? + ICSSG_CMD_POP_SLICE0 : ICSSG_CMD_POP_SLICE1); + if (addr < 0) + return addr; + + /* First 4 bytes have FW owned buffer linking info which should + * not be touched + */ + memcpy_toio(prueth->shram.va + addr + 4, cmd, sizeof(*cmd)); + icssg_queue_push(prueth, slice == 0 ? + ICSSG_CMD_PUSH_SLICE0 : ICSSG_CMD_PUSH_SLICE1, addr); + ret = read_poll_timeout(icssg_queue_pop, addr, addr >= 0, + 2000, 20000000, false, prueth, slice == 0 ? + ICSSG_RSP_POP_SLICE0 : ICSSG_RSP_POP_SLICE1); + if (ret) { + netdev_err(emac->ndev, "Timedout sending HWQ message\n"); + return ret; + } + + memcpy_fromio(rsp, prueth->shram.va + addr, sizeof(*rsp)); + /* Return buffer back for to pool */ + icssg_queue_push(prueth, slice == 0 ? + ICSSG_RSP_PUSH_SLICE0 : ICSSG_RSP_PUSH_SLICE1, addr); + + return 0; +} + +static void icssg_fdb_setup(struct prueth_emac *emac, struct mgmt_cmd *fdb_cmd, + const unsigned char *addr, u8 fid, int cmd) +{ + int slice = prueth_emac_slice(emac); + u8 mac_fid[ETH_ALEN + 2]; + u16 fdb_slot; + + ether_addr_copy(mac_fid, addr); + + /* 1-1 VID-FID mapping is already setup */ + mac_fid[ETH_ALEN] = fid; + mac_fid[ETH_ALEN + 1] = 0; + + fdb_slot = bitrev32(crc32_le(0, mac_fid, 8)) & PRUETH_SWITCH_FDB_MASK; + + fdb_cmd->header = ICSSG_FW_MGMT_CMD_HEADER; + fdb_cmd->type = ICSSG_FW_MGMT_FDB_CMD_TYPE; + fdb_cmd->seqnum = ++(emac->prueth->icssg_hwcmdseq); + fdb_cmd->param = cmd; + fdb_cmd->param |= (slice << 4); + + memcpy(&fdb_cmd->cmd_args[0], addr, 4); + memcpy(&fdb_cmd->cmd_args[1], &addr[4], 2); + fdb_cmd->cmd_args[2] = fdb_slot; + + netdev_dbg(emac->ndev, "MAC %pM slot %X FID %X\n", addr, fdb_slot, fid); +} + +int icssg_fdb_add_del(struct prueth_emac *emac, const unsigned char *addr, + u8 vid, u8 fid_c2, bool add) +{ + struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 }; + struct mgmt_cmd fdb_cmd = { 0 }; + u8 fid = vid; + int ret; + + icssg_fdb_setup(emac, &fdb_cmd, addr, fid, add ? ICSS_CMD_ADD_FDB : ICSS_CMD_DEL_FDB); + + fid_c2 |= ICSSG_FDB_ENTRY_VALID; + fdb_cmd.cmd_args[1] |= ((fid << 16) | (fid_c2 << 24)); + + ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp); + if (ret) + return ret; + + WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum); + if (fdb_cmd_rsp.status == 1) + return 0; + + return -EINVAL; +} + +int icssg_fdb_lookup(struct prueth_emac *emac, const unsigned char *addr, + u8 vid) +{ + struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 }; + struct mgmt_cmd fdb_cmd = { 0 }; + struct prueth_fdb_slot *slot; + u8 fid = vid; + int ret, i; + + icssg_fdb_setup(emac, &fdb_cmd, addr, fid, ICSS_CMD_GET_FDB_SLOT); + + fdb_cmd.cmd_args[1] |= fid << 16; + + ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp); + if (ret) + return ret; + + WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum); + + slot = (struct prueth_fdb_slot __force *)(emac->dram.va + FDB_CMD_BUFFER); + for (i = 0; i < 4; i++) { + if (ether_addr_equal(addr, slot->mac) && vid == slot->fid) + return (slot->fid_c2 & ~ICSSG_FDB_ENTRY_VALID); + slot++; + } + + return 0; +} + +void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask, + u8 untag_mask, bool add) +{ + struct prueth *prueth = emac->prueth; + struct prueth_vlan_tbl *tbl; + u8 fid_c1; + + tbl = prueth->vlan_tbl; + fid_c1 = tbl[vid].fid_c1; + + /* FID_C1: bit0..2 port membership mask, + * bit3..5 tagging mask for each port + * bit6 Stream VID (not handled currently) + * bit7 MC flood (not handled currently) + */ + if (add) { + fid_c1 |= (port_mask | port_mask << 3); + fid_c1 &= ~(untag_mask << 3); + } else { + fid_c1 &= ~(port_mask | port_mask << 3); + } + + tbl[vid].fid_c1 = fid_c1; +} + +u16 icssg_get_pvid(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + u32 pvid; + + if (emac->port_id == PRUETH_PORT_MII0) + pvid = readl(prueth->shram.va + EMAC_ICSSG_SWITCH_PORT1_DEFAULT_VLAN_OFFSET); + else + pvid = readl(prueth->shram.va + EMAC_ICSSG_SWITCH_PORT2_DEFAULT_VLAN_OFFSET); + + pvid = pvid >> 24; + + return pvid; +} + +void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port) +{ + u32 pvid; + + /* only 256 VLANs are supported */ + pvid = (u32 __force)cpu_to_be32((ETH_P_8021Q << 16) | (vid & 0xff)); + + if (port == PRUETH_PORT_MII0) + writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT1_DEFAULT_VLAN_OFFSET); + else if (port == PRUETH_PORT_MII1) + writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT2_DEFAULT_VLAN_OFFSET); + else + writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET); +} diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index cf2ea4bd22a2..1ac60283923b 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -35,6 +35,15 @@ struct icssg_flow_cfg { (2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \ PRUETH_EMAC_RX_CTX_BUF_SIZE * 2)) +#define PRUETH_SW_BUF_POOL_SIZE_HOST SZ_4K +#define PRUETH_SW_NUM_BUF_POOLS_HOST 8 +#define PRUETH_SW_NUM_BUF_POOLS_PER_PRU 4 +#define MSMC_RAM_SIZE_SWITCH_MODE \ + (MSMC_RAM_SIZE + \ + (2 * PRUETH_SW_BUF_POOL_SIZE_HOST * PRUETH_SW_NUM_BUF_POOLS_HOST)) + +#define PRUETH_SWITCH_FDB_MASK ((SIZE_OF_FDB / NUMBER_OF_FDB_BUCKET_ENTRIES) - 1) + struct icssg_rxq_ctx { __le32 start[3]; __le32 end; @@ -202,6 +211,23 @@ struct icssg_setclock_desc { #define ICSSG_TS_PUSH_SLICE0 40 #define ICSSG_TS_PUSH_SLICE1 41 +struct mgmt_cmd { + u8 param; + u8 seqnum; + u8 type; + u8 header; + u32 cmd_args[3]; +}; + +struct mgmt_cmd_rsp { + u32 reserved; + u8 status; + u8 seqnum; + u8 type; + u8 header; + u32 cmd_args[3]; +}; + /* FDB FID_C2 flag definitions */ /* Indicates host port membership.*/ #define ICSSG_FDB_ENTRY_P0_MEMBERSHIP BIT(0) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 1ea3fbd5e954..6e65aa0977d4 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -27,13 +27,19 @@ #include <linux/remoteproc/pruss.h> #include <linux/regmap.h> #include <linux/remoteproc.h> +#include <net/switchdev.h> #include "icssg_prueth.h" #include "icssg_mii_rt.h" +#include "icssg_switchdev.h" #include "../k3-cppi-desc-pool.h" #define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG Ethernet driver" +#define DEFAULT_VID 1 +#define DEFAULT_PORT_MASK 1 +#define DEFAULT_UNTAG_MASK 1 + /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) @@ -112,6 +118,19 @@ static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id) return IRQ_HANDLED; } +static struct icssg_firmwares icssg_switch_firmwares[] = { + { + .pru = "ti-pruss/am65x-sr2-pru0-prusw-fw.elf", + .rtu = "ti-pruss/am65x-sr2-rtu0-prusw-fw.elf", + .txpru = "ti-pruss/am65x-sr2-txpru0-prusw-fw.elf", + }, + { + .pru = "ti-pruss/am65x-sr2-pru1-prusw-fw.elf", + .rtu = "ti-pruss/am65x-sr2-rtu1-prusw-fw.elf", + .txpru = "ti-pruss/am65x-sr2-txpru1-prusw-fw.elf", + } +}; + static struct icssg_firmwares icssg_emac_firmwares[] = { { .pru = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf", @@ -131,7 +150,10 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) struct device *dev = prueth->dev; int slice, ret; - firmwares = icssg_emac_firmwares; + if (prueth->is_switch_mode) + firmwares = icssg_switch_firmwares; + else + firmwares = icssg_emac_firmwares; slice = prueth_emac_slice(emac); if (slice < 0) { @@ -445,9 +467,8 @@ static int emac_ndo_open(struct net_device *ndev) ether_addr_copy(emac->mac_addr, ndev->dev_addr); icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); - icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); - icssg_class_default(prueth->miig_rt, slice, 0, false); + icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); /* Notify the stack of the actual queue counts. */ ret = netif_set_real_num_tx_queues(ndev, num_data_chn); @@ -833,6 +854,214 @@ free_ndev: return ret; } +bool prueth_dev_check(const struct net_device *ndev) +{ + if (ndev->netdev_ops == &emac_netdev_ops && netif_running(ndev)) { + struct prueth_emac *emac = netdev_priv(ndev); + + return emac->prueth->is_switch_mode; + } + + return false; +} + +static void prueth_offload_fwd_mark_update(struct prueth *prueth) +{ + int set_val = 0; + int i; + + if (prueth->br_members == (BIT(PRUETH_PORT_MII0) | BIT(PRUETH_PORT_MII1))) + set_val = 1; + + dev_dbg(prueth->dev, "set offload_fwd_mark %d\n", set_val); + + for (i = PRUETH_MAC0; i < PRUETH_NUM_MACS; i++) { + struct prueth_emac *emac = prueth->emac[i]; + + if (!emac || !emac->ndev) + continue; + + emac->offload_fwd_mark = set_val; + } +} + +static void prueth_emac_restart(struct prueth *prueth) +{ + struct prueth_emac *emac0 = prueth->emac[PRUETH_MAC0]; + struct prueth_emac *emac1 = prueth->emac[PRUETH_MAC1]; + + /* Detach the net_device for both PRUeth ports*/ + if (netif_running(emac0->ndev)) + netif_device_detach(emac0->ndev); + if (netif_running(emac1->ndev)) + netif_device_detach(emac1->ndev); + + /* Disable both PRUeth ports */ + emac_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE); + emac_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE); + + /* Stop both pru cores for both PRUeth ports*/ + prueth_emac_stop(emac0); + prueth->emacs_initialized--; + prueth_emac_stop(emac1); + prueth->emacs_initialized--; + + /* Start both pru cores for both PRUeth ports */ + prueth_emac_start(prueth, emac0); + prueth->emacs_initialized++; + prueth_emac_start(prueth, emac1); + prueth->emacs_initialized++; + + /* Enable forwarding for both PRUeth ports */ + emac_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD); + emac_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD); + + /* Attache net_device for both PRUeth ports */ + netif_device_attach(emac0->ndev); + netif_device_attach(emac1->ndev); +} + +static void icssg_enable_switch_mode(struct prueth *prueth) +{ + struct prueth_emac *emac; + int mac; + + prueth_emac_restart(prueth); + + for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { + emac = prueth->emac[mac]; + if (netif_running(emac->ndev)) { + icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan, + ICSSG_FDB_ENTRY_P0_MEMBERSHIP | + ICSSG_FDB_ENTRY_P1_MEMBERSHIP | + ICSSG_FDB_ENTRY_P2_MEMBERSHIP | + ICSSG_FDB_ENTRY_BLOCK, + true); + icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID, + BIT(emac->port_id) | DEFAULT_PORT_MASK, + BIT(emac->port_id) | DEFAULT_UNTAG_MASK, + true); + icssg_set_pvid(prueth, emac->port_vlan, emac->port_id); + emac_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE); + } + } +} + +static int prueth_netdevice_port_link(struct net_device *ndev, + struct net_device *br_ndev, + struct netlink_ext_ack *extack) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + int err; + + if (!prueth->br_members) { + prueth->hw_bridge_dev = br_ndev; + } else { + /* This is adding the port to a second bridge, this is + * unsupported + */ + if (prueth->hw_bridge_dev != br_ndev) + return -EOPNOTSUPP; + } + + err = switchdev_bridge_port_offload(br_ndev, ndev, emac, + &prueth->prueth_switchdev_nb, + &prueth->prueth_switchdev_bl_nb, + false, extack); + if (err) + return err; + + prueth->br_members |= BIT(emac->port_id); + + if (!prueth->is_switch_mode) { + if (prueth->br_members & BIT(PRUETH_PORT_MII0) && + prueth->br_members & BIT(PRUETH_PORT_MII1)) { + prueth->is_switch_mode = true; + prueth->default_vlan = 1; + emac->port_vlan = prueth->default_vlan; + icssg_enable_switch_mode(prueth); + } + } + + prueth_offload_fwd_mark_update(prueth); + + return NOTIFY_DONE; +} + +static void prueth_netdevice_port_unlink(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + + prueth->br_members &= ~BIT(emac->port_id); + + if (prueth->is_switch_mode) { + prueth->is_switch_mode = false; + emac->port_vlan = 0; + prueth_emac_restart(prueth); + } + + prueth_offload_fwd_mark_update(prueth); + + if (!prueth->br_members) + prueth->hw_bridge_dev = NULL; +} + +/* netdev notifier */ +static int prueth_netdevice_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info; + int ret = NOTIFY_DONE; + + if (ndev->netdev_ops != &emac_netdev_ops) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_CHANGEUPPER: + info = ptr; + + if (netif_is_bridge_master(info->upper_dev)) { + if (info->linking) + ret = prueth_netdevice_port_link(ndev, info->upper_dev, extack); + else + prueth_netdevice_port_unlink(ndev); + } + break; + default: + return NOTIFY_DONE; + } + + return notifier_from_errno(ret); +} + +static int prueth_register_notifiers(struct prueth *prueth) +{ + int ret = 0; + + prueth->prueth_netdevice_nb.notifier_call = &prueth_netdevice_event; + ret = register_netdevice_notifier(&prueth->prueth_netdevice_nb); + if (ret) { + dev_err(prueth->dev, "can't register netdevice notifier\n"); + return ret; + } + + ret = prueth_switchdev_register_notifiers(prueth); + if (ret) + unregister_netdevice_notifier(&prueth->prueth_netdevice_nb); + + return ret; +} + +static void prueth_unregister_notifiers(struct prueth *prueth) +{ + prueth_switchdev_unregister_notifiers(prueth); + unregister_netdevice_notifier(&prueth->prueth_netdevice_nb); +} + static int prueth_probe(struct platform_device *pdev) { struct device_node *eth_node, *eth_ports_node; @@ -960,6 +1189,9 @@ static int prueth_probe(struct platform_device *pdev) } msmc_ram_size = MSMC_RAM_SIZE; + prueth->is_switchmode_supported = prueth->pdata.switch_mode; + if (prueth->is_switchmode_supported) + msmc_ram_size = MSMC_RAM_SIZE_SWITCH_MODE; /* NOTE: FW bug needs buffer base to be 64KB aligned */ prueth->msmcram.va = @@ -1065,6 +1297,14 @@ static int prueth_probe(struct platform_device *pdev) phy_attached_info(prueth->emac[PRUETH_MAC1]->ndev->phydev); } + if (prueth->is_switchmode_supported) { + ret = prueth_register_notifiers(prueth); + if (ret) + goto netdev_unregister; + + sprintf(prueth->switch_id, "%s", dev_name(dev)); + } + dev_info(dev, "TI PRU ethernet driver initialized: %s EMAC mode\n", (!eth0_node || !eth1_node) ? "single" : "dual"); @@ -1134,6 +1374,8 @@ static void prueth_remove(struct platform_device *pdev) struct device_node *eth_node; int i; + prueth_unregister_notifiers(prueth); + for (i = 0; i < PRUETH_NUM_MACS; i++) { if (!prueth->registered_netdevs[i]) continue; @@ -1175,10 +1417,12 @@ static void prueth_remove(struct platform_device *pdev) static const struct prueth_pdata am654_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, .quirk_10m_link_issue = 1, + .switch_mode = 1, }; static const struct prueth_pdata am64x_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_RING, + .switch_mode = 1, }; static const struct of_device_id prueth_dt_match[] = { diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index a78c5eb75fb8..5eeeccb73665 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -186,6 +186,9 @@ struct prueth_emac { struct pruss_mem_region dram; + bool offload_fwd_mark; + int port_vlan; + struct delayed_work stats_work; u64 stats[ICSSG_NUM_STATS]; @@ -198,10 +201,12 @@ struct prueth_emac { * struct prueth_pdata - PRUeth platform data * @fdqring_mode: Free desc queue mode * @quirk_10m_link_issue: 10M link detect errata + * @switch_mode: switch firmware support */ struct prueth_pdata { enum k3_ring_mode fdqring_mode; u32 quirk_10m_link_issue:1; + u32 switch_mode:1; }; struct icssg_firmwares { @@ -232,6 +237,16 @@ struct icssg_firmwares { * @emacs_initialized: num of EMACs/ext ports that are up/running * @iep0: pointer to IEP0 device * @iep1: pointer to IEP1 device + * @vlan_tbl: VLAN-FID table pointer + * @hw_bridge_dev: pointer to HW bridge net device + * @br_members: bitmask of bridge member ports + * @prueth_netdevice_nb: netdevice notifier block + * @prueth_switchdev_nb: switchdev notifier block + * @prueth_switchdev_bl_nb: switchdev blocking notifier block + * @is_switch_mode: flag to indicate if device is in Switch mode + * @is_switchmode_supported: indicates platform support for switch mode + * @switch_id: ID for mapping switch ports to bridge + * @default_vlan: Default VLAN for host */ struct prueth { struct device *dev; @@ -256,6 +271,17 @@ struct prueth { int emacs_initialized; struct icss_iep *iep0; struct icss_iep *iep1; + struct prueth_vlan_tbl *vlan_tbl; + + struct net_device *hw_bridge_dev; + u8 br_members; + struct notifier_block prueth_netdevice_nb; + struct notifier_block prueth_switchdev_nb; + struct notifier_block prueth_switchdev_bl_nb; + bool is_switch_mode; + bool is_switchmode_supported; + unsigned char switch_id[MAX_PHYS_ITEM_ID_LEN]; + int default_vlan; }; struct emac_tx_ts_response { @@ -313,6 +339,16 @@ int icssg_queue_pop(struct prueth *prueth, u8 queue); void icssg_queue_push(struct prueth *prueth, int queue, u16 addr); u32 icssg_queue_level(struct prueth *prueth, int queue); +int icssg_send_fdb_msg(struct prueth_emac *emac, struct mgmt_cmd *cmd, + struct mgmt_cmd_rsp *rsp); +int icssg_fdb_add_del(struct prueth_emac *emac, const unsigned char *addr, + u8 vid, u8 fid_c2, bool add); +int icssg_fdb_lookup(struct prueth_emac *emac, const unsigned char *addr, + u8 vid); +void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask, + u8 untag_mask, bool add); +u16 icssg_get_pvid(struct prueth_emac *emac); +void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port); #define prueth_napi_to_tx_chn(pnapi) \ container_of(pnapi, struct prueth_tx_chn, napi_tx) diff --git a/drivers/net/ethernet/ti/icssg/icssg_switchdev.c b/drivers/net/ethernet/ti/icssg/icssg_switchdev.c new file mode 100644 index 000000000000..fceb8bb7d34e --- /dev/null +++ b/drivers/net/ethernet/ti/icssg/icssg_switchdev.c @@ -0,0 +1,477 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Texas Instruments K3 ICSSG Ethernet Switchdev Driver + * + * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/ + * + */ + +#include <linux/etherdevice.h> +#include <linux/if_bridge.h> +#include <linux/netdevice.h> +#include <linux/workqueue.h> +#include <net/switchdev.h> + +#include "icssg_prueth.h" +#include "icssg_switchdev.h" +#include "icssg_mii_rt.h" + +struct prueth_switchdev_event_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct prueth_emac *emac; + unsigned long event; +}; + +static int prueth_switchdev_stp_state_set(struct prueth_emac *emac, + u8 state) +{ + enum icssg_port_state_cmd emac_state; + int ret = 0; + + switch (state) { + case BR_STATE_FORWARDING: + emac_state = ICSSG_EMAC_PORT_FORWARD; + break; + case BR_STATE_DISABLED: + emac_state = ICSSG_EMAC_PORT_DISABLE; + break; + case BR_STATE_LISTENING: + case BR_STATE_BLOCKING: + emac_state = ICSSG_EMAC_PORT_BLOCK; + break; + default: + return -EOPNOTSUPP; + } + + emac_set_port_state(emac, emac_state); + netdev_dbg(emac->ndev, "STP state: %u\n", emac_state); + + return ret; +} + +static int prueth_switchdev_attr_br_flags_set(struct prueth_emac *emac, + struct net_device *orig_dev, + struct switchdev_brport_flags brport_flags) +{ + enum icssg_port_state_cmd emac_state; + + if (brport_flags.mask & BR_MCAST_FLOOD) + emac_state = ICSSG_EMAC_PORT_MC_FLOODING_ENABLE; + else + emac_state = ICSSG_EMAC_PORT_MC_FLOODING_DISABLE; + + netdev_dbg(emac->ndev, "BR_MCAST_FLOOD: %d port %u\n", + emac_state, emac->port_id); + + emac_set_port_state(emac, emac_state); + + return 0; +} + +static int prueth_switchdev_attr_br_flags_pre_set(struct net_device *netdev, + struct switchdev_brport_flags brport_flags) +{ + if (brport_flags.mask & ~(BR_LEARNING | BR_MCAST_FLOOD)) + return -EINVAL; + + return 0; +} + +static int prueth_switchdev_attr_set(struct net_device *ndev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct prueth_emac *emac = netdev_priv(ndev); + int ret; + + netdev_dbg(ndev, "attr: id %u port: %u\n", attr->id, emac->port_id); + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: + ret = prueth_switchdev_attr_br_flags_pre_set(ndev, + attr->u.brport_flags); + break; + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: + ret = prueth_switchdev_stp_state_set(emac, + attr->u.stp_state); + netdev_dbg(ndev, "stp state: %u\n", attr->u.stp_state); + break; + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + ret = prueth_switchdev_attr_br_flags_set(emac, attr->orig_dev, + attr->u.brport_flags); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + +static void prueth_switchdev_fdb_offload_notify(struct net_device *ndev, + struct switchdev_notifier_fdb_info *rcv) +{ + struct switchdev_notifier_fdb_info info; + + memset(&info, 0, sizeof(info)); + info.addr = rcv->addr; + info.vid = rcv->vid; + info.offloaded = true; + call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, + ndev, &info.info, NULL); +} + +static void prueth_switchdev_event_work(struct work_struct *work) +{ + struct prueth_switchdev_event_work *switchdev_work = + container_of(work, struct prueth_switchdev_event_work, work); + struct prueth_emac *emac = switchdev_work->emac; + struct switchdev_notifier_fdb_info *fdb; + int port_id = emac->port_id; + int ret; + + rtnl_lock(); + switch (switchdev_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + fdb = &switchdev_work->fdb_info; + + netdev_dbg(emac->ndev, "prueth_fdb_add: MACID = %pM vid = %u flags = %u %u -- port %d\n", + fdb->addr, fdb->vid, fdb->added_by_user, + fdb->offloaded, port_id); + + if (!fdb->added_by_user) + break; + if (!ether_addr_equal(emac->mac_addr, fdb->addr)) + break; + + ret = icssg_fdb_add_del(emac, fdb->addr, fdb->vid, + BIT(port_id), true); + if (!ret) + prueth_switchdev_fdb_offload_notify(emac->ndev, fdb); + break; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb = &switchdev_work->fdb_info; + + netdev_dbg(emac->ndev, "prueth_fdb_del: MACID = %pM vid = %u flags = %u %u -- port %d\n", + fdb->addr, fdb->vid, fdb->added_by_user, + fdb->offloaded, port_id); + + if (!fdb->added_by_user) + break; + if (!ether_addr_equal(emac->mac_addr, fdb->addr)) + break; + icssg_fdb_add_del(emac, fdb->addr, fdb->vid, + BIT(port_id), false); + break; + default: + break; + } + rtnl_unlock(); + + kfree(switchdev_work->fdb_info.addr); + kfree(switchdev_work); + dev_put(emac->ndev); +} + +static int prueth_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *ndev = switchdev_notifier_info_to_dev(ptr); + struct prueth_switchdev_event_work *switchdev_work; + struct switchdev_notifier_fdb_info *fdb_info = ptr; + struct prueth_emac *emac = netdev_priv(ndev); + int err; + + if (!prueth_dev_check(ndev)) + return NOTIFY_DONE; + + if (event == SWITCHDEV_PORT_ATTR_SET) { + err = switchdev_handle_port_attr_set(ndev, ptr, + prueth_dev_check, + prueth_switchdev_attr_set); + return notifier_from_errno(err); + } + + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (WARN_ON(!switchdev_work)) + return NOTIFY_BAD; + + INIT_WORK(&switchdev_work->work, prueth_switchdev_event_work); + switchdev_work->emac = emac; + switchdev_work->event = event; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + memcpy(&switchdev_work->fdb_info, ptr, + sizeof(switchdev_work->fdb_info)); + switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!switchdev_work->fdb_info.addr) + goto err_addr_alloc; + ether_addr_copy((u8 *)switchdev_work->fdb_info.addr, + fdb_info->addr); + dev_hold(ndev); + break; + default: + kfree(switchdev_work); + return NOTIFY_DONE; + } + + queue_work(system_long_wq, &switchdev_work->work); + + return NOTIFY_DONE; + +err_addr_alloc: + kfree(switchdev_work); + return NOTIFY_BAD; +} + +static int prueth_switchdev_vlan_add(struct prueth_emac *emac, bool untag, bool pvid, + u8 vid, struct net_device *orig_dev) +{ + bool cpu_port = netif_is_bridge_master(orig_dev); + int untag_mask = 0; + int port_mask; + int ret = 0; + + if (cpu_port) + port_mask = BIT(PRUETH_PORT_HOST); + else + port_mask = BIT(emac->port_id); + + if (untag) + untag_mask = port_mask; + + icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true); + + netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X PVID %d\n", + vid, port_mask, untag_mask, pvid); + + if (!pvid) + return ret; + + icssg_set_pvid(emac->prueth, vid, emac->port_id); + + return ret; +} + +static int prueth_switchdev_vlan_del(struct prueth_emac *emac, u16 vid, + struct net_device *orig_dev) +{ + bool cpu_port = netif_is_bridge_master(orig_dev); + int port_mask; + int ret = 0; + + if (cpu_port) + port_mask = BIT(PRUETH_PORT_HOST); + else + port_mask = BIT(emac->port_id); + + icssg_vtbl_modify(emac, vid, port_mask, 0, false); + + if (cpu_port) + icssg_fdb_add_del(emac, emac->mac_addr, vid, + BIT(PRUETH_PORT_HOST), false); + + if (vid == icssg_get_pvid(emac)) + icssg_set_pvid(emac->prueth, 0, emac->port_id); + + netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X\n", + vid, port_mask); + + return ret; +} + +static int prueth_switchdev_vlans_add(struct prueth_emac *emac, + const struct switchdev_obj_port_vlan *vlan) +{ + 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(emac->ndev, "VID add vid:%u flags:%X\n", + vlan->vid, vlan->flags); + + if (cpu_port && !(vlan->flags & BRIDGE_VLAN_INFO_BRENTRY)) + return 0; + + if (vlan->vid > 0xff) + return 0; + + return prueth_switchdev_vlan_add(emac, untag, pvid, vlan->vid, + orig_dev); +} + +static int prueth_switchdev_vlans_del(struct prueth_emac *emac, + const struct switchdev_obj_port_vlan *vlan) +{ + if (vlan->vid > 0xff) + return 0; + + return prueth_switchdev_vlan_del(emac, vlan->vid, + vlan->obj.orig_dev); +} + +static int prueth_switchdev_mdb_add(struct prueth_emac *emac, + struct switchdev_obj_port_mdb *mdb) +{ + struct net_device *orig_dev = mdb->obj.orig_dev; + u8 port_mask, fid_c2; + bool cpu_port; + int err; + + cpu_port = netif_is_bridge_master(orig_dev); + + if (cpu_port) + port_mask = BIT(PRUETH_PORT_HOST); + else + port_mask = BIT(emac->port_id); + + fid_c2 = icssg_fdb_lookup(emac, mdb->addr, mdb->vid); + + err = icssg_fdb_add_del(emac, mdb->addr, mdb->vid, fid_c2 | port_mask, true); + netdev_dbg(emac->ndev, "MDB add vid %u:%pM ports: %X\n", + mdb->vid, mdb->addr, port_mask); + + return err; +} + +static int prueth_switchdev_mdb_del(struct prueth_emac *emac, + struct switchdev_obj_port_mdb *mdb) +{ + struct net_device *orig_dev = mdb->obj.orig_dev; + int del_mask, ret, fid_c2; + bool cpu_port; + + cpu_port = netif_is_bridge_master(orig_dev); + + if (cpu_port) + del_mask = BIT(PRUETH_PORT_HOST); + else + del_mask = BIT(emac->port_id); + + fid_c2 = icssg_fdb_lookup(emac, mdb->addr, mdb->vid); + + if (fid_c2 & ~del_mask) + ret = icssg_fdb_add_del(emac, mdb->addr, mdb->vid, fid_c2 & ~del_mask, true); + else + ret = icssg_fdb_add_del(emac, mdb->addr, mdb->vid, 0, false); + + netdev_dbg(emac->ndev, "MDB del vid %u:%pM ports: %X\n", + mdb->vid, mdb->addr, del_mask); + + return ret; +} + +static int prueth_switchdev_obj_add(struct net_device *ndev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + struct switchdev_obj_port_mdb *mdb = SWITCHDEV_OBJ_PORT_MDB(obj); + struct prueth_emac *emac = netdev_priv(ndev); + int err = 0; + + netdev_dbg(ndev, "obj_add: id %u port: %u\n", obj->id, emac->port_id); + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + err = prueth_switchdev_vlans_add(emac, vlan); + break; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + err = prueth_switchdev_mdb_add(emac, mdb); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int prueth_switchdev_obj_del(struct net_device *ndev, const void *ctx, + const struct switchdev_obj *obj) +{ + struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + struct switchdev_obj_port_mdb *mdb = SWITCHDEV_OBJ_PORT_MDB(obj); + struct prueth_emac *emac = netdev_priv(ndev); + int err = 0; + + netdev_dbg(ndev, "obj_del: id %u port: %u\n", obj->id, emac->port_id); + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + err = prueth_switchdev_vlans_del(emac, vlan); + break; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + err = prueth_switchdev_mdb_del(emac, mdb); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int prueth_switchdev_blocking_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add(dev, ptr, + prueth_dev_check, + prueth_switchdev_obj_add); + return notifier_from_errno(err); + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del(dev, ptr, + prueth_dev_check, + prueth_switchdev_obj_del); + return notifier_from_errno(err); + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + prueth_dev_check, + prueth_switchdev_attr_set); + return notifier_from_errno(err); + default: + break; + } + + return NOTIFY_DONE; +} + +int prueth_switchdev_register_notifiers(struct prueth *prueth) +{ + int ret = 0; + + prueth->prueth_switchdev_nb.notifier_call = &prueth_switchdev_event; + ret = register_switchdev_notifier(&prueth->prueth_switchdev_nb); + if (ret) { + dev_err(prueth->dev, "register switchdev notifier fail ret:%d\n", + ret); + return ret; + } + + prueth->prueth_switchdev_bl_nb.notifier_call = &prueth_switchdev_blocking_event; + ret = register_switchdev_blocking_notifier(&prueth->prueth_switchdev_bl_nb); + if (ret) { + dev_err(prueth->dev, "register switchdev blocking notifier ret:%d\n", + ret); + unregister_switchdev_notifier(&prueth->prueth_switchdev_nb); + } + + return ret; +} + +void prueth_switchdev_unregister_notifiers(struct prueth *prueth) +{ + unregister_switchdev_blocking_notifier(&prueth->prueth_switchdev_bl_nb); + unregister_switchdev_notifier(&prueth->prueth_switchdev_nb); +} diff --git a/drivers/net/ethernet/ti/icssg/icssg_switchdev.h b/drivers/net/ethernet/ti/icssg/icssg_switchdev.h new file mode 100644 index 000000000000..0e64e7760a00 --- /dev/null +++ b/drivers/net/ethernet/ti/icssg/icssg_switchdev.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com/ + */ +#ifndef __NET_TI_ICSSG_SWITCHDEV_H +#define __NET_TI_ICSSG_SWITCHDEV_H + +#include "icssg_prueth.h" + +int prueth_switchdev_register_notifiers(struct prueth *prueth); +void prueth_switchdev_unregister_notifiers(struct prueth *prueth); +bool prueth_dev_check(const struct net_device *ndev); + +#endif /* __NET_TI_ICSSG_SWITCHDEV_H */ diff --git a/drivers/net/fjes/fjes_trace.h b/drivers/net/fjes/fjes_trace.h index 166ef015262b..37c6071cb333 100644 --- a/drivers/net/fjes/fjes_trace.h +++ b/drivers/net/fjes/fjes_trace.h @@ -358,7 +358,7 @@ TRACE_EVENT(fjes_stop_req_irq_post, #undef TRACE_INCLUDE_PATH #undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_PATH ../../../drivers/net/fjes +#define TRACE_INCLUDE_PATH ../../drivers/net/fjes #define TRACE_INCLUDE_FILE fjes_trace /* This part must be outside protection */ diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index d7070dd4fe73..ab8a0623b1a1 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -1262,6 +1262,8 @@ static int __init init_netconsole(void) while ((target_config = strsep(&input, ";"))) { nt = alloc_param_target(target_config, count); if (IS_ERR(nt)) { + if (IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) + continue; err = PTR_ERR(nt); goto fail; } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 994471fad833..02427378acfd 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -885,26 +885,31 @@ static int phylink_parse_mode(struct phylink *pl, const char *managed; unsigned long caps; + if (pl->config->default_an_inband) + pl->cfg_link_an_mode = MLO_AN_INBAND; + dn = fwnode_get_named_child_node(fwnode, "fixed-link"); if (dn || fwnode_property_present(fwnode, "fixed-link")) pl->cfg_link_an_mode = MLO_AN_FIXED; fwnode_handle_put(dn); if ((fwnode_property_read_string(fwnode, "managed", &managed) == 0 && - strcmp(managed, "in-band-status") == 0) || - pl->config->ovr_an_inband) { + strcmp(managed, "in-band-status") == 0)) { if (pl->cfg_link_an_mode == MLO_AN_FIXED) { phylink_err(pl, "can't use both fixed-link and in-band-status\n"); return -EINVAL; } + pl->cfg_link_an_mode = MLO_AN_INBAND; + } + + if (pl->cfg_link_an_mode == MLO_AN_INBAND) { linkmode_zero(pl->supported); phylink_set(pl->supported, MII); phylink_set(pl->supported, Autoneg); phylink_set(pl->supported, Asym_Pause); phylink_set(pl->supported, Pause); - pl->cfg_link_an_mode = MLO_AN_INBAND; switch (pl->link_config.interface) { case PHY_INTERFACE_MODE_SGMII: diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index 7b1bc5fcef9b..7c51daecf18e 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -15,6 +15,7 @@ #include <linux/mii.h> #include <linux/mdio.h> #include <linux/phy.h> +#include <linux/clk.h> #include <linux/of_mdio.h> #define XILINX_GMII2RGMII_REG 0x10 @@ -85,11 +86,17 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev) struct device *dev = &mdiodev->dev; struct device_node *np = dev->of_node, *phy_node; struct gmii2rgmii *priv; + struct clk *clkin; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + clkin = devm_clk_get_optional_enabled(dev, NULL); + if (IS_ERR(clkin)) + return dev_err_probe(dev, PTR_ERR(clkin), + "Failed to get and enable clock from Device Tree\n"); + phy_node = of_parse_phandle(np, "phy-handle", 0); if (!phy_node) { dev_err(dev, "Couldn't parse phy-handle\n"); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 5a2c38b63012..7a5cc49ebec6 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -380,11 +380,6 @@ struct skb_data { /* skb->cb is one of these */ int num_of_packet; }; -struct usb_context { - struct usb_ctrlrequest req; - struct lan78xx_net *dev; -}; - #define EVENT_TX_HALT 0 #define EVENT_RX_HALT 1 #define EVENT_RX_MEMORY 2 diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 0726e18bee6f..78c821349f48 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -61,11 +61,6 @@ struct smsc75xx_priv { u8 suspend_flags; }; -struct usb_context { - struct usb_ctrlrequest req; - struct usbnet *dev; -}; - static bool turbo_mode = true; module_param(turbo_mode, bool, 0644); MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction"); diff --git a/include/linux/filter.h b/include/linux/filter.h index 0f12cf01070e..b02aea291b7e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1406,7 +1406,7 @@ struct bpf_sock_ops_kern { struct bpf_sysctl_kern { struct ctl_table_header *head; - struct ctl_table *table; + const struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 5ea6b2ad2396..a30a692acc32 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -141,7 +141,8 @@ enum phylink_op_type { * @mac_requires_rxc: if true, the MAC always requires a receive clock from PHY. * The PHY driver should start the clock signal as soon as * possible and avoid stopping it during suspend events. - * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND + * @default_an_inband: if true, defaults to MLO_AN_INBAND rather than + * MLO_AN_PHY. A fixed-link specification will override. * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx @@ -154,7 +155,7 @@ struct phylink_config { bool poll_fixed_state; bool mac_managed_pm; bool mac_requires_rxc; - bool ovr_an_inband; + bool default_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1c2902eaebd3..fe7d8dbef77e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -706,6 +706,13 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +enum skb_tstamp_type { + SKB_CLOCK_REALTIME, + SKB_CLOCK_MONOTONIC, + SKB_CLOCK_TAI, + __SKB_CLOCK_MAX = SKB_CLOCK_TAI, +}; + /** * DOC: Basic sk_buff geometry * @@ -823,10 +830,8 @@ typedef unsigned char *sk_buff_data_t; * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required - * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e. EDT). Otherwise, the - * skb->tstamp has the (rcv) timestamp at ingress and - * delivery_time at egress. + * @tstamp_type: When set, skb->tstamp has the + * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. @@ -954,7 +959,7 @@ struct sk_buff { /* private: */ __u8 __mono_tc_offset[0]; /* public: */ - __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ + __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; @@ -1084,15 +1089,16 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move tc_at_ingress or mono_delivery_time +/* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) -#define TC_AT_INGRESS_MASK (1 << 6) +#define SKB_TSTAMP_TYPE_MASK (3 << 6) +#define SKB_TSTAMP_TYPE_RSHIFT (6) +#define TC_AT_INGRESS_MASK (1 << 5) #else -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) -#define TC_AT_INGRESS_MASK (1 << 1) +#define SKB_TSTAMP_TYPE_MASK (3) +#define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) @@ -4179,7 +4185,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb, static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); - skb->mono_delivery_time = 0; + skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) @@ -4188,10 +4194,36 @@ static inline ktime_t net_timedelta(ktime_t t) } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, - bool mono) + u8 tstamp_type) { skb->tstamp = kt; - skb->mono_delivery_time = kt && mono; + + if (kt) + skb->tstamp_type = tstamp_type; + else + skb->tstamp_type = SKB_CLOCK_REALTIME; +} + +static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, + ktime_t kt, clockid_t clockid) +{ + u8 tstamp_type = SKB_CLOCK_REALTIME; + + switch (clockid) { + case CLOCK_REALTIME: + break; + case CLOCK_MONOTONIC: + tstamp_type = SKB_CLOCK_MONOTONIC; + break; + case CLOCK_TAI: + tstamp_type = SKB_CLOCK_TAI; + break; + default: + WARN_ON_ONCE(1); + kt = 0; + } + + skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); @@ -4201,8 +4233,8 @@ DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { - if (skb->mono_delivery_time) { - skb->mono_delivery_time = 0; + if (skb->tstamp_type) { + skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else @@ -4212,7 +4244,7 @@ static inline void skb_clear_delivery_time(struct sk_buff *skb) static inline void skb_clear_tstamp(struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return; skb->tstamp = 0; @@ -4220,7 +4252,7 @@ static inline void skb_clear_tstamp(struct sk_buff *skb) static inline ktime_t skb_tstamp(const struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return 0; return skb->tstamp; @@ -4228,7 +4260,7 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb) static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { - if (!skb->mono_delivery_time && skb->tstamp) + if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index f92c195c76ed..8f0f156d50d3 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -83,7 +83,7 @@ struct stmmac_priv; struct stmmac_mdio_bus_data { unsigned int phy_mask; unsigned int has_xpcs; - unsigned int xpcs_an_inband; + unsigned int default_an_inband; int *irqs; int probed_phy_irq; bool needs_reset; diff --git a/include/net/dsa.h b/include/net/dsa.h index b60e7e410aba..f9ae3ca66b6f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -882,15 +882,9 @@ struct dsa_switch_ops { struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, int port, phy_interface_t iface); - int (*phylink_mac_prepare)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface); void (*phylink_mac_config)(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); - int (*phylink_mac_finish)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface); void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 153960663ce4..5af6eb14c5db 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -76,7 +76,7 @@ struct frag_v6_compare_key { * @stamp: timestamp of the last received fragment * @len: total length of the original datagram * @meat: length of received fragments so far - * @mono_delivery_time: stamp has a mono delivery time (EDT) + * @tstamp_type: stamp has a mono delivery time (EDT) * @flags: fragment queue flags * @max_size: maximum received fragment size * @fqdir: pointer to struct fqdir @@ -97,7 +97,7 @@ struct inet_frag_queue { ktime_t stamp; int len; int meat; - u8 mono_delivery_time; + u8 tstamp_type; __u8 flags; u16 max_size; struct fqdir *fqdir; diff --git a/include/net/seg6.h b/include/net/seg6.h index af668f17b398..82b3fbbcbb93 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -52,10 +52,17 @@ static inline struct seg6_pernet_data *seg6_pernet(struct net *net) extern int seg6_init(void); extern void seg6_exit(void); +#ifdef CONFIG_IPV6_SEG6_LWTUNNEL extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); extern int seg6_local_init(void); extern void seg6_local_exit(void); +#else +static inline int seg6_iptunnel_init(void) { return 0; } +static inline void seg6_iptunnel_exit(void) {} +static inline int seg6_local_init(void) { return 0; } +static inline void seg6_local_exit(void) {} +#endif extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags); diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h index 2b5d2ee5613e..24f733b3e3fe 100644 --- a/include/net/seg6_hmac.h +++ b/include/net/seg6_hmac.h @@ -49,9 +49,16 @@ extern int seg6_hmac_info_del(struct net *net, u32 key); extern int seg6_push_hmac(struct net *net, struct in6_addr *saddr, struct ipv6_sr_hdr *srh); extern bool seg6_hmac_validate_skb(struct sk_buff *skb); +#ifdef CONFIG_IPV6_SEG6_HMAC extern int seg6_hmac_init(void); extern void seg6_hmac_exit(void); extern int seg6_hmac_net_init(struct net *net); extern void seg6_hmac_net_exit(struct net *net); +#else +static inline int seg6_hmac_init(void) { return 0; } +static inline void seg6_hmac_exit(void) {} +static inline int seg6_hmac_net_init(struct net *net) { return 0; } +static inline void seg6_hmac_net_exit(struct net *net) {} +#endif #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index 060e95b331a2..32815a40dea1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -677,6 +677,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); +void tcp_done_with_error(struct sock *sk, int err); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 90706a47f6ff..25ea393cf084 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6207,12 +6207,17 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ enum { - BPF_SKB_TSTAMP_UNSPEC, - BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ - /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, - * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC - * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. */ }; diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 976cb258a0ed..c938dea5ddbf 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -782,8 +782,8 @@ bpf_local_storage_map_alloc(union bpf_attr *attr, nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); - smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets), - nbuckets, GFP_USER | __GFP_NOWARN); + smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets, + sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN); if (!smap->buckets) { err = -ENOMEM; goto free_smap; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index c3c51b9a6826..816bb0fde718 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -32,7 +32,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; unsigned int hlen, ll_rs, mtu; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; @@ -82,7 +82,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, if (iter.frag) ip_fraglist_prepare(skb, &iter); - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -113,7 +113,7 @@ slow_path: goto blackhole; } - skb_set_delivery_time(skb2, tstamp, mono_delivery_time); + skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/core/dev.c b/net/core/dev.c index e1bb6d7856d9..85fe8138f3e4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2160,7 +2160,7 @@ EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; - skb->mono_delivery_time = 0; + skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); } diff --git a/net/core/filter.c b/net/core/filter.c index 2510464692af..7c46ecba3b01 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2274,12 +2274,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; @@ -2380,12 +2380,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; @@ -7726,17 +7726,21 @@ BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, return -EOPNOTSUPP; switch (tstamp_type) { - case BPF_SKB_TSTAMP_DELIVERY_MONO: + case BPF_SKB_CLOCK_REALTIME: + skb->tstamp = tstamp; + skb->tstamp_type = SKB_CLOCK_REALTIME; + break; + case BPF_SKB_CLOCK_MONOTONIC: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; - skb->mono_delivery_time = 1; + skb->tstamp_type = SKB_CLOCK_MONOTONIC; break; - case BPF_SKB_TSTAMP_UNSPEC: - if (tstamp) + case BPF_SKB_CLOCK_TAI: + if (!tstamp) return -EINVAL; - skb->tstamp = 0; - skb->mono_delivery_time = 0; + skb->tstamp = tstamp; + skb->tstamp_type = SKB_CLOCK_TAI; break; default: return -EINVAL; @@ -9387,16 +9391,17 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; - /* AX is needed because src_reg and dst_reg could be the same */ - __u8 tmp_reg = BPF_REG_AX; - - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, - SKB_BF_MONO_TC_OFFSET); - *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, - SKB_MONO_DELIVERY_TIME_MASK, 2); - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC); - *insn++ = BPF_JMP_A(1); - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO); + BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI); + BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME); + BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC); + BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI); + *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK); +#ifdef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT); +#else + BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1)); +#endif return insn; } @@ -9439,11 +9444,12 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, - TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg, - TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2); - /* skb->tc_at_ingress && skb->mono_delivery_time, + /* check if ingress mask bits is set */ + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); + *insn++ = BPF_JMP_A(4); + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1); + *insn++ = BPF_JMP_A(2); + /* skb->tc_at_ingress && skb->tstamp_type, * read 0 as the (rcv) timestamp. */ *insn++ = BPF_MOV64_IMM(value_reg, 0); @@ -9468,7 +9474,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, * the bpf prog is aware the tstamp could have delivery time. * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the - * mono_delivery_time bit also. + * skb->tstamp_type bit also. */ if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; @@ -9478,8 +9484,8 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); /* goto <store> */ *insn++ = BPF_JMP_A(2); - /* <clear>: mono_delivery_time */ - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK); + /* <clear>: skb->tstamp_type */ + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK); *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 45fd88405b6b..277751375b0a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3578,7 +3578,7 @@ static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, rcu_read_unlock(); } -static void neigh_proc_update(struct ctl_table *ctl, int write) +static void neigh_proc_update(const struct ctl_table *ctl, int write) { struct net_device *dev = ctl->extra1; struct neigh_parms *p = ctl->extra2; diff --git a/net/core/sock.c b/net/core/sock.c index 8629f9aecf91..521e6373d4f7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2262,7 +2262,12 @@ static void sk_init_common(struct sock *sk) lockdep_set_class_and_name(&sk->sk_error_queue.lock, af_elock_keys + sk->sk_family, af_family_elock_key_strings[sk->sk_family]); - lockdep_set_class_and_name(&sk->sk_callback_lock, + if (sk->sk_kern_sock) + lockdep_set_class_and_name(&sk->sk_callback_lock, + af_kern_callback_keys + sk->sk_family, + af_family_kern_clock_key_strings[sk->sk_family]); + else + lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); } @@ -3460,18 +3465,6 @@ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) } sk->sk_uid = uid; - rwlock_init(&sk->sk_callback_lock); - if (sk->sk_kern_sock) - lockdep_set_class_and_name( - &sk->sk_callback_lock, - af_kern_callback_keys + sk->sk_family, - af_family_kern_clock_key_strings[sk->sk_family]); - else - lockdep_set_class_and_name( - &sk->sk_callback_lock, - af_callback_keys + sk->sk_family, - af_family_clock_key_strings[sk->sk_family]); - sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 12521a7d4048..668c729946ea 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1507,9 +1507,7 @@ static int dsa_switch_probe(struct dsa_switch *ds) if (ds->phylink_mac_ops) { if (ds->ops->phylink_mac_select_pcs || - ds->ops->phylink_mac_prepare || ds->ops->phylink_mac_config || - ds->ops->phylink_mac_finish || ds->ops->phylink_mac_link_down || ds->ops->phylink_mac_link_up) return -EINVAL; diff --git a/net/dsa/port.c b/net/dsa/port.c index 9a249d4ac3a5..e23db9507546 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1549,21 +1549,6 @@ dsa_port_phylink_mac_select_pcs(struct phylink_config *config, return pcs; } -static int dsa_port_phylink_mac_prepare(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct dsa_switch *ds = dp->ds; - int err = 0; - - if (ds->ops->phylink_mac_prepare) - err = ds->ops->phylink_mac_prepare(ds, dp->index, mode, - interface); - - return err; -} - static void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -1577,21 +1562,6 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config, ds->ops->phylink_mac_config(ds, dp->index, mode, state); } -static int dsa_port_phylink_mac_finish(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct dsa_switch *ds = dp->ds; - int err = 0; - - if (ds->ops->phylink_mac_finish) - err = ds->ops->phylink_mac_finish(ds, dp->index, mode, - interface); - - return err; -} - static void dsa_port_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) @@ -1624,9 +1594,7 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .mac_select_pcs = dsa_port_phylink_mac_select_pcs, - .mac_prepare = dsa_port_phylink_mac_prepare, .mac_config = dsa_port_phylink_mac_config, - .mac_finish = dsa_port_phylink_mac_finish, .mac_link_down = dsa_port_phylink_mac_link_down, .mac_link_up = dsa_port_phylink_mac_link_up, }; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 56ef873828f4..867d637d86f0 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -130,7 +130,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, goto err; fq->q.stamp = skb->tstamp; - fq->q.mono_delivery_time = skb->mono_delivery_time; + fq->q.tstamp_type = skb->tstamp_type; if (frag_type == LOWPAN_DISPATCH_FRAG1) fq->q.flags |= INET_FRAG_FIRST_IN; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index faaec92a46ac..d179a2c84222 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -619,7 +619,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, skb_mark_not_on_list(head); head->prev = NULL; head->tstamp = q->stamp; - head->mono_delivery_time = q->mono_delivery_time; + head->tstamp_type = q->tstamp_type; if (sk) refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 08e2c92e25ab..a92664a5ef2e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -355,7 +355,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) qp->iif = dev->ifindex; qp->q.stamp = skb->tstamp; - qp->q.mono_delivery_time = skb->mono_delivery_time; + qp->q.tstamp_type = skb->tstamp_type; qp->q.meat += skb->len; qp->ecn |= ecn; add_frag_mem_limit(qp->q.fqdir, skb->truesize); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9500031a1f55..b90d0f78ac80 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -764,7 +764,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, { struct iphdr *iph; struct sk_buff *skb2; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; @@ -856,7 +856,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, } } - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) @@ -912,7 +912,7 @@ slow_path: /* * Put this fragment into the sending queue. */ - skb_set_delivery_time(skb2, tstamp, mono_delivery_time); + skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, skb2); if (err) goto fail; @@ -1457,7 +1457,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; - skb->tstamp = cork->transmit_time; + if (sk_is_tcp(sk)) + skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); + else + skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid); /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount @@ -1649,7 +1652,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - nskb->mono_delivery_time = !!transmit_time; + if (transmit_time) + nskb->tstamp_type = SKB_CLOCK_MONOTONIC; if (txhash) skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4cb43401e0e0..1a0953650356 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -360,7 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->protocol = htons(ETH_P_IP); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_dst_set(skb, &rt->dst); *rtp = NULL; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 162a0a3b6ba5..d7892f34a15b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -130,7 +130,8 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, return ret; } -static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high) +static void inet_get_ping_group_range_table(const struct ctl_table *table, + kgid_t *low, kgid_t *high) { kgid_t *data = table->data; struct net *net = @@ -145,7 +146,8 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low } /* Update system visible IP port range */ -static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high) +static void set_ping_group_range(const struct ctl_table *table, + kgid_t low, kgid_t high) { kgid_t *data = table->data; struct net *net = diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 681b54e1f3a6..5fa68e7f6ddb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -598,7 +598,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask |= EPOLLOUT | EPOLLWRNORM; } - /* This barrier is coupled with smp_wmb() in tcp_reset() */ + /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) @@ -4576,14 +4576,10 @@ int tcp_abort(struct sock *sk, int err) bh_lock_sock(sk); if (!sock_flag(sk, SOCK_DEAD)) { - WRITE_ONCE(sk->sk_err, err); - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - sk_error_report(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_NOT_SPECIFIED); - tcp_done(sk); + tcp_done_with_error(sk, err); } bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9c04a9c8be9d..5aadf64e554d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4436,9 +4436,26 @@ static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp, return SKB_NOT_DROPPED_YET; } + +void tcp_done_with_error(struct sock *sk, int err) +{ + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + WRITE_ONCE(sk->sk_err, err); + smp_wmb(); + + tcp_write_queue_purge(sk); + tcp_done(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); +} +EXPORT_SYMBOL(tcp_done_with_error); + /* When we get a reset we do this. */ void tcp_reset(struct sock *sk, struct sk_buff *skb) { + int err; + trace_tcp_receive_reset(sk); /* mptcp can't tell us to ignore reset pkts, @@ -4450,24 +4467,17 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) /* We want the right error as BSD sees it (and indeed as we do). */ switch (sk->sk_state) { case TCP_SYN_SENT: - WRITE_ONCE(sk->sk_err, ECONNREFUSED); + err = ECONNREFUSED; break; case TCP_CLOSE_WAIT: - WRITE_ONCE(sk->sk_err, EPIPE); + err = EPIPE; break; case TCP_CLOSE: return; default: - WRITE_ONCE(sk->sk_err, ECONNRESET); + err = ECONNRESET; } - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - - tcp_write_queue_purge(sk); - tcp_done(sk); - - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); + tcp_done_with_error(sk, err); } /* diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b710958393e6..59d5b064f233 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -611,15 +611,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); - if (!sock_owned_by_user(sk)) { - WRITE_ONCE(sk->sk_err, err); - - sk_error_report(sk); - - tcp_done(sk); - } else { + if (!sock_owned_by_user(sk)) + tcp_done_with_error(sk, err); + else WRITE_ONCE(sk->sk_err_soft, err); - } goto out; } @@ -3620,6 +3615,8 @@ void __init tcp_v4_init(void) */ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + sk->sk_clockid = CLOCK_MONOTONIC; + per_cpu(ipv4_tcp_sk, cpu) = sk; } if (register_pernet_subsys(&tcp_sk_ops)) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 95618d0e78e4..f97e098f18a5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1301,7 +1301,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tp = tcp_sk(sk); prior_wstamp = tp->tcp_wstamp_ns; tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); - skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); + skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); if (clone_it) { oskb = skb; @@ -1655,7 +1655,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, skb_split(skb, buff, len); - skb_set_delivery_time(buff, skb->tstamp, true); + skb_set_delivery_time(buff, skb->tstamp, SKB_CLOCK_MONOTONIC); tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); @@ -2764,7 +2764,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ tp->tcp_wstamp_ns = tp->tcp_clock_cache; - skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); + skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ @@ -3752,11 +3752,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) skb_set_delivery_time(skb, cookie_init_timestamp(req, now), - true); + SKB_CLOCK_MONOTONIC); else #endif { - skb_set_delivery_time(skb, now, true); + skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */ tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb); } @@ -3843,7 +3843,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, synack_type, &opts); - skb_set_delivery_time(skb, now, true); + skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); tcp_add_tx_delay(skb, tp); return skb; @@ -4027,7 +4027,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, true); + skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, SKB_CLOCK_MONOTONIC); /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 83fe7f62f7f1..3e8604ae7d06 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -74,11 +74,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) static void tcp_write_err(struct sock *sk) { - WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); - sk_error_report(sk); - - tcp_write_queue_purge(sk); - tcp_done(sk); + tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5c424a0e7232..1e69756d53d9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -863,7 +863,7 @@ static void addrconf_forward_change(struct net *net, __s32 newf) } } -static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) +static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int newf) { struct net *net; int old; @@ -931,7 +931,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf) } } -static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) +static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int newf) { struct net *net; int old; @@ -6378,7 +6378,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf) } } -static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) +static int addrconf_disable_ipv6(const struct ctl_table *table, int *p, int newf) { struct net *net = (struct net *)table->extra2; int old; @@ -6669,7 +6669,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) } static -int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) +int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val) { struct net *net = (struct net *)ctl->extra2; struct inet6_dev *idev; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 27d8725445e3..e7a19df3125e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -859,7 +859,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; ktime_t tstamp = skb->tstamp; @@ -955,7 +955,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), @@ -1016,7 +1016,7 @@ slow_path: /* * Put this fragment into the sending queue. */ - skb_set_delivery_time(frag, tstamp, mono_delivery_time); + skb_set_delivery_time(frag, tstamp, tstamp_type); err = output(net, sk, frag); if (err) goto fail; @@ -1924,7 +1924,10 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; - skb->tstamp = cork->base.transmit_time; + if (sk_is_tcp(sk)) + skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); + else + skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid); ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d914b23256ce..254b192c5705 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1936,7 +1936,7 @@ static struct notifier_block ndisc_netdev_notifier = { }; #ifdef CONFIG_SYSCTL -static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, +static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 53d255838e6a..e0c2347b4dc6 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -126,7 +126,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; ktime_t tstamp = skb->tstamp; struct ip6_frag_state state; u8 *prevhdr, nexthdr = 0; @@ -192,7 +192,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -225,7 +225,7 @@ slow_path: goto blackhole; } - skb_set_delivery_time(skb2, tstamp, mono_delivery_time); + skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 5e1b50c6a44d..6f0844c9315d 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -263,7 +263,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; - fq->q.mono_delivery_time = skb->mono_delivery_time; + fq->q.tstamp_type = skb->tstamp_type; fq->q.meat += skb->len; fq->ecn |= ecn; if (payload_len > fq->q.max_size) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 2eedf255600b..f838366e8256 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -621,7 +621,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->protocol = htons(ETH_P_IPV6); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_put(skb, length); skb_reset_network_header(skb); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 327caca64257..a48be617a8ab 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -198,7 +198,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; - fq->q.mono_delivery_time = skb->mono_delivery_time; + fq->q.tstamp_type = skb->tstamp_type; fq->q.meat += skb->len; fq->ecn |= ecn; add_frag_mem_limit(fq->q.fqdir, skb->truesize); diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index a31521e270f7..180da19c148c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -21,9 +21,7 @@ #include <net/genetlink.h> #include <linux/seg6.h> #include <linux/seg6_genl.h> -#ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> -#endif bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced) { @@ -437,13 +435,11 @@ static int __net_init seg6_net_init(struct net *net) net->ipv6.seg6_data = sdata; -#ifdef CONFIG_IPV6_SEG6_HMAC if (seg6_hmac_net_init(net)) { kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); return -ENOMEM; } -#endif return 0; } @@ -452,9 +448,7 @@ static void __net_exit seg6_net_exit(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); -#ifdef CONFIG_IPV6_SEG6_HMAC seg6_hmac_net_exit(net); -#endif kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); @@ -520,41 +514,28 @@ int __init seg6_init(void) if (err) goto out_unregister_pernet; -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) goto out_unregister_genl; err = seg6_local_init(); - if (err) { - seg6_iptunnel_exit(); - goto out_unregister_genl; - } -#endif + if (err) + goto out_unregister_iptun; -#ifdef CONFIG_IPV6_SEG6_HMAC err = seg6_hmac_init(); if (err) - goto out_unregister_iptun; -#endif + goto out_unregister_seg6; pr_info("Segment Routing with IPv6\n"); out: return err; -#ifdef CONFIG_IPV6_SEG6_HMAC -out_unregister_iptun: -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL +out_unregister_seg6: seg6_local_exit(); +out_unregister_iptun: seg6_iptunnel_exit(); -#endif -#endif -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL out_unregister_genl: -#endif -#if IS_ENABLED(CONFIG_IPV6_SEG6_LWTUNNEL) || IS_ENABLED(CONFIG_IPV6_SEG6_HMAC) genl_unregister_family(&seg6_genl_family); -#endif out_unregister_pernet: unregister_pernet_subsys(&ip6_segments_ops); goto out; @@ -562,13 +543,9 @@ out_unregister_pernet: void seg6_exit(void) { -#ifdef CONFIG_IPV6_SEG6_HMAC seg6_hmac_exit(); -#endif -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL seg6_local_exit(); seg6_iptunnel_exit(); -#endif genl_unregister_family(&seg6_genl_family); unregister_pernet_subsys(&ip6_segments_ops); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8c577b651bfc..5fe4365de89d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -490,14 +490,10 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); - if (!sock_owned_by_user(sk)) { - WRITE_ONCE(sk->sk_err, err); - sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ - - tcp_done(sk); - } else { + if (!sock_owned_by_user(sk)) + tcp_done_with_error(sk, err); + else WRITE_ONCE(sk->sk_err_soft, err); - } goto out; case TCP_LISTEN: break; @@ -975,7 +971,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 mark = inet_twsk(sk)->tw_mark; else mark = READ_ONCE(sk->sk_mark); - skb_set_delivery_time(buff, tcp_transmit_time(sk), true); + skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC); } if (txhash) { /* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */ @@ -2382,8 +2378,14 @@ static struct inet_protosw tcpv6_protosw = { static int __net_init tcpv6_net_init(struct net *net) { - return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, - SOCK_RAW, IPPROTO_TCP, net); + int res; + + res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, + SOCK_RAW, IPPROTO_TCP, net); + if (!res) + net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC; + + return res; } static void __net_exit tcpv6_net_exit(struct net *net) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b6d0dcf3a5c3..78a1cc72dc38 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1924,7 +1924,8 @@ proc_do_sync_ports(struct ctl_table *table, int write, return rc; } -static int ipvs_proc_est_cpumask_set(struct ctl_table *table, void *buffer) +static int ipvs_proc_est_cpumask_set(const struct ctl_table *table, + void *buffer) { struct netns_ipvs *ipvs = table->extra2; cpumask_var_t *valp = table->data; @@ -1962,8 +1963,8 @@ out: return ret; } -static int ipvs_proc_est_cpumask_get(struct ctl_table *table, void *buffer, - size_t size) +static int ipvs_proc_est_cpumask_get(const struct ctl_table *table, + void *buffer, size_t size) { struct netns_ipvs *ipvs = table->extra2; cpumask_var_t *valp = table->data; diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index d2492d050fe6..4a136fc3a9c0 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -32,7 +32,9 @@ * -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) + * -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (16) or 12 + * -EINVAL - opts->ct_zone_id set when + opts__sz isn't NF_BPF_CT_OPTS_SZ (16) * -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 @@ -42,6 +44,8 @@ * Values: * IPPROTO_TCP, IPPROTO_UDP * @dir: - connection tracking tuple direction. + * @ct_zone_id - connection tracking zone id. + * @ct_zone_dir - connection tracking zone direction. * @reserved - Reserved member, will be reused for more options in future * Values: * 0 @@ -51,11 +55,13 @@ struct bpf_ct_opts { s32 error; u8 l4proto; u8 dir; - u8 reserved[2]; + u16 ct_zone_id; + u8 ct_zone_dir; + u8 reserved[3]; }; enum { - NF_BPF_CT_OPTS_SZ = 12, + NF_BPF_CT_OPTS_SZ = 16, }; static int bpf_nf_ct_tuple_parse(struct bpf_sock_tuple *bpf_tuple, @@ -104,12 +110,21 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple, u32 timeout) { struct nf_conntrack_tuple otuple, rtuple; + struct nf_conntrack_zone ct_zone; struct nf_conn *ct; int err; - if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] || - opts_len != NF_BPF_CT_OPTS_SZ) + if (!opts || !bpf_tuple) return ERR_PTR(-EINVAL); + if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12)) + return ERR_PTR(-EINVAL); + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2]) + return ERR_PTR(-EINVAL); + } else { + if (opts->ct_zone_id) + return ERR_PTR(-EINVAL); + } if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) return ERR_PTR(-EINVAL); @@ -130,7 +145,16 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple, return ERR_PTR(-ENONET); } - ct = nf_conntrack_alloc(net, &nf_ct_zone_dflt, &otuple, &rtuple, + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->ct_zone_dir == 0) + opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; + nf_ct_zone_init(&ct_zone, + opts->ct_zone_id, opts->ct_zone_dir, 0); + } else { + ct_zone = nf_ct_zone_dflt; + } + + ct = nf_conntrack_alloc(net, &ct_zone, &otuple, &rtuple, GFP_ATOMIC); if (IS_ERR(ct)) goto out; @@ -152,12 +176,21 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net, { struct nf_conntrack_tuple_hash *hash; struct nf_conntrack_tuple tuple; + struct nf_conntrack_zone ct_zone; struct nf_conn *ct; int err; - if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] || - opts_len != NF_BPF_CT_OPTS_SZ) + if (!opts || !bpf_tuple) return ERR_PTR(-EINVAL); + if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12)) + return ERR_PTR(-EINVAL); + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2]) + return ERR_PTR(-EINVAL); + } else { + if (opts->ct_zone_id) + return ERR_PTR(-EINVAL); + } if (unlikely(opts->l4proto != IPPROTO_TCP && opts->l4proto != IPPROTO_UDP)) return ERR_PTR(-EPROTO); if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) @@ -174,7 +207,16 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net, return ERR_PTR(-ENONET); } - hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple); + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->ct_zone_dir == 0) + opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; + nf_ct_zone_init(&ct_zone, + opts->ct_zone_id, opts->ct_zone_dir, 0); + } else { + ct_zone = nf_ct_zone_dflt; + } + + hash = nf_conntrack_find_get(net, &ct_zone, &tuple); if (opts->netns_id >= 0) put_net(net); if (!hash) @@ -245,7 +287,7 @@ __bpf_kfunc_start_defs(); * @opts - Additional options for allocation (documented above) * Cannot be NULL * @opts__sz - Length of the bpf_ct_opts structure - * Must be NF_BPF_CT_OPTS_SZ (12) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn___init * bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, @@ -279,7 +321,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @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) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn * bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, @@ -312,7 +354,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts - Additional options for allocation (documented above) * Cannot be NULL * @opts__sz - Length of the bpf_ct_opts structure - * Must be NF_BPF_CT_OPTS_SZ (12) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn___init * bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, @@ -347,7 +389,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, * @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) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn * bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ea3ebc160e25..fce390887591 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2056,8 +2056,7 @@ retry: skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); - skb->tstamp = sockc.transmit_time; - + skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2584,7 +2583,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->dev = dev; skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3062,7 +3061,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; - skb->tstamp = sockc.transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 0e3cf11ae5fc..396b576390d0 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -54,8 +54,8 @@ TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb, bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(filter, skb); } - if (unlikely(!skb->tstamp && skb->mono_delivery_time)) - skb->mono_delivery_time = 0; + if (unlikely(!skb->tstamp && skb->tstamp_type)) + skb->tstamp_type = SKB_CLOCK_REALTIME; if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 5e83e890f6a4..1941ebec23ff 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -104,8 +104,8 @@ TC_INDIRECT_SCOPE int cls_bpf_classify(struct sk_buff *skb, bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(prog->filter, skb); } - if (unlikely(!skb->tstamp && skb->mono_delivery_time)) - skb->mono_delivery_time = 0; + if (unlikely(!skb->tstamp && skb->tstamp_type)) + skb->tstamp_type = SKB_CLOCK_REALTIME; if (prog->exts_integrated) { res->class = 0; diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c index 944f13fe164a..7ec7143e2757 100644 --- a/samples/bpf/cpustat_kern.c +++ b/samples/bpf/cpustat_kern.c @@ -211,7 +211,7 @@ int bpf_prog1(struct cpu_args *ctx) SEC("tracepoint/power/cpu_frequency") int bpf_prog2(struct cpu_args *ctx) { - u64 *pts, *cstate, *pstate, prev_state, cur_ts, delta; + u64 *pts, *cstate, *pstate, cur_ts, delta; u32 key, cpu, pstate_idx; u64 *val; @@ -232,7 +232,6 @@ int bpf_prog2(struct cpu_args *ctx) if (!cstate) return 0; - prev_state = *pstate; *pstate = ctx->state; if (!*pts) { diff --git a/scripts/Makefile.btf b/scripts/Makefile.btf index 2d6e5ed9081e..bca8a8f26ea4 100644 --- a/scripts/Makefile.btf +++ b/scripts/Makefile.btf @@ -14,9 +14,7 @@ pahole-flags-$(call test-ge, $(pahole-ver), 121) += --btf_gen_floats pahole-flags-$(call test-ge, $(pahole-ver), 122) += -j -ifeq ($(pahole-ver), 125) -pahole-flags-y += --skip_encoding_btf_inconsistent_proto --btf_gen_optimized -endif +pahole-flags-$(call test-ge, $(pahole-ver), 125) += --skip_encoding_btf_inconsistent_proto --btf_gen_optimized else diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index eaba24320fb2..3f6bca03ad2e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -28,7 +28,7 @@ BTF COMMANDS | **bpftool** **btf help** | | *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* } -| *FORMAT* := { **raw** | **c** } +| *FORMAT* := { **raw** | **c** [**unsorted**] } | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } @@ -63,7 +63,9 @@ bpftool btf dump *BTF_SRC* pahole. **format** option can be used to override default (raw) output format. Raw - (**raw**) or C-syntax (**c**) output formats are supported. + (**raw**) or C-syntax (**c**) output formats are supported. With C-style + formatting, the output is sorted by default. Use the **unsorted** option + to avoid sorting the output. bpftool btf help Print short help message. diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index dfa4f1bebbb3..ba927379eb20 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -204,10 +204,11 @@ ifeq ($(feature-clang-bpf-co-re),1) BUILD_BPF_SKELS := 1 -$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) ifeq ($(VMLINUX_H),) +$(OUTPUT)vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL_BOOTSTRAP) $(QUIET_GEN)$(BPFTOOL_BOOTSTRAP) btf dump file $< format c > $@ else +$(OUTPUT)vmlinux.h: $(VMLINUX_H) $(Q)cp "$(VMLINUX_H)" $@ endif diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 04afe2ac2228..be99d49b8714 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -930,6 +930,9 @@ _bpftool() format) COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) ;; + c) + COMPREPLY=( $( compgen -W "unsorted" -- "$cur" ) ) + ;; *) # emit extra options case ${words[3]} in diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 91fcb75babe3..af047dedde38 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -43,6 +43,13 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_ENUM64] = "ENUM64", }; +struct sort_datum { + int index; + int type_rank; + const char *sort_name; + const char *own_name; +}; + static const char *btf_int_enc_str(__u8 encoding) { switch (encoding) { @@ -460,9 +467,122 @@ static void __printf(2, 0) btf_dump_printf(void *ctx, vfprintf(stdout, fmt, args); } +static int btf_type_rank(const struct btf *btf, __u32 index, bool has_name) +{ + const struct btf_type *t = btf__type_by_id(btf, index); + const int kind = btf_kind(t); + const int max_rank = 10; + + if (t->name_off) + has_name = true; + + switch (kind) { + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + return has_name ? 1 : 0; + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + return 2; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return has_name ? 3 : max_rank; + case BTF_KIND_FUNC_PROTO: + return has_name ? 4 : max_rank; + case BTF_KIND_ARRAY: + if (has_name) + return btf_type_rank(btf, btf_array(t)->type, has_name); + return max_rank; + case BTF_KIND_TYPE_TAG: + case BTF_KIND_CONST: + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_DECL_TAG: + if (has_name) + return btf_type_rank(btf, t->type, has_name); + return max_rank; + default: + return max_rank; + } +} + +static const char *btf_type_sort_name(const struct btf *btf, __u32 index, bool from_ref) +{ + const struct btf_type *t = btf__type_by_id(btf, index); + + switch (btf_kind(t)) { + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: { + int name_off = t->name_off; + + /* Use name of the first element for anonymous enums if allowed */ + if (!from_ref && !t->name_off && btf_vlen(t)) + name_off = btf_enum(t)->name_off; + + return btf__name_by_offset(btf, name_off); + } + case BTF_KIND_ARRAY: + return btf_type_sort_name(btf, btf_array(t)->type, true); + case BTF_KIND_TYPE_TAG: + case BTF_KIND_CONST: + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + case BTF_KIND_DECL_TAG: + return btf_type_sort_name(btf, t->type, true); + default: + return btf__name_by_offset(btf, t->name_off); + } + return NULL; +} + +static int btf_type_compare(const void *left, const void *right) +{ + const struct sort_datum *d1 = (const struct sort_datum *)left; + const struct sort_datum *d2 = (const struct sort_datum *)right; + int r; + + if (d1->type_rank != d2->type_rank) + return d1->type_rank < d2->type_rank ? -1 : 1; + + r = strcmp(d1->sort_name, d2->sort_name); + if (r) + return r; + + return strcmp(d1->own_name, d2->own_name); +} + +static struct sort_datum *sort_btf_c(const struct btf *btf) +{ + struct sort_datum *datums; + int n; + + n = btf__type_cnt(btf); + datums = malloc(sizeof(struct sort_datum) * n); + if (!datums) + return NULL; + + for (int i = 0; i < n; ++i) { + struct sort_datum *d = datums + i; + const struct btf_type *t = btf__type_by_id(btf, i); + + d->index = i; + d->type_rank = btf_type_rank(btf, i, false); + d->sort_name = btf_type_sort_name(btf, i, false); + d->own_name = btf__name_by_offset(btf, t->name_off); + } + + qsort(datums, n, sizeof(struct sort_datum), btf_type_compare); + + return datums; +} + static int dump_btf_c(const struct btf *btf, - __u32 *root_type_ids, int root_type_cnt) + __u32 *root_type_ids, int root_type_cnt, bool sort_dump) { + struct sort_datum *datums = NULL; struct btf_dump *d; int err = 0, i; @@ -486,8 +606,12 @@ static int dump_btf_c(const struct btf *btf, } else { int cnt = btf__type_cnt(btf); + if (sort_dump) + datums = sort_btf_c(btf); for (i = 1; i < cnt; i++) { - err = btf_dump__dump_type(d, i); + int idx = datums ? datums[i].index : i; + + err = btf_dump__dump_type(d, idx); if (err) goto done; } @@ -500,6 +624,7 @@ static int dump_btf_c(const struct btf *btf, printf("#endif /* __VMLINUX_H__ */\n"); done: + free(datums); btf_dump__free(d); return err; } @@ -549,10 +674,10 @@ static bool btf_is_kernel_module(__u32 btf_id) static int do_dump(int argc, char **argv) { + bool dump_c = false, sort_dump_c = true; struct btf *btf = NULL, *base = NULL; __u32 root_type_ids[2]; int root_type_cnt = 0; - bool dump_c = false; __u32 btf_id = -1; const char *src; int fd = -1; @@ -663,6 +788,9 @@ static int do_dump(int argc, char **argv) goto done; } NEXT_ARG(); + } else if (is_prefix(*argv, "unsorted")) { + sort_dump_c = false; + NEXT_ARG(); } else { p_err("unrecognized option: '%s'", *argv); err = -EINVAL; @@ -691,7 +819,7 @@ static int do_dump(int argc, char **argv) err = -ENOTSUP; goto done; } - err = dump_btf_c(btf, root_type_ids, root_type_cnt); + err = dump_btf_c(btf, root_type_ids, root_type_cnt, sort_dump_c); } else { err = dump_btf_raw(btf, root_type_ids, root_type_cnt); } @@ -1063,7 +1191,7 @@ static int do_help(int argc, char **argv) " %1$s %2$s help\n" "\n" " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" - " FORMAT := { raw | c }\n" + " FORMAT := { raw | c [unsorted] }\n" " " HELP_SPEC_MAP "\n" " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS " |\n" diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 958e92acca8e..9b75639434b8 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -410,7 +410,7 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, { const char *prog_name = prog_info->name; const struct btf_type *func_type; - const struct bpf_func_info finfo = {}; + struct bpf_func_info finfo = {}; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); struct btf *prog_btf = NULL; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 90706a47f6ff..25ea393cf084 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6207,12 +6207,17 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ enum { - BPF_SKB_TSTAMP_UNSPEC, - BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ - /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, - * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC - * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. */ }; diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h index 6cf890080dc0..80791c34730c 100644 --- a/tools/net/ynl/lib/ynl-priv.h +++ b/tools/net/ynl/lib/ynl-priv.h @@ -79,7 +79,7 @@ static inline void *ynl_dump_obj_next(void *obj) struct ynl_dump_list_type *list; uptr -= offsetof(struct ynl_dump_list_type, data); - list = (void *)uptr; + list = (struct ynl_dump_list_type *)uptr; uptr = (unsigned long)list->next; uptr += offsetof(struct ynl_dump_list_type, data); @@ -139,7 +139,7 @@ int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); static inline struct nlmsghdr *ynl_nlmsg_put_header(void *buf) { - struct nlmsghdr *nlh = buf; + struct nlmsghdr *nlh = (struct nlmsghdr *)buf; memset(nlh, 0, sizeof(*nlh)); nlh->nlmsg_len = NLMSG_HDRLEN; @@ -196,7 +196,7 @@ static inline void *ynl_attr_data(const struct nlattr *attr) static inline void *ynl_attr_data_end(const struct nlattr *attr) { - return ynl_attr_data(attr) + ynl_attr_data_len(attr); + return (char *)ynl_attr_data(attr) + ynl_attr_data_len(attr); } #define ynl_attr_for_each(attr, nlh, fixed_hdr_sz) \ @@ -228,7 +228,7 @@ ynl_attr_next(const void *end, const struct nlattr *prev) { struct nlattr *attr; - attr = (void *)((char *)prev + NLA_ALIGN(prev->nla_len)); + attr = (struct nlattr *)((char *)prev + NLA_ALIGN(prev->nla_len)); return ynl_attr_if_good(end, attr); } @@ -237,8 +237,8 @@ ynl_attr_first(const void *start, size_t len, size_t skip) { struct nlattr *attr; - attr = (void *)((char *)start + NLMSG_ALIGN(skip)); - return ynl_attr_if_good(start + len, attr); + attr = (struct nlattr *)((char *)start + NLMSG_ALIGN(skip)); + return ynl_attr_if_good((char *)start + len, attr); } static inline bool @@ -262,9 +262,9 @@ ynl_attr_nest_start(struct nlmsghdr *nlh, unsigned int attr_type) struct nlattr *attr; if (__ynl_attr_put_overflow(nlh, 0)) - return ynl_nlmsg_end_addr(nlh) - NLA_HDRLEN; + return (struct nlattr *)ynl_nlmsg_end_addr(nlh) - 1; - attr = ynl_nlmsg_end_addr(nlh); + attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type | NLA_F_NESTED; nlh->nlmsg_len += NLA_HDRLEN; @@ -286,7 +286,7 @@ ynl_attr_put(struct nlmsghdr *nlh, unsigned int attr_type, if (__ynl_attr_put_overflow(nlh, size)) return; - attr = ynl_nlmsg_end_addr(nlh); + attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; attr->nla_len = NLA_HDRLEN + size; @@ -305,10 +305,10 @@ ynl_attr_put_str(struct nlmsghdr *nlh, unsigned int attr_type, const char *str) if (__ynl_attr_put_overflow(nlh, len)) return; - attr = ynl_nlmsg_end_addr(nlh); + attr = (struct nlattr *)ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; - strcpy(ynl_attr_data(attr), str); + strcpy((char *)ynl_attr_data(attr), str); attr->nla_len = NLA_HDRLEN + NLA_ALIGN(len); nlh->nlmsg_len += NLMSG_ALIGN(attr->nla_len); diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/ynl-gen-rst.py index 657e881d2ea4..6c56d0d726b4 100755 --- a/tools/net/ynl/ynl-gen-rst.py +++ b/tools/net/ynl/ynl-gen-rst.py @@ -49,7 +49,7 @@ def inline(text: str) -> str: def sanitize(text: str) -> str: """Remove newlines and multiple spaces""" # This is useful for some fields that are spread across multiple lines - return str(text).replace("\n", "").strip() + return str(text).replace("\n", " ").strip() def rst_fields(key: str, value: str, level: int = 0) -> str: @@ -156,7 +156,10 @@ def parse_do(do_dict: Dict[str, Any], level: int = 0) -> str: lines = [] for key in do_dict.keys(): lines.append(rst_paragraph(bold(key), level + 1)) - lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n") + if key in ['request', 'reply']: + lines.append(parse_do_attributes(do_dict[key], level + 1) + "\n") + else: + lines.append(headroom(level + 2) + do_dict[key] + "\n") return "\n".join(lines) @@ -172,13 +175,13 @@ def parse_do_attributes(attrs: Dict[str, Any], level: int = 0) -> str: def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str: """Parse operations block""" - preprocessed = ["name", "doc", "title", "do", "dump"] + preprocessed = ["name", "doc", "title", "do", "dump", "flags"] linkable = ["fixed-header", "attribute-set"] lines = [] for operation in operations: lines.append(rst_section(namespace, 'operation', operation["name"])) - lines.append(rst_paragraph(sanitize(operation["doc"])) + "\n") + lines.append(rst_paragraph(operation["doc"]) + "\n") for key in operation.keys(): if key in preprocessed: @@ -188,6 +191,8 @@ def parse_operations(operations: List[Dict[str, Any]], namespace: str) -> str: if key in linkable: value = rst_ref(namespace, key, value) lines.append(rst_fields(key, value, 0)) + if 'flags' in operation: + lines.append(rst_fields('flags', rst_list_inline(operation['flags']))) if "do" in operation: lines.append(rst_paragraph(":do:", 0)) diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index eeabd798bc3a..2fb16da78dce 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -80,6 +80,7 @@ CONFIG_NETFILTER_XT_TARGET_CT=y CONFIG_NETKIT=y CONFIG_NF_CONNTRACK=y CONFIG_NF_CONNTRACK_MARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_DEFRAG_IPV4=y CONFIG_NF_DEFRAG_IPV6=y CONFIG_NF_NAT=y diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c index b30ff6b3b81a..a4a1f93878d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -104,6 +104,7 @@ static void test_bpf_nf_ct(int mode) 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_reserved_new, -EINVAL, "Test EINVAL for reserved in new struct 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"); @@ -122,6 +123,12 @@ static void test_bpf_nf_ct(int mode) ASSERT_EQ(skel->bss->test_exist_lookup_mark, 43, "Test existing connection lookup ctmark"); ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting"); ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting"); + ASSERT_EQ(skel->data->test_ct_zone_id_alloc_entry, 0, "Test for alloc new entry in specified ct zone"); + ASSERT_EQ(skel->data->test_ct_zone_id_insert_entry, 0, "Test for insert new entry in specified ct zone"); + ASSERT_EQ(skel->data->test_ct_zone_id_succ_lookup, 0, "Test for successful lookup in specified ct_zone"); + ASSERT_EQ(skel->bss->test_ct_zone_dir_enoent_lookup, -ENOENT, "Test ENOENT for lookup with wrong ct zone dir"); + ASSERT_EQ(skel->bss->test_ct_zone_id_enoent_lookup, -ENOENT, "Test ENOENT for lookup in wrong ct zone"); + end: if (client_fd != -1) close(client_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c index 3b7c57fe55a5..08b6391f2f56 100644 --- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c +++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c @@ -69,15 +69,17 @@ static struct test_case test_cases[] = { { N(SCHED_CLS, struct __sk_buff, tstamp), .read = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);" - "w11 &= 3;" - "if w11 != 0x3 goto pc+2;" + "if w11 & 0x4 goto pc+1;" + "goto pc+4;" + "if w11 & 0x3 goto pc+1;" + "goto pc+2;" "$dst = 0;" "goto pc+1;" "$dst = *(u64 *)($ctx + sk_buff::tstamp);", .write = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);" - "if w11 & 0x2 goto pc+1;" + "if w11 & 0x4 goto pc+1;" "goto pc+2;" - "w11 &= -2;" + "w11 &= -4;" "*(u8 *)($ctx + sk_buff::__mono_tc_offset) = r11;" "*(u64 *)($ctx + sk_buff::tstamp) = $src;", }, diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index b1073d36d77a..327d51f59142 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -890,9 +890,6 @@ static void test_udp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd) ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, dtime_cnt_str(t, INGRESS_FWDNS_P100)); - /* non mono delivery time is not forwarded */ - ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0, - dtime_cnt_str(t, INGRESS_FWDNS_P101)); for (i = EGRESS_FWDNS_P100; i < SET_DTIME; i++) ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i)); diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c index 77ad8adf68da..0289d8ce2b80 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -9,10 +9,14 @@ #define EINVAL 22 #define ENOENT 2 +#define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL) +#define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY) + extern unsigned long CONFIG_HZ __kconfig; int test_einval_bpf_tuple = 0; int test_einval_reserved = 0; +int test_einval_reserved_new = 0; int test_einval_netns_id = 0; int test_einval_len_opts = 0; int test_eproto_l4proto = 0; @@ -22,6 +26,11 @@ int test_eafnosupport = 0; int test_alloc_entry = -EINVAL; int test_insert_entry = -EAFNOSUPPORT; int test_succ_lookup = -ENOENT; +int test_ct_zone_id_alloc_entry = -EINVAL; +int test_ct_zone_id_insert_entry = -EAFNOSUPPORT; +int test_ct_zone_id_succ_lookup = -ENOENT; +int test_ct_zone_dir_enoent_lookup = 0; +int test_ct_zone_id_enoent_lookup = 0; u32 test_delta_timeout = 0; u32 test_status = 0; u32 test_insert_lookup_mark = 0; @@ -45,6 +54,17 @@ struct bpf_ct_opts___local { s32 netns_id; s32 error; u8 l4proto; + u8 dir; + u8 reserved[2]; +}; + +struct bpf_ct_opts___new { + s32 netns_id; + s32 error; + u8 l4proto; + u8 dir; + u16 ct_zone_id; + u8 ct_zone_dir; u8 reserved[3]; } __attribute__((preserve_access_index)); @@ -220,10 +240,97 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, } } +static __always_inline void +nf_ct_opts_new_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___new *, u32), + struct nf_conn *(*alloc_fn)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___new *, u32), + void *ctx) +{ + struct bpf_ct_opts___new 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)); + + opts_def.reserved[0] = 1; + ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + opts_def.reserved[0] = 0; + if (ct) + bpf_ct_release(ct); + else + test_einval_reserved_new = opts_def.error; + + bpf_tuple.ipv4.saddr = bpf_get_prandom_u32(); /* src IP */ + bpf_tuple.ipv4.daddr = bpf_get_prandom_u32(); /* dst IP */ + bpf_tuple.ipv4.sport = bpf_get_prandom_u32(); /* src port */ + bpf_tuple.ipv4.dport = bpf_get_prandom_u32(); /* dst port */ + + /* use non-default ct zone */ + opts_def.ct_zone_id = 10; + opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG; + ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, + sizeof(opts_def)); + if (ct) { + __u16 sport = bpf_get_prandom_u32(); + __u16 dport = bpf_get_prandom_u32(); + union nf_inet_addr saddr = {}; + union nf_inet_addr daddr = {}; + struct nf_conn *ct_ins; + + bpf_ct_set_timeout(ct, 10000); + + /* snat */ + saddr.ip = bpf_get_prandom_u32(); + bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local); + /* dnat */ + daddr.ip = bpf_get_prandom_u32(); + bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local); + + ct_ins = bpf_ct_insert_entry(ct); + if (ct_ins) { + struct nf_conn *ct_lk; + + /* entry should exist in same ct zone we inserted it */ + ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), + &opts_def, sizeof(opts_def)); + if (ct_lk) { + bpf_ct_release(ct_lk); + test_ct_zone_id_succ_lookup = 0; + } + + /* entry should not exist with wrong direction */ + opts_def.ct_zone_dir = NF_CT_ZONE_DIR_REPL; + ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), + &opts_def, sizeof(opts_def)); + opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG; + if (ct_lk) + bpf_ct_release(ct_lk); + else + test_ct_zone_dir_enoent_lookup = opts_def.error; + + /* entry should not exist in default ct zone */ + opts_def.ct_zone_id = 0; + ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), + &opts_def, sizeof(opts_def)); + if (ct_lk) + bpf_ct_release(ct_lk); + else + test_ct_zone_id_enoent_lookup = opts_def.error; + + bpf_ct_release(ct_ins); + test_ct_zone_id_insert_entry = 0; + } + test_ct_zone_id_alloc_entry = 0; + } +} + SEC("xdp") int nf_xdp_ct_test(struct xdp_md *ctx) { nf_ct_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx); + nf_ct_opts_new_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx); return 0; } @@ -231,6 +338,7 @@ SEC("tc") int nf_skb_ct_test(struct __sk_buff *ctx) { nf_ct_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx); + nf_ct_opts_new_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c index 74ec09f040b7..ca8e8734d901 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -222,17 +222,21 @@ int egress_host(struct __sk_buff *skb) return TC_ACT_OK; if (skb_proto(skb_type) == IPPROTO_TCP) { - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC && skb->tstamp) inc_dtimes(EGRESS_ENDHOST); else inc_errs(EGRESS_ENDHOST); - } else { - if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC && + } else if (skb_proto(skb_type) == IPPROTO_UDP) { + if (skb->tstamp_type == BPF_SKB_CLOCK_TAI && skb->tstamp) inc_dtimes(EGRESS_ENDHOST); else inc_errs(EGRESS_ENDHOST); + } else { + if (skb->tstamp_type == BPF_SKB_CLOCK_REALTIME && + skb->tstamp) + inc_errs(EGRESS_ENDHOST); } skb->tstamp = EGRESS_ENDHOST_MAGIC; @@ -252,7 +256,7 @@ int ingress_host(struct __sk_buff *skb) if (!skb_type) return TC_ACT_OK; - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC && skb->tstamp == EGRESS_FWDNS_MAGIC) inc_dtimes(INGRESS_ENDHOST); else @@ -315,7 +319,6 @@ int egress_fwdns_prio100(struct __sk_buff *skb) SEC("tc") int ingress_fwdns_prio101(struct __sk_buff *skb) { - __u64 expected_dtime = EGRESS_ENDHOST_MAGIC; int skb_type; skb_type = skb_get_type(skb); @@ -323,29 +326,24 @@ int ingress_fwdns_prio101(struct __sk_buff *skb) /* Should have handled in prio100 */ return TC_ACT_SHOT; - if (skb_proto(skb_type) == IPPROTO_UDP) - expected_dtime = 0; - if (skb->tstamp_type) { if (fwdns_clear_dtime() || - skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || - skb->tstamp != expected_dtime) + (skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC && + skb->tstamp_type != BPF_SKB_CLOCK_TAI) || + skb->tstamp != EGRESS_ENDHOST_MAGIC) inc_errs(INGRESS_FWDNS_P101); else inc_dtimes(INGRESS_FWDNS_P101); } else { - if (!fwdns_clear_dtime() && expected_dtime) + if (!fwdns_clear_dtime()) inc_errs(INGRESS_FWDNS_P101); } - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) { skb->tstamp = INGRESS_FWDNS_MAGIC; } else { if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_DELIVERY_MONO)) - inc_errs(SET_DTIME); - if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_UNSPEC)) + BPF_SKB_CLOCK_MONOTONIC)) inc_errs(SET_DTIME); } @@ -370,7 +368,7 @@ int egress_fwdns_prio101(struct __sk_buff *skb) if (skb->tstamp_type) { if (fwdns_clear_dtime() || - skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC || skb->tstamp != INGRESS_FWDNS_MAGIC) inc_errs(EGRESS_FWDNS_P101); else @@ -380,14 +378,11 @@ int egress_fwdns_prio101(struct __sk_buff *skb) inc_errs(EGRESS_FWDNS_P101); } - if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) { skb->tstamp = EGRESS_FWDNS_MAGIC; } else { if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_DELIVERY_MONO)) - inc_errs(SET_DTIME); - if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, - BPF_SKB_TSTAMP_UNSPEC)) + BPF_SKB_CLOCK_MONOTONIC)) inc_errs(SET_DTIME); } diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 92752f5eeded..4499b3cfc3a6 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -63,7 +63,7 @@ int passed; int failed; int map_fd[9]; struct bpf_map *maps[9]; -int prog_fd[11]; +int prog_fd[9]; int txmsg_pass; int txmsg_redir; @@ -1793,8 +1793,6 @@ int prog_attach_type[] = { BPF_SK_MSG_VERDICT, BPF_SK_MSG_VERDICT, BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, - BPF_SK_MSG_VERDICT, }; int prog_type[] = { @@ -1807,8 +1805,6 @@ int prog_type[] = { BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_SK_MSG, BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, - BPF_PROG_TYPE_SK_MSG, }; static int populate_progs(char *bpf_file) |