diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 7250c0542828..7b0c4291c686 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -72,6 +72,7 @@ two flavors of JITs, the newer eBPF JIT currently supported on: - riscv64 - riscv32 - loongarch64 + - arc And the older cBPF JIT supported on the following archs: diff --git a/Documentation/networking/filter.rst b/Documentation/networking/filter.rst index 7d8c5380492f..8eb9a5d40f31 100644 --- a/Documentation/networking/filter.rst +++ b/Documentation/networking/filter.rst @@ -513,7 +513,7 @@ JIT compiler ------------ The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, -PowerPC, ARM, ARM64, MIPS, RISC-V and s390 and can be enabled through +PowerPC, ARM, ARM64, MIPS, RISC-V, s390, and ARC and can be enabled through CONFIG_BPF_JIT. The JIT compiler is transparently invoked for each attached filter from user space or for internal kernel users if it has been previously enabled by root:: @@ -650,7 +650,7 @@ before a conversion to the new layout is being done behind the scenes! Currently, the classic BPF format is being used for JITing on most 32-bit architectures, whereas x86-64, aarch64, s390x, powerpc64, -sparc64, arm32, riscv64, riscv32, loongarch64 perform JIT compilation +sparc64, arm32, riscv64, riscv32, loongarch64, arc perform JIT compilation from eBPF instruction set. Testing diff --git a/MAINTAINERS b/MAINTAINERS index b81b2be60b77..757206d86048 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3712,6 +3712,12 @@ S: Maintained F: Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml F: drivers/iio/imu/bmi323/ +BPF JIT for ARC +M: Shahab Vahedi +L: bpf@vger.kernel.org +S: Maintained +F: arch/arc/net/ + BPF JIT for ARM M: Russell King M: Puranjay Mohan diff --git a/arch/arc/Kbuild b/arch/arc/Kbuild index b94102fff68b..20ea7dd482d4 100644 --- a/arch/arc/Kbuild +++ b/arch/arc/Kbuild @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += kernel/ obj-y += mm/ +obj-y += net/ # for cleaning subdir- += boot diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 4092bec198be..fd0b0a0d4686 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -51,6 +51,7 @@ config ARC select PCI_SYSCALL if PCI select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32 select TRACE_IRQFLAGS_SUPPORT + select HAVE_EBPF_JIT if ISA_ARCV2 config LOCKDEP_SUPPORT def_bool y diff --git a/arch/arc/net/Makefile b/arch/arc/net/Makefile new file mode 100644 index 000000000000..ea5790952e9a --- /dev/null +++ b/arch/arc/net/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only + +ifeq ($(CONFIG_ISA_ARCV2),y) + obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o + obj-$(CONFIG_BPF_JIT) += bpf_jit_arcv2.o +endif diff --git a/arch/arc/net/bpf_jit.h b/arch/arc/net/bpf_jit.h new file mode 100644 index 000000000000..ec44873c42d1 --- /dev/null +++ b/arch/arc/net/bpf_jit.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * The interface that a back-end should provide to bpf_jit_core.c. + * + * Copyright (c) 2024 Synopsys Inc. + * Author: Shahab Vahedi + */ + +#ifndef _ARC_BPF_JIT_H +#define _ARC_BPF_JIT_H + +#include +#include + +/* Print debug info and assert. */ +//#define ARC_BPF_JIT_DEBUG + +/* Determine the address type of the target. */ +#ifdef CONFIG_ISA_ARCV2 +#define ARC_ADDR u32 +#endif + +/* + * For the translation of some BPF instructions, a temporary register + * might be needed for some interim data. + */ +#define JIT_REG_TMP MAX_BPF_JIT_REG + +/* + * Buffer access: If buffer "b" is not NULL, advance by "n" bytes. + * + * This macro must be used in any place that potentially requires a + * "buf + len". This way, we make sure that the "buf" argument for + * the underlying "arc_*(buf, ...)" ends up as NULL instead of something + * like "0+4" or "0+8", etc. Those "arc_*()" functions check their "buf" + * value to decide if instructions should be emitted or not. + */ +#define BUF(b, n) (((b) != NULL) ? ((b) + (n)) : (b)) + +/************** Functions that the back-end must provide **************/ +/* Extension for 32-bit operations. */ +inline u8 zext(u8 *buf, u8 rd); +/***** Moves *****/ +u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext); +u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm); +u8 mov_r64(u8 *buf, u8 rd, u8 rs, u8 sign_ext); +u8 mov_r64_i32(u8 *buf, u8 reg, s32 imm); +u8 mov_r64_i64(u8 *buf, u8 reg, u32 lo, u32 hi); +/***** Loads and stores *****/ +u8 load_r(u8 *buf, u8 rd, u8 rs, s16 off, u8 size, bool sign_ext); +u8 store_r(u8 *buf, u8 rd, u8 rs, s16 off, u8 size); +u8 store_i(u8 *buf, s32 imm, u8 rd, s16 off, u8 size); +/***** Addition *****/ +u8 add_r32(u8 *buf, u8 rd, u8 rs); +u8 add_r32_i32(u8 *buf, u8 rd, s32 imm); +u8 add_r64(u8 *buf, u8 rd, u8 rs); +u8 add_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Subtraction *****/ +u8 sub_r32(u8 *buf, u8 rd, u8 rs); +u8 sub_r32_i32(u8 *buf, u8 rd, s32 imm); +u8 sub_r64(u8 *buf, u8 rd, u8 rs); +u8 sub_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Multiplication *****/ +u8 mul_r32(u8 *buf, u8 rd, u8 rs); +u8 mul_r32_i32(u8 *buf, u8 rd, s32 imm); +u8 mul_r64(u8 *buf, u8 rd, u8 rs); +u8 mul_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Division *****/ +u8 div_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext); +u8 div_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext); +/***** Remainder *****/ +u8 mod_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext); +u8 mod_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext); +/***** Bitwise AND *****/ +u8 and_r32(u8 *buf, u8 rd, u8 rs); +u8 and_r32_i32(u8 *buf, u8 rd, s32 imm); +u8 and_r64(u8 *buf, u8 rd, u8 rs); +u8 and_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Bitwise OR *****/ +u8 or_r32(u8 *buf, u8 rd, u8 rs); +u8 or_r32_i32(u8 *buf, u8 rd, s32 imm); +u8 or_r64(u8 *buf, u8 rd, u8 rs); +u8 or_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Bitwise XOR *****/ +u8 xor_r32(u8 *buf, u8 rd, u8 rs); +u8 xor_r32_i32(u8 *buf, u8 rd, s32 imm); +u8 xor_r64(u8 *buf, u8 rd, u8 rs); +u8 xor_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Bitwise Negate *****/ +u8 neg_r32(u8 *buf, u8 r); +u8 neg_r64(u8 *buf, u8 r); +/***** Bitwise left shift *****/ +u8 lsh_r32(u8 *buf, u8 rd, u8 rs); +u8 lsh_r32_i32(u8 *buf, u8 rd, u8 imm); +u8 lsh_r64(u8 *buf, u8 rd, u8 rs); +u8 lsh_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Bitwise right shift (logical) *****/ +u8 rsh_r32(u8 *buf, u8 rd, u8 rs); +u8 rsh_r32_i32(u8 *buf, u8 rd, u8 imm); +u8 rsh_r64(u8 *buf, u8 rd, u8 rs); +u8 rsh_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Bitwise right shift (arithmetic) *****/ +u8 arsh_r32(u8 *buf, u8 rd, u8 rs); +u8 arsh_r32_i32(u8 *buf, u8 rd, u8 imm); +u8 arsh_r64(u8 *buf, u8 rd, u8 rs); +u8 arsh_r64_i32(u8 *buf, u8 rd, s32 imm); +/***** Frame related *****/ +u32 mask_for_used_regs(u8 bpf_reg, bool is_call); +u8 arc_prologue(u8 *buf, u32 usage, u16 frame_size); +u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size); +/***** Jumps *****/ +/* + * Different sorts of conditions (ARC enum as opposed to BPF_*). + * + * Do not change the order of enums here. ARC_CC_SLE+1 is used + * to determine the number of JCCs. + */ +enum ARC_CC { + ARC_CC_UGT = 0, /* unsigned > */ + ARC_CC_UGE, /* unsigned >= */ + ARC_CC_ULT, /* unsigned < */ + ARC_CC_ULE, /* unsigned <= */ + ARC_CC_SGT, /* signed > */ + ARC_CC_SGE, /* signed >= */ + ARC_CC_SLT, /* signed < */ + ARC_CC_SLE, /* signed <= */ + ARC_CC_AL, /* always */ + ARC_CC_EQ, /* == */ + ARC_CC_NE, /* != */ + ARC_CC_SET, /* test */ + ARC_CC_LAST +}; + +/* + * A few notes: + * + * - check_jmp_*() are prerequisites before calling the gen_jmp_*(). + * They return "true" if the jump is possible and "false" otherwise. + * + * - The notion of "*_off" is to emphasize that these parameters are + * merely offsets in the JIT stream and not absolute addresses. One + * can look at them as addresses if the JIT code would start from + * address 0x0000_0000. Nonetheless, since the buffer address for the + * JIT is on a word-aligned address, this works and actually makes + * things simpler (offsets are in the range of u32 which is more than + * enough). + */ +bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond); +bool check_jmp_64(u32 curr_off, u32 targ_off, u8 cond); +u8 gen_jmp_32(u8 *buf, u8 rd, u8 rs, u8 cond, u32 c_off, u32 t_off); +u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 c_off, u32 t_off); +/***** Miscellaneous *****/ +u8 gen_func_call(u8 *buf, ARC_ADDR func_addr, bool external_func); +u8 arc_to_bpf_return(u8 *buf); +/* + * - Perform byte swaps on "rd" based on the "size". + * - If "force" is set, do it unconditionally. Otherwise, consider the + * desired "endian"ness and the host endianness. + * - For data "size"s up to 32 bits, perform a zero-extension if asked + * by the "do_zext" boolean. + */ +u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext); + +#endif /* _ARC_BPF_JIT_H */ diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c new file mode 100644 index 000000000000..31bfb6e9ce00 --- /dev/null +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -0,0 +1,3005 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The ARCv2 backend of Just-In-Time compiler for eBPF bytecode. + * + * Copyright (c) 2024 Synopsys Inc. + * Author: Shahab Vahedi + */ +#include +#include "bpf_jit.h" + +/* ARC core registers. */ +enum { + ARC_R_0, ARC_R_1, ARC_R_2, ARC_R_3, ARC_R_4, ARC_R_5, + ARC_R_6, ARC_R_7, ARC_R_8, ARC_R_9, ARC_R_10, ARC_R_11, + ARC_R_12, ARC_R_13, ARC_R_14, ARC_R_15, ARC_R_16, ARC_R_17, + ARC_R_18, ARC_R_19, ARC_R_20, ARC_R_21, ARC_R_22, ARC_R_23, + ARC_R_24, ARC_R_25, ARC_R_26, ARC_R_FP, ARC_R_SP, ARC_R_ILINK, + ARC_R_30, ARC_R_BLINK, + /* + * Having ARC_R_IMM encoded as source register means there is an + * immediate that must be interpreted from the next 4 bytes. If + * encoded as the destination register though, it implies that the + * output of the operation is not assigned to any register. The + * latter is helpful if we only care about updating the CPU status + * flags. + */ + ARC_R_IMM = 62 +}; + +/* + * Remarks about the rationale behind the chosen mapping: + * + * - BPF_REG_{1,2,3,4} are the argument registers and must be mapped to + * argument registers in ARCv2 ABI: r0-r7. The r7 registers is the last + * argument register in the ABI. Therefore BPF_REG_5, as the fifth + * argument, must be pushed onto the stack. This is a must for calling + * in-kernel functions. + * + * - In ARCv2 ABI, the return value is in r0 for 32-bit results and (r1,r0) + * for 64-bit results. However, because they're already used for BPF_REG_1, + * the next available scratch registers, r8 and r9, are the best candidates + * for BPF_REG_0. After a "call" to a(n) (in-kernel) function, the result + * is "mov"ed to these registers. At a BPF_EXIT, their value is "mov"ed to + * (r1,r0). + * It is worth mentioning that scratch registers are the best choice for + * BPF_REG_0, because it is very popular in BPF instruction encoding. + * + * - JIT_REG_TMP is an artifact needed to translate some BPF instructions. + * Its life span is one single BPF instruction. Since during the + * analyze_reg_usage(), it is not known if temporary registers are used, + * it is mapped to ARC's scratch registers: r10 and r11. Therefore, they + * don't matter in analysing phase and don't need saving. This temporary + * register is added as yet another index in the bpf2arc array, so it will + * unfold like the rest of registers during the code generation process. + * + * - Mapping of callee-saved BPF registers, BPF_REG_{6,7,8,9}, starts from + * (r15,r14) register pair. The (r13,r12) is not a good choice, because + * in ARCv2 ABI, r12 is not a callee-saved register and this can cause + * problem when calling an in-kernel function. Theoretically, the mapping + * could start from (r14,r13), but it is not a conventional ARCv2 register + * pair. To have a future proof design, I opted for this arrangement. + * If/when we decide to add ARCv2 instructions that do use register pairs, + * the mapping, hopefully, doesn't need to be revisited. + */ +const u8 bpf2arc[][2] = { + /* Return value from in-kernel function, and exit value from eBPF */ + [BPF_REG_0] = {ARC_R_8, ARC_R_9}, + /* Arguments from eBPF program to in-kernel function */ + [BPF_REG_1] = {ARC_R_0, ARC_R_1}, + [BPF_REG_2] = {ARC_R_2, ARC_R_3}, + [BPF_REG_3] = {ARC_R_4, ARC_R_5}, + [BPF_REG_4] = {ARC_R_6, ARC_R_7}, + /* Remaining arguments, to be passed on the stack per 32-bit ABI */ + [BPF_REG_5] = {ARC_R_22, ARC_R_23}, + /* Callee-saved registers that in-kernel function will preserve */ + [BPF_REG_6] = {ARC_R_14, ARC_R_15}, + [BPF_REG_7] = {ARC_R_16, ARC_R_17}, + [BPF_REG_8] = {ARC_R_18, ARC_R_19}, + [BPF_REG_9] = {ARC_R_20, ARC_R_21}, + /* Read-only frame pointer to access the eBPF stack. 32-bit only. */ + [BPF_REG_FP] = {ARC_R_FP, }, + /* Register for blinding constants */ + [BPF_REG_AX] = {ARC_R_24, ARC_R_25}, + /* Temporary registers for internal use */ + [JIT_REG_TMP] = {ARC_R_10, ARC_R_11} +}; + +#define ARC_CALLEE_SAVED_REG_FIRST ARC_R_13 +#define ARC_CALLEE_SAVED_REG_LAST ARC_R_25 + +#define REG_LO(r) (bpf2arc[(r)][0]) +#define REG_HI(r) (bpf2arc[(r)][1]) + +/* + * To comply with ARCv2 ABI, BPF's arg5 must be put on stack. After which, + * the stack needs to be restored by ARG5_SIZE. + */ +#define ARG5_SIZE 8 + +/* Instruction lengths in bytes. */ +enum { + INSN_len_normal = 4, /* Normal instructions length. */ + INSN_len_imm = 4 /* Length of an extra 32-bit immediate. */ +}; + +/* ZZ defines the size of operation in encodings that it is used. */ +enum { + ZZ_1_byte = 1, + ZZ_2_byte = 2, + ZZ_4_byte = 0, + ZZ_8_byte = 3 +}; + +/* + * AA is mostly about address write back mode. It determines if the + * address in question should be updated before usage or after: + * addr += offset; data = *addr; + * data = *addr; addr += offset; + * + * In "scaling" mode, the effective address will become the sum + * of "address" + "index"*"size". The "size" is specified by the + * "ZZ" field. There is no write back when AA is set for scaling: + * data = *(addr + offset<= 0) +#define IN_S9_RANGE(x) ((x) <= (0x100 - 1) && (x) >= -0x100) +#define IN_S12_RANGE(x) ((x) <= (0x800 - 1) && (x) >= -0x800) +#define IN_S21_RANGE(x) ((x) <= (0x100000 - 1) && (x) >= -0x100000) +#define IN_S25_RANGE(x) ((x) <= (0x1000000 - 1) && (x) >= -0x1000000) + +/* Operands in most of the encodings. */ +#define OP_A(x) ((x) & 0x03f) +#define OP_B(x) ((((x) & 0x07) << 24) | (((x) & 0x38) << 9)) +#define OP_C(x) (((x) & 0x03f) << 6) +#define OP_IMM (OP_C(ARC_R_IMM)) +#define COND(x) (OP_A((x) & 31)) +#define FLAG(x) (((x) & 1) << 15) + +/* + * The 4-byte encoding of "mov b,c": + * + * 0010_0bbb 0000_1010 0BBB_cccc cc00_0000 + * + * b: BBBbbb destination register + * c: cccccc source register + */ +#define OPC_MOV 0x200a0000 + +/* + * The 4-byte encoding of "mov b,s12" (used for moving small immediates): + * + * 0010_0bbb 1000_1010 0BBB_ssss ssSS_SSSS + * + * b: BBBbbb destination register + * s: SSSSSSssssss source immediate (signed) + */ +#define OPC_MOVI 0x208a0000 +#define MOVI_S12(x) ((((x) & 0xfc0) >> 6) | (((x) & 0x3f) << 6)) + +/* + * The 4-byte encoding of "mov[.qq] b,u6", used for conditional + * moving of even smaller immediates: + * + * 0010_0bbb 1100_1010 0BBB_cccc cciq_qqqq + * + * qq: qqqqq condition code + * i: If set, c is considered a 6-bit immediate, else a reg. + * + * b: BBBbbb destination register + * c: cccccc source + */ +#define OPC_MOV_CC 0x20ca0000 +#define MOV_CC_I BIT(5) +#define OPC_MOVU_CC (OPC_MOV_CC | MOV_CC_I) + +/* + * The 4-byte encoding of "sexb b,c" (8-bit sign extension): + * + * 0010_0bbb 0010_1111 0BBB_cccc cc00_0101 + * + * b: BBBbbb destination register + * c: cccccc source register + */ +#define OPC_SEXB 0x202f0005 + +/* + * The 4-byte encoding of "sexh b,c" (16-bit sign extension): + * + * 0010_0bbb 0010_1111 0BBB_cccc cc00_0110 + * + * b: BBBbbb destination register + * c: cccccc source register + */ +#define OPC_SEXH 0x202f0006 + +/* + * The 4-byte encoding of "ld[zz][.x][.aa] c,[b,s9]": + * + * 0001_0bbb ssss_ssss SBBB_0aaz zxcc_cccc + * + * zz: size mode + * aa: address write back mode + * x: extension mode + * + * s9: S_ssss_ssss 9-bit signed number + * b: BBBbbb source reg for address + * c: cccccc destination register + */ +#define OPC_LOAD 0x10000000 +#define LOAD_X(x) ((x) << 6) +#define LOAD_ZZ(x) ((x) << 7) +#define LOAD_AA(x) ((x) << 9) +#define LOAD_S9(x) ((((x) & 0x0ff) << 16) | (((x) & 0x100) << 7)) +#define LOAD_C(x) ((x) & 0x03f) +/* Unsigned and signed loads. */ +#define OPC_LDU (OPC_LOAD | LOAD_X(X_zero)) +#define OPC_LDS (OPC_LOAD | LOAD_X(X_sign)) +/* 32-bit load. */ +#define OPC_LD32 (OPC_LDU | LOAD_ZZ(ZZ_4_byte)) +/* "pop reg" is merely a "ld.ab reg,[sp,4]". */ +#define OPC_POP \ + (OPC_LD32 | LOAD_AA(AA_post) | LOAD_S9(4) | OP_B(ARC_R_SP)) + +/* + * The 4-byte encoding of "st[zz][.aa] c,[b,s9]": + * + * 0001_1bbb ssss_ssss SBBB_cccc cc0a_azz0 + * + * zz: zz size mode + * aa: aa address write back mode + * + * s9: S_ssss_ssss 9-bit signed number + * b: BBBbbb source reg for address + * c: cccccc source reg to be stored + */ +#define OPC_STORE 0x18000000 +#define STORE_ZZ(x) ((x) << 1) +#define STORE_AA(x) ((x) << 3) +#define STORE_S9(x) ((((x) & 0x0ff) << 16) | (((x) & 0x100) << 7)) +/* 32-bit store. */ +#define OPC_ST32 (OPC_STORE | STORE_ZZ(ZZ_4_byte)) +/* "push reg" is merely a "st.aw reg,[sp,-4]". */ +#define OPC_PUSH \ + (OPC_ST32 | STORE_AA(AA_pre) | STORE_S9(-4) | OP_B(ARC_R_SP)) + +/* + * The 4-byte encoding of "add a,b,c": + * + * 0010_0bbb 0i00_0000 fBBB_cccc ccaa_aaaa + * + * f: indicates if flags (carry, etc.) should be updated + * i: If set, c is considered a 6-bit immediate, else a reg. + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_ADD 0x20000000 +/* Addition with updating the pertinent flags in "status32" register. */ +#define OPC_ADDF (OPC_ADD | FLAG(1)) +#define ADDI BIT(22) +#define ADDI_U6(x) OP_C(x) +#define OPC_ADDI (OPC_ADD | ADDI) +#define OPC_ADDIF (OPC_ADDI | FLAG(1)) +#define OPC_ADD_I (OPC_ADD | OP_IMM) + +/* + * The 4-byte encoding of "adc a,b,c" (addition with carry): + * + * 0010_0bbb 0i00_0001 0BBB_cccc ccaa_aaaa + * + * i: if set, c is considered a 6-bit immediate, else a reg. + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_ADC 0x20010000 +#define ADCI BIT(22) +#define ADCI_U6(x) OP_C(x) +#define OPC_ADCI (OPC_ADC | ADCI) + +/* + * The 4-byte encoding of "sub a,b,c": + * + * 0010_0bbb 0i00_0010 fBBB_cccc ccaa_aaaa + * + * f: indicates if flags (carry, etc.) should be updated + * i: if set, c is considered a 6-bit immediate, else a reg. + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_SUB 0x20020000 +/* Subtraction with updating the pertinent flags in "status32" register. */ +#define OPC_SUBF (OPC_SUB | FLAG(1)) +#define SUBI BIT(22) +#define SUBI_U6(x) OP_C(x) +#define OPC_SUBI (OPC_SUB | SUBI) +#define OPC_SUB_I (OPC_SUB | OP_IMM) + +/* + * The 4-byte encoding of "sbc a,b,c" (subtraction with carry): + * + * 0010_0bbb 0000_0011 fBBB_cccc ccaa_aaaa + * + * f: indicates if flags (carry, etc.) should be updated + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_SBC 0x20030000 + +/* + * The 4-byte encoding of "cmp[.qq] b,c": + * + * 0010_0bbb 1100_1100 1BBB_cccc cc0q_qqqq + * + * qq: qqqqq condition code + * + * b: BBBbbb the 1st operand + * c: cccccc the 2nd operand + */ +#define OPC_CMP 0x20cc8000 + +/* + * The 4-byte encoding of "neg a,b": + * + * 0010_0bbb 0100_1110 0BBB_0000 00aa_aaaa + * + * a: aaaaaa result + * b: BBBbbb input + */ +#define OPC_NEG 0x204e0000 + +/* + * The 4-byte encoding of "mpy a,b,c". + * mpy is the signed 32-bit multiplication with the lower 32-bit + * of the product as the result. + * + * 0010_0bbb 0001_1010 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_MPY 0x201a0000 +#define OPC_MPYI (OPC_MPY | OP_IMM) + +/* + * The 4-byte encoding of "mpydu a,b,c". + * mpydu is the unsigned 32-bit multiplication with the lower 32-bit of + * the product in register "a" and the higher 32-bit in register "a+1". + * + * 0010_1bbb 0001_1001 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa 64-bit result in registers (R_a+1,R_a) + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_MPYDU 0x28190000 +#define OPC_MPYDUI (OPC_MPYDU | OP_IMM) + +/* + * The 4-byte encoding of "divu a,b,c" (unsigned division): + * + * 0010_1bbb 0000_0101 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa result (quotient) + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand (divisor) + */ +#define OPC_DIVU 0x28050000 +#define OPC_DIVUI (OPC_DIVU | OP_IMM) + +/* + * The 4-byte encoding of "div a,b,c" (signed division): + * + * 0010_1bbb 0000_0100 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa result (quotient) + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand (divisor) + */ +#define OPC_DIVS 0x28040000 +#define OPC_DIVSI (OPC_DIVS | OP_IMM) + +/* + * The 4-byte encoding of "remu a,b,c" (unsigned remainder): + * + * 0010_1bbb 0000_1001 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa result (remainder) + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand (divisor) + */ +#define OPC_REMU 0x28090000 +#define OPC_REMUI (OPC_REMU | OP_IMM) + +/* + * The 4-byte encoding of "rem a,b,c" (signed remainder): + * + * 0010_1bbb 0000_1000 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa result (remainder) + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand (divisor) + */ +#define OPC_REMS 0x28080000 +#define OPC_REMSI (OPC_REMS | OP_IMM) + +/* + * The 4-byte encoding of "and a,b,c": + * + * 0010_0bbb 0000_0100 fBBB_cccc ccaa_aaaa + * + * f: indicates if zero and negative flags should be updated + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_AND 0x20040000 +#define OPC_ANDI (OPC_AND | OP_IMM) + +/* + * The 4-byte encoding of "tst[.qq] b,c". + * Checks if the two input operands have any bit set at the same + * position. + * + * 0010_0bbb 1100_1011 1BBB_cccc cc0q_qqqq + * + * qq: qqqqq condition code + * + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_TST 0x20cb8000 + +/* + * The 4-byte encoding of "or a,b,c": + * + * 0010_0bbb 0000_0101 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_OR 0x20050000 +#define OPC_ORI (OPC_OR | OP_IMM) + +/* + * The 4-byte encoding of "xor a,b,c": + * + * 0010_0bbb 0000_0111 0BBB_cccc ccaa_aaaa + * + * a: aaaaaa result + * b: BBBbbb the 1st input operand + * c: cccccc the 2nd input operand + */ +#define OPC_XOR 0x20070000 +#define OPC_XORI (OPC_XOR | OP_IMM) + +/* + * The 4-byte encoding of "not b,c": + * + * 0010_0bbb 0010_1111 0BBB_cccc cc00_1010 + * + * b: BBBbbb result + * c: cccccc input + */ +#define OPC_NOT 0x202f000a + +/* + * The 4-byte encoding of "btst b,u6": + * + * 0010_0bbb 0101_0001 1BBB_uuuu uu00_0000 + * + * b: BBBbbb input number to check + * u6: uuuuuu 6-bit unsigned number specifying bit position to check + */ +#define OPC_BTSTU6 0x20518000 +#define BTST_U6(x) (OP_C((x) & 63)) + +/* + * The 4-byte encoding of "asl[.qq] b,b,c" (arithmetic shift left): + * + * 0010_1bbb 0i00_0000 0BBB_cccc ccaa_aaaa + * + * i: if set, c is considered a 5-bit immediate, else a reg. + * + * b: BBBbbb result and the first operand (number to be shifted) + * c: cccccc amount to be shifted + */ +#define OPC_ASL 0x28000000 +#define ASL_I BIT(22) +#define ASLI_U6(x) OP_C((x) & 31) +#define OPC_ASLI (OPC_ASL | ASL_I) + +/* + * The 4-byte encoding of "asr a,b,c" (arithmetic shift right): + * + * 0010_1bbb 0i00_0010 0BBB_cccc ccaa_aaaa + * + * i: if set, c is considered a 6-bit immediate, else a reg. + * + * a: aaaaaa result + * b: BBBbbb first input: number to be shifted + * c: cccccc second input: amount to be shifted + */ +#define OPC_ASR 0x28020000 +#define ASR_I ASL_I +#define ASRI_U6(x) ASLI_U6(x) +#define OPC_ASRI (OPC_ASR | ASR_I) + +/* + * The 4-byte encoding of "lsr a,b,c" (logical shift right): + * + * 0010_1bbb 0i00_0001 0BBB_cccc ccaa_aaaa + * + * i: if set, c is considered a 6-bit immediate, else a reg. + * + * a: aaaaaa result + * b: BBBbbb first input: number to be shifted + * c: cccccc second input: amount to be shifted + */ +#define OPC_LSR 0x28010000 +#define LSR_I ASL_I +#define LSRI_U6(x) ASLI_U6(x) +#define OPC_LSRI (OPC_LSR | LSR_I) + +/* + * The 4-byte encoding of "swape b,c": + * + * 0010_1bbb 0010_1111 0bbb_cccc cc00_1001 + * + * b: BBBbbb destination register + * c: cccccc source register + */ +#define OPC_SWAPE 0x282f0009 + +/* + * Encoding for jump to an address in register: + * j reg_c + * + * 0010_0000 1110_0000 0000_cccc cc00_0000 + * + * c: cccccc register holding the destination address + */ +#define OPC_JMP 0x20e00000 +/* Jump to "branch-and-link" register, which effectively is a "return". */ +#define OPC_J_BLINK (OPC_JMP | OP_C(ARC_R_BLINK)) + +/* + * Encoding for jump-and-link to an address in register: + * jl reg_c + * + * 0010_0000 0010_0010 0000_cccc cc00_0000 + * + * c: cccccc register holding the destination address + */ +#define OPC_JL 0x20220000 + +/* + * Encoding for (conditional) branch to an offset from the current location + * that is word aligned: (PC & 0xffff_fffc) + s21 + * B[qq] s21 + * + * 0000_0sss ssss_sss0 SSSS_SSSS SS0q_qqqq + * + * qq: qqqqq condition code + * s21: SSSS SSSS_SSss ssss_ssss The displacement (21-bit signed) + * + * The displacement is supposed to be 16-bit (2-byte) aligned. Therefore, + * it should be a multiple of 2. Hence, there is an implied '0' bit at its + * LSB: S_SSSS SSSS_Ssss ssss_sss0 + */ +#define OPC_BCC 0x00000000 +#define BCC_S21(d) ((((d) & 0x7fe) << 16) | (((d) & 0x1ff800) >> 5)) + +/* + * Encoding for unconditional branch to an offset from the current location + * that is word aligned: (PC & 0xffff_fffc) + s25 + * B s25 + * + * 0000_0sss ssss_sss1 SSSS_SSSS SS00_TTTT + * + * s25: TTTT SSSS SSSS_SSss ssss_ssss The displacement (25-bit signed) + * + * The displacement is supposed to be 16-bit (2-byte) aligned. Therefore, + * it should be a multiple of 2. Hence, there is an implied '0' bit at its + * LSB: T TTTS_SSSS SSSS_Ssss ssss_sss0 + */ +#define OPC_B 0x00010000 +#define B_S25(d) ((((d) & 0x1e00000) >> 21) | BCC_S21(d)) + +static inline void emit_2_bytes(u8 *buf, u16 bytes) +{ + *((u16 *)buf) = bytes; +} + +static inline void emit_4_bytes(u8 *buf, u32 bytes) +{ + emit_2_bytes(buf, bytes >> 16); + emit_2_bytes(buf + 2, bytes & 0xffff); +} + +static inline u8 bpf_to_arc_size(u8 size) +{ + switch (size) { + case BPF_B: + return ZZ_1_byte; + case BPF_H: + return ZZ_2_byte; + case BPF_W: + return ZZ_4_byte; + case BPF_DW: + return ZZ_8_byte; + default: + return ZZ_4_byte; + } +} + +/************** Encoders (Deal with ARC regs) ************/ + +/* Move an immediate to register with a 4-byte instruction. */ +static u8 arc_movi_r(u8 *buf, u8 reg, s16 imm) +{ + const u32 insn = OPC_MOVI | OP_B(reg) | MOVI_S12(imm); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* rd <- rs */ +static u8 arc_mov_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_MOV | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* The emitted code may have different sizes based on "imm". */ +static u8 arc_mov_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_MOV | OP_B(rd) | OP_IMM; + + if (IN_S12_RANGE(imm)) + return arc_movi_r(buf, rd, imm); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* The emitted code will always have the same size (8). */ +static u8 arc_mov_i_fixed(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_MOV | OP_B(rd) | OP_IMM; + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* Conditional move. */ +static u8 arc_mov_cc_r(u8 *buf, u8 cc, u8 rd, u8 rs) +{ + const u32 insn = OPC_MOV_CC | OP_B(rd) | OP_C(rs) | COND(cc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* Conditional move of a small immediate to rd. */ +static u8 arc_movu_cc_r(u8 *buf, u8 cc, u8 rd, u8 imm) +{ + const u32 insn = OPC_MOVU_CC | OP_B(rd) | OP_C(imm) | COND(cc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* Sign extension from a byte. */ +static u8 arc_sexb_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_SEXB | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* Sign extension from two bytes. */ +static u8 arc_sexh_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_SEXH | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* st reg, [reg_mem, off] */ +static u8 arc_st_r(u8 *buf, u8 reg, u8 reg_mem, s16 off, u8 zz) +{ + const u32 insn = OPC_STORE | STORE_ZZ(zz) | OP_C(reg) | + OP_B(reg_mem) | STORE_S9(off); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* st.aw reg, [sp, -4] */ +static u8 arc_push_r(u8 *buf, u8 reg) +{ + const u32 insn = OPC_PUSH | OP_C(reg); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* ld reg, [reg_mem, off] (unsigned) */ +static u8 arc_ld_r(u8 *buf, u8 reg, u8 reg_mem, s16 off, u8 zz) +{ + const u32 insn = OPC_LDU | LOAD_ZZ(zz) | LOAD_C(reg) | + OP_B(reg_mem) | LOAD_S9(off); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* ld.x reg, [reg_mem, off] (sign extend) */ +static u8 arc_ldx_r(u8 *buf, u8 reg, u8 reg_mem, s16 off, u8 zz) +{ + const u32 insn = OPC_LDS | LOAD_ZZ(zz) | LOAD_C(reg) | + OP_B(reg_mem) | LOAD_S9(off); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* ld.ab reg,[sp,4] */ +static u8 arc_pop_r(u8 *buf, u8 reg) +{ + const u32 insn = OPC_POP | LOAD_C(reg); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* add Ra,Ra,Rc */ +static u8 arc_add_r(u8 *buf, u8 ra, u8 rc) +{ + const u32 insn = OPC_ADD | OP_A(ra) | OP_B(ra) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* add.f Ra,Ra,Rc */ +static u8 arc_addf_r(u8 *buf, u8 ra, u8 rc) +{ + const u32 insn = OPC_ADDF | OP_A(ra) | OP_B(ra) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* add.f Ra,Ra,u6 */ +static u8 arc_addif_r(u8 *buf, u8 ra, u8 u6) +{ + const u32 insn = OPC_ADDIF | OP_A(ra) | OP_B(ra) | ADDI_U6(u6); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* add Ra,Ra,u6 */ +static u8 arc_addi_r(u8 *buf, u8 ra, u8 u6) +{ + const u32 insn = OPC_ADDI | OP_A(ra) | OP_B(ra) | ADDI_U6(u6); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* add Ra,Rb,imm */ +static u8 arc_add_i(u8 *buf, u8 ra, u8 rb, s32 imm) +{ + const u32 insn = OPC_ADD_I | OP_A(ra) | OP_B(rb); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* adc Ra,Ra,Rc */ +static u8 arc_adc_r(u8 *buf, u8 ra, u8 rc) +{ + const u32 insn = OPC_ADC | OP_A(ra) | OP_B(ra) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* adc Ra,Ra,u6 */ +static u8 arc_adci_r(u8 *buf, u8 ra, u8 u6) +{ + const u32 insn = OPC_ADCI | OP_A(ra) | OP_B(ra) | ADCI_U6(u6); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* sub Ra,Ra,Rc */ +static u8 arc_sub_r(u8 *buf, u8 ra, u8 rc) +{ + const u32 insn = OPC_SUB | OP_A(ra) | OP_B(ra) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* sub.f Ra,Ra,Rc */ +static u8 arc_subf_r(u8 *buf, u8 ra, u8 rc) +{ + const u32 insn = OPC_SUBF | OP_A(ra) | OP_B(ra) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* sub Ra,Ra,u6 */ +static u8 arc_subi_r(u8 *buf, u8 ra, u8 u6) +{ + const u32 insn = OPC_SUBI | OP_A(ra) | OP_B(ra) | SUBI_U6(u6); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* sub Ra,Ra,imm */ +static u8 arc_sub_i(u8 *buf, u8 ra, s32 imm) +{ + const u32 insn = OPC_SUB_I | OP_A(ra) | OP_B(ra); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* sbc Ra,Ra,Rc */ +static u8 arc_sbc_r(u8 *buf, u8 ra, u8 rc) +{ + const u32 insn = OPC_SBC | OP_A(ra) | OP_B(ra) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* cmp Rb,Rc */ +static u8 arc_cmp_r(u8 *buf, u8 rb, u8 rc) +{ + const u32 insn = OPC_CMP | OP_B(rb) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* + * cmp.z Rb,Rc + * + * This "cmp.z" variant of compare instruction is used on lower + * 32-bits of register pairs after "cmp"ing their upper parts. If the + * upper parts are equal (z), then this one will proceed to check the + * rest. + */ +static u8 arc_cmpz_r(u8 *buf, u8 rb, u8 rc) +{ + const u32 insn = OPC_CMP | OP_B(rb) | OP_C(rc) | CC_equal; + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* neg Ra,Rb */ +static u8 arc_neg_r(u8 *buf, u8 ra, u8 rb) +{ + const u32 insn = OPC_NEG | OP_A(ra) | OP_B(rb); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* mpy Ra,Rb,Rc */ +static u8 arc_mpy_r(u8 *buf, u8 ra, u8 rb, u8 rc) +{ + const u32 insn = OPC_MPY | OP_A(ra) | OP_B(rb) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* mpy Ra,Rb,imm */ +static u8 arc_mpy_i(u8 *buf, u8 ra, u8 rb, s32 imm) +{ + const u32 insn = OPC_MPYI | OP_A(ra) | OP_B(rb); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* mpydu Ra,Ra,Rc */ +static u8 arc_mpydu_r(u8 *buf, u8 ra, u8 rc) +{ + const u32 insn = OPC_MPYDU | OP_A(ra) | OP_B(ra) | OP_C(rc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* mpydu Ra,Ra,imm */ +static u8 arc_mpydu_i(u8 *buf, u8 ra, s32 imm) +{ + const u32 insn = OPC_MPYDUI | OP_A(ra) | OP_B(ra); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* divu Rd,Rd,Rs */ +static u8 arc_divu_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_DIVU | OP_A(rd) | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* divu Rd,Rd,imm */ +static u8 arc_divu_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_DIVUI | OP_A(rd) | OP_B(rd); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* div Rd,Rd,Rs */ +static u8 arc_divs_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_DIVS | OP_A(rd) | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* div Rd,Rd,imm */ +static u8 arc_divs_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_DIVSI | OP_A(rd) | OP_B(rd); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* remu Rd,Rd,Rs */ +static u8 arc_remu_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_REMU | OP_A(rd) | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* remu Rd,Rd,imm */ +static u8 arc_remu_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_REMUI | OP_A(rd) | OP_B(rd); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* rem Rd,Rd,Rs */ +static u8 arc_rems_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_REMS | OP_A(rd) | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* rem Rd,Rd,imm */ +static u8 arc_rems_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_REMSI | OP_A(rd) | OP_B(rd); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* and Rd,Rd,Rs */ +static u8 arc_and_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_AND | OP_A(rd) | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* and Rd,Rd,limm */ +static u8 arc_and_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_ANDI | OP_A(rd) | OP_B(rd); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +/* tst Rd,Rs */ +static u8 arc_tst_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_TST | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* + * This particular version, "tst.z ...", is meant to be used after a + * "tst" on the low 32-bit of register pairs. If that "tst" is not + * zero, then we don't need to test the upper 32-bits lest it sets + * the zero flag. + */ +static u8 arc_tstz_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_TST | OP_B(rd) | OP_C(rs) | CC_equal; + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_or_r(u8 *buf, u8 rd, u8 rs1, u8 rs2) +{ + const u32 insn = OPC_OR | OP_A(rd) | OP_B(rs1) | OP_C(rs2); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_or_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_ORI | OP_A(rd) | OP_B(rd); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +static u8 arc_xor_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_XOR | OP_A(rd) | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_xor_i(u8 *buf, u8 rd, s32 imm) +{ + const u32 insn = OPC_XORI | OP_A(rd) | OP_B(rd); + + if (buf) { + emit_4_bytes(buf, insn); + emit_4_bytes(buf + INSN_len_normal, imm); + } + return INSN_len_normal + INSN_len_imm; +} + +static u8 arc_not_r(u8 *buf, u8 rd, u8 rs) +{ + const u32 insn = OPC_NOT | OP_B(rd) | OP_C(rs); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_btst_i(u8 *buf, u8 rs, u8 imm) +{ + const u32 insn = OPC_BTSTU6 | OP_B(rs) | BTST_U6(imm); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_asl_r(u8 *buf, u8 rd, u8 rs1, u8 rs2) +{ + const u32 insn = OPC_ASL | OP_A(rd) | OP_B(rs1) | OP_C(rs2); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_asli_r(u8 *buf, u8 rd, u8 rs, u8 imm) +{ + const u32 insn = OPC_ASLI | OP_A(rd) | OP_B(rs) | ASLI_U6(imm); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_asr_r(u8 *buf, u8 rd, u8 rs1, u8 rs2) +{ + const u32 insn = OPC_ASR | OP_A(rd) | OP_B(rs1) | OP_C(rs2); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_asri_r(u8 *buf, u8 rd, u8 rs, u8 imm) +{ + const u32 insn = OPC_ASRI | OP_A(rd) | OP_B(rs) | ASRI_U6(imm); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_lsr_r(u8 *buf, u8 rd, u8 rs1, u8 rs2) +{ + const u32 insn = OPC_LSR | OP_A(rd) | OP_B(rs1) | OP_C(rs2); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_lsri_r(u8 *buf, u8 rd, u8 rs, u8 imm) +{ + const u32 insn = OPC_LSRI | OP_A(rd) | OP_B(rs) | LSRI_U6(imm); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_swape_r(u8 *buf, u8 r) +{ + const u32 insn = OPC_SWAPE | OP_B(r) | OP_C(r); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +static u8 arc_jmp_return(u8 *buf) +{ + if (buf) + emit_4_bytes(buf, OPC_J_BLINK); + return INSN_len_normal; +} + +static u8 arc_jl(u8 *buf, u8 reg) +{ + const u32 insn = OPC_JL | OP_C(reg); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* + * Conditional jump to an address that is max 21 bits away (signed). + * + * b s21 + */ +static u8 arc_bcc(u8 *buf, u8 cc, int offset) +{ + const u32 insn = OPC_BCC | BCC_S21(offset) | COND(cc); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/* + * Unconditional jump to an address that is max 25 bits away (signed). + * + * b s25 + */ +static u8 arc_b(u8 *buf, s32 offset) +{ + const u32 insn = OPC_B | B_S25(offset); + + if (buf) + emit_4_bytes(buf, insn); + return INSN_len_normal; +} + +/************* Packers (Deal with BPF_REGs) **************/ + +inline u8 zext(u8 *buf, u8 rd) +{ + if (rd != BPF_REG_FP) + return arc_movi_r(buf, REG_HI(rd), 0); + else + return 0; +} + +u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext) +{ + u8 len = 0; + + if (sign_ext) { + if (sign_ext == 8) + len = arc_sexb_r(buf, REG_LO(rd), REG_LO(rs)); + else if (sign_ext == 16) + len = arc_sexh_r(buf, REG_LO(rd), REG_LO(rs)); + else if (sign_ext == 32 && rd != rs) + len = arc_mov_r(buf, REG_LO(rd), REG_LO(rs)); + + return len; + } + + /* Unsigned move. */ + + if (rd != rs) + len = arc_mov_r(buf, REG_LO(rd), REG_LO(rs)); + + return len; +} + +u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm) +{ + return arc_mov_i(buf, REG_LO(reg), imm); +} + +u8 mov_r64(u8 *buf, u8 rd, u8 rs, u8 sign_ext) +{ + u8 len = 0; + + if (sign_ext) { + /* First handle the low 32-bit part. */ + len = mov_r32(buf, rd, rs, sign_ext); + + /* Now propagate the sign bit of LO to HI. */ + if (sign_ext == 8 || sign_ext == 16 || sign_ext == 32) { + len += arc_asri_r(BUF(buf, len), + REG_HI(rd), REG_LO(rd), 31); + } + + return len; + } + + /* Unsigned move. */ + + if (rd == rs) + return 0; + + len = arc_mov_r(buf, REG_LO(rd), REG_LO(rs)); + + if (rs != BPF_REG_FP) + len += arc_mov_r(BUF(buf, len), REG_HI(rd), REG_HI(rs)); + /* BPF_REG_FP is mapped to 32-bit "fp" register. */ + else + len += arc_movi_r(BUF(buf, len), REG_HI(rd), 0); + + return len; +} + +/* Sign extend the 32-bit immediate into 64-bit register pair. */ +u8 mov_r64_i32(u8 *buf, u8 reg, s32 imm) +{ + u8 len = 0; + + len = arc_mov_i(buf, REG_LO(reg), imm); + + /* BPF_REG_FP is mapped to 32-bit "fp" register. */ + if (reg != BPF_REG_FP) { + if (imm >= 0) + len += arc_movi_r(BUF(buf, len), REG_HI(reg), 0); + else + len += arc_movi_r(BUF(buf, len), REG_HI(reg), -1); + } + + return len; +} + +/* + * This is merely used for translation of "LD R, IMM64" instructions + * of the BPF. These sort of instructions are sometimes used for + * relocations. If during the normal pass, the relocation value is + * not known, the BPF instruction may look something like: + * + * LD R <- 0x0000_0001_0000_0001 + * + * Which will nicely translate to two 4-byte ARC instructions: + * + * mov R_lo, 1 # imm is small enough to be s12 + * mov R_hi, 1 # same + * + * However, during the extra pass, the IMM64 will have changed + * to the resolved address and looks something like: + * + * LD R <- 0x0000_0000_1234_5678 + * + * Now, the translated code will require 12 bytes: + * + * mov R_lo, 0x12345678 # this is an 8-byte instruction + * mov R_hi, 0 # still 4 bytes + * + * Which in practice will result in overwriting the following + * instruction. To avoid such cases, we will always emit codes + * with fixed sizes. + */ +u8 mov_r64_i64(u8 *buf, u8 reg, u32 lo, u32 hi) +{ + u8 len; + + len = arc_mov_i_fixed(buf, REG_LO(reg), lo); + len += arc_mov_i_fixed(BUF(buf, len), REG_HI(reg), hi); + + return len; +} + +/* + * If the "off"set is too big (doesn't encode as S9) for: + * + * {ld,st} r, [rm, off] + * + * Then emit: + * + * add r10, REG_LO(rm), off + * + * and make sure that r10 becomes the effective address: + * + * {ld,st} r, [r10, 0] + */ +static u8 adjust_mem_access(u8 *buf, s16 *off, u8 size, + u8 rm, u8 *arc_reg_mem) +{ + u8 len = 0; + *arc_reg_mem = REG_LO(rm); + + if (!IN_S9_RANGE(*off) || + (size == BPF_DW && !IN_S9_RANGE(*off + 4))) { + len += arc_add_i(BUF(buf, len), + REG_LO(JIT_REG_TMP), REG_LO(rm), (u32)(*off)); + *arc_reg_mem = REG_LO(JIT_REG_TMP); + *off = 0; + } + + return len; +} + +/* store rs, [rd, off] */ +u8 store_r(u8 *buf, u8 rs, u8 rd, s16 off, u8 size) +{ + u8 len, arc_reg_mem; + + len = adjust_mem_access(buf, &off, size, rd, &arc_reg_mem); + + if (size == BPF_DW) { + len += arc_st_r(BUF(buf, len), REG_LO(rs), arc_reg_mem, + off, ZZ_4_byte); + len += arc_st_r(BUF(buf, len), REG_HI(rs), arc_reg_mem, + off + 4, ZZ_4_byte); + } else { + u8 zz = bpf_to_arc_size(size); + + len += arc_st_r(BUF(buf, len), REG_LO(rs), arc_reg_mem, + off, zz); + } + + return len; +} + +/* + * For {8,16,32}-bit stores: + * mov r21, imm + * st r21, [...] + * For 64-bit stores: + * mov r21, imm + * st r21, [...] + * mov r21, {0,-1} + * st r21, [...+4] + */ +u8 store_i(u8 *buf, s32 imm, u8 rd, s16 off, u8 size) +{ + u8 len, arc_reg_mem; + /* REG_LO(JIT_REG_TMP) might be used by "adjust_mem_access()". */ + const u8 arc_rs = REG_HI(JIT_REG_TMP); + + len = adjust_mem_access(buf, &off, size, rd, &arc_reg_mem); + + if (size == BPF_DW) { + len += arc_mov_i(BUF(buf, len), arc_rs, imm); + len += arc_st_r(BUF(buf, len), arc_rs, arc_reg_mem, + off, ZZ_4_byte); + imm = (imm >= 0 ? 0 : -1); + len += arc_mov_i(BUF(buf, len), arc_rs, imm); + len += arc_st_r(BUF(buf, len), arc_rs, arc_reg_mem, + off + 4, ZZ_4_byte); + } else { + u8 zz = bpf_to_arc_size(size); + + len += arc_mov_i(BUF(buf, len), arc_rs, imm); + len += arc_st_r(BUF(buf, len), arc_rs, arc_reg_mem, off, zz); + } + + return len; +} + +/* + * For the calling convention of a little endian machine, the LO part + * must be on top of the stack. + */ +static u8 push_r64(u8 *buf, u8 reg) +{ + u8 len = 0; + +#ifdef __LITTLE_ENDIAN + /* BPF_REG_FP is mapped to 32-bit "fp" register. */ + if (reg != BPF_REG_FP) + len += arc_push_r(BUF(buf, len), REG_HI(reg)); + len += arc_push_r(BUF(buf, len), REG_LO(reg)); +#else + len += arc_push_r(BUF(buf, len), REG_LO(reg)); + if (reg != BPF_REG_FP) + len += arc_push_r(BUF(buf, len), REG_HI(reg)); +#endif + + return len; +} + +/* load rd, [rs, off] */ +u8 load_r(u8 *buf, u8 rd, u8 rs, s16 off, u8 size, bool sign_ext) +{ + u8 len, arc_reg_mem; + + len = adjust_mem_access(buf, &off, size, rs, &arc_reg_mem); + + if (size == BPF_B || size == BPF_H || size == BPF_W) { + const u8 zz = bpf_to_arc_size(size); + + /* Use LD.X only if the data size is less than 32-bit. */ + if (sign_ext && (zz == ZZ_1_byte || zz == ZZ_2_byte)) { + len += arc_ldx_r(BUF(buf, len), REG_LO(rd), + arc_reg_mem, off, zz); + } else { + len += arc_ld_r(BUF(buf, len), REG_LO(rd), + arc_reg_mem, off, zz); + } + + if (sign_ext) { + /* Propagate the sign bit to the higher reg. */ + len += arc_asri_r(BUF(buf, len), + REG_HI(rd), REG_LO(rd), 31); + } else { + len += arc_movi_r(BUF(buf, len), REG_HI(rd), 0); + } + } else if (size == BPF_DW) { + /* + * We are about to issue 2 consecutive loads: + * + * ld rx, [rb, off+0] + * ld ry, [rb, off+4] + * + * If "rx" and "rb" are the same registers, then the order + * should change to guarantee that "rb" remains intact + * during these 2 operations: + * + * ld ry, [rb, off+4] + * ld rx, [rb, off+0] + */ + if (REG_LO(rd) != arc_reg_mem) { + len += arc_ld_r(BUF(buf, len), REG_LO(rd), arc_reg_mem, + off, ZZ_4_byte); + len += arc_ld_r(BUF(buf, len), REG_HI(rd), arc_reg_mem, + off + 4, ZZ_4_byte); + } else { + len += arc_ld_r(BUF(buf, len), REG_HI(rd), arc_reg_mem, + off + 4, ZZ_4_byte); + len += arc_ld_r(BUF(buf, len), REG_LO(rd), arc_reg_mem, + off, ZZ_4_byte); + } + } + + return len; +} + +u8 add_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_add_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 add_r32_i32(u8 *buf, u8 rd, s32 imm) +{ + if (IN_U6_RANGE(imm)) + return arc_addi_r(buf, REG_LO(rd), imm); + else + return arc_add_i(buf, REG_LO(rd), REG_LO(rd), imm); +} + +u8 add_r64(u8 *buf, u8 rd, u8 rs) +{ + u8 len; + + len = arc_addf_r(buf, REG_LO(rd), REG_LO(rs)); + len += arc_adc_r(BUF(buf, len), REG_HI(rd), REG_HI(rs)); + return len; +} + +u8 add_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + u8 len; + + if (IN_U6_RANGE(imm)) { + len = arc_addif_r(buf, REG_LO(rd), imm); + len += arc_adci_r(BUF(buf, len), REG_HI(rd), 0); + } else { + len = mov_r64_i32(buf, JIT_REG_TMP, imm); + len += add_r64(BUF(buf, len), rd, JIT_REG_TMP); + } + return len; +} + +u8 sub_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_sub_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 sub_r32_i32(u8 *buf, u8 rd, s32 imm) +{ + if (IN_U6_RANGE(imm)) + return arc_subi_r(buf, REG_LO(rd), imm); + else + return arc_sub_i(buf, REG_LO(rd), imm); +} + +u8 sub_r64(u8 *buf, u8 rd, u8 rs) +{ + u8 len; + + len = arc_subf_r(buf, REG_LO(rd), REG_LO(rs)); + len += arc_sbc_r(BUF(buf, len), REG_HI(rd), REG_HI(rs)); + return len; +} + +u8 sub_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + u8 len; + + len = mov_r64_i32(buf, JIT_REG_TMP, imm); + len += sub_r64(BUF(buf, len), rd, JIT_REG_TMP); + return len; +} + +static u8 cmp_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_cmp_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 neg_r32(u8 *buf, u8 r) +{ + return arc_neg_r(buf, REG_LO(r), REG_LO(r)); +} + +/* In a two's complement system, -r is (~r + 1). */ +u8 neg_r64(u8 *buf, u8 r) +{ + u8 len; + + len = arc_not_r(buf, REG_LO(r), REG_LO(r)); + len += arc_not_r(BUF(buf, len), REG_HI(r), REG_HI(r)); + len += add_r64_i32(BUF(buf, len), r, 1); + return len; +} + +u8 mul_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_mpy_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs)); +} + +u8 mul_r32_i32(u8 *buf, u8 rd, s32 imm) +{ + return arc_mpy_i(buf, REG_LO(rd), REG_LO(rd), imm); +} + +/* + * MUL B, C + * -------- + * mpy t0, B_hi, C_lo + * mpy t1, B_lo, C_hi + * mpydu B_lo, B_lo, C_lo + * add B_hi, B_hi, t0 + * add B_hi, B_hi, t1 + */ +u8 mul_r64(u8 *buf, u8 rd, u8 rs) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 t1 = REG_HI(JIT_REG_TMP); + const u8 C_lo = REG_LO(rs); + const u8 C_hi = REG_HI(rs); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + u8 len; + + len = arc_mpy_r(buf, t0, B_hi, C_lo); + len += arc_mpy_r(BUF(buf, len), t1, B_lo, C_hi); + len += arc_mpydu_r(BUF(buf, len), B_lo, C_lo); + len += arc_add_r(BUF(buf, len), B_hi, t0); + len += arc_add_r(BUF(buf, len), B_hi, t1); + + return len; +} + +/* + * MUL B, imm + * ---------- + * + * To get a 64-bit result from a signed 64x32 multiplication: + * + * B_hi B_lo * + * sign imm + * ----------------------------- + * HI(B_lo*imm) LO(B_lo*imm) + + * B_hi*imm + + * B_lo*sign + * ----------------------------- + * res_hi res_lo + * + * mpy t1, B_lo, sign(imm) + * mpy t0, B_hi, imm + * mpydu B_lo, B_lo, imm + * add B_hi, B_hi, t0 + * add B_hi, B_hi, t1 + * + * Note: We can't use signed double multiplication, "mpyd", instead of an + * unsigned version, "mpydu", and then get rid of the sign adjustments + * calculated in "t1". The signed multiplication, "mpyd", will consider + * both operands, "B_lo" and "imm", as signed inputs. However, for this + * 64x32 multiplication, "B_lo" must be treated as an unsigned number. + */ +u8 mul_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 t1 = REG_HI(JIT_REG_TMP); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + u8 len = 0; + + if (imm == 1) + return 0; + + /* Is the sign-extension of the immediate "-1"? */ + if (imm < 0) + len += arc_neg_r(BUF(buf, len), t1, B_lo); + + len += arc_mpy_i(BUF(buf, len), t0, B_hi, imm); + len += arc_mpydu_i(BUF(buf, len), B_lo, imm); + len += arc_add_r(BUF(buf, len), B_hi, t0); + + /* Add the "sign*B_lo" part, if necessary. */ + if (imm < 0) + len += arc_add_r(BUF(buf, len), B_hi, t1); + + return len; +} + +u8 div_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext) +{ + if (sign_ext) + return arc_divs_r(buf, REG_LO(rd), REG_LO(rs)); + else + return arc_divu_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 div_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext) +{ + if (imm == 0) + return 0; + + if (sign_ext) + return arc_divs_i(buf, REG_LO(rd), imm); + else + return arc_divu_i(buf, REG_LO(rd), imm); +} + +u8 mod_r32(u8 *buf, u8 rd, u8 rs, bool sign_ext) +{ + if (sign_ext) + return arc_rems_r(buf, REG_LO(rd), REG_LO(rs)); + else + return arc_remu_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 mod_r32_i32(u8 *buf, u8 rd, s32 imm, bool sign_ext) +{ + if (imm == 0) + return 0; + + if (sign_ext) + return arc_rems_i(buf, REG_LO(rd), imm); + else + return arc_remu_i(buf, REG_LO(rd), imm); +} + +u8 and_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_and_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 and_r32_i32(u8 *buf, u8 rd, s32 imm) +{ + return arc_and_i(buf, REG_LO(rd), imm); +} + +u8 and_r64(u8 *buf, u8 rd, u8 rs) +{ + u8 len; + + len = arc_and_r(buf, REG_LO(rd), REG_LO(rs)); + len += arc_and_r(BUF(buf, len), REG_HI(rd), REG_HI(rs)); + return len; +} + +u8 and_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + u8 len; + + len = mov_r64_i32(buf, JIT_REG_TMP, imm); + len += and_r64(BUF(buf, len), rd, JIT_REG_TMP); + return len; +} + +static u8 tst_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_tst_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 or_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_or_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs)); +} + +u8 or_r32_i32(u8 *buf, u8 rd, s32 imm) +{ + return arc_or_i(buf, REG_LO(rd), imm); +} + +u8 or_r64(u8 *buf, u8 rd, u8 rs) +{ + u8 len; + + len = arc_or_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs)); + len += arc_or_r(BUF(buf, len), REG_HI(rd), REG_HI(rd), REG_HI(rs)); + return len; +} + +u8 or_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + u8 len; + + len = mov_r64_i32(buf, JIT_REG_TMP, imm); + len += or_r64(BUF(buf, len), rd, JIT_REG_TMP); + return len; +} + +u8 xor_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_xor_r(buf, REG_LO(rd), REG_LO(rs)); +} + +u8 xor_r32_i32(u8 *buf, u8 rd, s32 imm) +{ + return arc_xor_i(buf, REG_LO(rd), imm); +} + +u8 xor_r64(u8 *buf, u8 rd, u8 rs) +{ + u8 len; + + len = arc_xor_r(buf, REG_LO(rd), REG_LO(rs)); + len += arc_xor_r(BUF(buf, len), REG_HI(rd), REG_HI(rs)); + return len; +} + +u8 xor_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + u8 len; + + len = mov_r64_i32(buf, JIT_REG_TMP, imm); + len += xor_r64(BUF(buf, len), rd, JIT_REG_TMP); + return len; +} + +/* "asl a,b,c" --> "a = (b << (c & 31))". */ +u8 lsh_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_asl_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs)); +} + +u8 lsh_r32_i32(u8 *buf, u8 rd, u8 imm) +{ + return arc_asli_r(buf, REG_LO(rd), REG_LO(rd), imm); +} + +/* + * algorithm + * --------- + * if (n <= 32) + * to_hi = lo >> (32-n) # (32-n) is the negate of "n" in a 5-bit width. + * lo <<= n + * hi <<= n + * hi |= to_hi + * else + * hi = lo << (n-32) + * lo = 0 + * + * assembly translation for "LSH B, C" + * (heavily influenced by ARC gcc) + * ----------------------------------- + * not t0, C_lo # The first 3 lines are almost the same as: + * lsr t1, B_lo, 1 # neg t0, C_lo + * lsr t1, t1, t0 # lsr t1, B_lo, t0 --> t1 is "to_hi" + * mov t0, C_lo* # with one important difference. In "neg" + * asl B_lo, B_lo, t0 # version, when C_lo=0, t1 becomes B_lo while + * asl B_hi, B_hi, t0 # it should be 0. The "not" approach instead, + * or B_hi, B_hi, t1 # "shift"s t1 once and 31 times, practically + * btst t0, 5 # setting it to 0 when C_lo=0. + * mov.ne B_hi, B_lo** + * mov.ne B_lo, 0 + * + * *The "mov t0, C_lo" is necessary to cover the cases that C is the same + * register as B. + * + * **ARC performs a shift in this manner: B <<= (C & 31) + * For 32<=n<64, "n-32" and "n&31" are the same. Therefore, "B << n" and + * "B << (n-32)" yield the same results. e.g. the results of "B << 35" and + * "B << 3" are the same. + * + * The behaviour is undefined for n >= 64. + */ +u8 lsh_r64(u8 *buf, u8 rd, u8 rs) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 t1 = REG_HI(JIT_REG_TMP); + const u8 C_lo = REG_LO(rs); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + u8 len; + + len = arc_not_r(buf, t0, C_lo); + len += arc_lsri_r(BUF(buf, len), t1, B_lo, 1); + len += arc_lsr_r(BUF(buf, len), t1, t1, t0); + len += arc_mov_r(BUF(buf, len), t0, C_lo); + len += arc_asl_r(BUF(buf, len), B_lo, B_lo, t0); + len += arc_asl_r(BUF(buf, len), B_hi, B_hi, t0); + len += arc_or_r(BUF(buf, len), B_hi, B_hi, t1); + len += arc_btst_i(BUF(buf, len), t0, 5); + len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_hi, B_lo); + len += arc_movu_cc_r(BUF(buf, len), CC_unequal, B_lo, 0); + + return len; +} + +/* + * if (n < 32) + * to_hi = B_lo >> 32-n # extract upper n bits + * lo <<= n + * hi <<=n + * hi |= to_hi + * else if (n < 64) + * hi = lo << n-32 + * lo = 0 + */ +u8 lsh_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + const u8 n = (u8)imm; + u8 len = 0; + + if (n == 0) { + return 0; + } else if (n <= 31) { + len = arc_lsri_r(buf, t0, B_lo, 32 - n); + len += arc_asli_r(BUF(buf, len), B_lo, B_lo, n); + len += arc_asli_r(BUF(buf, len), B_hi, B_hi, n); + len += arc_or_r(BUF(buf, len), B_hi, B_hi, t0); + } else if (n <= 63) { + len = arc_asli_r(buf, B_hi, B_lo, n - 32); + len += arc_movi_r(BUF(buf, len), B_lo, 0); + } + /* n >= 64 is undefined behaviour. */ + + return len; +} + +/* "lsr a,b,c" --> "a = (b >> (c & 31))". */ +u8 rsh_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_lsr_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs)); +} + +u8 rsh_r32_i32(u8 *buf, u8 rd, u8 imm) +{ + return arc_lsri_r(buf, REG_LO(rd), REG_LO(rd), imm); +} + +/* + * For better commentary, see lsh_r64(). + * + * algorithm + * --------- + * if (n <= 32) + * to_lo = hi << (32-n) + * hi >>= n + * lo >>= n + * lo |= to_lo + * else + * lo = hi >> (n-32) + * hi = 0 + * + * RSH B,C + * ---------- + * not t0, C_lo + * asl t1, B_hi, 1 + * asl t1, t1, t0 + * mov t0, C_lo + * lsr B_hi, B_hi, t0 + * lsr B_lo, B_lo, t0 + * or B_lo, B_lo, t1 + * btst t0, 5 + * mov.ne B_lo, B_hi + * mov.ne B_hi, 0 + */ +u8 rsh_r64(u8 *buf, u8 rd, u8 rs) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 t1 = REG_HI(JIT_REG_TMP); + const u8 C_lo = REG_LO(rs); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + u8 len; + + len = arc_not_r(buf, t0, C_lo); + len += arc_asli_r(BUF(buf, len), t1, B_hi, 1); + len += arc_asl_r(BUF(buf, len), t1, t1, t0); + len += arc_mov_r(BUF(buf, len), t0, C_lo); + len += arc_lsr_r(BUF(buf, len), B_hi, B_hi, t0); + len += arc_lsr_r(BUF(buf, len), B_lo, B_lo, t0); + len += arc_or_r(BUF(buf, len), B_lo, B_lo, t1); + len += arc_btst_i(BUF(buf, len), t0, 5); + len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_lo, B_hi); + len += arc_movu_cc_r(BUF(buf, len), CC_unequal, B_hi, 0); + + return len; +} + +/* + * if (n < 32) + * to_lo = B_lo << 32-n # extract lower n bits, right-padded with 32-n 0s + * lo >>=n + * hi >>=n + * hi |= to_lo + * else if (n < 64) + * lo = hi >> n-32 + * hi = 0 + */ +u8 rsh_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + const u8 n = (u8)imm; + u8 len = 0; + + if (n == 0) { + return 0; + } else if (n <= 31) { + len = arc_asli_r(buf, t0, B_hi, 32 - n); + len += arc_lsri_r(BUF(buf, len), B_lo, B_lo, n); + len += arc_lsri_r(BUF(buf, len), B_hi, B_hi, n); + len += arc_or_r(BUF(buf, len), B_lo, B_lo, t0); + } else if (n <= 63) { + len = arc_lsri_r(buf, B_lo, B_hi, n - 32); + len += arc_movi_r(BUF(buf, len), B_hi, 0); + } + /* n >= 64 is undefined behaviour. */ + + return len; +} + +/* "asr a,b,c" --> "a = (b s>> (c & 31))". */ +u8 arsh_r32(u8 *buf, u8 rd, u8 rs) +{ + return arc_asr_r(buf, REG_LO(rd), REG_LO(rd), REG_LO(rs)); +} + +u8 arsh_r32_i32(u8 *buf, u8 rd, u8 imm) +{ + return arc_asri_r(buf, REG_LO(rd), REG_LO(rd), imm); +} + +/* + * For comparison, see rsh_r64(). + * + * algorithm + * --------- + * if (n <= 32) + * to_lo = hi << (32-n) + * hi s>>= n + * lo >>= n + * lo |= to_lo + * else + * hi_sign = hi s>>31 + * lo = hi s>> (n-32) + * hi = hi_sign + * + * ARSH B,C + * ---------- + * not t0, C_lo + * asl t1, B_hi, 1 + * asl t1, t1, t0 + * mov t0, C_lo + * asr B_hi, B_hi, t0 + * lsr B_lo, B_lo, t0 + * or B_lo, B_lo, t1 + * btst t0, 5 + * asr t0, B_hi, 31 # now, t0 = 0 or -1 based on B_hi's sign + * mov.ne B_lo, B_hi + * mov.ne B_hi, t0 + */ +u8 arsh_r64(u8 *buf, u8 rd, u8 rs) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 t1 = REG_HI(JIT_REG_TMP); + const u8 C_lo = REG_LO(rs); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + u8 len; + + len = arc_not_r(buf, t0, C_lo); + len += arc_asli_r(BUF(buf, len), t1, B_hi, 1); + len += arc_asl_r(BUF(buf, len), t1, t1, t0); + len += arc_mov_r(BUF(buf, len), t0, C_lo); + len += arc_asr_r(BUF(buf, len), B_hi, B_hi, t0); + len += arc_lsr_r(BUF(buf, len), B_lo, B_lo, t0); + len += arc_or_r(BUF(buf, len), B_lo, B_lo, t1); + len += arc_btst_i(BUF(buf, len), t0, 5); + len += arc_asri_r(BUF(buf, len), t0, B_hi, 31); + len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_lo, B_hi); + len += arc_mov_cc_r(BUF(buf, len), CC_unequal, B_hi, t0); + + return len; +} + +/* + * if (n < 32) + * to_lo = lo << 32-n # extract lower n bits, right-padded with 32-n 0s + * lo >>=n + * hi s>>=n + * hi |= to_lo + * else if (n < 64) + * lo = hi s>> n-32 + * hi = (lo[msb] ? -1 : 0) + */ +u8 arsh_r64_i32(u8 *buf, u8 rd, s32 imm) +{ + const u8 t0 = REG_LO(JIT_REG_TMP); + const u8 B_lo = REG_LO(rd); + const u8 B_hi = REG_HI(rd); + const u8 n = (u8)imm; + u8 len = 0; + + if (n == 0) { + return 0; + } else if (n <= 31) { + len = arc_asli_r(buf, t0, B_hi, 32 - n); + len += arc_lsri_r(BUF(buf, len), B_lo, B_lo, n); + len += arc_asri_r(BUF(buf, len), B_hi, B_hi, n); + len += arc_or_r(BUF(buf, len), B_lo, B_lo, t0); + } else if (n <= 63) { + len = arc_asri_r(buf, B_lo, B_hi, n - 32); + len += arc_movi_r(BUF(buf, len), B_hi, -1); + len += arc_btst_i(BUF(buf, len), B_lo, 31); + len += arc_movu_cc_r(BUF(buf, len), CC_equal, B_hi, 0); + } + /* n >= 64 is undefined behaviour. */ + + return len; +} + +u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext) +{ + u8 len = 0; +#ifdef __BIG_ENDIAN + const u8 host_endian = BPF_FROM_BE; +#else + const u8 host_endian = BPF_FROM_LE; +#endif + if (host_endian != endian || force) { + switch (size) { + case 16: + /* + * r = B4B3_B2B1 << 16 --> r = B2B1_0000 + * then, swape(r) would become the desired 0000_B1B2 + */ + len = arc_asli_r(buf, REG_LO(rd), REG_LO(rd), 16); + fallthrough; + case 32: + len += arc_swape_r(BUF(buf, len), REG_LO(rd)); + if (do_zext) + len += zext(BUF(buf, len), rd); + break; + case 64: + /* + * swap "hi" and "lo": + * hi ^= lo; + * lo ^= hi; + * hi ^= lo; + * and then swap the bytes in "hi" and "lo". + */ + len = arc_xor_r(buf, REG_HI(rd), REG_LO(rd)); + len += arc_xor_r(BUF(buf, len), REG_LO(rd), REG_HI(rd)); + len += arc_xor_r(BUF(buf, len), REG_HI(rd), REG_LO(rd)); + len += arc_swape_r(BUF(buf, len), REG_LO(rd)); + len += arc_swape_r(BUF(buf, len), REG_HI(rd)); + break; + default: + /* The caller must have handled this. */ + } + } else { + /* + * If the same endianness, there's not much to do other + * than zeroing out the upper bytes based on the "size". + */ + switch (size) { + case 16: + len = arc_and_i(buf, REG_LO(rd), 0xffff); + fallthrough; + case 32: + if (do_zext) + len += zext(BUF(buf, len), rd); + break; + case 64: + break; + default: + /* The caller must have handled this. */ + } + } + + return len; +} + +/* + * To create a frame, all that is needed is: + * + * push fp + * mov fp, sp + * sub sp, + * + * "push fp" is taken care of separately while saving the clobbered registers. + * All that remains is copying SP value to FP and shrinking SP's address space + * for any possible function call to come. + */ +static inline u8 frame_create(u8 *buf, u16 size) +{ + u8 len; + + len = arc_mov_r(buf, ARC_R_FP, ARC_R_SP); + if (IN_U6_RANGE(size)) + len += arc_subi_r(BUF(buf, len), ARC_R_SP, size); + else + len += arc_sub_i(BUF(buf, len), ARC_R_SP, size); + return len; +} + +/* + * mov sp, fp + * + * The value of SP upon entering was copied to FP. + */ +static inline u8 frame_restore(u8 *buf) +{ + return arc_mov_r(buf, ARC_R_SP, ARC_R_FP); +} + +/* + * Going from a JITed code to the native caller: + * + * mov ARC_ABI_RET_lo, BPF_REG_0_lo # r0 <- r8 + * mov ARC_ABI_RET_hi, BPF_REG_0_hi # r1 <- r9 + */ +static u8 bpf_to_arc_return(u8 *buf) +{ + u8 len; + + len = arc_mov_r(buf, ARC_R_0, REG_LO(BPF_REG_0)); + len += arc_mov_r(BUF(buf, len), ARC_R_1, REG_HI(BPF_REG_0)); + return len; +} + +/* + * Coming back from an external (in-kernel) function to the JITed code: + * + * mov ARC_ABI_RET_lo, BPF_REG_0_lo # r8 <- r0 + * mov ARC_ABI_RET_hi, BPF_REG_0_hi # r9 <- r1 + */ +u8 arc_to_bpf_return(u8 *buf) +{ + u8 len; + + len = arc_mov_r(buf, REG_LO(BPF_REG_0), ARC_R_0); + len += arc_mov_r(BUF(buf, len), REG_HI(BPF_REG_0), ARC_R_1); + return len; +} + +/* + * This translation leads to: + * + * mov r10, addr # always an 8-byte instruction + * jl [r10] + * + * The length of the "mov" must be fixed (8), otherwise it may diverge + * during the normal and extra passes: + * + * normal pass extra pass + * + * 180: mov r10,0 | 180: mov r10,0x700578d8 + * 184: jl [r10] | 188: jl [r10] + * 188: add.f r16,r16,0x1 | 18c: adc r17,r17,0 + * 18c: adc r17,r17,0 | + * + * In the above example, the change from "r10 <- 0" to "r10 <- 0x700578d8" + * has led to an increase in the length of the "mov" instruction. + * Inadvertently, that caused the loss of the "add.f" instruction. + */ +static u8 jump_and_link(u8 *buf, u32 addr) +{ + u8 len; + + len = arc_mov_i_fixed(buf, REG_LO(JIT_REG_TMP), addr); + len += arc_jl(BUF(buf, len), REG_LO(JIT_REG_TMP)); + return len; +} + +/* + * This function determines which ARC registers must be saved and restored. + * It does so by looking into: + * + * "bpf_reg": The clobbered (destination) BPF register + * "is_call": Indicator if the current instruction is a call + * + * When a register of interest is clobbered, its corresponding bit position + * in return value, "usage", is set to true. + */ +u32 mask_for_used_regs(u8 bpf_reg, bool is_call) +{ + u32 usage = 0; + + /* BPF registers that must be saved. */ + if (bpf_reg >= BPF_REG_6 && bpf_reg <= BPF_REG_9) { + usage |= BIT(REG_LO(bpf_reg)); + usage |= BIT(REG_HI(bpf_reg)); + /* + * Using the frame pointer register implies that it should + * be saved and reinitialised with the current frame data. + */ + } else if (bpf_reg == BPF_REG_FP) { + usage |= BIT(REG_LO(BPF_REG_FP)); + /* Could there be some ARC registers that must to be saved? */ + } else { + if (REG_LO(bpf_reg) >= ARC_CALLEE_SAVED_REG_FIRST && + REG_LO(bpf_reg) <= ARC_CALLEE_SAVED_REG_LAST) + usage |= BIT(REG_LO(bpf_reg)); + + if (REG_HI(bpf_reg) >= ARC_CALLEE_SAVED_REG_FIRST && + REG_HI(bpf_reg) <= ARC_CALLEE_SAVED_REG_LAST) + usage |= BIT(REG_HI(bpf_reg)); + } + + /* A "call" indicates that ARC's "blink" reg must be saved. */ + usage |= is_call ? BIT(ARC_R_BLINK) : 0; + + return usage; +} + +/* + * push blink # if blink is marked as clobbered + * push r[0-n] # if r[i] is marked as clobbered + * push fp # if fp is marked as clobbered + * mov fp, sp # if frame_size > 0 (clobbers fp) + * sub sp, # same as above + */ +u8 arc_prologue(u8 *buf, u32 usage, u16 frame_size) +{ + u8 len = 0; + u32 gp_regs = 0; + + /* Deal with blink first. */ + if (usage & BIT(ARC_R_BLINK)) + len += arc_push_r(BUF(buf, len), ARC_R_BLINK); + + gp_regs = usage & ~(BIT(ARC_R_BLINK) | BIT(ARC_R_FP)); + while (gp_regs) { + u8 reg = __builtin_ffs(gp_regs) - 1; + + len += arc_push_r(BUF(buf, len), reg); + gp_regs &= ~BIT(reg); + } + + /* Deal with fp last. */ + if ((usage & BIT(ARC_R_FP)) || frame_size > 0) + len += arc_push_r(BUF(buf, len), ARC_R_FP); + + if (frame_size > 0) + len += frame_create(BUF(buf, len), frame_size); + +#ifdef ARC_BPF_JIT_DEBUG + if ((usage & BIT(ARC_R_FP)) && frame_size == 0) { + pr_err("FP is being saved while there is no frame."); + BUG(); + } +#endif + + return len; +} + +/* + * mov sp, fp # if frame_size > 0 + * pop fp # if fp is marked as clobbered + * pop r[n-0] # if r[i] is marked as clobbered + * pop blink # if blink is marked as clobbered + * mov r0, r8 # always: ABI_return <- BPF_return + * mov r1, r9 # continuation of above + * j [blink] # always + * + * "fp being marked as clobbered" and "frame_size > 0" are the two sides of + * the same coin. + */ +u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size) +{ + u32 len = 0; + u32 gp_regs = 0; + +#ifdef ARC_BPF_JIT_DEBUG + if ((usage & BIT(ARC_R_FP)) && frame_size == 0) { + pr_err("FP is being saved while there is no frame."); + BUG(); + } +#endif + + if (frame_size > 0) + len += frame_restore(BUF(buf, len)); + + /* Deal with fp first. */ + if ((usage & BIT(ARC_R_FP)) || frame_size > 0) + len += arc_pop_r(BUF(buf, len), ARC_R_FP); + + gp_regs = usage & ~(BIT(ARC_R_BLINK) | BIT(ARC_R_FP)); + while (gp_regs) { + /* "usage" is 32-bit, each bit indicating an ARC register. */ + u8 reg = 31 - __builtin_clz(gp_regs); + + len += arc_pop_r(BUF(buf, len), reg); + gp_regs &= ~BIT(reg); + } + + /* Deal with blink last. */ + if (usage & BIT(ARC_R_BLINK)) + len += arc_pop_r(BUF(buf, len), ARC_R_BLINK); + + /* Wrap up the return value and jump back to the caller. */ + len += bpf_to_arc_return(BUF(buf, len)); + len += arc_jmp_return(BUF(buf, len)); + + return len; +} + +/* + * For details on the algorithm, see the comments of "gen_jcc_64()". + * + * This data structure is holding information for jump translations. + * + * jit_off: How many bytes into the current JIT address, "b"ranch insn. occurs + * cond: The condition that the ARC branch instruction must use + * + * e.g.: + * + * BPF_JGE R1, R0, @target + * ------------------------ + * | + * v + * 0x1000: cmp r3, r1 # 0x1000 is the JIT address for "BPF_JGE ..." insn + * 0x1004: bhi @target # first jump (branch higher) + * 0x1008: blo @end # second jump acting as a skip (end is 0x1014) + * 0x100C: cmp r2, r0 # the lower 32 bits are evaluated + * 0x1010: bhs @target # third jump (branch higher or same) + * 0x1014: ... + * + * The jit_off(set) of the "bhi" is 4 bytes. + * The cond(ition) for the "bhi" is "CC_great_u". + * + * The jit_off(set) is necessary for calculating the exact displacement + * to the "target" address: + * + * jit_address + jit_off(set) - @target + * 0x1000 + 4 - @target + */ +#define JCC64_NR_OF_JMPS 3 /* Number of jumps in jcc64 template. */ +#define JCC64_INSNS_TO_END 3 /* Number of insn. inclusive the 2nd jmp to end. */ +#define JCC64_SKIP_JMP 1 /* Index of the "skip" jump to "end". */ +const struct { + /* + * "jit_off" is common between all "jmp[]" and is coupled with + * "cond" of each "jmp[]" instance. e.g.: + * + * arcv2_64_jccs.jit_off[1] + * arcv2_64_jccs.jmp[ARC_CC_UGT].cond[1] + * + * Are indicating that the second jump in JITed code of "UGT" + * is at offset "jit_off[1]" while its condition is "cond[1]". + */ + u8 jit_off[JCC64_NR_OF_JMPS]; + + struct { + u8 cond[JCC64_NR_OF_JMPS]; + } jmp[ARC_CC_SLE + 1]; +} arcv2_64_jccs = { + .jit_off = { + INSN_len_normal * 1, + INSN_len_normal * 2, + INSN_len_normal * 4 + }, + /* + * cmp rd_hi, rs_hi + * bhi @target # 1: u> + * blo @end # 2: u< + * cmp rd_lo, rs_lo + * bhi @target # 3: u> + * end: + */ + .jmp[ARC_CC_UGT] = { + .cond = {CC_great_u, CC_less_u, CC_great_u} + }, + /* + * cmp rd_hi, rs_hi + * bhi @target # 1: u> + * blo @end # 2: u< + * cmp rd_lo, rs_lo + * bhs @target # 3: u>= + * end: + */ + .jmp[ARC_CC_UGE] = { + .cond = {CC_great_u, CC_less_u, CC_great_eq_u} + }, + /* + * cmp rd_hi, rs_hi + * blo @target # 1: u< + * bhi @end # 2: u> + * cmp rd_lo, rs_lo + * blo @target # 3: u< + * end: + */ + .jmp[ARC_CC_ULT] = { + .cond = {CC_less_u, CC_great_u, CC_less_u} + }, + /* + * cmp rd_hi, rs_hi + * blo @target # 1: u< + * bhi @end # 2: u> + * cmp rd_lo, rs_lo + * bls @target # 3: u<= + * end: + */ + .jmp[ARC_CC_ULE] = { + .cond = {CC_less_u, CC_great_u, CC_less_eq_u} + }, + /* + * cmp rd_hi, rs_hi + * bgt @target # 1: s> + * blt @end # 2: s< + * cmp rd_lo, rs_lo + * bhi @target # 3: u> + * end: + */ + .jmp[ARC_CC_SGT] = { + .cond = {CC_great_s, CC_less_s, CC_great_u} + }, + /* + * cmp rd_hi, rs_hi + * bgt @target # 1: s> + * blt @end # 2: s< + * cmp rd_lo, rs_lo + * bhs @target # 3: u>= + * end: + */ + .jmp[ARC_CC_SGE] = { + .cond = {CC_great_s, CC_less_s, CC_great_eq_u} + }, + /* + * cmp rd_hi, rs_hi + * blt @target # 1: s< + * bgt @end # 2: s> + * cmp rd_lo, rs_lo + * blo @target # 3: u< + * end: + */ + .jmp[ARC_CC_SLT] = { + .cond = {CC_less_s, CC_great_s, CC_less_u} + }, + /* + * cmp rd_hi, rs_hi + * blt @target # 1: s< + * bgt @end # 2: s> + * cmp rd_lo, rs_lo + * bls @target # 3: u<= + * end: + */ + .jmp[ARC_CC_SLE] = { + .cond = {CC_less_s, CC_great_s, CC_less_eq_u} + } +}; + +/* + * The displacement (offset) for ARC's "b"ranch instruction is the distance + * from the aligned version of _current_ instruction (PCL) to the target + * instruction: + * + * DISP = TARGET - PCL # PCL is the word aligned PC + */ +static inline s32 get_displacement(u32 curr_off, u32 targ_off) +{ + return (s32)(targ_off - (curr_off & ~3L)); +} + +/* + * "disp"lacement should be: + * + * 1. 16-bit aligned. + * 2. fit in S25, because no "condition code" is supposed to be encoded. + */ +static inline bool is_valid_far_disp(s32 disp) +{ + return (!(disp & 1) && IN_S25_RANGE(disp)); +} + +/* + * "disp"lacement should be: + * + * 1. 16-bit aligned. + * 2. fit in S21, because "condition code" is supposed to be encoded too. + */ +static inline bool is_valid_near_disp(s32 disp) +{ + return (!(disp & 1) && IN_S21_RANGE(disp)); +} + +/* + * cmp rd_hi, rs_hi + * cmp.z rd_lo, rs_lo + * b{eq,ne} @target + * | | + * | `--> "eq" param is false (JNE) + * `-----> "eq" param is true (JEQ) + */ +static int gen_j_eq_64(u8 *buf, u8 rd, u8 rs, bool eq, + u32 curr_off, u32 targ_off) +{ + s32 disp; + u8 len = 0; + + len += arc_cmp_r(BUF(buf, len), REG_HI(rd), REG_HI(rs)); + len += arc_cmpz_r(BUF(buf, len), REG_LO(rd), REG_LO(rs)); + disp = get_displacement(curr_off + len, targ_off); + len += arc_bcc(BUF(buf, len), eq ? CC_equal : CC_unequal, disp); + + return len; +} + +/* + * tst rd_hi, rs_hi + * tst.z rd_lo, rs_lo + * bne @target + */ +static u8 gen_jset_64(u8 *buf, u8 rd, u8 rs, u32 curr_off, u32 targ_off) +{ + u8 len = 0; + s32 disp; + + len += arc_tst_r(BUF(buf, len), REG_HI(rd), REG_HI(rs)); + len += arc_tstz_r(BUF(buf, len), REG_LO(rd), REG_LO(rs)); + disp = get_displacement(curr_off + len, targ_off); + len += arc_bcc(BUF(buf, len), CC_unequal, disp); + + return len; +} + +/* + * Verify if all the jumps for a JITed jcc64 operation are valid, + * by consulting the data stored at "arcv2_64_jccs". + */ +static bool check_jcc_64(u32 curr_off, u32 targ_off, u8 cond) +{ + size_t i; + + if (cond >= ARC_CC_LAST) + return false; + + for (i = 0; i < JCC64_NR_OF_JMPS; i++) { + u32 from, to; + + from = curr_off + arcv2_64_jccs.jit_off[i]; + /* for the 2nd jump, we jump to the end of block. */ + if (i != JCC64_SKIP_JMP) + to = targ_off; + else + to = from + (JCC64_INSNS_TO_END * INSN_len_normal); + /* There is a "cc" in the instruction, so a "near" jump. */ + if (!is_valid_near_disp(get_displacement(from, to))) + return false; + } + + return true; +} + +/* Can the jump from "curr_off" to "targ_off" actually happen? */ +bool check_jmp_64(u32 curr_off, u32 targ_off, u8 cond) +{ + s32 disp; + + switch (cond) { + case ARC_CC_UGT: + case ARC_CC_UGE: + case ARC_CC_ULT: + case ARC_CC_ULE: + case ARC_CC_SGT: + case ARC_CC_SGE: + case ARC_CC_SLT: + case ARC_CC_SLE: + return check_jcc_64(curr_off, targ_off, cond); + case ARC_CC_EQ: + case ARC_CC_NE: + case ARC_CC_SET: + /* + * The "jump" for the JITed BPF_J{SET,EQ,NE} is actually the + * 3rd instruction. See comments of "gen_j{set,_eq}_64()". + */ + curr_off += 2 * INSN_len_normal; + disp = get_displacement(curr_off, targ_off); + /* There is a "cc" field in the issued instruction. */ + return is_valid_near_disp(disp); + case ARC_CC_AL: + disp = get_displacement(curr_off, targ_off); + return is_valid_far_disp(disp); + default: + return false; + } +} + +/* + * The template for the 64-bit jumps with the following BPF conditions + * + * u< u<= u> u>= s< s<= s> s>= + * + * Looks like below: + * + * cmp rd_hi, rs_hi + * b @target + * b @end + * cmp rd_lo, rs_lo # if execution reaches here, r{d,s}_hi are equal + * b @target + * end: + * + * "c1" is the condition that JIT is handling minus the equality part. + * For instance if we have to translate an "unsigned greater or equal", + * then "c1" will be "unsigned greater". We won't know about equality + * until all 64-bits of data (higeher and lower registers) are processed. + * + * "c2" is the counter logic of "c1". For instance, if "c1" is originated + * from "s>", then "c2" would be "s<". Notice that equality doesn't play + * a role here either, because the lower 32 bits are not processed yet. + * + * "c3" is the unsigned version of "c1", no matter if the BPF condition + * was signed or unsigned. An unsigned version is necessary, because the + * MSB of the lower 32 bits does not reflect a sign in the whole 64-bit + * scheme. Otherwise, 64-bit comparisons like + * (0x0000_0000,0x8000_0000) s>= (0x0000_0000,0x0000_0000) + * would yield an incorrect result. Finally, if there is an equality + * check in the BPF condition, it will be reflected in "c3". + * + * You can find all the instances of this template where the + * "arcv2_64_jccs" is getting initialised. + */ +static u8 gen_jcc_64(u8 *buf, u8 rd, u8 rs, u8 cond, + u32 curr_off, u32 targ_off) +{ + s32 disp; + u32 end_off; + const u8 *cc = arcv2_64_jccs.jmp[cond].cond; + u8 len = 0; + + /* cmp rd_hi, rs_hi */ + len += arc_cmp_r(buf, REG_HI(rd), REG_HI(rs)); + + /* b @target */ + disp = get_displacement(curr_off + len, targ_off); + len += arc_bcc(BUF(buf, len), cc[0], disp); + + /* b @end */ + end_off = curr_off + len + (JCC64_INSNS_TO_END * INSN_len_normal); + disp = get_displacement(curr_off + len, end_off); + len += arc_bcc(BUF(buf, len), cc[1], disp); + + /* cmp rd_lo, rs_lo */ + len += arc_cmp_r(BUF(buf, len), REG_LO(rd), REG_LO(rs)); + + /* b @target */ + disp = get_displacement(curr_off + len, targ_off); + len += arc_bcc(BUF(buf, len), cc[2], disp); + + return len; +} + +/* + * This function only applies the necessary logic to make the proper + * translations. All the sanity checks must have already been done + * by calling the check_jmp_64(). + */ +u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off) +{ + u8 len = 0; + bool eq = false; + s32 disp; + + switch (cond) { + case ARC_CC_AL: + disp = get_displacement(curr_off, targ_off); + len = arc_b(buf, disp); + break; + case ARC_CC_UGT: + case ARC_CC_UGE: + case ARC_CC_ULT: + case ARC_CC_ULE: + case ARC_CC_SGT: + case ARC_CC_SGE: + case ARC_CC_SLT: + case ARC_CC_SLE: + len = gen_jcc_64(buf, rd, rs, cond, curr_off, targ_off); + break; + case ARC_CC_EQ: + eq = true; + fallthrough; + case ARC_CC_NE: + len = gen_j_eq_64(buf, rd, rs, eq, curr_off, targ_off); + break; + case ARC_CC_SET: + len = gen_jset_64(buf, rd, rs, curr_off, targ_off); + break; + default: +#ifdef ARC_BPF_JIT_DEBUG + pr_err("64-bit jump condition is not known."); + BUG(); +#endif + } + return len; +} + +/* + * The condition codes to use when generating JIT instructions + * for 32-bit jumps. + * + * The "ARC_CC_AL" index is not really used by the code, but it + * is here for the sake of completeness. + * + * The "ARC_CC_SET" becomes "CC_unequal" because of the "tst" + * instruction that precedes the conditional branch. + */ +const u8 arcv2_32_jmps[ARC_CC_LAST] = { + [ARC_CC_UGT] = CC_great_u, + [ARC_CC_UGE] = CC_great_eq_u, + [ARC_CC_ULT] = CC_less_u, + [ARC_CC_ULE] = CC_less_eq_u, + [ARC_CC_SGT] = CC_great_s, + [ARC_CC_SGE] = CC_great_eq_s, + [ARC_CC_SLT] = CC_less_s, + [ARC_CC_SLE] = CC_less_eq_s, + [ARC_CC_AL] = CC_always, + [ARC_CC_EQ] = CC_equal, + [ARC_CC_NE] = CC_unequal, + [ARC_CC_SET] = CC_unequal +}; + +/* Can the jump from "curr_off" to "targ_off" actually happen? */ +bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond) +{ + u8 addendum; + s32 disp; + + if (cond >= ARC_CC_LAST) + return false; + + /* + * The unconditional jump happens immediately, while the rest + * are either preceded by a "cmp" or "tst" instruction. + */ + addendum = (cond == ARC_CC_AL) ? 0 : INSN_len_normal; + disp = get_displacement(curr_off + addendum, targ_off); + + if (ARC_CC_AL) + return is_valid_far_disp(disp); + else + return is_valid_near_disp(disp); +} + +/* + * The JITed code for 32-bit (conditional) branches: + * + * ARC_CC_AL @target + * b @jit_targ_addr + * + * ARC_CC_SET rd, rs, @target + * tst rd, rs + * bnz @jit_targ_addr + * + * ARC_CC_xx rd, rs, @target + * cmp rd, rs + * b @jit_targ_addr # cc = arcv2_32_jmps[xx] + */ +u8 gen_jmp_32(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off) +{ + s32 disp; + u8 len = 0; + + /* + * Although this must have already been checked by "check_jmp_32()", + * we're not going to risk accessing "arcv2_32_jmps" array without + * the boundary check. + */ + if (cond >= ARC_CC_LAST) { +#ifdef ARC_BPF_JIT_DEBUG + pr_err("32-bit jump condition is not known."); + BUG(); +#endif + return 0; + } + + /* If there is a "condition", issue the "cmp" or "tst" first. */ + if (cond != ARC_CC_AL) { + if (cond == ARC_CC_SET) + len = tst_r32(buf, rd, rs); + else + len = cmp_r32(buf, rd, rs); + /* + * The issued instruction affects the "disp"lacement as + * it alters the "curr_off" by its "len"gth. The "curr_off" + * should always point to the jump instruction. + */ + disp = get_displacement(curr_off + len, targ_off); + len += arc_bcc(BUF(buf, len), arcv2_32_jmps[cond], disp); + } else { + /* The straight forward unconditional jump. */ + disp = get_displacement(curr_off, targ_off); + len = arc_b(buf, disp); + } + + return len; +} + +/* + * Generate code for functions calls. There can be two types of calls: + * + * - Calling another BPF function + * - Calling an in-kernel function which is compiled by ARC gcc + * + * In the later case, we must comply to ARCv2 ABI and handle arguments + * and return values accordingly. + */ +u8 gen_func_call(u8 *buf, ARC_ADDR func_addr, bool external_func) +{ + u8 len = 0; + + /* + * In case of an in-kernel function call, always push the 5th + * argument onto the stack, because that's where the ABI dictates + * it should be found. If the callee doesn't really use it, no harm + * is done. The stack is readjusted either way after the call. + */ + if (external_func) + len += push_r64(BUF(buf, len), BPF_REG_5); + + len += jump_and_link(BUF(buf, len), func_addr); + + if (external_func) + len += arc_add_i(BUF(buf, len), ARC_R_SP, ARC_R_SP, ARG5_SIZE); + + return len; +} diff --git a/arch/arc/net/bpf_jit_core.c b/arch/arc/net/bpf_jit_core.c new file mode 100644 index 000000000000..6f6b4ffccf2c --- /dev/null +++ b/arch/arc/net/bpf_jit_core.c @@ -0,0 +1,1425 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The back-end-agnostic part of Just-In-Time compiler for eBPF bytecode. + * + * Copyright (c) 2024 Synopsys Inc. + * Author: Shahab Vahedi + */ +#include +#include "bpf_jit.h" + +/* + * Check for the return value. A pattern used often in this file. + * There must be a "ret" variable of type "int" in the scope. + */ +#define CHECK_RET(cmd) \ + do { \ + ret = (cmd); \ + if (ret < 0) \ + return ret; \ + } while (0) + +#ifdef ARC_BPF_JIT_DEBUG +/* Dumps bytes in /var/log/messages at KERN_INFO level (4). */ +static void dump_bytes(const u8 *buf, u32 len, const char *header) +{ + u8 line[64]; + size_t i, j; + + pr_info("-----------------[ %s ]-----------------\n", header); + + for (i = 0, j = 0; i < len; i++) { + /* Last input byte? */ + if (i == len - 1) { + j += scnprintf(line + j, 64 - j, "0x%02x", buf[i]); + pr_info("%s\n", line); + break; + } + /* End of line? */ + else if (i % 8 == 7) { + j += scnprintf(line + j, 64 - j, "0x%02x", buf[i]); + pr_info("%s\n", line); + j = 0; + } else { + j += scnprintf(line + j, 64 - j, "0x%02x, ", buf[i]); + } + } +} +#endif /* ARC_BPF_JIT_DEBUG */ + +/********************* JIT context ***********************/ + +/* + * buf: Translated instructions end up here. + * len: The length of whole block in bytes. + * index: The offset at which the _next_ instruction may be put. + */ +struct jit_buffer { + u8 *buf; + u32 len; + u32 index; +}; + +/* + * This is a subset of "struct jit_context" that its information is deemed + * necessary for the next extra pass to come. + * + * bpf_header: Needed to finally lock the region. + * bpf2insn: Used to find the translation for instructions of interest. + * + * Things like "jit.buf" and "jit.len" can be retrieved respectively from + * "prog->bpf_func" and "prog->jited_len". + */ +struct arc_jit_data { + struct bpf_binary_header *bpf_header; + u32 *bpf2insn; +}; + +/* + * The JIT pertinent context that is used by different functions. + * + * prog: The current eBPF program being handled. + * orig_prog: The original eBPF program before any possible change. + * jit: The JIT buffer and its length. + * bpf_header: The JITed program header. "jit.buf" points inside it. + * emit: If set, opcodes are written to memory; else, a dry-run. + * do_zext: If true, 32-bit sub-regs must be zero extended. + * bpf2insn: Maps BPF insn indices to their counterparts in jit.buf. + * bpf2insn_valid: Indicates if "bpf2ins" is populated with the mappings. + * jit_data: A piece of memory to transfer data to the next pass. + * arc_regs_clobbered: Each bit status determines if that arc reg is clobbered. + * save_blink: Whether ARC's "blink" register needs to be saved. + * frame_size: Derived from "prog->aux->stack_depth". + * epilogue_offset: Used by early "return"s in the code to jump here. + * need_extra_pass: A forecast if an "extra_pass" will occur. + * is_extra_pass: Indicates if the current pass is an extra pass. + * user_bpf_prog: True, if VM opcodes come from a real program. + * blinded: True if "constant blinding" step returned a new "prog". + * success: Indicates if the whole JIT went OK. + */ +struct jit_context { + struct bpf_prog *prog; + struct bpf_prog *orig_prog; + struct jit_buffer jit; + struct bpf_binary_header *bpf_header; + bool emit; + bool do_zext; + u32 *bpf2insn; + bool bpf2insn_valid; + struct arc_jit_data *jit_data; + u32 arc_regs_clobbered; + bool save_blink; + u16 frame_size; + u32 epilogue_offset; + bool need_extra_pass; + bool is_extra_pass; + bool user_bpf_prog; + bool blinded; + bool success; +}; + +/* + * If we're in ARC_BPF_JIT_DEBUG mode and the debug level is right, dump the + * input BPF stream. "bpf_jit_dump()" is not fully suited for this purpose. + */ +static void vm_dump(const struct bpf_prog *prog) +{ +#ifdef ARC_BPF_JIT_DEBUG + if (bpf_jit_enable > 1) + dump_bytes((u8 *)prog->insns, 8 * prog->len, " VM "); +#endif +} + +/* + * If the right level of debug is set, dump the bytes. There are 2 variants + * of this function: + * + * 1. Use the standard bpf_jit_dump() which is meant only for JITed code. + * 2. Use the dump_bytes() to match its "vm_dump()" instance. + */ +static void jit_dump(const struct jit_context *ctx) +{ +#ifdef ARC_BPF_JIT_DEBUG + u8 header[8]; +#endif + const int pass = ctx->is_extra_pass ? 2 : 1; + + if (bpf_jit_enable <= 1 || !ctx->prog->jited) + return; + +#ifdef ARC_BPF_JIT_DEBUG + scnprintf(header, sizeof(header), "JIT:%d", pass); + dump_bytes(ctx->jit.buf, ctx->jit.len, header); + pr_info("\n"); +#else + bpf_jit_dump(ctx->prog->len, ctx->jit.len, pass, ctx->jit.buf); +#endif +} + +/* Initialise the context so there's no garbage. */ +static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog) +{ + memset(ctx, 0, sizeof(ctx)); + + ctx->orig_prog = prog; + + /* If constant blinding was requested but failed, scram. */ + ctx->prog = bpf_jit_blind_constants(prog); + if (IS_ERR(ctx->prog)) + return PTR_ERR(ctx->prog); + ctx->blinded = (ctx->prog == ctx->orig_prog ? false : true); + + /* If the verifier doesn't zero-extend, then we have to do it. */ + ctx->do_zext = !ctx->prog->aux->verifier_zext; + + ctx->is_extra_pass = ctx->prog->jited; + ctx->user_bpf_prog = ctx->prog->is_func; + + return 0; +} + +/* + * Only after the first iteration of normal pass (the dry-run), + * there are valid offsets in ctx->bpf2insn array. + */ +static inline bool offsets_available(const struct jit_context *ctx) +{ + return ctx->bpf2insn_valid; +} + +/* + * "*mem" should be freed when there is no "extra pass" to come, + * or the compilation terminated abruptly. A few of such memory + * allocations are: ctx->jit_data and ctx->bpf2insn. + */ +static inline void maybe_free(struct jit_context *ctx, void **mem) +{ + if (*mem) { + if (!ctx->success || !ctx->need_extra_pass) { + kfree(*mem); + *mem = NULL; + } + } +} + +/* + * Free memories based on the status of the context. + * + * A note about "bpf_header": On successful runs, "bpf_header" is + * not freed, because "jit.buf", a sub-array of it, is returned as + * the "bpf_func". However, "bpf_header" is lost and nothing points + * to it. This should not cause a leakage, because apparently + * "bpf_header" can be revived by "bpf_jit_binary_hdr()". This is + * how "bpf_jit_free()" in "kernel/bpf/core.c" releases the memory. + */ +static void jit_ctx_cleanup(struct jit_context *ctx) +{ + if (ctx->blinded) { + /* if all went well, release the orig_prog. */ + if (ctx->success) + bpf_jit_prog_release_other(ctx->prog, ctx->orig_prog); + else + bpf_jit_prog_release_other(ctx->orig_prog, ctx->prog); + } + + maybe_free(ctx, (void **)&ctx->bpf2insn); + maybe_free(ctx, (void **)&ctx->jit_data); + + if (!ctx->bpf2insn) + ctx->bpf2insn_valid = false; + + /* Freeing "bpf_header" is enough. "jit.buf" is a sub-array of it. */ + if (!ctx->success && ctx->bpf_header) { + bpf_jit_binary_free(ctx->bpf_header); + ctx->bpf_header = NULL; + ctx->jit.buf = NULL; + ctx->jit.index = 0; + ctx->jit.len = 0; + } + + ctx->emit = false; + ctx->do_zext = false; +} + +/* + * Analyse the register usage and record the frame size. + * The register usage is determined by consulting the back-end. + */ +static void analyze_reg_usage(struct jit_context *ctx) +{ + size_t i; + u32 usage = 0; + const struct bpf_insn *insn = ctx->prog->insnsi; + + for (i = 0; i < ctx->prog->len; i++) { + u8 bpf_reg; + bool call; + + bpf_reg = insn[i].dst_reg; + call = (insn[i].code == (BPF_JMP | BPF_CALL)) ? true : false; + usage |= mask_for_used_regs(bpf_reg, call); + } + + ctx->arc_regs_clobbered = usage; + ctx->frame_size = ctx->prog->aux->stack_depth; +} + +/* Verify that no instruction will be emitted when there is no buffer. */ +static inline int jit_buffer_check(const struct jit_context *ctx) +{ + if (ctx->emit) { + if (!ctx->jit.buf) { + pr_err("bpf-jit: inconsistence state; no " + "buffer to emit instructions.\n"); + return -EINVAL; + } else if (ctx->jit.index > ctx->jit.len) { + pr_err("bpf-jit: estimated JIT length is less " + "than the emitted instructions.\n"); + return -EFAULT; + } + } + return 0; +} + +/* On a dry-run (emit=false), "jit.len" is growing gradually. */ +static inline void jit_buffer_update(struct jit_context *ctx, u32 n) +{ + if (!ctx->emit) + ctx->jit.len += n; + else + ctx->jit.index += n; +} + +/* Based on "emit", determine the address where instructions are emitted. */ +static inline u8 *effective_jit_buf(const struct jit_context *ctx) +{ + return ctx->emit ? (ctx->jit.buf + ctx->jit.index) : NULL; +} + +/* Prologue based on context variables set by "analyze_reg_usage()". */ +static int handle_prologue(struct jit_context *ctx) +{ + int ret; + u8 *buf = effective_jit_buf(ctx); + u32 len = 0; + + CHECK_RET(jit_buffer_check(ctx)); + + len = arc_prologue(buf, ctx->arc_regs_clobbered, ctx->frame_size); + jit_buffer_update(ctx, len); + + return 0; +} + +/* The counter part for "handle_prologue()". */ +static int handle_epilogue(struct jit_context *ctx) +{ + int ret; + u8 *buf = effective_jit_buf(ctx); + u32 len = 0; + + CHECK_RET(jit_buffer_check(ctx)); + + len = arc_epilogue(buf, ctx->arc_regs_clobbered, ctx->frame_size); + jit_buffer_update(ctx, len); + + return 0; +} + +/* Tell which number of the BPF instruction we are dealing with. */ +static inline s32 get_index_for_insn(const struct jit_context *ctx, + const struct bpf_insn *insn) +{ + return (insn - ctx->prog->insnsi); +} + +/* + * In most of the cases, the "offset" is read from "insn->off". However, + * if it is an unconditional BPF_JMP32, then it comes from "insn->imm". + * + * (Courtesy of "cpu=v4" support) + */ +static inline s32 get_offset(const struct bpf_insn *insn) +{ + if ((BPF_CLASS(insn->code) == BPF_JMP32) && + (BPF_OP(insn->code) == BPF_JA)) + return insn->imm; + else + return insn->off; +} + +/* + * Determine to which number of the BPF instruction we're jumping to. + * + * The "offset" is interpreted as the "number" of BPF instructions + * from the _next_ BPF instruction. e.g.: + * + * 4 means 4 instructions after the next insn + * 0 means 0 instructions after the next insn -> fallthrough. + * -1 means 1 instruction before the next insn -> jmp to current insn. + * + * Another way to look at this, "offset" is the number of instructions + * that exist between the current instruction and the target instruction. + * + * It is worth noting that a "mov r,i64", which is 16-byte long, is + * treated as two instructions long, therefore "offset" needn't be + * treated specially for those. Everything is uniform. + */ +static inline s32 get_target_index_for_insn(const struct jit_context *ctx, + const struct bpf_insn *insn) +{ + return (get_index_for_insn(ctx, insn) + 1) + get_offset(insn); +} + +/* Is there an immediate operand encoded in the "insn"? */ +static inline bool has_imm(const struct bpf_insn *insn) +{ + return BPF_SRC(insn->code) == BPF_K; +} + +/* Is the last BPF instruction? */ +static inline bool is_last_insn(const struct bpf_prog *prog, u32 idx) +{ + return idx == (prog->len - 1); +} + +/* + * Invocation of this function, conditionally signals the need for + * an extra pass. The conditions that must be met are: + * + * 1. The current pass itself shouldn't be an extra pass. + * 2. The stream of bytes being JITed must come from a user program. + */ +static inline void set_need_for_extra_pass(struct jit_context *ctx) +{ + if (!ctx->is_extra_pass) + ctx->need_extra_pass = ctx->user_bpf_prog; +} + +/* + * Check if the "size" is valid and then transfer the control to + * the back-end for the swap. + */ +static int handle_swap(u8 *buf, u8 rd, u8 size, u8 endian, + bool force, bool do_zext, u8 *len) +{ + /* Sanity check on the size. */ + switch (size) { + case 16: + case 32: + case 64: + break; + default: + pr_err("bpf-jit: invalid size for swap.\n"); + return -EINVAL; + } + + *len = gen_swap(buf, rd, size, endian, force, do_zext); + + return 0; +} + +/* Checks if the (instruction) index is in valid range. */ +static inline bool check_insn_idx_valid(const struct jit_context *ctx, + const s32 idx) +{ + return (idx >= 0 && idx < ctx->prog->len); +} + +/* + * Decouple the back-end from BPF by converting BPF conditions + * to internal enum. ARC_CC_* start from 0 and are used as index + * to an array. BPF_J* usage must end after this conversion. + */ +static int bpf_cond_to_arc(const u8 op, u8 *arc_cc) +{ + switch (op) { + case BPF_JA: + *arc_cc = ARC_CC_AL; + break; + case BPF_JEQ: + *arc_cc = ARC_CC_EQ; + break; + case BPF_JGT: + *arc_cc = ARC_CC_UGT; + break; + case BPF_JGE: + *arc_cc = ARC_CC_UGE; + break; + case BPF_JSET: + *arc_cc = ARC_CC_SET; + break; + case BPF_JNE: + *arc_cc = ARC_CC_NE; + break; + case BPF_JSGT: + *arc_cc = ARC_CC_SGT; + break; + case BPF_JSGE: + *arc_cc = ARC_CC_SGE; + break; + case BPF_JLT: + *arc_cc = ARC_CC_ULT; + break; + case BPF_JLE: + *arc_cc = ARC_CC_ULE; + break; + case BPF_JSLT: + *arc_cc = ARC_CC_SLT; + break; + case BPF_JSLE: + *arc_cc = ARC_CC_SLE; + break; + default: + pr_err("bpf-jit: can't handle condition 0x%02X\n", op); + return -EINVAL; + } + return 0; +} + +/* + * Check a few things for a supposedly "jump" instruction: + * + * 0. "insn" is a "jump" instruction, but not the "call/exit" variant. + * 1. The current "insn" index is in valid range. + * 2. The index of target instruction is in valid range. + */ +static int check_bpf_jump(const struct jit_context *ctx, + const struct bpf_insn *insn) +{ + const u8 class = BPF_CLASS(insn->code); + const u8 op = BPF_OP(insn->code); + + /* Must be a jmp(32) instruction that is not a "call/exit". */ + if ((class != BPF_JMP && class != BPF_JMP32) || + (op == BPF_CALL || op == BPF_EXIT)) { + pr_err("bpf-jit: not a jump instruction.\n"); + return -EINVAL; + } + + if (!check_insn_idx_valid(ctx, get_index_for_insn(ctx, insn))) { + pr_err("bpf-jit: the bpf jump insn is not in prog.\n"); + return -EINVAL; + } + + if (!check_insn_idx_valid(ctx, get_target_index_for_insn(ctx, insn))) { + pr_err("bpf-jit: bpf jump label is out of range.\n"); + return -EINVAL; + } + + return 0; +} + +/* + * Based on input "insn", consult "ctx->bpf2insn" to get the + * related index (offset) of the translation in JIT stream. + */ +static u32 get_curr_jit_off(const struct jit_context *ctx, + const struct bpf_insn *insn) +{ + const s32 idx = get_index_for_insn(ctx, insn); +#ifdef ARC_BPF_JIT_DEBUG + BUG_ON(!offsets_available(ctx) || !check_insn_idx_valid(ctx, idx)); +#endif + return ctx->bpf2insn[idx]; +} + +/* + * The input "insn" must be a jump instruction. + * + * Based on input "insn", consult "ctx->bpf2insn" to get the + * related JIT index (offset) of "target instruction" that + * "insn" would jump to. + */ +static u32 get_targ_jit_off(const struct jit_context *ctx, + const struct bpf_insn *insn) +{ + const s32 tidx = get_target_index_for_insn(ctx, insn); +#ifdef ARC_BPF_JIT_DEBUG + BUG_ON(!offsets_available(ctx) || !check_insn_idx_valid(ctx, tidx)); +#endif + return ctx->bpf2insn[tidx]; +} + +/* + * This function will return 0 for a feasible jump. + * + * Consult the back-end to check if it finds it feasible to emit + * the necessary instructions based on "cond" and the displacement + * between the "from_off" and the "to_off". + */ +static int feasible_jit_jump(u32 from_off, u32 to_off, u8 cond, bool j32) +{ + int ret = 0; + + if (j32) { + if (!check_jmp_32(from_off, to_off, cond)) + ret = -EFAULT; + } else { + if (!check_jmp_64(from_off, to_off, cond)) + ret = -EFAULT; + } + + if (ret != 0) + pr_err("bpf-jit: the JIT displacement is not OK.\n"); + + return ret; +} + +/* + * This jump handler performs the following steps: + * + * 1. Compute ARC's internal condition code from BPF's + * 2. Determine the bitness of the operation (32 vs. 64) + * 3. Sanity check on BPF stream + * 4. Sanity check on what is supposed to be JIT's displacement + * 5. And finally, emit the necessary instructions + * + * The last two steps are performed through the back-end. + * The value of steps 1 and 2 are necessary inputs for the back-end. + */ +static int handle_jumps(const struct jit_context *ctx, + const struct bpf_insn *insn, + u8 *len) +{ + u8 cond; + int ret = 0; + u8 *buf = effective_jit_buf(ctx); + const bool j32 = (BPF_CLASS(insn->code) == BPF_JMP32) ? true : false; + const u8 rd = insn->dst_reg; + u8 rs = insn->src_reg; + u32 curr_off = 0, targ_off = 0; + + *len = 0; + + /* Map the BPF condition to internal enum. */ + CHECK_RET(bpf_cond_to_arc(BPF_OP(insn->code), &cond)); + + /* Sanity check on the BPF byte stream. */ + CHECK_RET(check_bpf_jump(ctx, insn)); + + /* + * Move the immediate into a temporary register _now_ for 2 reasons: + * + * 1. "gen_jmp_{32,64}()" deal with operands in registers. + * + * 2. The "len" parameter will grow so that the current jit offset + * (curr_off) will have increased to a point where the necessary + * instructions can be inserted by "gen_jmp_{32,64}()". + */ + if (has_imm(insn) && cond != ARC_CC_AL) { + if (j32) { + *len += mov_r32_i32(BUF(buf, *len), JIT_REG_TMP, + insn->imm); + } else { + *len += mov_r64_i32(BUF(buf, *len), JIT_REG_TMP, + insn->imm); + } + rs = JIT_REG_TMP; + } + + /* If the offsets are known, check if the branch can occur. */ + if (offsets_available(ctx)) { + curr_off = get_curr_jit_off(ctx, insn) + *len; + targ_off = get_targ_jit_off(ctx, insn); + + /* Sanity check on the back-end side. */ + CHECK_RET(feasible_jit_jump(curr_off, targ_off, cond, j32)); + } + + if (j32) { + *len += gen_jmp_32(BUF(buf, *len), rd, rs, cond, + curr_off, targ_off); + } else { + *len += gen_jmp_64(BUF(buf, *len), rd, rs, cond, + curr_off, targ_off); + } + + return ret; +} + +/* Jump to translated epilogue address. */ +static int handle_jmp_epilogue(struct jit_context *ctx, + const struct bpf_insn *insn, u8 *len) +{ + u8 *buf = effective_jit_buf(ctx); + u32 curr_off = 0, epi_off = 0; + + /* Check the offset only if the data is available. */ + if (offsets_available(ctx)) { + curr_off = get_curr_jit_off(ctx, insn); + epi_off = ctx->epilogue_offset; + + if (!check_jmp_64(curr_off, epi_off, ARC_CC_AL)) { + pr_err("bpf-jit: epilogue offset is not valid.\n"); + return -EINVAL; + } + } + + /* Jump to "epilogue offset" (rd and rs don't matter). */ + *len = gen_jmp_64(buf, 0, 0, ARC_CC_AL, curr_off, epi_off); + + return 0; +} + +/* Try to get the resolved address and generate the instructions. */ +static int handle_call(struct jit_context *ctx, + const struct bpf_insn *insn, + u8 *len) +{ + int ret; + bool in_kernel_func, fixed = false; + u64 addr = 0; + u8 *buf = effective_jit_buf(ctx); + + ret = bpf_jit_get_func_addr(ctx->prog, insn, ctx->is_extra_pass, + &addr, &fixed); + if (ret < 0) { + pr_err("bpf-jit: can't get the address for call.\n"); + return ret; + } + in_kernel_func = (fixed ? true : false); + + /* No valuable address retrieved (yet). */ + if (!fixed && !addr) + set_need_for_extra_pass(ctx); + + *len = gen_func_call(buf, (ARC_ADDR)addr, in_kernel_func); + + if (insn->src_reg != BPF_PSEUDO_CALL) { + /* Assigning ABI's return reg to JIT's return reg. */ + *len += arc_to_bpf_return(BUF(buf, *len)); + } + + return 0; +} + +/* + * Try to generate instructions for loading a 64-bit immediate. + * These sort of instructions are usually associated with the 64-bit + * relocations: R_BPF_64_64. Therefore, signal the need for an extra + * pass if the circumstances are right. + */ +static int handle_ld_imm64(struct jit_context *ctx, + const struct bpf_insn *insn, + u8 *len) +{ + const s32 idx = get_index_for_insn(ctx, insn); + u8 *buf = effective_jit_buf(ctx); + + /* We're about to consume 2 VM instructions. */ + if (is_last_insn(ctx->prog, idx)) { + pr_err("bpf-jit: need more data for 64-bit immediate.\n"); + return -EINVAL; + } + + *len = mov_r64_i64(buf, insn->dst_reg, insn->imm, (insn + 1)->imm); + + if (bpf_pseudo_func(insn)) + set_need_for_extra_pass(ctx); + + return 0; +} + +/* + * Handles one eBPF instruction at a time. To make this function faster, + * it does not call "jit_buffer_check()". Else, it would call it for every + * instruction. As a result, it should not be invoked directly. Only + * "handle_body()", that has already executed the "check", may call this + * function. + * + * If the "ret" value is negative, something has went wrong. Else, + * it mostly holds the value 0 and rarely 1. Number 1 signals + * the loop in "handle_body()" to skip the next instruction, because + * it has been consumed as part of a 64-bit immediate value. + */ +static int handle_insn(struct jit_context *ctx, u32 idx) +{ + const struct bpf_insn *insn = &ctx->prog->insnsi[idx]; + const u8 code = insn->code; + const u8 dst = insn->dst_reg; + const u8 src = insn->src_reg; + const s16 off = insn->off; + const s32 imm = insn->imm; + u8 *buf = effective_jit_buf(ctx); + u8 len = 0; + int ret = 0; + + switch (code) { + /* dst += src (32-bit) */ + case BPF_ALU | BPF_ADD | BPF_X: + len = add_r32(buf, dst, src); + break; + /* dst += imm (32-bit) */ + case BPF_ALU | BPF_ADD | BPF_K: + len = add_r32_i32(buf, dst, imm); + break; + /* dst -= src (32-bit) */ + case BPF_ALU | BPF_SUB | BPF_X: + len = sub_r32(buf, dst, src); + break; + /* dst -= imm (32-bit) */ + case BPF_ALU | BPF_SUB | BPF_K: + len = sub_r32_i32(buf, dst, imm); + break; + /* dst = -dst (32-bit) */ + case BPF_ALU | BPF_NEG: + len = neg_r32(buf, dst); + break; + /* dst *= src (32-bit) */ + case BPF_ALU | BPF_MUL | BPF_X: + len = mul_r32(buf, dst, src); + break; + /* dst *= imm (32-bit) */ + case BPF_ALU | BPF_MUL | BPF_K: + len = mul_r32_i32(buf, dst, imm); + break; + /* dst /= src (32-bit) */ + case BPF_ALU | BPF_DIV | BPF_X: + len = div_r32(buf, dst, src, off == 1); + break; + /* dst /= imm (32-bit) */ + case BPF_ALU | BPF_DIV | BPF_K: + len = div_r32_i32(buf, dst, imm, off == 1); + break; + /* dst %= src (32-bit) */ + case BPF_ALU | BPF_MOD | BPF_X: + len = mod_r32(buf, dst, src, off == 1); + break; + /* dst %= imm (32-bit) */ + case BPF_ALU | BPF_MOD | BPF_K: + len = mod_r32_i32(buf, dst, imm, off == 1); + break; + /* dst &= src (32-bit) */ + case BPF_ALU | BPF_AND | BPF_X: + len = and_r32(buf, dst, src); + break; + /* dst &= imm (32-bit) */ + case BPF_ALU | BPF_AND | BPF_K: + len = and_r32_i32(buf, dst, imm); + break; + /* dst |= src (32-bit) */ + case BPF_ALU | BPF_OR | BPF_X: + len = or_r32(buf, dst, src); + break; + /* dst |= imm (32-bit) */ + case BPF_ALU | BPF_OR | BPF_K: + len = or_r32_i32(buf, dst, imm); + break; + /* dst ^= src (32-bit) */ + case BPF_ALU | BPF_XOR | BPF_X: + len = xor_r32(buf, dst, src); + break; + /* dst ^= imm (32-bit) */ + case BPF_ALU | BPF_XOR | BPF_K: + len = xor_r32_i32(buf, dst, imm); + break; + /* dst <<= src (32-bit) */ + case BPF_ALU | BPF_LSH | BPF_X: + len = lsh_r32(buf, dst, src); + break; + /* dst <<= imm (32-bit) */ + case BPF_ALU | BPF_LSH | BPF_K: + len = lsh_r32_i32(buf, dst, imm); + break; + /* dst >>= src (32-bit) [unsigned] */ + case BPF_ALU | BPF_RSH | BPF_X: + len = rsh_r32(buf, dst, src); + break; + /* dst >>= imm (32-bit) [unsigned] */ + case BPF_ALU | BPF_RSH | BPF_K: + len = rsh_r32_i32(buf, dst, imm); + break; + /* dst >>= src (32-bit) [signed] */ + case BPF_ALU | BPF_ARSH | BPF_X: + len = arsh_r32(buf, dst, src); + break; + /* dst >>= imm (32-bit) [signed] */ + case BPF_ALU | BPF_ARSH | BPF_K: + len = arsh_r32_i32(buf, dst, imm); + break; + /* dst = src (32-bit) */ + case BPF_ALU | BPF_MOV | BPF_X: + len = mov_r32(buf, dst, src, (u8)off); + break; + /* dst = imm32 (32-bit) */ + case BPF_ALU | BPF_MOV | BPF_K: + len = mov_r32_i32(buf, dst, imm); + break; + /* dst = swap(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_LE: + case BPF_ALU | BPF_END | BPF_FROM_BE: + case BPF_ALU64 | BPF_END | BPF_FROM_LE: { + CHECK_RET(handle_swap(buf, dst, imm, BPF_SRC(code), + BPF_CLASS(code) == BPF_ALU64, + ctx->do_zext, &len)); + break; + } + /* dst += src (64-bit) */ + case BPF_ALU64 | BPF_ADD | BPF_X: + len = add_r64(buf, dst, src); + break; + /* dst += imm32 (64-bit) */ + case BPF_ALU64 | BPF_ADD | BPF_K: + len = add_r64_i32(buf, dst, imm); + break; + /* dst -= src (64-bit) */ + case BPF_ALU64 | BPF_SUB | BPF_X: + len = sub_r64(buf, dst, src); + break; + /* dst -= imm32 (64-bit) */ + case BPF_ALU64 | BPF_SUB | BPF_K: + len = sub_r64_i32(buf, dst, imm); + break; + /* dst = -dst (64-bit) */ + case BPF_ALU64 | BPF_NEG: + len = neg_r64(buf, dst); + break; + /* dst *= src (64-bit) */ + case BPF_ALU64 | BPF_MUL | BPF_X: + len = mul_r64(buf, dst, src); + break; + /* dst *= imm32 (64-bit) */ + case BPF_ALU64 | BPF_MUL | BPF_K: + len = mul_r64_i32(buf, dst, imm); + break; + /* dst &= src (64-bit) */ + case BPF_ALU64 | BPF_AND | BPF_X: + len = and_r64(buf, dst, src); + break; + /* dst &= imm32 (64-bit) */ + case BPF_ALU64 | BPF_AND | BPF_K: + len = and_r64_i32(buf, dst, imm); + break; + /* dst |= src (64-bit) */ + case BPF_ALU64 | BPF_OR | BPF_X: + len = or_r64(buf, dst, src); + break; + /* dst |= imm32 (64-bit) */ + case BPF_ALU64 | BPF_OR | BPF_K: + len = or_r64_i32(buf, dst, imm); + break; + /* dst ^= src (64-bit) */ + case BPF_ALU64 | BPF_XOR | BPF_X: + len = xor_r64(buf, dst, src); + break; + /* dst ^= imm32 (64-bit) */ + case BPF_ALU64 | BPF_XOR | BPF_K: + len = xor_r64_i32(buf, dst, imm); + break; + /* dst <<= src (64-bit) */ + case BPF_ALU64 | BPF_LSH | BPF_X: + len = lsh_r64(buf, dst, src); + break; + /* dst <<= imm32 (64-bit) */ + case BPF_ALU64 | BPF_LSH | BPF_K: + len = lsh_r64_i32(buf, dst, imm); + break; + /* dst >>= src (64-bit) [unsigned] */ + case BPF_ALU64 | BPF_RSH | BPF_X: + len = rsh_r64(buf, dst, src); + break; + /* dst >>= imm32 (64-bit) [unsigned] */ + case BPF_ALU64 | BPF_RSH | BPF_K: + len = rsh_r64_i32(buf, dst, imm); + break; + /* dst >>= src (64-bit) [signed] */ + case BPF_ALU64 | BPF_ARSH | BPF_X: + len = arsh_r64(buf, dst, src); + break; + /* dst >>= imm32 (64-bit) [signed] */ + case BPF_ALU64 | BPF_ARSH | BPF_K: + len = arsh_r64_i32(buf, dst, imm); + break; + /* dst = src (64-bit) */ + case BPF_ALU64 | BPF_MOV | BPF_X: + len = mov_r64(buf, dst, src, (u8)off); + break; + /* dst = imm32 (sign extend to 64-bit) */ + case BPF_ALU64 | BPF_MOV | BPF_K: + len = mov_r64_i32(buf, dst, imm); + break; + /* dst = imm64 */ + case BPF_LD | BPF_DW | BPF_IMM: + CHECK_RET(handle_ld_imm64(ctx, insn, &len)); + /* Tell the loop to skip the next instruction. */ + ret = 1; + break; + /* dst = *(size *)(src + off) */ + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_DW: + len = load_r(buf, dst, src, off, BPF_SIZE(code), false); + break; + case BPF_LDX | BPF_MEMSX | BPF_W: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_B: + len = load_r(buf, dst, src, off, BPF_SIZE(code), true); + break; + /* *(size *)(dst + off) = src */ + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_DW: + len = store_r(buf, src, dst, off, BPF_SIZE(code)); + break; + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_DW: + len = store_i(buf, imm, dst, off, BPF_SIZE(code)); + break; + case BPF_JMP | BPF_JA: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JA: + case BPF_JMP32 | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_X: + case BPF_JMP32 | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_K: + CHECK_RET(handle_jumps(ctx, insn, &len)); + break; + case BPF_JMP | BPF_CALL: + CHECK_RET(handle_call(ctx, insn, &len)); + break; + + case BPF_JMP | BPF_EXIT: + /* If this is the last instruction, epilogue will follow. */ + if (is_last_insn(ctx->prog, idx)) + break; + CHECK_RET(handle_jmp_epilogue(ctx, insn, &len)); + break; + default: + pr_err("bpf-jit: can't handle instruction code 0x%02X\n", code); + return -EOPNOTSUPP; + } + + if (BPF_CLASS(code) == BPF_ALU) { + /* + * Skip the "swap" instructions. Even 64-bit swaps are of type + * BPF_ALU (and not BPF_ALU64). Therefore, for the swaps, one + * has to look at the "size" of the operations rather than the + * ALU type. "gen_swap()" specifically takes care of that. + */ + if (BPF_OP(code) != BPF_END && ctx->do_zext) + len += zext(BUF(buf, len), dst); + } + + jit_buffer_update(ctx, len); + + return ret; +} + +static int handle_body(struct jit_context *ctx) +{ + int ret; + bool populate_bpf2insn = false; + const struct bpf_prog *prog = ctx->prog; + + CHECK_RET(jit_buffer_check(ctx)); + + /* + * Record the mapping for the instructions during the dry-run. + * Doing it this way allows us to have the mapping ready for + * the jump instructions during the real compilation phase. + */ + if (!ctx->emit) + populate_bpf2insn = true; + + for (u32 i = 0; i < prog->len; i++) { + /* During the dry-run, jit.len grows gradually per BPF insn. */ + if (populate_bpf2insn) + ctx->bpf2insn[i] = ctx->jit.len; + + CHECK_RET(handle_insn(ctx, i)); + if (ret > 0) { + /* "ret" is 1 if two (64-bit) chunks were consumed. */ + ctx->bpf2insn[i + 1] = ctx->bpf2insn[i]; + i++; + } + } + + /* If bpf2insn had to be populated, then it is done at this point. */ + if (populate_bpf2insn) + ctx->bpf2insn_valid = true; + + return 0; +} + +/* + * Initialize the memory with "unimp_s" which is the mnemonic for + * "unimplemented" instruction and always raises an exception. + * + * The instruction is 2 bytes. If "size" is odd, there is not much + * that can be done about the last byte in "area". Because, the + * CPU always fetches instructions in two bytes. Therefore, the + * byte beyond the last one is going to accompany it during a + * possible fetch. In the most likely case of a little endian + * system, that beyond-byte will become the major opcode and + * we have no control over its initialisation. + */ +static void fill_ill_insn(void *area, unsigned int size) +{ + const u16 unimp_s = 0x79e0; + + if (size & 1) { + *((u8 *)area + (size - 1)) = 0xff; + size -= 1; + } + + memset16(area, unimp_s, size >> 1); +} + +/* Piece of memory that can be allocated at the beginning of jit_prepare(). */ +static int jit_prepare_early_mem_alloc(struct jit_context *ctx) +{ + ctx->bpf2insn = kcalloc(ctx->prog->len, sizeof(ctx->jit.len), + GFP_KERNEL); + + if (!ctx->bpf2insn) { + pr_err("bpf-jit: could not allocate memory for " + "mapping of the instructions.\n"); + return -ENOMEM; + } + + return 0; +} + +/* + * Memory allocations that rely on parameters known at the end of + * jit_prepare(). + */ +static int jit_prepare_final_mem_alloc(struct jit_context *ctx) +{ + const size_t alignment = sizeof(u32); + + ctx->bpf_header = bpf_jit_binary_alloc(ctx->jit.len, &ctx->jit.buf, + alignment, fill_ill_insn); + if (!ctx->bpf_header) { + pr_err("bpf-jit: could not allocate memory for translation.\n"); + return -ENOMEM; + } + + if (ctx->need_extra_pass) { + ctx->jit_data = kzalloc(sizeof(*ctx->jit_data), GFP_KERNEL); + if (!ctx->jit_data) + return -ENOMEM; + } + + return 0; +} + +/* + * The first phase of the translation without actually emitting any + * instruction. It helps in getting a forecast on some aspects, such + * as the length of the whole program or where the epilogue starts. + * + * Whenever the necessary parameters are known, memories are allocated. + */ +static int jit_prepare(struct jit_context *ctx) +{ + int ret; + + /* Dry run. */ + ctx->emit = false; + + CHECK_RET(jit_prepare_early_mem_alloc(ctx)); + + /* Get the length of prologue section after some register analysis. */ + analyze_reg_usage(ctx); + CHECK_RET(handle_prologue(ctx)); + + CHECK_RET(handle_body(ctx)); + + /* Record at which offset epilogue begins. */ + ctx->epilogue_offset = ctx->jit.len; + + /* Process the epilogue section now. */ + CHECK_RET(handle_epilogue(ctx)); + + CHECK_RET(jit_prepare_final_mem_alloc(ctx)); + + return 0; +} + +/* + * All the "handle_*()" functions have been called before by the + * "jit_prepare()". If there was an error, we would know by now. + * Therefore, no extra error checking at this point, other than + * a sanity check at the end that expects the calculated length + * (jit.len) to be equal to the length of generated instructions + * (jit.index). + */ +static int jit_compile(struct jit_context *ctx) +{ + int ret; + + /* Let there be code. */ + ctx->emit = true; + + CHECK_RET(handle_prologue(ctx)); + + CHECK_RET(handle_body(ctx)); + + CHECK_RET(handle_epilogue(ctx)); + + if (ctx->jit.index != ctx->jit.len) { + pr_err("bpf-jit: divergence between the phases; " + "%u vs. %u (bytes).\n", + ctx->jit.len, ctx->jit.index); + return -EFAULT; + } + + return 0; +} + +/* + * Calling this function implies a successful JIT. A successful + * translation is signaled by setting the right parameters: + * + * prog->jited=1, prog->jited_len=..., prog->bpf_func=... + */ +static int jit_finalize(struct jit_context *ctx) +{ + struct bpf_prog *prog = ctx->prog; + + /* We're going to need this information for the "do_extra_pass()". */ + if (ctx->need_extra_pass) { + ctx->jit_data->bpf_header = ctx->bpf_header; + ctx->jit_data->bpf2insn = ctx->bpf2insn; + prog->aux->jit_data = (void *)ctx->jit_data; + } else { + /* + * If things seem finalised, then mark the JITed memory + * as R-X and flush it. + */ + if (bpf_jit_binary_lock_ro(ctx->bpf_header)) { + pr_err("bpf-jit: Could not lock the JIT memory.\n"); + return -EFAULT; + } + flush_icache_range((unsigned long)ctx->bpf_header, + (unsigned long) + BUF(ctx->jit.buf, ctx->jit.len)); + prog->aux->jit_data = NULL; + bpf_prog_fill_jited_linfo(prog, ctx->bpf2insn); + } + + ctx->success = true; + prog->bpf_func = (void *)ctx->jit.buf; + prog->jited_len = ctx->jit.len; + prog->jited = 1; + + jit_ctx_cleanup(ctx); + jit_dump(ctx); + + return 0; +} + +/* + * A lenient verification for the existence of JIT context in "prog". + * Apparently the JIT internals, namely jit_subprogs() in bpf/verifier.c, + * may request for a second compilation although nothing needs to be done. + */ +static inline int check_jit_context(const struct bpf_prog *prog) +{ + if (!prog->aux->jit_data) { + pr_notice("bpf-jit: no jit data for the extra pass.\n"); + return 1; + } else { + return 0; + } +} + +/* Reuse the previous pass's data. */ +static int jit_resume_context(struct jit_context *ctx) +{ + struct arc_jit_data *jdata = + (struct arc_jit_data *)ctx->prog->aux->jit_data; + + if (!jdata) { + pr_err("bpf-jit: no jit data for the extra pass.\n"); + return -EINVAL; + } + + ctx->jit.buf = (u8 *)ctx->prog->bpf_func; + ctx->jit.len = ctx->prog->jited_len; + ctx->bpf_header = jdata->bpf_header; + ctx->bpf2insn = (u32 *)jdata->bpf2insn; + ctx->bpf2insn_valid = ctx->bpf2insn ? true : false; + ctx->jit_data = jdata; + + return 0; +} + +/* + * Patch in the new addresses. The instructions of interest are: + * + * - call + * - ld r64, imm64 + * + * For "call"s, it resolves the addresses one more time through the + * handle_call(). + * + * For 64-bit immediate loads, it just retranslates them, because the BPF + * core in kernel might have changed the value since the normal pass. + */ +static int jit_patch_relocations(struct jit_context *ctx) +{ + const u8 bpf_opc_call = BPF_JMP | BPF_CALL; + const u8 bpf_opc_ldi64 = BPF_LD | BPF_DW | BPF_IMM; + const struct bpf_prog *prog = ctx->prog; + int ret; + + ctx->emit = true; + for (u32 i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &prog->insnsi[i]; + u8 dummy; + /* + * Adjust "ctx.jit.index", so "gen_*()" functions below + * can use it for their output addresses. + */ + ctx->jit.index = ctx->bpf2insn[i]; + + if (insn->code == bpf_opc_call) { + CHECK_RET(handle_call(ctx, insn, &dummy)); + } else if (insn->code == bpf_opc_ldi64) { + CHECK_RET(handle_ld_imm64(ctx, insn, &dummy)); + /* Skip the next instruction. */ + ++i; + } + } + return 0; +} + +/* + * A normal pass that involves a "dry-run" phase, jit_prepare(), + * to get the necessary data for the real compilation phase, + * jit_compile(). + */ +static struct bpf_prog *do_normal_pass(struct bpf_prog *prog) +{ + struct jit_context ctx; + + /* Bail out if JIT is disabled. */ + if (!prog->jit_requested) + return prog; + + if (jit_ctx_init(&ctx, prog)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + /* Get the lengths and allocate buffer. */ + if (jit_prepare(&ctx)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + if (jit_compile(&ctx)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + if (jit_finalize(&ctx)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + return ctx.prog; +} + +/* + * If there are multi-function BPF programs that call each other, + * their translated addresses are not known all at once. Therefore, + * an extra pass is needed to consult the bpf_jit_get_func_addr() + * again to get the newly translated addresses in order to resolve + * the "call"s. + */ +static struct bpf_prog *do_extra_pass(struct bpf_prog *prog) +{ + struct jit_context ctx; + + /* Skip if there's no context to resume from. */ + if (check_jit_context(prog)) + return prog; + + if (jit_ctx_init(&ctx, prog)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + if (jit_resume_context(&ctx)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + if (jit_patch_relocations(&ctx)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + if (jit_finalize(&ctx)) { + jit_ctx_cleanup(&ctx); + return prog; + } + + return ctx.prog; +} + +/* + * This function may be invoked twice for the same stream of BPF + * instructions. The "extra pass" happens, when there are "call"s + * involved that their addresses are not known during the first + * invocation. + */ +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) +{ + vm_dump(prog); + + /* Was this program already translated? */ + if (!prog->jited) + return do_normal_pass(prog); + else + return do_extra_pass(prog); + + return prog; +} diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index db1aeacd4cd9..8c0a36f72d6f 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -135,6 +135,12 @@ enum aarch64_insn_special_register { AARCH64_INSN_SPCLREG_SP_EL2 = 0xF210 }; +enum aarch64_insn_system_register { + AARCH64_INSN_SYSREG_TPIDR_EL1 = 0x4684, + AARCH64_INSN_SYSREG_TPIDR_EL2 = 0x6682, + AARCH64_INSN_SYSREG_SP_EL0 = 0x4208, +}; + enum aarch64_insn_variant { AARCH64_INSN_VARIANT_32BIT, AARCH64_INSN_VARIANT_64BIT @@ -686,6 +692,8 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, } #endif u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type); +u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, + enum aarch64_insn_system_register sysreg); s32 aarch64_get_branch_offset(u32 insn); u32 aarch64_set_branch_offset(u32 insn, s32 offset); diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index a635ab83fee3..b008a9b46a7f 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -1515,3 +1515,14 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) return insn; } + +u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, + enum aarch64_insn_system_register sysreg) +{ + u32 insn = aarch64_insn_get_mrs_value(); + + insn &= ~GENMASK(19, 0); + insn |= sysreg << 5; + return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, + insn, result); +} diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 23b1b34db088..b22ab2f97a30 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -297,4 +297,12 @@ #define A64_ADR(Rd, offset) \ aarch64_insn_gen_adr(0, offset, Rd, AARCH64_INSN_ADR_TYPE_ADR) +/* MRS */ +#define A64_MRS_TPIDR_EL1(Rt) \ + aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_TPIDR_EL1) +#define A64_MRS_TPIDR_EL2(Rt) \ + aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_TPIDR_EL2) +#define A64_MRS_SP_EL0(Rt) \ + aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_SP_EL0) + #endif /* _BPF_JIT_H */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index cf9a9ebb4cda..1d88711467bb 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -494,20 +494,26 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) { const u8 code = insn->code; + const u8 arena_vm_base = bpf2a64[ARENA_VM_START]; const u8 dst = bpf2a64[insn->dst_reg]; const u8 src = bpf2a64[insn->src_reg]; const u8 tmp = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; const bool isdw = BPF_SIZE(code) == BPF_DW; + const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC; const s16 off = insn->off; - u8 reg; + u8 reg = dst; - if (!off) { - reg = dst; - } else { - emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_ADD(1, tmp, tmp, dst), ctx); - reg = tmp; + if (off || arena) { + if (off) { + emit_a64_mov_i(1, tmp, off, ctx); + emit(A64_ADD(1, tmp, tmp, dst), ctx); + reg = tmp; + } + if (arena) { + emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx); + reg = tmp; + } } switch (insn->imm) { @@ -576,6 +582,12 @@ static int emit_ll_sc_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx) u8 reg; s32 jmp_offset; + if (BPF_MODE(code) == BPF_PROBE_ATOMIC) { + /* ll_sc based atomics don't support unsafe pointers yet. */ + pr_err_once("unknown atomic opcode %02x\n", code); + return -EINVAL; + } + if (!off) { reg = dst; } else { @@ -777,7 +789,8 @@ static int add_exception_handler(const struct bpf_insn *insn, if (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX && - BPF_MODE(insn->code) != BPF_PROBE_MEM32) + BPF_MODE(insn->code) != BPF_PROBE_MEM32 && + BPF_MODE(insn->code) != BPF_PROBE_ATOMIC) return 0; if (!ctx->prog->aux->extable || @@ -877,6 +890,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit(A64_ORR(1, tmp, dst, tmp), ctx); emit(A64_MOV(1, dst, tmp), ctx); break; + } else if (insn_is_mov_percpu_addr(insn)) { + if (dst != src) + emit(A64_MOV(1, dst, src), ctx); + if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN)) + emit(A64_MRS_TPIDR_EL2(tmp), ctx); + else + emit(A64_MRS_TPIDR_EL1(tmp), ctx); + emit(A64_ADD(1, dst, dst, tmp), ctx); + break; } switch (insn->off) { case 0: @@ -1206,6 +1228,21 @@ emit_cond_jmp: const u8 r0 = bpf2a64[BPF_REG_0]; bool func_addr_fixed; u64 func_addr; + u32 cpu_offset; + + /* Implement helper call to bpf_get_smp_processor_id() inline */ + if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) { + cpu_offset = offsetof(struct thread_info, cpu); + + emit(A64_MRS_SP_EL0(tmp), ctx); + if (is_lsi_offset(cpu_offset, 2)) { + emit(A64_LDR32I(r0, tmp, cpu_offset), ctx); + } else { + emit_a64_mov_i(1, tmp2, cpu_offset, ctx); + emit(A64_LDR32(r0, tmp, tmp2), ctx); + } + break; + } ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &func_addr, &func_addr_fixed); @@ -1474,12 +1511,18 @@ emit_cond_jmp: case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_W: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW: if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) ret = emit_lse_atomic(insn, ctx); else ret = emit_ll_sc_atomic(insn, ctx); if (ret) return ret; + + ret = add_exception_handler(insn, ctx, dst); + if (ret) + return ret; break; default: @@ -2527,6 +2570,34 @@ bool bpf_jit_supports_arena(void) return true; } +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) +{ + if (!in_arena) + return true; + switch (insn->code) { + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) + return false; + } + return true; +} + +bool bpf_jit_supports_percpu_insn(void) +{ + return true; +} + +bool bpf_jit_inlines_helper_call(s32 imm) +{ + switch (imm) { + case BPF_FUNC_get_smp_processor_id: + return true; + default: + return false; + } +} + void bpf_jit_free(struct bpf_prog *prog) { if (prog->jited) { diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index 5fc374ed98ea..fdbf88ca8b70 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -608,7 +608,7 @@ static inline u32 rv_nop(void) return rv_i_insn(0, 0, 0, 0, 0x13); } -/* RVC instrutions. */ +/* RVC instructions. */ static inline u16 rvc_addi4spn(u8 rd, u32 imm10) { @@ -737,7 +737,7 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2) return rv_css_insn(0x6, imm, rs2, 0x2); } -/* RVZBB instrutions. */ +/* RVZBB instructions. */ static inline u32 rvzbb_sextb(u8 rd, u8 rs1) { return rv_i_insn(0x604, rs1, 1, rd, 0x13); diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index e713704be837..79a001d5533e 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "bpf_jit.h" #define RV_FENTRY_NINSNS 2 @@ -503,33 +504,33 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, break; /* src_reg = atomic_fetch_(dst_reg + off16, src_reg) */ case BPF_ADD | BPF_FETCH: - emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) : - rv_amoadd_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) : + rv_amoadd_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zextw(rs, rs, ctx); break; case BPF_AND | BPF_FETCH: - emit(is64 ? rv_amoand_d(rs, rs, rd, 0, 0) : - rv_amoand_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) : + rv_amoand_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zextw(rs, rs, ctx); break; case BPF_OR | BPF_FETCH: - emit(is64 ? rv_amoor_d(rs, rs, rd, 0, 0) : - rv_amoor_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) : + rv_amoor_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zextw(rs, rs, ctx); break; case BPF_XOR | BPF_FETCH: - emit(is64 ? rv_amoxor_d(rs, rs, rd, 0, 0) : - rv_amoxor_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) : + rv_amoxor_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zextw(rs, rs, ctx); break; /* src_reg = atomic_xchg(dst_reg + off16, src_reg); */ case BPF_XCHG: - emit(is64 ? rv_amoswap_d(rs, rs, rd, 0, 0) : - rv_amoswap_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) : + rv_amoswap_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zextw(rs, rs, ctx); break; @@ -1089,6 +1090,24 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_or(RV_REG_T1, rd, RV_REG_T1, ctx); emit_mv(rd, RV_REG_T1, ctx); break; + } else if (insn_is_mov_percpu_addr(insn)) { + if (rd != rs) + emit_mv(rd, rs, ctx); +#ifdef CONFIG_SMP + /* Load current CPU number in T1 */ + emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu), + RV_REG_TP, ctx); + /* << 3 because offsets are 8 bytes */ + emit_slli(RV_REG_T1, RV_REG_T1, 3, ctx); + /* Load address of __per_cpu_offset array in T2 */ + emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx); + /* Add offset of current CPU to __per_cpu_offset */ + emit_add(RV_REG_T1, RV_REG_T2, RV_REG_T1, ctx); + /* Load __per_cpu_offset[cpu] in T1 */ + emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx); + /* Add the offset to Rd */ + emit_add(rd, rd, RV_REG_T1, ctx); +#endif } if (imm == 1) { /* Special mov32 for zext */ @@ -1474,6 +1493,22 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, bool fixed_addr; u64 addr; + /* Inline calls to bpf_get_smp_processor_id() + * + * RV_REG_TP holds the address of the current CPU's task_struct and thread_info is + * at offset 0 in task_struct. + * Load cpu from thread_info: + * Set R0 to ((struct thread_info *)(RV_REG_TP))->cpu + * + * This replicates the implementation of raw_smp_processor_id() on RISCV + */ + if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) { + /* Load current CPU number in R0 */ + emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu), + RV_REG_TP, ctx); + break; + } + mark_call(ctx); ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, &fixed_addr); @@ -2038,3 +2073,18 @@ bool bpf_jit_supports_arena(void) { return true; } + +bool bpf_jit_supports_percpu_insn(void) +{ + return true; +} + +bool bpf_jit_inlines_helper_call(s32 imm) +{ + switch (imm) { + case BPF_FUNC_get_smp_processor_id: + return true; + default: + return false; + } +} diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index fa2f824e3b06..4be8f5cadd02 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1427,8 +1427,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, is32 ? (op32) : (op64), \ (insn->imm & BPF_FETCH) ? src_reg : REG_W0, \ src_reg, dst_reg, off); \ - if (is32 && (insn->imm & BPF_FETCH)) \ - EMIT_ZERO(src_reg); \ + if (insn->imm & BPF_FETCH) { \ + /* bcr 14,0 - see atomic_fetch_{add,and,or,xor}() */ \ + _EMIT2(0x07e0); \ + if (is32) \ + EMIT_ZERO(src_reg); \ + } \ } while (0) case BPF_ADD: case BPF_ADD | BPF_FETCH: diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index e24aabfe8ecc..c0e3e1426a82 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; diff --git a/include/linux/filter.h b/include/linux/filter.h index d5fea03cb6e6..0f12cf01070e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -993,6 +993,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); diff --git a/include/net/tcp.h b/include/net/tcp.h index 8f63a163c7de..060e95b331a2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1164,7 +1164,7 @@ struct tcp_congestion_ops { /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ - void (*cong_control)(struct sock *sk, const struct rate_sample *rs); + void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); /* new value of cwnd after loss (required) */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d94a72593ead..90706a47f6ff 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1115,6 +1115,7 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_GETSOCKNAME, BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 85786fd97d2a..7eb9ad3a3ae6 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -44,7 +44,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o obj-$(CONFIG_BPF_SYSCALL) += cpumask.o obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif -ifeq ($(CONFIG_CRYPTO),y) +ifneq ($(CONFIG_CRYPTO),) obj-$(CONFIG_BPF_SYSCALL) += crypto.o endif obj-$(CONFIG_BPF_PRELOAD) += preload/ diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 6c81630c5293..f5953f1a95cd 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -251,7 +251,7 @@ static vm_fault_t arena_vm_fault(struct vm_fault *vmf) int ret; kbase = bpf_arena_get_kern_vm_start(arena); - kaddr = kbase + (u32)(vmf->address & PAGE_MASK); + kaddr = kbase + (u32)(vmf->address); guard(mutex)(&arena->lock); page = vmalloc_to_page((void *)kaddr); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 580d07b15471..feabc0193852 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -436,13 +436,14 @@ static void array_map_free_timers_wq(struct bpf_map *map) /* We don't reset or free fields other than timer and workqueue * on uref dropping to zero. */ - if (btf_record_has_field(map->record, BPF_TIMER)) - for (i = 0; i < array->map.max_entries; i++) - bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); - - if (btf_record_has_field(map->record, BPF_WORKQUEUE)) - for (i = 0; i < array->map.max_entries; i++) - bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i)); + if (btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE)) { + for (i = 0; i < array->map.max_entries; i++) { + if (btf_record_has_field(map->record, BPF_TIMER)) + bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); + if (btf_record_has_field(map->record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(map->record, array_map_elem_ptr(array, i)); + } + } } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 8291fbfd27b1..821063660d9f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -218,6 +218,7 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_SOCKET_FILTER, BTF_KFUNC_HOOK_LWT, BTF_KFUNC_HOOK_NETFILTER, + BTF_KFUNC_HOOK_KPROBE, BTF_KFUNC_HOOK_MAX, }; @@ -8157,6 +8158,8 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) return BTF_KFUNC_HOOK_LWT; case BPF_PROG_TYPE_NETFILTER: return BTF_KFUNC_HOOK_NETFILTER; + case BPF_PROG_TYPE_KPROBE: + return BTF_KFUNC_HOOK_KPROBE; default: return BTF_KFUNC_HOOK_MAX; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 192f67dd1f25..733fca2634b7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -849,7 +850,7 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, return -EINVAL; } - tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL); + tab = krealloc_array(tab, size, sizeof(*poke), GFP_KERNEL); if (!tab) return -ENOMEM; @@ -2455,13 +2456,14 @@ EXPORT_SYMBOL(bpf_empty_prog_array); struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { - if (prog_cnt) - return kzalloc(sizeof(struct bpf_prog_array) + - sizeof(struct bpf_prog_array_item) * - (prog_cnt + 1), - flags); + struct bpf_prog_array *p; - return &bpf_empty_prog_array.hdr; + if (prog_cnt) + p = kzalloc(struct_size(p, items, prog_cnt + 1), flags); + else + p = &bpf_empty_prog_array.hdr; + + return p; } void bpf_prog_array_free(struct bpf_prog_array *progs) @@ -2939,6 +2941,17 @@ bool __weak bpf_jit_needs_zext(void) return false; } +/* Return true if the JIT inlines the call to the helper corresponding to + * the imm. + * + * The verifier will not patch the insn->imm for the call to the helper if + * this returns true. + */ +bool __weak bpf_jit_inlines_helper_call(s32 imm) +{ + return false; +} + /* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */ bool __weak bpf_jit_supports_subprog_tailcalls(void) { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 0179183c543a..06115f8728e8 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -221,13 +221,11 @@ static bool htab_has_extra_elems(struct bpf_htab *htab) return !htab_is_percpu(htab) && !htab_is_lru(htab); } -static void htab_free_prealloced_timers(struct bpf_htab *htab) +static void htab_free_prealloced_timers_and_wq(struct bpf_htab *htab) { u32 num_entries = htab->map.max_entries; int i; - if (!btf_record_has_field(htab->map.record, BPF_TIMER)) - return; if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); @@ -235,27 +233,12 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_obj_free_timer(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); - cond_resched(); - } -} - -static void htab_free_prealloced_wq(struct bpf_htab *htab) -{ - u32 num_entries = htab->map.max_entries; - int i; - - if (!btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) - return; - if (htab_has_extra_elems(htab)) - num_entries += num_possible_cpus(); - - for (i = 0; i < num_entries; i++) { - struct htab_elem *elem; - - elem = get_htab_elem(htab, i); - bpf_obj_free_workqueue(htab->map.record, - elem->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_TIMER)) + bpf_obj_free_timer(htab->map.record, + elem->key + round_up(htab->map.key_size, 8)); + if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) + bpf_obj_free_workqueue(htab->map.record, + elem->key + round_up(htab->map.key_size, 8)); cond_resched(); } } @@ -1515,7 +1498,7 @@ static void delete_all_elements(struct bpf_htab *htab) migrate_enable(); } -static void htab_free_malloced_timers_or_wq(struct bpf_htab *htab, bool is_timer) +static void htab_free_malloced_timers_and_wq(struct bpf_htab *htab) { int i; @@ -1527,10 +1510,10 @@ static void htab_free_malloced_timers_or_wq(struct bpf_htab *htab, bool is_timer hlist_nulls_for_each_entry(l, n, head, hash_node) { /* We only free timer on uref dropping to zero */ - if (is_timer) + if (btf_record_has_field(htab->map.record, BPF_TIMER)) bpf_obj_free_timer(htab->map.record, l->key + round_up(htab->map.key_size, 8)); - else + if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) bpf_obj_free_workqueue(htab->map.record, l->key + round_up(htab->map.key_size, 8)); } @@ -1544,17 +1527,11 @@ static void htab_map_free_timers_and_wq(struct bpf_map *map) struct bpf_htab *htab = container_of(map, struct bpf_htab, map); /* We only free timer and workqueue on uref dropping to zero */ - if (btf_record_has_field(htab->map.record, BPF_TIMER)) { + if (btf_record_has_field(htab->map.record, BPF_TIMER | BPF_WORKQUEUE)) { if (!htab_is_prealloc(htab)) - htab_free_malloced_timers_or_wq(htab, true); + htab_free_malloced_timers_and_wq(htab); else - htab_free_prealloced_timers(htab); - } - if (btf_record_has_field(htab->map.record, BPF_WORKQUEUE)) { - if (!htab_is_prealloc(htab)) - htab_free_malloced_timers_or_wq(htab, false); - else - htab_free_prealloced_wq(htab); + htab_free_prealloced_timers_and_wq(htab); } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f655adf42e39..13ad74ecf2cd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4016,11 +4016,15 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; + if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION && + attach_type != BPF_TRACE_KPROBE_SESSION) + return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; if (attach_type != BPF_PERF_EVENT && attach_type != BPF_TRACE_KPROBE_MULTI && + attach_type != BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; return 0; @@ -5281,7 +5285,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); - else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI) + else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || + attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION) ret = bpf_kprobe_multi_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI) ret = bpf_uprobe_multi_link_attach(attr, prog); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 719c633e500a..77da1f438bec 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2368,6 +2368,8 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env, regs[regno].type = PTR_TO_BTF_ID | flag; regs[regno].btf = btf; regs[regno].btf_id = btf_id; + if (type_may_be_null(flag)) + regs[regno].id = ++env->id_gen; } #define DEF_NOT_SUBREG (0) @@ -5400,8 +5402,6 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, */ mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field)); - /* For mark_ptr_or_null_reg */ - val_reg->id = ++env->id_gen; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && @@ -5719,7 +5719,8 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg) return true; /* Types listed in the reg2btf_ids are always trusted */ - if (reg2btf_ids[base_type(reg->type)]) + if (reg2btf_ids[base_type(reg->type)] && + !bpf_type_has_unsafe_modifiers(reg->type)) return true; /* If a register is not referenced, it is trusted if it has the @@ -6339,6 +6340,7 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, #define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu) #define BTF_TYPE_SAFE_RCU_OR_NULL(__type) __PASTE(__type, __safe_rcu_or_null) #define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted) +#define BTF_TYPE_SAFE_TRUSTED_OR_NULL(__type) __PASTE(__type, __safe_trusted_or_null) /* * Allow list few fields as RCU trusted or full trusted. @@ -6402,7 +6404,7 @@ BTF_TYPE_SAFE_TRUSTED(struct dentry) { struct inode *d_inode; }; -BTF_TYPE_SAFE_TRUSTED(struct socket) { +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) { struct sock *sk; }; @@ -6437,11 +6439,20 @@ static bool type_is_trusted(struct bpf_verifier_env *env, BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); - BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct socket)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); } +static bool type_is_trusted_or_null(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const char *field_name, u32 btf_id) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, + "__safe_trusted_or_null"); +} + static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, @@ -6550,6 +6561,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, */ if (type_is_trusted(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED; + } else if (type_is_trusted_or_null(env, reg, field_name, btf_id)) { + flag |= PTR_TRUSTED | PTR_MAYBE_NULL; } else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) { if (type_is_rcu(env, reg, field_name, btf_id)) { /* ignore __rcu tag and mark it MEM_RCU */ @@ -11050,6 +11063,7 @@ enum special_kfunc_type { KF_bpf_preempt_disable, KF_bpf_preempt_enable, KF_bpf_iter_css_task_new, + KF_bpf_session_cookie, }; BTF_SET_START(special_kfunc_set) @@ -11110,6 +11124,7 @@ BTF_ID(func, bpf_iter_css_task_new) #else BTF_ID_UNUSED #endif +BTF_ID(func, bpf_session_cookie) static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -12281,6 +12296,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } } + if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) { + meta.r0_size = sizeof(u64); + meta.r0_rdonly = false; + } + if (is_bpf_wq_set_callback_impl_kfunc(meta.func_id)) { err = push_callback_call(env, insn, insn_idx, meta.subprogno, set_timer_callback_state); @@ -13858,6 +13878,46 @@ static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, __update_reg_bounds(dst_reg); } +static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn, + const struct bpf_reg_state *src_reg) +{ + bool src_is_const = false; + u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; + + if (insn_bitness == 32) { + if (tnum_subreg_is_const(src_reg->var_off) + && src_reg->s32_min_value == src_reg->s32_max_value + && src_reg->u32_min_value == src_reg->u32_max_value) + src_is_const = true; + } else { + if (tnum_is_const(src_reg->var_off) + && src_reg->smin_value == src_reg->smax_value + && src_reg->umin_value == src_reg->umax_value) + src_is_const = true; + } + + switch (BPF_OP(insn->code)) { + case BPF_ADD: + case BPF_SUB: + case BPF_AND: + case BPF_XOR: + case BPF_OR: + case BPF_MUL: + return true; + + /* Shift operators range is only computable if shift dimension operand + * is a constant. Shifts greater than 31 or 63 are undefined. This + * includes shifts by a negative number. + */ + case BPF_LSH: + case BPF_RSH: + case BPF_ARSH: + return (src_is_const && src_reg->umax_value < insn_bitness); + default: + return false; + } +} + /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. @@ -13867,53 +13927,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *dst_reg, struct bpf_reg_state src_reg) { - struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); - bool src_known; - s64 smin_val, smax_val; - u64 umin_val, umax_val; - s32 s32_min_val, s32_max_val; - u32 u32_min_val, u32_max_val; - u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); int ret; - smin_val = src_reg.smin_value; - smax_val = src_reg.smax_value; - umin_val = src_reg.umin_value; - umax_val = src_reg.umax_value; - - s32_min_val = src_reg.s32_min_value; - s32_max_val = src_reg.s32_max_value; - u32_min_val = src_reg.u32_min_value; - u32_max_val = src_reg.u32_max_value; - - if (alu32) { - src_known = tnum_subreg_is_const(src_reg.var_off); - if ((src_known && - (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) || - s32_min_val > s32_max_val || u32_min_val > u32_max_val) { - /* Taint dst register if offset had invalid bounds - * derived from e.g. dead branches. - */ - __mark_reg_unknown(env, dst_reg); - return 0; - } - } else { - src_known = tnum_is_const(src_reg.var_off); - if ((src_known && - (smin_val != smax_val || umin_val != umax_val)) || - smin_val > smax_val || umin_val > umax_val) { - /* Taint dst register if offset had invalid bounds - * derived from e.g. dead branches. - */ - __mark_reg_unknown(env, dst_reg); - return 0; - } - } - - if (!src_known && - opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { + if (!is_safe_to_compute_dst_reg_range(insn, &src_reg)) { __mark_reg_unknown(env, dst_reg); return 0; } @@ -13970,46 +13988,24 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, scalar_min_max_xor(dst_reg, &src_reg); break; case BPF_LSH: - if (umax_val >= insn_bitness) { - /* Shifts greater than 31 or 63 are undefined. - * This includes shifts by a negative number. - */ - mark_reg_unknown(env, regs, insn->dst_reg); - break; - } if (alu32) scalar32_min_max_lsh(dst_reg, &src_reg); else scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: - if (umax_val >= insn_bitness) { - /* Shifts greater than 31 or 63 are undefined. - * This includes shifts by a negative number. - */ - mark_reg_unknown(env, regs, insn->dst_reg); - break; - } if (alu32) scalar32_min_max_rsh(dst_reg, &src_reg); else scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: - if (umax_val >= insn_bitness) { - /* Shifts greater than 31 or 63 are undefined. - * This includes shifts by a negative number. - */ - mark_reg_unknown(env, regs, insn->dst_reg); - break; - } if (alu32) scalar32_min_max_arsh(dst_reg, &src_reg); else scalar_min_max_arsh(dst_reg, &src_reg); break; default: - mark_reg_unknown(env, regs, insn->dst_reg); break; } @@ -20029,6 +20025,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto next_insn; } + /* Skip inlining the helper call if the JIT does it. */ + if (bpf_jit_inlines_helper_call(insn->imm)) + goto next_insn; + if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0ba722b57af3..f5154c051d2c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1631,6 +1631,17 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static bool is_kprobe_multi(const struct bpf_prog *prog) +{ + return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI || + prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; +} + +static inline bool is_kprobe_session(const struct bpf_prog *prog) +{ + return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; +} + static const struct bpf_func_proto * kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1646,13 +1657,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_override_return_proto; #endif case BPF_FUNC_get_func_ip: - if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI) + if (is_kprobe_multi(prog)) return &bpf_get_func_ip_proto_kprobe_multi; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI) return &bpf_get_func_ip_proto_uprobe_multi; return &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: - if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI) + if (is_kprobe_multi(prog)) return &bpf_get_attach_cookie_proto_kmulti; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI) return &bpf_get_attach_cookie_proto_umulti; @@ -2585,6 +2596,12 @@ static int __init bpf_event_init(void) fs_initcall(bpf_event_init); #endif /* CONFIG_MODULES */ +struct bpf_session_run_ctx { + struct bpf_run_ctx run_ctx; + bool is_return; + void *data; +}; + #ifdef CONFIG_FPROBE struct bpf_kprobe_multi_link { struct bpf_link link; @@ -2598,7 +2615,7 @@ struct bpf_kprobe_multi_link { }; struct bpf_kprobe_multi_run_ctx { - struct bpf_run_ctx run_ctx; + struct bpf_session_run_ctx session_ctx; struct bpf_kprobe_multi_link *link; unsigned long entry_ip; }; @@ -2777,7 +2794,8 @@ static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) if (WARN_ON_ONCE(!ctx)) return 0; - run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); + run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, + session_ctx.run_ctx); link = run_ctx->link; if (!link->cookies) return 0; @@ -2794,15 +2812,21 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { struct bpf_kprobe_multi_run_ctx *run_ctx; - run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); + run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, + session_ctx.run_ctx); return run_ctx->entry_ip; } static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, - unsigned long entry_ip, struct pt_regs *regs) + unsigned long entry_ip, struct pt_regs *regs, + bool is_return, void *data) { struct bpf_kprobe_multi_run_ctx run_ctx = { + .session_ctx = { + .is_return = is_return, + .data = data, + }, .link = link, .entry_ip = entry_ip, }; @@ -2817,7 +2841,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, migrate_disable(); rcu_read_lock(); - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); + old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); @@ -2834,10 +2858,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, void *data) { struct bpf_kprobe_multi_link *link; + int err; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); - return 0; + err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data); + return is_kprobe_session(link->link.prog) ? err : 0; } static void @@ -2848,7 +2873,7 @@ kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); - kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); + kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) @@ -2981,7 +3006,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (sizeof(u64) != sizeof(void *)) return -EOPNOTSUPP; - if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI) + if (!is_kprobe_multi(prog)) return -EINVAL; flags = attr->link_create.kprobe_multi.flags; @@ -3062,10 +3087,12 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (err) goto error; - if (flags & BPF_F_KPROBE_MULTI_RETURN) - link->fp.exit_handler = kprobe_multi_link_exit_handler; - else + if (!(flags & BPF_F_KPROBE_MULTI_RETURN)) link->fp.entry_handler = kprobe_multi_link_handler; + if ((flags & BPF_F_KPROBE_MULTI_RETURN) || is_kprobe_session(prog)) + link->fp.exit_handler = kprobe_multi_link_exit_handler; + if (is_kprobe_session(prog)) + link->fp.entry_data_size = sizeof(u64); link->addrs = addrs; link->cookies = cookies; @@ -3491,3 +3518,54 @@ static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx) return 0; } #endif /* CONFIG_UPROBES */ + +#ifdef CONFIG_FPROBE +__bpf_kfunc_start_defs(); + +__bpf_kfunc bool bpf_session_is_return(void) +{ + struct bpf_session_run_ctx *session_ctx; + + session_ctx = container_of(current->bpf_ctx, struct bpf_session_run_ctx, run_ctx); + return session_ctx->is_return; +} + +__bpf_kfunc __u64 *bpf_session_cookie(void) +{ + struct bpf_session_run_ctx *session_ctx; + + session_ctx = container_of(current->bpf_ctx, struct bpf_session_run_ctx, run_ctx); + return session_ctx->data; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(kprobe_multi_kfunc_set_ids) +BTF_ID_FLAGS(func, bpf_session_is_return) +BTF_ID_FLAGS(func, bpf_session_cookie) +BTF_KFUNCS_END(kprobe_multi_kfunc_set_ids) + +static int bpf_kprobe_multi_filter(const struct bpf_prog *prog, u32 kfunc_id) +{ + if (!btf_id_set8_contains(&kprobe_multi_kfunc_set_ids, kfunc_id)) + return 0; + + if (!is_kprobe_session(prog)) + return -EACCES; + + return 0; +} + +static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = { + .owner = THIS_MODULE, + .set = &kprobe_multi_kfunc_set_ids, + .filter = bpf_kprobe_multi_filter, +}; + +static int __init bpf_kprobe_multi_kfuncs_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set); +} + +late_initcall(bpf_kprobe_multi_kfuncs_init); +#endif diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 7f518ea5f4ac..18227757ec0c 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -107,6 +107,9 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, case offsetof(struct tcp_sock, snd_cwnd_cnt): end = offsetofend(struct tcp_sock, snd_cwnd_cnt); break; + case offsetof(struct tcp_sock, snd_cwnd_stamp): + end = offsetofend(struct tcp_sock, snd_cwnd_stamp); + break; case offsetof(struct tcp_sock, snd_ssthresh): end = offsetofend(struct tcp_sock, snd_ssthresh); break; @@ -307,7 +310,8 @@ static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk) return 0; } -static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs) +static void bpf_tcp_ca_cong_control(struct sock *sk, u32 ack, int flag, + const struct rate_sample *rs) { } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 7e52ab24e40a..760941e55153 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1024,7 +1024,7 @@ static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) bbr_update_gains(sk); } -__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs) +__bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4ccfec4bb624..9c04a9c8be9d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3542,7 +3542,7 @@ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked, const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cong_control) { - icsk->icsk_ca_ops->cong_control(sk, rs); + icsk->icsk_ca_ops->cong_control(sk, ack, flag, rs); return; } diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 933f6c3fe6b0..9aa027b144df 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -337,7 +337,7 @@ $(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) ifeq ($(VMLINUX_H),) ifeq ($(VMLINUX_BTF),) $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)",\ - build the kernel or set VMLINUX_BTF or VMLINUX_H variable) + build the kernel or set VMLINUX_BTF like "VMLINUX_BTF=/sys/kernel/btf/vmlinux" or VMLINUX_H variable) endif $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ else diff --git a/scripts/Makefile.btf b/scripts/Makefile.btf index 82377e470aed..2d6e5ed9081e 100644 --- a/scripts/Makefile.btf +++ b/scripts/Makefile.btf @@ -3,6 +3,8 @@ pahole-ver := $(CONFIG_PAHOLE_VERSION) pahole-flags-y := +ifeq ($(call test-le, $(pahole-ver), 125),y) + # pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars ifeq ($(call test-le, $(pahole-ver), 121),y) pahole-flags-$(call test-ge, $(pahole-ver), 118) += --skip_encoding_btf_vars @@ -12,8 +14,17 @@ pahole-flags-$(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 + +else + +# Switch to using --btf_features for v1.26 and later. +pahole-flags-$(call test-ge, $(pahole-ver), 126) = -j --btf_features=encode_force,var,float,enum64,decl_tag,type_tag,optimized_func,consistent_func + +endif + pahole-flags-$(CONFIG_PAHOLE_HAS_LANG_EXCLUDE) += --lang_exclude=rust -pahole-flags-$(call test-ge, $(pahole-ver), 125) += --skip_encoding_btf_inconsistent_proto --btf_gen_optimized - export PAHOLE_FLAGS := $(pahole-flags-y) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index b67454b45a49..dfa4f1bebbb3 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -147,7 +147,7 @@ ifeq ($(feature-llvm),1) # If LLVM is available, use it for JIT disassembly CFLAGS += -DHAVE_LLVM_SUPPORT LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets - CFLAGS += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS)) + CFLAGS += $(shell $(LLVM_CONFIG) --cflags) LIBS += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS)) ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static) LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS)) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d94a72593ead..90706a47f6ff 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1115,6 +1115,7 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_GETSOCKNAME, BPF_NETKIT_PRIMARY, BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h deleted file mode 100644 index 11fc18988bc2..000000000000 --- a/tools/include/uapi/linux/ethtool.h +++ /dev/null @@ -1,2271 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * ethtool.h: Defines for Linux ethtool. - * - * Copyright (C) 1998 David S. Miller (davem@redhat.com) - * Copyright 2001 Jeff Garzik - * Portions Copyright 2001 Sun Microsystems (thockin@sun.com) - * Portions Copyright 2002 Intel (eli.kupermann@intel.com, - * christopher.leech@intel.com, - * scott.feldman@intel.com) - * Portions Copyright (C) Sun Microsystems 2008 - */ - -#ifndef _UAPI_LINUX_ETHTOOL_H -#define _UAPI_LINUX_ETHTOOL_H - -#include -#include -#include - -#ifndef __KERNEL__ -#include /* for INT_MAX */ -#endif - -/* All structures exposed to userland should be defined such that they - * have the same layout for 32-bit and 64-bit userland. - */ - -/* Note on reserved space. - * Reserved fields must not be accessed directly by user space because - * they may be replaced by a different field in the future. They must - * be initialized to zero before making the request, e.g. via memset - * of the entire structure or implicitly by not being set in a structure - * initializer. - */ - -/** - * struct ethtool_cmd - DEPRECATED, link control and status - * This structure is DEPRECATED, please use struct ethtool_link_settings. - * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET - * @supported: Bitmask of %SUPPORTED_* flags for the link modes, - * physical connectors and other link features for which the - * interface supports autonegotiation or auto-detection. - * Read-only. - * @advertising: Bitmask of %ADVERTISED_* flags for the link modes, - * physical connectors and other link features that are - * advertised through autonegotiation or enabled for - * auto-detection. - * @speed: Low bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN - * @duplex: Duplex mode; one of %DUPLEX_* - * @port: Physical connector type; one of %PORT_* - * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not - * applicable. For clause 45 PHYs this is the PRTAD. - * @transceiver: Historically used to distinguish different possible - * PHY types, but not in a consistent way. Deprecated. - * @autoneg: Enable/disable autonegotiation and auto-detection; - * either %AUTONEG_DISABLE or %AUTONEG_ENABLE - * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO - * protocols supported by the interface; 0 if unknown. - * Read-only. - * @maxtxpkt: Historically used to report TX IRQ coalescing; now - * obsoleted by &struct ethtool_coalesce. Read-only; deprecated. - * @maxrxpkt: Historically used to report RX IRQ coalescing; now - * obsoleted by &struct ethtool_coalesce. Read-only; deprecated. - * @speed_hi: High bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN - * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of - * %ETH_TP_MDI_*. If the status is unknown or not applicable, the - * value will be %ETH_TP_MDI_INVALID. Read-only. - * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of - * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads - * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. - * When written successfully, the link should be renegotiated if - * necessary. - * @lp_advertising: Bitmask of %ADVERTISED_* flags for the link modes - * and other link features that the link partner advertised - * through autonegotiation; 0 if unknown or not applicable. - * Read-only. - * @reserved: Reserved for future use; see the note on reserved space. - * - * The link speed in Mbps is split between @speed and @speed_hi. Use - * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to - * access it. - * - * If autonegotiation is disabled, the speed and @duplex represent the - * fixed link mode and are writable if the driver supports multiple - * link modes. If it is enabled then they are read-only; if the link - * is up they represent the negotiated link mode; if the link is down, - * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and - * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. - * - * Some hardware interfaces may have multiple PHYs and/or physical - * connectors fitted or do not allow the driver to detect which are - * fitted. For these interfaces @port and/or @phy_address may be - * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. - * Otherwise, attempts to write different values may be ignored or - * rejected. - * - * Users should assume that all fields not marked read-only are - * writable and subject to validation by the driver. They should use - * %ETHTOOL_GSET to get the current values before making specific - * changes and then applying them with %ETHTOOL_SSET. - * - * Deprecated fields should be ignored by both users and drivers. - */ -struct ethtool_cmd { - __u32 cmd; - __u32 supported; - __u32 advertising; - __u16 speed; - __u8 duplex; - __u8 port; - __u8 phy_address; - __u8 transceiver; - __u8 autoneg; - __u8 mdio_support; - __u32 maxtxpkt; - __u32 maxrxpkt; - __u16 speed_hi; - __u8 eth_tp_mdix; - __u8 eth_tp_mdix_ctrl; - __u32 lp_advertising; - __u32 reserved[2]; -}; - -static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep, - __u32 speed) -{ - ep->speed = (__u16)(speed & 0xFFFF); - ep->speed_hi = (__u16)(speed >> 16); -} - -static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) -{ - return (ep->speed_hi << 16) | ep->speed; -} - -/* Device supports clause 22 register access to PHY or peripherals - * using the interface defined in . This should not be - * set if there are known to be no such peripherals present or if - * the driver only emulates clause 22 registers for compatibility. - */ -#define ETH_MDIO_SUPPORTS_C22 1 - -/* Device supports clause 45 register access to PHY or peripherals - * using the interface defined in and . - * This should not be set if there are known to be no such peripherals - * present. - */ -#define ETH_MDIO_SUPPORTS_C45 2 - -#define ETHTOOL_FWVERS_LEN 32 -#define ETHTOOL_BUSINFO_LEN 32 -#define ETHTOOL_EROMVERS_LEN 32 - -/** - * struct ethtool_drvinfo - general driver and device information - * @cmd: Command number = %ETHTOOL_GDRVINFO - * @driver: Driver short name. This should normally match the name - * in its bus driver structure (e.g. pci_driver::name). Must - * not be an empty string. - * @version: Driver version string; may be an empty string - * @fw_version: Firmware version string; driver defined; may be an - * empty string - * @erom_version: Expansion ROM version string; driver defined; may be - * an empty string - * @bus_info: Device bus address. This should match the dev_name() - * string for the underlying bus device, if there is one. May be - * an empty string. - * @reserved2: Reserved for future use; see the note on reserved space. - * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and - * %ETHTOOL_SPFLAGS commands; also the number of strings in the - * %ETH_SS_PRIV_FLAGS set - * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS - * command; also the number of strings in the %ETH_SS_STATS set - * @testinfo_len: Number of results returned by the %ETHTOOL_TEST - * command; also the number of strings in the %ETH_SS_TEST set - * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM - * and %ETHTOOL_SEEPROM commands, in bytes - * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS - * command, in bytes - * - * Users can use the %ETHTOOL_GSSET_INFO command to get the number of - * strings in any string set (from Linux 2.6.34). - */ -struct ethtool_drvinfo { - __u32 cmd; - char driver[32]; - char version[32]; - char fw_version[ETHTOOL_FWVERS_LEN]; - char bus_info[ETHTOOL_BUSINFO_LEN]; - char erom_version[ETHTOOL_EROMVERS_LEN]; - char reserved2[12]; - __u32 n_priv_flags; - __u32 n_stats; - __u32 testinfo_len; - __u32 eedump_len; - __u32 regdump_len; -}; - -#define SOPASS_MAX 6 - -/** - * struct ethtool_wolinfo - Wake-On-Lan configuration - * @cmd: Command number = %ETHTOOL_GWOL or %ETHTOOL_SWOL - * @supported: Bitmask of %WAKE_* flags for supported Wake-On-Lan modes. - * Read-only. - * @wolopts: Bitmask of %WAKE_* flags for enabled Wake-On-Lan modes. - * @sopass: SecureOn(tm) password; meaningful only if %WAKE_MAGICSECURE - * is set in @wolopts. - */ -struct ethtool_wolinfo { - __u32 cmd; - __u32 supported; - __u32 wolopts; - __u8 sopass[SOPASS_MAX]; -}; - -/* for passing single values */ -struct ethtool_value { - __u32 cmd; - __u32 data; -}; - -#define PFC_STORM_PREVENTION_AUTO 0xffff -#define PFC_STORM_PREVENTION_DISABLE 0 - -enum tunable_id { - ETHTOOL_ID_UNSPEC, - ETHTOOL_RX_COPYBREAK, - ETHTOOL_TX_COPYBREAK, - ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ - ETHTOOL_TX_COPYBREAK_BUF_SIZE, - /* - * Add your fresh new tunable attribute above and remember to update - * tunable_strings[] in net/ethtool/common.c - */ - __ETHTOOL_TUNABLE_COUNT, -}; - -enum tunable_type_id { - ETHTOOL_TUNABLE_UNSPEC, - ETHTOOL_TUNABLE_U8, - ETHTOOL_TUNABLE_U16, - ETHTOOL_TUNABLE_U32, - ETHTOOL_TUNABLE_U64, - ETHTOOL_TUNABLE_STRING, - ETHTOOL_TUNABLE_S8, - ETHTOOL_TUNABLE_S16, - ETHTOOL_TUNABLE_S32, - ETHTOOL_TUNABLE_S64, -}; - -struct ethtool_tunable { - __u32 cmd; - __u32 id; - __u32 type_id; - __u32 len; - void *data[]; -}; - -#define DOWNSHIFT_DEV_DEFAULT_COUNT 0xff -#define DOWNSHIFT_DEV_DISABLE 0 - -/* Time in msecs after which link is reported as down - * 0 = lowest time supported by the PHY - * 0xff = off, link down detection according to standard - */ -#define ETHTOOL_PHY_FAST_LINK_DOWN_ON 0 -#define ETHTOOL_PHY_FAST_LINK_DOWN_OFF 0xff - -/* Energy Detect Power Down (EDPD) is a feature supported by some PHYs, where - * the PHY's RX & TX blocks are put into a low-power mode when there is no - * link detected (typically cable is un-plugged). For RX, only a minimal - * link-detection is available, and for TX the PHY wakes up to send link pulses - * to avoid any lock-ups in case the peer PHY may also be running in EDPD mode. - * - * Some PHYs may support configuration of the wake-up interval for TX pulses, - * and some PHYs may support only disabling TX pulses entirely. For the latter - * a special value is required (ETHTOOL_PHY_EDPD_NO_TX) so that this can be - * configured from userspace (should the user want it). - * - * The interval units for TX wake-up are in milliseconds, since this should - * cover a reasonable range of intervals: - * - from 1 millisecond, which does not sound like much of a power-saver - * - to ~65 seconds which is quite a lot to wait for a link to come up when - * plugging a cable - */ -#define ETHTOOL_PHY_EDPD_DFLT_TX_MSECS 0xffff -#define ETHTOOL_PHY_EDPD_NO_TX 0xfffe -#define ETHTOOL_PHY_EDPD_DISABLE 0 - -enum phy_tunable_id { - ETHTOOL_PHY_ID_UNSPEC, - ETHTOOL_PHY_DOWNSHIFT, - ETHTOOL_PHY_FAST_LINK_DOWN, - ETHTOOL_PHY_EDPD, - /* - * Add your fresh new phy tunable attribute above and remember to update - * phy_tunable_strings[] in net/ethtool/common.c - */ - __ETHTOOL_PHY_TUNABLE_COUNT, -}; - -/** - * struct ethtool_regs - hardware register dump - * @cmd: Command number = %ETHTOOL_GREGS - * @version: Dump format version. This is driver-specific and may - * distinguish different chips/revisions. Drivers must use new - * version numbers whenever the dump format changes in an - * incompatible way. - * @len: On entry, the real length of @data. On return, the number of - * bytes used. - * @data: Buffer for the register dump - * - * Users should use %ETHTOOL_GDRVINFO to find the maximum length of - * a register dump for the interface. They must allocate the buffer - * immediately following this structure. - */ -struct ethtool_regs { - __u32 cmd; - __u32 version; - __u32 len; - __u8 data[]; -}; - -/** - * struct ethtool_eeprom - EEPROM dump - * @cmd: Command number = %ETHTOOL_GEEPROM, %ETHTOOL_GMODULEEEPROM or - * %ETHTOOL_SEEPROM - * @magic: A 'magic cookie' value to guard against accidental changes. - * The value passed in to %ETHTOOL_SEEPROM must match the value - * returned by %ETHTOOL_GEEPROM for the same device. This is - * unused when @cmd is %ETHTOOL_GMODULEEEPROM. - * @offset: Offset within the EEPROM to begin reading/writing, in bytes - * @len: On entry, number of bytes to read/write. On successful - * return, number of bytes actually read/written. In case of - * error, this may indicate at what point the error occurred. - * @data: Buffer to read/write from - * - * Users may use %ETHTOOL_GDRVINFO or %ETHTOOL_GMODULEINFO to find - * the length of an on-board or module EEPROM, respectively. They - * must allocate the buffer immediately following this structure. - */ -struct ethtool_eeprom { - __u32 cmd; - __u32 magic; - __u32 offset; - __u32 len; - __u8 data[]; -}; - -/** - * struct ethtool_eee - Energy Efficient Ethernet information - * @cmd: ETHTOOL_{G,S}EEE - * @supported: Mask of %SUPPORTED_* flags for the speed/duplex combinations - * for which there is EEE support. - * @advertised: Mask of %ADVERTISED_* flags for the speed/duplex combinations - * advertised as eee capable. - * @lp_advertised: Mask of %ADVERTISED_* flags for the speed/duplex - * combinations advertised by the link partner as eee capable. - * @eee_active: Result of the eee auto negotiation. - * @eee_enabled: EEE configured mode (enabled/disabled). - * @tx_lpi_enabled: Whether the interface should assert its tx lpi, given - * that eee was negotiated. - * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting - * its tx lpi (after reaching 'idle' state). Effective only when eee - * was negotiated and tx_lpi_enabled was set. - * @reserved: Reserved for future use; see the note on reserved space. - */ -struct ethtool_eee { - __u32 cmd; - __u32 supported; - __u32 advertised; - __u32 lp_advertised; - __u32 eee_active; - __u32 eee_enabled; - __u32 tx_lpi_enabled; - __u32 tx_lpi_timer; - __u32 reserved[2]; -}; - -/** - * struct ethtool_modinfo - plugin module eeprom information - * @cmd: %ETHTOOL_GMODULEINFO - * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx - * @eeprom_len: Length of the eeprom - * @reserved: Reserved for future use; see the note on reserved space. - * - * This structure is used to return the information to - * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM. - * The type code indicates the eeprom data format - */ -struct ethtool_modinfo { - __u32 cmd; - __u32 type; - __u32 eeprom_len; - __u32 reserved[8]; -}; - -/** - * struct ethtool_coalesce - coalescing parameters for IRQs and stats updates - * @cmd: ETHTOOL_{G,S}COALESCE - * @rx_coalesce_usecs: How many usecs to delay an RX interrupt after - * a packet arrives. - * @rx_max_coalesced_frames: Maximum number of packets to receive - * before an RX interrupt. - * @rx_coalesce_usecs_irq: Same as @rx_coalesce_usecs, except that - * this value applies while an IRQ is being serviced by the host. - * @rx_max_coalesced_frames_irq: Same as @rx_max_coalesced_frames, - * except that this value applies while an IRQ is being serviced - * by the host. - * @tx_coalesce_usecs: How many usecs to delay a TX interrupt after - * a packet is sent. - * @tx_max_coalesced_frames: Maximum number of packets to be sent - * before a TX interrupt. - * @tx_coalesce_usecs_irq: Same as @tx_coalesce_usecs, except that - * this value applies while an IRQ is being serviced by the host. - * @tx_max_coalesced_frames_irq: Same as @tx_max_coalesced_frames, - * except that this value applies while an IRQ is being serviced - * by the host. - * @stats_block_coalesce_usecs: How many usecs to delay in-memory - * statistics block updates. Some drivers do not have an - * in-memory statistic block, and in such cases this value is - * ignored. This value must not be zero. - * @use_adaptive_rx_coalesce: Enable adaptive RX coalescing. - * @use_adaptive_tx_coalesce: Enable adaptive TX coalescing. - * @pkt_rate_low: Threshold for low packet rate (packets per second). - * @rx_coalesce_usecs_low: How many usecs to delay an RX interrupt after - * a packet arrives, when the packet rate is below @pkt_rate_low. - * @rx_max_coalesced_frames_low: Maximum number of packets to be received - * before an RX interrupt, when the packet rate is below @pkt_rate_low. - * @tx_coalesce_usecs_low: How many usecs to delay a TX interrupt after - * a packet is sent, when the packet rate is below @pkt_rate_low. - * @tx_max_coalesced_frames_low: Maximum nuumber of packets to be sent before - * a TX interrupt, when the packet rate is below @pkt_rate_low. - * @pkt_rate_high: Threshold for high packet rate (packets per second). - * @rx_coalesce_usecs_high: How many usecs to delay an RX interrupt after - * a packet arrives, when the packet rate is above @pkt_rate_high. - * @rx_max_coalesced_frames_high: Maximum number of packets to be received - * before an RX interrupt, when the packet rate is above @pkt_rate_high. - * @tx_coalesce_usecs_high: How many usecs to delay a TX interrupt after - * a packet is sent, when the packet rate is above @pkt_rate_high. - * @tx_max_coalesced_frames_high: Maximum number of packets to be sent before - * a TX interrupt, when the packet rate is above @pkt_rate_high. - * @rate_sample_interval: How often to do adaptive coalescing packet rate - * sampling, measured in seconds. Must not be zero. - * - * Each pair of (usecs, max_frames) fields specifies that interrupts - * should be coalesced until - * (usecs > 0 && time_since_first_completion >= usecs) || - * (max_frames > 0 && completed_frames >= max_frames) - * - * It is illegal to set both usecs and max_frames to zero as this - * would cause interrupts to never be generated. To disable - * coalescing, set usecs = 0 and max_frames = 1. - * - * Some implementations ignore the value of max_frames and use the - * condition time_since_first_completion >= usecs - * - * This is deprecated. Drivers for hardware that does not support - * counting completions should validate that max_frames == !rx_usecs. - * - * Adaptive RX/TX coalescing is an algorithm implemented by some - * drivers to improve latency under low packet rates and improve - * throughput under high packet rates. Some drivers only implement - * one of RX or TX adaptive coalescing. Anything not implemented by - * the driver causes these values to be silently ignored. - * - * When the packet rate is below @pkt_rate_high but above - * @pkt_rate_low (both measured in packets per second) the - * normal {rx,tx}_* coalescing parameters are used. - */ -struct ethtool_coalesce { - __u32 cmd; - __u32 rx_coalesce_usecs; - __u32 rx_max_coalesced_frames; - __u32 rx_coalesce_usecs_irq; - __u32 rx_max_coalesced_frames_irq; - __u32 tx_coalesce_usecs; - __u32 tx_max_coalesced_frames; - __u32 tx_coalesce_usecs_irq; - __u32 tx_max_coalesced_frames_irq; - __u32 stats_block_coalesce_usecs; - __u32 use_adaptive_rx_coalesce; - __u32 use_adaptive_tx_coalesce; - __u32 pkt_rate_low; - __u32 rx_coalesce_usecs_low; - __u32 rx_max_coalesced_frames_low; - __u32 tx_coalesce_usecs_low; - __u32 tx_max_coalesced_frames_low; - __u32 pkt_rate_high; - __u32 rx_coalesce_usecs_high; - __u32 rx_max_coalesced_frames_high; - __u32 tx_coalesce_usecs_high; - __u32 tx_max_coalesced_frames_high; - __u32 rate_sample_interval; -}; - -/** - * struct ethtool_ringparam - RX/TX ring parameters - * @cmd: Command number = %ETHTOOL_GRINGPARAM or %ETHTOOL_SRINGPARAM - * @rx_max_pending: Maximum supported number of pending entries per - * RX ring. Read-only. - * @rx_mini_max_pending: Maximum supported number of pending entries - * per RX mini ring. Read-only. - * @rx_jumbo_max_pending: Maximum supported number of pending entries - * per RX jumbo ring. Read-only. - * @tx_max_pending: Maximum supported number of pending entries per - * TX ring. Read-only. - * @rx_pending: Current maximum number of pending entries per RX ring - * @rx_mini_pending: Current maximum number of pending entries per RX - * mini ring - * @rx_jumbo_pending: Current maximum number of pending entries per RX - * jumbo ring - * @tx_pending: Current maximum supported number of pending entries - * per TX ring - * - * If the interface does not have separate RX mini and/or jumbo rings, - * @rx_mini_max_pending and/or @rx_jumbo_max_pending will be 0. - * - * There may also be driver-dependent minimum values for the number - * of entries per ring. - */ -struct ethtool_ringparam { - __u32 cmd; - __u32 rx_max_pending; - __u32 rx_mini_max_pending; - __u32 rx_jumbo_max_pending; - __u32 tx_max_pending; - __u32 rx_pending; - __u32 rx_mini_pending; - __u32 rx_jumbo_pending; - __u32 tx_pending; -}; - -/** - * struct ethtool_channels - configuring number of network channel - * @cmd: ETHTOOL_{G,S}CHANNELS - * @max_rx: Read only. Maximum number of receive channel the driver support. - * @max_tx: Read only. Maximum number of transmit channel the driver support. - * @max_other: Read only. Maximum number of other channel the driver support. - * @max_combined: Read only. Maximum number of combined channel the driver - * support. Set of queues RX, TX or other. - * @rx_count: Valid values are in the range 1 to the max_rx. - * @tx_count: Valid values are in the range 1 to the max_tx. - * @other_count: Valid values are in the range 1 to the max_other. - * @combined_count: Valid values are in the range 1 to the max_combined. - * - * This can be used to configure RX, TX and other channels. - */ - -struct ethtool_channels { - __u32 cmd; - __u32 max_rx; - __u32 max_tx; - __u32 max_other; - __u32 max_combined; - __u32 rx_count; - __u32 tx_count; - __u32 other_count; - __u32 combined_count; -}; - -/** - * struct ethtool_pauseparam - Ethernet pause (flow control) parameters - * @cmd: Command number = %ETHTOOL_GPAUSEPARAM or %ETHTOOL_SPAUSEPARAM - * @autoneg: Flag to enable autonegotiation of pause frame use - * @rx_pause: Flag to enable reception of pause frames - * @tx_pause: Flag to enable transmission of pause frames - * - * Drivers should reject a non-zero setting of @autoneg when - * autoneogotiation is disabled (or not supported) for the link. - * - * If the link is autonegotiated, drivers should use - * mii_advertise_flowctrl() or similar code to set the advertised - * pause frame capabilities based on the @rx_pause and @tx_pause flags, - * even if @autoneg is zero. They should also allow the advertised - * pause frame capabilities to be controlled directly through the - * advertising field of &struct ethtool_cmd. - * - * If @autoneg is non-zero, the MAC is configured to send and/or - * receive pause frames according to the result of autonegotiation. - * Otherwise, it is configured directly based on the @rx_pause and - * @tx_pause flags. - */ -struct ethtool_pauseparam { - __u32 cmd; - __u32 autoneg; - __u32 rx_pause; - __u32 tx_pause; -}; - -/* Link extended state */ -enum ethtool_link_ext_state { - ETHTOOL_LINK_EXT_STATE_AUTONEG, - ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE, - ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH, - ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY, - ETHTOOL_LINK_EXT_STATE_NO_CABLE, - ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE, - ETHTOOL_LINK_EXT_STATE_EEPROM_ISSUE, - ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE, - ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, - ETHTOOL_LINK_EXT_STATE_OVERHEAT, - ETHTOOL_LINK_EXT_STATE_MODULE, -}; - -/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ -enum ethtool_link_ext_substate_autoneg { - ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1, - ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED, - ETHTOOL_LINK_EXT_SUBSTATE_AN_NEXT_PAGE_EXCHANGE_FAILED, - ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED_FORCE_MODE, - ETHTOOL_LINK_EXT_SUBSTATE_AN_FEC_MISMATCH_DURING_OVERRIDE, - ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD, -}; - -/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. - */ -enum ethtool_link_ext_substate_link_training { - ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1, - ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_INHIBIT_TIMEOUT, - ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_PARTNER_DID_NOT_SET_RECEIVER_READY, - ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT, -}; - -/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. - */ -enum ethtool_link_ext_substate_link_logical_mismatch { - ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1, - ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_AM_LOCK, - ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_GET_ALIGN_STATUS, - ETHTOOL_LINK_EXT_SUBSTATE_LLM_FC_FEC_IS_NOT_LOCKED, - ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED, -}; - -/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. - */ -enum ethtool_link_ext_substate_bad_signal_integrity { - ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1, - ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE, - ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_REFERENCE_CLOCK_LOST, - ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_ALOS, -}; - -/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */ -enum ethtool_link_ext_substate_cable_issue { - ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1, - ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, -}; - -/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */ -enum ethtool_link_ext_substate_module { - ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1, -}; - -#define ETH_GSTRING_LEN 32 - -/** - * enum ethtool_stringset - string set ID - * @ETH_SS_TEST: Self-test result names, for use with %ETHTOOL_TEST - * @ETH_SS_STATS: Statistic names, for use with %ETHTOOL_GSTATS - * @ETH_SS_PRIV_FLAGS: Driver private flag names, for use with - * %ETHTOOL_GPFLAGS and %ETHTOOL_SPFLAGS - * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE; - * now deprecated - * @ETH_SS_FEATURES: Device feature names - * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names - * @ETH_SS_TUNABLES: tunable names - * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS - * @ETH_SS_PHY_TUNABLES: PHY tunable names - * @ETH_SS_LINK_MODES: link mode names - * @ETH_SS_MSG_CLASSES: debug message class names - * @ETH_SS_WOL_MODES: wake-on-lan modes - * @ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags - * @ETH_SS_TS_TX_TYPES: timestamping Tx types - * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters - * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types - * @ETH_SS_STATS_STD: standardized stats - * @ETH_SS_STATS_ETH_PHY: names of IEEE 802.3 PHY statistics - * @ETH_SS_STATS_ETH_MAC: names of IEEE 802.3 MAC statistics - * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics - * @ETH_SS_STATS_RMON: names of RMON statistics - * - * @ETH_SS_COUNT: number of defined string sets - */ -enum ethtool_stringset { - ETH_SS_TEST = 0, - ETH_SS_STATS, - ETH_SS_PRIV_FLAGS, - ETH_SS_NTUPLE_FILTERS, - ETH_SS_FEATURES, - ETH_SS_RSS_HASH_FUNCS, - ETH_SS_TUNABLES, - ETH_SS_PHY_STATS, - ETH_SS_PHY_TUNABLES, - ETH_SS_LINK_MODES, - ETH_SS_MSG_CLASSES, - ETH_SS_WOL_MODES, - ETH_SS_SOF_TIMESTAMPING, - ETH_SS_TS_TX_TYPES, - ETH_SS_TS_RX_FILTERS, - ETH_SS_UDP_TUNNEL_TYPES, - ETH_SS_STATS_STD, - ETH_SS_STATS_ETH_PHY, - ETH_SS_STATS_ETH_MAC, - ETH_SS_STATS_ETH_CTRL, - ETH_SS_STATS_RMON, - - /* add new constants above here */ - ETH_SS_COUNT -}; - -/** - * enum ethtool_mac_stats_src - source of ethtool MAC statistics - * @ETHTOOL_MAC_STATS_SRC_AGGREGATE: - * if device supports a MAC merge layer, this retrieves the aggregate - * statistics of the eMAC and pMAC. Otherwise, it retrieves just the - * statistics of the single (express) MAC. - * @ETHTOOL_MAC_STATS_SRC_EMAC: - * if device supports a MM layer, this retrieves the eMAC statistics. - * Otherwise, it retrieves the statistics of the single (express) MAC. - * @ETHTOOL_MAC_STATS_SRC_PMAC: - * if device supports a MM layer, this retrieves the pMAC statistics. - */ -enum ethtool_mac_stats_src { - ETHTOOL_MAC_STATS_SRC_AGGREGATE, - ETHTOOL_MAC_STATS_SRC_EMAC, - ETHTOOL_MAC_STATS_SRC_PMAC, -}; - -/** - * enum ethtool_module_power_mode_policy - plug-in module power mode policy - * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode. - * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host - * to high power mode when the first port using it is put administratively - * up and to low power mode when the last port using it is put - * administratively down. - */ -enum ethtool_module_power_mode_policy { - ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1, - ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO, -}; - -/** - * enum ethtool_module_power_mode - plug-in module power mode - * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode. - * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode. - */ -enum ethtool_module_power_mode { - ETHTOOL_MODULE_POWER_MODE_LOW = 1, - ETHTOOL_MODULE_POWER_MODE_HIGH, -}; - -/** - * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE - * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState - * @ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN: state of PoDL PSE functions are - * unknown - * @ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED: PoDL PSE functions are disabled - * @ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED: PoDL PSE functions are enabled - */ -enum ethtool_podl_pse_admin_state { - ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN = 1, - ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED, - ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED, -}; - -/** - * enum ethtool_podl_pse_pw_d_status - power detection status of the PoDL PSE. - * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: - * @ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN: PoDL PSE - * @ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED: "The enumeration “disabled” is - * asserted true when the PoDL PSE state diagram variable mr_pse_enable is - * false" - * @ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING: "The enumeration “searching” is - * asserted true when either of the PSE state diagram variables - * pi_detecting or pi_classifying is true." - * @ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING: "The enumeration “deliveringPower” - * is asserted true when the PoDL PSE state diagram variable pi_powered is - * true." - * @ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP: "The enumeration “sleep” is asserted - * true when the PoDL PSE state diagram variable pi_sleeping is true." - * @ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE: "The enumeration “idle” is asserted true - * when the logical combination of the PoDL PSE state diagram variables - * pi_prebiased*!pi_sleeping is true." - * @ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR: "The enumeration “error” is asserted - * true when the PoDL PSE state diagram variable overload_held is true." - */ -enum ethtool_podl_pse_pw_d_status { - ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN = 1, - ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED, - ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING, - ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING, - ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP, - ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE, - ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR, -}; - -/** - * enum ethtool_mm_verify_status - status of MAC Merge Verify function - * @ETHTOOL_MM_VERIFY_STATUS_UNKNOWN: - * verification status is unknown - * @ETHTOOL_MM_VERIFY_STATUS_INITIAL: - * the 802.3 Verify State diagram is in the state INIT_VERIFICATION - * @ETHTOOL_MM_VERIFY_STATUS_VERIFYING: - * the Verify State diagram is in the state VERIFICATION_IDLE, - * SEND_VERIFY or WAIT_FOR_RESPONSE - * @ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED: - * indicates that the Verify State diagram is in the state VERIFIED - * @ETHTOOL_MM_VERIFY_STATUS_FAILED: - * the Verify State diagram is in the state VERIFY_FAIL - * @ETHTOOL_MM_VERIFY_STATUS_DISABLED: - * verification of preemption operation is disabled - */ -enum ethtool_mm_verify_status { - ETHTOOL_MM_VERIFY_STATUS_UNKNOWN, - ETHTOOL_MM_VERIFY_STATUS_INITIAL, - ETHTOOL_MM_VERIFY_STATUS_VERIFYING, - ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED, - ETHTOOL_MM_VERIFY_STATUS_FAILED, - ETHTOOL_MM_VERIFY_STATUS_DISABLED, -}; - -/** - * struct ethtool_gstrings - string set for data tagging - * @cmd: Command number = %ETHTOOL_GSTRINGS - * @string_set: String set ID; one of &enum ethtool_stringset - * @len: On return, the number of strings in the string set - * @data: Buffer for strings. Each string is null-padded to a size of - * %ETH_GSTRING_LEN. - * - * Users must use %ETHTOOL_GSSET_INFO to find the number of strings in - * the string set. They must allocate a buffer of the appropriate - * size immediately following this structure. - */ -struct ethtool_gstrings { - __u32 cmd; - __u32 string_set; - __u32 len; - __u8 data[]; -}; - -/** - * struct ethtool_sset_info - string set information - * @cmd: Command number = %ETHTOOL_GSSET_INFO - * @reserved: Reserved for future use; see the note on reserved space. - * @sset_mask: On entry, a bitmask of string sets to query, with bits - * numbered according to &enum ethtool_stringset. On return, a - * bitmask of those string sets queried that are supported. - * @data: Buffer for string set sizes. On return, this contains the - * size of each string set that was queried and supported, in - * order of ID. - * - * Example: The user passes in @sset_mask = 0x7 (sets 0, 1, 2) and on - * return @sset_mask == 0x6 (sets 1, 2). Then @data[0] contains the - * size of set 1 and @data[1] contains the size of set 2. - * - * Users must allocate a buffer of the appropriate size (4 * number of - * sets queried) immediately following this structure. - */ -struct ethtool_sset_info { - __u32 cmd; - __u32 reserved; - __u64 sset_mask; - __u32 data[]; -}; - -/** - * enum ethtool_test_flags - flags definition of ethtool_test - * @ETH_TEST_FL_OFFLINE: if set perform online and offline tests, otherwise - * only online tests. - * @ETH_TEST_FL_FAILED: Driver set this flag if test fails. - * @ETH_TEST_FL_EXTERNAL_LB: Application request to perform external loopback - * test. - * @ETH_TEST_FL_EXTERNAL_LB_DONE: Driver performed the external loopback test - */ - -enum ethtool_test_flags { - ETH_TEST_FL_OFFLINE = (1 << 0), - ETH_TEST_FL_FAILED = (1 << 1), - ETH_TEST_FL_EXTERNAL_LB = (1 << 2), - ETH_TEST_FL_EXTERNAL_LB_DONE = (1 << 3), -}; - -/** - * struct ethtool_test - device self-test invocation - * @cmd: Command number = %ETHTOOL_TEST - * @flags: A bitmask of flags from &enum ethtool_test_flags. Some - * flags may be set by the user on entry; others may be set by - * the driver on return. - * @reserved: Reserved for future use; see the note on reserved space. - * @len: On return, the number of test results - * @data: Array of test results - * - * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the - * number of test results that will be returned. They must allocate a - * buffer of the appropriate size (8 * number of results) immediately - * following this structure. - */ -struct ethtool_test { - __u32 cmd; - __u32 flags; - __u32 reserved; - __u32 len; - __u64 data[]; -}; - -/** - * struct ethtool_stats - device-specific statistics - * @cmd: Command number = %ETHTOOL_GSTATS - * @n_stats: On return, the number of statistics - * @data: Array of statistics - * - * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the - * number of statistics that will be returned. They must allocate a - * buffer of the appropriate size (8 * number of statistics) - * immediately following this structure. - */ -struct ethtool_stats { - __u32 cmd; - __u32 n_stats; - __u64 data[]; -}; - -/** - * struct ethtool_perm_addr - permanent hardware address - * @cmd: Command number = %ETHTOOL_GPERMADDR - * @size: On entry, the size of the buffer. On return, the size of the - * address. The command fails if the buffer is too small. - * @data: Buffer for the address - * - * Users must allocate the buffer immediately following this structure. - * A buffer size of %MAX_ADDR_LEN should be sufficient for any address - * type. - */ -struct ethtool_perm_addr { - __u32 cmd; - __u32 size; - __u8 data[]; -}; - -/* boolean flags controlling per-interface behavior characteristics. - * When reading, the flag indicates whether or not a certain behavior - * is enabled/present. When writing, the flag indicates whether - * or not the driver should turn on (set) or off (clear) a behavior. - * - * Some behaviors may read-only (unconditionally absent or present). - * If such is the case, return EINVAL in the set-flags operation if the - * flag differs from the read-only value. - */ -enum ethtool_flags { - ETH_FLAG_TXVLAN = (1 << 7), /* TX VLAN offload enabled */ - ETH_FLAG_RXVLAN = (1 << 8), /* RX VLAN offload enabled */ - ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */ - ETH_FLAG_NTUPLE = (1 << 27), /* N-tuple filters enabled */ - ETH_FLAG_RXHASH = (1 << 28), -}; - -/* The following structures are for supporting RX network flow - * classification and RX n-tuple configuration. Note, all multibyte - * fields, e.g., ip4src, ip4dst, psrc, pdst, spi, etc. are expected to - * be in network byte order. - */ - -/** - * struct ethtool_tcpip4_spec - flow specification for TCP/IPv4 etc. - * @ip4src: Source host - * @ip4dst: Destination host - * @psrc: Source port - * @pdst: Destination port - * @tos: Type-of-service - * - * This can be used to specify a TCP/IPv4, UDP/IPv4 or SCTP/IPv4 flow. - */ -struct ethtool_tcpip4_spec { - __be32 ip4src; - __be32 ip4dst; - __be16 psrc; - __be16 pdst; - __u8 tos; -}; - -/** - * struct ethtool_ah_espip4_spec - flow specification for IPsec/IPv4 - * @ip4src: Source host - * @ip4dst: Destination host - * @spi: Security parameters index - * @tos: Type-of-service - * - * This can be used to specify an IPsec transport or tunnel over IPv4. - */ -struct ethtool_ah_espip4_spec { - __be32 ip4src; - __be32 ip4dst; - __be32 spi; - __u8 tos; -}; - -#define ETH_RX_NFC_IP4 1 - -/** - * struct ethtool_usrip4_spec - general flow specification for IPv4 - * @ip4src: Source host - * @ip4dst: Destination host - * @l4_4_bytes: First 4 bytes of transport (layer 4) header - * @tos: Type-of-service - * @ip_ver: Value must be %ETH_RX_NFC_IP4; mask must be 0 - * @proto: Transport protocol number; mask must be 0 - */ -struct ethtool_usrip4_spec { - __be32 ip4src; - __be32 ip4dst; - __be32 l4_4_bytes; - __u8 tos; - __u8 ip_ver; - __u8 proto; -}; - -/** - * struct ethtool_tcpip6_spec - flow specification for TCP/IPv6 etc. - * @ip6src: Source host - * @ip6dst: Destination host - * @psrc: Source port - * @pdst: Destination port - * @tclass: Traffic Class - * - * This can be used to specify a TCP/IPv6, UDP/IPv6 or SCTP/IPv6 flow. - */ -struct ethtool_tcpip6_spec { - __be32 ip6src[4]; - __be32 ip6dst[4]; - __be16 psrc; - __be16 pdst; - __u8 tclass; -}; - -/** - * struct ethtool_ah_espip6_spec - flow specification for IPsec/IPv6 - * @ip6src: Source host - * @ip6dst: Destination host - * @spi: Security parameters index - * @tclass: Traffic Class - * - * This can be used to specify an IPsec transport or tunnel over IPv6. - */ -struct ethtool_ah_espip6_spec { - __be32 ip6src[4]; - __be32 ip6dst[4]; - __be32 spi; - __u8 tclass; -}; - -/** - * struct ethtool_usrip6_spec - general flow specification for IPv6 - * @ip6src: Source host - * @ip6dst: Destination host - * @l4_4_bytes: First 4 bytes of transport (layer 4) header - * @tclass: Traffic Class - * @l4_proto: Transport protocol number (nexthdr after any Extension Headers) - */ -struct ethtool_usrip6_spec { - __be32 ip6src[4]; - __be32 ip6dst[4]; - __be32 l4_4_bytes; - __u8 tclass; - __u8 l4_proto; -}; - -union ethtool_flow_union { - struct ethtool_tcpip4_spec tcp_ip4_spec; - struct ethtool_tcpip4_spec udp_ip4_spec; - struct ethtool_tcpip4_spec sctp_ip4_spec; - struct ethtool_ah_espip4_spec ah_ip4_spec; - struct ethtool_ah_espip4_spec esp_ip4_spec; - struct ethtool_usrip4_spec usr_ip4_spec; - struct ethtool_tcpip6_spec tcp_ip6_spec; - struct ethtool_tcpip6_spec udp_ip6_spec; - struct ethtool_tcpip6_spec sctp_ip6_spec; - struct ethtool_ah_espip6_spec ah_ip6_spec; - struct ethtool_ah_espip6_spec esp_ip6_spec; - struct ethtool_usrip6_spec usr_ip6_spec; - struct ethhdr ether_spec; - __u8 hdata[52]; -}; - -/** - * struct ethtool_flow_ext - additional RX flow fields - * @h_dest: destination MAC address - * @vlan_etype: VLAN EtherType - * @vlan_tci: VLAN tag control information - * @data: user defined data - * @padding: Reserved for future use; see the note on reserved space. - * - * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT - * is set in &struct ethtool_rx_flow_spec @flow_type. - * @h_dest is valid if %FLOW_MAC_EXT is set. - */ -struct ethtool_flow_ext { - __u8 padding[2]; - unsigned char h_dest[ETH_ALEN]; - __be16 vlan_etype; - __be16 vlan_tci; - __be32 data[2]; -}; - -/** - * struct ethtool_rx_flow_spec - classification rule for RX flows - * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW - * @h_u: Flow fields to match (dependent on @flow_type) - * @h_ext: Additional fields to match - * @m_u: Masks for flow field bits to be matched - * @m_ext: Masks for additional field bits to be matched - * Note, all additional fields must be ignored unless @flow_type - * includes the %FLOW_EXT or %FLOW_MAC_EXT flag - * (see &struct ethtool_flow_ext description). - * @ring_cookie: RX ring/queue index to deliver to, or %RX_CLS_FLOW_DISC - * if packets should be discarded, or %RX_CLS_FLOW_WAKE if the - * packets should be used for Wake-on-LAN with %WAKE_FILTER - * @location: Location of rule in the table. Locations must be - * numbered such that a flow matching multiple rules will be - * classified according to the first (lowest numbered) rule. - */ -struct ethtool_rx_flow_spec { - __u32 flow_type; - union ethtool_flow_union h_u; - struct ethtool_flow_ext h_ext; - union ethtool_flow_union m_u; - struct ethtool_flow_ext m_ext; - __u64 ring_cookie; - __u32 location; -}; - -/* How rings are laid out when accessing virtual functions or - * offloaded queues is device specific. To allow users to do flow - * steering and specify these queues the ring cookie is partitioned - * into a 32bit queue index with an 8 bit virtual function id. - * This also leaves the 3bytes for further specifiers. It is possible - * future devices may support more than 256 virtual functions if - * devices start supporting PCIe w/ARI. However at the moment I - * do not know of any devices that support this so I do not reserve - * space for this at this time. If a future patch consumes the next - * byte it should be aware of this possibility. - */ -#define ETHTOOL_RX_FLOW_SPEC_RING 0x00000000FFFFFFFFLL -#define ETHTOOL_RX_FLOW_SPEC_RING_VF 0x000000FF00000000LL -#define ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF 32 -static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie) -{ - return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie; -} - -static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie) -{ - return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >> - ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; -} - -/** - * struct ethtool_rxnfc - command to get or set RX flow classification rules - * @cmd: Specific command number - %ETHTOOL_GRXFH, %ETHTOOL_SRXFH, - * %ETHTOOL_GRXRINGS, %ETHTOOL_GRXCLSRLCNT, %ETHTOOL_GRXCLSRULE, - * %ETHTOOL_GRXCLSRLALL, %ETHTOOL_SRXCLSRLDEL or %ETHTOOL_SRXCLSRLINS - * @flow_type: Type of flow to be affected, e.g. %TCP_V4_FLOW - * @data: Command-dependent value - * @fs: Flow classification rule - * @rss_context: RSS context to be affected - * @rule_cnt: Number of rules to be affected - * @rule_locs: Array of used rule locations - * - * For %ETHTOOL_GRXFH and %ETHTOOL_SRXFH, @data is a bitmask indicating - * the fields included in the flow hash, e.g. %RXH_IP_SRC. The following - * structure fields must not be used, except that if @flow_type includes - * the %FLOW_RSS flag, then @rss_context determines which RSS context to - * act on. - * - * For %ETHTOOL_GRXRINGS, @data is set to the number of RX rings/queues - * on return. - * - * For %ETHTOOL_GRXCLSRLCNT, @rule_cnt is set to the number of defined - * rules on return. If @data is non-zero on return then it is the - * size of the rule table, plus the flag %RX_CLS_LOC_SPECIAL if the - * driver supports any special location values. If that flag is not - * set in @data then special location values should not be used. - * - * For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an - * existing rule on entry and @fs contains the rule on return; if - * @fs.@flow_type includes the %FLOW_RSS flag, then @rss_context is - * filled with the RSS context ID associated with the rule. - * - * For %ETHTOOL_GRXCLSRLALL, @rule_cnt specifies the array size of the - * user buffer for @rule_locs on entry. On return, @data is the size - * of the rule table, @rule_cnt is the number of defined rules, and - * @rule_locs contains the locations of the defined rules. Drivers - * must use the second parameter to get_rxnfc() instead of @rule_locs. - * - * For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update. - * @fs.@location either specifies the location to use or is a special - * location value with %RX_CLS_LOC_SPECIAL flag set. On return, - * @fs.@location is the actual rule location. If @fs.@flow_type - * includes the %FLOW_RSS flag, @rss_context is the RSS context ID to - * use for flow spreading traffic which matches this rule. The value - * from the rxfh indirection table will be added to @fs.@ring_cookie - * to choose which ring to deliver to. - * - * For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an - * existing rule on entry. - * - * A driver supporting the special location values for - * %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused - * location, and may remove a rule at a later location (lower - * priority) that matches exactly the same set of flows. The special - * values are %RX_CLS_LOC_ANY, selecting any location; - * %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum - * priority); and %RX_CLS_LOC_LAST, selecting the last suitable - * location (minimum priority). Additional special values may be - * defined in future and drivers must return -%EINVAL for any - * unrecognised value. - */ -struct ethtool_rxnfc { - __u32 cmd; - __u32 flow_type; - __u64 data; - struct ethtool_rx_flow_spec fs; - union { - __u32 rule_cnt; - __u32 rss_context; - }; - __u32 rule_locs[]; -}; - - -/** - * struct ethtool_rxfh_indir - command to get or set RX flow hash indirection - * @cmd: Specific command number - %ETHTOOL_GRXFHINDIR or %ETHTOOL_SRXFHINDIR - * @size: On entry, the array size of the user buffer, which may be zero. - * On return from %ETHTOOL_GRXFHINDIR, the array size of the hardware - * indirection table. - * @ring_index: RX ring/queue index for each hash value - * - * For %ETHTOOL_GRXFHINDIR, a @size of zero means that only the size - * should be returned. For %ETHTOOL_SRXFHINDIR, a @size of zero means - * the table should be reset to default values. This last feature - * is not supported by the original implementations. - */ -struct ethtool_rxfh_indir { - __u32 cmd; - __u32 size; - __u32 ring_index[]; -}; - -/** - * struct ethtool_rxfh - command to get/set RX flow hash indir or/and hash key. - * @cmd: Specific command number - %ETHTOOL_GRSSH or %ETHTOOL_SRSSH - * @rss_context: RSS context identifier. Context 0 is the default for normal - * traffic; other contexts can be referenced as the destination for RX flow - * classification rules. %ETH_RXFH_CONTEXT_ALLOC is used with command - * %ETHTOOL_SRSSH to allocate a new RSS context; on return this field will - * contain the ID of the newly allocated context. - * @indir_size: On entry, the array size of the user buffer for the - * indirection table, which may be zero, or (for %ETHTOOL_SRSSH), - * %ETH_RXFH_INDIR_NO_CHANGE. On return from %ETHTOOL_GRSSH, - * the array size of the hardware indirection table. - * @key_size: On entry, the array size of the user buffer for the hash key, - * which may be zero. On return from %ETHTOOL_GRSSH, the size of the - * hardware hash key. - * @hfunc: Defines the current RSS hash function used by HW (or to be set to). - * Valid values are one of the %ETH_RSS_HASH_*. - * @input_xfrm: Defines how the input data is transformed. Valid values are one - * of %RXH_XFRM_*. - * @rsvd8: Reserved for future use; see the note on reserved space. - * @rsvd32: Reserved for future use; see the note on reserved space. - * @rss_config: RX ring/queue index for each hash value i.e., indirection table - * of @indir_size __u32 elements, followed by hash key of @key_size - * bytes. - * - * For %ETHTOOL_GRSSH, a @indir_size and key_size of zero means that only the - * size should be returned. For %ETHTOOL_SRSSH, an @indir_size of - * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested - * and a @indir_size of zero means the indir table should be reset to default - * values (if @rss_context == 0) or that the RSS context should be deleted. - * An hfunc of zero means that hash function setting is not requested. - */ -struct ethtool_rxfh { - __u32 cmd; - __u32 rss_context; - __u32 indir_size; - __u32 key_size; - __u8 hfunc; - __u8 input_xfrm; - __u8 rsvd8[2]; - __u32 rsvd32; - __u32 rss_config[]; -}; -#define ETH_RXFH_CONTEXT_ALLOC 0xffffffff -#define ETH_RXFH_INDIR_NO_CHANGE 0xffffffff - -/** - * struct ethtool_rx_ntuple_flow_spec - specification for RX flow filter - * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW - * @h_u: Flow field values to match (dependent on @flow_type) - * @m_u: Masks for flow field value bits to be ignored - * @vlan_tag: VLAN tag to match - * @vlan_tag_mask: Mask for VLAN tag bits to be ignored - * @data: Driver-dependent data to match - * @data_mask: Mask for driver-dependent data bits to be ignored - * @action: RX ring/queue index to deliver to (non-negative) or other action - * (negative, e.g. %ETHTOOL_RXNTUPLE_ACTION_DROP) - * - * For flow types %TCP_V4_FLOW, %UDP_V4_FLOW and %SCTP_V4_FLOW, where - * a field value and mask are both zero this is treated as if all mask - * bits are set i.e. the field is ignored. - */ -struct ethtool_rx_ntuple_flow_spec { - __u32 flow_type; - union { - struct ethtool_tcpip4_spec tcp_ip4_spec; - struct ethtool_tcpip4_spec udp_ip4_spec; - struct ethtool_tcpip4_spec sctp_ip4_spec; - struct ethtool_ah_espip4_spec ah_ip4_spec; - struct ethtool_ah_espip4_spec esp_ip4_spec; - struct ethtool_usrip4_spec usr_ip4_spec; - struct ethhdr ether_spec; - __u8 hdata[72]; - } h_u, m_u; - - __u16 vlan_tag; - __u16 vlan_tag_mask; - __u64 data; - __u64 data_mask; - - __s32 action; -#define ETHTOOL_RXNTUPLE_ACTION_DROP (-1) /* drop packet */ -#define ETHTOOL_RXNTUPLE_ACTION_CLEAR (-2) /* clear filter */ -}; - -/** - * struct ethtool_rx_ntuple - command to set or clear RX flow filter - * @cmd: Command number - %ETHTOOL_SRXNTUPLE - * @fs: Flow filter specification - */ -struct ethtool_rx_ntuple { - __u32 cmd; - struct ethtool_rx_ntuple_flow_spec fs; -}; - -#define ETHTOOL_FLASH_MAX_FILENAME 128 -enum ethtool_flash_op_type { - ETHTOOL_FLASH_ALL_REGIONS = 0, -}; - -/* for passing firmware flashing related parameters */ -struct ethtool_flash { - __u32 cmd; - __u32 region; - char data[ETHTOOL_FLASH_MAX_FILENAME]; -}; - -/** - * struct ethtool_dump - used for retrieving, setting device dump - * @cmd: Command number - %ETHTOOL_GET_DUMP_FLAG, %ETHTOOL_GET_DUMP_DATA, or - * %ETHTOOL_SET_DUMP - * @version: FW version of the dump, filled in by driver - * @flag: driver dependent flag for dump setting, filled in by driver during - * get and filled in by ethtool for set operation. - * flag must be initialized by macro ETH_FW_DUMP_DISABLE value when - * firmware dump is disabled. - * @len: length of dump data, used as the length of the user buffer on entry to - * %ETHTOOL_GET_DUMP_DATA and this is returned as dump length by driver - * for %ETHTOOL_GET_DUMP_FLAG command - * @data: data collected for get dump data operation - */ -struct ethtool_dump { - __u32 cmd; - __u32 version; - __u32 flag; - __u32 len; - __u8 data[]; -}; - -#define ETH_FW_DUMP_DISABLE 0 - -/* for returning and changing feature sets */ - -/** - * struct ethtool_get_features_block - block with state of 32 features - * @available: mask of changeable features - * @requested: mask of features requested to be enabled if possible - * @active: mask of currently enabled features - * @never_changed: mask of features not changeable for any device - */ -struct ethtool_get_features_block { - __u32 available; - __u32 requested; - __u32 active; - __u32 never_changed; -}; - -/** - * struct ethtool_gfeatures - command to get state of device's features - * @cmd: command number = %ETHTOOL_GFEATURES - * @size: On entry, the number of elements in the features[] array; - * on return, the number of elements in features[] needed to hold - * all features - * @features: state of features - */ -struct ethtool_gfeatures { - __u32 cmd; - __u32 size; - struct ethtool_get_features_block features[]; -}; - -/** - * struct ethtool_set_features_block - block with request for 32 features - * @valid: mask of features to be changed - * @requested: values of features to be changed - */ -struct ethtool_set_features_block { - __u32 valid; - __u32 requested; -}; - -/** - * struct ethtool_sfeatures - command to request change in device's features - * @cmd: command number = %ETHTOOL_SFEATURES - * @size: array size of the features[] array - * @features: feature change masks - */ -struct ethtool_sfeatures { - __u32 cmd; - __u32 size; - struct ethtool_set_features_block features[]; -}; - -/** - * struct ethtool_ts_info - holds a device's timestamping and PHC association - * @cmd: command number = %ETHTOOL_GET_TS_INFO - * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags - * @phc_index: device index of the associated PHC, or -1 if there is none - * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values - * @tx_reserved: Reserved for future use; see the note on reserved space. - * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values - * @rx_reserved: Reserved for future use; see the note on reserved space. - * - * The bits in the 'tx_types' and 'rx_filters' fields correspond to - * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values, - * respectively. For example, if the device supports HWTSTAMP_TX_ON, - * then (1 << HWTSTAMP_TX_ON) in 'tx_types' will be set. - * - * Drivers should only report the filters they actually support without - * upscaling in the SIOCSHWTSTAMP ioctl. If the SIOCSHWSTAMP request for - * HWTSTAMP_FILTER_V1_SYNC is supported by HWTSTAMP_FILTER_V1_EVENT, then the - * driver should only report HWTSTAMP_FILTER_V1_EVENT in this op. - */ -struct ethtool_ts_info { - __u32 cmd; - __u32 so_timestamping; - __s32 phc_index; - __u32 tx_types; - __u32 tx_reserved[3]; - __u32 rx_filters; - __u32 rx_reserved[3]; -}; - -/* - * %ETHTOOL_SFEATURES changes features present in features[].valid to the - * values of corresponding bits in features[].requested. Bits in .requested - * not set in .valid or not changeable are ignored. - * - * Returns %EINVAL when .valid contains undefined or never-changeable bits - * or size is not equal to required number of features words (32-bit blocks). - * Returns >= 0 if request was completed; bits set in the value mean: - * %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not - * changeable (not present in %ETHTOOL_GFEATURES' features[].available) - * those bits were ignored. - * %ETHTOOL_F_WISH - some or all changes requested were recorded but the - * resulting state of bits masked by .valid is not equal to .requested. - * Probably there are other device-specific constraints on some features - * in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered - * here as though ignored bits were cleared. - * %ETHTOOL_F_COMPAT - some or all changes requested were made by calling - * compatibility functions. Requested offload state cannot be properly - * managed by kernel. - * - * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of - * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands - * for ETH_SS_FEATURES string set. First entry in the table corresponds to least - * significant bit in features[0] fields. Empty strings mark undefined features. - */ -enum ethtool_sfeatures_retval_bits { - ETHTOOL_F_UNSUPPORTED__BIT, - ETHTOOL_F_WISH__BIT, - ETHTOOL_F_COMPAT__BIT, -}; - -#define ETHTOOL_F_UNSUPPORTED (1 << ETHTOOL_F_UNSUPPORTED__BIT) -#define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT) -#define ETHTOOL_F_COMPAT (1 << ETHTOOL_F_COMPAT__BIT) - -#define MAX_NUM_QUEUE 4096 - -/** - * struct ethtool_per_queue_op - apply sub command to the queues in mask. - * @cmd: ETHTOOL_PERQUEUE - * @sub_command: the sub command which apply to each queues - * @queue_mask: Bitmap of the queues which sub command apply to - * @data: A complete command structure following for each of the queues addressed - */ -struct ethtool_per_queue_op { - __u32 cmd; - __u32 sub_command; - __u32 queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; - char data[]; -}; - -/** - * struct ethtool_fecparam - Ethernet Forward Error Correction parameters - * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM - * @active_fec: FEC mode which is active on the port, single bit set, GET only. - * @fec: Bitmask of configured FEC modes. - * @reserved: Reserved for future extensions, ignore on GET, write 0 for SET. - * - * Note that @reserved was never validated on input and ethtool user space - * left it uninitialized when calling SET. Hence going forward it can only be - * used to return a value to userspace with GET. - * - * FEC modes supported by the device can be read via %ETHTOOL_GLINKSETTINGS. - * FEC settings are configured by link autonegotiation whenever it's enabled. - * With autoneg on %ETHTOOL_GFECPARAM can be used to read the current mode. - * - * When autoneg is disabled %ETHTOOL_SFECPARAM controls the FEC settings. - * It is recommended that drivers only accept a single bit set in @fec. - * When multiple bits are set in @fec drivers may pick mode in an implementation - * dependent way. Drivers should reject mixing %ETHTOOL_FEC_AUTO_BIT with other - * FEC modes, because it's unclear whether in this case other modes constrain - * AUTO or are independent choices. - * Drivers must reject SET requests if they support none of the requested modes. - * - * If device does not support FEC drivers may use %ETHTOOL_FEC_NONE instead - * of returning %EOPNOTSUPP from %ETHTOOL_GFECPARAM. - * - * See enum ethtool_fec_config_bits for definition of valid bits for both - * @fec and @active_fec. - */ -struct ethtool_fecparam { - __u32 cmd; - /* bitmask of FEC modes */ - __u32 active_fec; - __u32 fec; - __u32 reserved; -}; - -/** - * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration - * @ETHTOOL_FEC_NONE_BIT: FEC mode configuration is not supported. Should not - * be used together with other bits. GET only. - * @ETHTOOL_FEC_AUTO_BIT: Select default/best FEC mode automatically, usually - * based link mode and SFP parameters read from module's - * EEPROM. This bit does _not_ mean autonegotiation. - * @ETHTOOL_FEC_OFF_BIT: No FEC Mode - * @ETHTOOL_FEC_RS_BIT: Reed-Solomon FEC Mode - * @ETHTOOL_FEC_BASER_BIT: Base-R/Reed-Solomon FEC Mode - * @ETHTOOL_FEC_LLRS_BIT: Low Latency Reed Solomon FEC Mode (25G/50G Ethernet - * Consortium) - */ -enum ethtool_fec_config_bits { - ETHTOOL_FEC_NONE_BIT, - ETHTOOL_FEC_AUTO_BIT, - ETHTOOL_FEC_OFF_BIT, - ETHTOOL_FEC_RS_BIT, - ETHTOOL_FEC_BASER_BIT, - ETHTOOL_FEC_LLRS_BIT, -}; - -#define ETHTOOL_FEC_NONE (1 << ETHTOOL_FEC_NONE_BIT) -#define ETHTOOL_FEC_AUTO (1 << ETHTOOL_FEC_AUTO_BIT) -#define ETHTOOL_FEC_OFF (1 << ETHTOOL_FEC_OFF_BIT) -#define ETHTOOL_FEC_RS (1 << ETHTOOL_FEC_RS_BIT) -#define ETHTOOL_FEC_BASER (1 << ETHTOOL_FEC_BASER_BIT) -#define ETHTOOL_FEC_LLRS (1 << ETHTOOL_FEC_LLRS_BIT) - -/* CMDs currently supported */ -#define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. - * Please use ETHTOOL_GLINKSETTINGS - */ -#define ETHTOOL_SSET 0x00000002 /* DEPRECATED, Set settings. - * Please use ETHTOOL_SLINKSETTINGS - */ -#define ETHTOOL_GDRVINFO 0x00000003 /* Get driver info. */ -#define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ -#define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ -#define ETHTOOL_SWOL 0x00000006 /* Set wake-on-lan options. */ -#define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ -#define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ -#define ETHTOOL_NWAY_RST 0x00000009 /* Restart autonegotiation. */ -/* Get link status for host, i.e. whether the interface *and* the - * physical port (if there is one) are up (ethtool_value). */ -#define ETHTOOL_GLINK 0x0000000a -#define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ -#define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ -#define ETHTOOL_GCOALESCE 0x0000000e /* Get coalesce config */ -#define ETHTOOL_SCOALESCE 0x0000000f /* Set coalesce config. */ -#define ETHTOOL_GRINGPARAM 0x00000010 /* Get ring parameters */ -#define ETHTOOL_SRINGPARAM 0x00000011 /* Set ring parameters. */ -#define ETHTOOL_GPAUSEPARAM 0x00000012 /* Get pause parameters */ -#define ETHTOOL_SPAUSEPARAM 0x00000013 /* Set pause parameters. */ -#define ETHTOOL_GRXCSUM 0x00000014 /* Get RX hw csum enable (ethtool_value) */ -#define ETHTOOL_SRXCSUM 0x00000015 /* Set RX hw csum enable (ethtool_value) */ -#define ETHTOOL_GTXCSUM 0x00000016 /* Get TX hw csum enable (ethtool_value) */ -#define ETHTOOL_STXCSUM 0x00000017 /* Set TX hw csum enable (ethtool_value) */ -#define ETHTOOL_GSG 0x00000018 /* Get scatter-gather enable - * (ethtool_value) */ -#define ETHTOOL_SSG 0x00000019 /* Set scatter-gather enable - * (ethtool_value). */ -#define ETHTOOL_TEST 0x0000001a /* execute NIC self-test. */ -#define ETHTOOL_GSTRINGS 0x0000001b /* get specified string set */ -#define ETHTOOL_PHYS_ID 0x0000001c /* identify the NIC */ -#define ETHTOOL_GSTATS 0x0000001d /* get NIC-specific statistics */ -#define ETHTOOL_GTSO 0x0000001e /* Get TSO enable (ethtool_value) */ -#define ETHTOOL_STSO 0x0000001f /* Set TSO enable (ethtool_value) */ -#define ETHTOOL_GPERMADDR 0x00000020 /* Get permanent hardware address */ -#define ETHTOOL_GUFO 0x00000021 /* Get UFO enable (ethtool_value) */ -#define ETHTOOL_SUFO 0x00000022 /* Set UFO enable (ethtool_value) */ -#define ETHTOOL_GGSO 0x00000023 /* Get GSO enable (ethtool_value) */ -#define ETHTOOL_SGSO 0x00000024 /* Set GSO enable (ethtool_value) */ -#define ETHTOOL_GFLAGS 0x00000025 /* Get flags bitmap(ethtool_value) */ -#define ETHTOOL_SFLAGS 0x00000026 /* Set flags bitmap(ethtool_value) */ -#define ETHTOOL_GPFLAGS 0x00000027 /* Get driver-private flags bitmap */ -#define ETHTOOL_SPFLAGS 0x00000028 /* Set driver-private flags bitmap */ - -#define ETHTOOL_GRXFH 0x00000029 /* Get RX flow hash configuration */ -#define ETHTOOL_SRXFH 0x0000002a /* Set RX flow hash configuration */ -#define ETHTOOL_GGRO 0x0000002b /* Get GRO enable (ethtool_value) */ -#define ETHTOOL_SGRO 0x0000002c /* Set GRO enable (ethtool_value) */ -#define ETHTOOL_GRXRINGS 0x0000002d /* Get RX rings available for LB */ -#define ETHTOOL_GRXCLSRLCNT 0x0000002e /* Get RX class rule count */ -#define ETHTOOL_GRXCLSRULE 0x0000002f /* Get RX classification rule */ -#define ETHTOOL_GRXCLSRLALL 0x00000030 /* Get all RX classification rule */ -#define ETHTOOL_SRXCLSRLDEL 0x00000031 /* Delete RX classification rule */ -#define ETHTOOL_SRXCLSRLINS 0x00000032 /* Insert RX classification rule */ -#define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ -#define ETHTOOL_RESET 0x00000034 /* Reset hardware */ -#define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ -#define ETHTOOL_GRXNTUPLE 0x00000036 /* deprecated */ -#define ETHTOOL_GSSET_INFO 0x00000037 /* Get string set info */ -#define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */ -#define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */ - -#define ETHTOOL_GFEATURES 0x0000003a /* Get device offload settings */ -#define ETHTOOL_SFEATURES 0x0000003b /* Change device offload settings */ -#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */ -#define ETHTOOL_SCHANNELS 0x0000003d /* Set no of channels */ -#define ETHTOOL_SET_DUMP 0x0000003e /* Set dump settings */ -#define ETHTOOL_GET_DUMP_FLAG 0x0000003f /* Get dump settings */ -#define ETHTOOL_GET_DUMP_DATA 0x00000040 /* Get dump data */ -#define ETHTOOL_GET_TS_INFO 0x00000041 /* Get time stamping and PHC info */ -#define ETHTOOL_GMODULEINFO 0x00000042 /* Get plug-in module information */ -#define ETHTOOL_GMODULEEEPROM 0x00000043 /* Get plug-in module eeprom */ -#define ETHTOOL_GEEE 0x00000044 /* Get EEE settings */ -#define ETHTOOL_SEEE 0x00000045 /* Set EEE settings */ - -#define ETHTOOL_GRSSH 0x00000046 /* Get RX flow hash configuration */ -#define ETHTOOL_SRSSH 0x00000047 /* Set RX flow hash configuration */ -#define ETHTOOL_GTUNABLE 0x00000048 /* Get tunable configuration */ -#define ETHTOOL_STUNABLE 0x00000049 /* Set tunable configuration */ -#define ETHTOOL_GPHYSTATS 0x0000004a /* get PHY-specific statistics */ - -#define ETHTOOL_PERQUEUE 0x0000004b /* Set per queue options */ - -#define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */ -#define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ -#define ETHTOOL_PHY_GTUNABLE 0x0000004e /* Get PHY tunable configuration */ -#define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */ -#define ETHTOOL_GFECPARAM 0x00000050 /* Get FEC settings */ -#define ETHTOOL_SFECPARAM 0x00000051 /* Set FEC settings */ - -/* compatibility with older code */ -#define SPARC_ETH_GSET ETHTOOL_GSET -#define SPARC_ETH_SSET ETHTOOL_SSET - -/* Link mode bit indices */ -enum ethtool_link_mode_bit_indices { - ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0, - ETHTOOL_LINK_MODE_10baseT_Full_BIT = 1, - ETHTOOL_LINK_MODE_100baseT_Half_BIT = 2, - ETHTOOL_LINK_MODE_100baseT_Full_BIT = 3, - ETHTOOL_LINK_MODE_1000baseT_Half_BIT = 4, - ETHTOOL_LINK_MODE_1000baseT_Full_BIT = 5, - ETHTOOL_LINK_MODE_Autoneg_BIT = 6, - ETHTOOL_LINK_MODE_TP_BIT = 7, - ETHTOOL_LINK_MODE_AUI_BIT = 8, - ETHTOOL_LINK_MODE_MII_BIT = 9, - ETHTOOL_LINK_MODE_FIBRE_BIT = 10, - ETHTOOL_LINK_MODE_BNC_BIT = 11, - ETHTOOL_LINK_MODE_10000baseT_Full_BIT = 12, - ETHTOOL_LINK_MODE_Pause_BIT = 13, - ETHTOOL_LINK_MODE_Asym_Pause_BIT = 14, - ETHTOOL_LINK_MODE_2500baseX_Full_BIT = 15, - ETHTOOL_LINK_MODE_Backplane_BIT = 16, - ETHTOOL_LINK_MODE_1000baseKX_Full_BIT = 17, - ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT = 18, - ETHTOOL_LINK_MODE_10000baseKR_Full_BIT = 19, - ETHTOOL_LINK_MODE_10000baseR_FEC_BIT = 20, - ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21, - ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT = 22, - ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT = 23, - ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT = 24, - ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT = 25, - ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT = 26, - ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT = 27, - ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28, - ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29, - ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30, - ETHTOOL_LINK_MODE_25000baseCR_Full_BIT = 31, - - /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit - * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* - * macro for bits > 31. The only way to use indices > 31 is to - * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. - */ - - ETHTOOL_LINK_MODE_25000baseKR_Full_BIT = 32, - ETHTOOL_LINK_MODE_25000baseSR_Full_BIT = 33, - ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT = 34, - ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT = 35, - ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT = 36, - ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT = 37, - ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT = 38, - ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT = 39, - ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT = 40, - ETHTOOL_LINK_MODE_1000baseX_Full_BIT = 41, - ETHTOOL_LINK_MODE_10000baseCR_Full_BIT = 42, - ETHTOOL_LINK_MODE_10000baseSR_Full_BIT = 43, - ETHTOOL_LINK_MODE_10000baseLR_Full_BIT = 44, - ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT = 45, - ETHTOOL_LINK_MODE_10000baseER_Full_BIT = 46, - ETHTOOL_LINK_MODE_2500baseT_Full_BIT = 47, - ETHTOOL_LINK_MODE_5000baseT_Full_BIT = 48, - - ETHTOOL_LINK_MODE_FEC_NONE_BIT = 49, - ETHTOOL_LINK_MODE_FEC_RS_BIT = 50, - ETHTOOL_LINK_MODE_FEC_BASER_BIT = 51, - ETHTOOL_LINK_MODE_50000baseKR_Full_BIT = 52, - ETHTOOL_LINK_MODE_50000baseSR_Full_BIT = 53, - ETHTOOL_LINK_MODE_50000baseCR_Full_BIT = 54, - ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT = 55, - ETHTOOL_LINK_MODE_50000baseDR_Full_BIT = 56, - ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT = 57, - ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT = 58, - ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT = 59, - ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT = 60, - ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT = 61, - ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT = 62, - ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT = 63, - ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT = 64, - ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT = 65, - ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT = 66, - ETHTOOL_LINK_MODE_100baseT1_Full_BIT = 67, - ETHTOOL_LINK_MODE_1000baseT1_Full_BIT = 68, - ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT = 69, - ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT = 70, - ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT = 71, - ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT = 72, - ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT = 73, - ETHTOOL_LINK_MODE_FEC_LLRS_BIT = 74, - ETHTOOL_LINK_MODE_100000baseKR_Full_BIT = 75, - ETHTOOL_LINK_MODE_100000baseSR_Full_BIT = 76, - ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT = 77, - ETHTOOL_LINK_MODE_100000baseCR_Full_BIT = 78, - ETHTOOL_LINK_MODE_100000baseDR_Full_BIT = 79, - ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT = 80, - ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT = 81, - ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT = 82, - ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT = 83, - ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT = 84, - ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT = 85, - ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT = 86, - ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87, - ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT = 88, - ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, - ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, - ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, - ETHTOOL_LINK_MODE_10baseT1L_Full_BIT = 92, - ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT = 93, - ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT = 94, - ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT = 95, - ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT = 96, - ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT = 97, - ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT = 98, - ETHTOOL_LINK_MODE_10baseT1S_Full_BIT = 99, - ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, - ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, - - /* must be last entry */ - __ETHTOOL_LINK_MODE_MASK_NBITS -}; - -#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ - (1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT)) - -/* DEPRECATED macros. Please migrate to - * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT - * define any new SUPPORTED_* macro for bits > 31. - */ -#define SUPPORTED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) -#define SUPPORTED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) -#define SUPPORTED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) -#define SUPPORTED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) -#define SUPPORTED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) -#define SUPPORTED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) -#define SUPPORTED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) -#define SUPPORTED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) -#define SUPPORTED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) -#define SUPPORTED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) -#define SUPPORTED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) -#define SUPPORTED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) -#define SUPPORTED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) -#define SUPPORTED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) -#define SUPPORTED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) -#define SUPPORTED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) -#define SUPPORTED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) -#define SUPPORTED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) -#define SUPPORTED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) -#define SUPPORTED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) -#define SUPPORTED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) -#define SUPPORTED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) -#define SUPPORTED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) -#define SUPPORTED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) -#define SUPPORTED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) -#define SUPPORTED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) -#define SUPPORTED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) -#define SUPPORTED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) -#define SUPPORTED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) -#define SUPPORTED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) -#define SUPPORTED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) -/* Please do not define any new SUPPORTED_* macro for bits > 31, see - * notice above. - */ - -/* - * DEPRECATED macros. Please migrate to - * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT - * define any new ADERTISE_* macro for bits > 31. - */ -#define ADVERTISED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) -#define ADVERTISED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) -#define ADVERTISED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) -#define ADVERTISED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) -#define ADVERTISED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) -#define ADVERTISED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) -#define ADVERTISED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) -#define ADVERTISED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) -#define ADVERTISED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) -#define ADVERTISED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) -#define ADVERTISED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) -#define ADVERTISED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) -#define ADVERTISED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) -#define ADVERTISED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) -#define ADVERTISED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) -#define ADVERTISED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) -#define ADVERTISED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) -#define ADVERTISED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) -#define ADVERTISED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) -#define ADVERTISED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) -#define ADVERTISED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) -#define ADVERTISED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) -#define ADVERTISED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) -#define ADVERTISED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) -#define ADVERTISED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) -#define ADVERTISED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) -#define ADVERTISED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) -#define ADVERTISED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) -#define ADVERTISED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) -#define ADVERTISED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) -#define ADVERTISED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) -/* Please do not define any new ADVERTISED_* macro for bits > 31, see - * notice above. - */ - -/* The following are all involved in forcing a particular link - * mode for the device for setting things. When getting the - * devices settings, these indicate the current mode and whether - * it was forced up into this mode or autonegotiated. - */ - -/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal. - * Update drivers/net/phy/phy.c:phy_speed_to_str() and - * drivers/net/bonding/bond_3ad.c:__get_link_speed() when adding new values. - */ -#define SPEED_10 10 -#define SPEED_100 100 -#define SPEED_1000 1000 -#define SPEED_2500 2500 -#define SPEED_5000 5000 -#define SPEED_10000 10000 -#define SPEED_14000 14000 -#define SPEED_20000 20000 -#define SPEED_25000 25000 -#define SPEED_40000 40000 -#define SPEED_50000 50000 -#define SPEED_56000 56000 -#define SPEED_100000 100000 -#define SPEED_200000 200000 -#define SPEED_400000 400000 -#define SPEED_800000 800000 - -#define SPEED_UNKNOWN -1 - -static inline int ethtool_validate_speed(__u32 speed) -{ - return speed <= INT_MAX || speed == (__u32)SPEED_UNKNOWN; -} - -/* Duplex, half or full. */ -#define DUPLEX_HALF 0x00 -#define DUPLEX_FULL 0x01 -#define DUPLEX_UNKNOWN 0xff - -static inline int ethtool_validate_duplex(__u8 duplex) -{ - switch (duplex) { - case DUPLEX_HALF: - case DUPLEX_FULL: - case DUPLEX_UNKNOWN: - return 1; - } - - return 0; -} - -#define MASTER_SLAVE_CFG_UNSUPPORTED 0 -#define MASTER_SLAVE_CFG_UNKNOWN 1 -#define MASTER_SLAVE_CFG_MASTER_PREFERRED 2 -#define MASTER_SLAVE_CFG_SLAVE_PREFERRED 3 -#define MASTER_SLAVE_CFG_MASTER_FORCE 4 -#define MASTER_SLAVE_CFG_SLAVE_FORCE 5 -#define MASTER_SLAVE_STATE_UNSUPPORTED 0 -#define MASTER_SLAVE_STATE_UNKNOWN 1 -#define MASTER_SLAVE_STATE_MASTER 2 -#define MASTER_SLAVE_STATE_SLAVE 3 -#define MASTER_SLAVE_STATE_ERR 4 - -/* These are used to throttle the rate of data on the phy interface when the - * native speed of the interface is higher than the link speed. These should - * not be used for phy interfaces which natively support multiple speeds (e.g. - * MII or SGMII). - */ -/* No rate matching performed. */ -#define RATE_MATCH_NONE 0 -/* The phy sends pause frames to throttle the MAC. */ -#define RATE_MATCH_PAUSE 1 -/* The phy asserts CRS to prevent the MAC from transmitting. */ -#define RATE_MATCH_CRS 2 -/* The MAC is programmed with a sufficiently-large IPG. */ -#define RATE_MATCH_OPEN_LOOP 3 - -/* Which connector port. */ -#define PORT_TP 0x00 -#define PORT_AUI 0x01 -#define PORT_MII 0x02 -#define PORT_FIBRE 0x03 -#define PORT_BNC 0x04 -#define PORT_DA 0x05 -#define PORT_NONE 0xef -#define PORT_OTHER 0xff - -/* Which transceiver to use. */ -#define XCVR_INTERNAL 0x00 /* PHY and MAC are in the same package */ -#define XCVR_EXTERNAL 0x01 /* PHY and MAC are in different packages */ -#define XCVR_DUMMY1 0x02 -#define XCVR_DUMMY2 0x03 -#define XCVR_DUMMY3 0x04 - -/* Enable or disable autonegotiation. */ -#define AUTONEG_DISABLE 0x00 -#define AUTONEG_ENABLE 0x01 - -/* MDI or MDI-X status/control - if MDI/MDI_X/AUTO is set then - * the driver is required to renegotiate link - */ -#define ETH_TP_MDI_INVALID 0x00 /* status: unknown; control: unsupported */ -#define ETH_TP_MDI 0x01 /* status: MDI; control: force MDI */ -#define ETH_TP_MDI_X 0x02 /* status: MDI-X; control: force MDI-X */ -#define ETH_TP_MDI_AUTO 0x03 /* control: auto-select */ - -/* Wake-On-Lan options. */ -#define WAKE_PHY (1 << 0) -#define WAKE_UCAST (1 << 1) -#define WAKE_MCAST (1 << 2) -#define WAKE_BCAST (1 << 3) -#define WAKE_ARP (1 << 4) -#define WAKE_MAGIC (1 << 5) -#define WAKE_MAGICSECURE (1 << 6) /* only meaningful if WAKE_MAGIC */ -#define WAKE_FILTER (1 << 7) - -#define WOL_MODE_COUNT 8 - -/* RSS hash function data - * XOR the corresponding source and destination fields of each specified - * protocol. Both copies of the XOR'ed fields are fed into the RSS and RXHASH - * calculation. Note that this XORing reduces the input set entropy and could - * be exploited to reduce the RSS queue spread. - */ -#define RXH_XFRM_SYM_XOR (1 << 0) -#define RXH_XFRM_NO_CHANGE 0xff - -/* L2-L4 network traffic flow types */ -#define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ -#define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ -#define SCTP_V4_FLOW 0x03 /* hash or spec (sctp_ip4_spec) */ -#define AH_ESP_V4_FLOW 0x04 /* hash only */ -#define TCP_V6_FLOW 0x05 /* hash or spec (tcp_ip6_spec; nfc only) */ -#define UDP_V6_FLOW 0x06 /* hash or spec (udp_ip6_spec; nfc only) */ -#define SCTP_V6_FLOW 0x07 /* hash or spec (sctp_ip6_spec; nfc only) */ -#define AH_ESP_V6_FLOW 0x08 /* hash only */ -#define AH_V4_FLOW 0x09 /* hash or spec (ah_ip4_spec) */ -#define ESP_V4_FLOW 0x0a /* hash or spec (esp_ip4_spec) */ -#define AH_V6_FLOW 0x0b /* hash or spec (ah_ip6_spec; nfc only) */ -#define ESP_V6_FLOW 0x0c /* hash or spec (esp_ip6_spec; nfc only) */ -#define IPV4_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */ -#define IP_USER_FLOW IPV4_USER_FLOW -#define IPV6_USER_FLOW 0x0e /* spec only (usr_ip6_spec; nfc only) */ -#define IPV4_FLOW 0x10 /* hash only */ -#define IPV6_FLOW 0x11 /* hash only */ -#define ETHER_FLOW 0x12 /* spec only (ether_spec) */ - -/* Used for GTP-U IPv4 and IPv6. - * The format of GTP packets only includes - * elements such as TEID and GTP version. - * It is primarily intended for data communication of the UE. - */ -#define GTPU_V4_FLOW 0x13 /* hash only */ -#define GTPU_V6_FLOW 0x14 /* hash only */ - -/* Use for GTP-C IPv4 and v6. - * The format of these GTP packets does not include TEID. - * Primarily expected to be used for communication - * to create sessions for UE data communication, - * commonly referred to as CSR (Create Session Request). - */ -#define GTPC_V4_FLOW 0x15 /* hash only */ -#define GTPC_V6_FLOW 0x16 /* hash only */ - -/* Use for GTP-C IPv4 and v6. - * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. - * After session creation, it becomes this packet. - * This is mainly used for requests to realize UE handover. - */ -#define GTPC_TEID_V4_FLOW 0x17 /* hash only */ -#define GTPC_TEID_V6_FLOW 0x18 /* hash only */ - -/* Use for GTP-U and extended headers for the PSC (PDU Session Container). - * The format of these GTP packets includes TEID and QFI. - * In 5G communication using UPF (User Plane Function), - * data communication with this extended header is performed. - */ -#define GTPU_EH_V4_FLOW 0x19 /* hash only */ -#define GTPU_EH_V6_FLOW 0x1a /* hash only */ - -/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. - * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by - * UL/DL included in the PSC. - * There are differences in the data included based on Downlink/Uplink, - * and can be used to distinguish packets. - * The functions described so far are useful when you want to - * handle communication from the mobile network in UPF, PGW, etc. - */ -#define GTPU_UL_V4_FLOW 0x1b /* hash only */ -#define GTPU_UL_V6_FLOW 0x1c /* hash only */ -#define GTPU_DL_V4_FLOW 0x1d /* hash only */ -#define GTPU_DL_V6_FLOW 0x1e /* hash only */ - -/* Flag to enable additional fields in struct ethtool_rx_flow_spec */ -#define FLOW_EXT 0x80000000 -#define FLOW_MAC_EXT 0x40000000 -/* Flag to enable RSS spreading of traffic matching rule (nfc only) */ -#define FLOW_RSS 0x20000000 - -/* L3-L4 network traffic flow hash options */ -#define RXH_L2DA (1 << 1) -#define RXH_VLAN (1 << 2) -#define RXH_L3_PROTO (1 << 3) -#define RXH_IP_SRC (1 << 4) -#define RXH_IP_DST (1 << 5) -#define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ -#define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ -#define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */ -#define RXH_DISCARD (1 << 31) - -#define RX_CLS_FLOW_DISC 0xffffffffffffffffULL -#define RX_CLS_FLOW_WAKE 0xfffffffffffffffeULL - -/* Special RX classification rule insert location values */ -#define RX_CLS_LOC_SPECIAL 0x80000000 /* flag */ -#define RX_CLS_LOC_ANY 0xffffffff -#define RX_CLS_LOC_FIRST 0xfffffffe -#define RX_CLS_LOC_LAST 0xfffffffd - -/* EEPROM Standards for plug in modules */ -#define ETH_MODULE_SFF_8079 0x1 -#define ETH_MODULE_SFF_8079_LEN 256 -#define ETH_MODULE_SFF_8472 0x2 -#define ETH_MODULE_SFF_8472_LEN 512 -#define ETH_MODULE_SFF_8636 0x3 -#define ETH_MODULE_SFF_8636_LEN 256 -#define ETH_MODULE_SFF_8436 0x4 -#define ETH_MODULE_SFF_8436_LEN 256 - -#define ETH_MODULE_SFF_8636_MAX_LEN 640 -#define ETH_MODULE_SFF_8436_MAX_LEN 640 - -/* Reset flags */ -/* The reset() operation must clear the flags for the components which - * were actually reset. On successful return, the flags indicate the - * components which were not reset, either because they do not exist - * in the hardware or because they cannot be reset independently. The - * driver must never reset any components that were not requested. - */ -enum ethtool_reset_flags { - /* These flags represent components dedicated to the interface - * the command is addressed to. Shift any flag left by - * ETH_RESET_SHARED_SHIFT to reset a shared component of the - * same type. - */ - ETH_RESET_MGMT = 1 << 0, /* Management processor */ - ETH_RESET_IRQ = 1 << 1, /* Interrupt requester */ - ETH_RESET_DMA = 1 << 2, /* DMA engine */ - ETH_RESET_FILTER = 1 << 3, /* Filtering/flow direction */ - ETH_RESET_OFFLOAD = 1 << 4, /* Protocol offload */ - ETH_RESET_MAC = 1 << 5, /* Media access controller */ - ETH_RESET_PHY = 1 << 6, /* Transceiver/PHY */ - ETH_RESET_RAM = 1 << 7, /* RAM shared between - * multiple components */ - ETH_RESET_AP = 1 << 8, /* Application processor */ - - ETH_RESET_DEDICATED = 0x0000ffff, /* All components dedicated to - * this interface */ - ETH_RESET_ALL = 0xffffffff, /* All components used by this - * interface, even if shared */ -}; -#define ETH_RESET_SHARED_SHIFT 16 - - -/** - * struct ethtool_link_settings - link control and status - * - * IMPORTANT, Backward compatibility notice: When implementing new - * user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and - * if it succeeds use %ETHTOOL_SLINKSETTINGS to change link - * settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS - * succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in - * that case. Conversely, if %ETHTOOL_GLINKSETTINGS fails, use - * %ETHTOOL_GSET to query and %ETHTOOL_SSET to change link - * settings; do not use %ETHTOOL_SLINKSETTINGS if - * %ETHTOOL_GLINKSETTINGS failed: stick to - * %ETHTOOL_GSET/%ETHTOOL_SSET in that case. - * - * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS - * @speed: Link speed (Mbps) - * @duplex: Duplex mode; one of %DUPLEX_* - * @port: Physical connector type; one of %PORT_* - * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not - * applicable. For clause 45 PHYs this is the PRTAD. - * @autoneg: Enable/disable autonegotiation and auto-detection; - * either %AUTONEG_DISABLE or %AUTONEG_ENABLE - * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO - * protocols supported by the interface; 0 if unknown. - * Read-only. - * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of - * %ETH_TP_MDI_*. If the status is unknown or not applicable, the - * value will be %ETH_TP_MDI_INVALID. Read-only. - * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of - * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads - * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. - * When written successfully, the link should be renegotiated if - * necessary. - * @link_mode_masks_nwords: Number of 32-bit words for each of the - * supported, advertising, lp_advertising link mode bitmaps. For - * %ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user - * (>= 0); on return, if handshake in progress, negative if - * request size unsupported by kernel: absolute value indicates - * kernel expected size and all the other fields but cmd - * are 0; otherwise (handshake completed), strictly positive - * to indicate size used by kernel and cmd field stays - * %ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For - * %ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive - * value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise - * refused. For drivers: ignore this field (use kernel's - * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will - * be overwritten by kernel. - * @transceiver: Used to distinguish different possible PHY types, - * reported consistently by PHYLIB. Read-only. - * @master_slave_cfg: Master/slave port mode. - * @master_slave_state: Master/slave port state. - * @rate_matching: Rate adaptation performed by the PHY - * @reserved: Reserved for future use; see the note on reserved space. - * @link_mode_masks: Variable length bitmaps. - * - * If autonegotiation is disabled, the speed and @duplex represent the - * fixed link mode and are writable if the driver supports multiple - * link modes. If it is enabled then they are read-only; if the link - * is up they represent the negotiated link mode; if the link is down, - * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and - * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. - * - * Some hardware interfaces may have multiple PHYs and/or physical - * connectors fitted or do not allow the driver to detect which are - * fitted. For these interfaces @port and/or @phy_address may be - * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. - * Otherwise, attempts to write different values may be ignored or - * rejected. - * - * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt - * are not available in %ethtool_link_settings. These fields will be - * always set to zero in %ETHTOOL_GSET reply and %ETHTOOL_SSET will - * fail if any of them is set to non-zero value. - * - * Users should assume that all fields not marked read-only are - * writable and subject to validation by the driver. They should use - * %ETHTOOL_GLINKSETTINGS to get the current values before making specific - * changes and then applying them with %ETHTOOL_SLINKSETTINGS. - * - * Drivers that implement %get_link_ksettings and/or - * %set_link_ksettings should ignore the @cmd - * and @link_mode_masks_nwords fields (any change to them overwritten - * by kernel), and rely only on kernel's internal - * %__ETHTOOL_LINK_MODE_MASK_NBITS and - * %ethtool_link_mode_mask_t. Drivers that implement - * %set_link_ksettings() should validate all fields other than @cmd - * and @link_mode_masks_nwords that are not described as read-only or - * deprecated, and must ignore all fields described as read-only. - * - * @link_mode_masks is divided into three bitfields, each of length - * @link_mode_masks_nwords: - * - supported: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, physical - * connectors and other link features for which the interface - * supports autonegotiation or auto-detection. Read-only. - * - advertising: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, physical - * connectors and other link features that are advertised through - * autonegotiation or enabled for auto-detection. - * - lp_advertising: Bitmap with each bit meaning given by - * %ethtool_link_mode_bit_indices for the link modes, and other - * link features that the link partner advertised through - * autonegotiation; 0 if unknown or not applicable. Read-only. - */ -struct ethtool_link_settings { - __u32 cmd; - __u32 speed; - __u8 duplex; - __u8 port; - __u8 phy_address; - __u8 autoneg; - __u8 mdio_support; - __u8 eth_tp_mdix; - __u8 eth_tp_mdix_ctrl; - __s8 link_mode_masks_nwords; - __u8 transceiver; - __u8 master_slave_cfg; - __u8 master_slave_state; - __u8 rate_matching; - __u32 reserved[7]; - __u32 link_mode_masks[]; - /* layout of link_mode_masks fields: - * __u32 map_supported[link_mode_masks_nwords]; - * __u32 map_advertising[link_mode_masks_nwords]; - * __u32 map_lp_advertising[link_mode_masks_nwords]; - */ -}; -#endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index c9f4e04f38fe..466a29d80124 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -766,6 +766,7 @@ int bpf_link_create(int prog_fd, int target_fd, return libbpf_err(-EINVAL); break; case BPF_TRACE_KPROBE_MULTI: + case BPF_TRACE_KPROBE_SESSION: attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0); attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0); attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0)); diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index b5c7ce5c243a..c0e13cdf9660 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -104,6 +104,7 @@ enum bpf_enum_value_kind { case 2: val = *(const unsigned short *)p; break; \ case 4: val = *(const unsigned int *)p; break; \ case 8: val = *(const unsigned long long *)p; break; \ + default: val = 0; break; \ } \ val <<= __CORE_RELO(s, field, LSHIFT_U64); \ if (__CORE_RELO(s, field, SIGNED)) \ diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 62e1c0cc4a59..305c62817dd3 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -186,10 +186,21 @@ enum libbpf_tristate { #define __kptr __attribute__((btf_type_tag("kptr"))) #define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr"))) -#define bpf_ksym_exists(sym) ({ \ - _Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak"); \ - !!sym; \ +#if defined (__clang__) +#define bpf_ksym_exists(sym) ({ \ + _Static_assert(!__builtin_constant_p(!!sym), \ + #sym " should be marked as __weak"); \ + !!sym; \ }) +#elif __GNUC__ > 8 +#define bpf_ksym_exists(sym) ({ \ + _Static_assert(__builtin_has_attribute (*sym, __weak__), \ + #sym " should be marked as __weak"); \ + !!sym; \ +}) +#else +#define bpf_ksym_exists(sym) !!sym +#endif #define __arg_ctx __attribute__((btf_decl_tag("arg:ctx"))) #define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull"))) diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 1c13f8e88833..9314fa95f04e 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -633,18 +633,18 @@ struct pt_regs; #endif #define ___bpf_ctx_cast0() ctx -#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] -#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] -#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] -#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] -#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] -#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] -#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] -#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] -#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] -#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] -#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] -#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] +#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), ctx[8] +#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), ctx[9] +#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), ctx[10] +#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), ctx[11] #define ___bpf_ctx_cast(args...) ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) /* @@ -786,14 +786,14 @@ ____##name(unsigned long long *ctx ___bpf_ctx_decl(args)) struct pt_regs; #define ___bpf_kprobe_args0() ctx -#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) -#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) -#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) -#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) -#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) -#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(ctx) -#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (void *)PT_REGS_PARM7(ctx) -#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (void *)PT_REGS_PARM8(ctx) +#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (unsigned long long)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (unsigned long long)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (unsigned long long)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (unsigned long long)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (unsigned long long)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (unsigned long long)PT_REGS_PARM6(ctx) +#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (unsigned long long)PT_REGS_PARM7(ctx) +#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (unsigned long long)PT_REGS_PARM8(ctx) #define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) /* @@ -821,7 +821,7 @@ static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args) #define ___bpf_kretprobe_args0() ctx -#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) +#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (unsigned long long)PT_REGS_RC(ctx) #define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) /* @@ -845,24 +845,24 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) /* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */ #define ___bpf_syscall_args0() ctx -#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs) -#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs) -#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs) -#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs) -#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs) -#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_SYSCALL(regs) -#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (void *)PT_REGS_PARM7_SYSCALL(regs) +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (unsigned long long)PT_REGS_PARM1_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (unsigned long long)PT_REGS_PARM2_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (unsigned long long)PT_REGS_PARM3_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (unsigned long long)PT_REGS_PARM4_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (unsigned long long)PT_REGS_PARM5_SYSCALL(regs) +#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (unsigned long long)PT_REGS_PARM6_SYSCALL(regs) +#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (unsigned long long)PT_REGS_PARM7_SYSCALL(regs) #define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) /* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */ #define ___bpf_syswrap_args0() ctx -#define ___bpf_syswrap_args1(x) ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (void *)PT_REGS_PARM7_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args1(x) ___bpf_syswrap_args0(), (unsigned long long)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (unsigned long long)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (unsigned long long)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (unsigned long long)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (unsigned long long)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (unsigned long long)PT_REGS_PARM6_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (unsigned long long)PT_REGS_PARM7_CORE_SYSCALL(regs) #define ___bpf_syswrap_args(args...) ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args) /* diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 97eb6e5dd7c8..5401f2df463d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -132,6 +132,7 @@ static const char * const attach_type_name[] = { [BPF_TRACE_UPROBE_MULTI] = "trace_uprobe_multi", [BPF_NETKIT_PRIMARY] = "netkit_primary", [BPF_NETKIT_PEER] = "netkit_peer", + [BPF_TRACE_KPROBE_SESSION] = "trace_kprobe_session", }; static const char * const link_type_name[] = { @@ -1127,6 +1128,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) const struct btf_type *mtype, *kern_mtype; __u32 mtype_id, kern_mtype_id; void *mdata, *kern_mdata; + struct bpf_program *prog; __s64 msize, kern_msize; __u32 moff, kern_moff; __u32 kern_member_idx; @@ -1144,18 +1146,28 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) kern_member = find_member_by_name(kern_btf, kern_type, mname); if (!kern_member) { - /* Skip all zeros or null fields if they are not - * presented in the kernel BTF. - */ - if (libbpf_is_mem_zeroed(mdata, msize)) { - pr_info("struct_ops %s: member %s not found in kernel, skipping it as it's set to zero\n", + if (!libbpf_is_mem_zeroed(mdata, msize)) { + pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", map->name, mname); - continue; + return -ENOTSUP; } - pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", + if (st_ops->progs[i]) { + /* If we had declaratively set struct_ops callback, we need to + * force its autoload to false, because it doesn't have + * a chance of succeeding from POV of the current struct_ops map. + * If this program is still referenced somewhere else, though, + * then bpf_object_adjust_struct_ops_autoload() will update its + * autoload accordingly. + */ + st_ops->progs[i]->autoload = false; + st_ops->progs[i] = NULL; + } + + /* Skip all-zero/NULL fields if they are not present in the kernel BTF */ + pr_info("struct_ops %s: member %s not found in kernel, skipping it as it's set to zero\n", map->name, mname); - return -ENOTSUP; + continue; } kern_member_idx = kern_member - btf_members(kern_type); @@ -1181,13 +1193,19 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) } if (btf_is_ptr(mtype)) { - struct bpf_program *prog; + prog = *(void **)mdata; + /* just like for !kern_member case above, reset declaratively + * set (at compile time) program's autload to false, + * if user replaced it with another program or NULL + */ + if (st_ops->progs[i] && st_ops->progs[i] != prog) + st_ops->progs[i]->autoload = false; /* Update the value from the shadow type */ - prog = *(void **)mdata; st_ops->progs[i] = prog; if (!prog) continue; + if (!is_valid_st_ops_program(obj, prog)) { pr_warn("struct_ops init_kern %s: member %s is not a struct_ops program\n", map->name, mname); @@ -7354,7 +7372,11 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog __u32 log_level = prog->log_level; int ret, err; - if (prog->type == BPF_PROG_TYPE_UNSPEC) { + /* Be more helpful by rejecting programs that can't be validated early + * with more meaningful and actionable error message. + */ + switch (prog->type) { + case BPF_PROG_TYPE_UNSPEC: /* * The program type must be set. Most likely we couldn't find a proper * section definition at load time, and thus we didn't infer the type. @@ -7362,6 +7384,15 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog pr_warn("prog '%s': missing BPF prog type, check ELF section name '%s'\n", prog->name, prog->sec_name); return -EINVAL; + case BPF_PROG_TYPE_STRUCT_OPS: + if (prog->attach_btf_id == 0) { + pr_warn("prog '%s': SEC(\"struct_ops\") program isn't referenced anywhere, did you forget to use it?\n", + prog->name); + return -EINVAL; + } + break; + default: + break; } if (!insns || !insns_cnt) @@ -9272,6 +9303,7 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_kprobe_session(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); @@ -9288,6 +9320,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("uretprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), SEC_DEF("kprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("kretprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("kprobe.session+", KPROBE, BPF_TRACE_KPROBE_SESSION, SEC_NONE, attach_kprobe_session), SEC_DEF("uprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), SEC_DEF("uretprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), SEC_DEF("uprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), @@ -9858,16 +9891,28 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, enum bpf_attach_type attach_type, int *btf_obj_fd, int *btf_type_id) { - int ret, i; + int ret, i, mod_len; + const char *fn_name, *mod_name = NULL; - ret = find_attach_btf_id(obj->btf_vmlinux, attach_name, attach_type); - if (ret > 0) { - *btf_obj_fd = 0; /* vmlinux BTF */ - *btf_type_id = ret; - return 0; + fn_name = strchr(attach_name, ':'); + if (fn_name) { + mod_name = attach_name; + mod_len = fn_name - mod_name; + fn_name++; + } + + if (!mod_name || strncmp(mod_name, "vmlinux", mod_len) == 0) { + ret = find_attach_btf_id(obj->btf_vmlinux, + mod_name ? fn_name : attach_name, + attach_type); + if (ret > 0) { + *btf_obj_fd = 0; /* vmlinux BTF */ + *btf_type_id = ret; + return 0; + } + if (ret != -ENOENT) + return ret; } - if (ret != -ENOENT) - return ret; ret = load_module_btfs(obj); if (ret) @@ -9876,7 +9921,12 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, for (i = 0; i < obj->btf_module_cnt; i++) { const struct module_btf *mod = &obj->btf_modules[i]; - ret = find_attach_btf_id(mod->btf, attach_name, attach_type); + if (mod_name && strncmp(mod->name, mod_name, mod_len) != 0) + continue; + + ret = find_attach_btf_id(mod->btf, + mod_name ? fn_name : attach_name, + attach_type); if (ret > 0) { *btf_obj_fd = mod->fd; *btf_type_id = ret; @@ -11380,13 +11430,14 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, struct kprobe_multi_resolve res = { .pattern = pattern, }; + enum bpf_attach_type attach_type; struct bpf_link *link = NULL; char errmsg[STRERR_BUFSIZE]; const unsigned long *addrs; int err, link_fd, prog_fd; + bool retprobe, session; const __u64 *cookies; const char **syms; - bool retprobe; size_t cnt; if (!OPTS_VALID(opts, bpf_kprobe_multi_opts)) @@ -11425,6 +11476,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, } retprobe = OPTS_GET(opts, retprobe, false); + session = OPTS_GET(opts, session, false); + + if (retprobe && session) + return libbpf_err_ptr(-EINVAL); + + attach_type = session ? BPF_TRACE_KPROBE_SESSION : BPF_TRACE_KPROBE_MULTI; lopts.kprobe_multi.syms = syms; lopts.kprobe_multi.addrs = addrs; @@ -11439,7 +11496,7 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, } link->detach = &bpf_link__detach_fd; - link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts); + link_fd = bpf_link_create(prog_fd, 0, attach_type, &lopts); if (link_fd < 0) { err = -errno; pr_warn("prog '%s': failed to attach: %s\n", @@ -11536,7 +11593,7 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); if (n < 1) { - pr_warn("kprobe multi pattern is invalid: %s\n", pattern); + pr_warn("kprobe multi pattern is invalid: %s\n", spec); return -EINVAL; } @@ -11545,6 +11602,32 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru return libbpf_get_error(*link); } +static int attach_kprobe_session(const struct bpf_program *prog, long cookie, + struct bpf_link **link) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts, .session = true); + const char *spec; + char *pattern; + int n; + + *link = NULL; + + /* no auto-attach for SEC("kprobe.session") */ + if (strcmp(prog->sec_name, "kprobe.session") == 0) + return 0; + + spec = prog->sec_name + sizeof("kprobe.session/") - 1; + n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); + if (n < 1) { + pr_warn("kprobe session pattern is invalid: %s\n", spec); + return -EINVAL; + } + + *link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts); + free(pattern); + return *link ? 0 : -errno; +} + static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) { char *probe_type = NULL, *binary_path = NULL, *func_name = NULL; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 1333ae20ebe6..c3f77d9260fe 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -539,10 +539,12 @@ struct bpf_kprobe_multi_opts { size_t cnt; /* create return kprobes */ bool retprobe; + /* create session kprobes */ + bool session; size_t :0; }; -#define bpf_kprobe_multi_opts__last_field retprobe +#define bpf_kprobe_multi_opts__last_field session LIBBPF_API struct bpf_link * bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 99e44cf02321..bfd8dac4c0cc 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -301,7 +301,7 @@ int ring_buffer__consume_n(struct ring_buffer *rb, size_t n) if (n == 0) break; } - return res; + return res > INT_MAX ? INT_MAX : res; } /* Consume available ring buffer(s) data without event polling. @@ -405,7 +405,7 @@ int ring__map_fd(const struct ring *r) int ring__consume_n(struct ring *r, size_t n) { - int res; + int64_t res; res = ringbuf_process_ring(r, n); if (res < 0) diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c index 146da01979c7..5e6a1e27ddf9 100644 --- a/tools/lib/bpf/str_error.c +++ b/tools/lib/bpf/str_error.c @@ -2,6 +2,7 @@ #undef _GNU_SOURCE #include #include +#include #include "str_error.h" /* make sure libbpf doesn't use kernel-only integer typedefs */ @@ -15,7 +16,18 @@ char *libbpf_strerror_r(int err, char *dst, int len) { int ret = strerror_r(err < 0 ? -err : err, dst, len); - if (ret) - snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + /* on glibc <2.13, ret == -1 and errno is set, if strerror_r() can't + * handle the error, on glibc >=2.13 *positive* (errno-like) error + * code is returned directly + */ + if (ret == -1) + ret = errno; + if (ret) { + if (ret == EINVAL) + /* strerror_r() doesn't recognize this specific error */ + snprintf(dst, len, "unknown error (%d)", err < 0 ? err : -err); + else + snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + } return dst; } diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index f6763300b26a..76359bcdc94a 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -214,18 +214,18 @@ long bpf_usdt_cookie(struct pt_regs *ctx) /* we rely on ___bpf_apply() and ___bpf_narg() macros already defined in bpf_tracing.h */ #define ___bpf_usdt_args0() ctx -#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); (void *)_x; }) -#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); (void *)_x; }) -#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; }) -#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; }) -#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; }) -#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; }) -#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; }) -#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; }) -#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; }) -#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; }) -#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; }) -#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; }) +#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); _x; }) +#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); _x; }) +#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); _x; }) +#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); _x; }) +#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); _x; }) +#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); _x; }) +#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); _x; }) +#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); _x; }) +#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); _x; }) +#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); _x; }) +#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); _x; }) +#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); _x; }) #define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args) /* diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index f1aebabfb017..5025401323af 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -17,7 +17,6 @@ test_dev_cgroup test_verifier_log feature test_sock -test_sock_addr urandom_read test_sockmap test_lirc_mode2_user diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index cf657fc35619..0445ac38bc07 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -10,4 +10,3 @@ fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_mu fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95 missed/kprobe_recursion # missed_kprobe_recursion__attach unexpected error: -95 (errno 95) -arena_atomics diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 82247aeef857..e0b3887b3d2d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -53,6 +53,7 @@ progs/syscall.c-CFLAGS := -fno-strict-aliasing progs/test_pkt_md_access.c-CFLAGS := -fno-strict-aliasing progs/test_sk_lookup.c-CFLAGS := -fno-strict-aliasing progs/timer_crash.c-CFLAGS := -fno-strict-aliasing +progs/test_global_func9.c-CFLAGS := -fno-strict-aliasing ifneq ($(LLVM),) # Silence some warnings when compiled with clang @@ -81,11 +82,24 @@ TEST_INST_SUBDIRS += bpf_gcc # The following tests contain C code that, although technically legal, # triggers GCC warnings that cannot be disabled: declaration of # anonymous struct types in function parameter lists. -progs/btf_dump_test_case_bitfields.c-CFLAGS := -Wno-error -progs/btf_dump_test_case_namespacing.c-CFLAGS := -Wno-error -progs/btf_dump_test_case_packing.c-CFLAGS := -Wno-error -progs/btf_dump_test_case_padding.c-CFLAGS := -Wno-error -progs/btf_dump_test_case_syntax.c-CFLAGS := -Wno-error +progs/btf_dump_test_case_bitfields.c-bpf_gcc-CFLAGS := -Wno-error +progs/btf_dump_test_case_namespacing.c-bpf_gcc-CFLAGS := -Wno-error +progs/btf_dump_test_case_packing.c-bpf_gcc-CFLAGS := -Wno-error +progs/btf_dump_test_case_padding.c-bpf_gcc-CFLAGS := -Wno-error +progs/btf_dump_test_case_syntax.c-bpf_gcc-CFLAGS := -Wno-error + +# The following tests do type-punning, via the __imm_insn macro, from +# `struct bpf_insn' to long and then uses the value. This triggers an +# "is used uninitialized" warning in GCC due to strict-aliasing +# rules. +progs/verifier_ref_tracking.c-bpf_gcc-CFLAGS := -fno-strict-aliasing +progs/verifier_unpriv.c-bpf_gcc-CFLAGS := -fno-strict-aliasing +progs/verifier_cgroup_storage.c-bpf_gcc-CFLAGS := -fno-strict-aliasing +progs/verifier_ld_ind.c-bpf_gcc-CFLAGS := -fno-strict-aliasing +progs/verifier_map_ret_val.c-bpf_gcc-CFLAGS := -fno-strict-aliasing +progs/verifier_spill_fill.c-bpf_gcc-CFLAGS := -fno-strict-aliasing +progs/verifier_subprog_precision.c-bpf_gcc-CFLAGS := -fno-strict-aliasing +progs/verifier_uninit.c-bpf_gcc-CFLAGS := -fno-strict-aliasing endif ifneq ($(CLANG_CPUV4),) @@ -102,7 +116,6 @@ TEST_PROGS := test_kmod.sh \ test_xdp_redirect_multi.sh \ test_xdp_meta.sh \ test_xdp_veth.sh \ - test_sock_addr.sh \ test_tunnel.sh \ test_lwt_seg6local.sh \ test_lirc_mode2.sh \ @@ -127,7 +140,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \ test_xdp_vlan.sh test_bpftool.py # Compile but not part of 'make run_tests' -TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ +TEST_GEN_PROGS_EXTENDED = test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ @@ -262,7 +275,7 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ - BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ + BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf/ \ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) \ EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS)' \ EXTRA_LDFLAGS='$(SAN_LDFLAGS)' && \ @@ -283,7 +296,6 @@ NETWORK_HELPERS := $(OUTPUT)/network_helpers.o $(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_sock: $(CGROUP_HELPERS) $(TESTING_HELPERS) -$(OUTPUT)/test_sock_addr: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(NETWORK_HELPERS) $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS) $(OUTPUT)/get_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) @@ -297,6 +309,7 @@ $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) $(OUTPUT)/test_maps: $(TESTING_HELPERS) $(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) $(UNPRIV_HELPERS) $(OUTPUT)/xsk.o: $(BPFOBJ) +$(OUTPUT)/test_tcp_check_syncookie_user: $(NETWORK_HELPERS) BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ @@ -431,7 +444,7 @@ endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2) - $(Q)$(BPF_GCC) $3 -O2 -c $1 -o $2 + $(Q)$(BPF_GCC) $3 -DBPF_NO_PRESERVE_ACCESS_INDEX -Wno-attributes -O2 -c $1 -o $2 endef SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c @@ -470,7 +483,7 @@ LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(ske # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES. # Parameters: # $1 - test runner base binary name (e.g., test_progs) -# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc) +# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, bpf_gcc, etc) define DEFINE_TEST_RUNNER TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2 @@ -498,7 +511,7 @@ endef # Using TRUNNER_XXX variables, provided by callers of DEFINE_TEST_RUNNER and # set up by DEFINE_TEST_RUNNER itself, create test runner build rules with: # $1 - test runner base binary name (e.g., test_progs) -# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, gcc-bpf, etc) +# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, bpf_gcc, etc) define DEFINE_TEST_RUNNER_RULES ifeq ($($(TRUNNER_OUTPUT)-dir),) @@ -521,7 +534,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.bpf.o: \ | $(TRUNNER_OUTPUT) $$(BPFOBJ) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS) \ - $$($$<-CFLAGS)) + $$($$<-CFLAGS) \ + $$($$<-$2-CFLAGS)) $(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) diff --git a/tools/testing/selftests/bpf/bpf_arena_list.h b/tools/testing/selftests/bpf/bpf_arena_list.h index b99b9f408eff..85dbc3ea4da5 100644 --- a/tools/testing/selftests/bpf/bpf_arena_list.h +++ b/tools/testing/selftests/bpf/bpf_arena_list.h @@ -29,6 +29,7 @@ static inline void *bpf_iter_num_new(struct bpf_iter_num *it, int i, int j) { re static inline void bpf_iter_num_destroy(struct bpf_iter_num *it) {} static inline bool bpf_iter_num_next(struct bpf_iter_num *it) { return true; } #define cond_break ({}) +#define can_loop true #endif /* Safely walk link list elements. Deletion of elements is allowed. */ @@ -36,8 +37,7 @@ static inline bool bpf_iter_num_next(struct bpf_iter_num *it) { return true; } for (void * ___tmp = (pos = list_entry_safe((head)->first, \ typeof(*(pos)), member), \ (void *)0); \ - pos && ({ ___tmp = (void *)pos->member.next; 1; }); \ - cond_break, \ + pos && ({ ___tmp = (void *)pos->member.next; 1; }) && can_loop; \ pos = list_entry_safe((void __arena *)___tmp, typeof(*(pos)), member)) static inline void list_add_head(arena_list_node_t *n, arena_list_head_t *h) diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 8b9cc87be4c4..3d9e4b8c6b81 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -326,19 +326,48 @@ l_true: \ }) #endif +/* + * Note that cond_break can only be portably used in the body of a breakable + * construct, whereas can_loop can be used anywhere. + */ #ifdef __BPF_FEATURE_MAY_GOTO +#define can_loop \ + ({ __label__ l_break, l_continue; \ + bool ret = true; \ + asm volatile goto("may_goto %l[l_break]" \ + :::: l_break); \ + goto l_continue; \ + l_break: ret = false; \ + l_continue:; \ + ret; \ + }) + #define cond_break \ ({ __label__ l_break, l_continue; \ - asm volatile goto("may_goto %l[l_break]" \ + asm volatile goto("may_goto %l[l_break]" \ :::: l_break); \ goto l_continue; \ l_break: break; \ l_continue:; \ }) #else +#define can_loop \ + ({ __label__ l_break, l_continue; \ + bool ret = true; \ + asm volatile goto("1:.byte 0xe5; \ + .byte 0; \ + .long ((%l[l_break] - 1b - 8) / 8) & 0xffff; \ + .short 0" \ + :::: l_break); \ + goto l_continue; \ + l_break: ret = false; \ + l_continue:; \ + ret; \ + }) + #define cond_break \ ({ __label__ l_break, l_continue; \ - asm volatile goto("1:.byte 0xe5; \ + asm volatile goto("1:.byte 0xe5; \ .byte 0; \ .long ((%l[l_break] - 1b - 8) / 8) & 0xffff; \ .short 0" \ diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 14ebe7d9e1a3..be91a6919315 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -75,4 +75,7 @@ extern void bpf_key_put(struct bpf_key *key) __ksym; extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr, struct bpf_dynptr *sig_ptr, struct bpf_key *trusted_keyring) __ksym; + +extern bool bpf_session_is_return(void) __ksym __weak; +extern long *bpf_session_cookie(void) __ksym __weak; #endif diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h deleted file mode 100644 index 82a7c9de95f9..000000000000 --- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h +++ /dev/null @@ -1,241 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __BPF_TCP_HELPERS_H -#define __BPF_TCP_HELPERS_H - -#include -#include -#include -#include -#include - -#define BPF_STRUCT_OPS(name, args...) \ -SEC("struct_ops/"#name) \ -BPF_PROG(name, args) - -#ifndef SOL_TCP -#define SOL_TCP 6 -#endif - -#ifndef TCP_CA_NAME_MAX -#define TCP_CA_NAME_MAX 16 -#endif - -#define tcp_jiffies32 ((__u32)bpf_jiffies64()) - -struct sock_common { - unsigned char skc_state; - __u16 skc_num; -} __attribute__((preserve_access_index)); - -enum sk_pacing { - SK_PACING_NONE = 0, - SK_PACING_NEEDED = 1, - SK_PACING_FQ = 2, -}; - -struct sock { - struct sock_common __sk_common; -#define sk_state __sk_common.skc_state - unsigned long sk_pacing_rate; - __u32 sk_pacing_status; /* see enum sk_pacing */ -} __attribute__((preserve_access_index)); - -struct inet_sock { - struct sock sk; -} __attribute__((preserve_access_index)); - -struct inet_connection_sock { - struct inet_sock icsk_inet; - __u8 icsk_ca_state:6, - icsk_ca_setsockopt:1, - icsk_ca_dst_locked:1; - struct { - __u8 pending; - } icsk_ack; - __u64 icsk_ca_priv[104 / sizeof(__u64)]; -} __attribute__((preserve_access_index)); - -struct request_sock { - struct sock_common __req_common; -} __attribute__((preserve_access_index)); - -struct tcp_sock { - struct inet_connection_sock inet_conn; - - __u32 rcv_nxt; - __u32 snd_nxt; - __u32 snd_una; - __u32 window_clamp; - __u8 ecn_flags; - __u32 delivered; - __u32 delivered_ce; - __u32 snd_cwnd; - __u32 snd_cwnd_cnt; - __u32 snd_cwnd_clamp; - __u32 snd_ssthresh; - __u8 syn_data:1, /* SYN includes data */ - syn_fastopen:1, /* SYN includes Fast Open option */ - syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ - syn_fastopen_ch:1, /* Active TFO re-enabling probe */ - syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ - save_syn:1, /* Save headers of SYN packet */ - is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ - syn_smc:1; /* SYN includes SMC */ - __u32 max_packets_out; - __u32 lsndtime; - __u32 prior_cwnd; - __u64 tcp_mstamp; /* most recent packet received/sent */ - bool is_mptcp; -} __attribute__((preserve_access_index)); - -static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk) -{ - return (struct inet_connection_sock *)sk; -} - -static __always_inline void *inet_csk_ca(const struct sock *sk) -{ - return (void *)inet_csk(sk)->icsk_ca_priv; -} - -static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk) -{ - return (struct tcp_sock *)sk; -} - -static __always_inline bool before(__u32 seq1, __u32 seq2) -{ - return (__s32)(seq1-seq2) < 0; -} -#define after(seq2, seq1) before(seq1, seq2) - -#define TCP_ECN_OK 1 -#define TCP_ECN_QUEUE_CWR 2 -#define TCP_ECN_DEMAND_CWR 4 -#define TCP_ECN_SEEN 8 - -enum inet_csk_ack_state_t { - ICSK_ACK_SCHED = 1, - ICSK_ACK_TIMER = 2, - ICSK_ACK_PUSHED = 4, - ICSK_ACK_PUSHED2 = 8, - ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ -}; - -enum tcp_ca_event { - CA_EVENT_TX_START = 0, - CA_EVENT_CWND_RESTART = 1, - CA_EVENT_COMPLETE_CWR = 2, - CA_EVENT_LOSS = 3, - CA_EVENT_ECN_NO_CE = 4, - CA_EVENT_ECN_IS_CE = 5, -}; - -struct ack_sample { - __u32 pkts_acked; - __s32 rtt_us; - __u32 in_flight; -} __attribute__((preserve_access_index)); - -struct rate_sample { - __u64 prior_mstamp; /* starting timestamp for interval */ - __u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ - __s32 delivered; /* number of packets delivered over interval */ - long interval_us; /* time for tp->delivered to incr "delivered" */ - __u32 snd_interval_us; /* snd interval for delivered packets */ - __u32 rcv_interval_us; /* rcv interval for delivered packets */ - long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ - int losses; /* number of packets marked lost upon ACK */ - __u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ - __u32 prior_in_flight; /* in flight before this ACK */ - bool is_app_limited; /* is sample from packet with bubble in pipe? */ - bool is_retrans; /* is sample from retransmission? */ - bool is_ack_delayed; /* is this (likely) a delayed ACK? */ -} __attribute__((preserve_access_index)); - -#define TCP_CA_NAME_MAX 16 -#define TCP_CONG_NEEDS_ECN 0x2 - -struct tcp_congestion_ops { - char name[TCP_CA_NAME_MAX]; - __u32 flags; - - /* initialize private data (optional) */ - void (*init)(struct sock *sk); - /* cleanup private data (optional) */ - void (*release)(struct sock *sk); - - /* return slow start threshold (required) */ - __u32 (*ssthresh)(struct sock *sk); - /* do new cwnd calculation (required) */ - void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked); - /* call before changing ca_state (optional) */ - void (*set_state)(struct sock *sk, __u8 new_state); - /* call when cwnd event occurs (optional) */ - void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); - /* call when ack arrives (optional) */ - void (*in_ack_event)(struct sock *sk, __u32 flags); - /* new value of cwnd after loss (required) */ - __u32 (*undo_cwnd)(struct sock *sk); - /* hook for packet ack accounting (optional) */ - void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); - /* override sysctl_tcp_min_tso_segs */ - __u32 (*min_tso_segs)(struct sock *sk); - /* returns the multiplier used in tcp_sndbuf_expand (optional) */ - __u32 (*sndbuf_expand)(struct sock *sk); - /* call when packets are delivered to update cwnd and pacing rate, - * after all the ca_state processing. (optional) - */ - void (*cong_control)(struct sock *sk, const struct rate_sample *rs); - void *owner; -}; - -#define min(a, b) ((a) < (b) ? (a) : (b)) -#define max(a, b) ((a) > (b) ? (a) : (b)) -#define min_not_zero(x, y) ({ \ - typeof(x) __x = (x); \ - typeof(y) __y = (y); \ - __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) - -static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp) -{ - return tp->snd_cwnd < tp->snd_ssthresh; -} - -static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - - /* If in slow start, ensure cwnd grows to twice what was ACKed. */ - if (tcp_in_slow_start(tp)) - return tp->snd_cwnd < 2 * tp->max_packets_out; - - return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited); -} - -static __always_inline bool tcp_cc_eq(const char *a, const char *b) -{ - int i; - - for (i = 0; i < TCP_CA_NAME_MAX; i++) { - if (a[i] != b[i]) - return false; - if (!a[i]) - break; - } - - return true; -} - -extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym; -extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym; - -struct mptcp_sock { - struct inet_connection_sock sk; - - __u32 token; - struct sock *first; - char ca_name[TCP_CA_NAME_MAX]; -} __attribute__((preserve_access_index)); - -#endif diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 0b3cef2c5159..2a18bd320e92 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -10,18 +10,30 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include +#include #include "bpf_testmod.h" #include "bpf_testmod_kfunc.h" #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" +#define CONNECT_TIMEOUT_SEC 1 + typedef int (*func_proto_typedef)(long); typedef int (*func_proto_typedef_nested1)(func_proto_typedef); typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; long bpf_testmod_test_struct_arg_result; +static DEFINE_MUTEX(sock_lock); +static struct socket *sock; struct bpf_testmod_struct_arg_1 { int a; @@ -501,6 +513,237 @@ __bpf_kfunc void bpf_kfunc_call_test_sleepable(void) { } +__bpf_kfunc int bpf_kfunc_init_sock(struct init_sock_args *args) +{ + int proto; + int err; + + mutex_lock(&sock_lock); + + if (sock) { + pr_err("%s called without releasing old sock", __func__); + err = -EPERM; + goto out; + } + + switch (args->af) { + case AF_INET: + case AF_INET6: + proto = args->type == SOCK_STREAM ? IPPROTO_TCP : IPPROTO_UDP; + break; + case AF_UNIX: + proto = PF_UNIX; + break; + default: + pr_err("invalid address family %d\n", args->af); + err = -EINVAL; + goto out; + } + + err = sock_create_kern(current->nsproxy->net_ns, args->af, args->type, + proto, &sock); + + if (!err) + /* Set timeout for call to kernel_connect() to prevent it from hanging, + * and consider the connection attempt failed if it returns + * -EINPROGRESS. + */ + sock->sk->sk_sndtimeo = CONNECT_TIMEOUT_SEC * HZ; +out: + mutex_unlock(&sock_lock); + + return err; +} + +__bpf_kfunc void bpf_kfunc_close_sock(void) +{ + mutex_lock(&sock_lock); + + if (sock) { + sock_release(sock); + sock = NULL; + } + + mutex_unlock(&sock_lock); +} + +__bpf_kfunc int bpf_kfunc_call_kernel_connect(struct addr_args *args) +{ + int err; + + if (args->addrlen > sizeof(args->addr)) + return -EINVAL; + + mutex_lock(&sock_lock); + + if (!sock) { + pr_err("%s called without initializing sock", __func__); + err = -EPERM; + goto out; + } + + err = kernel_connect(sock, (struct sockaddr *)&args->addr, + args->addrlen, 0); +out: + mutex_unlock(&sock_lock); + + return err; +} + +__bpf_kfunc int bpf_kfunc_call_kernel_bind(struct addr_args *args) +{ + int err; + + if (args->addrlen > sizeof(args->addr)) + return -EINVAL; + + mutex_lock(&sock_lock); + + if (!sock) { + pr_err("%s called without initializing sock", __func__); + err = -EPERM; + goto out; + } + + err = kernel_bind(sock, (struct sockaddr *)&args->addr, args->addrlen); +out: + mutex_unlock(&sock_lock); + + return err; +} + +__bpf_kfunc int bpf_kfunc_call_kernel_listen(void) +{ + int err; + + mutex_lock(&sock_lock); + + if (!sock) { + pr_err("%s called without initializing sock", __func__); + err = -EPERM; + goto out; + } + + err = kernel_listen(sock, 128); +out: + mutex_unlock(&sock_lock); + + return err; +} + +__bpf_kfunc int bpf_kfunc_call_kernel_sendmsg(struct sendmsg_args *args) +{ + struct msghdr msg = { + .msg_name = &args->addr.addr, + .msg_namelen = args->addr.addrlen, + }; + struct kvec iov; + int err; + + if (args->addr.addrlen > sizeof(args->addr.addr) || + args->msglen > sizeof(args->msg)) + return -EINVAL; + + iov.iov_base = args->msg; + iov.iov_len = args->msglen; + + mutex_lock(&sock_lock); + + if (!sock) { + pr_err("%s called without initializing sock", __func__); + err = -EPERM; + goto out; + } + + err = kernel_sendmsg(sock, &msg, &iov, 1, args->msglen); + args->addr.addrlen = msg.msg_namelen; +out: + mutex_unlock(&sock_lock); + + return err; +} + +__bpf_kfunc int bpf_kfunc_call_sock_sendmsg(struct sendmsg_args *args) +{ + struct msghdr msg = { + .msg_name = &args->addr.addr, + .msg_namelen = args->addr.addrlen, + }; + struct kvec iov; + int err; + + if (args->addr.addrlen > sizeof(args->addr.addr) || + args->msglen > sizeof(args->msg)) + return -EINVAL; + + iov.iov_base = args->msg; + iov.iov_len = args->msglen; + + iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, args->msglen); + mutex_lock(&sock_lock); + + if (!sock) { + pr_err("%s called without initializing sock", __func__); + err = -EPERM; + goto out; + } + + err = sock_sendmsg(sock, &msg); + args->addr.addrlen = msg.msg_namelen; +out: + mutex_unlock(&sock_lock); + + return err; +} + +__bpf_kfunc int bpf_kfunc_call_kernel_getsockname(struct addr_args *args) +{ + int err; + + mutex_lock(&sock_lock); + + if (!sock) { + pr_err("%s called without initializing sock", __func__); + err = -EPERM; + goto out; + } + + err = kernel_getsockname(sock, (struct sockaddr *)&args->addr); + if (err < 0) + goto out; + + args->addrlen = err; + err = 0; +out: + mutex_unlock(&sock_lock); + + return err; +} + +__bpf_kfunc int bpf_kfunc_call_kernel_getpeername(struct addr_args *args) +{ + int err; + + mutex_lock(&sock_lock); + + if (!sock) { + pr_err("%s called without initializing sock", __func__); + err = -EPERM; + goto out; + } + + err = kernel_getpeername(sock, (struct sockaddr *)&args->addr); + if (err < 0) + goto out; + + args->addrlen = err; + err = 0; +out: + mutex_unlock(&sock_lock); + + return err; +} + BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc) BTF_ID_FLAGS(func, bpf_kfunc_call_test1) @@ -528,6 +771,15 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_ID_FLAGS(func, bpf_kfunc_call_test_sleepable, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_init_sock, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_close_sock, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_connect, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_bind, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_listen, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_sendmsg, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_sock_sendmsg, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getsockname, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getpeername, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids) static int bpf_testmod_ops_init(struct btf *btf) @@ -658,6 +910,8 @@ static int bpf_testmod_init(void) return ret; if (bpf_fentry_test1(0) < 0) return -EINVAL; + sock = NULL; + mutex_init(&sock_lock); return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } @@ -671,6 +925,7 @@ static void bpf_testmod_exit(void) while (refcount_read(&prog_test_struct.cnt) > 1) msleep(20); + bpf_kfunc_close_sock(); sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h index ce5cd763561c..b0d586a6751f 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h @@ -64,6 +64,22 @@ struct prog_test_fail3 { char arr2[]; }; +struct init_sock_args { + int af; + int type; +}; + +struct addr_args { + char addr[sizeof(struct __kernel_sockaddr_storage)]; + int addrlen; +}; + +struct sendmsg_args { + struct addr_args addr; + char msg[10]; + int msglen; +}; + struct prog_test_ref_kfunc * bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) __ksym; void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; @@ -107,4 +123,15 @@ void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p); void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len); void bpf_kfunc_common_test(void) __ksym; + +int bpf_kfunc_init_sock(struct init_sock_args *args) __ksym; +void bpf_kfunc_close_sock(void) __ksym; +int bpf_kfunc_call_kernel_connect(struct addr_args *args) __ksym; +int bpf_kfunc_call_kernel_bind(struct addr_args *args) __ksym; +int bpf_kfunc_call_kernel_listen(void) __ksym; +int bpf_kfunc_call_kernel_sendmsg(struct sendmsg_args *args) __ksym; +int bpf_kfunc_call_sock_sendmsg(struct sendmsg_args *args) __ksym; +int bpf_kfunc_call_kernel_getsockname(struct addr_args *args) __ksym; +int bpf_kfunc_call_kernel_getpeername(struct addr_args *args) __ksym; + #endif /* _BPF_TESTMOD_KFUNC_H */ diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index f2952a65dcc2..23bb9a9e6a7d 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -508,6 +508,9 @@ int cgroup_setup_and_join(const char *path) { /** * setup_classid_environment() - Setup the cgroupv1 net_cls environment * + * This function should only be called in a custom mount namespace, e.g. + * created by running setup_cgroup_environment. + * * After calling this function, cleanup_classid_environment should be called * once testing is complete. * diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index a9e4905a2115..35250e6cde7f 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -80,24 +80,22 @@ int settimeo(int fd, int timeout_ms) #define save_errno_close(fd) ({ int __save = errno; close(fd); errno = __save; }) -static int __start_server(int type, int protocol, const struct sockaddr *addr, - socklen_t addrlen, int timeout_ms, bool reuseport) +static int __start_server(int type, const struct sockaddr *addr, socklen_t addrlen, + const struct network_helper_opts *opts) { - int on = 1; int fd; - fd = socket(addr->sa_family, type, protocol); + fd = socket(addr->sa_family, type, opts->proto); if (fd < 0) { log_err("Failed to create server socket"); return -1; } - if (settimeo(fd, timeout_ms)) + if (settimeo(fd, opts->timeout_ms)) goto error_close; - if (reuseport && - setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &on, sizeof(on))) { - log_err("Failed to set SO_REUSEPORT"); + if (opts->post_socket_cb && opts->post_socket_cb(fd, NULL)) { + log_err("Failed to call post_socket_cb"); goto error_close; } @@ -120,35 +118,35 @@ error_close: return -1; } -static int start_server_proto(int family, int type, int protocol, - const char *addr_str, __u16 port, int timeout_ms) +int start_server(int family, int type, const char *addr_str, __u16 port, + int timeout_ms) { + struct network_helper_opts opts = { + .timeout_ms = timeout_ms, + }; struct sockaddr_storage addr; socklen_t addrlen; if (make_sockaddr(family, addr_str, port, &addr, &addrlen)) return -1; - return __start_server(type, protocol, (struct sockaddr *)&addr, - addrlen, timeout_ms, false); + return __start_server(type, (struct sockaddr *)&addr, addrlen, &opts); } -int start_server(int family, int type, const char *addr_str, __u16 port, - int timeout_ms) +static int reuseport_cb(int fd, const struct post_socket_opts *opts) { - return start_server_proto(family, type, 0, addr_str, port, timeout_ms); -} + int on = 1; -int start_mptcp_server(int family, const char *addr_str, __u16 port, - int timeout_ms) -{ - return start_server_proto(family, SOCK_STREAM, IPPROTO_MPTCP, addr_str, - port, timeout_ms); + return setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &on, sizeof(on)); } int *start_reuseport_server(int family, int type, const char *addr_str, __u16 port, int timeout_ms, unsigned int nr_listens) { + struct network_helper_opts opts = { + .timeout_ms = timeout_ms, + .post_socket_cb = reuseport_cb, + }; struct sockaddr_storage addr; unsigned int nr_fds = 0; socklen_t addrlen; @@ -164,8 +162,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str, if (!fds) return NULL; - fds[0] = __start_server(type, 0, (struct sockaddr *)&addr, addrlen, - timeout_ms, true); + fds[0] = __start_server(type, (struct sockaddr *)&addr, addrlen, &opts); if (fds[0] == -1) goto close_fds; nr_fds = 1; @@ -174,8 +171,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str, goto close_fds; for (; nr_fds < nr_listens; nr_fds++) { - fds[nr_fds] = __start_server(type, 0, (struct sockaddr *)&addr, - addrlen, timeout_ms, true); + fds[nr_fds] = __start_server(type, (struct sockaddr *)&addr, addrlen, &opts); if (fds[nr_fds] == -1) goto close_fds; } @@ -193,8 +189,7 @@ int start_server_addr(int type, const struct sockaddr_storage *addr, socklen_t l if (!opts) opts = &default_opts; - return __start_server(type, 0, (struct sockaddr *)addr, len, - opts->timeout_ms, 0); + return __start_server(type, (struct sockaddr *)addr, len, opts); } void free_fds(int *fds, unsigned int nr_close_fds) diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 5a8c5cf4ec1a..883c7ea9d8d5 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -21,6 +21,8 @@ typedef __u16 __sum16; #define VIP_NUM 5 #define MAGIC_BYTES 123 +struct post_socket_opts {}; + struct network_helper_opts { const char *cc; int timeout_ms; @@ -28,6 +30,7 @@ struct network_helper_opts { bool noconnect; int type; int proto; + int (*post_socket_cb)(int fd, const struct post_socket_opts *opts); }; /* ipv4 test vector */ @@ -49,8 +52,6 @@ extern struct ipv6_packet pkt_v6; int settimeo(int fd, int timeout_ms); int start_server(int family, int type, const char *addr, __u16 port, int timeout_ms); -int start_mptcp_server(int family, const char *addr, __u16 port, - int timeout_ms); int *start_reuseport_server(int family, int type, const char *addr_str, __u16 port, int timeout_ms, unsigned int nr_listens); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index 907bac46c774..0aca02532794 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -14,6 +14,7 @@ #include "tcp_ca_incompl_cong_ops.skel.h" #include "tcp_ca_unsupp_cong_op.skel.h" #include "tcp_ca_kfunc.skel.h" +#include "bpf_cc_cubic.skel.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -452,6 +453,27 @@ static void test_tcp_ca_kfunc(void) tcp_ca_kfunc__destroy(skel); } +static void test_cc_cubic(void) +{ + struct bpf_cc_cubic *cc_cubic_skel; + struct bpf_link *link; + + cc_cubic_skel = bpf_cc_cubic__open_and_load(); + if (!ASSERT_OK_PTR(cc_cubic_skel, "bpf_cc_cubic__open_and_load")) + return; + + link = bpf_map__attach_struct_ops(cc_cubic_skel->maps.cc_cubic); + if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) { + bpf_cc_cubic__destroy(cc_cubic_skel); + return; + } + + do_test("bpf_cc_cubic", NULL); + + bpf_link__destroy(link); + bpf_cc_cubic__destroy(cc_cubic_skel); +} + void test_bpf_tcp_ca(void) { if (test__start_subtest("dctcp")) @@ -482,4 +504,6 @@ void test_bpf_tcp_ca(void) test_link_replace(); if (test__start_subtest("tcp_ca_kfunc")) test_tcp_ca_kfunc(); + if (test__start_subtest("cc_cubic")) + test_cc_cubic(); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c index 74d6d7546f40..25332e596750 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c @@ -87,9 +87,12 @@ void test_cgroup1_hierarchy(void) goto destroy; /* Setup cgroup1 hierarchy */ + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto destroy; err = setup_classid_environment(); if (!ASSERT_OK(err, "setup_classid_environment")) - goto destroy; + goto cleanup_cgroup; err = join_classid(); if (!ASSERT_OK(err, "join_cgroup1")) @@ -153,6 +156,8 @@ void test_cgroup1_hierarchy(void) cleanup: cleanup_classid_environment(); +cleanup_cgroup: + cleanup_cgroup_environment(); destroy: test_cgroup1_hierarchy__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 51628455b6f5..960c9323d1e0 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -4,6 +4,8 @@ #include "trace_helpers.h" #include "kprobe_multi_empty.skel.h" #include "kprobe_multi_override.skel.h" +#include "kprobe_multi_session.skel.h" +#include "kprobe_multi_session_cookie.skel.h" #include "bpf/libbpf_internal.h" #include "bpf/hashmap.h" @@ -326,6 +328,74 @@ cleanup: kprobe_multi__destroy(skel); } +static void test_session_skel_api(void) +{ + struct kprobe_multi_session *skel = NULL; + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct bpf_link *link = NULL; + int i, err, prog_fd; + + skel = kprobe_multi_session__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_multi_session__open_and_load")) + return; + + skel->bss->pid = getpid(); + + err = kprobe_multi_session__attach(skel); + if (!ASSERT_OK(err, " kprobe_multi_session__attach")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + /* bpf_fentry_test1-4 trigger return probe, result is 2 */ + for (i = 0; i < 4; i++) + ASSERT_EQ(skel->bss->kprobe_session_result[i], 2, "kprobe_session_result"); + + /* bpf_fentry_test5-8 trigger only entry probe, result is 1 */ + for (i = 4; i < 8; i++) + ASSERT_EQ(skel->bss->kprobe_session_result[i], 1, "kprobe_session_result"); + +cleanup: + bpf_link__destroy(link); + kprobe_multi_session__destroy(skel); +} + +static void test_session_cookie_skel_api(void) +{ + struct kprobe_multi_session_cookie *skel = NULL; + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct bpf_link *link = NULL; + int err, prog_fd; + + skel = kprobe_multi_session_cookie__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + return; + + skel->bss->pid = getpid(); + + err = kprobe_multi_session_cookie__attach(skel); + if (!ASSERT_OK(err, " kprobe_multi_wrapper__attach")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->test_kprobe_1_result, 1, "test_kprobe_1_result"); + ASSERT_EQ(skel->bss->test_kprobe_2_result, 2, "test_kprobe_2_result"); + ASSERT_EQ(skel->bss->test_kprobe_3_result, 3, "test_kprobe_3_result"); + +cleanup: + bpf_link__destroy(link); + kprobe_multi_session_cookie__destroy(skel); +} + static size_t symbol_hash(long key, void *ctx __maybe_unused) { return str_hash((const char *) key); @@ -690,4 +760,8 @@ void test_kprobe_multi_test(void) test_attach_api_fails(); if (test__start_subtest("attach_override")) test_attach_override(); + if (test__start_subtest("session")) + test_session_skel_api(); + if (test__start_subtest("session_cookie")) + test_session_cookie_skel_api(); } diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index f53d658ed080..6d391d95f96e 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -51,6 +51,10 @@ void test_module_attach(void) 0, "bpf_testmod_test_read"); ASSERT_OK(err, "set_attach_target"); + err = bpf_program__set_attach_target(skel->progs.handle_fentry_explicit_manual, + 0, "bpf_testmod:bpf_testmod_test_read"); + ASSERT_OK(err, "set_attach_target_explicit"); + err = test_module_attach__load(skel); if (CHECK(err, "skel_load", "failed to load skeleton\n")) return; @@ -70,6 +74,8 @@ void test_module_attach(void) ASSERT_EQ(bss->tp_btf_read_sz, READ_SZ, "tp_btf"); ASSERT_EQ(bss->fentry_read_sz, READ_SZ, "fentry"); ASSERT_EQ(bss->fentry_manual_read_sz, READ_SZ, "fentry_manual"); + ASSERT_EQ(bss->fentry_explicit_read_sz, READ_SZ, "fentry_explicit"); + ASSERT_EQ(bss->fentry_explicit_manual_read_sz, READ_SZ, "fentry_explicit_manual"); ASSERT_EQ(bss->fexit_read_sz, READ_SZ, "fexit"); ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet"); ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret"); diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index 4e0f69295872..274d2e033e39 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -82,6 +82,22 @@ static void cleanup_netns(struct nstoken *nstoken) SYS_NOFAIL("ip netns del %s", NS_TEST); } +static int start_mptcp_server(int family, const char *addr_str, __u16 port, + int timeout_ms) +{ + struct network_helper_opts opts = { + .timeout_ms = timeout_ms, + .proto = IPPROTO_MPTCP, + }; + struct sockaddr_storage addr; + socklen_t addrlen; + + if (make_sockaddr(family, addr_str, port, &addr, &addrlen)) + return -1; + + return start_server_addr(SOCK_STREAM, &addr, addrlen, &opts); +} + static int verify_tsk(int map_fd, int client_fd) { int err, cfd = client_fd; diff --git a/tools/testing/selftests/bpf/prog_tests/sock_addr.c b/tools/testing/selftests/bpf/prog_tests/sock_addr.c index 61668e0f11b0..b880c564a204 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_addr.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_addr.c @@ -3,16 +3,56 @@ #include "test_progs.h" +#include "sock_addr_kern.skel.h" +#include "bind4_prog.skel.h" +#include "bind6_prog.skel.h" #include "connect_unix_prog.skel.h" +#include "connect4_prog.skel.h" +#include "connect6_prog.skel.h" +#include "sendmsg4_prog.skel.h" +#include "sendmsg6_prog.skel.h" +#include "recvmsg4_prog.skel.h" +#include "recvmsg6_prog.skel.h" #include "sendmsg_unix_prog.skel.h" #include "recvmsg_unix_prog.skel.h" +#include "getsockname4_prog.skel.h" +#include "getsockname6_prog.skel.h" #include "getsockname_unix_prog.skel.h" +#include "getpeername4_prog.skel.h" +#include "getpeername6_prog.skel.h" #include "getpeername_unix_prog.skel.h" #include "network_helpers.h" +#ifndef ENOTSUPP +# define ENOTSUPP 524 +#endif + +#define TEST_NS "sock_addr" +#define TEST_IF_PREFIX "test_sock_addr" +#define TEST_IPV4 "127.0.0.4" +#define TEST_IPV6 "::6" + +#define SERV4_IP "192.168.1.254" +#define SERV4_REWRITE_IP "127.0.0.1" +#define SRC4_IP "172.16.0.1" +#define SRC4_REWRITE_IP TEST_IPV4 +#define SERV4_PORT 4040 +#define SERV4_REWRITE_PORT 4444 + +#define SERV6_IP "face:b00c:1234:5678::abcd" +#define SERV6_REWRITE_IP "::1" +#define SERV6_V4MAPPED_IP "::ffff:192.168.0.4" +#define SRC6_IP "::1" +#define SRC6_REWRITE_IP TEST_IPV6 +#define WILDCARD6_IP "::" +#define SERV6_PORT 6060 +#define SERV6_REWRITE_PORT 6666 + #define SERVUN_ADDRESS "bpf_cgroup_unix_test" #define SERVUN_REWRITE_ADDRESS "bpf_cgroup_unix_test_rewrite" -#define SRCUN_ADDRESS "bpf_cgroup_unix_test_src" +#define SRCUN_ADDRESS "bpf_cgroup_unix_test_src" + +#define save_errno_do(op) ({ int __save = errno; op; errno = __save; }) enum sock_addr_test_type { SOCK_ADDR_TEST_BIND, @@ -23,15 +63,301 @@ enum sock_addr_test_type { SOCK_ADDR_TEST_GETPEERNAME, }; -typedef void *(*load_fn)(int cgroup_fd); +typedef void *(*load_fn)(int cgroup_fd, + enum bpf_attach_type attach_type, + bool expect_reject); typedef void (*destroy_fn)(void *skel); +static int cmp_addr(const struct sockaddr_storage *addr1, socklen_t addr1_len, + const struct sockaddr_storage *addr2, socklen_t addr2_len, + bool cmp_port); + +struct init_sock_args { + int af; + int type; +}; + +struct addr_args { + char addr[sizeof(struct sockaddr_storage)]; + int addrlen; +}; + +struct sendmsg_args { + struct addr_args addr; + char msg[10]; + int msglen; +}; + +static struct sock_addr_kern *skel; + +static int run_bpf_prog(const char *prog_name, void *ctx, int ctx_size) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct bpf_program *prog; + int prog_fd, err; + + topts.ctx_in = ctx; + topts.ctx_size_in = ctx_size; + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) + goto err; + + prog_fd = bpf_program__fd(prog); + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, prog_name)) + goto err; + + err = topts.retval; + errno = -topts.retval; + goto out; +err: + err = -1; +out: + return err; +} + +static int kernel_init_sock(int af, int type, int protocol) +{ + struct init_sock_args args = { + .af = af, + .type = type, + }; + + return run_bpf_prog("init_sock", &args, sizeof(args)); +} + +static int kernel_close_sock(int fd) +{ + return run_bpf_prog("close_sock", NULL, 0); +} + +static int sock_addr_op(const char *name, struct sockaddr *addr, + socklen_t *addrlen, bool expect_change) +{ + struct addr_args args; + int err; + + if (addrlen) + args.addrlen = *addrlen; + + if (addr) + memcpy(&args.addr, addr, *addrlen); + + err = run_bpf_prog(name, &args, sizeof(args)); + + if (!expect_change && addr) + if (!ASSERT_EQ(cmp_addr((struct sockaddr_storage *)addr, + *addrlen, + (struct sockaddr_storage *)&args.addr, + args.addrlen, 1), + 0, "address_param_modified")) + return -1; + + if (addrlen) + *addrlen = args.addrlen; + + if (addr) + memcpy(addr, &args.addr, *addrlen); + + return err; +} + +static int send_msg_op(const char *name, struct sockaddr *addr, + socklen_t addrlen, const char *msg, int msglen) +{ + struct sendmsg_args args; + int err; + + memset(&args, 0, sizeof(args)); + memcpy(&args.addr.addr, addr, addrlen); + args.addr.addrlen = addrlen; + memcpy(args.msg, msg, msglen); + args.msglen = msglen; + + err = run_bpf_prog(name, &args, sizeof(args)); + + if (!ASSERT_EQ(cmp_addr((struct sockaddr_storage *)addr, + addrlen, + (struct sockaddr_storage *)&args.addr.addr, + args.addr.addrlen, 1), + 0, "address_param_modified")) + return -1; + + return err; +} + +static int kernel_connect(struct sockaddr *addr, socklen_t addrlen) +{ + return sock_addr_op("kernel_connect", addr, &addrlen, false); +} + +static int kernel_bind(int fd, struct sockaddr *addr, socklen_t addrlen) +{ + return sock_addr_op("kernel_bind", addr, &addrlen, false); +} + +static int kernel_listen(void) +{ + return sock_addr_op("kernel_listen", NULL, NULL, false); +} + +static int kernel_sendmsg(int fd, struct sockaddr *addr, socklen_t addrlen, + char *msg, int msglen) +{ + return send_msg_op("kernel_sendmsg", addr, addrlen, msg, msglen); +} + +static int sock_sendmsg(int fd, struct sockaddr *addr, socklen_t addrlen, + char *msg, int msglen) +{ + return send_msg_op("sock_sendmsg", addr, addrlen, msg, msglen); +} + +static int kernel_getsockname(int fd, struct sockaddr *addr, socklen_t *addrlen) +{ + return sock_addr_op("kernel_getsockname", addr, addrlen, true); +} + +static int kernel_getpeername(int fd, struct sockaddr *addr, socklen_t *addrlen) +{ + return sock_addr_op("kernel_getpeername", addr, addrlen, true); +} + +int kernel_connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t addrlen, + const struct network_helper_opts *opts) +{ + int err; + + if (!ASSERT_OK(kernel_init_sock(addr->ss_family, type, 0), + "kernel_init_sock")) + goto err; + + if (kernel_connect((struct sockaddr *)addr, addrlen) < 0) + goto err; + + /* Test code expects a "file descriptor" on success. */ + err = 1; + goto out; +err: + err = -1; + save_errno_do(ASSERT_OK(kernel_close_sock(0), "kernel_close_sock")); +out: + return err; +} + +int kernel_start_server(int family, int type, const char *addr_str, __u16 port, + int timeout_ms) +{ + struct sockaddr_storage addr; + socklen_t addrlen; + int err; + + if (!ASSERT_OK(kernel_init_sock(family, type, 0), "kernel_init_sock")) + goto err; + + if (make_sockaddr(family, addr_str, port, &addr, &addrlen)) + goto err; + + if (kernel_bind(0, (struct sockaddr *)&addr, addrlen) < 0) + goto err; + + if (type == SOCK_STREAM) { + if (!ASSERT_OK(kernel_listen(), "kernel_listen")) + goto err; + } + + /* Test code expects a "file descriptor" on success. */ + err = 1; + goto out; +err: + err = -1; + save_errno_do(ASSERT_OK(kernel_close_sock(0), "kernel_close_sock")); +out: + return err; +} + +struct sock_ops { + int (*connect_to_addr)(int type, const struct sockaddr_storage *addr, + socklen_t addrlen, + const struct network_helper_opts *opts); + int (*start_server)(int family, int type, const char *addr_str, + __u16 port, int timeout_ms); + int (*socket)(int famil, int type, int protocol); + int (*bind)(int fd, struct sockaddr *addr, socklen_t addrlen); + int (*getsockname)(int fd, struct sockaddr *addr, socklen_t *addrlen); + int (*getpeername)(int fd, struct sockaddr *addr, socklen_t *addrlen); + int (*sendmsg)(int fd, struct sockaddr *addr, socklen_t addrlen, + char *msg, int msglen); + int (*close)(int fd); +}; + +static int user_sendmsg(int fd, struct sockaddr *addr, socklen_t addrlen, + char *msg, int msglen) +{ + struct msghdr hdr; + struct iovec iov; + + memset(&iov, 0, sizeof(iov)); + iov.iov_base = msg; + iov.iov_len = msglen; + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_name = (void *)addr; + hdr.msg_namelen = addrlen; + hdr.msg_iov = &iov; + hdr.msg_iovlen = 1; + + return sendmsg(fd, &hdr, 0); +} + +static int user_bind(int fd, struct sockaddr *addr, socklen_t addrlen) +{ + return bind(fd, (const struct sockaddr *)addr, addrlen); +} + +struct sock_ops user_ops = { + .connect_to_addr = connect_to_addr, + .start_server = start_server, + .socket = socket, + .bind = user_bind, + .getsockname = getsockname, + .getpeername = getpeername, + .sendmsg = user_sendmsg, + .close = close, +}; + +struct sock_ops kern_ops_sock_sendmsg = { + .connect_to_addr = kernel_connect_to_addr, + .start_server = kernel_start_server, + .socket = kernel_init_sock, + .bind = kernel_bind, + .getsockname = kernel_getsockname, + .getpeername = kernel_getpeername, + .sendmsg = sock_sendmsg, + .close = kernel_close_sock, +}; + +struct sock_ops kern_ops_kernel_sendmsg = { + .connect_to_addr = kernel_connect_to_addr, + .start_server = kernel_start_server, + .socket = kernel_init_sock, + .bind = kernel_bind, + .getsockname = kernel_getsockname, + .getpeername = kernel_getpeername, + .sendmsg = kernel_sendmsg, + .close = kernel_close_sock, +}; + struct sock_addr_test { enum sock_addr_test_type type; const char *name; /* BPF prog properties */ load_fn loadfn; destroy_fn destroyfn; + enum bpf_attach_type attach_type; + /* Socket operations */ + struct sock_ops *ops; /* Socket properties */ int socket_family; int socket_type; @@ -41,134 +367,651 @@ struct sock_addr_test { const char *expected_addr; unsigned short expected_port; const char *expected_src_addr; + /* Expected test result */ + enum { + LOAD_REJECT, + ATTACH_REJECT, + SYSCALL_EPERM, + SYSCALL_ENOTSUPP, + SUCCESS, + } expected_result; }; -static void *connect_unix_prog_load(int cgroup_fd) -{ - struct connect_unix_prog *skel; +#define BPF_SKEL_FUNCS_RAW(skel_name, prog_name) \ +static void *prog_name##_load_raw(int cgroup_fd, \ + enum bpf_attach_type attach_type, \ + bool expect_reject) \ +{ \ + struct skel_name *skel = skel_name##__open(); \ + int prog_fd = -1; \ + if (!ASSERT_OK_PTR(skel, "skel_open")) \ + goto cleanup; \ + if (!ASSERT_OK(skel_name##__load(skel), "load")) \ + goto cleanup; \ + prog_fd = bpf_program__fd(skel->progs.prog_name); \ + if (!ASSERT_GT(prog_fd, 0, "prog_fd")) \ + goto cleanup; \ + if (bpf_prog_attach(prog_fd, cgroup_fd, attach_type, \ + BPF_F_ALLOW_OVERRIDE), "bpf_prog_attach") { \ + ASSERT_TRUE(expect_reject, "unexpected rejection"); \ + goto cleanup; \ + } \ + if (!ASSERT_FALSE(expect_reject, "expected rejection")) \ + goto cleanup; \ +cleanup: \ + if (prog_fd > 0) \ + bpf_prog_detach(cgroup_fd, attach_type); \ + skel_name##__destroy(skel); \ + return NULL; \ +} \ +static void prog_name##_destroy_raw(void *progfd) \ +{ \ + /* No-op. *_load_raw does all cleanup. */ \ +} \ - skel = connect_unix_prog__open_and_load(); - if (!ASSERT_OK_PTR(skel, "skel_open")) - goto cleanup; - - skel->links.connect_unix_prog = bpf_program__attach_cgroup( - skel->progs.connect_unix_prog, cgroup_fd); - if (!ASSERT_OK_PTR(skel->links.connect_unix_prog, "prog_attach")) - goto cleanup; - - return skel; -cleanup: - connect_unix_prog__destroy(skel); - return NULL; +#define BPF_SKEL_FUNCS(skel_name, prog_name) \ +static void *prog_name##_load(int cgroup_fd, \ + enum bpf_attach_type attach_type, \ + bool expect_reject) \ +{ \ + struct skel_name *skel = skel_name##__open(); \ + if (!ASSERT_OK_PTR(skel, "skel_open")) \ + goto cleanup; \ + if (!ASSERT_OK(bpf_program__set_expected_attach_type(skel->progs.prog_name, \ + attach_type), \ + "set_expected_attach_type")) \ + goto cleanup; \ + if (skel_name##__load(skel)) { \ + ASSERT_TRUE(expect_reject, "unexpected rejection"); \ + goto cleanup; \ + } \ + if (!ASSERT_FALSE(expect_reject, "expected rejection")) \ + goto cleanup; \ + skel->links.prog_name = bpf_program__attach_cgroup( \ + skel->progs.prog_name, cgroup_fd); \ + if (!ASSERT_OK_PTR(skel->links.prog_name, "prog_attach")) \ + goto cleanup; \ + return skel; \ +cleanup: \ + skel_name##__destroy(skel); \ + return NULL; \ +} \ +static void prog_name##_destroy(void *skel) \ +{ \ + skel_name##__destroy(skel); \ } -static void connect_unix_prog_destroy(void *skel) -{ - connect_unix_prog__destroy(skel); -} - -static void *sendmsg_unix_prog_load(int cgroup_fd) -{ - struct sendmsg_unix_prog *skel; - - skel = sendmsg_unix_prog__open_and_load(); - if (!ASSERT_OK_PTR(skel, "skel_open")) - goto cleanup; - - skel->links.sendmsg_unix_prog = bpf_program__attach_cgroup( - skel->progs.sendmsg_unix_prog, cgroup_fd); - if (!ASSERT_OK_PTR(skel->links.sendmsg_unix_prog, "prog_attach")) - goto cleanup; - - return skel; -cleanup: - sendmsg_unix_prog__destroy(skel); - return NULL; -} - -static void sendmsg_unix_prog_destroy(void *skel) -{ - sendmsg_unix_prog__destroy(skel); -} - -static void *recvmsg_unix_prog_load(int cgroup_fd) -{ - struct recvmsg_unix_prog *skel; - - skel = recvmsg_unix_prog__open_and_load(); - if (!ASSERT_OK_PTR(skel, "skel_open")) - goto cleanup; - - skel->links.recvmsg_unix_prog = bpf_program__attach_cgroup( - skel->progs.recvmsg_unix_prog, cgroup_fd); - if (!ASSERT_OK_PTR(skel->links.recvmsg_unix_prog, "prog_attach")) - goto cleanup; - - return skel; -cleanup: - recvmsg_unix_prog__destroy(skel); - return NULL; -} - -static void recvmsg_unix_prog_destroy(void *skel) -{ - recvmsg_unix_prog__destroy(skel); -} - -static void *getsockname_unix_prog_load(int cgroup_fd) -{ - struct getsockname_unix_prog *skel; - - skel = getsockname_unix_prog__open_and_load(); - if (!ASSERT_OK_PTR(skel, "skel_open")) - goto cleanup; - - skel->links.getsockname_unix_prog = bpf_program__attach_cgroup( - skel->progs.getsockname_unix_prog, cgroup_fd); - if (!ASSERT_OK_PTR(skel->links.getsockname_unix_prog, "prog_attach")) - goto cleanup; - - return skel; -cleanup: - getsockname_unix_prog__destroy(skel); - return NULL; -} - -static void getsockname_unix_prog_destroy(void *skel) -{ - getsockname_unix_prog__destroy(skel); -} - -static void *getpeername_unix_prog_load(int cgroup_fd) -{ - struct getpeername_unix_prog *skel; - - skel = getpeername_unix_prog__open_and_load(); - if (!ASSERT_OK_PTR(skel, "skel_open")) - goto cleanup; - - skel->links.getpeername_unix_prog = bpf_program__attach_cgroup( - skel->progs.getpeername_unix_prog, cgroup_fd); - if (!ASSERT_OK_PTR(skel->links.getpeername_unix_prog, "prog_attach")) - goto cleanup; - - return skel; -cleanup: - getpeername_unix_prog__destroy(skel); - return NULL; -} - -static void getpeername_unix_prog_destroy(void *skel) -{ - getpeername_unix_prog__destroy(skel); -} +BPF_SKEL_FUNCS(bind4_prog, bind_v4_prog); +BPF_SKEL_FUNCS_RAW(bind4_prog, bind_v4_prog); +BPF_SKEL_FUNCS(bind4_prog, bind_v4_deny_prog); +BPF_SKEL_FUNCS(bind6_prog, bind_v6_prog); +BPF_SKEL_FUNCS_RAW(bind6_prog, bind_v6_prog); +BPF_SKEL_FUNCS(bind6_prog, bind_v6_deny_prog); +BPF_SKEL_FUNCS(connect4_prog, connect_v4_prog); +BPF_SKEL_FUNCS_RAW(connect4_prog, connect_v4_prog); +BPF_SKEL_FUNCS(connect4_prog, connect_v4_deny_prog); +BPF_SKEL_FUNCS(connect6_prog, connect_v6_prog); +BPF_SKEL_FUNCS_RAW(connect6_prog, connect_v6_prog); +BPF_SKEL_FUNCS(connect6_prog, connect_v6_deny_prog); +BPF_SKEL_FUNCS(connect_unix_prog, connect_unix_prog); +BPF_SKEL_FUNCS_RAW(connect_unix_prog, connect_unix_prog); +BPF_SKEL_FUNCS(connect_unix_prog, connect_unix_deny_prog); +BPF_SKEL_FUNCS(sendmsg4_prog, sendmsg_v4_prog); +BPF_SKEL_FUNCS_RAW(sendmsg4_prog, sendmsg_v4_prog); +BPF_SKEL_FUNCS(sendmsg4_prog, sendmsg_v4_deny_prog); +BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_prog); +BPF_SKEL_FUNCS_RAW(sendmsg6_prog, sendmsg_v6_prog); +BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_deny_prog); +BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_preserve_dst_prog); +BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_v4mapped_prog); +BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_wildcard_prog); +BPF_SKEL_FUNCS(sendmsg_unix_prog, sendmsg_unix_prog); +BPF_SKEL_FUNCS_RAW(sendmsg_unix_prog, sendmsg_unix_prog); +BPF_SKEL_FUNCS(sendmsg_unix_prog, sendmsg_unix_deny_prog); +BPF_SKEL_FUNCS(recvmsg4_prog, recvmsg4_prog); +BPF_SKEL_FUNCS_RAW(recvmsg4_prog, recvmsg4_prog); +BPF_SKEL_FUNCS(recvmsg6_prog, recvmsg6_prog); +BPF_SKEL_FUNCS_RAW(recvmsg6_prog, recvmsg6_prog); +BPF_SKEL_FUNCS(recvmsg_unix_prog, recvmsg_unix_prog); +BPF_SKEL_FUNCS_RAW(recvmsg_unix_prog, recvmsg_unix_prog); +BPF_SKEL_FUNCS(getsockname_unix_prog, getsockname_unix_prog); +BPF_SKEL_FUNCS_RAW(getsockname_unix_prog, getsockname_unix_prog); +BPF_SKEL_FUNCS(getsockname4_prog, getsockname_v4_prog); +BPF_SKEL_FUNCS_RAW(getsockname4_prog, getsockname_v4_prog); +BPF_SKEL_FUNCS(getsockname6_prog, getsockname_v6_prog); +BPF_SKEL_FUNCS_RAW(getsockname6_prog, getsockname_v6_prog); +BPF_SKEL_FUNCS(getpeername_unix_prog, getpeername_unix_prog); +BPF_SKEL_FUNCS_RAW(getpeername_unix_prog, getpeername_unix_prog); +BPF_SKEL_FUNCS(getpeername4_prog, getpeername_v4_prog); +BPF_SKEL_FUNCS_RAW(getpeername4_prog, getpeername_v4_prog); +BPF_SKEL_FUNCS(getpeername6_prog, getpeername_v6_prog); +BPF_SKEL_FUNCS_RAW(getpeername6_prog, getpeername_v6_prog); static struct sock_addr_test tests[] = { + /* bind - system calls */ + { + SOCK_ADDR_TEST_BIND, + "bind4: bind (stream)", + bind_v4_prog_load, + bind_v4_prog_destroy, + BPF_CGROUP_INET4_BIND, + &user_ops, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: bind deny (stream)", + bind_v4_deny_prog_load, + bind_v4_deny_prog_destroy, + BPF_CGROUP_INET4_BIND, + &user_ops, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: bind (dgram)", + bind_v4_prog_load, + bind_v4_prog_destroy, + BPF_CGROUP_INET4_BIND, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: bind deny (dgram)", + bind_v4_deny_prog_load, + bind_v4_deny_prog_destroy, + BPF_CGROUP_INET4_BIND, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: load prog with wrong expected attach type", + bind_v4_prog_load, + bind_v4_prog_destroy, + BPF_CGROUP_INET6_BIND, + &user_ops, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: attach prog with wrong attach type", + bind_v4_prog_load_raw, + bind_v4_prog_destroy_raw, + BPF_CGROUP_INET6_BIND, + &user_ops, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: bind (stream)", + bind_v6_prog_load, + bind_v6_prog_destroy, + BPF_CGROUP_INET6_BIND, + &user_ops, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: bind deny (stream)", + bind_v6_deny_prog_load, + bind_v6_deny_prog_destroy, + BPF_CGROUP_INET6_BIND, + &user_ops, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: bind (dgram)", + bind_v6_prog_load, + bind_v6_prog_destroy, + BPF_CGROUP_INET6_BIND, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: bind deny (dgram)", + bind_v6_deny_prog_load, + bind_v6_deny_prog_destroy, + BPF_CGROUP_INET6_BIND, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: load prog with wrong expected attach type", + bind_v6_prog_load, + bind_v6_prog_destroy, + BPF_CGROUP_INET4_BIND, + &user_ops, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: attach prog with wrong attach type", + bind_v6_prog_load_raw, + bind_v6_prog_destroy_raw, + BPF_CGROUP_INET4_BIND, + &user_ops, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + + /* bind - kernel calls */ + { + SOCK_ADDR_TEST_BIND, + "bind4: kernel_bind (stream)", + bind_v4_prog_load, + bind_v4_prog_destroy, + BPF_CGROUP_INET4_BIND, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: kernel_bind deny (stream)", + bind_v4_deny_prog_load, + bind_v4_deny_prog_destroy, + BPF_CGROUP_INET4_BIND, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: kernel_bind (dgram)", + bind_v4_prog_load, + bind_v4_prog_destroy, + BPF_CGROUP_INET4_BIND, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind4: kernel_bind deny (dgram)", + bind_v4_deny_prog_load, + bind_v4_deny_prog_destroy, + BPF_CGROUP_INET4_BIND, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: kernel_bind (stream)", + bind_v6_prog_load, + bind_v6_prog_destroy, + BPF_CGROUP_INET6_BIND, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: kernel_bind deny (stream)", + bind_v6_deny_prog_load, + bind_v6_deny_prog_destroy, + BPF_CGROUP_INET6_BIND, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: kernel_bind (dgram)", + bind_v6_prog_load, + bind_v6_prog_destroy, + BPF_CGROUP_INET6_BIND, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_BIND, + "bind6: kernel_bind deny (dgram)", + bind_v6_deny_prog_load, + bind_v6_deny_prog_destroy, + BPF_CGROUP_INET6_BIND, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SYSCALL_EPERM, + }, + + /* connect - system calls */ { SOCK_ADDR_TEST_CONNECT, - "connect_unix", + "connect4: connect (stream)", + connect_v4_prog_load, + connect_v4_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &user_ops, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: connect deny (stream)", + connect_v4_deny_prog_load, + connect_v4_deny_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &user_ops, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: connect (dgram)", + connect_v4_prog_load, + connect_v4_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: connect deny (dgram)", + connect_v4_deny_prog_load, + connect_v4_deny_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: load prog with wrong expected attach type", + connect_v4_prog_load, + connect_v4_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &user_ops, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: attach prog with wrong attach type", + connect_v4_prog_load_raw, + connect_v4_prog_destroy_raw, + BPF_CGROUP_INET6_CONNECT, + &user_ops, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: connect (stream)", + connect_v6_prog_load, + connect_v6_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &user_ops, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: connect deny (stream)", + connect_v6_deny_prog_load, + connect_v6_deny_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &user_ops, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: connect (dgram)", + connect_v6_prog_load, + connect_v6_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: connect deny (dgram)", + connect_v6_deny_prog_load, + connect_v6_deny_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: load prog with wrong expected attach type", + connect_v6_prog_load, + connect_v6_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &user_ops, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: attach prog with wrong attach type", + connect_v6_prog_load_raw, + connect_v6_prog_destroy_raw, + BPF_CGROUP_INET4_CONNECT, + &user_ops, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect_unix: connect (stream)", connect_unix_prog_load, connect_unix_prog_destroy, + BPF_CGROUP_UNIX_CONNECT, + &user_ops, AF_UNIX, SOCK_STREAM, SERVUN_ADDRESS, @@ -176,12 +1019,387 @@ static struct sock_addr_test tests[] = { SERVUN_REWRITE_ADDRESS, 0, NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect_unix: connect deny (stream)", + connect_unix_deny_prog_load, + connect_unix_deny_prog_destroy, + BPF_CGROUP_UNIX_CONNECT, + &user_ops, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect_unix: attach prog with wrong attach type", + connect_unix_prog_load_raw, + connect_unix_prog_destroy_raw, + BPF_CGROUP_INET4_CONNECT, + &user_ops, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + ATTACH_REJECT, + }, + + /* connect - kernel calls */ + { + SOCK_ADDR_TEST_CONNECT, + "connect4: kernel_connect (stream)", + connect_v4_prog_load, + connect_v4_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: kernel_connect deny (stream)", + connect_v4_deny_prog_load, + connect_v4_deny_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: kernel_connect (dgram)", + connect_v4_prog_load, + connect_v4_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect4: kernel_connect deny (dgram)", + connect_v4_deny_prog_load, + connect_v4_deny_prog_destroy, + BPF_CGROUP_INET4_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: kernel_connect (stream)", + connect_v6_prog_load, + connect_v6_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: kernel_connect deny (stream)", + connect_v6_deny_prog_load, + connect_v6_deny_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: kernel_connect (dgram)", + connect_v6_prog_load, + connect_v6_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect6: kernel_connect deny (dgram)", + connect_v6_deny_prog_load, + connect_v6_deny_prog_destroy, + BPF_CGROUP_INET6_CONNECT, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect_unix: kernel_connect (dgram)", + connect_unix_prog_load, + connect_unix_prog_destroy, + BPF_CGROUP_UNIX_CONNECT, + &kern_ops_sock_sendmsg, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_CONNECT, + "connect_unix: kernel_connect deny (dgram)", + connect_unix_deny_prog_load, + connect_unix_deny_prog_destroy, + BPF_CGROUP_UNIX_CONNECT, + &kern_ops_sock_sendmsg, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SYSCALL_EPERM, + }, + + /* sendmsg - system calls */ + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg4: sendmsg (dgram)", + sendmsg_v4_prog_load, + sendmsg_v4_prog_destroy, + BPF_CGROUP_UDP4_SENDMSG, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, }, { SOCK_ADDR_TEST_SENDMSG, - "sendmsg_unix", + "sendmsg4: sendmsg deny (dgram)", + sendmsg_v4_deny_prog_load, + sendmsg_v4_deny_prog_destroy, + BPF_CGROUP_UDP4_SENDMSG, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg4: load prog with wrong expected attach type", + sendmsg_v4_prog_load, + sendmsg_v4_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &user_ops, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg4: attach prog with wrong attach type", + sendmsg_v4_prog_load_raw, + sendmsg_v4_prog_destroy_raw, + BPF_CGROUP_UDP6_SENDMSG, + &user_ops, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sendmsg (dgram)", + sendmsg_v6_prog_load, + sendmsg_v6_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sendmsg [::] (BSD'ism) (dgram)", + sendmsg_v6_preserve_dst_prog_load, + sendmsg_v6_preserve_dst_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + WILDCARD6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_PORT, + SRC6_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sendmsg deny (dgram)", + sendmsg_v6_deny_prog_load, + sendmsg_v6_deny_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sendmsg IPv4-mapped IPv6 (dgram)", + sendmsg_v6_v4mapped_prog_load, + sendmsg_v6_v4mapped_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_ENOTSUPP, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sendmsg dst IP = [::] (BSD'ism) (dgram)", + sendmsg_v6_wildcard_prog_load, + sendmsg_v6_wildcard_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: load prog with wrong expected attach type", + sendmsg_v6_prog_load, + sendmsg_v6_prog_destroy, + BPF_CGROUP_UDP4_SENDMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: attach prog with wrong attach type", + sendmsg_v6_prog_load_raw, + sendmsg_v6_prog_destroy_raw, + BPF_CGROUP_UDP4_SENDMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg_unix: sendmsg (dgram)", sendmsg_unix_prog_load, sendmsg_unix_prog_destroy, + BPF_CGROUP_UNIX_SENDMSG, + &user_ops, AF_UNIX, SOCK_DGRAM, SERVUN_ADDRESS, @@ -189,12 +1407,341 @@ static struct sock_addr_test tests[] = { SERVUN_REWRITE_ADDRESS, 0, NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg_unix: sendmsg deny (dgram)", + sendmsg_unix_deny_prog_load, + sendmsg_unix_deny_prog_destroy, + BPF_CGROUP_UNIX_SENDMSG, + &user_ops, + AF_UNIX, + SOCK_DGRAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg_unix: attach prog with wrong attach type", + sendmsg_unix_prog_load_raw, + sendmsg_unix_prog_destroy_raw, + BPF_CGROUP_UDP4_SENDMSG, + &user_ops, + AF_UNIX, + SOCK_DGRAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + ATTACH_REJECT, + }, + + /* sendmsg - kernel calls (sock_sendmsg) */ + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg4: sock_sendmsg (dgram)", + sendmsg_v4_prog_load, + sendmsg_v4_prog_destroy, + BPF_CGROUP_UDP4_SENDMSG, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg4: sock_sendmsg deny (dgram)", + sendmsg_v4_deny_prog_load, + sendmsg_v4_deny_prog_destroy, + BPF_CGROUP_UDP4_SENDMSG, + &kern_ops_sock_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sock_sendmsg (dgram)", + sendmsg_v6_prog_load, + sendmsg_v6_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sock_sendmsg [::] (BSD'ism) (dgram)", + sendmsg_v6_preserve_dst_prog_load, + sendmsg_v6_preserve_dst_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_DGRAM, + WILDCARD6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_PORT, + SRC6_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: sock_sendmsg deny (dgram)", + sendmsg_v6_deny_prog_load, + sendmsg_v6_deny_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &kern_ops_sock_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg_unix: sock_sendmsg (dgram)", + sendmsg_unix_prog_load, + sendmsg_unix_prog_destroy, + BPF_CGROUP_UNIX_SENDMSG, + &kern_ops_sock_sendmsg, + AF_UNIX, + SOCK_DGRAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg_unix: sock_sendmsg deny (dgram)", + sendmsg_unix_deny_prog_load, + sendmsg_unix_deny_prog_destroy, + BPF_CGROUP_UNIX_SENDMSG, + &kern_ops_sock_sendmsg, + AF_UNIX, + SOCK_DGRAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SYSCALL_EPERM, + }, + + /* sendmsg - kernel calls (kernel_sendmsg) */ + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg4: kernel_sendmsg (dgram)", + sendmsg_v4_prog_load, + sendmsg_v4_prog_destroy, + BPF_CGROUP_UDP4_SENDMSG, + &kern_ops_kernel_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg4: kernel_sendmsg deny (dgram)", + sendmsg_v4_deny_prog_load, + sendmsg_v4_deny_prog_destroy, + BPF_CGROUP_UDP4_SENDMSG, + &kern_ops_kernel_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: kernel_sendmsg (dgram)", + sendmsg_v6_prog_load, + sendmsg_v6_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &kern_ops_kernel_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: kernel_sendmsg [::] (BSD'ism) (dgram)", + sendmsg_v6_preserve_dst_prog_load, + sendmsg_v6_preserve_dst_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &kern_ops_kernel_sendmsg, + AF_INET6, + SOCK_DGRAM, + WILDCARD6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_PORT, + SRC6_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg6: kernel_sendmsg deny (dgram)", + sendmsg_v6_deny_prog_load, + sendmsg_v6_deny_prog_destroy, + BPF_CGROUP_UDP6_SENDMSG, + &kern_ops_kernel_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg_unix: sock_sendmsg (dgram)", + sendmsg_unix_prog_load, + sendmsg_unix_prog_destroy, + BPF_CGROUP_UNIX_SENDMSG, + &kern_ops_kernel_sendmsg, + AF_UNIX, + SOCK_DGRAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_SENDMSG, + "sendmsg_unix: kernel_sendmsg deny (dgram)", + sendmsg_unix_deny_prog_load, + sendmsg_unix_deny_prog_destroy, + BPF_CGROUP_UNIX_SENDMSG, + &kern_ops_kernel_sendmsg, + AF_UNIX, + SOCK_DGRAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SYSCALL_EPERM, + }, + + /* recvmsg - system calls */ + { + SOCK_ADDR_TEST_RECVMSG, + "recvmsg4: recvfrom (dgram)", + recvmsg4_prog_load, + recvmsg4_prog_destroy, + BPF_CGROUP_UDP4_RECVMSG, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SUCCESS, }, { SOCK_ADDR_TEST_RECVMSG, - "recvmsg_unix-dgram", + "recvmsg4: attach prog with wrong attach type", + recvmsg4_prog_load_raw, + recvmsg4_prog_destroy_raw, + BPF_CGROUP_UDP6_RECVMSG, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_RECVMSG, + "recvmsg6: recvfrom (dgram)", + recvmsg6_prog_load, + recvmsg6_prog_destroy, + BPF_CGROUP_UDP6_RECVMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SUCCESS, + }, + { + SOCK_ADDR_TEST_RECVMSG, + "recvmsg6: attach prog with wrong attach type", + recvmsg6_prog_load_raw, + recvmsg6_prog_destroy_raw, + BPF_CGROUP_UDP4_RECVMSG, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_RECVMSG, + "recvmsg_unix: recvfrom (dgram)", recvmsg_unix_prog_load, recvmsg_unix_prog_destroy, + BPF_CGROUP_UNIX_RECVMSG, + &user_ops, AF_UNIX, SOCK_DGRAM, SERVUN_REWRITE_ADDRESS, @@ -202,12 +1749,15 @@ static struct sock_addr_test tests[] = { SERVUN_REWRITE_ADDRESS, 0, SERVUN_ADDRESS, + SUCCESS, }, { SOCK_ADDR_TEST_RECVMSG, - "recvmsg_unix-stream", + "recvmsg_unix: recvfrom (stream)", recvmsg_unix_prog_load, recvmsg_unix_prog_destroy, + BPF_CGROUP_UNIX_RECVMSG, + &user_ops, AF_UNIX, SOCK_STREAM, SERVUN_REWRITE_ADDRESS, @@ -215,12 +1765,129 @@ static struct sock_addr_test tests[] = { SERVUN_REWRITE_ADDRESS, 0, SERVUN_ADDRESS, + SUCCESS, + }, + { + SOCK_ADDR_TEST_RECVMSG, + "recvmsg_unix: attach prog with wrong attach type", + recvmsg_unix_prog_load_raw, + recvmsg_unix_prog_destroy_raw, + BPF_CGROUP_UDP4_RECVMSG, + &user_ops, + AF_INET6, + SOCK_STREAM, + SERVUN_REWRITE_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + SERVUN_ADDRESS, + ATTACH_REJECT, + }, + + /* getsockname - system calls */ + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname4: getsockname (stream)", + getsockname_v4_prog_load, + getsockname_v4_prog_destroy, + BPF_CGROUP_INET4_GETSOCKNAME, + &user_ops, + AF_INET, + SOCK_STREAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, }, { SOCK_ADDR_TEST_GETSOCKNAME, - "getsockname_unix", + "getsockname4: getsockname (dgram)", + getsockname_v4_prog_load, + getsockname_v4_prog_destroy, + BPF_CGROUP_INET4_GETSOCKNAME, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname4: attach prog with wrong attach type", + getsockname_v4_prog_load_raw, + getsockname_v4_prog_destroy_raw, + BPF_CGROUP_INET6_GETSOCKNAME, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname6: getsockname (stream)", + getsockname_v6_prog_load, + getsockname_v6_prog_destroy, + BPF_CGROUP_INET6_GETSOCKNAME, + &user_ops, + AF_INET6, + SOCK_STREAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname6: getsockname (dgram)", + getsockname_v6_prog_load, + getsockname_v6_prog_destroy, + BPF_CGROUP_INET6_GETSOCKNAME, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname6: attach prog with wrong attach type", + getsockname_v6_prog_load_raw, + getsockname_v6_prog_destroy_raw, + BPF_CGROUP_INET4_GETSOCKNAME, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname_unix: getsockname", getsockname_unix_prog_load, getsockname_unix_prog_destroy, + BPF_CGROUP_UNIX_GETSOCKNAME, + &user_ops, AF_UNIX, SOCK_STREAM, SERVUN_ADDRESS, @@ -228,12 +1895,211 @@ static struct sock_addr_test tests[] = { SERVUN_REWRITE_ADDRESS, 0, NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname_unix: attach prog with wrong attach type", + getsockname_unix_prog_load_raw, + getsockname_unix_prog_destroy_raw, + BPF_CGROUP_INET4_GETSOCKNAME, + &user_ops, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + ATTACH_REJECT, + }, + + /* getsockname - kernel calls */ + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname4: kernel_getsockname (stream)", + getsockname_v4_prog_load, + getsockname_v4_prog_destroy, + BPF_CGROUP_INET4_GETSOCKNAME, + &kern_ops_kernel_sendmsg, + AF_INET, + SOCK_STREAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname4: kernel_getsockname (dgram)", + getsockname_v4_prog_load, + getsockname_v4_prog_destroy, + BPF_CGROUP_INET4_GETSOCKNAME, + &kern_ops_kernel_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname6: kernel_getsockname (stream)", + getsockname_v6_prog_load, + getsockname_v6_prog_destroy, + BPF_CGROUP_INET6_GETSOCKNAME, + &kern_ops_kernel_sendmsg, + AF_INET6, + SOCK_STREAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname6: kernel_getsockname (dgram)", + getsockname_v6_prog_load, + getsockname_v6_prog_destroy, + BPF_CGROUP_INET6_GETSOCKNAME, + &kern_ops_kernel_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETSOCKNAME, + "getsockname_unix: kernel_getsockname", + getsockname_unix_prog_load, + getsockname_unix_prog_destroy, + BPF_CGROUP_UNIX_GETSOCKNAME, + &kern_ops_kernel_sendmsg, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SUCCESS, + }, + + /* getpeername - system calls */ + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername4: getpeername (stream)", + getpeername_v4_prog_load, + getpeername_v4_prog_destroy, + BPF_CGROUP_INET4_GETPEERNAME, + &user_ops, + AF_INET, + SOCK_STREAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, }, { SOCK_ADDR_TEST_GETPEERNAME, - "getpeername_unix", + "getpeername4: getpeername (dgram)", + getpeername_v4_prog_load, + getpeername_v4_prog_destroy, + BPF_CGROUP_INET4_GETPEERNAME, + &user_ops, + AF_INET, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername4: attach prog with wrong attach type", + getpeername_v4_prog_load_raw, + getpeername_v4_prog_destroy_raw, + BPF_CGROUP_INET6_GETSOCKNAME, + &user_ops, + AF_UNIX, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername6: getpeername (stream)", + getpeername_v6_prog_load, + getpeername_v6_prog_destroy, + BPF_CGROUP_INET6_GETPEERNAME, + &user_ops, + AF_INET6, + SOCK_STREAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername6: getpeername (dgram)", + getpeername_v6_prog_load, + getpeername_v6_prog_destroy, + BPF_CGROUP_INET6_GETPEERNAME, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername6: attach prog with wrong attach type", + getpeername_v6_prog_load_raw, + getpeername_v6_prog_destroy_raw, + BPF_CGROUP_INET4_GETSOCKNAME, + &user_ops, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + ATTACH_REJECT, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername_unix: getpeername", getpeername_unix_prog_load, getpeername_unix_prog_destroy, + BPF_CGROUP_UNIX_GETPEERNAME, + &user_ops, AF_UNIX, SOCK_STREAM, SERVUN_ADDRESS, @@ -241,6 +2107,105 @@ static struct sock_addr_test tests[] = { SERVUN_REWRITE_ADDRESS, 0, NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername_unix: attach prog with wrong attach type", + getpeername_unix_prog_load_raw, + getpeername_unix_prog_destroy_raw, + BPF_CGROUP_INET4_GETSOCKNAME, + &user_ops, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + ATTACH_REJECT, + }, + + /* getpeername - kernel calls */ + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername4: kernel_getpeername (stream)", + getpeername_v4_prog_load, + getpeername_v4_prog_destroy, + BPF_CGROUP_INET4_GETPEERNAME, + &kern_ops_kernel_sendmsg, + AF_INET, + SOCK_STREAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername4: kernel_getpeername (dgram)", + getpeername_v4_prog_load, + getpeername_v4_prog_destroy, + BPF_CGROUP_INET4_GETPEERNAME, + &kern_ops_kernel_sendmsg, + AF_INET, + SOCK_DGRAM, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SERV4_IP, + SERV4_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername6: kernel_getpeername (stream)", + getpeername_v6_prog_load, + getpeername_v6_prog_destroy, + BPF_CGROUP_INET6_GETPEERNAME, + &kern_ops_kernel_sendmsg, + AF_INET6, + SOCK_STREAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername6: kernel_getpeername (dgram)", + getpeername_v6_prog_load, + getpeername_v6_prog_destroy, + BPF_CGROUP_INET6_GETPEERNAME, + &kern_ops_kernel_sendmsg, + AF_INET6, + SOCK_DGRAM, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SERV6_IP, + SERV6_PORT, + NULL, + SUCCESS, + }, + { + SOCK_ADDR_TEST_GETPEERNAME, + "getpeername_unix: kernel_getpeername", + getpeername_unix_prog_load, + getpeername_unix_prog_destroy, + BPF_CGROUP_UNIX_GETPEERNAME, + &kern_ops_kernel_sendmsg, + AF_UNIX, + SOCK_STREAM, + SERVUN_ADDRESS, + 0, + SERVUN_REWRITE_ADDRESS, + 0, + NULL, + SUCCESS, }, }; @@ -294,28 +2259,40 @@ static int cmp_sock_addr(info_fn fn, int sock1, return cmp_addr(&addr1, len1, addr2, addr2_len, cmp_port); } -static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2, - socklen_t addr2_len, bool cmp_port) +static int load_sock_addr_kern(void) { - return cmp_sock_addr(getsockname, sock1, addr2, addr2_len, cmp_port); + int err; + + skel = sock_addr_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel")) + goto err; + + err = 0; + goto out; +err: + err = -1; +out: + return err; } -static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2, - socklen_t addr2_len, bool cmp_port) +static void unload_sock_addr_kern(void) { - return cmp_sock_addr(getpeername, sock1, addr2, addr2_len, cmp_port); + sock_addr_kern__destroy(skel); } -static void test_bind(struct sock_addr_test *test) +static int test_bind(struct sock_addr_test *test) { struct sockaddr_storage expected_addr; socklen_t expected_addr_len = sizeof(struct sockaddr_storage); int serv = -1, client = -1, err; - serv = start_server(test->socket_family, test->socket_type, - test->requested_addr, test->requested_port, 0); - if (!ASSERT_GE(serv, 0, "start_server")) - goto cleanup; + serv = test->ops->start_server(test->socket_family, test->socket_type, + test->requested_addr, + test->requested_port, 0); + if (serv < 0) { + err = errno; + goto err; + } err = make_sockaddr(test->socket_family, test->expected_addr, test->expected_port, @@ -323,7 +2300,8 @@ static void test_bind(struct sock_addr_test *test) if (!ASSERT_EQ(err, 0, "make_sockaddr")) goto cleanup; - err = cmp_local_addr(serv, &expected_addr, expected_addr_len, true); + err = cmp_sock_addr(test->ops->getsockname, serv, &expected_addr, + expected_addr_len, true); if (!ASSERT_EQ(err, 0, "cmp_local_addr")) goto cleanup; @@ -333,13 +2311,17 @@ static void test_bind(struct sock_addr_test *test) goto cleanup; cleanup: + err = 0; +err: if (client != -1) close(client); if (serv != -1) - close(serv); + test->ops->close(serv); + + return err; } -static void test_connect(struct sock_addr_test *test) +static int test_connect(struct sock_addr_test *test) { struct sockaddr_storage addr, expected_addr, expected_src_addr; socklen_t addr_len = sizeof(struct sockaddr_storage), @@ -357,9 +2339,12 @@ static void test_connect(struct sock_addr_test *test) if (!ASSERT_EQ(err, 0, "make_sockaddr")) goto cleanup; - client = connect_to_addr(test->socket_type, &addr, addr_len, NULL); - if (!ASSERT_GE(client, 0, "connect_to_addr")) - goto cleanup; + client = test->ops->connect_to_addr(test->socket_type, &addr, addr_len, + NULL); + if (client < 0) { + err = errno; + goto err; + } err = make_sockaddr(test->socket_family, test->expected_addr, test->expected_port, &expected_addr, &expected_addr_len); @@ -373,29 +2358,34 @@ static void test_connect(struct sock_addr_test *test) goto cleanup; } - err = cmp_peer_addr(client, &expected_addr, expected_addr_len, true); + err = cmp_sock_addr(test->ops->getpeername, client, &expected_addr, + expected_addr_len, true); if (!ASSERT_EQ(err, 0, "cmp_peer_addr")) goto cleanup; if (test->expected_src_addr) { - err = cmp_local_addr(client, &expected_src_addr, expected_src_addr_len, false); + err = cmp_sock_addr(test->ops->getsockname, client, + &expected_src_addr, expected_src_addr_len, + false); if (!ASSERT_EQ(err, 0, "cmp_local_addr")) goto cleanup; } cleanup: + err = 0; +err: if (client != -1) - close(client); + test->ops->close(client); if (serv != -1) close(serv); + + return err; } -static void test_xmsg(struct sock_addr_test *test) +static int test_xmsg(struct sock_addr_test *test) { struct sockaddr_storage addr, src_addr; socklen_t addr_len = sizeof(struct sockaddr_storage), src_addr_len = sizeof(struct sockaddr_storage); - struct msghdr hdr; - struct iovec iov; char data = 'a'; int serv = -1, client = -1, err; @@ -408,7 +2398,7 @@ static void test_xmsg(struct sock_addr_test *test) if (!ASSERT_GE(serv, 0, "start_server")) goto cleanup; - client = socket(test->socket_family, test->socket_type, 0); + client = test->ops->socket(test->socket_family, test->socket_type, 0); if (!ASSERT_GE(client, 0, "socket")) goto cleanup; @@ -418,7 +2408,8 @@ static void test_xmsg(struct sock_addr_test *test) if (!ASSERT_EQ(err, 0, "make_sockaddr")) goto cleanup; - err = bind(client, (const struct sockaddr *) &src_addr, src_addr_len); + err = test->ops->bind(client, (struct sockaddr *)&src_addr, + src_addr_len); if (!ASSERT_OK(err, "bind")) goto cleanup; } @@ -429,17 +2420,13 @@ static void test_xmsg(struct sock_addr_test *test) goto cleanup; if (test->socket_type == SOCK_DGRAM) { - memset(&iov, 0, sizeof(iov)); - iov.iov_base = &data; - iov.iov_len = sizeof(data); + err = test->ops->sendmsg(client, (struct sockaddr *)&addr, + addr_len, &data, sizeof(data)); + if (err < 0) { + err = errno; + goto err; + } - memset(&hdr, 0, sizeof(hdr)); - hdr.msg_name = (void *)&addr; - hdr.msg_namelen = addr_len; - hdr.msg_iov = &iov; - hdr.msg_iovlen = 1; - - err = sendmsg(client, &hdr, 0); if (!ASSERT_EQ(err, sizeof(data), "sendmsg")) goto cleanup; } else { @@ -489,19 +2476,23 @@ static void test_xmsg(struct sock_addr_test *test) } cleanup: + err = 0; +err: if (client != -1) - close(client); + test->ops->close(client); if (serv != -1) close(serv); + + return err; } -static void test_getsockname(struct sock_addr_test *test) +static int test_getsockname(struct sock_addr_test *test) { struct sockaddr_storage expected_addr; socklen_t expected_addr_len = sizeof(struct sockaddr_storage); int serv = -1, err; - serv = start_server(test->socket_family, test->socket_type, + serv = test->ops->start_server(test->socket_family, test->socket_type, test->requested_addr, test->requested_port, 0); if (!ASSERT_GE(serv, 0, "start_server")) goto cleanup; @@ -512,16 +2503,18 @@ static void test_getsockname(struct sock_addr_test *test) if (!ASSERT_EQ(err, 0, "make_sockaddr")) goto cleanup; - err = cmp_local_addr(serv, &expected_addr, expected_addr_len, true); + err = cmp_sock_addr(test->ops->getsockname, serv, &expected_addr, expected_addr_len, true); if (!ASSERT_EQ(err, 0, "cmp_local_addr")) goto cleanup; cleanup: if (serv != -1) - close(serv); + test->ops->close(serv); + + return 0; } -static void test_getpeername(struct sock_addr_test *test) +static int test_getpeername(struct sock_addr_test *test) { struct sockaddr_storage addr, expected_addr; socklen_t addr_len = sizeof(struct sockaddr_storage), @@ -538,7 +2531,8 @@ static void test_getpeername(struct sock_addr_test *test) if (!ASSERT_EQ(err, 0, "make_sockaddr")) goto cleanup; - client = connect_to_addr(test->socket_type, &addr, addr_len, NULL); + client = test->ops->connect_to_addr(test->socket_type, &addr, addr_len, + NULL); if (!ASSERT_GE(client, 0, "connect_to_addr")) goto cleanup; @@ -547,19 +2541,58 @@ static void test_getpeername(struct sock_addr_test *test) if (!ASSERT_EQ(err, 0, "make_sockaddr")) goto cleanup; - err = cmp_peer_addr(client, &expected_addr, expected_addr_len, true); + err = cmp_sock_addr(test->ops->getpeername, client, &expected_addr, + expected_addr_len, true); if (!ASSERT_EQ(err, 0, "cmp_peer_addr")) goto cleanup; cleanup: if (client != -1) - close(client); + test->ops->close(client); if (serv != -1) close(serv); + + return 0; +} + +static int setup_test_env(struct nstoken **tok) +{ + int err; + + SYS_NOFAIL("ip netns delete %s", TEST_NS); + SYS(fail, "ip netns add %s", TEST_NS); + *tok = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(*tok, "netns token")) + goto fail; + + SYS(fail, "ip link add dev %s1 type veth peer name %s2", TEST_IF_PREFIX, + TEST_IF_PREFIX); + SYS(fail, "ip link set lo up"); + SYS(fail, "ip link set %s1 up", TEST_IF_PREFIX); + SYS(fail, "ip link set %s2 up", TEST_IF_PREFIX); + SYS(fail, "ip -4 addr add %s/8 dev %s1", TEST_IPV4, TEST_IF_PREFIX); + SYS(fail, "ip -6 addr add %s/128 nodad dev %s1", TEST_IPV6, TEST_IF_PREFIX); + + err = 0; + goto out; +fail: + err = -1; + close_netns(*tok); + *tok = NULL; + SYS_NOFAIL("ip netns delete %s", TEST_NS); +out: + return err; +} + +static void cleanup_test_env(struct nstoken *tok) +{ + close_netns(tok); + SYS_NOFAIL("ip netns delete %s", TEST_NS); } void test_sock_addr(void) { + struct nstoken *tok = NULL; int cgroup_fd = -1; void *skel; @@ -567,13 +2600,22 @@ void test_sock_addr(void) if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup")) goto cleanup; + if (!ASSERT_OK(setup_test_env(&tok), "setup_test_env")) + goto cleanup; + + if (!ASSERT_OK(load_sock_addr_kern(), "load_sock_addr_kern")) + goto cleanup; + for (size_t i = 0; i < ARRAY_SIZE(tests); ++i) { struct sock_addr_test *test = &tests[i]; + int err; if (!test__start_subtest(test->name)) continue; - skel = test->loadfn(cgroup_fd); + skel = test->loadfn(cgroup_fd, test->attach_type, + test->expected_result == LOAD_REJECT || + test->expected_result == ATTACH_REJECT); if (!skel) continue; @@ -583,30 +2625,39 @@ void test_sock_addr(void) * the future. */ case SOCK_ADDR_TEST_BIND: - test_bind(test); + err = test_bind(test); break; case SOCK_ADDR_TEST_CONNECT: - test_connect(test); + err = test_connect(test); break; case SOCK_ADDR_TEST_SENDMSG: case SOCK_ADDR_TEST_RECVMSG: - test_xmsg(test); + err = test_xmsg(test); break; case SOCK_ADDR_TEST_GETSOCKNAME: - test_getsockname(test); + err = test_getsockname(test); break; case SOCK_ADDR_TEST_GETPEERNAME: - test_getpeername(test); + err = test_getpeername(test); break; default: ASSERT_TRUE(false, "Unknown sock addr test type"); break; } + if (test->expected_result == SYSCALL_EPERM) + ASSERT_EQ(err, EPERM, "socket operation returns EPERM"); + else if (test->expected_result == SYSCALL_ENOTSUPP) + ASSERT_EQ(err, ENOTSUPP, "socket operation returns ENOTSUPP"); + else if (test->expected_result == SUCCESS) + ASSERT_OK(err, "socket operation succeeds"); + test->destroyfn(skel); } cleanup: + unload_sock_addr_kern(); + cleanup_test_env(tok); if (cgroup_fd >= 0) close(cgroup_fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 917f486db826..1d3a20f01b60 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include "cgroup_helpers.h" +#include "network_helpers.h" #include "sockopt_inherit.skel.h" @@ -9,35 +10,6 @@ #define CUSTOM_INHERIT2 1 #define CUSTOM_LISTENER 2 -static int connect_to_server(int server_fd) -{ - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int fd; - - fd = socket(AF_INET, SOCK_STREAM, 0); - if (fd < 0) { - log_err("Failed to create client socket"); - return -1; - } - - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - goto out; - } - - if (connect(fd, (const struct sockaddr *)&addr, len) < 0) { - log_err("Fail to connect to server"); - goto out; - } - - return fd; - -out: - close(fd); - return -1; -} - static int verify_sockopt(int fd, int optname, const char *msg, char expected) { socklen_t optlen = 1; @@ -98,47 +70,36 @@ static void *server_thread(void *arg) return (void *)(long)err; } -static int start_server(void) +static int custom_cb(int fd, const struct post_socket_opts *opts) { - struct sockaddr_in addr = { - .sin_family = AF_INET, - .sin_addr.s_addr = htonl(INADDR_LOOPBACK), - }; char buf; int err; - int fd; int i; - fd = socket(AF_INET, SOCK_STREAM, 0); - if (fd < 0) { - log_err("Failed to create server socket"); - return -1; - } - for (i = CUSTOM_INHERIT1; i <= CUSTOM_LISTENER; i++) { buf = 0x01; err = setsockopt(fd, SOL_CUSTOM, i, &buf, 1); if (err) { log_err("Failed to call setsockopt(%d)", i); - close(fd); return -1; } } - if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) { - log_err("Failed to bind socket"); - close(fd); - return -1; - } - - return fd; + return 0; } static void run_test(int cgroup_fd) { struct bpf_link *link_getsockopt = NULL; struct bpf_link *link_setsockopt = NULL; + struct network_helper_opts opts = { + .post_socket_cb = custom_cb, + }; int server_fd = -1, client_fd; + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_LOOPBACK), + }; struct sockopt_inherit *obj; void *server_err; pthread_t tid; @@ -160,7 +121,8 @@ static void run_test(int cgroup_fd) if (!ASSERT_OK_PTR(link_setsockopt, "cg-attach-setsockopt")) goto close_bpf_object; - server_fd = start_server(); + server_fd = start_server_addr(SOCK_STREAM, (struct sockaddr_storage *)&addr, + sizeof(addr), &opts); if (!ASSERT_GE(server_fd, 0, "start_server")) goto close_bpf_object; @@ -173,7 +135,7 @@ static void run_test(int cgroup_fd) pthread_cond_wait(&server_started, &server_started_mtx); pthread_mutex_unlock(&server_started_mtx); - client_fd = connect_to_server(server_fd); + client_fd = connect_to_fd(server_fd, 0); if (!ASSERT_GE(client_fd, 0, "connect_to_server")) goto close_server_fd; diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c index 7cf2b9ddd3e1..29e183a80f49 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c @@ -4,6 +4,8 @@ #include #include "struct_ops_module.skel.h" +#include "struct_ops_nulled_out_cb.skel.h" +#include "struct_ops_forgotten_cb.skel.h" static void check_map_info(struct bpf_map_info *info) { @@ -66,6 +68,7 @@ static void test_struct_ops_load(void) * auto-loading, or it will fail to load. */ bpf_program__set_autoload(skel->progs.test_2, false); + bpf_map__set_autocreate(skel->maps.testmod_zeroed, false); err = struct_ops_module__load(skel); if (!ASSERT_OK(err, "struct_ops_module_load")) @@ -103,6 +106,10 @@ static void test_struct_ops_not_zeroed(void) if (!ASSERT_OK_PTR(skel, "struct_ops_module_open")) return; + skel->struct_ops.testmod_zeroed->zeroed = 0; + /* zeroed_op prog should be not loaded automatically now */ + skel->struct_ops.testmod_zeroed->zeroed_op = NULL; + err = struct_ops_module__load(skel); ASSERT_OK(err, "struct_ops_module_load"); @@ -118,6 +125,7 @@ static void test_struct_ops_not_zeroed(void) * value of "zeroed" is non-zero. */ skel->struct_ops.testmod_zeroed->zeroed = 0xdeadbeef; + skel->struct_ops.testmod_zeroed->zeroed_op = NULL; err = struct_ops_module__load(skel); ASSERT_ERR(err, "struct_ops_module_load_not_zeroed"); @@ -148,25 +156,103 @@ static void test_struct_ops_incompatible(void) { struct struct_ops_module *skel; struct bpf_link *link; + int err; - skel = struct_ops_module__open_and_load(); - if (!ASSERT_OK_PTR(skel, "open_and_load")) + skel = struct_ops_module__open(); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open")) return; + bpf_map__set_autocreate(skel->maps.testmod_zeroed, false); + + err = struct_ops_module__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + link = bpf_map__attach_struct_ops(skel->maps.testmod_incompatible); if (ASSERT_OK_PTR(link, "attach_struct_ops")) bpf_link__destroy(link); +cleanup: struct_ops_module__destroy(skel); } +/* validate that it's ok to "turn off" callback that kernel supports */ +static void test_struct_ops_nulled_out_cb(void) +{ + struct struct_ops_nulled_out_cb *skel; + int err; + + skel = struct_ops_nulled_out_cb__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + /* kernel knows about test_1, but we still null it out */ + skel->struct_ops.ops->test_1 = NULL; + + err = struct_ops_nulled_out_cb__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + ASSERT_FALSE(bpf_program__autoload(skel->progs.test_1_turn_off), "prog_autoload"); + ASSERT_LT(bpf_program__fd(skel->progs.test_1_turn_off), 0, "prog_fd"); + +cleanup: + struct_ops_nulled_out_cb__destroy(skel); +} + +/* validate that libbpf generates reasonable error message if struct_ops is + * not referenced in any struct_ops map + */ +static void test_struct_ops_forgotten_cb(void) +{ + struct struct_ops_forgotten_cb *skel; + char *log; + int err; + + skel = struct_ops_forgotten_cb__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + start_libbpf_log_capture(); + + err = struct_ops_forgotten_cb__load(skel); + if (!ASSERT_ERR(err, "skel_load")) + goto cleanup; + + log = stop_libbpf_log_capture(); + ASSERT_HAS_SUBSTR(log, + "prog 'test_1_forgotten': SEC(\"struct_ops\") program isn't referenced anywhere, did you forget to use it?", + "libbpf_log"); + free(log); + + struct_ops_forgotten_cb__destroy(skel); + + /* now let's programmatically use it, we should be fine now */ + skel = struct_ops_forgotten_cb__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->struct_ops.ops->test_1 = skel->progs.test_1_forgotten; /* not anymore */ + + err = struct_ops_forgotten_cb__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + +cleanup: + struct_ops_forgotten_cb__destroy(skel); +} + void serial_test_struct_ops_module(void) { - if (test__start_subtest("test_struct_ops_load")) + if (test__start_subtest("struct_ops_load")) test_struct_ops_load(); - if (test__start_subtest("test_struct_ops_not_zeroed")) + if (test__start_subtest("struct_ops_not_zeroed")) test_struct_ops_not_zeroed(); - if (test__start_subtest("test_struct_ops_incompatible")) + if (test__start_subtest("struct_ops_incompatible")) test_struct_ops_incompatible(); + if (test__start_subtest("struct_ops_null_out_cb")) + test_struct_ops_nulled_out_cb(); + if (test__start_subtest("struct_ops_forgotten_cb")) + test_struct_ops_forgotten_cb(); } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index c4f9f306646e..c60db8beeb73 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -66,6 +66,7 @@ #include "verifier_sdiv.skel.h" #include "verifier_search_pruning.skel.h" #include "verifier_sock.skel.h" +#include "verifier_sock_addr.skel.h" #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" @@ -181,6 +182,7 @@ void test_verifier_scalar_ids(void) { RUN(verifier_scalar_ids); } void test_verifier_sdiv(void) { RUN(verifier_sdiv); } void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); } void test_verifier_sock(void) { RUN(verifier_sock); } +void test_verifier_sock_addr(void) { RUN(verifier_sock_addr); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } diff --git a/tools/testing/selftests/bpf/prog_tests/wq.c b/tools/testing/selftests/bpf/prog_tests/wq.c index c4bacd3160e1..99e438fe12ac 100644 --- a/tools/testing/selftests/bpf/prog_tests/wq.c +++ b/tools/testing/selftests/bpf/prog_tests/wq.c @@ -36,7 +36,5 @@ void serial_test_wq(void) void serial_test_failures_wq(void) { - LIBBPF_OPTS(bpf_test_run_opts, topts); - RUN_TESTS(wq_failures); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index 498d3bdaa4b0..bad0ea167be7 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -107,8 +107,8 @@ void test_xdp_do_redirect(void) .attach_point = BPF_TC_INGRESS); memcpy(&data[sizeof(__u64)], &pkt_udp, sizeof(pkt_udp)); - *((__u32 *)data) = 0x42; /* metadata test value */ - *((__u32 *)data + 4) = 0; + ((__u32 *)data)[0] = 0x42; /* metadata test value */ + ((__u32 *)data)[1] = 0; skel = test_xdp_do_redirect__open(); if (!ASSERT_OK_PTR(skel, "skel")) diff --git a/tools/testing/selftests/bpf/progs/arena_list.c b/tools/testing/selftests/bpf/progs/arena_list.c index c0422c58cee2..93bd0600eba0 100644 --- a/tools/testing/selftests/bpf/progs/arena_list.c +++ b/tools/testing/selftests/bpf/progs/arena_list.c @@ -49,7 +49,7 @@ int arena_list_add(void *ctx) list_head = &global_head; - for (i = zero; i < cnt; cond_break, i++) { + for (i = zero; i < cnt && can_loop; i++) { struct elem __arena *n = bpf_alloc(sizeof(*n)); test_val++; diff --git a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c index e4bfbba6c193..c8ec0d0368e4 100644 --- a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c +++ b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c @@ -61,14 +61,15 @@ SEC("lsm.s/socket_post_create") int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, int protocol, int kern) { + struct sock *sk = sock->sk; struct storage *stg; __u32 pid; pid = bpf_get_current_pid_tgid() >> 32; - if (pid != bench_pid) + if (pid != bench_pid || !sk) return 0; - stg = bpf_sk_storage_get(&sk_storage_map, sock->sk, NULL, + stg = bpf_sk_storage_get(&sk_storage_map, sk, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); if (stg) diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c index a487f60b73ac..b7ddf8ec4ee8 100644 --- a/tools/testing/selftests/bpf/progs/bind4_prog.c +++ b/tools/testing/selftests/bpf/progs/bind4_prog.c @@ -12,6 +12,8 @@ #include #include +#include "bind_prog.h" + #define SERV4_IP 0xc0a801feU /* 192.168.1.254 */ #define SERV4_PORT 4040 #define SERV4_REWRITE_IP 0x7f000001U /* 127.0.0.1 */ @@ -118,23 +120,23 @@ int bind_v4_prog(struct bpf_sock_addr *ctx) // u8 narrow loads: user_ip4 = 0; - user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[0] << 0; - user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[1] << 8; - user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[2] << 16; - user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[3] << 24; + user_ip4 |= load_byte(ctx->user_ip4, 0, sizeof(user_ip4)); + user_ip4 |= load_byte(ctx->user_ip4, 1, sizeof(user_ip4)); + user_ip4 |= load_byte(ctx->user_ip4, 2, sizeof(user_ip4)); + user_ip4 |= load_byte(ctx->user_ip4, 3, sizeof(user_ip4)); if (ctx->user_ip4 != user_ip4) return 0; user_port = 0; - user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0; - user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8; + user_port |= load_byte(ctx->user_port, 0, sizeof(user_port)); + user_port |= load_byte(ctx->user_port, 1, sizeof(user_port)); if (ctx->user_port != user_port) return 0; // u16 narrow loads: user_ip4 = 0; - user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[0] << 0; - user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[1] << 16; + user_ip4 |= load_word(ctx->user_ip4, 0, sizeof(user_ip4)); + user_ip4 |= load_word(ctx->user_ip4, 1, sizeof(user_ip4)); if (ctx->user_ip4 != user_ip4) return 0; @@ -156,4 +158,10 @@ int bind_v4_prog(struct bpf_sock_addr *ctx) return 1; } +SEC("cgroup/bind4") +int bind_v4_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c index d62cd9e9cf0e..501c3fc11d35 100644 --- a/tools/testing/selftests/bpf/progs/bind6_prog.c +++ b/tools/testing/selftests/bpf/progs/bind6_prog.c @@ -12,6 +12,8 @@ #include #include +#include "bind_prog.h" + #define SERV6_IP_0 0xfaceb00c /* face:b00c:1234:5678::abcd */ #define SERV6_IP_1 0x12345678 #define SERV6_IP_2 0x00000000 @@ -129,25 +131,25 @@ int bind_v6_prog(struct bpf_sock_addr *ctx) // u8 narrow loads: for (i = 0; i < 4; i++) { user_ip6 = 0; - user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[0] << 0; - user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[1] << 8; - user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[2] << 16; - user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[3] << 24; + user_ip6 |= load_byte(ctx->user_ip6[i], 0, sizeof(user_ip6)); + user_ip6 |= load_byte(ctx->user_ip6[i], 1, sizeof(user_ip6)); + user_ip6 |= load_byte(ctx->user_ip6[i], 2, sizeof(user_ip6)); + user_ip6 |= load_byte(ctx->user_ip6[i], 3, sizeof(user_ip6)); if (ctx->user_ip6[i] != user_ip6) return 0; } user_port = 0; - user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0; - user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8; + user_port |= load_byte(ctx->user_port, 0, sizeof(user_port)); + user_port |= load_byte(ctx->user_port, 1, sizeof(user_port)); if (ctx->user_port != user_port) return 0; // u16 narrow loads: for (i = 0; i < 4; i++) { user_ip6 = 0; - user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[0] << 0; - user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[1] << 16; + user_ip6 |= load_word(ctx->user_ip6[i], 0, sizeof(user_ip6)); + user_ip6 |= load_word(ctx->user_ip6[i], 1, sizeof(user_ip6)); if (ctx->user_ip6[i] != user_ip6) return 0; } @@ -173,4 +175,10 @@ int bind_v6_prog(struct bpf_sock_addr *ctx) return 1; } +SEC("cgroup/bind6") +int bind_v6_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bind_prog.h b/tools/testing/selftests/bpf/progs/bind_prog.h new file mode 100644 index 000000000000..e830caa940c3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bind_prog.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BIND_PROG_H__ +#define __BIND_PROG_H__ + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define load_byte(src, b, s) \ + (((volatile __u8 *)&(src))[b] << 8 * b) +#define load_word(src, w, s) \ + (((volatile __u16 *)&(src))[w] << 16 * w) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#define load_byte(src, b, s) \ + (((volatile __u8 *)&(src))[(b) + (sizeof(src) - (s))] << 8 * ((s) - (b) - 1)) +#define load_word(src, w, s) \ + (((volatile __u16 *)&(src))[w] << 16 * (((s) / 2) - (w) - 1)) +#else +# error "Fix your compiler's __BYTE_ORDER__?!" +#endif + +#endif diff --git a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c new file mode 100644 index 000000000000..1654a530aa3d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c @@ -0,0 +1,189 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* Highlights: + * 1. The major difference between this bpf program and tcp_cubic.c + * is that this bpf program relies on `cong_control` rather than + * `cong_avoid` in the struct tcp_congestion_ops. + * 2. Logic such as tcp_cwnd_reduction, tcp_cong_avoid, and + * tcp_update_pacing_rate is bypassed when `cong_control` is + * defined, so moving these logic to `cong_control`. + * 3. WARNING: This bpf program is NOT the same as tcp_cubic.c. + * The main purpose is to show use cases of the arguments in + * `cong_control`. For simplicity's sake, it reuses tcp cubic's + * kernel functions. + */ + +#include "bpf_tracing_net.h" +#include +#include + +#define USEC_PER_SEC 1000000UL +#define TCP_PACING_SS_RATIO (200) +#define TCP_PACING_CA_RATIO (120) +#define TCP_REORDERING (12) + +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define after(seq2, seq1) before(seq1, seq2) + +extern void cubictcp_init(struct sock *sk) __ksym; +extern void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym; +extern __u32 cubictcp_recalc_ssthresh(struct sock *sk) __ksym; +extern void cubictcp_state(struct sock *sk, __u8 new_state) __ksym; +extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym; +extern void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) __ksym; +extern void cubictcp_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym; + +static bool before(__u32 seq1, __u32 seq2) +{ + return (__s32)(seq1-seq2) < 0; +} + +static __u64 div64_u64(__u64 dividend, __u64 divisor) +{ + return dividend / divisor; +} + +static void tcp_update_pacing_rate(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + __u64 rate; + + /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ + rate = (__u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3); + + /* current rate is (cwnd * mss) / srtt + * In Slow Start [1], set sk_pacing_rate to 200 % the current rate. + * In Congestion Avoidance phase, set it to 120 % the current rate. + * + * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh) + * If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching + * end of slow start and should slow down. + */ + if (tp->snd_cwnd < tp->snd_ssthresh / 2) + rate *= TCP_PACING_SS_RATIO; + else + rate *= TCP_PACING_CA_RATIO; + + rate *= max(tp->snd_cwnd, tp->packets_out); + + if (tp->srtt_us) + rate = div64_u64(rate, (__u64)tp->srtt_us); + + sk->sk_pacing_rate = min(rate, sk->sk_max_pacing_rate); +} + +static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, + int newly_lost, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + int sndcnt = 0; + __u32 pkts_in_flight = tp->packets_out - (tp->sacked_out + tp->lost_out) + tp->retrans_out; + int delta = tp->snd_ssthresh - pkts_in_flight; + + if (newly_acked_sacked <= 0 || !tp->prior_cwnd) + return; + + __u32 prr_delivered = tp->prr_delivered + newly_acked_sacked; + + if (delta < 0) { + __u64 dividend = + (__u64)tp->snd_ssthresh * prr_delivered + tp->prior_cwnd - 1; + sndcnt = (__u32)div64_u64(dividend, (__u64)tp->prior_cwnd) - tp->prr_out; + } else { + sndcnt = max(prr_delivered - tp->prr_out, newly_acked_sacked); + if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost) + sndcnt++; + sndcnt = min(delta, sndcnt); + } + /* Force a fast retransmit upon entering fast recovery */ + sndcnt = max(sndcnt, (tp->prr_out ? 0 : 1)); + tp->snd_cwnd = pkts_in_flight + sndcnt; +} + +/* Decide wheather to run the increase function of congestion control. */ +static bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) +{ + if (tcp_sk(sk)->reordering > TCP_REORDERING) + return flag & FLAG_FORWARD_PROGRESS; + + return flag & FLAG_DATA_ACKED; +} + +SEC("struct_ops") +void BPF_PROG(bpf_cubic_init, struct sock *sk) +{ + cubictcp_init(sk); +} + +SEC("struct_ops") +void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event) +{ + cubictcp_cwnd_event(sk, event); +} + +SEC("struct_ops") +void BPF_PROG(bpf_cubic_cong_control, struct sock *sk, __u32 ack, int flag, + const struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (((1<icsk_ca_state)) { + /* Reduce cwnd if state mandates */ + tcp_cwnd_reduction(sk, rs->acked_sacked, rs->losses, flag); + + if (!before(tp->snd_una, tp->high_seq)) { + /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ + if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH && + inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) { + tp->snd_cwnd = tp->snd_ssthresh; + tp->snd_cwnd_stamp = tcp_jiffies32; + } + } + } else if (tcp_may_raise_cwnd(sk, flag)) { + /* Advance cwnd if state allows */ + cubictcp_cong_avoid(sk, ack, rs->acked_sacked); + tp->snd_cwnd_stamp = tcp_jiffies32; + } + + tcp_update_pacing_rate(sk); +} + +SEC("struct_ops") +__u32 BPF_PROG(bpf_cubic_recalc_ssthresh, struct sock *sk) +{ + return cubictcp_recalc_ssthresh(sk); +} + +SEC("struct_ops") +void BPF_PROG(bpf_cubic_state, struct sock *sk, __u8 new_state) +{ + cubictcp_state(sk, new_state); +} + +SEC("struct_ops") +void BPF_PROG(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample) +{ + cubictcp_acked(sk, sample); +} + +SEC("struct_ops") +__u32 BPF_PROG(bpf_cubic_undo_cwnd, struct sock *sk) +{ + return tcp_reno_undo_cwnd(sk); +} + +SEC(".struct_ops") +struct tcp_congestion_ops cc_cubic = { + .init = (void *)bpf_cubic_init, + .ssthresh = (void *)bpf_cubic_recalc_ssthresh, + .cong_control = (void *)bpf_cubic_cong_control, + .set_state = (void *)bpf_cubic_state, + .undo_cwnd = (void *)bpf_cubic_undo_cwnd, + .cwnd_event = (void *)bpf_cubic_cwnd_event, + .pkts_acked = (void *)bpf_cubic_acked, + .name = "bpf_cc_cubic", +}; + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index c997e3e3d3fb..d665b8a15cc4 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -14,14 +14,22 @@ * "ca->ack_cnt / delta" operation. */ -#include -#include -#include -#include "bpf_tcp_helpers.h" +#include "bpf_tracing_net.h" +#include char _license[] SEC("license") = "GPL"; #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define max(a, b) ((a) > (b) ? (a) : (b)) +static bool before(__u32 seq1, __u32 seq2) +{ + return (__s32)(seq1-seq2) < 0; +} +#define after(seq2, seq1) before(seq1, seq2) + +extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym; +extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym; #define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation * max_cwnd = snd_cwnd * beta @@ -70,7 +78,7 @@ static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ)) / (bic_scale * 10); /* BIC TCP Parameters */ -struct bictcp { +struct bpf_bictcp { __u32 cnt; /* increase cwnd by 1 after ACKs */ __u32 last_max_cwnd; /* last maximum snd_cwnd */ __u32 last_cwnd; /* the last snd_cwnd */ @@ -91,7 +99,7 @@ struct bictcp { __u32 curr_rtt; /* the minimum rtt of current round */ }; -static inline void bictcp_reset(struct bictcp *ca) +static void bictcp_reset(struct bpf_bictcp *ca) { ca->cnt = 0; ca->last_max_cwnd = 0; @@ -112,7 +120,7 @@ extern unsigned long CONFIG_HZ __kconfig; #define USEC_PER_SEC 1000000UL #define USEC_PER_JIFFY (USEC_PER_SEC / HZ) -static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor) +static __u64 div64_u64(__u64 dividend, __u64 divisor) { return dividend / divisor; } @@ -120,7 +128,7 @@ static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor) #define div64_ul div64_u64 #define BITS_PER_U64 (sizeof(__u64) * 8) -static __always_inline int fls64(__u64 x) +static int fls64(__u64 x) { int num = BITS_PER_U64 - 1; @@ -153,15 +161,15 @@ static __always_inline int fls64(__u64 x) return num + 1; } -static __always_inline __u32 bictcp_clock_us(const struct sock *sk) +static __u32 bictcp_clock_us(const struct sock *sk) { return tcp_sk(sk)->tcp_mstamp; } -static __always_inline void bictcp_hystart_reset(struct sock *sk) +static void bictcp_hystart_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct bictcp *ca = inet_csk_ca(sk); + struct bpf_bictcp *ca = inet_csk_ca(sk); ca->round_start = ca->last_ack = bictcp_clock_us(sk); ca->end_seq = tp->snd_nxt; @@ -169,11 +177,10 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } -/* "struct_ops/" prefix is a requirement */ -SEC("struct_ops/bpf_cubic_init") +SEC("struct_ops") void BPF_PROG(bpf_cubic_init, struct sock *sk) { - struct bictcp *ca = inet_csk_ca(sk); + struct bpf_bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); @@ -184,12 +191,11 @@ void BPF_PROG(bpf_cubic_init, struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } -/* "struct_ops" prefix is a requirement */ -SEC("struct_ops/bpf_cubic_cwnd_event") +SEC("struct_ops") void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { - struct bictcp *ca = inet_csk_ca(sk); + struct bpf_bictcp *ca = inet_csk_ca(sk); __u32 now = tcp_jiffies32; __s32 delta; @@ -230,7 +236,7 @@ static const __u8 v[] = { * Newton-Raphson iteration. * Avg err ~= 0.195% */ -static __always_inline __u32 cubic_root(__u64 a) +static __u32 cubic_root(__u64 a) { __u32 x, b, shift; @@ -263,8 +269,7 @@ static __always_inline __u32 cubic_root(__u64 a) /* * Compute congestion window to use. */ -static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd, - __u32 acked) +static void bictcp_update(struct bpf_bictcp *ca, __u32 cwnd, __u32 acked) { __u32 delta, bic_target, max_cnt; __u64 offs, t; @@ -377,11 +382,11 @@ tcp_friendliness: ca->cnt = max(ca->cnt, 2U); } -/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */ -void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) +SEC("struct_ops") +void BPF_PROG(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) { struct tcp_sock *tp = tcp_sk(sk); - struct bictcp *ca = inet_csk_ca(sk); + struct bpf_bictcp *ca = inet_csk_ca(sk); if (!tcp_is_cwnd_limited(sk)) return; @@ -397,10 +402,11 @@ void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acke tcp_cong_avoid_ai(tp, ca->cnt, acked); } -__u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk) +SEC("struct_ops") +__u32 BPF_PROG(bpf_cubic_recalc_ssthresh, struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); - struct bictcp *ca = inet_csk_ca(sk); + struct bpf_bictcp *ca = inet_csk_ca(sk); ca->epoch_start = 0; /* end of epoch */ @@ -414,7 +420,8 @@ __u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk) return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U); } -void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state) +SEC("struct_ops") +void BPF_PROG(bpf_cubic_state, struct sock *sk, __u8 new_state) { if (new_state == TCP_CA_Loss) { bictcp_reset(inet_csk_ca(sk)); @@ -433,7 +440,7 @@ void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state) * We apply another 100% factor because @rate is doubled at this point. * We cap the cushion to 1ms. */ -static __always_inline __u32 hystart_ack_delay(struct sock *sk) +static __u32 hystart_ack_delay(struct sock *sk) { unsigned long rate; @@ -444,10 +451,10 @@ static __always_inline __u32 hystart_ack_delay(struct sock *sk) div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); } -static __always_inline void hystart_update(struct sock *sk, __u32 delay) +static void hystart_update(struct sock *sk, __u32 delay) { struct tcp_sock *tp = tcp_sk(sk); - struct bictcp *ca = inet_csk_ca(sk); + struct bpf_bictcp *ca = inet_csk_ca(sk); __u32 threshold; if (hystart_detect & HYSTART_ACK_TRAIN) { @@ -492,11 +499,11 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay) int bpf_cubic_acked_called = 0; -void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk, - const struct ack_sample *sample) +SEC("struct_ops") +void BPF_PROG(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); - struct bictcp *ca = inet_csk_ca(sk); + struct bpf_bictcp *ca = inet_csk_ca(sk); __u32 delay; bpf_cubic_acked_called = 1; @@ -524,7 +531,8 @@ void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk, extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym; -__u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk) +SEC("struct_ops") +__u32 BPF_PROG(bpf_cubic_undo_cwnd, struct sock *sk) { return tcp_reno_undo_cwnd(sk); } diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c index 460682759aed..3c9ffe340312 100644 --- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -6,15 +6,23 @@ * the kernel BPF logic. */ -#include -#include -#include -#include -#include -#include +#include "bpf_tracing_net.h" #include #include -#include "bpf_tcp_helpers.h" + +#ifndef EBUSY +#define EBUSY 16 +#endif +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define min_not_zero(x, y) ({ \ + typeof(x) __x = (x); \ + typeof(y) __y = (y); \ + __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) +static bool before(__u32 seq1, __u32 seq2) +{ + return (__s32)(seq1-seq2) < 0; +} char _license[] SEC("license") = "GPL"; @@ -35,7 +43,7 @@ struct { #define DCTCP_MAX_ALPHA 1024U -struct dctcp { +struct bpf_dctcp { __u32 old_delivered; __u32 old_delivered_ce; __u32 prior_rcv_nxt; @@ -48,8 +56,7 @@ struct dctcp { static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */ static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA; -static __always_inline void dctcp_reset(const struct tcp_sock *tp, - struct dctcp *ca) +static void dctcp_reset(const struct tcp_sock *tp, struct bpf_dctcp *ca) { ca->next_seq = tp->snd_nxt; @@ -57,11 +64,11 @@ static __always_inline void dctcp_reset(const struct tcp_sock *tp, ca->old_delivered_ce = tp->delivered_ce; } -SEC("struct_ops/dctcp_init") +SEC("struct_ops") void BPF_PROG(dctcp_init, struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); - struct dctcp *ca = inet_csk_ca(sk); + struct bpf_dctcp *ca = inet_csk_ca(sk); int *stg; if (!(tp->ecn_flags & TCP_ECN_OK) && fallback[0]) { @@ -104,21 +111,21 @@ void BPF_PROG(dctcp_init, struct sock *sk) dctcp_reset(tp, ca); } -SEC("struct_ops/dctcp_ssthresh") +SEC("struct_ops") __u32 BPF_PROG(dctcp_ssthresh, struct sock *sk) { - struct dctcp *ca = inet_csk_ca(sk); + struct bpf_dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); ca->loss_cwnd = tp->snd_cwnd; return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); } -SEC("struct_ops/dctcp_update_alpha") +SEC("struct_ops") void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags) { const struct tcp_sock *tp = tcp_sk(sk); - struct dctcp *ca = inet_csk_ca(sk); + struct bpf_dctcp *ca = inet_csk_ca(sk); /* Expired RTT */ if (!before(tp->snd_una, ca->next_seq)) { @@ -144,16 +151,16 @@ void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags) } } -static __always_inline void dctcp_react_to_loss(struct sock *sk) +static void dctcp_react_to_loss(struct sock *sk) { - struct dctcp *ca = inet_csk_ca(sk); + struct bpf_dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); ca->loss_cwnd = tp->snd_cwnd; tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); } -SEC("struct_ops/dctcp_state") +SEC("struct_ops") void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state) { if (new_state == TCP_CA_Recovery && @@ -164,7 +171,7 @@ void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state) */ } -static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state) +static void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state) { struct tcp_sock *tp = tcp_sk(sk); @@ -179,9 +186,8 @@ static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state) * S: 0 <- last pkt was non-CE * 1 <- last pkt was CE */ -static __always_inline -void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, - __u32 *prior_rcv_nxt, __u32 *ce_state) +static void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, + __u32 *prior_rcv_nxt, __u32 *ce_state) { __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0; @@ -201,10 +207,10 @@ void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, dctcp_ece_ack_cwr(sk, new_ce_state); } -SEC("struct_ops/dctcp_cwnd_event") +SEC("struct_ops") void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev) { - struct dctcp *ca = inet_csk_ca(sk); + struct bpf_dctcp *ca = inet_csk_ca(sk); switch (ev) { case CA_EVENT_ECN_IS_CE: @@ -220,17 +226,17 @@ void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev) } } -SEC("struct_ops/dctcp_cwnd_undo") +SEC("struct_ops") __u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk) { - const struct dctcp *ca = inet_csk_ca(sk); + const struct bpf_dctcp *ca = inet_csk_ca(sk); return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); } extern void tcp_reno_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym; -SEC("struct_ops/dctcp_reno_cong_avoid") +SEC("struct_ops") void BPF_PROG(dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) { tcp_reno_cong_avoid(sk, ack, acked); diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c index d836f7c372f0..c91763f248b2 100644 --- a/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c @@ -1,19 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include -#include -#include -#include -#include +#include "bpf_tracing_net.h" #include #include -#include "bpf_tcp_helpers.h" char _license[] SEC("license") = "GPL"; const char cubic[] = "cubic"; -void BPF_STRUCT_OPS(dctcp_nouse_release, struct sock *sk) +SEC("struct_ops") +void BPF_PROG(dctcp_nouse_release, struct sock *sk) { bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION, (void *)cubic, sizeof(cubic)); diff --git a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c index 2ecd833dcd41..8a7a4c1b54e8 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c +++ b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c @@ -1,14 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include -#include +#include "bpf_tracing_net.h" #include -#include "bpf_tcp_helpers.h" char _license[] SEC("license") = "X"; -void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk) +SEC("struct_ops") +void BPF_PROG(nogpltcp_init, struct sock *sk) { } diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 7001965d1cc3..59843b430f76 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -2,6 +2,9 @@ #ifndef __BPF_TRACING_NET_H__ #define __BPF_TRACING_NET_H__ +#include +#include + #define AF_INET 2 #define AF_INET6 10 @@ -22,6 +25,7 @@ #define IP_TOS 1 +#define SOL_IPV6 41 #define IPV6_TCLASS 67 #define IPV6_AUTOFLOWLABEL 70 @@ -46,6 +50,13 @@ #define TCP_CA_NAME_MAX 16 #define TCP_NAGLE_OFF 1 +#define TCP_ECN_OK 1 +#define TCP_ECN_QUEUE_CWR 2 +#define TCP_ECN_DEMAND_CWR 4 +#define TCP_ECN_SEEN 8 + +#define TCP_CONG_NEEDS_ECN 0x2 + #define ICSK_TIME_RETRANS 1 #define ICSK_TIME_PROBE0 3 #define ICSK_TIME_LOSS_PROBE 5 @@ -80,6 +91,14 @@ #define TCP_INFINITE_SSTHRESH 0x7fffffff #define TCP_PINGPONG_THRESH 3 +#define FLAG_DATA_ACKED 0x04 /* This ACK acknowledged new data. */ +#define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */ +#define FLAG_DATA_SACKED 0x20 /* New SACK. */ +#define FLAG_SND_UNA_ADVANCED \ + 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ +#define FLAG_ACKED (FLAG_DATA_ACKED | FLAG_SYN_ACKED) +#define FLAG_FORWARD_PROGRESS (FLAG_ACKED | FLAG_DATA_SACKED) + #define fib_nh_dev nh_common.nhc_dev #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw6 nh_common.nhc_gw.ipv6 @@ -119,4 +138,37 @@ #define tw_v6_daddr __tw_common.skc_v6_daddr #define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr +#define tcp_jiffies32 ((__u32)bpf_jiffies64()) + +static inline struct inet_connection_sock *inet_csk(const struct sock *sk) +{ + return (struct inet_connection_sock *)sk; +} + +static inline void *inet_csk_ca(const struct sock *sk) +{ + return (void *)inet_csk(sk)->icsk_ca_priv; +} + +static inline struct tcp_sock *tcp_sk(const struct sock *sk) +{ + return (struct tcp_sock *)sk; +} + +static inline bool tcp_in_slow_start(const struct tcp_sock *tp) +{ + return tp->snd_cwnd < tp->snd_ssthresh; +} + +static inline bool tcp_is_cwnd_limited(const struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ + if (tcp_in_slow_start(tp)) + return tp->snd_cwnd < 2 * tp->max_packets_out; + + return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited); +} + #endif diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 7ef49ec04838..9e9ebf27b878 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -14,8 +14,6 @@ #include #include -#include "bpf_tcp_helpers.h" - #define SRC_REWRITE_IP4 0x7f000004U #define DST_REWRITE_IP4 0x7f000001U #define DST_REWRITE_PORT4 4444 @@ -32,6 +30,10 @@ #define IFNAMSIZ 16 #endif +#ifndef SOL_TCP +#define SOL_TCP 6 +#endif + __attribute__ ((noinline)) __weak int do_bind(struct bpf_sock_addr *ctx) { @@ -197,4 +199,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx) return do_bind(ctx) ? 1 : 0; } +SEC("cgroup/connect4") +int connect_v4_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c index 40266d2c737c..e98573b00ddb 100644 --- a/tools/testing/selftests/bpf/progs/connect6_prog.c +++ b/tools/testing/selftests/bpf/progs/connect6_prog.c @@ -90,4 +90,10 @@ int connect_v6_prog(struct bpf_sock_addr *ctx) return 1; } +SEC("cgroup/connect6") +int connect_v6_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/connect_unix_prog.c b/tools/testing/selftests/bpf/progs/connect_unix_prog.c index 2ef0e0c46d17..ba60adadb335 100644 --- a/tools/testing/selftests/bpf/progs/connect_unix_prog.c +++ b/tools/testing/selftests/bpf/progs/connect_unix_prog.c @@ -36,4 +36,10 @@ int connect_unix_prog(struct bpf_sock_addr *ctx) return 1; } +SEC("cgroup/connect_unix") +int connect_unix_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index c705d8112a35..b979e91f55f0 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -9,7 +9,7 @@ int err; -#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8))) +#define private(name) SEC(".bss." #name) __attribute__((aligned(8))) private(MASK) static struct bpf_cpumask __kptr * global_mask; struct __cpumask_map_value { diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c index a9bf6ea336cf..a988d2823b52 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_failure.c +++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c @@ -61,11 +61,8 @@ SEC("tp_btf/task_newtask") __failure __msg("bpf_cpumask_set_cpu args#1 expected pointer to STRUCT bpf_cpumask") int BPF_PROG(test_mutate_cpumask, struct task_struct *task, u64 clone_flags) { - struct bpf_cpumask *cpumask; - /* Can't set the CPU of a non-struct bpf_cpumask. */ bpf_cpumask_set_cpu(0, (struct bpf_cpumask *)task->cpus_ptr); - __sink(cpumask); return 0; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 7ce7e827d5f0..66a60bfb5867 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -80,7 +80,7 @@ SEC("?raw_tp") __failure __msg("Unreleased reference id=2") int ringbuf_missing_release1(void *ctx) { - struct bpf_dynptr ptr; + struct bpf_dynptr ptr = {}; bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); @@ -1385,7 +1385,7 @@ SEC("?raw_tp") __failure __msg("Expected an initialized dynptr as arg #1") int dynptr_adjust_invalid(void *ctx) { - struct bpf_dynptr ptr; + struct bpf_dynptr ptr = {}; /* this should fail */ bpf_dynptr_adjust(&ptr, 1, 2); @@ -1398,7 +1398,7 @@ SEC("?raw_tp") __failure __msg("Expected an initialized dynptr as arg #1") int dynptr_is_null_invalid(void *ctx) { - struct bpf_dynptr ptr; + struct bpf_dynptr ptr = {}; /* this should fail */ bpf_dynptr_is_null(&ptr); @@ -1411,7 +1411,7 @@ SEC("?raw_tp") __failure __msg("Expected an initialized dynptr as arg #1") int dynptr_is_rdonly_invalid(void *ctx) { - struct bpf_dynptr ptr; + struct bpf_dynptr ptr = {}; /* this should fail */ bpf_dynptr_is_rdonly(&ptr); @@ -1424,7 +1424,7 @@ SEC("?raw_tp") __failure __msg("Expected an initialized dynptr as arg #1") int dynptr_size_invalid(void *ctx) { - struct bpf_dynptr ptr; + struct bpf_dynptr ptr = {}; /* this should fail */ bpf_dynptr_size(&ptr); @@ -1437,7 +1437,7 @@ SEC("?raw_tp") __failure __msg("Expected an initialized dynptr as arg #1") int clone_invalid1(void *ctx) { - struct bpf_dynptr ptr1; + struct bpf_dynptr ptr1 = {}; struct bpf_dynptr ptr2; /* this should fail */ diff --git a/tools/testing/selftests/bpf/progs/fib_lookup.c b/tools/testing/selftests/bpf/progs/fib_lookup.c index c4514dd58c62..7b5dd2214ff4 100644 --- a/tools/testing/selftests/bpf/progs/fib_lookup.c +++ b/tools/testing/selftests/bpf/progs/fib_lookup.c @@ -3,8 +3,8 @@ #include #include +#include #include -#include "bpf_tracing_net.h" struct bpf_fib_lookup fib_params = {}; int fib_lookup_ret = 0; diff --git a/tools/testing/selftests/bpf/progs/getpeername4_prog.c b/tools/testing/selftests/bpf/progs/getpeername4_prog.c new file mode 100644 index 000000000000..4c97208cd25d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/getpeername4_prog.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google LLC */ + +#include "vmlinux.h" + +#include +#include +#include +#include +#include "bpf_kfuncs.h" + +#define REWRITE_ADDRESS_IP4 0xc0a801fe // 192.168.1.254 +#define REWRITE_ADDRESS_PORT4 4040 + +SEC("cgroup/getpeername4") +int getpeername_v4_prog(struct bpf_sock_addr *ctx) +{ + ctx->user_ip4 = bpf_htonl(REWRITE_ADDRESS_IP4); + ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT4); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/getpeername6_prog.c b/tools/testing/selftests/bpf/progs/getpeername6_prog.c new file mode 100644 index 000000000000..070e4d7f636c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/getpeername6_prog.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google LLC */ + +#include "vmlinux.h" + +#include +#include +#include +#include +#include "bpf_kfuncs.h" + +#define REWRITE_ADDRESS_IP6_0 0xfaceb00c +#define REWRITE_ADDRESS_IP6_1 0x12345678 +#define REWRITE_ADDRESS_IP6_2 0x00000000 +#define REWRITE_ADDRESS_IP6_3 0x0000abcd + +#define REWRITE_ADDRESS_PORT6 6060 + +SEC("cgroup/getpeername6") +int getpeername_v6_prog(struct bpf_sock_addr *ctx) +{ + ctx->user_ip6[0] = bpf_htonl(REWRITE_ADDRESS_IP6_0); + ctx->user_ip6[1] = bpf_htonl(REWRITE_ADDRESS_IP6_1); + ctx->user_ip6[2] = bpf_htonl(REWRITE_ADDRESS_IP6_2); + ctx->user_ip6[3] = bpf_htonl(REWRITE_ADDRESS_IP6_3); + ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT6); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/getsockname4_prog.c b/tools/testing/selftests/bpf/progs/getsockname4_prog.c new file mode 100644 index 000000000000..e298487c6347 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/getsockname4_prog.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google LLC */ + +#include "vmlinux.h" + +#include +#include +#include +#include +#include "bpf_kfuncs.h" + +#define REWRITE_ADDRESS_IP4 0xc0a801fe // 192.168.1.254 +#define REWRITE_ADDRESS_PORT4 4040 + +SEC("cgroup/getsockname4") +int getsockname_v4_prog(struct bpf_sock_addr *ctx) +{ + ctx->user_ip4 = bpf_htonl(REWRITE_ADDRESS_IP4); + ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT4); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/getsockname6_prog.c b/tools/testing/selftests/bpf/progs/getsockname6_prog.c new file mode 100644 index 000000000000..811d10cd5525 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/getsockname6_prog.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google LLC */ + +#include "vmlinux.h" + +#include +#include +#include +#include +#include "bpf_kfuncs.h" + +#define REWRITE_ADDRESS_IP6_0 0xfaceb00c +#define REWRITE_ADDRESS_IP6_1 0x12345678 +#define REWRITE_ADDRESS_IP6_2 0x00000000 +#define REWRITE_ADDRESS_IP6_3 0x0000abcd + +#define REWRITE_ADDRESS_PORT6 6060 + +SEC("cgroup/getsockname6") +int getsockname_v6_prog(struct bpf_sock_addr *ctx) +{ + ctx->user_ip6[0] = bpf_htonl(REWRITE_ADDRESS_IP6_0); + ctx->user_ip6[1] = bpf_htonl(REWRITE_ADDRESS_IP6_1); + ctx->user_ip6[2] = bpf_htonl(REWRITE_ADDRESS_IP6_2); + ctx->user_ip6[3] = bpf_htonl(REWRITE_ADDRESS_IP6_3); + ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT6); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c index f46965053acb..4d619bea9c75 100644 --- a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c +++ b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c @@ -4,6 +4,10 @@ #include #include "bpf_misc.h" +#ifndef __clang__ +#pragma GCC diagnostic ignored "-Warray-bounds" +#endif + char _license[] SEC("license") = "GPL"; struct { diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_session.c b/tools/testing/selftests/bpf/progs/kprobe_multi_session.c new file mode 100644 index 000000000000..bbba9eb46551 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi_session.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include "bpf_kfuncs.h" + +#define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0])) + +char _license[] SEC("license") = "GPL"; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_fentry_test5 __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; +extern const void bpf_fentry_test8 __ksym; + +int pid = 0; + +__u64 kprobe_session_result[8]; + +static int session_check(void *ctx) +{ + unsigned int i; + __u64 addr; + const void *kfuncs[] = { + &bpf_fentry_test1, + &bpf_fentry_test2, + &bpf_fentry_test3, + &bpf_fentry_test4, + &bpf_fentry_test5, + &bpf_fentry_test6, + &bpf_fentry_test7, + &bpf_fentry_test8, + }; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 1; + + addr = bpf_get_func_ip(ctx); + + for (i = 0; i < ARRAY_SIZE(kfuncs); i++) { + if (kfuncs[i] == (void *) addr) { + kprobe_session_result[i]++; + break; + } + } + + /* + * Force probes for function bpf_fentry_test[5-8] not to + * install and execute the return probe + */ + if (((const void *) addr == &bpf_fentry_test5) || + ((const void *) addr == &bpf_fentry_test6) || + ((const void *) addr == &bpf_fentry_test7) || + ((const void *) addr == &bpf_fentry_test8)) + return 1; + + return 0; +} + +/* + * No tests in here, just to trigger 'bpf_fentry_test*' + * through tracing test_run + */ +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(trigger) +{ + return 0; +} + +SEC("kprobe.session/bpf_fentry_test*") +int test_kprobe(struct pt_regs *ctx) +{ + return session_check(ctx); +} diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c new file mode 100644 index 000000000000..d49070803e22 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include "bpf_kfuncs.h" + +char _license[] SEC("license") = "GPL"; + +int pid = 0; + +__u64 test_kprobe_1_result = 0; +__u64 test_kprobe_2_result = 0; +__u64 test_kprobe_3_result = 0; + +/* + * No tests in here, just to trigger 'bpf_fentry_test*' + * through tracing test_run + */ +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(trigger) +{ + return 0; +} + +static int check_cookie(__u64 val, __u64 *result) +{ + long *cookie; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 1; + + cookie = bpf_session_cookie(); + + if (bpf_session_is_return()) + *result = *cookie == val ? val : 0; + else + *cookie = val; + return 0; +} + +SEC("kprobe.session/bpf_fentry_test1") +int test_kprobe_1(struct pt_regs *ctx) +{ + return check_cookie(1, &test_kprobe_1_result); +} + +SEC("kprobe.session/bpf_fentry_test1") +int test_kprobe_2(struct pt_regs *ctx) +{ + return check_cookie(2, &test_kprobe_2_result); +} + +SEC("kprobe.session/bpf_fentry_test1") +int test_kprobe_3(struct pt_regs *ctx) +{ + return check_cookie(3, &test_kprobe_3_result); +} diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c index e5e3a8b8dd07..637e75df2e14 100644 --- a/tools/testing/selftests/bpf/progs/local_storage.c +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -140,11 +140,12 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, { __u32 pid = bpf_get_current_pid_tgid() >> 32; struct local_storage *storage; + struct sock *sk = sock->sk; - if (pid != monitored_pid) + if (pid != monitored_pid || !sk) return 0; - storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, 0); + storage = bpf_sk_storage_get(&sk_storage_map, sk, 0, 0); if (!storage) return 0; @@ -155,24 +156,24 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, /* This tests that we can associate multiple elements * with the local storage. */ - storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!storage) return 0; - if (bpf_sk_storage_delete(&sk_storage_map2, sock->sk)) + if (bpf_sk_storage_delete(&sk_storage_map2, sk)) return 0; - storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!storage) return 0; - if (bpf_sk_storage_delete(&sk_storage_map, sock->sk)) + if (bpf_sk_storage_delete(&sk_storage_map, sk)) return 0; /* Ensure that the sk_storage_map is disconnected from the storage. */ - if (!sock->sk->sk_bpf_storage || sock->sk->sk_bpf_storage->smap) + if (!sk->sk_bpf_storage || sk->sk_bpf_storage->smap) return 0; sk_storage_result = 0; @@ -185,11 +186,12 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, { __u32 pid = bpf_get_current_pid_tgid() >> 32; struct local_storage *storage; + struct sock *sk = sock->sk; - if (pid != monitored_pid) + if (pid != monitored_pid || !sk) return 0; - storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, + storage = bpf_sk_storage_get(&sk_storage_map, sk, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!storage) return 0; diff --git a/tools/testing/selftests/bpf/progs/lsm_cgroup.c b/tools/testing/selftests/bpf/progs/lsm_cgroup.c index 02c11d16b692..d7598538aa2d 100644 --- a/tools/testing/selftests/bpf/progs/lsm_cgroup.c +++ b/tools/testing/selftests/bpf/progs/lsm_cgroup.c @@ -103,11 +103,15 @@ static __always_inline int real_bind(struct socket *sock, int addrlen) { struct sockaddr_ll sa = {}; + struct sock *sk = sock->sk; - if (sock->sk->__sk_common.skc_family != AF_PACKET) + if (!sk) return 1; - if (sock->sk->sk_kern_sock) + if (sk->__sk_common.skc_family != AF_PACKET) + return 1; + + if (sk->sk_kern_sock) return 1; bpf_probe_read_kernel(&sa, sizeof(sa), address); diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c index 91a0d7eff2ac..f3acb90588c7 100644 --- a/tools/testing/selftests/bpf/progs/mptcp_sock.c +++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c @@ -2,9 +2,9 @@ /* Copyright (c) 2020, Tessares SA. */ /* Copyright (c) 2022, SUSE. */ -#include +#include "bpf_tracing_net.h" #include -#include "bpf_tcp_helpers.h" +#include char _license[] SEC("license") = "GPL"; __u32 token = 0; diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c index 351e79aef2fa..edc159598a0e 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c @@ -49,4 +49,10 @@ int sendmsg_v4_prog(struct bpf_sock_addr *ctx) return 1; } +SEC("cgroup/sendmsg4") +int sendmsg_v4_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index bf9b46b806f6..36a7f960799f 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -20,6 +20,11 @@ #define DST_REWRITE_IP6_2 0 #define DST_REWRITE_IP6_3 1 +#define DST_REWRITE_IP6_V4_MAPPED_0 0 +#define DST_REWRITE_IP6_V4_MAPPED_1 0 +#define DST_REWRITE_IP6_V4_MAPPED_2 0x0000FFFF +#define DST_REWRITE_IP6_V4_MAPPED_3 0xc0a80004 // 192.168.0.4 + #define DST_REWRITE_PORT6 6666 SEC("cgroup/sendmsg6") @@ -59,4 +64,56 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx) return 1; } +SEC("cgroup/sendmsg6") +int sendmsg_v6_v4mapped_prog(struct bpf_sock_addr *ctx) +{ + /* Rewrite source. */ + ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0); + ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1); + ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2); + ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3); + + /* Rewrite destination. */ + ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_0); + ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_1); + ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_2); + ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_3); + + ctx->user_port = bpf_htons(DST_REWRITE_PORT6); + + return 1; +} + +SEC("cgroup/sendmsg6") +int sendmsg_v6_wildcard_prog(struct bpf_sock_addr *ctx) +{ + /* Rewrite source. */ + ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0); + ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1); + ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2); + ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3); + + /* Rewrite destination. */ + ctx->user_ip6[0] = bpf_htonl(0); + ctx->user_ip6[1] = bpf_htonl(0); + ctx->user_ip6[2] = bpf_htonl(0); + ctx->user_ip6[3] = bpf_htonl(0); + + ctx->user_port = bpf_htons(DST_REWRITE_PORT6); + + return 1; +} + +SEC("cgroup/sendmsg6") +int sendmsg_v6_preserve_dst_prog(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/sendmsg6") +int sendmsg_v6_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c index d8869b03dda9..332d0eb1116f 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c @@ -36,4 +36,10 @@ int sendmsg_unix_prog(struct bpf_sock_addr *ctx) return 1; } +SEC("cgroup/sendmsg_unix") +int sendmsg_unix_deny_prog(struct bpf_sock_addr *ctx) +{ + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c index 992b7861003a..db4abd2682fc 100644 --- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c +++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#ifndef BPF_NO_PRESERVE_ACCESS_INDEX #define BPF_NO_PRESERVE_ACCESS_INDEX +#endif #include #include #include diff --git a/tools/testing/selftests/bpf/progs/sock_addr_kern.c b/tools/testing/selftests/bpf/progs/sock_addr_kern.c new file mode 100644 index 000000000000..8386bb15ccdc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_addr_kern.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google LLC */ +#include +#include +#include "../bpf_testmod/bpf_testmod_kfunc.h" + +SEC("syscall") +int init_sock(struct init_sock_args *args) +{ + bpf_kfunc_init_sock(args); + + return 0; +} + +SEC("syscall") +int close_sock(void *ctx) +{ + bpf_kfunc_close_sock(); + + return 0; +} + +SEC("syscall") +int kernel_connect(struct addr_args *args) +{ + return bpf_kfunc_call_kernel_connect(args); +} + +SEC("syscall") +int kernel_bind(struct addr_args *args) +{ + return bpf_kfunc_call_kernel_bind(args); +} + +SEC("syscall") +int kernel_listen(struct addr_args *args) +{ + return bpf_kfunc_call_kernel_listen(); +} + +SEC("syscall") +int kernel_sendmsg(struct sendmsg_args *args) +{ + return bpf_kfunc_call_kernel_sendmsg(args); +} + +SEC("syscall") +int sock_sendmsg(struct sendmsg_args *args) +{ + return bpf_kfunc_call_sock_sendmsg(args); +} + +SEC("syscall") +int kernel_getsockname(struct addr_args *args) +{ + return bpf_kfunc_call_kernel_getsockname(args); +} + +SEC("syscall") +int kernel_getpeername(struct addr_args *args) +{ + return bpf_kfunc_call_kernel_getpeername(args); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c index 83753b00a556..5c3614333b01 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c @@ -1,24 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include -#include -#include -#include -#include -#include "bpf_tcp_helpers.h" +#include "bpf_tracing_net.h" char _license[] SEC("license") = "GPL"; __s32 page_size = 0; +const char cc_reno[TCP_CA_NAME_MAX] = "reno"; +const char cc_cubic[TCP_CA_NAME_MAX] = "cubic"; + SEC("cgroup/setsockopt") int sockopt_qos_to_cc(struct bpf_sockopt *ctx) { void *optval_end = ctx->optval_end; int *optval = ctx->optval; char buf[TCP_CA_NAME_MAX]; - char cc_reno[TCP_CA_NAME_MAX] = "reno"; - char cc_cubic[TCP_CA_NAME_MAX] = "cubic"; if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS) goto out; @@ -29,11 +25,11 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) if (bpf_getsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf))) return 0; - if (!tcp_cc_eq(buf, cc_cubic)) + if (bpf_strncmp(buf, sizeof(buf), cc_cubic)) return 0; if (*optval == 0x2d) { - if (bpf_setsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &cc_reno, + if (bpf_setsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, (void *)&cc_reno, sizeof(cc_reno))) return 0; } diff --git a/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c new file mode 100644 index 000000000000..3c822103bd40 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +SEC("struct_ops/test_1") +int BPF_PROG(test_1_forgotten) +{ + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops ops = { + /* we forgot to reference test_1_forgotten above, oops */ +}; + diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c index 63b065dae002..4c56d4a9d9f4 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_module.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c @@ -63,10 +63,17 @@ struct bpf_testmod_ops___zeroed { int zeroed; }; +SEC("struct_ops/test_3") +int BPF_PROG(zeroed_op) +{ + return 1; +} + SEC(".struct_ops.link") struct bpf_testmod_ops___zeroed testmod_zeroed = { .test_1 = (void *)test_1, .test_2 = (void *)test_2_v2, + .zeroed_op = (void *)zeroed_op, }; struct bpf_testmod_ops___incompatible { diff --git a/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c new file mode 100644 index 000000000000..fa2021388485 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +int rand; +int arr[1]; + +SEC("struct_ops/test_1") +int BPF_PROG(test_1_turn_off) +{ + return arr[rand]; /* potentially way out of range access */ +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops ops = { + .test_1 = (void *)test_1_turn_off, +}; + diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c b/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c index 7bb872fb22dd..0016c90e9c13 100644 --- a/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c +++ b/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c @@ -1,24 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 -#include "vmlinux.h" - +#include "bpf_tracing_net.h" #include #include char _license[] SEC("license") = "GPL"; -static inline struct tcp_sock *tcp_sk(const struct sock *sk) -{ - return (struct tcp_sock *)sk; -} - -SEC("struct_ops/incompl_cong_ops_ssthresh") +SEC("struct_ops") __u32 BPF_PROG(incompl_cong_ops_ssthresh, struct sock *sk) { return tcp_sk(sk)->snd_ssthresh; } -SEC("struct_ops/incompl_cong_ops_undo_cwnd") +SEC("struct_ops") __u32 BPF_PROG(incompl_cong_ops_undo_cwnd, struct sock *sk) { return tcp_sk(sk)->snd_cwnd; diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c index fcfbfe0336b4..f95862f570b7 100644 --- a/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c +++ b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c @@ -5,7 +5,7 @@ #include extern void bbr_init(struct sock *sk) __ksym; -extern void bbr_main(struct sock *sk, const struct rate_sample *rs) __ksym; +extern void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) __ksym; extern u32 bbr_sndbuf_expand(struct sock *sk) __ksym; extern u32 bbr_undo_cwnd(struct sock *sk) __ksym; extern void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym; @@ -27,7 +27,7 @@ extern void cubictcp_state(struct sock *sk, u8 new_state) __ksym; extern void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym; extern void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) __ksym; -SEC("struct_ops/init") +SEC("struct_ops") void BPF_PROG(init, struct sock *sk) { bbr_init(sk); @@ -35,38 +35,38 @@ void BPF_PROG(init, struct sock *sk) cubictcp_init(sk); } -SEC("struct_ops/in_ack_event") +SEC("struct_ops") void BPF_PROG(in_ack_event, struct sock *sk, u32 flags) { dctcp_update_alpha(sk, flags); } -SEC("struct_ops/cong_control") -void BPF_PROG(cong_control, struct sock *sk, const struct rate_sample *rs) +SEC("struct_ops") +void BPF_PROG(cong_control, struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) { - bbr_main(sk, rs); + bbr_main(sk, ack, flag, rs); } -SEC("struct_ops/cong_avoid") +SEC("struct_ops") void BPF_PROG(cong_avoid, struct sock *sk, u32 ack, u32 acked) { cubictcp_cong_avoid(sk, ack, acked); } -SEC("struct_ops/sndbuf_expand") +SEC("struct_ops") u32 BPF_PROG(sndbuf_expand, struct sock *sk) { return bbr_sndbuf_expand(sk); } -SEC("struct_ops/undo_cwnd") +SEC("struct_ops") u32 BPF_PROG(undo_cwnd, struct sock *sk) { bbr_undo_cwnd(sk); return dctcp_cwnd_undo(sk); } -SEC("struct_ops/cwnd_event") +SEC("struct_ops") void BPF_PROG(cwnd_event, struct sock *sk, enum tcp_ca_event event) { bbr_cwnd_event(sk, event); @@ -74,7 +74,7 @@ void BPF_PROG(cwnd_event, struct sock *sk, enum tcp_ca_event event) cubictcp_cwnd_event(sk, event); } -SEC("struct_ops/ssthresh") +SEC("struct_ops") u32 BPF_PROG(ssthresh, struct sock *sk) { bbr_ssthresh(sk); @@ -82,13 +82,13 @@ u32 BPF_PROG(ssthresh, struct sock *sk) return cubictcp_recalc_ssthresh(sk); } -SEC("struct_ops/min_tso_segs") +SEC("struct_ops") u32 BPF_PROG(min_tso_segs, struct sock *sk) { return bbr_min_tso_segs(sk); } -SEC("struct_ops/set_state") +SEC("struct_ops") void BPF_PROG(set_state, struct sock *sk, u8 new_state) { bbr_set_state(sk, new_state); @@ -96,7 +96,7 @@ void BPF_PROG(set_state, struct sock *sk, u8 new_state) cubictcp_state(sk, new_state); } -SEC("struct_ops/pkts_acked") +SEC("struct_ops") void BPF_PROG(pkts_acked, struct sock *sk, const struct ack_sample *sample) { cubictcp_acked(sk, sample); diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c b/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c index c06f4a41c21a..54f916a931c6 100644 --- a/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c +++ b/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c @@ -7,7 +7,7 @@ char _license[] SEC("license") = "GPL"; -SEC("struct_ops/unsupp_cong_op_get_info") +SEC("struct_ops") size_t BPF_PROG(unsupp_cong_op_get_info, struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_update.c b/tools/testing/selftests/bpf/progs/tcp_ca_update.c index b93a0ed33057..e4bd82bc0d01 100644 --- a/tools/testing/selftests/bpf/progs/tcp_ca_update.c +++ b/tools/testing/selftests/bpf/progs/tcp_ca_update.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include "vmlinux.h" - +#include "bpf_tracing_net.h" #include #include @@ -10,36 +9,31 @@ char _license[] SEC("license") = "GPL"; int ca1_cnt = 0; int ca2_cnt = 0; -static inline struct tcp_sock *tcp_sk(const struct sock *sk) -{ - return (struct tcp_sock *)sk; -} - -SEC("struct_ops/ca_update_1_init") +SEC("struct_ops") void BPF_PROG(ca_update_1_init, struct sock *sk) { ca1_cnt++; } -SEC("struct_ops/ca_update_2_init") +SEC("struct_ops") void BPF_PROG(ca_update_2_init, struct sock *sk) { ca2_cnt++; } -SEC("struct_ops/ca_update_cong_control") +SEC("struct_ops") void BPF_PROG(ca_update_cong_control, struct sock *sk, const struct rate_sample *rs) { } -SEC("struct_ops/ca_update_ssthresh") +SEC("struct_ops") __u32 BPF_PROG(ca_update_ssthresh, struct sock *sk) { return tcp_sk(sk)->snd_ssthresh; } -SEC("struct_ops/ca_update_undo_cwnd") +SEC("struct_ops") __u32 BPF_PROG(ca_update_undo_cwnd, struct sock *sk) { return tcp_sk(sk)->snd_cwnd; diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c index 0724a79cec78..a58b5194fc89 100644 --- a/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c +++ b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include "vmlinux.h" - +#include "bpf_tracing_net.h" #include #include @@ -11,22 +10,17 @@ char _license[] SEC("license") = "GPL"; #define min(a, b) ((a) < (b) ? (a) : (b)) -static inline struct tcp_sock *tcp_sk(const struct sock *sk) -{ - return (struct tcp_sock *)sk; -} - -static inline unsigned int tcp_left_out(const struct tcp_sock *tp) +static unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; } -static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) +static unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) { return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; } -SEC("struct_ops/write_sk_pacing_init") +SEC("struct_ops") void BPF_PROG(write_sk_pacing_init, struct sock *sk) { #ifdef ENABLE_ATOMICS_TESTS @@ -37,7 +31,7 @@ void BPF_PROG(write_sk_pacing_init, struct sock *sk) #endif } -SEC("struct_ops/write_sk_pacing_cong_control") +SEC("struct_ops") void BPF_PROG(write_sk_pacing_cong_control, struct sock *sk, const struct rate_sample *rs) { @@ -49,13 +43,13 @@ void BPF_PROG(write_sk_pacing_cong_control, struct sock *sk, tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ?: 1; } -SEC("struct_ops/write_sk_pacing_ssthresh") +SEC("struct_ops") __u32 BPF_PROG(write_sk_pacing_ssthresh, struct sock *sk) { return tcp_sk(sk)->snd_ssthresh; } -SEC("struct_ops/write_sk_pacing_undo_cwnd") +SEC("struct_ops") __u32 BPF_PROG(write_sk_pacing_undo_cwnd, struct sock *sk) { return tcp_sk(sk)->snd_cwnd; diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c index e2bea4da194b..f0759efff6ef 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c @@ -1,19 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ -#include -#include -#include -#include -#include -#include -#include -#include -#include - +#include "bpf_tracing_net.h" #include #include -#include "bpf_tcp_helpers.h" + +#ifndef ENOENT +#define ENOENT 2 +#endif struct sockaddr_in6 srv_sa6 = {}; __u16 listen_tp_sport = 0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c index 8fba3f3649e2..5da001ca57a5 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func10.c +++ b/tools/testing/selftests/bpf/progs/test_global_func10.c @@ -4,6 +4,10 @@ #include #include "bpf_misc.h" +#if !defined(__clang__) +#pragma GCC diagnostic ignored "-Wmaybe-uninitialized" +#endif + struct Small { long x; }; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c index 8c895122f293..83439b87b766 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c @@ -3,7 +3,7 @@ #include #include #include -#include "bpf_tracing_net.h" +#include /* We don't care about whether the packet can be received by network stack. * Just care if the packet is sent to the correct device at correct direction diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c index 8a1b50f3a002..cc1a012d038f 100644 --- a/tools/testing/selftests/bpf/progs/test_module_attach.c +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -73,6 +73,29 @@ int BPF_PROG(handle_fentry_manual, return 0; } +__u32 fentry_explicit_read_sz = 0; + +SEC("fentry/bpf_testmod:bpf_testmod_test_read") +int BPF_PROG(handle_fentry_explicit, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + fentry_explicit_read_sz = len; + return 0; +} + + +__u32 fentry_explicit_manual_read_sz = 0; + +SEC("fentry") +int BPF_PROG(handle_fentry_explicit_manual, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + fentry_explicit_manual_read_sz = len; + return 0; +} + __u32 fexit_read_sz = 0; int fexit_ret = 0; diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index f75e531bf36f..196844be349c 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -7,7 +7,6 @@ #include #include -#include "bpf_tcp_helpers.h" enum bpf_linum_array_idx { EGRESS_LINUM_IDX, @@ -42,6 +41,10 @@ struct { __type(value, struct bpf_spinlock_cnt); } sk_pkt_out_cnt10 SEC(".maps"); +struct tcp_sock { + __u32 lsndtime; +} __attribute__((preserve_access_index)); + struct bpf_tcp_sock listen_tp = {}; struct sockaddr_in6 srv_sa6 = {}; struct bpf_tcp_sock cli_tp = {}; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index a3f3f43fc195..6935f32eeb8f 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -1,18 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include +#include "bpf_tracing_net.h" #include #include -#include "bpf_tcp_helpers.h" #include "test_tcpbpf.h" struct tcpbpf_globals global = {}; diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 3e436e6f7312..3f5abcf3ff13 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -567,12 +567,18 @@ int ip6vxlan_get_tunnel_src(struct __sk_buff *skb) return TC_ACT_OK; } +struct local_geneve_opt { + struct geneve_opt gopt; + int data; +}; + SEC("tc") int geneve_set_tunnel(struct __sk_buff *skb) { int ret; struct bpf_tunnel_key key; - struct geneve_opt gopt; + struct local_geneve_opt local_gopt; + struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt; __builtin_memset(&key, 0x0, sizeof(key)); key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ @@ -580,14 +586,14 @@ int geneve_set_tunnel(struct __sk_buff *skb) key.tunnel_tos = 0; key.tunnel_ttl = 64; - __builtin_memset(&gopt, 0x0, sizeof(gopt)); - gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ - gopt.type = 0x08; - gopt.r1 = 0; - gopt.r2 = 0; - gopt.r3 = 0; - gopt.length = 2; /* 4-byte multiple */ - *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef); + __builtin_memset(gopt, 0x0, sizeof(local_gopt)); + gopt->opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt->type = 0x08; + gopt->r1 = 0; + gopt->r2 = 0; + gopt->r3 = 0; + gopt->length = 2; /* 4-byte multiple */ + *(int *) &gopt->opt_data = bpf_htonl(0xdeadbeef); ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX); @@ -596,7 +602,7 @@ int geneve_set_tunnel(struct __sk_buff *skb) return TC_ACT_SHOT; } - ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(local_gopt)); if (ret < 0) { log_err(ret); return TC_ACT_SHOT; @@ -631,7 +637,8 @@ SEC("tc") int ip6geneve_set_tunnel(struct __sk_buff *skb) { struct bpf_tunnel_key key; - struct geneve_opt gopt; + struct local_geneve_opt local_gopt; + struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt; int ret; __builtin_memset(&key, 0x0, sizeof(key)); @@ -647,16 +654,16 @@ int ip6geneve_set_tunnel(struct __sk_buff *skb) return TC_ACT_SHOT; } - __builtin_memset(&gopt, 0x0, sizeof(gopt)); - gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ - gopt.type = 0x08; - gopt.r1 = 0; - gopt.r2 = 0; - gopt.r3 = 0; - gopt.length = 2; /* 4-byte multiple */ - *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef); + __builtin_memset(gopt, 0x0, sizeof(local_gopt)); + gopt->opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt->type = 0x08; + gopt->r1 = 0; + gopt->r2 = 0; + gopt->r3 = 0; + gopt->length = 2; /* 4-byte multiple */ + *(int *) &gopt->opt_data = bpf_htonl(0xfeedbeef); - ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt)); if (ret < 0) { log_err(ret); return TC_ACT_SHOT; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 5c7e4758a0ca..fad94e41cef9 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -318,6 +318,14 @@ bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval, return true; } +#ifndef __clang__ +#pragma GCC push_options +/* GCC optimization collapses functions and increases the number of arguments + * beyond the compatible amount supported by BPF. + */ +#pragma GCC optimize("-fno-ipa-sra") +#endif + static __attribute__ ((noinline)) bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, struct packet_description *pckt, @@ -372,6 +380,10 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, return true; } +#ifndef __clang__ +#pragma GCC pop_options +#endif + static __attribute__ ((noinline)) int swap_mac_and_send(void *data, void *data_end) { @@ -588,12 +600,13 @@ static void connection_table_lookup(struct real_definition **real, __attribute__ ((noinline)) static int process_l3_headers_v6(struct packet_description *pckt, __u8 *protocol, __u64 off, - __u16 *pkt_bytes, void *data, - void *data_end) + __u16 *pkt_bytes, void *extra_args[2]) { struct ipv6hdr *ip6h; __u64 iph_len; int action; + void *data = extra_args[0]; + void *data_end = extra_args[1]; ip6h = data + off; if (ip6h + 1 > data_end) @@ -619,11 +632,12 @@ static int process_l3_headers_v6(struct packet_description *pckt, __attribute__ ((noinline)) static int process_l3_headers_v4(struct packet_description *pckt, __u8 *protocol, __u64 off, - __u16 *pkt_bytes, void *data, - void *data_end) + __u16 *pkt_bytes, void *extra_args[2]) { struct iphdr *iph; int action; + void *data = extra_args[0]; + void *data_end = extra_args[1]; iph = data + off; if (iph + 1 > data_end) @@ -666,13 +680,14 @@ static int process_packet(void *data, __u64 off, void *data_end, __u8 protocol; __u32 vip_num; int action; + void *extra_args[2] = { data, data_end }; if (is_ipv6) action = process_l3_headers_v6(&pckt, &protocol, off, - &pkt_bytes, data, data_end); + &pkt_bytes, extra_args); else action = process_l3_headers_v4(&pckt, &protocol, off, - &pkt_bytes, data, data_end); + &pkt_bytes, extra_args); if (action >= 0) return action; protocol = pckt.flow.proto; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c index f3ec8086482d..a7588302268d 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c @@ -160,7 +160,7 @@ int xdp_prognum1(struct xdp_md *ctx) /* Modifying VLAN, preserve top 4 bits */ vlan_hdr->h_vlan_TCI = - bpf_htons((bpf_ntohs(vlan_hdr->h_vlan_TCI) & 0xf000) + bpf_htons((bpf_ntohs(vlan_hdr->h_vlan_TCI) & 0xf000U) | TO_VLAN); } diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c index f615da97df26..4c677c001258 100644 --- a/tools/testing/selftests/bpf/progs/timer.c +++ b/tools/testing/selftests/bpf/progs/timer.c @@ -2,9 +2,10 @@ /* Copyright (c) 2021 Facebook */ #include #include +#include #include #include -#include "bpf_tcp_helpers.h" +#include char _license[] SEC("license") = "GPL"; struct hmap_elem { diff --git a/tools/testing/selftests/bpf/progs/timer_failure.c b/tools/testing/selftests/bpf/progs/timer_failure.c index 0996c2486f05..5a2e9dabf1c6 100644 --- a/tools/testing/selftests/bpf/progs/timer_failure.c +++ b/tools/testing/selftests/bpf/progs/timer_failure.c @@ -5,8 +5,8 @@ #include #include #include +#include #include "bpf_misc.h" -#include "bpf_tcp_helpers.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/timer_mim.c b/tools/testing/selftests/bpf/progs/timer_mim.c index 2fee7ab105ef..50ebc3f68522 100644 --- a/tools/testing/selftests/bpf/progs/timer_mim.c +++ b/tools/testing/selftests/bpf/progs/timer_mim.c @@ -4,7 +4,7 @@ #include #include #include -#include "bpf_tcp_helpers.h" +#include char _license[] SEC("license") = "GPL"; struct hmap_elem { diff --git a/tools/testing/selftests/bpf/progs/timer_mim_reject.c b/tools/testing/selftests/bpf/progs/timer_mim_reject.c index 5d648e3d8a41..dd3f1ed6d6e6 100644 --- a/tools/testing/selftests/bpf/progs/timer_mim_reject.c +++ b/tools/testing/selftests/bpf/progs/timer_mim_reject.c @@ -4,7 +4,7 @@ #include #include #include -#include "bpf_tcp_helpers.h" +#include char _license[] SEC("license") = "GPL"; struct hmap_elem { diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 960998f16306..a0bb7fb40ea5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -885,6 +885,69 @@ l1_%=: r0 = 0; \ : __clobber_all); } +SEC("socket") +__description("bounds check for non const xor src dst") +__success __log_level(2) +__msg("5: (af) r0 ^= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))") +__naked void non_const_xor_src_dst(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r6 &= 0xaf; \ + r0 &= 0x1a0; \ + r0 ^= r6; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for non const or src dst") +__success __log_level(2) +__msg("5: (4f) r0 |= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))") +__naked void non_const_or_src_dst(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r6 &= 0xaf; \ + r0 &= 0x1a0; \ + r0 |= r6; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("bounds check for non const mul regs") +__success __log_level(2) +__msg("5: (2f) r0 *= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=3825,var_off=(0x0; 0xfff))") +__naked void non_const_mul_regs(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r6 = r0; \ + call %[bpf_get_prandom_u32]; \ + r6 &= 0xff; \ + r0 &= 0x0f; \ + r0 *= r6; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b), + __imm(bpf_get_prandom_u32) + : __clobber_all); +} + SEC("socket") __description("bounds checks after 32-bit truncation. test 1") __success __failure_unpriv __msg_unpriv("R0 leaks addr") diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index baff5ffe9405..a9fc30ed4d73 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -8,6 +8,13 @@ #include "xdp_metadata.h" #include "bpf_kfuncs.h" +/* The compiler may be able to detect the access to uninitialized + memory in the routines performing out of bound memory accesses and + emit warnings about it. This is the case of GCC. */ +#if !defined(__clang__) +#pragma GCC diagnostic ignored "-Wmaybe-uninitialized" +#endif + int arr[1]; int unkn_idx; const volatile bool call_dead_subprog = false; diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index 99e561f18f9b..bd676d7e615f 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -318,7 +318,7 @@ int cond_break1(const void *ctx) unsigned long i; unsigned int sum = 0; - for (i = zero; i < ARR_SZ; cond_break, i++) + for (i = zero; i < ARR_SZ && can_loop; i++) sum += i; for (i = zero; i < ARR_SZ; i++) { barrier_var(i); @@ -336,12 +336,11 @@ int cond_break2(const void *ctx) int i, j; int sum = 0; - for (i = zero; i < 1000; cond_break, i++) + for (i = zero; i < 1000 && can_loop; i++) for (j = zero; j < 1000; j++) { sum += i + j; cond_break; - } - + } return sum; } @@ -349,7 +348,7 @@ static __noinline int loop(void) { int i, sum = 0; - for (i = zero; i <= 1000000; i++, cond_break) + for (i = zero; i <= 1000000 && can_loop; i++) sum += i; return sum; diff --git a/tools/testing/selftests/bpf/progs/verifier_sock_addr.c b/tools/testing/selftests/bpf/progs/verifier_sock_addr.c new file mode 100644 index 000000000000..9c31448a0f52 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_sock_addr.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google LLC */ + +#include +#include +#include +#include "bpf_misc.h" + +SEC("cgroup/recvmsg4") +__success +int recvmsg4_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/recvmsg4") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int recvmsg4_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/recvmsg6") +__success +int recvmsg6_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/recvmsg6") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int recvmsg6_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/recvmsg_unix") +__success +int recvmsg_unix_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/recvmsg_unix") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int recvmsg_unix_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/sendmsg4") +__success +int sendmsg4_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/sendmsg4") +__success +int sendmsg4_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/sendmsg4") +__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]") +int sendmsg4_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 2; +} + +SEC("cgroup/sendmsg6") +__success +int sendmsg6_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/sendmsg6") +__success +int sendmsg6_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/sendmsg6") +__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]") +int sendmsg6_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 2; +} + +SEC("cgroup/sendmsg_unix") +__success +int sendmsg_unix_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/sendmsg_unix") +__success +int sendmsg_unix_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/sendmsg_unix") +__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]") +int sendmsg_unix_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 2; +} + +SEC("cgroup/getpeername4") +__success +int getpeername4_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/getpeername4") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int getpeername4_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/getpeername6") +__success +int getpeername6_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/getpeername6") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int getpeername6_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/getpeername_unix") +__success +int getpeername_unix_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/getpeername_unix") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int getpeername_unix_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/getsockname4") +__success +int getsockname4_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/getsockname4") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int getsockname4_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/getsockname6") +__success +int getsockname6_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/getsockname6") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int getsockname6_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/getsockname_unix") +__success +int getsockname_unix_good_return_code(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/getsockname_unix") +__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]") +int getsockname_unix_unix_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/bind4") +__success +int bind4_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/bind4") +__success +int bind4_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/bind4") +__success +int bind4_good_return_code_2(struct bpf_sock_addr *ctx) +{ + return 2; +} + +SEC("cgroup/bind4") +__success +int bind4_good_return_code_3(struct bpf_sock_addr *ctx) +{ + return 3; +} + +SEC("cgroup/bind4") +__failure __msg("At program exit the register R0 has smin=4 smax=4 should have been in [0, 3]") +int bind4_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 4; +} + +SEC("cgroup/bind6") +__success +int bind6_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/bind6") +__success +int bind6_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/bind6") +__success +int bind6_good_return_code_2(struct bpf_sock_addr *ctx) +{ + return 2; +} + +SEC("cgroup/bind6") +__success +int bind6_good_return_code_3(struct bpf_sock_addr *ctx) +{ + return 3; +} + +SEC("cgroup/bind6") +__failure __msg("At program exit the register R0 has smin=4 smax=4 should have been in [0, 3]") +int bind6_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 4; +} + +SEC("cgroup/connect4") +__success +int connect4_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/connect4") +__success +int connect4_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/connect4") +__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]") +int connect4_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 2; +} + +SEC("cgroup/connect6") +__success +int connect6_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/connect6") +__success +int connect6_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/connect6") +__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]") +int connect6_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 2; +} + +SEC("cgroup/connect_unix") +__success +int connect_unix_good_return_code_0(struct bpf_sock_addr *ctx) +{ + return 0; +} + +SEC("cgroup/connect_unix") +__success +int connect_unix_good_return_code_1(struct bpf_sock_addr *ctx) +{ + return 1; +} + +SEC("cgroup/connect_unix") +__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]") +int connect_unix_bad_return_code(struct bpf_sock_addr *ctx) +{ + return 2; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c deleted file mode 100644 index c412de84b88f..000000000000 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ /dev/null @@ -1,1332 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2018 Facebook - -#define _GNU_SOURCE - -#include -#include -#include - -#include -#include -#include -#include -#include - -#include - -#include -#include - -#include "cgroup_helpers.h" -#include "network_helpers.h" -#include "testing_helpers.h" -#include "bpf_util.h" - -#ifndef ENOTSUPP -# define ENOTSUPP 524 -#endif - -#define CG_PATH "/foo" -#define CONNECT4_PROG_PATH "./connect4_prog.bpf.o" -#define CONNECT6_PROG_PATH "./connect6_prog.bpf.o" -#define SENDMSG4_PROG_PATH "./sendmsg4_prog.bpf.o" -#define SENDMSG6_PROG_PATH "./sendmsg6_prog.bpf.o" -#define RECVMSG4_PROG_PATH "./recvmsg4_prog.bpf.o" -#define RECVMSG6_PROG_PATH "./recvmsg6_prog.bpf.o" -#define BIND4_PROG_PATH "./bind4_prog.bpf.o" -#define BIND6_PROG_PATH "./bind6_prog.bpf.o" - -#define SERV4_IP "192.168.1.254" -#define SERV4_REWRITE_IP "127.0.0.1" -#define SRC4_IP "172.16.0.1" -#define SRC4_REWRITE_IP "127.0.0.4" -#define SERV4_PORT 4040 -#define SERV4_REWRITE_PORT 4444 - -#define SERV6_IP "face:b00c:1234:5678::abcd" -#define SERV6_REWRITE_IP "::1" -#define SERV6_V4MAPPED_IP "::ffff:192.168.0.4" -#define SRC6_IP "::1" -#define SRC6_REWRITE_IP "::6" -#define WILDCARD6_IP "::" -#define SERV6_PORT 6060 -#define SERV6_REWRITE_PORT 6666 - -#define INET_NTOP_BUF 40 - -struct sock_addr_test; - -typedef int (*load_fn)(const struct sock_addr_test *test); -typedef int (*info_fn)(int, struct sockaddr *, socklen_t *); - -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - -struct sock_addr_test { - const char *descr; - /* BPF prog properties */ - load_fn loadfn; - enum bpf_attach_type expected_attach_type; - enum bpf_attach_type attach_type; - /* Socket properties */ - int domain; - int type; - /* IP:port pairs for BPF prog to override */ - const char *requested_ip; - unsigned short requested_port; - const char *expected_ip; - unsigned short expected_port; - const char *expected_src_ip; - /* Expected test result */ - enum { - LOAD_REJECT, - ATTACH_REJECT, - ATTACH_OKAY, - SYSCALL_EPERM, - SYSCALL_ENOTSUPP, - SUCCESS, - } expected_result; -}; - -static int bind4_prog_load(const struct sock_addr_test *test); -static int bind6_prog_load(const struct sock_addr_test *test); -static int connect4_prog_load(const struct sock_addr_test *test); -static int connect6_prog_load(const struct sock_addr_test *test); -static int sendmsg_allow_prog_load(const struct sock_addr_test *test); -static int sendmsg_deny_prog_load(const struct sock_addr_test *test); -static int recvmsg_allow_prog_load(const struct sock_addr_test *test); -static int recvmsg_deny_prog_load(const struct sock_addr_test *test); -static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test); -static int recvmsg4_rw_c_prog_load(const struct sock_addr_test *test); -static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test); -static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test); -static int recvmsg6_rw_c_prog_load(const struct sock_addr_test *test); -static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test); -static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test); -static int sendmsg6_rw_wildcard_prog_load(const struct sock_addr_test *test); - -static struct sock_addr_test tests[] = { - /* bind */ - { - "bind4: load prog with wrong expected attach type", - bind4_prog_load, - BPF_CGROUP_INET6_BIND, - BPF_CGROUP_INET4_BIND, - AF_INET, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "bind4: attach prog with wrong attach type", - bind4_prog_load, - BPF_CGROUP_INET4_BIND, - BPF_CGROUP_INET6_BIND, - AF_INET, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_REJECT, - }, - { - "bind4: rewrite IP & TCP port in", - bind4_prog_load, - BPF_CGROUP_INET4_BIND, - BPF_CGROUP_INET4_BIND, - AF_INET, - SOCK_STREAM, - SERV4_IP, - SERV4_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - NULL, - SUCCESS, - }, - { - "bind4: rewrite IP & UDP port in", - bind4_prog_load, - BPF_CGROUP_INET4_BIND, - BPF_CGROUP_INET4_BIND, - AF_INET, - SOCK_DGRAM, - SERV4_IP, - SERV4_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - NULL, - SUCCESS, - }, - { - "bind6: load prog with wrong expected attach type", - bind6_prog_load, - BPF_CGROUP_INET4_BIND, - BPF_CGROUP_INET6_BIND, - AF_INET6, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "bind6: attach prog with wrong attach type", - bind6_prog_load, - BPF_CGROUP_INET6_BIND, - BPF_CGROUP_INET4_BIND, - AF_INET, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_REJECT, - }, - { - "bind6: rewrite IP & TCP port in", - bind6_prog_load, - BPF_CGROUP_INET6_BIND, - BPF_CGROUP_INET6_BIND, - AF_INET6, - SOCK_STREAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - NULL, - SUCCESS, - }, - { - "bind6: rewrite IP & UDP port in", - bind6_prog_load, - BPF_CGROUP_INET6_BIND, - BPF_CGROUP_INET6_BIND, - AF_INET6, - SOCK_DGRAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - NULL, - SUCCESS, - }, - - /* connect */ - { - "connect4: load prog with wrong expected attach type", - connect4_prog_load, - BPF_CGROUP_INET6_CONNECT, - BPF_CGROUP_INET4_CONNECT, - AF_INET, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "connect4: attach prog with wrong attach type", - connect4_prog_load, - BPF_CGROUP_INET4_CONNECT, - BPF_CGROUP_INET6_CONNECT, - AF_INET, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_REJECT, - }, - { - "connect4: rewrite IP & TCP port", - connect4_prog_load, - BPF_CGROUP_INET4_CONNECT, - BPF_CGROUP_INET4_CONNECT, - AF_INET, - SOCK_STREAM, - SERV4_IP, - SERV4_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - SRC4_REWRITE_IP, - SUCCESS, - }, - { - "connect4: rewrite IP & UDP port", - connect4_prog_load, - BPF_CGROUP_INET4_CONNECT, - BPF_CGROUP_INET4_CONNECT, - AF_INET, - SOCK_DGRAM, - SERV4_IP, - SERV4_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - SRC4_REWRITE_IP, - SUCCESS, - }, - { - "connect6: load prog with wrong expected attach type", - connect6_prog_load, - BPF_CGROUP_INET4_CONNECT, - BPF_CGROUP_INET6_CONNECT, - AF_INET6, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "connect6: attach prog with wrong attach type", - connect6_prog_load, - BPF_CGROUP_INET6_CONNECT, - BPF_CGROUP_INET4_CONNECT, - AF_INET, - SOCK_STREAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_REJECT, - }, - { - "connect6: rewrite IP & TCP port", - connect6_prog_load, - BPF_CGROUP_INET6_CONNECT, - BPF_CGROUP_INET6_CONNECT, - AF_INET6, - SOCK_STREAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SRC6_REWRITE_IP, - SUCCESS, - }, - { - "connect6: rewrite IP & UDP port", - connect6_prog_load, - BPF_CGROUP_INET6_CONNECT, - BPF_CGROUP_INET6_CONNECT, - AF_INET6, - SOCK_DGRAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SRC6_REWRITE_IP, - SUCCESS, - }, - - /* sendmsg */ - { - "sendmsg4: load prog with wrong expected attach type", - sendmsg4_rw_asm_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP4_SENDMSG, - AF_INET, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "sendmsg4: attach prog with wrong attach type", - sendmsg4_rw_asm_prog_load, - BPF_CGROUP_UDP4_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_REJECT, - }, - { - "sendmsg4: rewrite IP & port (asm)", - sendmsg4_rw_asm_prog_load, - BPF_CGROUP_UDP4_SENDMSG, - BPF_CGROUP_UDP4_SENDMSG, - AF_INET, - SOCK_DGRAM, - SERV4_IP, - SERV4_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - SRC4_REWRITE_IP, - SUCCESS, - }, - { - "sendmsg4: rewrite IP & port (C)", - sendmsg4_rw_c_prog_load, - BPF_CGROUP_UDP4_SENDMSG, - BPF_CGROUP_UDP4_SENDMSG, - AF_INET, - SOCK_DGRAM, - SERV4_IP, - SERV4_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - SRC4_REWRITE_IP, - SUCCESS, - }, - { - "sendmsg4: deny call", - sendmsg_deny_prog_load, - BPF_CGROUP_UDP4_SENDMSG, - BPF_CGROUP_UDP4_SENDMSG, - AF_INET, - SOCK_DGRAM, - SERV4_IP, - SERV4_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - SRC4_REWRITE_IP, - SYSCALL_EPERM, - }, - { - "sendmsg6: load prog with wrong expected attach type", - sendmsg6_rw_asm_prog_load, - BPF_CGROUP_UDP4_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET6, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "sendmsg6: attach prog with wrong attach type", - sendmsg6_rw_asm_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP4_SENDMSG, - AF_INET6, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_REJECT, - }, - { - "sendmsg6: rewrite IP & port (asm)", - sendmsg6_rw_asm_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET6, - SOCK_DGRAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SRC6_REWRITE_IP, - SUCCESS, - }, - { - "sendmsg6: rewrite IP & port (C)", - sendmsg6_rw_c_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET6, - SOCK_DGRAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SRC6_REWRITE_IP, - SUCCESS, - }, - { - "sendmsg6: IPv4-mapped IPv6", - sendmsg6_rw_v4mapped_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET6, - SOCK_DGRAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SRC6_REWRITE_IP, - SYSCALL_ENOTSUPP, - }, - { - "sendmsg6: set dst IP = [::] (BSD'ism)", - sendmsg6_rw_wildcard_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET6, - SOCK_DGRAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SRC6_REWRITE_IP, - SUCCESS, - }, - { - "sendmsg6: preserve dst IP = [::] (BSD'ism)", - sendmsg_allow_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET6, - SOCK_DGRAM, - WILDCARD6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_PORT, - SRC6_IP, - SUCCESS, - }, - { - "sendmsg6: deny call", - sendmsg_deny_prog_load, - BPF_CGROUP_UDP6_SENDMSG, - BPF_CGROUP_UDP6_SENDMSG, - AF_INET6, - SOCK_DGRAM, - SERV6_IP, - SERV6_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SRC6_REWRITE_IP, - SYSCALL_EPERM, - }, - - /* recvmsg */ - { - "recvmsg4: return code ok", - recvmsg_allow_prog_load, - BPF_CGROUP_UDP4_RECVMSG, - BPF_CGROUP_UDP4_RECVMSG, - AF_INET, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_OKAY, - }, - { - "recvmsg4: return code !ok", - recvmsg_deny_prog_load, - BPF_CGROUP_UDP4_RECVMSG, - BPF_CGROUP_UDP4_RECVMSG, - AF_INET, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "recvmsg6: return code ok", - recvmsg_allow_prog_load, - BPF_CGROUP_UDP6_RECVMSG, - BPF_CGROUP_UDP6_RECVMSG, - AF_INET6, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - ATTACH_OKAY, - }, - { - "recvmsg6: return code !ok", - recvmsg_deny_prog_load, - BPF_CGROUP_UDP6_RECVMSG, - BPF_CGROUP_UDP6_RECVMSG, - AF_INET6, - SOCK_DGRAM, - NULL, - 0, - NULL, - 0, - NULL, - LOAD_REJECT, - }, - { - "recvmsg4: rewrite IP & port (C)", - recvmsg4_rw_c_prog_load, - BPF_CGROUP_UDP4_RECVMSG, - BPF_CGROUP_UDP4_RECVMSG, - AF_INET, - SOCK_DGRAM, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - SERV4_REWRITE_IP, - SERV4_REWRITE_PORT, - SERV4_IP, - SUCCESS, - }, - { - "recvmsg6: rewrite IP & port (C)", - recvmsg6_rw_c_prog_load, - BPF_CGROUP_UDP6_RECVMSG, - BPF_CGROUP_UDP6_RECVMSG, - AF_INET6, - SOCK_DGRAM, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SERV6_REWRITE_IP, - SERV6_REWRITE_PORT, - SERV6_IP, - SUCCESS, - }, -}; - -static int load_insns(const struct sock_addr_test *test, - const struct bpf_insn *insns, size_t insns_cnt) -{ - LIBBPF_OPTS(bpf_prog_load_opts, opts); - int ret; - - opts.expected_attach_type = test->expected_attach_type; - opts.log_buf = bpf_log_buf; - opts.log_size = BPF_LOG_BUF_SIZE; - - ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, NULL, "GPL", insns, insns_cnt, &opts); - if (ret < 0 && test->expected_result != LOAD_REJECT) { - log_err(">>> Loading program error.\n" - ">>> Verifier output:\n%s\n-------\n", bpf_log_buf); - } - - return ret; -} - -static int load_path(const struct sock_addr_test *test, const char *path) -{ - struct bpf_object *obj; - struct bpf_program *prog; - int err; - - obj = bpf_object__open_file(path, NULL); - err = libbpf_get_error(obj); - if (err) { - log_err(">>> Opening BPF object (%s) error.\n", path); - return -1; - } - - prog = bpf_object__next_program(obj, NULL); - if (!prog) - goto err_out; - - bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR); - bpf_program__set_expected_attach_type(prog, test->expected_attach_type); - bpf_program__set_flags(prog, testing_prog_flags()); - - err = bpf_object__load(obj); - if (err) { - if (test->expected_result != LOAD_REJECT) - log_err(">>> Loading program (%s) error.\n", path); - goto err_out; - } - - return bpf_program__fd(prog); -err_out: - bpf_object__close(obj); - return -1; -} - -static int bind4_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, BIND4_PROG_PATH); -} - -static int bind6_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, BIND6_PROG_PATH); -} - -static int connect4_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, CONNECT4_PROG_PATH); -} - -static int connect6_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, CONNECT6_PROG_PATH); -} - -static int xmsg_ret_only_prog_load(const struct sock_addr_test *test, - int32_t rc) -{ - struct bpf_insn insns[] = { - /* return rc */ - BPF_MOV64_IMM(BPF_REG_0, rc), - BPF_EXIT_INSN(), - }; - return load_insns(test, insns, ARRAY_SIZE(insns)); -} - -static int sendmsg_allow_prog_load(const struct sock_addr_test *test) -{ - return xmsg_ret_only_prog_load(test, /*rc*/ 1); -} - -static int sendmsg_deny_prog_load(const struct sock_addr_test *test) -{ - return xmsg_ret_only_prog_load(test, /*rc*/ 0); -} - -static int recvmsg_allow_prog_load(const struct sock_addr_test *test) -{ - return xmsg_ret_only_prog_load(test, /*rc*/ 1); -} - -static int recvmsg_deny_prog_load(const struct sock_addr_test *test) -{ - return xmsg_ret_only_prog_load(test, /*rc*/ 0); -} - -static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) -{ - struct sockaddr_in dst4_rw_addr; - struct in_addr src4_rw_ip; - - if (inet_pton(AF_INET, SRC4_REWRITE_IP, (void *)&src4_rw_ip) != 1) { - log_err("Invalid IPv4: %s", SRC4_REWRITE_IP); - return -1; - } - - if (make_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT, - (struct sockaddr_storage *)&dst4_rw_addr, - NULL) == -1) - return -1; - - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - - /* if (sk.family == AF_INET && */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, family)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 8), - - /* sk.type == SOCK_DGRAM) { */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, type)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 6), - - /* msg_src_ip4 = src4_rw_ip */ - BPF_MOV32_IMM(BPF_REG_7, src4_rw_ip.s_addr), - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, - offsetof(struct bpf_sock_addr, msg_src_ip4)), - - /* user_ip4 = dst4_rw_addr.sin_addr */ - BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_addr.s_addr), - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, - offsetof(struct bpf_sock_addr, user_ip4)), - - /* user_port = dst4_rw_addr.sin_port */ - BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_port), - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, - offsetof(struct bpf_sock_addr, user_port)), - /* } */ - - /* return 1 */ - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }; - - return load_insns(test, insns, ARRAY_SIZE(insns)); -} - -static int recvmsg4_rw_c_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, RECVMSG4_PROG_PATH); -} - -static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, SENDMSG4_PROG_PATH); -} - -static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test, - const char *rw_dst_ip) -{ - struct sockaddr_in6 dst6_rw_addr; - struct in6_addr src6_rw_ip; - - if (inet_pton(AF_INET6, SRC6_REWRITE_IP, (void *)&src6_rw_ip) != 1) { - log_err("Invalid IPv6: %s", SRC6_REWRITE_IP); - return -1; - } - - if (make_sockaddr(AF_INET6, rw_dst_ip, SERV6_REWRITE_PORT, - (struct sockaddr_storage *)&dst6_rw_addr, - NULL) == -1) - return -1; - - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - - /* if (sk.family == AF_INET6) { */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, family)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18), - -#define STORE_IPV6_WORD_N(DST, SRC, N) \ - BPF_MOV32_IMM(BPF_REG_7, SRC[N]), \ - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \ - offsetof(struct bpf_sock_addr, DST[N])) - -#define STORE_IPV6(DST, SRC) \ - STORE_IPV6_WORD_N(DST, SRC, 0), \ - STORE_IPV6_WORD_N(DST, SRC, 1), \ - STORE_IPV6_WORD_N(DST, SRC, 2), \ - STORE_IPV6_WORD_N(DST, SRC, 3) - - STORE_IPV6(msg_src_ip6, src6_rw_ip.s6_addr32), - STORE_IPV6(user_ip6, dst6_rw_addr.sin6_addr.s6_addr32), - - /* user_port = dst6_rw_addr.sin6_port */ - BPF_MOV32_IMM(BPF_REG_7, dst6_rw_addr.sin6_port), - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, - offsetof(struct bpf_sock_addr, user_port)), - - /* } */ - - /* return 1 */ - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }; - - return load_insns(test, insns, ARRAY_SIZE(insns)); -} - -static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test) -{ - return sendmsg6_rw_dst_asm_prog_load(test, SERV6_REWRITE_IP); -} - -static int recvmsg6_rw_c_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, RECVMSG6_PROG_PATH); -} - -static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test) -{ - return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP); -} - -static int sendmsg6_rw_wildcard_prog_load(const struct sock_addr_test *test) -{ - return sendmsg6_rw_dst_asm_prog_load(test, WILDCARD6_IP); -} - -static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test) -{ - return load_path(test, SENDMSG6_PROG_PATH); -} - -static int cmp_addr(const struct sockaddr_storage *addr1, - const struct sockaddr_storage *addr2, int cmp_port) -{ - const struct sockaddr_in *four1, *four2; - const struct sockaddr_in6 *six1, *six2; - - if (addr1->ss_family != addr2->ss_family) - return -1; - - if (addr1->ss_family == AF_INET) { - four1 = (const struct sockaddr_in *)addr1; - four2 = (const struct sockaddr_in *)addr2; - return !((four1->sin_port == four2->sin_port || !cmp_port) && - four1->sin_addr.s_addr == four2->sin_addr.s_addr); - } else if (addr1->ss_family == AF_INET6) { - six1 = (const struct sockaddr_in6 *)addr1; - six2 = (const struct sockaddr_in6 *)addr2; - return !((six1->sin6_port == six2->sin6_port || !cmp_port) && - !memcmp(&six1->sin6_addr, &six2->sin6_addr, - sizeof(struct in6_addr))); - } - - return -1; -} - -static int cmp_sock_addr(info_fn fn, int sock1, - const struct sockaddr_storage *addr2, int cmp_port) -{ - struct sockaddr_storage addr1; - socklen_t len1 = sizeof(addr1); - - memset(&addr1, 0, len1); - if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0) - return -1; - - return cmp_addr(&addr1, addr2, cmp_port); -} - -static int cmp_local_ip(int sock1, const struct sockaddr_storage *addr2) -{ - return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 0); -} - -static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2) -{ - return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 1); -} - -static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2) -{ - return cmp_sock_addr(getpeername, sock1, addr2, /*cmp_port*/ 1); -} - -int init_pktinfo(int domain, struct cmsghdr *cmsg) -{ - struct in6_pktinfo *pktinfo6; - struct in_pktinfo *pktinfo4; - - if (domain == AF_INET) { - cmsg->cmsg_level = SOL_IP; - cmsg->cmsg_type = IP_PKTINFO; - cmsg->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo)); - pktinfo4 = (struct in_pktinfo *)CMSG_DATA(cmsg); - memset(pktinfo4, 0, sizeof(struct in_pktinfo)); - if (inet_pton(domain, SRC4_IP, - (void *)&pktinfo4->ipi_spec_dst) != 1) - return -1; - } else if (domain == AF_INET6) { - cmsg->cmsg_level = SOL_IPV6; - cmsg->cmsg_type = IPV6_PKTINFO; - cmsg->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo)); - pktinfo6 = (struct in6_pktinfo *)CMSG_DATA(cmsg); - memset(pktinfo6, 0, sizeof(struct in6_pktinfo)); - if (inet_pton(domain, SRC6_IP, - (void *)&pktinfo6->ipi6_addr) != 1) - return -1; - } else { - return -1; - } - - return 0; -} - -static int sendmsg_to_server(int type, const struct sockaddr_storage *addr, - socklen_t addr_len, int set_cmsg, int flags, - int *syscall_err) -{ - union { - char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))]; - struct cmsghdr align; - } control6; - union { - char buf[CMSG_SPACE(sizeof(struct in_pktinfo))]; - struct cmsghdr align; - } control4; - struct msghdr hdr; - struct iovec iov; - char data = 'a'; - int domain; - int fd = -1; - - domain = addr->ss_family; - - if (domain != AF_INET && domain != AF_INET6) { - log_err("Unsupported address family"); - goto err; - } - - fd = socket(domain, type, 0); - if (fd == -1) { - log_err("Failed to create client socket"); - goto err; - } - - memset(&iov, 0, sizeof(iov)); - iov.iov_base = &data; - iov.iov_len = sizeof(data); - - memset(&hdr, 0, sizeof(hdr)); - hdr.msg_name = (void *)addr; - hdr.msg_namelen = addr_len; - hdr.msg_iov = &iov; - hdr.msg_iovlen = 1; - - if (set_cmsg) { - if (domain == AF_INET) { - hdr.msg_control = &control4; - hdr.msg_controllen = sizeof(control4.buf); - } else if (domain == AF_INET6) { - hdr.msg_control = &control6; - hdr.msg_controllen = sizeof(control6.buf); - } - if (init_pktinfo(domain, CMSG_FIRSTHDR(&hdr))) { - log_err("Fail to init pktinfo"); - goto err; - } - } - - if (sendmsg(fd, &hdr, flags) != sizeof(data)) { - log_err("Fail to send message to server"); - *syscall_err = errno; - goto err; - } - - goto out; -err: - close(fd); - fd = -1; -out: - return fd; -} - -static int fastconnect_to_server(const struct sockaddr_storage *addr, - socklen_t addr_len) -{ - int sendmsg_err; - - return sendmsg_to_server(SOCK_STREAM, addr, addr_len, /*set_cmsg*/0, - MSG_FASTOPEN, &sendmsg_err); -} - -static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr) -{ - struct timeval tv; - struct msghdr hdr; - struct iovec iov; - char data[64]; - fd_set rfds; - - FD_ZERO(&rfds); - FD_SET(sockfd, &rfds); - - tv.tv_sec = 2; - tv.tv_usec = 0; - - if (select(sockfd + 1, &rfds, NULL, NULL, &tv) <= 0 || - !FD_ISSET(sockfd, &rfds)) - return -1; - - memset(&iov, 0, sizeof(iov)); - iov.iov_base = data; - iov.iov_len = sizeof(data); - - memset(&hdr, 0, sizeof(hdr)); - hdr.msg_name = src_addr; - hdr.msg_namelen = sizeof(struct sockaddr_storage); - hdr.msg_iov = &iov; - hdr.msg_iovlen = 1; - - return recvmsg(sockfd, &hdr, 0); -} - -static int init_addrs(const struct sock_addr_test *test, - struct sockaddr_storage *requested_addr, - struct sockaddr_storage *expected_addr, - struct sockaddr_storage *expected_src_addr) -{ - if (make_sockaddr(test->domain, test->expected_ip, test->expected_port, - expected_addr, NULL) == -1) - goto err; - - if (make_sockaddr(test->domain, test->requested_ip, test->requested_port, - requested_addr, NULL) == -1) - goto err; - - if (test->expected_src_ip && - make_sockaddr(test->domain, test->expected_src_ip, 0, - expected_src_addr, NULL) == -1) - goto err; - - return 0; -err: - return -1; -} - -static int run_bind_test_case(const struct sock_addr_test *test) -{ - socklen_t addr_len = sizeof(struct sockaddr_storage); - struct sockaddr_storage requested_addr; - struct sockaddr_storage expected_addr; - int clientfd = -1; - int servfd = -1; - int err = 0; - - if (init_addrs(test, &requested_addr, &expected_addr, NULL)) - goto err; - - servfd = start_server_addr(test->type, &requested_addr, addr_len, NULL); - if (servfd == -1) - goto err; - - if (cmp_local_addr(servfd, &expected_addr)) - goto err; - - /* Try to connect to server just in case */ - clientfd = connect_to_addr(test->type, &expected_addr, addr_len, NULL); - if (clientfd == -1) - goto err; - - goto out; -err: - err = -1; -out: - close(clientfd); - close(servfd); - return err; -} - -static int run_connect_test_case(const struct sock_addr_test *test) -{ - socklen_t addr_len = sizeof(struct sockaddr_storage); - struct sockaddr_storage expected_src_addr; - struct sockaddr_storage requested_addr; - struct sockaddr_storage expected_addr; - int clientfd = -1; - int servfd = -1; - int err = 0; - - if (init_addrs(test, &requested_addr, &expected_addr, - &expected_src_addr)) - goto err; - - /* Prepare server to connect to */ - servfd = start_server_addr(test->type, &expected_addr, addr_len, NULL); - if (servfd == -1) - goto err; - - clientfd = connect_to_addr(test->type, &requested_addr, addr_len, NULL); - if (clientfd == -1) - goto err; - - /* Make sure src and dst addrs were overridden properly */ - if (cmp_peer_addr(clientfd, &expected_addr)) - goto err; - - if (cmp_local_ip(clientfd, &expected_src_addr)) - goto err; - - if (test->type == SOCK_STREAM) { - /* Test TCP Fast Open scenario */ - clientfd = fastconnect_to_server(&requested_addr, addr_len); - if (clientfd == -1) - goto err; - - /* Make sure src and dst addrs were overridden properly */ - if (cmp_peer_addr(clientfd, &expected_addr)) - goto err; - - if (cmp_local_ip(clientfd, &expected_src_addr)) - goto err; - } - - goto out; -err: - err = -1; -out: - close(clientfd); - close(servfd); - return err; -} - -static int run_xmsg_test_case(const struct sock_addr_test *test, int max_cmsg) -{ - socklen_t addr_len = sizeof(struct sockaddr_storage); - struct sockaddr_storage expected_addr; - struct sockaddr_storage server_addr; - struct sockaddr_storage sendmsg_addr; - struct sockaddr_storage recvmsg_addr; - int clientfd = -1; - int servfd = -1; - int set_cmsg; - int err = 0; - - if (test->type != SOCK_DGRAM) - goto err; - - if (init_addrs(test, &sendmsg_addr, &server_addr, &expected_addr)) - goto err; - - /* Prepare server to sendmsg to */ - servfd = start_server_addr(test->type, &server_addr, addr_len, NULL); - if (servfd == -1) - goto err; - - for (set_cmsg = 0; set_cmsg <= max_cmsg; ++set_cmsg) { - if (clientfd >= 0) - close(clientfd); - - clientfd = sendmsg_to_server(test->type, &sendmsg_addr, - addr_len, set_cmsg, /*flags*/0, - &err); - if (err) - goto out; - else if (clientfd == -1) - goto err; - - /* Try to receive message on server instead of using - * getpeername(2) on client socket, to check that client's - * destination address was rewritten properly, since - * getpeername(2) doesn't work with unconnected datagram - * sockets. - * - * Get source address from recvmsg(2) as well to make sure - * source was rewritten properly: getsockname(2) can't be used - * since socket is unconnected and source defined for one - * specific packet may differ from the one used by default and - * returned by getsockname(2). - */ - if (recvmsg_from_client(servfd, &recvmsg_addr) == -1) - goto err; - - if (cmp_addr(&recvmsg_addr, &expected_addr, /*cmp_port*/0)) - goto err; - } - - goto out; -err: - err = -1; -out: - close(clientfd); - close(servfd); - return err; -} - -static int run_test_case(int cgfd, const struct sock_addr_test *test) -{ - int progfd = -1; - int err = 0; - - printf("Test case: %s .. ", test->descr); - - progfd = test->loadfn(test); - if (test->expected_result == LOAD_REJECT && progfd < 0) - goto out; - else if (test->expected_result == LOAD_REJECT || progfd < 0) - goto err; - - err = bpf_prog_attach(progfd, cgfd, test->attach_type, - BPF_F_ALLOW_OVERRIDE); - if (test->expected_result == ATTACH_REJECT && err) { - err = 0; /* error was expected, reset it */ - goto out; - } else if (test->expected_result == ATTACH_REJECT || err) { - goto err; - } else if (test->expected_result == ATTACH_OKAY) { - err = 0; - goto out; - } - - switch (test->attach_type) { - case BPF_CGROUP_INET4_BIND: - case BPF_CGROUP_INET6_BIND: - err = run_bind_test_case(test); - break; - case BPF_CGROUP_INET4_CONNECT: - case BPF_CGROUP_INET6_CONNECT: - err = run_connect_test_case(test); - break; - case BPF_CGROUP_UDP4_SENDMSG: - case BPF_CGROUP_UDP6_SENDMSG: - err = run_xmsg_test_case(test, 1); - break; - case BPF_CGROUP_UDP4_RECVMSG: - case BPF_CGROUP_UDP6_RECVMSG: - err = run_xmsg_test_case(test, 0); - break; - default: - goto err; - } - - if (test->expected_result == SYSCALL_EPERM && err == EPERM) { - err = 0; /* error was expected, reset it */ - goto out; - } - - if (test->expected_result == SYSCALL_ENOTSUPP && err == ENOTSUPP) { - err = 0; /* error was expected, reset it */ - goto out; - } - - if (err || test->expected_result != SUCCESS) - goto err; - - goto out; -err: - err = -1; -out: - /* Detaching w/o checking return code: best effort attempt. */ - if (progfd != -1) - bpf_prog_detach(cgfd, test->attach_type); - close(progfd); - printf("[%s]\n", err ? "FAIL" : "PASS"); - return err; -} - -static int run_tests(int cgfd) -{ - int passes = 0; - int fails = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(tests); ++i) { - if (run_test_case(cgfd, &tests[i])) - ++fails; - else - ++passes; - } - printf("Summary: %d PASSED, %d FAILED\n", passes, fails); - return fails ? -1 : 0; -} - -int main(int argc, char **argv) -{ - int cgfd = -1; - int err = 0; - - if (argc < 2) { - fprintf(stderr, - "%s has to be run via %s.sh. Skip direct run.\n", - argv[0], argv[0]); - exit(err); - } - - cgfd = cgroup_setup_and_join(CG_PATH); - if (cgfd < 0) - goto err; - - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - - if (run_tests(cgfd)) - goto err; - - goto out; -err: - err = -1; -out: - close(cgfd); - cleanup_cgroup_environment(); - return err; -} diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh deleted file mode 100755 index 3b9fdb8094aa..000000000000 --- a/tools/testing/selftests/bpf/test_sock_addr.sh +++ /dev/null @@ -1,58 +0,0 @@ -#!/bin/sh - -set -eu - -ping_once() -{ - type ping${1} >/dev/null 2>&1 && PING="ping${1}" || PING="ping -${1}" - $PING -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1 -} - -wait_for_ip() -{ - local _i - echo -n "Wait for testing IPv4/IPv6 to become available " - for _i in $(seq ${MAX_PING_TRIES}); do - echo -n "." - if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then - echo " OK" - return - fi - done - echo 1>&2 "ERROR: Timeout waiting for test IP to become available." - exit 1 -} - -setup() -{ - # Create testing interfaces not to interfere with current environment. - ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER} - ip link set ${TEST_IF} up - ip link set ${TEST_IF_PEER} up - - ip -4 addr add ${TEST_IPv4} dev ${TEST_IF} - ip -6 addr add ${TEST_IPv6} dev ${TEST_IF} - wait_for_ip -} - -cleanup() -{ - ip link del ${TEST_IF} 2>/dev/null || : - ip link del ${TEST_IF_PEER} 2>/dev/null || : -} - -main() -{ - trap cleanup EXIT 2 3 6 15 - setup - ./test_sock_addr setup_done -} - -BASENAME=$(basename $0 .sh) -TEST_IF="${BASENAME}1" -TEST_IF_PEER="${BASENAME}2" -TEST_IPv4="127.0.0.4/8" -TEST_IPv6="::6/128" -MAX_PING_TRIES=5 - -main diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 43612de44fbf..92752f5eeded 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1887,10 +1887,13 @@ static int check_whitelist(struct _test *t, struct sockmap_options *opt) while (entry) { if ((opt->prepend && strstr(opt->prepend, entry) != 0) || strstr(opt->map, entry) != 0 || - strstr(t->title, entry) != 0) + strstr(t->title, entry) != 0) { + free(ptr); return 0; + } entry = strtok(NULL, ","); } + free(ptr); return -EINVAL; } @@ -1907,10 +1910,13 @@ static int check_blacklist(struct _test *t, struct sockmap_options *opt) while (entry) { if ((opt->prepend && strstr(opt->prepend, entry) != 0) || strstr(opt->map, entry) != 0 || - strstr(t->title, entry) != 0) + strstr(t->title, entry) != 0) { + free(ptr); return 0; + } entry = strtok(NULL, ","); } + free(ptr); return -EINVAL; } diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index 32df93747095..7b5fc98838cd 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -16,68 +16,7 @@ #include #include "cgroup_helpers.h" - -static int start_server(const struct sockaddr *addr, socklen_t len, bool dual) -{ - int mode = !dual; - int fd; - - fd = socket(addr->sa_family, SOCK_STREAM, 0); - if (fd == -1) { - log_err("Failed to create server socket"); - goto out; - } - - if (addr->sa_family == AF_INET6) { - if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode, - sizeof(mode)) == -1) { - log_err("Failed to set the dual-stack mode"); - goto close_out; - } - } - - if (bind(fd, addr, len) == -1) { - log_err("Failed to bind server socket"); - goto close_out; - } - - if (listen(fd, 128) == -1) { - log_err("Failed to listen on server socket"); - goto close_out; - } - - goto out; - -close_out: - close(fd); - fd = -1; -out: - return fd; -} - -static int connect_to_server(const struct sockaddr *addr, socklen_t len) -{ - int fd = -1; - - fd = socket(addr->sa_family, SOCK_STREAM, 0); - if (fd == -1) { - log_err("Failed to create client socket"); - goto out; - } - - if (connect(fd, (const struct sockaddr *)addr, len) == -1) { - log_err("Fail to connect to server"); - goto close_out; - } - - goto out; - -close_out: - close(fd); - fd = -1; -out: - return fd; -} +#include "network_helpers.h" static int get_map_fd_by_prog_id(int prog_id, bool *xdp) { @@ -117,8 +56,7 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd, bool xdp, - const struct sockaddr *addr, socklen_t len) +static int run_test(int server_fd, int results_fd, bool xdp) { int client = -1, srv_client = -1; int ret = 0; @@ -144,7 +82,7 @@ static int run_test(int server_fd, int results_fd, bool xdp, goto err; } - client = connect_to_server(addr, len); + client = connect_to_fd(server_fd, 0); if (client == -1) goto err; @@ -201,23 +139,23 @@ out: return ret; } -static bool get_port(int server_fd, in_port_t *port) +static int v6only_true(int fd, const struct post_socket_opts *opts) { - struct sockaddr_in addr; - socklen_t len = sizeof(addr); + int mode = true; - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - return false; - } + return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode)); +} - /* sin_port and sin6_port are located at the same offset. */ - *port = addr.sin_port; - return true; +static int v6only_false(int fd, const struct post_socket_opts *opts) +{ + int mode = false; + + return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode)); } int main(int argc, char **argv) { + struct network_helper_opts opts = { 0 }; struct sockaddr_in addr4; struct sockaddr_in6 addr6; struct sockaddr_in addr4dual; @@ -259,31 +197,30 @@ int main(int argc, char **argv) addr6dual.sin6_addr = in6addr_any; addr6dual.sin6_port = 0; - server = start_server((const struct sockaddr *)&addr4, sizeof(addr4), - false); - if (server == -1 || !get_port(server, &addr4.sin_port)) + server = start_server_addr(SOCK_STREAM, (struct sockaddr_storage *)&addr4, + sizeof(addr4), NULL); + if (server == -1) goto err; - server_v6 = start_server((const struct sockaddr *)&addr6, - sizeof(addr6), false); - if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port)) + opts.post_socket_cb = v6only_true; + server_v6 = start_server_addr(SOCK_STREAM, (struct sockaddr_storage *)&addr6, + sizeof(addr6), &opts); + if (server_v6 == -1) goto err; - server_dual = start_server((const struct sockaddr *)&addr6dual, - sizeof(addr6dual), true); - if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port)) + opts.post_socket_cb = v6only_false; + server_dual = start_server_addr(SOCK_STREAM, (struct sockaddr_storage *)&addr6dual, + sizeof(addr6dual), &opts); + if (server_dual == -1) goto err; - if (run_test(server, results, xdp, - (const struct sockaddr *)&addr4, sizeof(addr4))) + if (run_test(server, results, xdp)) goto err; - if (run_test(server_v6, results, xdp, - (const struct sockaddr *)&addr6, sizeof(addr6))) + if (run_test(server_v6, results, xdp)) goto err; - if (run_test(server_dual, results, xdp, - (const struct sockaddr *)&addr4dual, sizeof(addr4dual))) + if (run_test(server_dual, results, xdp)) goto err; printf("ok\n"); diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 244d4996e06e..b2854238d4a0 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -792,10 +792,13 @@ static int parse_stats(const char *stats_str, struct stat_specs *specs) while ((next = strtok_r(state ? NULL : input, ",", &state))) { err = parse_stat(next, specs); - if (err) + if (err) { + free(input); return err; + } } + free(input); return 0; } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 0859fe727da7..6f9956eed797 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -581,6 +581,8 @@ static void cleanup(void) if (bpf_obj) xdp_hw_metadata__destroy(bpf_obj); + + free((void *)saved_hwtstamp_ifname); } static void handle_signal(int sig)