diff options
107 files changed, 5771 insertions, 1700 deletions
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 287b98708a40..e043c9213388 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -67,7 +67,8 @@ two flavors of JITs, the newer eBPF JIT currently supported on: - sparc64 - mips64 - s390x - - riscv + - riscv64 + - riscv32 And the older cBPF JIT supported on the following archs: diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index c4a328f2d57a..2f0f8b17dade 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -606,7 +606,7 @@ 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, riscv (RV64G) perform JIT compilation from eBPF +sparc64, arm32, riscv64, riscv32 perform JIT compilation from eBPF instruction set. Some core changes of the new internal format: diff --git a/MAINTAINERS b/MAINTAINERS index 439151d589a4..5dbee41045bc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3213,11 +3213,22 @@ L: bpf@vger.kernel.org S: Maintained F: arch/powerpc/net/ -BPF JIT for RISC-V (RV64G) +BPF JIT for RISC-V (32-bit) +M: Luke Nelson <luke.r.nels@gmail.com> +M: Xi Wang <xi.wang@gmail.com> +L: netdev@vger.kernel.org +L: bpf@vger.kernel.org +S: Maintained +F: arch/riscv/net/ +X: arch/riscv/net/bpf_jit_comp64.c + +BPF JIT for RISC-V (64-bit) M: Björn Töpel <bjorn.topel@gmail.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/riscv/net/ +X: arch/riscv/net/bpf_jit_comp32.c BPF JIT for S390 M: Ilya Leoshkevich <iii@linux.ibm.com> @@ -9350,6 +9361,8 @@ F: include/net/l3mdev.h L7 BPF FRAMEWORK M: John Fastabend <john.fastabend@gmail.com> M: Daniel Borkmann <daniel@iogearbox.net> +M: Jakub Sitnicki <jakub@cloudflare.com> +M: Lorenz Bauer <lmb@cloudflare.com> L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Maintained @@ -9357,6 +9370,7 @@ F: include/linux/skmsg.h F: net/core/skmsg.c F: net/core/sock_map.c F: net/ipv4/tcp_bpf.c +F: net/ipv4/udp_bpf.c LANTIQ / INTEL Ethernet drivers M: Hauke Mehrtens <hauke@hauke-m.de> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 1a3b5a5276be..2366698df179 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -56,7 +56,7 @@ config RISCV select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MMIOWB select ARCH_HAS_DEBUG_VIRTUAL - select HAVE_EBPF_JIT if 64BIT + select HAVE_EBPF_JIT select EDAC_SUPPORT select ARCH_HAS_GIGANTIC_PAGE select ARCH_WANT_HUGE_PMD_SHARE if 64BIT diff --git a/arch/riscv/net/Makefile b/arch/riscv/net/Makefile index ec5b14763316..9a1e5f0a94e5 100644 --- a/arch/riscv/net/Makefile +++ b/arch/riscv/net/Makefile @@ -1,2 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o + +obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o + +ifeq ($(CONFIG_ARCH_RV64I),y) + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o +else + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o +endif diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h new file mode 100644 index 000000000000..20e235d06f66 --- /dev/null +++ b/arch/riscv/net/bpf_jit.h @@ -0,0 +1,514 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common functionality for RV32 and RV64 BPF JIT compilers + * + * Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com> + * + */ + +#ifndef _BPF_JIT_H +#define _BPF_JIT_H + +#include <linux/bpf.h> +#include <linux/filter.h> +#include <asm/cacheflush.h> + +enum { + RV_REG_ZERO = 0, /* The constant value 0 */ + RV_REG_RA = 1, /* Return address */ + RV_REG_SP = 2, /* Stack pointer */ + RV_REG_GP = 3, /* Global pointer */ + RV_REG_TP = 4, /* Thread pointer */ + RV_REG_T0 = 5, /* Temporaries */ + RV_REG_T1 = 6, + RV_REG_T2 = 7, + RV_REG_FP = 8, /* Saved register/frame pointer */ + RV_REG_S1 = 9, /* Saved register */ + RV_REG_A0 = 10, /* Function argument/return values */ + RV_REG_A1 = 11, /* Function arguments */ + RV_REG_A2 = 12, + RV_REG_A3 = 13, + RV_REG_A4 = 14, + RV_REG_A5 = 15, + RV_REG_A6 = 16, + RV_REG_A7 = 17, + RV_REG_S2 = 18, /* Saved registers */ + RV_REG_S3 = 19, + RV_REG_S4 = 20, + RV_REG_S5 = 21, + RV_REG_S6 = 22, + RV_REG_S7 = 23, + RV_REG_S8 = 24, + RV_REG_S9 = 25, + RV_REG_S10 = 26, + RV_REG_S11 = 27, + RV_REG_T3 = 28, /* Temporaries */ + RV_REG_T4 = 29, + RV_REG_T5 = 30, + RV_REG_T6 = 31, +}; + +struct rv_jit_context { + struct bpf_prog *prog; + u32 *insns; /* RV insns */ + int ninsns; + int epilogue_offset; + int *offset; /* BPF to RV */ + unsigned long flags; + int stack_size; +}; + +struct rv_jit_data { + struct bpf_binary_header *header; + u8 *image; + struct rv_jit_context ctx; +}; + +static inline void bpf_fill_ill_insns(void *area, unsigned int size) +{ + memset(area, 0, size); +} + +static inline void bpf_flush_icache(void *start, void *end) +{ + flush_icache_range((unsigned long)start, (unsigned long)end); +} + +static inline void emit(const u32 insn, struct rv_jit_context *ctx) +{ + if (ctx->insns) + ctx->insns[ctx->ninsns] = insn; + + ctx->ninsns++; +} + +static inline int epilogue_offset(struct rv_jit_context *ctx) +{ + int to = ctx->epilogue_offset, from = ctx->ninsns; + + return (to - from) << 2; +} + +/* Return -1 or inverted cond. */ +static inline int invert_bpf_cond(u8 cond) +{ + switch (cond) { + case BPF_JEQ: + return BPF_JNE; + case BPF_JGT: + return BPF_JLE; + case BPF_JLT: + return BPF_JGE; + case BPF_JGE: + return BPF_JLT; + case BPF_JLE: + return BPF_JGT; + case BPF_JNE: + return BPF_JEQ; + case BPF_JSGT: + return BPF_JSLE; + case BPF_JSLT: + return BPF_JSGE; + case BPF_JSGE: + return BPF_JSLT; + case BPF_JSLE: + return BPF_JSGT; + } + return -1; +} + +static inline bool is_12b_int(long val) +{ + return -(1L << 11) <= val && val < (1L << 11); +} + +static inline int is_12b_check(int off, int insn) +{ + if (!is_12b_int(off)) { + pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n", + insn, (int)off); + return -1; + } + return 0; +} + +static inline bool is_13b_int(long val) +{ + return -(1L << 12) <= val && val < (1L << 12); +} + +static inline bool is_21b_int(long val) +{ + return -(1L << 20) <= val && val < (1L << 20); +} + +static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) +{ + int from, to; + + off++; /* BPF branch is from PC+1, RV is from PC */ + from = (insn > 0) ? ctx->offset[insn - 1] : 0; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; + return (to - from) << 2; +} + +/* Instruction formats. */ + +static inline u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, + u8 opcode) +{ + return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (rd << 7) | opcode; +} + +static inline u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode) +{ + return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | + opcode; +} + +static inline u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f; + + return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_0 << 7) | opcode; +} + +static inline u32 rv_b_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4); + u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10); + + return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_1 << 7) | opcode; +} + +static inline u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode) +{ + return (imm31_12 << 12) | (rd << 7) | opcode; +} + +static inline u32 rv_j_insn(u32 imm20_1, u8 rd, u8 opcode) +{ + u32 imm; + + imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) | + ((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11); + + return (imm << 12) | (rd << 7) | opcode; +} + +static inline u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1, + u8 funct3, u8 rd, u8 opcode) +{ + u8 funct7 = (funct5 << 2) | (aq << 1) | rl; + + return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode); +} + +/* Instructions shared by both RV32 and RV64. */ + +static inline u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x13); +} + +static inline u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 7, rd, 0x13); +} + +static inline u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x13); +} + +static inline u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x13); +} + +static inline u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x13); +} + +static inline u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x13); +} + +static inline u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13); +} + +static inline u32 rv_lui(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x37); +} + +static inline u32 rv_auipc(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x17); +} + +static inline u32 rv_add(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_sub(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_sltu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 3, rd, 0x33); +} + +static inline u32 rv_and(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 7, rd, 0x33); +} + +static inline u32 rv_or(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 6, rd, 0x33); +} + +static inline u32 rv_xor(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 4, rd, 0x33); +} + +static inline u32 rv_sll(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x33); +} + +static inline u32 rv_srl(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_sra(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_mul(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_mulhu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 3, rd, 0x33); +} + +static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); +} + +static inline u32 rv_jal(u8 rd, u32 imm20_1) +{ + return rv_j_insn(imm20_1, rd, 0x6f); +} + +static inline u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x67); +} + +static inline u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 0, 0x63); +} + +static inline u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 1, 0x63); +} + +static inline u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 6, 0x63); +} + +static inline u32 rv_bgtu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bltu(rs2, rs1, imm12_1); +} + +static inline u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 7, 0x63); +} + +static inline u32 rv_bleu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bgeu(rs2, rs1, imm12_1); +} + +static inline u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 4, 0x63); +} + +static inline u32 rv_bgt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_blt(rs2, rs1, imm12_1); +} + +static inline u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 5, 0x63); +} + +static inline u32 rv_ble(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bge(rs2, rs1, imm12_1); +} + +static inline u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 2, rd, 0x03); +} + +static inline u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x03); +} + +static inline u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x03); +} + +static inline u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23); +} + +static inline u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23); +} + +static inline u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23); +} + +static inline u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +/* + * RV64-only instructions. + * + * These instructions are not available on RV32. Wrap them below a #if to + * ensure that the RV32 JIT doesn't emit any of these instructions. + */ + +#if __riscv_xlen == 64 + +static inline u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b); +} + +static inline u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b); +} + +static inline u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b); +} + +static inline u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b); +} + +static inline u32 rv_addw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_subw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_sllw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b); +} + +static inline u32 rv_srlw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_sraw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); +} + +static inline u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 3, rd, 0x03); +} + +static inline u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x03); +} + +static inline u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23); +} + +static inline u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +#endif /* __riscv_xlen == 64 */ + +void bpf_jit_build_prologue(struct rv_jit_context *ctx); +void bpf_jit_build_epilogue(struct rv_jit_context *ctx); + +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass); + +#endif /* _BPF_JIT_H */ diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c new file mode 100644 index 000000000000..302934177760 --- /dev/null +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -0,0 +1,1310 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * BPF JIT compiler for RV32G + * + * Copyright (c) 2020 Luke Nelson <luke.r.nels@gmail.com> + * Copyright (c) 2020 Xi Wang <xi.wang@gmail.com> + * + * The code is based on the BPF JIT compiler for RV64G by Björn Töpel and + * the BPF JIT compiler for 32-bit ARM by Shubham Bansal and Mircea Gherzan. + */ + +#include <linux/bpf.h> +#include <linux/filter.h> +#include "bpf_jit.h" + +enum { + /* Stack layout - these are offsets from (top of stack - 4). */ + BPF_R6_HI, + BPF_R6_LO, + BPF_R7_HI, + BPF_R7_LO, + BPF_R8_HI, + BPF_R8_LO, + BPF_R9_HI, + BPF_R9_LO, + BPF_AX_HI, + BPF_AX_LO, + /* Stack space for BPF_REG_6 through BPF_REG_9 and BPF_REG_AX. */ + BPF_JIT_SCRATCH_REGS, +}; + +#define STACK_OFFSET(k) (-4 - ((k) * 4)) + +#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) +#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) + +#define RV_REG_TCC RV_REG_T6 +#define RV_REG_TCC_SAVED RV_REG_S7 + +static const s8 bpf2rv32[][2] = { + /* Return value from in-kernel function, and exit value from eBPF. */ + [BPF_REG_0] = {RV_REG_S2, RV_REG_S1}, + /* Arguments from eBPF program to in-kernel function. */ + [BPF_REG_1] = {RV_REG_A1, RV_REG_A0}, + [BPF_REG_2] = {RV_REG_A3, RV_REG_A2}, + [BPF_REG_3] = {RV_REG_A5, RV_REG_A4}, + [BPF_REG_4] = {RV_REG_A7, RV_REG_A6}, + [BPF_REG_5] = {RV_REG_S4, RV_REG_S3}, + /* + * Callee-saved registers that in-kernel function will preserve. + * Stored on the stack. + */ + [BPF_REG_6] = {STACK_OFFSET(BPF_R6_HI), STACK_OFFSET(BPF_R6_LO)}, + [BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)}, + [BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)}, + [BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)}, + /* Read-only frame pointer to access BPF stack. */ + [BPF_REG_FP] = {RV_REG_S6, RV_REG_S5}, + /* Temporary register for blinding constants. Stored on the stack. */ + [BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)}, + /* + * Temporary registers used by the JIT to operate on registers stored + * on the stack. Save t0 and t1 to be used as temporaries in generated + * code. + */ + [TMP_REG_1] = {RV_REG_T3, RV_REG_T2}, + [TMP_REG_2] = {RV_REG_T5, RV_REG_T4}, +}; + +static s8 hi(const s8 *r) +{ + return r[0]; +} + +static s8 lo(const s8 *r) +{ + return r[1]; +} + +static void emit_imm(const s8 rd, s32 imm, struct rv_jit_context *ctx) +{ + u32 upper = (imm + (1 << 11)) >> 12; + u32 lower = imm & 0xfff; + + if (upper) { + emit(rv_lui(rd, upper), ctx); + emit(rv_addi(rd, rd, lower), ctx); + } else { + emit(rv_addi(rd, RV_REG_ZERO, lower), ctx); + } +} + +static void emit_imm32(const s8 *rd, s32 imm, struct rv_jit_context *ctx) +{ + /* Emit immediate into lower bits. */ + emit_imm(lo(rd), imm, ctx); + + /* Sign-extend into upper bits. */ + if (imm >= 0) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + else + emit(rv_addi(hi(rd), RV_REG_ZERO, -1), ctx); +} + +static void emit_imm64(const s8 *rd, s32 imm_hi, s32 imm_lo, + struct rv_jit_context *ctx) +{ + emit_imm(lo(rd), imm_lo, ctx); + emit_imm(hi(rd), imm_hi, ctx); +} + +static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) +{ + int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 4; + const s8 *r0 = bpf2rv32[BPF_REG_0]; + + store_offset -= 4 * BPF_JIT_SCRATCH_REGS; + + /* Set return value if not tail call. */ + if (!is_tail_call) { + emit(rv_addi(RV_REG_A0, lo(r0), 0), ctx); + emit(rv_addi(RV_REG_A1, hi(r0), 0), ctx); + } + + /* Restore callee-saved registers. */ + emit(rv_lw(RV_REG_RA, store_offset - 0, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_FP, store_offset - 4, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S1, store_offset - 8, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S2, store_offset - 12, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S3, store_offset - 16, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S4, store_offset - 20, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S5, store_offset - 24, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S6, store_offset - 28, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S7, store_offset - 32, RV_REG_SP), ctx); + + emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx); + + if (is_tail_call) { + /* + * goto *(t0 + 4); + * Skips first instruction of prologue which initializes tail + * call counter. Assumes t0 contains address of target program, + * see emit_bpf_tail_call. + */ + emit(rv_jalr(RV_REG_ZERO, RV_REG_T0, 4), ctx); + } else { + emit(rv_jalr(RV_REG_ZERO, RV_REG_RA, 0), ctx); + } +} + +static bool is_stacked(s8 reg) +{ + return reg < 0; +} + +static const s8 *bpf_get_reg64(const s8 *reg, const s8 *tmp, + struct rv_jit_context *ctx) +{ + if (is_stacked(hi(reg))) { + emit(rv_lw(hi(tmp), hi(reg), RV_REG_FP), ctx); + emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx); + reg = tmp; + } + return reg; +} + +static void bpf_put_reg64(const s8 *reg, const s8 *src, + struct rv_jit_context *ctx) +{ + if (is_stacked(hi(reg))) { + emit(rv_sw(RV_REG_FP, hi(reg), hi(src)), ctx); + emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx); + } +} + +static const s8 *bpf_get_reg32(const s8 *reg, const s8 *tmp, + struct rv_jit_context *ctx) +{ + if (is_stacked(lo(reg))) { + emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx); + reg = tmp; + } + return reg; +} + +static void bpf_put_reg32(const s8 *reg, const s8 *src, + struct rv_jit_context *ctx) +{ + if (is_stacked(lo(reg))) { + emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_sw(RV_REG_FP, hi(reg), RV_REG_ZERO), ctx); + } else if (!ctx->prog->aux->verifier_zext) { + emit(rv_addi(hi(reg), RV_REG_ZERO, 0), ctx); + } +} + +static void emit_jump_and_link(u8 rd, s32 rvoff, bool force_jalr, + struct rv_jit_context *ctx) +{ + s32 upper, lower; + + if (rvoff && is_21b_int(rvoff) && !force_jalr) { + emit(rv_jal(rd, rvoff >> 1), ctx); + return; + } + + upper = (rvoff + (1 << 11)) >> 12; + lower = rvoff & 0xfff; + emit(rv_auipc(RV_REG_T1, upper), ctx); + emit(rv_jalr(rd, RV_REG_T1, lower), ctx); +} + +static void emit_alu_i64(const s8 *dst, s32 imm, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (op) { + case BPF_MOV: + emit_imm32(rd, imm, ctx); + break; + case BPF_AND: + if (is_12b_int(imm)) { + emit(rv_andi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm >= 0) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_OR: + if (is_12b_int(imm)) { + emit(rv_ori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm < 0) + emit(rv_ori(hi(rd), RV_REG_ZERO, -1), ctx); + break; + case BPF_XOR: + if (is_12b_int(imm)) { + emit(rv_xori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm < 0) + emit(rv_xori(hi(rd), hi(rd), -1), ctx); + break; + case BPF_LSH: + if (imm >= 32) { + emit(rv_slli(hi(rd), lo(rd), imm - 32), ctx); + emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_srli(RV_REG_T0, lo(rd), 32 - imm), ctx); + emit(rv_slli(hi(rd), hi(rd), imm), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_slli(lo(rd), lo(rd), imm), ctx); + } + break; + case BPF_RSH: + if (imm >= 32) { + emit(rv_srli(lo(rd), hi(rd), imm - 32), ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx); + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srli(hi(rd), hi(rd), imm), ctx); + } + break; + case BPF_ARSH: + if (imm >= 32) { + emit(rv_srai(lo(rd), hi(rd), imm - 32), ctx); + emit(rv_srai(hi(rd), hi(rd), 31), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx); + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srai(hi(rd), hi(rd), imm), ctx); + } + break; + } + + bpf_put_reg64(dst, rd, ctx); +} + +static void emit_alu_i32(const s8 *dst, s32 imm, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *rd = bpf_get_reg32(dst, tmp1, ctx); + + switch (op) { + case BPF_MOV: + emit_imm(lo(rd), imm, ctx); + break; + case BPF_ADD: + if (is_12b_int(imm)) { + emit(rv_addi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_add(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_SUB: + if (is_12b_int(-imm)) { + emit(rv_addi(lo(rd), lo(rd), -imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sub(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_AND: + if (is_12b_int(imm)) { + emit(rv_andi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_OR: + if (is_12b_int(imm)) { + emit(rv_ori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_XOR: + if (is_12b_int(imm)) { + emit(rv_xori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_LSH: + if (is_12b_int(imm)) { + emit(rv_slli(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sll(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_RSH: + if (is_12b_int(imm)) { + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_srl(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_ARSH: + if (is_12b_int(imm)) { + emit(rv_srai(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sra(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + } + + bpf_put_reg32(dst, rd, ctx); +} + +static void emit_alu_r64(const s8 *dst, const s8 *src, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + switch (op) { + case BPF_MOV: + emit(rv_addi(lo(rd), lo(rs), 0), ctx); + emit(rv_addi(hi(rd), hi(rs), 0), ctx); + break; + case BPF_ADD: + if (rd == rs) { + emit(rv_srli(RV_REG_T0, lo(rd), 31), ctx); + emit(rv_slli(hi(rd), hi(rd), 1), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_slli(lo(rd), lo(rd), 1), ctx); + } else { + emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), hi(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx); + } + break; + case BPF_SUB: + emit(rv_sub(RV_REG_T1, hi(rd), hi(rs)), ctx); + emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx); + emit(rv_sub(hi(rd), RV_REG_T1, RV_REG_T0), ctx); + emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_AND: + emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_and(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_OR: + emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_XOR: + emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_xor(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_MUL: + emit(rv_mul(RV_REG_T0, hi(rs), lo(rd)), ctx); + emit(rv_mul(hi(rd), hi(rd), lo(rs)), ctx); + emit(rv_mulhu(RV_REG_T1, lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T1), ctx); + break; + case BPF_LSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_sll(hi(rd), lo(rd), RV_REG_T0), ctx); + emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_srli(RV_REG_T0, lo(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_srl(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_sll(hi(rd), hi(rd), lo(rs)), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_RSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_srl(lo(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srl(hi(rd), hi(rd), lo(rs)), ctx); + break; + case BPF_ARSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_sra(lo(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_srai(hi(rd), hi(rd), 31), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_sra(hi(rd), hi(rd), lo(rs)), ctx); + break; + case BPF_NEG: + emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx); + emit(rv_sltu(RV_REG_T0, RV_REG_ZERO, lo(rd)), ctx); + emit(rv_sub(hi(rd), RV_REG_ZERO, hi(rd)), ctx); + emit(rv_sub(hi(rd), hi(rd), RV_REG_T0), ctx); + break; + } + + bpf_put_reg64(dst, rd, ctx); +} + +static void emit_alu_r32(const s8 *dst, const s8 *src, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg32(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg32(src, tmp2, ctx); + + switch (op) { + case BPF_MOV: + emit(rv_addi(lo(rd), lo(rs), 0), ctx); + break; + case BPF_ADD: + emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_SUB: + emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_AND: + emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_OR: + emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_XOR: + emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_MUL: + emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_DIV: + emit(rv_divu(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_MOD: + emit(rv_remu(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_LSH: + emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_RSH: + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_ARSH: + emit(rv_sra(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_NEG: + emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx); + break; + } + + bpf_put_reg32(dst, rd, ctx); +} + +static int emit_branch_r64(const s8 *src1, const s8 *src2, s32 rvoff, + struct rv_jit_context *ctx, const u8 op) +{ + int e, s = ctx->ninsns; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + const s8 *rs1 = bpf_get_reg64(src1, tmp1, ctx); + const s8 *rs2 = bpf_get_reg64(src2, tmp2, ctx); + + /* + * NO_JUMP skips over the rest of the instructions and the + * emit_jump_and_link, meaning the BPF branch is not taken. + * JUMP skips directly to the emit_jump_and_link, meaning + * the BPF branch is taken. + * + * The fallthrough case results in the BPF branch being taken. + */ +#define NO_JUMP(idx) (6 + (2 * (idx))) +#define JUMP(idx) (2 + (2 * (idx))) + + switch (op) { + case BPF_JEQ: + emit(rv_bne(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bne(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JGT: + emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JLT: + emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JGE: + emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JLE: + emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JNE: + emit(rv_bne(hi(rs1), hi(rs2), JUMP(1)), ctx); + emit(rv_beq(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSGT: + emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSLT: + emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSGE: + emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSLE: + emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSET: + emit(rv_and(RV_REG_T0, hi(rs1), hi(rs2)), ctx); + emit(rv_bne(RV_REG_T0, RV_REG_ZERO, JUMP(2)), ctx); + emit(rv_and(RV_REG_T0, lo(rs1), lo(rs2)), ctx); + emit(rv_beq(RV_REG_T0, RV_REG_ZERO, NO_JUMP(0)), ctx); + break; + } + +#undef NO_JUMP +#undef JUMP + + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= (e - s) << 2; + emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + return 0; +} + +static int emit_bcc(u8 op, u8 rd, u8 rs, int rvoff, struct rv_jit_context *ctx) +{ + int e, s = ctx->ninsns; + bool far = false; + int off; + + if (op == BPF_JSET) { + /* + * BPF_JSET is a special case: it has no inverse so we always + * treat it as a far branch. + */ + far = true; + } else if (!is_13b_int(rvoff)) { + op = invert_bpf_cond(op); + far = true; + } + + /* + * For a far branch, the condition is negated and we jump over the + * branch itself, and the two instructions from emit_jump_and_link. + * For a near branch, just use rvoff. + */ + off = far ? 6 : (rvoff >> 1); + + switch (op) { + case BPF_JEQ: + emit(rv_beq(rd, rs, off), ctx); + break; + case BPF_JGT: + emit(rv_bgtu(rd, rs, off), ctx); + break; + case BPF_JLT: + emit(rv_bltu(rd, rs, off), ctx); + break; + case BPF_JGE: + emit(rv_bgeu(rd, rs, off), ctx); + break; + case BPF_JLE: + emit(rv_bleu(rd, rs, off), ctx); + break; + case BPF_JNE: + emit(rv_bne(rd, rs, off), ctx); + break; + case BPF_JSGT: + emit(rv_bgt(rd, rs, off), ctx); + break; + case BPF_JSLT: + emit(rv_blt(rd, rs, off), ctx); + break; + case BPF_JSGE: + emit(rv_bge(rd, rs, off), ctx); + break; + case BPF_JSLE: + emit(rv_ble(rd, rs, off), ctx); + break; + case BPF_JSET: + emit(rv_and(RV_REG_T0, rd, rs), ctx); + emit(rv_beq(RV_REG_T0, RV_REG_ZERO, off), ctx); + break; + } + + if (far) { + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= (e - s) << 2; + emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + } + return 0; +} + +static int emit_branch_r32(const s8 *src1, const s8 *src2, s32 rvoff, + struct rv_jit_context *ctx, const u8 op) +{ + int e, s = ctx->ninsns; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + const s8 *rs1 = bpf_get_reg32(src1, tmp1, ctx); + const s8 *rs2 = bpf_get_reg32(src2, tmp2, ctx); + + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= (e - s) << 2; + + if (emit_bcc(op, lo(rs1), lo(rs2), rvoff, ctx)) + return -1; + + return 0; +} + +static void emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) +{ + const s8 *r0 = bpf2rv32[BPF_REG_0]; + const s8 *r5 = bpf2rv32[BPF_REG_5]; + u32 upper = ((u32)addr + (1 << 11)) >> 12; + u32 lower = addr & 0xfff; + + /* R1-R4 already in correct registers---need to push R5 to stack. */ + emit(rv_addi(RV_REG_SP, RV_REG_SP, -16), ctx); + emit(rv_sw(RV_REG_SP, 0, lo(r5)), ctx); + emit(rv_sw(RV_REG_SP, 4, hi(r5)), ctx); + + /* Backup TCC. */ + emit(rv_addi(RV_REG_TCC_SAVED, RV_REG_TCC, 0), ctx); + + /* + * Use lui/jalr pair to jump to absolute address. Don't use emit_imm as + * the number of emitted instructions should not depend on the value of + * addr. + */ + emit(rv_lui(RV_REG_T1, upper), ctx); + emit(rv_jalr(RV_REG_RA, RV_REG_T1, lower), ctx); + + /* Restore TCC. */ + emit(rv_addi(RV_REG_TCC, RV_REG_TCC_SAVED, 0), ctx); + + /* Set return value and restore stack. */ + emit(rv_addi(lo(r0), RV_REG_A0, 0), ctx); + emit(rv_addi(hi(r0), RV_REG_A1, 0), ctx); + emit(rv_addi(RV_REG_SP, RV_REG_SP, 16), ctx); +} + +static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) +{ + /* + * R1 -> &ctx + * R2 -> &array + * R3 -> index + */ + int tc_ninsn, off, start_insn = ctx->ninsns; + const s8 *arr_reg = bpf2rv32[BPF_REG_2]; + const s8 *idx_reg = bpf2rv32[BPF_REG_3]; + + tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] : + ctx->offset[0]; + + /* max_entries = array->map.max_entries; */ + off = offsetof(struct bpf_array, map.max_entries); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T1, off, lo(arr_reg)), ctx); + + /* + * if (index >= max_entries) + * goto out; + */ + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx); + + /* + * if ((temp_tcc = tcc - 1) < 0) + * goto out; + */ + emit(rv_addi(RV_REG_T1, RV_REG_TCC, -1), ctx); + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + emit_bcc(BPF_JSLT, RV_REG_T1, RV_REG_ZERO, off, ctx); + + /* + * prog = array->ptrs[index]; + * if (!prog) + * goto out; + */ + emit(rv_slli(RV_REG_T0, lo(idx_reg), 2), ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(arr_reg)), ctx); + off = offsetof(struct bpf_array, ptrs); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + emit_bcc(BPF_JEQ, RV_REG_T0, RV_REG_ZERO, off, ctx); + + /* + * tcc = temp_tcc; + * goto *(prog->bpf_func + 4); + */ + off = offsetof(struct bpf_prog, bpf_func); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); + emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx); + /* Epilogue jumps to *(t0 + 4). */ + __build_epilogue(true, ctx); + return 0; +} + +static int emit_load_r64(const s8 *dst, const s8 *src, s16 off, + struct rv_jit_context *ctx, const u8 size) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + emit_imm(RV_REG_T0, off, ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rs)), ctx); + + switch (size) { + case BPF_B: + emit(rv_lbu(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_H: + emit(rv_lhu(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_W: + emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_DW: + emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx); + emit(rv_lw(hi(rd), 4, RV_REG_T0), ctx); + break; + } + + bpf_put_reg64(dst, rd, ctx); + return 0; +} + +static int emit_store_r64(const s8 *dst, const s8 *src, s16 off, + struct rv_jit_context *ctx, const u8 size, + const u8 mode) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + if (mode == BPF_XADD && size != BPF_W) + return -1; + + emit_imm(RV_REG_T0, off, ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rd)), ctx); + + switch (size) { + case BPF_B: + emit(rv_sb(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_H: + emit(rv_sh(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_W: + switch (mode) { + case BPF_MEM: + emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_XADD: + emit(rv_amoadd_w(RV_REG_ZERO, lo(rs), RV_REG_T0, 0, 0), + ctx); + break; + } + break; + case BPF_DW: + emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx); + emit(rv_sw(RV_REG_T0, 4, hi(rs)), ctx); + break; + } + + return 0; +} + +static void emit_rev16(const s8 rd, struct rv_jit_context *ctx) +{ + emit(rv_slli(rd, rd, 16), ctx); + emit(rv_slli(RV_REG_T1, rd, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_add(RV_REG_T1, rd, RV_REG_T1), ctx); + emit(rv_srli(rd, RV_REG_T1, 16), ctx); +} + +static void emit_rev32(const s8 rd, struct rv_jit_context *ctx) +{ + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 0), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_addi(rd, RV_REG_T1, 0), ctx); +} + +static void emit_zext64(const s8 *dst, struct rv_jit_context *ctx) +{ + const s8 *rd; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + + rd = bpf_get_reg64(dst, tmp1, ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + bpf_put_reg64(dst, rd, ctx); +} + +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) +{ + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || + BPF_CLASS(insn->code) == BPF_JMP; + int s, e, rvoff, i = insn - ctx->prog->insnsi; + u8 code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; + + const s8 *dst = bpf2rv32[insn->dst_reg]; + const s8 *src = bpf2rv32[insn->src_reg]; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + switch (code) { + case BPF_ALU64 | BPF_MOV | BPF_X: + + case BPF_ALU64 | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_K: + + case BPF_ALU64 | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_K: + + case BPF_ALU64 | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + + case BPF_ALU64 | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_K: + + case BPF_ALU64 | BPF_LSH | BPF_X: + case BPF_ALU64 | BPF_RSH | BPF_X: + case BPF_ALU64 | BPF_ARSH | BPF_X: + if (BPF_SRC(code) == BPF_K) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + emit_alu_r64(dst, src, ctx, BPF_OP(code)); + break; + + case BPF_ALU64 | BPF_NEG: + emit_alu_r64(dst, tmp2, ctx, BPF_OP(code)); + break; + + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_K: + goto notsupported; + + case BPF_ALU64 | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + emit_alu_i64(dst, imm, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_MOV | BPF_X: + if (imm == 1) { + /* Special mov32 for zext. */ + emit_zext64(dst, ctx); + break; + } + /* Fallthrough. */ + + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_X: + + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_ARSH | BPF_X: + if (BPF_SRC(code) == BPF_K) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + emit_alu_r32(dst, src, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_ARSH | BPF_K: + /* + * mul,div,mod are handled in the BPF_X case since there are + * no RISC-V I-type equivalents. + */ + emit_alu_i32(dst, imm, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_NEG: + /* + * src is ignored---choose tmp2 as a dummy register since it + * is not on the stack. + */ + emit_alu_r32(dst, tmp2, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_END | BPF_FROM_LE: + { + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (imm) { + case 16: + emit(rv_slli(lo(rd), lo(rd), 16), ctx); + emit(rv_srli(lo(rd), lo(rd), 16), ctx); + /* Fallthrough. */ + case 32: + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 64: + /* Do nothing. */ + break; + default: + pr_err("bpf-jit: BPF_END imm %d invalid\n", imm); + return -1; + } + + bpf_put_reg64(dst, rd, ctx); + break; + } + + case BPF_ALU | BPF_END | BPF_FROM_BE: + { + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (imm) { + case 16: + emit_rev16(lo(rd), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 32: + emit_rev32(lo(rd), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 64: + /* Swap upper and lower halves. */ + emit(rv_addi(RV_REG_T0, lo(rd), 0), ctx); + emit(rv_addi(lo(rd), hi(rd), 0), ctx); + emit(rv_addi(hi(rd), RV_REG_T0, 0), ctx); + + /* Swap each half. */ + emit_rev32(lo(rd), ctx); + emit_rev32(hi(rd), ctx); + break; + default: + pr_err("bpf-jit: BPF_END imm %d invalid\n", imm); + return -1; + } + + bpf_put_reg64(dst, rd, ctx); + break; + } + + case BPF_JMP | BPF_JA: + rvoff = rv_offset(i, off, ctx); + emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + break; + + case BPF_JMP | BPF_CALL: + { + bool fixed; + int ret; + u64 addr; + + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, + &fixed); + if (ret < 0) + return ret; + emit_call(fixed, addr, ctx); + break; + } + + case BPF_JMP | BPF_TAIL_CALL: + if (emit_bpf_tail_call(i, ctx)) + return -1; + break; + + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_K: + + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_K: + + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_K: + + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_K: + + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_K: + + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_K: + + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_K: + + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_K: + + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_K: + + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_K: + + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_X: + case BPF_JMP32 | BPF_JSET | BPF_K: + rvoff = rv_offset(i, off, ctx); + if (BPF_SRC(code) == BPF_K) { + s = ctx->ninsns; + emit_imm32(tmp2, imm, ctx); + src = tmp2; + e = ctx->ninsns; + rvoff -= (e - s) << 2; + } + + if (is64) + emit_branch_r64(dst, src, rvoff, ctx, BPF_OP(code)); + else + emit_branch_r32(dst, src, rvoff, ctx, BPF_OP(code)); + break; + + case BPF_JMP | BPF_EXIT: + if (i == ctx->prog->len - 1) + break; + + rvoff = epilogue_offset(ctx); + emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + break; + + case BPF_LD | BPF_IMM | BPF_DW: + { + struct bpf_insn insn1 = insn[1]; + s32 imm_lo = imm; + s32 imm_hi = insn1.imm; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + emit_imm64(rd, imm_hi, imm_lo, ctx); + bpf_put_reg64(dst, rd, ctx); + return 1; + } + + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_DW: + if (emit_load_r64(dst, src, off, ctx, BPF_SIZE(code))) + return -1; + break; + + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_DW: + + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_DW: + case BPF_STX | BPF_XADD | BPF_W: + if (BPF_CLASS(code) == BPF_ST) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + + if (emit_store_r64(dst, src, off, ctx, BPF_SIZE(code), + BPF_MODE(code))) + return -1; + break; + + /* No hardware support for 8-byte atomics in RV32. */ + case BPF_STX | BPF_XADD | BPF_DW: + /* Fallthrough. */ + +notsupported: + pr_info_once("bpf-jit: not supported: opcode %02x ***\n", code); + return -EFAULT; + + default: + pr_err("bpf-jit: unknown opcode %02x\n", code); + return -EINVAL; + } + + return 0; +} + +void bpf_jit_build_prologue(struct rv_jit_context *ctx) +{ + /* Make space to save 9 registers: ra, fp, s1--s7. */ + int stack_adjust = 9 * sizeof(u32), store_offset, bpf_stack_adjust; + const s8 *fp = bpf2rv32[BPF_REG_FP]; + const s8 *r1 = bpf2rv32[BPF_REG_1]; + + bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); + stack_adjust += bpf_stack_adjust; + + store_offset = stack_adjust - 4; + + stack_adjust += 4 * BPF_JIT_SCRATCH_REGS; + + /* + * The first instruction sets the tail-call-counter (TCC) register. + * This instruction is skipped by tail calls. + */ + emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx); + + emit(rv_addi(RV_REG_SP, RV_REG_SP, -stack_adjust), ctx); + + /* Save callee-save registers. */ + emit(rv_sw(RV_REG_SP, store_offset - 0, RV_REG_RA), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 4, RV_REG_FP), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 8, RV_REG_S1), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 12, RV_REG_S2), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 16, RV_REG_S3), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 20, RV_REG_S4), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 24, RV_REG_S5), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 28, RV_REG_S6), ctx); + emit(rv_sw(RV_REG_SP, store_offset - 32, RV_REG_S7), ctx); + + /* Set fp: used as the base address for stacked BPF registers. */ + emit(rv_addi(RV_REG_FP, RV_REG_SP, stack_adjust), ctx); + + /* Set up BPF stack pointer. */ + emit(rv_addi(lo(fp), RV_REG_SP, bpf_stack_adjust), ctx); + emit(rv_addi(hi(fp), RV_REG_ZERO, 0), ctx); + + /* Set up context pointer. */ + emit(rv_addi(lo(r1), RV_REG_A0, 0), ctx); + emit(rv_addi(hi(r1), RV_REG_ZERO, 0), ctx); + + ctx->stack_size = stack_adjust; +} + +void bpf_jit_build_epilogue(struct rv_jit_context *ctx) +{ + __build_epilogue(false, ctx); +} diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp64.c index 483f4ad7f4dc..cc1985d8750a 100644 --- a/arch/riscv/net/bpf_jit_comp.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -7,42 +7,7 @@ #include <linux/bpf.h> #include <linux/filter.h> -#include <asm/cacheflush.h> - -enum { - RV_REG_ZERO = 0, /* The constant value 0 */ - RV_REG_RA = 1, /* Return address */ - RV_REG_SP = 2, /* Stack pointer */ - RV_REG_GP = 3, /* Global pointer */ - RV_REG_TP = 4, /* Thread pointer */ - RV_REG_T0 = 5, /* Temporaries */ - RV_REG_T1 = 6, - RV_REG_T2 = 7, - RV_REG_FP = 8, - RV_REG_S1 = 9, /* Saved registers */ - RV_REG_A0 = 10, /* Function argument/return values */ - RV_REG_A1 = 11, /* Function arguments */ - RV_REG_A2 = 12, - RV_REG_A3 = 13, - RV_REG_A4 = 14, - RV_REG_A5 = 15, - RV_REG_A6 = 16, - RV_REG_A7 = 17, - RV_REG_S2 = 18, /* Saved registers */ - RV_REG_S3 = 19, - RV_REG_S4 = 20, - RV_REG_S5 = 21, - RV_REG_S6 = 22, - RV_REG_S7 = 23, - RV_REG_S8 = 24, - RV_REG_S9 = 25, - RV_REG_S10 = 26, - RV_REG_S11 = 27, - RV_REG_T3 = 28, /* Temporaries */ - RV_REG_T4 = 29, - RV_REG_T5 = 30, - RV_REG_T6 = 31, -}; +#include "bpf_jit.h" #define RV_REG_TCC RV_REG_A6 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ @@ -73,22 +38,6 @@ enum { RV_CTX_F_SEEN_S6 = RV_REG_S6, }; -struct rv_jit_context { - struct bpf_prog *prog; - u32 *insns; /* RV insns */ - int ninsns; - int epilogue_offset; - int *offset; /* BPF to RV */ - unsigned long flags; - int stack_size; -}; - -struct rv_jit_data { - struct bpf_binary_header *header; - u8 *image; - struct rv_jit_context ctx; -}; - static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx) { u8 reg = regmap[bpf_reg]; @@ -156,346 +105,11 @@ static u8 rv_tail_call_reg(struct rv_jit_context *ctx) return RV_REG_A6; } -static void emit(const u32 insn, struct rv_jit_context *ctx) -{ - if (ctx->insns) - ctx->insns[ctx->ninsns] = insn; - - ctx->ninsns++; -} - -static u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, u8 opcode) -{ - return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | - (rd << 7) | opcode; -} - -static u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode) -{ - return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | - opcode; -} - -static u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode) -{ - u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f; - - return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | - (imm4_0 << 7) | opcode; -} - -static u32 rv_sb_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode) -{ - u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4); - u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10); - - return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | - (imm4_1 << 7) | opcode; -} - -static u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode) -{ - return (imm31_12 << 12) | (rd << 7) | opcode; -} - -static u32 rv_uj_insn(u32 imm20_1, u8 rd, u8 opcode) -{ - u32 imm; - - imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) | - ((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11); - - return (imm << 12) | (rd << 7) | opcode; -} - -static u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1, - u8 funct3, u8 rd, u8 opcode) -{ - u8 funct7 = (funct5 << 2) | (aq << 1) | rl; - - return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode); -} - -static u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b); -} - -static u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 0, rd, 0x13); -} - -static u32 rv_addw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b); -} - -static u32 rv_add(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 0, rd, 0x33); -} - -static u32 rv_subw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b); -} - -static u32 rv_sub(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33); -} - -static u32 rv_and(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 7, rd, 0x33); -} - -static u32 rv_or(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 6, rd, 0x33); -} - -static u32 rv_xor(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 4, rd, 0x33); -} - -static u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); -} - -static u32 rv_mul(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 0, rd, 0x33); -} - -static u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); -} - -static u32 rv_divu(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); -} - -static u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); -} - -static u32 rv_remu(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); -} - -static u32 rv_sllw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b); -} - -static u32 rv_sll(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 1, rd, 0x33); -} - -static u32 rv_srlw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b); -} - -static u32 rv_srl(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0, rs2, rs1, 5, rd, 0x33); -} - -static u32 rv_sraw(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b); -} - -static u32 rv_sra(u8 rd, u8 rs1, u8 rs2) -{ - return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33); -} - -static u32 rv_lui(u8 rd, u32 imm31_12) -{ - return rv_u_insn(imm31_12, rd, 0x37); -} - -static u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 1, rd, 0x13); -} - -static u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 7, rd, 0x13); -} - -static u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 6, rd, 0x13); -} - -static u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 4, rd, 0x13); -} - -static u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b); -} - -static u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b); -} - -static u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 5, rd, 0x13); -} - -static u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b); -} - -static u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13); -} - -static u32 rv_jal(u8 rd, u32 imm20_1) -{ - return rv_uj_insn(imm20_1, rd, 0x6f); -} - -static u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0) -{ - return rv_i_insn(imm11_0, rs1, 0, rd, 0x67); -} - -static u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 0, 0x63); -} - -static u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 6, 0x63); -} - -static u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 7, 0x63); -} - -static u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 1, 0x63); -} - -static u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 4, 0x63); -} - -static u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1) -{ - return rv_sb_insn(imm12_1, rs2, rs1, 5, 0x63); -} - -static u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23); -} - -static u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23); -} - -static u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23); -} - -static u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2) -{ - return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23); -} - -static u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 4, rd, 0x03); -} - -static u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 5, rd, 0x03); -} - -static u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 6, rd, 0x03); -} - -static u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1) -{ - return rv_i_insn(imm11_0, rs1, 3, rd, 0x03); -} - -static u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) -{ - return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f); -} - -static u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) -{ - return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f); -} - -static u32 rv_auipc(u8 rd, u32 imm31_12) -{ - return rv_u_insn(imm31_12, rd, 0x17); -} - -static bool is_12b_int(s64 val) -{ - return -(1 << 11) <= val && val < (1 << 11); -} - -static bool is_13b_int(s64 val) -{ - return -(1 << 12) <= val && val < (1 << 12); -} - -static bool is_21b_int(s64 val) -{ - return -(1L << 20) <= val && val < (1L << 20); -} - static bool is_32b_int(s64 val) { return -(1L << 31) <= val && val < (1L << 31); } -static int is_12b_check(int off, int insn) -{ - if (!is_12b_int(off)) { - pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n", - insn, (int)off); - return -1; - } - return 0; -} - static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) { /* Note that the immediate from the add is sign-extended, @@ -535,23 +149,6 @@ static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) emit(rv_addi(rd, rd, lower), ctx); } -static int rv_offset(int insn, int off, struct rv_jit_context *ctx) -{ - int from, to; - - off++; /* BPF branch is from PC+1, RV is from PC */ - from = (insn > 0) ? ctx->offset[insn - 1] : 0; - to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; - return (to - from) << 2; -} - -static int epilogue_offset(struct rv_jit_context *ctx) -{ - int to = ctx->epilogue_offset, from = ctx->ninsns; - - return (to - from) << 2; -} - static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) { int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8; @@ -596,34 +193,6 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) ctx); } -/* return -1 or inverted cond */ -static int invert_bpf_cond(u8 cond) -{ - switch (cond) { - case BPF_JEQ: - return BPF_JNE; - case BPF_JGT: - return BPF_JLE; - case BPF_JLT: - return BPF_JGE; - case BPF_JGE: - return BPF_JLT; - case BPF_JLE: - return BPF_JGT; - case BPF_JNE: - return BPF_JEQ; - case BPF_JSGT: - return BPF_JSLE; - case BPF_JSLT: - return BPF_JSGE; - case BPF_JSGE: - return BPF_JSLT; - case BPF_JSLE: - return BPF_JSGT; - } - return -1; -} - static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff, struct rv_jit_context *ctx) { @@ -855,8 +424,8 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) return 0; } -static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, - bool extra_pass) +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || BPF_CLASS(insn->code) == BPF_JMP; @@ -1434,7 +1003,7 @@ out_be: return 0; } -static void build_prologue(struct rv_jit_context *ctx) +void bpf_jit_build_prologue(struct rv_jit_context *ctx) { int stack_adjust = 0, store_offset, bpf_stack_adjust; @@ -1515,175 +1084,11 @@ static void build_prologue(struct rv_jit_context *ctx) ctx->stack_size = stack_adjust; } -static void build_epilogue(struct rv_jit_context *ctx) +void bpf_jit_build_epilogue(struct rv_jit_context *ctx) { __build_epilogue(false, ctx); } -static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) -{ - const struct bpf_prog *prog = ctx->prog; - int i; - - for (i = 0; i < prog->len; i++) { - const struct bpf_insn *insn = &prog->insnsi[i]; - int ret; - - ret = emit_insn(insn, ctx, extra_pass); - if (ret > 0) { - i++; - if (offset) - offset[i] = ctx->ninsns; - continue; - } - if (offset) - offset[i] = ctx->ninsns; - if (ret) - return ret; - } - return 0; -} - -static void bpf_fill_ill_insns(void *area, unsigned int size) -{ - memset(area, 0, size); -} - -static void bpf_flush_icache(void *start, void *end) -{ - flush_icache_range((unsigned long)start, (unsigned long)end); -} - -bool bpf_jit_needs_zext(void) -{ - return true; -} - -struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) -{ - bool tmp_blinded = false, extra_pass = false; - struct bpf_prog *tmp, *orig_prog = prog; - int pass = 0, prev_ninsns = 0, i; - struct rv_jit_data *jit_data; - unsigned int image_size = 0; - struct rv_jit_context *ctx; - - if (!prog->jit_requested) - return orig_prog; - - tmp = bpf_jit_blind_constants(prog); - if (IS_ERR(tmp)) - return orig_prog; - if (tmp != prog) { - tmp_blinded = true; - prog = tmp; - } - - jit_data = prog->aux->jit_data; - if (!jit_data) { - jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); - if (!jit_data) { - prog = orig_prog; - goto out; - } - prog->aux->jit_data = jit_data; - } - - ctx = &jit_data->ctx; - - if (ctx->offset) { - extra_pass = true; - image_size = sizeof(u32) * ctx->ninsns; - goto skip_init_ctx; - } - - ctx->prog = prog; - ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); - if (!ctx->offset) { - prog = orig_prog; - goto out_offset; - } - for (i = 0; i < prog->len; i++) { - prev_ninsns += 32; - ctx->offset[i] = prev_ninsns; - } - - for (i = 0; i < 16; i++) { - pass++; - ctx->ninsns = 0; - if (build_body(ctx, extra_pass, ctx->offset)) { - prog = orig_prog; - goto out_offset; - } - build_prologue(ctx); - ctx->epilogue_offset = ctx->ninsns; - build_epilogue(ctx); - - if (ctx->ninsns == prev_ninsns) { - if (jit_data->header) - break; - - image_size = sizeof(u32) * ctx->ninsns; - jit_data->header = - bpf_jit_binary_alloc(image_size, - &jit_data->image, - sizeof(u32), - bpf_fill_ill_insns); - if (!jit_data->header) { - prog = orig_prog; - goto out_offset; - } - - ctx->insns = (u32 *)jit_data->image; - /* Now, when the image is allocated, the image - * can potentially shrink more (auipc/jalr -> - * jal). - */ - } - prev_ninsns = ctx->ninsns; - } - - if (i == 16) { - pr_err("bpf-jit: image did not converge in <%d passes!\n", i); - bpf_jit_binary_free(jit_data->header); - prog = orig_prog; - goto out_offset; - } - -skip_init_ctx: - pass++; - ctx->ninsns = 0; - - build_prologue(ctx); - if (build_body(ctx, extra_pass, NULL)) { - bpf_jit_binary_free(jit_data->header); - prog = orig_prog; - goto out_offset; - } - build_epilogue(ctx); - - if (bpf_jit_enable > 1) - bpf_jit_dump(prog->len, image_size, pass, ctx->insns); - - prog->bpf_func = (void *)ctx->insns; - prog->jited = 1; - prog->jited_len = image_size; - - bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); - - if (!prog->is_func || extra_pass) { -out_offset: - kfree(ctx->offset); - kfree(jit_data); - prog->aux->jit_data = NULL; - } -out: - if (tmp_blinded) - bpf_jit_prog_release_other(prog, prog == orig_prog ? - tmp : orig_prog); - return prog; -} - void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c new file mode 100644 index 000000000000..709b94ece3ed --- /dev/null +++ b/arch/riscv/net/bpf_jit_core.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common functionality for RV32 and RV64 BPF JIT compilers + * + * Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com> + * + */ + +#include <linux/bpf.h> +#include <linux/filter.h> +#include "bpf_jit.h" + +/* Number of iterations to try until offsets converge. */ +#define NR_JIT_ITERATIONS 16 + +static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) +{ + const struct bpf_prog *prog = ctx->prog; + int i; + + for (i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &prog->insnsi[i]; + int ret; + + ret = bpf_jit_emit_insn(insn, ctx, extra_pass); + /* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */ + if (ret > 0) + i++; + if (offset) + offset[i] = ctx->ninsns; + if (ret < 0) + return ret; + } + return 0; +} + +bool bpf_jit_needs_zext(void) +{ + return true; +} + +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) +{ + bool tmp_blinded = false, extra_pass = false; + struct bpf_prog *tmp, *orig_prog = prog; + int pass = 0, prev_ninsns = 0, i; + struct rv_jit_data *jit_data; + struct rv_jit_context *ctx; + unsigned int image_size = 0; + + if (!prog->jit_requested) + return orig_prog; + + tmp = bpf_jit_blind_constants(prog); + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } + + jit_data = prog->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); + if (!jit_data) { + prog = orig_prog; + goto out; + } + prog->aux->jit_data = jit_data; + } + + ctx = &jit_data->ctx; + + if (ctx->offset) { + extra_pass = true; + image_size = sizeof(u32) * ctx->ninsns; + goto skip_init_ctx; + } + + ctx->prog = prog; + ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); + if (!ctx->offset) { + prog = orig_prog; + goto out_offset; + } + for (i = 0; i < prog->len; i++) { + prev_ninsns += 32; + ctx->offset[i] = prev_ninsns; + } + + for (i = 0; i < NR_JIT_ITERATIONS; i++) { + pass++; + ctx->ninsns = 0; + if (build_body(ctx, extra_pass, ctx->offset)) { + prog = orig_prog; + goto out_offset; + } + bpf_jit_build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; + bpf_jit_build_epilogue(ctx); + + if (ctx->ninsns == prev_ninsns) { + if (jit_data->header) + break; + + image_size = sizeof(u32) * ctx->ninsns; + jit_data->header = + bpf_jit_binary_alloc(image_size, + &jit_data->image, + sizeof(u32), + bpf_fill_ill_insns); + if (!jit_data->header) { + prog = orig_prog; + goto out_offset; + } + + ctx->insns = (u32 *)jit_data->image; + /* + * Now, when the image is allocated, the image can + * potentially shrink more (auipc/jalr -> jal). + */ + } + prev_ninsns = ctx->ninsns; + } + + if (i == NR_JIT_ITERATIONS) { + pr_err("bpf-jit: image did not converge in <%d passes!\n", i); + bpf_jit_binary_free(jit_data->header); + prog = orig_prog; + goto out_offset; + } + +skip_init_ctx: + pass++; + ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx); + if (build_body(ctx, extra_pass, NULL)) { + bpf_jit_binary_free(jit_data->header); + prog = orig_prog; + goto out_offset; + } + bpf_jit_build_epilogue(ctx); + + if (bpf_jit_enable > 1) + bpf_jit_dump(prog->len, image_size, pass, ctx->insns); + + prog->bpf_func = (void *)ctx->insns; + prog->jited = 1; + prog->jited_len = image_size; + + bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); + + if (!prog->is_func || extra_pass) { +out_offset: + kfree(ctx->offset); + kfree(jit_data); + prog->aux->jit_data = NULL; + } +out: + + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); + return prog; +} diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 23df4885bbed..eb6ede2c3d43 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -238,7 +238,11 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) } } -static inline int is_kernel_text(unsigned long addr) +/* + * The <linux/kallsyms.h> already defines is_kernel_text, + * using '__' prefix not to get in conflict. + */ +static inline int __is_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end) return 1; @@ -328,8 +332,8 @@ repeat: addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1; - if (is_kernel_text(addr) || - is_kernel_text(addr2)) + if (__is_kernel_text(addr) || + __is_kernel_text(addr2)) prot = PAGE_KERNEL_LARGE_EXEC; pages_2m++; @@ -354,7 +358,7 @@ repeat: */ pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR); - if (is_kernel_text(addr)) + if (__is_kernel_text(addr)) prot = PAGE_KERNEL_EXEC; pages_4k++; @@ -881,7 +885,7 @@ static void mark_nxdata_nx(void) */ unsigned long start = PFN_ALIGN(_etext); /* - * This comes from is_kernel_text upper limit. Also HPAGE where used: + * This comes from __is_kernel_text upper limit. Also HPAGE where used: */ unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 9ba08e9abc09..5ea7c2cf7ab4 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1361,37 +1361,140 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, -(stack_size - i * 8)); } +static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, + struct bpf_prog *p, int stack_size, bool mod_ret) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (emit_call(&prog, __bpf_prog_enter, prog)) + return -EINVAL; + /* remember prog start time returned by __bpf_prog_enter */ + emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + + /* arg1: lea rdi, [rbp - stack_size] */ + EMIT4(0x48, 0x8D, 0x7D, -stack_size); + /* arg2: progs[i]->insnsi for interpreter */ + if (!p->jited) + emit_mov_imm64(&prog, BPF_REG_2, + (long) p->insnsi >> 32, + (u32) (long) p->insnsi); + /* call JITed bpf program or interpreter */ + if (emit_call(&prog, p->bpf_func, prog)) + return -EINVAL; + + /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + * of the previous call which is then passed on the stack to + * the next BPF program. + */ + if (mod_ret) + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, + (u32) (long) p); + /* arg2: mov rsi, rbx <- start time in nsec */ + emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); + if (emit_call(&prog, __bpf_prog_exit, prog)) + return -EINVAL; + + *pprog = prog; + return 0; +} + +static void emit_nops(u8 **pprog, unsigned int len) +{ + unsigned int i, noplen; + u8 *prog = *pprog; + int cnt = 0; + + while (len > 0) { + noplen = len; + + if (noplen > ASM_NOP_MAX) + noplen = ASM_NOP_MAX; + + for (i = 0; i < noplen; i++) + EMIT1(ideal_nops[noplen][i]); + len -= noplen; + } + + *pprog = prog; +} + +static void emit_align(u8 **pprog, u32 align) +{ + u8 *target, *prog = *pprog; + + target = PTR_ALIGN(prog, align); + if (target != prog) + emit_nops(&prog, target - prog); + + *pprog = prog; +} + +static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) +{ + u8 *prog = *pprog; + int cnt = 0; + s64 offset; + + offset = func - (ip + 2 + 4); + if (!is_simm32(offset)) { + pr_err("Target %p is out of range\n", func); + return -EINVAL; + } + EMIT2_off32(0x0F, jmp_cond + 0x10, offset); + *pprog = prog; + return 0; +} + static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, - struct bpf_prog **progs, int prog_cnt, int stack_size) + struct bpf_tramp_progs *tp, int stack_size) { + int i; u8 *prog = *pprog; - int cnt = 0, i; - for (i = 0; i < prog_cnt; i++) { - if (emit_call(&prog, __bpf_prog_enter, prog)) - return -EINVAL; - /* remember prog start time returned by __bpf_prog_enter */ - emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); - - /* arg1: lea rdi, [rbp - stack_size] */ - EMIT4(0x48, 0x8D, 0x7D, -stack_size); - /* arg2: progs[i]->insnsi for interpreter */ - if (!progs[i]->jited) - emit_mov_imm64(&prog, BPF_REG_2, - (long) progs[i]->insnsi >> 32, - (u32) (long) progs[i]->insnsi); - /* call JITed bpf program or interpreter */ - if (emit_call(&prog, progs[i]->bpf_func, prog)) + for (i = 0; i < tp->nr_progs; i++) { + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) return -EINVAL; + } + *pprog = prog; + return 0; +} + +static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, + struct bpf_tramp_progs *tp, int stack_size, + u8 **branches) +{ + u8 *prog = *pprog; + int i, cnt = 0; - /* arg1: mov rdi, progs[i] */ - emit_mov_imm64(&prog, BPF_REG_1, (long) progs[i] >> 32, - (u32) (long) progs[i]); - /* arg2: mov rsi, rbx <- start time in nsec */ - emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); - if (emit_call(&prog, __bpf_prog_exit, prog)) + /* The first fmod_ret program will receive a garbage return value. + * Set this to 0 to avoid confusing the program. + */ + emit_mov_imm32(&prog, false, BPF_REG_0, 0); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + for (i = 0; i < tp->nr_progs; i++) { + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, true)) return -EINVAL; + + /* mod_ret prog stored return value into [rbp - 8]. Emit: + * if (*(u64 *)(rbp - 8) != 0) + * goto do_fexit; + */ + /* cmp QWORD PTR [rbp - 0x8], 0x0 */ + EMIT4(0x48, 0x83, 0x7d, 0xf8); EMIT1(0x00); + + /* Save the location of the branch and Generate 6 nops + * (4 bytes for an offset and 2 bytes for the jump) These nops + * are replaced with a conditional jump once do_fexit (i.e. the + * start of the fexit invocation) is finalized. + */ + branches[i] = prog; + emit_nops(&prog, 4 + 2); } + *pprog = prog; return 0; } @@ -1458,12 +1561,15 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, */ int arch_prepare_bpf_trampoline(void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_prog **fentry_progs, int fentry_cnt, - struct bpf_prog **fexit_progs, int fexit_cnt, + struct bpf_tramp_progs *tprogs, void *orig_call) { - int cnt = 0, nr_args = m->nr_args; + int ret, i, cnt = 0, nr_args = m->nr_args; int stack_size = nr_args * 8; + struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY]; + struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT]; + struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; + u8 **branches = NULL; u8 *prog; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ @@ -1492,28 +1598,64 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, save_regs(m, &prog, nr_args, stack_size); - if (fentry_cnt) - if (invoke_bpf(m, &prog, fentry_progs, fentry_cnt, stack_size)) + if (fentry->nr_progs) + if (invoke_bpf(m, &prog, fentry, stack_size)) return -EINVAL; + if (fmod_ret->nr_progs) { + branches = kcalloc(fmod_ret->nr_progs, sizeof(u8 *), + GFP_KERNEL); + if (!branches) + return -ENOMEM; + + if (invoke_bpf_mod_ret(m, &prog, fmod_ret, stack_size, + branches)) { + ret = -EINVAL; + goto cleanup; + } + } + if (flags & BPF_TRAMP_F_CALL_ORIG) { - if (fentry_cnt) + if (fentry->nr_progs || fmod_ret->nr_progs) restore_regs(m, &prog, nr_args, stack_size); /* call original function */ - if (emit_call(&prog, orig_call, prog)) - return -EINVAL; + if (emit_call(&prog, orig_call, prog)) { + ret = -EINVAL; + goto cleanup; + } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); } - if (fexit_cnt) - if (invoke_bpf(m, &prog, fexit_progs, fexit_cnt, stack_size)) - return -EINVAL; + if (fmod_ret->nr_progs) { + /* From Intel 64 and IA-32 Architectures Optimization + * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler + * Coding Rule 11: All branch targets should be 16-byte + * aligned. + */ + emit_align(&prog, 16); + /* Update the branches saved in invoke_bpf_mod_ret with the + * aligned address of do_fexit. + */ + for (i = 0; i < fmod_ret->nr_progs; i++) + emit_cond_near_jump(&branches[i], prog, branches[i], + X86_JNE); + } + + if (fexit->nr_progs) + if (invoke_bpf(m, &prog, fexit, stack_size)) { + ret = -EINVAL; + goto cleanup; + } if (flags & BPF_TRAMP_F_RESTORE_REGS) restore_regs(m, &prog, nr_args, stack_size); + /* This needs to be done regardless. If there were fmod_ret programs, + * the return value is only updated on the stack and still needs to be + * restored to R0. + */ if (flags & BPF_TRAMP_F_CALL_ORIG) /* restore original return value back into RAX */ emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); @@ -1525,45 +1667,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ EMIT1(0xC3); /* ret */ /* Make sure the trampoline generation logic doesn't overflow */ - if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) - return -EFAULT; - return prog - (u8 *)image; -} - -static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) -{ - u8 *prog = *pprog; - int cnt = 0; - s64 offset; - - offset = func - (ip + 2 + 4); - if (!is_simm32(offset)) { - pr_err("Target %p is out of range\n", func); - return -EINVAL; - } - EMIT2_off32(0x0F, jmp_cond + 0x10, offset); - *pprog = prog; - return 0; -} - -static void emit_nops(u8 **pprog, unsigned int len) -{ - unsigned int i, noplen; - u8 *prog = *pprog; - int cnt = 0; - - while (len > 0) { - noplen = len; - - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - - for (i = 0; i < noplen; i++) - EMIT1(ideal_nops[noplen][i]); - len -= noplen; + if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { + ret = -EFAULT; + goto cleanup; } + ret = prog - (u8 *)image; - *pprog = prog; +cleanup: + kfree(branches); + return ret; } static int emit_fallback_jump(u8 **pprog) @@ -1588,7 +1700,7 @@ static int emit_fallback_jump(u8 **pprog) static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) { - u8 *jg_reloc, *jg_target, *prog = *pprog; + u8 *jg_reloc, *prog = *pprog; int pivot, err, jg_bytes = 1, cnt = 0; s64 jg_offset; @@ -1643,9 +1755,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) * Coding Rule 11: All branch targets should be 16-byte * aligned. */ - jg_target = PTR_ALIGN(prog, 16); - if (jg_target != prog) - emit_nops(&prog, jg_target - prog); + emit_align(&prog, 16); jg_offset = prog - jg_reloc; emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes); diff --git a/fs/nsfs.c b/fs/nsfs.c index b13bfd406820..4f1205725cfe 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -247,6 +247,20 @@ out_invalid: return ERR_PTR(-EINVAL); } +/** + * ns_match() - Returns true if current namespace matches dev/ino provided. + * @ns_common: current ns + * @dev: dev_t from nsfs that will be matched against current nsfs + * @ino: ino_t from nsfs that will be matched against current nsfs + * + * Return: true if dev and ino matches the current nsfs. + */ +bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino) +{ + return (ns->inum == ino) && (nsfs_mnt->mnt_sb->s_dev == dev); +} + + static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry) { struct inode *inode = d_inode(dentry); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6015a4daf118..bdb981c204fa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -18,6 +18,7 @@ #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> +#include <linux/kallsyms.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -433,6 +434,16 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) +/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 + * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 + */ +#define BPF_MAX_TRAMP_PROGS 40 + +struct bpf_tramp_progs { + struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; + int nr_progs; +}; + /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS @@ -455,16 +466,25 @@ struct btf_func_model { */ int arch_prepare_bpf_trampoline(void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_prog **fentry_progs, int fentry_cnt, - struct bpf_prog **fexit_progs, int fexit_cnt, + struct bpf_tramp_progs *tprogs, void *orig_call); /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); +struct bpf_ksym { + unsigned long start; + unsigned long end; + char name[KSYM_NAME_LEN]; + struct list_head lnode; + struct latch_tree_node tnode; + bool prog; +}; + enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, + BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ }; @@ -493,6 +513,7 @@ struct bpf_trampoline { /* Executable image of trampoline */ void *image; u64 selector; + struct bpf_ksym ksym; }; #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ @@ -510,9 +531,10 @@ struct bpf_dispatcher { int num_progs; void *image; u32 image_off; + struct bpf_ksym ksym; }; -static __always_inline unsigned int bpf_dispatcher_nopfunc( +static __always_inline unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, @@ -525,17 +547,21 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key); int bpf_trampoline_link_prog(struct bpf_prog *prog); int bpf_trampoline_unlink_prog(struct bpf_prog *prog); void bpf_trampoline_put(struct bpf_trampoline *tr); -#define BPF_DISPATCHER_INIT(name) { \ - .mutex = __MUTEX_INITIALIZER(name.mutex), \ - .func = &name##func, \ - .progs = {}, \ - .num_progs = 0, \ - .image = NULL, \ - .image_off = 0 \ +#define BPF_DISPATCHER_INIT(_name) { \ + .mutex = __MUTEX_INITIALIZER(_name.mutex), \ + .func = &_name##_func, \ + .progs = {}, \ + .num_progs = 0, \ + .image = NULL, \ + .image_off = 0, \ + .ksym = { \ + .name = #_name, \ + .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ + }, \ } #define DEFINE_BPF_DISPATCHER(name) \ - noinline unsigned int name##func( \ + noinline unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ unsigned int (*bpf_func)(const void *, \ @@ -543,26 +569,26 @@ void bpf_trampoline_put(struct bpf_trampoline *tr); { \ return bpf_func(ctx, insnsi); \ } \ - EXPORT_SYMBOL(name##func); \ - struct bpf_dispatcher name = BPF_DISPATCHER_INIT(name); + EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ + struct bpf_dispatcher bpf_dispatcher_##name = \ + BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ - unsigned int name##func( \ + unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ unsigned int (*bpf_func)(const void *, \ const struct bpf_insn *)); \ - extern struct bpf_dispatcher name; -#define BPF_DISPATCHER_FUNC(name) name##func -#define BPF_DISPATCHER_PTR(name) (&name) + extern struct bpf_dispatcher bpf_dispatcher_##name; +#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func +#define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); -struct bpf_image { - struct latch_tree_node tnode; - unsigned char data[]; -}; -#define BPF_IMAGE_SIZE (PAGE_SIZE - sizeof(struct bpf_image)) -bool is_bpf_image_address(unsigned long address); -void *bpf_image_alloc(void); +/* Called only from JIT-enabled code, so there's no need for stubs. */ +void *bpf_jit_alloc_exec_page(void); +void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); +void bpf_image_ksym_del(struct bpf_ksym *ksym); +void bpf_ksym_add(struct bpf_ksym *ksym); +void bpf_ksym_del(struct bpf_ksym *ksym); #else static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { @@ -579,7 +605,7 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) -#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nopfunc +#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func #define BPF_DISPATCHER_PTR(name) NULL static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, @@ -640,8 +666,7 @@ struct bpf_prog_aux { void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; u32 size_poke_tab; - struct latch_tree_node ksym_tnode; - struct list_head ksym_lnode; + struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct bpf_prog *prog; @@ -1056,6 +1081,21 @@ extern int sysctl_unprivileged_bpf_disabled; int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); +struct bpf_link; + +struct bpf_link_ops { + void (*release)(struct bpf_link *link); + void (*dealloc)(struct bpf_link *link); +}; + +void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, + struct bpf_prog *prog); +void bpf_link_inc(struct bpf_link *link); +void bpf_link_put(struct bpf_link *link); +int bpf_link_new_fd(struct bpf_link *link); +struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); +struct bpf_link *bpf_link_get_from_fd(u32 ufd); + int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); @@ -1133,6 +1173,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_tracing(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); @@ -1290,6 +1333,13 @@ static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, return -ENOTSUPP; } +static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) @@ -1386,6 +1436,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #if defined(CONFIG_BPF_STREAM_PARSER) int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +void sock_map_unhash(struct sock *sk); +void sock_map_close(struct sock *sk, long timeout); #else static inline int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which) @@ -1398,7 +1450,7 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, { return -EINVAL; } -#endif +#endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); @@ -1459,6 +1511,7 @@ extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; +extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index 43b5e455d2f5..9b5aa5c483cc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -577,7 +577,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); ret; }) #define BPF_PROG_RUN(prog, ctx) \ - __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nopfunc) + __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) /* * Use in preemptible and therefore migratable context to make sure that @@ -596,7 +596,7 @@ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, u32 ret; migrate_disable(); - ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nopfunc); + ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func); migrate_enable(); return ret; } @@ -722,7 +722,7 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, return res; } -DECLARE_BPF_DISPATCHER(bpf_dispatcher_xdp) +DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) @@ -733,8 +733,7 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, * already takes rcu_read_lock() when fetching the program, so * it's not necessary here anymore. */ - return __BPF_PROG_RUN(prog, xdp, - BPF_DISPATCHER_FUNC(bpf_dispatcher_xdp)); + return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); @@ -1084,7 +1083,6 @@ bpf_address_lookup(unsigned long addr, unsigned long *size, void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); -void bpf_get_prog_name(const struct bpf_prog *prog, char *sym); #else /* CONFIG_BPF_JIT */ @@ -1153,11 +1151,6 @@ static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } -static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) -{ - sym[0] = '\0'; -} - #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 4626b1ac3b6c..adff08bfecf9 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -85,6 +85,8 @@ typedef struct ns_common *ns_get_path_helper_t(void *); extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, void *private_data); +extern bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); + extern int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops); extern void nsfs_init(void); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 112765bd146d..8a709f63c5e5 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -323,14 +323,6 @@ static inline void sk_psock_free_link(struct sk_psock_link *link) } struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); -#if defined(CONFIG_BPF_STREAM_PARSER) -void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link); -#else -static inline void sk_psock_unlink(struct sock *sk, - struct sk_psock_link *link) -{ -} -#endif void __sk_psock_purge_ingress_msg(struct sk_psock *psock); @@ -347,11 +339,23 @@ static inline void sk_psock_update_proto(struct sock *sk, struct sk_psock *psock, struct proto *ops) { - psock->saved_unhash = sk->sk_prot->unhash; - psock->saved_close = sk->sk_prot->close; - psock->saved_write_space = sk->sk_write_space; + /* Initialize saved callbacks and original proto only once, since this + * function may be called multiple times for a psock, e.g. when + * psock->progs.msg_parser is updated. + * + * Since we've not installed the new proto, psock is not yet in use and + * we can initialize it without synchronization. + */ + if (!psock->sk_proto) { + struct proto *orig = READ_ONCE(sk->sk_prot); + + psock->saved_unhash = orig->unhash; + psock->saved_close = orig->close; + psock->saved_write_space = sk->sk_write_space; + + psock->sk_proto = orig; + } - psock->sk_proto = sk->sk_prot; /* Pairs with lockless read in sk_clone_lock() */ WRITE_ONCE(sk->sk_prot, ops); } @@ -360,7 +364,13 @@ static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { sk->sk_prot->unhash = psock->saved_unhash; - tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); + if (inet_csk_has_ulp(sk)) { + tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); + } else { + sk->sk_write_space = psock->saved_write_space; + /* Pairs with lockless read in sk_clone_lock() */ + WRITE_ONCE(sk->sk_prot, psock->sk_proto); + } } static inline void sk_psock_set_state(struct sk_psock *psock, @@ -381,26 +391,6 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock, return test_bit(bit, &psock->state); } -static inline struct sk_psock *sk_psock_get_checked(struct sock *sk) -{ - struct sk_psock *psock; - - rcu_read_lock(); - psock = sk_psock(sk); - if (psock) { - if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) { - psock = ERR_PTR(-EBUSY); - goto out; - } - - if (!refcount_inc_not_zero(&psock->refcnt)) - psock = ERR_PTR(-EBUSY); - } -out: - rcu_read_unlock(); - return psock; -} - static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 895546058a20..a3f076befa4f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -335,4 +335,10 @@ static inline void inet_csk_inc_pingpong_cnt(struct sock *sk) if (icsk->icsk_ack.pingpong < U8_MAX) icsk->icsk_ack.pingpong++; } + +static inline bool inet_csk_has_ulp(struct sock *sk) +{ + return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops; +} + #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 07f947cc80e6..43fa07a36fa6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2195,21 +2195,23 @@ void tcp_update_ulp(struct sock *sk, struct proto *p, struct sk_msg; struct sk_psock; -int tcp_bpf_init(struct sock *sk); -void tcp_bpf_reinit(struct sock *sk); +#ifdef CONFIG_BPF_STREAM_PARSER +struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); +void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); +#else +static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +{ +} +#endif /* CONFIG_BPF_STREAM_PARSER */ + +#ifdef CONFIG_NET_SOCK_MSG int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, int flags); int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); -#ifdef CONFIG_NET_SOCK_MSG -void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); -#else -static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) -{ -} -#endif +#endif /* CONFIG_NET_SOCK_MSG */ /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF diff --git a/include/net/udp.h b/include/net/udp.h index e55d5f765807..a8fa6c0c6ded 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -503,4 +503,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, return segs; } +#ifdef CONFIG_BPF_STREAM_PARSER +struct sk_psock; +struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); +#endif /* BPF_STREAM_PARSER */ + #endif /* _UDP_H */ diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index b04c29270973..1ce3be63add1 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -75,13 +75,17 @@ static inline void bpf_test_probe_##call(void) \ check_trace_callback_type_##call(__bpf_trace_##template); \ } \ typedef void (*btf_trace_##call)(void *__data, proto); \ -static struct bpf_raw_event_map __used \ - __attribute__((section("__bpf_raw_tp_map"))) \ -__bpf_trace_tp_map_##call = { \ - .tp = &__tracepoint_##call, \ - .bpf_func = (void *)(btf_trace_##call)__bpf_trace_##template, \ - .num_args = COUNT_ARGS(args), \ - .writable_size = size, \ +static union { \ + struct bpf_raw_event_map event; \ + btf_trace_##call handler; \ +} __bpf_trace_tp_map_##call __used \ +__attribute__((section("__bpf_raw_tp_map"))) = { \ + .event = { \ + .tp = &__tracepoint_##call, \ + .bpf_func = __bpf_trace_##template, \ + .num_args = COUNT_ARGS(args), \ + .writable_size = size, \ + }, \ }; #define FIRST(x, ...) x diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8e98ced0963b..5d01c5c7e598 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -210,6 +210,7 @@ enum bpf_attach_type { BPF_TRACE_RAW_TP, BPF_TRACE_FENTRY, BPF_TRACE_FEXIT, + BPF_MODIFY_RETURN, __MAX_BPF_ATTACH_TYPE }; @@ -325,44 +326,46 @@ enum bpf_attach_type { #define BPF_PSEUDO_CALL 1 /* flags for BPF_MAP_UPDATE_ELEM command */ -#define BPF_ANY 0 /* create new element or update existing */ -#define BPF_NOEXIST 1 /* create new element if it didn't exist */ -#define BPF_EXIST 2 /* update existing element */ -#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ +enum { + BPF_ANY = 0, /* create new element or update existing */ + BPF_NOEXIST = 1, /* create new element if it didn't exist */ + BPF_EXIST = 2, /* update existing element */ + BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */ +}; /* flags for BPF_MAP_CREATE command */ -#define BPF_F_NO_PREALLOC (1U << 0) +enum { + BPF_F_NO_PREALLOC = (1U << 0), /* Instead of having one common LRU list in the * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list * which can scale and perform better. * Note, the LRU nodes (including free nodes) cannot be moved * across different LRU lists. */ -#define BPF_F_NO_COMMON_LRU (1U << 1) + BPF_F_NO_COMMON_LRU = (1U << 1), /* Specify numa node during map creation */ -#define BPF_F_NUMA_NODE (1U << 2) - -#define BPF_OBJ_NAME_LEN 16U + BPF_F_NUMA_NODE = (1U << 2), /* Flags for accessing BPF object from syscall side. */ -#define BPF_F_RDONLY (1U << 3) -#define BPF_F_WRONLY (1U << 4) + BPF_F_RDONLY = (1U << 3), + BPF_F_WRONLY = (1U << 4), /* Flag for stack_map, store build_id+offset instead of pointer */ -#define BPF_F_STACK_BUILD_ID (1U << 5) + BPF_F_STACK_BUILD_ID = (1U << 5), /* Zero-initialize hash function seed. This should only be used for testing. */ -#define BPF_F_ZERO_SEED (1U << 6) + BPF_F_ZERO_SEED = (1U << 6), /* Flags for accessing BPF object from program side. */ -#define BPF_F_RDONLY_PROG (1U << 7) -#define BPF_F_WRONLY_PROG (1U << 8) + BPF_F_RDONLY_PROG = (1U << 7), + BPF_F_WRONLY_PROG = (1U << 8), /* Clone map from listener for newly accepted socket */ -#define BPF_F_CLONE (1U << 9) + BPF_F_CLONE = (1U << 9), /* Enable memory-mapping BPF map */ -#define BPF_F_MMAPABLE (1U << 10) + BPF_F_MMAPABLE = (1U << 10), +}; /* Flags for BPF_PROG_QUERY. */ @@ -391,6 +394,8 @@ struct bpf_stack_build_id { }; }; +#define BPF_OBJ_NAME_LEN 16U + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -2909,6 +2914,42 @@ union bpf_attr { * of sizeof(struct perf_branch_entry). * * **-ENOENT** if architecture does not support branch records. + * + * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) + * Description + * Returns 0 on success, values for *pid* and *tgid* as seen from the current + * *namespace* will be returned in *nsdata*. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if dev and inum supplied don't match dev_t and inode number + * with nsfs of current task, or if dev conversion to dev_t lost high bits. + * + * **-ENOENT** if pidns does not exists for the current task. + * + * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct xdp_buff. + * + * This helper is similar to **bpf_perf_eventoutput**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3030,7 +3071,9 @@ union bpf_attr { FN(tcp_send_ack), \ FN(send_signal_thread), \ FN(jiffies64), \ - FN(read_branch_records), + FN(read_branch_records), \ + FN(get_ns_current_pid_tgid), \ + FN(xdp_output), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3045,72 +3088,100 @@ enum bpf_func_id { /* All flags used by eBPF helper functions, placed here. */ /* BPF_FUNC_skb_store_bytes flags. */ -#define BPF_F_RECOMPUTE_CSUM (1ULL << 0) -#define BPF_F_INVALIDATE_HASH (1ULL << 1) +enum { + BPF_F_RECOMPUTE_CSUM = (1ULL << 0), + BPF_F_INVALIDATE_HASH = (1ULL << 1), +}; /* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. * First 4 bits are for passing the header field size. */ -#define BPF_F_HDR_FIELD_MASK 0xfULL +enum { + BPF_F_HDR_FIELD_MASK = 0xfULL, +}; /* BPF_FUNC_l4_csum_replace flags. */ -#define BPF_F_PSEUDO_HDR (1ULL << 4) -#define BPF_F_MARK_MANGLED_0 (1ULL << 5) -#define BPF_F_MARK_ENFORCE (1ULL << 6) +enum { + BPF_F_PSEUDO_HDR = (1ULL << 4), + BPF_F_MARK_MANGLED_0 = (1ULL << 5), + BPF_F_MARK_ENFORCE = (1ULL << 6), +}; /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -#define BPF_F_INGRESS (1ULL << 0) +enum { + BPF_F_INGRESS = (1ULL << 0), +}; /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ -#define BPF_F_TUNINFO_IPV6 (1ULL << 0) +enum { + BPF_F_TUNINFO_IPV6 = (1ULL << 0), +}; /* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ -#define BPF_F_SKIP_FIELD_MASK 0xffULL -#define BPF_F_USER_STACK (1ULL << 8) +enum { + BPF_F_SKIP_FIELD_MASK = 0xffULL, + BPF_F_USER_STACK = (1ULL << 8), /* flags used by BPF_FUNC_get_stackid only. */ -#define BPF_F_FAST_STACK_CMP (1ULL << 9) -#define BPF_F_REUSE_STACKID (1ULL << 10) + BPF_F_FAST_STACK_CMP = (1ULL << 9), + BPF_F_REUSE_STACKID = (1ULL << 10), /* flags used by BPF_FUNC_get_stack only. */ -#define BPF_F_USER_BUILD_ID (1ULL << 11) + BPF_F_USER_BUILD_ID = (1ULL << 11), +}; /* BPF_FUNC_skb_set_tunnel_key flags. */ -#define BPF_F_ZERO_CSUM_TX (1ULL << 1) -#define BPF_F_DONT_FRAGMENT (1ULL << 2) -#define BPF_F_SEQ_NUMBER (1ULL << 3) +enum { + BPF_F_ZERO_CSUM_TX = (1ULL << 1), + BPF_F_DONT_FRAGMENT = (1ULL << 2), + BPF_F_SEQ_NUMBER = (1ULL << 3), +}; /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and * BPF_FUNC_perf_event_read_value flags. */ -#define BPF_F_INDEX_MASK 0xffffffffULL -#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +enum { + BPF_F_INDEX_MASK = 0xffffffffULL, + BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, /* BPF_FUNC_perf_event_output for sk_buff input context. */ -#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) + BPF_F_CTXLEN_MASK = (0xfffffULL << 32), +}; /* Current network namespace */ -#define BPF_F_CURRENT_NETNS (-1L) +enum { + BPF_F_CURRENT_NETNS = (-1L), +}; /* BPF_FUNC_skb_adjust_room flags. */ -#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) +enum { + BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2), + BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), + BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), +}; -#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff -#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 +enum { + BPF_ADJ_ROOM_ENCAP_L2_MASK = 0xff, + BPF_ADJ_ROOM_ENCAP_L2_SHIFT = 56, +}; -#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) -#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) -#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) -#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) #define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ BPF_ADJ_ROOM_ENCAP_L2_MASK) \ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) /* BPF_FUNC_sysctl_get_name flags. */ -#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) +enum { + BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), +}; /* BPF_FUNC_sk_storage_get flags */ -#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) +enum { + BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), +}; /* BPF_FUNC_read_branch_records flags. */ -#define BPF_F_GET_BRANCH_RECORDS_SIZE (1ULL << 0) +enum { + BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0), +}; /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { @@ -3176,6 +3247,7 @@ struct __sk_buff { __u32 wire_len; __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); + __u32 gso_size; }; struct bpf_tunnel_key { @@ -3528,13 +3600,14 @@ struct bpf_sock_ops { }; /* Definitions for bpf_sock_ops_cb_flags */ -#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) -#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) -#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) -#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) -#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently - * supported cb flags - */ +enum { + BPF_SOCK_OPS_RTO_CB_FLAG = (1<<0), + BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), + BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), + BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), +/* Mask of all currently supported cb flags */ + BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF, +}; /* List of known BPF sock_ops operators. * New entries can only be added at the end @@ -3613,8 +3686,10 @@ enum { BPF_TCP_MAX_STATES /* Leave at the end! */ }; -#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ -#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ +enum { + TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ + TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ +}; struct bpf_perf_event_value { __u64 counter; @@ -3622,12 +3697,16 @@ struct bpf_perf_event_value { __u64 running; }; -#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) -#define BPF_DEVCG_ACC_READ (1ULL << 1) -#define BPF_DEVCG_ACC_WRITE (1ULL << 2) +enum { + BPF_DEVCG_ACC_MKNOD = (1ULL << 0), + BPF_DEVCG_ACC_READ = (1ULL << 1), + BPF_DEVCG_ACC_WRITE = (1ULL << 2), +}; -#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) -#define BPF_DEVCG_DEV_CHAR (1ULL << 1) +enum { + BPF_DEVCG_DEV_BLOCK = (1ULL << 0), + BPF_DEVCG_DEV_CHAR = (1ULL << 1), +}; struct bpf_cgroup_dev_ctx { /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ @@ -3643,8 +3722,10 @@ struct bpf_raw_tracepoint_args { /* DIRECT: Skip the FIB rules and go to FIB table associated with device * OUTPUT: Do lookup from egress perspective; default is ingress */ -#define BPF_FIB_LOOKUP_DIRECT (1U << 0) -#define BPF_FIB_LOOKUP_OUTPUT (1U << 1) +enum { + BPF_FIB_LOOKUP_DIRECT = (1U << 0), + BPF_FIB_LOOKUP_OUTPUT = (1U << 1), +}; enum { BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ @@ -3716,9 +3797,11 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; -#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) -#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) -#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) +enum { + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG = (1U << 0), + BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL = (1U << 1), + BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP = (1U << 2), +}; struct bpf_flow_keys { __u16 nhoff; @@ -3784,4 +3867,8 @@ struct bpf_sockopt { __s32 retval; }; +struct bpf_pidns_info { + __u32 pid; + __u32 tgid; +}; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index c498f0fffb40..ca5cc8cdb6eb 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -320,6 +320,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_struct_ops_value *uvalue, *kvalue; const struct btf_member *member; const struct btf_type *t = st_ops->type; + struct bpf_tramp_progs *tprogs = NULL; void *udata, *kdata; int prog_fd, err = 0; void *image; @@ -343,6 +344,10 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (uvalue->state || refcount_read(&uvalue->refcnt)) return -EINVAL; + tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); + if (!tprogs) + return -ENOMEM; + uvalue = (struct bpf_struct_ops_value *)st_map->uvalue; kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue; @@ -425,10 +430,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto reset_unlock; } + tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; + tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; err = arch_prepare_bpf_trampoline(image, st_map->image + PAGE_SIZE, &st_ops->func_models[i], 0, - &prog, 1, NULL, 0, NULL); + tprogs, NULL); if (err < 0) goto reset_unlock; @@ -469,6 +476,7 @@ reset_unlock: memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); unlock: + kfree(tprogs); mutex_unlock(&st_map->lock); return err; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 787140095e58..50080add2ab9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3710,13 +3710,26 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, nr_args--; } - if (prog->expected_attach_type == BPF_TRACE_FEXIT && - arg == nr_args) { - if (!t) - /* Default prog with 5 args. 6th arg is retval. */ - return true; - /* function return type */ - t = btf_type_by_id(btf, t->type); + if (arg == nr_args) { + if (prog->expected_attach_type == BPF_TRACE_FEXIT) { + if (!t) + return true; + t = btf_type_by_id(btf, t->type); + } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { + /* For now the BPF_MODIFY_RETURN can only be attached to + * functions that return an int. + */ + if (!t) + return false; + + t = btf_type_skip_modifiers(btf, t->type, NULL); + if (!btf_type_is_int(t)) { + bpf_log(log, + "ret type %s not allowed for fmod_ret\n", + btf_kind_str[BTF_INFO_KIND(t->info)]); + return false; + } + } } else if (arg >= nr_args) { bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg + 1); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 973a20d49749..914f3463aa41 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -97,7 +97,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); - INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode); + INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); return fp; } @@ -523,22 +523,22 @@ int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; -static __always_inline void -bpf_get_prog_addr_region(const struct bpf_prog *prog, - unsigned long *symbol_start, - unsigned long *symbol_end) +static void +bpf_prog_ksym_set_addr(struct bpf_prog *prog) { const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog); unsigned long addr = (unsigned long)hdr; WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); - *symbol_start = addr; - *symbol_end = addr + hdr->pages * PAGE_SIZE; + prog->aux->ksym.start = (unsigned long) prog->bpf_func; + prog->aux->ksym.end = addr + hdr->pages * PAGE_SIZE; } -void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) +static void +bpf_prog_ksym_set_name(struct bpf_prog *prog) { + char *sym = prog->aux->ksym.name; const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; const char *func_name; @@ -572,36 +572,27 @@ void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) *sym = 0; } -static __always_inline unsigned long -bpf_get_prog_addr_start(struct latch_tree_node *n) +static unsigned long bpf_get_ksym_start(struct latch_tree_node *n) { - unsigned long symbol_start, symbol_end; - const struct bpf_prog_aux *aux; - - aux = container_of(n, struct bpf_prog_aux, ksym_tnode); - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); - - return symbol_start; + return container_of(n, struct bpf_ksym, tnode)->start; } static __always_inline bool bpf_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) { - return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b); + return bpf_get_ksym_start(a) < bpf_get_ksym_start(b); } static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) { unsigned long val = (unsigned long)key; - unsigned long symbol_start, symbol_end; - const struct bpf_prog_aux *aux; + const struct bpf_ksym *ksym; - aux = container_of(n, struct bpf_prog_aux, ksym_tnode); - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); + ksym = container_of(n, struct bpf_ksym, tnode); - if (val < symbol_start) + if (val < ksym->start) return -1; - if (val >= symbol_end) + if (val >= ksym->end) return 1; return 0; @@ -616,20 +607,29 @@ static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; -static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux) +void bpf_ksym_add(struct bpf_ksym *ksym) { - WARN_ON_ONCE(!list_empty(&aux->ksym_lnode)); - list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms); - latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops); + spin_lock_bh(&bpf_lock); + WARN_ON_ONCE(!list_empty(&ksym->lnode)); + list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms); + latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops); + spin_unlock_bh(&bpf_lock); } -static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux) +static void __bpf_ksym_del(struct bpf_ksym *ksym) { - if (list_empty(&aux->ksym_lnode)) + if (list_empty(&ksym->lnode)) return; - latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops); - list_del_rcu(&aux->ksym_lnode); + latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops); + list_del_rcu(&ksym->lnode); +} + +void bpf_ksym_del(struct bpf_ksym *ksym) +{ + spin_lock_bh(&bpf_lock); + __bpf_ksym_del(ksym); + spin_unlock_bh(&bpf_lock); } static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) @@ -639,8 +639,8 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { - return list_empty(&fp->aux->ksym_lnode) || - fp->aux->ksym_lnode.prev == LIST_POISON2; + return list_empty(&fp->aux->ksym.lnode) || + fp->aux->ksym.lnode.prev == LIST_POISON2; } void bpf_prog_kallsyms_add(struct bpf_prog *fp) @@ -649,9 +649,11 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp) !capable(CAP_SYS_ADMIN)) return; - spin_lock_bh(&bpf_lock); - bpf_prog_ksym_node_add(fp->aux); - spin_unlock_bh(&bpf_lock); + bpf_prog_ksym_set_addr(fp); + bpf_prog_ksym_set_name(fp); + fp->aux->ksym.prog = true; + + bpf_ksym_add(&fp->aux->ksym); } void bpf_prog_kallsyms_del(struct bpf_prog *fp) @@ -659,33 +661,30 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp) if (!bpf_prog_kallsyms_candidate(fp)) return; - spin_lock_bh(&bpf_lock); - bpf_prog_ksym_node_del(fp->aux); - spin_unlock_bh(&bpf_lock); + bpf_ksym_del(&fp->aux->ksym); } -static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr) +static struct bpf_ksym *bpf_ksym_find(unsigned long addr) { struct latch_tree_node *n; n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops); - return n ? - container_of(n, struct bpf_prog_aux, ksym_tnode)->prog : - NULL; + return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { - unsigned long symbol_start, symbol_end; - struct bpf_prog *prog; + struct bpf_ksym *ksym; char *ret = NULL; rcu_read_lock(); - prog = bpf_prog_kallsyms_find(addr); - if (prog) { - bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end); - bpf_get_prog_name(prog, sym); + ksym = bpf_ksym_find(addr); + if (ksym) { + unsigned long symbol_start = ksym->start; + unsigned long symbol_end = ksym->end; + + strncpy(sym, ksym->name, KSYM_NAME_LEN); ret = sym; if (size) @@ -703,19 +702,28 @@ bool is_bpf_text_address(unsigned long addr) bool ret; rcu_read_lock(); - ret = bpf_prog_kallsyms_find(addr) != NULL; + ret = bpf_ksym_find(addr) != NULL; rcu_read_unlock(); return ret; } +static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) +{ + struct bpf_ksym *ksym = bpf_ksym_find(addr); + + return ksym && ksym->prog ? + container_of(ksym, struct bpf_prog_aux, ksym)->prog : + NULL; +} + const struct exception_table_entry *search_bpf_extables(unsigned long addr) { const struct exception_table_entry *e = NULL; struct bpf_prog *prog; rcu_read_lock(); - prog = bpf_prog_kallsyms_find(addr); + prog = bpf_prog_ksym_find(addr); if (!prog) goto out; if (!prog->aux->num_exentries) @@ -730,7 +738,7 @@ out: int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { - struct bpf_prog_aux *aux; + struct bpf_ksym *ksym; unsigned int it = 0; int ret = -ERANGE; @@ -738,13 +746,13 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, return ret; rcu_read_lock(); - list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) { + list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) { if (it++ != symnum) continue; - bpf_get_prog_name(aux->prog, sym); + strncpy(sym, ksym->name, KSYM_NAME_LEN); - *value = (unsigned long)aux->prog->bpf_func; + *value = ksym->start; *type = BPF_SYM_ELF_TYPE; ret = 0; @@ -2149,6 +2157,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; +const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index b3e5b214fed8..2444bd15cc2d 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -113,7 +113,7 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) noff = 0; } else { old = d->image + d->image_off; - noff = d->image_off ^ (BPF_IMAGE_SIZE / 2); + noff = d->image_off ^ (PAGE_SIZE / 2); } new = d->num_progs ? d->image + noff : NULL; @@ -140,9 +140,10 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, mutex_lock(&d->mutex); if (!d->image) { - d->image = bpf_image_alloc(); + d->image = bpf_jit_alloc_exec_page(); if (!d->image) goto out; + bpf_image_ksym_add(d->image, &d->ksym); } prev_num_progs = d->num_progs; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index d8b7b110a1c5..01878db15eaf 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -12,6 +12,8 @@ #include <linux/filter.h> #include <linux/ctype.h> #include <linux/jiffies.h> +#include <linux/pid_namespace.h> +#include <linux/proc_ns.h> #include "../../lib/kstrtox.h" @@ -499,3 +501,46 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg4_type = ARG_PTR_TO_LONG, }; #endif + +BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino, + struct bpf_pidns_info *, nsdata, u32, size) +{ + struct task_struct *task = current; + struct pid_namespace *pidns; + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_pidns_info))) + goto clear; + + if (unlikely((u64)(dev_t)dev != dev)) + goto clear; + + if (unlikely(!task)) + goto clear; + + pidns = task_active_pid_ns(task); + if (unlikely(!pidns)) { + err = -ENOENT; + goto clear; + } + + if (!ns_match(&pidns->ns, (dev_t)dev, ino)) + goto clear; + + nsdata->pid = task_pid_nr_ns(task, pidns); + nsdata->tgid = task_tgid_nr_ns(task, pidns); + return 0; +clear: + memset((void *)nsdata, 0, (size_t) size); + return err; +} + +const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto = { + .func = bpf_get_ns_current_pid_tgid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 5e40e7fccc21..95087d9f4ed3 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -25,6 +25,7 @@ enum bpf_type { BPF_TYPE_UNSPEC = 0, BPF_TYPE_PROG, BPF_TYPE_MAP, + BPF_TYPE_LINK, }; static void *bpf_any_get(void *raw, enum bpf_type type) @@ -36,6 +37,9 @@ static void *bpf_any_get(void *raw, enum bpf_type type) case BPF_TYPE_MAP: bpf_map_inc_with_uref(raw); break; + case BPF_TYPE_LINK: + bpf_link_inc(raw); + break; default: WARN_ON_ONCE(1); break; @@ -53,6 +57,9 @@ static void bpf_any_put(void *raw, enum bpf_type type) case BPF_TYPE_MAP: bpf_map_put_with_uref(raw); break; + case BPF_TYPE_LINK: + bpf_link_put(raw); + break; default: WARN_ON_ONCE(1); break; @@ -63,20 +70,32 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) { void *raw; - *type = BPF_TYPE_MAP; raw = bpf_map_get_with_uref(ufd); - if (IS_ERR(raw)) { + if (!IS_ERR(raw)) { + *type = BPF_TYPE_MAP; + return raw; + } + + raw = bpf_prog_get(ufd); + if (!IS_ERR(raw)) { *type = BPF_TYPE_PROG; - raw = bpf_prog_get(ufd); + return raw; } - return raw; + raw = bpf_link_get_from_fd(ufd); + if (!IS_ERR(raw)) { + *type = BPF_TYPE_LINK; + return raw; + } + + return ERR_PTR(-EINVAL); } static const struct inode_operations bpf_dir_iops; static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; +static const struct inode_operations bpf_link_iops = { }; static struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, @@ -114,6 +133,8 @@ static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) *type = BPF_TYPE_PROG; else if (inode->i_op == &bpf_map_iops) *type = BPF_TYPE_MAP; + else if (inode->i_op == &bpf_link_iops) + *type = BPF_TYPE_LINK; else return -EACCES; @@ -335,6 +356,12 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) &bpffs_map_fops : &bpffs_obj_fops); } +static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg) +{ + return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops, + &bpffs_obj_fops); +} + static struct dentry * bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) { @@ -411,6 +438,9 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, case BPF_TYPE_MAP: ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw); break; + case BPF_TYPE_LINK: + ret = vfs_mkobj(dentry, mode, bpf_mklink, raw); + break; default: ret = -EPERM; } @@ -487,6 +517,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); + else if (type == BPF_TYPE_LINK) + ret = bpf_link_new_fd(raw); else return -ENOENT; @@ -504,6 +536,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type if (inode->i_op == &bpf_map_iops) return ERR_PTR(-EINVAL); + if (inode->i_op == &bpf_link_iops) + return ERR_PTR(-EINVAL); if (inode->i_op != &bpf_prog_iops) return ERR_PTR(-EACCES); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c536c65256ad..85567a6ea5f9 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2173,84 +2173,274 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } -static int bpf_tracing_prog_release(struct inode *inode, struct file *filp) +struct bpf_link { + atomic64_t refcnt; + const struct bpf_link_ops *ops; + struct bpf_prog *prog; + struct work_struct work; +}; + +void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, + struct bpf_prog *prog) { - struct bpf_prog *prog = filp->private_data; + atomic64_set(&link->refcnt, 1); + link->ops = ops; + link->prog = prog; +} - WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); - bpf_prog_put(prog); +/* Clean up bpf_link and corresponding anon_inode file and FD. After + * anon_inode is created, bpf_link can't be just kfree()'d due to deferred + * anon_inode's release() call. This helper manages marking bpf_link as + * defunct, releases anon_inode file and puts reserved FD. + */ +static void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, + int link_fd) +{ + link->prog = NULL; + fput(link_file); + put_unused_fd(link_fd); +} + +void bpf_link_inc(struct bpf_link *link) +{ + atomic64_inc(&link->refcnt); +} + +/* bpf_link_free is guaranteed to be called from process context */ +static void bpf_link_free(struct bpf_link *link) +{ + if (link->prog) { + /* detach BPF program, clean up used resources */ + link->ops->release(link); + bpf_prog_put(link->prog); + } + /* free bpf_link and its containing memory */ + link->ops->dealloc(link); +} + +static void bpf_link_put_deferred(struct work_struct *work) +{ + struct bpf_link *link = container_of(work, struct bpf_link, work); + + bpf_link_free(link); +} + +/* bpf_link_put can be called from atomic context, but ensures that resources + * are freed from process context + */ +void bpf_link_put(struct bpf_link *link) +{ + if (!atomic64_dec_and_test(&link->refcnt)) + return; + + if (in_atomic()) { + INIT_WORK(&link->work, bpf_link_put_deferred); + schedule_work(&link->work); + } else { + bpf_link_free(link); + } +} + +static int bpf_link_release(struct inode *inode, struct file *filp) +{ + struct bpf_link *link = filp->private_data; + + bpf_link_put(link); return 0; } -static const struct file_operations bpf_tracing_prog_fops = { - .release = bpf_tracing_prog_release, +#ifdef CONFIG_PROC_FS +static const struct bpf_link_ops bpf_raw_tp_lops; +static const struct bpf_link_ops bpf_tracing_link_lops; +static const struct bpf_link_ops bpf_xdp_link_lops; + +static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) +{ + const struct bpf_link *link = filp->private_data; + const struct bpf_prog *prog = link->prog; + char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; + const char *link_type; + + if (link->ops == &bpf_raw_tp_lops) + link_type = "raw_tracepoint"; + else if (link->ops == &bpf_tracing_link_lops) + link_type = "tracing"; + else + link_type = "unknown"; + + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); + seq_printf(m, + "link_type:\t%s\n" + "prog_tag:\t%s\n" + "prog_id:\t%u\n", + link_type, + prog_tag, + prog->aux->id); +} +#endif + +const struct file_operations bpf_link_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = bpf_link_show_fdinfo, +#endif + .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; +int bpf_link_new_fd(struct bpf_link *link) +{ + return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); +} + +/* Similar to bpf_link_new_fd, create anon_inode for given bpf_link, but + * instead of immediately installing fd in fdtable, just reserve it and + * return. Caller then need to either install it with fd_install(fd, file) or + * release with put_unused_fd(fd). + * This is useful for cases when bpf_link attachment/detachment are + * complicated and expensive operations and should be delayed until all the fd + * reservation and anon_inode creation succeeds. + */ +struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd) +{ + struct file *file; + int fd; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return ERR_PTR(fd); + + file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC); + if (IS_ERR(file)) { + put_unused_fd(fd); + return file; + } + + *reserved_fd = fd; + return file; +} + +struct bpf_link *bpf_link_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_link *link; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_link_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + link = f.file->private_data; + bpf_link_inc(link); + fdput(f); + + return link; +} + +struct bpf_tracing_link { + struct bpf_link link; +}; + +static void bpf_tracing_link_release(struct bpf_link *link) +{ + WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog)); +} + +static void bpf_tracing_link_dealloc(struct bpf_link *link) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link); + + kfree(tr_link); +} + +static const struct bpf_link_ops bpf_tracing_link_lops = { + .release = bpf_tracing_link_release, + .dealloc = bpf_tracing_link_dealloc, +}; + static int bpf_tracing_prog_attach(struct bpf_prog *prog) { - int tr_fd, err; + struct bpf_tracing_link *link; + struct file *link_file; + int link_fd, err; if (prog->expected_attach_type != BPF_TRACE_FENTRY && prog->expected_attach_type != BPF_TRACE_FEXIT && + prog->expected_attach_type != BPF_MODIFY_RETURN && prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; } - err = bpf_trampoline_link_prog(prog); - if (err) + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_prog; + } + bpf_link_init(&link->link, &bpf_tracing_link_lops, prog); + + link_file = bpf_link_new_file(&link->link, &link_fd); + if (IS_ERR(link_file)) { + kfree(link); + err = PTR_ERR(link_file); goto out_put_prog; + } - tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops, - prog, O_CLOEXEC); - if (tr_fd < 0) { - WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); - err = tr_fd; + err = bpf_trampoline_link_prog(prog); + if (err) { + bpf_link_cleanup(&link->link, link_file, link_fd); goto out_put_prog; } - return tr_fd; + + fd_install(link_fd, link_file); + return link_fd; out_put_prog: bpf_prog_put(prog); return err; } -struct bpf_raw_tracepoint { +struct bpf_raw_tp_link { + struct bpf_link link; struct bpf_raw_event_map *btp; - struct bpf_prog *prog; }; -static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp) +static void bpf_raw_tp_link_release(struct bpf_link *link) { - struct bpf_raw_tracepoint *raw_tp = filp->private_data; + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); - if (raw_tp->prog) { - bpf_probe_unregister(raw_tp->btp, raw_tp->prog); - bpf_prog_put(raw_tp->prog); - } + bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog); bpf_put_raw_tracepoint(raw_tp->btp); +} + +static void bpf_raw_tp_link_dealloc(struct bpf_link *link) +{ + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); + kfree(raw_tp); - return 0; } -static const struct file_operations bpf_raw_tp_fops = { - .release = bpf_raw_tracepoint_release, - .read = bpf_dummy_read, - .write = bpf_dummy_write, +static const struct bpf_link_ops bpf_raw_tp_lops = { + .release = bpf_raw_tp_link_release, + .dealloc = bpf_raw_tp_link_dealloc, }; #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { - struct bpf_raw_tracepoint *raw_tp; + struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; + struct file *link_file; struct bpf_prog *prog; const char *tp_name; char buf[128]; - int tp_fd, err; + int link_fd, err; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; @@ -2297,29 +2487,30 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) goto out_put_prog; } - raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER); - if (!raw_tp) { + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { err = -ENOMEM; goto out_put_btp; } - raw_tp->btp = btp; - raw_tp->prog = prog; + bpf_link_init(&link->link, &bpf_raw_tp_lops, prog); + link->btp = btp; - err = bpf_probe_register(raw_tp->btp, prog); - if (err) - goto out_free_tp; + link_file = bpf_link_new_file(&link->link, &link_fd); + if (IS_ERR(link_file)) { + kfree(link); + err = PTR_ERR(link_file); + goto out_put_btp; + } - tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp, - O_CLOEXEC); - if (tp_fd < 0) { - bpf_probe_unregister(raw_tp->btp, prog); - err = tp_fd; - goto out_free_tp; + err = bpf_probe_register(link->btp, prog); + if (err) { + bpf_link_cleanup(&link->link, link_file, link_fd); + goto out_put_btp; } - return tp_fd; -out_free_tp: - kfree(raw_tp); + fd_install(link_fd, link_file); + return link_fd; + out_put_btp: bpf_put_raw_tracepoint(btp); out_put_prog: @@ -3266,15 +3457,21 @@ static int bpf_task_fd_query(const union bpf_attr *attr, if (err) goto out; - if (file->f_op == &bpf_raw_tp_fops) { - struct bpf_raw_tracepoint *raw_tp = file->private_data; - struct bpf_raw_event_map *btp = raw_tp->btp; + if (file->f_op == &bpf_link_fops) { + struct bpf_link *link = file->private_data; - err = bpf_task_fd_query_copy(attr, uattr, - raw_tp->prog->aux->id, - BPF_FD_TYPE_RAW_TRACEPOINT, - btp->tp->name, 0, 0); - goto put_file; + if (link->ops == &bpf_raw_tp_lops) { + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); + struct bpf_raw_event_map *btp = raw_tp->btp; + + err = bpf_task_fd_query_copy(attr, uattr, + raw_tp->link.prog->aux->id, + BPF_FD_TYPE_RAW_TRACEPOINT, + btp->tp->name, 0, 0); + goto put_file; + } + goto out_not_supp; } event = perf_get_event(file); @@ -3294,6 +3491,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, goto put_file; } +out_not_supp: err = -ENOTSUPP; put_file: fput(file); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 704fa787fec0..f30bca2a4d01 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -5,6 +5,7 @@ #include <linux/filter.h> #include <linux/ftrace.h> #include <linux/rbtree_latch.h> +#include <linux/perf_event.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -17,12 +18,11 @@ const struct bpf_prog_ops bpf_extension_prog_ops = { #define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS) static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; -static struct latch_tree_root image_tree __cacheline_aligned; -/* serializes access to trampoline_table and image_tree */ +/* serializes access to trampoline_table */ static DEFINE_MUTEX(trampoline_mutex); -static void *bpf_jit_alloc_exec_page(void) +void *bpf_jit_alloc_exec_page(void) { void *image; @@ -38,62 +38,28 @@ static void *bpf_jit_alloc_exec_page(void) return image; } -static __always_inline bool image_tree_less(struct latch_tree_node *a, - struct latch_tree_node *b) +void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym) { - struct bpf_image *ia = container_of(a, struct bpf_image, tnode); - struct bpf_image *ib = container_of(b, struct bpf_image, tnode); - - return ia < ib; -} - -static __always_inline int image_tree_comp(void *addr, struct latch_tree_node *n) -{ - void *image = container_of(n, struct bpf_image, tnode); - - if (addr < image) - return -1; - if (addr >= image + PAGE_SIZE) - return 1; - - return 0; -} - -static const struct latch_tree_ops image_tree_ops = { - .less = image_tree_less, - .comp = image_tree_comp, -}; - -static void *__bpf_image_alloc(bool lock) -{ - struct bpf_image *image; - - image = bpf_jit_alloc_exec_page(); - if (!image) - return NULL; - - if (lock) - mutex_lock(&trampoline_mutex); - latch_tree_insert(&image->tnode, &image_tree, &image_tree_ops); - if (lock) - mutex_unlock(&trampoline_mutex); - return image->data; + ksym->start = (unsigned long) data; + ksym->end = ksym->start + PAGE_SIZE; + bpf_ksym_add(ksym); + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, + PAGE_SIZE, false, ksym->name); } -void *bpf_image_alloc(void) +void bpf_image_ksym_del(struct bpf_ksym *ksym) { - return __bpf_image_alloc(true); + bpf_ksym_del(ksym); + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, + PAGE_SIZE, true, ksym->name); } -bool is_bpf_image_address(unsigned long addr) +static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr) { - bool ret; - - rcu_read_lock(); - ret = latch_tree_find((void *) addr, &image_tree, &image_tree_ops) != NULL; - rcu_read_unlock(); + struct bpf_ksym *ksym = &tr->ksym; - return ret; + snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key); + bpf_image_ksym_add(tr->image, ksym); } struct bpf_trampoline *bpf_trampoline_lookup(u64 key) @@ -116,7 +82,7 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) goto out; /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ - image = __bpf_image_alloc(false); + image = bpf_jit_alloc_exec_page(); if (!image) { kfree(tr); tr = NULL; @@ -131,6 +97,8 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) for (i = 0; i < BPF_TRAMP_MAX; i++) INIT_HLIST_HEAD(&tr->progs_hlist[i]); tr->image = image; + INIT_LIST_HEAD_RCU(&tr->ksym.lnode); + bpf_trampoline_ksym_add(tr); out: mutex_unlock(&trampoline_mutex); return tr; @@ -190,40 +158,50 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) return ret; } -/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 - * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 - */ -#define BPF_MAX_TRAMP_PROGS 40 +static struct bpf_tramp_progs * +bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total) +{ + const struct bpf_prog_aux *aux; + struct bpf_tramp_progs *tprogs; + struct bpf_prog **progs; + int kind; + + *total = 0; + tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); + if (!tprogs) + return ERR_PTR(-ENOMEM); + + for (kind = 0; kind < BPF_TRAMP_MAX; kind++) { + tprogs[kind].nr_progs = tr->progs_cnt[kind]; + *total += tr->progs_cnt[kind]; + progs = tprogs[kind].progs; + + hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) + *progs++ = aux->prog; + } + return tprogs; +} static int bpf_trampoline_update(struct bpf_trampoline *tr) { - void *old_image = tr->image + ((tr->selector + 1) & 1) * BPF_IMAGE_SIZE/2; - void *new_image = tr->image + (tr->selector & 1) * BPF_IMAGE_SIZE/2; - struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS]; - int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY]; - int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT]; - struct bpf_prog **progs, **fentry, **fexit; + void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2; + void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2; + struct bpf_tramp_progs *tprogs; u32 flags = BPF_TRAMP_F_RESTORE_REGS; - struct bpf_prog_aux *aux; - int err; + int err, total; + + tprogs = bpf_trampoline_get_progs(tr, &total); + if (IS_ERR(tprogs)) + return PTR_ERR(tprogs); - if (fentry_cnt + fexit_cnt == 0) { + if (total == 0) { err = unregister_fentry(tr, old_image); tr->selector = 0; goto out; } - /* populate fentry progs */ - fentry = progs = progs_to_run; - hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FENTRY], tramp_hlist) - *progs++ = aux->prog; - - /* populate fexit progs */ - fexit = progs; - hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FEXIT], tramp_hlist) - *progs++ = aux->prog; - - if (fexit_cnt) + if (tprogs[BPF_TRAMP_FEXIT].nr_progs || + tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; /* Though the second half of trampoline page is unused a task could be @@ -232,12 +210,11 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) * preempted task. Hence wait for tasks to voluntarily schedule or go * to userspace. */ + synchronize_rcu_tasks(); - err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2, - &tr->func.model, flags, - fentry, fentry_cnt, - fexit, fexit_cnt, + err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2, + &tr->func.model, flags, tprogs, tr->func.addr); if (err < 0) goto out; @@ -252,6 +229,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) goto out; tr->selector++; out: + kfree(tprogs); return err; } @@ -260,6 +238,8 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) switch (t) { case BPF_TRACE_FENTRY: return BPF_TRAMP_FENTRY; + case BPF_MODIFY_RETURN: + return BPF_TRAMP_MODIFY_RETURN; case BPF_TRACE_FEXIT: return BPF_TRAMP_FEXIT; default: @@ -344,8 +324,6 @@ out: void bpf_trampoline_put(struct bpf_trampoline *tr) { - struct bpf_image *image; - if (!tr) return; mutex_lock(&trampoline_mutex); @@ -356,11 +334,10 @@ void bpf_trampoline_put(struct bpf_trampoline *tr) goto out; if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) goto out; - image = container_of(tr->image, struct bpf_image, data); - latch_tree_erase(&image->tnode, &image_tree, &image_tree_ops); + bpf_image_ksym_del(&tr->ksym); /* wait for tasks to get out of trampoline before freeing it */ synchronize_rcu_tasks(); - bpf_jit_free_exec(image); + bpf_jit_free_exec(tr->image); hlist_del(&tr->hlist); kfree(tr); out: @@ -375,6 +352,7 @@ out: * call __bpf_prog_exit */ u64 notrace __bpf_prog_enter(void) + __acquires(RCU) { u64 start = 0; @@ -386,6 +364,7 @@ u64 notrace __bpf_prog_enter(void) } void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) + __releases(RCU) { struct bpf_prog_stats *stats; @@ -409,8 +388,7 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) int __weak arch_prepare_bpf_trampoline(void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_prog **fentry_progs, int fentry_cnt, - struct bpf_prog **fexit_progs, int fexit_cnt, + struct bpf_tramp_progs *tprogs, void *orig_call) { return -ENOTSUPP; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 289383edfc8c..745f3cfdf3b2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -19,6 +19,7 @@ #include <linux/sort.h> #include <linux/perf_event.h> #include <linux/ctype.h> +#include <linux/error-injection.h> #include "disasm.h" @@ -3649,7 +3650,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_perf_event_read && func_id != BPF_FUNC_perf_event_output && func_id != BPF_FUNC_skb_output && - func_id != BPF_FUNC_perf_event_read_value) + func_id != BPF_FUNC_perf_event_read_value && + func_id != BPF_FUNC_xdp_output) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -3739,6 +3741,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_perf_event_output: case BPF_FUNC_perf_event_read_value: case BPF_FUNC_skb_output: + case BPF_FUNC_xdp_output: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; @@ -9800,6 +9803,26 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return 0; } +#define SECURITY_PREFIX "security_" + +static int check_attach_modify_return(struct bpf_verifier_env *env) +{ + struct bpf_prog *prog = env->prog; + unsigned long addr = (unsigned long) prog->aux->trampoline->func.addr; + + /* This is expected to be cleaned up in the future with the KRSI effort + * introducing the LSM_HOOK macro for cleaning up lsm_hooks.h. + */ + if (within_error_injection_list(addr) || + !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name, + sizeof(SECURITY_PREFIX) - 1)) + return 0; + + verbose(env, "fmod_ret attach_btf_id %u (%s) is not modifiable\n", + prog->aux->attach_btf_id, prog->aux->attach_func_name); + + return -EINVAL; +} static int check_attach_btf_id(struct bpf_verifier_env *env) { @@ -9950,6 +9973,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (!prog_extension) return -EINVAL; /* fallthrough */ + case BPF_MODIFY_RETURN: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: if (!btf_type_is_func(t)) { @@ -9999,6 +10023,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) } tr->func.addr = (void *)addr; prog->aux->trampoline = tr; + + if (prog->expected_attach_type == BPF_MODIFY_RETURN) + ret = check_attach_modify_return(env); out: mutex_unlock(&tr->mutex); if (ret) diff --git a/kernel/events/core.c b/kernel/events/core.c index bbdfac0182f4..9b89ef176247 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8255,23 +8255,22 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog, enum perf_bpf_event_type type) { bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD; - char sym[KSYM_NAME_LEN]; int i; if (prog->aux->func_cnt == 0) { - bpf_get_prog_name(prog, sym); perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, (u64)(unsigned long)prog->bpf_func, - prog->jited_len, unregister, sym); + prog->jited_len, unregister, + prog->aux->ksym.name); } else { for (i = 0; i < prog->aux->func_cnt; i++) { struct bpf_prog *subprog = prog->aux->func[i]; - bpf_get_prog_name(subprog, sym); perf_event_ksymbol( PERF_RECORD_KSYMBOL_TYPE_BPF, (u64)(unsigned long)subprog->bpf_func, - subprog->jited_len, unregister, sym); + subprog->jited_len, unregister, + prog->aux->ksym.name); } } } diff --git a/kernel/extable.c b/kernel/extable.c index a0024f27d3a1..7681f87e89dd 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -149,8 +149,6 @@ int kernel_text_address(unsigned long addr) goto out; if (is_bpf_text_address(addr)) goto out; - if (is_bpf_image_address(addr)) - goto out; ret = 0; out: if (no_rcu) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 07764c761073..e619eedb5919 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -843,6 +843,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_send_signal_thread_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; + case BPF_FUNC_get_ns_current_pid_tgid: + return &bpf_get_ns_current_pid_tgid_proto; default: return NULL; } @@ -1143,6 +1145,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { }; extern const struct bpf_func_proto bpf_skb_output_proto; +extern const struct bpf_func_proto bpf_xdp_output_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) @@ -1218,6 +1221,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #ifdef CONFIG_NET case BPF_FUNC_skb_output: return &bpf_skb_output_proto; + case BPF_FUNC_xdp_output: + return &bpf_xdp_output_proto; #endif default: return raw_tp_prog_func_proto(func_id, prog); @@ -1252,6 +1257,13 @@ static bool tracing_prog_is_valid_access(int off, int size, return btf_ctx_access(off, size, type, prog, info); } +int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_prog_is_valid_access, @@ -1266,6 +1278,7 @@ const struct bpf_verifier_ops tracing_verifier_ops = { }; const struct bpf_prog_ops tracing_prog_ops = { + .test_run = bpf_prog_test_run_tracing, }; static bool raw_tp_writable_prog_is_valid_access(int off, int size, diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 562443f94133..4c921f5154e0 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -10,6 +10,7 @@ #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <net/tcp.h> +#include <linux/error-injection.h> #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h> @@ -143,6 +144,14 @@ int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f) return a + (long)b + c + d + (long)e + f; } +int noinline bpf_modify_return_test(int a, int *b) +{ + *b += 1; + return a + *b; +} + +ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); + static void *bpf_test_init(const union bpf_attr *kattr, u32 size, u32 headroom, u32 tailroom) { @@ -160,18 +169,48 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size, kfree(data); return ERR_PTR(-EFAULT); } - if (bpf_fentry_test1(1) != 2 || - bpf_fentry_test2(2, 3) != 5 || - bpf_fentry_test3(4, 5, 6) != 15 || - bpf_fentry_test4((void *)7, 8, 9, 10) != 34 || - bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 || - bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111) { - kfree(data); - return ERR_PTR(-EFAULT); - } + return data; } +int bpf_prog_test_run_tracing(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + u16 side_effect = 0, ret = 0; + int b = 2, err = -EFAULT; + u32 retval = 0; + + switch (prog->expected_attach_type) { + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + if (bpf_fentry_test1(1) != 2 || + bpf_fentry_test2(2, 3) != 5 || + bpf_fentry_test3(4, 5, 6) != 15 || + bpf_fentry_test4((void *)7, 8, 9, 10) != 34 || + bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 || + bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111) + goto out; + break; + case BPF_MODIFY_RETURN: + ret = bpf_modify_return_test(1, &b); + if (b != 2) + side_effect = 1; + break; + default: + goto out; + } + + retval = ((u32)side_effect << 16) | ret; + if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) + goto out; + + err = 0; +out: + trace_bpf_test_finish(&err); + return err; +} + static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) { void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in); @@ -277,6 +316,12 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) /* gso_segs is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_segs), + offsetof(struct __sk_buff, gso_size))) + return -EINVAL; + + /* gso_size is allowed */ + + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_size), sizeof(struct __sk_buff))) return -EINVAL; @@ -297,6 +342,7 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) if (__skb->gso_segs > GSO_MAX_SEGS) return -EINVAL; skb_shinfo(skb)->gso_segs = __skb->gso_segs; + skb_shinfo(skb)->gso_size = __skb->gso_size; return 0; } diff --git a/net/core/filter.c b/net/core/filter.c index 4a08c9fb2be7..96350a743539 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4061,7 +4061,8 @@ BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; - if (unlikely(xdp_size > (unsigned long)(xdp->data_end - xdp->data))) + if (unlikely(!xdp || + xdp_size > (unsigned long)(xdp->data_end - xdp->data))) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, xdp->data, @@ -4079,6 +4080,19 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +static int bpf_xdp_output_btf_ids[5]; +const struct bpf_func_proto bpf_xdp_output_proto = { + .func = bpf_xdp_event_output, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_xdp_output_btf_ids, +}; + BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { return skb->sk ? sock_gen_cookie(skb->sk) : 0; @@ -7139,6 +7153,27 @@ static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, + struct bpf_insn *insn) +{ + /* si->dst_reg = skb_shinfo(SKB); */ +#ifdef NET_SKBUFF_DATA_USES_OFFSET + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, end)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, head)); + *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); +#else + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, end)); +#endif + + return insn; +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, @@ -7461,26 +7496,21 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, gso_segs): - /* si->dst_reg = skb_shinfo(SKB); */ -#ifdef NET_SKBUFF_DATA_USES_OFFSET - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - BPF_REG_AX, si->src_reg, - offsetof(struct sk_buff, end)); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, - offsetof(struct sk_buff, head)); - *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); -#else - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - si->dst_reg, si->src_reg, - offsetof(struct sk_buff, end)); -#endif + insn = bpf_convert_shinfo_access(si, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_segs, 2, target_size)); break; + case offsetof(struct __sk_buff, gso_size): + insn = bpf_convert_shinfo_access(si, insn); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), + si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + gso_size, 2, + target_size)); + break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); @@ -8829,10 +8859,9 @@ const struct bpf_prog_ops sk_reuseport_prog_ops = { }; #endif /* CONFIG_INET */ -DEFINE_BPF_DISPATCHER(bpf_dispatcher_xdp) +DEFINE_BPF_DISPATCHER(xdp) void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) { - bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(bpf_dispatcher_xdp), - prev_prog, prog); + bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 2e0f465295c3..a7075b3b4489 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/jhash.h> #include <linux/sock_diag.h> +#include <net/udp.h> struct bpf_stab { struct bpf_map map; @@ -141,12 +142,58 @@ static void sock_map_unref(struct sock *sk, void *link_raw) } } +static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock) +{ + struct proto *prot; + + sock_owned_by_me(sk); + + switch (sk->sk_type) { + case SOCK_STREAM: + prot = tcp_bpf_get_proto(sk, psock); + break; + + case SOCK_DGRAM: + prot = udp_bpf_get_proto(sk, psock); + break; + + default: + return -EINVAL; + } + + if (IS_ERR(prot)) + return PTR_ERR(prot); + + sk_psock_update_proto(sk, psock, prot); + return 0; +} + +static struct sk_psock *sock_map_psock_get_checked(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock) { + if (sk->sk_prot->close != sock_map_close) { + psock = ERR_PTR(-EBUSY); + goto out; + } + + if (!refcount_inc_not_zero(&psock->refcnt)) + psock = ERR_PTR(-EBUSY); + } +out: + rcu_read_unlock(); + return psock; +} + static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, struct sock *sk) { struct bpf_prog *msg_parser, *skb_parser, *skb_verdict; - bool skb_progs, sk_psock_is_new = false; struct sk_psock *psock; + bool skb_progs; int ret; skb_verdict = READ_ONCE(progs->skb_verdict); @@ -172,7 +219,7 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, } } - psock = sk_psock_get_checked(sk); + psock = sock_map_psock_get_checked(sk); if (IS_ERR(psock)) { ret = PTR_ERR(psock); goto out_progs; @@ -191,18 +238,14 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, ret = -ENOMEM; goto out_progs; } - sk_psock_is_new = true; } if (msg_parser) psock_set_prog(&psock->progs.msg_parser, msg_parser); - if (sk_psock_is_new) { - ret = tcp_bpf_init(sk); - if (ret < 0) - goto out_drop; - } else { - tcp_bpf_reinit(sk); - } + + ret = sock_map_init_proto(sk, psock); + if (ret < 0) + goto out_drop; write_lock_bh(&sk->sk_callback_lock); if (skb_progs && !psock->parser.enabled) { @@ -235,20 +278,17 @@ static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk) struct sk_psock *psock; int ret; - psock = sk_psock_get_checked(sk); + psock = sock_map_psock_get_checked(sk); if (IS_ERR(psock)) return PTR_ERR(psock); - if (psock) { - tcp_bpf_reinit(sk); - return 0; + if (!psock) { + psock = sk_psock_init(sk, map->numa_node); + if (!psock) + return -ENOMEM; } - psock = sk_psock_init(sk, map->numa_node); - if (!psock) - return -ENOMEM; - - ret = tcp_bpf_init(sk); + ret = sock_map_init_proto(sk, psock); if (ret < 0) sk_psock_put(sk, psock); return ret; @@ -384,7 +424,6 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct inet_connection_sock *icsk = inet_csk(sk); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; @@ -395,7 +434,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; - if (unlikely(rcu_access_pointer(icsk->icsk_ulp_data))) + if (inet_csk_has_ulp(sk)) return -EINVAL; link = sk_psock_init_link(); @@ -448,15 +487,31 @@ static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } -static bool sock_map_sk_is_suitable(const struct sock *sk) +static bool sk_is_tcp(const struct sock *sk) { return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; } +static bool sk_is_udp(const struct sock *sk) +{ + return sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP; +} + +static bool sock_map_sk_is_suitable(const struct sock *sk) +{ + return sk_is_tcp(sk) || sk_is_udp(sk); +} + static bool sock_map_sk_state_allowed(const struct sock *sk) { - return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); + if (sk_is_tcp(sk)) + return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); + else if (sk_is_udp(sk)) + return sk_hashed(sk); + + return false; } static int sock_map_update_elem(struct bpf_map *map, void *key, @@ -738,7 +793,6 @@ static int sock_hash_update_common(struct bpf_map *map, void *key, struct sock *sk, u64 flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct inet_connection_sock *icsk = inet_csk(sk); u32 key_size = map->key_size, hash; struct bpf_htab_elem *elem, *elem_new; struct bpf_htab_bucket *bucket; @@ -749,7 +803,7 @@ static int sock_hash_update_common(struct bpf_map *map, void *key, WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; - if (unlikely(icsk->icsk_ulp_data)) + if (inet_csk_has_ulp(sk)) return -EINVAL; link = sk_psock_init_link(); @@ -1129,7 +1183,7 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, return 0; } -void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link) +static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link) { switch (link->map->map_type) { case BPF_MAP_TYPE_SOCKMAP: @@ -1142,3 +1196,54 @@ void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link) break; } } + +static void sock_map_remove_links(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_link *link; + + while ((link = sk_psock_link_pop(psock))) { + sock_map_unlink(sk, link); + sk_psock_free_link(link); + } +} + +void sock_map_unhash(struct sock *sk) +{ + void (*saved_unhash)(struct sock *sk); + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + if (sk->sk_prot->unhash) + sk->sk_prot->unhash(sk); + return; + } + + saved_unhash = psock->saved_unhash; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + saved_unhash(sk); +} + +void sock_map_close(struct sock *sk, long timeout) +{ + void (*saved_close)(struct sock *sk, long timeout); + struct sk_psock *psock; + + lock_sock(sk); + rcu_read_lock(); + psock = sk_psock(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + release_sock(sk); + return sk->sk_prot->close(sk, timeout); + } + + saved_close = psock->saved_close; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + release_sock(sk); + saved_close(sk, timeout); +} diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 9d97bace13c8..9e1a186a3671 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -61,6 +61,7 @@ obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o +obj-$(CONFIG_BPF_STREAM_PARSER) += udp_bpf.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 7d6e1b75d4d4..fe7b4fbc31c1 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -528,57 +528,7 @@ out_err: return copied ? copied : err; } -static void tcp_bpf_remove(struct sock *sk, struct sk_psock *psock) -{ - struct sk_psock_link *link; - - while ((link = sk_psock_link_pop(psock))) { - sk_psock_unlink(sk, link); - sk_psock_free_link(link); - } -} - -static void tcp_bpf_unhash(struct sock *sk) -{ - void (*saved_unhash)(struct sock *sk); - struct sk_psock *psock; - - rcu_read_lock(); - psock = sk_psock(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - if (sk->sk_prot->unhash) - sk->sk_prot->unhash(sk); - return; - } - - saved_unhash = psock->saved_unhash; - tcp_bpf_remove(sk, psock); - rcu_read_unlock(); - saved_unhash(sk); -} - -static void tcp_bpf_close(struct sock *sk, long timeout) -{ - void (*saved_close)(struct sock *sk, long timeout); - struct sk_psock *psock; - - lock_sock(sk); - rcu_read_lock(); - psock = sk_psock(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - return sk->sk_prot->close(sk, timeout); - } - - saved_close = psock->saved_close; - tcp_bpf_remove(sk, psock); - rcu_read_unlock(); - release_sock(sk); - saved_close(sk, timeout); -} - +#ifdef CONFIG_BPF_STREAM_PARSER enum { TCP_BPF_IPV4, TCP_BPF_IPV6, @@ -599,8 +549,8 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], struct proto *base) { prot[TCP_BPF_BASE] = *base; - prot[TCP_BPF_BASE].unhash = tcp_bpf_unhash; - prot[TCP_BPF_BASE].close = tcp_bpf_close; + prot[TCP_BPF_BASE].unhash = sock_map_unhash; + prot[TCP_BPF_BASE].close = sock_map_close; prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read; @@ -629,28 +579,6 @@ static int __init tcp_bpf_v4_build_proto(void) } core_initcall(tcp_bpf_v4_build_proto); -static void tcp_bpf_update_sk_prot(struct sock *sk, struct sk_psock *psock) -{ - int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; - int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; - - sk_psock_update_proto(sk, psock, &tcp_bpf_prots[family][config]); -} - -static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock) -{ - int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; - int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; - - /* Reinit occurs when program types change e.g. TCP_BPF_TX is removed - * or added requiring sk_prot hook updates. We keep original saved - * hooks in this case. - * - * Pairs with lockless read in sk_clone_lock(). - */ - WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]); -} - static int tcp_bpf_assert_proto_ops(struct proto *ops) { /* In order to avoid retpoline, we make assumptions when we call @@ -662,36 +590,21 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops) ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP; } -void tcp_bpf_reinit(struct sock *sk) +struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock) { - struct sk_psock *psock; - - sock_owned_by_me(sk); - - rcu_read_lock(); - psock = sk_psock(sk); - tcp_bpf_reinit_sk_prot(sk, psock); - rcu_read_unlock(); -} + int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; + int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; -int tcp_bpf_init(struct sock *sk) -{ - struct proto *ops = READ_ONCE(sk->sk_prot); - struct sk_psock *psock; + if (!psock->sk_proto) { + struct proto *ops = READ_ONCE(sk->sk_prot); - sock_owned_by_me(sk); + if (tcp_bpf_assert_proto_ops(ops)) + return ERR_PTR(-EINVAL); - rcu_read_lock(); - psock = sk_psock(sk); - if (unlikely(!psock || psock->sk_proto || - tcp_bpf_assert_proto_ops(ops))) { - rcu_read_unlock(); - return -EINVAL; + tcp_bpf_check_v6_needs_rebuild(sk, ops); } - tcp_bpf_check_v6_needs_rebuild(sk, ops); - tcp_bpf_update_sk_prot(sk, psock); - rcu_read_unlock(); - return 0; + + return &tcp_bpf_prots[family][config]; } /* If a child got cloned from a listening socket that had tcp_bpf @@ -707,3 +620,4 @@ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) newsk->sk_prot = sk->sk_prot_creator; } +#endif /* CONFIG_BPF_STREAM_PARSER */ diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 2703f24c5d1a..7c27aa629af1 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -105,13 +105,6 @@ void tcp_update_ulp(struct sock *sk, struct proto *proto, { struct inet_connection_sock *icsk = inet_csk(sk); - if (!icsk->icsk_ulp_ops) { - sk->sk_write_space = write_space; - /* Pairs with lockless read in sk_clone_lock() */ - WRITE_ONCE(sk->sk_prot, proto); - return; - } - if (icsk->icsk_ulp_ops->update) icsk->icsk_ulp_ops->update(sk, proto, write_space); } diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c new file mode 100644 index 000000000000..eddd973e6575 --- /dev/null +++ b/net/ipv4/udp_bpf.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Cloudflare Ltd https://cloudflare.com */ + +#include <linux/skmsg.h> +#include <net/sock.h> +#include <net/udp.h> + +enum { + UDP_BPF_IPV4, + UDP_BPF_IPV6, + UDP_BPF_NUM_PROTS, +}; + +static struct proto *udpv6_prot_saved __read_mostly; +static DEFINE_SPINLOCK(udpv6_prot_lock); +static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS]; + +static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) +{ + *prot = *base; + prot->unhash = sock_map_unhash; + prot->close = sock_map_close; +} + +static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops) +{ + if (sk->sk_family == AF_INET6 && + unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) { + spin_lock_bh(&udpv6_prot_lock); + if (likely(ops != udpv6_prot_saved)) { + udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops); + smp_store_release(&udpv6_prot_saved, ops); + } + spin_unlock_bh(&udpv6_prot_lock); + } +} + +static int __init udp_bpf_v4_build_proto(void) +{ + udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot); + return 0; +} +core_initcall(udp_bpf_v4_build_proto); + +struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock) +{ + int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; + + if (!psock->sk_proto) + udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot)); + + return &udp_bpf_prots[family]; +} diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index cebed6fb5bbb..f43d193aff3a 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -400,6 +400,7 @@ class PrinterHelpers(Printer): 'struct bpf_fib_lookup', 'struct bpf_perf_event_data', 'struct bpf_perf_event_value', + 'struct bpf_pidns_info', 'struct bpf_sock', 'struct bpf_sock_addr', 'struct bpf_sock_ops', @@ -435,6 +436,7 @@ class PrinterHelpers(Printer): 'struct bpf_fib_lookup', 'struct bpf_perf_event_data', 'struct bpf_perf_event_value', + 'struct bpf_pidns_info', 'struct bpf_sock', 'struct bpf_sock_addr', 'struct bpf_sock_ops', diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index dd484e92752e..ac569e197bfa 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -63,12 +63,18 @@ vmlinux_link() local lds="${objtree}/${KBUILD_LDS}" local output=${1} local objects + local strip_debug info LD ${output} # skip output file argument shift + # The kallsyms linking does not need debug symbols included. + if [ "$output" != "${output#.tmp_vmlinux.kallsyms}" ] ; then + strip_debug=-Wl,--strip-debug + fi + if [ "${SRCARCH}" != "um" ]; then objects="--whole-archive \ ${KBUILD_VMLINUX_OBJS} \ @@ -79,6 +85,7 @@ vmlinux_link() ${@}" ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} \ + ${strip_debug#-Wl,} \ -o ${output} \ -T ${lds} ${objects} else @@ -91,6 +98,7 @@ vmlinux_link() ${@}" ${CC} ${CFLAGS_vmlinux} \ + ${strip_debug} \ -o ${output} \ -Wl,-T,${lds} \ ${objects} \ @@ -106,6 +114,8 @@ gen_btf() { local pahole_ver local bin_arch + local bin_format + local bin_file if ! [ -x "$(command -v ${PAHOLE})" ]; then echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available" @@ -118,8 +128,9 @@ gen_btf() return 1 fi - info "BTF" ${2} vmlinux_link ${1} + + info "BTF" ${2} LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1} # dump .BTF section into raw binary file to link with final vmlinux @@ -127,11 +138,12 @@ gen_btf() cut -d, -f1 | cut -d' ' -f2) bin_format=$(LANG=C ${OBJDUMP} -f ${1} | grep 'file format' | \ awk '{print $4}') + bin_file=.btf.vmlinux.bin ${OBJCOPY} --change-section-address .BTF=0 \ --set-section-flags .BTF=alloc -O binary \ - --only-section=.BTF ${1} .btf.vmlinux.bin + --only-section=.BTF ${1} $bin_file ${OBJCOPY} -I binary -O ${bin_format} -B ${bin_arch} \ - --rename-section .data=.BTF .btf.vmlinux.bin ${2} + --rename-section .data=.BTF $bin_file ${2} } # Create ${2} .o file with all symbols from the ${1} object file @@ -166,8 +178,8 @@ kallsyms() kallsyms_step() { kallsymso_prev=${kallsymso} - kallsymso=.tmp_kallsyms${1}.o - kallsyms_vmlinux=.tmp_vmlinux${1} + kallsyms_vmlinux=.tmp_vmlinux.kallsyms${1} + kallsymso=${kallsyms_vmlinux}.o vmlinux_link ${kallsyms_vmlinux} "${kallsymso_prev}" ${btf_vmlinux_bin_o} kallsyms ${kallsyms_vmlinux} ${kallsymso} @@ -190,7 +202,6 @@ cleanup() { rm -f .btf.* rm -f .tmp_System.map - rm -f .tmp_kallsyms* rm -f .tmp_vmlinux* rm -f System.map rm -f vmlinux @@ -257,9 +268,8 @@ tr '\0' '\n' < modules.builtin.modinfo | sed -n 's/^[[:alnum:]:_]*\.file=//p' | btf_vmlinux_bin_o="" if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then - if gen_btf .tmp_vmlinux.btf .btf.vmlinux.bin.o ; then - btf_vmlinux_bin_o=.btf.vmlinux.bin.o - else + btf_vmlinux_bin_o=.btf.vmlinux.bin.o + if ! gen_btf .tmp_vmlinux.btf $btf_vmlinux_bin_o ; then echo >&2 "Failed to generate BTF for vmlinux" echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF" exit 1 diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index b13926432b84..8d6e8901ed2b 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,7 +1,9 @@ *.d +/_bpftool /bpftool bpftool*.8 bpf-helpers.* FEATURE-DUMP.bpftool feature libbpf +profiler.skel.h diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 46862e85fed2..9f19404f470e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -30,6 +30,7 @@ PROG COMMANDS | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** | **bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*] +| **bpftool** **prog profile** *PROG* [**duration** *DURATION*] *METRICs* | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } @@ -48,6 +49,9 @@ PROG COMMANDS | *ATTACH_TYPE* := { | **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** | } +| *METRIC* := { +| **cycles** | **instructions** | **l1d_loads** | **llc_misses** +| } DESCRIPTION @@ -189,6 +193,12 @@ DESCRIPTION not all of them can take the **ctx_in**/**ctx_out** arguments. bpftool does not perform checks on program types. + **bpftool prog profile** *PROG* [**duration** *DURATION*] *METRICs* + Profile *METRICs* for bpf program *PROG* for *DURATION* + seconds or until user hits Ctrl-C. *DURATION* is optional. + If *DURATION* is not specified, the profiling will run up to + UINT_MAX seconds. + **bpftool prog help** Print short help message. @@ -311,6 +321,15 @@ EXAMPLES **# rm /sys/fs/bpf/xdp1** +| +| **# bpftool prog profile id 337 duration 10 cycles instructions llc_misses** + +:: + 51397 run_cnt + 40176203 cycles (83.05%) + 42518139 instructions # 1.06 insns per cycle (83.39%) + 123 llc_misses # 2.89 LLC misses per million insns (83.15%) + SEE ALSO ======== **bpf**\ (2), diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index c4e810335810..f584d1fdfc64 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -59,10 +59,12 @@ LIBS = $(LIBBPF) -lelf -lz INSTALL ?= install RM ?= rm -f +CLANG ?= clang FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib -FEATURE_DISPLAY = libbfd disassembler-four-args zlib +FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib \ + clang-bpf-global-var +FEATURE_DISPLAY = libbfd disassembler-four-args zlib clang-bpf-global-var check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -110,14 +112,39 @@ SRCS += $(BFD_SRCS) endif OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o +_OBJS = $(filter-out $(OUTPUT)prog.o,$(OBJS)) $(OUTPUT)_prog.o + +ifeq ($(feature-clang-bpf-global-var),1) + __OBJS = $(OBJS) +else + __OBJS = $(_OBJS) +endif + +$(OUTPUT)_prog.o: prog.c + $(QUIET_CC)$(COMPILE.c) -MMD -DBPFTOOL_WITHOUT_SKELETONS -o $@ $< + +$(OUTPUT)_bpftool: $(_OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(_OBJS) $(LIBS) + +skeleton/profiler.bpf.o: skeleton/profiler.bpf.c $(LIBBPF) + $(QUIET_CLANG)$(CLANG) \ + -I$(srctree)/tools/include/uapi/ \ + -I$(LIBBPF_PATH) -I$(srctree)/tools/lib \ + -g -O2 -target bpf -c $< -o $@ + +profiler.skel.h: $(OUTPUT)_bpftool skeleton/profiler.bpf.o + $(QUIET_GEN)$(OUTPUT)./_bpftool gen skeleton skeleton/profiler.bpf.o > $@ + +$(OUTPUT)prog.o: prog.c profiler.skel.h + $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< $(OUTPUT)feature.o: | zdep -$(OUTPUT)bpftool: $(OBJS) $(LIBBPF) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS) +$(OUTPUT)bpftool: $(__OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(__OBJS) $(LIBS) $(OUTPUT)%.o: %.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< @@ -125,6 +152,7 @@ $(OUTPUT)%.o: %.c clean: $(LIBBPF)-clean $(call QUIET_CLEAN, bpftool) $(Q)$(RM) -- $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + $(Q)$(RM) -- $(OUTPUT)_bpftool profiler.skel.h skeleton/profiler.bpf.o $(Q)$(RM) -r -- $(OUTPUT)libbpf/ $(call QUIET_CLEAN, core-gen) $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index f2838a658339..9b0534f558f1 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -337,6 +337,7 @@ _bpftool() local PROG_TYPE='id pinned tag name' local MAP_TYPE='id pinned name' + local METRIC_TYPE='cycles instructions l1d_loads llc_misses' case $command in show|list) [[ $prev != "$command" ]] && return 0 @@ -388,7 +389,7 @@ _bpftool() _bpftool_get_prog_ids ;; name) - _bpftool_get_map_names + _bpftool_get_prog_names ;; pinned) _filedir @@ -498,9 +499,51 @@ _bpftool() tracelog) return 0 ;; + profile) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 4) + case $prev in + id) + _bpftool_get_prog_ids + ;; + name) + _bpftool_get_prog_names + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 5) + COMPREPLY=( $( compgen -W "$METRIC_TYPE duration" -- "$cur" ) ) + return 0 + ;; + 6) + case $prev in + duration) + return 0 + ;; + *) + COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) ) + return 0 + ;; + esac + return 0 + ;; + *) + COMPREPLY=( $( compgen -W "$METRIC_TYPE" -- "$cur" ) ) + return 0 + ;; + esac + ;; run) - if [[ ${#words[@]} -lt 5 ]]; then - _filedir + if [[ ${#words[@]} -eq 4 ]]; then + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) return 0 fi case $prev in @@ -508,6 +551,10 @@ _bpftool() _bpftool_get_prog_ids return 0 ;; + name) + _bpftool_get_prog_names + return 0 + ;; data_in|data_out|ctx_in|ctx_out) _filedir return 0 @@ -525,7 +572,7 @@ _bpftool() *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'dump help pin attach detach \ - load loadall show list tracelog run' -- "$cur" ) ) + load loadall show list tracelog run profile' -- "$cur" ) ) ;; esac ;; @@ -713,11 +760,17 @@ _bpftool() esac ;; pin) - if [[ $prev == "$command" ]]; then - COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) - else - _filedir - fi + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + ;; + id) + _bpftool_get_map_ids + ;; + name) + _bpftool_get_map_names + ;; + esac return 0 ;; event_pipe) @@ -844,7 +897,7 @@ _bpftool() case $command in skeleton) _filedir - ;; + ;; *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) ) @@ -944,6 +997,9 @@ _bpftool() id) _bpftool_get_prog_ids ;; + name) + _bpftool_get_prog_names + ;; pinned) _filedir ;; diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index b3745ed711ba..bcaf55b59498 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -389,6 +389,9 @@ static int dump_btf_c(const struct btf *btf, if (IS_ERR(d)) return PTR_ERR(d); + printf("#ifndef __VMLINUX_H__\n"); + printf("#define __VMLINUX_H__\n"); + printf("\n"); printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n"); printf("#endif\n\n"); @@ -412,6 +415,8 @@ static int dump_btf_c(const struct btf *btf, printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); printf("#pragma clang attribute pop\n"); printf("#endif\n"); + printf("\n"); + printf("#endif /* __VMLINUX_H__ */\n"); done: btf_dump__free(d); diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index b75b8ec5469c..f2223dbdfb0a 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -211,39 +211,14 @@ int do_pin_fd(int fd, const char *name) return err; } -int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) +int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) { - unsigned int id; - char *endptr; int err; int fd; - if (argc < 3) { - p_err("too few arguments, id ID and FILE path is required"); - return -1; - } else if (argc > 3) { - p_err("too many arguments"); - return -1; - } - - if (!is_prefix(*argv, "id")) { - p_err("expected 'id' got %s", *argv); - return -1; - } - NEXT_ARG(); - - id = strtoul(*argv, &endptr, 0); - if (*endptr) { - p_err("can't parse %s as ID", *argv); - return -1; - } - NEXT_ARG(); - - fd = get_fd_by_id(id); - if (fd < 0) { - p_err("can't open object by id (%u): %s", id, strerror(errno)); - return -1; - } + fd = get_fd(&argc, &argv); + if (fd < 0) + return fd; err = do_pin_fd(fd, *argv); @@ -597,3 +572,10 @@ int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what) return 0; } + +int __printf(2, 0) +print_all_levels(__maybe_unused enum libbpf_print_level level, + const char *format, va_list args) +{ + return vfprintf(stderr, format, args); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 6d41bbfc6459..06449e846e4b 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -79,13 +79,6 @@ static int do_version(int argc, char **argv) return 0; } -static int __printf(2, 0) -print_all_levels(__maybe_unused enum libbpf_print_level level, - const char *format, va_list args) -{ - return vfprintf(stderr, format, args); -} - int cmd_select(const struct cmd *cmds, int argc, char **argv, int (*help)(int argc, char **argv)) { diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 724ef9d941d3..5f6dccd43622 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -14,6 +14,8 @@ #include <linux/hashtable.h> #include <tools/libc_compat.h> +#include <bpf/libbpf.h> + #include "json_writer.h" #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) @@ -146,7 +148,7 @@ char *get_fdinfo(int fd, const char *key); int open_obj_pinned(char *path, bool quiet); int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type); int mount_bpffs_for_pin(const char *name); -int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)); +int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); int do_pin_fd(int fd, const char *name); int do_prog(int argc, char **arg); @@ -229,4 +231,7 @@ struct tcmsg; int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb); int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind, const char *devname, int ifindex); + +int print_all_levels(__maybe_unused enum libbpf_print_level level, + const char *format, va_list args); #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e6c85680b34d..693a632f6813 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1384,7 +1384,7 @@ static int do_pin(int argc, char **argv) { int err; - err = do_pin_any(argc, argv, bpf_map_get_fd_by_id); + err = do_pin_any(argc, argv, map_parse_fd); if (!err && json_output) jsonw_null(json_wtr); return err; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 1996e67a2f00..f6a5974a7b0a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -4,6 +4,7 @@ #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> +#include <signal.h> #include <stdarg.h> #include <stdio.h> #include <stdlib.h> @@ -11,10 +12,13 @@ #include <time.h> #include <unistd.h> #include <net/if.h> +#include <sys/ioctl.h> #include <sys/types.h> #include <sys/stat.h> +#include <sys/syscall.h> #include <linux/err.h> +#include <linux/perf_event.h> #include <linux/sizes.h> #include <bpf/bpf.h> @@ -809,7 +813,7 @@ static int do_pin(int argc, char **argv) { int err; - err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id); + err = do_pin_any(argc, argv, prog_parse_fd); if (!err && json_output) jsonw_null(json_wtr); return err; @@ -1243,6 +1247,25 @@ free_data_in: return err; } +static int +get_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type) +{ + libbpf_print_fn_t print_backup; + int ret; + + ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type); + if (!ret) + return ret; + + /* libbpf_prog_type_by_name() failed, let's re-run with debug level */ + print_backup = libbpf_set_print(print_all_levels); + ret = libbpf_prog_type_by_name(name, prog_type, expected_attach_type); + libbpf_set_print(print_backup); + + return ret; +} + static int load_with_options(int argc, char **argv, bool first_prog_only) { enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC; @@ -1292,8 +1315,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) strcat(type, *argv); strcat(type, "/"); - err = libbpf_prog_type_by_name(type, &common_prog_type, - &expected_attach_type); + err = get_prog_type_by_name(type, &common_prog_type, + &expected_attach_type); free(type); if (err < 0) goto err_free_reuse_maps; @@ -1392,8 +1415,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) if (prog_type == BPF_PROG_TYPE_UNSPEC) { const char *sec_name = bpf_program__title(pos, false); - err = libbpf_prog_type_by_name(sec_name, &prog_type, - &expected_attach_type); + err = get_prog_type_by_name(sec_name, &prog_type, + &expected_attach_type); if (err < 0) goto err_close_obj; } @@ -1537,6 +1560,422 @@ static int do_loadall(int argc, char **argv) return load_with_options(argc, argv, false); } +#ifdef BPFTOOL_WITHOUT_SKELETONS + +static int do_profile(int argc, char **argv) +{ + p_err("bpftool prog profile command is not supported. Please build bpftool with clang >= 10.0.0"); + return 0; +} + +#else /* BPFTOOL_WITHOUT_SKELETONS */ + +#include "profiler.skel.h" + +struct profile_metric { + const char *name; + struct bpf_perf_event_value val; + struct perf_event_attr attr; + bool selected; + + /* calculate ratios like instructions per cycle */ + const int ratio_metric; /* 0 for N/A, 1 for index 0 (cycles) */ + const char *ratio_desc; + const float ratio_mul; +} metrics[] = { + { + .name = "cycles", + .attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .exclude_user = 1, + }, + }, + { + .name = "instructions", + .attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .exclude_user = 1, + }, + .ratio_metric = 1, + .ratio_desc = "insns per cycle", + .ratio_mul = 1.0, + }, + { + .name = "l1d_loads", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_L1D | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16), + .exclude_user = 1, + }, + }, + { + .name = "llc_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_LL | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "LLC misses per million insns", + .ratio_mul = 1e6, + }, +}; + +static __u64 profile_total_count; + +#define MAX_NUM_PROFILE_METRICS 4 + +static int profile_parse_metrics(int argc, char **argv) +{ + unsigned int metric_cnt; + int selected_cnt = 0; + unsigned int i; + + metric_cnt = sizeof(metrics) / sizeof(struct profile_metric); + + while (argc > 0) { + for (i = 0; i < metric_cnt; i++) { + if (is_prefix(argv[0], metrics[i].name)) { + if (!metrics[i].selected) + selected_cnt++; + metrics[i].selected = true; + break; + } + } + if (i == metric_cnt) { + p_err("unknown metric %s", argv[0]); + return -1; + } + NEXT_ARG(); + } + if (selected_cnt > MAX_NUM_PROFILE_METRICS) { + p_err("too many (%d) metrics, please specify no more than %d metrics at at time", + selected_cnt, MAX_NUM_PROFILE_METRICS); + return -1; + } + return selected_cnt; +} + +static void profile_read_values(struct profiler_bpf *obj) +{ + __u32 m, cpu, num_cpu = obj->rodata->num_cpu; + int reading_map_fd, count_map_fd; + __u64 counts[num_cpu]; + __u32 key = 0; + int err; + + reading_map_fd = bpf_map__fd(obj->maps.accum_readings); + count_map_fd = bpf_map__fd(obj->maps.counts); + if (reading_map_fd < 0 || count_map_fd < 0) { + p_err("failed to get fd for map"); + return; + } + + err = bpf_map_lookup_elem(count_map_fd, &key, counts); + if (err) { + p_err("failed to read count_map: %s", strerror(errno)); + return; + } + + profile_total_count = 0; + for (cpu = 0; cpu < num_cpu; cpu++) + profile_total_count += counts[cpu]; + + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + struct bpf_perf_event_value values[num_cpu]; + + if (!metrics[m].selected) + continue; + + err = bpf_map_lookup_elem(reading_map_fd, &key, values); + if (err) { + p_err("failed to read reading_map: %s", + strerror(errno)); + return; + } + for (cpu = 0; cpu < num_cpu; cpu++) { + metrics[m].val.counter += values[cpu].counter; + metrics[m].val.enabled += values[cpu].enabled; + metrics[m].val.running += values[cpu].running; + } + key++; + } +} + +static void profile_print_readings_json(void) +{ + __u32 m; + + jsonw_start_array(json_wtr); + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + if (!metrics[m].selected) + continue; + jsonw_start_object(json_wtr); + jsonw_string_field(json_wtr, "metric", metrics[m].name); + jsonw_lluint_field(json_wtr, "run_cnt", profile_total_count); + jsonw_lluint_field(json_wtr, "value", metrics[m].val.counter); + jsonw_lluint_field(json_wtr, "enabled", metrics[m].val.enabled); + jsonw_lluint_field(json_wtr, "running", metrics[m].val.running); + + jsonw_end_object(json_wtr); + } + jsonw_end_array(json_wtr); +} + +static void profile_print_readings_plain(void) +{ + __u32 m; + + printf("\n%18llu %-20s\n", profile_total_count, "run_cnt"); + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + struct bpf_perf_event_value *val = &metrics[m].val; + int r; + + if (!metrics[m].selected) + continue; + printf("%18llu %-20s", val->counter, metrics[m].name); + + r = metrics[m].ratio_metric - 1; + if (r >= 0 && metrics[r].selected && + metrics[r].val.counter > 0) { + printf("# %8.2f %-30s", + val->counter * metrics[m].ratio_mul / + metrics[r].val.counter, + metrics[m].ratio_desc); + } else { + printf("%-41s", ""); + } + + if (val->enabled > val->running) + printf("(%4.2f%%)", + val->running * 100.0 / val->enabled); + printf("\n"); + } +} + +static void profile_print_readings(void) +{ + if (json_output) + profile_print_readings_json(); + else + profile_print_readings_plain(); +} + +static char *profile_target_name(int tgt_fd) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_func_info *func_info; + const struct btf_type *t; + char *name = NULL; + struct btf *btf; + + info_linear = bpf_program__get_prog_info_linear( + tgt_fd, 1UL << BPF_PROG_INFO_FUNC_INFO); + if (IS_ERR_OR_NULL(info_linear)) { + p_err("failed to get info_linear for prog FD %d", tgt_fd); + return NULL; + } + + if (info_linear->info.btf_id == 0 || + btf__get_from_id(info_linear->info.btf_id, &btf)) { + p_err("prog FD %d doesn't have valid btf", tgt_fd); + goto out; + } + + func_info = (struct bpf_func_info *)(info_linear->info.func_info); + t = btf__type_by_id(btf, func_info[0].type_id); + if (!t) { + p_err("btf %d doesn't have type %d", + info_linear->info.btf_id, func_info[0].type_id); + goto out; + } + name = strdup(btf__name_by_offset(btf, t->name_off)); +out: + free(info_linear); + return name; +} + +static struct profiler_bpf *profile_obj; +static int profile_tgt_fd = -1; +static char *profile_tgt_name; +static int *profile_perf_events; +static int profile_perf_event_cnt; + +static void profile_close_perf_events(struct profiler_bpf *obj) +{ + int i; + + for (i = profile_perf_event_cnt - 1; i >= 0; i--) + close(profile_perf_events[i]); + + free(profile_perf_events); + profile_perf_event_cnt = 0; +} + +static int profile_open_perf_events(struct profiler_bpf *obj) +{ + unsigned int cpu, m; + int map_fd, pmu_fd; + + profile_perf_events = calloc( + sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); + if (!profile_perf_events) { + p_err("failed to allocate memory for perf_event array: %s", + strerror(errno)); + return -1; + } + map_fd = bpf_map__fd(obj->maps.events); + if (map_fd < 0) { + p_err("failed to get fd for events map"); + return -1; + } + + for (m = 0; m < ARRAY_SIZE(metrics); m++) { + if (!metrics[m].selected) + continue; + for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { + pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr, + -1/*pid*/, cpu, -1/*group_fd*/, 0); + if (pmu_fd < 0 || + bpf_map_update_elem(map_fd, &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + p_err("failed to create event %s on cpu %d", + metrics[m].name, cpu); + return -1; + } + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + } + } + return 0; +} + +static void profile_print_and_cleanup(void) +{ + profile_close_perf_events(profile_obj); + profile_read_values(profile_obj); + profile_print_readings(); + profiler_bpf__destroy(profile_obj); + + close(profile_tgt_fd); + free(profile_tgt_name); +} + +static void int_exit(int signo) +{ + profile_print_and_cleanup(); + exit(0); +} + +static int do_profile(int argc, char **argv) +{ + int num_metric, num_cpu, err = -1; + struct bpf_program *prog; + unsigned long duration; + char *endptr; + + /* we at least need two args for the prog and one metric */ + if (!REQ_ARGS(3)) + return -EINVAL; + + /* parse target fd */ + profile_tgt_fd = prog_parse_fd(&argc, &argv); + if (profile_tgt_fd < 0) { + p_err("failed to parse fd"); + return -1; + } + + /* parse profiling optional duration */ + if (argc > 2 && is_prefix(argv[0], "duration")) { + NEXT_ARG(); + duration = strtoul(*argv, &endptr, 0); + if (*endptr) + usage(); + NEXT_ARG(); + } else { + duration = UINT_MAX; + } + + num_metric = profile_parse_metrics(argc, argv); + if (num_metric <= 0) + goto out; + + num_cpu = libbpf_num_possible_cpus(); + if (num_cpu <= 0) { + p_err("failed to identify number of CPUs"); + goto out; + } + + profile_obj = profiler_bpf__open(); + if (!profile_obj) { + p_err("failed to open and/or load BPF object"); + goto out; + } + + profile_obj->rodata->num_cpu = num_cpu; + profile_obj->rodata->num_metric = num_metric; + + /* adjust map sizes */ + bpf_map__resize(profile_obj->maps.events, num_metric * num_cpu); + bpf_map__resize(profile_obj->maps.fentry_readings, num_metric); + bpf_map__resize(profile_obj->maps.accum_readings, num_metric); + bpf_map__resize(profile_obj->maps.counts, 1); + + /* change target name */ + profile_tgt_name = profile_target_name(profile_tgt_fd); + if (!profile_tgt_name) + goto out; + + bpf_object__for_each_program(prog, profile_obj->obj) { + err = bpf_program__set_attach_target(prog, profile_tgt_fd, + profile_tgt_name); + if (err) { + p_err("failed to set attach target\n"); + goto out; + } + } + + set_max_rlimit(); + err = profiler_bpf__load(profile_obj); + if (err) { + p_err("failed to load profile_obj"); + goto out; + } + + err = profile_open_perf_events(profile_obj); + if (err) + goto out; + + err = profiler_bpf__attach(profile_obj); + if (err) { + p_err("failed to attach profile_obj"); + goto out; + } + signal(SIGINT, int_exit); + + sleep(duration); + profile_print_and_cleanup(); + return 0; + +out: + profile_close_perf_events(profile_obj); + if (profile_obj) + profiler_bpf__destroy(profile_obj); + close(profile_tgt_fd); + free(profile_tgt_name); + return err; +} + +#endif /* BPFTOOL_WITHOUT_SKELETONS */ + static int do_help(int argc, char **argv) { if (json_output) { @@ -1560,6 +1999,7 @@ static int do_help(int argc, char **argv) " [data_out FILE [data_size_out L]] \\\n" " [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n" " [repeat N]\n" + " %s %s profile PROG [duration DURATION] METRICs\n" " %s %s tracelog\n" " %s %s help\n" "\n" @@ -1577,12 +2017,13 @@ static int do_help(int argc, char **argv) " struct_ops | fentry | fexit | freplace }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" + " METRIC := { cycles | instructions | l1d_loads | llc_misses }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2]); return 0; } @@ -1599,6 +2040,7 @@ static const struct cmd cmds[] = { { "detach", do_detach }, { "tracelog", do_tracelog }, { "run", do_run }, + { "profile", do_profile }, { 0 } }; diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c new file mode 100644 index 000000000000..20034c12f7c5 --- /dev/null +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook +#include "profiler.h" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* map of perf event fds, num_cpu * num_metric entries */ +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(int)); +} events SEC(".maps"); + +/* readings at fentry */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); +} fentry_readings SEC(".maps"); + +/* accumulated readings */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); +} accum_readings SEC(".maps"); + +/* sample counts, one per cpu */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u64)); +} counts SEC(".maps"); + +const volatile __u32 num_cpu = 1; +const volatile __u32 num_metric = 1; +#define MAX_NUM_MATRICS 4 + +SEC("fentry/XXX") +int BPF_PROG(fentry_XXX) +{ + struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS]; + u32 key = bpf_get_smp_processor_id(); + u32 i; + + /* look up before reading, to reduce error */ + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + u32 flag = i; + + ptrs[i] = bpf_map_lookup_elem(&fentry_readings, &flag); + if (!ptrs[i]) + return 0; + } + + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + struct bpf_perf_event_value reading; + int err; + + err = bpf_perf_event_read_value(&events, key, &reading, + sizeof(reading)); + if (err) + return 0; + *(ptrs[i]) = reading; + key += num_cpu; + } + + return 0; +} + +static inline void +fexit_update_maps(u32 id, struct bpf_perf_event_value *after) +{ + struct bpf_perf_event_value *before, diff, *accum; + + before = bpf_map_lookup_elem(&fentry_readings, &id); + /* only account samples with a valid fentry_reading */ + if (before && before->counter) { + struct bpf_perf_event_value *accum; + + diff.counter = after->counter - before->counter; + diff.enabled = after->enabled - before->enabled; + diff.running = after->running - before->running; + + accum = bpf_map_lookup_elem(&accum_readings, &id); + if (accum) { + accum->counter += diff.counter; + accum->enabled += diff.enabled; + accum->running += diff.running; + } + } +} + +SEC("fexit/XXX") +int BPF_PROG(fexit_XXX) +{ + struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; + u32 cpu = bpf_get_smp_processor_id(); + u32 i, one = 1, zero = 0; + int err; + u64 *count; + + /* read all events before updating the maps, to reduce error */ + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) { + err = bpf_perf_event_read_value(&events, cpu + i * num_cpu, + readings + i, sizeof(*readings)); + if (err) + return 0; + } + count = bpf_map_lookup_elem(&counts, &zero); + if (count) { + *count += 1; + for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) + fexit_update_maps(i, &readings[i]); + } + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/bpf/bpftool/skeleton/profiler.h b/tools/bpf/bpftool/skeleton/profiler.h new file mode 100644 index 000000000000..1f767e9510f7 --- /dev/null +++ b/tools/bpf/bpftool/skeleton/profiler.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __PROFILER_H +#define __PROFILER_H + +/* useful typedefs from vmlinux.h */ + +typedef signed char __s8; +typedef unsigned char __u8; +typedef short int __s16; +typedef short unsigned int __u16; +typedef int __s32; +typedef unsigned int __u32; +typedef long long int __s64; +typedef long long unsigned int __u64; + +typedef __s8 s8; +typedef __u8 u8; +typedef __s16 s16; +typedef __u16 u16; +typedef __s32 s32; +typedef __u32 u32; +typedef __s64 s64; +typedef __u64 u64; + +enum { + false = 0, + true = 1, +}; + +#ifdef __CHECKER__ +#define __bitwise__ __attribute__((bitwise)) +#else +#define __bitwise__ +#endif + +typedef __u16 __bitwise__ __le16; +typedef __u16 __bitwise__ __be16; +typedef __u32 __bitwise__ __le32; +typedef __u32 __bitwise__ __be32; +typedef __u64 __bitwise__ __le64; +typedef __u64 __bitwise__ __be64; + +typedef __u16 __bitwise__ __sum16; +typedef __u32 __bitwise__ __wsum; + +#endif /* __PROFILER_H */ diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index 48a39f72fadf..1f18a409f044 100644 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -5,9 +5,7 @@ #include "runqslower.h" #define TASK_RUNNING 0 - -#define BPF_F_INDEX_MASK 0xffffffffULL -#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +#define BPF_F_CURRENT_CPU 0xffffffffULL const volatile __u64 min_us = 0; const volatile pid_t targ_pid = 0; diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 7ac0d8088565..ab8e89a7009c 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -67,7 +67,8 @@ FILES= \ test-llvm.bin \ test-llvm-version.bin \ test-libaio.bin \ - test-libzstd.bin + test-libzstd.bin \ + test-clang-bpf-global-var.bin FILES := $(addprefix $(OUTPUT),$(FILES)) @@ -75,6 +76,7 @@ CC ?= $(CROSS_COMPILE)gcc CXX ?= $(CROSS_COMPILE)g++ PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config LLVM_CONFIG ?= llvm-config +CLANG ?= clang all: $(FILES) @@ -321,6 +323,11 @@ $(OUTPUT)test-libaio.bin: $(OUTPUT)test-libzstd.bin: $(BUILD) -lzstd +$(OUTPUT)test-clang-bpf-global-var.bin: + $(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) | \ + grep BTF_KIND_VAR + + ############################### clean: diff --git a/tools/build/feature/test-clang-bpf-global-var.c b/tools/build/feature/test-clang-bpf-global-var.c new file mode 100644 index 000000000000..221f1481d52e --- /dev/null +++ b/tools/build/feature/test-clang-bpf-global-var.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Facebook + +volatile int global_value_for_test = 1; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 906e9f2752db..5d01c5c7e598 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -73,7 +73,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[0]; /* Arbitrary size */ + __u8 data[]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { @@ -210,6 +210,7 @@ enum bpf_attach_type { BPF_TRACE_RAW_TP, BPF_TRACE_FENTRY, BPF_TRACE_FEXIT, + BPF_MODIFY_RETURN, __MAX_BPF_ATTACH_TYPE }; @@ -325,44 +326,46 @@ enum bpf_attach_type { #define BPF_PSEUDO_CALL 1 /* flags for BPF_MAP_UPDATE_ELEM command */ -#define BPF_ANY 0 /* create new element or update existing */ -#define BPF_NOEXIST 1 /* create new element if it didn't exist */ -#define BPF_EXIST 2 /* update existing element */ -#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ +enum { + BPF_ANY = 0, /* create new element or update existing */ + BPF_NOEXIST = 1, /* create new element if it didn't exist */ + BPF_EXIST = 2, /* update existing element */ + BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */ +}; /* flags for BPF_MAP_CREATE command */ -#define BPF_F_NO_PREALLOC (1U << 0) +enum { + BPF_F_NO_PREALLOC = (1U << 0), /* Instead of having one common LRU list in the * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list * which can scale and perform better. * Note, the LRU nodes (including free nodes) cannot be moved * across different LRU lists. */ -#define BPF_F_NO_COMMON_LRU (1U << 1) + BPF_F_NO_COMMON_LRU = (1U << 1), /* Specify numa node during map creation */ -#define BPF_F_NUMA_NODE (1U << 2) - -#define BPF_OBJ_NAME_LEN 16U + BPF_F_NUMA_NODE = (1U << 2), /* Flags for accessing BPF object from syscall side. */ -#define BPF_F_RDONLY (1U << 3) -#define BPF_F_WRONLY (1U << 4) + BPF_F_RDONLY = (1U << 3), + BPF_F_WRONLY = (1U << 4), /* Flag for stack_map, store build_id+offset instead of pointer */ -#define BPF_F_STACK_BUILD_ID (1U << 5) + BPF_F_STACK_BUILD_ID = (1U << 5), /* Zero-initialize hash function seed. This should only be used for testing. */ -#define BPF_F_ZERO_SEED (1U << 6) + BPF_F_ZERO_SEED = (1U << 6), /* Flags for accessing BPF object from program side. */ -#define BPF_F_RDONLY_PROG (1U << 7) -#define BPF_F_WRONLY_PROG (1U << 8) + BPF_F_RDONLY_PROG = (1U << 7), + BPF_F_WRONLY_PROG = (1U << 8), /* Clone map from listener for newly accepted socket */ -#define BPF_F_CLONE (1U << 9) + BPF_F_CLONE = (1U << 9), /* Enable memory-mapping BPF map */ -#define BPF_F_MMAPABLE (1U << 10) + BPF_F_MMAPABLE = (1U << 10), +}; /* Flags for BPF_PROG_QUERY. */ @@ -391,6 +394,8 @@ struct bpf_stack_build_id { }; }; +#define BPF_OBJ_NAME_LEN 16U + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -2909,6 +2914,42 @@ union bpf_attr { * of sizeof(struct perf_branch_entry). * * **-ENOENT** if architecture does not support branch records. + * + * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) + * Description + * Returns 0 on success, values for *pid* and *tgid* as seen from the current + * *namespace* will be returned in *nsdata*. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if dev and inum supplied don't match dev_t and inode number + * with nsfs of current task, or if dev conversion to dev_t lost high bits. + * + * **-ENOENT** if pidns does not exists for the current task. + * + * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct xdp_buff. + * + * This helper is similar to **bpf_perf_eventoutput**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3030,7 +3071,9 @@ union bpf_attr { FN(tcp_send_ack), \ FN(send_signal_thread), \ FN(jiffies64), \ - FN(read_branch_records), + FN(read_branch_records), \ + FN(get_ns_current_pid_tgid), \ + FN(xdp_output), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3045,72 +3088,100 @@ enum bpf_func_id { /* All flags used by eBPF helper functions, placed here. */ /* BPF_FUNC_skb_store_bytes flags. */ -#define BPF_F_RECOMPUTE_CSUM (1ULL << 0) -#define BPF_F_INVALIDATE_HASH (1ULL << 1) +enum { + BPF_F_RECOMPUTE_CSUM = (1ULL << 0), + BPF_F_INVALIDATE_HASH = (1ULL << 1), +}; /* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. * First 4 bits are for passing the header field size. */ -#define BPF_F_HDR_FIELD_MASK 0xfULL +enum { + BPF_F_HDR_FIELD_MASK = 0xfULL, +}; /* BPF_FUNC_l4_csum_replace flags. */ -#define BPF_F_PSEUDO_HDR (1ULL << 4) -#define BPF_F_MARK_MANGLED_0 (1ULL << 5) -#define BPF_F_MARK_ENFORCE (1ULL << 6) +enum { + BPF_F_PSEUDO_HDR = (1ULL << 4), + BPF_F_MARK_MANGLED_0 = (1ULL << 5), + BPF_F_MARK_ENFORCE = (1ULL << 6), +}; /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -#define BPF_F_INGRESS (1ULL << 0) +enum { + BPF_F_INGRESS = (1ULL << 0), +}; /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ -#define BPF_F_TUNINFO_IPV6 (1ULL << 0) +enum { + BPF_F_TUNINFO_IPV6 = (1ULL << 0), +}; /* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ -#define BPF_F_SKIP_FIELD_MASK 0xffULL -#define BPF_F_USER_STACK (1ULL << 8) +enum { + BPF_F_SKIP_FIELD_MASK = 0xffULL, + BPF_F_USER_STACK = (1ULL << 8), /* flags used by BPF_FUNC_get_stackid only. */ -#define BPF_F_FAST_STACK_CMP (1ULL << 9) -#define BPF_F_REUSE_STACKID (1ULL << 10) + BPF_F_FAST_STACK_CMP = (1ULL << 9), + BPF_F_REUSE_STACKID = (1ULL << 10), /* flags used by BPF_FUNC_get_stack only. */ -#define BPF_F_USER_BUILD_ID (1ULL << 11) + BPF_F_USER_BUILD_ID = (1ULL << 11), +}; /* BPF_FUNC_skb_set_tunnel_key flags. */ -#define BPF_F_ZERO_CSUM_TX (1ULL << 1) -#define BPF_F_DONT_FRAGMENT (1ULL << 2) -#define BPF_F_SEQ_NUMBER (1ULL << 3) +enum { + BPF_F_ZERO_CSUM_TX = (1ULL << 1), + BPF_F_DONT_FRAGMENT = (1ULL << 2), + BPF_F_SEQ_NUMBER = (1ULL << 3), +}; /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and * BPF_FUNC_perf_event_read_value flags. */ -#define BPF_F_INDEX_MASK 0xffffffffULL -#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +enum { + BPF_F_INDEX_MASK = 0xffffffffULL, + BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, /* BPF_FUNC_perf_event_output for sk_buff input context. */ -#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) + BPF_F_CTXLEN_MASK = (0xfffffULL << 32), +}; /* Current network namespace */ -#define BPF_F_CURRENT_NETNS (-1L) +enum { + BPF_F_CURRENT_NETNS = (-1L), +}; /* BPF_FUNC_skb_adjust_room flags. */ -#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) +enum { + BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2), + BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), + BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), +}; -#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff -#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 +enum { + BPF_ADJ_ROOM_ENCAP_L2_MASK = 0xff, + BPF_ADJ_ROOM_ENCAP_L2_SHIFT = 56, +}; -#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) -#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) -#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) -#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) #define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ BPF_ADJ_ROOM_ENCAP_L2_MASK) \ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) /* BPF_FUNC_sysctl_get_name flags. */ -#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) +enum { + BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), +}; /* BPF_FUNC_sk_storage_get flags */ -#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) +enum { + BPF_SK_STORAGE_GET_F_CREATE = (1ULL << 0), +}; /* BPF_FUNC_read_branch_records flags. */ -#define BPF_F_GET_BRANCH_RECORDS_SIZE (1ULL << 0) +enum { + BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0), +}; /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { @@ -3176,6 +3247,7 @@ struct __sk_buff { __u32 wire_len; __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); + __u32 gso_size; }; struct bpf_tunnel_key { @@ -3528,13 +3600,14 @@ struct bpf_sock_ops { }; /* Definitions for bpf_sock_ops_cb_flags */ -#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) -#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) -#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) -#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) -#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently - * supported cb flags - */ +enum { + BPF_SOCK_OPS_RTO_CB_FLAG = (1<<0), + BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), + BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), + BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), +/* Mask of all currently supported cb flags */ + BPF_SOCK_OPS_ALL_CB_FLAGS = 0xF, +}; /* List of known BPF sock_ops operators. * New entries can only be added at the end @@ -3613,8 +3686,10 @@ enum { BPF_TCP_MAX_STATES /* Leave at the end! */ }; -#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ -#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ +enum { + TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ + TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ +}; struct bpf_perf_event_value { __u64 counter; @@ -3622,12 +3697,16 @@ struct bpf_perf_event_value { __u64 running; }; -#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) -#define BPF_DEVCG_ACC_READ (1ULL << 1) -#define BPF_DEVCG_ACC_WRITE (1ULL << 2) +enum { + BPF_DEVCG_ACC_MKNOD = (1ULL << 0), + BPF_DEVCG_ACC_READ = (1ULL << 1), + BPF_DEVCG_ACC_WRITE = (1ULL << 2), +}; -#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) -#define BPF_DEVCG_DEV_CHAR (1ULL << 1) +enum { + BPF_DEVCG_DEV_BLOCK = (1ULL << 0), + BPF_DEVCG_DEV_CHAR = (1ULL << 1), +}; struct bpf_cgroup_dev_ctx { /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ @@ -3643,8 +3722,10 @@ struct bpf_raw_tracepoint_args { /* DIRECT: Skip the FIB rules and go to FIB table associated with device * OUTPUT: Do lookup from egress perspective; default is ingress */ -#define BPF_FIB_LOOKUP_DIRECT (1U << 0) -#define BPF_FIB_LOOKUP_OUTPUT (1U << 1) +enum { + BPF_FIB_LOOKUP_DIRECT = (1U << 0), + BPF_FIB_LOOKUP_OUTPUT = (1U << 1), +}; enum { BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ @@ -3716,9 +3797,11 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; -#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) -#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) -#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) +enum { + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG = (1U << 0), + BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL = (1U << 1), + BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP = (1U << 2), +}; struct bpf_flow_keys { __u16 nhoff; @@ -3784,4 +3867,8 @@ struct bpf_sockopt { __s32 retval; }; +struct bpf_pidns_info { + __u32 pid; + __u32 tgid; +}; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/testing/selftests/bpf/include/uapi/linux/types.h b/tools/include/uapi/linux/types.h index 91fa51a9c31d..91fa51a9c31d 100644 --- a/tools/testing/selftests/bpf/include/uapi/linux/types.h +++ b/tools/include/uapi/linux/types.h diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index b0dafe8b4ebc..b0c9ae5c73b5 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -49,7 +49,8 @@ #if defined(bpf_target_x86) -#ifdef __KERNEL__ +#if defined(__KERNEL__) || defined(__VMLINUX_H__) + #define PT_REGS_PARM1(x) ((x)->di) #define PT_REGS_PARM2(x) ((x)->si) #define PT_REGS_PARM3(x) ((x)->dx) @@ -60,7 +61,20 @@ #define PT_REGS_RC(x) ((x)->ax) #define PT_REGS_SP(x) ((x)->sp) #define PT_REGS_IP(x) ((x)->ip) + +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip) + #else + #ifdef __i386__ /* i386 kernel is built with -mregparm=3 */ #define PT_REGS_PARM1(x) ((x)->eax) @@ -73,7 +87,20 @@ #define PT_REGS_RC(x) ((x)->eax) #define PT_REGS_SP(x) ((x)->esp) #define PT_REGS_IP(x) ((x)->eip) + +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx) +#define PT_REGS_PARM4_CORE(x) 0 +#define PT_REGS_PARM5_CORE(x) 0 +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip) + #else + #define PT_REGS_PARM1(x) ((x)->rdi) #define PT_REGS_PARM2(x) ((x)->rsi) #define PT_REGS_PARM3(x) ((x)->rdx) @@ -84,6 +111,18 @@ #define PT_REGS_RC(x) ((x)->rax) #define PT_REGS_SP(x) ((x)->rsp) #define PT_REGS_IP(x) ((x)->rip) + +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip) + #endif #endif @@ -104,6 +143,17 @@ struct pt_regs; #define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15]) #define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr) +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3]) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4]) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5]) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14]) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11]) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15]) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr) + #elif defined(bpf_target_arm) #define PT_REGS_PARM1(x) ((x)->uregs[0]) @@ -117,6 +167,17 @@ struct pt_regs; #define PT_REGS_SP(x) ((x)->uregs[13]) #define PT_REGS_IP(x) ((x)->uregs[12]) +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0]) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1]) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2]) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3]) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14]) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11]) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0]) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13]) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12]) + #elif defined(bpf_target_arm64) /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ @@ -134,6 +195,17 @@ struct pt_regs; #define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp) #define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc) +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0]) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1]) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2]) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3]) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30]) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29]) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0]) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc) + #elif defined(bpf_target_mips) #define PT_REGS_PARM1(x) ((x)->regs[4]) @@ -147,6 +219,17 @@ struct pt_regs; #define PT_REGS_SP(x) ((x)->regs[29]) #define PT_REGS_IP(x) ((x)->cp0_epc) +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4]) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5]) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6]) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7]) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31]) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30]) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[1]) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29]) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc) + #elif defined(bpf_target_powerpc) #define PT_REGS_PARM1(x) ((x)->gpr[3]) @@ -158,6 +241,15 @@ struct pt_regs; #define PT_REGS_SP(x) ((x)->sp) #define PT_REGS_IP(x) ((x)->nip) +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3]) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4]) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5]) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6]) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7]) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3]) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip) + #elif defined(bpf_target_sparc) #define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0]) @@ -169,11 +261,22 @@ struct pt_regs; #define PT_REGS_RC(x) ((x)->u_regs[UREG_I0]) #define PT_REGS_SP(x) ((x)->u_regs[UREG_FP]) +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0]) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1]) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2]) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3]) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7]) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0]) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP]) + /* Should this also be a bpf_target check for the sparc case? */ #if defined(__arch64__) #define PT_REGS_IP(x) ((x)->tpc) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc) #else #define PT_REGS_IP(x) ((x)->pc) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc) #endif #endif @@ -192,4 +295,122 @@ struct pt_regs; (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) #endif +#define ___bpf_concat(a, b) a ## b +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#define ___bpf_narg(...) \ + ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#define ___bpf_empty(...) \ + ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) + +#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_cast(args...) \ + ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) + +/* + * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and + * similar kinds of BPF programs, that accept input arguments as a single + * pointer to untyped u64 array, where each u64 can actually be a typed + * pointer or integer of different size. Instead of requring user to write + * manual casts and work with array elements by index, BPF_PROG macro + * allows user to declare a list of named and typed input arguments in the + * same syntax as for normal C function. All the casting is hidden and + * performed transparently, while user code can just assume working with + * function arguments of specified type and name. + * + * Original raw context argument is preserved as well as 'ctx' argument. + * This is useful when using BPF helpers that expect original context + * as one of the parameters (e.g., for bpf_perf_event_output()). + */ +#define BPF_PROG(name, args...) \ +name(unsigned long long *ctx); \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_ctx_cast(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(unsigned long long *ctx, ##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_args(args...) \ + ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) + +/* + * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for + * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific + * low-level way of getting kprobe input arguments from struct pt_regs, and + * provides a familiar typed and named function arguments syntax and + * semantics of accessing kprobe input paremeters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + */ +#define BPF_KPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __attribute__((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_RET(ctx) +#define ___bpf_kretprobe_args(args...) \ + ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) + +/* + * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional + * return value (in addition to `struct pt_regs *ctx`), but no input + * arguments, because they will be clobbered by the time probed function + * returns. + */ +#define BPF_KRETPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kretprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) + #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index bd09ed1710f1..0c28ee82834b 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -916,13 +916,13 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, /* enumerators share namespace with typedef idents */ dup_cnt = btf_dump_name_dups(d, d->ident_names, name); if (dup_cnt > 1) { - btf_dump_printf(d, "\n%s%s___%zu = %d,", + btf_dump_printf(d, "\n%s%s___%zu = %u,", pfx(lvl + 1), name, dup_cnt, - (__s32)v->val); + (__u32)v->val); } else { - btf_dump_printf(d, "\n%s%s = %d,", + btf_dump_printf(d, "\n%s%s = %u,", pfx(lvl + 1), name, - (__s32)v->val); + (__u32)v->val); } } btf_dump_printf(d, "\n%s}", pfx(lvl)); @@ -1030,7 +1030,7 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts)) return -EINVAL; - fname = OPTS_GET(opts, field_name, NULL); + fname = OPTS_GET(opts, field_name, ""); lvl = OPTS_GET(opts, indent_level, 0); btf_dump_emit_type_decl(d, id, fname, lvl); return 0; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 996162801f7a..085e41f9b68e 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2284,9 +2284,16 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) } } -static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) +static bool libbpf_needs_btf(const struct bpf_object *obj) { - return obj->efile.st_ops_shndx >= 0 || obj->nr_extern > 0; + return obj->efile.btf_maps_shndx >= 0 || + obj->efile.st_ops_shndx >= 0 || + obj->nr_extern > 0; +} + +static bool kernel_needs_btf(const struct bpf_object *obj) +{ + return obj->efile.st_ops_shndx >= 0; } static int bpf_object__init_btf(struct bpf_object *obj, @@ -2322,7 +2329,7 @@ static int bpf_object__init_btf(struct bpf_object *obj, } } out: - if (err && bpf_object__is_btf_mandatory(obj)) { + if (err && libbpf_needs_btf(obj)) { pr_warn("BTF is required, but is missing or corrupted.\n"); return err; } @@ -2346,7 +2353,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj) btf_ext__free(obj->btf_ext); obj->btf_ext = NULL; - if (bpf_object__is_btf_mandatory(obj)) { + if (libbpf_needs_btf(obj)) { pr_warn("BTF is required, but is missing or corrupted.\n"); return -ENOENT; } @@ -2410,7 +2417,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) obj->btf_ext = NULL; } - if (bpf_object__is_btf_mandatory(obj)) + if (kernel_needs_btf(obj)) return err; } return 0; @@ -3866,6 +3873,10 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, if (str_is_empty(targ_name)) continue; + t = skip_mods_and_typedefs(targ_btf, i, NULL); + if (!btf_is_composite(t) && !btf_is_array(t)) + continue; + targ_essent_len = bpf_core_essential_name_len(targ_name); if (targ_essent_len != local_essent_len) continue; @@ -6288,6 +6299,10 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_FENTRY, .is_attach_btf = true, .attach_fn = attach_trace), + SEC_DEF("fmod_ret/", TRACING, + .expected_attach_type = BPF_MODIFY_RETURN, + .is_attach_btf = true, + .attach_fn = attach_trace), SEC_DEF("fexit/", TRACING, .expected_attach_type = BPF_TRACE_FEXIT, .is_attach_btf = true, @@ -6931,6 +6946,8 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, struct bpf_link { int (*detach)(struct bpf_link *link); int (*destroy)(struct bpf_link *link); + char *pin_path; /* NULL, if not pinned */ + int fd; /* hook FD, -1 if not applicable */ bool disconnected; }; @@ -6960,26 +6977,109 @@ int bpf_link__destroy(struct bpf_link *link) err = link->detach(link); if (link->destroy) link->destroy(link); + if (link->pin_path) + free(link->pin_path); free(link); return err; } -struct bpf_link_fd { - struct bpf_link link; /* has to be at the top of struct */ - int fd; /* hook FD */ -}; +int bpf_link__fd(const struct bpf_link *link) +{ + return link->fd; +} + +const char *bpf_link__pin_path(const struct bpf_link *link) +{ + return link->pin_path; +} + +static int bpf_link__detach_fd(struct bpf_link *link) +{ + return close(link->fd); +} + +struct bpf_link *bpf_link__open(const char *path) +{ + struct bpf_link *link; + int fd; + + fd = bpf_obj_get(path); + if (fd < 0) { + fd = -errno; + pr_warn("failed to open link at %s: %d\n", path, fd); + return ERR_PTR(fd); + } + + link = calloc(1, sizeof(*link)); + if (!link) { + close(fd); + return ERR_PTR(-ENOMEM); + } + link->detach = &bpf_link__detach_fd; + link->fd = fd; + + link->pin_path = strdup(path); + if (!link->pin_path) { + bpf_link__destroy(link); + return ERR_PTR(-ENOMEM); + } + + return link; +} + +int bpf_link__pin(struct bpf_link *link, const char *path) +{ + int err; + + if (link->pin_path) + return -EBUSY; + err = make_parent_dir(path); + if (err) + return err; + err = check_path(path); + if (err) + return err; + + link->pin_path = strdup(path); + if (!link->pin_path) + return -ENOMEM; + + if (bpf_obj_pin(link->fd, link->pin_path)) { + err = -errno; + zfree(&link->pin_path); + return err; + } + + pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path); + return 0; +} + +int bpf_link__unpin(struct bpf_link *link) +{ + int err; + + if (!link->pin_path) + return -EINVAL; + + err = unlink(link->pin_path); + if (err != 0) + return -errno; + + pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path); + zfree(&link->pin_path); + return 0; +} static int bpf_link__detach_perf_event(struct bpf_link *link) { - struct bpf_link_fd *l = (void *)link; int err; - err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0); + err = ioctl(link->fd, PERF_EVENT_IOC_DISABLE, 0); if (err) err = -errno; - close(l->fd); + close(link->fd); return err; } @@ -6987,7 +7087,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd) { char errmsg[STRERR_BUFSIZE]; - struct bpf_link_fd *link; + struct bpf_link *link; int prog_fd, err; if (pfd < 0) { @@ -7005,7 +7105,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.detach = &bpf_link__detach_perf_event; + link->detach = &bpf_link__detach_perf_event; link->fd = pfd; if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { @@ -7024,7 +7124,7 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); return ERR_PTR(err); } - return (struct bpf_link *)link; + return link; } /* @@ -7312,18 +7412,11 @@ out: return link; } -static int bpf_link__detach_fd(struct bpf_link *link) -{ - struct bpf_link_fd *l = (void *)link; - - return close(l->fd); -} - struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, const char *tp_name) { char errmsg[STRERR_BUFSIZE]; - struct bpf_link_fd *link; + struct bpf_link *link; int prog_fd, pfd; prog_fd = bpf_program__fd(prog); @@ -7336,7 +7429,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.detach = &bpf_link__detach_fd; + link->detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); if (pfd < 0) { @@ -7348,7 +7441,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return ERR_PTR(pfd); } link->fd = pfd; - return (struct bpf_link *)link; + return link; } static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, @@ -7362,7 +7455,7 @@ static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; - struct bpf_link_fd *link; + struct bpf_link *link; int prog_fd, pfd; prog_fd = bpf_program__fd(prog); @@ -7375,7 +7468,7 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.detach = &bpf_link__detach_fd; + link->detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(NULL, prog_fd); if (pfd < 0) { @@ -7409,10 +7502,9 @@ struct bpf_link *bpf_program__attach(struct bpf_program *prog) static int bpf_link__detach_struct_ops(struct bpf_link *link) { - struct bpf_link_fd *l = (void *)link; __u32 zero = 0; - if (bpf_map_delete_elem(l->fd, &zero)) + if (bpf_map_delete_elem(link->fd, &zero)) return -errno; return 0; @@ -7421,7 +7513,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link) struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) { struct bpf_struct_ops *st_ops; - struct bpf_link_fd *link; + struct bpf_link *link; __u32 i, zero = 0; int err; @@ -7453,10 +7545,10 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) return ERR_PTR(err); } - link->link.detach = bpf_link__detach_struct_ops; + link->detach = bpf_link__detach_struct_ops; link->fd = map->fd; - return (struct bpf_link *)link; + return link; } enum bpf_perf_event_ret diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 02fc58a21a7f..d38d7a629417 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -219,6 +219,11 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog); struct bpf_link; +LIBBPF_API struct bpf_link *bpf_link__open(const char *path); +LIBBPF_API int bpf_link__fd(const struct bpf_link *link); +LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link); +LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); +LIBBPF_API int bpf_link__unpin(struct bpf_link *link); LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 7b014c8cdece..5129283c0284 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -238,5 +238,10 @@ LIBBPF_0.0.7 { LIBBPF_0.0.8 { global: + bpf_link__fd; + bpf_link__open; + bpf_link__pin; + bpf_link__pin_path; + bpf_link__unpin; bpf_program__set_attach_target; } LIBBPF_0.0.7; diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index ded7a950dc40..59f31f01cb93 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -106,6 +106,7 @@ ifneq ($(silent),1) ifneq ($(V),1) QUIET_CC = @echo ' CC '$@; QUIET_CC_FPIC = @echo ' CC FPIC '$@; + QUIET_CLANG = @echo ' CLANG '$@; QUIET_AR = @echo ' AR '$@; QUIET_LINK = @echo ' LINK '$@; QUIET_MKDIR = @echo ' MKDIR '$@; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index ec464859c6b6..2198cd876675 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -31,6 +31,7 @@ test_tcp_check_syncookie_user test_sysctl test_hashmap test_btf_dump +test_current_pid_tgid_new_ns xdping test_cpp *.skel.h diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 2d7f5df33f04..7729892e0b04 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -20,8 +20,9 @@ CLANG ?= clang LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy BPF_GCC ?= $(shell command -v bpf-gcc;) -CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR) \ +CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -I$(CURDIR) \ -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \ + -I$(APIDIR) \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program LDLIBS += -lcap -lelf -lz -lrt -lpthread @@ -32,7 +33,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ test_cgroup_storage \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ - test_progs-no_alu32 + test_progs-no_alu32 \ + test_current_pid_tgid_new_ns # Also test bpf-gcc, if present ifneq ($(BPF_GCC),) @@ -129,10 +131,13 @@ $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) $(call msg,CC,,$@) $(CC) -c $(CFLAGS) -o $@ $< -VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux) \ - /sys/kernel/btf/vmlinux \ - /boot/vmlinux-$(shell uname -r) -VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS))) +VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) + $(OUTPUT)/runqslower: $(BPFOBJ) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \ @@ -172,6 +177,10 @@ $(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR): $(call msg,MKDIR,,$@) mkdir -p $@ +$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) | $(BPFTOOL) $(INCLUDE_DIR) + $(call msg,GEN,,$@) + $(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ + # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. @@ -190,8 +199,8 @@ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ - -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi \ - -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include) + -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ + -I$(abspath $(OUTPUT)/../usr/include) CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ -Wno-compare-distinct-pointer-types @@ -280,6 +289,7 @@ $(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs := y $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ + $$(INCLUDE_DIR)/vmlinux.h \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS), \ diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h index 8f21965ffc6c..5bf2fe9b1efa 100644 --- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h +++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h @@ -6,7 +6,7 @@ #include <linux/types.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> #define BPF_STRUCT_OPS(name, args...) \ SEC("struct_ops/"#name) \ diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h deleted file mode 100644 index c6f1354d93fb..000000000000 --- a/tools/testing/selftests/bpf/bpf_trace_helpers.h +++ /dev/null @@ -1,120 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __BPF_TRACE_HELPERS_H -#define __BPF_TRACE_HELPERS_H - -#include <bpf/bpf_helpers.h> - -#define ___bpf_concat(a, b) a ## b -#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) -#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N -#define ___bpf_narg(...) \ - ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) -#define ___bpf_empty(...) \ - ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) - -#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_cast(args...) \ - ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) - -/* - * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and - * similar kinds of BPF programs, that accept input arguments as a single - * pointer to untyped u64 array, where each u64 can actually be a typed - * pointer or integer of different size. Instead of requring user to write - * manual casts and work with array elements by index, BPF_PROG macro - * allows user to declare a list of named and typed input arguments in the - * same syntax as for normal C function. All the casting is hidden and - * performed transparently, while user code can just assume working with - * function arguments of specified type and name. - * - * Original raw context argument is preserved as well as 'ctx' argument. - * This is useful when using BPF helpers that expect original context - * as one of the parameters (e.g., for bpf_perf_event_output()). - */ -#define BPF_PROG(name, args...) \ -name(unsigned long long *ctx); \ -static __always_inline typeof(name(0)) \ -____##name(unsigned long long *ctx, ##args); \ -typeof(name(0)) name(unsigned long long *ctx) \ -{ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_ctx_cast(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __always_inline typeof(name(0)) \ -____##name(unsigned long long *ctx, ##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_args(args...) \ - ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) - -/* - * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for - * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific - * low-level way of getting kprobe input arguments from struct pt_regs, and - * provides a familiar typed and named function arguments syntax and - * semantics of accessing kprobe input paremeters. - * - * Original struct pt_regs* context is preserved as 'ctx' argument. This might - * be necessary when using BPF helpers like bpf_perf_event_output(). - */ -#define BPF_KPROBE(name, args...) \ -name(struct pt_regs *ctx); \ -static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\ -typeof(name(0)) name(struct pt_regs *ctx) \ -{ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_kprobe_args(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) - -#define ___bpf_kretprobe_args0() ctx -#define ___bpf_kretprobe_argsN(x, args...) \ - ___bpf_kprobe_args(args), (void *)PT_REGS_RET(ctx) -#define ___bpf_kretprobe_args(args...) \ - ___bpf_apply(___bpf_kretprobe_args, ___bpf_empty(args))(args) - -/* - * BPF_KRETPROBE is similar to BPF_KPROBE, except, in addition to listing all - * input kprobe arguments, one last extra argument has to be specified, which - * captures kprobe return value. - */ -#define BPF_KRETPROBE(name, args...) \ -name(struct pt_regs *ctx); \ -static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\ -typeof(name(0)) name(struct pt_regs *ctx) \ -{ \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - return ____##name(___bpf_kretprobe_args(args)); \ - _Pragma("GCC diagnostic pop") \ -} \ -static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) -#endif diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c index 5b13f2c6c402..70e94e783070 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -6,7 +6,7 @@ #define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" -char bpf_log_buf[BPF_LOG_BUF_SIZE]; +static char bpf_log_buf[BPF_LOG_BUF_SIZE]; static int prog_load(void) { diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index 2ff21dbce179..139f8e82c7c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -6,7 +6,7 @@ #define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" -char bpf_log_buf[BPF_LOG_BUF_SIZE]; +static char bpf_log_buf[BPF_LOG_BUF_SIZE]; static int map_fd = -1; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c index 9d8cb48b99de..9e96f8d87fea 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -8,7 +8,7 @@ #define BAR "/foo/bar/" #define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" -char bpf_log_buf[BPF_LOG_BUF_SIZE]; +static char bpf_log_buf[BPF_LOG_BUF_SIZE]; static int prog_load(int verdict) { diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 235ac4f67f5b..83493bd5745c 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,22 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "test_pkt_access.skel.h" #include "fentry_test.skel.h" #include "fexit_test.skel.h" void test_fentry_fexit(void) { - struct test_pkt_access *pkt_skel = NULL; struct fentry_test *fentry_skel = NULL; struct fexit_test *fexit_skel = NULL; __u64 *fentry_res, *fexit_res; __u32 duration = 0, retval; - int err, pkt_fd, i; + int err, prog_fd, i; - pkt_skel = test_pkt_access__open_and_load(); - if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) - return; fentry_skel = fentry_test__open_and_load(); if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) goto close_prog; @@ -31,8 +26,8 @@ void test_fentry_fexit(void) if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto close_prog; - pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), + prog_fd = bpf_program__fd(fexit_skel->progs.test1); + err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", "err %d errno %d retval %d duration %d\n", @@ -49,7 +44,6 @@ void test_fentry_fexit(void) } close_prog: - test_pkt_access__destroy(pkt_skel); fentry_test__destroy(fentry_skel); fexit_test__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 5cc06021f27d..04ebbf1cb390 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,20 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "test_pkt_access.skel.h" #include "fentry_test.skel.h" void test_fentry_test(void) { - struct test_pkt_access *pkt_skel = NULL; struct fentry_test *fentry_skel = NULL; - int err, pkt_fd, i; + int err, prog_fd, i; __u32 duration = 0, retval; __u64 *result; - pkt_skel = test_pkt_access__open_and_load(); - if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) - return; fentry_skel = fentry_test__open_and_load(); if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) goto cleanup; @@ -23,10 +18,10 @@ void test_fentry_test(void) if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) goto cleanup; - pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), + prog_fd = bpf_program__fd(fentry_skel->progs.test1); + err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", + CHECK(err || retval, "test_run", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); @@ -39,5 +34,4 @@ void test_fentry_test(void) cleanup: fentry_test__destroy(fentry_skel); - test_pkt_access__destroy(pkt_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index d2c3655dd7a3..78d7a2765c27 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -1,64 +1,37 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "fexit_test.skel.h" void test_fexit_test(void) { - struct bpf_prog_load_attr attr = { - .file = "./fexit_test.o", - }; - - char prog_name[] = "fexit/bpf_fentry_testX"; - struct bpf_object *obj = NULL, *pkt_obj; - int err, pkt_fd, kfree_skb_fd, i; - struct bpf_link *link[6] = {}; - struct bpf_program *prog[6]; + struct fexit_test *fexit_skel = NULL; + int err, prog_fd, i; __u32 duration = 0, retval; - struct bpf_map *data_map; - const int zero = 0; - u64 result[6]; + __u64 *result; - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) - return; - err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) - goto close_prog; + fexit_skel = fexit_test__open_and_load(); + if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) + goto cleanup; - for (i = 0; i < 6; i++) { - prog_name[sizeof(prog_name) - 2] = '1' + i; - prog[i] = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map = bpf_object__find_map_by_name(obj, "fexit_te.bss"); - if (CHECK(!data_map, "find_data_map", "data map not found\n")) - goto close_prog; + err = fexit_test__attach(fexit_skel); + if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) + goto cleanup; - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), + prog_fd = bpf_program__fd(fexit_skel->progs.test1); + err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", + CHECK(err || retval, "test_run", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - for (i = 0; i < 6; i++) - if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n", - i + 1, result[i])) - goto close_prog; + result = (__u64 *)fexit_skel->bss; + for (i = 0; i < 6; i++) { + if (CHECK(result[i] != 1, "result", + "fexit_test%d failed err %lld\n", i + 1, result[i])) + goto cleanup; + } -close_prog: - for (i = 0; i < 6; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - bpf_object__close(obj); - bpf_object__close(pkt_obj); +cleanup: + fexit_test__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/link_pinning.c b/tools/testing/selftests/bpf/prog_tests/link_pinning.c new file mode 100644 index 000000000000..a743288cf384 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/link_pinning.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> +#include <sys/stat.h> + +#include "test_link_pinning.skel.h" + +static int duration = 0; + +void test_link_pinning_subtest(struct bpf_program *prog, + struct test_link_pinning__bss *bss) +{ + const char *link_pin_path = "/sys/fs/bpf/pinned_link_test"; + struct stat statbuf = {}; + struct bpf_link *link; + int err, i; + + link = bpf_program__attach(prog); + if (CHECK(IS_ERR(link), "link_attach", "err: %ld\n", PTR_ERR(link))) + goto cleanup; + + bss->in = 1; + usleep(1); + CHECK(bss->out != 1, "res_check1", "exp %d, got %d\n", 1, bss->out); + + /* pin link */ + err = bpf_link__pin(link, link_pin_path); + if (CHECK(err, "link_pin", "err: %d\n", err)) + goto cleanup; + + CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path1", + "exp %s, got %s\n", link_pin_path, bpf_link__pin_path(link)); + + /* check that link was pinned */ + err = stat(link_pin_path, &statbuf); + if (CHECK(err, "stat_link", "err %d errno %d\n", err, errno)) + goto cleanup; + + bss->in = 2; + usleep(1); + CHECK(bss->out != 2, "res_check2", "exp %d, got %d\n", 2, bss->out); + + /* destroy link, pinned link should keep program attached */ + bpf_link__destroy(link); + link = NULL; + + bss->in = 3; + usleep(1); + CHECK(bss->out != 3, "res_check3", "exp %d, got %d\n", 3, bss->out); + + /* re-open link from BPFFS */ + link = bpf_link__open(link_pin_path); + if (CHECK(IS_ERR(link), "link_open", "err: %ld\n", PTR_ERR(link))) + goto cleanup; + + CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path2", + "exp %s, got %s\n", link_pin_path, bpf_link__pin_path(link)); + + /* unpin link from BPFFS, program still attached */ + err = bpf_link__unpin(link); + if (CHECK(err, "link_unpin", "err: %d\n", err)) + goto cleanup; + + /* still active, as we have FD open now */ + bss->in = 4; + usleep(1); + CHECK(bss->out != 4, "res_check4", "exp %d, got %d\n", 4, bss->out); + + bpf_link__destroy(link); + link = NULL; + + /* Validate it's finally detached. + * Actual detachment might get delayed a bit, so there is no reliable + * way to validate it immediately here, let's count up for long enough + * and see if eventually output stops being updated + */ + for (i = 5; i < 10000; i++) { + bss->in = i; + usleep(1); + if (bss->out == i - 1) + break; + } + CHECK(i == 10000, "link_attached", "got to iteration #%d\n", i); + +cleanup: + if (!IS_ERR(link)) + bpf_link__destroy(link); +} + +void test_link_pinning(void) +{ + struct test_link_pinning* skel; + + skel = test_link_pinning__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + + if (test__start_subtest("pin_raw_tp")) + test_link_pinning_subtest(skel->progs.raw_tp_prog, skel->bss); + if (test__start_subtest("pin_tp_btf")) + test_link_pinning_subtest(skel->progs.tp_btf_prog, skel->bss); + + test_link_pinning__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c new file mode 100644 index 000000000000..97fec70c600b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include <test_progs.h> +#include "modify_return.skel.h" + +#define LOWER(x) ((x) & 0xffff) +#define UPPER(x) ((x) >> 16) + + +static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) +{ + struct modify_return *skel = NULL; + int err, prog_fd; + __u32 duration = 0, retval; + __u16 side_effect; + __s16 ret; + + skel = modify_return__open_and_load(); + if (CHECK(!skel, "skel_load", "modify_return skeleton failed\n")) + goto cleanup; + + err = modify_return__attach(skel); + if (CHECK(err, "modify_return", "attach failed: %d\n", err)) + goto cleanup; + + skel->bss->input_retval = input_retval; + prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); + err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, 0, + &retval, &duration); + + CHECK(err, "test_run", "err %d errno %d\n", err, errno); + + side_effect = UPPER(retval); + ret = LOWER(retval); + + CHECK(ret != want_ret, "test_run", + "unexpected ret: %d, expected: %d\n", ret, want_ret); + CHECK(side_effect != want_side_effect, "modify_return", + "unexpected side_effect: %d\n", side_effect); + + CHECK(skel->bss->fentry_result != 1, "modify_return", + "fentry failed\n"); + CHECK(skel->bss->fexit_result != 1, "modify_return", + "fexit failed\n"); + CHECK(skel->bss->fmod_ret_result != 1, "modify_return", + "fmod_ret failed\n"); + +cleanup: + modify_return__destroy(skel); +} + +void test_modify_return(void) +{ + run_test(0 /* input_retval */, + 1 /* want_side_effect */, + 4 /* want_ret */); + run_test(-EINVAL /* input_retval */, + 0 /* want_side_effect */, + -EINVAL /* want_ret */); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c new file mode 100644 index 000000000000..542240e16564 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Carlos Neira cneirabustos@gmail.com */ +#include <test_progs.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <sys/syscall.h> + +struct bss { + __u64 dev; + __u64 ino; + __u64 pid_tgid; + __u64 user_pid_tgid; +}; + +void test_ns_current_pid_tgid(void) +{ + const char *probe_name = "raw_tracepoint/sys_enter"; + const char *file = "test_ns_current_pid_tgid.o"; + int err, key = 0, duration = 0; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_map *bss_map; + struct bpf_object *obj; + struct bss bss; + struct stat st; + __u64 id; + + obj = bpf_object__open_file(file, NULL); + if (CHECK(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj))) + return; + + err = bpf_object__load(obj); + if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) + goto cleanup; + + bss_map = bpf_object__find_map_by_name(obj, "test_ns_.bss"); + if (CHECK(!bss_map, "find_bss_map", "failed\n")) + goto cleanup; + + prog = bpf_object__find_program_by_title(obj, probe_name); + if (CHECK(!prog, "find_prog", "prog '%s' not found\n", + probe_name)) + goto cleanup; + + memset(&bss, 0, sizeof(bss)); + pid_t tid = syscall(SYS_gettid); + pid_t pid = getpid(); + + id = (__u64) tid << 32 | pid; + bss.user_pid_tgid = id; + + if (CHECK_FAIL(stat("/proc/self/ns/pid", &st))) { + perror("Failed to stat /proc/self/ns/pid"); + goto cleanup; + } + + bss.dev = st.st_dev; + bss.ino = st.st_ino; + + err = bpf_map_update_elem(bpf_map__fd(bss_map), &key, &bss, 0); + if (CHECK(err, "setting_bss", "failed to set bss : %d\n", err)) + goto cleanup; + + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", + PTR_ERR(link))) { + link = NULL; + goto cleanup; + } + + /* trigger some syscalls */ + usleep(1); + + err = bpf_map_lookup_elem(bpf_map__fd(bss_map), &key, &bss); + if (CHECK(err, "set_bss", "failed to get bss : %d\n", err)) + goto cleanup; + + if (CHECK(id != bss.pid_tgid, "Compare user pid/tgid vs. bpf pid/tgid", + "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid)) + goto cleanup; +cleanup: + if (!link) { + bpf_link__destroy(link); + link = NULL; + } + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index a1dd13b34d4b..821b4146b7b6 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -805,12 +805,6 @@ static void test_config(int sotype, sa_family_t family, bool inany) char s[MAX_TEST_NAME]; const struct test *t; - /* SOCKMAP/SOCKHASH don't support UDP yet */ - if (sotype == SOCK_DGRAM && - (inner_map_type == BPF_MAP_TYPE_SOCKMAP || - inner_map_type == BPF_MAP_TYPE_SOCKHASH)) - return; - for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { if (t->need_sotype && t->need_sotype != sotype) continue; /* test not compatible with socket type */ diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index c6d6b685a946..4538bd08203f 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -14,6 +14,7 @@ void test_skb_ctx(void) .wire_len = 100, .gso_segs = 8, .mark = 9, + .gso_size = 10, }; struct bpf_prog_test_run_attr tattr = { .data_in = &pkt_v4, diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index b1b2acea0638..d7d65a700799 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -16,6 +16,7 @@ #include <pthread.h> #include <stdlib.h> #include <string.h> +#include <sys/select.h> #include <unistd.h> #include <bpf/bpf.h> @@ -25,6 +26,7 @@ #include "test_progs.h" #include "test_sockmap_listen.skel.h" +#define IO_TIMEOUT_SEC 30 #define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 @@ -44,9 +46,10 @@ /* Wrappers that fail the test on error and report it. */ -#define xaccept(fd, addr, len) \ +#define xaccept_nonblock(fd, addr, len) \ ({ \ - int __ret = accept((fd), (addr), (len)); \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ if (__ret == -1) \ FAIL_ERRNO("accept"); \ __ret; \ @@ -108,6 +111,23 @@ __ret; \ }) +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + #define xsocket(family, sotype, flags) \ ({ \ int __ret = socket(family, sotype, flags); \ @@ -175,6 +195,40 @@ __ret; \ }) +static int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len) { struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); @@ -230,7 +284,7 @@ static int enable_reuseport(int s, int progfd) return 0; } -static int listen_loopback_reuseport(int family, int sotype, int progfd) +static int socket_loopback_reuseport(int family, int sotype, int progfd) { struct sockaddr_storage addr; socklen_t len; @@ -249,6 +303,9 @@ static int listen_loopback_reuseport(int family, int sotype, int progfd) if (err) goto close; + if (sotype & SOCK_DGRAM) + return s; + err = xlisten(s, SOMAXCONN); if (err) goto close; @@ -259,9 +316,9 @@ close: return -1; } -static int listen_loopback(int family, int sotype) +static int socket_loopback(int family, int sotype) { - return listen_loopback_reuseport(family, sotype, -1); + return socket_loopback_reuseport(family, sotype, -1); } static void test_insert_invalid(int family, int sotype, int mapfd) @@ -327,13 +384,13 @@ close: xclose(s); } -static void test_insert_listening(int family, int sotype, int mapfd) +static void test_insert(int family, int sotype, int mapfd) { u64 value; u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -349,7 +406,7 @@ static void test_delete_after_insert(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -366,7 +423,7 @@ static void test_delete_after_close(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -390,7 +447,7 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -417,7 +474,7 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -439,7 +496,7 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd) u32 key, value32; int err, s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -464,17 +521,17 @@ close: xclose(s); } -static void test_update_listening(int family, int sotype, int mapfd) +static void test_update_existing(int family, int sotype, int mapfd) { int s1, s2; u64 value; u32 key; - s1 = listen_loopback(family, sotype); + s1 = socket_loopback(family, sotype); if (s1 < 0) return; - s2 = listen_loopback(family, sotype); + s2 = socket_loopback(family, sotype); if (s2 < 0) goto close_s1; @@ -500,7 +557,7 @@ static void test_destroy_orphan_child(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -534,7 +591,7 @@ static void test_clone_after_delete(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -570,7 +627,7 @@ static void test_accept_after_delete(int family, int sotype, int mapfd) socklen_t len; u64 value; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s == -1) return; @@ -598,7 +655,7 @@ static void test_accept_after_delete(int family, int sotype, int mapfd) if (err) goto close_cli; - p = xaccept(s, NULL, NULL); + p = xaccept_nonblock(s, NULL, NULL); if (p == -1) goto close_cli; @@ -624,7 +681,7 @@ static void test_accept_before_delete(int family, int sotype, int mapfd) socklen_t len; u64 value; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s == -1) return; @@ -647,7 +704,7 @@ static void test_accept_before_delete(int family, int sotype, int mapfd) if (err) goto close_cli; - p = xaccept(s, NULL, NULL); + p = xaccept_nonblock(s, NULL, NULL); if (p == -1) goto close_cli; @@ -711,7 +768,7 @@ static void *connect_accept_thread(void *arg) break; } - p = xaccept(s, NULL, NULL); + p = xaccept_nonblock(s, NULL, NULL); if (p < 0) { xclose(c); break; @@ -735,7 +792,7 @@ static void test_syn_recv_insert_delete(int family, int sotype, int mapfd) int err, s; u64 value; - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -877,7 +934,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, zero_verdict_count(verd_mapfd); - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -893,7 +950,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (err) goto close_cli0; - p0 = xaccept(s, NULL, NULL); + p0 = xaccept_nonblock(s, NULL, NULL); if (p0 < 0) goto close_cli0; @@ -904,7 +961,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (err) goto close_cli1; - p1 = xaccept(s, NULL, NULL); + p1 = xaccept_nonblock(s, NULL, NULL); if (p1 < 0) goto close_cli1; @@ -1009,7 +1066,7 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd, zero_verdict_count(verd_mapfd); - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -1025,7 +1082,7 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd, if (err) goto close_cli; - p = xaccept(s, NULL, NULL); + p = xaccept_nonblock(s, NULL, NULL); if (p < 0) goto close_cli; @@ -1113,14 +1170,15 @@ static void test_reuseport_select_listening(int family, int sotype, { struct sockaddr_storage addr; unsigned int pass; - int s, c, p, err; + int s, c, err; socklen_t len; u64 value; u32 key; zero_verdict_count(verd_map); - s = listen_loopback_reuseport(family, sotype, reuseport_prog); + s = socket_loopback_reuseport(family, sotype | SOCK_NONBLOCK, + reuseport_prog); if (s < 0) return; @@ -1142,19 +1200,33 @@ static void test_reuseport_select_listening(int family, int sotype, if (err) goto close_cli; - p = xaccept(s, NULL, NULL); - if (p < 0) - goto close_cli; + if (sotype == SOCK_STREAM) { + int p; + + p = xaccept_nonblock(s, NULL, NULL); + if (p < 0) + goto close_cli; + xclose(p); + } else { + char b = 'a'; + ssize_t n; + + n = xsend(c, &b, sizeof(b), 0); + if (n == -1) + goto close_cli; + + n = xrecv_nonblock(s, &b, sizeof(b), 0); + if (n == -1) + goto close_cli; + } key = SK_PASS; err = xbpf_map_lookup_elem(verd_map, &key, &pass); if (err) - goto close_peer; + goto close_cli; if (pass != 1) FAIL("want pass count 1, have %d", pass); -close_peer: - xclose(p); close_cli: xclose(c); close_srv: @@ -1174,7 +1246,7 @@ static void test_reuseport_select_connected(int family, int sotype, zero_verdict_count(verd_map); - s = listen_loopback_reuseport(family, sotype, reuseport_prog); + s = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s < 0) return; @@ -1198,9 +1270,24 @@ static void test_reuseport_select_connected(int family, int sotype, if (err) goto close_cli0; - p0 = xaccept(s, NULL, NULL); - if (err) - goto close_cli0; + if (sotype == SOCK_STREAM) { + p0 = xaccept_nonblock(s, NULL, NULL); + if (p0 < 0) + goto close_cli0; + } else { + p0 = xsocket(family, sotype, 0); + if (p0 < 0) + goto close_cli0; + + len = sizeof(addr); + err = xgetsockname(c0, sockaddr(&addr), &len); + if (err) + goto close_cli0; + + err = xconnect(p0, sockaddr(&addr), len); + if (err) + goto close_cli0; + } /* Update sock_map[0] to redirect to a connected socket */ key = 0; @@ -1213,8 +1300,24 @@ static void test_reuseport_select_connected(int family, int sotype, if (c1 < 0) goto close_peer0; + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + errno = 0; err = connect(c1, sockaddr(&addr), len); + if (sotype == SOCK_DGRAM) { + char b = 'a'; + ssize_t n; + + n = xsend(c1, &b, sizeof(b), 0); + if (n == -1) + goto close_cli1; + + n = recv_timeout(c1, &b, sizeof(b), 0, IO_TIMEOUT_SEC); + err = n == -1; + } if (!err || errno != ECONNREFUSED) FAIL_ERRNO("connect: expected ECONNREFUSED"); @@ -1249,11 +1352,11 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map, zero_verdict_count(verd_map); /* Create two listeners, each in its own reuseport group */ - s1 = listen_loopback_reuseport(family, sotype, reuseport_prog); + s1 = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s1 < 0) return; - s2 = listen_loopback_reuseport(family, sotype, reuseport_prog); + s2 = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s2 < 0) goto close_srv1; @@ -1278,7 +1381,18 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map, goto close_srv2; err = connect(c, sockaddr(&addr), len); - if (err && errno != ECONNREFUSED) { + if (sotype == SOCK_DGRAM) { + char b = 'a'; + ssize_t n; + + n = xsend(c, &b, sizeof(b), 0); + if (n == -1) + goto close_cli; + + n = recv_timeout(c, &b, sizeof(b), 0, IO_TIMEOUT_SEC); + err = n == -1; + } + if (!err || errno != ECONNREFUSED) { FAIL_ERRNO("connect: expected ECONNREFUSED"); goto close_cli; } @@ -1299,9 +1413,9 @@ close_srv1: xclose(s1); } -#define TEST(fn) \ +#define TEST(fn, ...) \ { \ - fn, #fn \ + fn, #fn, __VA_ARGS__ \ } static void test_ops_cleanup(const struct bpf_map *map) @@ -1350,18 +1464,31 @@ static const char *map_type_str(const struct bpf_map *map) } } +static const char *sotype_str(int sotype) +{ + switch (sotype) { + case SOCK_DGRAM: + return "UDP"; + case SOCK_STREAM: + return "TCP"; + default: + return "unknown"; + } +} + static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, int family, int sotype) { const struct op_test { void (*fn)(int family, int sotype, int mapfd); const char *name; + int sotype; } tests[] = { /* insert */ TEST(test_insert_invalid), TEST(test_insert_opened), - TEST(test_insert_bound), - TEST(test_insert_listening), + TEST(test_insert_bound, SOCK_STREAM), + TEST(test_insert), /* delete */ TEST(test_delete_after_insert), TEST(test_delete_after_close), @@ -1370,28 +1497,32 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, TEST(test_lookup_after_delete), TEST(test_lookup_32_bit_value), /* update */ - TEST(test_update_listening), + TEST(test_update_existing), /* races with insert/delete */ - TEST(test_destroy_orphan_child), - TEST(test_syn_recv_insert_delete), - TEST(test_race_insert_listen), + TEST(test_destroy_orphan_child, SOCK_STREAM), + TEST(test_syn_recv_insert_delete, SOCK_STREAM), + TEST(test_race_insert_listen, SOCK_STREAM), /* child clone */ - TEST(test_clone_after_delete), - TEST(test_accept_after_delete), - TEST(test_accept_before_delete), + TEST(test_clone_after_delete, SOCK_STREAM), + TEST(test_accept_after_delete, SOCK_STREAM), + TEST(test_accept_before_delete, SOCK_STREAM), }; - const char *family_name, *map_name; + const char *family_name, *map_name, *sotype_name; const struct op_test *t; char s[MAX_TEST_NAME]; int map_fd; family_name = family_str(family); map_name = map_type_str(map); + sotype_name = sotype_str(sotype); map_fd = bpf_map__fd(map); for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, - t->name); + snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name, + sotype_name, t->name); + + if (t->sotype != 0 && t->sotype != sotype) + continue; if (!test__start_subtest(s)) continue; @@ -1424,6 +1555,7 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map, for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, t->name); + if (!test__start_subtest(s)) continue; @@ -1438,26 +1570,31 @@ static void test_reuseport(struct test_sockmap_listen *skel, void (*fn)(int family, int sotype, int socket_map, int verdict_map, int reuseport_prog); const char *name; + int sotype; } tests[] = { TEST(test_reuseport_select_listening), TEST(test_reuseport_select_connected), TEST(test_reuseport_mixed_groups), }; int socket_map, verdict_map, reuseport_prog; - const char *family_name, *map_name; + const char *family_name, *map_name, *sotype_name; const struct reuseport_test *t; char s[MAX_TEST_NAME]; family_name = family_str(family); map_name = map_type_str(map); + sotype_name = sotype_str(sotype); socket_map = bpf_map__fd(map); verdict_map = bpf_map__fd(skel->maps.verdict_map); reuseport_prog = bpf_program__fd(skel->progs.prog_reuseport); for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, - t->name); + snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name, + sotype_name, t->name); + + if (t->sotype != 0 && t->sotype != sotype) + continue; if (!test__start_subtest(s)) continue; @@ -1470,8 +1607,10 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map, int family) { test_ops(skel, map, family, SOCK_STREAM); + test_ops(skel, map, family, SOCK_DGRAM); test_redir(skel, map, family, SOCK_STREAM); test_reuseport(skel, map, family, SOCK_STREAM); + test_reuseport(skel, map, family, SOCK_DGRAM); } void test_sockmap_listen(void) diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index f4cd60d6fba2..e08f6bb17700 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -188,7 +188,7 @@ static int start_server(void) }; int fd; - fd = socket(AF_INET, SOCK_STREAM, 0); + fd = socket(AF_INET, SOCK_STREAM | SOCK_NONBLOCK, 0); if (fd < 0) { log_err("Failed to create server socket"); return -1; @@ -205,6 +205,7 @@ static int start_server(void) static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER; static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER; +static volatile bool server_done = false; static void *server_thread(void *arg) { @@ -222,23 +223,24 @@ static void *server_thread(void *arg) if (CHECK_FAIL(err < 0)) { perror("Failed to listed on socket"); - return NULL; + return ERR_PTR(err); } - client_fd = accept(fd, (struct sockaddr *)&addr, &len); + while (!server_done) { + client_fd = accept(fd, (struct sockaddr *)&addr, &len); + if (client_fd == -1 && errno == EAGAIN) { + usleep(50); + continue; + } + break; + } if (CHECK_FAIL(client_fd < 0)) { perror("Failed to accept client"); - return NULL; + return ERR_PTR(err); } - /* Wait for the next connection (that never arrives) - * to keep this thread alive to prevent calling - * close() on client_fd. - */ - if (CHECK_FAIL(accept(fd, (struct sockaddr *)&addr, &len) >= 0)) { - perror("Unexpected success in second accept"); - return NULL; - } + while (!server_done) + usleep(50); close(client_fd); @@ -249,6 +251,7 @@ void test_tcp_rtt(void) { int server_fd, cgroup_fd; pthread_t tid; + void *server_res; cgroup_fd = test__join_cgroup("/tcp_rtt"); if (CHECK_FAIL(cgroup_fd < 0)) @@ -267,6 +270,11 @@ void test_tcp_rtt(void) pthread_mutex_unlock(&server_started_mtx); CHECK_FAIL(run_test(cgroup_fd, server_fd)); + + server_done = true; + pthread_join(tid, &server_res); + CHECK_FAIL(IS_ERR(server_res)); + close_server_fd: close(server_fd); close_cgroup_fd: diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c new file mode 100644 index 000000000000..04939eda1325 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> +#include <time.h> +#include "test_vmlinux.skel.h" + +#define MY_TV_NSEC 1337 + +static void nsleep() +{ + struct timespec ts = { .tv_nsec = MY_TV_NSEC }; + + (void)nanosleep(&ts, NULL); +} + +void test_vmlinux(void) +{ + int duration = 0, err; + struct test_vmlinux* skel; + struct test_vmlinux__bss *bss; + + skel = test_vmlinux__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + bss = skel->bss; + + err = test_vmlinux__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* trigger everything */ + nsleep(); + + CHECK(!bss->tp_called, "tp", "not called\n"); + CHECK(!bss->raw_tp_called, "raw_tp", "not called\n"); + CHECK(!bss->tp_btf_called, "tp_btf", "not called\n"); + CHECK(!bss->kprobe_called, "kprobe", "not called\n"); + CHECK(!bss->fentry_called, "fentry", "not called\n"); + +cleanup: + test_vmlinux__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index 4ba011031d4c..a0f688c37023 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -4,17 +4,51 @@ #include "test_xdp.skel.h" #include "test_xdp_bpf2bpf.skel.h" +struct meta { + int ifindex; + int pkt_len; +}; + +static void on_sample(void *ctx, int cpu, void *data, __u32 size) +{ + int duration = 0; + struct meta *meta = (struct meta *)data; + struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta); + + if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta), + "check_size", "size %u < %zu\n", + size, sizeof(pkt_v4) + sizeof(*meta))) + return; + + if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex", + "meta->ifindex = %d\n", meta->ifindex)) + return; + + if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len", + "meta->pkt_len = %zd\n", sizeof(pkt_v4))) + return; + + if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), + "check_packet_content", "content not the same\n")) + return; + + *(bool *)ctx = true; +} + void test_xdp_bpf2bpf(void) { __u32 duration = 0, retval, size; char buf[128]; int err, pkt_fd, map_fd; + bool passed = false; struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); struct iptnl_info value4 = {.family = AF_INET}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; struct bpf_program *prog; + struct perf_buffer *pb = NULL; + struct perf_buffer_opts pb_opts = {}; /* Load XDP program to introspect */ pkt_skel = test_xdp__open_and_load(); @@ -50,6 +84,14 @@ void test_xdp_bpf2bpf(void) if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err)) goto out; + /* Set up perf buffer */ + pb_opts.sample_cb = on_sample; + pb_opts.ctx = &passed; + pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), + 1, &pb_opts); + if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) + goto out; + /* Run test program */ err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); @@ -60,6 +102,15 @@ void test_xdp_bpf2bpf(void) err, errno, retval, size)) goto out; + /* Make sure bpf_xdp_output() was triggered and it sent the expected + * data to the perf ring buffer. + */ + err = perf_buffer__poll(pb, 100); + if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) + goto out; + + CHECK_FAIL(!passed); + /* Verify test results */ if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), "result", "fentry failed err %llu\n", @@ -70,6 +121,8 @@ void test_xdp_bpf2bpf(void) "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); out: + if (pb) + perf_buffer__free(pb); test_xdp__destroy(pkt_skel); test_xdp_bpf2bpf__destroy(ftrace_skel); } diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c index b631fb5032d2..127ea762a062 100644 --- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -9,7 +9,7 @@ #include <linux/bpf.h> #include <linux/types.h> #include <bpf/bpf_helpers.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> #include "bpf_tcp_helpers.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c index d4a02fe44a12..31975c96e2c9 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c @@ -13,7 +13,7 @@ enum e1 { enum e2 { C = 100, - D = -100, + D = 4294967295, E = 0, }; diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index 38d3a82144ca..9365b686f84b 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -2,7 +2,7 @@ /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c index c329fccf9842..98e1efe14549 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -5,7 +5,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> struct sk_buff { unsigned int len; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c index 92f3fa47cf40..85c0b516d6ee 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c @@ -2,7 +2,7 @@ /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> struct sk_buff { unsigned int len; diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c index 348109b9ea07..bd1e17d8024c 100644 --- a/tools/testing/selftests/bpf/progs/fexit_test.c +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -2,7 +2,7 @@ /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index 8f48a909f079..a46a264ce24e 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -4,7 +4,7 @@ #include <stdbool.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; struct { diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c new file mode 100644 index 000000000000..8b7466a15c6b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/modify_return.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +static int sequence = 0; +__s32 input_retval = 0; + +__u64 fentry_result = 0; +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(fentry_test, int a, __u64 b) +{ + sequence++; + fentry_result = (sequence == 1); + return 0; +} + +__u64 fmod_ret_result = 0; +SEC("fmod_ret/bpf_modify_return_test") +int BPF_PROG(fmod_ret_test, int a, int *b, int ret) +{ + sequence++; + /* This is the first fmod_ret program, the ret passed should be 0 */ + fmod_ret_result = (sequence == 2 && ret == 0); + return input_retval; +} + +__u64 fexit_result = 0; +SEC("fexit/bpf_modify_return_test") +int BPF_PROG(fexit_test, int a, __u64 b, int ret) +{ + sequence++; + /* If the input_reval is non-zero a successful modification should have + * occurred. + */ + if (input_retval) + fexit_result = (sequence == 3 && ret == input_retval); + else + fexit_result = (sequence == 3 && ret == 4); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c index dd8fae6660ab..8056a4c6d918 100644 --- a/tools/testing/selftests/bpf/progs/test_attach_probe.c +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -4,6 +4,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> int kprobe_res = 0; int kretprobe_res = 0; @@ -18,7 +19,7 @@ int handle_kprobe(struct pt_regs *ctx) } SEC("kretprobe/sys_nanosleep") -int handle_kretprobe(struct pt_regs *ctx) +int BPF_KRETPROBE(handle_kretprobe) { kretprobe_res = 2; return 0; diff --git a/tools/testing/selftests/bpf/progs/test_link_pinning.c b/tools/testing/selftests/bpf/progs/test_link_pinning.c new file mode 100644 index 000000000000..bbf2a5264dc0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_link_pinning.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int in = 0; +int out = 0; + +SEC("raw_tp/sys_enter") +int raw_tp_prog(const void *ctx) +{ + out = in; + return 0; +} + +SEC("tp_btf/sys_enter") +int tp_btf_prog(const void *ctx) +{ + out = in; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c new file mode 100644 index 000000000000..1dca70a6de2f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Carlos Neira cneirabustos@gmail.com */ + +#include <linux/bpf.h> +#include <stdint.h> +#include <bpf/bpf_helpers.h> + +static volatile struct { + __u64 dev; + __u64 ino; + __u64 pid_tgid; + __u64 user_pid_tgid; +} res; + +SEC("raw_tracepoint/sys_enter") +int trace(void *ctx) +{ + __u64 ns_pid_tgid, expected_pid; + struct bpf_pidns_info nsdata; + __u32 key = 0; + + if (bpf_get_ns_current_pid_tgid(res.dev, res.ino, &nsdata, + sizeof(struct bpf_pidns_info))) + return 0; + + ns_pid_tgid = (__u64)nsdata.tgid << 32 | nsdata.pid; + expected_pid = res.user_pid_tgid; + + if (expected_pid != ns_pid_tgid) + return 0; + + res.pid_tgid = ns_pid_tgid; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index bfe9fbcb9684..56a50b25cd33 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -6,7 +6,6 @@ #include <linux/ptrace.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bpf_trace_helpers.h" struct task_struct; @@ -17,11 +16,9 @@ int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec) } SEC("kretprobe/__set_task_comm") -int BPF_KRETPROBE(prog2, - struct task_struct *tsk, const char *buf, bool exec, - int ret) +int BPF_KRETPROBE(prog2, int ret) { - return !PT_REGS_PARM1(ctx) && ret; + return ret; } SEC("raw_tp/task_rename") diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c index 0f7e27d97567..a1ccc831c882 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_branches.c +++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c @@ -5,7 +5,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> int valid = 0; int required_size_out = 0; diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index ebfcc9f50c35..ad59c4c9aba8 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -4,7 +4,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_tracing.h> struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index d556b1572cc6..89b3532ccc75 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -7,7 +7,6 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bpf_trace_helpers.h" static struct sockaddr_in old; diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index 202de3938494..b02ea589ce7e 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -23,6 +23,8 @@ int process(struct __sk_buff *skb) return 1; if (skb->gso_segs != 8) return 1; + if (skb->gso_size != 10) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c index e51e6e3a81c2..f030e469d05b 100644 --- a/tools/testing/selftests/bpf/progs/test_trampoline_count.c +++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c @@ -2,7 +2,8 @@ #include <stdbool.h> #include <stddef.h> #include <linux/bpf.h> -#include "bpf_trace_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> struct task_struct; diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c new file mode 100644 index 000000000000..5611b564d3b1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <asm/unistd.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#define MY_TV_NSEC 1337 + +bool tp_called = false; +bool raw_tp_called = false; +bool tp_btf_called = false; +bool kprobe_called = false; +bool fentry_called = false; + +SEC("tp/syscalls/sys_enter_nanosleep") +int handle__tp(struct trace_event_raw_sys_enter *args) +{ + struct __kernel_timespec *ts; + + if (args->id != __NR_nanosleep) + return 0; + + ts = (void *)args->args[0]; + if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + return 0; + + tp_called = true; + return 0; +} + +SEC("raw_tp/sys_enter") +int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id) +{ + struct __kernel_timespec *ts; + + if (id != __NR_nanosleep) + return 0; + + ts = (void *)PT_REGS_PARM1_CORE(regs); + if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + return 0; + + raw_tp_called = true; + return 0; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) +{ + struct __kernel_timespec *ts; + + if (id != __NR_nanosleep) + return 0; + + ts = (void *)PT_REGS_PARM1_CORE(regs); + if (BPF_CORE_READ(ts, tv_nsec) != MY_TV_NSEC) + return 0; + + tp_btf_called = true; + return 0; +} + +SEC("kprobe/hrtimer_nanosleep") +int BPF_KPROBE(handle__kprobe, + ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid) +{ + if (rqtp == MY_TV_NSEC) + kprobe_called = true; + return 0; +} + +SEC("fentry/hrtimer_nanosleep") +int BPF_PROG(handle__fentry, + ktime_t rqtp, enum hrtimer_mode mode, clockid_t clockid) +{ + if (rqtp == MY_TV_NSEC) + fentry_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index b840fc9e3ed5..a038e827f850 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -1,7 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> +#include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> -#include "bpf_trace_helpers.h" + +char _license[] SEC("license") = "GPL"; struct net_device { /* Structure does not need to contain all entries, @@ -27,10 +29,32 @@ struct xdp_buff { struct xdp_rxq_info *rxq; } __attribute__((preserve_access_index)); +struct meta { + int ifindex; + int pkt_len; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} perf_buf_map SEC(".maps"); + __u64 test_result_fentry = 0; SEC("fentry/FUNC") int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) { + struct meta meta; + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + meta.ifindex = xdp->rxq->dev->ifindex; + meta.pkt_len = data_end - data; + bpf_xdp_output(xdp, &perf_buf_map, + ((__u64) meta.pkt_len << 32) | + BPF_F_CURRENT_CPU, + &meta, sizeof(meta)); + test_result_fentry = xdp->rxq->dev->ifindex; return 0; } diff --git a/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c new file mode 100644 index 000000000000..ed253f252cd0 --- /dev/null +++ b/tools/testing/selftests/bpf/test_current_pid_tgid_new_ns.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Carlos Neira cneirabustos@gmail.com */ +#define _GNU_SOURCE +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <sched.h> +#include <sys/wait.h> +#include <sys/mount.h> +#include "test_progs.h" + +#define CHECK_NEWNS(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + printf("%s:FAIL:%s ", __func__, tag); \ + printf(format); \ + } else { \ + printf("%s:PASS:%s\n", __func__, tag); \ + } \ + __ret; \ +}) + +struct bss { + __u64 dev; + __u64 ino; + __u64 pid_tgid; + __u64 user_pid_tgid; +}; + +int main(int argc, char **argv) +{ + pid_t pid; + int exit_code = 1; + struct stat st; + + printf("Testing bpf_get_ns_current_pid_tgid helper in new ns\n"); + + if (stat("/proc/self/ns/pid", &st)) { + perror("stat failed on /proc/self/ns/pid ns\n"); + printf("%s:FAILED\n", argv[0]); + return exit_code; + } + + if (CHECK_NEWNS(unshare(CLONE_NEWPID | CLONE_NEWNS), + "unshare CLONE_NEWPID | CLONE_NEWNS", "error errno=%d\n", errno)) + return exit_code; + + pid = fork(); + if (pid == -1) { + perror("Fork() failed\n"); + printf("%s:FAILED\n", argv[0]); + return exit_code; + } + + if (pid > 0) { + int status; + + usleep(5); + waitpid(pid, &status, 0); + return 0; + } else { + + pid = fork(); + if (pid == -1) { + perror("Fork() failed\n"); + printf("%s:FAILED\n", argv[0]); + return exit_code; + } + + if (pid > 0) { + int status; + waitpid(pid, &status, 0); + return 0; + } else { + if (CHECK_NEWNS(mount("none", "/proc", NULL, MS_PRIVATE|MS_REC, NULL), + "Unmounting proc", "Cannot umount proc! errno=%d\n", errno)) + return exit_code; + + if (CHECK_NEWNS(mount("proc", "/proc", "proc", MS_NOSUID|MS_NOEXEC|MS_NODEV, NULL), + "Mounting proc", "Cannot mount proc! errno=%d\n", errno)) + return exit_code; + + const char *probe_name = "raw_tracepoint/sys_enter"; + const char *file = "test_ns_current_pid_tgid.o"; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_map *bss_map; + struct bpf_object *obj; + int exit_code = 1; + int err, key = 0; + struct bss bss; + struct stat st; + __u64 id; + + obj = bpf_object__open_file(file, NULL); + if (CHECK_NEWNS(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj))) + return exit_code; + + err = bpf_object__load(obj); + if (CHECK_NEWNS(err, "obj_load", "err %d errno %d\n", err, errno)) + goto cleanup; + + bss_map = bpf_object__find_map_by_name(obj, "test_ns_.bss"); + if (CHECK_NEWNS(!bss_map, "find_bss_map", "failed\n")) + goto cleanup; + + prog = bpf_object__find_program_by_title(obj, probe_name); + if (CHECK_NEWNS(!prog, "find_prog", "prog '%s' not found\n", + probe_name)) + goto cleanup; + + memset(&bss, 0, sizeof(bss)); + pid_t tid = syscall(SYS_gettid); + pid_t pid = getpid(); + + id = (__u64) tid << 32 | pid; + bss.user_pid_tgid = id; + + if (CHECK_NEWNS(stat("/proc/self/ns/pid", &st), + "stat new ns", "Failed to stat /proc/self/ns/pid errno=%d\n", errno)) + goto cleanup; + + bss.dev = st.st_dev; + bss.ino = st.st_ino; + + err = bpf_map_update_elem(bpf_map__fd(bss_map), &key, &bss, 0); + if (CHECK_NEWNS(err, "setting_bss", "failed to set bss : %d\n", err)) + goto cleanup; + + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK_NEWNS(IS_ERR(link), "attach_raw_tp", "err %ld\n", + PTR_ERR(link))) { + link = NULL; + goto cleanup; + } + + /* trigger some syscalls */ + usleep(1); + + err = bpf_map_lookup_elem(bpf_map__fd(bss_map), &key, &bss); + if (CHECK_NEWNS(err, "set_bss", "failed to get bss : %d\n", err)) + goto cleanup; + + if (CHECK_NEWNS(id != bss.pid_tgid, "Compare user pid/tgid vs. bpf pid/tgid", + "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid)) + goto cleanup; + + exit_code = 0; + printf("%s:PASS\n", argv[0]); +cleanup: + if (!link) { + bpf_link__destroy(link); + link = NULL; + } + bpf_object__close(obj); + } + } +} diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index a969c77e9456..f85a06512541 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -29,6 +29,24 @@ struct prog_test_def { int old_error_cnt; }; +/* Override C runtime library's usleep() implementation to ensure nanosleep() + * is always called. Usleep is frequently used in selftests as a way to + * trigger kprobe and tracepoints. + */ +int usleep(useconds_t usec) +{ + struct timespec ts; + + if (usec > 999999) { + ts.tv_sec = usec / 1000000; + ts.tv_nsec = usec % 1000000; + } else { + ts.tv_sec = 0; + ts.tv_nsec = usec; + } + return nanosleep(&ts, NULL); +} + static bool should_run(struct test_selector *sel, int num, const char *name) { int i; @@ -198,7 +216,7 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) map = bpf_object__find_map_by_name(obj, name); if (!map) { - printf("%s:FAIL:map '%s' not found\n", test, name); + fprintf(stdout, "%s:FAIL:map '%s' not found\n", test, name); test__fail(); return -1; } @@ -369,7 +387,7 @@ static int libbpf_print_fn(enum libbpf_print_level level, { if (env.verbosity < VERBOSE_VERY && level == LIBBPF_DEBUG) return 0; - vprintf(format, args); + vfprintf(stdout, format, args); return 0; } @@ -615,7 +633,7 @@ int cd_flavor_subdir(const char *exec_name) if (!flavor) return 0; flavor++; - printf("Switching to flavor '%s' subdirectory...\n", flavor); + fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor); return chdir(flavor); } @@ -698,8 +716,8 @@ int main(int argc, char **argv) cleanup_cgroup_environment(); } stdio_restore(); - printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", - env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", + env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); free(env.test_selector.blacklist.strs); free(env.test_selector.whitelist.strs); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index bcfa9ef23fda..fd85fa61dbf7 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -109,10 +109,10 @@ extern struct ipv6_packet pkt_v6; int __save_errno = errno; \ if (__ret) { \ test__fail(); \ - printf("%s:FAIL:%s ", __func__, tag); \ - printf(format); \ + fprintf(stdout, "%s:FAIL:%s ", __func__, tag); \ + fprintf(stdout, ##format); \ } else { \ - printf("%s:PASS:%s %d nsec\n", \ + fprintf(stdout, "%s:PASS:%s %d nsec\n", \ __func__, tag, duration); \ } \ errno = __save_errno; \ @@ -124,7 +124,7 @@ extern struct ipv6_packet pkt_v6; int __save_errno = errno; \ if (__ret) { \ test__fail(); \ - printf("%s:FAIL:%d\n", __func__, __LINE__); \ + fprintf(stdout, "%s:FAIL:%d\n", __func__, __LINE__); \ } \ errno = __save_errno; \ __ret; \ diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index d438193804b2..2e16b8e268f2 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -1011,6 +1011,53 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "read gso_size from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, gso_size)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read gso_size from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, gso_size)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "write gso_size from CGROUP_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, gso_size)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=176 size=4", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read gso_size from CLS", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, gso_size)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ "check wire_len is not readable by sockets", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, |