add optional attributes for BPF_PROG_LOAD syscall: BPF_PROG_LOG_LEVEL, /* verbosity level of eBPF verifier */ BPF_PROG_LOG_BUF, /* user supplied buffer */ BPF_PROG_LOG_SIZE, /* size of user buffer */ In such case the verifier will return its verification log in the user supplied buffer which can be used by humans to analyze why verifier rejected given program Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxxxx> --- include/uapi/linux/bpf.h | 4 + kernel/bpf/syscall.c | 3 + kernel/bpf/verifier.c | 236 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 243 insertions(+) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7468fe55db7b..d280acad4b28 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -379,6 +379,10 @@ enum bpf_prog_attributes { BPF_PROG_UNSPEC, BPF_PROG_TEXT, /* array of eBPF instructions */ BPF_PROG_LICENSE, /* license string */ + /* optional program attributes */ + BPF_PROG_LOG_LEVEL, /* verbosity level of eBPF verifier */ + BPF_PROG_LOG_BUF, /* user supplied buffer */ + BPF_PROG_LOG_SIZE, /* size of user buffer */ __BPF_PROG_ATTR_MAX, }; #define BPF_PROG_ATTR_MAX (__BPF_PROG_ATTR_MAX - 1) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a3581646ee11..60cb760cb423 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -443,6 +443,9 @@ struct bpf_prog *bpf_prog_get(u32 ufd) static const struct nla_policy prog_policy[BPF_PROG_ATTR_MAX + 1] = { [BPF_PROG_TEXT] = { .type = NLA_BINARY }, [BPF_PROG_LICENSE] = { .type = NLA_NUL_STRING }, + [BPF_PROG_LOG_LEVEL] = { .type = NLA_U32 }, + [BPF_PROG_LOG_BUF] = { .len = sizeof(void *) }, + [BPF_PROG_LOG_SIZE] = { .type = NLA_U32 }, }; static int bpf_prog_load(enum bpf_prog_type type, struct nlattr __user *uattr, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c1dc2441994a..2484a3387ca2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -144,9 +144,245 @@ * load/store to bpf_context are checked against known fields */ +/* single container for all structs + * one verifier_env per bpf_check() call + */ +struct verifier_env { +}; + +/* verbose verifier prints what it's seeing + * bpf_check() is called under lock, so no race to access these global vars + */ +static u32 log_level, log_size, log_len; +static void *log_buf; + +static DEFINE_MUTEX(bpf_verifier_lock); + +/* log_level controls verbosity level of eBPF verifier. + * verbose() is used to dump the verification trace to the log, so the user + * can figure out what's wrong with the program + */ +static void verbose(const char *fmt, ...) +{ + va_list args; + + if (log_level == 0 || log_len >= log_size - 1) + return; + + va_start(args, fmt); + log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args); + va_end(args); +} + +static const char *const bpf_class_string[] = { + [BPF_LD] = "ld", + [BPF_LDX] = "ldx", + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_ALU] = "alu", + [BPF_JMP] = "jmp", + [BPF_RET] = "BUG", + [BPF_ALU64] = "alu64", +}; + +static const char *const bpf_alu_string[] = { + [BPF_ADD >> 4] = "+=", + [BPF_SUB >> 4] = "-=", + [BPF_MUL >> 4] = "*=", + [BPF_DIV >> 4] = "/=", + [BPF_OR >> 4] = "|=", + [BPF_AND >> 4] = "&=", + [BPF_LSH >> 4] = "<<=", + [BPF_RSH >> 4] = ">>=", + [BPF_NEG >> 4] = "neg", + [BPF_MOD >> 4] = "%=", + [BPF_XOR >> 4] = "^=", + [BPF_MOV >> 4] = "=", + [BPF_ARSH >> 4] = "s>>=", + [BPF_END >> 4] = "endian", +}; + +static const char *const bpf_ldst_string[] = { + [BPF_W >> 3] = "u32", + [BPF_H >> 3] = "u16", + [BPF_B >> 3] = "u8", + [BPF_DW >> 3] = "u64", +}; + +static const char *const bpf_jmp_string[] = { + [BPF_JA >> 4] = "jmp", + [BPF_JEQ >> 4] = "==", + [BPF_JGT >> 4] = ">", + [BPF_JGE >> 4] = ">=", + [BPF_JSET >> 4] = "&", + [BPF_JNE >> 4] = "!=", + [BPF_JSGT >> 4] = "s>", + [BPF_JSGE >> 4] = "s>=", + [BPF_CALL >> 4] = "call", + [BPF_EXIT >> 4] = "exit", +}; + +static void print_bpf_insn(struct bpf_insn *insn) +{ + u8 class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) == BPF_X) + verbose("(%02x) %sr%d %s %sr%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->src_reg); + else + verbose("(%02x) %sr%d %s %s%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->imm); + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_MEM) + verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->src_reg); + else if (BPF_MODE(insn->code) == BPF_XADD) + verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + else + verbose("BUG_%02x\n", insn->code); + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose("BUG_st_%02x\n", insn->code); + return; + } + verbose("(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (class == BPF_LDX) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose("BUG_ldx_%02x\n", insn->code); + return; + } + verbose("(%02x) r%d = *(%s *)(r%d %+d)\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (class == BPF_LD) { + if (BPF_MODE(insn->code) == BPF_ABS) { + verbose("(%02x) r0 = *(%s *)skb[%d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IND) { + verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IMM) { + verbose("(%02x) r%d = 0x%x\n", + insn->code, insn->dst_reg, insn->imm); + } else { + verbose("BUG_ld_%02x\n", insn->code); + return; + } + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + verbose("(%02x) call %d\n", insn->code, insn->imm); + } else if (insn->code == (BPF_JMP | BPF_JA)) { + verbose("(%02x) goto pc%+d\n", + insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_EXIT)) { + verbose("(%02x) exit\n", insn->code); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose("(%02x) if r%d %s r%d goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->src_reg, insn->off); + } else { + verbose("(%02x) if r%d %s 0x%x goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->imm, insn->off); + } + } else { + verbose("(%02x) %s\n", insn->code, bpf_class_string[class]); + } +} + int bpf_check(struct bpf_prog *prog, struct nlattr *tb[BPF_PROG_ATTR_MAX + 1]) { + void __user *log_ubuf = NULL; + struct verifier_env *env; int ret = -EINVAL; + if (prog->len <= 0 || prog->len > BPF_MAXINSNS) + return -E2BIG; + + /* 'struct verifier_env' can be global, but since it's not small, + * allocate/free it every time bpf_check() is called + */ + env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL); + if (!env) + return -ENOMEM; + + /* grab the mutex to protect few globals used by verifier */ + mutex_lock(&bpf_verifier_lock); + + if (tb[BPF_PROG_LOG_LEVEL] && tb[BPF_PROG_LOG_BUF] && + tb[BPF_PROG_LOG_SIZE]) { + /* user requested verbose verifier output + * and supplied buffer to store the verification trace + */ + log_level = nla_get_u32(tb[BPF_PROG_LOG_LEVEL]); + log_ubuf = *(void __user **) nla_data(tb[BPF_PROG_LOG_BUF]); + log_size = nla_get_u32(tb[BPF_PROG_LOG_SIZE]); + log_len = 0; + + ret = -EINVAL; + /* log_* values have to be sane */ + if (log_size < 128 || log_size > UINT_MAX >> 8 || + log_level == 0 || log_ubuf == NULL) + goto free_env; + + ret = -ENOMEM; + log_buf = vmalloc(log_size); + if (!log_buf) + goto free_env; + } else { + log_level = 0; + } + + /* ret = do_check(env); */ + + if (log_level && log_len >= log_size - 1) { + BUG_ON(log_len >= log_size); + /* verifier log exceeded user supplied buffer */ + ret = -ENOSPC; + /* fall through to return what was recorded */ + } + + /* copy verifier log back to user space including trailing zero */ + if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) { + ret = -EFAULT; + goto free_log_buf; + } + + +free_log_buf: + if (log_level) + vfree(log_buf); +free_env: + kfree(env); + mutex_unlock(&bpf_verifier_lock); return ret; } -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html