// SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "disasm.h" static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. * * The first pass is depth-first-search to check that the program is a DAG. * It rejects the following programs: * - larger than BPF_MAXINSNS insns * - if loop is present (detected via back-edge) * - unreachable insns exist (shouldn't be a forest. program = one function) * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. * Since it's analyzing all pathes through the program, the length of the * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k * * On entry to each instruction, each register has a type, and the instruction * changes the types of the registers depending on instruction semantics. * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is * copied to R1. * * All registers are 64-bit. * R0 - return register * R1-R5 argument passing registers * R6-R9 callee saved registers * R10 - frame pointer read-only * * At the start of BPF program the register R1 contains a pointer to bpf_context * and has type PTR_TO_CTX. * * Verifier tracks arithmetic operations on pointers in case: * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20), * 1st insn copies R10 (which has FRAME_PTR) type into R1 * and 2nd arithmetic instruction is pattern matched to recognize * that it wants to construct a pointer to some element within stack. * So after 2nd insn, the register R1 has type PTR_TO_STACK * (and -20 constant is saved for further stack bounds checking). * Meaning that this reg is a pointer to stack plus known immediate constant. * * Most of the time the registers have SCALAR_VALUE type, which * means the register has some value, but it's not a valid pointer. * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. * * registers used to pass values to function calls are checked against * function argument constraints. * * ARG_PTR_TO_MAP_KEY is one of such argument constraints. * It means that the register type passed to this function must be * PTR_TO_STACK and it will be used inside the function as * 'pointer to map element key' * * For example the argument constraints for bpf_map_lookup_elem(): * .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, * .arg1_type = ARG_CONST_MAP_PTR, * .arg2_type = ARG_PTR_TO_MAP_KEY, * * ret_type says that this function returns 'pointer to map elem value or null' * function expects 1st argument to be a const pointer to 'struct bpf_map' and * 2nd argument should be a pointer to stack, which will be used inside * the helper function as a pointer to map element key. * * On the kernel side the helper function looks like: * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) * { * struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; * void *key = (void *) (unsigned long) r2; * void *value; * * here kernel can access 'key' and 'map' pointers safely, knowing that * [key, key + map->key_size) bytes are valid and were initialized on * the stack of eBPF program. * } * * Corresponding eBPF program may look like: * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK * BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), * here verifier looks at prototype of map_lookup_elem() and sees: * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok, * Now verifier knows that this map has key of R1->map_ptr->key_size bytes * * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far, * Now verifier checks that [R2, R2 + map's key_size) are within stack limits * and were initialized prior to this call. * If it's ok, then verifier allows this BPF_CALL insn and looks at * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function * returns ether pointer to map value or NULL. * * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' * insn, the register holding that pointer in the true branch changes state to * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false * branch. See check_cond_jmp_op(). * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. * * The following reference types represent a potential reference to a kernel * resource which, after first being allocated, must be checked and freed by * the BPF program: * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET * * When the verifier sees a helper call return a reference type, it allocates a * pointer id for the reference and stores it in the current function state. * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type * passes through a NULL-check conditional. For the branch wherein the state is * changed to CONST_IMM, the verifier releases the reference. * * For each helper function that allocates a reference, such as * bpf_sk_lookup_tcp(), there is a corresponding release function, such as * bpf_sk_release(). When a reference type passes into the release function, * the verifier also releases the reference. If any unchecked or unreleased * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ struct bpf_verifier_stack_elem { /* verifer state is 'st' * before processing instruction 'insn_idx' * and after processing instruction 'prev_insn_idx' */ struct bpf_verifier_state st; int insn_idx; int prev_insn_idx; struct bpf_verifier_stack_elem *next; /* length of verifier log at the time this state was pushed on stack */ u32 log_pos; }; #define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 #define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_MAP_KEY_POISON (1ULL << 63) #define BPF_MAP_KEY_SEEN (1ULL << 62) #define BPF_MAP_PTR_UNPRIV 1UL #define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ POISON_POINTER_DELTA)) #define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV)) static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON; } static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) { return aux->map_ptr_state & BPF_MAP_PTR_UNPRIV; } static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, const struct bpf_map *map, bool unpriv) { BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV); unpriv |= bpf_map_ptr_unpriv(aux); aux->map_ptr_state = (unsigned long)map | (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); } static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & BPF_MAP_KEY_POISON; } static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux) { return !(aux->map_key_state & BPF_MAP_KEY_SEEN); } static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON); } static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) { bool poisoned = bpf_map_key_poisoned(aux); aux->map_key_state = state | BPF_MAP_KEY_SEEN | (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; bool pkt_access; int regno; int access_size; int mem_size; u64 msize_max_value; int ref_obj_id; int func_id; u32 btf_id; }; struct btf *btf_vmlinux; static DEFINE_MUTEX(bpf_verifier_lock); static const struct bpf_line_info * find_linfo(const struct bpf_verifier_env *env, u32 insn_off) { const struct bpf_line_info *linfo; const struct bpf_prog *prog; u32 i, nr_linfo; prog = env->prog; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || insn_off >= prog->len) return NULL; linfo = prog->aux->linfo; for (i = 1; i < nr_linfo; i++) if (insn_off < linfo[i].insn_off) break; return &linfo[i - 1]; } void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args) { unsigned int n; n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, "verifier log line truncated - local buffer too short\n"); n = min(log->len_total - log->len_used - 1, n); log->kbuf[n] = '\0'; if (log->level == BPF_LOG_KERNEL) { pr_err("BPF:%s\n", log->kbuf); return; } if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) log->len_used += n; else log->ubuf = NULL; } static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos) { char zero = 0; if (!bpf_verifier_log_needed(log)) return; log->len_used = new_pos; if (put_user(zero, log->ubuf + new_pos)) log->ubuf = NULL; } /* log_level controls verbosity level of eBPF verifier. * bpf_verifier_log_write() is used to dump the verification trace to the log, * so the user can figure out what's wrong with the program */ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } EXPORT_SYMBOL_GPL(bpf_verifier_log_write); __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { struct bpf_verifier_env *env = private_data; va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(log)) return; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } static const char *ltrim(const char *s) { while (isspace(*s)) s++; return s; } __printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...) { const struct bpf_line_info *linfo; if (!bpf_verifier_log_needed(&env->log)) return; linfo = find_linfo(env, insn_off); if (!linfo || linfo == env->prev_linfo) return; if (prefix_fmt) { va_list args; va_start(args, prefix_fmt); bpf_verifier_vlog(&env->log, prefix_fmt, args); va_end(args); } verbose(env, "%s\n", ltrim(btf_name_by_offset(env->prog->aux->btf, linfo->line_off))); env->prev_linfo = linfo; } static bool type_is_pkt_pointer(enum bpf_reg_type type) { return type == PTR_TO_PACKET || type == PTR_TO_PACKET_META; } static bool type_is_sk_pointer(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_SOCK_COMMON || type == PTR_TO_TCP_SOCK || type == PTR_TO_XDP_SOCK; } static bool reg_type_not_null(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || type == PTR_TO_SOCK_COMMON; } static bool reg_type_may_be_null(enum bpf_reg_type type) { return type == PTR_TO_MAP_VALUE_OR_NULL || type == PTR_TO_SOCKET_OR_NULL || type == PTR_TO_SOCK_COMMON_OR_NULL || type == PTR_TO_TCP_SOCK_OR_NULL || type == PTR_TO_BTF_ID_OR_NULL || type == PTR_TO_MEM_OR_NULL || type == PTR_TO_RDONLY_BUF_OR_NULL || type == PTR_TO_RDWR_BUF_OR_NULL; } static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && map_value_has_spin_lock(reg->map_ptr); } static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL || type == PTR_TO_TCP_SOCK || type == PTR_TO_TCP_SOCK_OR_NULL || type == PTR_TO_MEM || type == PTR_TO_MEM_OR_NULL; } static bool arg_type_may_be_refcounted(enum bpf_arg_type type) { return type == ARG_PTR_TO_SOCK_COMMON; } /* Determine whether the function releases some resources allocated by another * function call. The first reference type argument will be assumed to be * released by release_reference(). */ static bool is_release_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_release || func_id == BPF_FUNC_ringbuf_submit || func_id == BPF_FUNC_ringbuf_discard; } static bool may_be_acquire_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || func_id == BPF_FUNC_skc_lookup_tcp || func_id == BPF_FUNC_map_lookup_elem || func_id == BPF_FUNC_ringbuf_reserve; } static bool is_acquire_function(enum bpf_func_id func_id, const struct bpf_map *map) { enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC; if (func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || func_id == BPF_FUNC_skc_lookup_tcp || func_id == BPF_FUNC_ringbuf_reserve) return true; if (func_id == BPF_FUNC_map_lookup_elem && (map_type == BPF_MAP_TYPE_SOCKMAP || map_type == BPF_MAP_TYPE_SOCKHASH)) return true; return false; } static bool is_ptr_cast_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_tcp_sock || func_id == BPF_FUNC_sk_fullsock; } /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "inv", [PTR_TO_CTX] = "ctx", [CONST_PTR_TO_MAP] = "map_ptr", [PTR_TO_MAP_VALUE] = "map_value", [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", [PTR_TO_SOCKET] = "sock", [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", [PTR_TO_SOCK_COMMON] = "sock_common", [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_", [PTR_TO_MEM] = "mem", [PTR_TO_MEM_OR_NULL] = "mem_or_null", [PTR_TO_RDONLY_BUF] = "rdonly_buf", [PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null", [PTR_TO_RDWR_BUF] = "rdwr_buf", [PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null", }; static char slot_type_char[] = { [STACK_INVALID] = '?', [STACK_SPILL] = 'r', [STACK_MISC] = 'm', [STACK_ZERO] = '0', }; static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) verbose(env, "_"); if (live & REG_LIVE_READ) verbose(env, "r"); if (live & REG_LIVE_WRITTEN) verbose(env, "w"); if (live & REG_LIVE_DONE) verbose(env, "D"); } static struct bpf_func_state *func(struct bpf_verifier_env *env, const struct bpf_reg_state *reg) { struct bpf_verifier_state *cur = env->cur_state; return cur->frame[reg->frameno]; } const char *kernel_type_name(u32 id) { return btf_name_by_offset(btf_vmlinux, btf_type_by_id(btf_vmlinux, id)->name_off); } static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { const struct bpf_reg_state *reg; enum bpf_reg_type t; int i; if (state->frameno) verbose(env, " frame%d:", state->frameno); for (i = 0; i < MAX_BPF_REG; i++) { reg = &state->regs[i]; t = reg->type; if (t == NOT_INIT) continue; verbose(env, " R%d", i); print_liveness(env, reg->live); verbose(env, "=%s", reg_type_str[t]); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); } else { if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL) verbose(env, "%s", kernel_type_name(reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); if (t != SCALAR_VALUE) verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) verbose(env, ",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || t == PTR_TO_MAP_VALUE_OR_NULL) verbose(env, ",ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); if (tnum_is_const(reg->var_off)) { /* Typically an immediate SCALAR_VALUE, but * could be a pointer whose offset is too big * for reg->off */ verbose(env, ",imm=%llx", reg->var_off.value); } else { if (reg->smin_value != reg->umin_value && reg->smin_value != S64_MIN) verbose(env, ",smin_value=%lld", (long long)reg->smin_value); if (reg->smax_value != reg->umax_value && reg->smax_value != S64_MAX) verbose(env, ",smax_value=%lld", (long long)reg->smax_value); if (reg->umin_value != 0) verbose(env, ",umin_value=%llu", (unsigned long long)reg->umin_value); if (reg->umax_value != U64_MAX) verbose(env, ",umax_value=%llu", (unsigned long long)reg->umax_value); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, ",var_off=%s", tn_buf); } if (reg->s32_min_value != reg->smin_value && reg->s32_min_value != S32_MIN) verbose(env, ",s32_min_value=%d", (int)(reg->s32_min_value)); if (reg->s32_max_value != reg->smax_value && reg->s32_max_value != S32_MAX) verbose(env, ",s32_max_value=%d", (int)(reg->s32_max_value)); if (reg->u32_min_value != reg->umin_value && reg->u32_min_value != U32_MIN) verbose(env, ",u32_min_value=%d", (int)(reg->u32_min_value)); if (reg->u32_max_value != reg->umax_value && reg->u32_max_value != U32_MAX) verbose(env, ",u32_max_value=%d", (int)(reg->u32_max_value)); } verbose(env, ")"); } } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { char types_buf[BPF_REG_SIZE + 1]; bool valid = false; int j; for (j = 0; j < BPF_REG_SIZE; j++) { if (state->stack[i].slot_type[j] != STACK_INVALID) valid = true; types_buf[j] = slot_type_char[ state->stack[i].slot_type[j]]; } types_buf[BPF_REG_SIZE] = 0; if (!valid) continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); if (state->stack[i].slot_type[0] == STACK_SPILL) { reg = &state->stack[i].spilled_ptr; t = reg->type; verbose(env, "=%s", reg_type_str[t]); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) verbose(env, "%lld", reg->var_off.value + reg->off); } else { verbose(env, "=%s", types_buf); } } if (state->acquired_refs && state->refs[0].id) { verbose(env, " refs=%d", state->refs[0].id); for (i = 1; i < state->acquired_refs; i++) if (state->refs[i].id) verbose(env, ",%d", state->refs[i].id); } verbose(env, "\n"); } #define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \ static int copy_##NAME##_state(struct bpf_func_state *dst, \ const struct bpf_func_state *src) \ { \ if (!src->FIELD) \ return 0; \ if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \ /* internal bug, make state invalid to reject the program */ \ memset(dst, 0, sizeof(*dst)); \ return -EFAULT; \ } \ memcpy(dst->FIELD, src->FIELD, \ sizeof(*src->FIELD) * (src->COUNT / SIZE)); \ return 0; \ } /* copy_reference_state() */ COPY_STATE_FN(reference, acquired_refs, refs, 1) /* copy_stack_state() */ COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) #undef COPY_STATE_FN #define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \ static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \ bool copy_old) \ { \ u32 old_size = state->COUNT; \ struct bpf_##NAME##_state *new_##FIELD; \ int slot = size / SIZE; \ \ if (size <= old_size || !size) { \ if (copy_old) \ return 0; \ state->COUNT = slot * SIZE; \ if (!size && old_size) { \ kfree(state->FIELD); \ state->FIELD = NULL; \ } \ return 0; \ } \ new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \ GFP_KERNEL); \ if (!new_##FIELD) \ return -ENOMEM; \ if (copy_old) { \ if (state->FIELD) \ memcpy(new_##FIELD, state->FIELD, \ sizeof(*new_##FIELD) * (old_size / SIZE)); \ memset(new_##FIELD + old_size / SIZE, 0, \ sizeof(*new_##FIELD) * (size - old_size) / SIZE); \ } \ state->COUNT = slot * SIZE; \ kfree(state->FIELD); \ state->FIELD = new_##FIELD; \ return 0; \ } /* realloc_reference_state() */ REALLOC_STATE_FN(reference, acquired_refs, refs, 1) /* realloc_stack_state() */ REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) #undef REALLOC_STATE_FN /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from * the program calls into realloc_func_state() to grow the stack size. * Note there is a non-zero 'parent' pointer inside bpf_verifier_state * which realloc_stack_state() copies over. It points to previous * bpf_verifier_state which is never reallocated. */ static int realloc_func_state(struct bpf_func_state *state, int stack_size, int refs_size, bool copy_old) { int err = realloc_reference_state(state, refs_size, copy_old); if (err) return err; return realloc_stack_state(state, stack_size, copy_old); } /* Acquire a pointer id from the env and update the state->refs to include * this new pointer reference. * On success, returns a valid pointer id to associate with the register * On failure, returns a negative errno. */ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_func_state *state = cur_func(env); int new_ofs = state->acquired_refs; int id, err; err = realloc_reference_state(state, state->acquired_refs + 1, true); if (err) return err; id = ++env->id_gen; state->refs[new_ofs].id = id; state->refs[new_ofs].insn_idx = insn_idx; return id; } /* release function corresponding to acquire_reference_state(). Idempotent. */ static int release_reference_state(struct bpf_func_state *state, int ptr_id) { int i, last_idx; last_idx = state->acquired_refs - 1; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].id == ptr_id) { if (last_idx && i != last_idx) memcpy(&state->refs[i], &state->refs[last_idx], sizeof(*state->refs)); memset(&state->refs[last_idx], 0, sizeof(*state->refs)); state->acquired_refs--; return 0; } } return -EINVAL; } static int transfer_reference_state(struct bpf_func_state *dst, struct bpf_func_state *src) { int err = realloc_reference_state(dst, src->acquired_refs, false); if (err) return err; err = copy_reference_state(dst, src); if (err) return err; return 0; } static void free_func_state(struct bpf_func_state *state) { if (!state) return; kfree(state->refs); kfree(state->stack); kfree(state); } static void clear_jmp_history(struct bpf_verifier_state *state) { kfree(state->jmp_history); state->jmp_history = NULL; state->jmp_history_cnt = 0; } static void free_verifier_state(struct bpf_verifier_state *state, bool free_self) { int i; for (i = 0; i <= state->curframe; i++) { free_func_state(state->frame[i]); state->frame[i] = NULL; } clear_jmp_history(state); if (free_self) kfree(state); } /* copy verifier state from src to dst growing dst stack space * when necessary to accommodate larger src stack */ static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { int err; err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs, false); if (err) return err; memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); err = copy_reference_state(dst, src); if (err) return err; return copy_stack_state(dst, src); } static int copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src) { struct bpf_func_state *dst; u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt; int i, err; if (dst_state->jmp_history_cnt < src->jmp_history_cnt) { kfree(dst_state->jmp_history); dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER); if (!dst_state->jmp_history) return -ENOMEM; } memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz); dst_state->jmp_history_cnt = src->jmp_history_cnt; /* if dst has more stack frames then src frame, free them */ for (i = src->curframe + 1; i <= dst_state->curframe; i++) { free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; dst_state->active_spin_lock = src->active_spin_lock; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { dst = kzalloc(sizeof(*dst), GFP_KERNEL); if (!dst) return -ENOMEM; dst_state->frame[i] = dst; } err = copy_func_state(dst, src->frame[i]); if (err) return err; } return 0; } static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { while (st) { u32 br = --st->branches; /* WARN_ON(br > 1) technically makes sense here, * but see comment in push_stack(), hence: */ WARN_ONCE((int)br < 0, "BUG update_branch_counts:branches_to_explore=%d\n", br); if (br) break; st = st->parent; } } static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, int *insn_idx, bool pop_log) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem, *head = env->head; int err; if (env->head == NULL) return -ENOENT; if (cur) { err = copy_verifier_state(cur, &head->st); if (err) return err; } if (pop_log) bpf_vlog_reset(&env->log, head->log_pos); if (insn_idx) *insn_idx = head->insn_idx; if (prev_insn_idx) *prev_insn_idx = head->prev_insn_idx; elem = head->next; free_verifier_state(&head->st, false); kfree(head); env->head = elem; env->stack_size--; return 0; } static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, bool speculative) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem; int err; elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); if (!elem) goto err; elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; elem->log_pos = env->log.len_used; env->head = elem; env->stack_size++; err = copy_verifier_state(&elem->st, cur); if (err) goto err; elem->st.speculative |= speculative; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex.\n", env->stack_size); goto err; } if (elem->st.parent) { ++elem->st.parent->branches; /* WARN_ON(branches > 2) technically makes sense here, * but * 1. speculative states will bump 'branches' for non-branch * instructions * 2. is_state_visited() heuristics may decide not to create * a new state for a sequence of branches and all such current * and cloned states will be pointing to a single parent state * which might have large 'branches' count. */ } return &elem->st; err: free_verifier_state(env->cur_state, true); env->cur_state = NULL; /* pop all elements and return */ while (!pop_stack(env, NULL, NULL, false)); return NULL; } #define CALLER_SAVED_REGS 6 static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { /* Clear id, off, and union(map_ptr, range) */ memset(((u8 *)reg) + sizeof(reg->type), 0, offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); reg->var_off = tnum_const(imm); reg->smin_value = (s64)imm; reg->smax_value = (s64)imm; reg->umin_value = imm; reg->umax_value = imm; reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const_subreg(reg->var_off, imm); reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } /* Mark the 'variable offset' part of a register as zero. This should be * used only on registers holding a pointer type. */ static void __mark_reg_known_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); } static void __mark_reg_const_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); reg->type = SCALAR_VALUE; } static void mark_reg_known_zero(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); } static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) { return type_is_pkt_pointer(reg->type); } static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) { return reg_is_pkt_pointer(reg) || reg->type == PTR_TO_PACKET_END; } /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, enum bpf_reg_type which) { /* The register can already have a range from prior markings. * This is fine as long as it hasn't been advanced from its * origin. */ return reg->type == which && reg->id == 0 && reg->off == 0 && tnum_equals_const(reg->var_off, 0); } /* Reset the min/max bounds of a register */ static void __mark_reg_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void __mark_reg64_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; } static void __mark_reg32_unbounded(struct bpf_reg_state *reg) { reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void __update_reg32_bounds(struct bpf_reg_state *reg) { struct tnum var32_off = tnum_subreg(reg->var_off); /* min signed is max(sign bit) | min(other bits) */ reg->s32_min_value = max_t(s32, reg->s32_min_value, var32_off.value | (var32_off.mask & S32_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->s32_max_value = min_t(s32, reg->s32_max_value, var32_off.value | (var32_off.mask & S32_MAX)); reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value); reg->u32_max_value = min(reg->u32_max_value, (u32)(var32_off.value | var32_off.mask)); } static void __update_reg64_bounds(struct bpf_reg_state *reg) { /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, reg->var_off.value | (reg->var_off.mask & S64_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->smax_value = min_t(s64, reg->smax_value, reg->var_off.value | (reg->var_off.mask & S64_MAX)); reg->umin_value = max(reg->umin_value, reg->var_off.value); reg->umax_value = min(reg->umax_value, reg->var_off.value | reg->var_off.mask); } static void __update_reg_bounds(struct bpf_reg_state *reg) { __update_reg32_bounds(reg); __update_reg64_bounds(reg); } /* Uses signed min/max values to inform unsigned, and vice-versa */ static void __reg32_deduce_bounds(struct bpf_reg_state *reg) { /* Learn sign from signed bounds. * If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) { reg->s32_min_value = reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->s32_max_value = reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); return; } /* Learn sign from unsigned bounds. Signed bounds cross the sign * boundary, so we must be careful. */ if ((s32)reg->u32_max_value >= 0) { /* Positive. We can't learn anything from the smin, but smax * is positive, hence safe. */ reg->s32_min_value = reg->u32_min_value; reg->s32_max_value = reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); } else if ((s32)reg->u32_min_value < 0) { /* Negative. We can't learn anything from the smax, but smin * is negative, hence safe. */ reg->s32_min_value = reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->s32_max_value = reg->u32_max_value; } } static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { /* Learn sign from signed bounds. * If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if (reg->smin_value >= 0 || reg->smax_value < 0) { reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); return; } /* Learn sign from unsigned bounds. Signed bounds cross the sign * boundary, so we must be careful. */ if ((s64)reg->umax_value >= 0) { /* Positive. We can't learn anything from the smin, but smax * is positive, hence safe. */ reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); } else if ((s64)reg->umin_value < 0) { /* Negative. We can't learn anything from the smax, but smin * is negative, hence safe. */ reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); reg->smax_value = reg->umax_value; } } static void __reg_deduce_bounds(struct bpf_reg_state *reg) { __reg32_deduce_bounds(reg); __reg64_deduce_bounds(reg); } /* Attempts to improve var_off based on unsigned min/max information */ static void __reg_bound_offset(struct bpf_reg_state *reg) { struct tnum var64_off = tnum_intersect(reg->var_off, tnum_range(reg->umin_value, reg->umax_value)); struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off), tnum_range(reg->u32_min_value, reg->u32_max_value)); reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; /* Attempt to pull 32-bit signed bounds into 64-bit bounds * but must be positive otherwise set to worse case bounds * and refine later from tnum. */ if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0) reg->smax_value = reg->s32_max_value; else reg->smax_value = U32_MAX; if (reg->s32_min_value >= 0) reg->smin_value = reg->s32_min_value; else reg->smin_value = 0; } static void __reg_combine_32_into_64(struct bpf_reg_state *reg) { /* special case when 64-bit register has upper 32-bit register * zeroed. Typically happens after zext or <<32, >>32 sequence * allowing us to use 32-bit bounds directly, */ if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) { __reg_assign_32_into_64(reg); } else { /* Otherwise the best we can do is push lower 32bit known and * unknown bits into register (var_off set from jmp logic) * then learn as much as possible from the 64-bit tnum * known and unknown bits. The previous smin/smax bounds are * invalid here because of jmp32 compare so mark them unknown * so they do not impact tnum bounds calculation. */ __mark_reg64_unbounded(reg); __update_reg_bounds(reg); } /* Intersecting with the old var_off might have improved our bounds * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. */ __reg_deduce_bounds(reg); __reg_bound_offset(reg); __update_reg_bounds(reg); } static bool __reg64_bound_s32(s64 a) { if (a > S32_MIN && a < S32_MAX) return true; return false; } static bool __reg64_bound_u32(u64 a) { if (a > U32_MIN && a < U32_MAX) return true; return false; } static void __reg_combine_64_into_32(struct bpf_reg_state *reg) { __mark_reg32_unbounded(reg); if (__reg64_bound_s32(reg->smin_value)) reg->s32_min_value = (s32)reg->smin_value; if (__reg64_bound_s32(reg->smax_value)) reg->s32_max_value = (s32)reg->smax_value; if (__reg64_bound_u32(reg->umin_value)) reg->u32_min_value = (u32)reg->umin_value; if (__reg64_bound_u32(reg->umax_value)) reg->u32_max_value = (u32)reg->umax_value; /* Intersecting with the old var_off might have improved our bounds * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. */ __reg_deduce_bounds(reg); __reg_bound_offset(reg); __update_reg_bounds(reg); } /* Mark a register as having a completely unknown (scalar) value. */ static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and * padding between 'type' and union */ memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; reg->precise = env->subprog_cnt > 1 || !env->bpf_capable; __mark_reg_unbounded(reg); } static void mark_reg_unknown(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_unknown(env, regs + regno); } static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } static void mark_reg_not_init(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_not_init(env, regs + regno); } static void mark_btf_ld_reg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, enum bpf_reg_type reg_type, u32 btf_id) { if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, regno); return; } mark_reg_known_zero(env, regs, regno); regs[regno].type = PTR_TO_BTF_ID; regs[regno].btf_id = btf_id; } #define DEF_NOT_SUBREG (0) static void init_reg_state(struct bpf_verifier_env *env, struct bpf_func_state *state) { struct bpf_reg_state *regs = state->regs; int i; for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; regs[i].parent = NULL; regs[i].subreg_def = DEF_NOT_SUBREG; } /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; mark_reg_known_zero(env, regs, BPF_REG_FP); regs[BPF_REG_FP].frameno = state->frameno; } #define BPF_MAIN_FUNC (-1) static void init_func_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int callsite, int frameno, int subprogno) { state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; init_reg_state(env, state); } enum reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ DST_OP_NO_MARK /* same as above, check only, don't mark */ }; static int cmp_subprogs(const void *a, const void *b) { return ((struct bpf_subprog_info *)a)->start - ((struct bpf_subprog_info *)b)->start; } static int find_subprog(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *p; p = bsearch(&off, env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs); if (!p) return -ENOENT; return p - env->subprog_info; } static int add_subprog(struct bpf_verifier_env *env, int off) { int insn_cnt = env->prog->len; int ret; if (off >= insn_cnt || off < 0) { verbose(env, "call to invalid destination\n"); return -EINVAL; } ret = find_subprog(env, off); if (ret >= 0) return 0; if (env->subprog_cnt >= BPF_MAX_SUBPROGS) { verbose(env, "too many subprograms\n"); return -E2BIG; } env->subprog_info[env->subprog_cnt++].start = off; sort(env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs, NULL); return 0; } static int check_subprogs(struct bpf_verifier_env *env) { int i, ret, subprog_start, subprog_end, off, cur_subprog = 0; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; /* Add entry function. */ ret = add_subprog(env, 0); if (ret < 0) return ret; /* determine subprog starts. The end is one before the next starts */ for (i = 0; i < insn_cnt; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) continue; if (insn[i].src_reg != BPF_PSEUDO_CALL) continue; if (!env->bpf_capable) { verbose(env, "function calls to other bpf functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n"); return -EPERM; } ret = add_subprog(env, i + insn[i].imm + 1); if (ret < 0) return ret; } /* Add a fake 'exit' subprog which could simplify subprog iteration * logic. 'subprog_cnt' should not be increased. */ subprog[env->subprog_cnt].start = insn_cnt; if (env->log.level & BPF_LOG_LEVEL2) for (i = 0; i < env->subprog_cnt; i++) verbose(env, "func#%d @%d\n", i, subprog[i].start); /* now check that all jumps are within the same subprog */ subprog_start = subprog[cur_subprog].start; subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) goto next; off = i + insn[i].off + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; } next: if (i == subprog_end - 1) { /* to avoid fall-through from one subprog into another * the last insn of the subprog should be either exit * or unconditional jump back */ if (code != (BPF_JMP | BPF_EXIT) && code != (BPF_JMP | BPF_JA)) { verbose(env, "last insn is not an exit or jmp\n"); return -EINVAL; } subprog_start = subprog_end; cur_subprog++; if (cur_subprog < env->subprog_cnt) subprog_end = subprog[cur_subprog + 1].start; } } return 0; } /* Parentage chain of this register (or stack slot) should take care of all * issues like callee-saved registers, stack slot allocation time, etc. */ static int mark_reg_read(struct bpf_verifier_env *env, const struct bpf_reg_state *state, struct bpf_reg_state *parent, u8 flag) { bool writes = parent == state->parent; /* Observe write marks */ int cnt = 0; while (parent) { /* if read wasn't screened by an earlier write ... */ if (writes && state->live & REG_LIVE_WRITTEN) break; if (parent->live & REG_LIVE_DONE) { verbose(env, "verifier BUG type %s var_off %lld off %d\n", reg_type_str[parent->type], parent->var_off.value, parent->off); return -EFAULT; } /* The first condition is more likely to be true than the * second, checked it first. */ if ((parent->live & REG_LIVE_READ) == flag || parent->live & REG_LIVE_READ64) /* The parentage chain never changes and * this parent was already marked as LIVE_READ. * There is no need to keep walking the chain again and * keep re-marking all parents as LIVE_READ. * This case happens when the same register is read * multiple times without writes into it in-between. * Also, if parent has the stronger REG_LIVE_READ64 set, * then no need to set the weak REG_LIVE_READ32. */ break; /* ... then we depend on parent's value */ parent->live |= flag; /* REG_LIVE_READ64 overrides REG_LIVE_READ32. */ if (flag == REG_LIVE_READ64) parent->live &= ~REG_LIVE_READ32; state = parent; parent = state->parent; writes = true; cnt++; } if (env->longest_mark_read_walk < cnt) env->longest_mark_read_walk = cnt; return 0; } /* This function is supposed to be used by the following 32-bit optimization * code only. It returns TRUE if the source or destination register operates * on 64-bit, otherwise return FALSE. */ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t) { u8 code, class, op; code = insn->code; class = BPF_CLASS(code); op = BPF_OP(code); if (class == BPF_JMP) { /* BPF_EXIT for "main" will reach here. Return TRUE * conservatively. */ if (op == BPF_EXIT) return true; if (op == BPF_CALL) { /* BPF to BPF call will reach here because of marking * caller saved clobber with DST_OP_NO_MARK for which we * don't care the register def because they are anyway * marked as NOT_INIT already. */ if (insn->src_reg == BPF_PSEUDO_CALL) return false; /* Helper call will reach here because of arg type * check, conservatively return TRUE. */ if (t == SRC_OP) return true; return false; } } if (class == BPF_ALU64 || class == BPF_JMP || /* BPF_END always use BPF_ALU class. */ (class == BPF_ALU && op == BPF_END && insn->imm == 64)) return true; if (class == BPF_ALU || class == BPF_JMP32) return false; if (class == BPF_LDX) { if (t != SRC_OP) return BPF_SIZE(code) == BPF_DW; /* LDX source must be ptr. */ return true; } if (class == BPF_STX) { if (reg->type != SCALAR_VALUE) return true; return BPF_SIZE(code) == BPF_DW; } if (class == BPF_LD) { u8 mode = BPF_MODE(code); /* LD_IMM64 */ if (mode == BPF_IMM) return true; /* Both LD_IND and LD_ABS return 32-bit data. */ if (t != SRC_OP) return false; /* Implicit ctx ptr. */ if (regno == BPF_REG_6) return true; /* Explicit source could be any width. */ return true; } if (class == BPF_ST) /* The only source register for BPF_ST is a ptr. */ return true; /* Conservatively return true at default. */ return true; } /* Return TRUE if INSN doesn't have explicit value define. */ static bool insn_no_def(struct bpf_insn *insn) { u8 class = BPF_CLASS(insn->code); return (class == BPF_JMP || class == BPF_JMP32 || class == BPF_STX || class == BPF_ST); } /* Return TRUE if INSN has defined any 32-bit value explicitly. */ static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn) { if (insn_no_def(insn)) return false; return !is_reg64(env, insn, insn->dst_reg, NULL, DST_OP); } static void mark_insn_zext(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { s32 def_idx = reg->subreg_def; if (def_idx == DEF_NOT_SUBREG) return; env->insn_aux_data[def_idx - 1].zext_dst = true; /* The dst will be zero extended, so won't be sub-register anymore. */ reg->subreg_def = DEF_NOT_SUBREG; } static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum reg_arg_type t) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; struct bpf_reg_state *reg, *regs = state->regs; bool rw64; if (regno >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", regno); return -EINVAL; } reg = ®s[regno]; rw64 = is_reg64(env, insn, regno, reg, t); if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (reg->type == NOT_INIT) { verbose(env, "R%d !read_ok\n", regno); return -EACCES; } /* We don't need to worry about FP liveness because it's read-only */ if (regno == BPF_REG_FP) return 0; if (rw64) mark_insn_zext(env, reg); return mark_reg_read(env, reg, reg->parent, rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { verbose(env, "frame pointer is read only\n"); return -EACCES; } reg->live |= REG_LIVE_WRITTEN; reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1; if (t == DST_OP) mark_reg_unknown(env, regs, regno); } return 0; } /* for any branch, call, exit record the history of jmps in the given state */ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur) { u32 cnt = cur->jmp_history_cnt; struct bpf_idx_pair *p; cnt++; p = krealloc(cur->jmp_history, cnt * sizeof(*p), GFP_USER); if (!p) return -ENOMEM; p[cnt - 1].idx = env->insn_idx; p[cnt - 1].prev_idx = env->prev_insn_idx; cur->jmp_history = p; cur->jmp_history_cnt = cnt; return 0; } /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; } else { i--; } return i; } /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, u32 *reg_mask, u64 *stack_mask) { const struct bpf_insn_cbs cbs = { .cb_print = verbose, .private_data = env, }; struct bpf_insn *insn = env->prog->insnsi + idx; u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); u32 dreg = 1u << insn->dst_reg; u32 sreg = 1u << insn->src_reg; u32 spi; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); verbose(env, "%d: ", idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (class == BPF_ALU || class == BPF_ALU64) { if (!(*reg_mask & dreg)) return 0; if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { /* dreg = sreg * dreg needs precision after this insn * sreg needs precision before this insn */ *reg_mask &= ~dreg; *reg_mask |= sreg; } else { /* dreg = K * dreg needs precision after this insn. * Corresponding register is already marked * as precise=true in this verifier state. * No further markings in parent are necessary */ *reg_mask &= ~dreg; } } else { if (BPF_SRC(insn->code) == BPF_X) { /* dreg += sreg * both dreg and sreg need precision * before this insn */ *reg_mask |= sreg; } /* else dreg += K * dreg still needs precision before this insn */ } } else if (class == BPF_LDX) { if (!(*reg_mask & dreg)) return 0; *reg_mask &= ~dreg; /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. * The desire to keep that precision is already indicated * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ if (insn->src_reg != BPF_REG_FP) return 0; if (BPF_SIZE(insn->code) != BPF_DW) return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } *stack_mask |= 1ull << spi; } else if (class == BPF_STX || class == BPF_ST) { if (*reg_mask & dreg) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ return -ENOTSUPP; /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; if (BPF_SIZE(insn->code) != BPF_DW) return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } if (!(*stack_mask & (1ull << spi))) return 0; *stack_mask &= ~(1ull << spi); if (class == BPF_STX) *reg_mask |= sreg; } else if (class == BPF_JMP || class == BPF_JMP32) { if (opcode == BPF_CALL) { if (insn->src_reg == BPF_PSEUDO_CALL) return -ENOTSUPP; /* regular helper call sets R0 */ *reg_mask &= ~1; if (*reg_mask & 0x3f) { /* if backtracing was looking for registers R1-R5 * they should have been found already. */ verbose(env, "BUG regs %x\n", *reg_mask); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; } } else if (class == BPF_LD) { if (!(*reg_mask & dreg)) return 0; *reg_mask &= ~dreg; /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary */ if (mode == BPF_IND || mode == BPF_ABS) /* to be analyzed */ return -ENOTSUPP; } return 0; } /* the scalar precision tracking algorithm: * . at the start all registers have precise=false. * . scalar ranges are tracked as normal through alu and jmp insns. * . once precise value of the scalar register is used in: * . ptr + scalar alu * . if (scalar cond K|scalar) * . helper_call(.., scalar, ...) where ARG_CONST is expected * backtrack through the verifier states and mark all registers and * stack slots with spilled constants that these scalar regisers * should be precise. * . during state pruning two registers (or spilled stack slots) * are equivalent if both are not precise. * * Note the verifier cannot simply walk register parentage chain, * since many different registers and stack slots could have been * used to compute single precise scalar. * * The approach of starting with precise=true for all registers and then * backtrack to mark a register as not precise when the verifier detects * that program doesn't care about specific value (e.g., when helper * takes register as ARG_ANYTHING parameter) is not safe. * * It's ok to walk single parentage chain of the verifier states. * It's possible that this backtracking will go all the way till 1st insn. * All other branches will be explored for needing precision later. * * The backtracking needs to deal with cases like: * R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0) * r9 -= r8 * r5 = r9 * if r5 > 0x79f goto pc+7 * R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff)) * r5 += 1 * ... * call bpf_perf_event_output#25 * where .arg5_type = ARG_CONST_SIZE_OR_ZERO * * and this case: * r6 = 1 * call foo // uses callee's r6 inside to compute r0 * r0 += r6 * if r0 == 0 goto * * to track above reg_mask/stack_mask needs to be independent for each frame. * * Also if parent's curframe > frame where backtracking started, * the verifier need to mark registers in both frames, otherwise callees * may incorrectly prune callers. This is similar to * commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences") * * For now backtracking falls back into conservative marking. */ static void mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. */ for (; st; st = st->parent) for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE) continue; reg->precise = true; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (func->stack[j].slot_type[0] != STACK_SPILL) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) continue; reg->precise = true; } } } static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, int spi) { struct bpf_verifier_state *st = env->cur_state; int first_idx = st->first_insn_idx; int last_idx = env->insn_idx; struct bpf_func_state *func; struct bpf_reg_state *reg; u32 reg_mask = regno >= 0 ? 1u << regno : 0; u64 stack_mask = spi >= 0 ? 1ull << spi : 0; bool skip_first = true; bool new_marks = false; int i, err; if (!env->bpf_capable) return 0; func = st->frame[st->curframe]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { WARN_ONCE(1, "backtracing misuse"); return -EFAULT; } if (!reg->precise) new_marks = true; else reg_mask = 0; reg->precise = true; } while (spi >= 0) { if (func->stack[spi].slot_type[0] != STACK_SPILL) { stack_mask = 0; break; } reg = &func->stack[spi].spilled_ptr; if (reg->type != SCALAR_VALUE) { stack_mask = 0; break; } if (!reg->precise) new_marks = true; else stack_mask = 0; reg->precise = true; break; } if (!new_marks) return 0; if (!reg_mask && !stack_mask) return 0; for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; if (env->log.level & BPF_LOG_LEVEL) verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); for (i = last_idx;;) { if (skip_first) { err = 0; skip_first = false; } else { err = backtrack_insn(env, i, ®_mask, &stack_mask); } if (err == -ENOTSUPP) { mark_all_scalars_precise(env, st); return 0; } else if (err) { return err; } if (!reg_mask && !stack_mask) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. */ return 0; if (i == first_idx) break; i = get_prev_insn_idx(st, i, &history); if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask * to backtrack. * It means the backtracking missed the spot where * particular register was initialized with a constant. */ verbose(env, "BUG backtracking idx %d\n", i); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } st = st->parent; if (!st) break; new_marks = false; func = st->frame[st->curframe]; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; if (reg->type != SCALAR_VALUE) { reg_mask &= ~(1u << i); continue; } if (!reg->precise) new_marks = true; reg->precise = true; } bitmap_from_u64(mask, stack_mask); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { /* the sequence of instructions: * 2: (bf) r3 = r10 * 3: (7b) *(u64 *)(r3 -8) = r0 * 4: (79) r4 = *(u64 *)(r10 -8) * doesn't contain jmps. It's backtracked * as a single block. * During backtracking insn 3 is not recognized as * stack access, so at the end of backtracking * stack slot fp-8 is still marked in stack_mask. * However the parent state may not have accessed * fp-8 and it's "unallocated" stack space. * In such case fallback to conservative. */ mark_all_scalars_precise(env, st); return 0; } if (func->stack[i].slot_type[0] != STACK_SPILL) { stack_mask &= ~(1ull << i); continue; } reg = &func->stack[i].spilled_ptr; if (reg->type != SCALAR_VALUE) { stack_mask &= ~(1ull << i); continue; } if (!reg->precise) new_marks = true; reg->precise = true; } if (env->log.level & BPF_LOG_LEVEL) { print_verifier_state(env, func); verbose(env, "parent %s regs=%x stack=%llx marks\n", new_marks ? "didn't have" : "already had", reg_mask, stack_mask); } if (!reg_mask && !stack_mask) break; if (!new_marks) break; last_idx = st->last_insn_idx; first_idx = st->first_insn_idx; } return 0; } static int mark_chain_precision(struct bpf_verifier_env *env, int regno) { return __mark_chain_precision(env, regno, -1); } static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi) { return __mark_chain_precision(env, -1, spi); } static bool is_spillable_regtype(enum bpf_reg_type type) { switch (type) { case PTR_TO_MAP_VALUE: case PTR_TO_MAP_VALUE_OR_NULL: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: case PTR_TO_BTF_ID_OR_NULL: case PTR_TO_RDONLY_BUF: case PTR_TO_RDONLY_BUF_OR_NULL: case PTR_TO_RDWR_BUF: case PTR_TO_RDWR_BUF_OR_NULL: return true; default: return false; } } /* Does this register contain a constant zero? */ static bool register_is_null(struct bpf_reg_state *reg) { return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); } static bool register_is_const(struct bpf_reg_state *reg) { return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off); } static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { if (allow_ptr_leaks) return false; return reg->type != SCALAR_VALUE; } static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg) { int i; state->stack[spi].spilled_ptr = *reg; state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; for (i = 0; i < BPF_REG_SIZE; i++) state->stack[spi].slot_type[i] = STACK_SPILL; } /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ static int check_stack_write(struct bpf_verifier_env *env, struct bpf_func_state *state, /* func where register points to */ int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg; struct bpf_reg_state *reg = NULL; err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), state->acquired_refs, true); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ if (!env->allow_ptr_leaks && state->stack[spi].slot_type[0] == STACK_SPILL && size != BPF_REG_SIZE) { verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; } cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; if (reg && size == BPF_REG_SIZE && register_is_const(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit * stack slot address like [fp - 8]. Other spill of * scalar via different register has to be conervative. * Backtrack from here and mark all registers as precise * that contributed into 'reg' being a constant. */ err = mark_chain_precision(env, value_regno); if (err) return err; } save_register_state(state, spi, reg); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { verbose_linfo(env, insn_idx, "; "); verbose(env, "invalid size of register spill\n"); return -EACCES; } if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } if (!env->bypass_spec_v4) { bool sanitize = false; if (state->stack[spi].slot_type[0] == STACK_SPILL && register_is_const(&state->stack[spi].spilled_ptr)) sanitize = true; for (i = 0; i < BPF_REG_SIZE; i++) if (state->stack[spi].slot_type[i] == STACK_MISC) { sanitize = true; break; } if (sanitize) { int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; int soff = (-spi - 1) * BPF_REG_SIZE; /* detected reuse of integer stack slot with a pointer * which means either llvm is reusing stack slot or * an attacker is trying to exploit CVE-2018-3639 * (speculative store bypass) * Have to sanitize that slot with preemptive * store of zero. */ if (*poff && *poff != soff) { /* disallow programs where single insn stores * into two different stack slots, since verifier * cannot sanitize them */ verbose(env, "insn %d cannot access two stack slots fp%d and fp%d", insn_idx, *poff, soff); return -EINVAL; } *poff = soff; } } save_register_state(state, spi, reg); } else { u8 type = STACK_MISC; /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ if (state->stack[spi].slot_type[0] == STACK_SPILL) for (i = 0; i < BPF_REG_SIZE; i++) state->stack[spi].slot_type[i] = STACK_MISC; /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon * when stack slots are partially written. * This heuristic means that read propagation will be * conservative, since it will add reg_live_read marks * to stack slots all the way to first state when programs * writes+reads less than 8 bytes */ if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; /* when we zero initialize stack slots mark them as such */ if (reg && register_is_null(reg)) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) return err; type = STACK_ZERO; } /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; } return 0; } static int check_stack_read(struct bpf_verifier_env *env, struct bpf_func_state *reg_state /* func where register points to */, int off, int size, int value_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; u8 *stype; if (reg_state->allocated_stack <= slot) { verbose(env, "invalid read from stack off %d+0 size %d\n", off, size); return -EACCES; } stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; if (stype[0] == STACK_SPILL) { if (size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } if (value_regno >= 0) { mark_reg_unknown(env, state->regs, value_regno); state->regs[value_regno].live |= REG_LIVE_WRITTEN; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); return 0; } for (i = 1; i < BPF_REG_SIZE; i++) { if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { verbose(env, "corrupted spill memory\n"); return -EACCES; } } if (value_regno >= 0) { /* restore register state from stack */ state->regs[value_regno] = *reg; /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) { /* If value_regno==-1, the caller is asking us whether * it is acceptable to use this value as a SCALAR_VALUE * (e.g. for XADD). * We must not allow unprivileged callers to do that * with spilled pointers. */ verbose(env, "leaking pointer from stack off %d\n", off); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { int zeros = 0; for (i = 0; i < size; i++) { if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC) continue; if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) { zeros++; continue; } verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (value_regno >= 0) { if (zeros == size) { /* any size read into register is zero extended, * so the whole register == const_zero */ __mark_reg_const_zero(&state->regs[value_regno]); /* backtracking doesn't support STACK_ZERO yet, * so mark it precise here, so that later * backtracking can stop here. * Backtracking may not need this if this register * doesn't participate in pointer adjustment. * Forward propagation of precise flag is not * necessary either. This mark is only to stop * backtracking. Any register that contributed * to const 0 was marked precise before spill. */ state->regs[value_regno].precise = true; } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, value_regno); } state->regs[value_regno].live |= REG_LIVE_WRITTEN; } } return 0; } static int check_stack_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size) { /* Stack accesses must be at a fixed offset, so that we * can determine what type of data were returned. See * check_stack_read(). */ if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable stack access var_off=%s off=%d size=%d\n", tn_buf, off, size); return -EACCES; } if (off >= 0 || off < -MAX_BPF_STACK) { verbose(env, "invalid stack off=%d size=%d\n", off, size); return -EACCES; } return 0; } static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, int off, int size, enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_map *map = regs[regno].map_ptr; u32 cap = bpf_map_flags_to_cap(map); if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) { verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) { verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } return 0; } /* check read/write into memory region (e.g., map value, ringbuf sample, etc) */ static int __check_mem_access(struct bpf_verifier_env *env, int regno, int off, int size, u32 mem_size, bool zero_size_allowed) { bool size_ok = size > 0 || (size == 0 && zero_size_allowed); struct bpf_reg_state *reg; if (off >= 0 && size_ok && (u64)off + size <= mem_size) return 0; reg = &cur_regs(env)[regno]; switch (reg->type) { case PTR_TO_MAP_VALUE: verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, off, mem_size); break; case PTR_TO_MEM: default: verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n", mem_size, off, size); } return -EACCES; } /* check read/write into a memory region with possible variable offset */ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, int off, int size, u32 mem_size, bool zero_size_allowed) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; int err; /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ if (env->log.level & BPF_LOG_LEVEL) print_verifier_state(env, state); /* The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use * will have a set floor within our range. */ if (reg->smin_value < 0 && (reg->smin_value == S64_MIN || (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) || reg->smin_value + off < 0)) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->smin_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d min value is outside of the allowed memory range\n", regno); return err; } /* If we haven't set a max value then we need to bail since we can't be * sure we won't do bad things. * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->umax_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d max value is outside of the allowed memory range\n", regno); return err; } return 0; } /* check read/write into a map element with possible variable offset */ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; int err; err = check_mem_region_access(env, regno, off, size, map->value_size, zero_size_allowed); if (err) return err; if (map_value_has_spin_lock(map)) { u32 lock = map->spin_lock_off; /* if any part of struct bpf_spin_lock can be touched by * load/store reject this program. * To check that [x1, x2) overlaps with [y1, y2) * it is sufficient to check x1 < y2 && y1 < x2. */ if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) && lock < reg->umax_value + off + size) { verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); return -EACCES; } } return err; } #define MAX_PACKET_OFF 0xffff static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) { return prog->aux->linked_prog ? prog->aux->linked_prog->type : prog->type; } static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); switch (prog_type) { /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; /* fallthrough */ /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: if (meta) return meta->pkt_access; env->seen_direct_write = true; return true; case BPF_PROG_TYPE_CGROUP_SOCKOPT: if (t == BPF_WRITE) env->seen_direct_write = true; return true; default: return false; } } static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; int err; /* We may have added a variable offset to the packet pointer; but any * reg->range we have comes after that. We are only checking the fixed * offset. */ /* We don't allow negative numbers, because we aren't tracking enough * detail to prove they're safe. */ if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_mem_access(env, regno, off, size, reg->range, zero_size_allowed); if (err) { verbose(env, "R%d offset is outside of the packet\n", regno); return err; } /* __check_mem_access has made sure "off + size - 1" is within u16. * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, * otherwise find_good_pkt_pointers would have refused to set range info * that __check_mem_access would have rejected this pkt access. * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. */ env->prog->aux->max_pkt_offset = max_t(u32, env->prog->aux->max_pkt_offset, off + reg->umax_value + size - 1); return err; } /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, u32 *btf_id) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, .log = &env->log, }; if (env->ops->is_valid_access && env->ops->is_valid_access(off, size, t, env->prog, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower * access than actual ctx access size. A zero info.ctx_field_size * will only allow for whole field access and rejects any other * type of narrower access. */ *reg_type = info.reg_type; if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) *btf_id = info.btf_id; else env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; return 0; } verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; } static int check_flow_keys_access(struct bpf_verifier_env *env, int off, int size) { if (size < 0 || off < 0 || (u64)off + size > sizeof(struct bpf_flow_keys)) { verbose(env, "invalid access to flow keys off=%d size=%d\n", off, size); return -EACCES; } return 0; } static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int size, enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; struct bpf_insn_access_aux info = {}; bool valid; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } switch (reg->type) { case PTR_TO_SOCK_COMMON: valid = bpf_sock_common_is_valid_access(off, size, t, &info); break; case PTR_TO_SOCKET: valid = bpf_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_TCP_SOCK: valid = bpf_tcp_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_XDP_SOCK: valid = bpf_xdp_sock_is_valid_access(off, size, t, &info); break; default: valid = false; } if (valid) { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; return 0; } verbose(env, "R%d invalid %s access off=%d size=%d\n", regno, reg_type_str[reg->type], off, size); return -EACCES; } static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) { return cur_regs(env) + regno; } static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno)); } static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return reg->type == PTR_TO_CTX; } static bool is_sk_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_sk_pointer(reg->type); } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_pkt_pointer(reg->type); } static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); /* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */ return reg->type == PTR_TO_FLOW_KEYS; } static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) { struct tnum reg_off; int ip_align; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; /* For platforms that do not have a Kconfig enabling * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of * NET_IP_ALIGN is universally set to '2'. And on platforms * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get * to this code only in strict mode where we want to emulate * the NET_IP_ALIGN==2 checking. Therefore use an * unconditional IP align value of '2'. */ ip_align = 2; reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned packet access off %d+%s+%d+%d size %d\n", ip_align, tn_buf, reg->off, off, size); return -EACCES; } return 0; } static int check_generic_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char *pointer_desc, int off, int size, bool strict) { struct tnum reg_off; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned %saccess off %s+%d+%d size %d\n", pointer_desc, tn_buf, reg->off, off, size); return -EACCES; } return 0; } static int check_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict_alignment_once) { bool strict = env->strict_alignment || strict_alignment_once; const char *pointer_desc = ""; switch (reg->type) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: /* Special case, because of NET_IP_ALIGN. Given metadata sits * right in front, treat it the very same way. */ return check_pkt_ptr_alignment(env, reg, off, size, strict); case PTR_TO_FLOW_KEYS: pointer_desc = "flow keys "; break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; case PTR_TO_CTX: pointer_desc = "context "; break; case PTR_TO_STACK: pointer_desc = "stack "; /* The stack spill tracking logic in check_stack_write() * and check_stack_read() relies on stack accesses being * aligned. */ strict = true; break; case PTR_TO_SOCKET: pointer_desc = "sock "; break; case PTR_TO_SOCK_COMMON: pointer_desc = "sock_common "; break; case PTR_TO_TCP_SOCK: pointer_desc = "tcp_sock "; break; case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; default: break; } return check_generic_ptr_alignment(env, reg, pointer_desc, off, size, strict); } static int update_stack_depth(struct bpf_verifier_env *env, const struct bpf_func_state *func, int off) { u16 stack = env->subprog_info[func->subprogno].stack_depth; if (stack >= -off) return 0; /* update known max for given subprogram */ env->subprog_info[func->subprogno].stack_depth = -off; return 0; } /* starting from main bpf function walk all instructions of the function * and recursively walk all callees that given function can call. * Ignore jump and exit insns. * Since recursion is prevented by check_cfg() this algorithm * only needs a local stack of MAX_CALL_FRAMES to remember callsites */ static int check_max_stack_depth(struct bpf_verifier_env *env) { int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; process_func: /* round up to 32-bytes, since this is granularity * of interpreter stack size */ depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); return -EACCES; } continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) continue; if (insn[i].src_reg != BPF_PSEUDO_CALL) continue; /* remember insn and function to return to */ ret_insn[frame] = i + 1; ret_prog[frame] = idx; /* find the callee */ i = i + insn[i].imm + 1; idx = find_subprog(env, i); if (idx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", i); return -EFAULT; } frame++; if (frame >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep !\n", frame); return -E2BIG; } goto process_func; } /* end of for() loop means the last insn of the 'subprog' * was reached. Doesn't matter whether it was JA or EXIT */ if (frame == 0) return 0; depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); frame--; i = ret_insn[frame]; idx = ret_prog[frame]; goto continue_func; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) { int start = idx + insn->imm + 1, subprog; subprog = find_subprog(env, start); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", start); return -EFAULT; } return env->subprog_info[subprog].stack_depth; } #endif int check_ctx_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno) { /* Access to ctx or passing it to a helper is only allowed in * its original, unmodified form. */ if (reg->off) { verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n", regno, reg->off); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf); return -EACCES; } return 0; } static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, int regno, int off, int size) { if (off < 0) { verbose(env, "R%d invalid %s buffer access: off=%d, size=%d\n", regno, buf_info, off, size); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d invalid variable buffer offset: off=%d, var_off=%s\n", regno, off, tn_buf); return -EACCES; } return 0; } static int check_tp_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size) { int err; err = __check_buffer_access(env, "tracepoint", reg, regno, off, size); if (err) return err; if (off + size > env->prog->aux->max_tp_access) env->prog->aux->max_tp_access = off + size; return 0; } static int check_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size, bool zero_size_allowed, const char *buf_info, u32 *max_access) { int err; err = __check_buffer_access(env, buf_info, reg, regno, off, size); if (err) return err; if (off + size > *max_access) *max_access = off + size; return 0; } /* BPF architecture zero extends alu32 ops into 64-bit registesr */ static void zext_32_to_64(struct bpf_reg_state *reg) { reg->var_off = tnum_subreg(reg->var_off); __reg_assign_32_into_64(reg); } /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) { u64 mask; /* clear high bits in bit representation */ reg->var_off = tnum_cast(reg->var_off, size); /* fix arithmetic bounds */ mask = ((u64)1 << (size * 8)) - 1; if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) { reg->umin_value &= mask; reg->umax_value &= mask; } else { reg->umin_value = 0; reg->umax_value = mask; } reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value; /* If size is smaller than 32bit register the 32bit register * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ if (size >= 4) return; __reg_combine_64_into_32(reg); } static bool bpf_map_is_rdonly(const struct bpf_map *map) { return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) { void *ptr; u64 addr; int err; err = map->ops->map_direct_value_addr(map, &addr, off); if (err) return err; ptr = (void *)(long)addr + off; switch (size) { case sizeof(u8): *val = (u64)*(u8 *)ptr; break; case sizeof(u16): *val = (u64)*(u16 *)ptr; break; case sizeof(u32): *val = (u64)*(u32 *)ptr; break; case sizeof(u64): *val = *(u64 *)ptr; break; default: return -EINVAL; } return 0; } static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id); const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off); u32 btf_id; int ret; if (off < 0) { verbose(env, "R%d is ptr_%s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n", regno, tname, off, tn_buf); return -EACCES; } if (env->ops->btf_struct_access) { ret = env->ops->btf_struct_access(&env->log, t, off, size, atype, &btf_id); } else { if (atype != BPF_READ) { verbose(env, "only read is supported\n"); return -EACCES; } ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id); } if (ret < 0) return ret; if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); return 0; } static int check_ptr_to_map_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; struct bpf_map *map = reg->map_ptr; const struct btf_type *t; const char *tname; u32 btf_id; int ret; if (!btf_vmlinux) { verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n"); return -ENOTSUPP; } if (!map->ops->map_btf_id || !*map->ops->map_btf_id) { verbose(env, "map_ptr access not supported for map type %d\n", map->map_type); return -ENOTSUPP; } t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id); tname = btf_name_by_offset(btf_vmlinux, t->name_off); if (!env->allow_ptr_to_map_access) { verbose(env, "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", tname); return -EPERM; } if (off < 0) { verbose(env, "R%d is %s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (atype != BPF_READ) { verbose(env, "only read from %s is supported\n", tname); return -EACCES; } ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id); if (ret < 0) return ret; if (value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); return 0; } /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, int value_regno, bool strict_alignment_once) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; struct bpf_func_state *state; int size, err = 0; size = bpf_size_to_bytes(bpf_size); if (size < 0) return size; /* alignment checks will add in reg->off themselves */ err = check_ptr_alignment(env, reg, off, size, strict_alignment_once); if (err) return err; /* for access checks, reg->off is just part of off */ off += reg->off; if (reg->type == PTR_TO_MAP_VALUE) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } err = check_map_access_type(env, regno, off, size, t); if (err) return err; err = check_map_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; /* if map is read-only, track its contents as scalars */ if (tnum_is_const(reg->var_off) && bpf_map_is_rdonly(map) && map->ops->map_direct_value_addr) { int map_off = off + reg->var_off.value; u64 val = 0; err = bpf_map_direct_read(map, map_off, size, &val); if (err) return err; regs[value_regno].type = SCALAR_VALUE; __mark_reg_known(®s[value_regno], val); } else { mark_reg_unknown(env, regs, value_regno); } } } else if (reg->type == PTR_TO_MEM) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into mem\n", value_regno); return -EACCES; } err = check_mem_region_access(env, regno, off, size, reg->mem_size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } err = check_ctx_reg(env, reg, regno); if (err < 0) return err; err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf_id); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, value_regno); } else { mark_reg_known_zero(env, regs, value_regno); if (reg_type_may_be_null(reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the * insn. When the dst is PTR, it is for sure not * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; if (reg_type == PTR_TO_BTF_ID || reg_type == PTR_TO_BTF_ID_OR_NULL) regs[value_regno].btf_id = btf_id; } regs[value_regno].type = reg_type; } } else if (reg->type == PTR_TO_STACK) { off += reg->var_off.value; err = check_stack_access(env, reg, off, size); if (err) return err; state = func(env, reg); err = update_stack_depth(env, state, off); if (err) return err; if (t == BPF_WRITE) err = check_stack_write(env, state, off, size, value_regno, insn_idx); else err = check_stack_read(env, state, off, size, value_regno); } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose(env, "cannot write into packet\n"); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into packet\n", value_regno); return -EACCES; } err = check_packet_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_FLOW_KEYS) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into flow keys\n", value_regno); return -EACCES; } err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str[reg->type]); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_TP_BUFFER) { err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_BTF_ID) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == CONST_PTR_TO_MAP) { err = check_ptr_to_map_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == PTR_TO_RDONLY_BUF) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str[reg->type]); return -EACCES; } err = check_buffer_access(env, reg, regno, off, size, false, "rdonly", &env->prog->aux->max_rdonly_access); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_RDWR_BUF) { err = check_buffer_access(env, reg, regno, off, size, false, "rdwr", &env->prog->aux->max_rdwr_access); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); return -EACCES; } if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && regs[value_regno].type == SCALAR_VALUE) { /* b/h/w load zero-extends, mark upper bits as known 0 */ coerce_reg_to_size(®s[value_regno], size); } return err; } static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { int err; if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || insn->imm != 0) { verbose(env, "BPF_XADD uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; } if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || is_flow_key_reg(env, insn->dst_reg) || is_sk_reg(env, insn->dst_reg)) { verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str[reg_state(env, insn->dst_reg)->type]); return -EACCES; } /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1, true); if (err) return err; /* check whether atomic_add can write into the same memory */ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true); } static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno, int off, int access_size, bool zero_size_allowed) { struct bpf_reg_state *reg = reg_state(env, regno); if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || access_size < 0 || (access_size == 0 && !zero_size_allowed)) { if (tnum_is_const(reg->var_off)) { verbose(env, "invalid stack type R%d off=%d access_size=%d\n", regno, off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n", regno, tn_buf, access_size); } return -EACCES; } return 0; } /* when register 'regno' is passed into function that will read 'access_size' * bytes from that pointer, make sure that it's within stack boundary * and all elements of stack are initialized. * Unlike most pointer bounds-checking functions, this one doesn't take an * 'off' argument, so it has to add in reg->off itself. */ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); int err, min_off, max_off, i, j, slot, spi; if (reg->type != PTR_TO_STACK) { /* Allow zero-byte read from NULL, regardless of pointer type */ if (zero_size_allowed && access_size == 0 && register_is_null(reg)) return 0; verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[reg->type], reg_type_str[PTR_TO_STACK]); return -EACCES; } if (tnum_is_const(reg->var_off)) { min_off = max_off = reg->var_off.value + reg->off; err = __check_stack_boundary(env, regno, min_off, access_size, zero_size_allowed); if (err) return err; } else { /* Variable offset is prohibited for unprivileged mode for * simplicity since it requires corresponding support in * Spectre masking for stack ALU. * See also retrieve_ptr_limit(). */ if (!env->bypass_spec_v1) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n", regno, tn_buf); return -EACCES; } /* Only initialized buffer on stack is allowed to be accessed * with variable offset. With uninitialized buffer it's hard to * guarantee that whole memory is marked as initialized on * helper return since specific bounds are unknown what may * cause uninitialized stack leaking. */ if (meta && meta->raw_mode) meta = NULL; if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smax_value <= -BPF_MAX_VAR_OFF) { verbose(env, "R%d unbounded indirect variable offset stack access\n", regno); return -EACCES; } min_off = reg->smin_value + reg->off; max_off = reg->smax_value + reg->off; err = __check_stack_boundary(env, regno, min_off, access_size, zero_size_allowed); if (err) { verbose(env, "R%d min value is outside of stack bound\n", regno); return err; } err = __check_stack_boundary(env, regno, max_off, access_size, zero_size_allowed); if (err) { verbose(env, "R%d max value is outside of stack bound\n", regno); return err; } } if (meta && meta->raw_mode) { meta->access_size = access_size; meta->regno = regno; return 0; } for (i = min_off; i < max_off + access_size; i++) { u8 *stype; slot = -i - 1; spi = slot / BPF_REG_SIZE; if (state->allocated_stack <= slot) goto err; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; if (*stype == STACK_MISC) goto mark; if (*stype == STACK_ZERO) { /* helper can write anything into the stack */ *stype = STACK_MISC; goto mark; } if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID) goto mark; if (state->stack[spi].slot_type[0] == STACK_SPILL && state->stack[spi].spilled_ptr.type == SCALAR_VALUE) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) state->stack[spi].slot_type[j] = STACK_MISC; goto mark; } err: if (tnum_is_const(reg->var_off)) { verbose(env, "invalid indirect read from stack off %d+%d size %d\n", min_off, i - min_off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid indirect read from stack var_off %s+%d size %d\n", tn_buf, i - min_off, access_size); } return -EACCES; mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ mark_reg_read(env, &state->stack[spi].spilled_ptr, state->stack[spi].spilled_ptr.parent, REG_LIVE_READ64); } return update_stack_depth(env, state, min_off); } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; switch (reg->type) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_VALUE: if (check_map_access_type(env, regno, reg->off, access_size, meta && meta->raw_mode ? BPF_WRITE : BPF_READ)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MEM: return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); case PTR_TO_RDONLY_BUF: if (meta && meta->raw_mode) return -EACCES; return check_buffer_access(env, reg, regno, reg->off, access_size, zero_size_allowed, "rdonly", &env->prog->aux->max_rdonly_access); case PTR_TO_RDWR_BUF: return check_buffer_access(env, reg, regno, reg->off, access_size, zero_size_allowed, "rdwr", &env->prog->aux->max_rdwr_access); default: /* scalar_value|ptr_to_stack or invalid ptr */ return check_stack_boundary(env, regno, access_size, zero_size_allowed, meta); } } /* Implementation details: * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL * Two bpf_map_lookups (even with the same key) will have different reg->id. * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after * value_or_null->value transition, since the verifier only cares about * the range of access to valid map value pointer and doesn't care about actual * address of the map element. * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps * reg->id > 0 after value_or_null->value transition. By doing so * two bpf_map_lookups will be considered two different pointers that * point to different bpf_spin_locks. * The verifier allows taking only one bpf_spin_lock at a time to avoid * dead-locks. * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. * cur_state->active_spin_lock remembers which map value element got locked * and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, bool is_lock) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_verifier_state *cur = env->cur_state; bool is_const = tnum_is_const(reg->var_off); struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; if (reg->type != PTR_TO_MAP_VALUE) { verbose(env, "R%d is not a pointer to map_value\n", regno); return -EINVAL; } if (!is_const) { verbose(env, "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", regno); return -EINVAL; } if (!map->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_spin_lock\n", map->name); return -EINVAL; } if (!map_value_has_spin_lock(map)) { if (map->spin_lock_off == -E2BIG) verbose(env, "map '%s' has more than one 'struct bpf_spin_lock'\n", map->name); else if (map->spin_lock_off == -ENOENT) verbose(env, "map '%s' doesn't have 'struct bpf_spin_lock'\n", map->name); else verbose(env, "map '%s' is not a struct type or bpf_spin_lock is mangled\n", map->name); return -EINVAL; } if (map->spin_lock_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", val + reg->off); return -EINVAL; } if (is_lock) { if (cur->active_spin_lock) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } cur->active_spin_lock = reg->id; } else { if (!cur->active_spin_lock) { verbose(env, "bpf_spin_unlock without taking a lock\n"); return -EINVAL; } if (cur->active_spin_lock != reg->id) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } cur->active_spin_lock = 0; } return 0; } static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_MEM || type == ARG_PTR_TO_MEM_OR_NULL || type == ARG_PTR_TO_UNINIT_MEM; } static bool arg_type_is_mem_size(enum bpf_arg_type type) { return type == ARG_CONST_SIZE || type == ARG_CONST_SIZE_OR_ZERO; } static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_ALLOC_MEM || type == ARG_PTR_TO_ALLOC_MEM_OR_NULL; } static bool arg_type_is_alloc_size(enum bpf_arg_type type) { return type == ARG_CONST_ALLOC_SIZE_OR_ZERO; } static bool arg_type_is_int_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_INT || type == ARG_PTR_TO_LONG; } static int int_ptr_type_to_size(enum bpf_arg_type type) { if (type == ARG_PTR_TO_INT) return sizeof(u32); else if (type == ARG_PTR_TO_LONG) return sizeof(u64); return -EINVAL; } static int resolve_map_arg_type(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_arg_type *arg_type) { if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->type\n"); return -EACCES; } switch (meta->map_ptr->map_type) { case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: if (*arg_type == ARG_PTR_TO_MAP_VALUE) { *arg_type = ARG_PTR_TO_SOCKET; } else { verbose(env, "invalid arg_type for sockmap/sockhash\n"); return -EINVAL; } break; default: break; } return 0; } static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn) { u32 regno = BPF_REG_1 + arg; struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_reg_type expected_type, type = reg->type; enum bpf_arg_type arg_type = fn->arg_type[arg]; int err = 0; if (arg_type == ARG_DONTCARE) return 0; err = check_reg_arg(env, regno, SRC_OP); if (err) return err; if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { verbose(env, "R%d leaks addr into helper function\n", regno); return -EACCES; } return 0; } if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose(env, "helper access to the packet is not allowed\n"); return -EACCES; } if (arg_type == ARG_PTR_TO_MAP_VALUE || arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; } if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE || arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { expected_type = PTR_TO_STACK; if (register_is_null(reg) && arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) /* final test in check_stack_boundary() */; else if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO || arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) { expected_type = SCALAR_VALUE; if (type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_MAP_PTR) { expected_type = CONST_PTR_TO_MAP; if (type != expected_type) goto err_type; } else if (arg_type == ARG_PTR_TO_CTX || arg_type == ARG_PTR_TO_CTX_OR_NULL) { expected_type = PTR_TO_CTX; if (!(register_is_null(reg) && arg_type == ARG_PTR_TO_CTX_OR_NULL)) { if (type != expected_type) goto err_type; err = check_ctx_reg(env, reg, regno); if (err < 0) return err; } } else if (arg_type == ARG_PTR_TO_SOCK_COMMON) { expected_type = PTR_TO_SOCK_COMMON; /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ if (!type_is_sk_pointer(type)) goto err_type; if (reg->ref_obj_id) { if (meta->ref_obj_id) { verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", regno, reg->ref_obj_id, meta->ref_obj_id); return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; } } else if (arg_type == ARG_PTR_TO_SOCKET || arg_type == ARG_PTR_TO_SOCKET_OR_NULL) { expected_type = PTR_TO_SOCKET; if (!(register_is_null(reg) && arg_type == ARG_PTR_TO_SOCKET_OR_NULL)) { if (type != expected_type) goto err_type; } } else if (arg_type == ARG_PTR_TO_BTF_ID) { bool ids_match = false; expected_type = PTR_TO_BTF_ID; if (type != expected_type) goto err_type; if (!fn->check_btf_id) { if (reg->btf_id != meta->btf_id) { ids_match = btf_struct_ids_match(&env->log, reg->off, reg->btf_id, meta->btf_id); if (!ids_match) { verbose(env, "Helper has type %s got %s in R%d\n", kernel_type_name(meta->btf_id), kernel_type_name(reg->btf_id), regno); return -EACCES; } } } else if (!fn->check_btf_id(reg->btf_id, arg)) { verbose(env, "Helper does not support %s in R%d\n", kernel_type_name(reg->btf_id), regno); return -EACCES; } if ((reg->off && !ids_match) || !tnum_is_const(reg->var_off) || reg->var_off.value) { verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n", regno); return -EACCES; } } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) return -EACCES; } else if (meta->func_id == BPF_FUNC_spin_unlock) { if (process_spin_lock(env, regno, false)) return -EACCES; } else { verbose(env, "verifier internal error\n"); return -EFAULT; } } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be * passed in as argument, it's a SCALAR_VALUE type. Final test * happens during stack boundary checking. */ if (register_is_null(reg) && (arg_type == ARG_PTR_TO_MEM_OR_NULL || arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL)) /* final test in check_stack_boundary() */; else if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != PTR_TO_MEM && type != PTR_TO_RDONLY_BUF && type != PTR_TO_RDWR_BUF && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; } else if (arg_type_is_alloc_mem_ptr(arg_type)) { expected_type = PTR_TO_MEM; if (register_is_null(reg) && arg_type == ARG_PTR_TO_ALLOC_MEM_OR_NULL) /* final test in check_stack_boundary() */; else if (type != expected_type) goto err_type; if (meta->ref_obj_id) { verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", regno, reg->ref_obj_id, meta->ref_obj_id); return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; } else if (arg_type_is_int_ptr(arg_type)) { expected_type = PTR_TO_STACK; if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; } else { verbose(env, "unsupported arg_type %d\n", arg_type); return -EFAULT; } if (arg_type == ARG_CONST_MAP_PTR) { /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ meta->map_ptr = reg->map_ptr; } else if (arg_type == ARG_PTR_TO_MAP_KEY) { /* bpf_map_xxx(..., map_ptr, ..., key) call: * check that [key, key + map->key_size) are within * stack limits and initialized */ if (!meta->map_ptr) { /* in function declaration map_ptr must come before * map_key, so that it's verified and known before * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); } else if (arg_type == ARG_PTR_TO_MAP_VALUE || (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && !register_is_null(reg)) || arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE); err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, meta); } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); /* This is used to refine r0 return value bounds for helpers * that enforce this value as an upper bound on return values. * See do_refine_retval_range() for helpers that can refine * the return value. C type of helper is u32 so we pull register * bound from umax_value however, if negative verifier errors * out. Only upper bounds can be learned because retval is an * int type and negative retvals are allowed. */ meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check * happens using its boundaries. */ if (!tnum_is_const(reg->var_off)) /* For unprivileged variable accesses, disable raw * mode so that the program is required to * initialize all the memory that the helper could * just partially fill up. */ meta = NULL; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", regno); return -EACCES; } if (reg->umin_value == 0) { err = check_helper_mem_access(env, regno - 1, 0, zero_size_allowed, meta); if (err) return err; } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } err = check_helper_mem_access(env, regno - 1, reg->umax_value, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); } else if (arg_type_is_alloc_size(arg_type)) { if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d unbounded size, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } meta->mem_size = reg->var_off.value; } else if (arg_type_is_int_ptr(arg_type)) { int size = int_ptr_type_to_size(arg_type); err = check_helper_mem_access(env, regno, size, false, meta); if (err) return err; err = check_ptr_alignment(env, reg, 0, size, true); } return err; err_type: verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[type], reg_type_str[expected_type]); return -EACCES; } static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) { enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); if (func_id != BPF_FUNC_map_update_elem) return false; /* It's not possible to get access to a locked struct sock in these * contexts, so updating is safe. */ switch (type) { case BPF_PROG_TYPE_TRACING: if (eatype == BPF_TRACE_ITER) return true; break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: return true; default: break; } verbose(env, "cannot update sockmap in this context\n"); return false; } static int check_map_func_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, int func_id) { if (!map) return 0; /* We need a two way check, first is from map perspective ... */ switch (map->map_type) { case BPF_MAP_TYPE_PROG_ARRAY: if (func_id != BPF_FUNC_tail_call) goto error; break; case BPF_MAP_TYPE_PERF_EVENT_ARRAY: 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_xdp_output) goto error; break; case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && func_id != BPF_FUNC_ringbuf_submit && func_id != BPF_FUNC_ringbuf_discard && func_id != BPF_FUNC_ringbuf_query) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: if (func_id != BPF_FUNC_get_stackid) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: if (func_id != BPF_FUNC_skb_under_cgroup && func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; /* Restrict bpf side of cpumap and xskmap, open when use-cases * appear. */ case BPF_MAP_TYPE_CPUMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_push_elem) goto error; break; case BPF_MAP_TYPE_SK_STORAGE: if (func_id != BPF_FUNC_sk_storage_get && func_id != BPF_FUNC_sk_storage_delete) goto error; break; case BPF_MAP_TYPE_INODE_STORAGE: if (func_id != BPF_FUNC_inode_storage_get && func_id != BPF_FUNC_inode_storage_delete) goto error; break; default: break; } /* ... and second from the function itself. */ switch (func_id) { case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; if (env->subprog_cnt > 1) { verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n"); return -EINVAL; } break; case BPF_FUNC_perf_event_read: 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; case BPF_FUNC_get_stackid: if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; case BPF_FUNC_current_task_under_cgroup: case BPF_FUNC_skb_under_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; break; case BPF_FUNC_sk_redirect_map: case BPF_FUNC_msg_redirect_map: case BPF_FUNC_sock_map_update: if (map->map_type != BPF_MAP_TYPE_SOCKMAP) goto error; break; case BPF_FUNC_sk_redirect_hash: case BPF_FUNC_msg_redirect_hash: case BPF_FUNC_sock_hash_update: if (map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_get_local_storage: if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_pop_elem: case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto error; break; case BPF_FUNC_inode_storage_get: case BPF_FUNC_inode_storage_delete: if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE) goto error; break; default: break; } return 0; error: verbose(env, "cannot pass map_type %d into func %s#%d\n", map->map_type, func_id_name(func_id), func_id); return -EINVAL; } static bool check_raw_mode_ok(const struct bpf_func_proto *fn) { int count = 0; if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM) count++; if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM) count++; /* We only support one arg being in raw mode at the moment, * which is sufficient for the helper functions we have * right now. */ return count <= 1; } static bool check_args_pair_invalid(enum bpf_arg_type arg_curr, enum bpf_arg_type arg_next) { return (arg_type_is_mem_ptr(arg_curr) && !arg_type_is_mem_size(arg_next)) || (!arg_type_is_mem_ptr(arg_curr) && arg_type_is_mem_size(arg_next)); } static bool check_arg_pair_ok(const struct bpf_func_proto *fn) { /* bpf_xxx(..., buf, len) call will access 'len' * bytes from memory 'buf'. Both arg types need * to be paired, so make sure there's no buggy * helper function specification. */ if (arg_type_is_mem_size(fn->arg1_type) || arg_type_is_mem_ptr(fn->arg5_type) || check_args_pair_invalid(fn->arg1_type, fn->arg2_type) || check_args_pair_invalid(fn->arg2_type, fn->arg3_type) || check_args_pair_invalid(fn->arg3_type, fn->arg4_type) || check_args_pair_invalid(fn->arg4_type, fn->arg5_type)) return false; return true; } static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id) { int count = 0; if (arg_type_may_be_refcounted(fn->arg1_type)) count++; if (arg_type_may_be_refcounted(fn->arg2_type)) count++; if (arg_type_may_be_refcounted(fn->arg3_type)) count++; if (arg_type_may_be_refcounted(fn->arg4_type)) count++; if (arg_type_may_be_refcounted(fn->arg5_type)) count++; /* A reference acquiring function cannot acquire * another refcounted ptr. */ if (may_be_acquire_function(func_id) && count) return false; /* We only support one arg being unreferenced at the moment, * which is sufficient for the helper functions we have right now. */ return count <= 1; } static int check_func_proto(const struct bpf_func_proto *fn, int func_id) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && check_refcount_ok(fn, func_id) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, struct bpf_func_state *state) { struct bpf_reg_state *regs = state->regs, *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(env, regs, i); bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; if (reg_is_pkt_pointer_any(reg)) __mark_reg_unknown(env, reg); } } static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { struct bpf_verifier_state *vstate = env->cur_state; int i; for (i = 0; i <= vstate->curframe; i++) __clear_all_pkt_pointers(env, vstate->frame[i]); } static void release_reg_references(struct bpf_verifier_env *env, struct bpf_func_state *state, int ref_obj_id) { struct bpf_reg_state *regs = state->regs, *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) if (regs[i].ref_obj_id == ref_obj_id) mark_reg_unknown(env, regs, i); bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; if (reg->ref_obj_id == ref_obj_id) __mark_reg_unknown(env, reg); } } /* The pointer with the specified id has released its reference to kernel * resources. Identify all copies of the same pointer and clear the reference. */ static int release_reference(struct bpf_verifier_env *env, int ref_obj_id) { struct bpf_verifier_state *vstate = env->cur_state; int err; int i; err = release_reference_state(cur_func(env), ref_obj_id); if (err) return err; for (i = 0; i <= vstate->curframe; i++) release_reg_references(env, vstate->frame[i], ref_obj_id); return 0; } static void clear_caller_saved_regs(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { int i; /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_info_aux *func_info_aux; struct bpf_func_state *caller, *callee; int i, err, subprog, target_insn; bool is_global = false; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", state->curframe + 2); return -E2BIG; } target_insn = *insn_idx + insn->imm; subprog = find_subprog(env, target_insn + 1); if (subprog < 0) { verbose(env, "verifier bug. No program starts at insn %d\n", target_insn + 1); return -EFAULT; } caller = state->frame[state->curframe]; if (state->frame[state->curframe + 1]) { verbose(env, "verifier bug. Frame %d already allocated\n", state->curframe + 1); return -EFAULT; } func_info_aux = env->prog->aux->func_info_aux; if (func_info_aux) is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; err = btf_check_func_arg_match(env, subprog, caller->regs); if (err == -EFAULT) return err; if (is_global) { if (err) { verbose(env, "Caller passes invalid args into func#%d\n", subprog); return err; } else { if (env->log.level & BPF_LOG_LEVEL) verbose(env, "Func#%d is global and valid. Skipping.\n", subprog); clear_caller_saved_regs(env, caller->regs); /* All global functions return SCALAR_VALUE */ mark_reg_unknown(env, caller->regs, BPF_REG_0); /* continue with next insn after call */ return 0; } } callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; state->frame[state->curframe + 1] = callee; /* callee cannot access r0, r6 - r9 for reading and has to write * into its own stack before reading from it. * callee can read/write into caller's stack */ init_func_state(env, callee, /* remember the callsite, it will be used by bpf_exit */ *insn_idx /* callsite */, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); /* Transfer references to the callee */ err = transfer_reference_state(callee, caller); if (err) return err; /* copy r1 - r5 args that callee can access. The copy includes parent * pointers, which connects us up to the liveness chain */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; clear_caller_saved_regs(env, caller->regs); /* only increment it after check_reg_arg() finished */ state->curframe++; /* and go analyze first insn of the callee */ *insn_idx = target_insn; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); print_verifier_state(env, caller); verbose(env, "callee:\n"); print_verifier_state(env, callee); } return 0; } static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; if (r0->type == PTR_TO_STACK) { /* technically it's ok to return caller's stack pointer * (or caller's caller's pointer) back to the caller, * since these pointers are valid. Only current stack * pointer will be invalid as soon as function exits, * but let's be conservative */ verbose(env, "cannot return stack pointer to the caller\n"); return -EINVAL; } state->curframe--; caller = state->frame[state->curframe]; /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; /* Transfer references to the caller */ err = transfer_reference_state(caller, callee); if (err) return err; *insn_idx = callee->callsite + 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, callee); verbose(env, "to caller at %d:\n", *insn_idx); print_verifier_state(env, caller); } /* clear everything in the callee */ free_func_state(callee); state->frame[state->curframe + 1] = NULL; return 0; } static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, int func_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; if (ret_type != RET_INTEGER || (func_id != BPF_FUNC_get_stack && func_id != BPF_FUNC_probe_read_str && func_id != BPF_FUNC_probe_read_kernel_str && func_id != BPF_FUNC_probe_read_user_str)) return; ret_reg->smax_value = meta->msize_max_value; ret_reg->s32_max_value = meta->msize_max_value; __reg_deduce_bounds(ret_reg); __reg_bound_offset(ret_reg); __update_reg_bounds(ret_reg); } static int record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_map *map = meta->map_ptr; if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_map_push_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_peek_elem) return 0; if (map == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } /* In case of read-only, some additional restrictions * need to be applied in order to prevent altering the * state of the map from program side. */ if ((map->map_flags & BPF_F_RDONLY_PROG) && (func_id == BPF_FUNC_map_delete_elem || func_id == BPF_FUNC_map_update_elem || func_id == BPF_FUNC_map_push_elem || func_id == BPF_FUNC_map_pop_elem)) { verbose(env, "write into map forbidden\n"); return -EACCES; } if (!BPF_MAP_PTR(aux->map_ptr_state)) bpf_map_ptr_store(aux, meta->map_ptr, !meta->map_ptr->bypass_spec_v1); else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr) bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON, !meta->map_ptr->bypass_spec_v1); return 0; } static int record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_reg_state *regs = cur_regs(env), *reg; struct bpf_map *map = meta->map_ptr; struct tnum range; u64 val; int err; if (func_id != BPF_FUNC_tail_call) return 0; if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } range = tnum_range(0, map->max_entries - 1); reg = ®s[BPF_REG_3]; if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } err = mark_chain_precision(env, BPF_REG_3); if (err) return err; val = reg->var_off.value; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); else if (!bpf_map_key_poisoned(aux) && bpf_map_key_immediate(aux) != val) bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } static int check_reference_leak(struct bpf_verifier_env *env) { struct bpf_func_state *state = cur_func(env); int i; for (i = 0; i < state->acquired_refs; i++) { verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); } return state->acquired_refs ? -EINVAL : 0; } static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; bool changes_data; int i, err; /* find function prototype */ if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { verbose(env, "invalid func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } if (env->ops->get_func_proto) fn = env->ops->get_func_proto(func_id, env->prog); if (!fn) { verbose(env, "unknown func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n"); return -EINVAL; } if (fn->allowed && !fn->allowed(env->prog)) { verbose(env, "helper call is not allowed in probe\n"); return -EINVAL; } /* With LD_ABS/IND some JITs save/restore skb from r1. */ changes_data = bpf_helper_changes_pkt_data(fn->func); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n", func_id_name(func_id), func_id); return -EINVAL; } memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; err = check_func_proto(fn, func_id); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); return err; } meta.func_id = func_id; /* check args */ for (i = 0; i < 5; i++) { if (!fn->check_btf_id) { err = btf_resolve_helper_id(&env->log, fn, i); if (err > 0) meta.btf_id = err; } err = check_func_arg(env, i, &meta, fn); if (err) return err; } err = record_func_map(env, &meta, func_id, insn_idx); if (err) return err; err = record_func_key(env, &meta, func_id, insn_idx); if (err) return err; /* Mark slots with STACK_MISC in case of raw mode, stack offset * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1, false); if (err) return err; } if (func_id == BPF_FUNC_tail_call) { err = check_reference_leak(env); if (err) { verbose(env, "tail_call would lead to reference leak\n"); return err; } } else if (is_release_function(func_id)) { err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); return err; } } regs = cur_regs(env); /* check that flags argument in get_local_storage(map, flags) is 0, * this is required because get_local_storage() can't return an error. */ if (func_id == BPF_FUNC_get_local_storage && !register_is_null(®s[BPF_REG_2])) { verbose(env, "get_local_storage() doesn't support non-zero flags\n"); return -EINVAL; } /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* helper call returns 64-bit value. */ regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* update return register (already marked as written above) */ if (fn->ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); } else if (fn->ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || fn->ret_type == RET_PTR_TO_MAP_VALUE) { /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() */ if (meta.map_ptr == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; if (map_value_has_spin_lock(meta.map_ptr)) regs[BPF_REG_0].id = ++env->id_gen; } else { regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; } } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; regs[BPF_REG_0].mem_size = meta.mem_size; } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) { int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL; ret_btf_id = *fn->ret_btf_id; if (ret_btf_id == 0) { verbose(env, "invalid return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } regs[BPF_REG_0].btf_id = ret_btf_id; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } if (is_ptr_cast_function(func_id)) { /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else if (is_acquire_function(func_id, meta.map_ptr)) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = id; /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = id; } do_refine_retval_range(regs, fn->ret_type, func_id, &meta); err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; if ((func_id == BPF_FUNC_get_stack || func_id == BPF_FUNC_get_task_stack) && !env->prog->has_callchain_buf) { const char *err_str; #ifdef CONFIG_PERF_EVENTS err = get_callchain_buffers(sysctl_perf_event_max_stack); err_str = "cannot get callchain buffer for func %s#%d\n"; #else err = -ENOTSUPP; err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n"; #endif if (err) { verbose(env, err_str, func_id_name(func_id), func_id); return err; } env->prog->has_callchain_buf = true; } if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack) env->prog->call_get_stack = true; if (changes_data) clear_all_pkt_pointers(env); return 0; } static bool signed_add_overflows(s64 a, s64 b) { /* Do the add in u64, where overflow is well-defined */ s64 res = (s64)((u64)a + (u64)b); if (b < 0) return res > a; return res < a; } static bool signed_add32_overflows(s64 a, s64 b) { /* Do the add in u32, where overflow is well-defined */ s32 res = (s32)((u32)a + (u32)b); if (b < 0) return res > a; return res < a; } static bool signed_sub_overflows(s32 a, s32 b) { /* Do the sub in u64, where overflow is well-defined */ s64 res = (s64)((u64)a - (u64)b); if (b < 0) return res < a; return res > a; } static bool signed_sub32_overflows(s32 a, s32 b) { /* Do the sub in u64, where overflow is well-defined */ s32 res = (s32)((u32)a - (u32)b); if (b < 0) return res < a; return res > a; } static bool check_reg_sane_offset(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, enum bpf_reg_type type) { bool known = tnum_is_const(reg->var_off); s64 val = reg->var_off.value; s64 smin = reg->smin_value; if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", reg_type_str[type], val); return false; } if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %d is not allowed\n", reg_type_str[type], reg->off); return false; } if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", reg_type_str[type]); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", smin, reg_type_str[type]); return false; } return true; } static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) { return &env->insn_aux_data[env->insn_idx]; } static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, u32 *ptr_limit, u8 opcode, bool off_is_neg) { bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || (opcode == BPF_SUB && !off_is_neg); u32 off; switch (ptr_reg->type) { case PTR_TO_STACK: /* Indirect variable offset stack access is prohibited in * unprivileged mode so it's not handled here. */ off = ptr_reg->off + ptr_reg->var_off.value; if (mask_to_left) *ptr_limit = MAX_BPF_STACK + off; else *ptr_limit = -off; return 0; case PTR_TO_MAP_VALUE: if (mask_to_left) { *ptr_limit = ptr_reg->umax_value + ptr_reg->off; } else { off = ptr_reg->smin_value + ptr_reg->off; *ptr_limit = ptr_reg->map_ptr->value_size - off; } return 0; default: return -EINVAL; } } static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K; } static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, u32 alu_state, u32 alu_limit) { /* If we arrived here from different branches with different * state or limits to sanitize, then this won't work. */ if (aux->alu_state && (aux->alu_state != alu_state || aux->alu_limit != alu_limit)) return -EACCES; /* Corresponding fixup done in fixup_bpf_calls(). */ aux->alu_state = alu_state; aux->alu_limit = alu_limit; return 0; } static int sanitize_val_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); if (can_skip_alu_sanitation(env, insn)) return 0; return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); } static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, struct bpf_reg_state *dst_reg, bool off_is_neg) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_insn_aux_data *aux = cur_aux(env); bool ptr_is_dst_reg = ptr_reg == dst_reg; u8 opcode = BPF_OP(insn->code); u32 alu_state, alu_limit; struct bpf_reg_state tmp; bool ret; if (can_skip_alu_sanitation(env, insn)) return 0; /* We already marked aux for masking from non-speculative * paths, thus we got here in the first place. We only care * to explore bad access from here. */ if (vstate->speculative) goto do_sim; alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg)) return 0; if (update_alu_sanitation_state(aux, alu_state, alu_limit)) return -EACCES; do_sim: /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of * masking when off was not within expected range. If off * sits in dst, then we temporarily need to move ptr there * to simulate dst (== 0) +/-= ptr. Needed, for example, * for cases where we use K-based arithmetic in one direction * and truncated reg-based in the other in order to explore * bad access. */ if (!ptr_is_dst_reg) { tmp = *dst_reg; *dst_reg = *ptr_reg; } ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? -EFAULT : 0; } /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. * If we return -EACCES, caller may want to try again treating pointer as a * scalar. So we only emit a diagnostic if !env->allow_ptr_leaks. */ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg; bool known = tnum_is_const(off_reg->var_off); s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; u32 dst = insn->dst_reg, src = insn->src_reg; u8 opcode = BPF_OP(insn->code); int ret; dst_reg = ®s[dst]; if ((known && (smin_val != smax_val || umin_val != umax_val)) || smin_val > smax_val || umin_val > umax_val) { /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { __mark_reg_unknown(env, dst_reg); return 0; } verbose(env, "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } switch (ptr_reg->type) { case PTR_TO_MAP_VALUE_OR_NULL: verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; case PTR_TO_MAP_VALUE: if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) { verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n", off_reg == dst_reg ? dst : src); return -EACCES; } /* fall-through */ default: break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. * The id may be overwritten later if we create a new variable offset. */ dst_reg->type = ptr_reg->type; dst_reg->id = ptr_reg->id; if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) || !check_reg_sane_offset(env, ptr_reg, ptr_reg->type)) return -EINVAL; /* pointer types do not carry 32-bit bounds at the moment. */ __mark_reg32_unbounded(dst_reg); switch (opcode) { case BPF_ADD: ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); if (ret < 0) { verbose(env, "R%d tried to add from different maps or paths\n", dst); return ret; } /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ if (known && (ptr_reg->off + smin_val == (s64)(s32)(ptr_reg->off + smin_val))) { /* pointer += K. Accumulate it into fixed offset */ dst_reg->smin_value = smin_ptr; dst_reg->smax_value = smax_ptr; dst_reg->umin_value = umin_ptr; dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->off = ptr_reg->off + smin_val; dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. Note that off_reg->off * == 0, since it's a scalar. * dst_reg gets the pointer type and since some positive * integer value was added to the pointer, give it a new 'id' * if it's a PTR_TO_PACKET. * this creates a new 'base' pointer, off_reg (variable) gets * added into the variable offset, and we copy the fixed offset * from ptr_reg. */ if (signed_add_overflows(smin_ptr, smin_val) || signed_add_overflows(smax_ptr, smax_val)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = smin_ptr + smin_val; dst_reg->smax_value = smax_ptr + smax_val; } if (umin_ptr + umin_val < umin_ptr || umax_ptr + umax_val < umax_ptr) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value = umin_ptr + umin_val; dst_reg->umax_value = umax_ptr + umax_val; } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ dst_reg->raw = 0; } break; case BPF_SUB: ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); if (ret < 0) { verbose(env, "R%d tried to sub from different maps or paths\n", dst); return ret; } if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", dst); return -EACCES; } /* We don't allow subtraction from FP, because (according to * test_verifier.c test "invalid fp arithmetic", JITs might not * be able to deal with it. */ if (ptr_reg->type == PTR_TO_STACK) { verbose(env, "R%d subtraction from stack pointer prohibited\n", dst); return -EACCES; } if (known && (ptr_reg->off - smin_val == (s64)(s32)(ptr_reg->off - smin_val))) { /* pointer -= K. Subtract it from fixed offset */ dst_reg->smin_value = smin_ptr; dst_reg->smax_value = smax_ptr; dst_reg->umin_value = umin_ptr; dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->id = ptr_reg->id; dst_reg->off = ptr_reg->off - smin_val; dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. If the subtrahend is known * nonnegative, then any reg->range we had before is still good. */ if (signed_sub_overflows(smin_ptr, smax_val) || signed_sub_overflows(smax_ptr, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = smin_ptr - smax_val; dst_reg->smax_value = smax_ptr - smin_val; } if (umin_ptr < umax_val) { /* Overflow possible, we know nothing */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->umin_value = umin_ptr - umax_val; dst_reg->umax_value = umax_ptr - umin_val; } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) dst_reg->raw = 0; } break; case BPF_AND: case BPF_OR: case BPF_XOR: /* bitwise ops on pointers are troublesome, prohibit. */ verbose(env, "R%d bitwise operator %s on pointer prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; } if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type)) return -EINVAL; __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); /* For unprivileged we require that resulting offset must be in bounds * in order to be able to sanitize access later on. */ if (!env->bypass_spec_v1) { if (dst_reg->type == PTR_TO_MAP_VALUE && check_map_access(env, dst, dst_reg->off, 1, false)) { verbose(env, "R%d pointer arithmetic of map value goes out of range, " "prohibited for !root\n", dst); return -EACCES; } else if (dst_reg->type == PTR_TO_STACK && check_stack_access(env, dst_reg, dst_reg->off + dst_reg->var_off.value, 1)) { verbose(env, "R%d stack pointer arithmetic goes out of range, " "prohibited for !root\n", dst); return -EACCES; } } return 0; } static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; s32 smax_val = src_reg->s32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) || signed_add32_overflows(dst_reg->s32_max_value, smax_val)) { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value += smin_val; dst_reg->s32_max_value += smax_val; } if (dst_reg->u32_min_value + umin_val < umin_val || dst_reg->u32_max_value + umax_val < umax_val) { dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { dst_reg->u32_min_value += umin_val; dst_reg->u32_max_value += umax_val; } } static void scalar_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; s64 smax_val = src_reg->smax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (signed_add_overflows(dst_reg->smin_value, smin_val) || signed_add_overflows(dst_reg->smax_value, smax_val)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value += smin_val; dst_reg->smax_value += smax_val; } if (dst_reg->umin_value + umin_val < umin_val || dst_reg->umax_value + umax_val < umax_val) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value += umin_val; dst_reg->umax_value += umax_val; } } static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; s32 smax_val = src_reg->s32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) || signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value -= smax_val; dst_reg->s32_max_value -= smin_val; } if (dst_reg->u32_min_value < umax_val) { /* Overflow possible, we know nothing */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->u32_min_value -= umax_val; dst_reg->u32_max_value -= umin_val; } } static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; s64 smax_val = src_reg->smax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (signed_sub_overflows(dst_reg->smin_value, smax_val) || signed_sub_overflows(dst_reg->smax_value, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value -= smax_val; dst_reg->smax_value -= smin_val; } if (dst_reg->umin_value < umax_val) { /* Overflow possible, we know nothing */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->umin_value -= umax_val; dst_reg->umax_value -= umin_val; } } static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (smin_val < 0 || dst_reg->s32_min_value < 0) { /* Ain't nobody got time to multiply that sign */ __mark_reg32_unbounded(dst_reg); return; } /* Both values are positive, so we can work with unsigned and * copy the result to signed (unless it exceeds S32_MAX). */ if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) { /* Potential overflow, we know nothing */ __mark_reg32_unbounded(dst_reg); return; } dst_reg->u32_min_value *= umin_val; dst_reg->u32_max_value *= umax_val; if (dst_reg->u32_max_value > S32_MAX) { /* Overflow possible, we know nothing */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } } static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (smin_val < 0 || dst_reg->smin_value < 0) { /* Ain't nobody got time to multiply that sign */ __mark_reg64_unbounded(dst_reg); return; } /* Both values are positive, so we can work with unsigned and * copy the result to signed (unless it exceeds S64_MAX). */ if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { /* Potential overflow, we know nothing */ __mark_reg64_unbounded(dst_reg); return; } dst_reg->umin_value *= umin_val; dst_reg->umax_value *= umax_val; if (dst_reg->umax_value > S64_MAX) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } } static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; u32 umax_val = src_reg->u32_max_value; /* Assuming scalar64_min_max_and will be called so its safe * to skip updating register for known 32-bit case. */ if (src_known && dst_known) return; /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val); if (dst_reg->s32_min_value < 0 || smin_val < 0) { /* Lose signed bounds when ANDing negative numbers, * ain't nobody got time for that. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { /* ANDing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); s64 smin_val = src_reg->smin_value; u64 umax_val = src_reg->umax_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value & src_reg->var_off.value); return; } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = min(dst_reg->umax_value, umax_val); if (dst_reg->smin_value < 0 || smin_val < 0) { /* Lose signed bounds when ANDing negative numbers, * ain't nobody got time for that. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { /* ANDing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->smin_value; u32 umin_val = src_reg->umin_value; /* Assuming scalar64_min_max_or will be called so it is safe * to skip updating register for known case. */ if (src_known && dst_known) return; /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val); dst_reg->u32_max_value = var32_off.value | var32_off.mask; if (dst_reg->s32_min_value < 0 || smin_val < 0) { /* Lose signed bounds when ORing negative numbers, * ain't nobody got time for that. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { /* ORing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->s32_min_value = dst_reg->umin_value; dst_reg->s32_max_value = dst_reg->umax_value; } } static void scalar_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); s64 smin_val = src_reg->smin_value; u64 umin_val = src_reg->umin_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value | src_reg->var_off.value); return; } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->umin_value = max(dst_reg->umin_value, umin_val); dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; if (dst_reg->smin_value < 0 || smin_val < 0) { /* Lose signed bounds when ORing negative numbers, * ain't nobody got time for that. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { /* ORing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; /* Assuming scalar64_min_max_xor will be called so it is safe * to skip updating register for known case. */ if (src_known && dst_known) return; /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = var32_off.value | var32_off.mask; if (dst_reg->s32_min_value >= 0 && smin_val >= 0) { /* XORing two positive sign numbers gives a positive, * so safe to cast u32 result into s32. */ dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); s64 smin_val = src_reg->smin_value; if (src_known && dst_known) { /* dst_reg->var_off.value has been updated earlier */ __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get both minimum and maximum from the var_off. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; if (dst_reg->smin_value >= 0 && smin_val >= 0) { /* XORing two positive sign numbers gives a positive, * so safe to cast u64 result into s64. */ dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } __update_reg_bounds(dst_reg); } static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* We lose all sign bit information (except what we can pick * up from var_off) */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; /* If we might shift our top bit out, then we know nothing */ if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) { dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { dst_reg->u32_min_value <<= umin_val; dst_reg->u32_max_value <<= umax_val; } } static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* u32 alu operation will zext upper bits */ struct tnum subreg = tnum_subreg(dst_reg->var_off); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val)); /* Not required but being careful mark reg64 bounds as unknown so * that we are forced to pick them up from tnum and zext later and * if some path skips this step we are still safe. */ __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* Special case <<32 because it is a common compiler pattern to sign * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are * positive we know this shift will also be positive so we can track * bounds correctly. Otherwise we lose all sign bit information except * what we can pick up from var_off. Perhaps we can generalize this * later to shifts of any length. */ if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0) dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32; else dst_reg->smax_value = S64_MAX; if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0) dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32; else dst_reg->smin_value = S64_MIN; /* If we might shift our top bit out, then we know nothing */ if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value <<= umin_val; dst_reg->umax_value <<= umax_val; } } static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* scalar64 calc uses 32bit unshifted bounds so must be called first */ __scalar64_min_max_lsh(dst_reg, umin_val, umax_val); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { struct tnum subreg = tnum_subreg(dst_reg->var_off); u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounts capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; dst_reg->var_off = tnum_rshift(subreg, umin_val); dst_reg->u32_min_value >>= umax_val; dst_reg->u32_max_value >>= umin_val; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounts capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); dst_reg->umin_value >>= umax_val; dst_reg->umax_value >>= umin_val; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in. Take easy way out and mark unbounded * so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->u32_min_value; /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val); dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val); dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->umin_value; /* Upon reaching here, src_known is true and umax_val is equal * to umin_val. */ dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in from upper 32-bits. Take easy way out * and mark unbounded so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. */ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state src_reg) { struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); bool src_known; s64 smin_val, smax_val; u64 umin_val, umax_val; s32 s32_min_val, s32_max_val; u32 u32_min_val, u32_max_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; u32 dst = insn->dst_reg; int ret; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; umin_val = src_reg.umin_value; umax_val = src_reg.umax_value; s32_min_val = src_reg.s32_min_value; s32_max_val = src_reg.s32_max_value; u32_min_val = src_reg.u32_min_value; u32_max_val = src_reg.u32_max_value; if (alu32) { src_known = tnum_subreg_is_const(src_reg.var_off); if ((src_known && (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) || s32_min_val > s32_max_val || u32_min_val > u32_max_val) { /* Taint dst register if offset had invalid bounds * derived from e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } } else { src_known = tnum_is_const(src_reg.var_off); if ((src_known && (smin_val != smax_val || umin_val != umax_val)) || smin_val > smax_val || umin_val > umax_val) { /* Taint dst register if offset had invalid bounds * derived from e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { __mark_reg_unknown(env, dst_reg); return 0; } /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. * There are two classes of instructions: The first class we track both * alu32 and alu64 sign/unsigned bounds independently this provides the * greatest amount of precision when alu operations are mixed with jmp32 * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD, * and BPF_OR. This is possible because these ops have fairly easy to * understand and calculate behavior in both 32-bit and 64-bit alu ops. * See alu32 verifier tests for examples. The second class of * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy * with regards to tracking sign/unsigned bounds because the bits may * cross subreg boundaries in the alu64 case. When this happens we mark * the reg unbounded in the subreg bound space and use the resulting * tnum to calculate an approximation of the sign/unsigned bounds. */ switch (opcode) { case BPF_ADD: ret = sanitize_val_alu(env, insn); if (ret < 0) { verbose(env, "R%d tried to add from different pointers or scalars\n", dst); return ret; } scalar32_min_max_add(dst_reg, &src_reg); scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: ret = sanitize_val_alu(env, insn); if (ret < 0) { verbose(env, "R%d tried to sub from different pointers or scalars\n", dst); return ret; } scalar32_min_max_sub(dst_reg, &src_reg); scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; case BPF_MUL: dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); scalar32_min_max_mul(dst_reg, &src_reg); scalar_min_max_mul(dst_reg, &src_reg); break; case BPF_AND: dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off); scalar32_min_max_and(dst_reg, &src_reg); scalar_min_max_and(dst_reg, &src_reg); break; case BPF_OR: dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off); scalar32_min_max_or(dst_reg, &src_reg); scalar_min_max_or(dst_reg, &src_reg); break; case BPF_XOR: dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off); scalar32_min_max_xor(dst_reg, &src_reg); scalar_min_max_xor(dst_reg, &src_reg); break; case BPF_LSH: if (umax_val >= insn_bitness) { /* Shifts greater than 31 or 63 are undefined. * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; } if (alu32) scalar32_min_max_lsh(dst_reg, &src_reg); else scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: if (umax_val >= insn_bitness) { /* Shifts greater than 31 or 63 are undefined. * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; } if (alu32) scalar32_min_max_rsh(dst_reg, &src_reg); else scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: if (umax_val >= insn_bitness) { /* Shifts greater than 31 or 63 are undefined. * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; } if (alu32) scalar32_min_max_arsh(dst_reg, &src_reg); else scalar_min_max_arsh(dst_reg, &src_reg); break; default: mark_reg_unknown(env, regs, insn->dst_reg); break; } /* ALU32 ops are zero extended into 64bit register */ if (alu32) zext_32_to_64(dst_reg); __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); return 0; } /* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max * and var_off. */ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); int err; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; if (BPF_SRC(insn->code) == BPF_X) { src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields * an arbitrary scalar. Disallow all math except * pointer subtraction */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } verbose(env, "R%d pointer %s pointer prohibited\n", insn->dst_reg, bpf_alu_string[opcode >> 4]); return -EACCES; } else { /* scalar += pointer * This is legal, but we have to reverse our * src/dest handling in computing the range */ err = mark_chain_precision(env, insn->dst_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ err = mark_chain_precision(env, insn->src_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); } } else { /* Pretend the src is a reg with a known value, since we only * need to be able to read from this state. */ off_reg.type = SCALAR_VALUE; __mark_reg_known(&off_reg, insn->imm); src_reg = &off_reg; if (ptr_reg) /* pointer += K */ return adjust_ptr_min_max_vals(env, insn, ptr_reg, src_reg); } /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { print_verifier_state(env, state); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { print_verifier_state(env, state); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); } /* check validity of 32-bit and 64-bit arithmetic operations */ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); int err; if (opcode == BPF_END || opcode == BPF_NEG) { if (opcode == BPF_NEG) { if (BPF_SRC(insn->code) != 0 || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { verbose(env, "BPF_NEG uses reserved fields\n"); return -EINVAL; } } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || BPF_CLASS(insn->code) == BPF_ALU64) { verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } } /* check src operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer arithmetic prohibited\n", insn->dst_reg); return -EACCES; } /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } /* check dest operand, mark as required later */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = regs + insn->src_reg; struct bpf_reg_state *dst_reg = regs + insn->dst_reg; if (BPF_CLASS(insn->code) == BPF_ALU64) { /* case: R1 = R2 * copy register state to dest reg */ *dst_reg = *src_reg; dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { *dst_reg = *src_reg; dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = env->insn_idx + 1; } else { mark_reg_unknown(env, regs, insn->dst_reg); } zext_32_to_64(dst_reg); } } else { /* case: R = imm * remember the value we stored into this reg */ /* clear any state __mark_reg_known doesn't set */ mark_reg_unknown(env, regs, insn->dst_reg); regs[insn->dst_reg].type = SCALAR_VALUE; if (BPF_CLASS(insn->code) == BPF_ALU64) { __mark_reg_known(regs + insn->dst_reg, insn->imm); } else { __mark_reg_known(regs + insn->dst_reg, (u32)insn->imm); } } } else if (opcode > BPF_END) { verbose(env, "invalid BPF_ALU opcode %x\n", opcode); return -EINVAL; } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if ((opcode == BPF_MOD || opcode == BPF_DIV) && BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { verbose(env, "div by zero\n"); return -EINVAL; } if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; if (insn->imm < 0 || insn->imm >= size) { verbose(env, "invalid shift %d\n", insn->imm); return -EINVAL; } } /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; return adjust_reg_min_max_vals(env, insn); } return 0; } static void __find_good_pkt_pointers(struct bpf_func_state *state, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, u16 new_range) { struct bpf_reg_state *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) { reg = &state->regs[i]; if (reg->type == type && reg->id == dst_reg->id) /* keep the maximum range already checked */ reg->range = max(reg->range, new_range); } bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; if (reg->type == type && reg->id == dst_reg->id) reg->range = max(reg->range, new_range); } } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { u16 new_range; int i; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) /* This doesn't give us any range */ return; if (dst_reg->umax_value > MAX_PACKET_OFF || dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF) /* Risk of overflow. For instance, ptr + (1<<63) may be less * than pkt_end, but that's because it's also less than pkt. */ return; new_range = dst_reg->off; if (range_right_open) new_range--; /* Examples for register markings: * * pkt_data in dst register: * * r2 = r3; * r2 += 8; * if (r2 > pkt_end) goto * * * r2 = r3; * r2 += 8; * if (r2 < pkt_end) goto * * * Where: * r2 == dst_reg, pkt_end == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * pkt_data in src register: * * r2 = r3; * r2 += 8; * if (pkt_end >= r2) goto * * * r2 = r3; * r2 += 8; * if (pkt_end <= r2) goto * * * Where: * pkt_end == dst_reg, r2 == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) * and [r3, r3 + 8-1) respectively is safe to access depending on * the check. */ /* If our ids match, then we must have the same max_value. And we * don't care about the other reg's fixed offset, since if it's too big * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ for (i = 0; i <= vstate->curframe; i++) __find_good_pkt_pointers(vstate->frame[i], dst_reg, type, new_range); } static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) { struct tnum subreg = tnum_subreg(reg->var_off); s32 sval = (s32)val; switch (opcode) { case BPF_JEQ: if (tnum_is_const(subreg)) return !!tnum_equals_const(subreg, val); break; case BPF_JNE: if (tnum_is_const(subreg)) return !tnum_equals_const(subreg, val); break; case BPF_JSET: if ((~subreg.mask & subreg.value) & val) return 1; if (!((subreg.mask | subreg.value) & val)) return 0; break; case BPF_JGT: if (reg->u32_min_value > val) return 1; else if (reg->u32_max_value <= val) return 0; break; case BPF_JSGT: if (reg->s32_min_value > sval) return 1; else if (reg->s32_max_value < sval) return 0; break; case BPF_JLT: if (reg->u32_max_value < val) return 1; else if (reg->u32_min_value >= val) return 0; break; case BPF_JSLT: if (reg->s32_max_value < sval) return 1; else if (reg->s32_min_value >= sval) return 0; break; case BPF_JGE: if (reg->u32_min_value >= val) return 1; else if (reg->u32_max_value < val) return 0; break; case BPF_JSGE: if (reg->s32_min_value >= sval) return 1; else if (reg->s32_max_value < sval) return 0; break; case BPF_JLE: if (reg->u32_max_value <= val) return 1; else if (reg->u32_min_value > val) return 0; break; case BPF_JSLE: if (reg->s32_max_value <= sval) return 1; else if (reg->s32_min_value > sval) return 0; break; } return -1; } static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) { s64 sval = (s64)val; switch (opcode) { case BPF_JEQ: if (tnum_is_const(reg->var_off)) return !!tnum_equals_const(reg->var_off, val); break; case BPF_JNE: if (tnum_is_const(reg->var_off)) return !tnum_equals_const(reg->var_off, val); break; case BPF_JSET: if ((~reg->var_off.mask & reg->var_off.value) & val) return 1; if (!((reg->var_off.mask | reg->var_off.value) & val)) return 0; break; case BPF_JGT: if (reg->umin_value > val) return 1; else if (reg->umax_value <= val) return 0; break; case BPF_JSGT: if (reg->smin_value > sval) return 1; else if (reg->smax_value < sval) return 0; break; case BPF_JLT: if (reg->umax_value < val) return 1; else if (reg->umin_value >= val) return 0; break; case BPF_JSLT: if (reg->smax_value < sval) return 1; else if (reg->smin_value >= sval) return 0; break; case BPF_JGE: if (reg->umin_value >= val) return 1; else if (reg->umax_value < val) return 0; break; case BPF_JSGE: if (reg->smin_value >= sval) return 1; else if (reg->smax_value < sval) return 0; break; case BPF_JLE: if (reg->umax_value <= val) return 1; else if (reg->umin_value > val) return 0; break; case BPF_JSLE: if (reg->smax_value <= sval) return 1; else if (reg->smin_value > sval) return 0; break; } return -1; } /* compute branch direction of the expression "if (reg opcode val) goto target;" * and return: * 1 - branch will be taken and "goto target" will be executed * 0 - branch will not be taken and fall-through to next insn * -1 - unknown. Example: "if (reg < 5)" is unknown when register value * range [0,10] */ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, bool is_jmp32) { if (__is_pointer_value(false, reg)) { if (!reg_type_not_null(reg->type)) return -1; /* If pointer is valid tests against zero will fail so we can * use this to direct branch taken. */ if (val != 0) return -1; switch (opcode) { case BPF_JEQ: return 0; case BPF_JNE: return 1; default: return -1; } } if (is_jmp32) return is_branch32_taken(reg, val, opcode); return is_branch64_taken(reg, val, opcode); } /* Adjusts the register min/max values in the case that the dst_reg is the * variable register that we are working on, and src_reg is a constant or we're * simply doing a BPF_K check. * In JEQ/JNE cases we also adjust the var_off values. */ static void reg_set_min_max(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u32 val32, u8 opcode, bool is_jmp32) { struct tnum false_32off = tnum_subreg(false_reg->var_off); struct tnum false_64off = false_reg->var_off; struct tnum true_32off = tnum_subreg(true_reg->var_off); struct tnum true_64off = true_reg->var_off; s64 sval = (s64)val; s32 sval32 = (s32)val32; /* If the dst_reg is a pointer, we can't learn anything about its * variable offset from the compare (unless src_reg were a pointer into * the same object, but we don't bother with that. * Since false_reg and true_reg have the same type by construction, we * only need to check one of them for pointerness. */ if (__is_pointer_value(false, false_reg)) return; switch (opcode) { case BPF_JEQ: case BPF_JNE: { struct bpf_reg_state *reg = opcode == BPF_JEQ ? true_reg : false_reg; /* For BPF_JEQ, if this is false we know nothing Jon Snow, but * if it is true we know the value for sure. Likewise for * BPF_JNE. */ if (is_jmp32) __mark_reg32_known(reg, val32); else __mark_reg_known(reg, val); break; } case BPF_JSET: if (is_jmp32) { false_32off = tnum_and(false_32off, tnum_const(~val32)); if (is_power_of_2(val32)) true_32off = tnum_or(true_32off, tnum_const(val32)); } else { false_64off = tnum_and(false_64off, tnum_const(~val)); if (is_power_of_2(val)) true_64off = tnum_or(true_64off, tnum_const(val)); } break; case BPF_JGE: case BPF_JGT: { if (is_jmp32) { u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1; u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32; false_reg->u32_max_value = min(false_reg->u32_max_value, false_umax); true_reg->u32_min_value = max(true_reg->u32_min_value, true_umin); } else { u64 false_umax = opcode == BPF_JGT ? val : val - 1; u64 true_umin = opcode == BPF_JGT ? val + 1 : val; false_reg->umax_value = min(false_reg->umax_value, false_umax); true_reg->umin_value = max(true_reg->umin_value, true_umin); } break; } case BPF_JSGE: case BPF_JSGT: { if (is_jmp32) { s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1; s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32; false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax); true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin); } else { s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; false_reg->smax_value = min(false_reg->smax_value, false_smax); true_reg->smin_value = max(true_reg->smin_value, true_smin); } break; } case BPF_JLE: case BPF_JLT: { if (is_jmp32) { u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1; u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32; false_reg->u32_min_value = max(false_reg->u32_min_value, false_umin); true_reg->u32_max_value = min(true_reg->u32_max_value, true_umax); } else { u64 false_umin = opcode == BPF_JLT ? val : val + 1; u64 true_umax = opcode == BPF_JLT ? val - 1 : val; false_reg->umin_value = max(false_reg->umin_value, false_umin); true_reg->umax_value = min(true_reg->umax_value, true_umax); } break; } case BPF_JSLE: case BPF_JSLT: { if (is_jmp32) { s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1; s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32; false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin); true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax); } else { s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; false_reg->smin_value = max(false_reg->smin_value, false_smin); true_reg->smax_value = min(true_reg->smax_value, true_smax); } break; } default: return; } if (is_jmp32) { false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off), tnum_subreg(false_32off)); true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off), tnum_subreg(true_32off)); __reg_combine_32_into_64(false_reg); __reg_combine_32_into_64(true_reg); } else { false_reg->var_off = false_64off; true_reg->var_off = true_64off; __reg_combine_64_into_32(false_reg); __reg_combine_64_into_32(true_reg); } } /* Same as above, but for the case that dst_reg holds a constant and src_reg is * the variable reg. */ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u32 val32, u8 opcode, bool is_jmp32) { /* How can we transform "a b" into "b a"? */ static const u8 opcode_flip[16] = { /* these stay the same */ [BPF_JEQ >> 4] = BPF_JEQ, [BPF_JNE >> 4] = BPF_JNE, [BPF_JSET >> 4] = BPF_JSET, /* these swap "lesser" and "greater" (L and G in the opcodes) */ [BPF_JGE >> 4] = BPF_JLE, [BPF_JGT >> 4] = BPF_JLT, [BPF_JLE >> 4] = BPF_JGE, [BPF_JLT >> 4] = BPF_JGT, [BPF_JSGE >> 4] = BPF_JSLE, [BPF_JSGT >> 4] = BPF_JSLT, [BPF_JSLE >> 4] = BPF_JSGE, [BPF_JSLT >> 4] = BPF_JSGT }; opcode = opcode_flip[opcode >> 4]; /* This uses zero as "not present in table"; luckily the zero opcode, * BPF_JA, can't get here. */ if (opcode) reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32); } /* Regs are known to be equal, so intersect their min/max/var_off */ static void __reg_combine_min_max(struct bpf_reg_state *src_reg, struct bpf_reg_state *dst_reg) { src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value, dst_reg->umin_value); src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value, dst_reg->umax_value); src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value, dst_reg->smin_value); src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value, dst_reg->smax_value); src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off, dst_reg->var_off); /* We might have learned new bounds from the var_off. */ __update_reg_bounds(src_reg); __update_reg_bounds(dst_reg); /* We might have learned something about the sign bit. */ __reg_deduce_bounds(src_reg); __reg_deduce_bounds(dst_reg); /* We might have learned some bits from the bounds. */ __reg_bound_offset(src_reg); __reg_bound_offset(dst_reg); /* Intersecting with the old var_off might have improved our bounds * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. */ __update_reg_bounds(src_reg); __update_reg_bounds(dst_reg); } static void reg_combine_min_max(struct bpf_reg_state *true_src, struct bpf_reg_state *true_dst, struct bpf_reg_state *false_src, struct bpf_reg_state *false_dst, u8 opcode) { switch (opcode) { case BPF_JEQ: __reg_combine_min_max(true_src, true_dst); break; case BPF_JNE: __reg_combine_min_max(false_src, false_dst); break; } } static void mark_ptr_or_null_reg(struct bpf_func_state *state, struct bpf_reg_state *reg, u32 id, bool is_null) { if (reg_type_may_be_null(reg->type) && reg->id == id) { /* Old offset (both fixed and variable parts) should * have been known-zero, because we don't allow pointer * arithmetic on pointers that might be NULL. */ if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0) || reg->off)) { __mark_reg_known_zero(reg); reg->off = 0; } if (is_null) { reg->type = SCALAR_VALUE; } else if (reg->type == PTR_TO_MAP_VALUE_OR_NULL) { const struct bpf_map *map = reg->map_ptr; if (map->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = map->inner_map_meta; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || map->map_type == BPF_MAP_TYPE_SOCKHASH) { reg->type = PTR_TO_SOCKET; } else { reg->type = PTR_TO_MAP_VALUE; } } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { reg->type = PTR_TO_SOCKET; } else if (reg->type == PTR_TO_SOCK_COMMON_OR_NULL) { reg->type = PTR_TO_SOCK_COMMON; } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { reg->type = PTR_TO_TCP_SOCK; } else if (reg->type == PTR_TO_BTF_ID_OR_NULL) { reg->type = PTR_TO_BTF_ID; } else if (reg->type == PTR_TO_MEM_OR_NULL) { reg->type = PTR_TO_MEM; } else if (reg->type == PTR_TO_RDONLY_BUF_OR_NULL) { reg->type = PTR_TO_RDONLY_BUF; } else if (reg->type == PTR_TO_RDWR_BUF_OR_NULL) { reg->type = PTR_TO_RDWR_BUF; } if (is_null) { /* We don't need id and ref_obj_id from this point * onwards anymore, thus we should better reset it, * so that state pruning has chances to take effect. */ reg->id = 0; reg->ref_obj_id = 0; } else if (!reg_may_point_to_spin_lock(reg)) { /* For not-NULL ptr, reg->ref_obj_id will be reset * in release_reg_references(). * * reg->id is still used by spin_lock ptr. Other * than spin_lock ptr type, reg->id can be reset. */ reg->id = 0; } } } static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id, bool is_null) { struct bpf_reg_state *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) mark_ptr_or_null_reg(state, &state->regs[i], id, is_null); bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; mark_ptr_or_null_reg(state, reg, id, is_null); } } /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs; u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; int i; if (ref_obj_id && ref_obj_id == id && is_null) /* regs[regno] is in the " == NULL" branch. * No one could have freed the reference state before * doing the NULL check. */ WARN_ON_ONCE(release_reference_state(state, id)); for (i = 0; i <= vstate->curframe; i++) __mark_ptr_or_null_regs(vstate->frame[i], id, is_null); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg, struct bpf_verifier_state *this_branch, struct bpf_verifier_state *other_branch) { if (BPF_SRC(insn->code) != BPF_X) return false; /* Pointers are always 64-bit. */ if (BPF_CLASS(insn->code) == BPF_JMP32) return false; switch (BPF_OP(insn->code)) { case BPF_JGT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' > pkt_end, pkt_meta' > pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end > pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, true); } else { return false; } break; case BPF_JLT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' < pkt_end, pkt_meta' < pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end < pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, false); } else { return false; } break; case BPF_JGE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, false); } else { return false; } break; case BPF_JLE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, true); } else { return false; } break; default: return false; } return true; } static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *this_branch = env->cur_state; struct bpf_verifier_state *other_branch; struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; int err; /* Only conditional jumps are expected to reach here. */ if (opcode == BPF_JA || opcode > BPF_JSLE) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } src_reg = ®s[insn->src_reg]; } else { if (insn->src_reg != BPF_REG_0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg = ®s[insn->dst_reg]; is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; if (BPF_SRC(insn->code) == BPF_K) { pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32); } else if (src_reg->type == SCALAR_VALUE && is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) { pred = is_branch_taken(dst_reg, tnum_subreg(src_reg->var_off).value, opcode, is_jmp32); } else if (src_reg->type == SCALAR_VALUE && !is_jmp32 && tnum_is_const(src_reg->var_off)) { pred = is_branch_taken(dst_reg, src_reg->var_off.value, opcode, is_jmp32); } if (pred >= 0) { /* If we get here with a dst_reg pointer type it is because * above is_branch_taken() special cased the 0 comparison. */ if (!__is_pointer_value(false, dst_reg)) err = mark_chain_precision(env, insn->dst_reg); if (BPF_SRC(insn->code) == BPF_X && !err) err = mark_chain_precision(env, insn->src_reg); if (err) return err; } if (pred == 1) { /* only follow the goto, ignore fall-through */ *insn_idx += insn->off; return 0; } else if (pred == 0) { /* only follow fall-through branch, since * that's where the program will go */ return 0; } other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, false); if (!other_branch) return -EFAULT; other_branch_regs = other_branch->frame[other_branch->curframe]->regs; /* detect if we are comparing against a constant value so we can adjust * our min/max values for our dst register. * this is only legit if both are scalars (or pointers to the same * object, I suppose, but we don't support that right now), because * otherwise the different base pointers mean the offsets aren't * comparable. */ if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = ®s[insn->src_reg]; if (dst_reg->type == SCALAR_VALUE && src_reg->type == SCALAR_VALUE) { if (tnum_is_const(src_reg->var_off) || (is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off)))) reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, src_reg->var_off.value, tnum_subreg(src_reg->var_off).value, opcode, is_jmp32); else if (tnum_is_const(dst_reg->var_off) || (is_jmp32 && tnum_is_const(tnum_subreg(dst_reg->var_off)))) reg_set_min_max_inv(&other_branch_regs[insn->src_reg], src_reg, dst_reg->var_off.value, tnum_subreg(dst_reg->var_off).value, opcode, is_jmp32); else if (!is_jmp32 && (opcode == BPF_JEQ || opcode == BPF_JNE)) /* Comparing for equality, we can combine knowledge */ reg_combine_min_max(&other_branch_regs[insn->src_reg], &other_branch_regs[insn->dst_reg], src_reg, dst_reg, opcode); } } else if (dst_reg->type == SCALAR_VALUE) { reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, insn->imm, (u32)insn->imm, opcode, is_jmp32); } /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). * NOTE: these optimizations below are related with pointer comparison * which will never be JMP32. */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && reg_type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ mark_ptr_or_null_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); mark_ptr_or_null_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], this_branch, other_branch) && is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) print_verifier_state(env, this_branch->frame[this_branch->curframe]); return 0; } /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); struct bpf_map *map; int err; if (BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid BPF_LD_IMM insn\n"); return -EINVAL; } if (insn->off != 0) { verbose(env, "BPF_LD_IMM64 uses reserved fields\n"); return -EINVAL; } err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; if (insn->src_reg == 0) { u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; regs[insn->dst_reg].type = SCALAR_VALUE; __mark_reg_known(®s[insn->dst_reg], imm); return 0; } map = env->used_maps[aux->map_index]; mark_reg_known_zero(env, regs, insn->dst_reg); regs[insn->dst_reg].map_ptr = map; if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) { regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; regs[insn->dst_reg].off = aux->map_off; if (map_value_has_spin_lock(map)) regs[insn->dst_reg].id = ++env->id_gen; } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { regs[insn->dst_reg].type = CONST_PTR_TO_MAP; } else { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } return 0; } static bool may_access_skb(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: return true; default: return false; } } /* verify safety of LD_ABS|LD_IND instructions: * - they can only appear in the programs where ctx == skb * - since they are wrappers of function calls, they scratch R1-R5 registers, * preserve R6-R9, and store return value into R0 * * Implicit input: * ctx == skb == R6 == CTX * * Explicit input: * SRC == any register * IMM == 32-bit immediate * * Output: * R0 - 8/16/32-bit skb data converted to cpu endianness */ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; if (!may_access_skb(resolve_prog_type(env->prog))) { verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } if (!env->ops->gen_ld_abs) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } if (env->subprog_cnt > 1) { /* when program has LD_ABS insn JITs and interpreter assume * that r1 == ctx == skb which is not the case for callees * that can have arbitrary arguments. It's problematic * for main prog as well since JITs would need to analyze * all functions in order to make proper register save/restore * decisions in the main prog. Hence disallow LD_ABS with calls */ verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n"); return -EINVAL; } if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n"); return -EINVAL; } /* check whether implicit source operand (register R6) is readable */ err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as * gen_ld_abs() may terminate the program at runtime, leading to * reference leak. */ err = check_reference_leak(env); if (err) { verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); return err; } if (env->cur_state->active_spin_lock) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); return -EINVAL; } if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; } if (mode == BPF_IND) { /* check explicit source operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* mark destination R0 register as readable, since it contains * the value fetched from the packet. * Already marked as written above. */ mark_reg_unknown(env, regs, BPF_REG_0); /* ld_abs load up to 32-bit skb data. */ regs[BPF_REG_0].subreg_def = env->insn_idx + 1; return 0; } static int check_return_code(struct bpf_verifier_env *env) { struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; struct tnum range = tnum_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; /* LSM and struct_ops func-ptr's return type could be "void" */ if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS || prog_type == BPF_PROG_TYPE_LSM) && !prog->aux->attach_func_proto->type) return 0; /* eBPF calling convetion is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time * of bpf_exit, which means that program wrote * something into it earlier */ err = check_reg_arg(env, BPF_REG_0, SRC_OP); if (err) return err; if (is_pointer_value(env, BPF_REG_0)) { verbose(env, "R0 leaks addr as return value\n"); return -EACCES; } switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) range = tnum_range(1, 1); break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { range = tnum_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } break; case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: break; case BPF_PROG_TYPE_RAW_TRACEPOINT: if (!env->prog->aux->attach_btf_id) return 0; range = tnum_const(0); break; case BPF_PROG_TYPE_TRACING: switch (env->prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: range = tnum_const(0); break; case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: return 0; case BPF_TRACE_ITER: break; default: return -ENOTSUPP; } break; case BPF_PROG_TYPE_SK_LOOKUP: range = tnum_range(SK_DROP, SK_PASS); break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value * depends on the to-be-replaced kernel func or bpf program. */ default: return 0; } reg = cur_regs(env) + BPF_REG_0; if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", reg_type_str[reg->type]); return -EINVAL; } if (!tnum_in(range, reg->var_off)) { char tn_buf[48]; verbose(env, "At program exit the register R0 "); if (!tnum_is_unknown(reg->var_off)) { tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "has value %s", tn_buf); } else { verbose(env, "has unknown scalar value"); } tnum_strn(tn_buf, sizeof(tn_buf), range); verbose(env, " should have been in %s\n", tn_buf); return -EINVAL; } if (!tnum_is_unknown(enforce_attach_type_range) && tnum_in(enforce_attach_type_range, reg->var_off)) env->prog->enforce_expected_attach_type = 1; return 0; } /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered * 3 let S be a stack * 4 S.push(v) * 5 while S is not empty * 6 t <- S.pop() * 7 if t is what we're looking for: * 8 return t * 9 for all edges e in G.adjacentEdges(t) do * 10 if edge e is already labelled * 11 continue with the next edge * 12 w <- G.adjacentVertex(t,e) * 13 if vertex w is not discovered and not explored * 14 label e as tree-edge * 15 label w as discovered * 16 S.push(w) * 17 continue at 5 * 18 else if vertex w is discovered * 19 label e as back-edge * 20 else * 21 // vertex w is explored * 22 label e as forward- or cross-edge * 23 label t as explored * 24 S.pop() * * convention: * 0x10 - discovered * 0x11 - discovered and fall-through edge labelled * 0x12 - discovered and fall-through and branch edges labelled * 0x20 - explored */ enum { DISCOVERED = 0x10, EXPLORED = 0x20, FALLTHROUGH = 1, BRANCH = 2, }; static u32 state_htab_size(struct bpf_verifier_env *env) { return env->prog->len; } static struct bpf_verifier_state_list **explored_state( struct bpf_verifier_env *env, int idx) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_func_state *state = cur->frame[cur->curframe]; return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } static void init_explored_state(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; } /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction * e - edge */ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, bool loop_ok) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) return 0; if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) return 0; if (w < 0 || w >= env->prog->len) { verbose_linfo(env, t, "%d: ", t); verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } if (e == BRANCH) /* mark branch target for state pruning */ init_explored_state(env, w); if (insn_state[w] == 0) { /* tree-edge */ insn_state[t] = DISCOVERED | e; insn_state[w] = DISCOVERED; if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { if (loop_ok && env->bpf_capable) return 0; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { verbose(env, "insn state internal bug\n"); return -EFAULT; } return 0; } /* non-recursive depth-first-search to detect loops in BPF program * loop == back-edge in directed graph */ static int check_cfg(struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; int *insn_stack, *insn_state; int ret = 0; int i, t; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_stack) { kvfree(insn_state); return -ENOMEM; } insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; peek_stack: if (env->cfg.cur_stack == 0) goto check_state; t = insn_stack[env->cfg.cur_stack - 1]; if (BPF_CLASS(insns[t].code) == BPF_JMP || BPF_CLASS(insns[t].code) == BPF_JMP32) { u8 opcode = BPF_OP(insns[t].code); if (opcode == BPF_EXIT) { goto mark_explored; } else if (opcode == BPF_CALL) { ret = push_insn(t, t + 1, FALLTHROUGH, env, false); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; if (t + 1 < insn_cnt) init_explored_state(env, t + 1); if (insns[t].src_reg == BPF_PSEUDO_CALL) { init_explored_state(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, false); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; } } else if (opcode == BPF_JA) { if (BPF_SRC(insns[t].code) != BPF_K) { ret = -EINVAL; goto err_free; } /* unconditional jump with single edge */ ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, true); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; /* unconditional jmp is not a good pruning point, * but it's marked, since backtracking needs * to record jmp history in is_state_visited(). */ init_explored_state(env, t + insns[t].off + 1); /* tell verifier to check for equivalent states * after every call and jump */ if (t + 1 < insn_cnt) init_explored_state(env, t + 1); } else { /* conditional jump with two edges */ init_explored_state(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env, true); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; ret = push_insn(t, t + insns[t].off + 1, BRANCH, env, true); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; } } else { /* all other non-branch instructions with single * fall-through edge */ ret = push_insn(t, t + 1, FALLTHROUGH, env, false); if (ret == 1) goto peek_stack; else if (ret < 0) goto err_free; } mark_explored: insn_state[t] = EXPLORED; if (env->cfg.cur_stack-- <= 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } goto peek_stack; check_state: for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } } ret = 0; /* cfg looks good */ err_free: kvfree(insn_state); kvfree(insn_stack); env->cfg.insn_state = env->cfg.insn_stack = NULL; return ret; } /* The minimum supported BTF func info size */ #define MIN_BPF_FUNCINFO_SIZE 8 #define MAX_FUNCINFO_REC_SIZE 252 static int check_btf_func(struct bpf_verifier_env *env, const union bpf_attr *attr, union bpf_attr __user *uattr) { u32 i, nfuncs, urec_size, min_size; u32 krec_size = sizeof(struct bpf_func_info); struct bpf_func_info *krecord; struct bpf_func_info_aux *info_aux = NULL; const struct btf_type *type; struct bpf_prog *prog; const struct btf *btf; void __user *urecord; u32 prev_offset = 0; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; if (!nfuncs) return 0; if (nfuncs != env->subprog_cnt) { verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); return -EINVAL; } urec_size = attr->func_info_rec_size; if (urec_size < MIN_BPF_FUNCINFO_SIZE || urec_size > MAX_FUNCINFO_REC_SIZE || urec_size % sizeof(u32)) { verbose(env, "invalid func info rec size %u\n", urec_size); return -EINVAL; } prog = env->prog; btf = prog->aux->btf; urecord = u64_to_user_ptr(attr->func_info); min_size = min_t(u32, krec_size, urec_size); krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); if (!krecord) return -ENOMEM; info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); if (!info_aux) goto err_free; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); if (ret) { if (ret == -E2BIG) { verbose(env, "nonzero tailing record in func info"); /* set the size kernel expects so loader can zero * out the rest of the record. */ if (put_user(min_size, &uattr->func_info_rec_size)) ret = -EFAULT; } goto err_free; } if (copy_from_user(&krecord[i], urecord, min_size)) { ret = -EFAULT; goto err_free; } /* check insn_off */ if (i == 0) { if (krecord[i].insn_off) { verbose(env, "nonzero insn_off %u for the first func info record", krecord[i].insn_off); ret = -EINVAL; goto err_free; } } else if (krecord[i].insn_off <= prev_offset) { verbose(env, "same or smaller insn offset (%u) than previous func info record (%u)", krecord[i].insn_off, prev_offset); ret = -EINVAL; goto err_free; } if (env->subprog_info[i].start != krecord[i].insn_off) { verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); ret = -EINVAL; goto err_free; } /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); if (!type || !btf_type_is_func(type)) { verbose(env, "invalid type id %d in func info", krecord[i].type_id); ret = -EINVAL; goto err_free; } info_aux[i].linkage = BTF_INFO_VLEN(type->info); prev_offset = krecord[i].insn_off; urecord += urec_size; } prog->aux->func_info = krecord; prog->aux->func_info_cnt = nfuncs; prog->aux->func_info_aux = info_aux; return 0; err_free: kvfree(krecord); kfree(info_aux); return ret; } static void adjust_btf_func(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; int i; if (!aux->func_info) return; for (i = 0; i < env->subprog_cnt; i++) aux->func_info[i].insn_off = env->subprog_info[i].start; } #define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \ sizeof(((struct bpf_line_info *)(0))->line_col)) #define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE static int check_btf_line(struct bpf_verifier_env *env, const union bpf_attr *attr, union bpf_attr __user *uattr) { u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; struct bpf_subprog_info *sub; struct bpf_line_info *linfo; struct bpf_prog *prog; const struct btf *btf; void __user *ulinfo; int err; nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || rec_size > MAX_LINEINFO_REC_SIZE || rec_size & (sizeof(u32) - 1)) return -EINVAL; /* Need to zero it in case the userspace may * pass in a smaller bpf_line_info object. */ linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info), GFP_KERNEL | __GFP_NOWARN); if (!linfo) return -ENOMEM; prog = env->prog; btf = prog->aux->btf; s = 0; sub = env->subprog_info; ulinfo = u64_to_user_ptr(attr->line_info); expected_size = sizeof(struct bpf_line_info); ncopy = min_t(u32, expected_size, rec_size); for (i = 0; i < nr_linfo; i++) { err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size); if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in line_info"); if (put_user(expected_size, &uattr->line_info_rec_size)) err = -EFAULT; } goto err_free; } if (copy_from_user(&linfo[i], ulinfo, ncopy)) { err = -EFAULT; goto err_free; } /* * Check insn_off to ensure * 1) strictly increasing AND * 2) bounded by prog->len * * The linfo[0].insn_off == 0 check logically falls into * the later "missing bpf_line_info for func..." case * because the first linfo[0].insn_off must be the * first sub also and the first sub must have * subprog_info[0].start == 0. */ if ((i && linfo[i].insn_off <= prev_offset) || linfo[i].insn_off >= prog->len) { verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n", i, linfo[i].insn_off, prev_offset, prog->len); err = -EINVAL; goto err_free; } if (!prog->insnsi[linfo[i].insn_off].code) { verbose(env, "Invalid insn code at line_info[%u].insn_off\n", i); err = -EINVAL; goto err_free; } if (!btf_name_by_offset(btf, linfo[i].line_off) || !btf_name_by_offset(btf, linfo[i].file_name_off)) { verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i); err = -EINVAL; goto err_free; } if (s != env->subprog_cnt) { if (linfo[i].insn_off == sub[s].start) { sub[s].linfo_idx = i; s++; } else if (sub[s].start < linfo[i].insn_off) { verbose(env, "missing bpf_line_info for func#%u\n", s); err = -EINVAL; goto err_free; } } prev_offset = linfo[i].insn_off; ulinfo += rec_size; } if (s != env->subprog_cnt) { verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n", env->subprog_cnt - s, s); err = -EINVAL; goto err_free; } prog->aux->linfo = linfo; prog->aux->nr_linfo = nr_linfo; return 0; err_free: kvfree(linfo); return err; } static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct btf *btf; int err; if (!attr->func_info_cnt && !attr->line_info_cnt) return 0; btf = btf_get_by_fd(attr->prog_btf_fd); if (IS_ERR(btf)) return PTR_ERR(btf); env->prog->aux->btf = btf; err = check_btf_func(env, attr, uattr); if (err) return err; err = check_btf_line(env, attr, uattr); if (err) return err; return 0; } /* check %cur's range satisfies %old's */ static bool range_within(struct bpf_reg_state *old, struct bpf_reg_state *cur) { return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && old->smin_value <= cur->smin_value && old->smax_value >= cur->smax_value; } /* Maximum number of register states that can exist at once */ #define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) struct idpair { u32 old; u32 cur; }; /* If in the old state two registers had the same id, then they need to have * the same id in the new state as well. But that id could be different from * the old state, so we need to track the mapping from old to new ids. * Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent * regs with old id 5 must also have new id 9 for the new state to be safe. But * regs with a different old id could still have new id 9, we don't care about * that. * So we look through our idmap to see if this old id has been seen before. If * so, we require the new id to match; otherwise, we add the id pair to the map. */ static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap) { unsigned int i; for (i = 0; i < ID_MAP_SIZE; i++) { if (!idmap[i].old) { /* Reached an empty slot; haven't seen this id before */ idmap[i].old = old_id; idmap[i].cur = cur_id; return true; } if (idmap[i].old == old_id) return idmap[i].cur == cur_id; } /* We ran out of idmap slots, which should be impossible */ WARN_ON_ONCE(1); return false; } static void clean_func_state(struct bpf_verifier_env *env, struct bpf_func_state *st) { enum bpf_reg_liveness live; int i, j; for (i = 0; i < BPF_REG_FP; i++) { live = st->regs[i].live; /* liveness must not touch this register anymore */ st->regs[i].live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) /* since the register is unused, clear its state * to make further comparison simpler */ __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { live = st->stack[i].spilled_ptr.live; /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } } } static void clean_verifier_state(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { int i; if (st->frame[0]->regs[0].live & REG_LIVE_DONE) /* all regs in this state in all frames were already marked */ return; for (i = 0; i <= st->curframe; i++) clean_func_state(env, st->frame[i]); } /* the parentage chains form a tree. * the verifier states are added to state lists at given insn and * pushed into state stack for future exploration. * when the verifier reaches bpf_exit insn some of the verifer states * stored in the state lists have their final liveness state already, * but a lot of states will get revised from liveness point of view when * the verifier explores other branches. * Example: * 1: r0 = 1 * 2: if r1 == 100 goto pc+1 * 3: r0 = 2 * 4: exit * when the verifier reaches exit insn the register r0 in the state list of * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch * of insn 2 and goes exploring further. At the insn 4 it will walk the * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ. * * Since the verifier pushes the branch states as it sees them while exploring * the program the condition of walking the branch instruction for the second * time means that all states below this branch were already explored and * their final liveness markes are already propagated. * Hence when the verifier completes the search of state list in is_state_visited() * we can call this clean_live_states() function to mark all liveness states * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' * will not be used. * This function also clears the registers and stack for states that !READ * to simplify state merging. * * Important note here that walking the same branch instruction in the callee * doesn't meant that the states are DONE. The verifier has to compare * the callsites */ static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state *cur) { struct bpf_verifier_state_list *sl; int i; sl = *explored_state(env, insn); while (sl) { if (sl->state.branches) goto next; if (sl->state.insn_idx != insn || sl->state.curframe != cur->curframe) goto next; for (i = 0; i <= cur->curframe; i++) if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) goto next; clean_verifier_state(env, &sl->state); next: sl = sl->next; } } /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct idpair *idmap) { bool equal; if (!(rold->live & REG_LIVE_READ)) /* explored state didn't use this */ return true; equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; if (rold->type == PTR_TO_STACK) /* two stack pointers are equal only if they're pointing to * the same stack frame, since fp-8 in foo != fp-8 in bar */ return equal && rold->frameno == rcur->frameno; if (equal) return true; if (rold->type == NOT_INIT) /* explored state can't have used this */ return true; if (rcur->type == NOT_INIT) return false; switch (rold->type) { case SCALAR_VALUE: if (rcur->type == SCALAR_VALUE) { if (!rold->precise && !rcur->precise) return true; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); } else { /* We're trying to use a pointer in place of a scalar. * Even if the scalar was unbounded, this could lead to * pointer leaks because scalars are allowed to leak * while pointers are not. We could make this safe in * special cases if root is calling us, but it's * probably not worth the hassle. */ return false; } case PTR_TO_MAP_VALUE: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. * 'id' is not compared, since it's only used for maps with * bpf_spin_lock inside map element and in such cases if * the rest of the prog is valid for one map element then * it's valid for all map elements regardless of the key * used in bpf_map_lookup() */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_MAP_VALUE_OR_NULL: /* a PTR_TO_MAP_VALUE could be safe to use as a * PTR_TO_MAP_VALUE_OR_NULL into the same map. * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- * checked, doing so could have affected others with the same * id, and we can't check for that because we lost the id when * we converted to a PTR_TO_MAP_VALUE. */ if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL) return false; if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: if (rcur->type != rold->type) return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are * still safe. This is true even if old range < old off, * since someone could have accessed through (ptr - k), or * even done ptr -= k in a register, to get a safe access. */ if (rold->range > rcur->range) return false; /* If the offsets don't match, we can't trust our alignment; * nor can we be sure that we won't fall out of range. */ if (rold->off != rcur->off) return false; /* id relations must be preserved */ if (rold->id && !check_ids(rold->id, rcur->id, idmap)) return false; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_CTX: case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: /* Only valid matches are exact, which memcmp() above * would have accepted */ default: /* Don't know what's going on, just say it's not safe */ return false; } /* Shouldn't get here; if we do, say it's not safe */ WARN_ON_ONCE(1); return false; } static bool stacksafe(struct bpf_func_state *old, struct bpf_func_state *cur, struct idpair *idmap) { int i, spi; /* walk slots of the explored stack and ignore any additional * slots in the current stack, since explored(safe) state * didn't use them */ for (i = 0; i < old->allocated_stack; i++) { spi = i / BPF_REG_SIZE; if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) { i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; } if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) continue; /* explored stack has more populated slots than current stack * and these slots were used */ if (i >= cur->allocated_stack) return false; /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true */ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC && cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO) continue; if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) /* Ex: old explored (safe) state has STACK_SPILL in * this stack slot, but current has STACK_MISC -> * this verifier states are not equivalent, * return false to continue verification of this path */ return false; if (i % BPF_REG_SIZE) continue; if (old->stack[spi].slot_type[0] != STACK_SPILL) continue; if (!regsafe(&old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap)) /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. * Ex: explored safe path could have stored * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8} * but current path has stored: * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16} * such verifier states are not equivalent. * return false to continue verification of this path */ return false; } return true; } static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) { if (old->acquired_refs != cur->acquired_refs) return false; return !memcmp(old->refs, cur->refs, sizeof(*old->refs) * old->acquired_refs); } /* compare two verifier states * * all states stored in state_list are known to be valid, since * verifier reached 'bpf_exit' instruction through them * * this function is called when verifier exploring different branches of * execution popped from the state stack. If it sees an old state that has * more strict register state and more strict stack state then this execution * branch doesn't need to be explored further, since verifier already * concluded that more strict state leads to valid finish. * * Therefore two states are equivalent if register state is more conservative * and explored stack state is more conservative than the current one. * Example: * explored current * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC) * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC) * * In other words if current stack state (one being explored) has more * valid slots than old one that already passed validation, it means * the verifier can stop exploring and conclude that current state is valid too * * Similarly with registers. If explored state has register type as invalid * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_func_state *old, struct bpf_func_state *cur) { struct idpair *idmap; bool ret = false; int i; idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL); /* If we failed to allocate the idmap, just say it's not safe */ if (!idmap) return false; for (i = 0; i < MAX_BPF_REG; i++) { if (!regsafe(&old->regs[i], &cur->regs[i], idmap)) goto out_free; } if (!stacksafe(old, cur, idmap)) goto out_free; if (!refsafe(old, cur)) goto out_free; ret = true; out_free: kfree(idmap); return ret; } static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { int i; if (old->curframe != cur->curframe) return false; /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. */ if (old->speculative && !cur->speculative) return false; if (old->active_spin_lock != cur->active_spin_lock) return false; /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ for (i = 0; i <= old->curframe; i++) { if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; if (!func_states_equal(old->frame[i], cur->frame[i])) return false; } return true; } /* Return 0 if no propagation happened. Return negative error code if error * happened. Otherwise, return the propagated bit. */ static int propagate_liveness_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct bpf_reg_state *parent_reg) { u8 parent_flag = parent_reg->live & REG_LIVE_READ; u8 flag = reg->live & REG_LIVE_READ; int err; /* When comes here, read flags of PARENT_REG or REG could be any of * REG_LIVE_READ64, REG_LIVE_READ32, REG_LIVE_NONE. There is no need * of propagation if PARENT_REG has strongest REG_LIVE_READ64. */ if (parent_flag == REG_LIVE_READ64 || /* Or if there is no read flag from REG. */ !flag || /* Or if the read flag from REG is the same as PARENT_REG. */ parent_flag == flag) return 0; err = mark_reg_read(env, reg, parent_reg, flag); if (err) return err; return flag; } /* A write screens off any subsequent reads; but write marks come from the * straight-line code between a state and its parent. When we arrive at an * equivalent state (jump target or such) we didn't arrive by the straight-line * code, so read marks in the state must propagate to the parent regardless * of the state's write marks. That's what 'parent == state->parent' comparison * in mark_reg_read() is for. */ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, struct bpf_verifier_state *vparent) { struct bpf_reg_state *state_reg, *parent_reg; struct bpf_func_state *state, *parent; int i, frame, err = 0; if (vparent->curframe != vstate->curframe) { WARN(1, "propagate_live: parent frame %d current frame %d\n", vparent->curframe, vstate->curframe); return -EFAULT; } /* Propagate read liveness of registers... */ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); for (frame = 0; frame <= vstate->curframe; frame++) { parent = vparent->frame[frame]; state = vstate->frame[frame]; parent_reg = parent->regs; state_reg = state->regs; /* We don't need to worry about FP liveness, it's read-only */ for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { err = propagate_liveness_reg(env, &state_reg[i], &parent_reg[i]); if (err < 0) return err; if (err == REG_LIVE_READ64) mark_insn_zext(env, &parent_reg[i]); } /* Propagate stack slots. */ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && i < parent->allocated_stack / BPF_REG_SIZE; i++) { parent_reg = &parent->stack[i].spilled_ptr; state_reg = &state->stack[i].spilled_ptr; err = propagate_liveness_reg(env, state_reg, parent_reg); if (err < 0) return err; } } return 0; } /* find precise scalars in the previous equivalent state and * propagate them into the current state */ static int propagate_precision(struct bpf_verifier_env *env, const struct bpf_verifier_state *old) { struct bpf_reg_state *state_reg; struct bpf_func_state *state; int i, err = 0; state = old->frame[old->curframe]; state_reg = state->regs; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || !state_reg->precise) continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "propagating r%d\n", i); err = mark_chain_precision(env, i); if (err < 0) return err; } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (state->stack[i].slot_type[0] != STACK_SPILL) continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || !state_reg->precise) continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "propagating fp%d\n", (-i - 1) * BPF_REG_SIZE); err = mark_chain_precision_stack(env, i); if (err < 0) return err; } return 0; } static bool states_maybe_looping(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; int i, fr = cur->curframe; if (old->curframe != fr) return false; fold = old->frame[fr]; fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) if (memcmp(&fold->regs[i], &fcur->regs[i], offsetof(struct bpf_reg_state, parent))) return false; return true; } static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; if (!env->insn_aux_data[insn_idx].prune_point) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ return 0; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 * Do not add new state for future pruning if the verifier hasn't seen * at least 2 jumps and at least 8 instructions. * This heuristics helps decrease 'total_states' and 'peak_states' metric. * In tests that amounts to up to 50% reduction into total verifier * memory consumption and 20% verifier time speedup. */ if (env->jmps_processed - env->prev_jmps_processed >= 2 && env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; pprev = explored_state(env, insn_idx); sl = *pprev; clean_live_states(env, insn_idx, cur); while (sl) { states_cnt++; if (sl->state.insn_idx != insn_idx) goto next; if (sl->state.branches) { if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur)) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); return -EINVAL; } /* if the verifier is processing a loop, avoid adding new state * too often, since different loop iterations have distinct * states and may not help future pruning. * This threshold shouldn't be too low to make sure that * a loop with large bound will be rejected quickly. * The most abusive loop will be: * r1 += 1 * if r1 < 1000000 goto pc-2 * 1M insn_procssed limit / 100 == 10k peak states. * This threshold shouldn't be too high either, since states * at the end of the loop are likely to be useful in pruning. */ if (env->jmps_processed - env->prev_jmps_processed < 20 && env->insn_processed - env->prev_insn_processed < 100) add_new_state = false; goto miss; } if (states_equal(env, &sl->state, cur)) { sl->hit_cnt++; /* reached equivalent register/stack state, * prune the search. * Registers read by the continuation are read by us. * If we have any write marks in env->cur_state, they * will prevent corresponding reads in the continuation * from reaching our parent (an explored_state). Our * own state will get the read marks recorded, but * they'll be immediately forgotten as we're pruning * this state and will pop a new one. */ err = propagate_liveness(env, &sl->state, cur); /* if previous state reached the exit with precision and * current state is equivalent to it (except precsion marks) * the precision needs to be propagated back in * the current state. */ err = err ? : push_jmp_history(env, cur); err = err ? : propagate_precision(env, &sl->state); if (err) return err; return 1; } miss: /* when new state is not going to be added do not increase miss count. * Otherwise several loop iterations will remove the state * recorded earlier. The goal of these heuristics is to have * states from some iterations of the loop (some in the beginning * and some at the end) to help pruning. */ if (add_new_state) sl->miss_cnt++; /* heuristic to determine whether this state is beneficial * to keep checking from state equivalence point of view. * Higher numbers increase max_states_per_insn and verification time, * but do not meaningfully decrease insn_processed. */ if (sl->miss_cnt > sl->hit_cnt * 3 + 3) { /* the state is unlikely to be useful. Remove it to * speed up verification */ *pprev = sl->next; if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) { u32 br = sl->state.branches; WARN_ONCE(br, "BUG live_done but branches_to_explore %d\n", br); free_verifier_state(&sl->state, false); kfree(sl); env->peak_states--; } else { /* cannot free this state, since parentage chain may * walk it later. Add it for free_list instead to * be freed at the end of verification */ sl->next = env->free_list; env->free_list = sl; } sl = *pprev; continue; } next: pprev = &sl->next; sl = *pprev; } if (env->max_states_per_insn < states_cnt) env->max_states_per_insn = states_cnt; if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) return push_jmp_history(env, cur); if (!add_new_state) return push_jmp_history(env, cur); /* There were no equivalent states, remember the current one. * Technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) * or it will be rejected. When there are no loops the verifier won't be * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx) * again on the way to bpf_exit. * When looping the sl->state.branches will be > 0 and this state * will not be considered for equivalence until branches == 0. */ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) return -ENOMEM; env->total_states++; env->peak_states++; env->prev_jmps_processed = env->jmps_processed; env->prev_insn_processed = env->insn_processed; /* add new state to the head of linked list */ new = &new_sl->state; err = copy_verifier_state(new, cur); if (err) { free_verifier_state(new, false); kfree(new_sl); return err; } new->insn_idx = insn_idx; WARN_ONCE(new->branches != 1, "BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx); cur->parent = new; cur->first_insn_idx = insn_idx; clear_jmp_history(cur); new_sl->next = *explored_state(env, insn_idx); *explored_state(env, insn_idx) = new_sl; /* connect new state to parentage chain. Current frame needs all * registers connected. Only r6 - r9 of the callers are alive (pushed * to the stack implicitly by JITs) so in callers' frames connect just * r6 - r9 as an optimization. Callers will have r1 - r5 connected to * the state of the call instruction (with WRITTEN set), and r0 comes * from callee with its full parentage chain, anyway. */ /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark * their parent and current state never has children yet. Only * explored_states can get read marks.) */ for (j = 0; j <= cur->curframe; j++) { for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; for (i = 0; i < BPF_REG_FP; i++) cur->frame[j]->regs[i].live = REG_LIVE_NONE; } /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { struct bpf_func_state *frame = cur->frame[j]; struct bpf_func_state *newframe = new->frame[j]; for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; frame->stack[i].spilled_ptr.parent = &newframe->stack[i].spilled_ptr; } } return 0; } /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { switch (type) { case PTR_TO_CTX: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: case PTR_TO_BTF_ID_OR_NULL: return false; default: return true; } } /* If an instruction was previously used with particular pointer types, then we * need to be careful to avoid cases such as the below, where it may be ok * for one branch accessing the pointer, but not ok for the other branch: * * R1 = sock_ptr * goto X; * ... * R1 = some_other_valid_ptr; * goto X; * ... * R2 = *(u32 *)(R1 + 0); */ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) { return src != prev && (!reg_type_mismatch_ok(src) || !reg_type_mismatch_ok(prev)); } static int do_check(struct bpf_verifier_env *env) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; int insn_cnt = env->prog->len; bool do_print_state = false; int prev_insn_idx = -1; for (;;) { struct bpf_insn *insn; u8 class; int err; env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", env->insn_idx, insn_cnt); return -EFAULT; } insn = &insns[env->insn_idx]; class = BPF_CLASS(insn->code); if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, "BPF program is too large. Processed %d insn\n", env->insn_processed); return -E2BIG; } err = is_state_visited(env, env->insn_idx); if (err < 0) return err; if (err == 1) { /* found equivalent state, can prune the search */ if (env->log.level & BPF_LOG_LEVEL) { if (do_print_state) verbose(env, "\nfrom %d to %d%s: safe\n", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); else verbose(env, "%d: safe\n", env->insn_idx); } goto process_bpf_exit; } if (signal_pending(current)) return -EAGAIN; if (need_resched()) cond_resched(); if (env->log.level & BPF_LOG_LEVEL2 || (env->log.level & BPF_LOG_LEVEL && do_print_state)) { if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "%d:", env->insn_idx); else verbose(env, "\nfrom %d to %d%s:", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); print_verifier_state(env, state->frame[state->curframe]); do_print_state = false; } if (env->log.level & BPF_LOG_LEVEL) { const struct bpf_insn_cbs cbs = { .cb_print = verbose, .private_data = env, }; verbose_linfo(env, env->insn_idx, "; "); verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (bpf_prog_is_dev_bound(env->prog->aux)) { err = bpf_prog_offload_verify_insn(env, env->insn_idx, env->prev_insn_idx); if (err) return err; } regs = cur_regs(env); env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) return err; } else if (class == BPF_LDX) { enum bpf_reg_type *prev_src_type, src_reg_type; /* check for reserved fields is already done */ /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; src_reg_type = regs[insn->src_reg].type; /* check that memory (src_reg + off) is readable, * the state of dst_reg will be updated by this func */ err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, false); if (err) return err; prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_src_type == NOT_INIT) { /* saw a valid insn * dst_reg = *(u32 *)(src_reg + off) * save type to validate intersecting paths */ *prev_src_type = src_reg_type; } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { /* ABuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: * src_reg == ctx in one branch and * src_reg == stack|map in some other branch. * Reject it. */ verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } else if (class == BPF_STX) { enum bpf_reg_type *prev_dst_type, dst_reg_type; if (BPF_MODE(insn->code) == BPF_XADD) { err = check_xadd(env, env->insn_idx, insn); if (err) return err; env->insn_idx++; continue; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg, false); if (err) return err; prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } else if (class == BPF_ST) { if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { verbose(env, "BPF_ST uses reserved fields\n"); return -EINVAL; } /* check src operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (is_ctx_reg(env, insn->dst_reg)) { verbose(env, "BPF_ST stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str[reg_state(env, insn->dst_reg)->type]); return -EACCES; } /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, false); if (err) return err; } else if (class == BPF_JMP || class == BPF_JMP32) { u8 opcode = BPF_OP(insn->code); env->jmps_processed++; if (opcode == BPF_CALL) { if (BPF_SRC(insn->code) != BPF_K || insn->off != 0 || (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL) || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } if (env->cur_state->active_spin_lock && (insn->src_reg == BPF_PSEUDO_CALL || insn->imm != BPF_FUNC_spin_unlock)) { verbose(env, "function calls are not allowed while holding a lock\n"); return -EINVAL; } if (insn->src_reg == BPF_PSEUDO_CALL) err = check_func_call(env, insn, &env->insn_idx); else err = check_helper_call(env, insn->imm, env->insn_idx); if (err) return err; } else if (opcode == BPF_JA) { if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } env->insn_idx += insn->off + 1; continue; } else if (opcode == BPF_EXIT) { if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } if (env->cur_state->active_spin_lock) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } if (state->curframe) { /* exit from nested function */ err = prepare_func_exit(env, &env->insn_idx); if (err) return err; do_print_state = true; continue; } err = check_reference_leak(env); if (err) return err; err = check_return_code(env); if (err) return err; process_bpf_exit: update_branch_counts(env, env->cur_state); err = pop_stack(env, &prev_insn_idx, &env->insn_idx, pop_log); if (err < 0) { if (err != -ENOENT) return err; break; } else { do_print_state = true; continue; } } else { err = check_cond_jmp_op(env, insn, &env->insn_idx); if (err) return err; } } else if (class == BPF_LD) { u8 mode = BPF_MODE(insn->code); if (mode == BPF_ABS || mode == BPF_IND) { err = check_ld_abs(env, insn); if (err) return err; } else if (mode == BPF_IMM) { err = check_ld_imm(env, insn); if (err) return err; env->insn_idx++; env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; } } else { verbose(env, "unknown insn class %d\n", class); return -EINVAL; } env->insn_idx++; } return 0; } static int check_map_prealloc(struct bpf_map *map) { return (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) || !(map->map_flags & BPF_F_NO_PREALLOC); } static bool is_tracing_prog_type(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: return true; default: return false; } } static bool is_preallocated_map(struct bpf_map *map) { if (!check_map_prealloc(map)) return false; if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta)) return false; return true; } static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) { enum bpf_prog_type prog_type = resolve_prog_type(prog); /* * Validate that trace type programs use preallocated hash maps. * * For programs attached to PERF events this is mandatory as the * perf NMI can hit any arbitrary code sequence. * * All other trace types using preallocated hash maps are unsafe as * well because tracepoint or kprobes can be inside locked regions * of the memory allocator or at a place where a recursion into the * memory allocator would see inconsistent state. * * On RT enabled kernels run-time allocation of all trace type * programs is strictly prohibited due to lock type constraints. On * !RT kernels it is allowed for backwards compatibility reasons for * now, but warnings are emitted so developers are made aware of * the unsafety and can fix their programs before this is enforced. */ if (is_tracing_prog_type(prog_type) && !is_preallocated_map(map)) { if (prog_type == BPF_PROG_TYPE_PERF_EVENT) { verbose(env, "perf_event programs can only use preallocated hash map\n"); return -EINVAL; } if (IS_ENABLED(CONFIG_PREEMPT_RT)) { verbose(env, "trace type programs can only use preallocated hash map\n"); return -EINVAL; } WARN_ONCE(1, "trace type BPF program uses run-time allocation\n"); verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n"); } if ((is_tracing_prog_type(prog_type) || prog_type == BPF_PROG_TYPE_SOCKET_FILTER) && map_value_has_spin_lock(map)) { verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; } if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { verbose(env, "bpf_struct_ops map cannot be used in prog\n"); return -EINVAL; } if (prog->aux->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_ARRAY: if (!is_preallocated_map(map)) { verbose(env, "Sleepable programs can only use preallocated hash maps\n"); return -EINVAL; } break; default: verbose(env, "Sleepable programs can only use array and hash maps\n"); return -EINVAL; } return 0; } static bool bpf_map_is_cgroup_storage(struct bpf_map *map) { return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); } /* look for pseudo eBPF instructions that access map FDs and * replace them with actual map pointers */ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, j, err; err = bpf_prog_calc_tag(env->prog); if (err) return err; for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } if (BPF_CLASS(insn->code) == BPF_STX && ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) { verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { struct bpf_insn_aux_data *aux; struct bpf_map *map; struct fd f; u64 addr; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || insn[1].off != 0) { verbose(env, "invalid bpf_ld_imm64 insn\n"); return -EINVAL; } if (insn[0].src_reg == 0) /* valid generic load 64-bit imm */ goto next_insn; /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD && insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) || (insn[0].src_reg == BPF_PSEUDO_MAP_FD && insn[1].imm != 0)) { verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } f = fdget(insn[0].imm); map = __bpf_map_get(f); if (IS_ERR(map)) { verbose(env, "fd %d is not pointing to valid bpf_map\n", insn[0].imm); return PTR_ERR(map); } err = check_map_prog_compatibility(env, map, env->prog); if (err) { fdput(f); return err; } aux = &env->insn_aux_data[i]; if (insn->src_reg == BPF_PSEUDO_MAP_FD) { addr = (unsigned long)map; } else { u32 off = insn[1].imm; if (off >= BPF_MAX_VAR_OFF) { verbose(env, "direct value offset of %u is not allowed\n", off); fdput(f); return -EINVAL; } if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); fdput(f); return -EINVAL; } err = map->ops->map_direct_value_addr(map, &addr, off); if (err) { verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", map->value_size, off); fdput(f); return err; } aux->map_off = off; addr += off; } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; /* check whether we recorded this map already */ for (j = 0; j < env->used_map_cnt; j++) { if (env->used_maps[j] == map) { aux->map_index = j; fdput(f); goto next_insn; } } if (env->used_map_cnt >= MAX_USED_MAPS) { fdput(f); return -E2BIG; } /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded * and all maps are released in free_used_maps() */ bpf_map_inc(map); aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; } fdput(f); next_insn: insn++; i++; continue; } /* Basic sanity check before we invest more work here. */ if (!bpf_opcode_in_insntable(insn->code)) { verbose(env, "unknown opcode %02x\n", insn->code); return -EINVAL; } } /* now all pseudo BPF_LD_IMM64 instructions load valid * 'struct bpf_map *' into a register instead of user map_fd. * These pointers will be used later by verifier to validate map access. */ return 0; } /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { __bpf_free_used_maps(env->prog->aux, env->used_maps, env->used_map_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) if (insn->code == (BPF_LD | BPF_IMM | BPF_DW)) insn->src_reg = 0; } /* single env->prog->insni[off] instruction was replaced with the range * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying * [0, off) and [off, end) to new locations, so the patched range stays zero */ static int adjust_insn_aux_data(struct bpf_verifier_env *env, struct bpf_prog *new_prog, u32 off, u32 cnt) { struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; u32 prog_len; int i; /* aux info at OFF always needs adjustment, no matter fast path * (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the * original insn at old prog. */ old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1); if (cnt == 1) return 0; prog_len = new_prog->len; new_data = vzalloc(array_size(prog_len, sizeof(struct bpf_insn_aux_data))); if (!new_data) return -ENOMEM; memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); for (i = off; i < off + cnt - 1; i++) { new_data[i].seen = env->pass_cnt; new_data[i].zext_dst = insn_has_def32(env, insn + i); } env->insn_aux_data = new_data; vfree(old_data); return 0; } static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) { int i; if (len == 1) return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } } static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { struct bpf_prog *new_prog; new_prog = bpf_patch_insn_single(env->prog, off, patch, len); if (IS_ERR(new_prog)) { if (PTR_ERR(new_prog) == -ERANGE) verbose(env, "insn %d cannot be patched due to 16-bit range\n", env->insn_aux_data[off].orig_idx); return NULL; } if (adjust_insn_aux_data(env, new_prog, off, len)) return NULL; adjust_subprog_starts(env, off, len); return new_prog; } static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { int i, j; /* find first prog starting at or after off (first to remove) */ for (i = 0; i < env->subprog_cnt; i++) if (env->subprog_info[i].start >= off) break; /* find first prog starting at or after off + cnt (first to stay) */ for (j = i; j < env->subprog_cnt; j++) if (env->subprog_info[j].start >= off + cnt) break; /* if j doesn't start exactly at off + cnt, we are just removing * the front of previous prog */ if (env->subprog_info[j].start != off + cnt) j--; if (j > i) { struct bpf_prog_aux *aux = env->prog->aux; int move; /* move fake 'exit' subprog as well */ move = env->subprog_cnt + 1 - j; memmove(env->subprog_info + i, env->subprog_info + j, sizeof(*env->subprog_info) * move); env->subprog_cnt -= j - i; /* remove func_info */ if (aux->func_info) { move = aux->func_info_cnt - j; memmove(aux->func_info + i, aux->func_info + j, sizeof(*aux->func_info) * move); aux->func_info_cnt -= j - i; /* func_info->insn_off is set after all code rewrites, * in adjust_btf_func() - no need to adjust */ } } else { /* convert i from "first prog to remove" to "first to adjust" */ if (env->subprog_info[i].start == off) i++; } /* update fake 'exit' subprog as well */ for (; i <= env->subprog_cnt; i++) env->subprog_info[i].start -= cnt; return 0; } static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_prog *prog = env->prog; u32 i, l_off, l_cnt, nr_linfo; struct bpf_line_info *linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo) return 0; linfo = prog->aux->linfo; /* find first line info to remove, count lines to be removed */ for (i = 0; i < nr_linfo; i++) if (linfo[i].insn_off >= off) break; l_off = i; l_cnt = 0; for (; i < nr_linfo; i++) if (linfo[i].insn_off < off + cnt) l_cnt++; else break; /* First live insn doesn't match first live linfo, it needs to "inherit" * last removed linfo. prog is already modified, so prog->len == off * means no live instructions after (tail of the program was removed). */ if (prog->len != off && l_cnt && (i == nr_linfo || linfo[i].insn_off != off + cnt)) { l_cnt--; linfo[--i].insn_off = off + cnt; } /* remove the line info which refer to the removed instructions */ if (l_cnt) { memmove(linfo + l_off, linfo + i, sizeof(*linfo) * (nr_linfo - i)); prog->aux->nr_linfo -= l_cnt; nr_linfo = prog->aux->nr_linfo; } /* pull all linfo[i].insn_off >= off + cnt in by cnt */ for (i = l_off; i < nr_linfo; i++) linfo[i].insn_off -= cnt; /* fix up all subprogs (incl. 'exit') which start >= off */ for (i = 0; i <= env->subprog_cnt; i++) if (env->subprog_info[i].linfo_idx > l_off) { /* program may have started in the removed region but * may not be fully removed */ if (env->subprog_info[i].linfo_idx >= l_off + l_cnt) env->subprog_info[i].linfo_idx -= l_cnt; else env->subprog_info[i].linfo_idx = l_off; } return 0; } static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; unsigned int orig_prog_len = env->prog->len; int err; if (bpf_prog_is_dev_bound(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); err = bpf_remove_insns(env->prog, off, cnt); if (err) return err; err = adjust_subprog_starts_after_remove(env, off, cnt); if (err) return err; err = bpf_adj_linfo_after_remove(env, off, cnt); if (err) return err; memmove(aux_data + off, aux_data + off + cnt, sizeof(*aux_data) * (orig_prog_len - off - cnt)); return 0; } /* The verifier does more data flow analysis than llvm and will not * explore branches that are dead at run time. Malicious programs can * have dead code too. Therefore replace all dead at-run-time code * with 'ja -1'. * * Just nops are not optimal, e.g. if they would sit at the end of the * program and through another bug we would manage to jump there, then * we'd execute beyond program memory otherwise. Returning exception * code also wouldn't work since we can have subprogs where the dead * code could be located. */ static void sanitize_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++) { if (aux_data[i].seen) continue; memcpy(insn + i, &trap, sizeof(trap)); } } static bool insn_is_cond_jump(u8 code) { u8 op; if (BPF_CLASS(code) == BPF_JMP32) return true; if (BPF_CLASS(code) != BPF_JMP) return false; op = BPF_OP(code); return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; } static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) { if (!insn_is_cond_jump(insn->code)) continue; if (!aux_data[i + 1].seen) ja.off = insn->off; else if (!aux_data[i + 1 + insn->off].seen) ja.off = 0; else continue; if (bpf_prog_is_dev_bound(env->prog->aux)) bpf_prog_offload_replace_insn(env, i, &ja); memcpy(insn, &ja, sizeof(ja)); } } static int opt_remove_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; int insn_cnt = env->prog->len; int i, err; for (i = 0; i < insn_cnt; i++) { int j; j = 0; while (i + j < insn_cnt && !aux_data[i + j].seen) j++; if (!j) continue; err = verifier_remove_insns(env, i, j); if (err) return err; insn_cnt = env->prog->len; } return 0; } static int opt_remove_nops(struct bpf_verifier_env *env) { const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, err; for (i = 0; i < insn_cnt; i++) { if (memcmp(&insn[i], &ja, sizeof(ja))) continue; err = verifier_remove_insns(env, i, 1); if (err) return err; insn_cnt--; i--; } return 0; } static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, const union bpf_attr *attr) { struct bpf_insn *patch, zext_patch[2], rnd_hi32_patch[4]; struct bpf_insn_aux_data *aux = env->insn_aux_data; int i, patch_len, delta = 0, len = env->prog->len; struct bpf_insn *insns = env->prog->insnsi; struct bpf_prog *new_prog; bool rnd_hi32; rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32; zext_patch[1] = BPF_ZEXT_REG(0); rnd_hi32_patch[1] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, 0); rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX); for (i = 0; i < len; i++) { int adj_idx = i + delta; struct bpf_insn insn; insn = insns[adj_idx]; if (!aux[adj_idx].zext_dst) { u8 code, class; u32 imm_rnd; if (!rnd_hi32) continue; code = insn.code; class = BPF_CLASS(code); if (insn_no_def(&insn)) continue; /* NOTE: arg "reg" (the fourth one) is only used for * BPF_STX which has been ruled out in above * check, it is safe to pass NULL here. */ if (is_reg64(env, &insn, insn.dst_reg, NULL, DST_OP)) { if (class == BPF_LD && BPF_MODE(code) == BPF_IMM) i++; continue; } /* ctx load could be transformed into wider load. */ if (class == BPF_LDX && aux[adj_idx].ptr_type == PTR_TO_CTX) continue; imm_rnd = get_random_int(); rnd_hi32_patch[0] = insn; rnd_hi32_patch[1].imm = imm_rnd; rnd_hi32_patch[3].dst_reg = insn.dst_reg; patch = rnd_hi32_patch; patch_len = 4; goto apply_patch_buffer; } if (!bpf_jit_needs_zext()) continue; zext_patch[0] = insn; zext_patch[1].dst_reg = insn.dst_reg; zext_patch[1].src_reg = insn.dst_reg; patch = zext_patch; patch_len = 2; apply_patch_buffer: new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len); if (!new_prog) return -ENOMEM; env->prog = new_prog; insns = new_prog->insnsi; aux = env->insn_aux_data; delta += patch_len - 1; } return 0; } /* convert load instructions that access fields of a context type into a * sequence of instructions that access fields of the underlying structure: * struct __sk_buff -> struct sk_buff * struct bpf_sock_ops -> struct sock */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) return -ENOMEM; env->prog = new_prog; delta += cnt - 1; } } if (bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) type = BPF_READ; else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || insn->code == (BPF_STX | BPF_MEM | BPF_H) || insn->code == (BPF_STX | BPF_MEM | BPF_W) || insn->code == (BPF_STX | BPF_MEM | BPF_DW)) type = BPF_WRITE; else continue; if (type == BPF_WRITE && env->insn_aux_data[i + delta].sanitize_stack_off) { struct bpf_insn patch[] = { /* Sanitize suspicious stack slot with zero. * There are no memory dependencies for this store, * since it's only using frame pointer and immediate * constant of zero */ BPF_ST_MEM(BPF_DW, BPF_REG_FP, env->insn_aux_data[i + delta].sanitize_stack_off, 0), /* the original STX instruction will immediately * overwrite the same stack slot with appropriate value */ *insn, }; cnt = ARRAY_SIZE(patch); new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } switch (env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) continue; convert_ctx_access = ops->convert_ctx_access; break; case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: convert_ctx_access = bpf_sock_convert_ctx_access; break; case PTR_TO_TCP_SOCK: convert_ctx_access = bpf_tcp_sock_convert_ctx_access; break; case PTR_TO_XDP_SOCK: convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; case PTR_TO_BTF_ID: if (type == BPF_READ) { insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); env->prog->aux->num_exentries++; } else if (resolve_prog_type(env->prog) != BPF_PROG_TYPE_STRUCT_OPS) { verbose(env, "Writes through BTF pointers are not allowed\n"); return -EINVAL; } continue; default: continue; } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); /* If the read access is a narrower load of the field, * convert to a 4/8-byte load, to minimum program type specific * convert_ctx_access changes. If conversion is successful, * we will apply proper mask to the result. */ is_narrower_load = size < ctx_field_size; size_default = bpf_ctx_off_adjust_machine(ctx_field_size); off = insn->off; if (is_narrower_load) { u8 size_code; if (type == BPF_WRITE) { verbose(env, "bpf verifier narrow ctx access misconfigured\n"); return -EINVAL; } size_code = BPF_H; if (ctx_field_size == 4) size_code = BPF_W; else if (ctx_field_size == 8) size_code = BPF_DW; insn->off = off & ~(size_default - 1); insn->code = BPF_LDX | BPF_MEM | size_code; } target_size = 0; cnt = convert_ctx_access(type, insn, insn_buf, env->prog, &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); } else { if (shift) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; /* keep walking new program and skip insns we just inserted */ env->prog = new_prog; insn = new_prog->insnsi + i + delta; } return 0; } static int jit_subprogs(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog, **func, *tmp; int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_insn *insn; void *old_bpf_func; int err, num_exentries; if (env->subprog_cnt <= 1) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", i + insn->imm + 1); return -EFAULT; } /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ insn->off = subprog; /* remember original imm in case JIT fails and fallback * to interpreter will be needed */ env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; } err = bpf_prog_alloc_jited_linfo(prog); if (err) goto out_undo_insn; err = -ENOMEM; func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; /* BPF_PROG_RUN doesn't call subprogs directly, * hence main prog stats include the runtime of subprogs. * subprogs don't have IDs and not reachable via prog_get_next_id * func[i]->aux->stats will never be accessed and stays NULL */ func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER); if (!func[i]) goto out_free; memcpy(func[i]->insnsi, &prog->insnsi[subprog_start], len * sizeof(struct bpf_insn)); func[i]->type = prog->type; func[i]->len = len; if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; func[i]->aux->func_idx = i; /* the btf and func_info will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; func[i]->aux->func_info = prog->aux->func_info; /* Use bpf_prog_F_tag to indicate functions in stack traces. * Long term would need debug info to populate names */ func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i]->aux->linfo = prog->aux->linfo; func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; num_exentries = 0; insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && BPF_MODE(insn->code) == BPF_PROBE_MEM) num_exentries++; } func[i]->aux->num_exentries = num_exentries; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; goto out_free; } cond_resched(); } /* at this point all bpf functions were successfully JITed * now populate all bpf_calls with correct addresses and * run last pass of JIT */ for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; subprog = insn->off; insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) - __bpf_call_base; } /* we use the aux data to keep a list of the start addresses * of the JITed images for each function in the program * * for some architectures, such as powerpc64, the imm field * might not be large enough to hold the offset of the start * address of the callee's JITed image from __bpf_call_base * * in such cases, we can lookup the start address of a callee * by using its subprog id, available from the off field of * the call instruction, as an index for this list */ func[i]->aux->func = func; func[i]->aux->func_cnt = env->subprog_cnt; } for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); err = -ENOTSUPP; goto out_free; } cond_resched(); } /* finally lock prog and jit images for all functions and * populate kallsysm */ for (i = 0; i < env->subprog_cnt; i++) { bpf_prog_lock_ro(func[i]); bpf_prog_kallsyms_add(func[i]); } /* Last step: make now unused interpreter insns from main * prog consistent for later dump requests, so they can * later look the same as if they were interpreted only. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); insn->imm = subprog; } prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt; bpf_prog_free_unused_jited_linfo(prog); return 0; out_free: for (i = 0; i < env->subprog_cnt; i++) if (func[i]) bpf_jit_free(func[i]); kfree(func); out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; insn->off = 0; insn->imm = env->insn_aux_data[i].call_imm; } bpf_prog_free_jited_linfo(prog); return err; } static int fixup_call_args(struct bpf_verifier_env *env) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON struct bpf_prog *prog = env->prog; struct bpf_insn *insn = prog->insnsi; int i, depth; #endif int err = 0; if (env->prog->jit_requested && !bpf_prog_is_dev_bound(env->prog->aux)) { err = jit_subprogs(env); if (err == 0) return 0; if (err == -EFAULT) return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON for (i = 0; i < prog->len; i++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || insn->src_reg != BPF_PSEUDO_CALL) continue; depth = get_callee_stack_depth(env, insn, i); if (depth < 0) return depth; bpf_patch_call_args(insn, depth); } err = 0; #endif return err; } /* fixup insn->imm field of bpf_call instructions * and inline eligible helpers as explicit sequence of BPF instructions * * this function is called after eBPF program passed verification */ static int fixup_bpf_calls(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; bool expect_blinding = bpf_jit_blinding_enabled(prog); struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; int i, ret, cnt, delta = 0; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || insn->code == (BPF_ALU | BPF_MOD | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; struct bpf_insn mask_and_div[] = { BPF_MOV32_REG(insn->src_reg, insn->src_reg), /* Rx div 0 -> 0 */ BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2), BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg), BPF_JMP_IMM(BPF_JA, 0, 0, 1), *insn, }; struct bpf_insn mask_and_mod[] = { BPF_MOV32_REG(insn->src_reg, insn->src_reg), /* Rx mod 0 -> Rx */ BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1), *insn, }; struct bpf_insn *patchlet; if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { patchlet = mask_and_div + (is64 ? 1 : 0); cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0); } else { patchlet = mask_and_mod + (is64 ? 1 : 0); cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0); } new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { cnt = env->ops->gen_ld_abs(insn, insn_buf); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) || insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) { const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X; const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; struct bpf_insn insn_buf[16]; struct bpf_insn *patch = &insn_buf[0]; bool issrc, isneg; u32 off_reg; aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) continue; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == BPF_ALU_SANITIZE_SRC; off_reg = issrc ? insn->src_reg : insn->dst_reg; if (isneg) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1); *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); if (issrc) { *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg); insn->src_reg = BPF_REG_AX; } else { *patch++ = BPF_ALU64_REG(BPF_AND, off_reg, BPF_REG_AX); } if (isneg) insn->code = insn->code == code_add ? code_sub : code_add; *patch++ = *insn; if (issrc && isneg) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) continue; if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); if (insn->imm == BPF_FUNC_override_return) prog->kprobe_override = 1; if (insn->imm == BPF_FUNC_tail_call) { /* If we tail call into other programs, we * cannot make any assumptions since they can * be replaced dynamically during runtime in * the program array. */ prog->cb_access = 1; env->prog->aux->stack_depth = MAX_BPF_STACK; env->prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpeter for every normal * call and to prevent accidental JITing by JIT compiler * that doesn't support bpf_tail_call yet */ insn->imm = 0; insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; if (env->bpf_capable && !expect_blinding && prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !bpf_map_ptr_unpriv(aux)) { struct bpf_jit_poke_descriptor desc = { .reason = BPF_POKE_REASON_TAIL_CALL, .tail_call.map = BPF_MAP_PTR(aux->map_ptr_state), .tail_call.key = bpf_map_key_immediate(aux), }; ret = bpf_jit_add_poke_descriptor(prog, &desc); if (ret < 0) { verbose(env, "adding tail call poke descriptor failed\n"); return ret; } insn->imm = ret + 1; continue; } if (!bpf_map_ptr_unpriv(aux)) continue; /* instead of changing every JIT dealing with tail_call * emit two extra insns: * if (index >= max_entries) goto out; * index &= array->index_mask; * to avoid out-of-bounds cpu speculation */ if (bpf_map_ptr_poisoned(aux)) { verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } map_ptr = BPF_MAP_PTR(aux->map_ptr_state); insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, container_of(map_ptr, struct bpf_array, map)->index_mask); insn_buf[2] = *insn; cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * and other inlining handlers are currently limited to 64 bit * only. */ if (prog->jit_requested && BITS_PER_LONG == 64 && (insn->imm == BPF_FUNC_map_lookup_elem || insn->imm == BPF_FUNC_map_update_elem || insn->imm == BPF_FUNC_map_delete_elem || insn->imm == BPF_FUNC_map_push_elem || insn->imm == BPF_FUNC_map_pop_elem || insn->imm == BPF_FUNC_map_peek_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; map_ptr = BPF_MAP_PTR(aux->map_ptr_state); ops = map_ptr->ops; if (insn->imm == BPF_FUNC_map_lookup_elem && ops->map_gen_lookup) { cnt = ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_delete_elem, (int (*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_update_elem, (int (*)(struct bpf_map *map, void *key, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_push_elem, (int (*)(struct bpf_map *map, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_pop_elem, (int (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_peek_elem, (int (*)(struct bpf_map *map, void *value))NULL)); switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - __bpf_call_base; continue; case BPF_FUNC_map_update_elem: insn->imm = BPF_CAST_CALL(ops->map_update_elem) - __bpf_call_base; continue; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - __bpf_call_base; continue; case BPF_FUNC_map_push_elem: insn->imm = BPF_CAST_CALL(ops->map_push_elem) - __bpf_call_base; continue; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CAST_CALL(ops->map_pop_elem) - __bpf_call_base; continue; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CAST_CALL(ops->map_peek_elem) - __bpf_call_base; continue; } goto patch_call_imm; } if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_jiffies64) { struct bpf_insn ld_jiffies_addr[2] = { BPF_LD_IMM64(BPF_REG_0, (unsigned long)&jiffies), }; insn_buf[0] = ld_jiffies_addr[0]; insn_buf[1] = ld_jiffies_addr[1]; insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ if (!fn->func) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } insn->imm = fn->func - __bpf_call_base; } /* Since poke tab is now finalized, publish aux to tracker. */ for (i = 0; i < prog->aux->size_poke_tab; i++) { map_ptr = prog->aux->poke_tab[i].tail_call.map; if (!map_ptr->ops->map_poke_track || !map_ptr->ops->map_poke_untrack || !map_ptr->ops->map_poke_run) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux); if (ret < 0) { verbose(env, "tracking tail call prog failed\n"); return ret; } } return 0; } static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl, *sln; int i; sl = env->free_list; while (sl) { sln = sl->next; free_verifier_state(&sl->state, false); kfree(sl); sl = sln; } env->free_list = NULL; if (!env->explored_states) return; for (i = 0; i < state_htab_size(env); i++) { sl = env->explored_states[i]; while (sl) { sln = sl->next; free_verifier_state(&sl->state, false); kfree(sl); sl = sln; } env->explored_states[i] = NULL; } } /* The verifier is using insn_aux_data[] to store temporary data during * verification and to store information for passes that run after the * verification like dead code sanitization. do_check_common() for subprogram N * may analyze many other subprograms. sanitize_insn_aux_data() clears all * temporary data after do_check_common() finds that subprogram N cannot be * verified independently. pass_cnt counts the number of times * do_check_common() was run and insn->aux->seen tells the pass number * insn_aux_data was touched. These variables are compared to clear temporary * data from failed pass. For testing and experiments do_check_common() can be * run multiple times even when prior attempt to verify is unsuccessful. */ static void sanitize_insn_aux_data(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; struct bpf_insn_aux_data *aux; int i, class; for (i = 0; i < env->prog->len; i++) { class = BPF_CLASS(insn[i].code); if (class != BPF_LDX && class != BPF_STX) continue; aux = &env->insn_aux_data[i]; if (aux->seen != env->pass_cnt) continue; memset(aux, 0, offsetof(typeof(*aux), orig_idx)); } } static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; env->prev_linfo = NULL; env->pass_cnt++; state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); if (!state) return -ENOMEM; state->curframe = 0; state->speculative = false; state->branches = 1; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); return -ENOMEM; } env->cur_state = state; init_func_state(env, state->frame[0], BPF_MAIN_FUNC /* callsite */, 0 /* frameno */, subprog); regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { ret = btf_prepare_func_args(env, subprog, regs); if (ret) goto out; for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (regs[i].type == PTR_TO_CTX) mark_reg_known_zero(env, regs, i); else if (regs[i].type == SCALAR_VALUE) mark_reg_unknown(env, regs, i); } } else { /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); ret = btf_check_func_arg_match(env, subprog, regs); if (ret == -EFAULT) /* unlikely verifier bug. abort. * ret == 0 and ret < 0 are sadly acceptable for * main() function due to backward compatibility. * Like socket filter program may be written as: * int bpf_prog(struct pt_regs *ctx) * and never dereference that ctx in the program. * 'struct pt_regs' is a type mismatch for socket * filter that should be using 'struct __sk_buff'. */ goto out; } ret = do_check(env); out: /* check for NULL is necessary, since cur_state can be freed inside * do_check() under memory pressure. */ if (env->cur_state) { free_verifier_state(env->cur_state, true); env->cur_state = NULL; } while (!pop_stack(env, NULL, NULL, false)); if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); if (ret) /* clean aux data in case subprog was rejected */ sanitize_insn_aux_data(env); return ret; } /* Verify all global functions in a BPF program one by one based on their BTF. * All global functions must pass verification. Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) * { * return bar(f); * } * int bar(int b) * { * ... * } * foo() will be verified first for R1=any_scalar_value. During verification it * will be assumed that bar() already verified successfully and call to bar() * from foo() will be checked for type match only. Later bar() will be verified * independently to check that it's safe for R1=any_scalar_value. */ static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; int i, ret; if (!aux->func_info) return 0; for (i = 1; i < env->subprog_cnt; i++) { if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) continue; env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "Func#%d is safe for any args that match its prototype\n", i); } } return 0; } static int do_check_main(struct bpf_verifier_env *env) { int ret; env->insn_idx = 0; ret = do_check_common(env, 0); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; } static void print_verification_stats(struct bpf_verifier_env *env) { int i; if (env->log.level & BPF_LOG_STATS) { verbose(env, "verification time %lld usec\n", div_u64(env->verification_time, 1000)); verbose(env, "stack depth "); for (i = 0; i < env->subprog_cnt; i++) { u32 depth = env->subprog_info[i].stack_depth; verbose(env, "%d", depth); if (i + 1 < env->subprog_cnt) verbose(env, "+"); } verbose(env, "\n"); } verbose(env, "processed %d insns (limit %d) max_states_per_insn %d " "total_states %d peak_states %d mark_read %d\n", env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS, env->max_states_per_insn, env->total_states, env->peak_states, env->longest_mark_read_walk); } static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; u32 btf_id, member_idx; const char *mname; btf_id = prog->aux->attach_btf_id; st_ops = bpf_struct_ops_find(btf_id); if (!st_ops) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } t = st_ops->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", member_idx, st_ops->name); return -EINVAL; } member = &btf_type_member(t)[member_idx]; mname = btf_name_by_offset(btf_vmlinux, member->name_off); func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", mname, member_idx, st_ops->name); return -EINVAL; } if (st_ops->check_member) { int err = st_ops->check_member(t, member); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", mname, st_ops->name); return err; } } prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; return 0; } #define SECURITY_PREFIX "security_" static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr) { if (within_error_injection_list(addr) || !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name, sizeof(SECURITY_PREFIX) - 1)) return 0; return -EINVAL; } /* non exhaustive list of sleepable bpf_lsm_*() functions */ BTF_SET_START(btf_sleepable_lsm_hooks) #ifdef CONFIG_BPF_LSM BTF_ID(func, bpf_lsm_bprm_committed_creds) #else BTF_ID_UNUSED #endif BTF_SET_END(btf_sleepable_lsm_hooks) static int check_sleepable_lsm_hook(u32 btf_id) { return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id); } /* list of non-sleepable functions that are otherwise on * ALLOW_ERROR_INJECTION list */ BTF_SET_START(btf_non_sleepable_error_inject) /* Three functions below can be called from sleepable and non-sleepable context. * Assume non-sleepable from bpf safety point of view. */ BTF_ID(func, __add_to_page_cache_locked) BTF_ID(func, should_fail_alloc_page) BTF_ID(func, should_failslab) BTF_SET_END(btf_non_sleepable_error_inject) static int check_non_sleepable_error_inject(u32 btf_id) { return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id); } static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; struct bpf_prog *tgt_prog = prog->aux->linked_prog; u32 btf_id = prog->aux->attach_btf_id; const char prefix[] = "btf_trace_"; struct btf_func_model fmodel; int ret = 0, subprog = -1, i; struct bpf_trampoline *tr; const struct btf_type *t; bool conservative = true; const char *tname; struct btf *btf; long addr; u64 key; if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n"); return -EINVAL; } if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) return check_struct_ops_btf_id(env); if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM && !prog_extension) return 0; if (!btf_id) { verbose(env, "Tracing programs must provide btf_id\n"); return -EINVAL; } btf = bpf_prog_get_target_btf(prog); if (!btf) { verbose(env, "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); return -EINVAL; } t = btf_type_by_id(btf, btf_id); if (!t) { verbose(env, "attach_btf_id %u is invalid\n", btf_id); return -EINVAL; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id); return -EINVAL; } if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; for (i = 0; i < aux->func_info_cnt; i++) if (aux->func_info[i].type_id == btf_id) { subprog = i; break; } if (subprog == -1) { verbose(env, "Subprog %s doesn't exist\n", tname); return -EINVAL; } conservative = aux->func_info_aux[subprog].unreliable; if (prog_extension) { if (conservative) { verbose(env, "Cannot replace static functions\n"); return -EINVAL; } if (!prog->jit_requested) { verbose(env, "Extension programs should be JITed\n"); return -EINVAL; } env->ops = bpf_verifier_ops[tgt_prog->type]; prog->expected_attach_type = tgt_prog->expected_attach_type; } if (!tgt_prog->jited) { verbose(env, "Can attach to only JITed progs\n"); return -EINVAL; } if (tgt_prog->type == prog->type) { /* Cannot fentry/fexit another fentry/fexit program. * Cannot attach program extension to another extension. * It's ok to attach fentry/fexit to extension program. */ verbose(env, "Cannot recursively attach\n"); return -EINVAL; } if (tgt_prog->type == BPF_PROG_TYPE_TRACING && prog_extension && (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY || tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) { /* Program extensions can extend all program types * except fentry/fexit. The reason is the following. * The fentry/fexit programs are used for performance * analysis, stats and can be attached to any program * type except themselves. When extension program is * replacing XDP function it is necessary to allow * performance analysis of all functions. Both original * XDP program and its program extension. Hence * attaching fentry/fexit to BPF_PROG_TYPE_EXT is * allowed. If extending of fentry/fexit was allowed it * would be possible to create long call chain * fentry->extension->fentry->extension beyond * reasonable stack size. Hence extending fentry is not * allowed. */ verbose(env, "Cannot extend fentry/fexit\n"); return -EINVAL; } key = ((u64)aux->id) << 32 | btf_id; } else { if (prog_extension) { verbose(env, "Cannot replace kernel functions\n"); return -EINVAL; } key = btf_id; } switch (prog->expected_attach_type) { case BPF_TRACE_RAW_TP: if (tgt_prog) { verbose(env, "Only FENTRY/FEXIT progs are attachable to another BPF prog\n"); return -EINVAL; } if (!btf_type_is_typedef(t)) { verbose(env, "attach_btf_id %u is not a typedef\n", btf_id); return -EINVAL; } if (strncmp(prefix, tname, sizeof(prefix) - 1)) { verbose(env, "attach_btf_id %u points to wrong type name %s\n", btf_id, tname); return -EINVAL; } tname += sizeof(prefix) - 1; t = btf_type_by_id(btf, t->type); if (!btf_type_is_ptr(t)) /* should never happen in valid vmlinux build */ return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) /* should never happen in valid vmlinux build */ return -EINVAL; /* remember two read only pointers that are valid for * the life time of the kernel */ prog->aux->attach_func_name = tname; prog->aux->attach_func_proto = t; prog->aux->attach_btf_trace = true; return 0; case BPF_TRACE_ITER: if (!btf_type_is_func(t)) { verbose(env, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; prog->aux->attach_func_name = tname; prog->aux->attach_func_proto = t; if (!bpf_iter_prog_supported(prog)) return -EINVAL; ret = btf_distill_func_proto(&env->log, btf, t, tname, &fmodel); return ret; default: if (!prog_extension) return -EINVAL; /* fallthrough */ case BPF_MODIFY_RETURN: case BPF_LSM_MAC: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: prog->aux->attach_func_name = tname; if (prog->type == BPF_PROG_TYPE_LSM) { ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; } if (!btf_type_is_func(t)) { verbose(env, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } if (prog_extension && btf_check_type_match(env, prog, btf, t)) return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; tr = bpf_trampoline_lookup(key); if (!tr) return -ENOMEM; /* t is either vmlinux type or another program's type */ prog->aux->attach_func_proto = t; mutex_lock(&tr->mutex); if (tr->func.addr) { prog->aux->trampoline = tr; goto out; } if (tgt_prog && conservative) { prog->aux->attach_func_proto = NULL; t = NULL; } ret = btf_distill_func_proto(&env->log, btf, t, tname, &tr->func.model); if (ret < 0) goto out; if (tgt_prog) { if (subprog == 0) addr = (long) tgt_prog->bpf_func; else addr = (long) tgt_prog->aux->func[subprog]->bpf_func; } else { addr = kallsyms_lookup_name(tname); if (!addr) { verbose(env, "The address of function %s cannot be found\n", tname); ret = -ENOENT; goto out; } } if (prog->aux->sleepable) { ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: /* fentry/fexit/fmod_ret progs can be sleepable only if they are * attached to ALLOW_ERROR_INJECTION and are not in denylist. */ if (!check_non_sleepable_error_inject(btf_id) && within_error_injection_list(addr)) ret = 0; break; case BPF_PROG_TYPE_LSM: /* LSM progs check that they are attached to bpf_lsm_*() funcs. * Only some of them are sleepable. */ if (check_sleepable_lsm_hook(btf_id)) ret = 0; break; default: break; } if (ret) verbose(env, "%s is not sleepable\n", prog->aux->attach_func_name); } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { ret = check_attach_modify_return(prog, addr); if (ret) verbose(env, "%s() is not modifiable\n", prog->aux->attach_func_name); } if (ret) goto out; tr->func.addr = (void *)addr; prog->aux->trampoline = tr; out: mutex_unlock(&tr->mutex); if (ret) bpf_trampoline_put(tr); return ret; } } int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, union bpf_attr __user *uattr) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; struct bpf_verifier_log *log; int i, len, ret = -EINVAL; bool is_priv; /* no program is valid */ if (ARRAY_SIZE(bpf_verifier_ops) == 0) return -EINVAL; /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; log = &env->log; len = (*prog)->len; env->insn_aux_data = vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); ret = -ENOMEM; if (!env->insn_aux_data) goto err_free_env; for (i = 0; i < len; i++) env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; is_priv = bpf_capable(); if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { mutex_lock(&bpf_verifier_lock); if (!btf_vmlinux) btf_vmlinux = btf_parse_vmlinux(); mutex_unlock(&bpf_verifier_lock); } /* grab the mutex to protect few globals used by verifier */ if (!is_priv) mutex_lock(&bpf_verifier_lock); if (attr->log_level || attr->log_buf || attr->log_size) { /* user requested verbose verifier output * and supplied buffer to store the verification trace */ log->level = attr->log_level; log->ubuf = (char __user *) (unsigned long) attr->log_buf; log->len_total = attr->log_size; ret = -EINVAL; /* log attributes have to be sane */ if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 || !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK) goto err_unlock; } if (IS_ERR(btf_vmlinux)) { /* Either gcc or pahole or kernel are broken. */ verbose(env, "in-kernel BTF is malformed\n"); ret = PTR_ERR(btf_vmlinux); goto skip_full_check; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; env->allow_ptr_leaks = bpf_allow_ptr_leaks(); env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access(); env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; if (bpf_prog_is_dev_bound(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; } env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); ret = -ENOMEM; if (!env->explored_states) goto skip_full_check; ret = check_subprogs(env); if (ret < 0) goto skip_full_check; ret = check_btf_info(env, attr, uattr); if (ret < 0) goto skip_full_check; ret = check_attach_btf_id(env); if (ret) goto skip_full_check; ret = check_cfg(env); if (ret < 0) goto skip_full_check; ret = do_check_subprogs(env); ret = ret ?: do_check_main(env); if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) ret = bpf_prog_offload_finalize(env); skip_full_check: kvfree(env->explored_states); if (ret == 0) ret = check_max_stack_depth(env); /* instruction rewrites happen after this point */ if (is_priv) { if (ret == 0) opt_hard_wire_dead_code_branches(env); if (ret == 0) ret = opt_remove_dead_code(env); if (ret == 0) ret = opt_remove_nops(env); } else { if (ret == 0) sanitize_dead_code(env); } if (ret == 0) /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); if (ret == 0) ret = fixup_bpf_calls(env); /* do 32-bit optimization after insn patching has done so those patched * insns could be handled correctly. */ if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) { ret = opt_subreg_zext_lo32_rnd_hi32(env, attr); env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret : false; } if (ret == 0) ret = fixup_call_args(env); env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; if (log->level && !log->ubuf) { ret = -EFAULT; goto err_release_maps; } if (ret == 0 && env->used_map_cnt) { /* if program passed verifier, update used_maps in bpf_prog_info */ env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt, sizeof(env->used_maps[0]), GFP_KERNEL); if (!env->prog->aux->used_maps) { ret = -ENOMEM; goto err_release_maps; } memcpy(env->prog->aux->used_maps, env->used_maps, sizeof(env->used_maps[0]) * env->used_map_cnt); env->prog->aux->used_map_cnt = env->used_map_cnt; /* program is valid. Convert pseudo bpf_ld_imm64 into generic * bpf_ld_imm64 instructions */ convert_pseudo_ld_imm64(env); } if (ret == 0) adjust_btf_func(env); err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_used_maps() will release them. */ release_maps(env); /* extension progs temporarily inherit the attach_type of their targets for verification purposes, so set it back to zero before returning */ if (env->prog->type == BPF_PROG_TYPE_EXT) env->prog->expected_attach_type = 0; *prog = env->prog; err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); vfree(env->insn_aux_data); err_free_env: kfree(env); return ret; }