diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/bpf/arraymap.c | 17 | ||||
| -rw-r--r-- | kernel/bpf/btf.c | 25 | ||||
| -rw-r--r-- | kernel/bpf/hashtab.c | 6 | ||||
| -rw-r--r-- | kernel/bpf/helpers.c | 32 | ||||
| -rw-r--r-- | kernel/bpf/percpu_freelist.c | 101 | ||||
| -rw-r--r-- | kernel/bpf/percpu_freelist.h | 1 | ||||
| -rw-r--r-- | kernel/bpf/syscall.c | 4 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 270 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 6 |
9 files changed, 403 insertions, 59 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index bd777dd6f967..c6c81eceb68f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -16,7 +16,7 @@ #define ARRAY_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \ - BPF_F_PRESERVE_ELEMS) + BPF_F_PRESERVE_ELEMS | BPF_F_INNER_MAP) static void bpf_array_free_percpu(struct bpf_array *array) { @@ -62,7 +62,7 @@ int array_map_alloc_check(union bpf_attr *attr) return -EINVAL; if (attr->map_type != BPF_MAP_TYPE_ARRAY && - attr->map_flags & BPF_F_MMAPABLE) + attr->map_flags & (BPF_F_MMAPABLE | BPF_F_INNER_MAP)) return -EINVAL; if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY && @@ -214,7 +214,7 @@ static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm, } /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ -static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +static int array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_insn *insn = insn_buf; @@ -223,6 +223,9 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) const int map_ptr = BPF_REG_1; const int index = BPF_REG_2; + if (map->map_flags & BPF_F_INNER_MAP) + return -EOPNOTSUPP; + *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); if (!map->bypass_spec_v1) { @@ -496,8 +499,10 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) static bool array_map_meta_equal(const struct bpf_map *meta0, const struct bpf_map *meta1) { - return meta0->max_entries == meta1->max_entries && - bpf_map_meta_equal(meta0, meta1); + if (!bpf_map_meta_equal(meta0, meta1)) + return false; + return meta0->map_flags & BPF_F_INNER_MAP ? true : + meta0->max_entries == meta1->max_entries; } struct bpf_iter_seq_array_map_info { @@ -1251,7 +1256,7 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } -static u32 array_of_map_gen_lookup(struct bpf_map *map, +static int array_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_array *array = container_of(map, struct bpf_array, map); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4d0ee7839fdb..ed7d02e8bc93 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -188,11 +188,6 @@ i < btf_type_vlen(struct_type); \ i++, member++) -#define for_each_vsi(i, struct_type, member) \ - for (i = 0, member = btf_type_var_secinfo(struct_type); \ - i < btf_type_vlen(struct_type); \ - i++, member++) - #define for_each_vsi_from(i, from, struct_type, member) \ for (i = from, member = btf_type_var_secinfo(struct_type) + from; \ i < btf_type_vlen(struct_type); \ @@ -440,16 +435,6 @@ static bool btf_type_nosize_or_null(const struct btf_type *t) return !t || btf_type_nosize(t); } -/* union is only a special case of struct: - * all its offsetof(member) == 0 - */ -static bool btf_type_is_struct(const struct btf_type *t) -{ - u8 kind = BTF_INFO_KIND(t->info); - - return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; -} - static bool __btf_type_is_struct(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; @@ -460,11 +445,6 @@ static bool btf_type_is_array(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; } -static bool btf_type_is_var(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; -} - static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; @@ -613,11 +593,6 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } -static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t) -{ - return (const struct btf_var_secinfo *)(t + 1); -} - static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3395cf140d22..1815e97d4c9c 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -612,7 +612,7 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key) * bpf_prog * __htab_map_lookup_elem */ -static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; @@ -651,7 +651,7 @@ static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key) return __htab_lru_map_lookup_elem(map, key, false); } -static u32 htab_lru_map_gen_lookup(struct bpf_map *map, +static int htab_lru_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; @@ -2070,7 +2070,7 @@ static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } -static u32 htab_of_map_gen_lookup(struct bpf_map *map, +static int htab_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index e825441781ab..25520f5eeaf6 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -623,6 +623,34 @@ const struct bpf_func_proto bpf_copy_from_user_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu) +{ + if (cpu >= nr_cpu_ids) + return (unsigned long)NULL; + + return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu); +} + +const struct bpf_func_proto bpf_per_cpu_ptr_proto = { + .func = bpf_per_cpu_ptr, + .gpl_only = false, + .ret_type = RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr) +{ + return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr); +} + +const struct bpf_func_proto bpf_this_cpu_ptr_proto = { + .func = bpf_this_cpu_ptr, + .gpl_only = false, + .ret_type = RET_PTR_TO_MEM_OR_BTF_ID, + .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, +}; + const struct bpf_func_proto bpf_get_current_task_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; const struct bpf_func_proto bpf_probe_read_user_str_proto __weak; @@ -689,6 +717,10 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_btf_proto; case BPF_FUNC_jiffies64: return &bpf_jiffies64_proto; + case BPF_FUNC_bpf_per_cpu_ptr: + return &bpf_per_cpu_ptr_proto; + case BPF_FUNC_bpf_this_cpu_ptr: + return &bpf_this_cpu_ptr_proto; default: break; } diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index b367430e611c..3d897de89061 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -17,6 +17,8 @@ int pcpu_freelist_init(struct pcpu_freelist *s) raw_spin_lock_init(&head->lock); head->first = NULL; } + raw_spin_lock_init(&s->extralist.lock); + s->extralist.first = NULL; return 0; } @@ -40,12 +42,50 @@ static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, raw_spin_unlock(&head->lock); } +static inline bool pcpu_freelist_try_push_extra(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + if (!raw_spin_trylock(&s->extralist.lock)) + return false; + + pcpu_freelist_push_node(&s->extralist, node); + raw_spin_unlock(&s->extralist.lock); + return true; +} + +static inline void ___pcpu_freelist_push_nmi(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + int cpu, orig_cpu; + + orig_cpu = cpu = raw_smp_processor_id(); + while (1) { + struct pcpu_freelist_head *head; + + head = per_cpu_ptr(s->freelist, cpu); + if (raw_spin_trylock(&head->lock)) { + pcpu_freelist_push_node(head, node); + raw_spin_unlock(&head->lock); + return; + } + cpu = cpumask_next(cpu, cpu_possible_mask); + if (cpu >= nr_cpu_ids) + cpu = 0; + + /* cannot lock any per cpu lock, try extralist */ + if (cpu == orig_cpu && + pcpu_freelist_try_push_extra(s, node)) + return; + } +} + void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { - struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - - ___pcpu_freelist_push(head, node); + if (in_nmi()) + ___pcpu_freelist_push_nmi(s, node); + else + ___pcpu_freelist_push(this_cpu_ptr(s->freelist), node); } void pcpu_freelist_push(struct pcpu_freelist *s, @@ -81,7 +121,7 @@ again: } } -struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) +static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; @@ -102,8 +142,59 @@ struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) if (cpu >= nr_cpu_ids) cpu = 0; if (cpu == orig_cpu) - return NULL; + break; + } + + /* per cpu lists are all empty, try extralist */ + raw_spin_lock(&s->extralist.lock); + node = s->extralist.first; + if (node) + s->extralist.first = node->next; + raw_spin_unlock(&s->extralist.lock); + return node; +} + +static struct pcpu_freelist_node * +___pcpu_freelist_pop_nmi(struct pcpu_freelist *s) +{ + struct pcpu_freelist_head *head; + struct pcpu_freelist_node *node; + int orig_cpu, cpu; + + orig_cpu = cpu = raw_smp_processor_id(); + while (1) { + head = per_cpu_ptr(s->freelist, cpu); + if (raw_spin_trylock(&head->lock)) { + node = head->first; + if (node) { + head->first = node->next; + raw_spin_unlock(&head->lock); + return node; + } + raw_spin_unlock(&head->lock); + } + cpu = cpumask_next(cpu, cpu_possible_mask); + if (cpu >= nr_cpu_ids) + cpu = 0; + if (cpu == orig_cpu) + break; } + + /* cannot pop from per cpu lists, try extralist */ + if (!raw_spin_trylock(&s->extralist.lock)) + return NULL; + node = s->extralist.first; + if (node) + s->extralist.first = node->next; + raw_spin_unlock(&s->extralist.lock); + return node; +} + +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) +{ + if (in_nmi()) + return ___pcpu_freelist_pop_nmi(s); + return ___pcpu_freelist_pop(s); } struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index fbf8a8a28979..3c76553cfe57 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -13,6 +13,7 @@ struct pcpu_freelist_head { struct pcpu_freelist { struct pcpu_freelist_head __percpu *freelist; + struct pcpu_freelist_head extralist; }; struct pcpu_freelist_node { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f1528c2a6927..1110ecd7d1f3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4323,8 +4323,10 @@ static int bpf_prog_bind_map(union bpf_attr *attr) used_maps_old = prog->aux->used_maps; for (i = 0; i < prog->aux->used_map_cnt; i++) - if (used_maps_old[i] == map) + if (used_maps_old[i] == map) { + bpf_map_put(map); goto out_unlock; + } used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1, sizeof(used_maps_new[0]), diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3923c570070b..c43a5e8f0818 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -238,6 +238,8 @@ struct bpf_call_arg_meta { u64 msize_max_value; int ref_obj_id; int func_id; + u32 btf_id; + u32 ret_btf_id; }; struct btf *btf_vmlinux; @@ -517,6 +519,7 @@ static const char * const reg_type_str[] = { [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_", + [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", [PTR_TO_MEM] = "mem", [PTR_TO_MEM_OR_NULL] = "mem_or_null", [PTR_TO_RDONLY_BUF] = "rdonly_buf", @@ -583,7 +586,9 @@ static void print_verifier_state(struct bpf_verifier_env *env, /* 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) + if (t == PTR_TO_BTF_ID || + t == PTR_TO_BTF_ID_OR_NULL || + t == PTR_TO_PERCPU_BTF_ID) verbose(env, "%s", kernel_type_name(reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) @@ -2204,6 +2209,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_RDONLY_BUF_OR_NULL: case PTR_TO_RDWR_BUF: case PTR_TO_RDWR_BUF_OR_NULL: + case PTR_TO_PERCPU_BTF_ID: return true; default: return false; @@ -2221,6 +2227,20 @@ static bool register_is_const(struct bpf_reg_state *reg) return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off); } +static bool __is_scalar_unbounded(struct bpf_reg_state *reg) +{ + return tnum_is_unknown(reg->var_off) && + 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 bool register_is_bounded(struct bpf_reg_state *reg) +{ + return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg); +} + static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -2272,7 +2292,7 @@ static int check_stack_write(struct bpf_verifier_env *env, if (value_regno >= 0) reg = &cur->regs[value_regno]; - if (reg && size == BPF_REG_SIZE && register_is_const(reg) && + if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit @@ -2667,7 +2687,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; - /* fallthrough */ + fallthrough; /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: @@ -3978,6 +3998,7 @@ static const struct bpf_reg_types sock_types = { }, }; +#ifdef CONFIG_NET static const struct bpf_reg_types btf_id_sock_common_types = { .types = { PTR_TO_SOCK_COMMON, @@ -3988,6 +4009,7 @@ static const struct bpf_reg_types btf_id_sock_common_types = { }, .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], }; +#endif static const struct bpf_reg_types mem_types = { .types = { @@ -4017,6 +4039,7 @@ static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } }; +static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } }; static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, @@ -4030,7 +4053,9 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_CTX] = &context_types, [ARG_PTR_TO_CTX_OR_NULL] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, +#ifdef CONFIG_NET [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, +#endif [ARG_PTR_TO_SOCKET] = &fullsock_types, [ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types, [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, @@ -4042,6 +4067,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, + [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, }; static int check_reg_type(struct bpf_verifier_env *env, u32 regno, @@ -4205,6 +4231,12 @@ skip_type_check: err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, meta); + } else if (arg_type == ARG_PTR_TO_PERCPU_BTF_ID) { + if (!reg->btf_id) { + verbose(env, "Helper has invalid btf_id in R%d\n", regno); + return -EACCES; + } + meta->ret_btf_id = reg->btf_id; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -5114,6 +5146,35 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn 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_MEM_OR_BTF_ID_OR_NULL || + fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) { + const struct btf_type *t; + + mark_reg_known_zero(env, regs, BPF_REG_0); + t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL); + if (!btf_type_is_struct(t)) { + u32 tsize; + const struct btf_type *ret; + const char *tname; + + /* resolve the type size of ksym. */ + ret = btf_resolve_size(btf_vmlinux, t, &tsize); + if (IS_ERR(ret)) { + tname = btf_name_by_offset(btf_vmlinux, t->name_off); + verbose(env, "unable to resolve the size of type '%s': %ld\n", + tname, PTR_ERR(ret)); + return -EINVAL; + } + regs[BPF_REG_0].type = + fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? + PTR_TO_MEM : PTR_TO_MEM_OR_NULL; + regs[BPF_REG_0].mem_size = tsize; + } else { + regs[BPF_REG_0].type = + fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? + PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL; + regs[BPF_REG_0].btf_id = meta.ret_btf_id; + } } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) { int ret_btf_id; @@ -5432,7 +5493,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) break; - /* fall-through */ + fallthrough; case PTR_TO_PACKET_END: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: @@ -6389,6 +6450,11 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, src_reg = NULL; if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; + else + /* Make sure ID is cleared otherwise dst_reg min/max could be + * incorrectly propagated into other registers by find_equal_scalars() + */ + dst_reg->id = 0; if (BPF_SRC(insn->code) == BPF_X) { src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { @@ -6522,6 +6588,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) /* case: R1 = R2 * copy register state to dest reg */ + if (src_reg->type == SCALAR_VALUE && !src_reg->id) + /* Assign src and dst registers the same ID + * that will be used by find_equal_scalars() + * to propagate min/max range. + */ + src_reg->id = ++env->id_gen; *dst_reg = *src_reg; dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; @@ -6534,6 +6606,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { *dst_reg = *src_reg; + /* Make sure ID is cleared otherwise + * dst_reg min/max could be incorrectly + * propagated into src_reg by find_equal_scalars() + */ + dst_reg->id = 0; dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = env->insn_idx + 1; } else { @@ -7322,6 +7399,30 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn, return true; } +static void find_equal_scalars(struct bpf_verifier_state *vstate, + struct bpf_reg_state *known_reg) +{ + struct bpf_func_state *state; + struct bpf_reg_state *reg; + int i, j; + + for (i = 0; i <= vstate->curframe; i++) { + state = vstate->frame[i]; + for (j = 0; j < MAX_BPF_REG; j++) { + reg = &state->regs[j]; + if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) + *reg = *known_reg; + } + + bpf_for_each_spilled_reg(j, state, reg) { + if (!reg) + continue; + if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) + *reg = *known_reg; + } + } +} + static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { @@ -7450,6 +7551,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, reg_combine_min_max(&other_branch_regs[insn->src_reg], &other_branch_regs[insn->dst_reg], src_reg, dst_reg, opcode); + if (src_reg->id) { + find_equal_scalars(this_branch, src_reg); + find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]); + } + } } else if (dst_reg->type == SCALAR_VALUE) { reg_set_min_max(&other_branch_regs[insn->dst_reg], @@ -7457,6 +7563,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, opcode, is_jmp32); } + if (dst_reg->type == SCALAR_VALUE && dst_reg->id) { + find_equal_scalars(this_branch, dst_reg); + find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]); + } + /* 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. @@ -7488,6 +7599,7 @@ 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_reg_state *dst_reg; struct bpf_map *map; int err; @@ -7504,25 +7616,45 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + dst_reg = ®s[insn->dst_reg]; if (insn->src_reg == 0) { u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - regs[insn->dst_reg].type = SCALAR_VALUE; + dst_reg->type = SCALAR_VALUE; __mark_reg_known(®s[insn->dst_reg], imm); return 0; } + if (insn->src_reg == BPF_PSEUDO_BTF_ID) { + mark_reg_known_zero(env, regs, insn->dst_reg); + + dst_reg->type = aux->btf_var.reg_type; + switch (dst_reg->type) { + case PTR_TO_MEM: + dst_reg->mem_size = aux->btf_var.mem_size; + break; + case PTR_TO_BTF_ID: + case PTR_TO_PERCPU_BTF_ID: + dst_reg->btf_id = aux->btf_var.btf_id; + break; + default: + verbose(env, "bpf verifier is misconfigured\n"); + return -EFAULT; + } + 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; + 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; + dst_reg->type = PTR_TO_MAP_VALUE; + dst_reg->off = aux->map_off; if (map_value_has_spin_lock(map)) - regs[insn->dst_reg].id = ++env->id_gen; + dst_reg->id = ++env->id_gen; } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { - regs[insn->dst_reg].type = CONST_PTR_TO_MAP; + dst_reg->type = CONST_PTR_TO_MAP; } else { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; @@ -9424,6 +9556,92 @@ process_bpf_exit: return 0; } +/* replace pseudo btf_id with kernel symbol address */ +static int check_pseudo_btf_id(struct bpf_verifier_env *env, + struct bpf_insn *insn, + struct bpf_insn_aux_data *aux) +{ + u32 datasec_id, type, id = insn->imm; + const struct btf_var_secinfo *vsi; + const struct btf_type *datasec; + const struct btf_type *t; + const char *sym_name; + bool percpu = false; + u64 addr; + int i; + + if (!btf_vmlinux) { + verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); + return -EINVAL; + } + + if (insn[1].imm != 0) { + verbose(env, "reserved field (insn[1].imm) is used in pseudo_btf_id ldimm64 insn.\n"); + return -EINVAL; + } + + t = btf_type_by_id(btf_vmlinux, id); + if (!t) { + verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id); + return -ENOENT; + } + + if (!btf_type_is_var(t)) { + verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n", + id); + return -EINVAL; + } + + sym_name = btf_name_by_offset(btf_vmlinux, t->name_off); + addr = kallsyms_lookup_name(sym_name); + if (!addr) { + verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n", + sym_name); + return -ENOENT; + } + + datasec_id = btf_find_by_name_kind(btf_vmlinux, ".data..percpu", + BTF_KIND_DATASEC); + if (datasec_id > 0) { + datasec = btf_type_by_id(btf_vmlinux, datasec_id); + for_each_vsi(i, datasec, vsi) { + if (vsi->type == id) { + percpu = true; + break; + } + } + } + + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; + + type = t->type; + t = btf_type_skip_modifiers(btf_vmlinux, type, NULL); + if (percpu) { + aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID; + aux->btf_var.btf_id = type; + } else if (!btf_type_is_struct(t)) { + const struct btf_type *ret; + const char *tname; + u32 tsize; + + /* resolve the type size of ksym. */ + ret = btf_resolve_size(btf_vmlinux, t, &tsize); + if (IS_ERR(ret)) { + tname = btf_name_by_offset(btf_vmlinux, t->name_off); + verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n", + tname, PTR_ERR(ret)); + return -EINVAL; + } + aux->btf_var.reg_type = PTR_TO_MEM; + aux->btf_var.mem_size = tsize; + } else { + aux->btf_var.reg_type = PTR_TO_BTF_ID; + aux->btf_var.btf_id = type; + } + return 0; +} + static int check_map_prealloc(struct bpf_map *map) { return (map->map_type != BPF_MAP_TYPE_HASH && @@ -9534,10 +9752,14 @@ static bool bpf_map_is_cgroup_storage(struct bpf_map *map) 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 +/* find and rewrite pseudo imm in ld_imm64 instructions: + * + * 1. if it accesses map FD, replace it with actual map pointer. + * 2. if it accesses btf_id of a VAR, replace it with pointer to the var. + * + * NOTE: btf_vmlinux is required for converting pseudo btf_id. */ -static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) +static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; @@ -9578,6 +9800,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) /* valid generic load 64-bit imm */ goto next_insn; + if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) { + aux = &env->insn_aux_data[i]; + err = check_pseudo_btf_id(env, insn, aux); + if (err) + return err; + goto next_insn; + } + /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ @@ -10819,7 +11049,9 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) 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)) { + if (cnt == -EOPNOTSUPP) + goto patch_map_ops_generic; + if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -10849,7 +11081,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) (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)); - +patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - @@ -11633,10 +11865,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, 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) @@ -11662,6 +11890,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (ret) goto skip_full_check; + ret = resolve_pseudo_ldimm64(env); + if (ret < 0) + goto skip_full_check; + ret = check_cfg(env); if (ret < 0) goto skip_full_check; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e118a83439c3..a2a4535b6277 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1327,6 +1327,10 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; + case BPF_FUNC_bpf_per_cpu_ptr: + return &bpf_per_cpu_ptr_proto; + case BPF_FUNC_bpf_this_cpu_ptr: + return &bpf_this_cpu_ptr_proto; default: return NULL; } @@ -1776,7 +1780,9 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { }; const struct bpf_prog_ops raw_tracepoint_prog_ops = { +#ifdef CONFIG_NET .test_run = bpf_prog_test_run_raw_tp, +#endif }; const struct bpf_verifier_ops tracing_verifier_ops = { |