diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/bpf/Makefile | 2 | ||||
| -rw-r--r-- | kernel/bpf/arraymap.c | 17 | ||||
| -rw-r--r-- | kernel/bpf/bpf_lsm.c | 17 | ||||
| -rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 71 | ||||
| -rw-r--r-- | kernel/bpf/btf.c | 6 | ||||
| -rw-r--r-- | kernel/bpf/core.c | 29 | ||||
| -rw-r--r-- | kernel/bpf/hashtab.c | 45 | ||||
| -rw-r--r-- | kernel/bpf/helpers.c | 199 | ||||
| -rw-r--r-- | kernel/bpf/link_iter.c | 107 | ||||
| -rw-r--r-- | kernel/bpf/ringbuf.c | 78 | ||||
| -rw-r--r-- | kernel/bpf/syscall.c | 75 | ||||
| -rw-r--r-- | kernel/bpf/trampoline.c | 118 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 324 | ||||
| -rw-r--r-- | kernel/kallsyms.c | 3 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 133 | ||||
| -rw-r--r-- | kernel/trace/fprobe.c | 32 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 62 |
17 files changed, 1120 insertions, 198 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index c1a9be6a4b9f..057ba8e01e70 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b3bf31fd9458..fe40d3b9458f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -243,6 +243,20 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) return this_cpu_ptr(array->pptrs[index & array->index_mask]); } +static void *percpu_array_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + + if (cpu >= nr_cpu_ids) + return NULL; + + if (unlikely(index >= array->map.max_entries)) + return NULL; + + return per_cpu_ptr(array->pptrs[index & array->index_mask], cpu); +} + int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) { struct bpf_array *array = container_of(map, struct bpf_array, map); @@ -725,6 +739,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_lookup_elem = percpu_array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem, .map_seq_show_elem = percpu_array_map_seq_show_elem, .map_check_btf = array_map_check_btf, .map_lookup_batch = generic_map_lookup_batch, @@ -1345,6 +1360,8 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = array_of_map_gen_lookup, + .map_lookup_batch = generic_map_lookup_batch, + .map_update_batch = generic_map_update_batch, .map_check_btf = map_check_no_btf, .map_btf_id = &array_map_btf_ids[0], }; diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 064eccba641d..c1351df9f7ee 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -117,6 +117,21 @@ static const struct bpf_func_proto bpf_ima_file_hash_proto = { .allowed = bpf_ima_inode_hash_allowed, }; +BPF_CALL_1(bpf_get_attach_cookie, void *, ctx) +{ + struct bpf_trace_run_ctx *run_ctx; + + run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); + return run_ctx->bpf_cookie; +} + +static const struct bpf_func_proto bpf_get_attach_cookie_proto = { + .func = bpf_get_attach_cookie, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -141,6 +156,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; case BPF_FUNC_ima_file_hash: return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL; + case BPF_FUNC_get_attach_cookie: + return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 3a0103ad97bc..d9a3c9207240 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -33,15 +33,15 @@ struct bpf_struct_ops_map { const struct bpf_struct_ops *st_ops; /* protect map_update */ struct mutex lock; - /* progs has all the bpf_prog that is populated + /* link has all the bpf_links that is populated * to the func ptr of the kernel's struct * (in kvalue.data). */ - struct bpf_prog **progs; + struct bpf_link **links; /* image is a page that has all the trampolines * that stores the func args before calling the bpf_prog. * A PAGE_SIZE "image" is enough to store all trampoline for - * "progs[]". + * "links[]". */ void *image; /* uvalue->data stores the kernel struct @@ -283,9 +283,9 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) u32 i; for (i = 0; i < btf_type_vlen(t); i++) { - if (st_map->progs[i]) { - bpf_prog_put(st_map->progs[i]); - st_map->progs[i] = NULL; + if (st_map->links[i]) { + bpf_link_put(st_map->links[i]); + st_map->links[i] = NULL; } } } @@ -316,18 +316,34 @@ static int check_zero_holes(const struct btf_type *t, void *data) return 0; } -int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, - struct bpf_prog *prog, +static void bpf_struct_ops_link_release(struct bpf_link *link) +{ +} + +static void bpf_struct_ops_link_dealloc(struct bpf_link *link) +{ + struct bpf_tramp_link *tlink = container_of(link, struct bpf_tramp_link, link); + + kfree(tlink); +} + +const struct bpf_link_ops bpf_struct_ops_link_lops = { + .release = bpf_struct_ops_link_release, + .dealloc = bpf_struct_ops_link_dealloc, +}; + +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, + struct bpf_tramp_link *link, const struct btf_func_model *model, void *image, void *image_end) { u32 flags; - tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; - tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + tlinks[BPF_TRAMP_FENTRY].links[0] = link; + tlinks[BPF_TRAMP_FENTRY].nr_links = 1; flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; return arch_prepare_bpf_trampoline(NULL, image, image_end, - model, flags, tprogs, NULL); + model, flags, tlinks, NULL); } static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, @@ -338,7 +354,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_struct_ops_value *uvalue, *kvalue; const struct btf_member *member; const struct btf_type *t = st_ops->type; - struct bpf_tramp_progs *tprogs = NULL; + struct bpf_tramp_links *tlinks = NULL; void *udata, *kdata; int prog_fd, err = 0; void *image, *image_end; @@ -362,8 +378,8 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (uvalue->state || refcount_read(&uvalue->refcnt)) return -EINVAL; - tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); - if (!tprogs) + tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); + if (!tlinks) return -ENOMEM; uvalue = (struct bpf_struct_ops_value *)st_map->uvalue; @@ -386,6 +402,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; + struct bpf_tramp_link *link; u32 moff; moff = __btf_member_bit_offset(t, member) / 8; @@ -439,16 +456,26 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, err = PTR_ERR(prog); goto reset_unlock; } - st_map->progs[i] = prog; if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || prog->aux->attach_btf_id != st_ops->type_id || prog->expected_attach_type != i) { + bpf_prog_put(prog); err = -EINVAL; goto reset_unlock; } - err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + bpf_prog_put(prog); + err = -ENOMEM; + goto reset_unlock; + } + bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, + &bpf_struct_ops_link_lops, prog); + st_map->links[i] = &link->link; + + err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[i], image, image_end); if (err < 0) @@ -491,7 +518,7 @@ reset_unlock: memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); unlock: - kfree(tprogs); + kfree(tlinks); mutex_unlock(&st_map->lock); return err; } @@ -546,9 +573,9 @@ static void bpf_struct_ops_map_free(struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - if (st_map->progs) + if (st_map->links) bpf_struct_ops_map_put_progs(st_map); - bpf_map_area_free(st_map->progs); + bpf_map_area_free(st_map->links); bpf_jit_free_exec(st_map->image); bpf_map_area_free(st_map->uvalue); bpf_map_area_free(st_map); @@ -597,11 +624,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) map = &st_map->map; st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); - st_map->progs = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *), + st_map->links = + bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), NUMA_NO_NODE); st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); - if (!st_map->uvalue || !st_map->progs || !st_map->image) { + if (!st_map->uvalue || !st_map->links || !st_map->image) { bpf_struct_ops_map_free(map); return ERR_PTR(-ENOMEM); } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2f0b0440131c..7bccaa4646e5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -202,6 +202,8 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_XDP, BTF_KFUNC_HOOK_TC, BTF_KFUNC_HOOK_STRUCT_OPS, + BTF_KFUNC_HOOK_TRACING, + BTF_KFUNC_HOOK_SYSCALL, BTF_KFUNC_HOOK_MAX, }; @@ -7110,6 +7112,10 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) return BTF_KFUNC_HOOK_TC; case BPF_PROG_TYPE_STRUCT_OPS: return BTF_KFUNC_HOOK_STRUCT_OPS; + case BPF_PROG_TYPE_TRACING: + return BTF_KFUNC_HOOK_TRACING; + case BPF_PROG_TYPE_SYSCALL: + return BTF_KFUNC_HOOK_SYSCALL; default: return BTF_KFUNC_HOOK_MAX; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 13e9dbeeedf3..cacd8684c3c4 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -873,7 +873,7 @@ static size_t select_bpf_prog_pack_size(void) return size; } -static struct bpf_prog_pack *alloc_new_pack(void) +static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; @@ -886,6 +886,7 @@ static struct bpf_prog_pack *alloc_new_pack(void) kfree(pack); return NULL; } + bpf_fill_ill_insns(pack->ptr, bpf_prog_pack_size); bitmap_zero(pack->bitmap, bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE); list_add_tail(&pack->list, &pack_list); @@ -895,7 +896,7 @@ static struct bpf_prog_pack *alloc_new_pack(void) return pack; } -static void *bpf_prog_pack_alloc(u32 size) +static void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) { unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); struct bpf_prog_pack *pack; @@ -910,6 +911,7 @@ static void *bpf_prog_pack_alloc(u32 size) size = round_up(size, PAGE_SIZE); ptr = module_alloc(size); if (ptr) { + bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); set_memory_ro((unsigned long)ptr, size / PAGE_SIZE); set_memory_x((unsigned long)ptr, size / PAGE_SIZE); @@ -923,7 +925,7 @@ static void *bpf_prog_pack_alloc(u32 size) goto found_free_area; } - pack = alloc_new_pack(); + pack = alloc_new_pack(bpf_fill_ill_insns); if (!pack) goto out; @@ -966,6 +968,9 @@ static void bpf_prog_pack_free(struct bpf_binary_header *hdr) nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); pos = ((unsigned long)hdr - (unsigned long)pack_ptr) >> BPF_PROG_CHUNK_SHIFT; + WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size), + "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); + bitmap_clear(pack->bitmap, pos, nbits); if (bitmap_find_next_zero_area(pack->bitmap, bpf_prog_chunk_count(), 0, bpf_prog_chunk_count(), 0) == 0) { @@ -1102,7 +1107,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, if (bpf_jit_charge_modmem(size)) return NULL; - ro_header = bpf_prog_pack_alloc(size); + ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns); if (!ro_header) { bpf_jit_uncharge_modmem(size); return NULL; @@ -1434,6 +1439,16 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { + if (bpf_pseudo_func(insn)) { + /* ld_imm64 with an address of bpf subprog is not + * a user controlled constant. Don't randomize it, + * since it will conflict with jit_subprogs() logic. + */ + insn++; + i++; + continue; + } + /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. @@ -2619,6 +2634,7 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; +const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; @@ -2727,6 +2743,11 @@ void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len) return ERR_PTR(-ENOTSUPP); } +int __weak bpf_arch_text_invalidate(void *dst, size_t len) +{ + return -ENOTSUPP; +} + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3e00e62b2218..17fb69c0e0dc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -140,7 +140,7 @@ static inline bool htab_use_raw_lock(const struct bpf_htab *htab) static void htab_init_buckets(struct bpf_htab *htab) { - unsigned i; + unsigned int i; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); @@ -1627,7 +1627,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, void __user *uvalues = u64_to_user_ptr(attr->batch.values); void __user *ukeys = u64_to_user_ptr(attr->batch.keys); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); - u32 batch, max_count, size, bucket_size; + u32 batch, max_count, size, bucket_size, map_id; struct htab_elem *node_to_free = NULL; u64 elem_map_flags, map_flags; struct hlist_nulls_head *head; @@ -1752,6 +1752,14 @@ again_nocopy: } } else { value = l->key + roundup_key_size; + if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + struct bpf_map **inner_map = value; + + /* Actual value is the id of the inner map */ + map_id = map->ops->map_fd_sys_lookup_elem(*inner_map); + value = &map_id; + } + if (elem_map_flags & BPF_F_LOCK) copy_map_value_locked(map, dst_val, value, true); @@ -2191,6 +2199,20 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static void *htab_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct htab_elem *l; + + if (cpu >= nr_cpu_ids) + return NULL; + + l = __htab_map_lookup_elem(map, key); + if (l) + return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu); + else + return NULL; +} + static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); @@ -2203,6 +2225,22 @@ static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static void *htab_lru_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu) +{ + struct htab_elem *l; + + if (cpu >= nr_cpu_ids) + return NULL; + + l = __htab_map_lookup_elem(map, key); + if (l) { + bpf_lru_node_set_ref(&l->lru_node); + return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu); + } + + return NULL; +} + int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) { struct htab_elem *l; @@ -2292,6 +2330,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, + .map_lookup_percpu_elem = htab_percpu_map_lookup_percpu_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, @@ -2310,6 +2349,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_lookup_percpu_elem = htab_lru_percpu_map_lookup_percpu_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, @@ -2450,5 +2490,6 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = htab_of_map_gen_lookup, .map_check_btf = map_check_no_btf, + BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3e709fed5306..225806a02efb 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -103,7 +103,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) @@ -116,7 +116,23 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, +}; + +BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu) +{ + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu); +} + +const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto = { + .func = bpf_map_lookup_percpu_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_KEY, + .arg3_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_get_prandom_u32_proto = { @@ -1396,6 +1412,169 @@ const struct bpf_func_proto bpf_kptr_xchg_proto = { .arg2_btf_id = BPF_PTR_POISON, }; +/* Since the upper 8 bits of dynptr->size is reserved, the + * maximum supported size is 2^24 - 1. + */ +#define DYNPTR_MAX_SIZE ((1UL << 24) - 1) +#define DYNPTR_TYPE_SHIFT 28 +#define DYNPTR_SIZE_MASK 0xFFFFFF +#define DYNPTR_RDONLY_BIT BIT(31) + +static bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr) +{ + return ptr->size & DYNPTR_RDONLY_BIT; +} + +static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_type type) +{ + ptr->size |= type << DYNPTR_TYPE_SHIFT; +} + +static u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr) +{ + return ptr->size & DYNPTR_SIZE_MASK; +} + +int bpf_dynptr_check_size(u32 size) +{ + return size > DYNPTR_MAX_SIZE ? -E2BIG : 0; +} + +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size) +{ + ptr->data = data; + ptr->offset = offset; + ptr->size = size; + bpf_dynptr_set_type(ptr, type); +} + +void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) +{ + memset(ptr, 0, sizeof(*ptr)); +} + +static int bpf_dynptr_check_off_len(struct bpf_dynptr_kern *ptr, u32 offset, u32 len) +{ + u32 size = bpf_dynptr_get_size(ptr); + + if (len > size || offset > size - len) + return -E2BIG; + + return 0; +} + +BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr) +{ + int err; + + err = bpf_dynptr_check_size(size); + if (err) + goto error; + + /* flags is currently unsupported */ + if (flags) { + err = -EINVAL; + goto error; + } + + bpf_dynptr_init(ptr, data, BPF_DYNPTR_TYPE_LOCAL, 0, size); + + return 0; + +error: + bpf_dynptr_set_null(ptr); + return err; +} + +const struct bpf_func_proto bpf_dynptr_from_mem_proto = { + .func = bpf_dynptr_from_mem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, +}; + +BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset) +{ + int err; + + if (!src->data) + return -EINVAL; + + err = bpf_dynptr_check_off_len(src, offset, len); + if (err) + return err; + + memcpy(dst, src->data + src->offset + offset, len); + + return 0; +} + +const struct bpf_func_proto bpf_dynptr_read_proto = { + .func = bpf_dynptr_read, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_PTR_TO_DYNPTR, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len) +{ + int err; + + if (!dst->data || bpf_dynptr_is_rdonly(dst)) + return -EINVAL; + + err = bpf_dynptr_check_off_len(dst, offset, len); + if (err) + return err; + + memcpy(dst->data + dst->offset + offset, src, len); + + return 0; +} + +const struct bpf_func_proto bpf_dynptr_write_proto = { + .func = bpf_dynptr_write, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_DYNPTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, +}; + +BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) +{ + int err; + + if (!ptr->data) + return 0; + + err = bpf_dynptr_check_off_len(ptr, offset, len); + if (err) + return 0; + + if (bpf_dynptr_is_rdonly(ptr)) + return 0; + + return (unsigned long)(ptr->data + ptr->offset + offset); +} + +const struct bpf_func_proto bpf_dynptr_data_proto = { + .func = bpf_dynptr_data, + .gpl_only = false, + .ret_type = RET_PTR_TO_DYNPTR_MEM_OR_NULL, + .arg1_type = ARG_PTR_TO_DYNPTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, +}; + const struct bpf_func_proto bpf_get_current_task_proto __weak; const struct bpf_func_proto bpf_get_current_task_btf_proto __weak; const struct bpf_func_proto bpf_probe_read_user_proto __weak; @@ -1420,6 +1599,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; + case BPF_FUNC_map_lookup_percpu_elem: + return &bpf_map_lookup_percpu_elem_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: @@ -1442,12 +1623,26 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ringbuf_discard_proto; case BPF_FUNC_ringbuf_query: return &bpf_ringbuf_query_proto; + case BPF_FUNC_ringbuf_reserve_dynptr: + return &bpf_ringbuf_reserve_dynptr_proto; + case BPF_FUNC_ringbuf_submit_dynptr: + return &bpf_ringbuf_submit_dynptr_proto; + case BPF_FUNC_ringbuf_discard_dynptr: + return &bpf_ringbuf_discard_dynptr_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; case BPF_FUNC_loop: return &bpf_loop_proto; case BPF_FUNC_strncmp: return &bpf_strncmp_proto; + case BPF_FUNC_dynptr_from_mem: + return &bpf_dynptr_from_mem_proto; + case BPF_FUNC_dynptr_read: + return &bpf_dynptr_read_proto; + case BPF_FUNC_dynptr_write: + return &bpf_dynptr_write_proto; + case BPF_FUNC_dynptr_data: + return &bpf_dynptr_data_proto; default: break; } diff --git a/kernel/bpf/link_iter.c b/kernel/bpf/link_iter.c new file mode 100644 index 000000000000..fec8005a121c --- /dev/null +++ b/kernel/bpf/link_iter.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2022 Red Hat, Inc. */ +#include <linux/bpf.h> +#include <linux/fs.h> +#include <linux/filter.h> +#include <linux/kernel.h> +#include <linux/btf_ids.h> + +struct bpf_iter_seq_link_info { + u32 link_id; +}; + +static void *bpf_link_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_link_info *info = seq->private; + struct bpf_link *link; + + link = bpf_link_get_curr_or_next(&info->link_id); + if (!link) + return NULL; + + if (*pos == 0) + ++*pos; + return link; +} + +static void *bpf_link_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_link_info *info = seq->private; + + ++*pos; + ++info->link_id; + bpf_link_put((struct bpf_link *)v); + return bpf_link_get_curr_or_next(&info->link_id); +} + +struct bpf_iter__bpf_link { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_link *, link); +}; + +DEFINE_BPF_ITER_FUNC(bpf_link, struct bpf_iter_meta *meta, struct bpf_link *link) + +static int __bpf_link_seq_show(struct seq_file *seq, void *v, bool in_stop) +{ + struct bpf_iter__bpf_link ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int ret = 0; + + ctx.meta = &meta; + ctx.link = v; + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (prog) + ret = bpf_iter_run_prog(prog, &ctx); + + return ret; +} + +static int bpf_link_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_link_seq_show(seq, v, false); +} + +static void bpf_link_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__bpf_link_seq_show(seq, v, true); + else + bpf_link_put((struct bpf_link *)v); +} + +static const struct seq_operations bpf_link_seq_ops = { + .start = bpf_link_seq_start, + .next = bpf_link_seq_next, + .stop = bpf_link_seq_stop, + .show = bpf_link_seq_show, +}; + +BTF_ID_LIST(btf_bpf_link_id) +BTF_ID(struct, bpf_link) + +static const struct bpf_iter_seq_info bpf_link_seq_info = { + .seq_ops = &bpf_link_seq_ops, + .init_seq_private = NULL, + .fini_seq_private = NULL, + .seq_priv_size = sizeof(struct bpf_iter_seq_link_info), +}; + +static struct bpf_iter_reg bpf_link_reg_info = { + .target = "bpf_link", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__bpf_link, link), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &bpf_link_seq_info, +}; + +static int __init bpf_link_iter_init(void) +{ + bpf_link_reg_info.ctx_arg_info[0].btf_id = *btf_bpf_link_id; + return bpf_iter_reg_target(&bpf_link_reg_info); +} + +late_initcall(bpf_link_iter_init); diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 311264ab80c4..ded4faeca192 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -475,3 +475,81 @@ const struct bpf_func_proto bpf_ringbuf_query_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; + +BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags, + struct bpf_dynptr_kern *, ptr) +{ + struct bpf_ringbuf_map *rb_map; + void *sample; + int err; + + if (unlikely(flags)) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + err = bpf_dynptr_check_size(size); + if (err) { + bpf_dynptr_set_null(ptr); + return err; + } + + rb_map = container_of(map, struct bpf_ringbuf_map, map); + + sample = __bpf_ringbuf_reserve(rb_map->rb, size); + if (!sample) { + bpf_dynptr_set_null(ptr); + return -EINVAL; + } + + bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { + .func = bpf_ringbuf_reserve_dynptr, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, +}; + +BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, false /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = { + .func = bpf_ringbuf_submit_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) +{ + if (!ptr->data) + return 0; + + bpf_ringbuf_commit(ptr->data, flags, true /* discard */); + + bpf_dynptr_set_null(ptr); + + return 0; +} + +const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = { + .func = bpf_ringbuf_discard_dynptr, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE, + .arg2_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e0aead17dff4..2b69306d3c6e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2864,19 +2864,12 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd) } EXPORT_SYMBOL(bpf_link_get_from_fd); -struct bpf_tracing_link { - struct bpf_link link; - enum bpf_attach_type attach_type; - struct bpf_trampoline *trampoline; - struct bpf_prog *tgt_prog; -}; - static void bpf_tracing_link_release(struct bpf_link *link) { struct bpf_tracing_link *tr_link = - container_of(link, struct bpf_tracing_link, link); + container_of(link, struct bpf_tracing_link, link.link); - WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog, + WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, tr_link->trampoline)); bpf_trampoline_put(tr_link->trampoline); @@ -2889,7 +2882,7 @@ static void bpf_tracing_link_release(struct bpf_link *link) static void bpf_tracing_link_dealloc(struct bpf_link *link) |
