* is not active yet. The JIT will do the final fixup * before setting it stable. The various * poke->tailcall_target_stable are successively * activated, so tail call updates can arrive from here * while JIT is still finishing its final fixup for * non-activated poke entries. * 3) On program teardown, the program's kallsym entry gets * removed out of RCU callback, but we can only untrack * from sleepable context, therefore bpf_arch_text_poke() * might not see that this is in BPF text section and * bails out with -EINVAL. As these are unreachable since * RCU grace period already passed, we simply skip them. * 4) Also programs reaching refcount of zero while patching * is in progress is okay since we're protected under * poke_mutex and untrack the programs before the JIT * buffer is freed. When we're still in the middle of * patching and suddenly kallsyms entry of the program * gets evicted, we just skip the rest which is fine due * to point 3). * 5) Any other error happening below from bpf_arch_text_poke() * is a unexpected bug. */ if (!READ_ONCE(poke->tailcall_target_stable)) continue; if (poke->reason != BPF_POKE_REASON_TAIL_CALL) continue; if (poke->tail_call.map != map || poke->tail_call.key != key) continue; old_bypass_addr = old ? NULL : poke->bypass_addr; old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; if (new) { ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, old_addr, new_addr); BUG_ON(ret < 0 && ret != -EINVAL); if (!old) { ret = bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, poke->bypass_addr, NULL); BUG_ON(ret < 0 && ret != -EINVAL); } } else { ret = bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, old_bypass_addr, poke->bypass_addr); BUG_ON(ret < 0 && ret != -EINVAL); /* let other CPUs finish the execution of program * so that it will not possible to expose them * to invalid nop, stack unwind, nop state */ if (!ret) synchronize_rcu(); ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, old_addr, NULL); BUG_ON(ret < 0 && ret != -EINVAL); } } }} static void prog_array_map_clear_deferred(struct work_struct *work){ struct bpf_map *map = container_of(work, struct bpf_array_aux, work)->map; bpf_fd_array_map_clear(map); bpf_map_put(map);} static void prog_array_map_clear(struct bpf_map *map){ struct bpf_array_aux *aux = container_of(map, struct bpf_array, map)->aux; bpf_map_inc(map); schedule_work(&aux->work);} static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr){ struct bpf_array_aux *aux; struct bpf_map *map; aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT); if (!aux) return ERR_PTR(-ENOMEM); INIT_WORK(&aux->work, prog_array_map_clear_deferred); INIT_LIST_HEAD(&aux->poke_progs); mutex_init(&aux->poke_mutex); map = array_map_alloc(attr); if (IS_ERR(map)) { kfree(aux); return map; } container_of(map, struct bpf_array, map)->aux = aux; aux->map = map; return map;} static void prog_array_map_free(struct bpf_map *map){ struct prog_poke_elem *elem, *tmp; struct bpf_array_aux *aux; aux = container_of(map, struct bpf_array, map)->aux; list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) { list_del_init(&elem->list); kfree(elem); } kfree(aux); fd_array_map_free(map);} /* prog_array->aux->{type,jited} is a runtime binding. * Doing static check alone in the verifier is not enough. * Thus, prog_array_map cannot be used as an inner_map * and map_meta_equal is not implemented. */const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = prog_array_map_alloc, .map_free = prog_array_map_free, .map_poke_track = prog_array_map_poke_track, .map_poke_untrack = prog_array_map_poke_untrack, .map_poke_run = prog_array_map_poke_run, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = prog_fd_array_get_ptr, .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = prog_array_map_clear, .map_seq_show_elem = prog_array_map_seq_show_elem, .map_btf_id = &array_map_btf_ids[0],}; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, struct file *map_file){ struct bpf_event_entry *ee; ee = kzalloc(sizeof(*ee), GFP_ATOMIC); if (ee) { ee->event = perf_file->private_data; ee->perf_file = perf_file; ee->map_file = map_file; } return ee;} static void __bpf_event_entry_free(struct rcu_head *rcu){ struct bpf_event_entry *ee; ee = container_of(rcu, struct bpf_event_entry, rcu); fput(ee->perf_file); kfree(ee);} static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee){ call_rcu(&ee->rcu, __bpf_event_entry_free);} static void *perf_event_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd){ struct bpf_event_entry *ee; struct perf_event *event; struct file *perf_file; u64 value; perf_file = perf_event_get(fd); if (IS_ERR(perf_file)) return perf_file; ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP) goto err_out; ee = bpf_event_entry_gen(perf_file, map_file); if (ee) return ee; ee = ERR_PTR(-ENOMEM);err_out: fput(perf_file); return ee;} static void perf_event_fd_array_put_ptr(void *ptr){ bpf_event_entry_free_rcu(ptr);} static void perf_event_fd_array_release(struct bpf_map *map, struct file *map_file){ struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_event_entry *ee; int i; if (map->map_flags & BPF_F_PRESERVE_ELEMS) return; rcu_read_lock(); for (i = 0; i < array->map.max_entries; i++) { ee = READ_ONCE(array->ptrs[i]); if (ee && ee->map_file == map_file) fd_array_map_delete_elem(map, &i); } rcu_read_unlock();} static void perf_event_fd_array_map_free(struct bpf_map *map){ if (map->map_flags & BPF_F_PRESERVE_ELEMS) bpf_fd_array_map_clear(map); fd_array_map_free(map);} const struct bpf_map_ops perf_event_array_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = perf_event_fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = perf_event_fd_array_get_ptr, .map_fd_put_ptr = perf_event_fd_array_put_ptr, .map_release = perf_event_fd_array_release, .map_check_btf = map_check_no_btf, .map_btf_id = &array_map_btf_ids[0],}; #ifdef CONFIG_CGROUPSstatic void *cgroup_fd_array_get_ptr(struct bpf_map *map, struct file *map_file /* not used */, int fd){ return cgroup_get_from_fd(fd);} static void cgroup_fd_array_put_ptr(void *ptr){ /* cgroup_put free cgrp after a rcu grace period */ cgroup_put(ptr);} static void cgroup_fd_array_free(struct bpf_map *map){ bpf_fd_array_map_clear(map); fd_array_map_free(map);} const struct bpf_map_ops cgroup_array_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = cgroup_fd_array_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = cgroup_fd_array_get_ptr, .map_fd_put_ptr = cgroup_fd_array_put_ptr, .map_check_btf = map_check_no_btf, .map_btf_id = &array_map_btf_ids[0],};#endif static struct bpf_map *array_of_map_alloc(union bpf_attr *attr){ struct bpf_map *map, *inner_map_meta; inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd); if (IS_ERR(inner_map_meta)) return inner_map_meta; map = array_map_alloc(attr); if (IS_ERR(map)) { bpf_map_meta_free(inner_map_meta); return map; } map->inner_map_meta = inner_map_meta; return map;} static void array_of_map_free(struct bpf_map *map){ /* map->inner_map_meta is only accessed by syscall which * is protected by fdget/fdput. */ bpf_map_meta_free(map->inner_map_meta); bpf_fd_array_map_clear(map); fd_array_map_free(map);} static void *array_of_map_lookup_elem(struct bpf_map *map, void *key){ struct bpf_map **inner_map = array_map_lookup_elem(map, key); if (!inner_map) return NULL; return READ_ONCE(*inner_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); u32 elem_size = round_up(map->value_size, 8); struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; const int map_ptr = BPF_REG_1; const int index = BPF_REG_2; *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) { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6); *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); } else { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); } if (is_power_of_2(elem_size)) *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); else *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *insn++ = BPF_MOV64_IMM(ret, 0); return insn - insn_buf;} const struct bpf_map_ops array_of_maps_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_of_map_alloc, .map_free = array_of_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = array_of_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = bpf_map_fd_get_ptr, .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],};Lines 1001–1367 of 1367. Previous lines
* is not active yet. The JIT will do the final fixup * before setting it stable. The various * poke->tailcall_target_stable are successively * activated, so tail call updates can arrive from here * while JIT is still finishing its final fixup for * non-activated poke entries. * 3) On program teardown, the program's kallsym entry gets * removed out of RCU callback, but we can only untrack * from sleepable context, therefore bpf_arch_text_poke() * might not see that this is in BPF text section and * bails out with -EINVAL. As these are unreachable since * RCU grace period already passed, we simply skip them. * 4) Also programs reaching refcount of zero while patching * is in progress is okay since we're protected under * poke_mutex and untrack the programs before the JIT * buffer is freed. When we're still in the middle of * patching and suddenly kallsyms entry of the program * gets evicted, we just skip the rest which is fine due * to point 3). * 5) Any other error happening below from bpf_arch_text_poke() * is a unexpected bug. */ if (!READ_ONCE(poke->tailcall_target_stable)) continue; if (poke->reason != BPF_POKE_REASON_TAIL_CALL) continue; if (poke->tail_call.map != map || poke->tail_call.key != key) continue; old_bypass_addr = old ? NULL : poke->bypass_addr; old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; if (new) { ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, old_addr, new_addr); BUG_ON(ret < 0 && ret != -EINVAL); if (!old) { ret = bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, poke->bypass_addr, NULL); BUG_ON(ret < 0 && ret != -EINVAL); } } else { ret = bpf_arch_text_poke(poke->tailcall_bypass, BPF_MOD_JUMP, old_bypass_addr, poke->bypass_addr); BUG_ON(ret < 0 && ret != -EINVAL); /* let other CPUs finish the execution of program * so that it will not possible to expose them * to invalid nop, stack unwind, nop state */ if (!ret) synchronize_rcu(); ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP, old_addr, NULL); BUG_ON(ret < 0 && ret != -EINVAL); } } } } static void prog_array_map_clear_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_array_aux, work)->map; bpf_fd_array_map_clear(map); bpf_map_put(map); } static void prog_array_map_clear(struct bpf_map *map) { struct bpf_array_aux *aux = container_of(map, struct bpf_array, map)->aux; bpf_map_inc(map); schedule_work(&aux->work); } static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) { struct bpf_array_aux *aux; struct bpf_map *map; aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT); if (!aux) return ERR_PTR(-ENOMEM); INIT_WORK(&aux->work, prog_array_map_clear_deferred); INIT_LIST_HEAD(&aux->poke_progs); mutex_init(&aux->poke_mutex); map = array_map_alloc(attr); if (IS_ERR(map)) { kfree(aux); return map; } container_of(map, struct bpf_array, map)->aux = aux; aux->map = map; return map; } static void prog_array_map_free(struct bpf_map *map) { struct prog_poke_elem *elem, *tmp; struct bpf_array_aux *aux; aux = container_of(map, struct bpf_array, map)->aux; list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) { list_del_init(&elem->list); kfree(elem); } kfree(aux); fd_array_map_free(map); } /* prog_array->aux->{type,jited} is a runtime binding. * Doing static check alone in the verifier is not enough. * Thus, prog_array_map cannot be used as an inner_map * and map_meta_equal is not implemented. */ const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = prog_array_map_alloc, .map_free = prog_array_map_free, .map_poke_track = prog_array_map_poke_track, .map_poke_untrack = prog_array_map_poke_untrack, .map_poke_run = prog_array_map_poke_run, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = prog_fd_array_get_ptr, .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = prog_array_map_clear, .map_seq_show_elem = prog_array_map_seq_show_elem, .map_btf_id = &array_map_btf_ids[0], }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, struct file *map_file) { struct bpf_event_entry *ee; ee = kzalloc(sizeof(*ee), GFP_ATOMIC); if (ee) { ee->event = perf_file->private_data; ee->perf_file = perf_file; ee->map_file = map_file; } return ee; } static void __bpf_event_entry_free(struct rcu_head *rcu) { struct bpf_event_entry *ee; ee = container_of(rcu, struct bpf_event_entry, rcu); fput(ee->perf_file); kfree(ee); } static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee) { call_rcu(&ee->rcu, __bpf_event_entry_free); } static void *perf_event_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { struct bpf_event_entry *ee; struct perf_event *event; struct file *perf_file; u64 value; perf_file = perf_event_get(fd); if (IS_ERR(perf_file)) return perf_file; ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP) goto err_out; ee = bpf_event_entry_gen(perf_file, map_file); if (ee) return ee; ee = ERR_PTR(-ENOMEM); err_out: fput(perf_file); return ee; } static void perf_event_fd_array_put_ptr(void *ptr) { bpf_event_entry_free_rcu(ptr); } static void perf_event_fd_array_release(struct bpf_map *map, struct file *map_file) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_event_entry *ee; int i; if (map->map_flags & BPF_F_PRESERVE_ELEMS) return; rcu_read_lock(); for (i = 0; i < array->map.max_entries; i++) { ee = READ_ONCE(array->ptrs[i]); if (ee && ee->map_file == map_file) fd_array_map_delete_elem(map, &i); } rcu_read_unlock(); } static void perf_event_fd_array_map_free(struct bpf_map *map) { if (map->map_flags & BPF_F_PRESERVE_ELEMS) bpf_fd_array_map_clear(map); fd_array_map_free(map); } const struct bpf_map_ops perf_event_array_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = perf_event_fd_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = perf_event_fd_array_get_ptr, .map_fd_put_ptr = perf_event_fd_array_put_ptr, .map_release = perf_event_fd_array_release, .map_check_btf = map_check_no_btf, .map_btf_id = &array_map_btf_ids[0], }; #ifdef CONFIG_CGROUPS static void *cgroup_fd_array_get_ptr(struct bpf_map *map, struct file *map_file /* not used */, int fd) { return cgroup_get_from_fd(fd); } static void cgroup_fd_array_put_ptr(void *ptr) { /* cgroup_put free cgrp after a rcu grace period */ cgroup_put(ptr); } static void cgroup_fd_array_free(struct bpf_map *map) { bpf_fd_array_map_clear(map); fd_array_map_free(map); } const struct bpf_map_ops cgroup_array_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, .map_free = cgroup_fd_array_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = cgroup_fd_array_get_ptr, .map_fd_put_ptr = cgroup_fd_array_put_ptr, .map_check_btf = map_check_no_btf, .map_btf_id = &array_map_btf_ids[0], }; #endif static struct bpf_map *array_of_map_alloc(union bpf_attr *attr) { struct bpf_map *map, *inner_map_meta; inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd); if (IS_ERR(inner_map_meta)) return inner_map_meta; map = array_map_alloc(attr); if (IS_ERR(map)) { bpf_map_meta_free(inner_map_meta); return map; } map->inner_map_meta = inner_map_meta; return map; } static void array_of_map_free(struct bpf_map *map) { /* map->inner_map_meta is only accessed by syscall which * is protected by fdget/fdput. */ bpf_map_meta_free(map->inner_map_meta); bpf_fd_array_map_clear(map); fd_array_map_free(map); } static void *array_of_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_map **inner_map = array_map_lookup_elem(map, key); if (!inner_map) return NULL; return READ_ONCE(*inner_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); u32 elem_size = round_up(map->value_size, 8); struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; const int map_ptr = BPF_REG_1; const int index = BPF_REG_2; *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) { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6); *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); } else { *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); } if (is_power_of_2(elem_size)) *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); else *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); *insn++ = BPF_MOV64_IMM(ret, 0); return insn - insn_buf; } const struct bpf_map_ops array_of_maps_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_of_map_alloc, .map_free = array_of_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = array_of_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = bpf_map_fd_get_ptr, .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], };