From patchwork Mon Aug 14 17:28:20 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yonghong Song X-Patchwork-Id: 13353130 X-Patchwork-Delegate: bpf@iogearbox.net Received: from lindbergh.monkeyblade.net (lindbergh.monkeyblade.net [23.128.96.19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 4338AC2FF for ; Mon, 14 Aug 2023 17:28:35 +0000 (UTC) Received: from 69-171-232-181.mail-mxout.facebook.com (69-171-232-181.mail-mxout.facebook.com [69.171.232.181]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C8772133 for ; Mon, 14 Aug 2023 10:28:33 -0700 (PDT) Received: by devbig309.ftw3.facebook.com (Postfix, from userid 128203) id 26A5B24C21F5B; Mon, 14 Aug 2023 10:28:20 -0700 (PDT) From: Yonghong Song To: bpf@vger.kernel.org Cc: Alexei Starovoitov , Andrii Nakryiko , Daniel Borkmann , kernel-team@fb.com, Martin KaFai Lau Subject: [PATCH bpf-next 02/15] bpf: Add BPF_KPTR_PERCPU_REF as a field type Date: Mon, 14 Aug 2023 10:28:20 -0700 Message-Id: <20230814172820.1362751-1-yonghong.song@linux.dev> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230814172809.1361446-1-yonghong.song@linux.dev> References: <20230814172809.1361446-1-yonghong.song@linux.dev> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Spam-Status: No, score=-0.3 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_BLOCKED,RDNS_DYNAMIC,SPF_HELO_PASS,SPF_SOFTFAIL, TVD_RCVD_IP autolearn=no autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net X-Patchwork-Delegate: bpf@iogearbox.net BPF_KPTR_PERCPU_REF represents a percpu field type like below struct val_t { ... fields ... }; struct t { ... struct val_t __percpu *percpu_data_ptr; ... }; where #define __percpu __attribute__((btf_type_tag("percpu"))) While BPF_KPTR_REF points to a trusted kernel object or a trusted local object, BPF_KPTR_PERCPU_REF points to a trusted local percpu object. This patch added basic support for BPF_KPTR_PERCPU_REF related to percpu field parsing, recording and free operations. BPF_KPTR_PERCPU_REF also supports the same map types as BPF_KPTR_REF does. Note that unlike a local kptr, it is possible that a BPF_KTPR_PERCUP_REF struct may not contain any special fields like other kptr, bpf_spin_lock, bpf_list_head, etc. Signed-off-by: Yonghong Song --- include/linux/bpf.h | 18 ++++++++++++------ kernel/bpf/btf.c | 5 +++++ kernel/bpf/syscall.c | 7 ++++++- 3 files changed, 23 insertions(+), 7 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 60e80e90c37d..e6348fd0a785 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -180,14 +180,15 @@ enum btf_field_type { BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), - BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, - BPF_LIST_HEAD = (1 << 4), - BPF_LIST_NODE = (1 << 5), - BPF_RB_ROOT = (1 << 6), - BPF_RB_NODE = (1 << 7), + BPF_KPTR_PERCPU_REF = (1 << 4), + BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU_REF, + BPF_LIST_HEAD = (1 << 5), + BPF_LIST_NODE = (1 << 6), + BPF_RB_ROOT = (1 << 7), + BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | BPF_RB_NODE | BPF_RB_ROOT, - BPF_REFCOUNT = (1 << 8), + BPF_REFCOUNT = (1 << 9), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -300,6 +301,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; + case BPF_KPTR_PERCPU_REF: + return "kptr_percpu"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: @@ -325,6 +328,7 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); @@ -351,6 +355,7 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); @@ -389,6 +394,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) case BPF_TIMER: case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: break; default: WARN_ON_ONCE(1); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 249657c466dd..bc1792edc64e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3293,6 +3293,8 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, type = BPF_KPTR_UNREF; else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) type = BPF_KPTR_REF; + else if (!strcmp("percpu", __btf_name_by_offset(btf, t->name_off))) + type = BPF_KPTR_PERCPU_REF; else return -EINVAL; @@ -3457,6 +3459,7 @@ static int btf_find_struct_field(const struct btf *btf, break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: ret = btf_find_kptr(btf, member_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3523,6 +3526,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: ret = btf_find_kptr(btf, var_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3783,6 +3787,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]); if (ret < 0) goto end; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7f4e8c357a6a..1c30b6ee84d4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -514,6 +514,7 @@ void btf_record_free(struct btf_record *rec) switch (rec->fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: if (rec->fields[i].kptr.module) module_put(rec->fields[i].kptr.module); btf_put(rec->fields[i].kptr.btf); @@ -560,6 +561,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) switch (fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: btf_get(fields[i].kptr.btf); if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { ret = -ENXIO; @@ -650,6 +652,7 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) WRITE_ONCE(*(u64 *)field_ptr, 0); break; case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0); if (!xchgd_field) break; @@ -657,7 +660,8 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) if (!btf_is_kernel(field->kptr.btf)) { pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, field->kptr.btf_id); - WARN_ON_ONCE(!pointee_struct_meta); + if (field->type != BPF_KPTR_PERCPU_REF) + WARN_ON_ONCE(!pointee_struct_meta); migrate_disable(); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? pointee_struct_meta->record : @@ -1046,6 +1050,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU_REF: case BPF_REFCOUNT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&