From patchwork Wed Nov 1 20:45:11 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Kui-Feng Lee X-Patchwork-Id: 13443050 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 AF95C10799 for ; Wed, 1 Nov 2023 20:45:35 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="hvQ+ftzB" Received: from mail-yb1-xb35.google.com (mail-yb1-xb35.google.com [IPv6:2607:f8b0:4864:20::b35]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C615510D for ; Wed, 1 Nov 2023 13:45:30 -0700 (PDT) Received: by mail-yb1-xb35.google.com with SMTP id 3f1490d57ef6-da077db5145so210042276.0 for ; Wed, 01 Nov 2023 13:45:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1698871529; x=1699476329; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=7tcX5oNAk7ZOPwWEiRwlLhoBkQ83mv+bPpii8i8xX6k=; b=hvQ+ftzBo7kuD0jaLS4vQbF2VSAXtIHl2e4OWaJljhWKkuDd4JMIBZAWdwxx2CRI6l 45NgjbrxSpu2KHtoKYgEqRaoZc4epEa5DWjlnjV3nExWqMO/20ai2p9lMr/UQKpBlxs9 lg7CxpziLz8t+bSPAFuMxHfaLF4WN5BBRjdX9sPlv1KiAy7wGRvFBpSMWhnxRL4QKhNr AK7zstiKTuSp91dNOxD8uEFQ6qm8k0sSByht5EeU2dULB78/stSrFbIYdRcIA0YC02pn uuYj/mV8iJr6kNJmkKobhbFuFmgfi8Mz16FZ/3Ya8x281Qix7K4zzgThCkeou4dXGo+k AFtg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1698871529; x=1699476329; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=7tcX5oNAk7ZOPwWEiRwlLhoBkQ83mv+bPpii8i8xX6k=; b=vsANTWrzr+w1cHJlVaj0HIdoknfK7qdiyudxOLkl6+UBc3FemaQA9E0YqpnXR+fZqi aT0N+aabxffv+GlmpMjKiXkJUzZ5CpwK0MApDc4x+Lr5UMI/cfC3h/DBZ2We9tP1+4Dg Xg2AL8MAkxGtwLvzJOBKO+TlThD6Wy0wAiff78GATQ/Ec1DCslFeVgPgCkD65AinCwFl eS/Nec06sfrcbw+zon90qvEufI/NrMaVE+70qEig4m87FvvK7Zec4zkUpnFDJy4K4KOe 70fFScGjtZ05zXDkPFo8/wCOpRsGjBeWwM7ApiKOnBAcDmCoqCZ6eYY5pwRXHn/fPVfq rahQ== X-Gm-Message-State: AOJu0YwcC6vKMSS5tsUrgAlIbCfPeY6+wGwiefEq61buwHSvm8kW444y o4bERqhgWIlAICp1xPh+6ILiPZzj2iw= X-Google-Smtp-Source: AGHT+IETLAZ4yJa/zQQlFw7PTAIw1a8xtbNgnIav/jI2CVWBbvChyi5hG4aYgcjO14fU7zqxKVgvVg== X-Received: by 2002:a25:244:0:b0:da3:b555:6474 with SMTP id 65-20020a250244000000b00da3b5556474mr3013355ybc.49.1698871529133; Wed, 01 Nov 2023 13:45:29 -0700 (PDT) Received: from kickker.attlocal.net ([2600:1700:6cf8:1240:eea0:6f66:c57d:6b7c]) by smtp.gmail.com with ESMTPSA id o83-20020a25d756000000b00da086d6921fsm342386ybg.50.2023.11.01.13.45.28 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 01 Nov 2023 13:45:28 -0700 (PDT) From: thinker.li@gmail.com To: bpf@vger.kernel.org, ast@kernel.org, martin.lau@linux.dev, song@kernel.org, kernel-team@meta.com, andrii@kernel.org, drosen@google.com Cc: sinquersw@gmail.com, kuifeng@meta.com, Kui-Feng Lee Subject: [PATCH bpf-next v9 04/12] bpf: add struct_ops_tab to btf. Date: Wed, 1 Nov 2023 13:45:11 -0700 Message-Id: <20231101204519.677870-5-thinker.li@gmail.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20231101204519.677870-1-thinker.li@gmail.com> References: <20231101204519.677870-1-thinker.li@gmail.com> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: bpf@iogearbox.net From: Kui-Feng Lee Maintain a registry of registered struct_ops types in the per-btf (module) struct_ops_tab. This registry allows for easy lookup of struct_ops types that are registered by a specific module. It is a preparation work for supporting kernel module struct_ops in a latter patch. Each struct_ops will be registered under its own kernel module btf and will be stored in the newly added btf->struct_ops_tab. The bpf verifier and bpf syscall (e.g. prog and map cmd) can find the struct_ops and its btf type/size/id... information from btf->struct_ops_tab. Signed-off-by: Kui-Feng Lee --- include/linux/btf.h | 5 +++ kernel/bpf/bpf_struct_ops.c | 24 +++++++----- kernel/bpf/btf.c | 74 +++++++++++++++++++++++++++++++++++++ 3 files changed, 94 insertions(+), 9 deletions(-) diff --git a/include/linux/btf.h b/include/linux/btf.h index c2231c64d60b..e613b6b45dc4 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -572,4 +572,9 @@ static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type return btf_type_is_struct(t); } +struct bpf_struct_ops_desc; + +const struct bpf_struct_ops_desc * +btf_get_struct_ops(struct btf *btf, u32 *ret_cnt); + #endif diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index d804801c7864..a0291877a792 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -46,6 +46,8 @@ struct bpf_struct_ops_map { * "links[]". */ void *image; + /* The owner moduler's btf. */ + struct btf *btf; /* uvalue->data stores the kernel struct * (e.g. tcp_congestion_ops) that is more useful * to userspace than the kvalue. For example, @@ -314,7 +316,7 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) } } -static int check_zero_holes(const struct btf_type *t, void *data) +static int check_zero_holes(const struct btf *btf, const struct btf_type *t, void *data) { const struct btf_member *member; u32 i, moff, msize, prev_mend = 0; @@ -326,8 +328,8 @@ static int check_zero_holes(const struct btf_type *t, void *data) memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(btf, member->type); + mtype = btf_resolve_size(btf, mtype, &msize); if (IS_ERR(mtype)) return PTR_ERR(mtype); prev_mend = moff + msize; @@ -395,12 +397,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (*(u32 *)key != 0) return -E2BIG; - err = check_zero_holes(st_ops_desc->value_type, value); + err = check_zero_holes(st_map->btf, st_ops_desc->value_type, value); if (err) return err; uvalue = value; - err = check_zero_holes(t, uvalue->data); + err = check_zero_holes(st_map->btf, t, uvalue->data); if (err) return err; @@ -436,7 +438,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, u32 moff; moff = __btf_member_bit_offset(t, member) / 8; - ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); + ptype = btf_type_resolve_ptr(st_map->btf, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) goto reset_unlock; @@ -461,8 +463,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (!ptype || !btf_type_is_func_proto(ptype)) { u32 msize; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(st_map->btf, member->type); + mtype = btf_resolve_size(st_map->btf, mtype, &msize); if (IS_ERR(mtype)) { err = PTR_ERR(mtype); goto reset_unlock; @@ -601,6 +603,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; void *value; int err; @@ -610,7 +613,8 @@ static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); if (!err) { - btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id, + btf_type_seq_show(st_map->btf, + map->btf_vmlinux_value_type_id, value, m); seq_puts(m, "\n"); } @@ -720,6 +724,8 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); } + st_map->btf = btf_vmlinux; + mutex_init(&st_map->lock); set_vm_flush_reset_perms(st_map->image); bpf_map_init_from_attr(map, attr); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 15d71d2986d3..2fd6fa0ea1f4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -241,6 +241,12 @@ struct btf_id_dtor_kfunc_tab { struct btf_id_dtor_kfunc dtors[]; }; +struct btf_struct_ops_tab { + u32 cnt; + u32 capacity; + struct bpf_struct_ops_desc ops[]; +}; + struct btf { void *data; struct btf_type **types; @@ -258,6 +264,7 @@ struct btf { struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; struct btf_struct_metas *struct_meta_tab; + struct btf_struct_ops_tab *struct_ops_tab; /* split BTF support */ struct btf *base_btf; @@ -1688,11 +1695,20 @@ static void btf_free_struct_meta_tab(struct btf *btf) btf->struct_meta_tab = NULL; } +static void btf_free_struct_ops_tab(struct btf *btf) +{ + struct btf_struct_ops_tab *tab = btf->struct_ops_tab; + + kfree(tab); + btf->struct_ops_tab = NULL; +} + static void btf_free(struct btf *btf) { btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); + btf_free_struct_ops_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); @@ -8602,3 +8618,61 @@ bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, return !strncmp(reg_name, arg_name, cmp_len); } + +static int +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops) +{ + struct btf_struct_ops_tab *tab, *new_tab; + int i; + + if (!btf) + return -ENOENT; + + /* Assume this function is called for a module when the module is + * loading. + */ + + tab = btf->struct_ops_tab; + if (!tab) { + tab = kzalloc(offsetof(struct btf_struct_ops_tab, ops[4]), + GFP_KERNEL); + if (!tab) + return -ENOMEM; + tab->capacity = 4; + btf->struct_ops_tab = tab; + } + + for (i = 0; i < tab->cnt; i++) + if (tab->ops[i].st_ops == st_ops) + return -EEXIST; + + if (tab->cnt == tab->capacity) { + new_tab = krealloc(tab, + offsetof(struct btf_struct_ops_tab, + ops[tab->capacity * 2]), + GFP_KERNEL); + if (!new_tab) + return -ENOMEM; + tab = new_tab; + tab->capacity *= 2; + btf->struct_ops_tab = tab; + } + + tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + + btf->struct_ops_tab->cnt++; + + return 0; +} + +const struct bpf_struct_ops_desc *btf_get_struct_ops(struct btf *btf, u32 *ret_cnt) +{ + if (!btf) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + *ret_cnt = btf->struct_ops_tab->cnt; + return (const struct bpf_struct_ops_desc *)btf->struct_ops_tab->ops; +} +