From patchwork Fri Feb 19 23:58:31 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Cong Wang X-Patchwork-Id: 385530 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-15.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI, SPF_HELO_NONE, SPF_PASS, URIBL_BLOCKED, USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 54A20C433E9 for ; Fri, 19 Feb 2021 23:59:45 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 3161964EE3 for ; Fri, 19 Feb 2021 23:59:45 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229810AbhBSX7e (ORCPT ); Fri, 19 Feb 2021 18:59:34 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52082 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229762AbhBSX70 (ORCPT ); Fri, 19 Feb 2021 18:59:26 -0500 Received: from mail-ot1-x329.google.com (mail-ot1-x329.google.com [IPv6:2607:f8b0:4864:20::329]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CF38DC06178B; Fri, 19 Feb 2021 15:58:45 -0800 (PST) Received: by mail-ot1-x329.google.com with SMTP id s107so6684553otb.8; Fri, 19 Feb 2021 15:58:45 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=Cn214jZGzgjFbft7eNgUOtSG+SxXEwz3c8kvQYZqNKs=; b=AuGqKE0jfE9wj48kupEajlfnSeqYyQtq11DssZg8pvGWHtw0v/vL86vwSJpZ7vBYwK WO66jy8yN+alDJxNXLQCYd6XaYqXMpqw1LDW7zqVO+8Akyf9fWT6lOk0YSFl/+1yBsbV igMVowixAToxRpcv2Sh6rCDGtZ/Ga75/sIptYm1YYq2aaDSplBx7E4EItDJM91lstdvy KvUv1FVpwPq/cxuEn4EXmTi3oCEhq1KvW+q3lXD1dw9NQIDeENwxWGmMII9nWyJR7yH4 ykBiJ6+9J9qUCdH+xpUXZisOfrus15klIZ0ITc10YkZdLvrkbFU6w91W5G/o4PMURI98 /raw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=Cn214jZGzgjFbft7eNgUOtSG+SxXEwz3c8kvQYZqNKs=; b=Sg21elZqzXxpTzUQx7+aEz9Xk9i/0tfbVZtuTKOboYy4laXQoUN7An4PgDcmpYuDNe QP6LoDdW4/XY8R0nqkH/A+4mqM7W/axmoug6B/7Z3r+ZXT/hRi5ApC9aDqkz4lbsiHoh FXee5Unh3+MZnkgndh7YfdU1puyHjDzchrXY6IkFQx7GpMJkwvnqDXMy8q4NwzWuvcUh NqrFislOdxzKqk6cEZa3ylnj1H8qUb3cUeJ+7z/pqRSVCGiz85aGEJskpRFs/FCcdO0m PM20ejgq1RCU8BQ7q0ZepZAbw9qZhu2fvvSb851Ru+B0f3Furv1JetCyUDXhHYJbwO69 t8/A== X-Gm-Message-State: AOAM530HFBOt1dwVAWpwK05Rn4OTXlbbxnDxwIG/NQZ6XQTVX2ju7FHP jzTu07GqWLHqpcgymg+pe0oSNWleISQ/Pw== X-Google-Smtp-Source: ABdhPJyFGXOesZUPKVW24/UgaTAY2kArOrIsSXv3cCel1b6RKeMZvRtoIkGV+4Uxlrqob6C5rB2bYQ== X-Received: by 2002:a9d:4595:: with SMTP id x21mr8865986ote.32.1613779125064; Fri, 19 Feb 2021 15:58:45 -0800 (PST) Received: from unknown.attlocal.net ([2600:1700:65a0:ab60:1d72:18:7c76:92e4]) by smtp.gmail.com with ESMTPSA id h11sm2064186ooj.36.2021.02.19.15.58.43 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 19 Feb 2021 15:58:44 -0800 (PST) From: Cong Wang To: netdev@vger.kernel.org Cc: bpf@vger.kernel.org, duanxiongchun@bytedance.com, wangdongdong.6@bytedance.com, jiang.wang@bytedance.com, Cong Wang , Jakub Sitnicki , Daniel Borkmann , Lorenz Bauer , John Fastabend Subject: [Patch bpf-next v5 3/8] bpf: compute data_end dynamically with JIT code Date: Fri, 19 Feb 2021 15:58:31 -0800 Message-Id: <20210219235836.100416-4-xiyou.wangcong@gmail.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210219235836.100416-1-xiyou.wangcong@gmail.com> References: <20210219235836.100416-1-xiyou.wangcong@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Cong Wang Currently, we compute ->data_end with a compile-time constant offset of skb. But as Jakub pointed out, we can actually compute it in eBPF JIT code at run-time, so that we can competely get rid of ->data_end. This is similar to skb_shinfo(skb) computation in bpf_convert_shinfo_access(). Suggested-by: Jakub Sitnicki Cc: Daniel Borkmann Cc: Lorenz Bauer Acked-by: John Fastabend Acked-by: Jakub Sitnicki Signed-off-by: Cong Wang --- include/net/tcp.h | 6 ------ net/core/filter.c | 48 +++++++++++++++++++++++++++-------------------- net/core/skmsg.c | 1 - 3 files changed, 28 insertions(+), 27 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index c00e125dcfb9..947ef5da6867 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -886,18 +886,12 @@ struct tcp_skb_cb { struct { __u32 flags; struct sock *sk_redir; - void *data_end; } bpf; }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) -static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) -{ - TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); -} - static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; diff --git a/net/core/filter.c b/net/core/filter.c index adfdad234674..13bcf248ee7b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1863,10 +1863,7 @@ static const struct bpf_func_proto bpf_sk_fullsock_proto = { static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { - int err = __bpf_try_make_writable(skb, write_len); - - bpf_compute_data_end_sk_skb(skb); - return err; + return __bpf_try_make_writable(skb, write_len); } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) @@ -3577,7 +3574,6 @@ BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, return -ENOMEM; __skb_pull(skb, len_diff_abs); } - bpf_compute_data_end_sk_skb(skb); if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); @@ -3742,10 +3738,7 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { - int ret = __bpf_skb_change_tail(skb, new_len, flags); - - bpf_compute_data_end_sk_skb(skb); - return ret; + return __bpf_skb_change_tail(skb, new_len, flags); } static const struct bpf_func_proto sk_skb_change_tail_proto = { @@ -3808,10 +3801,7 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { - int ret = __bpf_skb_change_head(skb, head_room, flags); - - bpf_compute_data_end_sk_skb(skb); - return ret; + return __bpf_skb_change_head(skb, head_room, flags); } static const struct bpf_func_proto sk_skb_change_head_proto = { @@ -9655,22 +9645,40 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +/* data_end = skb->data + skb_headlen() */ +static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, + struct bpf_insn *insn) +{ + /* si->dst_reg = skb->data */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, data)); + /* AX = skb->len */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, len)); + /* si->dst_reg = skb->data + skb->len */ + *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + /* AX = skb->data_len */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, data_len)); + /* si->dst_reg = skb->data + skb->len - skb->data_len */ + *insn++ = BPF_ALU64_REG(BPF_SUB, si->dst_reg, BPF_REG_AX); + + return insn; +} + static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; - int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): - off = si->off; - off -= offsetof(struct __sk_buff, data_end); - off += offsetof(struct sk_buff, cb); - off += offsetof(struct tcp_skb_cb, bpf.data_end); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, - si->src_reg, off); + insn = bpf_convert_data_end_access(si, insn); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 7f400d044cda..2d8bbb3fd87c 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -744,7 +744,6 @@ EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, struct sk_buff *skb) { - bpf_compute_data_end_sk_skb(skb); return bpf_prog_run_pin_on_cpu(prog, skb); }