From patchwork Tue Oct 12 06:57:03 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "liujian (CE)" X-Patchwork-Id: 12551563 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1AC5BC433EF for ; Tue, 12 Oct 2021 06:54:08 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 005F86103D for ; Tue, 12 Oct 2021 06:54:07 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234072AbhJLG4I (ORCPT ); Tue, 12 Oct 2021 02:56:08 -0400 Received: from szxga02-in.huawei.com ([45.249.212.188]:23366 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234174AbhJLGzw (ORCPT ); Tue, 12 Oct 2021 02:55:52 -0400 Received: from dggemv703-chm.china.huawei.com (unknown [172.30.72.54]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4HT5qj0GX2zYkb2; Tue, 12 Oct 2021 14:49:21 +0800 (CST) Received: from dggema772-chm.china.huawei.com (10.1.198.214) by dggemv703-chm.china.huawei.com (10.3.19.46) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256) id 15.1.2308.8; Tue, 12 Oct 2021 14:53:48 +0800 Received: from huawei.com (10.175.101.6) by dggema772-chm.china.huawei.com (10.1.198.214) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id 15.1.2308.8; Tue, 12 Oct 2021 14:53:47 +0800 From: Liu Jian To: , , , , , , , , , , , , , , CC: Subject: [PATHC bpf v5 1/3] skmsg: lose offset info in sk_psock_skb_ingress Date: Tue, 12 Oct 2021 14:57:03 +0800 Message-ID: <20211012065705.224643-1-liujian56@huawei.com> X-Mailer: git-send-email 2.17.1 MIME-Version: 1.0 X-Originating-IP: [10.175.101.6] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggema772-chm.china.huawei.com (10.1.198.214) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress. If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggestion, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian Reviewed-by: Cong Wang Acked-by: John Fastabend --- v1->v2: fix build error when disable CONFIG_BPF_STREAM_PARSER v2->v3: Add one bit in skb->_sk_redir to distinguish enable or disable strparser v3->v4: Remove "#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)" code; and let "stm" have a more precise scope. v4->v5: Add fix tag. include/linux/skmsg.h | 18 ++++++++++++++++-- net/core/skmsg.c | 40 ++++++++++++++++++++++++++++++---------- 2 files changed, 46 insertions(+), 12 deletions(-) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 14ab0c0bc924..94e2a1f6e58d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -508,8 +508,22 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) #if IS_ENABLED(CONFIG_NET_SOCK_MSG) -/* We only have one bit so far. */ -#define BPF_F_PTR_MASK ~(BPF_F_INGRESS) +#define BPF_F_STRPARSER (1UL << 1) + +/* We only have two bits so far. */ +#define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER) + +static inline bool skb_bpf_strparser(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return sk_redir & BPF_F_STRPARSER; +} + +static inline void skb_bpf_set_strparser(struct sk_buff *skb) +{ + skb->_sk_redir |= BPF_F_STRPARSER; +} static inline bool skb_bpf_ingress(const struct sk_buff *skb) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2d6249b28928..e85b7f8491b9 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -494,6 +494,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + u32 off, u32 len, struct sk_psock *psock, struct sock *sk, struct sk_msg *msg) @@ -507,11 +508,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, */ if (skb_linearize(skb)) return -EAGAIN; - num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); + num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (unlikely(num_sge < 0)) return num_sge; - copied = skb->len; + copied = len; msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; @@ -522,9 +523,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return copied; } -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sock *sk = psock->sk; struct sk_msg *msg; @@ -535,7 +538,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * correctly. */ if (unlikely(skb->sk == sk)) - return sk_psock_skb_ingress_self(psock, skb); + return sk_psock_skb_ingress_self(psock, skb, off, len); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; @@ -547,7 +550,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * into user buffers. */ skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -557,7 +560,8 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * skb. In this case we do not need to check memory limits or skb_set_owner_r * because the skb is already accounted for here. */ -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); struct sock *sk = psock->sk; @@ -567,7 +571,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb return -EAGAIN; sk_msg_init(msg); skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -581,7 +585,7 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - return sk_psock_skb_ingress(psock, skb); + return sk_psock_skb_ingress(psock, skb, off, len); } static void sk_psock_skb_state(struct sk_psock *psock, @@ -624,6 +628,12 @@ static void sk_psock_backlog(struct work_struct *work) while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); @@ -930,6 +940,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, { struct sock *sk_other; int err = 0; + u32 len, off; switch (verdict) { case __SK_PASS: @@ -949,7 +960,15 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress_self(psock, skb); + len = skb->len; + off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } + err = sk_psock_skb_ingress_self(psock, skb, off, len); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); @@ -1018,6 +1037,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } + skb_bpf_set_strparser(skb); sk_psock_verdict_apply(psock, skb, ret); out: rcu_read_unlock(); From patchwork Tue Oct 12 06:57:04 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "liujian (CE)" X-Patchwork-Id: 12551565 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id A3B63C433EF for ; Tue, 12 Oct 2021 06:54:16 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 8FF136103D for ; Tue, 12 Oct 2021 06:54:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234109AbhJLG4N (ORCPT ); Tue, 12 Oct 2021 02:56:13 -0400 Received: from szxga03-in.huawei.com ([45.249.212.189]:25175 "EHLO szxga03-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233890AbhJLGz5 (ORCPT ); Tue, 12 Oct 2021 02:55:57 -0400 Received: from dggemv711-chm.china.huawei.com (unknown [172.30.72.54]) by szxga03-in.huawei.com (SkyGuard) with ESMTP id 4HT5vg3gvTz8tbZ; Tue, 12 Oct 2021 14:52:47 +0800 (CST) Received: from dggema772-chm.china.huawei.com (10.1.198.214) by dggemv711-chm.china.huawei.com (10.1.198.66) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256) id 15.1.2308.8; Tue, 12 Oct 2021 14:53:48 +0800 Received: from huawei.com (10.175.101.6) by dggema772-chm.china.huawei.com (10.1.198.214) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id 15.1.2308.8; Tue, 12 Oct 2021 14:53:47 +0800 From: Liu Jian To: , , , , , , , , , , , , , , CC: Subject: [PATHC bpf v5 2/3] selftests, bpf: Fix test_txmsg_ingress_parser error Date: Tue, 12 Oct 2021 14:57:04 +0800 Message-ID: <20211012065705.224643-2-liujian56@huawei.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20211012065705.224643-1-liujian56@huawei.com> References: <20211012065705.224643-1-liujian56@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.175.101.6] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggema772-chm.china.huawei.com (10.1.198.214) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net After "skmsg: lose offset info in sk_psock_skb_ingress", the test case with ktls failed. This because ktls parser(tls_read_size) return value is 285 not 256. the case like this: tls_sk1 --> redir_sk --> tls_sk2 tls_sk1 sent out 512 bytes data, after tls related processing redir_sk recved 570 btyes data, and redirect 512 (skb_use_parser) bytes data to tls_sk2; but tls_sk2 needs 285 * 2 bytes data, receive timeout occurred. Signed-off-by: Liu Jian Acked-by: John Fastabend --- tools/testing/selftests/bpf/test_sockmap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index eefd445b96fc..06924917ad77 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1680,6 +1680,8 @@ static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt) { txmsg_pass = 1; skb_use_parser = 512; + if (ktls == 1) + skb_use_parser = 570; opt->iov_length = 256; opt->iov_count = 1; opt->rate = 2; From patchwork Tue Oct 12 06:57:05 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "liujian (CE)" X-Patchwork-Id: 12551567 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0EA50C4332F for ; Tue, 12 Oct 2021 06:54:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id EBA43608FE for ; Tue, 12 Oct 2021 06:54:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234022AbhJLG4a (ORCPT ); Tue, 12 Oct 2021 02:56:30 -0400 Received: from szxga02-in.huawei.com ([45.249.212.188]:14332 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234038AbhJLG4C (ORCPT ); Tue, 12 Oct 2021 02:56:02 -0400 Received: from dggemv704-chm.china.huawei.com (unknown [172.30.72.57]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4HT5qW00zhz905V; Tue, 12 Oct 2021 14:49:10 +0800 (CST) Received: from dggema772-chm.china.huawei.com (10.1.198.214) by dggemv704-chm.china.huawei.com (10.3.19.47) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256) id 15.1.2308.8; Tue, 12 Oct 2021 14:53:49 +0800 Received: from huawei.com (10.175.101.6) by dggema772-chm.china.huawei.com (10.1.198.214) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id 15.1.2308.8; Tue, 12 Oct 2021 14:53:48 +0800 From: Liu Jian To: , , , , , , , , , , , , , , CC: Subject: [PATHC bpf v5 3/3] selftests, bpf: Add one test for sockmap with strparser Date: Tue, 12 Oct 2021 14:57:05 +0800 Message-ID: <20211012065705.224643-3-liujian56@huawei.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20211012065705.224643-1-liujian56@huawei.com> References: <20211012065705.224643-1-liujian56@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.175.101.6] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggema772-chm.china.huawei.com (10.1.198.214) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net Add the test to check sockmap with strparser is working well. Signed-off-by: Liu Jian Acked-by: John Fastabend --- tools/testing/selftests/bpf/test_sockmap.c | 33 ++++++++++++++++++++-- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 06924917ad77..1ba7e7346afb 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -139,6 +139,7 @@ struct sockmap_options { bool sendpage; bool data_test; bool drop_expected; + bool check_recved_len; int iov_count; int iov_length; int rate; @@ -556,8 +557,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, int err, i, flags = MSG_NOSIGNAL; bool drop = opt->drop_expected; bool data = opt->data_test; + int iov_alloc_length = iov_length; - err = msg_alloc_iov(&msg, iov_count, iov_length, data, tx); + if (!tx && opt->check_recved_len) + iov_alloc_length *= 2; + + err = msg_alloc_iov(&msg, iov_count, iov_alloc_length, data, tx); if (err) goto out_errno; if (peek_flag) { @@ -665,6 +670,13 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, s->bytes_recvd += recv; + if (opt->check_recved_len && s->bytes_recvd > total_bytes) { + errno = EMSGSIZE; + fprintf(stderr, "recv failed(), bytes_recvd:%zd, total_bytes:%f\n", + s->bytes_recvd, total_bytes); + goto out_errno; + } + if (data) { int chunk_sz = opt->sendpage ? iov_length * cnt : @@ -744,7 +756,8 @@ static int sendmsg_test(struct sockmap_options *opt) rxpid = fork(); if (rxpid == 0) { - iov_buf -= (txmsg_pop - txmsg_start_pop + 1); + if (txmsg_pop || txmsg_start_pop) + iov_buf -= (txmsg_pop - txmsg_start_pop + 1); if (opt->drop_expected || txmsg_ktls_skb_drop) _exit(0); @@ -1688,6 +1701,19 @@ static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt) test_exec(cgrp, opt); } +static void test_txmsg_ingress_parser2(int cgrp, struct sockmap_options *opt) +{ + if (ktls == 1) + return; + skb_use_parser = 10; + opt->iov_length = 20; + opt->iov_count = 1; + opt->rate = 1; + opt->check_recved_len = true; + test_exec(cgrp, opt); + opt->check_recved_len = false; +} + char *map_names[] = { "sock_map", "sock_map_txmsg", @@ -1786,7 +1812,8 @@ struct _test test[] = { {"txmsg test pull-data", test_txmsg_pull}, {"txmsg test pop-data", test_txmsg_pop}, {"txmsg test push/pop data", test_txmsg_push_pop}, - {"txmsg text ingress parser", test_txmsg_ingress_parser}, + {"txmsg test ingress parser", test_txmsg_ingress_parser}, + {"txmsg test ingress parser2", test_txmsg_ingress_parser2}, }; static int check_whitelist(struct _test *t, struct sockmap_options *opt)