From patchwork Mon Apr 17 12:24:23 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yang Yang X-Patchwork-Id: 674293 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 64E95C77B70 for ; Mon, 17 Apr 2023 12:40:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231197AbjDQMkm (ORCPT ); Mon, 17 Apr 2023 08:40:42 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33116 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231203AbjDQMkb (ORCPT ); Mon, 17 Apr 2023 08:40:31 -0400 X-Greylist: delayed 607 seconds by postgrey-1.37 at lindbergh.monkeyblade.net; Mon, 17 Apr 2023 05:40:30 PDT Received: from ubuntu20 (unknown [193.203.214.57]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DC48E59EB; Mon, 17 Apr 2023 05:40:29 -0700 (PDT) Received: by ubuntu20 (Postfix, from userid 1003) id BBF41E0C2F; Mon, 17 Apr 2023 12:24:25 +0000 (UTC) From: Yang Yang To: davem@davemloft.net, edumazet@google.com, willemdebruijn.kernel@gmail.com Cc: yang.yang29@zte.com.cn, kuba@kernel.org, linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, netdev@vger.kernel.org, pabeni@redhat.com, shuah@kernel.org, zhang.yunkai@zte.com.cn, xu.xin16@zte.com.cn, Xuexin Jiang Subject: [PATCH linux-next 1/3] selftests: net: udpgso_bench_rx: Fix verifty exceptions Date: Mon, 17 Apr 2023 20:24:23 +0800 Message-Id: <20230417122423.193237-1-yang.yang29@zte.com.cn> X-Mailer: git-send-email 2.25.1 In-Reply-To: <202304172017351308785@zte.com.cn> References: <202304172017351308785@zte.com.cn> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org From: Zhang Yunkai (CGEL ZTE) The verification function of this test case is likely to encounter the following error, which may confuse users. Executing the following command fails: bash# udpgso_bench_tx -l 4 -4 -D "$DST" bash# udpgso_bench_tx -l 4 -4 -D "$DST" -S 0 bash# udpgso_bench_rx -4 -G -S 1472 -v udpgso_bench_rx: data[1472]: len 2944, a(97) != q(113) This is because the sending buffers are not aligned by 26 bytes, and the GRO is not merged sequentially, and the receiver does not judge this situation. We do the validation after the data is split at the receiving end, just as the application actually uses this feature. Signed-off-by: Zhang Yunkai (CGEL ZTE) Reviewed-by: xu xin (CGEL ZTE) Reviewed-by: Yang Yang (CGEL ZTE) Cc: Xuexin Jiang (CGEL ZTE) --- tools/testing/selftests/net/udpgso_bench_rx.c | 38 +++++++++++++++++++++------ 1 file changed, 30 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index f35a924d4a30..a5b7f30659a5 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -189,16 +189,16 @@ static char sanitized_char(char val) return (val >= 'a' && val <= 'z') ? val : '.'; } -static void do_verify_udp(const char *data, int len) +static void do_verify_udp(const char *data, int start, int len) { - char cur = data[0]; + char cur = data[start]; int i; /* verify contents */ if (cur < 'a' || cur > 'z') error(1, 0, "data initial byte out of range"); - for (i = 1; i < len; i++) { + for (i = start + 1; i < start + len; i++) { if (cur == 'z') cur = 'a'; else @@ -212,6 +212,24 @@ static void do_verify_udp(const char *data, int len) } } +static void do_verify_udp_gro(const char *data, int len, int gso_size) +{ + int remaining = len; + int start = 0; + + while (remaining) { + if (remaining < 0) + break; + + if (remaining > gso_size) + do_verify_udp(data, start, gso_size); + else + do_verify_udp(data, start, remaining); + start += gso_size; + remaining -= gso_size; + } +} + static int recv_msg(int fd, char *buf, int len, int *gso_size) { char control[CMSG_SPACE(sizeof(int))] = {0}; @@ -264,16 +282,20 @@ static void do_flush_udp(int fd) if (cfg_expected_pkt_len && ret != cfg_expected_pkt_len) error(1, 0, "recv: bad packet len, got %d," " expected %d\n", ret, cfg_expected_pkt_len); + if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size) + error(1, 0, "recv: bad gso size, got %d, expected %d %s", + gso_size, cfg_expected_gso_size, "(-1 == no gso cmsg))\n"); if (len && cfg_verify) { if (ret == 0) error(1, errno, "recv: 0 byte datagram\n"); - do_verify_udp(rbuf, ret); + if (!cfg_gro_segment) + do_verify_udp(rbuf, 0, ret); + else if (gso_size > 0) + do_verify_udp_gro(rbuf, ret, gso_size); + else + do_verify_udp_gro(rbuf, ret, ret); } - if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size) - error(1, 0, "recv: bad gso size, got %d, expected %d " - "(-1 == no gso cmsg))\n", gso_size, - cfg_expected_gso_size); packets++; bytes += ret; From patchwork Mon Apr 17 12:24:28 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yang Yang X-Patchwork-Id: 675461 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 44A49C77B70 for ; Mon, 17 Apr 2023 12:40:44 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231182AbjDQMkk (ORCPT ); Mon, 17 Apr 2023 08:40:40 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33126 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231205AbjDQMkb (ORCPT ); Mon, 17 Apr 2023 08:40:31 -0400 Received: from ubuntu20 (unknown [193.203.214.57]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DC1C65584; Mon, 17 Apr 2023 05:40:29 -0700 (PDT) Received: by ubuntu20 (Postfix, from userid 1003) id 46D24E1A71; Mon, 17 Apr 2023 12:24:30 +0000 (UTC) From: Yang Yang To: davem@davemloft.net, edumazet@google.com, willemdebruijn.kernel@gmail.com Cc: yang.yang29@zte.com.cn, kuba@kernel.org, linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, netdev@vger.kernel.org, pabeni@redhat.com, shuah@kernel.org, zhang.yunkai@zte.com.cn, xu.xin16@zte.com.cn, Xuexin Jiang Subject: [PATCH linux-next 2/3] selftests: net: udpgso_bench_rx: Fix gsosize exceptions Date: Mon, 17 Apr 2023 20:24:28 +0800 Message-Id: <20230417122428.193297-1-yang.yang29@zte.com.cn> X-Mailer: git-send-email 2.25.1 In-Reply-To: <202304172017351308785@zte.com.cn> References: <202304172017351308785@zte.com.cn> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org From: Zhang Yunkai (CGEL ZTE) The -S parameter of the receiving terminal will most likely cause the following error. Executing the following command fails: bash# udpgso_bench_tx -l 4 -4 -D "$DST" bash# udpgso_bench_tx -l 4 -4 -D "$DST" -S 0 bash# udpgso_bench_rx -4 -G -S 1472 udp rx: 15 MB/s 256 calls/s udp rx: 30 MB/s 512 calls/s udpgso_bench_rx: recv: bad gso size, got -1, expected 1472 (-1 == no gso cmsg)) The actual message on the receiving end is as follows: IP 192.168.2.199.55238 > 192.168.2.203.8000: UDP, length 7360 IP 192.168.2.199.55238 > 192.168.2.203.8000: UDP, length 1472 IP 192.168.2.199.55238 > 192.168.2.203.8000: UDP, length 1472 IP 192.168.2.199.55238 > 192.168.2.203.8000: UDP, length 4416 IP 192.168.2.199.55238 > 192.168.2.203.8000: UDP, length 11776 IP 192.168.2.199.55238 > 192.168.2.203.8000: UDP, length 20608 recv: got one message len:1472, probably not an error. recv: got one message len:1472, probably not an error. This is due to network, NAPI, timer, etc., only one message being received. We believe that this situation should be normal. We add judgment to filter out packets that are less than gso_size and do not contain CMSG information. Signed-off-by: Zhang Yunkai (CGEL ZTE) Reviewed-by: xu xin (CGEL ZTE) Reviewed-by: Yang Yang (CGEL ZTE) Cc: Xuexin Jiang (CGEL ZTE) --- tools/testing/selftests/net/udpgso_bench_rx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index a5b7f30659a5..784e88b31f7d 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -282,7 +282,9 @@ static void do_flush_udp(int fd) if (cfg_expected_pkt_len && ret != cfg_expected_pkt_len) error(1, 0, "recv: bad packet len, got %d," " expected %d\n", ret, cfg_expected_pkt_len); - if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size) + /* For some network reasons, ret less than gso_size is not an error */ + if (cfg_expected_gso_size && cfg_expected_gso_size != gso_size && + ret > cfg_expected_gso_size) error(1, 0, "recv: bad gso size, got %d, expected %d %s", gso_size, cfg_expected_gso_size, "(-1 == no gso cmsg))\n"); if (len && cfg_verify) { From patchwork Mon Apr 17 12:25:04 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yang Yang X-Patchwork-Id: 674294 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1F26DC77B76 for ; Mon, 17 Apr 2023 12:40:42 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231230AbjDQMkk (ORCPT ); Mon, 17 Apr 2023 08:40:40 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:33114 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231200AbjDQMkb (ORCPT ); Mon, 17 Apr 2023 08:40:31 -0400 Received: from ubuntu20 (unknown [193.203.214.57]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DC0AB5267; Mon, 17 Apr 2023 05:40:29 -0700 (PDT) Received: by ubuntu20 (Postfix, from userid 1003) id 21913E1A83; Mon, 17 Apr 2023 12:25:05 +0000 (UTC) From: Yang Yang To: davem@davemloft.net, edumazet@google.com, willemdebruijn.kernel@gmail.com Cc: yang.yang29@zte.com.cn, kuba@kernel.org, linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, netdev@vger.kernel.org, pabeni@redhat.com, shuah@kernel.org, zhang.yunkai@zte.com.cn, xu.xin16@zte.com.cn, Xuexin Jiang Subject: [PATCH linux-next 3/3] selftests: net: udpgso_bench_rx: Fix packet number exceptions Date: Mon, 17 Apr 2023 20:25:04 +0800 Message-Id: <20230417122504.193350-1-yang.yang29@zte.com.cn> X-Mailer: git-send-email 2.25.1 In-Reply-To: <202304172017351308785@zte.com.cn> References: <202304172017351308785@zte.com.cn> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org From: Zhang Yunkai (CGEL ZTE) The -n parameter is confusing and seems to only affect the frequency of determining whether the time reaches 1s. However, the final print of the program is the number of messages expected to be received, which is always 0. bash# udpgso_bench_rx -4 -n 100 bash# udpgso_bench_tx -l 1 -4 -D "$DST" udpgso_bench_rx: wrong packet number! got 0, expected 100 This is because the packets are always cleared after print. Signed-off-by: Zhang Yunkai (CGEL ZTE) Reviewed-by: xu xin (CGEL ZTE) Reviewed-by: Yang Yang (CGEL ZTE) Cc: Xuexin Jiang (CGEL ZTE) --- tools/testing/selftests/net/udpgso_bench_rx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 784e88b31f7d..b66bb53af19f 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -50,7 +50,7 @@ static int cfg_rcv_timeout_ms; static struct sockaddr_storage cfg_bind_addr; static bool interrupted; -static unsigned long packets, bytes; +static unsigned long packets, total_packets, bytes; static void sigint_handler(int signum) { @@ -405,6 +405,7 @@ static void do_recv(void) "%s rx: %6lu MB/s %8lu calls/s\n", cfg_tcp ? "tcp" : "udp", bytes >> 20, packets); + total_packets += packets; bytes = packets = 0; treport = tnow + 1000; } @@ -415,7 +416,7 @@ static void do_recv(void) if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr)) error(1, 0, "wrong packet number! got %ld, expected %d\n", - packets, cfg_expected_pkt_nr); + total_packets + packets, cfg_expected_pkt_nr); if (close(fd)) error(1, errno, "close");