netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stanislav Fomichev <sdf@fomichev.me>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
	pabeni@redhat.com, linux-kernel@vger.kernel.org,
	linux-kselftest@vger.kernel.org, andrew+netdev@lunn.ch,
	shuah@kernel.org, horms@kernel.org, almasrymina@google.com,
	sdf@fomichev.me, willemb@google.com, petrm@nvidia.com,
	jdamato@fastly.com
Subject: [PATCH net-next v8 08/12] selftests: ncdevmem: Use YNL to enable TCP header split
Date: Thu,  7 Nov 2024 10:12:07 -0800	[thread overview]
Message-ID: <20241107181211.3934153-9-sdf@fomichev.me> (raw)
In-Reply-To: <20241107181211.3934153-1-sdf@fomichev.me>

In the next patch the hard-coded queue numbers are gonna be removed.
So introduce some initial support for ethtool YNL and use
it to enable header split.

Also, tcp-data-split requires latest ethtool which is unlikely
to be present in the distros right now.

(ideally, we should not shell out to ethtool at all).

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
---
 tools/testing/selftests/net/Makefile   |  2 +-
 tools/testing/selftests/net/ncdevmem.c | 57 +++++++++++++++++++++++++-
 2 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 26a4883a65c9..759b1d2dc8b4 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -111,7 +111,7 @@ TEST_INCLUDES := forwarding/lib.sh
 include ../lib.mk
 
 # YNL build
-YNL_GENS := netdev
+YNL_GENS := ethtool netdev
 include ynl.mk
 
 $(OUTPUT)/epoll_busy_poll: LDLIBS += -lcap
diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
index ad6de8e0e97b..9ca2da3a2f63 100644
--- a/tools/testing/selftests/net/ncdevmem.c
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -55,10 +55,12 @@
 #include <linux/netlink.h>
 #include <linux/genetlink.h>
 #include <linux/netdev.h>
+#include <linux/ethtool_netlink.h>
 #include <time.h>
 #include <net/if.h>
 
 #include "netdev-user.h"
+#include "ethtool-user.h"
 #include <ynl.h>
 
 #define PAGE_SHIFT 12
@@ -231,10 +233,58 @@ static int reset_flow_steering(void)
 	return 0;
 }
 
+static const char *tcp_data_split_str(int val)
+{
+	switch (val) {
+	case 0:
+		return "off";
+	case 1:
+		return "auto";
+	case 2:
+		return "on";
+	default:
+		return "?";
+	}
+}
+
 static int configure_headersplit(bool on)
 {
-	return run_command("sudo ethtool -G %s tcp-data-split %s >&2", ifname,
-			   on ? "on" : "off");
+	struct ethtool_rings_get_req *get_req;
+	struct ethtool_rings_get_rsp *get_rsp;
+	struct ethtool_rings_set_req *req;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int ret;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = ethtool_rings_set_req_alloc();
+	ethtool_rings_set_req_set_header_dev_index(req, ifindex);
+	/* 0 - off, 1 - auto, 2 - on */
+	ethtool_rings_set_req_set_tcp_data_split(req, on ? 2 : 0);
+	ret = ethtool_rings_set(ys, req);
+	if (ret < 0)
+		fprintf(stderr, "YNL failed: %s\n", ys->err.msg);
+	ethtool_rings_set_req_free(req);
+
+	if (ret == 0) {
+		get_req = ethtool_rings_get_req_alloc();
+		ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+		get_rsp = ethtool_rings_get(ys, get_req);
+		ethtool_rings_get_req_free(get_req);
+		if (get_rsp)
+			fprintf(stderr, "TCP header split: %s\n",
+				tcp_data_split_str(get_rsp->tcp_data_split));
+		ethtool_rings_get_rsp_free(get_rsp);
+	}
+
+	ynl_sock_destroy(ys);
+
+	return ret;
 }
 
 static int configure_rss(void)
@@ -382,6 +432,9 @@ int do_server(struct memory_buffer *mem)
 	if (reset_flow_steering())
 		error(1, 0, "Failed to reset flow steering\n");
 
+	if (configure_headersplit(1))
+		error(1, 0, "Failed to enable TCP header split\n");
+
 	/* Configure RSS to divert all traffic from our devmem queues */
 	if (configure_rss())
 		error(1, 0, "Failed to configure rss\n");
-- 
2.47.0


  parent reply	other threads:[~2024-11-07 18:12 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-07 18:11 [PATCH net-next v8 00/12] selftests: ncdevmem: Add ncdevmem to ksft Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 01/12] selftests: ncdevmem: Redirect all non-payload output to stderr Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 02/12] selftests: ncdevmem: Separate out dmabuf provider Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 03/12] selftests: ncdevmem: Unify error handling Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 04/12] selftests: ncdevmem: Make client_ip optional Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 05/12] selftests: ncdevmem: Remove default arguments Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 06/12] selftests: ncdevmem: Switch to AF_INET6 Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 07/12] selftests: ncdevmem: Properly reset flow steering Stanislav Fomichev
2024-11-07 18:12 ` Stanislav Fomichev [this message]
2024-11-07 18:12 ` [PATCH net-next v8 09/12] selftests: ncdevmem: Remove hard-coded queue numbers Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 10/12] selftests: ncdevmem: Run selftest when none of the -s or -c has been provided Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 11/12] selftests: ncdevmem: Move ncdevmem under drivers/net/hw Stanislav Fomichev
2024-11-07 18:12 ` [PATCH net-next v8 12/12] selftests: ncdevmem: Add automated test Stanislav Fomichev
2024-11-07 18:37   ` Joe Damato
2024-11-07 18:41 ` [PATCH net-next v8 00/12] selftests: ncdevmem: Add ncdevmem to ksft Joe Damato
2024-11-08  1:18   ` Stanislav Fomichev
2024-11-12  1:10 ` patchwork-bot+netdevbpf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20241107181211.3934153-9-sdf@fomichev.me \
    --to=sdf@fomichev.me \
    --cc=almasrymina@google.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=horms@kernel.org \
    --cc=jdamato@fastly.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=petrm@nvidia.com \
    --cc=shuah@kernel.org \
    --cc=willemb@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).