bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Larysa Zaremba <larysa.zaremba@intel.com>
To: bpf@vger.kernel.org, Martin KaFai Lau <martin.lau@linux.dev>
Cc: Larysa Zaremba <larysa.zaremba@intel.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Andrii Nakryiko <andrii@kernel.org>, Song Liu <song@kernel.org>,
	Yonghong Song <yonghong.song@linux.dev>,
	John Fastabend <john.fastabend@gmail.com>,
	KP Singh <kpsingh@kernel.org>,
	Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>,
	Jiri Olsa <jolsa@kernel.org>,
	linux-kernel@vger.kernel.org,
	Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Subject: [PATCH bpf-next] selftests/bpf: add options and frags to xdp_hw_metadata
Date: Mon,  9 Oct 2023 18:05:16 +0200	[thread overview]
Message-ID: <20231009160520.20831-1-larysa.zaremba@intel.com> (raw)

This is a follow-up to the commit 9b2b86332a9b ("bpf: Allow to use kfunc
XDP hints and frags together").

The are some possible implementations problems that may arise when
providing metadata specifically for multi-buffer packets, therefore there
must be a possibility to test such option separately.

Add an option to use multi-buffer AF_XDP xdp_hw_metadata and mark used XDP
program as capable to use frags.

As for now, xdp_hw_metadata accepts no options, so add simple option
parsing logic and a help message.

For quick reference, also add an ingress packet generation command to the
help message. The command comes from [0].

Example of output for multi-buffer packet:

xsk_ring_cons__peek: 1
0xead018: rx_desc[15]->addr=10000000000f000 addr=f100 comp_addr=f000
rx_hash: 0x5789FCBB with RSS type:0x29
rx_timestamp:  1696856851535324697 (sec:1696856851.5353)
XDP RX-time:   1696856843158256391 (sec:1696856843.1583)
	delta sec:-8.3771 (-8377068.306 usec)
AF_XDP time:   1696856843158413078 (sec:1696856843.1584)
	delta sec:0.0002 (156.687 usec)
0xead018: complete idx=23 addr=f000
xsk_ring_cons__peek: 1
0xead018: rx_desc[16]->addr=100000000008000 addr=8100 comp_addr=8000
0xead018: complete idx=24 addr=8000
xsk_ring_cons__peek: 1
0xead018: rx_desc[17]->addr=100000000009000 addr=9100 comp_addr=9000 EoP
0xead018: complete idx=25 addr=9000

Metadata is printed for the first packet only.

[0] https://lore.kernel.org/all/20230119221536.3349901-18-sdf@google.com/

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 .../selftests/bpf/progs/xdp_hw_metadata.c     |  2 +-
 tools/testing/selftests/bpf/xdp_hw_metadata.c | 92 ++++++++++++++++---
 2 files changed, 79 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index 63d7de6c6bbb..8767d919c881 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -21,7 +21,7 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
 extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
 				    enum xdp_rss_hash_type *rss_type) __ksym;
 
-SEC("xdp")
+SEC("xdp.frags")
 int rx(struct xdp_md *ctx)
 {
 	void *data, *data_meta, *data_end;
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 17c980138796..25225720346b 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -26,6 +26,7 @@
 #include <linux/sockios.h>
 #include <sys/mman.h>
 #include <net/if.h>
+#include <ctype.h>
 #include <poll.h>
 #include <time.h>
 
@@ -49,19 +50,29 @@ struct xsk {
 struct xdp_hw_metadata *bpf_obj;
 struct xsk *rx_xsk;
 const char *ifname;
+bool use_frags;
 int ifindex;
 int rxq;
 
 void test__fail(void) { /* for network_helpers.c */ }
 
-static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
+static struct xsk_socket_config gen_socket_config(void)
 {
-	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
-	const struct xsk_socket_config socket_config = {
+	struct xsk_socket_config socket_config = {
 		.rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.bind_flags = XDP_COPY,
 	};
+
+	if (use_frags)
+		socket_config.bind_flags |= XDP_USE_SG;
+	return socket_config;
+}
+
+static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
+{
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+	struct xsk_socket_config socket_config = gen_socket_config();
 	const struct xsk_umem_config umem_config = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
@@ -263,11 +274,14 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 			verify_skb_metadata(server_fd);
 
 		for (i = 0; i < rxq; i++) {
+			bool first_seg = true;
+			bool is_eop = true;
+
 			if (fds[i].revents == 0)
 				continue;
 
 			struct xsk *xsk = &rx_xsk[i];
-
+peek:
 			ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx);
 			printf("xsk_ring_cons__peek: %d\n", ret);
 			if (ret != 1)
@@ -276,12 +290,19 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 			rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx);
 			comp_addr = xsk_umem__extract_addr(rx_desc->addr);
 			addr = xsk_umem__add_offset_to_addr(rx_desc->addr);
-			printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n",
-			       xsk, idx, rx_desc->addr, addr, comp_addr);
-			verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
-					    clock_id);
+			is_eop = !(rx_desc->options & XDP_PKT_CONTD);
+			printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx%s\n",
+			       xsk, idx, rx_desc->addr, addr, comp_addr, is_eop ? " EoP" : "");
+			if (first_seg) {
+				verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
+						    clock_id);
+				first_seg = false;
+			}
+
 			xsk_ring_cons__release(&xsk->rx, 1);
 			refill_rx(xsk, comp_addr);
+			if (!is_eop)
+				goto peek;
 		}
 	}
 
@@ -404,6 +425,54 @@ static void timestamping_enable(int fd, int val)
 		error(1, errno, "setsockopt(SO_TIMESTAMPING)");
 }
 
+static void print_usage(void)
+{
+	const char *usage =
+		"  Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n"
+		"  Options:\n"
+		"  -m            Enable multi-buffer XDP for larger MTU\n"
+		"  -h            Display this help and exit\n\n"
+		"  Generate test packets on the other machine with:\n"
+		"    echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
+
+	printf("%s", usage);
+}
+
+static void read_args(int argc, char *argv[])
+{
+	char opt;
+
+	while ((opt = getopt(argc, argv, "mh")) != -1) {
+		switch (opt) {
+		case 'm':
+			use_frags = true;
+			break;
+		case 'h':
+			print_usage();
+			exit(0);
+		case '?':
+			if (isprint(optopt))
+				fprintf(stderr, "Unknown option: -%c\n", optopt);
+			fallthrough;
+		default:
+			print_usage();
+			error(-1, opterr, "Command line options error");
+		}
+	}
+
+	if (optind >= argc) {
+		fprintf(stderr, "No device name provided\n");
+		print_usage();
+		exit(-1);
+	}
+
+	ifname = argv[optind];
+	ifindex = if_nametoindex(ifname);
+
+	if (!ifname)
+		error(-1, errno, "Invalid interface name");
+}
+
 int main(int argc, char *argv[])
 {
 	clockid_t clock_id = CLOCK_TAI;
@@ -413,13 +482,8 @@ int main(int argc, char *argv[])
 
 	struct bpf_program *prog;
 
-	if (argc != 2) {
-		fprintf(stderr, "pass device name\n");
-		return -1;
-	}
+	read_args(argc, argv);
 
-	ifname = argv[1];
-	ifindex = if_nametoindex(ifname);
 	rxq = rxq_num(ifname);
 
 	printf("rxq: %d\n", rxq);
-- 
2.41.0


             reply	other threads:[~2023-10-09 16:11 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-09 16:05 Larysa Zaremba [this message]
2023-10-09 16:49 ` [PATCH bpf-next] selftests/bpf: add options and frags to xdp_hw_metadata Stanislav Fomichev
2023-10-10  7:24   ` Larysa Zaremba
2023-10-10 16:04     ` Stanislav Fomichev
2023-10-10 16:35       ` Larysa Zaremba

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=20231009160520.20831-1-larysa.zaremba@intel.com \
    --to=larysa.zaremba@intel.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maciej.fijalkowski@intel.com \
    --cc=martin.lau@linux.dev \
    --cc=sdf@google.com \
    --cc=song@kernel.org \
    --cc=yonghong.song@linux.dev \
    /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).