XDP hardware hints discussion mail archive
 help / color / mirror / Atom feed
From: Stanislav Fomichev <sdf@google.com>
To: Larysa Zaremba <larysa.zaremba@intel.com>
Cc: bpf@vger.kernel.org, ast@kernel.org, daniel@iogearbox.net,
	andrii@kernel.org, martin.lau@linux.dev, song@kernel.org,
	yhs@fb.com, john.fastabend@gmail.com, kpsingh@kernel.org,
	haoluo@google.com, jolsa@kernel.org,
	David Ahern <dsahern@gmail.com>, Jakub Kicinski <kuba@kernel.org>,
	Willem de Bruijn <willemb@google.com>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Anatoly Burakov <anatoly.burakov@intel.com>,
	Alexander Lobakin <alexandr.lobakin@intel.com>,
	Magnus Karlsson <magnus.karlsson@gmail.com>,
	Maryam Tahhan <mtahhan@redhat.com>,
	xdp-hints@xdp-project.net, netdev@vger.kernel.org
Subject: [xdp-hints] Re: [PATCH bpf-next v3 19/21] selftests/bpf: Use AF_INET for TX in xdp_metadata
Date: Thu, 20 Jul 2023 15:05:17 -0700	[thread overview]
Message-ID: <ZLmvnRTFAYP2XZjU@google.com> (raw)
In-Reply-To: <20230719183734.21681-20-larysa.zaremba@intel.com>

On 07/19, Larysa Zaremba wrote:
> The easiest way to simulate stripped VLAN tag in veth is to send a packet
> from VLAN interface, attached to veth. Unfortunately, this approach is
> incompatible with AF_XDP on TX side, because VLAN interfaces do not have
> such feature.
> 
> Replace AF_XDP packet generation with sending the same datagram via
> AF_INET socket.
> 
> This does not change the packet contents or hints values with one notable
> exception: rx_hash_type, which previously was expected to be 0, now is
> expected be at least XDP_RSS_TYPE_L4.
> 
> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>

Acked-by: Stanislav Fomichev <sdf@google.com>

> ---
>  .../selftests/bpf/prog_tests/xdp_metadata.c   | 167 +++++++-----------
>  1 file changed, 59 insertions(+), 108 deletions(-)
> 
> diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
> index 626c461fa34d..1877e5c6d6c7 100644
> --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
> +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
> @@ -20,7 +20,7 @@
>  
>  #define UDP_PAYLOAD_BYTES 4
>  
> -#define AF_XDP_SOURCE_PORT 1234
> +#define UDP_SOURCE_PORT 1234
>  #define AF_XDP_CONSUMER_PORT 8080
>  
>  #define UMEM_NUM 16
> @@ -33,6 +33,12 @@
>  #define RX_ADDR "10.0.0.2"
>  #define PREFIX_LEN "8"
>  #define FAMILY AF_INET
> +#define TX_NETNS_NAME "xdp_metadata_tx"
> +#define RX_NETNS_NAME "xdp_metadata_rx"
> +#define TX_MAC "00:00:00:00:00:01"
> +#define RX_MAC "00:00:00:00:00:02"
> +
> +#define XDP_RSS_TYPE_L4 BIT(3)
>  
>  struct xsk {
>  	void *umem_area;
> @@ -119,90 +125,28 @@ static void close_xsk(struct xsk *xsk)
>  	munmap(xsk->umem_area, UMEM_SIZE);
>  }
>  
> -static void ip_csum(struct iphdr *iph)
> +static int generate_packet_udp(void)
>  {
> -	__u32 sum = 0;
> -	__u16 *p;
> -	int i;
> -
> -	iph->check = 0;
> -	p = (void *)iph;
> -	for (i = 0; i < sizeof(*iph) / sizeof(*p); i++)
> -		sum += p[i];
> -
> -	while (sum >> 16)
> -		sum = (sum & 0xffff) + (sum >> 16);
> -
> -	iph->check = ~sum;
> -}
> -
> -static int generate_packet(struct xsk *xsk, __u16 dst_port)
> -{
> -	struct xdp_desc *tx_desc;
> -	struct udphdr *udph;
> -	struct ethhdr *eth;
> -	struct iphdr *iph;
> -	void *data;
> -	__u32 idx;
> -	int ret;
> -
> -	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
> -	if (!ASSERT_EQ(ret, 1, "xsk_ring_prod__reserve"))
> -		return -1;
> -
> -	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
> -	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE;
> -	printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr);
> -	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
> -
> -	eth = data;
> -	iph = (void *)(eth + 1);
> -	udph = (void *)(iph + 1);
> -
> -	memcpy(eth->h_dest, "\x00\x00\x00\x00\x00\x02", ETH_ALEN);
> -	memcpy(eth->h_source, "\x00\x00\x00\x00\x00\x01", ETH_ALEN);
> -	eth->h_proto = htons(ETH_P_IP);
> -
> -	iph->version = 0x4;
> -	iph->ihl = 0x5;
> -	iph->tos = 0x9;
> -	iph->tot_len = htons(sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES);
> -	iph->id = 0;
> -	iph->frag_off = 0;
> -	iph->ttl = 0;
> -	iph->protocol = IPPROTO_UDP;
> -	ASSERT_EQ(inet_pton(FAMILY, TX_ADDR, &iph->saddr), 1, "inet_pton(TX_ADDR)");
> -	ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)");
> -	ip_csum(iph);
> -
> -	udph->source = htons(AF_XDP_SOURCE_PORT);
> -	udph->dest = htons(dst_port);
> -	udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES);
> -	udph->check = 0;
> -
> -	memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES);
> -
> -	tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES;
> -	xsk_ring_prod__submit(&xsk->tx, 1);
> -
> -	ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
> -	if (!ASSERT_GE(ret, 0, "sendto"))
> -		return ret;
> -
> -	return 0;
> -}
> -
> -static void complete_tx(struct xsk *xsk)
> -{
> -	__u32 idx;
> -	__u64 addr;
> -
> -	if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) {
> -		addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
> -
> -		printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
> -		xsk_ring_cons__release(&xsk->comp, 1);
> -	}
> +	char udp_payload[UDP_PAYLOAD_BYTES];
> +	struct sockaddr_in rx_addr;
> +	int sock_fd, err = 0;
> +
> +	/* Build a packet */
> +	memset(udp_payload, 0xAA, UDP_PAYLOAD_BYTES);
> +	rx_addr.sin_addr.s_addr = inet_addr(RX_ADDR);
> +	rx_addr.sin_family = AF_INET;
> +	rx_addr.sin_port = htons(UDP_SOURCE_PORT);
> +
> +	sock_fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
> +	if (!ASSERT_GE(sock_fd, 0, "socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP)"))
> +		return sock_fd;
> +
> +	err = sendto(sock_fd, udp_payload, UDP_PAYLOAD_BYTES, MSG_DONTWAIT,
> +		     (void *)&rx_addr, sizeof(rx_addr));
> +	ASSERT_GE(err, 0, "sendto");
> +
> +	close(sock_fd);
> +	return err;
>  }
>  
>  static void refill_rx(struct xsk *xsk, __u64 addr)
> @@ -268,7 +212,8 @@ static int verify_xsk_metadata(struct xsk *xsk)
>  	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
>  		return -1;
>  
> -	ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
> +	if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type"))
> +		return -1;
>  
>  	xsk_ring_cons__release(&xsk->rx, 1);
>  	refill_rx(xsk, comp_addr);
> @@ -284,36 +229,38 @@ void test_xdp_metadata(void)
>  	struct nstoken *tok = NULL;
>  	__u32 queue_id = QUEUE_ID;
>  	struct bpf_map *prog_arr;
> -	struct xsk tx_xsk = {};
>  	struct xsk rx_xsk = {};
>  	__u32 val, key = 0;
>  	int retries = 10;
>  	int rx_ifindex;
> -	int tx_ifindex;
>  	int sock_fd;
>  	int ret;
>  
> -	/* Setup new networking namespace, with a veth pair. */
> +	/* Setup new networking namespaces, with a veth pair. */
>  
> -	SYS(out, "ip netns add xdp_metadata");
> -	tok = open_netns("xdp_metadata");
> +	SYS(out, "ip netns add " TX_NETNS_NAME);
> +	SYS(out, "ip netns add " RX_NETNS_NAME);
> +
> +	tok = open_netns(TX_NETNS_NAME);
>  	SYS(out, "ip link add numtxqueues 1 numrxqueues 1 " TX_NAME
>  	    " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1");
> -	SYS(out, "ip link set dev " TX_NAME " address 00:00:00:00:00:01");
> -	SYS(out, "ip link set dev " RX_NAME " address 00:00:00:00:00:02");
> +	SYS(out, "ip link set " RX_NAME " netns " RX_NETNS_NAME);
> +
> +	SYS(out, "ip link set dev " TX_NAME " address " TX_MAC);
>  	SYS(out, "ip link set dev " TX_NAME " up");
> -	SYS(out, "ip link set dev " RX_NAME " up");
>  	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME);
> -	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
>  
> -	rx_ifindex = if_nametoindex(RX_NAME);
> -	tx_ifindex = if_nametoindex(TX_NAME);
> +	/* Avoid ARP calls */
> +	SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME);
> +	close_netns(tok);
>  
> -	/* Setup separate AF_XDP for TX and RX interfaces. */
> +	tok = open_netns(RX_NETNS_NAME);
> +	SYS(out, "ip link set dev " RX_NAME " address " RX_MAC);
> +	SYS(out, "ip link set dev " RX_NAME " up");
> +	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
> +	rx_ifindex = if_nametoindex(RX_NAME);
>  
> -	ret = open_xsk(tx_ifindex, &tx_xsk);
> -	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
> -		goto out;
> +	/* Setup AF_XDP for RX interface. */
>  
>  	ret = open_xsk(rx_ifindex, &rx_xsk);
>  	if (!ASSERT_OK(ret, "open_xsk(RX_NAME)"))
> @@ -353,19 +300,20 @@ void test_xdp_metadata(void)
>  	ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0);
>  	if (!ASSERT_GE(ret, 0, "bpf_map_update_elem"))
>  		goto out;
> +	close_netns(tok);
>  
>  	/* Send packet destined to RX AF_XDP socket. */
> -	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
> -		       "generate AF_XDP_CONSUMER_PORT"))
> +	tok = open_netns(TX_NETNS_NAME);
> +	if (!ASSERT_GE(generate_packet_udp(), 0, "generate UDP packet"))
>  		goto out;
> +	close_netns(tok);
>  
>  	/* Verify AF_XDP RX packet has proper metadata. */
> +	tok = open_netns(RX_NETNS_NAME);
>  	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0,
>  		       "verify_xsk_metadata"))
>  		goto out;
>  
> -	complete_tx(&tx_xsk);
> -
>  	/* Make sure freplace correctly picks up original bound device
>  	 * and doesn't crash.
>  	 */
> @@ -382,12 +330,15 @@ void test_xdp_metadata(void)
>  
>  	if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace"))
>  		goto out;
> +	close_netns(tok);
>  
>  	/* Send packet to trigger . */
> -	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
> -		       "generate freplace packet"))
> +	tok = open_netns(TX_NETNS_NAME);
> +	if (!ASSERT_GE(generate_packet_udp(), 0, "generate freplace packet"))
>  		goto out;
> +	close_netns(tok);
>  
> +	tok = open_netns(RX_NETNS_NAME);
>  	while (!retries--) {
>  		if (bpf_obj2->bss->called)
>  			break;
> @@ -397,10 +348,10 @@ void test_xdp_metadata(void)
>  
>  out:
>  	close_xsk(&rx_xsk);
> -	close_xsk(&tx_xsk);
>  	xdp_metadata2__destroy(bpf_obj2);
>  	xdp_metadata__destroy(bpf_obj);
>  	if (tok)
>  		close_netns(tok);
> -	SYS_NOFAIL("ip netns del xdp_metadata");
> +	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
> +	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
>  }
> -- 
> 2.41.0
> 

  reply	other threads:[~2023-07-20 22:05 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-19 18:37 [xdp-hints] [PATCH bpf-next v3 00/21] XDP metadata via kfuncs for ice Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 01/21] ice: make RX hash reading code more reusable Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 02/21] ice: make RX HW timestamp " Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 03/21] ice: make RX checksum checking " Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 04/21] ice: Make ptype internal to descriptor info processing Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 05/21] ice: Introduce ice_xdp_buff Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 06/21] ice: Support HW timestamp hint Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 07/21] ice: Support RX hash XDP hint Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 08/21] ice: Support XDP hints in AF_XDP ZC mode Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 09/21] xdp: Add VLAN tag hint Larysa Zaremba
2023-07-20 21:49   ` [xdp-hints] " Stanislav Fomichev
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 10/21] ice: Implement " Larysa Zaremba
2023-07-20 18:50   ` [xdp-hints] " Simon Horman
2023-07-21  7:38     ` Zaremba, Larysa
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 11/21] ice: use VLAN proto from ring packet context in skb path Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 12/21] xdp: Add checksum hint Larysa Zaremba
2023-07-19 21:42   ` [xdp-hints] " Willem de Bruijn
2023-07-20  9:57     ` Zaremba, Larysa
2023-07-20 10:10       ` Zaremba, Larysa
2023-07-20 13:55         ` Willem de Bruijn
2023-07-20 16:03           ` Zaremba, Larysa
2023-07-20 22:27             ` Willem de Bruijn
2023-07-21  8:01               ` Zaremba, Larysa
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 13/21] ice: Implement " Larysa Zaremba
2023-07-19 18:59   ` [xdp-hints] " Alexei Starovoitov
2023-07-19 21:51     ` Willem de Bruijn
2023-07-20  9:47       ` Zaremba, Larysa
2023-07-20 15:14         ` Alexei Starovoitov
2023-07-20 15:41           ` Zaremba, Larysa
2023-07-20 21:58             ` Stanislav Fomichev
2023-07-20 22:24               ` Willem de Bruijn
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 14/21] selftests/bpf: Allow VLAN packets in xdp_hw_metadata Larysa Zaremba
2023-07-20 21:58   ` [xdp-hints] " Stanislav Fomichev
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 15/21] net, xdp: allow metadata > 32 Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 16/21] selftests/bpf: Add flags and new hints to xdp_hw_metadata Larysa Zaremba
2023-07-20 22:00   ` [xdp-hints] " Stanislav Fomichev
2023-07-21  7:41     ` Zaremba, Larysa
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 17/21] veth: Implement VLAN tag and checksum XDP hint Larysa Zaremba
2023-07-20 22:02   ` [xdp-hints] " Stanislav Fomichev
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 18/21] net: make vlan_get_tag() return -ENODATA instead of -EINVAL Larysa Zaremba
2023-07-20 22:02   ` [xdp-hints] " Stanislav Fomichev
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 19/21] selftests/bpf: Use AF_INET for TX in xdp_metadata Larysa Zaremba
2023-07-20 22:05   ` Stanislav Fomichev [this message]
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 20/21] selftests/bpf: Check VLAN tag and proto " Larysa Zaremba
2023-07-20 22:14   ` [xdp-hints] " Stanislav Fomichev
2023-07-21  7:46     ` Zaremba, Larysa
2023-07-21 16:44       ` Stanislav Fomichev
2023-07-25  7:11         ` Larysa Zaremba
2023-07-19 18:37 ` [xdp-hints] [PATCH bpf-next v3 21/21] selftests/bpf: check checksum state " Larysa Zaremba
2023-07-20 22:14   ` [xdp-hints] " Stanislav Fomichev

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

  List information: https://lists.xdp-project.net/postorius/lists/xdp-hints.xdp-project.net/

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

  git send-email \
    --in-reply-to=ZLmvnRTFAYP2XZjU@google.com \
    --to=sdf@google.com \
    --cc=alexandr.lobakin@intel.com \
    --cc=anatoly.burakov@intel.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=dsahern@gmail.com \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=larysa.zaremba@intel.com \
    --cc=magnus.karlsson@gmail.com \
    --cc=martin.lau@linux.dev \
    --cc=mtahhan@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=song@kernel.org \
    --cc=willemb@google.com \
    --cc=xdp-hints@xdp-project.net \
    --cc=yhs@fb.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