[PATCH bpf-next 0/4] samples/bpf: xdpsock app enhancements

This patch series adds below capabilities to xdpsock app:-

1/4: Add VLAN tag (ID & Priority) to the generated Tx-Only frames.
2/4: Add DMAC and SMAC setting to the generated Tx-Only frames.
     If parameters are not set, the previous DMAC and SMAC are used.
3/4: Add cyclic transmission (cycle-time) setting for Tx-only operation.
     This option can be used together with batch size and packet count.
4/4: Add time-out with retries to Tx complete cleaning process to prevent
     unsuccessful XDP Transmission from causing the Tx cleaning process
     from polling indefinitely.

With above enhancements to xdpsock, we can know run concurrent VLAN-tagged
XDP TX streams in periodic Tx with batch size fashion.

For examples:
 DMAC (-G)             = fa:8d:f1:e2:0b:e8
 SMAC (-H)             = ce:17:07:17:3e:3a
 VLAN ID (-J)          = 1
 VLAN Pri (-K)         = 1-3
 Tx Queue (-q)         = 1-3
 Cycle Time in us (-T) = 1000
 Batch (-b)            = 16
 Packet Count          = 1000000

Sending Board
=============
Terminal-1:
 $ xdpsock -i enp0s29f1 -t -N -z -H ce:17:07:17:3e:3a -G fa:8d:f1:e2:0b:e8 -V -J 1 -K 1 -q 1 -T 1000 -b 16 -C 1000000 -x

Terminal-2:
 $ xdpsock -i enp0s29f1 -t -N -z -H ce:17:07:17:3e:3a -G fa:8d:f1:e2:0b:e8 -V -J 1 -K 2 -q 2 -T 1000 -b 16 -C 1000000 -x

Terminal-3:
 $ xdpsock -i enp0s29f1 -t -N -z -H ce:17:07:17:3e:3a -G fa:8d:f1:e2:0b:e8 -V -J 1 -K 3 -q 3 -T 1000 -b 16 -C 1000000 -x

Receiving Board
===============
Terminal-1:
 $ xdpsock -i enp0s29f1 -r -N -z -q 1

Terminal-2:
 $ xdpsock -i enp0s29f1 -r -N -z -q 2

Terminal-3:
 $ xdpsock -i enp0s29f1 -r -N -z -q 3

Thanks

Ong Boon Leong (4):
  samples/bpf: xdpsock: add VLAN support for Tx-only operation
  samples/bpf: xdpsock: add Dest and Src MAC setting for Tx-only
    operation
  samples/bpf: xdpsock: add period cycle time to Tx operation
  samples/bpf: xdpsock: add time-out for cleaning Tx

 samples/bpf/xdpsock_user.c | 154 ++++++++++++++++++++++++++++++++-----
 1 file changed, 134 insertions(+), 20 deletions(-)

-- 
2.25.1

In multi-queue environment testing, the support for VLAN-tag based
steering is useful. So, this patch adds the capability to add
VLAN tag (VLAN ID and Priority) to the generated Tx frame.

To set the VLAN ID=10 and Priority=2 for Tx only through TxQ=3:
 $ xdpsock -i eth0 -t -N -z -q 3 -V -J 10 -K 2

If VLAN ID (-J) and Priority (-K) is set, it default to
  VLAN ID = 1
  VLAN Priority = 0.

For example, VLAN-tagged Tx only, xdp copy mode through TxQ=1:
 $ xdpsock -i eth0 -t -N -c -q 1 -V

Signed-off-by: Ong Boon Leong <redacted>
---
 samples/bpf/xdpsock_user.c | 90 +++++++++++++++++++++++++++++++-------
 1 file changed, 75 insertions(+), 15 deletions(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 49d7a6ad7e3..e09fabecd69 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c

@@ -53,6 +53,12 @@
 
 #define DEBUG_HEXDUMP 0
 
+#define VLAN_PRIO_MASK		0xe000 /* Priority Code Point */
+#define VLAN_PRIO_SHIFT		13
+#define VLAN_VID_MASK		0x0fff /* VLAN Identifier */
+#define VLAN_VID__DEFAULT	1
+#define VLAN_PRI__DEFAULT	0
+
 typedef __u64 u64;
 typedef __u32 u32;
 typedef __u16 u16;

@@ -78,6 +84,9 @@ static u32 opt_batch_size = 64;
 static int opt_pkt_count;
 static u16 opt_pkt_size = MIN_PKT_SIZE;
 static u32 opt_pkt_fill_pattern = 0x12345678;
+static bool opt_vlan_tag;
+static u16 opt_pkt_vlan_id = VLAN_VID__DEFAULT;
+static u16 opt_pkt_vlan_pri = VLAN_PRI__DEFAULT;
 static bool opt_extra_stats;
 static bool opt_quiet;
 static bool opt_app_stats;

@@ -98,6 +107,14 @@ static u32 prog_id;
 static bool opt_busy_poll;
 static bool opt_reduced_cap;
 
+struct vlan_ethhdr {
+	unsigned char h_dest[6];
+	unsigned char h_source[6];
+	__be16 h_vlan_proto;
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
 struct xsk_ring_stats {
 	unsigned long rx_npkts;
 	unsigned long tx_npkts;

@@ -737,11 +754,13 @@ static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len,
 
 #define ETH_FCS_SIZE 4
 
-#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
+#define ETH_HDR_SIZE (opt_vlan_tag ? sizeof(struct vlan_ethhdr) : \
+		      sizeof(struct ethhdr))
+#define PKT_HDR_SIZE (ETH_HDR_SIZE + sizeof(struct iphdr) + \
 		      sizeof(struct udphdr))
 
 #define PKT_SIZE		(opt_pkt_size - ETH_FCS_SIZE)
-#define IP_PKT_SIZE		(PKT_SIZE - sizeof(struct ethhdr))
+#define IP_PKT_SIZE		(PKT_SIZE - ETH_HDR_SIZE)
 #define UDP_PKT_SIZE		(IP_PKT_SIZE - sizeof(struct iphdr))
 #define UDP_PKT_DATA_SIZE	(UDP_PKT_SIZE - sizeof(struct udphdr))
 

@@ -749,17 +768,42 @@ static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
 
 static void gen_eth_hdr_data(void)
 {
-	struct udphdr *udp_hdr = (struct udphdr *)(pkt_data +
-						   sizeof(struct ethhdr) +
-						   sizeof(struct iphdr));
-	struct iphdr *ip_hdr = (struct iphdr *)(pkt_data +
-						sizeof(struct ethhdr));
-	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
-
-	/* ethernet header */
-	memcpy(eth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN);
-	memcpy(eth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN);
-	eth_hdr->h_proto = htons(ETH_P_IP);
+	struct udphdr *udp_hdr;
+	struct iphdr *ip_hdr;
+
+	if (opt_vlan_tag) {
+		struct vlan_ethhdr *veth_hdr = (struct vlan_ethhdr *)pkt_data;
+		u16 vlan_tci = 0;
+
+		udp_hdr = (struct udphdr *)(pkt_data +
+					    sizeof(struct vlan_ethhdr) +
+					    sizeof(struct iphdr));
+		ip_hdr = (struct iphdr *)(pkt_data +
+					  sizeof(struct vlan_ethhdr));
+
+		/* ethernet & VLAN header */
+		memcpy(veth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN);
+		memcpy(veth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN);
+		veth_hdr->h_vlan_proto = htons(ETH_P_8021Q);
+		vlan_tci = opt_pkt_vlan_id & VLAN_VID_MASK;
+		vlan_tci |= (opt_pkt_vlan_pri << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK;
+		veth_hdr->h_vlan_TCI = htons(vlan_tci);
+		veth_hdr->h_vlan_encapsulated_proto = htons(ETH_P_IP);
+	} else {
+		struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
+
+		udp_hdr = (struct udphdr *)(pkt_data +
+					    sizeof(struct ethhdr) +
+					    sizeof(struct iphdr));
+		ip_hdr = (struct iphdr *)(pkt_data +
+					  sizeof(struct ethhdr));
+
+		/* ethernet header */
+		memcpy(eth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN);
+		memcpy(eth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN);
+		eth_hdr->h_proto = htons(ETH_P_IP);
+	}
+
 
 	/* IP header */
 	ip_hdr->version = IPVERSION;

@@ -917,6 +961,9 @@ static struct option long_options[] = {
 	{"tx-pkt-count", required_argument, 0, 'C'},
 	{"tx-pkt-size", required_argument, 0, 's'},
 	{"tx-pkt-pattern", required_argument, 0, 'P'},
+	{"tx-vlan", no_argument, 0, 'V'},
+	{"tx-vlan-id", required_argument, 0, 'J'},
+	{"tx-vlan-pri", required_argument, 0, 'K'},
 	{"extra-stats", no_argument, 0, 'x'},
 	{"quiet", no_argument, 0, 'Q'},
 	{"app-stats", no_argument, 0, 'a'},

@@ -957,6 +1004,9 @@ static void usage(const char *prog)
 		"			(Default: %d bytes)\n"
 		"			Min size: %d, Max size %d.\n"
 		"  -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n"
+		"  -V, --tx-vlan        Send VLAN tagged  packets (For -t|--txonly)\n"
+		"  -J, --tx-vlan-id=n   Tx VLAN ID [1-4095]. Default: %d (For -V|--tx-vlan)\n"
+		"  -K, --tx-vlan-pri=n  Tx VLAN Priority [0-7]. Default: %d (For -V|--tx-vlan)\n"
 		"  -x, --extra-stats	Display extra statistics.\n"
 		"  -Q, --quiet          Do not display any stats.\n"
 		"  -a, --app-stats	Display application (syscall) statistics.\n"

@@ -966,7 +1016,8 @@ static void usage(const char *prog)
 		"\n";
 	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE,
 		opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE,
-		XSK_UMEM__DEFAULT_FRAME_SIZE, opt_pkt_fill_pattern);
+		XSK_UMEM__DEFAULT_FRAME_SIZE, opt_pkt_fill_pattern,
+		VLAN_VID__DEFAULT, VLAN_PRI__DEFAULT);
 
 	exit(EXIT_FAILURE);
 }

@@ -978,7 +1029,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:BR",
+		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:VJ:K:xQaI:BR",
 				long_options, &option_index);
 		if (c == -1)
 			break;

@@ -1059,6 +1110,15 @@ static void parse_command_line(int argc, char **argv)
 		case 'P':
 			opt_pkt_fill_pattern = strtol(optarg, NULL, 16);
 			break;
+		case 'V':
+			opt_vlan_tag = true;
+			break;
+		case 'J':
+			opt_pkt_vlan_id = atoi(optarg);
+			break;
+		case 'K':
+			opt_pkt_vlan_pri = atoi(optarg);
+			break;
 		case 'x':
 			opt_extra_stats = 1;
 			break;

-- 
2.25.1

To set Dest MAC address (-G|--tx-dmac) only:
 $ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff

To set Source MAC address (-H|--tx-smac) only:
 $ xdpsock -i eth0 -t -N -z -H 11:22:33:44:55:66

To set both Dest and Source MAC address:
 $ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff \
   -H 11:22:33:44:55:66

The default Dest and Source MAC address remain the same as before.

Signed-off-by: Ong Boon Leong <redacted>
---
 samples/bpf/xdpsock_user.c | 36 +++++++++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index e09fabecd69..691f442bbb2 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c

@@ -14,6 +14,7 @@
 #include <arpa/inet.h>
 #include <locale.h>
 #include <net/ethernet.h>
+#include <netinet/ether.h>
 #include <net/if.h>
 #include <poll.h>
 #include <pthread.h>

@@ -87,6 +88,10 @@ static u32 opt_pkt_fill_pattern = 0x12345678;
 static bool opt_vlan_tag;
 static u16 opt_pkt_vlan_id = VLAN_VID__DEFAULT;
 static u16 opt_pkt_vlan_pri = VLAN_PRI__DEFAULT;
+static struct ether_addr opt_txdmac = {{ 0x3c, 0xfd, 0xfe,
+					 0x9e, 0x7f, 0x71 }};
+static struct ether_addr opt_txsmac = {{ 0xec, 0xb1, 0xd7,
+					 0x98, 0x3a, 0xc0 }};
 static bool opt_extra_stats;
 static bool opt_quiet;
 static bool opt_app_stats;

@@ -782,8 +787,9 @@ static void gen_eth_hdr_data(void)
 					  sizeof(struct vlan_ethhdr));
 
 		/* ethernet & VLAN header */
-		memcpy(veth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN);
-		memcpy(veth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN);
+
+		memcpy(veth_hdr->h_dest, &opt_txdmac, ETH_ALEN);
+		memcpy(veth_hdr->h_source, &opt_txsmac, ETH_ALEN);
 		veth_hdr->h_vlan_proto = htons(ETH_P_8021Q);
 		vlan_tci = opt_pkt_vlan_id & VLAN_VID_MASK;
 		vlan_tci |= (opt_pkt_vlan_pri << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK;

@@ -799,8 +805,8 @@ static void gen_eth_hdr_data(void)
 					  sizeof(struct ethhdr));
 
 		/* ethernet header */
-		memcpy(eth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN);
-		memcpy(eth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN);
+		memcpy(eth_hdr->h_dest, &opt_txdmac, ETH_ALEN);
+		memcpy(eth_hdr->h_source, &opt_txsmac, ETH_ALEN);
 		eth_hdr->h_proto = htons(ETH_P_IP);
 	}
 

@@ -964,6 +970,8 @@ static struct option long_options[] = {
 	{"tx-vlan", no_argument, 0, 'V'},
 	{"tx-vlan-id", required_argument, 0, 'J'},
 	{"tx-vlan-pri", required_argument, 0, 'K'},
+	{"tx-dmac", required_argument, 0, 'G'},
+	{"tx-smac", required_argument, 0, 'H'},
 	{"extra-stats", no_argument, 0, 'x'},
 	{"quiet", no_argument, 0, 'Q'},
 	{"app-stats", no_argument, 0, 'a'},

@@ -1007,6 +1015,8 @@ static void usage(const char *prog)
 		"  -V, --tx-vlan        Send VLAN tagged  packets (For -t|--txonly)\n"
 		"  -J, --tx-vlan-id=n   Tx VLAN ID [1-4095]. Default: %d (For -V|--tx-vlan)\n"
 		"  -K, --tx-vlan-pri=n  Tx VLAN Priority [0-7]. Default: %d (For -V|--tx-vlan)\n"
+		"  -G, --tx-dmac=<MAC>  Dest MAC addr of TX frame in aa:bb:cc:dd:ee:ff format (For -V|--tx-vlan)\n"
+		"  -H, --tx-smac=<MAC>  Src MAC addr of TX frame in aa:bb:cc:dd:ee:ff format (For -V|--tx-vlan)\n"
 		"  -x, --extra-stats	Display extra statistics.\n"
 		"  -Q, --quiet          Do not display any stats.\n"
 		"  -a, --app-stats	Display application (syscall) statistics.\n"

@@ -1029,7 +1039,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:VJ:K:xQaI:BR",
+		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:VJ:K:G:H:xQaI:BR",
 				long_options, &option_index);
 		if (c == -1)
 			break;

@@ -1119,6 +1129,22 @@ static void parse_command_line(int argc, char **argv)
 		case 'K':
 			opt_pkt_vlan_pri = atoi(optarg);
 			break;
+		case 'G':
+			if (!ether_aton_r(optarg,
+					  (struct ether_addr *)&opt_txdmac)) {
+				fprintf(stderr, "Invalid dmac address:%s\n",
+					optarg);
+				usage(basename(argv[0]));
+			}
+			break;
+		case 'H':
+			if (!ether_aton_r(optarg,
+					  (struct ether_addr *)&opt_txsmac)) {
+				fprintf(stderr, "Invalid smac address:%s\n",
+					optarg);
+				usage(basename(argv[0]));
+			}
+			break;
 		case 'x':
 			opt_extra_stats = 1;
 			break;

-- 
2.25.1

Tx cycle time is in micro-seconds unit. By combining the batch size (-b M)
and Tx cycle time (-T|--tx-cycle N), xdpsock now can transmit batch-size of
packets every N-us periodically.

For example to transmit 1 packet each 1ms cycle time for total of 2000000
packets:

 $ xdpsock -i eth0 -T -N -z -T 1000 -b 1 -C 2000000

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1996872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1997872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1998872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1999872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 128            2000000

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           0.00
rx                 0              0
tx                 0              2000000

Signed-off-by: Ong Boon Leong <redacted>
---
 samples/bpf/xdpsock_user.c | 36 +++++++++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 691f442bbb2..61d4063f11a 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c

@@ -111,6 +111,7 @@ static u32 opt_num_xsks = 1;
 static u32 prog_id;
 static bool opt_busy_poll;
 static bool opt_reduced_cap;
+static unsigned long opt_cycle_time;
 
 struct vlan_ethhdr {
 	unsigned char h_dest[6];

@@ -173,6 +174,8 @@ struct xsk_socket_info {
 	struct xsk_app_stats app_stats;
 	struct xsk_driver_stats drv_stats;
 	u32 outstanding_tx;
+	unsigned long prev_tx_time;
+	unsigned long tx_cycle_time;
 };
 
 static int num_socks;

@@ -972,6 +975,7 @@ static struct option long_options[] = {
 	{"tx-vlan-pri", required_argument, 0, 'K'},
 	{"tx-dmac", required_argument, 0, 'G'},
 	{"tx-smac", required_argument, 0, 'H'},
+	{"tx-cycle", required_argument, 0, 'T'},
 	{"extra-stats", no_argument, 0, 'x'},
 	{"quiet", no_argument, 0, 'Q'},
 	{"app-stats", no_argument, 0, 'a'},

@@ -1017,6 +1021,7 @@ static void usage(const char *prog)
 		"  -K, --tx-vlan-pri=n  Tx VLAN Priority [0-7]. Default: %d (For -V|--tx-vlan)\n"
 		"  -G, --tx-dmac=<MAC>  Dest MAC addr of TX frame in aa:bb:cc:dd:ee:ff format (For -V|--tx-vlan)\n"
 		"  -H, --tx-smac=<MAC>  Src MAC addr of TX frame in aa:bb:cc:dd:ee:ff format (For -V|--tx-vlan)\n"
+		"  -T, --tx-cycle=n     Tx cycle time in micro-seconds (For -t|--txonly).\n"
 		"  -x, --extra-stats	Display extra statistics.\n"
 		"  -Q, --quiet          Do not display any stats.\n"
 		"  -a, --app-stats	Display application (syscall) statistics.\n"

@@ -1039,7 +1044,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:VJ:K:G:H:xQaI:BR",
+		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:VJ:K:G:H:T:xQaI:BR",
 				long_options, &option_index);
 		if (c == -1)
 			break;

@@ -1145,6 +1150,10 @@ static void parse_command_line(int argc, char **argv)
 				usage(basename(argv[0]));
 			}
 			break;
+		case 'T':
+			opt_cycle_time = atoi(optarg);
+			opt_cycle_time *= 1000;
+			break;
 		case 'x':
 			opt_extra_stats = 1;
 			break;

@@ -1350,16 +1359,25 @@ static void rx_drop_all(void)
 	}
 }
 
-static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size)
+static int tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size)
 {
 	u32 idx;
 	unsigned int i;
 
+	if (xsk->tx_cycle_time) {
+		unsigned long now = get_nsecs();
+
+		if ((now - xsk->prev_tx_time) < xsk->tx_cycle_time)
+			return 0;
+
+		xsk->prev_tx_time = now;
+	}
+
 	while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) <
 				      batch_size) {
 		complete_tx_only(xsk, batch_size);
 		if (benchmark_done)
-			return;
+			return 0;
 	}
 
 	for (i = 0; i < batch_size; i++) {

@@ -1375,6 +1393,8 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size)
 	*frame_nb += batch_size;
 	*frame_nb %= NUM_FRAMES;
 	complete_tx_only(xsk, batch_size);
+
+	return batch_size;
 }
 
 static inline int get_batch_size(int pkt_cnt)

@@ -1407,6 +1427,7 @@ static void complete_tx_only_all(void)
 static void tx_only_all(void)
 {
 	struct pollfd fds[MAX_SOCKS] = {};
+	unsigned long now = get_nsecs();
 	u32 frame_nb[MAX_SOCKS] = {};
 	int pkt_cnt = 0;
 	int i, ret;

@@ -1414,10 +1435,15 @@ static void tx_only_all(void)
 	for (i = 0; i < num_socks; i++) {
 		fds[0].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[0].events = POLLOUT;
+		if (opt_cycle_time) {
+			xsks[i]->prev_tx_time = now;
+			xsks[i]->tx_cycle_time = opt_cycle_time;
+		}
 	}
 
 	while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) {
 		int batch_size = get_batch_size(pkt_cnt);
+		int tx_cnt = 0;
 
 		if (opt_poll) {
 			for (i = 0; i < num_socks; i++)

@@ -1431,9 +1457,9 @@ static void tx_only_all(void)
 		}
 
 		for (i = 0; i < num_socks; i++)
-			tx_only(xsks[i], &frame_nb[i], batch_size);
+			tx_cnt += tx_only(xsks[i], &frame_nb[i], batch_size);
 
-		pkt_cnt += batch_size;
+		pkt_cnt += tx_cnt;
 
 		if (benchmark_done)
 			break;

-- 
2.25.1

When user sets tx-pkt-count and in case where there are invalid Tx frame,
the complete_tx_only_all() process polls indefinitely. So, this patch
adds a time-out mechanism into the process so that the application
can terminate automatically after it retries 3*polling interval duration.

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 136383         1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         35             245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      957            7011

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7012

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7013

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7014

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      0              7014

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           0.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      0              7014

Signed-off-by: Ong Boon Leong <redacted>
---
 samples/bpf/xdpsock_user.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 61d4063f11a..9c3311329ec 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c

@@ -1410,6 +1410,7 @@ static inline int get_batch_size(int pkt_cnt)
 
 static void complete_tx_only_all(void)
 {
+	u32 retries = 3;
 	bool pending;
 	int i;
 

@@ -1421,7 +1422,8 @@ static void complete_tx_only_all(void)
 				pending = !!xsks[i]->outstanding_tx;
 			}
 		}
-	} while (pending);
+		sleep(opt_interval);
+	} while (pending && retries-- > 0);
 }
 
 static void tx_only_all(void)

-- 
2.25.1

On Wed, Nov 24, 2021 at 1:21 AM Ong Boon Leong [off-list ref] wrote:

To set Dest MAC address (-G|--tx-dmac) only:
 $ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff

To set Source MAC address (-H|--tx-smac) only:
 $ xdpsock -i eth0 -t -N -z -H 11:22:33:44:55:66

To set both Dest and Source MAC address:
 $ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff \
   -H 11:22:33:44:55:66

The default Dest and Source MAC address remain the same as before.

Signed-off-by: Ong Boon Leong <redacted>

Acked-by: Song Liu <redacted>

On Wed, Nov 24, 2021 at 1:22 AM Ong Boon Leong [off-list ref] wrote:

When user sets tx-pkt-count and in case where there are invalid Tx frame,
the complete_tx_only_all() process polls indefinitely. So, this patch
adds a time-out mechanism into the process so that the application
can terminate automatically after it retries 3*polling interval duration.

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 136383         1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         35             245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      957            7011

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7012

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7013

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7014

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      0              7014

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           0.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      0              7014

I am not following why we need examples above in the commit log.

Shall we make the retry value configurable? And maybe make it a timeout
value in seconds?

On Wed, Nov 24, 2021 at 1:21 AM Ong Boon Leong [off-list ref] wrote:

In multi-queue environment testing, the support for VLAN-tag based
steering is useful. So, this patch adds the capability to add
VLAN tag (VLAN ID and Priority) to the generated Tx frame.

To set the VLAN ID=10 and Priority=2 for Tx only through TxQ=3:
 $ xdpsock -i eth0 -t -N -z -q 3 -V -J 10 -K 2

If VLAN ID (-J) and Priority (-K) is set, it default to
  VLAN ID = 1
  VLAN Priority = 0.

For example, VLAN-tagged Tx only, xdp copy mode through TxQ=1:
 $ xdpsock -i eth0 -t -N -c -q 1 -V

Signed-off-by: Ong Boon Leong <redacted>

Acked-by: Song Liu <redacted>

On Wed, Nov 24, 2021 at 1:22 AM Ong Boon Leong [off-list ref] wrote:

Tx cycle time is in micro-seconds unit. By combining the batch size (-b M)
and Tx cycle time (-T|--tx-cycle N), xdpsock now can transmit batch-size of
packets every N-us periodically.

For example to transmit 1 packet each 1ms cycle time for total of 2000000
packets:

 $ xdpsock -i eth0 -T -N -z -T 1000 -b 1 -C 2000000

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1996872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1997872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1998872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 1000           1999872

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 128            2000000

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           0.00
rx                 0              0
tx                 0              2000000

Signed-off-by: Ong Boon Leong <redacted>

Acked-by: Song Liu <redacted>

On 24/11/2021 10.18, Ong Boon Leong wrote:

Why/how is this connected with the 'opt_interval' ?

(Which is used by the pthtread 'poller' dumping stats)

+	} while (pending && retries-- > 0);
  }
  
  static void tx_only_all(void)

On 24/11/2021 10.18, Ong Boon Leong wrote:

To set Dest MAC address (-G|--tx-dmac) only:
  $ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff

To set Source MAC address (-H|--tx-smac) only:
  $ xdpsock -i eth0 -t -N -z -H 11:22:33:44:55:66

To set both Dest and Source MAC address:
  $ xdpsock -i eth0 -t -N -z -G aa:bb:cc:dd:ee:ff \
    -H 11:22:33:44:55:66

The default Dest and Source MAC address remain the same as before.

Signed-off-by: Ong Boon Leong<redacted>
---
  samples/bpf/xdpsock_user.c | 36 +++++++++++++++++++++++++++++++-----
  1 file changed, 31 insertions(+), 5 deletions(-)

Acked-by: Jesper Dangaard Brouer <redacted>

On 24/11/2021 10.18, Ong Boon Leong wrote:

Tx cycle time is in micro-seconds unit. By combining the batch size (-b M)
and Tx cycle time (-T|--tx-cycle N), xdpsock now can transmit batch-size of
packets every N-us periodically.

Does this also work for --poll mode (which is a wakeup mode) ?

Converting to nanosec, right(?).

So, this test is actively spinning until the time is reached, spending 
100% CPU time on this. I guess we can have this as a test for most 
accurate transmit (cyclic period) with AF_XDP.

Do you have a use-case for this?

I have a customer use-case, but my customer don't want to actively spin.
My plan is to use clock_nanosleep() and wakeup slightly before the 
target time and then we can spin shortly for the Tx time slot.

I will need to code this up for the customer soon anyway... perhaps we 
can extend your code with this idea?

I have coded the period cycle Tx with UDP packets, here[1], if you like 
to see some code using clock_nanosleep().  Next step (for me) is doing 
this for AF_XDP (likely in my example[2].

[1] 
https://github.com/netoptimizer/network-testing/blob/master/src/udp_pacer.c

[2] 
https://github.com/xdp-project/bpf-examples/tree/master/AF_XDP-interaction

+
+		xsk->prev_tx_time = now;

Would it be valuable to know how-much we shoot "over" the tx_cycle_time?

For my use-case, I will be monitoring the other-side receiving the 
packets (and using HW RX-time) to evaluate how accurate my sender is. In 
this case, I would like to know if my software "knew" if was not 100% 
accurate.

+	}
+
  	while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) <
  				      batch_size) {
  		complete_tx_only(xsk, batch_size);
  		if (benchmark_done)
-			return;
+			return 0;
  	}

I wonder if this step can introduce jitter/delay before the actual Tx 
happens?

I mean, the real transmit cannot happen before xsk_ring_prod__submit() 
is called.  If the cycles spend are exactly the same, it doesn't matter 
if you tx_cycle_time timestamp is done above.
Here you have a potential call to complete_tx_only(), which can 
introduce variance for your period.

I will suggest moving the TX completion handling, so it doesn't 
interfere with accurate TX.

On Wed, Nov 24, 2021 at 1:22 AM Ong Boon Leong
[off-list ref] wrote:

quoted

When user sets tx-pkt-count and in case where there are invalid Tx frame,
the complete_tx_only_all() process polls indefinitely. So, this patch
adds a time-out mechanism into the process so that the application
can terminate automatically after it retries 3*polling interval duration.

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 136383         1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         35             245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      957            7011

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7012

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7013

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      1              7014

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           1.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      0              7014

 sock0@enp0s29f1:2 txonly xdp-drv
                   pps            pkts           0.00
rx                 0              0
tx                 0              1000000
rx dropped         0              0
rx invalid         0              0
tx invalid         0              245
rx queue full      0              0
fill ring empty    0              1
tx ring empty      0              7014

I am not following why we need examples above in the commit log.

I pasted the log to demonstrate the behavior of the time-out, that is
aligned with the stats poller. Will remove in next rev.

quoted

Signed-off-by: Ong Boon Leong <redacted>
---
 samples/bpf/xdpsock_user.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 61d4063f11a..9c3311329ec 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c

@@ -1410,6 +1410,7 @@ static inline int get_batch_size(int pkt_cnt)

 static void complete_tx_only_all(void)
 {
+       u32 retries = 3;

Shall we make the retry value configurable? And maybe make it a timeout
value in seconds?

OK, next rev will have seconds granularity. Ok, I can make it configurable. 

quoted

  static void complete_tx_only_all(void)
  {
+	u32 retries = 3;
  	bool pending;
  	int i;

@@ -1421,7 +1422,8 @@ static void complete_tx_only_all(void)
  				pending = !!xsks[i]->outstanding_tx;
  			}
  		}
-	} while (pending);
+		sleep(opt_interval);

Why/how is this connected with the 'opt_interval' ?

(Which is used by the pthtread 'poller' dumping stats)

The original thought was to use the poller interval since
it is what user would experience from terminal. In next rev,
I plan to make it configurable with second granularity as
suggested by Song Liu.

Thanks