test_xsk.c (revision 91ec2035134982b98fab0609a9fd8480e8217dc1) - OpenGrok cross reference for /linux/tools/testing/selftests/bpf/prog_tests/test_xsk.c

// SPDX-License-Identifier: GPL-2.0
#include <bpf/bpf.h>
#include <errno.h>
#include <linux/bitmap.h>
#include <linux/if_link.h>
#include <linux/mman.h>
#include <linux/netdev.h>
#include <poll.h>
#include <pthread.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/socket.h>
#include <sys/time.h>
#include <unistd.h>

#include "network_helpers.h"
#include "test_xsk.h"
#include "xsk_xdp_common.h"
#include "xsk_xdp_progs.skel.h"

#define DEFAULT_BATCH_SIZE		64
#define MIN_PKT_SIZE			64
#define MAX_ETH_JUMBO_SIZE		9000
#define MAX_INTERFACES			2
#define MAX_TEARDOWN_ITER		10
#define MAX_TX_BUDGET_DEFAULT		32
#define PKT_DUMP_NB_TO_PRINT		16
/* Just to align the data in the packet */
#define PKT_HDR_SIZE			(sizeof(struct ethhdr) + 2)
#define POLL_TMOUT			1000
#define THREAD_TMOUT			3
#define UMEM_HEADROOM_TEST_SIZE		128
#define XSK_DESC__INVALID_OPTION	(0xffff)
#define XSK_UMEM__INVALID_FRAME_SIZE	(MAX_ETH_JUMBO_SIZE + 1)
#define XSK_UMEM__LARGE_FRAME_SIZE	(3 * 1024)
#define XSK_UMEM__MAX_FRAME_SIZE	(4 * 1024)

static const u8 g_mac[ETH_ALEN] = {0x55, 0x44, 0x33, 0x22, 0x11, 0x00};

bool opt_verbose;
pthread_barrier_t barr;
pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER;

int pkts_in_flight;

/* The payload is a word consisting of a packet sequence number in the upper
 * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's
 * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0.
 */
static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size)
{
	u32 *ptr = (u32 *)dest, i;

	start /= sizeof(*ptr);
	size /= sizeof(*ptr);
	for (i = 0; i < size; i++)
		ptr[i] = htonl(pkt_nb << 16 | (i + start));
}

static void gen_eth_hdr(struct xsk_socket_info *xsk, struct ethhdr *eth_hdr)
{
	memcpy(eth_hdr->h_dest, xsk->dst_mac, ETH_ALEN);
	memcpy(eth_hdr->h_source, xsk->src_mac, ETH_ALEN);
	eth_hdr->h_proto = htons(ETH_P_LOOPBACK);
}

static u32 mode_to_xdp_flags(enum test_mode mode)
{
	return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE;
}

static u64 umem_size(struct xsk_umem_info *umem)
{
	return umem->num_frames * umem->frame_size;
}

int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer,
			      u64 size)
{
	struct xsk_umem_config cfg = {
		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
		.frame_size = umem->frame_size,
		.frame_headroom = umem->frame_headroom,
		.flags = XSK_UMEM__DEFAULT_FLAGS
	};
	int ret;

	if (umem->fill_size)
		cfg.fill_size = umem->fill_size;

	if (umem->comp_size)
		cfg.comp_size = umem->comp_size;

	if (umem->unaligned_mode)
		cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG;

	ret = xsk_umem__create(&umem->umem, buffer, size,
			       &umem->fq, &umem->cq, &cfg);
	if (ret)
		return ret;

	umem->buffer = buffer;
	if (ifobj->shared_umem && ifobj->rx_on) {
		umem->base_addr = umem_size(umem);
		umem->next_buffer = umem_size(umem);
	}

	return 0;
}

static u64 umem_alloc_buffer(struct xsk_umem_info *umem)
{
	u64 addr;

	addr = umem->next_buffer;
	umem->next_buffer += umem->frame_size;
	if (umem->next_buffer >= umem->base_addr + umem_size(umem))
		umem->next_buffer = umem->base_addr;

	return addr;
}

static void umem_reset_alloc(struct xsk_umem_info *umem)
{
	umem->next_buffer = 0;
}

static int enable_busy_poll(struct xsk_socket_info *xsk)
{
	int sock_opt;

	sock_opt = 1;
	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL,
		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
		return -errno;

	sock_opt = 20;
	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL,
		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
		return -errno;

	sock_opt = xsk->batch_size;
	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET,
		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
		return -errno;

	return 0;
}

int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
				  struct ifobject *ifobject, bool shared)
{
	struct xsk_socket_config cfg = {};
	struct xsk_ring_cons *rxr;
	struct xsk_ring_prod *txr;

	xsk->umem = umem;
	cfg.rx_size = xsk->rxqsize;
	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
	cfg.bind_flags = ifobject->bind_flags;
	if (shared)
		cfg.bind_flags |= XDP_SHARED_UMEM;
	if (ifobject->mtu > MAX_ETH_PKT_SIZE)
		cfg.bind_flags |= XDP_USE_SG;
	if (umem->comp_size)
		cfg.tx_size = umem->comp_size;
	if (umem->fill_size)
		cfg.rx_size = umem->fill_size;

	txr = ifobject->tx_on ? &xsk->tx : NULL;
	rxr = ifobject->rx_on ? &xsk->rx : NULL;
	return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg);
}

static int set_ring_size(struct ifobject *ifobj)
{
	int ret;
	u32 ctr = 0;

	while (ctr++ < SOCK_RECONF_CTR) {
		ret = set_hw_ring_size(ifobj->ifname, &ifobj->ring);
		if (!ret)
			break;

		/* Retry if it fails */
		if (ctr >= SOCK_RECONF_CTR || errno != EBUSY)
			return -errno;

		usleep(USLEEP_MAX);
	}

	return ret;
}

int hw_ring_size_reset(struct ifobject *ifobj)
{
	ifobj->ring.tx_pending = ifobj->set_ring.default_tx;
	ifobj->ring.rx_pending = ifobj->set_ring.default_rx;
	return set_ring_size(ifobj);
}

static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
			     struct ifobject *ifobj_rx)
{
	u32 i, j;

	for (i = 0; i < MAX_INTERFACES; i++) {
		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
		struct xsk_umem_info *umem_real;

		ifobj->xsk = &ifobj->xsk_arr[0];
		ifobj->use_poll = false;
		ifobj->use_fill_ring = true;
		ifobj->release_rx = true;
		ifobj->validation_func = NULL;
		ifobj->use_metadata = false;

		if (i == 0) {
			ifobj->rx_on = false;
			ifobj->tx_on = true;
		} else {
			ifobj->rx_on = true;
			ifobj->tx_on = false;
		}

		umem_real = ifobj->xsk_arr[0].umem_real;
		memset(umem_real, 0, sizeof(*umem_real));
		for (j = 0; j < MAX_SOCKETS; j++) {
			struct xsk_socket_info *xsk = &ifobj->xsk_arr[j];

			memset(xsk, 0, sizeof(*xsk));
			xsk->rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
			if (j == 0)
				xsk->umem_real = umem_real;
			xsk->umem = umem_real;
			xsk->batch_size = DEFAULT_BATCH_SIZE;
			if (i == 0)
				xsk->pkt_stream = test->tx_pkt_stream_default;
			else
				xsk->pkt_stream = test->rx_pkt_stream_default;

			memcpy(xsk->src_mac, g_mac, ETH_ALEN);
			memcpy(xsk->dst_mac, g_mac, ETH_ALEN);
			xsk->src_mac[5] += ((j * 2) + 0);
			xsk->dst_mac[5] += ((j * 2) + 1);
		}

		ifobj->xsk->umem->num_frames = DEFAULT_UMEM_BUFFERS;
		ifobj->xsk->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
	}

	if (ifobj_tx->hw_ring_size_supp)
		hw_ring_size_reset(ifobj_tx);

	test->ifobj_tx = ifobj_tx;
	test->ifobj_rx = ifobj_rx;
	test->current_step = 0;
	test->total_steps = 1;
	test->nb_sockets = 1;
	test->fail = false;
	test->set_ring = false;
	test->adjust_tail = false;
	test->adjust_tail_support = false;
	test->mtu = MAX_ETH_PKT_SIZE;
	test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog;
	test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk;
	test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog;
	test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk;
}

void test_init(struct test_spec *test, struct ifobject *ifobj_tx,
			   struct ifobject *ifobj_rx, enum test_mode mode,
			   const struct test_spec *test_to_run)
{
	struct pkt_stream *tx_pkt_stream;
	struct pkt_stream *rx_pkt_stream;
	u32 i;

	tx_pkt_stream = test->tx_pkt_stream_default;
	rx_pkt_stream = test->rx_pkt_stream_default;
	memset(test, 0, sizeof(*test));
	test->tx_pkt_stream_default = tx_pkt_stream;
	test->rx_pkt_stream_default = rx_pkt_stream;

	for (i = 0; i < MAX_INTERFACES; i++) {
		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;

		ifobj->bind_flags = XDP_USE_NEED_WAKEUP;
		if (mode == TEST_MODE_ZC)
			ifobj->bind_flags |= XDP_ZEROCOPY;
		else
			ifobj->bind_flags |= XDP_COPY;
	}

	memcpy(test->name, test_to_run->name, MAX_TEST_NAME_SIZE);
	test->test_func = test_to_run->test_func;
	test->mode = mode;
	__test_spec_init(test, ifobj_tx, ifobj_rx);
}

static void test_spec_reset(struct test_spec *test)
{
	__test_spec_init(test, test->ifobj_tx, test->ifobj_rx);
}

static void test_spec_set_unaligned(struct test_spec *test)
{
	test->ifobj_tx->xsk->umem->unaligned_mode = true;
	test->ifobj_rx->xsk->umem->unaligned_mode = true;
}

static void test_spec_set_frame_size(struct test_spec *test, u32 size)
{
	test->ifobj_tx->xsk->umem->frame_size = size;
	test->ifobj_rx->xsk->umem->frame_size = size;
}

static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx,
				   struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx,
				   struct bpf_map *xskmap_tx)
{
	test->xdp_prog_rx = xdp_prog_rx;
	test->xdp_prog_tx = xdp_prog_tx;
	test->xskmap_rx = xskmap_rx;
	test->xskmap_tx = xskmap_tx;
}

static int test_spec_set_mtu(struct test_spec *test, int mtu)
{
	int err;

	if (test->ifobj_rx->mtu != mtu) {
		err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu);
		if (err)
			return err;
		test->ifobj_rx->mtu = mtu;
	}
	if (test->ifobj_tx->mtu != mtu) {
		err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu);
		if (err)
			return err;
		test->ifobj_tx->mtu = mtu;
	}

	return 0;
}

void pkt_stream_reset(struct pkt_stream *pkt_stream)
{
	if (pkt_stream) {
		pkt_stream->current_pkt_nb = 0;
		pkt_stream->nb_rx_pkts = 0;
	}
}

static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream)
{
	if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts)
		return NULL;

	return &pkt_stream->pkts[pkt_stream->current_pkt_nb++];
}

static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent)
{
	while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) {
		(*pkts_sent)++;
		if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid)
			return &pkt_stream->pkts[pkt_stream->current_pkt_nb++];
		pkt_stream->current_pkt_nb++;
	}
	return NULL;
}

void pkt_stream_delete(struct pkt_stream *pkt_stream)
{
	free(pkt_stream->pkts);
	free(pkt_stream);
}

void pkt_stream_restore_default(struct test_spec *test)
{
	struct pkt_stream *tx_pkt_stream = test->ifobj_tx->xsk->pkt_stream;
	struct pkt_stream *rx_pkt_stream = test->ifobj_rx->xsk->pkt_stream;

	if (tx_pkt_stream != test->tx_pkt_stream_default) {
		pkt_stream_delete(test->ifobj_tx->xsk->pkt_stream);
		test->ifobj_tx->xsk->pkt_stream = test->tx_pkt_stream_default;
	}

	if (rx_pkt_stream != test->rx_pkt_stream_default) {
		pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream);
		test->ifobj_rx->xsk->pkt_stream = test->rx_pkt_stream_default;
	}
}

static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts)
{
	struct pkt_stream *pkt_stream;

	pkt_stream = calloc(1, sizeof(*pkt_stream));
	if (!pkt_stream)
		return NULL;

	pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts));
	if (!pkt_stream->pkts) {
		free(pkt_stream);
		return NULL;
	}

	pkt_stream->nb_pkts = nb_pkts;
	return pkt_stream;
}

static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt)
{
	u32 nb_frags = 1, next_frag;

	if (!pkt)
		return 1;

	if (!pkt_stream->verbatim) {
		if (!pkt->valid || !pkt->len)
			return 1;
		return ceil_u32(pkt->len, frame_size);
	}

	/* Search for the end of the packet in verbatim mode */
	if (!pkt_continues(pkt->options))
		return nb_frags;

	next_frag = pkt_stream->current_pkt_nb;
	pkt++;
	while (next_frag++ < pkt_stream->nb_pkts) {
		nb_frags++;
		if (!pkt_continues(pkt->options))
			break;
		pkt++;
	}
	return nb_frags;
}

static bool set_pkt_valid(int offset, u32 len)
{
	return len <= MAX_ETH_JUMBO_SIZE;
}

static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len)
{
	pkt->offset = offset;
	pkt->len = len;
	pkt->valid = set_pkt_valid(offset, len);
}

static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len)
{
	bool prev_pkt_valid = pkt->valid;

	pkt_set(pkt_stream, pkt, offset, len);
	pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid;
}

static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len)
{
	return ceil_u32(len, umem->frame_size) * umem->frame_size;
}

static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb_start, u32 nb_off)
{
	struct pkt_stream *pkt_stream;
	u32 i;

	pkt_stream = __pkt_stream_alloc(nb_pkts);
	if (!pkt_stream)
		return NULL;

	pkt_stream->nb_pkts = nb_pkts;
	pkt_stream->max_pkt_len = pkt_len;
	for (i = 0; i < nb_pkts; i++) {
		struct pkt *pkt = &pkt_stream->pkts[i];

		pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len);
		pkt->pkt_nb = nb_start + i * nb_off;
	}

	return pkt_stream;
}

struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
{
	return __pkt_stream_generate(nb_pkts, pkt_len, 0, 1);
}

static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream)
{
	return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
}

static int pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len)
{
	ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);

	if (!ifobj->xsk->pkt_stream)
		return -ENOMEM;

	return 0;
}

static int pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
{
	int ret;

	ret = pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len);
	if (ret)
		return ret;

	return pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len);
}

static int __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
				      int offset)
{
	struct pkt_stream *pkt_stream;
	u32 i;

	pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream);
	if (!pkt_stream)
		return -ENOMEM;

	for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2)
		pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len);

	ifobj->xsk->pkt_stream = pkt_stream;

	return 0;
}

static int pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset)
{
	int ret = __pkt_stream_replace_half(test->ifobj_tx, pkt_len, offset);

	if (ret)
		return ret;

	return __pkt_stream_replace_half(test->ifobj_rx, pkt_len, offset);
}

static int pkt_stream_receive_half(struct test_spec *test)
{
	struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream;
	u32 i;

	if (test->ifobj_rx->xsk->pkt_stream != test->rx_pkt_stream_default)
		/* Packet stream has already been replaced so we have to release this one.
		 * The newly created one will be freed by the restore_default() at the
		 * end of the test
		 */
		pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream);

	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(pkt_stream->nb_pkts,
							      pkt_stream->pkts[0].len);
	if (!test->ifobj_rx->xsk->pkt_stream)
		return -ENOMEM;

	pkt_stream = test->ifobj_rx->xsk->pkt_stream;
	for (i = 1; i < pkt_stream->nb_pkts; i += 2)
		pkt_stream->pkts[i].valid = false;

	pkt_stream->nb_valid_entries /= 2;

	return 0;
}

static int pkt_stream_even_odd_sequence(struct test_spec *test)
{
	struct pkt_stream *pkt_stream;
	u32 i;

	for (i = 0; i < test->nb_sockets; i++) {
		pkt_stream = test->ifobj_tx->xsk_arr[i].pkt_stream;
		pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2,
						   pkt_stream->pkts[0].len, i, 2);
		if (!pkt_stream)
			return -ENOMEM;
		test->ifobj_tx->xsk_arr[i].pkt_stream = pkt_stream;

		pkt_stream = test->ifobj_rx->xsk_arr[i].pkt_stream;
		pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2,
						   pkt_stream->pkts[0].len, i, 2);
		if (!pkt_stream)
			return -ENOMEM;
		test->ifobj_rx->xsk_arr[i].pkt_stream = pkt_stream;
	}

	return 0;
}

static void release_even_odd_sequence(struct test_spec *test)
{
	struct pkt_stream *later_free_tx = test->ifobj_tx->xsk->pkt_stream;
	struct pkt_stream *later_free_rx = test->ifobj_rx->xsk->pkt_stream;
	int i;

	for (i = 0; i < test->nb_sockets; i++) {
		/* later_free_{rx/tx} will be freed by restore_default() */
		if (test->ifobj_tx->xsk_arr[i].pkt_stream != later_free_tx)
			pkt_stream_delete(test->ifobj_tx->xsk_arr[i].pkt_stream);
		if (test->ifobj_rx->xsk_arr[i].pkt_stream != later_free_rx)
			pkt_stream_delete(test->ifobj_rx->xsk_arr[i].pkt_stream);
	}

}

static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem)
{
	if (!pkt->valid)
		return pkt->offset;
	return pkt->offset + umem_alloc_buffer(umem);
}

static void pkt_stream_cancel(struct pkt_stream *pkt_stream)
{
	pkt_stream->current_pkt_nb--;
}

static void pkt_generate(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, u64 addr, u32 len,
			 u32 pkt_nb, u32 bytes_written)
{
	void *data = xsk_umem__get_data(umem->buffer, addr);

	if (len < MIN_PKT_SIZE)
		return;

	if (!bytes_written) {
		gen_eth_hdr(xsk, data);

		len -= PKT_HDR_SIZE;
		data += PKT_HDR_SIZE;
	} else {
		bytes_written -= PKT_HDR_SIZE;
	}

	write_payload(data, pkt_nb, bytes_written, len);
}

static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames,
						       u32 nb_frames, bool verbatim)
{
	u32 i, len = 0, pkt_nb = 0, payload = 0;
	struct pkt_stream *pkt_stream;

	pkt_stream = __pkt_stream_alloc(nb_frames);
	if (!pkt_stream)
		return NULL;

	for (i = 0; i < nb_frames; i++) {
		struct pkt *pkt = &pkt_stream->pkts[pkt_nb];
		struct pkt *frame = &frames[i];

		pkt->offset = frame->offset;
		if (verbatim) {
			*pkt = *frame;
			pkt->pkt_nb = payload;
			if (!frame->valid || !pkt_continues(frame->options))
				payload++;
		} else {
			if (frame->valid) {
				len += frame->len;
				if (pkt_continues(frame->options))
					continue;
			}
			pkt->pkt_nb = pkt_nb;
			pkt->len = len;
			pkt->valid = frame->valid;
			pkt->options = 0;

			len = 0;
		}

		print_verbose("offset: %d len: %u valid: %u options: %u pkt_nb: %u\n",
			      pkt->offset, pkt->len, pkt->valid, pkt->options, pkt->pkt_nb);

		if (pkt->valid && pkt->len > pkt_stream->max_pkt_len)
			pkt_stream->max_pkt_len = pkt->len;

		if (pkt->valid)
			pkt_stream->nb_valid_entries++;

		pkt_nb++;
	}

	pkt_stream->nb_pkts = pkt_nb;
	pkt_stream->verbatim = verbatim;
	return pkt_stream;
}

static int pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts)
{
	struct pkt_stream *pkt_stream;

	pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true);
	if (!pkt_stream)
		return -ENOMEM;
	test->ifobj_tx->xsk->pkt_stream = pkt_stream;

	pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false);
	if (!pkt_stream)
		return -ENOMEM;
	test->ifobj_rx->xsk->pkt_stream = pkt_stream;

	return 0;
}

static void pkt_print_data(u32 *data, u32 cnt)
{
	u32 i;

	for (i = 0; i < cnt; i++) {
		u32 seqnum, pkt_nb;

		seqnum = ntohl(*data) & 0xffff;
		pkt_nb = ntohl(*data) >> 16;
		ksft_print_msg("%u:%u ", pkt_nb, seqnum);
		data++;
	}
}

static void pkt_dump(void *pkt, u32 len, bool eth_header)
{
	struct ethhdr *ethhdr = pkt;
	u32 i, *data;

	if (eth_header) {
		/*extract L2 frame */
		ksft_print_msg("DEBUG>> L2: dst mac: ");
		for (i = 0; i < ETH_ALEN; i++)
			ksft_print_msg("%02X", ethhdr->h_dest[i]);

		ksft_print_msg("\nDEBUG>> L2: src mac: ");
		for (i = 0; i < ETH_ALEN; i++)
			ksft_print_msg("%02X", ethhdr->h_source[i]);

		data = pkt + PKT_HDR_SIZE;
	} else {
		data = pkt;
	}

	/*extract L5 frame */
	ksft_print_msg("\nDEBUG>> L5: seqnum: ");
	pkt_print_data(data, PKT_DUMP_NB_TO_PRINT);
	ksft_print_msg("....");
	if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) {
		ksft_print_msg("\n.... ");
		pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT,
			       PKT_DUMP_NB_TO_PRINT);
	}
	ksft_print_msg("\n---------------------------------------\n");
}

static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr)
{
	u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom;
	u32 offset = addr % umem->frame_size, expected_offset;
	int pkt_offset = pkt->valid ? pkt->offset : 0;

	if (!umem->unaligned_mode)
		pkt_offset = 0;

	expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size;

	if (offset == expected_offset)
		return true;

	ksft_print_msg("[%s] expected [%u], got [%u]\n", __func__, expected_offset, offset);
	return false;
}

static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
{
	void *data = xsk_umem__get_data(buffer, addr);
	struct xdp_info *meta = data - sizeof(struct xdp_info);

	if (meta->count != pkt->pkt_nb) {
		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n",
			       __func__, pkt->pkt_nb,
			       (unsigned long long)meta->count);
		return false;
	}

	return true;
}

static int is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx, bool *supported)
{
	struct bpf_map *data_map;
	int adjust_value = 0;
	int key = 0;
	int ret;

	data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss");
	if (!data_map || !bpf_map__is_internal(data_map)) {
		ksft_print_msg("Error: could not find bss section of XDP program\n");
		return -EINVAL;
	}

	ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value);
	if (ret) {
		ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret);
		return ret;
	}

	/* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail
	 * helper is not supported. Skip the adjust_tail test case in this scenario.
	 */
	*supported = adjust_value != -EOPNOTSUPP;

	return 0;
}

static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb,
			  u32 bytes_processed)
{
	u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum;
	void *data = xsk_umem__get_data(umem->buffer, addr);
	u64 umem_sz = umem_size(umem);

	addr -= umem->base_addr;

	if (addr >= umem_sz || addr + len > umem_sz) {
		ksft_print_msg("Frag invalid addr: %llx len: %u\n",
			       (unsigned long long)addr, len);
		return false;
	}
	if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n",
			       (unsigned long long)addr, len);
		return false;
	}

	pkt_data = data;
	if (!bytes_processed) {
		pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data);
		len -= PKT_HDR_SIZE;
	} else {
		bytes_processed -= PKT_HDR_SIZE;
	}

	expected_seqnum = bytes_processed / sizeof(*pkt_data);
	seqnum = ntohl(*pkt_data) & 0xffff;
	pkt_nb = ntohl(*pkt_data) >> 16;

	if (expected_pkt_nb != pkt_nb) {
		ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n",
			       __func__, expected_pkt_nb, pkt_nb);
		goto error;
	}
	if (expected_seqnum != seqnum) {
		ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n",
			       __func__, expected_seqnum, seqnum);
		goto error;
	}

	words_to_end = len / sizeof(*pkt_data) - 1;
	pkt_data += words_to_end;
	seqnum = ntohl(*pkt_data) & 0xffff;
	expected_seqnum += words_to_end;
	if (expected_seqnum != seqnum) {
		ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n",
			       __func__, expected_seqnum, seqnum);
		goto error;
	}

	return true;

error:
	pkt_dump(data, len, !bytes_processed);
	return false;
}

static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
{
	if (pkt->len != len) {
		ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n",
			       __func__, pkt->len, len);
		pkt_dump(xsk_umem__get_data(buffer, addr), len, true);
		return false;
	}

	return true;
}

static u32 load_value(u32 *counter)
{
	return __atomic_load_n(counter, __ATOMIC_ACQUIRE);
}

static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret)
{
	u32 max_budget = MAX_TX_BUDGET_DEFAULT;
	u32 cons, ready_to_send;
	int delta;

	cons = load_value(xsk->tx.consumer);
	ready_to_send = load_value(xsk->tx.producer) - cons;
	*ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);

	delta = load_value(xsk->tx.consumer) - cons;
	/* By default, xsk should consume exact @max_budget descs at one
	 * send in this case where hitting the max budget limit in while
	 * loop is triggered in __xsk_generic_xmit(). Please make sure that
	 * the number of descs to be sent is larger than @max_budget, or
	 * else the tx.consumer will be updated in xskq_cons_peek_desc()
	 * in time which hides the issue we try to verify.
	 */
	if (ready_to_send > max_budget && delta != max_budget)
		return false;

	return true;
}

int kick_tx(struct xsk_socket_info *xsk)
{
	int ret;

	if (xsk->check_consumer) {
		if (!kick_tx_with_check(xsk, &ret))
			return TEST_FAILURE;
	} else {
		ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
	}
	if (ret >= 0)
		return TEST_PASS;
	if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) {
		usleep(100);
		return TEST_PASS;
	}
	return TEST_FAILURE;
}

int kick_rx(struct xsk_socket_info *xsk)
{
	int ret;

	ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL);
	if (ret < 0)
		return TEST_FAILURE;

	return TEST_PASS;
}

static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
{
	unsigned int rcvd;
	u32 idx;
	int ret;

	if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
		ret = kick_tx(xsk);
		if (ret)
			return TEST_FAILURE;
	}

	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
	if (rcvd) {
		if (rcvd > xsk->outstanding_tx) {
			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);

			ksft_print_msg("[%s] Too many packets completed\n", __func__);
			ksft_print_msg("Last completion address: %llx\n",
				       (unsigned long long)addr);
			return TEST_FAILURE;
		}

		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
		xsk->outstanding_tx -= rcvd;
	}

	return TEST_PASS;
}

static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk)
{
	u32 frags_processed = 0, nb_frags = 0, pkt_len = 0;
	u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0;
	struct pkt_stream *pkt_stream = xsk->pkt_stream;
	struct ifobject *ifobj = test->ifobj_rx;
	struct xsk_umem_info *umem = xsk->umem;
	struct pollfd fds = { };
	struct pkt *pkt;
	u64 first_addr = 0;
	int ret;

	fds.fd = xsk_socket__fd(xsk->xsk);
	fds.events = POLLIN;

	ret = kick_rx(xsk);
	if (ret)
		return TEST_FAILURE;

	if (ifobj->use_poll) {
		ret = poll(&fds, 1, POLL_TMOUT);
		if (ret < 0)
			return TEST_FAILURE;

		if (!ret) {
			if (test->poll_tmout)
				return TEST_PASS;

			ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__);
			return TEST_CONTINUE;
		}

		if (!(fds.revents & POLLIN))
			return TEST_CONTINUE;
	}

	rcvd = xsk_ring_cons__peek(&xsk->rx, xsk->batch_size, &idx_rx);
	if (!rcvd)
		return TEST_CONTINUE;

	if (ifobj->use_fill_ring) {
		ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
		while (ret != rcvd) {
			if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
				ret = poll(&fds, 1, POLL_TMOUT);
				if (ret < 0)
					return TEST_FAILURE;
			}
			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
		}
	}

	while (frags_processed < rcvd) {
		const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
		u64 addr = desc->addr, orig;

		orig = xsk_umem__extract_addr(addr);
		addr = xsk_umem__add_offset_to_addr(addr);

		if (!nb_frags) {
			pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
			if (!pkt) {
				ksft_print_msg("[%s] received too many packets addr: %lx len %u\n",
					       __func__, addr, desc->len);
				return TEST_FAILURE;
			}
		}

		print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n",
			      addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid);

		if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) ||
		    !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata &&
		    !is_metadata_correct(pkt, umem->buffer, addr)))
			return TEST_FAILURE;

		if (!nb_frags++)
			first_addr = addr;
		frags_processed++;
		pkt_len += desc->len;
		if (ifobj->use_fill_ring)
			*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;

		if (pkt_continues(desc->options))
			continue;

		/* The complete packet has been received */
		if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) ||
		    !is_offset_correct(umem, pkt, addr))
			return TEST_FAILURE;

		pkt_stream->nb_rx_pkts++;
		nb_frags = 0;
		pkt_len = 0;
	}

	if (nb_frags) {
		/* In the middle of a packet. Start over from beginning of packet. */
		idx_rx -= nb_frags;
		xsk_ring_cons__cancel(&xsk->rx, nb_frags);
		if (ifobj->use_fill_ring) {
			idx_fq -= nb_frags;
			xsk_ring_prod__cancel(&umem->fq, nb_frags);
		}
		frags_processed -= nb_frags;
		pkt_stream_cancel(pkt_stream);
		pkts_sent--;
	}

	if (ifobj->use_fill_ring)
		xsk_ring_prod__submit(&umem->fq, frags_processed);
	if (ifobj->release_rx)
		xsk_ring_cons__release(&xsk->rx, frags_processed);

	pthread_mutex_lock(&pacing_mutex);
	pkts_in_flight -= pkts_sent;
	pthread_mutex_unlock(&pacing_mutex);
	pkts_sent = 0;

	return TEST_CONTINUE;
}

bool all_packets_received(struct test_spec *test, struct xsk_socket_info *xsk, u32 sock_num,
			  unsigned long *bitmap)
{
	struct pkt_stream *pkt_stream = xsk->pkt_stream;

	if (!pkt_stream) {
		__set_bit(sock_num, bitmap);
		return false;
	}

	if (pkt_stream->nb_rx_pkts == pkt_stream->nb_valid_entries) {
		__set_bit(sock_num, bitmap);
		if (bitmap_full(bitmap, test->nb_sockets))
			return true;
	}

	return false;
}

static int receive_pkts(struct test_spec *test)
{
	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
	DECLARE_BITMAP(bitmap, test->nb_sockets);
	struct xsk_socket_info *xsk;
	u32 sock_num = 0;
	int res, ret;

	bitmap_zero(bitmap, test->nb_sockets);

	ret = gettimeofday(&tv_now, NULL);
	if (ret)
		return TEST_FAILURE;

	timeradd(&tv_now, &tv_timeout, &tv_end);

	while (1) {
		xsk = &test->ifobj_rx->xsk_arr[sock_num];

		if ((all_packets_received(test, xsk, sock_num, bitmap)))
			break;

		res = __receive_pkts(test, xsk);
		if (res != TEST_CONTINUE)
			return res;

		ret = gettimeofday(&tv_now, NULL);
		if (ret)
			return TEST_FAILURE;

		if (timercmp(&tv_now, &tv_end, >)) {
			ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__);
			return TEST_FAILURE;
		}
		sock_num = (sock_num + 1) % test->nb_sockets;
	}

	return TEST_PASS;
}

static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk,
		       bool test_timeout)
{
	u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len;
	struct xsk_umem_info *umem = ifobject->xsk_arr[0].umem_real;
	struct pkt_stream *pkt_stream = xsk->pkt_stream;
	bool use_poll = ifobject->use_poll;
	struct pollfd fds = { };
	int ret;

	buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len);
	/* pkts_in_flight might be negative if many invalid packets are sent */
	if (pkts_in_flight >= (int)((umem_size(umem) - xsk->batch_size * buffer_len) /
	    buffer_len) && !test_timeout) {
		ret = kick_tx(xsk);
		if (ret)
			return TEST_FAILURE;
		return TEST_CONTINUE;
	}

	fds.fd = xsk_socket__fd(xsk->xsk);
	fds.events = POLLOUT;

	while (xsk_ring_prod__reserve(&xsk->tx, xsk->batch_size, &idx) < xsk->batch_size) {
		if (use_poll) {
			ret = poll(&fds, 1, POLL_TMOUT);
			if (test_timeout) {
				if (ret < 0) {
					ksft_print_msg("ERROR: [%s] Poll error %d\n",
						       __func__, errno);
					return TEST_FAILURE;
				}
				if (ret == 0)
					return TEST_PASS;
				break;
			}
			if (ret <= 0) {
				ksft_print_msg("ERROR: [%s] Poll error %d\n",
					       __func__, errno);
				return TEST_FAILURE;
			}
		}

		complete_pkts(xsk, xsk->batch_size);
	}

	for (i = 0; i < xsk->batch_size; i++) {
		struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream);
		u32 nb_frags_left, nb_frags, bytes_written = 0;

		if (!pkt)
			break;

		nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt);
		if (nb_frags > xsk->batch_size - i) {
			pkt_stream_cancel(pkt_stream);
			xsk_ring_prod__cancel(&xsk->tx, xsk->batch_size - i);
			break;
		}
		nb_frags_left = nb_frags;

		while (nb_frags_left--) {
			struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);

			tx_desc->addr = pkt_get_addr(pkt, umem);
			if (pkt_stream->verbatim) {
				tx_desc->len = pkt->len;
				tx_desc->options = pkt->options;
			} else if (nb_frags_left) {
				tx_desc->len = umem->frame_size;
				tx_desc->options = XDP_PKT_CONTD;
			} else {
				tx_desc->len = pkt->len - bytes_written;
				tx_desc->options = 0;
			}
			if (pkt->valid)
				pkt_generate(xsk, umem, tx_desc->addr, tx_desc->len, pkt->pkt_nb,
					     bytes_written);
			bytes_written += tx_desc->len;

			print_verbose("Tx addr: %llx len: %u options: %u pkt_nb: %u\n",
				      tx_desc->addr, tx_desc->len, tx_desc->options, pkt->pkt_nb);

			if (nb_frags_left) {
				i++;
				if (pkt_stream->verbatim)
					pkt = pkt_stream_get_next_tx_pkt(pkt_stream);
			}
		}

		if (pkt && pkt->valid)
			valid_pkts++;
		valid_frags += nb_frags;
	}

	pthread_mutex_lock(&pacing_mutex);
	pkts_in_flight += valid_pkts;
	pthread_mutex_unlock(&pacing_mutex);

	xsk_ring_prod__submit(&xsk->tx, i);
	xsk->outstanding_tx += valid_frags;

	if (use_poll) {
		ret = poll(&fds, 1, POLL_TMOUT);
		if (ret <= 0) {
			if (ret == 0 && test_timeout)
				return TEST_PASS;

			ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret);
			return TEST_FAILURE;
		}
	}

	if (!test_timeout) {
		if (complete_pkts(xsk, i))
			return TEST_FAILURE;

		usleep(10);
	}

	/* Loop completion is driven by send_pkts() stream progress checks. */
	return TEST_CONTINUE;
}

static int wait_for_tx_completion(struct xsk_socket_info *xsk)
{
	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
	int ret;

	ret = gettimeofday(&tv_now, NULL);
	if (ret)
		return TEST_FAILURE;
	timeradd(&tv_now, &tv_timeout, &tv_end);

	while (xsk->outstanding_tx) {
		ret = gettimeofday(&tv_now, NULL);
		if (ret)
			return TEST_FAILURE;
		if (timercmp(&tv_now, &tv_end, >)) {
			ksft_print_msg("ERROR: [%s] Transmission loop timed out\n", __func__);
			return TEST_FAILURE;
		}

		complete_pkts(xsk, xsk->batch_size);
	}

	return TEST_PASS;
}

bool all_packets_sent(struct test_spec *test, unsigned long *bitmap)
{
	return bitmap_full(bitmap, test->nb_sockets);
}

static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
{
	DECLARE_BITMAP(bitmap, test->nb_sockets);
	u32 i, ret;

	bitmap_zero(bitmap, test->nb_sockets);

	while (!(all_packets_sent(test, bitmap))) {
		for (i = 0; i < test->nb_sockets; i++) {
			struct pkt_stream *pkt_stream;

			pkt_stream = ifobject->xsk_arr[i].pkt_stream;
			if (!pkt_stream || pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) {
				__set_bit(i, bitmap);
				continue;
			}
			ret = __send_pkts(ifobject, &ifobject->xsk_arr[i], test->poll_tmout);
			if (ret != TEST_CONTINUE)
				return ret;

			if (test->fail)
				return TEST_FAILURE;

			if (!test->poll_tmout) {
				ret = wait_for_tx_completion(&ifobject->xsk_arr[i]);
				if (ret)
					return TEST_FAILURE;
			}
		}
	}

	return TEST_PASS;
}

static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats)
{
	int fd = xsk_socket__fd(xsk), err;
	socklen_t optlen, expected_len;

	optlen = sizeof(*stats);
	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, stats, &optlen);
	if (err) {
		ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n",
			       __func__, -err, strerror(-err));
		return TEST_FAILURE;
	}

	expected_len = sizeof(struct xdp_statistics);
	if (optlen != expected_len) {
		ksft_print_msg("[%s] getsockopt optlen error. Expected: %u got: %u\n",
			       __func__, expected_len, optlen);
		return TEST_FAILURE;
	}

	return TEST_PASS;
}

static int validate_rx_dropped(struct ifobject *ifobject)
{
	struct xsk_socket *xsk = ifobject->xsk->xsk;
	struct xdp_statistics stats;
	int err;

	err = kick_rx(ifobject->xsk);
	if (err)
		return TEST_FAILURE;

	err = get_xsk_stats(xsk, &stats);
	if (err)
		return TEST_FAILURE;

	/* The receiver calls getsockopt after receiving the last (valid)
	 * packet which is not the final packet sent in this test (valid and
	 * invalid packets are sent in alternating fashion with the final
	 * packet being invalid). Since the last packet may or may not have
	 * been dropped already, both outcomes must be allowed.
	 */
	if (stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 ||
	    stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 - 1)
		return TEST_PASS;

	return TEST_FAILURE;
}

static int validate_rx_full(struct ifobject *ifobject)
{
	struct xsk_socket *xsk = ifobject->xsk->xsk;
	struct xdp_statistics stats;
	int err;

	usleep(1000);
	err = kick_rx(ifobject->xsk);
	if (err)
		return TEST_FAILURE;

	err = get_xsk_stats(xsk, &stats);
	if (err)
		return TEST_FAILURE;

	if (stats.rx_ring_full)
		return TEST_PASS;

	return TEST_FAILURE;
}

static int validate_fill_empty(struct ifobject *ifobject)
{
	struct xsk_socket *xsk = ifobject->xsk->xsk;
	struct xdp_statistics stats;
	int err;

	usleep(1000);
	err = kick_rx(ifobject->xsk);
	if (err)
		return TEST_FAILURE;

	err = get_xsk_stats(xsk, &stats);
	if (err)
		return TEST_FAILURE;

	if (stats.rx_fill_ring_empty_descs)
		return TEST_PASS;

	return TEST_FAILURE;
}

static int validate_tx_invalid_descs(struct ifobject *ifobject)
{
	struct xsk_socket *xsk = ifobject->xsk->xsk;
	int fd = xsk_socket__fd(xsk);
	struct xdp_statistics stats;
	socklen_t optlen;
	int err;

	optlen = sizeof(stats);
	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
	if (err) {
		ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n",
			       __func__, -err, strerror(-err));
		return TEST_FAILURE;
	}

	if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n",
			       __func__,
			       (unsigned long long)stats.tx_invalid_descs,
			       ifobject->xsk->pkt_stream->nb_pkts);
		return TEST_FAILURE;
	}

	return TEST_PASS;
}

static int xsk_configure(struct test_spec *test, struct ifobject *ifobject,
			  struct xsk_umem_info *umem, bool tx)
{
	int i, ret;

	for (i = 0; i < test->nb_sockets; i++) {
		bool shared = (ifobject->shared_umem && tx) ? true : !!i;
		u32 ctr = 0;

		while (ctr++ < SOCK_RECONF_CTR) {
			ret = xsk_configure_socket(&ifobject->xsk_arr[i], umem,
						     ifobject, shared);
			if (!ret)
				break;

			/* Retry if it fails as xsk_socket__create() is asynchronous */
			if (ctr >= SOCK_RECONF_CTR)
				return ret;
			usleep(USLEEP_MAX);
		}
		if (ifobject->busy_poll) {
			ret = enable_busy_poll(&ifobject->xsk_arr[i]);
			if (ret)
				return ret;
		}
	}

	return 0;
}

static int thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobject)
{
	struct xsk_umem_info *umem_rx, *umem_tx;
	int ret;

	if (!test->ifobj_rx || !test->ifobj_rx->xsk_arr[0].umem->umem) {
		ksft_print_msg("Error: RX UMEM is not initialized before shared-UMEM TX setup\n");
		return -EINVAL;
	}

	umem_rx = test->ifobj_rx->xsk_arr[0].umem;
	umem_tx = ifobject->xsk_arr[0].umem_real;
	memcpy(umem_tx, umem_rx, sizeof(*umem_tx));
	umem_tx->base_addr = 0;
	umem_tx->next_buffer = 0;

	ret = xsk_configure(test, ifobject, umem_rx, true);
	if (ret)
		return ret;
	ifobject->xsk = &ifobject->xsk_arr[0];
	ifobject->xskmap = test->ifobj_rx->xskmap;

	return 0;
}

static int xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream,
				   bool fill_up)
{
	u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM;
	u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts;
	int ret;

	if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS)
		buffers_to_fill = umem->num_frames;
	else
		buffers_to_fill = umem->fill_size;

	ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx);
	if (ret != buffers_to_fill)
		return -ENOSPC;

	while (filled < buffers_to_fill) {
		struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts);
		u64 addr;
		u32 i;

		for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) {
			if (!pkt) {
				if (!fill_up)
					break;
				addr = filled * umem->frame_size + umem->base_addr;
			} else if (pkt->offset >= 0) {
				addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem);
			} else {
				addr = pkt->offset + umem_alloc_buffer(umem);
			}

			*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
			if (++filled >= buffers_to_fill)
				break;
		}
	}
	xsk_ring_prod__submit(&umem->fq, filled);
	xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled);

	pkt_stream_reset(pkt_stream);
	umem_reset_alloc(umem);

	return 0;
}

static int thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
{
	struct xsk_umem_info *umem = ifobject->xsk->umem;
	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
	int mmap_flags;
	u64 umem_sz, mmap_sz;
	void *bufs;
	int ret;
	u32 i;

	umem_sz = umem_size(umem);
	mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;

	if (umem->unaligned_mode)
		mmap_flags |= MAP_HUGETLB | MAP_HUGE_2MB;

	if (ifobject->shared_umem)
		umem_sz *= 2;

	mmap_sz = umem->unaligned_mode ?
		ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE : umem_sz;

	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
	if (bufs == MAP_FAILED)
		return -errno;

	umem->mmap_size = mmap_sz;

	ret = xsk_configure_umem(ifobject, umem, bufs, umem_sz);
	if (ret)
		return ret;

	ret = xsk_configure(test, ifobject, umem, false);
	if (ret)
		return ret;

	ifobject->xsk = &ifobject->xsk_arr[0];

	if (!ifobject->rx_on)
		return 0;

	ret = xsk_populate_fill_ring(umem, ifobject->xsk->pkt_stream,
				     ifobject->use_fill_ring);
	if (ret)
		return ret;

	for (i = 0; i < test->nb_sockets; i++) {
		ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk_arr[i].xsk, i);
		if (ret)
			return ret;
	}

	return 0;
}

void *worker_testapp_validate_tx(void *arg)
{
	struct test_spec *test = (struct test_spec *)arg;
	struct ifobject *ifobject = test->ifobj_tx;
	int err;

	if (test->current_step == 1) {
		if (!ifobject->shared_umem) {
			if (thread_common_ops(test, ifobject)) {
				test->fail = true;
				pthread_exit(NULL);
			}
		} else {
			if (thread_common_ops_tx(test, ifobject)) {
				test->fail = true;
				pthread_exit(NULL);
			}
		}
	}

	err = send_pkts(test, ifobject);

	if (!err && ifobject->validation_func)
		err = ifobject->validation_func(ifobject);
	if (err)
		test->fail = true;

	pthread_exit(NULL);
}

void *worker_testapp_validate_rx(void *arg)
{
	struct test_spec *test = (struct test_spec *)arg;
	struct ifobject *ifobject = test->ifobj_rx;
	int err;

	if (test->current_step == 1) {
		err = thread_common_ops(test, ifobject);
	} else {
		xsk_clear_xskmap(ifobject->xskmap);
		err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0);
		if (err)
			ksft_print_msg("Error: Failed to update xskmap, error %s\n",
				       strerror(-err));
	}

	if (test->use_barrier)
		pthread_barrier_wait(&barr);

	/* We leave only now in case of error to avoid getting stuck in the barrier */
	if (err) {
		test->fail = true;
		pthread_exit(NULL);
	}

	err = receive_pkts(test);

	if (!err && ifobject->validation_func)
		err = ifobject->validation_func(ifobject);

	if (err) {
		if (!test->adjust_tail) {
			test->fail = true;
		} else {
			bool supported;

			if (is_adjust_tail_supported(ifobject->xdp_progs, &supported))
				test->fail = true;
			else if (!supported)
				test->adjust_tail_support = false;
			else
				test->fail = true;
		}
	}

	pthread_exit(NULL);
}

static void testapp_clean_xsk_umem(struct ifobject *ifobj)
{
	struct xsk_umem_info *umem = ifobj->xsk->umem;

	xsk_umem__delete(umem->umem);
	munmap(umem->buffer, umem->mmap_size);
}

static bool xdp_prog_changed_rx(struct test_spec *test)
{
	struct ifobject *ifobj = test->ifobj_rx;

	return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode;
}

static bool xdp_prog_changed_tx(struct test_spec *test)
{
	struct ifobject *ifobj = test->ifobj_tx;

	return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode;
}

static int xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog,
			     struct bpf_map *xskmap, enum test_mode mode)
{
	int err;

	xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode));
	err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode));
	if (err) {
		ksft_print_msg("Error attaching XDP program\n");
		return err;
	}

	if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC))
		if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) {
			ksft_print_msg("ERROR: XDP prog not in DRV mode\n");
			return -EINVAL;
		}

	ifobj->xdp_prog = xdp_prog;
	ifobj->xskmap = xskmap;
	ifobj->mode = mode;

	return 0;
}

static int xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx,
				 struct ifobject *ifobj_tx)
{
	int err = 0;

	if (xdp_prog_changed_rx(test)) {
		err = xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode);
		if (err)
			return err;
	}

	if (!ifobj_tx || ifobj_tx->shared_umem)
		return 0;

	if (xdp_prog_changed_tx(test))
		err = xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode);

	return err;
}

static void clean_sockets(struct test_spec *test, struct ifobject *ifobj)
{
	u32 i;

	if (!ifobj || !test)
		return;

	for (i = 0; i < test->nb_sockets; i++)
		xsk_socket__delete(ifobj->xsk_arr[i].xsk);
}

static void clean_umem(struct test_spec *test, struct ifobject *ifobj1, struct ifobject *ifobj2)
{
	if (!ifobj1)
		return;

	testapp_clean_xsk_umem(ifobj1);
	if (ifobj2 && !ifobj2->shared_umem)
		testapp_clean_xsk_umem(ifobj2);
}

static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1,
				      struct ifobject *ifobj2)
{
	pthread_t t0, t1;
	int err;

	if (test->mtu > MAX_ETH_PKT_SIZE) {
		if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp ||
						   (ifobj2 && !ifobj2->multi_buff_zc_supp))) {
			ksft_print_msg("Multi buffer for zero-copy not supported.\n");
			return TEST_SKIP;
		}
		if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp ||
						   (ifobj2 && !ifobj2->multi_buff_supp))) {
			ksft_print_msg("Multi buffer not supported.\n");
			return TEST_SKIP;
		}
	}
	err = test_spec_set_mtu(test, test->mtu);
	if (err) {
		ksft_print_msg("Error, could not set mtu.\n");
		return TEST_FAILURE;
	}

	err = xsk_attach_xdp_progs(test, ifobj1, ifobj2);
	if (err) {
		ksft_print_msg("Error: failed to attach XDP programs: %d (%s)\n",
			       err, strerror(-err));
		return TEST_FAILURE;
	}
	test->use_barrier = !!ifobj2;

	if (test->use_barrier) {
		if (pthread_barrier_init(&barr, NULL, 2))
			return TEST_FAILURE;

		pkt_stream_reset(ifobj2->xsk->pkt_stream);
	}

	test->current_step++;
	pkt_stream_reset(ifobj1->xsk->pkt_stream);
	pkts_in_flight = 0;

	/*Spawn RX thread */
	pthread_create(&t0, NULL, ifobj1->func_ptr, test);

	if (test->use_barrier) {
		pthread_barrier_wait(&barr);
		if (pthread_barrier_destroy(&barr)) {
			test->use_barrier = false;
			pthread_join(t0, NULL);
			clean_sockets(test, ifobj1);
			clean_umem(test, ifobj1, NULL);
			return TEST_FAILURE;
		}
	}

	if (ifobj2) {
		/*Spawn TX thread */
		pthread_create(&t1, NULL, ifobj2->func_ptr, test);
		pthread_join(t1, NULL);
	}

	pthread_join(t0, NULL);

	if (test->total_steps == test->current_step || test->fail) {
		clean_sockets(test, ifobj1);
		clean_sockets(test, ifobj2);
		clean_umem(test, ifobj1, ifobj2);
	}

	if (test->fail)
		return TEST_FAILURE;

	return TEST_PASS;
}

static int testapp_validate_traffic(struct test_spec *test)
{
	struct ifobject *ifobj_rx = test->ifobj_rx;
	struct ifobject *ifobj_tx = test->ifobj_tx;

	if ((ifobj_rx->xsk->umem->unaligned_mode && !ifobj_rx->unaligned_supp) ||
	    (ifobj_tx->xsk->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) {
		ksft_print_msg("No huge pages present.\n");
		return TEST_SKIP;
	}

	if (test->set_ring) {
		if (ifobj_tx->hw_ring_size_supp) {
			if (set_ring_size(ifobj_tx)) {
				ksft_print_msg("Failed to change HW ring size.\n");
				return TEST_FAILURE;
			}
		} else {
			ksft_print_msg("Changing HW ring size not supported.\n");
			return TEST_SKIP;
		}
	}

	return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx);
}

static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj)
{
	return __testapp_validate_traffic(test, ifobj, NULL);
}

int testapp_teardown(struct test_spec *test)
{
	int i;

	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
		if (testapp_validate_traffic(test))
			return TEST_FAILURE;
		test_spec_reset(test);
	}

	return TEST_PASS;
}

static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
{
	thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr;
	struct ifobject *tmp_ifobj = (*ifobj1);

	(*ifobj1)->func_ptr = (*ifobj2)->func_ptr;
	(*ifobj2)->func_ptr = tmp_func_ptr;

	*ifobj1 = *ifobj2;
	*ifobj2 = tmp_ifobj;
}

int testapp_bidirectional(struct test_spec *test)
{
	int res;

	test->ifobj_tx->rx_on = true;
	test->ifobj_rx->tx_on = true;
	test->total_steps = 2;
	if (testapp_validate_traffic(test))
		return TEST_FAILURE;

	print_verbose("Switching Tx/Rx direction\n");
	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
	res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx);

	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
	return res;
}

static int swap_xsk_resources(struct test_spec *test)
{
	int ret;

	test->ifobj_tx->xsk_arr[0].pkt_stream = NULL;
	test->ifobj_rx->xsk_arr[0].pkt_stream = NULL;
	test->ifobj_tx->xsk_arr[1].pkt_stream = test->tx_pkt_stream_default;
	test->ifobj_rx->xsk_arr[1].pkt_stream = test->rx_pkt_stream_default;
	test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1];
	test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1];

	ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk, 0);
	if (ret)
		return TEST_FAILURE;

	return TEST_PASS;
}

int testapp_xdp_prog_cleanup(struct test_spec *test)
{
	test->total_steps = 2;
	test->nb_sockets = 2;
	if (testapp_validate_traffic(test))
		return TEST_FAILURE;

	if (swap_xsk_resources(test)) {
		clean_sockets(test, test->ifobj_rx);
		clean_sockets(test, test->ifobj_tx);
		clean_umem(test, test->ifobj_rx, test->ifobj_tx);
		return TEST_FAILURE;
	}

	return testapp_validate_traffic(test);
}

int testapp_headroom(struct test_spec *test)
{
	test->ifobj_rx->xsk->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE;
	return testapp_validate_traffic(test);
}

int testapp_stats_rx_dropped(struct test_spec *test)
{
	struct xsk_umem_info *umem = test->ifobj_rx->xsk->umem;
	u32 umem_tr = test->ifobj_tx->umem_tailroom;

	if (test->mode == TEST_MODE_ZC) {
		ksft_print_msg("Can not run RX_DROPPED test for ZC mode\n");
		return TEST_SKIP;
	}

	if (pkt_stream_replace_half(test, (MIN_PKT_SIZE * 3) + umem_tr, 0))
		return TEST_FAILURE;
	umem->frame_headroom = umem->frame_size -
		XDP_PACKET_HEADROOM - (MIN_PKT_SIZE * 2) - umem_tr;
	if (pkt_stream_receive_half(test))
		return TEST_FAILURE;
	test->ifobj_rx->validation_func = validate_rx_dropped;
	return testapp_validate_traffic(test);
}

int testapp_stats_tx_invalid_descs(struct test_spec *test)
{
	if (pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0))
		return TEST_FAILURE;
	test->ifobj_tx->validation_func = validate_tx_invalid_descs;
	return testapp_validate_traffic(test);
}

int testapp_stats_rx_full(struct test_spec *test)
{
	struct pkt_stream *tmp;

	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
	if (!tmp)
		return TEST_FAILURE;
	test->ifobj_tx->xsk->pkt_stream = tmp;

	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
	if (!tmp)
		return TEST_FAILURE;
	test->ifobj_rx->xsk->pkt_stream = tmp;

	test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS;
	test->ifobj_rx->release_rx = false;
	test->ifobj_rx->validation_func = validate_rx_full;
	return testapp_validate_traffic(test);
}

int testapp_stats_fill_empty(struct test_spec *test)
{
	struct pkt_stream *tmp;

	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
	if (!tmp)
		return TEST_FAILURE;
	test->ifobj_tx->xsk->pkt_stream = tmp;

	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
	if (!tmp)
		return TEST_FAILURE;
	test->ifobj_rx->xsk->pkt_stream = tmp;

	test->ifobj_rx->use_fill_ring = false;
	test->ifobj_rx->validation_func = validate_fill_empty;
	return testapp_validate_traffic(test);
}

int testapp_send_receive_unaligned(struct test_spec *test)
{
	test_spec_set_unaligned(test);
	/* Let half of the packets straddle a 4K buffer boundary */
	if (pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2))
		return TEST_FAILURE;

	return testapp_validate_traffic(test);
}

int testapp_send_receive_unaligned_mb(struct test_spec *test)
{
	test->mtu = MAX_ETH_JUMBO_SIZE;
	test_spec_set_unaligned(test);
	if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE))
		return TEST_FAILURE;
	return testapp_validate_traffic(test);
}

int testapp_single_pkt(struct test_spec *test)
{
	struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}};

	if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)))
		return TEST_FAILURE;
	return testapp_validate_traffic(test);
}

int testapp_send_receive_mb(struct test_spec *test)
{
	test->mtu = MAX_ETH_JUMBO_SIZE;
	if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE))
		return TEST_FAILURE;

	return testapp_validate_traffic(test);
}

int testapp_invalid_desc_mb(struct test_spec *test)
{
	struct xsk_umem_info *umem = test->ifobj_tx->xsk->umem;
	u64 umem_sz = umem_size(umem);
	struct pkt pkts[] = {
		/* Valid packet for synch to start with */
		{0, MIN_PKT_SIZE, 0, true, 0},
		/* Zero frame len is not legal */
		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{0, 0, 0, false, 0},
		/* Invalid address in the second frame */
		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{umem_sz * 2, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{0, MIN_PKT_SIZE, 0, false, 0},
		/* Invalid len in the middle */
		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{0, MIN_PKT_SIZE, 0, false, 0},
		/* Invalid options in the middle */
		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION},
		{0, MIN_PKT_SIZE, 0, false, 0},
		/* Transmit 2 frags, receive 3 */
		{0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD},
		{0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0},
		/* Middle frame crosses chunk boundary with small length */
		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
		{-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0},
		/* Valid packet for synch so that something is received */
		{0, MIN_PKT_SIZE, 0, true, 0}};

	if (umem->unaligned_mode) {
		/* Crossing a chunk boundary allowed */
		pkts[15].valid = true;
		pkts[16].valid = true;
	}

	test->mtu = MAX_ETH_JUMBO_SIZE;
	if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)))
		return TEST_FAILURE;
	return testapp_validate_traffic(test);
}

int testapp_invalid_desc(struct test_spec *test)
{
	struct xsk_umem_info *umem = test->ifobj_tx->xsk->umem;
	u64 umem_sz = umem_size(umem);
	struct pkt pkts[] = {
		/* Zero packet address allowed */
		{0, MIN_PKT_SIZE, 0, true},
		/* Allowed packet */
		{0, MIN_PKT_SIZE, 0, true},
		/* Straddling the start of umem */
		{-2, MIN_PKT_SIZE, 0, false},
		/* Packet too large */
		{0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false},
		/* Up to end of umem allowed */
		{umem_sz - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true},
		/* After umem ends */
		{umem_sz, MIN_PKT_SIZE, 0, false},
		/* Straddle the end of umem */
		{umem_sz - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false},
		/* Straddle a 4K boundary */
		{0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false},
		/* Straddle a 2K boundary */
		{0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true},
		/* Valid packet for synch so that something is received */
		{0, MIN_PKT_SIZE, 0, true}};

	if (umem->unaligned_mode) {
		/* Crossing a page boundary allowed */
		pkts[7].valid = true;
	}
	if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) {
		/* Crossing a 2K frame size boundary not allowed */
		pkts[8].valid = false;
	}

	if (test->ifobj_tx->shared_umem) {
		pkts[4].offset += umem_sz;
		pkts[5].offset += umem_sz;
		pkts[6].offset += umem_sz;
	}

	if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)))
		return TEST_FAILURE;
	return testapp_validate_traffic(test);
}

int testapp_xdp_drop(struct test_spec *test)
{
	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;

	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop,
			       skel_rx->maps.xsk, skel_tx->maps.xsk);

	if (pkt_stream_receive_half(test))
		return TEST_FAILURE;
	return testapp_validate_traffic(test);
}

int testapp_xdp_metadata_copy(struct test_spec *test)
{
	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;

	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata,
			       skel_tx->progs.xsk_xdp_populate_metadata,
			       skel_rx->maps.xsk, skel_tx->maps.xsk);
	test->ifobj_rx->use_metadata = true;

	skel_rx->bss->count = 0;

	return testapp_validate_traffic(test);
}

int testapp_xdp_shared_umem(struct test_spec *test)
{
	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
	int ret;

	test->total_steps = 1;
	test->nb_sockets = 2;

	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_shared_umem,
			       skel_tx->progs.xsk_xdp_shared_umem,
			       skel_rx->maps.xsk, skel_tx->maps.xsk);

	if (pkt_stream_even_odd_sequence(test))
		return TEST_FAILURE;

	ret = testapp_validate_traffic(test);

	release_even_odd_sequence(test);

	return ret;
}

int testapp_poll_txq_tmout(struct test_spec *test)
{
	bool shared_umem = test->ifobj_tx->shared_umem;
	int ret;

	test->poll_tmout = true;
	/*
	 * POLL_TXQ_FULL exercises TX timeout setup in isolation.
	 * Keep TX out of shared-UMEM mode here so TX setup does not require
	 * RX UMEM to be initialized first.
	 */
	test->ifobj_tx->shared_umem = false;
	test->ifobj_tx->use_poll = true;
	/* create invalid frame by set umem frame_size and pkt length equal to 2048 */
	test->ifobj_tx->xsk->umem->frame_size = 2048;
	if (pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048)) {
		test->ifobj_tx->shared_umem = shared_umem;
		return TEST_FAILURE;
	}

	ret = testapp_validate_traffic_single_thread(test, test->ifobj_tx);
	test->ifobj_tx->shared_umem = shared_umem;

	return ret;
}

int testapp_poll_rxq_tmout(struct test_spec *test)
{
	test->poll_tmout = true;
	test->ifobj_rx->use_poll = true;
	return testapp_validate_traffic_single_thread(test, test->ifobj_rx);
}

int testapp_too_many_frags(struct test_spec *test)
{
	struct pkt *pkts;
	u32 max_frags, i;
	int ret = TEST_FAILURE;

	if (test->mode == TEST_MODE_ZC) {
		max_frags = test->ifobj_tx->xdp_zc_max_segs;
	} else {
		max_frags = test->ifobj_tx->max_skb_frags;
		max_frags += 1;
	}

	pkts = calloc(2 * max_frags + 3, sizeof(struct pkt));
	if (!pkts)
		return TEST_FAILURE;

	test->mtu = MAX_ETH_JUMBO_SIZE;

	/* Valid packet for synch */
	pkts[0].len = MIN_PKT_SIZE;
	pkts[0].valid = true;

	/* One valid packet with the max amount of frags */
	for (i = 1; i < max_frags + 1; i++) {
		pkts[i].len = MIN_PKT_SIZE;
		pkts[i].options = XDP_PKT_CONTD;
		pkts[i].valid = true;
	}
	pkts[max_frags].options = 0;

	/* An invalid packet with the max + 1 amount of frags */
	for (i = max_frags + 1; i < 2 * max_frags + 2; i++) {
		pkts[i].len = MIN_PKT_SIZE;
		pkts[i].options = XDP_PKT_CONTD;
		pkts[i].valid = true;
	}
	pkts[2 * max_frags + 1].options = 0;

	/* Valid packet for synch */
	pkts[2 * max_frags + 2].len = MIN_PKT_SIZE;
	pkts[2 * max_frags + 2].valid = true;

	if (pkt_stream_generate_custom(test, pkts, 2 * max_frags + 3)) {
		free(pkts);
		return TEST_FAILURE;
	}

	/* The generated Tx stream must keep the too-big packet valid so that
	 * __send_pkts() accounts its descriptors in outstanding_tx. The Rx
	 * stream, however, must not expect this packet on the wire.
	 */
	test->ifobj_rx->xsk->pkt_stream->pkts[2].valid = false;
	test->ifobj_rx->xsk->pkt_stream->nb_valid_entries--;

	ret = testapp_validate_traffic(test);
	free(pkts);
	return ret;
}

static int xsk_load_xdp_programs(struct ifobject *ifobj)
{
	ifobj->xdp_progs = xsk_xdp_progs__open_and_load();
	if (libbpf_get_error(ifobj->xdp_progs))
		return libbpf_get_error(ifobj->xdp_progs);

	return 0;
}

/* Simple test */
static bool hugepages_present(void)
{
	size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE;
	void *bufs;

	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
		    MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB);
	if (bufs == MAP_FAILED)
		return false;

	mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE;
	munmap(bufs, mmap_sz);
	return true;
}

int init_iface(struct ifobject *ifobj, thread_func_t func_ptr)
{
	LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
	int err;

	ifobj->func_ptr = func_ptr;

	err = xsk_load_xdp_programs(ifobj);
	if (err) {
		ksft_print_msg("Error loading XDP program\n");
		return err;
	}

	if (hugepages_present())
		ifobj->unaligned_supp = true;

	err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts);
	if (err) {
		ksft_print_msg("Error querying XDP capabilities\n");
		return err;
	}
	if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG)
		ifobj->multi_buff_supp = true;
	if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) {
		if (query_opts.xdp_zc_max_segs > 1) {
			ifobj->multi_buff_zc_supp = true;
			ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs;
		} else {
			ifobj->xdp_zc_max_segs = 0;
		}
	}

	return 0;
}

int testapp_send_receive(struct test_spec *test)
{
	return testapp_validate_traffic(test);
}

int testapp_send_receive_2k_frame(struct test_spec *test)
{
	test_spec_set_frame_size(test, 2048);
	if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE))
		return TEST_FAILURE;
	return testapp_validate_traffic(test);
}

int testapp_poll_rx(struct test_spec *test)
{
	test->ifobj_rx->use_poll = true;
	return testapp_validate_traffic(test);
}

int testapp_poll_tx(struct test_spec *test)
{
	test->ifobj_tx->use_poll = true;
	return testapp_validate_traffic(test);
}

int testapp_aligned_inv_desc(struct test_spec *test)
{
	return testapp_invalid_desc(test);
}

int testapp_aligned_inv_desc_2k_frame(struct test_spec *test)
{
	test_spec_set_frame_size(test, 2048);
	return testapp_invalid_desc(test);
}

int testapp_unaligned_inv_desc(struct test_spec *test)
{
	test_spec_set_unaligned(test);
	return testapp_invalid_desc(test);
}

int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test)
{
	u64 page_size, umem_sz;

	/* Odd frame size so the UMEM doesn't end near a page boundary. */
	test_spec_set_frame_size(test, 4001);
	test_spec_set_unaligned(test);
	/* This test exists to test descriptors that staddle the end of
	 * the UMEM but not a page.
	 */
	page_size = sysconf(_SC_PAGESIZE);
	umem_sz = umem_size(test->ifobj_tx->xsk->umem);
	assert(umem_sz % page_size > MIN_PKT_SIZE);
	assert(umem_sz % page_size < page_size - MIN_PKT_SIZE);

	return testapp_invalid_desc(test);
}

int testapp_aligned_inv_desc_mb(struct test_spec *test)
{
	return testapp_invalid_desc_mb(test);
}

int testapp_unaligned_inv_desc_mb(struct test_spec *test)
{
	test_spec_set_unaligned(test);
	return testapp_invalid_desc_mb(test);
}

int testapp_xdp_metadata(struct test_spec *test)
{
	return testapp_xdp_metadata_copy(test);
}

int testapp_xdp_metadata_mb(struct test_spec *test)
{
	test->mtu = MAX_ETH_JUMBO_SIZE;
	return testapp_xdp_metadata_copy(test);
}

int testapp_hw_sw_min_ring_size(struct test_spec *test)
{
	int ret;

	test->set_ring = true;
	test->total_steps = 2;
	test->ifobj_tx->ring.tx_pending = DEFAULT_BATCH_SIZE;
	test->ifobj_tx->ring.rx_pending = DEFAULT_BATCH_SIZE * 2;
	test->ifobj_tx->xsk->batch_size = 1;
	test->ifobj_rx->xsk->batch_size = 1;
	ret = testapp_validate_traffic(test);
	if (ret)
		return ret;

	/* Set batch size to hw_ring_size - 1 */
	test->ifobj_tx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1;
	test->ifobj_rx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1;
	return testapp_validate_traffic(test);
}

int testapp_hw_sw_max_ring_size(struct test_spec *test)
{
	u32 max_descs = XSK_RING_PROD__DEFAULT_NUM_DESCS * 4;
	int ret;

	test->set_ring = true;
	test->total_steps = 2;
	test->ifobj_tx->ring.tx_pending = test->ifobj_tx->ring.tx_max_pending;
	test->ifobj_tx->ring.rx_pending  = test->ifobj_tx->ring.rx_max_pending;
	test->ifobj_rx->xsk->umem->num_frames = max_descs;
	test->ifobj_rx->xsk->umem->fill_size = max_descs;
	test->ifobj_rx->xsk->umem->comp_size = max_descs;
	test->ifobj_tx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
	test->ifobj_rx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;

	ret = testapp_validate_traffic(test);
	if (ret)
		return ret;

	/* Set batch_size to 8152 for testing, as the ice HW ignores the 3 lowest bits when
	 * updating the Rx HW tail register.
	 */
	test->ifobj_tx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8;
	test->ifobj_rx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8;
	if (pkt_stream_replace(test, max_descs, MIN_PKT_SIZE)) {
		clean_sockets(test, test->ifobj_tx);
		clean_sockets(test, test->ifobj_rx);
		clean_umem(test, test->ifobj_rx, test->ifobj_tx);
		return TEST_FAILURE;
	}

	return testapp_validate_traffic(test);
}

static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value)
{
	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;

	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail,
			       skel_tx->progs.xsk_xdp_adjust_tail,
			       skel_rx->maps.xsk, skel_tx->maps.xsk);

	skel_rx->bss->adjust_value = adjust_value;

	return testapp_validate_traffic(test);
}

static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len)
{
	int ret;

	test->adjust_tail_support = true;
	test->adjust_tail = true;
	test->total_steps = 1;

	ret = pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len);
	if (ret)
		return TEST_FAILURE;

	ret = pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value);
	if (ret)
		return TEST_FAILURE;

	ret = testapp_xdp_adjust_tail(test, value);
	if (ret)
		return ret;

	if (!test->adjust_tail_support) {
		ksft_print_msg("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n",
				      mode_string(test), busy_poll_string(test));
		return TEST_SKIP;
	}

	return 0;
}

int testapp_adjust_tail_shrink(struct test_spec *test)
{
	/* Shrink by 4 bytes for testing purpose */
	return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2);
}

int testapp_adjust_tail_shrink_mb(struct test_spec *test)
{
	test->mtu = MAX_ETH_JUMBO_SIZE;
	/* Shrink by the frag size */
	return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2);
}

int testapp_adjust_tail_grow(struct test_spec *test)
{
	if (test->mode == TEST_MODE_SKB)
		return TEST_SKIP;

	/* Grow by 4 bytes for testing purpose */
	return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2);
}

int testapp_adjust_tail_grow_mb(struct test_spec *test)
{
	u32 grow_size;

	if (test->mode == TEST_MODE_SKB)
		return TEST_SKIP;

	/* worst case scenario is when underlying setup will work on 3k
	 * buffers, let us account for it; given that we will use 6k as
	 * pkt_len, expect that it will be broken down to 2 descs each
	 * with 3k payload;
	 *
	 * 4k is truesize, 3k payload, 256 HR, 320 TR;
	 */
	grow_size = XSK_UMEM__MAX_FRAME_SIZE -
		    XSK_UMEM__LARGE_FRAME_SIZE -
		    XDP_PACKET_HEADROOM -
		    test->ifobj_tx->umem_tailroom;
	test->mtu = MAX_ETH_JUMBO_SIZE;

	return testapp_adjust_tail(test, grow_size, XSK_UMEM__LARGE_FRAME_SIZE * 2);
}

int testapp_tx_queue_consumer(struct test_spec *test)
{
	int nr_packets;

	if (test->mode == TEST_MODE_ZC) {
		ksft_print_msg("Can not run TX_QUEUE_CONSUMER test for ZC mode\n");
		return TEST_SKIP;
	}

	nr_packets = MAX_TX_BUDGET_DEFAULT + 1;
	if (pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE))
		return TEST_FAILURE;
	test->ifobj_tx->xsk->batch_size = nr_packets;
	test->ifobj_tx->xsk->check_consumer = true;

	return testapp_validate_traffic(test);
}

struct ifobject *ifobject_create(void)
{
	struct ifobject *ifobj;

	ifobj = calloc(1, sizeof(struct ifobject));
	if (!ifobj)
		return NULL;

	ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr));
	if (!ifobj->xsk_arr)
		goto out_xsk_arr;

	ifobj->xsk_arr[0].umem_real = calloc(1, sizeof(struct xsk_umem_info));
	if (!ifobj->xsk_arr[0].umem_real)
		goto out_umem;

	return ifobj;

out_umem:
	free(ifobj->xsk_arr);
out_xsk_arr:
	free(ifobj);
	return NULL;
}

void ifobject_delete(struct ifobject *ifobj)
{
	if (ifobj->xsk_arr)
		free(ifobj->xsk_arr[0].umem_real);

	free(ifobj->xsk_arr);
	free(ifobj);
}