[PATCH bpf-next 17/20] selftests: xsk: add test for unaligned mode

[Magnus Karlsson <magnus.karlsson@gmail.com>]

From: Magnus Karlsson <magnus.karlsson@intel.com>

Add a test for unaligned mode in which packet buffers can be placed
anywhere within the umem. Some packets are made to straddle page
boundraries in order to check for correctness. On the Tx side, buffers
are now allocated according to the addresses found in the packet
stream. Thus, the placement of buffers can be controlled with the
boolean use_addr_for_fill in the packet stream.

One new pkt_stream insterface is introduced: pkt_stream_replace_half()
that replaces every other packet in the default packet stream with the
specified new packet.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
---
 tools/testing/selftests/bpf/xdpxceiver.c | 125 ++++++++++++++++++-----
 tools/testing/selftests/bpf/xdpxceiver.h |   4 +
 2 files changed, 106 insertions(+), 23 deletions(-)

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index d4aad4833754..a24068993cc3 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -19,7 +19,7 @@
  * Virtual Ethernet interfaces.
  *
  * For each mode, the following tests are run:
- *    a. nopoll - soft-irq processing
+ *    a. nopoll - soft-irq processing in run-to-completion mode
  *    b. poll - using poll() syscall
  *    c. Socket Teardown
  *       Create a Tx and a Rx socket, Tx from one socket, Rx on another. Destroy
@@ -45,6 +45,7 @@
  *       Configure sockets at indexes 0 and 1, run a traffic on queue ids 0,
  *       then remove xsk sockets from queue 0 on both veth interfaces and
  *       finally run a traffic on queues ids 1
+ *    g. unaligned mode
  *
  * Total tests: 12
  *
@@ -243,6 +244,9 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
 	};
 	int ret;
 
+	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)
@@ -252,19 +256,6 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
 	return 0;
 }
 
-static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
-{
-	int ret, i;
-	u32 idx = 0;
-
-	ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
-	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
-		exit_with_error(-ret);
-	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
-		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * umem->frame_size;
-	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
-}
-
 static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
 				struct ifobject *ifobject, u32 qid)
 {
@@ -487,7 +478,8 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 
 	pkt_stream->nb_pkts = nb_pkts;
 	for (i = 0; i < nb_pkts; i++) {
-		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size;
+		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size +
+			DEFAULT_OFFSET;
 		pkt_stream->pkts[i].len = pkt_len;
 		pkt_stream->pkts[i].payload = i;
 
@@ -500,6 +492,12 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 	return pkt_stream;
 }
 
+static struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem,
+					   struct pkt_stream *pkt_stream)
+{
+	return pkt_stream_generate(umem, pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
+}
+
 static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
 {
 	struct pkt_stream *pkt_stream;
@@ -507,8 +505,22 @@ static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
 	pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len);
 	test->ifobj_tx->pkt_stream = pkt_stream;
 	test->ifobj_rx->pkt_stream = pkt_stream;
+}
 
-	pkt_stream_delete(pkt_stream);
+static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, u32 offset)
+{
+	struct xsk_umem_info *umem = test->ifobj_tx->umem;
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default);
+	for (i = 0; i < test->pkt_stream_default->nb_pkts; i += 2) {
+		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset;
+		pkt_stream->pkts[i].len = pkt_len;
+	}
+
+	test->ifobj_tx->pkt_stream = pkt_stream;
+	test->ifobj_rx->pkt_stream = pkt_stream;
 }
 
 static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb)
@@ -572,9 +584,9 @@ static void pkt_dump(void *pkt, u32 len)
 	fprintf(stdout, "---------------------------------------\n");
 }
 
-static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *desc)
+static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
 {
-	void *data = xsk_umem__get_data(buffer, desc->addr);
+	void *data = xsk_umem__get_data(buffer, addr);
 	struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr));
 
 	if (!pkt) {
@@ -588,10 +600,10 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *d
 		if (opt_pkt_dump)
 			pkt_dump(data, PKT_SIZE);
 
-		if (pkt->len != desc->len) {
+		if (pkt->len != len) {
 			ksft_test_result_fail
 				("ERROR: [%s] expected length [%d], got length [%d]\n",
-					__func__, pkt->len, desc->len);
+					__func__, pkt->len, len);
 			return false;
 		}
 
@@ -673,7 +685,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 
 			orig = xsk_umem__extract_addr(addr);
 			addr = xsk_umem__add_offset_to_addr(addr);
-			if (!is_pkt_valid(pkt, xsk->umem->buffer, desc))
+			if (!is_pkt_valid(pkt, xsk->umem->buffer, addr, desc->len))
 				return;
 
 			*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
@@ -817,13 +829,16 @@ static void tx_stats_validate(struct ifobject *ifobject)
 
 static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 {
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 	u32 i;
 
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
+	if (ifobject->umem->unaligned_mode)
+		mmap_flags |= MAP_HUGETLB;
+
 	for (i = 0; i < test->nb_sockets; i++) {
 		u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
-		int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 		u32 ctr = 0;
 		void *bufs;
 
@@ -881,6 +896,32 @@ static void *worker_testapp_validate_tx(void *arg)
 	pthread_exit(NULL);
 }
 
+static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream)
+{
+	u32 idx = 0, i;
+	int ret;
+
+	ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
+	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+		exit_with_error(ENOSPC);
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) {
+		u64 addr;
+
+		if (pkt_stream->use_addr_for_fill) {
+			struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i);
+
+			if (!pkt)
+				break;
+			addr = pkt->addr;
+		} else {
+			addr = (i % umem->num_frames) * umem->frame_size + DEFAULT_OFFSET;
+		}
+
+		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
+	}
+	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+}
+
 static void *worker_testapp_validate_rx(void *arg)
 {
 	struct test_spec *test = (struct test_spec *)arg;
@@ -891,7 +932,7 @@ static void *worker_testapp_validate_rx(void *arg)
 		thread_common_ops(test, ifobject);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
-		xsk_populate_fill_ring(ifobject->umem);
+		xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream);
 
 	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds.events = POLLIN;
@@ -1035,6 +1076,40 @@ static void testapp_stats(struct test_spec *test)
 	test_spec_set_name(test, "STATS");
 }
 
+/* Simple test */
+static bool hugepages_present(struct ifobject *ifobject)
+{
+	const size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size;
+	void *bufs;
+
+	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+		    MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE | MAP_HUGETLB, -1, 0);
+	if (bufs == MAP_FAILED)
+		return false;
+
+	munmap(bufs, mmap_sz);
+	return true;
+}
+
+static bool testapp_unaligned(struct test_spec *test)
+{
+	if (!hugepages_present(test->ifobj_tx)) {
+		ksft_test_result_skip("No 2M huge pages present.\n");
+		return false;
+	}
+
+	test_spec_set_name(test, "UNALIGNED_MODE");
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	/* Let half of the packets straddle a buffer boundrary */
+	pkt_stream_replace_half(test, PKT_SIZE, test->ifobj_tx->umem->frame_size - 32);
+	test->ifobj_rx->pkt_stream->use_addr_for_fill = true;
+	testapp_validate_traffic(test);
+
+	pkt_stream_restore_default(test);
+	return true;
+}
+
 static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
 		       const char *dst_ip, const char *src_ip, const u16 dst_port,
 		       const u16 src_port, thread_func_t func_ptr)
@@ -1086,6 +1161,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test_spec_set_name(test, "POLL");
 		testapp_validate_traffic(test);
 		break;
+	case TEST_TYPE_UNALIGNED:
+		if (!testapp_unaligned(test))
+			return;
+		break;
 	default:
 		break;
 	}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e27fe348ae50..129801eb013c 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -39,6 +39,7 @@
 #define POLL_TMOUT 1000
 #define DEFAULT_PKT_CNT (4 * 1024)
 #define RX_FULL_RXQSIZE 32
+#define DEFAULT_OFFSET 256
 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1)
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
@@ -52,6 +53,7 @@ enum test_mode {
 enum test_type {
 	TEST_TYPE_NOPOLL,
 	TEST_TYPE_POLL,
+	TEST_TYPE_UNALIGNED,
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
 	TEST_TYPE_STATS,
@@ -81,6 +83,7 @@ struct xsk_umem_info {
 	u32 frame_headroom;
 	void *buffer;
 	u32 frame_size;
+	bool unaligned_mode;
 };
 
 struct xsk_socket_info {
@@ -102,6 +105,7 @@ struct pkt {
 struct pkt_stream {
 	u32 nb_pkts;
 	struct pkt *pkts;
+	bool use_addr_for_fill;
 };
 
 typedef void *(*thread_func_t)(void *arg);
-- 
2.29.0