Fix lpaif_type and DAI configuration for I2S

Merge series from Mohammad Rafi Shaik <mohammad.rafi.shaik@oss.qualcomm.com>:

Fix the lpaif_type configuration for the I2S interface.
The proper lpaif interface type required to allow DSP to vote
appropriate clock setting for I2S interface and also Add support
for configuring the DAI format on MI2S interfaces to allow setting
the appropriate bit clock and frame clock polarity, ensuring correct
audio data transmissionover MI2S.

22 files changed, 401 insertions, 96 deletions

diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index ed565eb52275..342e056c8c66 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -77,7 +77,7 @@ $(OUTPUT)gpio-watch: $(GPIO_WATCH_IN)
 
 clean:
 	rm -f $(ALL_PROGRAMS)
-	rm -f $(OUTPUT)include/linux/gpio.h
+	rm -rf $(OUTPUT)include
 	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete
 
 install: $(ALL_PROGRAMS)
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index ef032e17fec4..eb295756c3bf 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -830,7 +830,7 @@ class TypeArrayNest(Type):
                      'ynl_attr_for_each_nested(attr2, attr) {',
                      '\tif (ynl_attr_validate(yarg, attr2))',
                      '\t\treturn YNL_PARSE_CB_ERROR;',
-                     f'\t{var}->_count.{self.c_name}++;',
+                     f'\tn_{self.c_name}++;',
                      '}']
         return get_lines, None, local_vars
 
diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c
index 30c7da79e109..8b31d1d05f90 100644
--- a/tools/perf/tests/pe-file-parsing.c
+++ b/tools/perf/tests/pe-file-parsing.c
@@ -37,7 +37,7 @@ static int run_dir(const char *d)
 	size_t idx;
 
 	scnprintf(filename, PATH_MAX, "%s/pe-file.exe", d);
-	ret = filename__read_build_id(filename, &bid);
+	ret = filename__read_build_id(filename, &bid, /*block=*/true);
 	TEST_ASSERT_VAL("Failed to read build_id",
 			ret == sizeof(expect_build_id));
 	TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id,
@@ -49,7 +49,7 @@ static int run_dir(const char *d)
 			!strcmp(debuglink, expect_debuglink));
 
 	scnprintf(debugfile, PATH_MAX, "%s/%s", d, debuglink);
-	ret = filename__read_build_id(debugfile, &bid);
+	ret = filename__read_build_id(debugfile, &bid, /*block=*/true);
 	TEST_ASSERT_VAL("Failed to read debug file build_id",
 			ret == sizeof(expect_build_id));
 	TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id,
diff --git a/tools/perf/tests/shell/test_bpf_metadata.sh b/tools/perf/tests/shell/test_bpf_metadata.sh
index 69e3c2055134..be67d56e0f09 100755
--- a/tools/perf/tests/shell/test_bpf_metadata.sh
+++ b/tools/perf/tests/shell/test_bpf_metadata.sh
@@ -61,7 +61,7 @@ test_bpf_metadata() {
 		/perf_version/ {
 			if (entry) print $NF;
 		}
-	' | egrep "$VERS" > /dev/null
+	' | grep -qF "$VERS"
 	then
 		echo "Basic BPF metadata test [Failed invalid output]"
 		err=1
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 5b6d3e899e11..2298cd396c42 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -657,9 +657,15 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
 		info_node->info_linear = info_linear;
 		info_node->metadata = NULL;
 		if (!perf_env__insert_bpf_prog_info(env, info_node)) {
-			free(info_linear);
+			/*
+			 * Insert failed, likely because of a duplicate event
+			 * made by the sideband thread. Ignore synthesizing the
+			 * metadata.
+			 */
 			free(info_node);
+			goto out;
 		}
+		/* info_linear is now owned by info_node and shouldn't be freed below. */
 		info_linear = NULL;
 
 		/*
@@ -827,18 +833,18 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	return err;
 }
 
-static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
+static int perf_env__add_bpf_info(struct perf_env *env, u32 id)
 {
 	struct bpf_prog_info_node *info_node;
 	struct perf_bpil *info_linear;
 	struct btf *btf = NULL;
 	u64 arrays;
 	u32 btf_id;
-	int fd;
+	int fd, err = 0;
 
 	fd = bpf_prog_get_fd_by_id(id);
 	if (fd < 0)
-		return;
+		return -EINVAL;
 
 	arrays = 1UL << PERF_BPIL_JITED_KSYMS;
 	arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS;
@@ -852,6 +858,7 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
 	info_linear = get_bpf_prog_info_linear(fd, arrays);
 	if (IS_ERR_OR_NULL(info_linear)) {
 		pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
+		err = PTR_ERR(info_linear);
 		goto out;
 	}
 
@@ -862,38 +869,46 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
 		info_node->info_linear = info_linear;
 		info_node->metadata = bpf_metadata_create(&info_linear->info);
 		if (!perf_env__insert_bpf_prog_info(env, info_node)) {
+			pr_debug("%s: duplicate add bpf info request for id %u\n",
+				 __func__, btf_id);
 			free(info_linear);
 			free(info_node);
+			goto out;
 		}
-	} else
+	} else {
 		free(info_linear);
+		err = -ENOMEM;
+		goto out;
+	}
 
 	if (btf_id == 0)
 		goto out;
 
 	btf = btf__load_from_kernel_by_id(btf_id);
-	if (libbpf_get_error(btf)) {
-		pr_debug("%s: failed to get BTF of id %u, aborting\n",
-			 __func__, btf_id);
-		goto out;
+	if (!btf) {
+		err = -errno;
+		pr_debug("%s: failed to get BTF of id %u %d\n", __func__, btf_id, err);
+	} else {
+		perf_env__fetch_btf(env, btf_id, btf);
 	}
-	perf_env__fetch_btf(env, btf_id, btf);
 
 out:
 	btf__free(btf);
 	close(fd);
+	return err;
 }
 
 static int bpf_event__sb_cb(union perf_event *event, void *data)
 {
 	struct perf_env *env = data;
+	int ret = 0;
 
 	if (event->header.type != PERF_RECORD_BPF_EVENT)
 		return -1;
 
 	switch (event->bpf.type) {
 	case PERF_BPF_EVENT_PROG_LOAD:
-		perf_env__add_bpf_info(env, event->bpf.id);
+		ret = perf_env__add_bpf_info(env, event->bpf.id);
 
 	case PERF_BPF_EVENT_PROG_UNLOAD:
 		/*
@@ -907,7 +922,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c
index 80b1d2b3729b..5a66dc8594aa 100644
--- a/tools/perf/util/bpf-utils.c
+++ b/tools/perf/util/bpf-utils.c
@@ -20,7 +20,7 @@ struct bpil_array_desc {
 				 */
 };
 
-static struct bpil_array_desc bpil_array_desc[] = {
+static const struct bpil_array_desc bpil_array_desc[] = {
 	[PERF_BPIL_JITED_INSNS] = {
 		offsetof(struct bpf_prog_info, jited_prog_insns),
 		offsetof(struct bpf_prog_info, jited_prog_len),
@@ -115,7 +115,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 	__u32 info_len = sizeof(info);
 	__u32 data_len = 0;
 	int i, err;
-	void *ptr;
+	__u8 *ptr;
 
 	if (arrays >> PERF_BPIL_LAST_ARRAY)
 		return ERR_PTR(-EINVAL);
@@ -126,15 +126,15 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		pr_debug("can't get prog info: %s", strerror(errno));
 		return ERR_PTR(-EFAULT);
 	}
+	if (info.type >= __MAX_BPF_PROG_TYPE)
+		pr_debug("%s:%d: unexpected program type %u\n", __func__, __LINE__, info.type);
 
 	/* step 2: calculate total size of all arrays */
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		bool include_array = (arrays & (1UL << i)) > 0;
-		struct bpil_array_desc *desc;
 		__u32 count, size;
 
-		desc = bpil_array_desc + i;
-
 		/* kernel is too old to support this field */
 		if (info_len < desc->array_offset + sizeof(__u32) ||
 		    info_len < desc->count_offset + sizeof(__u32) ||
@@ -163,19 +163,20 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 	ptr = info_linear->data;
 
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u32 count, size;
 
 		if ((arrays & (1UL << i)) == 0)
 			continue;
 
-		desc  = bpil_array_desc + i;
 		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
 		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
 		bpf_prog_info_set_offset_u32(&info_linear->info,
 					     desc->count_offset, count);
 		bpf_prog_info_set_offset_u32(&info_linear->info,
 					     desc->size_offset, size);
+		assert(ptr >= info_linear->data);
+		assert(ptr < &info_linear->data[data_len]);
 		bpf_prog_info_set_offset_u64(&info_linear->info,
 					     desc->array_offset,
 					     ptr_to_u64(ptr));
@@ -189,27 +190,45 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		free(info_linear);
 		return ERR_PTR(-EFAULT);
 	}
+	if (info_linear->info.type >= __MAX_BPF_PROG_TYPE) {
+		pr_debug("%s:%d: unexpected program type %u\n",
+			 __func__, __LINE__, info_linear->info.type);
+	}
 
 	/* step 6: verify the data */
+	ptr = info_linear->data;
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
-		__u32 v1, v2;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
+		__u32 count1, count2, size1, size2;
+		__u64 ptr2;
 
 		if ((arrays & (1UL << i)) == 0)
 			continue;
 
-		desc = bpil_array_desc + i;
-		v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
-		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+		count1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+		count2 = bpf_prog_info_read_offset_u32(&info_linear->info,
 						   desc->count_offset);
-		if (v1 != v2)
-			pr_warning("%s: mismatch in element count\n", __func__);
+		if (count1 != count2) {
+			pr_warning("%s: mismatch in element count %u vs %u\n", __func__, count1, count2);
+			free(info_linear);
+			return ERR_PTR(-ERANGE);
+		}
 
-		v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
-		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+		size1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+		size2 = bpf_prog_info_read_offset_u32(&info_linear->info,
 						   desc->size_offset);
-		if (v1 != v2)
-			pr_warning("%s: mismatch in rec size\n", __func__);
+		if (size1 != size2) {
+			pr_warning("%s: mismatch in rec size %u vs %u\n", __func__, size1, size2);
+			free(info_linear);
+			return ERR_PTR(-ERANGE);
+		}
+		ptr2 = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset);
+		if (ptr_to_u64(ptr) != ptr2) {
+			pr_warning("%s: mismatch in array %p vs %llx\n", __func__, ptr, ptr2);
+			free(info_linear);
+			return ERR_PTR(-ERANGE);
+		}
+		ptr += roundup(count1 * size1, sizeof(__u64));
 	}
 
 	/* step 7: update info_len and data_len */
@@ -224,13 +243,12 @@ void bpil_addr_to_offs(struct perf_bpil *info_linear)
 	int i;
 
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u64 addr, offs;
 
 		if ((info_linear->arrays & (1UL << i)) == 0)
 			continue;
 
-		desc = bpil_array_desc + i;
 		addr = bpf_prog_info_read_offset_u64(&info_linear->info,
 						     desc->array_offset);
 		offs = addr - ptr_to_u64(info_linear->data);
@@ -244,13 +262,12 @@ void bpil_offs_to_addr(struct perf_bpil *info_linear)
 	int i;
 
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u64 addr, offs;
 
 		if ((info_linear->arrays & (1UL << i)) == 0)
 			continue;
 
-		desc = bpil_array_desc + i;
 		offs = bpf_prog_info_read_offset_u64(&info_linear->info,
 						     desc->array_offset);
 		addr = offs + ptr_to_u64(info_linear->data);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 033c79231a54..1346fd180653 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -873,13 +873,17 @@ out:
 
 #ifdef HAVE_LIBBFD_BUILDID_SUPPORT
 
-static int read_build_id(const char *filename, struct build_id *bid)
+static int read_build_id(const char *filename, struct build_id *bid, bool block)
 {
 	size_t size = sizeof(bid->data);
-	int err = -1;
+	int err = -1, fd;
 	bfd *abfd;
 
-	abfd = bfd_openr(filename, NULL);
+	fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK));
+	if (fd < 0)
+		return -1;
+
+	abfd = bfd_fdopenr(filename, /*target=*/NULL, fd);
 	if (!abfd)
 		return -1;
 
diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py
index cd23af875317..3e3a89a34afe 100755
--- a/tools/testing/selftests/drivers/net/hw/csum.py
+++ b/tools/testing/selftests/drivers/net/hw/csum.py
@@ -17,7 +17,7 @@ def test_receive(cfg, ipver="6", extra_args=None):
     ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}"
 
     rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}"
-    tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
+    tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
 
     with bkg(rx_cmd, exit_wait=True):
         wait_port_listen(34000, proto="udp")
@@ -37,7 +37,7 @@ def test_transmit(cfg, ipver="6", extra_args=None):
     if extra_args != "-U -Z":
         extra_args += " -r 1"
 
-    rx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
+    rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
     tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}"
 
     with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index d30625c18259..c744c603d688 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -1554,8 +1554,8 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc)
 	}
 
 	/* Read from the page to populate the shared zeropage. */
-	FORCE_READ(mem);
-	FORCE_READ(smem);
+	FORCE_READ(*mem);
+	FORCE_READ(*smem);
 
 	fn(mem, smem, pagesize);
 munmap:
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b0d42eb04e3a..8dd81c0a4a5a 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -145,7 +145,7 @@ static bool try_access_buf(char *ptr, bool write)
 		if (write)
 			*ptr = 'x';
 		else
-			FORCE_READ(ptr);
+			FORCE_READ(*ptr);
 	}
 
 	signal_jump_set = false;
diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c
index 1afe14b9dc0c..c5940c0595be 100644
--- a/tools/testing/selftests/mm/hugetlb-madvise.c
+++ b/tools/testing/selftests/mm/hugetlb-madvise.c
@@ -50,8 +50,10 @@ void read_fault_pages(void *addr, unsigned long nr_pages)
 	unsigned long i;
 
 	for (i = 0; i < nr_pages; i++) {
+		unsigned long *addr2 =
+			((unsigned long *)(addr + (i * huge_page_size)));
 		/* Prevent the compiler from optimizing out the entire loop: */
-		FORCE_READ(((unsigned long *)(addr + (i * huge_page_size))));
+		FORCE_READ(*addr2);
 	}
 }
 
diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c
index c5a73617796a..ea945eebec2f 100644
--- a/tools/testing/selftests/mm/migration.c
+++ b/tools/testing/selftests/mm/migration.c
@@ -110,7 +110,7 @@ void *access_mem(void *ptr)
 		 * the memory access actually happens and prevents the compiler
 		 * from optimizing away this entire loop.
 		 */
-		FORCE_READ((uint64_t *)ptr);
+		FORCE_READ(*(uint64_t *)ptr);
 	}
 
 	return NULL;
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index 0d4209eef0c3..e6face7c0166 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -1525,7 +1525,7 @@ void zeropfn_tests(void)
 
 	ret = madvise(mem, hpage_size, MADV_HUGEPAGE);
 	if (!ret) {
-		FORCE_READ(mem);
+		FORCE_READ(*mem);
 
 		ret = pagemap_ioctl(mem, hpage_size, &vec, 1, 0,
 				    0, PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO);
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 05de1fc0005b..44a3f8a58806 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -439,8 +439,11 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
 	}
 	madvise(*addr, fd_size, MADV_HUGEPAGE);
 
-	for (size_t i = 0; i < fd_size; i++)
-		FORCE_READ((*addr + i));
+	for (size_t i = 0; i < fd_size; i++) {
+		char *addr2 = *addr + i;
+
+		FORCE_READ(*addr2);
+	}
 
 	if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) {
 		ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n");
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index c20298ae98ea..b55d1809debc 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -23,7 +23,7 @@
  * anything with it in order to trigger a read page fault. We therefore must use
  * volatile to stop the compiler from optimising this away.
  */
-#define FORCE_READ(x) (*(volatile typeof(x) *)x)
+#define FORCE_READ(x) (*(const volatile typeof(x) *)&(x))
 
 extern unsigned int __page_size;
 extern unsigned int __page_shift;
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b31a71f2b372..c7e03e1d6f63 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -99,6 +99,7 @@ TEST_GEN_PROGS += bind_wildcard
 TEST_GEN_PROGS += bind_timewait
 TEST_PROGS += test_vxlan_mdb.sh
 TEST_PROGS += test_bridge_neigh_suppress.sh
+TEST_PROGS += test_vxlan_nh.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
 TEST_PROGS += test_neigh.sh
diff --git a/tools/testing/selftests/net/bind_bhash.c b/tools/testing/selftests/net/bind_bhash.c
index 57ff67a3751e..da04b0b19b73 100644
--- a/tools/testing/selftests/net/bind_bhash.c
+++ b/tools/testing/selftests/net/bind_bhash.c
@@ -75,7 +75,7 @@ static void *setup(void *arg)
 	int *array = (int *)arg;
 
 	for (i = 0; i < MAX_CONNECTIONS; i++) {
-		sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+		sock_fd = bind_socket(SO_REUSEPORT, setup_addr);
 		if (sock_fd < 0) {
 			ret = sock_fd;
 			pthread_exit(&ret);
@@ -103,7 +103,7 @@ int main(int argc, const char *argv[])
 
 	setup_addr = use_v6 ? setup_addr_v6 : setup_addr_v4;
 
-	listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+	listener_fd = bind_socket(SO_REUSEPORT, setup_addr);
 	if (listen(listener_fd, 100) < 0) {
 		perror("listen failed");
 		return -1;
diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
index 606a43a60f73..7fc6c5dbd551 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
@@ -99,7 +99,7 @@ run_one_clash_test()
 	local entries
 	local cre
 
-	if ! ip netns exec "$ns" ./udpclash $daddr $dport;then
+	if ! ip netns exec "$ns" timeout 30 ./udpclash $daddr $dport;then
 		echo "INFO: did not receive expected number of replies for $daddr:$dport"
 		ip netns exec "$ctns" conntrack -S
 		# don't fail: check if clash resolution triggered after all.
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
index 788cd56ea4a0..615fe3c6f405 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -187,7 +187,7 @@ ct_udpclash()
 	[ -x udpclash ] || return
 
         while [ $now -lt $end ]; do
-		ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
+		ip netns exec "$ns" timeout 30 ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
 
 		now=$(date +%s)
 	done
@@ -277,6 +277,7 @@ check_taint()
 insert_flood()
 {
 	local n="$1"
+	local timeout="$2"
 	local r=0
 
 	r=$((RANDOM%$insert_count))
@@ -302,7 +303,7 @@ test_floodresize_all()
 	read tainted_then < /proc/sys/kernel/tainted
 
 	for n in "$nsclient1" "$nsclient2";do
-		insert_flood "$n" &
+		insert_flood "$n" "$timeout" &
 	done
 
 	# resize table constantly while flood/insert/dump/flushs
diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
index a4ee5496f2a1..45832df98295 100755
--- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
@@ -20,6 +20,7 @@ ret=0
 SOCAT_TIMEOUT=60
 
 nsin=""
+nsin_small=""
 ns1out=""
 ns2out=""
 
@@ -36,7 +37,7 @@ cleanup() {
 
 	cleanup_all_ns
 
-	rm -f "$nsin" "$ns1out" "$ns2out"
+	rm -f "$nsin" "$nsin_small" "$ns1out" "$ns2out"
 
 	[ "$log_netns" -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns="$log_netns"
 }
@@ -72,6 +73,7 @@ lmtu=1500
 rmtu=2000
 
 filesize=$((2 * 1024 * 1024))
+filesize_small=$((filesize / 16))
 
 usage(){
 	echo "nft_flowtable.sh [OPTIONS]"
@@ -89,7 +91,10 @@ do
 		o) omtu=$OPTARG;;
 		l) lmtu=$OPTARG;;
 		r) rmtu=$OPTARG;;
-		s) filesize=$OPTARG;;
+		s)
+			filesize=$OPTARG
+			filesize_small=$((OPTARG / 16))
+		;;
 		*) usage;;
 	esac
 done
@@ -215,6 +220,7 @@ if ! ip netns exec "$ns2" ping -c 1 -q 10.0.1.99 > /dev/null; then
 fi
 
 nsin=$(mktemp)
+nsin_small=$(mktemp)
 ns1out=$(mktemp)
 ns2out=$(mktemp)
 
@@ -265,6 +271,7 @@ check_counters()
 check_dscp()
 {
 	local what=$1
+	local pmtud="$2"
 	local ok=1
 
 	local counter
@@ -277,37 +284,39 @@ check_dscp()
 	local pc4z=${counter%*bytes*}
 	local pc4z=${pc4z#*packets}
 
+	local failmsg="FAIL: pmtu $pmtu: $what counters do not match, expected"
+
 	case "$what" in
 	"dscp_none")
 		if [ "$pc4" -gt 0 ] || [ "$pc4z" -eq 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_fwd")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -eq 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_ingress")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_egress")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	*)
-		echo "FAIL: Unknown DSCP check" 1>&2
+		echo "$failmsg: Unknown DSCP check" 1>&2
 		ret=1
 		ok=0
 	esac
@@ -319,9 +328,9 @@ check_dscp()
 
 check_transfer()
 {
-	in=$1
-	out=$2
-	what=$3
+	local in=$1
+	local out=$2
+	local what=$3
 
 	if ! cmp "$in" "$out" > /dev/null 2>&1; then
 		echo "FAIL: file mismatch for $what" 1>&2
@@ -342,25 +351,39 @@ test_tcp_forwarding_ip()
 {
 	local nsa=$1
 	local nsb=$2
-	local dstip=$3
-	local dstport=$4
+	local pmtu=$3
+	local dstip=$4
+	local dstport=$5
 	local lret=0
+	local socatc
+	local socatl
+	local infile="$nsin"
+
+	if [ $pmtu -eq 0 ]; then
+		infile="$nsin_small"
+	fi
 
-	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$nsin" > "$ns2out" &
+	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" &
 	lpid=$!
 
 	busywait 1000 listener_ready
 
-	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$nsin" > "$ns1out"
+	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out"
+	socatc=$?
 
 	wait $lpid
+	socatl=$?
 
-	if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
+	if [ $socatl -ne 0 ] || [ $socatc -ne 0 ];then
+		rc=1
+	fi
+
+	if ! check_transfer "$infile" "$ns2out" "ns1 -> ns2"; then
 		lret=1
 		ret=1
 	fi
 
-	if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then
+	if ! check_transfer "$infile" "$ns1out" "ns1 <- ns2"; then
 		lret=1
 		ret=1
 	fi
@@ -370,14 +393,16 @@ test_tcp_forwarding_ip()
 
 test_tcp_forwarding()
 {
-	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+	local pmtu="$3"
+
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345
 
 	return $?
 }
 
 test_tcp_forwarding_set_dscp()
 {
-	check_dscp "dscp_none"
+	local pmtu="$3"
 
 ip netns exec "$nsr1" nft -f - <<EOF
 table netdev dscpmangle {
@@ -388,8 +413,8 @@ table netdev dscpmangle {
 }
 EOF
 if [ $? -eq 0 ]; then
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_ingress"
+	test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345
+	check_dscp "dscp_ingress" "$pmtu"
 
 	ip netns exec "$nsr1" nft delete table netdev dscpmangle
 else
@@ -405,10 +430,10 @@ table netdev dscpmangle {
 }
 EOF
 if [ $? -eq 0 ]; then
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_egress"
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu"  10.0.2.99 12345
+	check_dscp "dscp_egress" "$pmtu"
 
-	ip netns exec "$nsr1" nft flush table netdev dscpmangle
+	ip netns exec "$nsr1" nft delete table netdev dscpmangle
 else
 	echo "SKIP: Could not load netdev:egress for veth1"
 fi
@@ -416,48 +441,53 @@ fi
 	# partial.  If flowtable really works, then both dscp-is-0 and dscp-is-cs3
 	# counters should have seen packets (before and after ft offload kicks in).
 	ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_fwd"
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu"  10.0.2.99 12345
+	check_dscp "dscp_fwd" "$pmtu"
 }
 
 test_tcp_forwarding_nat()
 {
+	local nsa="$1"
+	local nsb="$2"
+	local pmtu="$3"
+	local what="$4"
 	local lret
-	local pmtu
 
-	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
-	lret=$?
+	[ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)"
 
-	pmtu=$3
-	what=$4
+	test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345
+	lret=$?
 
 	if [ "$lret" -eq 0 ] ; then
 		if [ "$pmtu" -eq 1 ] ;then
-			check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what"
+			check_counters "flow offload for ns1/ns2 with masquerade $what"
 		else
 			echo "PASS: flow offload for ns1/ns2 with masquerade $what"
 		fi
 
-		test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666
+		test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666
 		lret=$?
 		if [ "$pmtu" -eq 1 ] ;then
-			check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what"
+			check_counters "flow offload for ns1/ns2 with dnat $what"
 		elif [ "$lret" -eq 0 ] ; then
 			echo "PASS: flow offload for ns1/ns2 with dnat $what"
 		fi
+	else
+		echo "FAIL: flow offload for ns1/ns2 with dnat $what"
 	fi
 
 	return $lret
 }
 
 make_file "$nsin" "$filesize"
+make_file "$nsin_small" "$filesize_small"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
 # Due to MTU mismatch in both directions, all packets (except small packets like pure
 # acks) have to be handled by normal forwarding path.  Therefore, packet counters
 # are not checked.
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 0; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
@@ -489,8 +519,9 @@ table ip nat {
 }
 EOF
 
+check_dscp "dscp_none" "0"
 if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then
-	echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2
+	echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2
 	exit 0
 fi
 
@@ -513,6 +544,14 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 # For earlier tests (large mtus), packets cannot be handled via flowtable
 # (except pure acks and other small packets).
 ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
+ip netns exec "$ns2"  nft reset counters table inet filter >/dev/null
+
+if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then
+	echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2
+	exit 0
+fi
+
+ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
 
 if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then
 	echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
@@ -644,7 +683,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1
 ip -net "$ns2" route add default via 10.0.2.1
 ip -net "$ns2" route add default via dead:2::1
 
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 1; then
 	check_counters "ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
@@ -668,7 +707,7 @@ if [ "$1" = "" ]; then
 	fi
 
 	echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize"
-	$0 -o "$o" -l "$l" -r "$r" -s "$filesize"
+	$0 -o "$o" -l "$l" -r "$r" -s "$filesize" || ret=1
 fi
 
 exit $ret
diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c
index 85c7b906ad08..79de163d61ab 100644
--- a/tools/testing/selftests/net/netfilter/udpclash.c
+++ b/tools/testing/selftests/net/netfilter/udpclash.c
@@ -29,7 +29,7 @@ struct thread_args {
 	int sockfd;
 };
 
-static int wait = 1;
+static volatile int wait = 1;
 
 static void *thread_main(void *varg)
 {
diff --git a/tools/testing/selftests/net/test_vxlan_nh.sh b/tools/testing/selftests/net/test_vxlan_nh.sh
new file mode 100755
index 000000000000..20f3369f776b
--- /dev/null
+++ b/tools/testing/selftests/net/test_vxlan_nh.sh
@@ -0,0 +1,223 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+TESTS="
+	basic_tx_ipv4
+	basic_tx_ipv6
+	learning
+	proxy_ipv4
+	proxy_ipv6
+"
+VERBOSE=0
+
+################################################################################
+# Utilities
+
+run_cmd()
+{
+	local cmd="$1"
+	local out
+	local stderr="2>/dev/null"
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo "COMMAND: $cmd"
+		stderr=
+	fi
+
+	out=$(eval "$cmd" "$stderr")
+	rc=$?
+	if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	return $rc
+}
+
+################################################################################
+# Cleanup
+
+exit_cleanup_all()
+{
+	cleanup_all_ns
+	exit "${EXIT_STATUS}"
+}
+
+################################################################################
+# Tests
+
+nh_stats_get()
+{
+	ip -n "$ns1" -s -j nexthop show id 10 | jq ".[][\"group_stats\"][][\"packets\"]"
+}
+
+tc_stats_get()
+{
+	tc_rule_handle_stats_get "dev dummy1 egress" 101 ".packets" "-n $ns1"
+}
+
+basic_tx_common()
+{
+	local af_str=$1; shift
+	local proto=$1; shift
+	local local_addr=$1; shift
+	local plen=$1; shift
+	local remote_addr=$1; shift
+
+	RET=0
+
+	# Test basic Tx functionality. Check that stats are incremented on
+	# both the FDB nexthop group and the egress device.
+
+	run_cmd "ip -n $ns1 link add name dummy1 up type dummy"
+	run_cmd "ip -n $ns1 route add $remote_addr/$plen dev dummy1"
+	run_cmd "tc -n $ns1 qdisc add dev dummy1 clsact"
+	run_cmd "tc -n $ns1 filter add dev dummy1 egress proto $proto pref 1 handle 101 flower ip_proto udp dst_ip $remote_addr dst_port 4789 action pass"
+
+	run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789"
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 1 -q"
+
+	busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" nh_stats_get > /dev/null
+	check_err $? "FDB nexthop group stats did not increase"
+
+	busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" tc_stats_get > /dev/null
+	check_err $? "tc filter stats did not increase"
+
+	log_test "VXLAN FDB nexthop: $af_str basic Tx"
+}
+
+basic_tx_ipv4()
+{
+	basic_tx_common "IPv4" ipv4 192.0.2.1 32 192.0.2.2
+}
+
+basic_tx_ipv6()
+{
+	basic_tx_common "IPv6" ipv6 2001:db8:1::1 128 2001:db8:1::2
+}
+
+learning()
+{
+	RET=0
+
+	# When learning is enabled on the VXLAN device, an incoming packet
+	# might try to refresh an FDB entry that points to an FDB nexthop group
+	# instead of an ordinary remote destination. Check that the kernel does
+	# not crash in this situation.
+
+	run_cmd "ip -n $ns1 address add 192.0.2.1/32 dev lo"
+	run_cmd "ip -n $ns1 address add 192.0.2.2/32 dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via 192.0.2.3 fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass"
+	run_cmd "ip -n $ns1 link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning"
+
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020"
+	run_cmd "bridge -n $ns1 fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q"
+
+	log_test "VXLAN FDB nexthop: learning"
+}
+
+proxy_common()
+{
+	local af_str=$1; shift
+	local local_addr=$1; shift
+	local plen=$1; shift
+	local remote_addr=$1; shift
+	local neigh_addr=$1; shift
+	local ping_cmd=$1; shift
+
+	RET=0
+
+	# When the "proxy" option is enabled on the VXLAN device, the device
+	# will suppress ARP requests and IPv6 Neighbor Solicitation messages if
+	# it is able to reply on behalf of the remote host. That is, if a
+	# matching and valid neighbor entry is configured on the VXLAN device
+	# whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The
+	# FDB entry for the neighbor's MAC address might point to an FDB
+	# nexthop group instead of an ordinary remote destination. Check that
+	# the kernel does not crash in this situation.
+
+	run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789 proxy"
+
+	run_cmd "ip -n $ns1 neigh add $neigh_addr lladdr 00:11:22:33:44:55 nud perm dev vx0"
+
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 $ping_cmd"
+
+	log_test "VXLAN FDB nexthop: $af_str proxy"
+}
+
+proxy_ipv4()
+{
+	proxy_common "IPv4" 192.0.2.1 32 192.0.2.2 192.0.2.3 \
+		"arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3"
+}
+
+proxy_ipv6()
+{
+	proxy_common "IPv6" 2001:db8:1::1 128 2001:db8:1::2 2001:db8:1::3 \
+		"ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0"
+}
+
+################################################################################
+# Usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+
+        -t <test>   Test(s) to run (default: all)
+                    (options: $TESTS)
+        -p          Pause on fail
+        -v          Verbose mode (show commands and output)
+EOF
+}
+
+################################################################################
+# Main
+
+while getopts ":t:pvh" opt; do
+	case $opt in
+		t) TESTS=$OPTARG;;
+		p) PAUSE_ON_FAIL=yes;;
+		v) VERBOSE=$((VERBOSE + 1));;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+require_command mausezahn
+require_command arping
+require_command ndisc6
+require_command jq
+
+if ! ip nexthop help 2>&1 | grep -q "stats"; then
+	echo "SKIP: iproute2 ip too old, missing nexthop stats support"
+	exit "$ksft_skip"
+fi
+
+trap exit_cleanup_all EXIT
+
+for t in $TESTS
+do
+	setup_ns ns1; $t; cleanup_all_ns;
+done