Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-11-30

We've added 30 non-merge commits during the last 7 day(s) which contain
a total of 58 files changed, 1598 insertions(+), 154 deletions(-).

The main changes are:

1) Add initial TX metadata implementation for AF_XDP with support in mlx5
   and stmmac drivers. Two types of offloads are supported right now, that
   is, TX timestamp and TX checksum offload, from Stanislav Fomichev with
   stmmac implementation from Song Yoong Siang.

2) Change BPF verifier logic to validate global subprograms lazily instead
   of unconditionally before the main program, so they can be guarded using
   BPF CO-RE techniques, from Andrii Nakryiko.

3) Add BPF link_info support for uprobe multi link along with bpftool
   integration for the latter, from Jiri Olsa.

4) Use pkg-config in BPF selftests to determine ld flags which is
   in particular needed for linking statically, from Akihiko Odaki.

5) Fix a few BPF selftest failures to adapt to the upcoming LLVM18,
   from Yonghong Song.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (30 commits)
  bpf/tests: Remove duplicate JSGT tests
  selftests/bpf: Add TX side to xdp_hw_metadata
  selftests/bpf: Convert xdp_hw_metadata to XDP_USE_NEED_WAKEUP
  selftests/bpf: Add TX side to xdp_metadata
  selftests/bpf: Add csum helpers
  selftests/xsk: Support tx_metadata_len
  xsk: Add option to calculate TX checksum in SW
  xsk: Validate xsk_tx_metadata flags
  xsk: Document tx_metadata_len layout
  net: stmmac: Add Tx HWTS support to XDP ZC
  net/mlx5e: Implement AF_XDP TX timestamp and checksum offload
  tools: ynl: Print xsk-features from the sample
  xsk: Add TX timestamp and TX checksum offload support
  xsk: Support tx_metadata_len
  selftests/bpf: Use pkg-config for libelf
  selftests/bpf: Override PKG_CONFIG for static builds
  selftests/bpf: Choose pkg-config for the target
  bpftool: Add support to display uprobe_multi links
  selftests/bpf: Add link_info test for uprobe_multi link
  selftests/bpf: Use bpf_link__destroy in fill_link_info tests
  ...
====================

Conflicts:

Documentation/netlink/specs/netdev.yaml:
  839ff60df3ab ("net: page_pool: add nlspec for basic access to page pools")
  48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
https://lore.kernel.org/all/20231201094705.1ee3cab8@canb.auug.org.au/

While at it also regen, tree is dirty after:
  48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
looks like code wasn't re-rendered after "render-max" was removed.

Link: https://lore.kernel.org/r/20231130145708.32573-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

16 files changed, 627 insertions, 72 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 9c27b67bc7b1..617ae55c3bb5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -18,7 +18,7 @@ else
 GENDIR := $(abspath ../../../../include/generated)
 endif
 GENHDR := $(GENDIR)/autoconf.h
-HOSTPKG_CONFIG := pkg-config
+PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 
 ifneq ($(wildcard $(GENHDR)),)
   GENFLAGS := -DHAVE_GENHDR
@@ -29,13 +29,17 @@ SAN_CFLAGS	?=
 SAN_LDFLAGS	?= $(SAN_CFLAGS)
 RELEASE		?=
 OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
+
+LIBELF_CFLAGS	:= $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null)
+LIBELF_LIBS	:= $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
+
 CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
 	  -Wall -Werror 						\
-	  $(GENFLAGS) $(SAN_CFLAGS)					\
+	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
 LDFLAGS += $(SAN_LDFLAGS)
-LDLIBS += -lelf -lz -lrt -lpthread
+LDLIBS += $(LIBELF_LIBS) -lz -lrt -lpthread
 
 ifneq ($(LLVM),)
 # Silence some warnings when compiled with clang
@@ -219,9 +223,9 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r
 
 $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c
 	$(call msg,SIGN-FILE,,$@)
-	$(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \
+	$(Q)$(CC) $(shell $(PKG_CONFIG) --cflags libcrypto 2> /dev/null) \
 		  $< -o $@ \
-		  $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
+		  $(shell $(PKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
 
 $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
 	$(call msg,MOD,,$@)
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index cb9b95702ac6..9af79c7a9b58 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -77,7 +77,7 @@ In case of linker errors when running selftests, try using static linking:
 
 .. code-block:: console
 
-  $ LDLIBS=-static vmtest.sh
+  $ LDLIBS=-static PKG_CONFIG='pkg-config --static' vmtest.sh
 
 .. note:: Some distros may not support static linking.
 
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 34f1200a781b..94b9be24e39b 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -71,4 +71,47 @@ struct nstoken;
  */
 struct nstoken *open_netns(const char *name);
 void close_netns(struct nstoken *token);
+
+static __u16 csum_fold(__u32 csum)
+{
+	csum = (csum & 0xffff) + (csum >> 16);
+	csum = (csum & 0xffff) + (csum >> 16);
+
+	return (__u16)~csum;
+}
+
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+
+	s += (__u32)saddr;
+	s += (__u32)daddr;
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+	int i;
+
+	for (i = 0; i < 4; i++)
+		s += (__u32)saddr->s6_addr32[i];
+	for (i = 0; i < 4; i++)
+		s += (__u32)daddr->s6_addr32[i];
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
index 97142a4db374..d4b1901f7879 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -7,6 +7,7 @@
 #include <test_progs.h>
 #include "trace_helpers.h"
 #include "test_fill_link_info.skel.h"
+#include "bpf/libbpf_internal.h"
 
 #define TP_CAT "sched"
 #define TP_NAME "sched_switch"
@@ -140,14 +141,14 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 		.retprobe = type == BPF_PERF_EVENT_KRETPROBE,
 	);
 	ssize_t entry_offset = 0;
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.kprobe_run = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run,
-								 KPROBE_FUNC, &opts);
-	if (!ASSERT_OK_PTR(skel->links.kprobe_run, "attach_kprobe"))
+	link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run, KPROBE_FUNC, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.kprobe_run);
+	link_fd = bpf_link__fd(link);
 	if (!invalid) {
 		/* See also arch_adjust_kprobe_addr(). */
 		if (skel->kconfig->CONFIG_X86_KERNEL_IBT)
@@ -157,39 +158,41 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 	} else {
 		kprobe_fill_invalid_user_buffer(link_fd);
 	}
-	bpf_link__detach(skel->links.kprobe_run);
+	bpf_link__destroy(link);
 }
 
 static void test_tp_fill_link_info(struct test_fill_link_info *skel)
 {
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.tp_run = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
-	if (!ASSERT_OK_PTR(skel->links.tp_run, "attach_tp"))
+	link = bpf_program__attach_tracepoint(skel->progs.tp_run, TP_CAT, TP_NAME);
+	if (!ASSERT_OK_PTR(link, "attach_tp"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.tp_run);
+	link_fd = bpf_link__fd(link);
 	err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0);
 	ASSERT_OK(err, "verify_perf_link_info");
-	bpf_link__detach(skel->links.tp_run);
+	bpf_link__destroy(link);
 }
 
 static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
 				       enum bpf_perf_event_type type)
 {
+	struct bpf_link *link;
 	int link_fd, err;
 
-	skel->links.uprobe_run = bpf_program__attach_uprobe(skel->progs.uprobe_run,
-							    type == BPF_PERF_EVENT_URETPROBE,
-							    0, /* self pid */
-							    UPROBE_FILE, uprobe_offset);
-	if (!ASSERT_OK_PTR(skel->links.uprobe_run, "attach_uprobe"))
+	link = bpf_program__attach_uprobe(skel->progs.uprobe_run,
+					  type == BPF_PERF_EVENT_URETPROBE,
+					  0, /* self pid */
+					  UPROBE_FILE, uprobe_offset);
+	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.uprobe_run);
+	link_fd = bpf_link__fd(link);
 	err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0);
 	ASSERT_OK(err, "verify_perf_link_info");
-	bpf_link__detach(skel->links.uprobe_run);
+	bpf_link__destroy(link);
 }
 
 static int verify_kmulti_link_info(int fd, bool retprobe)
@@ -278,24 +281,214 @@ static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
 					     bool retprobe, bool invalid)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct bpf_link *link;
 	int link_fd, err;
 
 	opts.syms = kmulti_syms;
 	opts.cnt = KMULTI_CNT;
 	opts.retprobe = retprobe;
-	skel->links.kmulti_run = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run,
-								       NULL, &opts);
-	if (!ASSERT_OK_PTR(skel->links.kmulti_run, "attach_kprobe_multi"))
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe_multi"))
 		return;
 
-	link_fd = bpf_link__fd(skel->links.kmulti_run);
+	link_fd = bpf_link__fd(link);
 	if (!invalid) {
 		err = verify_kmulti_link_info(link_fd, retprobe);
 		ASSERT_OK(err, "verify_kmulti_link_info");
 	} else {
 		verify_kmulti_invalid_user_buffer(link_fd);
 	}
-	bpf_link__detach(skel->links.kmulti_run);
+	bpf_link__destroy(link);
+}
+
+#define SEC(name) __attribute__((section(name), used))
+
+static short uprobe_link_info_sema_1 SEC(".probes");
+static short uprobe_link_info_sema_2 SEC(".probes");
+static short uprobe_link_info_sema_3 SEC(".probes");
+
+noinline void uprobe_link_info_func_1(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_1++;
+}
+
+noinline void uprobe_link_info_func_2(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_2++;
+}
+
+noinline void uprobe_link_info_func_3(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_3++;
+}
+
+static int
+verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets,
+			__u64 *cookies, __u64 *ref_ctr_offsets)
+{
+	char path[PATH_MAX], path_buf[PATH_MAX];
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 ref_ctr_offsets_buf[3];
+	__u64 offsets_buf[3];
+	__u64 cookies_buf[3];
+	int i, err, bit;
+	__u32 count = 0;
+
+	memset(path, 0, sizeof(path));
+	err = readlink("/proc/self/exe", path, sizeof(path));
+	if (!ASSERT_NEQ(err, -1, "readlink"))
+		return -1;
+
+	for (bit = 0; bit < 8; bit++) {
+		memset(&info, 0, sizeof(info));
+		info.uprobe_multi.path = ptr_to_u64(path_buf);
+		info.uprobe_multi.path_size = sizeof(path_buf);
+		info.uprobe_multi.count = count;
+
+		if (bit & 0x1)
+			info.uprobe_multi.offsets = ptr_to_u64(offsets_buf);
+		if (bit & 0x2)
+			info.uprobe_multi.cookies = ptr_to_u64(cookies_buf);
+		if (bit & 0x4)
+			info.uprobe_multi.ref_ctr_offsets = ptr_to_u64(ref_ctr_offsets_buf);
+
+		err = bpf_link_get_info_by_fd(fd, &info, &len);
+		if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+			return -1;
+
+		if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_UPROBE_MULTI, "info.type"))
+			return -1;
+
+		ASSERT_EQ(info.uprobe_multi.pid, getpid(), "info.uprobe_multi.pid");
+		ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count");
+		ASSERT_EQ(info.uprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN,
+			  retprobe, "info.uprobe_multi.flags.retprobe");
+		ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, "info.uprobe_multi.path_size");
+		ASSERT_STREQ(path_buf, path, "info.uprobe_multi.path");
+
+		for (i = 0; i < info.uprobe_multi.count; i++) {
+			if (info.uprobe_multi.offsets)
+				ASSERT_EQ(offsets_buf[i], offsets[i], "info.uprobe_multi.offsets");
+			if (info.uprobe_multi.cookies)
+				ASSERT_EQ(cookies_buf[i], cookies[i], "info.uprobe_multi.cookies");
+			if (info.uprobe_multi.ref_ctr_offsets) {
+				ASSERT_EQ(ref_ctr_offsets_buf[i], ref_ctr_offsets[i],
+					  "info.uprobe_multi.ref_ctr_offsets");
+			}
+		}
+		count = count ?: info.uprobe_multi.count;
+	}
+
+	return 0;
+}
+
+static void verify_umulti_invalid_user_buffer(int fd)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 buf[3];
+	int err;
+
+	/* upath_size defined, not path */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_upath_size");
+
+	/* path defined, but small */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path = ptr_to_u64(buf);
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_LT(err, 0, "failed_upath_small");
+
+	/* path has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = PATH_MAX;
+	info.uprobe_multi.path = 123;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_bad_path_ptr");
+
+	/* count zero, with offsets */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_count");
+
+	/* offsets not big enough */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	info.uprobe_multi.count = 2;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -ENOSPC, "failed_small_count");
+
+	/* offsets has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = 123;
+	info.uprobe_multi.count = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_wrong_offsets");
+}
+
+static void test_uprobe_multi_fill_link_info(struct test_fill_link_info *skel,
+					     bool retprobe, bool invalid)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+		.retprobe = retprobe,
+	);
+	const char *syms[3] = {
+		"uprobe_link_info_func_1",
+		"uprobe_link_info_func_2",
+		"uprobe_link_info_func_3",
+	};
+	__u64 cookies[3] = {
+		0xdead,
+		0xbeef,
+		0xcafe,
+	};
+	const char *sema[3] = {
+		"uprobe_link_info_sema_1",
+		"uprobe_link_info_sema_2",
+		"uprobe_link_info_sema_3",
+	};
+	__u64 *offsets = NULL, *ref_ctr_offsets;
+	struct bpf_link *link;
+	int link_fd, err;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, sema,
+				       (unsigned long **) &ref_ctr_offsets, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_object"))
+		return;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, syms,
+				       (unsigned long **) &offsets, STT_FUNC);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_func"))
+		goto out;
+
+	opts.syms = syms;
+	opts.cookies = &cookies[0];
+	opts.ref_ctr_offsets = (unsigned long *) &ref_ctr_offsets[0];
+	opts.cnt = ARRAY_SIZE(syms);
+
+	link = bpf_program__attach_uprobe_multi(skel->progs.umulti_run, 0,
+						"/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto out;
+
+	link_fd = bpf_link__fd(link);
+	if (invalid)
+		verify_umulti_invalid_user_buffer(link_fd);
+	else
+		verify_umulti_link_info(link_fd, retprobe, offsets, cookies, ref_ctr_offsets);
+
+	bpf_link__destroy(link);
+out:
+	free(ref_ctr_offsets);
+	free(offsets);
 }
 
 void test_fill_link_info(void)
@@ -337,6 +530,13 @@ void test_fill_link_info(void)
 	if (test__start_subtest("kprobe_multi_invalid_ubuff"))
 		test_kprobe_multi_fill_link_info(skel, true, true);
 
+	if (test__start_subtest("uprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, false, false);
+	if (test__start_subtest("uretprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, true, false);
+	if (test__start_subtest("uprobe_multi_invalid"))
+		test_uprobe_multi_fill_link_info(skel, false, true);
+
 cleanup:
 	test_fill_link_info__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index cd051d3901a9..ece260cf2c0b 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -249,7 +249,7 @@ static void __test_link_api(struct child *child)
 	int link_extra_fd = -1;
 	int err;
 
-	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets);
+	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets, STT_FUNC);
 	if (!ASSERT_OK(err, "elf_resolve_syms_offsets"))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 5cfa7a6316b6..8d746642cbd7 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -25,6 +25,7 @@
 #include "verifier_direct_stack_access_wraparound.skel.h"
 #include "verifier_div0.skel.h"
 #include "verifier_div_overflow.skel.h"
+#include "verifier_global_subprogs.skel.h"
 #include "verifier_gotol.skel.h"
 #include "verifier_helper_access_var_len.skel.h"
 #include "verifier_helper_packet_access.skel.h"
@@ -134,6 +135,7 @@ void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_acces
 void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); }
 void test_verifier_div0(void)                 { RUN(verifier_div0); }
 void test_verifier_div_overflow(void)         { RUN(verifier_div_overflow); }
+void test_verifier_global_subprogs(void)      { RUN(verifier_global_subprogs); }
 void test_verifier_gotol(void)                { RUN(verifier_gotol); }
 void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); }
 void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 4439ba9392f8..33cdf88efa6b 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -56,7 +56,8 @@ static int open_xsk(int ifindex, struct xsk *xsk)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx;
 	u64 addr;
@@ -138,6 +139,7 @@ static void ip_csum(struct iphdr *iph)
 
 static int generate_packet(struct xsk *xsk, __u16 dst_port)
 {
+	struct xsk_tx_metadata *meta;
 	struct xdp_desc *tx_desc;
 	struct udphdr *udph;
 	struct ethhdr *eth;
@@ -151,10 +153,14 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 		return -1;
 
 	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
-	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE;
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
 	printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr);
 	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
 
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
 	eth = data;
 	iph = (void *)(eth + 1);
 	udph = (void *)(iph + 1);
@@ -178,11 +184,17 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	udph->source = htons(AF_XDP_SOURCE_PORT);
 	udph->dest = htons(dst_port);
 	udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES);
-	udph->check = 0;
+	udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+					 ntohs(udph->len), IPPROTO_UDP, 0);
 
 	memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES);
 
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
 	tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES;
+	tx_desc->options |= XDP_TX_METADATA;
 	xsk_ring_prod__submit(&xsk->tx, 1);
 
 	ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
@@ -194,13 +206,21 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 
 static void complete_tx(struct xsk *xsk)
 {
-	__u32 idx;
+	struct xsk_tx_metadata *meta;
 	__u64 addr;
+	void *data;
+	__u32 idx;
 
 	if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) {
 		addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
 
 		printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+		data = xsk_umem__get_data(xsk->umem_area, addr);
+		meta = data - sizeof(struct xsk_tx_metadata);
+
+		ASSERT_NEQ(meta->completion.tx_timestamp, 0, "tx_timestamp");
+
 		xsk_ring_cons__release(&xsk->comp, 1);
 	}
 }
@@ -221,6 +241,7 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	const struct xdp_desc *rx_desc;
 	struct pollfd fds = {};
 	struct xdp_meta *meta;
+	struct udphdr *udph;
 	struct ethhdr *eth;
 	struct iphdr *iph;
 	__u64 comp_addr;
@@ -257,6 +278,7 @@ static int verify_xsk_metadata(struct xsk *xsk)
 	ASSERT_EQ(eth->h_proto, htons(ETH_P_IP), "eth->h_proto");
 	iph = (void *)(eth + 1);
 	ASSERT_EQ((int)iph->version, 4, "iph->version");
+	udph = (void *)(iph + 1);
 
 	/* custom metadata */
 
@@ -270,6 +292,9 @@ static int verify_xsk_metadata(struct xsk *xsk)
 
 	ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
 
+	/* checksum offload */
+	ASSERT_EQ(udph->check, htons(0x721c), "csum");
+
 	xsk_ring_cons__release(&xsk->rx, 1);
 	refill_rx(xsk, comp_addr);
 
diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
index 564f402d56fe..69509f8bb680 100644
--- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c
+++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
@@ -39,4 +39,10 @@ int BPF_PROG(kmulti_run)
 	return 0;
 }
 
+SEC("uprobe.multi")
+int BPF_PROG(umulti_run)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c
index 7f159d83c6f6..6e03d42519a6 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func12.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func12.c
@@ -19,5 +19,7 @@ int global_func12(struct __sk_buff *skb)
 {
 	const struct S s = {.x = skb->len };
 
-	return foo(&s);
+	foo(&s);
+
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func17.c b/tools/testing/selftests/bpf/progs/test_global_func17.c
index a32e11c7d933..5de44b09e8ec 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func17.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func17.c
@@ -5,6 +5,7 @@
 
 __noinline int foo(int *p)
 {
+	barrier_var(p);
 	return p ? (*p = 42) : 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
new file mode 100644
index 000000000000..a0a5efd1caa1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <stdbool.h>
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+int arr[1];
+int unkn_idx;
+
+__noinline long global_bad(void)
+{
+	return arr[unkn_idx]; /* BOOM */
+}
+
+__noinline long global_good(void)
+{
+	return arr[0];
+}
+
+__noinline long global_calls_bad(void)
+{
+	return global_good() + global_bad() /* does BOOM indirectly */;
+}
+
+__noinline long global_calls_good_only(void)
+{
+	return global_good();
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+/* main prog is validated completely first */
+__msg("('global_calls_good_only') is global and assumed valid.")
+__msg("1: (95) exit")
+/* eventually global_good() is transitively validated as well */
+__msg("Validating global_good() func")
+__msg("('global_good') is safe for any args that match its prototype")
+int chained_global_func_calls_success(void)
+{
+	return global_calls_good_only();
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+/* main prog validated successfully first */
+__msg("1: (95) exit")
+/* eventually we validate global_bad() and fail */
+__msg("Validating global_bad() func")
+__msg("math between map_value pointer and register") /* BOOM */
+int chained_global_func_calls_bad(void)
+{
+	return global_calls_bad();
+}
+
+/* do out of bounds access forcing verifier to fail verification if this
+ * global func is called
+ */
+__noinline int global_unsupp(const int *mem)
+{
+	if (!mem)
+		return 0;
+	return mem[100]; /* BOOM */
+}
+
+const volatile bool skip_unsupp_global = true;
+
+SEC("?raw_tp")
+__success
+int guarded_unsupp_global_called(void)
+{
+	if (!skip_unsupp_global)
+		return global_unsupp(NULL);
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("Func#1 ('global_unsupp') is global and assumed valid.")
+__msg("Validating global_unsupp() func#1...")
+__msg("value is outside of the allowed memory range")
+int unguarded_unsupp_global_called(void)
+{
+	int x = 0;
+
+	return global_unsupp(&x);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index f61d623b1ce8..b5efcaeaa1ae 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -370,12 +370,10 @@ __naked int parent_stack_slot_precise(void)
 SEC("?raw_tp")
 __success __log_level(2)
 __msg("9: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 9 first_idx 6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)")
-__msg("mark_precise: frame0: parent state regs= stack=-8:")
-__msg("mark_precise: frame0: last_idx 5 first_idx 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6")
 __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6")
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 40cba8d368d9..6157f884d091 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -169,12 +169,14 @@ def bpftool(args, JSON=True, ns="", fail=True, include_stderr=False):
     return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns,
                 fail=fail, include_stderr=include_stderr)
 
-def bpftool_prog_list(expected=None, ns=""):
+def bpftool_prog_list(expected=None, ns="", exclude_orphaned=True):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
     # Remove the base progs
     for p in base_progs:
         if p in progs:
             progs.remove(p)
+    if exclude_orphaned:
+        progs = [ p for p in progs if not p['orphaned'] ]
     if expected is not None:
         if len(progs) != expected:
             fail(True, "%d BPF programs loaded, expected %d" %
@@ -612,11 +614,9 @@ def pin_map(file_name, idx=0, expected=1):
 
 def check_dev_info_removed(prog_file=None, map_file=None):
     bpftool_prog_list(expected=0)
+    bpftool_prog_list(expected=1, exclude_orphaned=False)
     ret, err = bpftool("prog show pin %s" % (prog_file), fail=False)
-    fail(ret == 0, "Showing prog with removed device did not fail")
-    fail(err["error"].find("No such device") == -1,
-         "Showing prog with removed device expected ENODEV, error is %s" %
-         (err["error"]))
+    fail(ret != 0, "failed to show prog with removed device")
 
     bpftool_map_list(expected=0)
     ret, err = bpftool("map show pin %s" % (map_file), fail=False)
@@ -1395,10 +1395,7 @@ try:
 
     start_test("Test multi-dev ASIC cross-dev destruction - orphaned...")
     ret, out = bpftool("prog show %s" % (progB), fail=False)
-    fail(ret == 0, "got information about orphaned program")
-    fail("error" not in out, "no error reported for get info on orphaned")
-    fail(out["error"] != "can't get prog info: No such device",
-         "wrong error for get info on orphaned")
+    fail(ret != 0, "couldn't get information about orphaned program")
 
     print("%s: OK" % (os.path.basename(__file__)))
 
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index c3ba40d0b9de..3291625ba4fb 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -10,7 +10,9 @@
  *   - rx_hash
  *
  * TX:
- * - TBD
+ * - UDP 9091 packets trigger TX reply
+ * - TX HW timestamp is requested and reported back upon completion
+ * - TX checksum is requested
  */
 
 #include <test_progs.h>
@@ -24,15 +26,18 @@
 #include <linux/net_tstamp.h>
 #include <linux/udp.h>
 #include <linux/sockios.h>
+#include <linux/if_xdp.h>
 #include <sys/mman.h>
 #include <net/if.h>
 #include <ctype.h>
 #include <poll.h>
 #include <time.h>
+#include <unistd.h>
+#include <libgen.h>
 
 #include "xdp_metadata.h"
 
-#define UMEM_NUM 16
+#define UMEM_NUM 256
 #define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
 #define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
 #define XDP_FLAGS (XDP_FLAGS_DRV_MODE | XDP_FLAGS_REPLACE)
@@ -48,11 +53,14 @@ struct xsk {
 };
 
 struct xdp_hw_metadata *bpf_obj;
-__u16 bind_flags = XDP_COPY;
+__u16 bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY;
 struct xsk *rx_xsk;
 const char *ifname;
 int ifindex;
 int rxq;
+bool skip_tx;
+__u64 last_hw_rx_timestamp;
+__u64 last_xdp_rx_timestamp;
 
 void test__fail(void) { /* for network_helpers.c */ }
 
@@ -68,7 +76,8 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+		.flags = XSK_UMEM__DEFAULT_FLAGS,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx;
 	u64 addr;
@@ -110,7 +119,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 	for (i = 0; i < UMEM_NUM / 2; i++) {
 		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
 		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
-		*xsk_ring_prod__fill_addr(&xsk->fill, i) = addr;
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx + i) = addr;
 	}
 	xsk_ring_prod__submit(&xsk->fill, ret);
 
@@ -131,12 +140,22 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	__u32 idx;
 
 	if (xsk_ring_prod__reserve(&xsk->fill, 1, &idx) == 1) {
-		printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr);
+		printf("%p: complete rx idx=%u addr=%llx\n", xsk, idx, addr);
 		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
 		xsk_ring_prod__submit(&xsk->fill, 1);
 	}
 }
 
+static int kick_tx(struct xsk *xsk)
+{
+	return sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
+}
+
+static int kick_rx(struct xsk *xsk)
+{
+	return recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+}
+
 #define NANOSEC_PER_SEC 1000000000 /* 10^9 */
 static __u64 gettime(clockid_t clock_id)
 {
@@ -152,6 +171,17 @@ static __u64 gettime(clockid_t clock_id)
 	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
 }
 
+static void print_tstamp_delta(const char *name, const char *refname,
+			       __u64 tstamp, __u64 reference)
+{
+	__s64 delta = (__s64)reference - (__s64)tstamp;
+
+	printf("%s:   %llu (sec:%0.4f) delta to %s sec:%0.4f (%0.3f usec)\n",
+	       name, tstamp, (double)tstamp / NANOSEC_PER_SEC, refname,
+	       (double)delta / NANOSEC_PER_SEC,
+	       (double)delta / 1000);
+}
+
 static void verify_xdp_metadata(void *data, clockid_t clock_id)
 {
 	struct xdp_meta *meta;
@@ -164,25 +194,20 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id)
 		printf("rx_hash: 0x%X with RSS type:0x%X\n",
 		       meta->rx_hash, meta->rx_hash_type);
 
-	printf("rx_timestamp:  %llu (sec:%0.4f)\n", meta->rx_timestamp,
-	       (double)meta->rx_timestamp / NANOSEC_PER_SEC);
 	if (meta->rx_timestamp) {
-		__u64 usr_clock = gettime(clock_id);
-		__u64 xdp_clock = meta->xdp_timestamp;
-		__s64 delta_X = xdp_clock - meta->rx_timestamp;
-		__s64 delta_X2U = usr_clock - xdp_clock;
-
-		printf("XDP RX-time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
-		       xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC,
-		       (double)delta_X / NANOSEC_PER_SEC,
-		       (double)delta_X / 1000);
-
-		printf("AF_XDP time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
-		       usr_clock, (double)usr_clock / NANOSEC_PER_SEC,
-		       (double)delta_X2U / NANOSEC_PER_SEC,
-		       (double)delta_X2U / 1000);
+		__u64 ref_tstamp = gettime(clock_id);
+
+		/* store received timestamps to calculate a delta at tx */
+		last_hw_rx_timestamp = meta->rx_timestamp;
+		last_xdp_rx_timestamp = meta->xdp_timestamp;
+
+		print_tstamp_delta("HW RX-time", "User RX-time",
+				   meta->rx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User RX-time",
+				   meta->xdp_timestamp, ref_tstamp);
+	} else {
+		printf("No rx_timestamp\n");
 	}
-
 }
 
 static void verify_skb_metadata(int fd)
@@ -230,6 +255,129 @@ static void verify_skb_metadata(int fd)
 	printf("skb hwtstamp is not found!\n");
 }
 
+static bool complete_tx(struct xsk *xsk, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	__u64 addr;
+	void *data;
+	__u32 idx;
+
+	if (!xsk_ring_cons__peek(&xsk->comp, 1, &idx))
+		return false;
+
+	addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
+	data = xsk_umem__get_data(xsk->umem_area, addr);
+	meta = data - sizeof(struct xsk_tx_metadata);
+
+	printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+	if (meta->completion.tx_timestamp) {
+		__u64 ref_tstamp = gettime(clock_id);
+
+		print_tstamp_delta("HW TX-complete-time", "User TX-complete-time",
+				   meta->completion.tx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User TX-complete-time",
+				   last_xdp_rx_timestamp, ref_tstamp);
+		print_tstamp_delta("HW RX-time", "HW TX-complete-time",
+				   last_hw_rx_timestamp, meta->completion.tx_timestamp);
+	} else {
+		printf("No tx_timestamp\n");
+	}
+
+	xsk_ring_cons__release(&xsk->comp, 1);
+
+	return true;
+}
+
+#define swap(a, b, len) do { \
+	for (int i = 0; i < len; i++) { \
+		__u8 tmp = ((__u8 *)a)[i]; \
+		((__u8 *)a)[i] = ((__u8 *)b)[i]; \
+		((__u8 *)b)[i] = tmp; \
+	} \
+} while (0)
+
+static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	struct ipv6hdr *ip6h = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_desc *tx_desc;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	__sum16 want_csum;
+	void *data;
+	__u32 idx;
+	int ret;
+	int len;
+
+	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
+	if (ret != 1) {
+		printf("%p: failed to reserve tx slot\n", xsk);
+		return;
+	}
+
+	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
+	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
+
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
+	eth = rx_packet;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		iph = (void *)(eth + 1);
+		udph = (void *)(iph + 1);
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		ip6h = (void *)(eth + 1);
+		udph = (void *)(ip6h + 1);
+	} else {
+		printf("%p: failed to detect IP version for ping pong %04x\n", xsk, eth->h_proto);
+		xsk_ring_prod__cancel(&xsk->tx, 1);
+		return;
+	}
+
+	len = ETH_HLEN;
+	if (ip6h)
+		len += sizeof(*ip6h) + ntohs(ip6h->payload_len);
+	if (iph)
+		len += ntohs(iph->tot_len);
+
+	swap(eth->h_dest, eth->h_source, ETH_ALEN);
+	if (iph)
+		swap(&iph->saddr, &iph->daddr, 4);
+	else
+		swap(&ip6h->saddr, &ip6h->daddr, 16);
+	swap(&udph->source, &udph->dest, 2);
+
+	want_csum = udph->check;
+	if (ip6h)
+		udph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+					       ntohs(udph->len), IPPROTO_UDP, 0);
+	else
+		udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+						 ntohs(udph->len), IPPROTO_UDP, 0);
+
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	if (iph)
+		meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	else
+		meta->request.csum_start = sizeof(*eth) + sizeof(*ip6h);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
+	printf("%p: ping-pong with csum=%04x (want %04x) csum_start=%d csum_offset=%d\n",
+	       xsk, ntohs(udph->check), ntohs(want_csum),
+	       meta->request.csum_start, meta->request.csum_offset);
+
+	memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */
+	tx_desc->options |= XDP_TX_METADATA;
+	tx_desc->len = len;
+
+	xsk_ring_prod__submit(&xsk->tx, 1);
+}
+
 static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id)
 {
 	const struct xdp_desc *rx_desc;
@@ -252,6 +400,13 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 
 	while (true) {
 		errno = 0;
+
+		for (i = 0; i < rxq; i++) {
+			ret = kick_rx(&rx_xsk[i]);
+			if (ret)
+				printf("kick_rx ret=%d\n", ret);
+		}
+
 		ret = poll(fds, rxq + 1, 1000);
 		printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n",
 		       ret, errno, bpf_obj->bss->pkts_skip,
@@ -288,6 +443,22 @@ peek:
 				verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
 						    clock_id);
 				first_seg = false;
+
+				if (!skip_tx) {
+					/* mirror first chunk back */
+					ping_pong(xsk, xsk_umem__get_data(xsk->umem_area, addr),
+						  clock_id);
+
+					ret = kick_tx(xsk);
+					if (ret)
+						printf("kick_tx ret=%d\n", ret);
+
+					for (int j = 0; j < 500; j++) {
+						if (complete_tx(xsk, clock_id))
+							break;
+						usleep(10*1000);
+					}
+				}
 			}
 
 			xsk_ring_cons__release(&xsk->rx, 1);
@@ -420,8 +591,10 @@ static void print_usage(void)
 {
 	const char *usage =
 		"Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n"
-		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -c    Run in copy mode (zerocopy is default)\n"
 		"  -h    Display this help and exit\n\n"
+		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -r    Don't generate AF_XDP reply (rx metadata only)\n"
 		"Generate test packets on the other machine with:\n"
 		"  echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
 
@@ -432,14 +605,22 @@ static void read_args(int argc, char *argv[])
 {
 	int opt;
 
-	while ((opt = getopt(argc, argv, "mh")) != -1) {
+	while ((opt = getopt(argc, argv, "chmr")) != -1) {
 		switch (opt) {
-		case 'm':
-			bind_flags |= XDP_USE_SG;
+		case 'c':
+			bind_flags &= ~XDP_USE_NEED_WAKEUP;
+			bind_flags &= ~XDP_ZEROCOPY;
+			bind_flags |= XDP_COPY;
 			break;
 		case 'h':
 			print_usage();
 			exit(0);
+		case 'm':
+			bind_flags |= XDP_USE_SG;
+			break;
+		case 'r':
+			skip_tx = true;
+			break;
 		case '?':
 			if (isprint(optopt))
 				fprintf(stderr, "Unknown option: -%c\n", optopt);
diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index e574711eeb84..25d568abf0f2 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -115,6 +115,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 		cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 		cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 		cfg->flags = XSK_UMEM__DEFAULT_FLAGS;
+		cfg->tx_metadata_len = 0;
 		return;
 	}
 
@@ -123,6 +124,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 	cfg->frame_size = usr_cfg->frame_size;
 	cfg->frame_headroom = usr_cfg->frame_headroom;
 	cfg->flags = usr_cfg->flags;
+	cfg->tx_metadata_len = usr_cfg->tx_metadata_len;
 }
 
 static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
@@ -252,6 +254,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area,
 	mr.chunk_size = umem->config.frame_size;
 	mr.headroom = umem->config.frame_headroom;
 	mr.flags = umem->config.flags;
+	mr.tx_metadata_len = umem->config.tx_metadata_len;
 
 	err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr));
 	if (err) {
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index 771570bc3731..93c2cc413cfc 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -200,6 +200,7 @@ struct xsk_umem_config {
 	__u32 frame_size;
 	__u32 frame_headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags);