Merge tag 'v6.14-rc4' into next

Sync up with the mainline.

26 files changed, 3108 insertions, 586 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_distill.c b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
index ca84726d5ac1..fb67ae195a73 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_distill.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
@@ -385,7 +385,7 @@ static void test_distilled_base_missing_err(void)
 		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
 	btf5 = btf__new_empty();
 	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
-		return;
+		goto cleanup;
 	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
 	VALIDATE_RAW_BTF(
 		btf5,
@@ -478,7 +478,7 @@ static void test_distilled_base_multi_err2(void)
 		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
 	btf5 = btf__new_empty();
 	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
-		return;
+		goto cleanup;
 	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
 	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [2] int */
 	VALIDATE_RAW_BTF(
@@ -601,6 +601,76 @@ cleanup:
 	btf__free(base);
 }
 
+/* If a needed composite type, which is the member of composite type
+ * in the split BTF, has a different size in the base BTF we wish to
+ * relocate with, btf__relocate() should error out.
+ */
+static void test_distilled_base_embedded_err(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_struct(btf1, "s1", 4);                 /* [2] struct s1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);            /*      int f1; */
+							/* } */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_struct(btf2, "with_embedded", 8);      /* [3] struct with_embedded { */
+	btf__add_field(btf2, "e1", 2, 0, 0);		/*      struct s1 e1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[3] STRUCT 'with_embedded' size=8 vlen=1\n"
+		"\t'e1' type_id=2 bits_offset=0");
+
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(2, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] STRUCT 's1' size=4 vlen=0",
+		"[2] STRUCT 'with_embedded' size=8 vlen=1\n"
+		"\t'e1' type_id=1 bits_offset=0");
+
+	btf5 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
+		goto cleanup;
+
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	/* struct with the same name but different size */
+	btf__add_struct(btf5, "s1", 8);                 /* [2] struct s1 { */
+	btf__add_field(btf5, "f1", 1, 0, 0);            /*      int f1; */
+							/* } */
+
+	ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split");
+cleanup:
+	btf__free(btf5);
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
 void test_btf_distill(void)
 {
 	if (test__start_subtest("distilled_base"))
@@ -613,6 +683,8 @@ void test_btf_distill(void)
 		test_distilled_base_multi_err();
 	if (test__start_subtest("distilled_base_multi_err2"))
 		test_distilled_base_multi_err2();
+	if (test__start_subtest("distilled_base_embedded_err"))
+		test_distilled_base_embedded_err();
 	if (test__start_subtest("distilled_base_vmlinux"))
 		test_distilled_base_vmlinux();
 	if (test__start_subtest("distilled_endianness"))
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c
new file mode 100644
index 000000000000..e1a90c10db8c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_skb_direct_packet_access.skel.h"
+
+void test_cgroup_skb_prog_run_direct_packet_access(void)
+{
+	int err;
+	struct cgroup_skb_direct_packet_access *skel;
+	char test_skb[64] = {};
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = test_skb,
+		.data_size_in = sizeof(test_skb),
+	);
+
+	skel = cgroup_skb_direct_packet_access__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "cgroup_skb_direct_packet_access__open_and_load"))
+		return;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.direct_packet_access), &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts err");
+	ASSERT_EQ(topts.retval, 1, "retval");
+
+	ASSERT_NEQ(skel->bss->data_end, 0, "data_end");
+
+	cgroup_skb_direct_packet_access__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 1c682550e0e7..e10ea92c3fe2 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -2,7 +2,7 @@
 #define _GNU_SOURCE
 #include <test_progs.h>
 #include "progs/core_reloc_types.h"
-#include "bpf_testmod/bpf_testmod.h"
+#include "test_kmods/bpf_testmod.h"
 #include <linux/limits.h>
 #include <sys/mman.h>
 #include <sys/syscall.h>
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
new file mode 100644
index 000000000000..a1d52e73fb16
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -0,0 +1,441 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include <linux/btf.h>
+#include <bpf/bpf.h>
+
+#include "../test_btf.h"
+
+static inline int new_map(void)
+{
+	const char *name = NULL;
+	__u32 max_entries = 1;
+	__u32 value_size = 8;
+	__u32 key_size = 4;
+
+	return bpf_map_create(BPF_MAP_TYPE_ARRAY, name,
+			      key_size, value_size,
+			      max_entries, NULL);
+}
+
+static int new_btf(void)
+{
+	struct btf_blob {
+		struct btf_header btf_hdr;
+		__u32 types[8];
+		__u32 str;
+	} raw_btf = {
+		.btf_hdr = {
+			.magic = BTF_MAGIC,
+			.version = BTF_VERSION,
+			.hdr_len = sizeof(struct btf_header),
+			.type_len = sizeof(raw_btf.types),
+			.str_off = offsetof(struct btf_blob, str) - offsetof(struct btf_blob, types),
+			.str_len = sizeof(raw_btf.str),
+		},
+		.types = {
+			/* long */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8),  /* [1] */
+			/* unsigned long */
+			BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),  /* [2] */
+		},
+	};
+
+	return bpf_btf_load(&raw_btf, sizeof(raw_btf), NULL);
+}
+
+#define Close(FD) do {		\
+	if ((FD) >= 0) {	\
+		close(FD);	\
+		FD = -1;	\
+	}			\
+} while(0)
+
+static bool map_exists(__u32 id)
+{
+	int fd;
+
+	fd = bpf_map_get_fd_by_id(id);
+	if (fd >= 0) {
+		close(fd);
+		return true;
+	}
+	return false;
+}
+
+static bool btf_exists(__u32 id)
+{
+	int fd;
+
+	fd = bpf_btf_get_fd_by_id(id);
+	if (fd >= 0) {
+		close(fd);
+		return true;
+	}
+	return false;
+}
+
+static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *map_ids)
+{
+	__u32 len = sizeof(struct bpf_prog_info);
+	struct bpf_prog_info info;
+	int err;
+
+	memset(&info, 0, len);
+	info.nr_map_ids = *nr_map_ids,
+	info.map_ids = ptr_to_u64(map_ids),
+
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		return -1;
+
+	*nr_map_ids = info.nr_map_ids;
+
+	return 0;
+}
+
+static int __load_test_prog(int map_fd, const int *fd_array, int fd_array_cnt)
+{
+	/* A trivial program which uses one map */
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+
+	opts.fd_array = fd_array;
+	opts.fd_array_cnt = fd_array_cnt;
+
+	return bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, ARRAY_SIZE(insns), &opts);
+}
+
+static int load_test_prog(const int *fd_array, int fd_array_cnt)
+{
+	int map_fd;
+	int ret;
+
+	map_fd = new_map();
+	if (!ASSERT_GE(map_fd, 0, "new_map"))
+		return map_fd;
+
+	ret = __load_test_prog(map_fd, fd_array, fd_array_cnt);
+	close(map_fd);
+	return ret;
+}
+
+static bool check_expected_map_ids(int prog_fd, int expected, __u32 *map_ids, __u32 *nr_map_ids)
+{
+	int err;
+
+	err = bpf_prog_get_map_ids(prog_fd, nr_map_ids, map_ids);
+	if (!ASSERT_OK(err, "bpf_prog_get_map_ids"))
+		return false;
+	if (!ASSERT_EQ(*nr_map_ids, expected, "unexpected nr_map_ids"))
+		return false;
+
+	return true;
+}
+
+/*
+ * Load a program, which uses one map. No fd_array maps are present.
+ * On return only one map is expected to be bound to prog.
+ */
+static void check_fd_array_cnt__no_fd_array(void)
+{
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	prog_fd = load_test_prog(NULL, 0);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		return;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids);
+	close(prog_fd);
+}
+
+/*
+ * Load a program, which uses one map, and pass two extra, non-equal, maps in
+ * fd_array with fd_array_cnt=2. On return three maps are expected to be bound
+ * to the program.
+ */
+static void check_fd_array_cnt__fd_array_ok(void)
+{
+	int extra_fds[2] = { -1, -1 };
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	extra_fds[0] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	extra_fds[1] = new_map();
+	if (!ASSERT_GE(extra_fds[1], 0, "new_map"))
+		goto cleanup;
+	prog_fd = load_test_prog(extra_fds, 2);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids))
+		goto cleanup;
+
+	/* maps should still exist when original file descriptors are closed */
+	Close(extra_fds[0]);
+	Close(extra_fds[1]);
+	if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map_ids[0] should exist"))
+		goto cleanup;
+	if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map_ids[1] should exist"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[1]);
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+/*
+ * Load a program with a few extra maps duplicated in the fd_array.
+ * After the load maps should only be referenced once.
+ */
+static void check_fd_array_cnt__duplicated_maps(void)
+{
+	int extra_fds[4] = { -1, -1, -1, -1 };
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	extra_fds[0] = extra_fds[2] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	extra_fds[1] = extra_fds[3] = new_map();
+	if (!ASSERT_GE(extra_fds[1], 0, "new_map"))
+		goto cleanup;
+	prog_fd = load_test_prog(extra_fds, 4);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids))
+		goto cleanup;
+
+	/* maps should still exist when original file descriptors are closed */
+	Close(extra_fds[0]);
+	Close(extra_fds[1]);
+	if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist"))
+		goto cleanup;
+	if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map should exist"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[1]);
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+/*
+ * Check that if maps which are referenced by a program are
+ * passed in fd_array, then they will be referenced only once
+ */
+static void check_fd_array_cnt__referenced_maps_in_fd_array(void)
+{
+	int extra_fds[1] = { -1 };
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	extra_fds[0] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	prog_fd = __load_test_prog(extra_fds[0], extra_fds, 1);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	if (!check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids))
+		goto cleanup;
+
+	/* map should still exist when original file descriptor is closed */
+	Close(extra_fds[0]);
+	if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+static int get_btf_id_by_fd(int btf_fd, __u32 *id)
+{
+	struct bpf_btf_info info;
+	__u32 info_len = sizeof(info);
+	int err;
+
+	memset(&info, 0, info_len);
+	err = bpf_btf_get_info_by_fd(btf_fd, &info, &info_len);
+	if (err)
+		return err;
+	if (id)
+		*id = info.id;
+	return 0;
+}
+
+/*
+ * Check that fd_array operates properly for btfs. Namely, to check that
+ * passing a btf fd in fd_array increases its reference count, do the
+ * following:
+ *  1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1
+ *  2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2
+ *  3) Close the btf_fd, now refcnt=1
+ * Wait and check that BTF stil exists.
+ */
+static void check_fd_array_cnt__referenced_btfs(void)
+{
+	int extra_fds[1] = { -1 };
+	int prog_fd = -1;
+	__u32 btf_id;
+	int tries;
+	int err;
+
+	extra_fds[0] = new_btf();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_btf"))
+		goto cleanup;
+	prog_fd = load_test_prog(extra_fds, 1);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+
+	/* btf should still exist when original file descriptor is closed */
+	err = get_btf_id_by_fd(extra_fds[0], &btf_id);
+	if (!ASSERT_GE(err, 0, "get_btf_id_by_fd"))
+		goto cleanup;
+
+	Close(extra_fds[0]);
+
+	if (!ASSERT_GE(kern_sync_rcu(), 0, "kern_sync_rcu 1"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(btf_exists(btf_id), true, "btf should exist"))
+		goto cleanup;
+
+	Close(prog_fd);
+
+	/* The program is freed by a workqueue, so no reliable
+	 * way to sync, so just wait a bit (max ~1 second). */
+	for (tries = 100; tries >= 0; tries--) {
+		usleep(1000);
+
+		if (!btf_exists(btf_id))
+			break;
+
+		if (tries)
+			continue;
+
+		PRINT_FAIL("btf should have been freed");
+	}
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+/*
+ * Test that a program with trash in fd_array can't be loaded:
+ * only map and BTF file descriptors should be accepted.
+ */
+static void check_fd_array_cnt__fd_array_with_trash(void)
+{
+	int extra_fds[3] = { -1, -1, -1 };
+	int prog_fd = -1;
+
+	extra_fds[0] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	extra_fds[1] = new_btf();
+	if (!ASSERT_GE(extra_fds[1], 0, "new_btf"))
+		goto cleanup;
+
+	/* trash 1: not a file descriptor */
+	extra_fds[2] = 0xbeef;
+	prog_fd = load_test_prog(extra_fds, 3);
+	if (!ASSERT_EQ(prog_fd, -EBADF, "prog should have been rejected with -EBADF"))
+		goto cleanup;
+
+	/* trash 2: not a map or btf */
+	extra_fds[2] = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(extra_fds[2], 0, "socket"))
+		goto cleanup;
+
+	prog_fd = load_test_prog(extra_fds, 3);
+	if (!ASSERT_EQ(prog_fd, -EINVAL, "prog should have been rejected with -EINVAL"))
+		goto cleanup;
+
+	/* Validate that the prog is ok if trash is removed */
+	Close(extra_fds[2]);
+	extra_fds[2] = new_btf();
+	if (!ASSERT_GE(extra_fds[2], 0, "new_btf"))
+		goto cleanup;
+
+	prog_fd = load_test_prog(extra_fds, 3);
+	if (!ASSERT_GE(prog_fd, 0, "prog should have been loaded"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[2]);
+	Close(extra_fds[1]);
+	Close(extra_fds[0]);
+}
+
+/*
+ * Test that a program with too big fd_array can't be loaded.
+ */
+static void check_fd_array_cnt__fd_array_too_big(void)
+{
+	int extra_fds[65];
+	int prog_fd = -1;
+	int i;
+
+	for (i = 0; i < 65; i++) {
+		extra_fds[i] = new_map();
+		if (!ASSERT_GE(extra_fds[i], 0, "new_map"))
+			goto cleanup_fds;
+	}
+
+	prog_fd = load_test_prog(extra_fds, 65);
+	ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG");
+
+cleanup_fds:
+	while (i > 0)
+		Close(extra_fds[--i]);
+}
+
+void test_fd_array_cnt(void)
+{
+	if (test__start_subtest("no-fd-array"))
+		check_fd_array_cnt__no_fd_array();
+
+	if (test__start_subtest("fd-array-ok"))
+		check_fd_array_cnt__fd_array_ok();
+
+	if (test__start_subtest("fd-array-dup-input"))
+		check_fd_array_cnt__duplicated_maps();
+
+	if (test__start_subtest("fd-array-ref-maps-in-array"))
+		check_fd_array_cnt__referenced_maps_in_fd_array();
+
+	if (test__start_subtest("fd-array-ref-btfs"))
+		check_fd_array_cnt__referenced_btfs();
+
+	if (test__start_subtest("fd-array-trash-input"))
+		check_fd_array_cnt__fd_array_with_trash();
+
+	if (test__start_subtest("fd-array-2big"))
+		check_fd_array_cnt__fd_array_too_big();
+}
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 d50cbd8040d4..e59af2aa6601 100644
--- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -171,6 +171,10 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
 		/* See also arch_adjust_kprobe_addr(). */
 		if (skel->kconfig->CONFIG_X86_KERNEL_IBT)
 			entry_offset = 4;
+		if (skel->kconfig->CONFIG_PPC64 &&
+		    skel->kconfig->CONFIG_KPROBES_ON_FTRACE &&
+		    !skel->kconfig->CONFIG_PPC_FTRACE_OUT_OF_LINE)
+			entry_offset = 4;
 		err = verify_perf_link_info(link_fd, type, kprobe_addr, 0, entry_offset);
 		ASSERT_OK(err, "verify_perf_link_info");
 	} else {
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index cfcc90cb7ffb..08bae13248c4 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -7,39 +7,14 @@
 
 #include "bpf_flow.skel.h"
 
+#define TEST_NS	"flow_dissector_ns"
 #define FLOW_CONTINUE_SADDR 0x7f00007f /* 127.0.0.127 */
+#define TEST_NAME_MAX_LEN	64
 
 #ifndef IP_MF
 #define IP_MF 0x2000
 #endif
 
-#define CHECK_FLOW_KEYS(desc, got, expected)				\
-	_CHECK(memcmp(&got, &expected, sizeof(got)) != 0,		\
-	      desc,							\
-	      topts.duration,						\
-	      "nhoff=%u/%u "						\
-	      "thoff=%u/%u "						\
-	      "addr_proto=0x%x/0x%x "					\
-	      "is_frag=%u/%u "						\
-	      "is_first_frag=%u/%u "					\
-	      "is_encap=%u/%u "						\
-	      "ip_proto=0x%x/0x%x "					\
-	      "n_proto=0x%x/0x%x "					\
-	      "flow_label=0x%x/0x%x "					\
-	      "sport=%u/%u "						\
-	      "dport=%u/%u\n",						\
-	      got.nhoff, expected.nhoff,				\
-	      got.thoff, expected.thoff,				\
-	      got.addr_proto, expected.addr_proto,			\
-	      got.is_frag, expected.is_frag,				\
-	      got.is_first_frag, expected.is_first_frag,		\
-	      got.is_encap, expected.is_encap,				\
-	      got.ip_proto, expected.ip_proto,				\
-	      got.n_proto, expected.n_proto,				\
-	      got.flow_label, expected.flow_label,			\
-	      got.sport, expected.sport,				\
-	      got.dport, expected.dport)
-
 struct ipv4_pkt {
 	struct ethhdr eth;
 	struct iphdr iph;
@@ -89,6 +64,19 @@ struct dvlan_ipv6_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct gre_base_hdr {
+	__be16 flags;
+	__be16 protocol;
+} gre_base_hdr;
+
+struct gre_minimal_pkt {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct gre_base_hdr gre_hdr;
+	struct iphdr iph_inner;
+	struct tcphdr tcp;
+} __packed;
+
 struct test {
 	const char *name;
 	union {
@@ -98,6 +86,7 @@ struct test {
 		struct ipv6_pkt ipv6;
 		struct ipv6_frag_pkt ipv6_frag;
 		struct dvlan_ipv6_pkt dvlan_ipv6;
+		struct gre_minimal_pkt gre_minimal;
 	} pkt;
 	struct bpf_flow_keys keys;
 	__u32 flags;
@@ -106,7 +95,6 @@ struct test {
 
 #define VLAN_HLEN	4
 
-static __u32 duration;
 struct test tests[] = {
 	{
 		.name = "ipv4",
@@ -444,8 +432,137 @@ struct test tests[] = {
 		},
 		.retval = BPF_FLOW_DISSECTOR_CONTINUE,
 	},
+	{
+		.name = "ip-gre",
+		.pkt.gre_minimal = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_GRE,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.gre_hdr = {
+				.flags = 0,
+				.protocol = __bpf_constant_htons(ETH_P_IP),
+			},
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr) * 2 +
+				 sizeof(struct gre_base_hdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.retval = BPF_OK,
+	},
+	{
+		.name = "ip-gre-no-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_GRE,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr)
+				 + sizeof(struct gre_base_hdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_GRE,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+		.retval = BPF_OK,
+	},
 };
 
+void serial_test_flow_dissector_namespace(void)
+{
+	struct bpf_flow *skel;
+	struct nstoken *ns;
+	int err, prog_fd;
+
+	skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
+		return;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (!ASSERT_OK_FD(prog_fd, "get dissector fd"))
+		goto out_destroy_skel;
+
+	/* We must be able to attach a flow dissector to root namespace */
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (!ASSERT_OK(err, "attach on root namespace ok"))
+		goto out_destroy_skel;
+
+	err = make_netns(TEST_NS);
+	if (!ASSERT_OK(err, "create non-root net namespace"))
+		goto out_destroy_skel;
+
+	/* We must not be able to additionally attach a flow dissector to a
+	 * non-root net namespace
+	 */
+	ns = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(ns, "enter non-root net namespace"))
+		goto out_clean_ns;
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (!ASSERT_ERR(err,
+			"refuse new flow dissector in non-root net namespace"))
+		bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	else
+		ASSERT_EQ(errno, EEXIST,
+			  "refused because of already attached prog");
+	close_netns(ns);
+
+	/* If no flow dissector is attached to the root namespace, we must
+	 * be able to attach one to a non-root net namespace
+	 */
+	bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	ns = open_netns(TEST_NS);
+	ASSERT_OK_PTR(ns, "enter non-root net namespace");
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	close_netns(ns);
+	ASSERT_OK(err, "accept new flow dissector in non-root net namespace");
+
+	/* If a flow dissector is attached to non-root net namespace, attaching
+	 * a flow dissector to root namespace must fail
+	 */
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (!ASSERT_ERR(err, "refuse new flow dissector on root namespace"))
+		bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	else
+		ASSERT_EQ(errno, EEXIST,
+			  "refused because of already attached prog");
+
+	ns = open_netns(TEST_NS);
+	bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	close_netns(ns);
+out_clean_ns:
+	remove_netns(TEST_NS);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
+}
+
 static int create_tap(const char *ifname)
 {
 	struct ifreq ifr = {
@@ -533,22 +650,27 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array)
 	return 0;
 }
 
-static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
+static void run_tests_skb_less(int tap_fd, struct bpf_map *keys,
+			       char *test_suffix)
 {
+	char test_name[TEST_NAME_MAX_LEN];
 	int i, err, keys_fd;
 
 	keys_fd = bpf_map__fd(keys);
-	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+	if (!ASSERT_OK_FD(keys_fd, "bpf_map__fd"))
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		/* Keep in sync with 'flags' from eth_get_headlen. */
 		__u32 eth_get_headlen_flags =
 			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
-		LIBBPF_OPTS(bpf_test_run_opts, topts);
 		struct bpf_flow_keys flow_keys = {};
 		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
 			    tests[i].keys.dport;
+		snprintf(test_name, TEST_NAME_MAX_LEN, "%s-%s", tests[i].name,
+			 test_suffix);
+		if (!test__start_subtest(test_name))
+			continue;
 
 		/* For skb-less case we can't pass input flags; run
 		 * only the tests that have a matching set of flags.
@@ -558,78 +680,139 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
 			continue;
 
 		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
-		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
+		if (!ASSERT_EQ(err, sizeof(tests[i].pkt), "tx_tap"))
+			continue;
 
 		/* check the stored flow_keys only if BPF_OK expected */
 		if (tests[i].retval != BPF_OK)
 			continue;
 
 		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
-		ASSERT_OK(err, "bpf_map_lookup_elem");
+		if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+			continue;
 
-		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+		ASSERT_MEMEQ(&flow_keys, &tests[i].keys,
+			     sizeof(struct bpf_flow_keys),
+			     "returned flow keys");
 
 		err = bpf_map_delete_elem(keys_fd, &key);
 		ASSERT_OK(err, "bpf_map_delete_elem");
 	}
 }
 
-static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd)
+void test_flow_dissector_skb_less_direct_attach(void)
 {
-	int err, prog_fd;
+	int err, prog_fd, tap_fd;
+	struct bpf_flow *skel;
+	struct netns_obj *ns;
 
-	prog_fd = bpf_program__fd(skel->progs._dissect);
-	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+	ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true);
+	if (!ASSERT_OK_PTR(ns, "create and open netns"))
 		return;
 
+	skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
+		goto out_clean_ns;
+
+	err = init_prog_array(skel->obj, skel->maps.jmp_table);
+	if (!ASSERT_OK(err, "init_prog_array"))
+		goto out_destroy_skel;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd"))
+		goto out_destroy_skel;
+
 	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
-	if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno))
-		return;
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out_destroy_skel;
+
+	tap_fd = create_tap("tap0");
+	if (!ASSERT_OK_FD(tap_fd, "create_tap"))
+		goto out_destroy_skel;
+	err = ifup("tap0");
+	if (!ASSERT_OK(err, "ifup"))
+		goto out_close_tap;
 
-	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection,
+			   "non-skb-direct-attach");
 
 	err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
-	CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno);
+	ASSERT_OK(err, "bpf_prog_detach2");
+
+out_close_tap:
+	close(tap_fd);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
+out_clean_ns:
+	netns_free(ns);
 }
 
-static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd)
+void test_flow_dissector_skb_less_indirect_attach(void)
 {
+	int err, net_fd, tap_fd;
+	struct bpf_flow *skel;
 	struct bpf_link *link;
-	int err, net_fd;
+	struct netns_obj *ns;
 
-	net_fd = open("/proc/self/ns/net", O_RDONLY);
-	if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno))
+	ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true);
+	if (!ASSERT_OK_PTR(ns, "create and open netns"))
 		return;
 
+	skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
+		goto out_clean_ns;
+
+	net_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (!ASSERT_OK_FD(net_fd, "open(/proc/self/ns/net"))
+		goto out_destroy_skel;
+
+	err = init_prog_array(skel->obj, skel->maps.jmp_table);
+	if (!ASSERT_OK(err, "init_prog_array"))
+		goto out_destroy_skel;
+
+	tap_fd = create_tap("tap0");
+	if (!ASSERT_OK_FD(tap_fd, "create_tap"))
+		goto out_close_ns;
+	err = ifup("tap0");
+	if (!ASSERT_OK(err, "ifup"))
+		goto out_close_tap;
+
 	link = bpf_program__attach_netns(skel->progs._dissect, net_fd);
 	if (!ASSERT_OK_PTR(link, "attach_netns"))
-		goto out_close;
+		goto out_close_tap;
 
-	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection,
+			   "non-skb-indirect-attach");
 
 	err = bpf_link__destroy(link);
-	CHECK(err, "bpf_link__destroy", "err %d\n", err);
-out_close:
+	ASSERT_OK(err, "bpf_link__destroy");
+
+out_close_tap:
+	close(tap_fd);
+out_close_ns:
 	close(net_fd);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
+out_clean_ns:
+	netns_free(ns);
 }
 
-void test_flow_dissector(void)
+void test_flow_dissector_skb(void)
 {
-	int i, err, prog_fd, keys_fd = -1, tap_fd;
+	char test_name[TEST_NAME_MAX_LEN];
 	struct bpf_flow *skel;
+	int i, err, prog_fd;
 
 	skel = bpf_flow__open_and_load();
-	if (CHECK(!skel, "skel", "failed to open/load skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs._dissect);
-	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
-		goto out_destroy_skel;
-	keys_fd = bpf_map__fd(skel->maps.last_dissection);
-	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
-		goto out_destroy_skel;
 	err = init_prog_array(skel->obj, skel->maps.jmp_table);
-	if (CHECK(err, "init_prog_array", "err %d\n", err))
+	if (!ASSERT_OK(err, "init_prog_array"))
+		goto out_destroy_skel;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd"))
 		goto out_destroy_skel;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
@@ -641,6 +824,10 @@ void test_flow_dissector(void)
 		);
 		static struct bpf_flow_keys ctx = {};
 
+		snprintf(test_name, TEST_NAME_MAX_LEN, "%s-skb", tests[i].name);
+		if (!test__start_subtest(test_name))
+			continue;
+
 		if (tests[i].flags) {
 			topts.ctx_in = &ctx;
 			topts.ctx_size_in = sizeof(ctx);
@@ -656,26 +843,12 @@ void test_flow_dissector(void)
 			continue;
 		ASSERT_EQ(topts.data_size_out, sizeof(flow_keys),
 			  "test_run data_size_out");
-		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+		ASSERT_MEMEQ(&flow_keys, &tests[i].keys,
+			     sizeof(struct bpf_flow_keys),
+			     "returned flow keys");
 	}
 
-	/* Do the same tests but for skb-less flow dissector.
-	 * We use a known path in the net/tun driver that calls
-	 * eth_get_headlen and we manually export bpf_flow_keys
-	 * via BPF map in this case.
-	 */
-
-	tap_fd = create_tap("tap0");
-	CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno);
-	err = ifup("tap0");
-	CHECK(err, "ifup", "err %d errno %d\n", err, errno);
-
-	/* Test direct prog attachment */
-	test_skb_less_prog_attach(skel, tap_fd);
-	/* Test indirect prog attachment via link */
-	test_skb_less_link_create(skel, tap_fd);
-
-	close(tap_fd);
 out_destroy_skel:
 	bpf_flow__destroy(skel);
 }
+
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c
new file mode 100644
index 000000000000..80b153d3ddec
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c
@@ -0,0 +1,797 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <bpf/bpf.h>
+#include <linux/bpf.h>
+#include <bpf/libbpf.h>
+#include <arpa/inet.h>
+#include <asm/byteorder.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "bpf_util.h"
+#include "bpf_flow.skel.h"
+
+#define CFG_PORT_INNER 8000
+#define CFG_PORT_GUE 6080
+#define SUBTEST_NAME_MAX_LEN 32
+#define TEST_NAME_MAX_LEN (32 + SUBTEST_NAME_MAX_LEN)
+#define MAX_SOURCE_PORTS 3
+#define TEST_PACKETS_COUNT 10
+#define TEST_PACKET_LEN 100
+#define TEST_PACKET_PATTERN 'a'
+#define TEST_IPV4 "192.168.0.1/32"
+#define TEST_IPV6 "100::a/128"
+#define TEST_TUNNEL_REMOTE "127.0.0.2"
+#define TEST_TUNNEL_LOCAL "127.0.0.1"
+
+#define INIT_ADDR4(addr4, port)					\
+	{							\
+		.sin_family = AF_INET,				\
+		.sin_port = __constant_htons(port),		\
+		.sin_addr.s_addr = __constant_htonl(addr4),	\
+	}
+
+#define INIT_ADDR6(addr6, port)				\
+	{						\
+		.sin6_family = AF_INET6,		\
+		.sin6_port = __constant_htons(port),	\
+		.sin6_addr = addr6,			\
+	}
+#define TEST_IN4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 2, 0)
+#define TEST_IN4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, CFG_PORT_INNER)
+#define TEST_OUT4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 1, 0)
+#define TEST_OUT4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, 0)
+
+#define TEST_IN6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0)
+#define TEST_IN6_DST_ADDR_DEFAULT \
+	INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER)
+#define TEST_OUT6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0)
+#define TEST_OUT6_DST_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0)
+
+#define TEST_IN4_SRC_ADDR_DISSECT_CONTINUE INIT_ADDR4(INADDR_LOOPBACK + 126, 0)
+#define TEST_IN4_SRC_ADDR_IPIP INIT_ADDR4((in_addr_t)0x01010101, 0)
+#define TEST_IN4_DST_ADDR_IPIP INIT_ADDR4((in_addr_t)0xC0A80001, CFG_PORT_INNER)
+
+struct grehdr {
+	uint16_t unused;
+	uint16_t protocol;
+} __packed;
+
+struct guehdr {
+	union {
+		struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+			__u8 hlen : 5, control : 1, version : 2;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+			__u8 version : 2, control : 1, hlen : 5;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+			__u8 proto_ctype;
+			__be16 flags;
+		};
+		__be32 word;
+	};
+};
+
+static char buf[ETH_DATA_LEN];
+
+struct test_configuration {
+	char name[SUBTEST_NAME_MAX_LEN];
+	int (*test_setup)(void);
+	void (*test_teardown)(void);
+	int source_ports[MAX_SOURCE_PORTS];
+	int cfg_l3_inner;
+	struct sockaddr_in in_saddr4;
+	struct sockaddr_in in_daddr4;
+	struct sockaddr_in6 in_saddr6;
+	struct sockaddr_in6 in_daddr6;
+	int cfg_l3_outer;
+	struct sockaddr_in out_saddr4;
+	struct sockaddr_in out_daddr4;
+	struct sockaddr_in6 out_saddr6;
+	struct sockaddr_in6 out_daddr6;
+	int cfg_encap_proto;
+	uint8_t cfg_dsfield_inner;
+	uint8_t cfg_dsfield_outer;
+	int cfg_l3_extra;
+	struct sockaddr_in extra_saddr4;
+	struct sockaddr_in extra_daddr4;
+	struct sockaddr_in6 extra_saddr6;
+	struct sockaddr_in6 extra_daddr6;
+};
+
+static unsigned long util_gettime(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void build_ipv4_header(void *header, uint8_t proto, uint32_t src,
+			      uint32_t dst, int payload_len, uint8_t tos)
+{
+	struct iphdr *iph = header;
+
+	iph->ihl = 5;
+	iph->version = 4;
+	iph->tos = tos;
+	iph->ttl = 8;
+	iph->tot_len = htons(sizeof(*iph) + payload_len);
+	iph->id = htons(1337);
+	iph->protocol = proto;
+	iph->saddr = src;
+	iph->daddr = dst;
+	iph->check = build_ip_csum((void *)iph);
+}
+
+static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield)
+{
+	uint16_t val, *ptr = (uint16_t *)ip6h;
+
+	val = ntohs(*ptr);
+	val &= 0xF00F;
+	val |= ((uint16_t)dsfield) << 4;
+	*ptr = htons(val);
+}
+
+static void build_ipv6_header(void *header, uint8_t proto,
+			      const struct sockaddr_in6 *src,
+			      const struct sockaddr_in6 *dst, int payload_len,
+			      uint8_t dsfield)
+{
+	struct ipv6hdr *ip6h = header;
+
+	ip6h->version = 6;
+	ip6h->payload_len = htons(payload_len);
+	ip6h->nexthdr = proto;
+	ip6h->hop_limit = 8;
+	ipv6_set_dsfield(ip6h, dsfield);
+
+	memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr));
+	memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr));
+}
+
+static void build_udp_header(void *header, int payload_len, uint16_t sport,
+			     uint16_t dport, int family)
+{
+	struct udphdr *udph = header;
+	int len = sizeof(*udph) + payload_len;
+
+	udph->source = htons(sport);
+	udph->dest = htons(dport);
+	udph->len = htons(len);
+	udph->check = 0;
+	if (family == AF_INET)
+		udph->check = build_udp_v4_csum(header - sizeof(struct iphdr),
+						udph);
+	else
+		udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr),
+						udph);
+}
+
+static void build_gue_header(void *header, uint8_t proto)
+{
+	struct guehdr *gueh = header;
+
+	gueh->proto_ctype = proto;
+}
+
+static void build_gre_header(void *header, uint16_t proto)
+{
+	struct grehdr *greh = header;
+
+	greh->protocol = htons(proto);
+}
+
+static int l3_length(int family)
+{
+	if (family == AF_INET)
+		return sizeof(struct iphdr);
+	else
+		return sizeof(struct ipv6hdr);
+}
+
+static int build_packet(const struct test_configuration *test, uint16_t sport)
+{
+	int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0;
+	int el3_len = 0, packet_len;
+
+	memset(buf, 0, ETH_DATA_LEN);
+
+	if (test->cfg_l3_extra)
+		el3_len = l3_length(test->cfg_l3_extra);
+
+	/* calculate header offsets */
+	if (test->cfg_encap_proto) {
+		ol3_len = l3_length(test->cfg_l3_outer);
+
+		if (test->cfg_encap_proto == IPPROTO_GRE)
+			ol4_len = sizeof(struct grehdr);
+		else if (test->cfg_encap_proto == IPPROTO_UDP)
+			ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr);
+	}
+
+	il3_len = l3_length(test->cfg_l3_inner);
+	il4_len = sizeof(struct udphdr);
+
+	packet_len = el3_len + ol3_len + ol4_len + il3_len + il4_len +
+		     TEST_PACKET_LEN;
+	if (!ASSERT_LE(packet_len, sizeof(buf), "check packet size"))
+		return -1;
+
+	/*
+	 * Fill packet from inside out, to calculate correct checksums.
+	 * But create ip before udp headers, as udp uses ip for pseudo-sum.
+	 */
+	memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len,
+	       TEST_PACKET_PATTERN, TEST_PACKET_LEN);
+
+	/* add zero byte for udp csum padding */
+	buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + TEST_PACKET_LEN] =
+		0;
+
+	switch (test->cfg_l3_inner) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP, test->in_saddr4.sin_addr.s_addr,
+				  test->in_daddr4.sin_addr.s_addr,
+				  il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_inner);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP, &test->in_saddr6,
+				  &test->in_daddr6, il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_inner);
+		break;
+	}
+
+	build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len,
+			 TEST_PACKET_LEN, sport, CFG_PORT_INNER,
+			 test->cfg_l3_inner);
+
+	if (!test->cfg_encap_proto)
+		return il3_len + il4_len + TEST_PACKET_LEN;
+
+	switch (test->cfg_l3_outer) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len, test->cfg_encap_proto,
+				  test->out_saddr4.sin_addr.s_addr,
+				  test->out_daddr4.sin_addr.s_addr,
+				  ol4_len + il3_len + il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_outer);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len, test->cfg_encap_proto,
+				  &test->out_saddr6, &test->out_daddr6,
+				  ol4_len + il3_len + il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_outer);
+		break;
+	}
+
+	switch (test->cfg_encap_proto) {
+	case IPPROTO_UDP:
+		build_gue_header(buf + el3_len + ol3_len + ol4_len -
+					 sizeof(struct guehdr),
+				 test->cfg_l3_inner == PF_INET ? IPPROTO_IPIP :
+								 IPPROTO_IPV6);
+		build_udp_header(buf + el3_len + ol3_len,
+				 sizeof(struct guehdr) + il3_len + il4_len +
+					 TEST_PACKET_LEN,
+				 sport, CFG_PORT_GUE, test->cfg_l3_outer);
+		break;
+	case IPPROTO_GRE:
+		build_gre_header(buf + el3_len + ol3_len,
+				 test->cfg_l3_inner == PF_INET ? ETH_P_IP :
+								 ETH_P_IPV6);
+		break;
+	}
+
+	switch (test->cfg_l3_extra) {
+	case PF_INET:
+		build_ipv4_header(buf,
+				  test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP :
+								  IPPROTO_IPV6,
+				  test->extra_saddr4.sin_addr.s_addr,
+				  test->extra_daddr4.sin_addr.s_addr,
+				  ol3_len + ol4_len + il3_len + il4_len +
+					  TEST_PACKET_LEN,
+				  0);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf,
+				  test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP :
+								  IPPROTO_IPV6,
+				  &test->extra_saddr6, &test->extra_daddr6,
+				  ol3_len + ol4_len + il3_len + il4_len +
+					  TEST_PACKET_LEN,
+				  0);
+		break;
+	}
+
+	return el3_len + ol3_len + ol4_len + il3_len + il4_len +
+	       TEST_PACKET_LEN;
+}
+
+/* sender transmits encapsulated over RAW or unencap'd over UDP */
+static int setup_tx(const struct test_configuration *test)
+{
+	int family, fd, ret;
+
+	if (test->cfg_l3_extra)
+		family = test->cfg_l3_extra;
+	else if (test->cfg_l3_outer)
+		family = test->cfg_l3_outer;
+	else
+		family = test->cfg_l3_inner;
+
+	fd = socket(family, SOCK_RAW, IPPROTO_RAW);
+	if (!ASSERT_OK_FD(fd, "setup tx socket"))
+		return fd;
+
+	if (test->cfg_l3_extra) {
+		if (test->cfg_l3_extra == PF_INET)
+			ret = connect(fd, (void *)&test->extra_daddr4,
+				      sizeof(test->extra_daddr4));
+		else
+			ret = connect(fd, (void *)&test->extra_daddr6,
+				      sizeof(test->extra_daddr6));
+		if (!ASSERT_OK(ret, "connect")) {
+			close(fd);
+			return ret;
+		}
+	} else if (test->cfg_l3_outer) {
+		/* connect to destination if not encapsulated */
+		if (test->cfg_l3_outer == PF_INET)
+			ret = connect(fd, (void *)&test->out_daddr4,
+				      sizeof(test->out_daddr4));
+		else
+			ret = connect(fd, (void *)&test->out_daddr6,
+				      sizeof(test->out_daddr6));
+		if (!ASSERT_OK(ret, "connect")) {
+			close(fd);
+			return ret;
+		}
+	} else {
+		/* otherwise using loopback */
+		if (test->cfg_l3_inner == PF_INET)
+			ret = connect(fd, (void *)&test->in_daddr4,
+				      sizeof(test->in_daddr4));
+		else
+			ret = connect(fd, (void *)&test->in_daddr6,
+				      sizeof(test->in_daddr6));
+		if (!ASSERT_OK(ret, "connect")) {
+			close(fd);
+			return ret;
+		}
+	}
+
+	return fd;
+}
+
+/* receiver reads unencapsulated UDP */
+static int setup_rx(const struct test_configuration *test)
+{
+	int fd, ret;
+
+	fd = socket(test->cfg_l3_inner, SOCK_DGRAM, 0);
+	if (!ASSERT_OK_FD(fd, "socket rx"))
+		return fd;
+
+	if (test->cfg_l3_inner == PF_INET)
+		ret = bind(fd, (void *)&test->in_daddr4,
+			   sizeof(test->in_daddr4));
+	else
+		ret = bind(fd, (void *)&test->in_daddr6,
+			   sizeof(test->in_daddr6));
+	if (!ASSERT_OK(ret, "bind rx")) {
+		close(fd);
+		return ret;
+	}
+
+	return fd;
+}
+
+static int do_tx(int fd, const char *pkt, int len)
+{
+	int ret;
+
+	ret = write(fd, pkt, len);
+	return ret != len;
+}
+
+static int do_poll(int fd, short events, int timeout)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.fd = fd;
+	pfd.events = events;
+
+	ret = poll(&pfd, 1, timeout);
+	return ret;
+}
+
+static int do_rx(int fd)
+{
+	char rbuf;
+	int ret, num = 0;
+
+	while (1) {
+		ret = recv(fd, &rbuf, 1, MSG_DONTWAIT);
+		if (ret == -1 && errno == EAGAIN)
+			break;
+		if (ret < 0)
+			return -1;
+		if (!ASSERT_EQ(rbuf, TEST_PACKET_PATTERN, "check pkt pattern"))
+			return -1;
+		num++;
+	}
+
+	return num;
+}
+
+static int run_test(const struct test_configuration *test,
+		    int source_port_index)
+{
+	int fdt = -1, fdr = -1, len, tx = 0, rx = 0, err;
+	unsigned long tstop, tcur;
+
+	fdr = setup_rx(test);
+	fdt = setup_tx(test);
+	if (!ASSERT_OK_FD(fdr, "setup rx") || !ASSERT_OK_FD(fdt, "setup tx")) {
+		err = -1;
+		goto out_close_sockets;
+	}
+
+	len = build_packet(test,
+			   (uint16_t)test->source_ports[source_port_index]);
+	if (!ASSERT_GT(len, 0, "build test packet"))
+		return -1;
+
+	tcur = util_gettime();
+	tstop = tcur;
+
+	while (tx < TEST_PACKETS_COUNT) {
+		if (!ASSERT_OK(do_tx(fdt, buf, len), "do_tx"))
+			break;
+		tx++;
+		err = do_rx(fdr);
+		if (!ASSERT_GE(err, 0, "do_rx"))
+			break;
+		rx += err;
+	}
+
+	/* read straggler packets, if any */
+	if (rx < tx) {
+		tstop = util_gettime() + 100;
+		while (rx < tx) {
+			tcur = util_gettime();
+			if (tcur >= tstop)
+				break;
+
+			err = do_poll(fdr, POLLIN, tstop - tcur);
+			if (err < 0)
+				break;
+			err = do_rx(fdr);
+			if (err >= 0)
+				rx += err;
+		}
+	}
+
+out_close_sockets:
+	close(fdt);
+	close(fdr);
+	return rx;
+}
+
+static int attach_and_configure_program(struct bpf_flow *skel)
+{
+	struct bpf_map *prog_array = skel->maps.jmp_table;
+	int main_prog_fd, sub_prog_fd, map_fd, i, err;
+	struct bpf_program *prog;
+	char prog_name[32];
+
+	main_prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (main_prog_fd < 0)
+		return main_prog_fd;
+
+	err = bpf_prog_attach(main_prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (err)
+		return err;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (map_fd < 0)
+		return map_fd;
+
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i);
+
+		prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+		if (!prog)
+			return -1;
+
+		sub_prog_fd = bpf_program__fd(prog);
+		if (sub_prog_fd < 0)
+			return -1;
+
+		err = bpf_map_update_elem(map_fd, &i, &sub_prog_fd, BPF_ANY);
+		if (err)
+			return -1;
+	}
+
+	return main_prog_fd;
+}
+
+static void detach_program(struct bpf_flow *skel, int prog_fd)
+{
+	bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+}
+
+static int set_port_drop(int pf, bool multi_port)
+{
+	char dst_port[16];
+
+	snprintf(dst_port, sizeof(dst_port), "%d", CFG_PORT_INNER);
+
+	SYS(fail, "tc qdisc add dev lo ingress");
+	SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s %s %s",
+	    "dev lo",
+	    "parent FFFF:",
+	    "protocol", pf == PF_INET6 ? "ipv6" : "ip",
+	    "pref 1337",
+	    "flower",
+	    "ip_proto udp",
+	    "src_port", multi_port ? "8-10" : "9",
+	    "dst_port", dst_port,
+	    "action drop");
+	return 0;
+
+fail_delete_qdisc:
+	SYS_NOFAIL("tc qdisc del dev lo ingress");
+fail:
+	return 1;
+}
+
+static void remove_filter(void)
+{
+	SYS_NOFAIL("tc filter del dev lo ingress");
+	SYS_NOFAIL("tc qdisc del dev lo ingress");
+}
+
+static int ipv4_setup(void)
+{
+	return set_port_drop(PF_INET, false);
+}
+
+static int ipv6_setup(void)
+{
+	return set_port_drop(PF_INET6, false);
+}
+
+static int port_range_setup(void)
+{
+	return set_port_drop(PF_INET, true);
+}
+
+static int set_addresses(void)
+{
+	SYS(out, "ip -4 addr add  %s dev lo", TEST_IPV4);
+	SYS(out_remove_ipv4, "ip -6 addr add %s dev lo", TEST_IPV6);
+	return 0;
+out_remove_ipv4:
+	SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4);
+out:
+	return -1;
+}
+
+static void unset_addresses(void)
+{
+	SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4);
+	SYS_NOFAIL("ip -6 addr del %s dev lo", TEST_IPV6);
+}
+
+static int ipip_setup(void)
+{
+	if (!ASSERT_OK(set_addresses(), "configure addresses"))
+		return -1;
+	if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter"))
+		goto out_unset_addresses;
+	SYS(out_remove_filter,
+	    "ip link add ipip_test type ipip remote %s local %s dev lo",
+	    TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL);
+	SYS(out_clean_netif, "ip link set ipip_test up");
+	return 0;
+
+out_clean_netif:
+	SYS_NOFAIL("ip link del ipip_test");
+out_remove_filter:
+	remove_filter();
+out_unset_addresses:
+	unset_addresses();
+	return -1;
+}
+
+static void ipip_shutdown(void)
+{
+	SYS_NOFAIL("ip link del ipip_test");
+	remove_filter();
+	unset_addresses();
+}
+
+static int gre_setup(void)
+{
+	if (!ASSERT_OK(set_addresses(), "configure addresses"))
+		return -1;
+	if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter"))
+		goto out_unset_addresses;
+	SYS(out_remove_filter,
+	    "ip link add gre_test type gre remote %s local %s dev lo",
+	    TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL);
+	SYS(out_clean_netif, "ip link set gre_test up");
+	return 0;
+
+out_clean_netif:
+	SYS_NOFAIL("ip link del ipip_test");
+out_remove_filter:
+	remove_filter();
+out_unset_addresses:
+	unset_addresses();
+	return -1;
+}
+
+static void gre_shutdown(void)
+{
+	SYS_NOFAIL("ip link del gre_test");
+	remove_filter();
+	unset_addresses();
+}
+
+static const struct test_configuration tests_input[] = {
+	{
+		.name = "ipv4",
+		.test_setup = ipv4_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT,
+		.in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT
+	},
+	{
+		.name = "ipv4_continue_dissect",
+		.test_setup = ipv4_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_DISSECT_CONTINUE,
+		.in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT },
+	{
+		.name = "ipip",
+		.test_setup = ipip_setup,
+		.test_teardown = ipip_shutdown,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_IPIP,
+		.in_daddr4 = TEST_IN4_DST_ADDR_IPIP,
+		.out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT,
+		.out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT,
+		.cfg_l3_outer = PF_INET,
+		.cfg_encap_proto = IPPROTO_IPIP,
+
+	},
+	{
+		.name = "gre",
+		.test_setup = gre_setup,
+		.test_teardown = gre_shutdown,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_IPIP,
+		.in_daddr4 = TEST_IN4_DST_ADDR_IPIP,
+		.out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT,
+		.out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT,
+		.cfg_l3_outer = PF_INET,
+		.cfg_encap_proto = IPPROTO_GRE,
+	},
+	{
+		.name = "port_range",
+		.test_setup = port_range_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 7, 9, 11 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT,
+		.in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT },
+	{
+		.name = "ipv6",
+		.test_setup = ipv6_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET6,
+		.in_saddr6 = TEST_IN6_SRC_ADDR_DEFAULT,
+		.in_daddr6 = TEST_IN6_DST_ADDR_DEFAULT
+	},
+};
+
+struct test_ctx {
+	struct bpf_flow *skel;
+	struct netns_obj *ns;
+	int prog_fd;
+};
+
+static int test_global_init(struct test_ctx *ctx)
+{
+	int err;
+
+	ctx->skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(ctx->skel, "open and load flow_dissector"))
+		return -1;
+
+	ctx->ns = netns_new("flow_dissector_classification", true);
+	if (!ASSERT_OK_PTR(ctx->ns, "switch ns"))
+		goto out_destroy_skel;
+
+	err = write_sysctl("/proc/sys/net/ipv4/conf/default/rp_filter", "0");
+	err |= write_sysctl("/proc/sys/net/ipv4/conf/all/rp_filter", "0");
+	err |= write_sysctl("/proc/sys/net/ipv4/conf/lo/rp_filter", "0");
+	if (!ASSERT_OK(err, "configure net tunables"))
+		goto out_clean_ns;
+
+	ctx->prog_fd = attach_and_configure_program(ctx->skel);
+	if (!ASSERT_OK_FD(ctx->prog_fd, "attach and configure program"))
+		goto out_clean_ns;
+	return 0;
+out_clean_ns:
+	netns_free(ctx->ns);
+out_destroy_skel:
+	bpf_flow__destroy(ctx->skel);
+	return -1;
+}
+
+static void test_global_shutdown(struct test_ctx *ctx)
+{
+	detach_program(ctx->skel, ctx->prog_fd);
+	netns_free(ctx->ns);
+	bpf_flow__destroy(ctx->skel);
+}
+
+void test_flow_dissector_classification(void)
+{
+	struct test_ctx ctx;
+	const struct test_configuration *test;
+	int i;
+
+	if (test_global_init(&ctx))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(tests_input); i++) {
+		if (!test__start_subtest(tests_input[i].name))
+			continue;
+		test = &tests_input[i];
+		/* All tests are expected to have one rx-ok port first,
+		 * then a non-working rx port, and finally a rx-ok port
+		 */
+		if (test->test_setup &&
+		    !ASSERT_OK(test->test_setup(), "init filter"))
+			continue;
+
+		ASSERT_EQ(run_test(test, 0), TEST_PACKETS_COUNT,
+			  "test first port");
+		ASSERT_EQ(run_test(test, 1), 0, "test second port");
+		ASSERT_EQ(run_test(test, 2), TEST_PACKETS_COUNT,
+			  "test third port");
+		if (test->test_teardown)
+			test->test_teardown();
+	}
+	test_global_shutdown(&ctx);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c
new file mode 100644
index 000000000000..b7b77a6b2979
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+
+#include "free_timer.skel.h"
+
+struct run_ctx {
+	struct bpf_program *start_prog;
+	struct bpf_program *overwrite_prog;
+	pthread_barrier_t notify;
+	int loop;
+	bool start;
+	bool stop;
+};
+
+static void start_threads(struct run_ctx *ctx)
+{
+	ctx->start = true;
+}
+
+static void stop_threads(struct run_ctx *ctx)
+{
+	ctx->stop = true;
+	/* Guarantee the order between ->stop and ->start */
+	__atomic_store_n(&ctx->start, true, __ATOMIC_RELEASE);
+}
+
+static int wait_for_start(struct run_ctx *ctx)
+{
+	while (!__atomic_load_n(&ctx->start, __ATOMIC_ACQUIRE))
+		usleep(10);
+
+	return ctx->stop;
+}
+
+static void *overwrite_timer_fn(void *arg)
+{
+	struct run_ctx *ctx = arg;
+	int loop, fd, err;
+	cpu_set_t cpuset;
+	long ret = 0;
+
+	/* Pin on CPU 0 */
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	/* Is the thread being stopped ? */
+	err = wait_for_start(ctx);
+	if (err)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->overwrite_prog);
+	loop = ctx->loop;
+	while (loop-- > 0) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+		/* Wait for start thread to complete */
+		pthread_barrier_wait(&ctx->notify);
+
+		/* Overwrite timers */
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err)
+			ret |= 1;
+		else if (opts.retval)
+			ret |= 2;
+
+		/* Notify start thread to start timers */
+		pthread_barrier_wait(&ctx->notify);
+	}
+
+	return (void *)ret;
+}
+
+static void *start_timer_fn(void *arg)
+{
+	struct run_ctx *ctx = arg;
+	int loop, fd, err;
+	cpu_set_t cpuset;
+	long ret = 0;
+
+	/* Pin on CPU 1 */
+	CPU_ZERO(&cpuset);
+	CPU_SET(1, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	/* Is the thread being stopped ? */
+	err = wait_for_start(ctx);
+	if (err)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->start_prog);
+	loop = ctx->loop;
+	while (loop-- > 0) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+		/* Run the prog to start timer */
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err)
+			ret |= 4;
+		else if (opts.retval)
+			ret |= 8;
+
+		/* Notify overwrite thread to do overwrite */
+		pthread_barrier_wait(&ctx->notify);
+
+		/* Wait for overwrite thread to complete */
+		pthread_barrier_wait(&ctx->notify);
+	}
+
+	return (void *)ret;
+}
+
+void test_free_timer(void)
+{
+	struct free_timer *skel;
+	struct bpf_program *prog;
+	struct run_ctx ctx;
+	pthread_t tid[2];
+	void *ret;
+	int err;
+
+	skel = free_timer__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	prog = bpf_object__find_program_by_name(skel->obj, "start_timer");
+	if (!ASSERT_OK_PTR(prog, "find start prog"))
+		goto out;
+	ctx.start_prog = prog;
+
+	prog = bpf_object__find_program_by_name(skel->obj, "overwrite_timer");
+	if (!ASSERT_OK_PTR(prog, "find overwrite prog"))
+		goto out;
+	ctx.overwrite_prog = prog;
+
+	pthread_barrier_init(&ctx.notify, NULL, 2);
+	ctx.loop = 10;
+
+	err = pthread_create(&tid[0], NULL, start_timer_fn, &ctx);
+	if (!ASSERT_OK(err, "create start_timer"))
+		goto out;
+
+	err = pthread_create(&tid[1], NULL, overwrite_timer_fn, &ctx);
+	if (!ASSERT_OK(err, "create overwrite_timer")) {
+		stop_threads(&ctx);
+		goto out;
+	}
+
+	start_threads(&ctx);
+
+	ret = NULL;
+	err = pthread_join(tid[0], &ret);
+	ASSERT_EQ(err | (long)ret, 0, "start_timer");
+	ret = NULL;
+	err = pthread_join(tid[1], &ret);
+	ASSERT_EQ(err | (long)ret, 0, "overwrite_timer");
+out:
+	free_timer__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 66ab1cae923e..e19ef509ebf8 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -397,6 +397,31 @@ cleanup:
 	kprobe_multi_session_cookie__destroy(skel);
 }
 
+static void test_unique_match(void)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct kprobe_multi *skel = NULL;
+	struct bpf_link *link = NULL;
+
+	skel = kprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load"))
+		return;
+
+	opts.unique_match = true;
+	skel->bss->pid = getpid();
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+						     "bpf_fentry_test*", &opts);
+	if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_multi_opts"))
+		bpf_link__destroy(link);
+
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+						     "bpf_fentry_test8*", &opts);
+	if (ASSERT_OK_PTR(link, "bpf_program__attach_kprobe_multi_opts"))
+		bpf_link__destroy(link);
+
+	kprobe_multi__destroy(skel);
+}
+
 static size_t symbol_hash(long key, void *ctx __maybe_unused)
 {
 	return str_hash((const char *) key);
@@ -765,5 +790,7 @@ void test_kprobe_multi_test(void)
 		test_session_skel_api();
 	if (test__start_subtest("session_cookie"))
 		test_session_cookie_skel_api();
+	if (test__start_subtest("unique_match"))
+		test_unique_match();
 	RUN_TESTS(kprobe_multi_verifier);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c
index 70d90c43537c..ed8857ae914a 100644
--- a/tools/testing/selftests/bpf/prog_tests/missed.c
+++ b/tools/testing/selftests/bpf/prog_tests/missed.c
@@ -85,6 +85,7 @@ static void test_missed_kprobe_recursion(void)
 	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses");
 	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses");
 	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test5)), 1, "test5_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test6)), 1, "test6_recursion_misses");
 
 cleanup:
 	missed_kprobe_recursion__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
new file mode 100644
index 000000000000..1bdfb79ef009
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
@@ -0,0 +1,394 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SOCKET_HELPERS__
+#define __SOCKET_HELPERS__
+
+#include <linux/vm_sockets.h>
+
+/* include/linux/net.h */
+#define SOCK_TYPE_MASK 0xf
+
+#define IO_TIMEOUT_SEC 30
+#define MAX_STRERR_LEN 256
+
+/* workaround for older vm_sockets.h */
+#ifndef VMADDR_CID_LOCAL
+#define VMADDR_CID_LOCAL 1
+#endif
+
+/* include/linux/cleanup.h */
+#define __get_and_null(p, nullvalue)                                           \
+	({                                                                     \
+		__auto_type __ptr = &(p);                                      \
+		__auto_type __val = *__ptr;                                    \
+		*__ptr = nullvalue;                                            \
+		__val;                                                         \
+	})
+
+#define take_fd(fd) __get_and_null(fd, -EBADF)
+
+/* Wrappers that fail the test on error and report it. */
+
+#define _FAIL(errnum, fmt...)                                                  \
+	({                                                                     \
+		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
+		CHECK_FAIL(true);                                              \
+	})
+#define FAIL(fmt...) _FAIL(0, fmt)
+#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
+#define FAIL_LIBBPF(err, msg)                                                  \
+	({                                                                     \
+		char __buf[MAX_STRERR_LEN];                                    \
+		libbpf_strerror((err), __buf, sizeof(__buf));                  \
+		FAIL("%s: %s", (msg), __buf);                                  \
+	})
+
+
+#define xaccept_nonblock(fd, addr, len)                                        \
+	({                                                                     \
+		int __ret =                                                    \
+			accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC);   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("accept");                                  \
+		__ret;                                                         \
+	})
+
+#define xbind(fd, addr, len)                                                   \
+	({                                                                     \
+		int __ret = bind((fd), (addr), (len));                         \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("bind");                                    \
+		__ret;                                                         \
+	})
+
+#define xclose(fd)                                                             \
+	({                                                                     \
+		int __ret = close((fd));                                       \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("close");                                   \
+		__ret;                                                         \
+	})
+
+#define xconnect(fd, addr, len)                                                \
+	({                                                                     \
+		int __ret = connect((fd), (addr), (len));                      \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("connect");                                 \
+		__ret;                                                         \
+	})
+
+#define xgetsockname(fd, addr, len)                                            \
+	({                                                                     \
+		int __ret = getsockname((fd), (addr), (len));                  \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("getsockname");                             \
+		__ret;                                                         \
+	})
+
+#define xgetsockopt(fd, level, name, val, len)                                 \
+	({                                                                     \
+		int __ret = getsockopt((fd), (level), (name), (val), (len));   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("getsockopt(" #name ")");                   \
+		__ret;                                                         \
+	})
+
+#define xlisten(fd, backlog)                                                   \
+	({                                                                     \
+		int __ret = listen((fd), (backlog));                           \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("listen");                                  \
+		__ret;                                                         \
+	})
+
+#define xsetsockopt(fd, level, name, val, len)                                 \
+	({                                                                     \
+		int __ret = setsockopt((fd), (level), (name), (val), (len));   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("setsockopt(" #name ")");                   \
+		__ret;                                                         \
+	})
+
+#define xsend(fd, buf, len, flags)                                             \
+	({                                                                     \
+		ssize_t __ret = send((fd), (buf), (len), (flags));             \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("send");                                    \
+		__ret;                                                         \
+	})
+
+#define xrecv_nonblock(fd, buf, len, flags)                                    \
+	({                                                                     \
+		ssize_t __ret = recv_timeout((fd), (buf), (len), (flags),      \
+					     IO_TIMEOUT_SEC);                  \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("recv");                                    \
+		__ret;                                                         \
+	})
+
+#define xsocket(family, sotype, flags)                                         \
+	({                                                                     \
+		int __ret = socket(family, sotype, flags);                     \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("socket");                                  \
+		__ret;                                                         \
+	})
+
+static inline void close_fd(int *fd)
+{
+	if (*fd >= 0)
+		xclose(*fd);
+}
+
+#define __close_fd __attribute__((cleanup(close_fd)))
+
+static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
+{
+	return (struct sockaddr *)ss;
+}
+
+static inline void init_addr_loopback4(struct sockaddr_storage *ss,
+				       socklen_t *len)
+{
+	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
+
+	addr4->sin_family = AF_INET;
+	addr4->sin_port = 0;
+	addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+	*len = sizeof(*addr4);
+}
+
+static inline void init_addr_loopback6(struct sockaddr_storage *ss,
+				       socklen_t *len)
+{
+	struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
+
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = 0;
+	addr6->sin6_addr = in6addr_loopback;
+	*len = sizeof(*addr6);
+}
+
+static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
+					    socklen_t *len)
+{
+	struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss));
+
+	addr->svm_family = AF_VSOCK;
+	addr->svm_port = VMADDR_PORT_ANY;
+	addr->svm_cid = VMADDR_CID_LOCAL;
+	*len = sizeof(*addr);
+}
+
+static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
+				      socklen_t *len)
+{
+	switch (family) {
+	case AF_INET:
+		init_addr_loopback4(ss, len);
+		return;
+	case AF_INET6:
+		init_addr_loopback6(ss, len);
+		return;
+	case AF_VSOCK:
+		init_addr_loopback_vsock(ss, len);
+		return;
+	default:
+		FAIL("unsupported address family %d", family);
+	}
+}
+
+static inline int enable_reuseport(int s, int progfd)
+{
+	int err, one = 1;
+
+	err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+	if (err)
+		return -1;
+	err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
+			  sizeof(progfd));
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = 0;
+	int err, s;
+
+	init_addr_loopback(family, &addr, &len);
+
+	s = xsocket(family, sotype, 0);
+	if (s == -1)
+		return -1;
+
+	if (progfd >= 0)
+		enable_reuseport(s, progfd);
+
+	err = xbind(s, sockaddr(&addr), len);
+	if (err)
+		goto close;
+
+	if (sotype & SOCK_DGRAM)
+		return s;
+
+	err = xlisten(s, SOMAXCONN);
+	if (err)
+		goto close;
+
+	return s;
+close:
+	xclose(s);
+	return -1;
+}
+
+static inline int socket_loopback(int family, int sotype)
+{
+	return socket_loopback_reuseport(family, sotype, -1);
+}
+
+static inline int poll_connect(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set wfds;
+	int r, eval;
+	socklen_t esize = sizeof(eval);
+
+	FD_ZERO(&wfds);
+	FD_SET(fd, &wfds);
+
+	r = select(fd + 1, NULL, &wfds, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+	if (r != 1)
+		return -1;
+
+	if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
+		return -1;
+	if (eval != 0) {
+		errno = eval;
+		return -1;
+	}
+
+	return 0;
+}
+
+static inline int poll_read(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set rfds;
+	int r;
+
+	FD_ZERO(&rfds);
+	FD_SET(fd, &rfds);
+
+	r = select(fd + 1, &rfds, NULL, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+
+	return r == 1 ? 0 : -1;
+}
+
+static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
+				 unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return accept(fd, addr, len);
+}
+
+static inline int recv_timeout(int fd, void *buf, size_t len, int flags,
+			       unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return recv(fd, buf, len, flags);
+}
+
+
+static inline int create_pair(int family, int sotype, int *p0, int *p1)
+{
+	__close_fd int s, c = -1, p = -1;
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	int err;
+
+	s = socket_loopback(family, sotype);
+	if (s < 0)
+		return s;
+
+	err = xgetsockname(s, sockaddr(&addr), &len);
+	if (err)
+		return err;
+
+	c = xsocket(family, sotype, 0);
+	if (c < 0)
+		return c;
+
+	err = connect(c, sockaddr(&addr), len);
+	if (err) {
+		if (errno != EINPROGRESS) {
+			FAIL_ERRNO("connect");
+			return err;
+		}
+
+		err = poll_connect(c, IO_TIMEOUT_SEC);
+		if (err) {
+			FAIL_ERRNO("poll_connect");
+			return err;
+		}
+	}
+
+	switch (sotype & SOCK_TYPE_MASK) {
+	case SOCK_DGRAM:
+		err = xgetsockname(c, sockaddr(&addr), &len);
+		if (err)
+			return err;
+
+		err = xconnect(s, sockaddr(&addr), len);
+		if (err)
+			return err;
+
+		*p0 = take_fd(s);
+		break;
+	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
+		p = xaccept_nonblock(s, NULL, NULL);
+		if (p < 0)
+			return p;
+
+		*p0 = take_fd(p);
+		break;
+	default:
+		FAIL("Unsupported socket type %#x", sotype);
+		return -EOPNOTSUPP;
+	}
+
+	*p1 = take_fd(c);
+	return 0;
+}
+
+static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
+				      int *p0, int *p1)
+{
+	int err;
+
+	err = create_pair(family, sotype, c0, p0);
+	if (err)
+		return err;
+
+	err = create_pair(family, sotype, c1, p1);
+	if (err) {
+		close(*c0);
+		close(*p0);
+	}
+
+	return err;
+}
+
+#endif // __SOCKET_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 248754296d97..1e3e4392dcca 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -12,6 +12,7 @@
 #include "test_sockmap_progs_query.skel.h"
 #include "test_sockmap_pass_prog.skel.h"
 #include "test_sockmap_drop_prog.skel.h"
+#include "test_sockmap_change_tail.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
 #include "sockmap_helpers.h"
@@ -110,31 +111,35 @@ out:
 
 static void test_sockmap_vsock_delete_on_close(void)
 {
-	int err, c, p, map;
-	const int zero = 0;
-
-	err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p);
-	if (!ASSERT_OK(err, "create_pair(AF_VSOCK)"))
-		return;
+	int map, c, p, err, zero = 0;
 
 	map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int),
 			     sizeof(int), 1, NULL);
-	if (!ASSERT_GE(map, 0, "bpf_map_create")) {
-		close(c);
-		goto out;
-	}
+	if (!ASSERT_OK_FD(map, "bpf_map_create"))
+		return;
 
-	err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST);
-	close(c);
-	if (!ASSERT_OK(err, "bpf_map_update"))
-		goto out;
+	err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p);
+	if (!ASSERT_OK(err, "create_pair"))
+		goto close_map;
 
-	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (xbpf_map_update_elem(map, &zero, &c, BPF_NOEXIST))
+		goto close_socks;
+
+	xclose(c);
+	xclose(p);
+
+	err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p);
+	if (!ASSERT_OK(err, "create_pair"))
+		goto close_map;
+
+	err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST);
 	ASSERT_OK(err, "after close(), bpf_map_update");
 
-out:
-	close(p);
-	close(map);
+close_socks:
+	xclose(c);
+	xclose(p);
+close_map:
+	xclose(map);
 }
 
 static void test_skmsg_helpers(enum bpf_map_type map_type)
@@ -521,8 +526,8 @@ static void test_sockmap_skb_verdict_shutdown(void)
 	if (!ASSERT_EQ(err, 1, "epoll_wait(fd)"))
 		goto out_close;
 
-	n = recv(c1, &b, 1, SOCK_NONBLOCK);
-	ASSERT_EQ(n, 0, "recv_timeout(fin)");
+	n = recv(c1, &b, 1, MSG_DONTWAIT);
+	ASSERT_EQ(n, 0, "recv(fin)");
 out_close:
 	close(c1);
 	close(p1);
@@ -530,57 +535,6 @@ out:
 	test_sockmap_pass_prog__destroy(skel);
 }
 
-static void test_sockmap_stream_pass(void)
-{
-	int zero = 0, sent, recvd;
-	int verdict, parser;
-	int err, map;
-	int c = -1, p = -1;
-	struct test_sockmap_pass_prog *pass = NULL;
-	char snd[256] = "0123456789";
-	char rcv[256] = "0";
-
-	pass = test_sockmap_pass_prog__open_and_load();
-	verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
-	parser = bpf_program__fd(pass->progs.prog_skb_parser);
-	map = bpf_map__fd(pass->maps.sock_map_rx);
-
-	err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0);
-	if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
-		goto out;
-
-	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
-	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
-		goto out;
-
-	err = create_pair(AF_INET, SOCK_STREAM, &c, &p);
-	if (err)
-		goto out;
-
-	/* sk_data_ready of 'p' will be replaced by strparser handler */
-	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
-	if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
-		goto out_close;
-
-	/*
-	 * as 'prog_skb_parser' return the original skb len and
-	 * 'prog_skb_verdict' return SK_PASS, the kernel will just
-	 * pass it through to original socket 'p'
-	 */
-	sent = xsend(c, snd, sizeof(snd), 0);
-	ASSERT_EQ(sent, sizeof(snd), "xsend(c)");
-
-	recvd = recv_timeout(p, rcv, sizeof(rcv), SOCK_NONBLOCK,
-			     IO_TIMEOUT_SEC);
-	ASSERT_EQ(recvd, sizeof(rcv), "recv_timeout(p)");
-
-out_close:
-	close(c);
-	close(p);
-
-out:
-	test_sockmap_pass_prog__destroy(pass);
-}
 
 static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 {
@@ -627,7 +581,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 	ASSERT_EQ(avail, expected, "ioctl(FIONREAD)");
 	/* On DROP test there will be no data to read */
 	if (pass_prog) {
-		recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC);
+		recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC);
 		ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)");
 	}
 
@@ -643,6 +597,54 @@ out:
 		test_sockmap_drop_prog__destroy(drop);
 }
 
+static void test_sockmap_skb_verdict_change_tail(void)
+{
+	struct test_sockmap_change_tail *skel;
+	int err, map, verdict;
+	int c1, p1, sent, recvd;
+	int zero = 0;
+	char buf[2];
+
+	skel = test_sockmap_change_tail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+	verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+	err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
+	if (!ASSERT_OK(err, "create_pair()"))
+		goto out;
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
+		goto out_close;
+	sent = xsend(p1, "Tr", 2, 0);
+	ASSERT_EQ(sent, 2, "xsend(p1)");
+	recvd = recv(c1, buf, 2, 0);
+	ASSERT_EQ(recvd, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	sent = xsend(p1, "G", 1, 0);
+	ASSERT_EQ(sent, 1, "xsend(p1)");
+	recvd = recv(c1, buf, 2, 0);
+	ASSERT_EQ(recvd, 2, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	sent = xsend(p1, "E", 1, 0);
+	ASSERT_EQ(sent, 1, "xsend(p1)");
+	recvd = recv(c1, buf, 1, 0);
+	ASSERT_EQ(recvd, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+out_close:
+	close(c1);
+	close(p1);
+out:
+	test_sockmap_change_tail__destroy(skel);
+}
+
 static void test_sockmap_skb_verdict_peek_helper(int map)
 {
 	int err, c1, p1, zero = 0, sent, recvd, avail;
@@ -1012,6 +1014,34 @@ destroy:
 	test_sockmap_pass_prog__destroy(skel);
 }
 
+static void test_sockmap_vsock_unconnected(void)
+{
+	struct sockaddr_storage addr;
+	int map, s, zero = 0;
+	socklen_t alen;
+
+	map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int),
+			     sizeof(int), 1, NULL);
+	if (!ASSERT_OK_FD(map, "bpf_map_create"))
+		return;
+
+	s = xsocket(AF_VSOCK, SOCK_STREAM, 0);
+	if (s < 0)
+		goto close_map;
+
+	/* Fail connect(), but trigger transport assignment. */
+	init_addr_loopback(AF_VSOCK, &addr, &alen);
+	if (!ASSERT_ERR(connect(s, sockaddr(&addr), alen), "connect"))
+		goto close_sock;
+
+	ASSERT_ERR(bpf_map_update_elem(map, &zero, &s, BPF_ANY), "map_update");
+
+close_sock:
+	xclose(s);
+close_map:
+	xclose(map);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -1052,12 +1082,12 @@ void test_sockmap_basic(void)
 		test_sockmap_progs_query(BPF_SK_SKB_VERDICT);
 	if (test__start_subtest("sockmap skb_verdict shutdown"))
 		test_sockmap_skb_verdict_shutdown();
-	if (test__start_subtest("sockmap stream parser and verdict pass"))
-		test_sockmap_stream_pass();
 	if (test__start_subtest("sockmap skb_verdict fionread"))
 		test_sockmap_skb_verdict_fionread(true);
 	if (test__start_subtest("sockmap skb_verdict fionread on drop"))
 		test_sockmap_skb_verdict_fionread(false);
+	if (test__start_subtest("sockmap skb_verdict change tail"))
+		test_sockmap_skb_verdict_change_tail();
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
 		test_sockmap_skb_verdict_peek();
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek with link"))
@@ -1076,4 +1106,6 @@ void test_sockmap_basic(void)
 		test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH);
 	if (test__start_subtest("sockmap skb_verdict vsock poll"))
 		test_sockmap_skb_verdict_vsock_poll();
+	if (test__start_subtest("sockmap vsock unconnected"))
+		test_sockmap_vsock_unconnected();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index 38e35c72bdaa..3e5571dd578d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -1,139 +1,12 @@
 #ifndef __SOCKMAP_HELPERS__
 #define __SOCKMAP_HELPERS__
 
-#include <linux/vm_sockets.h>
+#include "socket_helpers.h"
 
-/* include/linux/net.h */
-#define SOCK_TYPE_MASK 0xf
-
-#define IO_TIMEOUT_SEC 30
-#define MAX_STRERR_LEN 256
 #define MAX_TEST_NAME 80
 
-/* workaround for older vm_sockets.h */
-#ifndef VMADDR_CID_LOCAL
-#define VMADDR_CID_LOCAL 1
-#endif
-
 #define __always_unused	__attribute__((__unused__))
 
-/* include/linux/cleanup.h */
-#define __get_and_null(p, nullvalue)                                           \
-	({                                                                     \
-		__auto_type __ptr = &(p);                                      \
-		__auto_type __val = *__ptr;                                    \
-		*__ptr = nullvalue;                                            \
-		__val;                                                         \
-	})
-
-#define take_fd(fd) __get_and_null(fd, -EBADF)
-
-#define _FAIL(errnum, fmt...)                                                  \
-	({                                                                     \
-		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
-		CHECK_FAIL(true);                                              \
-	})
-#define FAIL(fmt...) _FAIL(0, fmt)
-#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
-#define FAIL_LIBBPF(err, msg)                                                  \
-	({                                                                     \
-		char __buf[MAX_STRERR_LEN];                                    \
-		libbpf_strerror((err), __buf, sizeof(__buf));                  \
-		FAIL("%s: %s", (msg), __buf);                                  \
-	})
-
-/* Wrappers that fail the test on error and report it. */
-
-#define xaccept_nonblock(fd, addr, len)                                        \
-	({                                                                     \
-		int __ret =                                                    \
-			accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC);   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("accept");                                  \
-		__ret;                                                         \
-	})
-
-#define xbind(fd, addr, len)                                                   \
-	({                                                                     \
-		int __ret = bind((fd), (addr), (len));                         \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("bind");                                    \
-		__ret;                                                         \
-	})
-
-#define xclose(fd)                                                             \
-	({                                                                     \
-		int __ret = close((fd));                                       \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("close");                                   \
-		__ret;                                                         \
-	})
-
-#define xconnect(fd, addr, len)                                                \
-	({                                                                     \
-		int __ret = connect((fd), (addr), (len));                      \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("connect");                                 \
-		__ret;                                                         \
-	})
-
-#define xgetsockname(fd, addr, len)                                            \
-	({                                                                     \
-		int __ret = getsockname((fd), (addr), (len));                  \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("getsockname");                             \
-		__ret;                                                         \
-	})
-
-#define xgetsockopt(fd, level, name, val, len)                                 \
-	({                                                                     \
-		int __ret = getsockopt((fd), (level), (name), (val), (len));   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("getsockopt(" #name ")");                   \
-		__ret;                                                         \
-	})
-
-#define xlisten(fd, backlog)                                                   \
-	({                                                                     \
-		int __ret = listen((fd), (backlog));                           \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("listen");                                  \
-		__ret;                                                         \
-	})
-
-#define xsetsockopt(fd, level, name, val, len)                                 \
-	({                                                                     \
-		int __ret = setsockopt((fd), (level), (name), (val), (len));   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("setsockopt(" #name ")");                   \
-		__ret;                                                         \
-	})
-
-#define xsend(fd, buf, len, flags)                                             \
-	({                                                                     \
-		ssize_t __ret = send((fd), (buf), (len), (flags));             \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("send");                                    \
-		__ret;                                                         \
-	})
-
-#define xrecv_nonblock(fd, buf, len, flags)                                    \
-	({                                                                     \
-		ssize_t __ret = recv_timeout((fd), (buf), (len), (flags),      \
-					     IO_TIMEOUT_SEC);                  \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("recv");                                    \
-		__ret;                                                         \
-	})
-
-#define xsocket(family, sotype, flags)                                         \
-	({                                                                     \
-		int __ret = socket(family, sotype, flags);                     \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("socket");                                  \
-		__ret;                                                         \
-	})
-
 #define xbpf_map_delete_elem(fd, key)                                          \
 	({                                                                     \
 		int __ret = bpf_map_delete_elem((fd), (key));                  \
@@ -193,130 +66,6 @@
 		__ret;                                                         \
 	})
 
-static inline void close_fd(int *fd)
-{
-	if (*fd >= 0)
-		xclose(*fd);
-}
-
-#define __close_fd __attribute__((cleanup(close_fd)))
-
-static inline int poll_connect(int fd, unsigned int timeout_sec)
-{
-	struct timeval timeout = { .tv_sec = timeout_sec };
-	fd_set wfds;
-	int r, eval;
-	socklen_t esize = sizeof(eval);
-
-	FD_ZERO(&wfds);
-	FD_SET(fd, &wfds);
-
-	r = select(fd + 1, NULL, &wfds, NULL, &timeout);
-	if (r == 0)
-		errno = ETIME;
-	if (r != 1)
-		return -1;
-
-	if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
-		return -1;
-	if (eval != 0) {
-		errno = eval;
-		return -1;
-	}
-
-	return 0;
-}
-
-static inline int poll_read(int fd, unsigned int timeout_sec)
-{
-	struct timeval timeout = { .tv_sec = timeout_sec };
-	fd_set rfds;
-	int r;
-
-	FD_ZERO(&rfds);
-	FD_SET(fd, &rfds);
-
-	r = select(fd + 1, &rfds, NULL, NULL, &timeout);
-	if (r == 0)
-		errno = ETIME;
-
-	return r == 1 ? 0 : -1;
-}
-
-static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
-				 unsigned int timeout_sec)
-{
-	if (poll_read(fd, timeout_sec))
-		return -1;
-
-	return accept(fd, addr, len);
-}
-
-static inline int recv_timeout(int fd, void *buf, size_t len, int flags,
-			       unsigned int timeout_sec)
-{
-	if (poll_read(fd, timeout_sec))
-		return -1;
-
-	return recv(fd, buf, len, flags);
-}
-
-static inline void init_addr_loopback4(struct sockaddr_storage *ss,
-				       socklen_t *len)
-{
-	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
-
-	addr4->sin_family = AF_INET;
-	addr4->sin_port = 0;
-	addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-	*len = sizeof(*addr4);
-}
-
-static inline void init_addr_loopback6(struct sockaddr_storage *ss,
-				       socklen_t *len)
-{
-	struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
-
-	addr6->sin6_family = AF_INET6;
-	addr6->sin6_port = 0;
-	addr6->sin6_addr = in6addr_loopback;
-	*len = sizeof(*addr6);
-}
-
-static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
-					    socklen_t *len)
-{
-	struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss));
-
-	addr->svm_family = AF_VSOCK;
-	addr->svm_port = VMADDR_PORT_ANY;
-	addr->svm_cid = VMADDR_CID_LOCAL;
-	*len = sizeof(*addr);
-}
-
-static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
-				      socklen_t *len)
-{
-	switch (family) {
-	case AF_INET:
-		init_addr_loopback4(ss, len);
-		return;
-	case AF_INET6:
-		init_addr_loopback6(ss, len);
-		return;
-	case AF_VSOCK:
-		init_addr_loopback_vsock(ss, len);
-		return;
-	default:
-		FAIL("unsupported address family %d", family);
-	}
-}
-
-static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
-{
-	return (struct sockaddr *)ss;
-}
-
 static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
 {
 	u64 value;
@@ -334,136 +83,4 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
 	return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
 }
 
-static inline int enable_reuseport(int s, int progfd)
-{
-	int err, one = 1;
-
-	err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
-	if (err)
-		return -1;
-	err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
-			  sizeof(progfd));
-	if (err)
-		return -1;
-
-	return 0;
-}
-
-static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
-{
-	struct sockaddr_storage addr;
-	socklen_t len = 0;
-	int err, s;
-
-	init_addr_loopback(family, &addr, &len);
-
-	s = xsocket(family, sotype, 0);
-	if (s == -1)
-		return -1;
-
-	if (progfd >= 0)
-		enable_reuseport(s, progfd);
-
-	err = xbind(s, sockaddr(&addr), len);
-	if (err)
-		goto close;
-
-	if (sotype & SOCK_DGRAM)
-		return s;
-
-	err = xlisten(s, SOMAXCONN);
-	if (err)
-		goto close;
-
-	return s;
-close:
-	xclose(s);
-	return -1;
-}
-
-static inline int socket_loopback(int family, int sotype)
-{
-	return socket_loopback_reuseport(family, sotype, -1);
-}
-
-static inline int create_pair(int family, int sotype, int *p0, int *p1)
-{
-	__close_fd int s, c = -1, p = -1;
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
-	int err;
-
-	s = socket_loopback(family, sotype);
-	if (s < 0)
-		return s;
-
-	err = xgetsockname(s, sockaddr(&addr), &len);
-	if (err)
-		return err;
-
-	c = xsocket(family, sotype, 0);
-	if (c < 0)
-		return c;
-
-	err = connect(c, sockaddr(&addr), len);
-	if (err) {
-		if (errno != EINPROGRESS) {
-			FAIL_ERRNO("connect");
-			return err;
-		}
-
-		err = poll_connect(c, IO_TIMEOUT_SEC);
-		if (err) {
-			FAIL_ERRNO("poll_connect");
-			return err;
-		}
-	}
-
-	switch (sotype & SOCK_TYPE_MASK) {
-	case SOCK_DGRAM:
-		err = xgetsockname(c, sockaddr(&addr), &len);
-		if (err)
-			return err;
-
-		err = xconnect(s, sockaddr(&addr), len);
-		if (err)
-			return err;
-
-		*p0 = take_fd(s);
-		break;
-	case SOCK_STREAM:
-	case SOCK_SEQPACKET:
-		p = xaccept_nonblock(s, NULL, NULL);
-		if (p < 0)
-			return p;
-
-		*p0 = take_fd(p);
-		break;
-	default:
-		FAIL("Unsupported socket type %#x", sotype);
-		return -EOPNOTSUPP;
-	}
-
-	*p1 = take_fd(c);
-	return 0;
-}
-
-static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
-				      int *p0, int *p1)
-{
-	int err;
-
-	err = create_pair(family, sotype, c0, p0);
-	if (err)
-		return err;
-
-	err = create_pair(family, sotype, c1, p1);
-	if (err) {
-		close(*c0);
-		close(*p0);
-	}
-
-	return err;
-}
-
 #endif // __SOCKMAP_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
new file mode 100644
index 000000000000..621b3b71888e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <netinet/tcp.h>
+#include <test_progs.h>
+#include "sockmap_helpers.h"
+#include "test_skmsg_load_helpers.skel.h"
+#include "test_sockmap_strp.skel.h"
+
+#define STRP_PKT_HEAD_LEN 4
+#define STRP_PKT_BODY_LEN 6
+#define STRP_PKT_FULL_LEN (STRP_PKT_HEAD_LEN + STRP_PKT_BODY_LEN)
+
+static const char packet[STRP_PKT_FULL_LEN] = "head+body\0";
+static const int test_packet_num = 100;
+
+/* Current implementation of tcp_bpf_recvmsg_parser() invokes data_ready
+ * with sk held if an skb exists in sk_receive_queue. Then for the
+ * data_ready implementation of strparser, it will delay the read
+ * operation if sk is held and EAGAIN is returned.
+ */
+static int sockmap_strp_consume_pre_data(int p)
+{
+	int recvd;
+	bool retried = false;
+	char rcv[10];
+
+retry:
+	errno = 0;
+	recvd = recv_timeout(p, rcv, sizeof(rcv), 0, 1);
+	if (recvd < 0 && errno == EAGAIN && retried == false) {
+		/* On the first call, EAGAIN will certainly be returned.
+		 * A 1-second wait is enough for the workqueue to finish.
+		 */
+		sleep(1);
+		retried = true;
+		goto retry;
+	}
+
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv error or truncated data") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+				"data mismatch"))
+		return -1;
+	return 0;
+}
+
+static struct test_sockmap_strp *sockmap_strp_init(int *out_map, bool pass,
+						   bool need_parser)
+{
+	struct test_sockmap_strp *strp = NULL;
+	int verdict, parser;
+	int err;
+
+	strp = test_sockmap_strp__open_and_load();
+	*out_map = bpf_map__fd(strp->maps.sock_map);
+
+	if (need_parser)
+		parser = bpf_program__fd(strp->progs.prog_skb_parser_partial);
+	else
+		parser = bpf_program__fd(strp->progs.prog_skb_parser);
+
+	if (pass)
+		verdict = bpf_program__fd(strp->progs.prog_skb_verdict_pass);
+	else
+		verdict = bpf_program__fd(strp->progs.prog_skb_verdict);
+
+	err = bpf_prog_attach(parser, *out_map, BPF_SK_SKB_STREAM_PARSER, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
+		goto err;
+
+	err = bpf_prog_attach(verdict, *out_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
+		goto err;
+
+	return strp;
+err:
+	test_sockmap_strp__destroy(strp);
+	return NULL;
+}
+
+/* Dispatch packets to different socket by packet size:
+ *
+ *                      ------  ------
+ *                     | pkt4 || pkt1 |... > remote socket
+ *  ------ ------     / ------  ------
+ * | pkt8 | pkt7 |...
+ *  ------ ------     \ ------  ------
+ *                     | pkt3 || pkt2 |... > local socket
+ *                      ------  ------
+ */
+static void test_sockmap_strp_dispatch_pkt(int family, int sotype)
+{
+	int i, j, zero = 0, one = 1, recvd;
+	int err, map;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	struct test_sockmap_strp *strp = NULL;
+	int test_cnt = 6;
+	char rcv[10];
+	struct {
+		char	data[7];
+		int	data_len;
+		int	send_cnt;
+		int	*receiver;
+	} send_dir[2] = {
+		/* data expected to deliver to local */
+		{"llllll", 6, 0, &p0},
+		/* data expected to deliver to remote */
+		{"rrrrr",  5, 0, &c1}
+	};
+
+	strp = sockmap_strp_init(&map, false, false);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto out_close;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+		goto out_close;
+
+	err = setsockopt(c1, IPPROTO_TCP, TCP_NODELAY, &zero, sizeof(zero));
+	if (!ASSERT_OK(err, "setsockopt(TCP_NODELAY)"))
+		goto out_close;
+
+	/* deliver data with data size greater than 5 to local */
+	strp->data->verdict_max_size = 5;
+
+	for (i = 0; i < test_cnt; i++) {
+		int d = i % 2;
+
+		xsend(c0, send_dir[d].data, send_dir[d].data_len, 0);
+		send_dir[d].send_cnt++;
+	}
+
+	for (i = 0; i < 2; i++) {
+		for (j = 0; j < send_dir[i].send_cnt; j++) {
+			int expected = send_dir[i].data_len;
+
+			recvd = recv_timeout(*send_dir[i].receiver, rcv,
+					     expected, MSG_DONTWAIT,
+					     IO_TIMEOUT_SEC);
+			if (!ASSERT_EQ(recvd, expected, "recv_timeout()"))
+				goto out_close;
+			if (!ASSERT_OK(memcmp(send_dir[i].data, rcv, recvd),
+				       "data mismatch"))
+				goto out_close;
+		}
+	}
+out_close:
+	close(c0);
+	close(c1);
+	close(p0);
+	close(p1);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* We have multiple packets in one skb
+ * ------------ ------------ ------------
+ * |  packet1  |   packet2  |  ...
+ * ------------ ------------ ------------
+ */
+static void test_sockmap_strp_multiple_pkt(int family, int sotype)
+{
+	int i, zero = 0;
+	int sent, recvd, total;
+	int err, map;
+	int c = -1, p = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char *snd = NULL, *rcv = NULL;
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+		goto out_close;
+
+	/* construct multiple packets in one buffer */
+	total = test_packet_num * STRP_PKT_FULL_LEN;
+	snd = malloc(total);
+	rcv = malloc(total + 1);
+	if (!ASSERT_TRUE(snd, "malloc(snd)") ||
+	    !ASSERT_TRUE(rcv, "malloc(rcv)"))
+		goto out_close;
+
+	for (i = 0; i < test_packet_num; i++) {
+		memcpy(snd + i * STRP_PKT_FULL_LEN,
+		       packet, STRP_PKT_FULL_LEN);
+	}
+
+	sent = xsend(c, snd, total, 0);
+	if (!ASSERT_EQ(sent, total, "xsend(c)"))
+		goto out_close;
+
+	/* try to recv one more byte to avoid truncation check */
+	recvd = recv_timeout(p, rcv, total + 1, MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, total, "recv(rcv)"))
+		goto out_close;
+
+	/* we sent TCP segment with multiple encapsulation
+	 * then check whether packets are handled correctly
+	 */
+	if (!ASSERT_OK(memcmp(snd, rcv, total), "data mismatch"))
+		goto out_close;
+
+out_close:
+	close(c);
+	close(p);
+	if (snd)
+		free(snd);
+	if (rcv)
+		free(rcv);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with partial read */
+static void test_sockmap_strp_partial_read(int family, int sotype)
+{
+	int zero = 0, recvd, off;
+	int err, map;
+	int c = -1, p = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	/* sk_data_ready of 'p' will be replaced by strparser handler */
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+		goto out_close;
+
+	/* 1.1 send partial head, 1 byte header left */
+	off = STRP_PKT_HEAD_LEN - 1;
+	xsend(c, packet, off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(-1, recvd, "partial head sent, expected no data"))
+		goto out_close;
+
+	/* 1.2 send remaining head and body */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+		goto out_close;
+
+	/* 2.1 send partial head, 1 byte header left */
+	off = STRP_PKT_HEAD_LEN - 1;
+	xsend(c, packet, off, 0);
+
+	/* 2.2 send remaining head and partial body, 1 byte body left */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off - 1, 0);
+	off = STRP_PKT_FULL_LEN - 1;
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(-1, recvd, "partial body sent, expected no data"))
+		goto out_close;
+
+	/* 2.3 send remaining body */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+		goto out_close;
+
+out_close:
+	close(c);
+	close(p);
+
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test simple socket read/write with strparser + FIONREAD */
+static void test_sockmap_strp_pass(int family, int sotype, bool fionread)
+{
+	int zero = 0, pkt_size = STRP_PKT_FULL_LEN, sent, recvd, avail;
+	int err, map;
+	int c = -1, p = -1;
+	int test_cnt = 10, i;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	/* inject some data before bpf process, it should be read
+	 * correctly because we check sk_receive_queue in
+	 * tcp_bpf_recvmsg_parser().
+	 */
+	sent = xsend(c, packet, pkt_size, 0);
+	if (!ASSERT_EQ(sent, pkt_size, "xsend(pre-data)"))
+		goto out_close;
+
+	/* sk_data_ready of 'p' will be replaced by strparser handler */
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
+		goto out_close;
+
+	/* consume previous data we injected */
+	if (sockmap_strp_consume_pre_data(p))
+		goto out_close;
+
+	/* Previously, we encountered issues such as deadlocks and
+	 * sequence errors that resulted in the inability to read
+	 * continuously. Therefore, we perform multiple iterations
+	 * of testing here.
+	 */
+	for (i = 0; i < test_cnt; i++) {
+		sent = xsend(c, packet, pkt_size, 0);
+		if (!ASSERT_EQ(sent, pkt_size, "xsend(c)"))
+			goto out_close;
+
+		recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+				     IO_TIMEOUT_SEC);
+		if (!ASSERT_EQ(recvd, pkt_size, "recv_timeout(p)") ||
+		    !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+				  "memcmp, data mismatch"))
+			goto out_close;
+	}
+
+	if (fionread) {
+		sent = xsend(c, packet, pkt_size, 0);
+		if (!ASSERT_EQ(sent, pkt_size, "second xsend(c)"))
+			goto out_close;
+
+		err = ioctl(p, FIONREAD, &avail);
+		if (!ASSERT_OK(err, "ioctl(FIONREAD) error") ||
+		    !ASSERT_EQ(avail, pkt_size, "ioctl(FIONREAD)"))
+			goto out_close;
+
+		recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+				     IO_TIMEOUT_SEC);
+		if (!ASSERT_EQ(recvd, pkt_size, "second recv_timeout(p)") ||
+		    !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+			      "second memcmp, data mismatch"))
+			goto out_close;
+	}
+
+out_close:
+	close(c);
+	close(p);
+
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with verdict mode */
+static void test_sockmap_strp_verdict(int family, int sotype)
+{
+	int zero = 0, one = 1, sent, recvd, off;
+	int err, map;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, false, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	/* We simulate a reverse proxy server.
+	 * When p0 receives data from c0, we forward it to c1.
+	 * From c1's perspective, it will consider this data
+	 * as being sent by p1.
+	 */
+	err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto out_close;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+		goto out_close;
+
+	sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+	if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "xsend(c0)"))
+		goto out_close;
+
+	recvd = recv_timeout(c1, rcv, sizeof(rcv), MSG_DONTWAIT,
+			     IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv_timeout(c1)") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+			  "received data does not match the sent data"))
+		goto out_close;
+
+	/* send again to ensure the stream is functioning correctly. */
+	sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+	if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "second xsend(c0)"))
+		goto out_close;
+
+	/* partial read */
+	off = STRP_PKT_FULL_LEN / 2;
+	recvd = recv_timeout(c1, rcv, off, MSG_DONTWAIT,
+			     IO_TIMEOUT_SEC);
+	recvd += recv_timeout(c1, rcv + off, sizeof(rcv) - off, MSG_DONTWAIT,
+			      IO_TIMEOUT_SEC);
+
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "partial recv_timeout(c1)") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+			  "partial received data does not match the sent data"))
+		goto out_close;
+
+out_close:
+	close(c0);
+	close(c1);
+	close(p0);
+	close(p1);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+void test_sockmap_strp(void)
+{
+	if (test__start_subtest("sockmap strp tcp pass"))
+		test_sockmap_strp_pass(AF_INET, SOCK_STREAM, false);
+	if (test__start_subtest("sockmap strp tcp v6 pass"))
+		test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, false);
+	if (test__start_subtest("sockmap strp tcp pass fionread"))
+		test_sockmap_strp_pass(AF_INET, SOCK_STREAM, true);
+	if (test__start_subtest("sockmap strp tcp v6 pass fionread"))
+		test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, true);
+	if (test__start_subtest("sockmap strp tcp verdict"))
+		test_sockmap_strp_verdict(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp v6 verdict"))
+		test_sockmap_strp_verdict(AF_INET6, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp partial read"))
+		test_sockmap_strp_partial_read(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp multiple packets"))
+		test_sockmap_strp_multiple_pkt(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp dispatch"))
+		test_sockmap_strp_dispatch_pkt(AF_INET, SOCK_STREAM);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index 05d0e07da394..ba6b3ec1156a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 
-#include <linux/tcp.h>
+#include <netinet/tcp.h>
 #include <linux/netlink.h>
 #include "sockopt_sk.skel.h"
 
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
new file mode 100644
index 000000000000..74752233e779
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <test_progs.h>
+#include <linux/pkt_cls.h>
+
+#include "test_tc_change_tail.skel.h"
+#include "socket_helpers.h"
+
+#define LO_IFINDEX 1
+
+void test_tc_change_tail(void)
+{
+	LIBBPF_OPTS(bpf_tcx_opts, tcx_opts);
+	struct test_tc_change_tail *skel = NULL;
+	struct bpf_link *link;
+	int c1, p1;
+	char buf[2];
+	int ret;
+
+	skel = test_tc_change_tail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load"))
+		return;
+
+	link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX,
+				     &tcx_opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx"))
+		goto destroy;
+
+	skel->links.change_tail = link;
+	ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1);
+	if (!ASSERT_OK(ret, "create_pair"))
+		goto destroy;
+
+	ret = xsend(p1, "Tr", 2, 0);
+	ASSERT_EQ(ret, 2, "xsend(p1)");
+	ret = recv(c1, buf, 2, 0);
+	ASSERT_EQ(ret, 2, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	ret = xsend(p1, "G", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 2, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	ret = xsend(p1, "E", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 1, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+	ret = xsend(p1, "Z", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 1, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+	close(c1);
+	close(p1);
+destroy:
+	test_tc_change_tail__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
index 151a4210028f..2461d183dee5 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -14,10 +14,16 @@
 #include "netlink_helpers.h"
 #include "tc_helpers.h"
 
+#define NETKIT_HEADROOM	32
+#define NETKIT_TAILROOM	8
+
 #define MARK		42
 #define PRIO		0xeb9f
 #define ICMP_ECHO	8
 
+#define FLAG_ADJUST_ROOM (1 << 0)
+#define FLAG_SAME_NETNS  (1 << 1)
+
 struct icmphdr {
 	__u8		type;
 	__u8		code;
@@ -35,7 +41,7 @@ struct iplink_req {
 };
 
 static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
-			 bool same_netns, int scrub, int peer_scrub)
+			 int scrub, int peer_scrub, __u32 flags)
 {
 	struct rtnl_handle rth = { .fd = -1 };
 	struct iplink_req req = {};
@@ -63,6 +69,10 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_SCRUB, scrub);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_SCRUB, peer_scrub);
 	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
+	if (flags & FLAG_ADJUST_ROOM) {
+		addattr16(&req.n, sizeof(req), IFLA_NETKIT_HEADROOM, NETKIT_HEADROOM);
+		addattr16(&req.n, sizeof(req), IFLA_NETKIT_TAILROOM, NETKIT_TAILROOM);
+	}
 	addattr_nest_end(&req.n, data);
 	addattr_nest_end(&req.n, linkinfo);
 
@@ -87,7 +97,7 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 				 " addr ee:ff:bb:cc:aa:dd"),
 				 "set hwaddress");
 	}
-	if (same_netns) {
+	if (flags & FLAG_SAME_NETNS) {
 		ASSERT_OK(system("ip link set dev " netkit_peer " up"),
 				 "up peer");
 		ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"),
@@ -184,8 +194,8 @@ void serial_test_tc_netkit_basic(void)
 	int err, ifindex;
 
 	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
-			    NETKIT_SCRUB_DEFAULT);
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
 	if (err)
 		return;
 
@@ -299,8 +309,8 @@ static void serial_test_tc_netkit_multi_links_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
-			    NETKIT_SCRUB_DEFAULT);
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
 	if (err)
 		return;
 
@@ -428,8 +438,8 @@ static void serial_test_tc_netkit_multi_opts_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
-			    NETKIT_SCRUB_DEFAULT);
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
 	if (err)
 		return;
 
@@ -543,8 +553,8 @@ void serial_test_tc_netkit_device(void)
 	int err, ifindex, ifindex2;
 
 	err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, true, NETKIT_SCRUB_DEFAULT,
-			    NETKIT_SCRUB_DEFAULT);
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS);
 	if (err)
 		return;
 
@@ -655,8 +665,8 @@ static void serial_test_tc_netkit_neigh_links_target(int mode, int target)
 	int err, ifindex;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false, NETKIT_SCRUB_DEFAULT,
-			    NETKIT_SCRUB_DEFAULT);
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
 	if (err)
 		return;
 
@@ -733,8 +743,8 @@ static void serial_test_tc_netkit_pkt_type_mode(int mode)
 	struct bpf_link *link;
 
 	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, true, NETKIT_SCRUB_DEFAULT,
-			    NETKIT_SCRUB_DEFAULT);
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS);
 	if (err)
 		return;
 
@@ -799,7 +809,7 @@ void serial_test_tc_netkit_pkt_type(void)
 	serial_test_tc_netkit_pkt_type_mode(NETKIT_L3);
 }
 
-static void serial_test_tc_netkit_scrub_type(int scrub)
+static void serial_test_tc_netkit_scrub_type(int scrub, bool room)
 {
 	LIBBPF_OPTS(bpf_netkit_opts, optl);
 	struct test_tc_link *skel;
@@ -807,7 +817,8 @@ static void serial_test_tc_netkit_scrub_type(int scrub)
 	int err, ifindex;
 
 	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
-			    &ifindex, false, scrub, scrub);
+			    &ifindex, scrub, scrub,
+			    room ? FLAG_ADJUST_ROOM : 0);
 	if (err)
 		return;
 
@@ -842,6 +853,8 @@ static void serial_test_tc_netkit_scrub_type(int scrub)
 	ASSERT_EQ(skel->bss->seen_tc8, true, "seen_tc8");
 	ASSERT_EQ(skel->bss->mark, scrub == NETKIT_SCRUB_NONE ? MARK : 0, "mark");
 	ASSERT_EQ(skel->bss->prio, scrub == NETKIT_SCRUB_NONE ? PRIO : 0, "prio");
+	ASSERT_EQ(skel->bss->headroom, room ? NETKIT_HEADROOM : 0, "headroom");
+	ASSERT_EQ(skel->bss->tailroom, room ? NETKIT_TAILROOM : 0, "tailroom");
 cleanup:
 	test_tc_link__destroy(skel);
 
@@ -852,6 +865,6 @@ cleanup:
 
 void serial_test_tc_netkit_scrub(void)
 {
-	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT);
-	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE);
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT, false);
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE, true);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 3ee40ee9413a..8a0e1ff8a2dc 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -52,6 +52,8 @@
 #include "verifier_map_ptr_mixing.skel.h"
 #include "verifier_map_ret_val.skel.h"
 #include "verifier_masking.skel.h"
+#include "verifier_may_goto_1.skel.h"
+#include "verifier_may_goto_2.skel.h"
 #include "verifier_meta_access.skel.h"
 #include "verifier_movsx.skel.h"
 #include "verifier_mtu.skel.h"
@@ -98,6 +100,7 @@
 #include "verifier_xdp_direct_packet_access.skel.h"
 #include "verifier_bits_iter.skel.h"
 #include "verifier_lsm.skel.h"
+#include "irq.skel.h"
 
 #define MAX_ENTRIES 11
 
@@ -181,6 +184,8 @@ void test_verifier_map_ptr(void)              { RUN(verifier_map_ptr); }
 void test_verifier_map_ptr_mixing(void)       { RUN(verifier_map_ptr_mixing); }
 void test_verifier_map_ret_val(void)          { RUN(verifier_map_ret_val); }
 void test_verifier_masking(void)              { RUN(verifier_masking); }
+void test_verifier_may_goto_1(void)           { RUN(verifier_may_goto_1); }
+void test_verifier_may_goto_2(void)           { RUN(verifier_may_goto_2); }
 void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
 void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
 void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
@@ -225,6 +230,7 @@ void test_verifier_xdp(void)                  { RUN(verifier_xdp); }
 void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }
 void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
 void test_verifier_lsm(void)                  { RUN(verifier_lsm); }
+void test_irq(void)			      { RUN(irq); }
 void test_verifier_mtu(void)		      { RUN(verifier_mtu); }
 
 static int init_test_val_map(struct bpf_object *obj, char *map_name)
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index 53d6ad8c2257..b2b2d85dbb1b 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -82,6 +82,8 @@ static void test_xdp_adjust_tail_grow2(void)
 	/* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */
 #if defined(__s390x__)
 	int tailroom = 512;
+#elif defined(__powerpc__)
+	int tailroom = 384;
 #else
 	int tailroom = 320;
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index 6d8b54124cb3..fb952703653e 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -17,7 +17,7 @@
 #include "network_helpers.h"
 #include <linux/if_bonding.h>
 #include <linux/limits.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
 #include <uapi/linux/netdev.h>
 
 #include "xdp_dummy.skel.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index e6a783c7f5db..937da9b7532a 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -2,6 +2,14 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "test_xdp_context_test_run.skel.h"
+#include "test_xdp_meta.skel.h"
+
+#define TX_ADDR "10.0.0.1"
+#define RX_ADDR "10.0.0.2"
+#define RX_NAME "veth0"
+#define TX_NAME "veth1"
+#define TX_NETNS "xdp_context_tx"
+#define RX_NETNS "xdp_context_rx"
 
 void test_xdp_context_error(int prog_fd, struct bpf_test_run_opts opts,
 			    __u32 data_meta, __u32 data, __u32 data_end,
@@ -103,3 +111,82 @@ void test_xdp_context_test_run(void)
 
 	test_xdp_context_test_run__destroy(skel);
 }
+
+void test_xdp_context_functional(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	struct netns_obj *rx_ns = NULL, *tx_ns = NULL;
+	struct bpf_program *tc_prog, *xdp_prog;
+	struct test_xdp_meta *skel = NULL;
+	struct nstoken *nstoken = NULL;
+	int rx_ifindex;
+	int ret;
+
+	tx_ns = netns_new(TX_NETNS, false);
+	if (!ASSERT_OK_PTR(tx_ns, "create tx_ns"))
+		return;
+
+	rx_ns = netns_new(RX_NETNS, false);
+	if (!ASSERT_OK_PTR(rx_ns, "create rx_ns"))
+		goto close;
+
+	SYS(close, "ip link add " RX_NAME " netns " RX_NETNS
+	    " type veth peer name " TX_NAME " netns " TX_NETNS);
+
+	nstoken = open_netns(RX_NETNS);
+	if (!ASSERT_OK_PTR(nstoken, "setns rx_ns"))
+		goto close;
+
+	SYS(close, "ip addr add " RX_ADDR "/24 dev " RX_NAME);
+	SYS(close, "ip link set dev " RX_NAME " up");
+
+	skel = test_xdp_meta__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		goto close;
+
+	rx_ifindex = if_nametoindex(RX_NAME);
+	if (!ASSERT_GE(rx_ifindex, 0, "if_nametoindex rx"))
+		goto close;
+
+	tc_hook.ifindex = rx_ifindex;
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto close;
+
+	tc_prog = bpf_object__find_program_by_name(skel->obj, "ing_cls");
+	if (!ASSERT_OK_PTR(tc_prog, "open ing_cls prog"))
+		goto close;
+
+	tc_opts.prog_fd = bpf_program__fd(tc_prog);
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto close;
+
+	xdp_prog = bpf_object__find_program_by_name(skel->obj, "ing_xdp");
+	if (!ASSERT_OK_PTR(xdp_prog, "open ing_xdp prog"))
+		goto close;
+
+	ret = bpf_xdp_attach(rx_ifindex,
+			     bpf_program__fd(xdp_prog),
+			     0, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	close_netns(nstoken);
+
+	nstoken = open_netns(TX_NETNS);
+	if (!ASSERT_OK_PTR(nstoken, "setns tx_ns"))
+		goto close;
+
+	SYS(close, "ip addr add " TX_ADDR "/24 dev " TX_NAME);
+	SYS(close, "ip link set dev " TX_NAME " up");
+	ASSERT_OK(SYS_NOFAIL("ping -c 1 " RX_ADDR), "ping");
+
+close:
+	close_netns(nstoken);
+	test_xdp_meta__destroy(skel);
+	netns_free(rx_ns);
+	netns_free(tx_ns);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index c7f74f068e78..df27535995af 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -52,10 +52,10 @@ static void test_xdp_with_cpumap_helpers(void)
 	ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id");
 
 	/* send a packet to trigger any potential bugs in there */
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index 27ffed17d4be..461ab18705d5 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -23,7 +23,7 @@ static void test_xdp_with_devmap_helpers(void)
 	__u32 len = sizeof(info);
 	int err, dm_fd, dm_fd_redir, map_fd;
 	struct nstoken *nstoken = NULL;
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	__u32 idx = 0;
 
 	SYS(out_close, "ip netns add %s", TEST_NS);
@@ -58,7 +58,7 @@ static void test_xdp_with_devmap_helpers(void)
 	/* send a packet to trigger any potential bugs in there */
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
@@ -158,7 +158,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
 	struct nstoken *nstoken = NULL;
 	__u32 len = sizeof(info);
 	int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst;
-	char data[10] = {};
+	char data[ETH_HLEN] = {};
 	__u32 idx = 0;
 
 	SYS(out_close, "ip netns add %s", TEST_NS);
@@ -208,7 +208,7 @@ static void test_xdp_with_devmap_helpers_veth(void)
 	/* send a packet to trigger any potential bugs in there */
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = 10,
+			    .data_size_in = sizeof(data),
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index bad0ea167be7..7dac044664ac 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -7,10 +7,11 @@
 #include <linux/if_link.h>
 #include <linux/ipv6.h>
 #include <linux/in6.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
 #include <bpf/bpf_endian.h>
 #include <uapi/linux/netdev.h>
 #include "test_xdp_do_redirect.skel.h"
+#include "xdp_dummy.skel.h"
 
 struct udp_packet {
 	struct ethhdr eth;
@@ -246,3 +247,166 @@ out:
 	SYS_NOFAIL("ip netns del testns");
 	test_xdp_do_redirect__destroy(skel);
 }
+
+#define NS_NB		3
+#define NS0		"NS0"
+#define NS1		"NS1"
+#define NS2		"NS2"
+#define IPV4_NETWORK	"10.1.1"
+#define VETH1_INDEX	111
+#define VETH2_INDEX	222
+
+struct test_data {
+	struct netns_obj *ns[NS_NB];
+	u32 xdp_flags;
+};
+
+static void cleanup(struct test_data *data)
+{
+	int i;
+
+	for (i = 0; i < NS_NB; i++)
+		netns_free(data->ns[i]);
+}
+
+/**
+ * ping_setup -
+ * Create two veth peers and forward packets in-between using XDP
+ *
+ *    ------------           ------------
+ *    |    NS1   |           |    NS2   |
+ *    |   veth0  |           |   veth0  |
+ *    | 10.1.1.1 |           | 10.1.1.2 |
+ *    -----|------           ------|-----
+ *         |                       |
+ *         |                       |
+ *    -----|-----------------------|-------
+ *    |  veth1                   veth2    |
+ *    | (id:111)                (id:222)  |
+ *    |    |                        |     |
+ *    |    ----- xdp forwarding -----     |
+ *    |                                   |
+ *    |               NS0                 |
+ *    -------------------------------------
+ */
+static int ping_setup(struct test_data *data)
+{
+	int i;
+
+	data->ns[0] = netns_new(NS0, false);
+	if (!ASSERT_OK_PTR(data->ns[0], "create ns"))
+		return -1;
+
+	for (i = 1; i < NS_NB; i++) {
+		char ns_name[4] = {};
+
+		snprintf(ns_name, 4, "NS%d", i);
+		data->ns[i] = netns_new(ns_name, false);
+		if (!ASSERT_OK_PTR(data->ns[i], "create ns"))
+			goto fail;
+
+		SYS(fail,
+		    "ip -n %s link add veth%d index %d%d%d type veth peer name veth0 netns %s",
+		    NS0, i, i, i, i, ns_name);
+		SYS(fail, "ip -n %s link set veth%d up", NS0, i);
+
+		SYS(fail, "ip -n %s addr add %s.%d/24 dev veth0", ns_name, IPV4_NETWORK, i);
+		SYS(fail, "ip -n %s link set veth0 up", ns_name);
+	}
+
+	return 0;
+
+fail:
+	cleanup(data);
+	return -1;
+}
+
+static void ping_test(struct test_data *data)
+{
+	struct test_xdp_do_redirect *skel = NULL;
+	struct xdp_dummy *skel_dummy = NULL;
+	struct nstoken *nstoken = NULL;
+	int i, ret;
+
+	skel_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(skel_dummy, "open and load xdp_dummy skeleton"))
+		goto close;
+
+	for (i = 1; i < NS_NB; i++) {
+		char ns_name[4] = {};
+
+		snprintf(ns_name, 4, "NS%d", i);
+		nstoken = open_netns(ns_name);
+		if (!ASSERT_OK_PTR(nstoken, "open ns"))
+			goto close;
+
+		ret = bpf_xdp_attach(if_nametoindex("veth0"),
+				     bpf_program__fd(skel_dummy->progs.xdp_dummy_prog),
+				     data->xdp_flags, NULL);
+		if (!ASSERT_GE(ret, 0, "bpf_xdp_attach dummy_prog"))
+			goto close;
+
+		close_netns(nstoken);
+		nstoken = NULL;
+	}
+
+	skel = test_xdp_do_redirect__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		goto close;
+
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto close;
+
+	ret = bpf_xdp_attach(VETH2_INDEX,
+			     bpf_program__fd(skel->progs.xdp_redirect_to_111),
+			     data->xdp_flags, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	ret = bpf_xdp_attach(VETH1_INDEX,
+			     bpf_program__fd(skel->progs.xdp_redirect_to_222),
+			     data->xdp_flags, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	nstoken = open_netns(NS1);
+	if (!ASSERT_OK_PTR(nstoken, "open NS1"))
+		goto close;
+
+	SYS(close, "ping -c 1 %s.2 > /dev/null", IPV4_NETWORK);
+
+close:
+	close_netns(nstoken);
+	xdp_dummy__destroy(skel_dummy);
+	test_xdp_do_redirect__destroy(skel);
+}
+
+
+static void xdp_redirect_ping(u32 xdp_flags)
+{
+	struct test_data data = {};
+
+	if (ping_setup(&data) < 0)
+		return;
+
+	data.xdp_flags = xdp_flags;
+	ping_test(&data);
+	cleanup(&data);
+}
+
+void test_xdp_index_redirect(void)
+{
+	if (test__start_subtest("noflag"))
+		xdp_redirect_ping(0);
+
+	if (test__start_subtest("drvflag"))
+		xdp_redirect_ping(XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("skbflag"))
+		xdp_redirect_ping(XDP_FLAGS_SKB_MODE);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
index e1bf141d3401..3f9146d83d79 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
@@ -3,7 +3,7 @@
 #include <network_helpers.h>
 #include <bpf/btf.h>
 #include <linux/if_link.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
 #include <net/if.h>
 #include <unistd.h>
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index c87ee2bf558c..3d47878ef6bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -10,7 +10,7 @@
 #include <linux/errqueue.h>
 #include <linux/if_link.h>
 #include <linux/net_tstamp.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
 #include <sys/mman.h>
 #include <net/if.h>
 #include <poll.h>
@@ -133,23 +133,6 @@ static void close_xsk(struct xsk *xsk)
 	munmap(xsk->umem_area, UMEM_SIZE);
 }
 
-static void ip_csum(struct iphdr *iph)
-{
-	__u32 sum = 0;
-	__u16 *p;
-	int i;
-
-	iph->check = 0;
-	p = (void *)iph;
-	for (i = 0; i < sizeof(*iph) / sizeof(*p); i++)
-		sum += p[i];
-
-	while (sum >> 16)
-		sum = (sum & 0xffff) + (sum >> 16);
-
-	iph->check = ~sum;
-}
-
 static int generate_packet(struct xsk *xsk, __u16 dst_port)
 {
 	struct xsk_tx_metadata *meta;
@@ -192,7 +175,7 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port)
 	iph->protocol = IPPROTO_UDP;
 	ASSERT_EQ(inet_pton(FAMILY, TX_ADDR, &iph->saddr), 1, "inet_pton(TX_ADDR)");
 	ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)");
-	ip_csum(iph);
+	iph->check = build_ip_csum(iph);
 
 	udph->source = htons(UDP_SOURCE_PORT);
 	udph->dest = htons(dst_port);