1 files changed, 543 insertions, 117 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index bb8fe646dd9f..58fe2c586ed7 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 /* test_tailcall_1 checks basic functionality by patching multiple locations
  * in a single program for a single tail call slot with nop->jmp, jmp->nop
@@ -11,16 +12,20 @@ static void test_tailcall_1(void)
 	struct bpf_map *prog_array;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	__u32 retval, duration;
 	char prog_name[32];
 	char buff[128] = {};
-
-	err = bpf_prog_load("tailcall1.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
-			    &prog_fd);
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall1.bpf.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+				 &prog_fd);
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -36,10 +41,10 @@ static void test_tailcall_1(void)
 	if (CHECK_FAIL(map_fd < 0))
 		goto out;
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -52,26 +57,24 @@ static void test_tailcall_1(void)
 			goto out;
 	}
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-					&duration, &retval, NULL);
-		CHECK(err || retval != i, "tailcall",
-		      "err %d errno %d retval %d\n", err, errno, retval);
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		err = bpf_prog_test_run_opts(main_fd, &topts);
+		ASSERT_OK(err, "tailcall");
+		ASSERT_EQ(topts.retval, i, "tailcall retval");
 
 		err = bpf_map_delete_elem(map_fd, &i);
 		if (CHECK_FAIL(err))
 			goto out;
 	}
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 3, "tailcall retval");
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -84,16 +87,15 @@ static void test_tailcall_1(void)
 			goto out;
 	}
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_OK(topts.retval, "tailcall retval");
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		j = bpf_map__def(prog_array)->max_entries - 1 - i;
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", j);
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		j = bpf_map__max_entries(prog_array) - 1 - i;
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", j);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -106,33 +108,30 @@ static void test_tailcall_1(void)
 			goto out;
 	}
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		j = bpf_map__def(prog_array)->max_entries - 1 - i;
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		j = bpf_map__max_entries(prog_array) - 1 - i;
 
-		err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-					&duration, &retval, NULL);
-		CHECK(err || retval != j, "tailcall",
-		      "err %d errno %d retval %d\n", err, errno, retval);
+		err = bpf_prog_test_run_opts(main_fd, &topts);
+		ASSERT_OK(err, "tailcall");
+		ASSERT_EQ(topts.retval, j, "tailcall retval");
 
 		err = bpf_map_delete_elem(map_fd, &i);
 		if (CHECK_FAIL(err))
 			goto out;
 	}
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 3, "tailcall retval");
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		err = bpf_map_delete_elem(map_fd, &i);
 		if (CHECK_FAIL(err >= 0 || errno != ENOENT))
 			goto out;
 
-		err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-					&duration, &retval, NULL);
-		CHECK(err || retval != 3, "tailcall",
-		      "err %d errno %d retval %d\n", err, errno, retval);
+		err = bpf_prog_test_run_opts(main_fd, &topts);
+		ASSERT_OK(err, "tailcall");
+		ASSERT_EQ(topts.retval, 3, "tailcall retval");
 	}
 
 out:
@@ -149,16 +148,20 @@ static void test_tailcall_2(void)
 	struct bpf_map *prog_array;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	__u32 retval, duration;
 	char prog_name[32];
 	char buff[128] = {};
-
-	err = bpf_prog_load("tailcall2.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
-			    &prog_fd);
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall2.bpf.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+				 &prog_fd);
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -174,10 +177,10 @@ static void test_tailcall_2(void)
 	if (CHECK_FAIL(map_fd < 0))
 		goto out;
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -190,52 +193,50 @@ static void test_tailcall_2(void)
 			goto out;
 	}
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 2, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 2, "tailcall retval");
 
 	i = 2;
 	err = bpf_map_delete_elem(map_fd, &i);
 	if (CHECK_FAIL(err))
 		goto out;
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
 
 	i = 0;
 	err = bpf_map_delete_elem(map_fd, &i);
 	if (CHECK_FAIL(err))
 		goto out;
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 3, "tailcall retval");
 out:
 	bpf_object__close(obj);
 }
 
-/* test_tailcall_3 checks that the count value of the tail call limit
- * enforcement matches with expectations.
- */
-static void test_tailcall_3(void)
+static void test_tailcall_count(const char *which)
 {
 	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
 	struct bpf_map *prog_array, *data_map;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	__u32 retval, duration;
 	char buff[128] = {};
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
 
-	err = bpf_prog_load("tailcall3.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+	err = bpf_prog_test_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj,
 			    &prog_fd);
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -251,7 +252,7 @@ static void test_tailcall_3(void)
 	if (CHECK_FAIL(map_fd < 0))
 		goto out;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier/0");
+	prog = bpf_object__find_program_by_name(obj, "classifier_0");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -264,10 +265,9 @@ static void test_tailcall_3(void)
 	if (CHECK_FAIL(err))
 		goto out;
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
@@ -279,22 +279,37 @@ static void test_tailcall_3(void)
 
 	i = 0;
 	err = bpf_map_lookup_elem(data_fd, &i, &val);
-	CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n",
-	      err, errno, val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 33, "tailcall count");
 
 	i = 0;
 	err = bpf_map_delete_elem(map_fd, &i);
 	if (CHECK_FAIL(err))
 		goto out;
 
-	err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-				&duration, &retval, NULL);
-	CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n",
-	      err, errno, retval);
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_OK(topts.retval, "tailcall retval");
 out:
 	bpf_object__close(obj);
 }
 
+/* test_tailcall_3 checks that the count value of the tail call limit
+ * enforcement matches with expectations. JIT uses direct jump.
+ */
+static void test_tailcall_3(void)
+{
+	test_tailcall_count("tailcall3.bpf.o");
+}
+
+/* test_tailcall_6 checks that the count value of the tail call limit
+ * enforcement matches with expectations. JIT uses indirect jump.
+ */
+static void test_tailcall_6(void)
+{
+	test_tailcall_count("tailcall6.bpf.o");
+}
+
 /* test_tailcall_4 checks that the kernel properly selects indirect jump
  * for the case where the key is not known. Latter is passed via global
  * data to select different targets we can compare return value of.
@@ -305,17 +320,21 @@ static void test_tailcall_4(void)
 	struct bpf_map *prog_array, *data_map;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	__u32 retval, duration;
 	static const int zero = 0;
 	char buff[128] = {};
 	char prog_name[32];
-
-	err = bpf_prog_load("tailcall4.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
-			    &prog_fd);
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall4.bpf.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+				 &prog_fd);
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -339,10 +358,10 @@ static void test_tailcall_4(void)
 	if (CHECK_FAIL(map_fd < 0))
 		return;
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -355,18 +374,17 @@ static void test_tailcall_4(void)
 			goto out;
 	}
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY);
 		if (CHECK_FAIL(err))
 			goto out;
 
-		err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-					&duration, &retval, NULL);
-		CHECK(err || retval != i, "tailcall",
-		      "err %d errno %d retval %d\n", err, errno, retval);
+		err = bpf_prog_test_run_opts(main_fd, &topts);
+		ASSERT_OK(err, "tailcall");
+		ASSERT_EQ(topts.retval, i, "tailcall retval");
 	}
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY);
 		if (CHECK_FAIL(err))
 			goto out;
@@ -375,10 +393,9 @@ static void test_tailcall_4(void)
 		if (CHECK_FAIL(err))
 			goto out;
 
-		err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-					&duration, &retval, NULL);
-		CHECK(err || retval != 3, "tailcall",
-		      "err %d errno %d retval %d\n", err, errno, retval);
+		err = bpf_prog_test_run_opts(main_fd, &topts);
+		ASSERT_OK(err, "tailcall");
+		ASSERT_EQ(topts.retval, 3, "tailcall retval");
 	}
 out:
 	bpf_object__close(obj);
@@ -393,17 +410,21 @@ static void test_tailcall_5(void)
 	struct bpf_map *prog_array, *data_map;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	__u32 retval, duration;
 	static const int zero = 0;
 	char buff[128] = {};
 	char prog_name[32];
-
-	err = bpf_prog_load("tailcall5.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
-			    &prog_fd);
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall5.bpf.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+				 &prog_fd);
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -427,10 +448,10 @@ static void test_tailcall_5(void)
 	if (CHECK_FAIL(map_fd < 0))
 		return;
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -443,18 +464,17 @@ static void test_tailcall_5(void)
 			goto out;
 	}
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY);
 		if (CHECK_FAIL(err))
 			goto out;
 
-		err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-					&duration, &retval, NULL);
-		CHECK(err || retval != i, "tailcall",
-		      "err %d errno %d retval %d\n", err, errno, retval);
+		err = bpf_prog_test_run_opts(main_fd, &topts);
+		ASSERT_OK(err, "tailcall");
+		ASSERT_EQ(topts.retval, i, "tailcall retval");
 	}
 
-	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY);
 		if (CHECK_FAIL(err))
 			goto out;
@@ -463,15 +483,407 @@ static void test_tailcall_5(void)
 		if (CHECK_FAIL(err))
 			goto out;
 
-		err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
-					&duration, &retval, NULL);
-		CHECK(err || retval != 3, "tailcall",
-		      "err %d errno %d retval %d\n", err, errno, retval);
+		err = bpf_prog_test_run_opts(main_fd, &topts);
+		ASSERT_OK(err, "tailcall");
+		ASSERT_EQ(topts.retval, 3, "tailcall retval");
+	}
+out:
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_1 purpose is to make sure that tailcalls are working
+ * correctly in correlation with BPF subprograms
+ */
+static void test_tailcall_bpf2bpf_1(void)
+{
+	int err, map_fd, prog_fd, main_fd, i;
+	struct bpf_map *prog_array;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char prog_name[32];
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall_bpf2bpf1.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
+				 &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_name(obj, "entry");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	/* nop -> jmp */
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
+
+		prog = bpf_object__find_program_by_name(obj, prog_name);
+		if (CHECK_FAIL(!prog))
+			goto out;
+
+		prog_fd = bpf_program__fd(prog);
+		if (CHECK_FAIL(prog_fd < 0))
+			goto out;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (CHECK_FAIL(err))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	/* jmp -> nop, call subprog that will do tailcall */
+	i = 1;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_OK(topts.retval, "tailcall retval");
+
+	/* make sure that subprog can access ctx and entry prog that
+	 * called this subprog can properly return
+	 */
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval");
+out:
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_2 checks that the count value of the tail call limit
+ * enforcement matches with expectations when tailcall is preceded with
+ * bpf2bpf call.
+ */
+static void test_tailcall_bpf2bpf_2(void)
+{
+	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+	struct bpf_map *prog_array, *data_map;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char buff[128] = {};
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall_bpf2bpf2.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
+				 &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_name(obj, "entry");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(obj, "classifier_0");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	prog_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(prog_fd < 0))
+		goto out;
+
+	i = 0;
+	err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
+	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
+		return;
+
+	data_fd = bpf_map__fd(data_map);
+	if (CHECK_FAIL(map_fd < 0))
+		return;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 33, "tailcall count");
+
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_OK(topts.retval, "tailcall retval");
+out:
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_3 checks that non-trivial amount of stack (up to
+ * 256 bytes) can be used within bpf subprograms that have the tailcalls
+ * in them
+ */
+static void test_tailcall_bpf2bpf_3(void)
+{
+	int err, map_fd, prog_fd, main_fd, i;
+	struct bpf_map *prog_array;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char prog_name[32];
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall_bpf2bpf3.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
+				 &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_name(obj, "entry");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
+
+		prog = bpf_object__find_program_by_name(obj, prog_name);
+		if (CHECK_FAIL(!prog))
+			goto out;
+
+		prog_fd = bpf_program__fd(prog);
+		if (CHECK_FAIL(prog_fd < 0))
+			goto out;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (CHECK_FAIL(err))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval");
+
+	i = 1;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, sizeof(pkt_v4), "tailcall retval");
+
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval");
+out:
+	bpf_object__close(obj);
+}
+
+#include "tailcall_bpf2bpf4.skel.h"
+
+/* test_tailcall_bpf2bpf_4 checks that tailcall counter is correctly preserved
+ * across tailcalls combined with bpf2bpf calls. for making sure that tailcall
+ * counter behaves correctly, bpf program will go through following flow:
+ *
+ * entry -> entry_subprog -> tailcall0 -> bpf_func0 -> subprog0 ->
+ * -> tailcall1 -> bpf_func1 -> subprog1 -> tailcall2 -> bpf_func2 ->
+ * subprog2 [here bump global counter] --------^
+ *
+ * We go through first two tailcalls and start counting from the subprog2 where
+ * the loop begins. At the end of the test make sure that the global counter is
+ * equal to 31, because tailcall counter includes the first two tailcalls
+ * whereas global counter is incremented only on loop presented on flow above.
+ *
+ * The noise parameter is used to insert bpf_map_update calls into the logic
+ * to force verifier to patch instructions. This allows us to ensure jump
+ * logic remains correct with instruction movement.
+ */
+static void test_tailcall_bpf2bpf_4(bool noise)
+{
+	int err, map_fd, prog_fd, main_fd, data_fd, i;
+	struct tailcall_bpf2bpf4__bss val;
+	struct bpf_map *prog_array, *data_map;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char prog_name[32];
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall_bpf2bpf4.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
+				 &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	prog = bpf_object__find_program_by_name(obj, "entry");
+	if (CHECK_FAIL(!prog))
+		goto out;
+
+	main_fd = bpf_program__fd(prog);
+	if (CHECK_FAIL(main_fd < 0))
+		goto out;
+
+	prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+	if (CHECK_FAIL(!prog_array))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (CHECK_FAIL(map_fd < 0))
+		goto out;
+
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
+
+		prog = bpf_object__find_program_by_name(obj, prog_name);
+		if (CHECK_FAIL(!prog))
+			goto out;
+
+		prog_fd = bpf_program__fd(prog);
+		if (CHECK_FAIL(prog_fd < 0))
+			goto out;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (CHECK_FAIL(err))
+			goto out;
 	}
+
+	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
+	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
+		return;
+
+	data_fd = bpf_map__fd(data_map);
+	if (CHECK_FAIL(map_fd < 0))
+		return;
+
+	i = 0;
+	val.noise = noise;
+	val.count = 0;
+	err = bpf_map_update_elem(data_fd, &i, &val, BPF_ANY);
+	if (CHECK_FAIL(err))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval");
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val.count, 31, "tailcall count");
+
 out:
 	bpf_object__close(obj);
 }
 
+#include "tailcall_bpf2bpf6.skel.h"
+
+/* Tail call counting works even when there is data on stack which is
+ * not aligned to 8 bytes.
+ */
+static void test_tailcall_bpf2bpf_6(void)
+{
+	struct tailcall_bpf2bpf6 *obj;
+	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+
+	obj = tailcall_bpf2bpf6__open_and_load();
+	if (!ASSERT_OK_PTR(obj, "open and load"))
+		return;
+
+	main_fd = bpf_program__fd(obj->progs.entry);
+	if (!ASSERT_GE(main_fd, 0, "entry prog fd"))
+		goto out;
+
+	map_fd = bpf_map__fd(obj->maps.jmp_table);
+	if (!ASSERT_GE(map_fd, 0, "jmp_table map fd"))
+		goto out;
+
+	prog_fd = bpf_program__fd(obj->progs.classifier_0);
+	if (!ASSERT_GE(prog_fd, 0, "classifier_0 prog fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "jmp_table map update"))
+		goto out;
+
+	err = bpf_prog_test_run_opts(main_fd, &topts);
+	ASSERT_OK(err, "entry prog test run");
+	ASSERT_EQ(topts.retval, 0, "tailcall retval");
+
+	data_fd = bpf_map__fd(obj->maps.bss);
+	if (!ASSERT_GE(map_fd, 0, "bss map fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "bss map lookup");
+	ASSERT_EQ(val, 1, "done flag is set");
+
+out:
+	tailcall_bpf2bpf6__destroy(obj);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -484,4 +896,18 @@ void test_tailcalls(void)
 		test_tailcall_4();
 	if (test__start_subtest("tailcall_5"))
 		test_tailcall_5();
+	if (test__start_subtest("tailcall_6"))
+		test_tailcall_6();
+	if (test__start_subtest("tailcall_bpf2bpf_1"))
+		test_tailcall_bpf2bpf_1();
+	if (test__start_subtest("tailcall_bpf2bpf_2"))
+		test_tailcall_bpf2bpf_2();
+	if (test__start_subtest("tailcall_bpf2bpf_3"))
+		test_tailcall_bpf2bpf_3();
+	if (test__start_subtest("tailcall_bpf2bpf_4"))
+		test_tailcall_bpf2bpf_4(false);
+	if (test__start_subtest("tailcall_bpf2bpf_5"))
+		test_tailcall_bpf2bpf_4(true);
+	if (test__start_subtest("tailcall_bpf2bpf_6"))
+		test_tailcall_bpf2bpf_6();
 }