selftests/bpf: Add tests for RCU lock transfer between subprogs

Add selftests covering the following cases:
- A static or global subprog called from within a RCU read section works
- A static subprog taking an RCU read lock which is released in caller works
- A static subprog releasing the caller's RCU read lock works

Global subprogs that leave the lock in an imbalanced state will not
work, as they are verified separately, so ensure those cases fail as
well.

Acked-by: Yonghong Song <[e-mail]>
Signed-off-by: Kumar Kartikeya Dwivedi <[e-mail]>
Acked-by: David Vernet <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c

···
 	bpf_program__set_autoload(skel->progs.non_sleepable_1, true);
 	bpf_program__set_autoload(skel->progs.non_sleepable_2, true);
 	bpf_program__set_autoload(skel->progs.task_trusted_non_rcuptr, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_global_subprog, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_lock, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_unlock, true);
 	err = rcu_read_lock__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
 		goto out;
···
 	"inproper_sleepable_helper",
 	"inproper_sleepable_kfunc",
 	"nested_rcu_region",
+	"rcu_read_lock_global_subprog_lock",
+	"rcu_read_lock_global_subprog_unlock",
 };
 
 static void test_inproper_region(void)

tools/testing/selftests/bpf/progs/rcu_read_lock.c

···
 	bpf_rcu_read_unlock();
 	return 0;
 }
+
+__noinline
+static int static_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog(NULL);
+}
+
+__noinline
+static int static_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog_lock(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog_lock(NULL);
+}
+
+__noinline
+static int static_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_unlock();
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog_unlock(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog_unlock(NULL);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		ret += static_subprog(ctx);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		ret += global_subprog(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	ret += static_subprog_lock(ctx);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	ret += global_subprog_lock(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += static_subprog_unlock(ctx);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_subprog_unlock(ret);
+	return 0;
+}