libbpf: Access first syscall argument with CO-RE direct read on s390

Currently PT_REGS_PARM1 SYSCALL(x) is consistent with PT_REGS_PARM1_CORE
SYSCALL(x), which will introduce the overhead of BPF_CORE_READ(), taking
into account the read pt_regs comes directly from the context, let's use
CO-RE direct read to access the first system call argument.
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Pu Lehui <pulehui@huawei.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240831041934.1629216-2-pulehui@huaweicloud.com

tools/lib/bpf/bpf_tracing.h

@@ -163,7 +163,7 @@
 
 struct pt_regs___s390 {
 	unsigned long orig_gpr2;
-};
+} __attribute__((preserve_access_index));
 
 /* s390 provides user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
@@ -179,7 +179,7 @@ struct pt_regs___s390 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG gprs[7]
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___s390 *)(x))->__PT_PARM1_SYSCALL_REG)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) \
 	BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG)