libbpf: Access first syscall argument with CO-RE direct read on arm64

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 <[email protected]>
Signed-off-by: Pu Lehui <[email protected]>
Signed-off-by: Andrii Nakryiko <[email protected]>
Acked-by: Xu Kuohai <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: Pu Lehui

tools/lib/bpf/bpf_tracing.h

@@ -222,7 +222,7 @@ struct pt_regs___s390 {
 
 struct pt_regs___arm64 {
 	unsigned long orig_x0;
-};
+} __attribute__((preserve_access_index));
 
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
@@ -241,7 +241,7 @@ struct pt_regs___arm64 {
 #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG
 #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG
 #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG
-#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x)
+#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___arm64 *)(x))->__PT_PARM1_SYSCALL_REG)
 #define PT_REGS_PARM1_CORE_SYSCALL(x) \
 	BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG)