selftests/bpf: Fix test_core_autosize on big-endian machines

The "probed" part of test_core_autosize copies an integer using
bpf_core_read() into an integer of a potentially different size.
On big-endian machines a destination offset is required for this to
produce a sensible result.

Fixes: 888d83b961f6 ("selftests/bpf: Validate libbpf's auto-sizing of LD/ST/STX instructions")
Signed-off-by: Ilya Leoshkevich <[e-mail]>
Signed-off-by: Andrii Nakryiko <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

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

···
 	return 0;
 }
 
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define bpf_core_read_int bpf_core_read
+#else
+#define bpf_core_read_int(dst, sz, src) ({ \
+	/* Prevent "subtraction from stack pointer prohibited" */ \
+	volatile long __off = sizeof(*dst) - (sz); \
+	bpf_core_read((char *)(dst) + __off, sz, src); \
+})
+#endif
+
 SEC("raw_tp/sys_enter")
 int handle_probed(void *ctx)
 {
···
 	__u64 tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->ptr), &in->ptr);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->ptr), &in->ptr);
 	ptr_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val1), &in->val1);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val1), &in->val1);
 	val1_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val2), &in->val2);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val2), &in->val2);
 	val2_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val3), &in->val3);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val3), &in->val3);
 	val3_probed = tmp;
 
 	tmp = 0;
-	bpf_core_read(&tmp, bpf_core_field_size(in->val4), &in->val4);
+	bpf_core_read_int(&tmp, bpf_core_field_size(in->val4), &in->val4);
 	val4_probed = tmp;
 
 	return 0;