[PATCH bpf-next v2 3/3] selftests/bpf: Fix test for 4-byte load from dst_port on big-endian

[Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>]

The check for 4-byte load from dst_port offset into bpf_sock is failing on
big-endian architecture - s390. The bpf access converter rewrites the
4-byte load to a 2-byte load from sock_common at skc_dport offset, as shown
below.

  * s390 / llvm-objdump -S --no-show-raw-insn

  00000000000002a0 <sk_dst_port__load_word>:
        84:       r1 = *(u32 *)(r1 + 48)
        85:       w0 = 1
        86:       if w1 == 51966 goto +1 <LBB5_2>
        87:       w0 = 0
  00000000000002c0 <LBB5_2>:
        88:       exit

  * s390 / bpftool prog dump xlated

  _Bool sk_dst_port__load_word(struct bpf_sock * sk):
    35: (69) r1 = *(u16 *)(r1 +12)
    36: (bc) w1 = w1
    37: (b4) w0 = 1
    38: (16) if w1 == 0xcafe goto pc+1
    39: (b4) w0 = 0
    40: (95) exit

  * s390 / llvm-objdump -S --no-show-raw-insn

  00000000000002a0 <sk_dst_port__load_word>:
        84:       r1 = *(u32 *)(r1 + 48)
        85:       w0 = 1
        86:       if w1 == 65226 goto +1 <LBB5_2>
        87:       w0 = 0
  00000000000002c0 <LBB5_2>:
        88:       exit

  * x86_64 / bpftool prog dump xlated

  _Bool sk_dst_port__load_word(struct bpf_sock * sk):
    33: (69) r1 = *(u16 *)(r1 +12)
    34: (b4) w0 = 1
    35: (16) if w1 == 0xfeca goto pc+1
    36: (b4) w0 = 0
    37: (95) exit

This leads to surprisings results. On big-endian platforms, the loaded
value is as expected. The user observes no difference between a 4-byte load
and 2-byte load. However, on little-endian platforms, the access conversion
is not what would be expected, that is the result is left shifted after
converting the value to the native byte order.

That said, 4-byte loads in BPF from sk->dst_port are not a use case we
expect to see, now that the dst_port field is clearly declared as a u16.

Account for the quirky behavior of the access converter in the test case,
so that the check passes on both endian variants.

Fixes: 8f50f16ff39d ("selftests/bpf: Extend verifier and bpf_sock tests for dst_port loads")
Signed-off-by: Jakub Sitnicki <jakub@xxxxxxxxxxxxxx>
---
 .../selftests/bpf/progs/test_sock_fields.c        | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c
index 186fed1deaab..3dddc173070c 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c
@@ -256,10 +256,23 @@ int ingress_read_sock_fields(struct __sk_buff *skb)
 	return CG_OK;
 }
 
+/*
+ * NOTE: 4-byte load from bpf_sock at dst_port offset is quirky. The
+ * result is left shifted on little-endian architectures because the
+ * access is converted to a 2-byte load. The quirky behavior is kept
+ * for backward compatibility.
+ */
 static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk)
 {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	const __u8 SHIFT = 16;
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	const __u8 SHIFT = 0;
+#else
+#error "Unrecognized __BYTE_ORDER__"
+#endif
 	__u32 *word = (__u32 *)&sk->dst_port;
-	return word[0] == bpf_htonl(0xcafe0000);
+	return word[0] == bpf_htonl(0xcafe << SHIFT);
 }
 
 static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk)
-- 
2.35.1