Re: [PATCH v2 2/2] bpf/arm64: support packet data load instructions

[Wathsala Vithanage <wathsala.vithanage@arm.com>]

Hi Christophe,

Thanks for doing this work. I saw that you intend to submit a v3 due to 
failure in Ubuntu. Please, see my comment regarding emit_b below.

>> +       /* A64_R(0) = mbuf->buf_addr */
>> +       emit_mov_imm(ctx, 1, tmp1, offsetof(struct rte_mbuf, buf_addr));
>> +       emit_ldr(ctx, EBPF_DW, A64_R(0), r6, tmp1);
>> +       /* tmp2 = * mbuf->data_off */
>> +       emit_mov_imm(ctx, 1, tmp2, offsetof(struct rte_mbuf, data_off));
>> +       emit_ldr(ctx, BPF_H, tmp2, r6, tmp2);
>> +
>> +       /* A64_R(0) += data_off + off */
>> +       emit_add(ctx, 1, A64_R(0), tmp2);
>> +       emit_add(ctx, 1, A64_R(0), A64_R(1));
>> +
>> +       /* End of Fast Path, skip slow path */
>> +       emit_b(ctx, 4);
>> +
Followed by emit_b() above there is an emit_call(). It invokes 
emit_mov_imm() which could possibly generate different number of movk 
instructions depending on the address of the __rte_pktmbuf_read. So, 
emit_b(ctx, 4), may not  necessarily land at the intended location 
because there could be more than 4 instructions emitted by emit_call.
>> +       /* slow path, call __rte_pktmbuf_read */
>> +       emit_call(ctx, tmp1, __rte_pktmbuf_read);
>> +       /* check return value of __rte_pktmbuf_read */
>> +       emit_return_zero_if_src_zero(ctx, 1, A64_R(0));
>> +
>> +       /* A64_R(0) points to the data, load 1/2/4 bytes into r0*/
>> +       emit_ldr(ctx, opsz, r0, A64_R(0), A64_ZR);
>> +       if (sz != sizeof(uint8_t))
>> +               emit_be(ctx, r0, sz * CHAR_BIT);
>> +}
>> +
>>   

--wathsala