Namhyung Kim wrote:
> The helper is for BPF programs attached to perf_event in order to read
> event-specific raw data. I followed the convention of the
> bpf_read_branch_records() helper so that it can tell the size of
> record using BPF_F_GET_RAW_RECORD flag.
>
> The use case is to filter perf event samples based on the HW provided
> data which have more detailed information about the sample.
>
> Note that it only reads the first fragment of the raw record. But it
> seems mostly ok since all the existing PMU raw data have only single
> fragment and the multi-fragment records are only for BPF output attached
> to sockets. So unless it's used with such an extreme case, it'd work
> for most of tracing use cases.
>
> Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
> ---
Acked-by: John Fastabend <john.fastabend@xxxxxxxxx>
> I don't know how to test this. As the raw data is available on some
> hardware PMU only (e.g. AMD IBS). I tried a tracepoint event but it was
> rejected by the verifier. Actually it needs a bpf_perf_event_data
> context so that's not an option IIUC.
not a pmu expert but also no good ideas on my side.
...
>
> +BPF_CALL_4(bpf_read_raw_record, struct bpf_perf_event_data_kern *, ctx,
> + void *, buf, u32, size, u64, flags)
> +{
> + struct perf_raw_record *raw = ctx->data->raw;
> + struct perf_raw_frag *frag;
> + u32 to_copy;
> +
> + if (unlikely(flags & ~BPF_F_GET_RAW_RECORD_SIZE))
> + return -EINVAL;
> +
> + if (unlikely(!raw))
> + return -ENOENT;
> +
> + if (flags & BPF_F_GET_RAW_RECORD_SIZE)
> + return raw->size;
> +
> + if (!buf || (size % sizeof(u32) != 0))
> + return -EINVAL;
> +
> + frag = &raw->frag;
> + WARN_ON_ONCE(!perf_raw_frag_last(frag));
> +
> + to_copy = min_t(u32, frag->size, size);
> + memcpy(buf, frag->data, to_copy);
> +
> + return to_copy;
> +}
> +
> +static const struct bpf_func_proto bpf_read_raw_record_proto = {
> + .func = bpf_read_raw_record,
> + .gpl_only = true,
> + .ret_type = RET_INTEGER,
> + .arg1_type = ARG_PTR_TO_CTX,
> + .arg2_type = ARG_PTR_TO_MEM_OR_NULL,
> + .arg3_type = ARG_CONST_SIZE_OR_ZERO,
> + .arg4_type = ARG_ANYTHING,
> +};
Patch lgtm but curious why allow the ARG_PTR_TO_MEM_OR_NULL from API
side instead of just ARG_PTR_TO_MEM? Maybe, just to match the
existing perf_event_read()? I acked it as I think matching existing
API is likely good enough reason.
> +
> static const struct bpf_func_proto *
> pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> {
> @@ -1548,6 +1587,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> return &bpf_read_branch_records_proto;
> case BPF_FUNC_get_attach_cookie:
> return &bpf_get_attach_cookie_proto_pe;
> + case BPF_FUNC_read_raw_record:
> + return &bpf_read_raw_record_proto;
> default:
> return bpf_tracing_func_proto(func_id, prog);
> }
> --
> 2.37.2.609.g9ff673ca1a-goog
>
