Re: [PATCH v2 bpf-next 0/4] tracing/probe: Add PERF_EVENT_IOC_QUERY_PROBE

["Daniel Xu" <dxu@dxuuu.xyz>]

On Fri, Aug 9, 2019, at 2:47 PM, Daniel Xu wrote:
> It's useful to know [uk]probe's nmissed and nhit stats. For example with
> tracing tools, it's important to know when events may have been lost.
> debugfs currently exposes a control file to get this information, but
> it is not compatible with probes registered with the perf API.
> 
> While bpf programs may be able to manually count nhit, there is no way
> to gather nmissed. In other words, it is currently not possible to
> retrieve information about FD-based probes.
> 
> This patch adds a new ioctl that lets users query nmissed (as well as
> nhit for completeness). We currently only add support for [uk]probes
> but leave the possibility open for other probes like tracepoint.
> 
> v1 -> v2:
> - More descriptive cover letter
> - Make API more generic and support uprobes as well
> - Use casters/getters for libbpf instead of single getter
> - Fix typos
> - Remove size field from ioctl struct
> - Split out libbpf.h sync to tools dir to separate commit
> 
> Daniel Xu (4):
>   tracing/probe: Add PERF_EVENT_IOC_QUERY_PROBE ioctl
>   libbpf: Add helpers to extract perf fd from bpf_link
>   tracing/probe: Sync perf_event.h to tools
>   tracing/probe: Add self test for PERF_EVENT_IOC_QUERY_PROBE
> 
>  include/linux/trace_events.h                  |  12 +++
>  include/uapi/linux/perf_event.h               |  19 ++++
>  kernel/events/core.c                          |  20 ++++
>  kernel/trace/trace_kprobe.c                   |  23 ++++
>  kernel/trace/trace_uprobe.c                   |  23 ++++
>  tools/include/uapi/linux/perf_event.h         |  19 ++++
>  tools/lib/bpf/libbpf.c                        |  19 ++++
>  tools/lib/bpf/libbpf.h                        |   8 ++
>  tools/lib/bpf/libbpf.map                      |   6 ++
>  .../selftests/bpf/prog_tests/attach_probe.c   | 102 ++++++++++++++++++
>  10 files changed, 251 insertions(+)
> 
> -- 
> 2.20.1
> 
>

CC PeterZ, whose email I misspelled. Apologies.

Daniel