Re: [PATCH RFC net-next 11/14] tracing: allow eBPF programs to be attached to events

On 06/28/2014 02:06 AM, Alexei Starovoitov wrote:

User interface:
cat bpf_123 > /sys/kernel/debug/tracing/__event__/filter

where 123 is an id of the eBPF program priorly loaded.
__event__ is static tracepoint event.
(kprobe events will be supported in the future patches)

eBPF programs can call in-kernel helper functions to:
- lookup/update/delete elements in maps
- memcmp
- trace_printk
- load_pointer
- dump_stack

Are there plans to let eBPF replace the generic event
filtering framework in tracing?

Signed-off-by: Alexei Starovoitov <ast-uqk4Ao+rVK5Wk0Htik3J/w@public.gmane.org>
---
  include/linux/ftrace_event.h       |    5 +
  include/trace/bpf_trace.h          |   29 +++++
  include/trace/ftrace.h             |   10 ++
  include/uapi/linux/bpf.h           |    5 +
  kernel/trace/Kconfig               |    1 +
  kernel/trace/Makefile              |    1 +
  kernel/trace/bpf_trace.c           |  217 ++++++++++++++++++++++++++++++++++++
  kernel/trace/trace.h               |    3 +
  kernel/trace/trace_events.c        |    7 ++
  kernel/trace/trace_events_filter.c |   72 +++++++++++-
  10 files changed, 349 insertions(+), 1 deletion(-)
  create mode 100644 include/trace/bpf_trace.h
  create mode 100644 kernel/trace/bpf_trace.c