Re: [PATCH bpf] bpf: fix nested bpf tracepoints with per-cpu data

2019-06-07 Thread Steven Rostedt
On Thu, 6 Jun 2019 19:59:18 -0700 Andrii Nakryiko wrote: > On Thu, Jun 6, 2019 at 1:17 PM Matt Mullins wrote: > > > > BPF_PROG_TYPE_RAW_TRACEPOINTs can be executed nested on the same CPU, as > > they do not increment bpf_prog_active while executing. > > > > This enables three levels of nesting,

Re: [PATCH bpf] bpf: fix nested bpf tracepoints with per-cpu data

2019-06-06 Thread Andrii Nakryiko
On Thu, Jun 6, 2019 at 1:17 PM Matt Mullins wrote: > > BPF_PROG_TYPE_RAW_TRACEPOINTs can be executed nested on the same CPU, as > they do not increment bpf_prog_active while executing. > > This enables three levels of nesting, to support > - a kprobe or raw tp or perf event, > - another one

Re: [PATCH bpf] bpf: fix nested bpf tracepoints with per-cpu data

2019-06-06 Thread Matt Mullins
On Thu, 2019-06-06 at 15:13 -0700, Jakub Kicinski wrote: > On Thu, 6 Jun 2019 11:54:27 -0700, Matt Mullins wrote: > > BPF_PROG_TYPE_RAW_TRACEPOINTs can be executed nested on the same CPU, as > > they do not increment bpf_prog_active while executing. > > > > This enables three levels of nesting,

Re: [PATCH bpf] bpf: fix nested bpf tracepoints with per-cpu data

2019-06-06 Thread Jakub Kicinski
On Thu, 6 Jun 2019 11:54:27 -0700, Matt Mullins wrote: > BPF_PROG_TYPE_RAW_TRACEPOINTs can be executed nested on the same CPU, as > they do not increment bpf_prog_active while executing. > > This enables three levels of nesting, to support > - a kprobe or raw tp or perf event, > - another one

[PATCH bpf] bpf: fix nested bpf tracepoints with per-cpu data

2019-06-06 Thread Matt Mullins
BPF_PROG_TYPE_RAW_TRACEPOINTs can be executed nested on the same CPU, as they do not increment bpf_prog_active while executing. This enables three levels of nesting, to support - a kprobe or raw tp or perf event, - another one of the above that irq context happens to call, and - another one