lkml.org 
[lkml]   [2014]   [Jun]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 1/2] perf/x86: update Haswell PEBS event constraints
On Mon, Jun 23, 2014 at 10:06:43AM +0200, Stephane Eranian wrote:
> > @@ -1736,8 +1742,17 @@ static int intel_pmu_hw_config(struct perf_event *event)
> > if (ret)
> > return ret;
> >
> > - if (event->attr.precise_ip && x86_pmu.pebs_aliases)
> > - x86_pmu.pebs_aliases(event);
> > + if (event->attr.precise_ip) {
> > + if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == 0x0000)
> > + return -EINVAL;
> > +
> > + if ((event->attr.config & ARCH_PERFMON_STRICT_PEBS) &&
> > + (x86_pmu.attr_strict_pebs || !capable(CAP_SYS_ADMIN)))
> > + return -EINVAL;
> > +
> I don't think filters work with any PEBS events. The event captured
> does not qualify
> for any of the filters (root or non-root).

Filters? You mean the inv,cmask etc? Well, we have the Intel provided
'cycle' events that use them, so exposing them makes sense and allows
such experimentation when we need another such alias.

> > + if (x86_pmu.pebs_aliases)
> > + x86_pmu.pebs_aliases(event);
> > + }
> >
> > if (intel_pmu_needs_lbr_smpl(event)) {
> > ret = intel_pmu_setup_lbr_filter(event);
> > diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> > index ae96cfa5eddd..36b1f2afa61c 100644
> > --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
> > +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> > @@ -540,6 +540,7 @@ struct event_constraint intel_core2_pebs_event_constraints[] = {
> > INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
> > INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
> > INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
> > + INTEL_UEVENT_CONSTRAINT(0x0000, 0x1), /* generic PEBS mask */
> > EVENT_CONSTRAINT_END
> > };
> >
> You probably need to explain that 0x0000 MUST be the last event in
> each table, i.e., catch all
> event.

Yeah, probably ;-) Alternatively we could make PEBS_CONSTRAINT_END that
includes it or so.

Like said (possibly in another email) this patch was a very quick draft
and I don't think I've even ran it, it was on the todo pile..


\
 
 \ /
  Last update: 2014-06-23 14:21    [W:0.058 / U:0.076 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site