Messages in this thread | | | Subject | Re: [PATCH v2 -tip] perf: x86, add SandyBridge support | From | Peter Zijlstra <> | Date | Mon, 28 Feb 2011 15:24:47 +0100 |
| |
On Mon, 2011-02-28 at 22:21 +0800, Lin Ming wrote: > > > #define INTEL_EVENT_CONSTRAINT(c, n) \ > > > EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) > > > +#define INTEL_EVENT_CONSTRAINT2(c, n) \ > > > + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) > > > > That's a particularly bad name, how about something like > > > > INTEL_UEVENT_CONSTRAINT or somesuch. > > OK. > > But any case it's duplicated with PEBS_EVENT_CONSTRAINT. > > #define PEBS_EVENT_CONSTRAINT(c, n) \ > EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
Ah, indeed, so maybe we can remove PEBS_EVENT_CONSTRAINT and use regular INTEL_*_CONSTRAINTS there, that could also help for PEBS events where all umasks are allowed (not sure there are any such things but the SNB PEBS list was quite large).
| |