Re: [PATCH 1/2] perf-events: Add support for supplementary eventregisters v2

From: Peter Zijlstra
Date: Fri Nov 12 2010 - 12:23:50 EST


On Fri, 2010-11-12 at 17:55 +0100, Andi Kleen wrote:
> static struct event_constraint *
> +intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
> +{
> + struct hw_perf_event *hwc = &event->hw;
> + unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT;
> + struct event_constraint *c;
> + struct intel_percore *pc;
> +
> + if (!x86_pmu.percore_constraints)
> + return NULL;
> +
> + for (c = x86_pmu.percore_constraints; c->cmask; c++) {
> + if (e != c->code)
> + continue;
> +
> + c = NULL;
> +
> + /*
> + * Allocate resource per core.
> + * Currently only one such per core resource can be allocated.
> + */
> + pc = cpuc->per_core;
> + if (!pc)
> + break;
> + raw_spin_lock(&pc->lock);
> + if (pc->ref > 0) {
> + /* Allow identical settings */
> + if (hwc->config == pc->config &&
> + hwc->extra_reg == pc->extra_reg &&
> + hwc->extra_config == pc->extra_config) {

Hrmm,. this doesn't really scale right wrt multiple extra_regs.

You made the extra_regs thing fairly extensible, but the above doesn't
really work well if there's multiple extra regs (say OFFCORE and
LBR_CONFIG -- possibly even the two OFFCORE regs present on westmere).

It basically needs a per-core state for each extra_reg possible.

> + pc->ref++;
> + cpuc->percore_used = 1;
> + } else {
> + /* Deny due to conflict */
> + c = &emptyconstraint;
> + }
> + } else {
> + pc->config = hwc->config;
> + pc->extra_reg = hwc->extra_reg;
> + pc->extra_config = hwc->extra_config;
> + pc->ref = 1;
> + cpuc->percore_used = 1;
> + }
> + raw_spin_unlock(&pc->lock);
> + return c;
> + }
> +
> + return NULL;
> +}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/