perf/x86: Make Intel KNC use full 40-bit width of counters

Early versions of Intel KNC chips have a bug where bits above 32
were not properly set.  We worked around this by only using the
bottom 32 bits (out of 40 that should be available).

It turns out this workaround breaks overflow handling.

The buggy silicon will in theory never be used in production
systems, so remove this workaround so we get proper overflow
support.

Signed-off-by: Vince Weaver <vincent.weaver@maine.edu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: eranian@gmail.com
Cc: Meadows Lawrence F <lawrence.f.meadows@intel.com>
Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1210171302140.23243@vincent-weaver-1.um.maine.edu
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Vince Weaver 2012-10-17 13:03:21 -04:00 committed by Ingo Molnar
parent 032c3851f5
commit ae5ba47a99
1 changed files with 3 additions and 4 deletions

View File

@ -226,12 +226,11 @@ static __initconst struct x86_pmu knc_pmu = {
.event_map = knc_pmu_event_map,
.max_events = ARRAY_SIZE(knc_perfmon_event_map),
.apic = 1,
.max_period = (1ULL << 31) - 1,
.max_period = (1ULL << 39) - 1,
.version = 0,
.num_counters = 2,
/* in theory 40 bits, early silicon is buggy though */
.cntval_bits = 32,
.cntval_mask = (1ULL << 32) - 1,
.cntval_bits = 40,
.cntval_mask = (1ULL << 40) - 1,
.get_event_constraints = x86_get_event_constraints,
.event_constraints = knc_event_constraints,
.format_attrs = intel_knc_formats_attr,