From 1da53e023029c067ba1277a33038c65d6e4c99b3 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 18 Jan 2010 10:58:01 +0200 Subject: perf_events, x86: Improve x86 event scheduling This patch improves event scheduling by maximizing the use of PMU registers regardless of the order in which events are created in a group. The algorithm takes into account the list of counter constraints for each event. It assigns events to counters from the most constrained, i.e., works on only one counter, to the least constrained, i.e., works on any counter. Intel Fixed counter events and the BTS special event are also handled via this algorithm which is designed to be fairly generic. The patch also updates the validation of an event to use the scheduling algorithm. This will cause early failure in perf_event_open(). The 2nd version of this patch follows the model used by PPC, by running the scheduling algorithm and the actual assignment separately. Actual assignment takes place in hw_perf_enable() whereas scheduling is implemented in hw_perf_group_sched_in() and x86_pmu_enable(). Signed-off-by: Stephane Eranian [ fixup whitespace and style nits as well as adding is_x86_event() ] Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: <4b5430c6.0f975e0a.1bf9.ffff85fe@mx.google.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/perf_event.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8d9f8548a87..dbc082685d5 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -26,7 +26,14 @@ /* * Includes eventsel and unit mask as well: */ -#define ARCH_PERFMON_EVENT_MASK 0xffff + + +#define INTEL_ARCH_EVTSEL_MASK 0x000000FFULL +#define INTEL_ARCH_UNIT_MASK 0x0000FF00ULL +#define INTEL_ARCH_EDGE_MASK 0x00040000ULL +#define INTEL_ARCH_INV_MASK 0x00800000ULL +#define INTEL_ARCH_CNT_MASK 0xFF000000ULL +#define INTEL_ARCH_EVENT_MASK (INTEL_ARCH_UNIT_MASK|INTEL_ARCH_EVTSEL_MASK) /* * filter mask to validate fixed counter events. @@ -37,7 +44,12 @@ * The other filters are supported by fixed counters. * The any-thread option is supported starting with v3. */ -#define ARCH_PERFMON_EVENT_FILTER_MASK 0xff840000 +#define INTEL_ARCH_FIXED_MASK \ + (INTEL_ARCH_CNT_MASK| \ + INTEL_ARCH_INV_MASK| \ + INTEL_ARCH_EDGE_MASK|\ + INTEL_ARCH_UNIT_MASK|\ + INTEL_ARCH_EVENT_MASK) #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) -- cgit v1.2.3