[PATCH 6/9] x86, perf: Add Top Down events to Intel Core

[Andi Kleen <andi@firstfloor.org>]

From: Andi Kleen <ak@linux.intel.com>

Add declarations for the events needed for TopDown to the
Intel big core CPUs starting with Sandy Bridge. We need
to report different values if HyperThreading is on or off.

The only thing this patch does is to export some events
in sysfs.

TopDown level 1 uses a set of abstracted metrics which
are generic to out of order CPU cores (although some
CPUs may not implement all of them):

topdown-total-slots	  Available slots in the pipeline
topdown-slots-issued	  Slots issued into the pipeline
topdown-slots-retired	  Slots successfully retired
topdown-fetch-bubbles	  Pipeline gaps in the frontend
topdown-recovery-bubbles  Pipeline gaps during recovery
			  from misspeculation

These metrics then allow to compute four useful metrics:
FrontendBound, BackendBound, Retiring, BadSpeculation.

The formulas to compute the metrics are generic, they
only change based on the availability on the abstracted
input values.

The kernel declares the events supported by the current
CPU and perf stat then computes the formulas based on the
available metrics.

Some events need a divisor. To handle this I redefined
".scale" slightly to let a negative value mean divide by.

For HyperThreading the any bit is needed to get accurate
values when both threads are executing. This implies that
the events can only be collected as root or with
perf_event_paranoid=-1 for now.

Hyper Threading also requires averaging events from both
threads together (the CPU cannot measure them independently).
In perf stat this is done by using per core mode, and then
forcing a divisor of two to get the average. The
new .agg-per-core attribute is added to the events, which
then forces perf stat to enable --per-core.
When hyperthreading is disabled the attribute has the value 0.

The basic scheme is based on the following paper:
Yasin,
A Top Down Method for Performance analysis and Counter architecture
ISPASS14
(pdf available via google)

with some extensions to handle HyperThreading.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 82 ++++++++++++++++++++++++++++++++++
 1 file changed, 82 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a478e3c..65b58cb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -217,9 +217,70 @@ struct attribute *nhm_events_attrs[] = {
 	NULL,
 };
 
+/*
+ * TopDown events for Core.
+ *
+ * With Hyper Threading on, TopDown metrics are averaged between the
+ * threads of a core: (count_core0 + count_core1) / 2. The 2 is expressed
+ * as a scale parameter. We also tell perf to aggregate per core
+ * by setting the .agg-per-core attribute for the alias to 1.
+ *
+ * Some events need to be multiplied by the pipeline width (4), which
+ * is expressed as a negative scale. In HT we cancel the factor 4
+ * with the 2 dividend for the core average, so we use -2.
+ */
+
+EVENT_ATTR_STR_HT(topdown-total-slots, td_total_slots,
+	"event=0x3c,umask=0x0",			/* cpu_clk_unhalted.thread */
+	"event=0x3c,umask=0x0,any=1");		/* cpu_clk_unhalted.thread_any */
+EVENT_ATTR_STR_HT(topdown-total-slots.scale, td_total_slots_scale,
+	"-4", "-2");
+EVENT_ATTR_STR_HT(topdown-total-slots.agg-per-core, td_total_slots_pc,
+	"0", "1");
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued,
+	"event=0xe,umask=0x1");			/* uops_issued.any */
+EVENT_ATTR_STR_HT(topdown-slots-issued.agg-per-core, td_slots_issued_pc,
+	"0", "1");
+EVENT_ATTR_STR_HT(topdown-slots-issued.scale, td_slots_issued_scale,
+	"0", "2");
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired,
+	"event=0xc2,umask=0x2");		/* uops_retired.retire_slots */
+EVENT_ATTR_STR_HT(topdown-slots-retired.agg-per-core, td_slots_retired_pc,
+	"0", "1");
+EVENT_ATTR_STR_HT(topdown-slots-retired.scale, td_slots_retired_scale,
+	"0", "2");
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles,
+	"event=0x9c,umask=0x1");		/* idq_uops_not_delivered_core */
+EVENT_ATTR_STR_HT(topdown-fetch-bubbles.agg-per-core, td_fetch_bubbles_pc,
+	"0", "1");
+EVENT_ATTR_STR_HT(topdown-fetch-bubbles.scale, td_fetch_bubbles_scale,
+	"0", "2");
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles, td_recovery_bubbles,
+	"event=0xd,umask=0x3,cmask=1",		/* int_misc.recovery_cycles */
+	"event=0xd,umask=0x3,cmask=1,any=1");	/* int_misc.recovery_cycles_any */
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
+	"-4", "-2");
+EVENT_ATTR_STR_HT(topdown-recovery-bubbles.agg-per-core, td_recovery_bubbles_pc,
+	"0", "1");
+
 struct attribute *snb_events_attrs[] = {
 	EVENT_PTR(mem_ld_snb),
 	EVENT_PTR(mem_st_snb),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_issued_scale),
+	EVENT_PTR(td_slots_issued_pc),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_slots_retired_scale),
+	EVENT_PTR(td_slots_retired_pc),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_fetch_bubbles_scale),
+	EVENT_PTR(td_fetch_bubbles_pc),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_total_slots_pc),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
+	EVENT_PTR(td_recovery_bubbles_pc),
 	NULL,
 };
 
@@ -3177,6 +3238,21 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(cycles_ct),
 	EVENT_PTR(mem_ld_hsw),
 	EVENT_PTR(mem_st_hsw),
+	EVENT_PTR(td_slots_issued),
+	EVENT_PTR(td_slots_issued_scale),
+	EVENT_PTR(td_slots_issued_pc),
+	EVENT_PTR(td_slots_retired),
+	EVENT_PTR(td_slots_retired_scale),
+	EVENT_PTR(td_slots_retired_pc),
+	EVENT_PTR(td_fetch_bubbles),
+	EVENT_PTR(td_fetch_bubbles_scale),
+	EVENT_PTR(td_fetch_bubbles_pc),
+	EVENT_PTR(td_total_slots),
+	EVENT_PTR(td_total_slots_scale),
+	EVENT_PTR(td_total_slots_pc),
+	EVENT_PTR(td_recovery_bubbles),
+	EVENT_PTR(td_recovery_bubbles_scale),
+	EVENT_PTR(td_recovery_bubbles_pc),
 	NULL
 };
 
@@ -3494,6 +3570,12 @@ __init int intel_pmu_init(void)
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 		intel_pmu_lbr_init_skl();
 
+		/* INT_MISC.RECOVERY_CYCLES has umask 1 in Skylake */
+		event_attr_td_recovery_bubbles.event_str_noht =
+			"event=0xd,umask=0x1,cmask=1";
+		event_attr_td_recovery_bubbles.event_str_ht =
+			"event=0xd,umask=0x1,cmask=1,any=1";
+
 		x86_pmu.event_constraints = intel_skl_event_constraints;
 		x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_skl_extra_regs;
-- 
2.4.3