[PATCH V4 06/23] perf/x86: Support constraint ranges

From: kan . liang
Date: Tue Mar 26 2019 - 12:13:10 EST


From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Icelake extended the general counters to 8, even when SMT is enabled.
However only a (large) subset of the events can be used on all 8
counters.

The events that can or cannot be used on all counters are organized
in ranges.

A lot of scheduler constraints are required to handle all this.

To avoid blowing up the tables add event code ranges to the constraint
tables, and a new inline function to match them.

Originally-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
---

No changes since V3.

arch/x86/events/intel/core.c | 2 +-
arch/x86/events/intel/ds.c | 2 +-
arch/x86/events/perf_event.h | 42 ++++++++++++++++++++++++++++++------
3 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 620beae035a0..d5d796e114a1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2688,7 +2688,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,

if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1a076beb5fb1..3ee1a0198c13 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -858,7 +858,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)

if (x86_pmu.pebs_constraints) {
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f2351e47de3d..a502e9bb02bb 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,11 +49,12 @@ struct event_constraint {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
- u64 code;
- u64 cmask;
- int weight;
- int overlap;
- int flags;
+ u64 code;
+ u64 cmask;
+ int weight;
+ int overlap;
+ int flags;
+ unsigned int size;
};
/*
* struct hw_perf_event.flags flags
@@ -71,6 +72,10 @@ struct event_constraint {
#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */

+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+ return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}

struct amd_nb {
int nb_id; /* NorthBridge id */
@@ -263,18 +268,29 @@ struct cpu_hw_events {
void *kfree_on_online[X86_PERF_KFREE_MAX];
};

-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \
{ .idxmsk64 = (n) }, \
.code = (c), \
+ .size = (e) - (c), \
.cmask = (m), \
.weight = (w), \
.overlap = (o), \
.flags = f, \
}

+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+ __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)

+/*
+ * Only works for Intel events, which has 'small' event codes.
+ * Need to fix the rang compare for 'big' event codes, e.g AMD64_EVENTSEL_EVENT
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+ __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
@@ -309,6 +325,12 @@ struct cpu_hw_events {
#define INTEL_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)

+/*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
/*
* Constraint on the Event code + UMask + fixed-mask
*
@@ -356,6 +378,9 @@ struct cpu_hw_events {
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)

+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
@@ -372,6 +397,11 @@ struct cpu_hw_events {
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)

+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+ __EVENT_CONSTRAINT_RANGE(code, end, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
--
2.17.1