[tip: perf/core] perf/x86/amd/uncore: Add PerfMonV2 DF event format

[tip-bot2 for Sandipan Das]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     c390241a93260b377c84ad9e7cd5242adf667aac
Gitweb:        https://git.kernel.org/tip/c390241a93260b377c84ad9e7cd5242adf667aac
Author:        Sandipan Das <sandipan.das@xxxxxxx>
AuthorDate:    Thu, 19 May 2022 15:33:33 +05:30
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Mon, 13 Jun 2022 10:15:14 +02:00

perf/x86/amd/uncore: Add PerfMonV2 DF event format

If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, use bits 0-7, 32-37 as EventSelect and bits
8-15, 24-27 as UnitMask for Data Fabric (DF) events.

Signed-off-by: Sandipan Das <sandipan.das@xxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/ffc24d5a3375b1d6e457d88e83241114de5c1942.1652954372.git.sandipan.das@xxxxxxx
---
 arch/x86/events/amd/uncore.c      | 24 +++++++++++++++++-------
 arch/x86/include/asm/perf_event.h | 13 +++++++++++++
 2 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 233dd40..ff4238e 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -209,10 +209,14 @@ static int amd_uncore_event_init(struct perf_event *event)
 {
 	struct amd_uncore *uncore;
 	struct hw_perf_event *hwc = &event->hw;
+	u64 event_mask = AMD64_RAW_EVENT_MASK_NB;
 
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
+	if (pmu_version >= 2 && is_nb_event(event))
+		event_mask = AMD64_PERFMON_V2_RAW_EVENT_MASK_NB;
+
 	/*
 	 * NB and Last level cache counters (MSRs) are shared across all cores
 	 * that share the same NB / Last level cache.  On family 16h and below,
@@ -221,7 +225,7 @@ static int amd_uncore_event_init(struct perf_event *event)
 	 * out. So we do not support sampling and per-thread events via
 	 * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
 	 */
-	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
+	hwc->config = event->attr.config & event_mask;
 	hwc->idx = -1;
 
 	if (event->cpu < 0)
@@ -300,8 +304,10 @@ static struct device_attribute format_attr_##_var =			\
 
 DEFINE_UNCORE_FORMAT_ATTR(event12,	event,		"config:0-7,32-35");
 DEFINE_UNCORE_FORMAT_ATTR(event14,	event,		"config:0-7,32-35,59-60"); /* F17h+ DF */
+DEFINE_UNCORE_FORMAT_ATTR(event14v2,	event,		"config:0-7,32-37");	   /* PerfMonV2 DF */
 DEFINE_UNCORE_FORMAT_ATTR(event8,	event,		"config:0-7");		   /* F17h+ L3 */
-DEFINE_UNCORE_FORMAT_ATTR(umask,	umask,		"config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(umask8,	umask,		"config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(umask12,	umask,		"config:8-15,24-27");	   /* PerfMonV2 DF */
 DEFINE_UNCORE_FORMAT_ATTR(coreid,	coreid,		"config:42-44");	   /* F19h L3 */
 DEFINE_UNCORE_FORMAT_ATTR(slicemask,	slicemask,	"config:48-51");	   /* F17h L3 */
 DEFINE_UNCORE_FORMAT_ATTR(threadmask8,	threadmask,	"config:56-63");	   /* F17h L3 */
@@ -313,14 +319,14 @@ DEFINE_UNCORE_FORMAT_ATTR(sliceid,	sliceid,	"config:48-50");	   /* F19h L3 */
 /* Common DF and NB attributes */
 static struct attribute *amd_uncore_df_format_attr[] = {
 	&format_attr_event12.attr,	/* event */
-	&format_attr_umask.attr,	/* umask */
+	&format_attr_umask8.attr,	/* umask */
 	NULL,
 };
 
 /* Common L2 and L3 attributes */
 static struct attribute *amd_uncore_l3_format_attr[] = {
 	&format_attr_event12.attr,	/* event */
-	&format_attr_umask.attr,	/* umask */
+	&format_attr_umask8.attr,	/* umask */
 	NULL,				/* threadmask */
 	NULL,
 };
@@ -659,8 +665,12 @@ static int __init amd_uncore_init(void)
 	}
 
 	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
-		if (boot_cpu_data.x86 >= 0x17)
+		if (pmu_version >= 2) {
+			*df_attr++ = &format_attr_event14v2.attr;
+			*df_attr++ = &format_attr_umask12.attr;
+		} else if (boot_cpu_data.x86 >= 0x17) {
 			*df_attr = &format_attr_event14.attr;
+		}
 
 		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
 		if (!amd_uncore_nb) {
@@ -686,11 +696,11 @@ static int __init amd_uncore_init(void)
 	if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) {
 		if (boot_cpu_data.x86 >= 0x19) {
 			*l3_attr++ = &format_attr_event8.attr;
-			*l3_attr++ = &format_attr_umask.attr;
+			*l3_attr++ = &format_attr_umask8.attr;
 			*l3_attr++ = &format_attr_threadmask2.attr;
 		} else if (boot_cpu_data.x86 >= 0x17) {
 			*l3_attr++ = &format_attr_event8.attr;
-			*l3_attr++ = &format_attr_umask.attr;
+			*l3_attr++ = &format_attr_umask8.attr;
 			*l3_attr++ = &format_attr_threadmask8.attr;
 		}
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index af157aa..34348ae 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -89,6 +89,19 @@
 #define AMD64_RAW_EVENT_MASK_NB		\
 	(AMD64_EVENTSEL_EVENT        |  \
 	 ARCH_PERFMON_EVENTSEL_UMASK)
+
+#define AMD64_PERFMON_V2_EVENTSEL_EVENT_NB	\
+	(AMD64_EVENTSEL_EVENT	|		\
+	 GENMASK_ULL(37, 36))
+
+#define AMD64_PERFMON_V2_EVENTSEL_UMASK_NB	\
+	(ARCH_PERFMON_EVENTSEL_UMASK	|	\
+	 GENMASK_ULL(27, 24))
+
+#define AMD64_PERFMON_V2_RAW_EVENT_MASK_NB		\
+	(AMD64_PERFMON_V2_EVENTSEL_EVENT_NB	|	\
+	 AMD64_PERFMON_V2_EVENTSEL_UMASK_NB)
+
 #define AMD64_NUM_COUNTERS				4
 #define AMD64_NUM_COUNTERS_CORE				6
 #define AMD64_NUM_COUNTERS_NB				4