[PATCH v2] perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events

[PATCH v2] perf/x86/amd/uncore: Set ThreadMask and SliceMask for L3 Cache perf events

[Natarajan, Janakarajan]

In Family 17h, some L3 Cache Performance events require the ThreadMask
and SliceMask to be set. For other events, these fields do not affect
the count either way.

Set ThreadMask and SliceMask to 0xFF and 0xF respectively.

Signed-off-by: Janakarajan Natarajan <Janakarajan.Natarajan@amd.com>
---
v2: Changed L3 Slice and L3 Thread mask to use unsigned long long instead
    of unsigned long. Fixes warning on i386 builds.

 arch/x86/events/amd/uncore.c      | 10 ++++++++++
 arch/x86/include/asm/perf_event.h |  8 ++++++++
 2 files changed, 18 insertions(+)

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 981ba5e..8671de1 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -36,6 +36,7 @@
 
 static int num_counters_llc;
 static int num_counters_nb;
+static bool l3_mask;
 
 static HLIST_HEAD(uncore_unused_list);
 
@@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event)
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
+	/*
+	 * SliceMask and ThreadMask need to be set for certain L3 events in
+	 * Family 17h. For other events, the two fields do not affect the count.
+	 */
+	if (l3_mask)
+		hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -525,6 +533,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l3";
 		format_attr_event_df.show = &event_show_df;
 		format_attr_event_l3.show = &event_show_l3;
+		l3_mask			  = true;
 	} else {
 		num_counters_nb		  = NUM_COUNTERS_NB;
 		num_counters_llc	  = NUM_COUNTERS_L2;
@@ -532,6 +541,7 @@ static int __init amd_uncore_init(void)
 		amd_llc_pmu.name	  = "amd_l2";
 		format_attr_event_df	  = format_attr_event;
 		format_attr_event_l3	  = format_attr_event;
+		l3_mask			  = false;
 	}
 
 	amd_nb_pmu.attr_groups	= amd_uncore_attr_groups_df;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 12f5408..78241b7 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -46,6 +46,14 @@
 #define INTEL_ARCH_EVENT_MASK	\
 	(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
 
+#define AMD64_L3_SLICE_SHIFT				48
+#define AMD64_L3_SLICE_MASK				\
+	((0xFULL) << AMD64_L3_SLICE_SHIFT)
+
+#define AMD64_L3_THREAD_SHIFT				56
+#define AMD64_L3_THREAD_MASK				\
+	((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+
 #define X86_RAW_EVENT_MASK		\
 	(ARCH_PERFMON_EVENTSEL_EVENT |	\
 	 ARCH_PERFMON_EVENTSEL_UMASK |	\
-- 
2.7.4