[PATCH 3.19.y-ckt 53/56] perf/x86/intel: Fix PEBS data source interpretation on Nehalem/Westmere

[Kamal Mostafa]

3.19.8-ckt19 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

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

commit e17dc65328057c00db7e1bfea249c8771a78b30b upstream.

Jiri reported some time ago that some entries in the PEBS data source table
in perf do not agree with the SDM. We investigated and the bits
changed for Sandy Bridge, but the SDM was not updated.

perf already implements the bits correctly for Sandy Bridge
and later. This patch patches it up for Nehalem and Westmere.

Signed-off-by: Andi Kleen <ak at linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz at infradead.org>
Cc: Linus Torvalds <torvalds at linux-foundation.org>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: jolsa at kernel.org
Link: http://lkml.kernel.org/r/1456871124-15985-1-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo at kernel.org>
[ luis: backported to 3.16:
  - file rename:
    arch/x86/events/intel/core.c -> arch/x86/kernel/cpu/perf_event_intel.c
    arch/x86/events/intel/ds.c -> arch/x86/kernel/cpu/perf_event_intel_ds.c
    arch/x86/events/perf_event.h -> arch/x86/kernel/cpu/perf_event.h ]
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>

Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 arch/x86/kernel/cpu/perf_event.h          |  2 ++
 arch/x86/kernel/cpu/perf_event_intel.c    |  2 ++
 arch/x86/kernel/cpu/perf_event_intel_ds.c | 11 ++++++++++-
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5959a0c..f2d3dfc 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -746,6 +746,8 @@ void intel_pmu_lbr_init_atom(void);
 
 void intel_pmu_lbr_init_snb(void);
 
+void intel_pmu_pebs_data_source_nhm(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 int p4_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 498b6d9..bd0ec1a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2410,6 +2410,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		x86_add_quirk(intel_nehalem_quirk);
 
 		pr_cont("Nehalem events, ");
@@ -2472,6 +2473,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		pr_cont("Westmere events, ");
 		break;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ae3accf..4b4bd1b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -51,7 +51,8 @@ union intel_x86_pebs_dse {
 #define OP_LH (P(OP, LOAD) | P(LVL, HIT))
 #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
 
-static const u64 pebs_data_source[] = {
+/* Version for Sandy Bridge and later */
+static u64 pebs_data_source[] = {
 	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
 	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
 	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */
@@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = {
 	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
 };
 
+/* Patch up minor differences in the bits */
+void __init intel_pmu_pebs_data_source_nhm(void)
+{
+	pebs_data_source[0x05] = OP_LH | P(LVL, L3)  | P(SNOOP, HIT);
+	pebs_data_source[0x06] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+	pebs_data_source[0x07] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
-- 
2.7.4