perf/x86/intel: Fix PEBS data source interpretation on Nehalem/Westmere

commit e17dc653 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@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1456871124-15985-1-git-send-email-andi@firstfloor.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/kernel/cpu/perf_event.h

@@ -908,6 +908,8 @@ void intel_pmu_lbr_init_hsw(void);
 
 void intel_pmu_lbr_init_skl(void);
 
+void intel_pmu_pebs_data_source_nhm(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);

arch/x86/kernel/cpu/perf_event_intel.c

@@ -3336,6 +3336,7 @@ __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, ");
@@ -3398,6 +3399,7 @@ __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;
 

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;