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

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@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.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 2ac94333bcfd73cf66c0e65ce945d4263ca463dc..82833ed3c1d2bbb57a6d684499b7de74b29502c1 100644 (file)
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -688,6 +688,8 @@ 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 d2080aa4322ab7d182f42896e74cd2d5bcbb4266..0c8fc76b2d2c5971ddd9c5c2a5b9aa1c9435f981 100644 (file)
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2344,6 +2344,7 @@ __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, ");
@@ -2405,6 +2406,7 @@ __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 8ad56b3b016943e41ace04d7a7ab3766698c799f..1cbc27963f68a84a7a9d94ad0352ba9a5c5eb6dc 100644 (file)
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -50,7 +50,8 @@ 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 */
@@ -69,6 +70,14 @@ 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;