perf events: Add stalled cycles generic event - PERF_COUNT_HW_STALLED_CYCLES

The new PERF_COUNT_HW_STALLED_CYCLES event tries to approximate
cycles the CPU does nothing useful, because it is stalled on a
cache-miss or some other condition.

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/n/tip-fue11vymwqsoo5to72jxxjyl@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 6 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 9ae4a2aa7398..efa2704c9dfd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1413,6 +1413,9 @@ static __init int intel_pmu_init(void)
                 x86_pmu.enable_all = intel_pmu_nhm_enable_all;
                 x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
+                /* Install the stalled-cycles event: 0xff: All reasons, 0xa2: Resource stalls */
+                intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES] = 0xffa2;
+
                 if (ebx & 0x40) {
                         /*
                          * Erratum AAJ80 detected, we work it around by using
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ee9f1e782800..ac636dd20a0c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -52,6 +52,7 @@ enum perf_hw_id {
         PERF_COUNT_HW_BRANCH_INSTRUCTIONS       = 4,
         PERF_COUNT_HW_BRANCH_MISSES             = 5,
         PERF_COUNT_HW_BUS_CYCLES                = 6,
+        PERF_COUNT_HW_STALLED_CYCLES            = 7,
 
         PERF_COUNT_HW_MAX,                      /* non-ABI */
 };
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 952b4ae3d954..1869e4c646db 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -38,6 +38,7 @@ static struct event_symbol event_symbols[] = {
   { CHW(BRANCH_INSTRUCTIONS),   "branch-instructions",  "branches"      },
   { CHW(BRANCH_MISSES),         "branch-misses",        ""              },
   { CHW(BUS_CYCLES),            "bus-cycles",           ""              },
+  { CHW(STALLED_CYCLES),        "stalled-cycles",       ""              },
 
   { CSW(CPU_CLOCK),             "cpu-clock",            ""              },
   { CSW(TASK_CLOCK),            "task-clock",           ""              },
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index f5e38451fdc5..406f613ee619 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -798,6 +798,7 @@ static struct {
         { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
         { "COUNT_HW_BRANCH_MISSES",       PERF_COUNT_HW_BRANCH_MISSES },
         { "COUNT_HW_BUS_CYCLES",          PERF_COUNT_HW_BUS_CYCLES },
+        { "COUNT_HW_STALLED_CYCLES",      PERF_COUNT_HW_STALLED_CYCLES },
         { "COUNT_HW_CACHE_L1D",           PERF_COUNT_HW_CACHE_L1D },
         { "COUNT_HW_CACHE_L1I",           PERF_COUNT_HW_CACHE_L1I },
         { "COUNT_HW_CACHE_LL",            PERF_COUNT_HW_CACHE_LL },