[PATCH V4 05/23] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them

[kan . liang]

From: Andi Kleen <a...@linux.intel.com>

With adaptive PEBS the CPU can directly supply the LBR information,
so we don't need to read it again. But the LBRs still need to be
enabled. Add a special count to the cpuc that distinguishes these
two cases, and avoid reading the LBRs unnecessarily when PEBS is
active.

Signed-off-by: Andi Kleen <a...@linux.intel.com>
Signed-off-by: Kan Liang <kan.li...@linux.intel.com>
---

No changes since V3.

 arch/x86/events/intel/lbr.c  | 13 ++++++++++++-
 arch/x86/events/perf_event.h |  1 +
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 07b7175fc378..6f814a27416b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event)
         * be 'new'. Conversely, a new event can get installed through the
         * context switch path for the first time.
         */
+       if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+               cpuc->lbr_pebs_users++;
        perf_sched_cb_inc(event->ctx->pmu);
        if (!cpuc->lbr_users++ && !event->total_time_running)
                intel_pmu_lbr_reset();
@@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event)
                task_ctx->lbr_callstack_users--;
        }
 
+       if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+               cpuc->lbr_pebs_users--;
        cpuc->lbr_users--;
        WARN_ON_ONCE(cpuc->lbr_users < 0);
+       WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
        perf_sched_cb_dec(event->ctx->pmu);
 }
 
@@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void)
 {
        struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-       if (!cpuc->lbr_users)
+       /*
+        * Don't read when all LBRs users are using adaptive PEBS.
+        *
+        * This could be smarter and actually check the event,
+        * but this simple approach seems to work for now.
+        */
+       if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
                return;
 
        if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 4ca20078ca92..f2351e47de3d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -216,6 +216,7 @@ struct cpu_hw_events {
         * Intel LBR bits
         */
        int                             lbr_users;
+       int                             lbr_pebs_users;
        struct perf_branch_stack        lbr_stack;
        struct perf_branch_entry        lbr_entries[MAX_LBR_ENTRIES];
        struct er_account               *lbr_sel;
-- 
2.17.1