perf/x86/intel: Streamline LBR MSR handling in PMI

The perf PMI currently does unnecessary MSR accesses when
LBRs are enabled. We use LBR freezing, or when in callstack
mode force the LBRs to only filter on ring 3.

So there is no need to disable the LBRs explicitely in the
PMI handler.

Also we always unnecessarily rewrite LBR_SELECT in the LBR
handler, even though it can never change.

 5)               |  /* write_msr: MSR_LBR_SELECT(1c8), value 0 */
 5)               |  /* read_msr: MSR_IA32_DEBUGCTLMSR(1d9), value 1801 */
 5)               |  /* write_msr: MSR_IA32_DEBUGCTLMSR(1d9), value 1801 */
 5)               |  /* write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value 70000000f */
 5)               |  /* write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value 0 */
 5)               |  /* write_msr: MSR_LBR_SELECT(1c8), value 0 */
 5)               |  /* read_msr: MSR_IA32_DEBUGCTLMSR(1d9), value 1801 */
 5)               |  /* write_msr: MSR_IA32_DEBUGCTLMSR(1d9), value 1801 */

This patch:

  - Avoids disabling already frozen LBRs unnecessarily in the PMI
  - Avoids changing LBR_SELECT in the PMI

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1426871484-21285-1-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 18 insertions, 5 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 59994602bb94..9da2400c2ec3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1244,7 +1244,10 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
-static void intel_pmu_disable_all(void)
+/*
+ * Use from PMIs where the LBRs are already disabled.
+ */
+static void __intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
@@ -1256,15 +1259,20 @@ static void intel_pmu_disable_all(void)
 		intel_bts_disable_local();
 
 	intel_pmu_pebs_disable_all();
+}
+
+static void intel_pmu_disable_all(void)
+{
+	__intel_pmu_disable_all();
 	intel_pmu_lbr_disable_all();
 }
 
-static void intel_pmu_enable_all(int added)
+static void __intel_pmu_enable_all(int added, bool pmi)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	intel_pmu_pebs_enable_all();
-	intel_pmu_lbr_enable_all();
+	intel_pmu_lbr_enable_all(pmi);
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
 			x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
 
@@ -1280,6 +1288,11 @@ static void intel_pmu_enable_all(int added)
 		intel_bts_enable_local();
 }
 
+static void intel_pmu_enable_all(int added)
+{
+	__intel_pmu_enable_all(added, false);
+}
+
 /*
  * Workaround for:
  *   Intel Errata AAK100 (model 26)
@@ -1573,7 +1586,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	 */
 	if (!x86_pmu.late_ack)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
-	intel_pmu_disable_all();
+	__intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	handled += intel_bts_interrupt();
 	status = intel_pmu_get_status();
@@ -1658,7 +1671,7 @@ again:
 		goto again;
 
 done:
-	intel_pmu_enable_all(0);
+	__intel_pmu_enable_all(0, true);
 	/*
 	 * Only unmask the NMI after the overflow counters
 	 * have been reset. This avoids spurious NMIs on