perf_counter: x86: Fix throttling

If counters are disabled globally when a perfcounter IRQ/NMI hits,
and if we throttle in that case, we'll promote the '0' value to
the next lapic IRQ and disable all perfcounters at that point,
permanently ...

Fix it.

[ Impact: fix hung perfcounters under load ]

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 3a92a2b2a80f56aa18c7dc96e7add019540637aa..88ae8cebf3c1cbda30cc5a90480b4f5727269057 100644 (file)
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -765,8 +765,13 @@ out:
        /*
         * Restore - do not reenable when global enable is off or throttled:
         */
-       if (++cpuc->interrupts < PERFMON_MAX_INTERRUPTS)
-               intel_pmu_restore_all(cpuc->throttle_ctrl);
+       if (cpuc->throttle_ctrl) {
+               if (++cpuc->interrupts < PERFMON_MAX_INTERRUPTS) {
+                       intel_pmu_restore_all(cpuc->throttle_ctrl);
+               } else {
+                       pr_info("CPU#%d: perfcounters: max interrupt rate exceeded! Throttle on.\n", smp_processor_id());
+               }
+       }
 
        return ret;
 }
@@ -817,11 +822,16 @@ void perf_counter_unthrottle(void)
 
        cpuc = &__get_cpu_var(cpu_hw_counters);
        if (cpuc->interrupts >= PERFMON_MAX_INTERRUPTS) {
-               if (printk_ratelimit())
-                       printk(KERN_WARNING "perfcounters: max interrupts exceeded!\n");
+               pr_info("CPU#%d: perfcounters: throttle off.\n", smp_processor_id());
+
+               /*
+                * Clear them before re-enabling irqs/NMIs again:
+                */
+               cpuc->interrupts = 0;
                hw_perf_restore(cpuc->throttle_ctrl);
+       } else {
+               cpuc->interrupts = 0;
        }
-       cpuc->interrupts = 0;
 }
 
 void smp_perf_counter_interrupt(struct pt_regs *regs)