perf_counter: x86: Disallow interval of 1

On certain CPUs i have observed a stuck PMU if interval was set to
1 and NMIs were used. The PMU had PMC0 set in MSR_CORE_PERF_GLOBAL_STATUS,
but it was not possible to ack it via MSR_CORE_PERF_GLOBAL_OVF_CTRL,
and the NMI loop got stuck infinitely.

[ Impact: fix rare hangs during high perfcounter load ]

Signed-off-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 1dcf67057f161162448c3d8b8f235cb6df58d4c5..46a82d1e4cbec1c827d772d7376926e1ec02ade2 100644 (file)
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -473,6 +473,11 @@ x86_perf_counter_set_period(struct perf_counter *counter,
                left += period;
                atomic64_set(&hwc->period_left, left);
        }
+       /*
+        * Quirk: certain CPUs dont like it if just 1 event is left:
+        */
+       if (unlikely(left < 2))
+               left = 2;
 
        per_cpu(prev_left[idx], smp_processor_id()) = left;