perf, x86: Make a second write to performance counter if needed

On Netburst PMU we need a second write to a performance counter
due to cpu erratum.

A simple flag test instead of alternative instructions was choosen
because wrmsrl is already a macro and if virtualization is turned
on will need an additional wrapper call which is more expencise.

nb: we should propably switch to jump-labels as only this facility
reach the mainline.

Signed-off-by: Cyrill Gorcunov <[e-mail]>
Signed-off-by: Peter Zijlstra <[e-mail]>
Cc: Robert Richter <[e-mail]>
Cc: Lin Ming <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Frederic Weisbecker <[e-mail]>
LKML-Reference: <20100602212304.GC5264@lenovo>
Signed-off-by: Ingo Molnar <[e-mail]>

arch/x86/kernel/cpu/perf_event.c

···
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
 	void		(*quirks)(void);
+	int		perfctr_second_write;
 
 	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
···
 	 */
 	atomic64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base + idx,
+	wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask);
+
+	/*
+	 * Due to erratum on certan cpu we need
+	 * a second write to be sure the register
+	 * is updated properly
+	 */
+	if (x86_pmu.perfctr_second_write) {
+		wrmsrl(hwc->event_base + idx,
 			(u64)(-left) & x86_pmu.cntval_mask);
+	}
 
 	perf_event_update_userpage(event);
 

arch/x86/kernel/cpu/perf_event_p4.c

···
 	.max_period		= (1ULL << 39) - 1,
 	.hw_config		= p4_hw_config,
 	.schedule_events	= p4_pmu_schedule_events,
+	/*
+	 * This handles erratum N15 in intel doc 249199-029,
+	 * the counter may not be updated correctly on write
+	 * so we need a second write operation to do the trick
+	 * (the official workaround didn't work)
+	 *
+	 * the former idea is taken from OProfile code
+	 */
+	.perfctr_second_write	= 1,
 };
 
 static __init int p4_pmu_init(void)