perf/x86: Move cpuc->running into P4 specific code

The 'running' variable is only used in the P4 PMU. Current perf sets the
variable in the critical function x86_pmu_start(), which wastes cycles
for everybody not running on P4.

Move cpuc->running into the P4 specific p4_pmu_enable_event().

Add a static per-CPU 'p4_running' variable to replace the 'running'
variable in the struct cpu_hw_events. Saves space for the generic
structure.

The p4_pmu_enable_all() also invokes the p4_pmu_enable_event(), but it
should not set cpuc->running. Factor out __p4_pmu_enable_event() for
p4_pmu_enable_all().
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1618410990-21383-1-git-send-email-kan.liang@linux.intel.com

arch/x86/events/core.c

@@ -1480,7 +1480,6 @@ static void x86_pmu_start(struct perf_event *event, int flags)
 
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
-	__set_bit(idx, cpuc->running);
 	static_call(x86_pmu_enable)(event);
 	perf_event_update_userpage(event);
 }

arch/x86/events/intel/p4.c

@@ -947,7 +947,7 @@ static void p4_pmu_enable_pebs(u64 config)
 	(void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT,	(u64)bind->metric_vert);
 }
 
-static void p4_pmu_enable_event(struct perf_event *event)
+static void __p4_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int thread = p4_ht_config_thread(hwc->config);
@@ -983,6 +983,16 @@ static void p4_pmu_enable_event(struct perf_event *event)
 				(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
 }
 
+static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(X86_PMC_IDX_MAX)], p4_running);
+
+static void p4_pmu_enable_event(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	__set_bit(idx, per_cpu(p4_running, smp_processor_id()));
+	__p4_pmu_enable_event(event);
+}
+
 static void p4_pmu_enable_all(int added)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -992,7 +1002,7 @@ static void p4_pmu_enable_all(int added)
 		struct perf_event *event = cpuc->events[idx];
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
-		p4_pmu_enable_event(event);
+		__p4_pmu_enable_event(event);
 	}
 }
 
@@ -1012,7 +1022,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 
 		if (!test_bit(idx, cpuc->active_mask)) {
 			/* catch in-flight IRQs */
-			if (__test_and_clear_bit(idx, cpuc->running))
+			if (__test_and_clear_bit(idx, per_cpu(p4_running, smp_processor_id())))
 				handled++;
 			continue;
 		}

arch/x86/events/perf_event.h

@@ -228,7 +228,6 @@ struct cpu_hw_events {
 	 */
 	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
-	unsigned long		running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	int			enabled;
 
 	int			n_events; /* the # of events in the below arrays */