drivers/perf: apple_m1: Force 63bit counters for M2 CPUs

Sidharth reports that on M2, the PMU never generates any interrupt
when using 'perf record', which is a annoying as you get no sample.
I'm temped to say "no sample, no problem", but others may have
a different opinion.

Upon investigation, it appears that the counters on M2 are
significantly different from the ones on M1, as they count on
64 bits instead of 48. Which of course, in the fine M1 tradition,
means that we can only use 63 bits, as the top bit is used to signal
the interrupt...

This results in having to introduce yet another flag to indicate yet
another odd counter width. Who knows what the next crazy implementation
will do...

With this, perf can work out the correct offset, and 'perf record'
works as intended.

Tested on M2 and M2-Pro CPUs.

Cc: Janne Grunau <[email protected]>
Cc: Hector Martin <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Will Deacon <[email protected]>
Fixes: 7d0bfb7 ("drivers/perf: apple_m1: Add Apple M2 support")
Reported-by: Sidharth Kshatriya <[email protected]>
Tested-by: Sidharth Kshatriya <[email protected]>
Signed-off-by: Marc Zyngier <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: Marc Zyngier

drivers/perf/apple_m1_cpu_pmu.c

@@ -493,6 +493,17 @@ static int m1_pmu_map_event(struct perf_event *event)
 	return armpmu_map_event(event, &m1_pmu_perf_map, NULL, M1_PMU_CFG_EVENT);
 }
 
+static int m2_pmu_map_event(struct perf_event *event)
+{
+	/*
+	 * Same deal as the above, except that M2 has 64bit counters.
+	 * Which, as far as we're concerned, actually means 63 bits.
+	 * Yes, this is getting awkward.
+	 */
+	event->hw.flags |= ARMPMU_EVT_63BIT;
+	return armpmu_map_event(event, &m1_pmu_perf_map, NULL, M1_PMU_CFG_EVENT);
+}
+
 static void m1_pmu_reset(void *info)
 {
 	int i;
@@ -525,7 +536,7 @@ static int m1_pmu_set_event_filter(struct hw_perf_event *event,
 	return 0;
 }
 
-static int m1_pmu_init(struct arm_pmu *cpu_pmu)
+static int m1_pmu_init(struct arm_pmu *cpu_pmu, u32 flags)
 {
 	cpu_pmu->handle_irq	  = m1_pmu_handle_irq;
 	cpu_pmu->enable		  = m1_pmu_enable_event;
@@ -536,7 +547,14 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->clear_event_idx  = m1_pmu_clear_event_idx;
 	cpu_pmu->start		  = m1_pmu_start;
 	cpu_pmu->stop		  = m1_pmu_stop;
-	cpu_pmu->map_event	  = m1_pmu_map_event;
+
+	if (flags & ARMPMU_EVT_47BIT)
+		cpu_pmu->map_event = m1_pmu_map_event;
+	else if (flags & ARMPMU_EVT_63BIT)
+		cpu_pmu->map_event = m2_pmu_map_event;
+	else
+		return WARN_ON(-EINVAL);
+
 	cpu_pmu->reset		  = m1_pmu_reset;
 	cpu_pmu->set_event_filter = m1_pmu_set_event_filter;
 
@@ -550,25 +568,25 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu)
 static int m1_pmu_ice_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->name = "apple_icestorm_pmu";
-	return m1_pmu_init(cpu_pmu);
+	return m1_pmu_init(cpu_pmu, ARMPMU_EVT_47BIT);
 }
 
 static int m1_pmu_fire_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->name = "apple_firestorm_pmu";
-	return m1_pmu_init(cpu_pmu);
+	return m1_pmu_init(cpu_pmu, ARMPMU_EVT_47BIT);
 }
 
 static int m2_pmu_avalanche_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->name = "apple_avalanche_pmu";
-	return m1_pmu_init(cpu_pmu);
+	return m1_pmu_init(cpu_pmu, ARMPMU_EVT_63BIT);
 }
 
 static int m2_pmu_blizzard_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->name = "apple_blizzard_pmu";
-	return m1_pmu_init(cpu_pmu);
+	return m1_pmu_init(cpu_pmu, ARMPMU_EVT_63BIT);
 }
 
 static const struct of_device_id m1_pmu_of_device_ids[] = {

drivers/perf/arm_pmu.c

@@ -109,6 +109,8 @@ static inline u64 arm_pmu_event_max_period(struct perf_event *event)
 {
 	if (event->hw.flags & ARMPMU_EVT_64BIT)
 		return GENMASK_ULL(63, 0);
+	else if (event->hw.flags & ARMPMU_EVT_63BIT)
+		return GENMASK_ULL(62, 0);
 	else if (event->hw.flags & ARMPMU_EVT_47BIT)
 		return GENMASK_ULL(46, 0);
 	else

include/linux/perf/arm_pmu.h

@@ -26,9 +26,11 @@
  */
 #define ARMPMU_EVT_64BIT		0x00001 /* Event uses a 64bit counter */
 #define ARMPMU_EVT_47BIT		0x00002 /* Event uses a 47bit counter */
+#define ARMPMU_EVT_63BIT		0x00004 /* Event uses a 63bit counter */
 
 static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_64BIT) == ARMPMU_EVT_64BIT);
 static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_47BIT) == ARMPMU_EVT_47BIT);
+static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_63BIT) == ARMPMU_EVT_63BIT);
 
 #define HW_OP_UNSUPPORTED		0xFFFF
 #define C(_x)				PERF_COUNT_HW_CACHE_##_x