[PATCH v2 3/5] arm64: pmu: Add function implementation to update event index in userpage.

[Raphael Gault]

In order to be able to access the counter directly for userspace,
we need to provide the index of the counter using the userpage.
We thus need to override the event_idx function to retrieve and
convert the perf_event index to armv8 hardware index.

Since the arm_pmu driver can be used by any implementation, even
if not armv8, two components play a role into making sure the
behaviour is correct and consistent with the PMU capabilities:

* the ARMPMU_EL0_RD_CNTR flag which denotes the capability to access
counter from userspace.
* the event_idx call back, which is implemented and initialized by
the PMU implementation: if no callback is provided, the default
behaviour applies, returning 0 as index value.

Signed-off-by: Raphael Gault <raphael.gault@xxxxxxx>
---
 arch/arm64/kernel/perf_event.c | 22 ++++++++++++++++++++++
 include/linux/perf/arm_pmu.h   |  2 ++
 2 files changed, 24 insertions(+)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 24575c0a0065..f6336197d29e 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -819,6 +819,22 @@ static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 		clear_bit(idx - 1, cpuc->used_mask);
 }
 
+static int armv8pmu_access_event_idx(struct perf_event *event)
+{
+	if (!(event->hw.flags & ARMPMU_EL0_RD_CNTR))
+		return 0;
+
+	/*
+	 * We remap the cycle counter index to 32 to
+	 * match the offset applied to the rest of
+	 * the counter indeces.
+	 */
+	if (event->hw.idx == ARMV8_IDX_CYCLE_COUNTER)
+		return 32;
+
+	return event->hw.idx;
+}
+
 /*
  * Add an event filter to a given event.
  */
@@ -912,6 +928,9 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
 	if (armv8pmu_event_is_64bit(event))
 		event->hw.flags |= ARMPMU_EVT_64BIT;
 
+	if (!cpus_have_const_cap(ARM64_HAS_HETEROGENEOUS_PMU))
+		event->hw.flags |= ARMPMU_EL0_RD_CNTR;
+
 	/* Only expose micro/arch events supported by this PMU */
 	if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS)
 	    && test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
@@ -1032,6 +1051,8 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
+	cpu_pmu->pmu.event_idx		= armv8pmu_access_event_idx;
+
 	return 0;
 }
 
@@ -1210,6 +1231,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	 */
 	freq = arch_timer_get_rate();
 	userpg->cap_user_time = 1;
+	userpg->cap_user_rdpmc = !!(event->hw.flags & ARMPMU_EL0_RD_CNTR);
 
 	clocks_calc_mult_shift(&userpg->time_mult, &shift, freq,
 			NSEC_PER_SEC, 0);
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 71f525a35ac2..1106a9ac00fd 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -26,6 +26,8 @@
  */
 /* Event uses a 64bit counter */
 #define ARMPMU_EVT_64BIT		1
+/* Allow access to hardware counter from userspace */
+#define ARMPMU_EL0_RD_CNTR		2
 
 #define HW_OP_UNSUPPORTED		0xFFFF
 #define C(_x)				PERF_COUNT_HW_CACHE_##_x
-- 
2.17.1