perf: arm_pmu: Remove event index to counter remapping

Xscale and Armv6 PMUs defined the cycle counter at 0 and event counters
starting at 1 and had 1:1 event index to counter numbering. On Armv7 and
later, this changed the cycle counter to 31 and event counters start at
0. The drivers for Armv7 and PMUv3 kept the old event index numbering
and introduced an event index to counter conversion. The conversion uses
masking to convert from event index to a counter number. This operation
relies on having at most 32 counters so that the cycle counter index 0
can be transformed to counter number 31.

Armv9.4 adds support for an additional fixed function counter
(instructions) which increases possible counters to more than 32, and
the conversion won't work anymore as a simple subtract and mask. The
primary reason for the translation (other than history) seems to be to
have a contiguous mask of counters 0-N. Keeping that would result in
more complicated index to counter conversions. Instead, store a mask of
available counters rather than just number of events. That provides more
information in addition to the number of events.

No (intended) functional changes.

Acked-by: Mark Rutland <[e-mail]>
Signed-off-by: Rob Herring (Arm) <[e-mail]>
Tested-by: James Clark <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Will Deacon <[e-mail]>

arch/arm64/kvm/pmu-emul.c

···
 	struct arm_pmu *arm_pmu = kvm->arch.arm_pmu;
 
 	/*
-	 * The arm_pmu->num_events considers the cycle counter as well.
-	 * Ignore that and return only the general-purpose counters.
+	 * The arm_pmu->cntr_mask considers the fixed counter(s) as well.
+	 * Ignore those and return only the general-purpose counters.
 	 */
-	return arm_pmu->num_events - 1;
+	return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS);
 }
 
 static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)

drivers/perf/apple_m1_cpu_pmu.c

···
 
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; idx++) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, M1_PMU_NR_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct perf_sample_data data;
 
···
 	cpu_pmu->reset		  = m1_pmu_reset;
 	cpu_pmu->set_event_filter = m1_pmu_set_event_filter;
 
-	cpu_pmu->num_events	  = M1_PMU_NR_COUNTERS;
+	bitmap_set(cpu_pmu->cntr_mask, 0, M1_PMU_NR_COUNTERS);
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &m1_pmu_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &m1_pmu_format_attr_group;
 	return 0;

drivers/perf/arm_pmu.c

···
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu);
 	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
-	bool enabled = !bitmap_empty(hw_events->used_mask, armpmu->num_events);
+	bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS);
 
 	/* For task-bound events we may be called on other CPUs */
 	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
···
 	struct perf_event *event;
 	int idx;
 
-	for (idx = 0; idx < armpmu->num_events; idx++) {
+	for_each_set_bit(idx, armpmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		event = hw_events->events[idx];
 		if (!event)
 			continue;
···
 {
 	struct arm_pmu *armpmu = container_of(b, struct arm_pmu, cpu_pm_nb);
 	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
-	bool enabled = !bitmap_empty(hw_events->used_mask, armpmu->num_events);
+	bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS);
 
 	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
 		return NOTIFY_DONE;
···
 	if (ret)
 		goto out_destroy;
 
-	pr_info("enabled with %s PMU driver, %d counters available%s\n",
-		pmu->name, pmu->num_events,
+	pr_info("enabled with %s PMU driver, %d (%*pb) counters available%s\n",
+		pmu->name, bitmap_weight(pmu->cntr_mask, ARMPMU_MAX_HWEVENTS),
+		ARMPMU_MAX_HWEVENTS, &pmu->cntr_mask,
 		has_nmi ? ", using NMIs" : "");
 
 	kvm_host_pmu_init(pmu);

drivers/perf/arm_pmuv3.c

···
 /*
  * Perf Events' indices
  */
-#define	ARMV8_IDX_CYCLE_COUNTER	0
-#define	ARMV8_IDX_COUNTER0	1
-#define	ARMV8_IDX_CYCLE_COUNTER_USER	32
+#define	ARMV8_IDX_CYCLE_COUNTER	31
 
 /*
  * We unconditionally enable ARMv8.5-PMU long event counter support
···
 	return !armv8pmu_event_has_user_read(event) &&
 	       armv8pmu_event_is_64bit(event) &&
 	       !armv8pmu_has_long_event(cpu_pmu) &&
-	       (idx != ARMV8_IDX_CYCLE_COUNTER);
+	       (idx < ARMV8_PMU_MAX_GENERAL_COUNTERS);
 }
 
 /*
  * ARMv8 low level PMU access
  */
-
-/*
- * Perf Event to low level counters mapping
- */
-#define	ARMV8_IDX_TO_COUNTER(x)	\
-	(((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK)
-
 static u64 armv8pmu_pmcr_read(void)
 {
 	return read_pmcr();
···
 
 static int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
 {
-	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
+	return pmnc & BIT(idx);
 }
 
 static u64 armv8pmu_read_evcntr(int idx)
 {
-	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
-
-	return read_pmevcntrn(counter);
+	return read_pmevcntrn(idx);
 }
 
 static u64 armv8pmu_read_hw_counter(struct perf_event *event)
···
 		return false;
 
 	if (armv8pmu_has_long_event(cpu_pmu) ||
-	    idx == ARMV8_IDX_CYCLE_COUNTER)
+	    idx >= ARMV8_PMU_MAX_GENERAL_COUNTERS)
 		return true;
 
 	return false;
···
 
 static void armv8pmu_write_evcntr(int idx, u64 value)
 {
-	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
-
-	write_pmevcntrn(counter, value);
+	write_pmevcntrn(idx, value);
 }
 
 static void armv8pmu_write_hw_counter(struct perf_event *event,
···
 
 static void armv8pmu_write_evtype(int idx, unsigned long val)
 {
-	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 	unsigned long mask = ARMV8_PMU_EVTYPE_EVENT |
 			     ARMV8_PMU_INCLUDE_EL2 |
 			     ARMV8_PMU_EXCLUDE_EL0 |
···
 		mask |= ARMV8_PMU_EVTYPE_TC | ARMV8_PMU_EVTYPE_TH;
 
 	val &= mask;
-	write_pmevtypern(counter, val);
+	write_pmevtypern(idx, val);
 }
 
 static void armv8pmu_write_event_type(struct perf_event *event)
···
 
 static u32 armv8pmu_event_cnten_mask(struct perf_event *event)
 {
-	int counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
+	int counter = event->hw.idx;
 	u32 mask = BIT(counter);
 
 	if (armv8pmu_event_is_chained(event))
···
 
 static void armv8pmu_enable_event_irq(struct perf_event *event)
 {
-	u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
-	armv8pmu_enable_intens(BIT(counter));
+	armv8pmu_enable_intens(BIT(event->hw.idx));
 }
 
 static void armv8pmu_disable_intens(u32 mask)
···
 
 static void armv8pmu_disable_event_irq(struct perf_event *event)
 {
-	u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
-	armv8pmu_disable_intens(BIT(counter));
+	armv8pmu_disable_intens(BIT(event->hw.idx));
 }
 
 static u32 armv8pmu_getreset_flags(void)
···
 	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 
 	/* Clear any unused counters to avoid leaking their contents */
-	for_each_clear_bit(i, cpuc->used_mask, cpu_pmu->num_events) {
+	for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask,
+			    ARMPMU_MAX_HWEVENTS) {
 		if (i == ARMV8_IDX_CYCLE_COUNTER)
 			write_pmccntr(0);
 		else
···
 	 * to prevent skews in group events.
 	 */
 	armv8pmu_stop(cpu_pmu);
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
···
 {
 	int idx;
 
-	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx++) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
 		if (!test_and_set_bit(idx, cpuc->used_mask))
 			return idx;
 	}
···
 	 * Chaining requires two consecutive event counters, where
 	 * the lower idx must be even.
 	 */
-	for (idx = ARMV8_IDX_COUNTER0 + 1; idx < cpu_pmu->num_events; idx += 2) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) {
+		if (!(idx & 0x1))
+			continue;
 		if (!test_and_set_bit(idx, cpuc->used_mask)) {
 			/* Check if the preceding even counter is available */
 			if (!test_and_set_bit(idx - 1, cpuc->used_mask))
···
 	if (!sysctl_perf_user_access || !armv8pmu_event_has_user_read(event))
 		return 0;
 
-	/*
-	 * We remap the cycle counter index to 32 to
-	 * match the offset applied to the rest of
-	 * the counter indices.
-	 */
-	if (event->hw.idx == ARMV8_IDX_CYCLE_COUNTER)
-		return ARMV8_IDX_CYCLE_COUNTER_USER;
-
-	return event->hw.idx;
+	return event->hw.idx + 1;
 }
 
 /*
···
 	probe->present = true;
 
 	/* Read the nb of CNTx counters supported from PMNC */
-	cpu_pmu->num_events = FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read());
+	bitmap_set(cpu_pmu->cntr_mask,
+		   0, FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read()));
 
 	/* Add the CPU cycles counter */
-	cpu_pmu->num_events += 1;
+	set_bit(ARMV8_IDX_CYCLE_COUNTER, cpu_pmu->cntr_mask);
 
 	pmceid[0] = pmceid_raw[0] = read_pmceid0();
 	pmceid[1] = pmceid_raw[1] = read_pmceid1();

drivers/perf/arm_v6_pmu.c

···
 	ARMV6_CYCLE_COUNTER = 0,
 	ARMV6_COUNTER0,
 	ARMV6_COUNTER1,
+	ARMV6_NUM_COUNTERS
 };
 
 /*
···
 	 */
 	armv6_pmcr_write(pmcr);
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV6_NUM_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
···
 	cpu_pmu->start		= armv6pmu_start;
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6_map_event;
-	cpu_pmu->num_events	= 3;
+
+	bitmap_set(cpu_pmu->cntr_mask, 0, ARMV6_NUM_COUNTERS);
 }
 
 static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)

drivers/perf/arm_v7_pmu.c

···
 /*
  * Perf Events' indices
  */
-#define	ARMV7_IDX_CYCLE_COUNTER	0
-#define	ARMV7_IDX_COUNTER0	1
-#define	ARMV7_IDX_COUNTER_LAST(cpu_pmu) \
-	(ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
-
-#define	ARMV7_MAX_COUNTERS	32
-#define	ARMV7_COUNTER_MASK	(ARMV7_MAX_COUNTERS - 1)
-
+#define	ARMV7_IDX_CYCLE_COUNTER	31
+#define	ARMV7_IDX_COUNTER_MAX	31
 /*
  * ARMv7 low level PMNC access
  */
-
-/*
- * Perf Event to low level counters mapping
- */
-#define	ARMV7_IDX_TO_COUNTER(x)	\
-	(((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK)
 
 /*
  * Per-CPU PMNC: config reg
···
 
 static inline int armv7_pmnc_counter_valid(struct arm_pmu *cpu_pmu, int idx)
 {
-	return idx >= ARMV7_IDX_CYCLE_COUNTER &&
-		idx <= ARMV7_IDX_COUNTER_LAST(cpu_pmu);
+	return test_bit(idx, cpu_pmu->cntr_mask);
 }
 
 static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx)
 {
-	return pmnc & BIT(ARMV7_IDX_TO_COUNTER(idx));
+	return pmnc & BIT(idx);
 }
 
 static inline void armv7_pmnc_select_counter(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter));
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (idx));
 	isb();
 }
 
···
 
 static inline void armv7_pmnc_enable_counter(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(idx)));
 }
 
 static inline void armv7_pmnc_disable_counter(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(idx)));
 }
 
 static inline void armv7_pmnc_enable_intens(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(idx)));
 }
 
 static inline void armv7_pmnc_disable_intens(int idx)
 {
-	u32 counter = ARMV7_IDX_TO_COUNTER(idx);
-	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(idx)));
 	isb();
 	/* Clear the overflow flag in case an interrupt is pending. */
-	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(counter)));
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(idx)));
 	isb();
 }
 
···
 	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
 	pr_info("CCNT  =0x%08x\n", val);
 
-	for (cnt = ARMV7_IDX_COUNTER0;
-			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+	for_each_set_bit(cnt, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		armv7_pmnc_select_counter(cnt);
 		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
-		pr_info("CNT[%d] count =0x%08x\n",
-			ARMV7_IDX_TO_COUNTER(cnt), val);
+		pr_info("CNT[%d] count =0x%08x\n", cnt, val);
 		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
-		pr_info("CNT[%d] evtsel=0x%08x\n",
-			ARMV7_IDX_TO_COUNTER(cnt), val);
+		pr_info("CNT[%d] evtsel=0x%08x\n", cnt, val);
 	}
 }
 #endif
···
 	 */
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
···
 	 * For anything other than a cycle counter, try and use
 	 * the events counters
 	 */
-	for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		if (!test_and_set_bit(idx, cpuc->used_mask))
 			return idx;
 	}
···
 static void armv7pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
-	u32 idx, nb_cnt = cpu_pmu->num_events, val;
+	u32 idx, val;
 
 	if (cpu_pmu->secure_access) {
 		asm volatile("mrc p15, 0, %0, c1, c1, 1" : "=r" (val));
···
 	}
 
 	/* The counter and interrupt enable registers are unknown at reset. */
-	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) {
 		armv7_pmnc_disable_counter(idx);
 		armv7_pmnc_disable_intens(idx);
 	}
···
 
 static void armv7_read_num_pmnc_events(void *info)
 {
-	int *nb_cnt = info;
+	int nb_cnt;
+	struct arm_pmu *cpu_pmu = info;
 
 	/* Read the nb of CNTx counters supported from PMNC */
-	*nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+	nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+	bitmap_set(cpu_pmu->cntr_mask, 0, nb_cnt);
 
 	/* Add the CPU cycles counter */
-	*nb_cnt += 1;
+	set_bit(ARMV7_IDX_CYCLE_COUNTER, cpu_pmu->cntr_mask);
 }
 
 static int armv7_probe_num_events(struct arm_pmu *arm_pmu)
 {
 	return smp_call_function_any(&arm_pmu->supported_cpus,
 				     armv7_read_num_pmnc_events,
-				     &arm_pmu->num_events, 1);
+				     arm_pmu, 1);
 }
 
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
···
 {
 	u32 vval, fval;
 	struct arm_pmu *cpu_pmu = info;
-	u32 idx, nb_cnt = cpu_pmu->num_events;
+	u32 idx;
 
 	armv7pmu_reset(info);
 
···
 	venum_post_pmresr(vval, fval);
 
 	/* Reset PMxEVNCTCR to sane default */
-	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		armv7_pmnc_select_counter(idx);
 		asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
 	}
···
 	 * Lower bits are reserved for use by the counters (see
 	 * armv7pmu_get_event_idx() for more info)
 	 */
-	bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1;
+	bit += bitmap_weight(cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX);
 
 	return bit;
 }
···
 {
 	u32 vval, fval;
 	struct arm_pmu *cpu_pmu = info;
-	u32 idx, nb_cnt = cpu_pmu->num_events;
+	u32 idx;
 
 	armv7pmu_reset(info);
 
···
 	venum_post_pmresr(vval, fval);
 
 	/* Reset PMxEVNCTCR to sane default */
-	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX) {
 		armv7_pmnc_select_counter(idx);
 		asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
 	}
···
 	 * Lower bits are reserved for use by the counters (see
 	 * armv7pmu_get_event_idx() for more info)
 	 */
-	bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1;
+	bit += bitmap_weight(cpu_pmu->cntr_mask, ARMV7_IDX_COUNTER_MAX);
 
 	return bit;
 }

drivers/perf/arm_xscale_pmu.c

···
 	XSCALE_COUNTER2,
 	XSCALE_COUNTER3,
 };
+#define XSCALE1_NUM_COUNTERS	3
+#define XSCALE2_NUM_COUNTERS	5
 
 static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
···
 
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, XSCALE1_NUM_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
···
 	cpu_pmu->start		= xscale1pmu_start;
 	cpu_pmu->stop		= xscale1pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
-	cpu_pmu->num_events	= 3;
+
+	bitmap_set(cpu_pmu->cntr_mask, 0, XSCALE1_NUM_COUNTERS);
 
 	return 0;
 }
···
 
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, XSCALE2_NUM_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
 
···
 	cpu_pmu->start		= xscale2pmu_start;
 	cpu_pmu->stop		= xscale2pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
-	cpu_pmu->num_events	= 5;
+
+	bitmap_set(cpu_pmu->cntr_mask, 0, XSCALE2_NUM_COUNTERS);
 
 	return 0;
 }

include/linux/perf/arm_pmu.h

···
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
-	int		num_events;
+	DECLARE_BITMAP(cntr_mask, ARMPMU_MAX_HWEVENTS);
 	bool		secure_access; /* 32-bit ARM only */
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40
 	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);

include/linux/perf/arm_pmuv3.h

···
 #ifndef __PERF_ARM_PMUV3_H
 #define __PERF_ARM_PMUV3_H
 
+#define ARMV8_PMU_MAX_GENERAL_COUNTERS	31
 #define ARMV8_PMU_MAX_COUNTERS	32
 #define ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)