arm64: perf: Add support for ARMv8.5-PMU 64-bit counters

At present ARMv8 event counters are limited to 32-bits, though by
using the CHAIN event it's possible to combine adjacent counters to
achieve 64-bits. The perf config1:0 bit can be set to use such a
configuration.

With the introduction of ARMv8.5-PMU support, all event counters can
now be used as 64-bit counters.

Let's enable 64-bit event counters where support exists. Unless the
user sets config1:0 we will adjust the counter value such that it
overflows upon 32-bit overflow. This follows the same behaviour as
the cycle counter which has always been (and remains) 64-bits.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
[Mark: fix ID field names, compare with 8.5 value]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>

3 files changed, 77 insertions, 17 deletions

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2bdbc79bbd01..e7765b62c712 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -176,9 +176,10 @@
 #define ARMV8_PMU_PMCR_X	(1 << 4) /* Export to ETM */
 #define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
+#define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
 #define	ARMV8_PMU_PMCR_N_SHIFT	11	 /* Number of counters supported */
 #define	ARMV8_PMU_PMCR_N_MASK	0x1f
-#define	ARMV8_PMU_PMCR_MASK	0x7f	 /* Mask for writable bits */
+#define	ARMV8_PMU_PMCR_MASK	0xff	 /* Mask for writable bits */
 
 /*
  * PMOVSR: counters overflow flag status reg
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d8f1eed070f0..9b66c5b5b36f 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -702,7 +702,11 @@
 #define ID_AA64DFR0_TRACEVER_SHIFT	4
 #define ID_AA64DFR0_DEBUGVER_SHIFT	0
 
+#define ID_AA64DFR0_PMUVER_8_0		0x1
 #define ID_AA64DFR0_PMUVER_8_1		0x4
+#define ID_AA64DFR0_PMUVER_8_4		0x5
+#define ID_AA64DFR0_PMUVER_8_5		0x6
+#define ID_AA64DFR0_PMUVER_IMP_DEF	0xf
 
 #define ID_DFR0_PERFMON_SHIFT		24
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 8062d79f4cbb..4d7879484cec 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -285,6 +285,17 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 #define	ARMV8_IDX_COUNTER_LAST(cpu_pmu) \
 	(ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
 
+
+/*
+ * We unconditionally enable ARMv8.5-PMU long event counter support
+ * (64-bit events) where supported. Indicate if this arm_pmu has long
+ * event counter support.
+ */
+static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu)
+{
+	return (cpu_pmu->pmuver >= ID_AA64DFR0_PMUVER_8_5);
+}
+
 /*
  * We must chain two programmable counters for 64 bit events,
  * except when we have allocated the 64bit cycle counter (for CPU
@@ -294,9 +305,11 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 static inline bool armv8pmu_event_is_chained(struct perf_event *event)
 {
 	int idx = event->hw.idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 
 	return !WARN_ON(idx < 0) &&
 	       armv8pmu_event_is_64bit(event) &&
+	       !armv8pmu_has_long_event(cpu_pmu) &&
 	       (idx != ARMV8_IDX_CYCLE_COUNTER);
 }
 
@@ -345,7 +358,7 @@ static inline void armv8pmu_select_counter(int idx)
 	isb();
 }
 
-static inline u32 armv8pmu_read_evcntr(int idx)
+static inline u64 armv8pmu_read_evcntr(int idx)
 {
 	armv8pmu_select_counter(idx);
 	return read_sysreg(pmxevcntr_el0);
@@ -362,6 +375,44 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
 	return val;
 }
 
+/*
+ * The cycle counter is always a 64-bit counter. When ARMV8_PMU_PMCR_LP
+ * is set the event counters also become 64-bit counters. Unless the
+ * user has requested a long counter (attr.config1) then we want to
+ * interrupt upon 32-bit overflow - we achieve this by applying a bias.
+ */
+static bool armv8pmu_event_needs_bias(struct perf_event *event)
+{
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (armv8pmu_event_is_64bit(event))
+		return false;
+
+	if (armv8pmu_has_long_event(cpu_pmu) ||
+	    idx == ARMV8_IDX_CYCLE_COUNTER)
+		return true;
+
+	return false;
+}
+
+static u64 armv8pmu_bias_long_counter(struct perf_event *event, u64 value)
+{
+	if (armv8pmu_event_needs_bias(event))
+		value |= GENMASK(63, 32);
+
+	return value;
+}
+
+static u64 armv8pmu_unbias_long_counter(struct perf_event *event, u64 value)
+{
+	if (armv8pmu_event_needs_bias(event))
+		value &= ~GENMASK(63, 32);
+
+	return value;
+}
+
 static u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
@@ -377,10 +428,10 @@ static u64 armv8pmu_read_counter(struct perf_event *event)
 	else
 		value = armv8pmu_read_hw_counter(event);
 
-	return value;
+	return  armv8pmu_unbias_long_counter(event, value);
 }
 
-static inline void armv8pmu_write_evcntr(int idx, u32 value)
+static inline void armv8pmu_write_evcntr(int idx, u64 value)
 {
 	armv8pmu_select_counter(idx);
 	write_sysreg(value, pmxevcntr_el0);
@@ -405,20 +456,14 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
+	value = armv8pmu_bias_long_counter(event, value);
+
 	if (!armv8pmu_counter_valid(cpu_pmu, idx))
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
-	else if (idx == ARMV8_IDX_CYCLE_COUNTER) {
-		/*
-		 * The cycles counter is really a 64-bit counter.
-		 * When treating it as a 32-bit counter, we only count
-		 * the lower 32 bits, and set the upper 32-bits so that
-		 * we get an interrupt upon 32-bit overflow.
-		 */
-		if (!armv8pmu_event_is_64bit(event))
-			value |= 0xffffffff00000000ULL;
+	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
 		write_sysreg(value, pmccntr_el0);
-	} else
+	else
 		armv8pmu_write_hw_counter(event, value);
 }
 
@@ -731,7 +776,8 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	/*
 	 * Otherwise use events counters
 	 */
-	if (armv8pmu_event_is_64bit(event))
+	if (armv8pmu_event_is_64bit(event) &&
+	    !armv8pmu_has_long_event(cpu_pmu))
 		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
 	else
 		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
@@ -802,6 +848,9 @@ static int armv8pmu_filter_match(struct perf_event *event)
 
 static void armv8pmu_reset(void *info)
 {
+	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
+	u32 pmcr;
+
 	/* The counter and interrupt enable registers are unknown at reset. */
 	armv8pmu_disable_counter(U32_MAX);
 	armv8pmu_disable_intens(U32_MAX);
@@ -813,8 +862,13 @@ static void armv8pmu_reset(void *info)
 	 * Initialize & Reset PMNC. Request overflow interrupt for
 	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().
 	 */
-	armv8pmu_pmcr_write(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C |
-			    ARMV8_PMU_PMCR_LC);
+	pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC;
+
+	/* Enable long event counter support where available */
+	if (armv8pmu_has_long_event(cpu_pmu))
+		pmcr |= ARMV8_PMU_PMCR_LP;
+
+	armv8pmu_pmcr_write(pmcr);
 }
 
 static int __armv8_pmuv3_map_event(struct perf_event *event,
@@ -897,6 +951,7 @@ static void __armv8pmu_probe_pmu(void *info)
 	if (pmuver == 0xf || pmuver == 0)
 		return;
 
+	cpu_pmu->pmuver = pmuver;
 	probe->present = true;
 
 	/* Read the nb of CNTx counters supported from PMNC */