Merge tag 'arm64-perf' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm[64] perf updates from Will Deacon:
 "I have another mixed bag of ARM-related perf patches here.

  It's about 25% CPU and 75% interconnect, but with drivers/bus/
  languishing without an obvious maintainer or tree, Olof and I agreed
  to keep all of these PMU patches together.  I suspect a whole load of
  code from drivers/bus/arm-* can be moved under drivers/perf/, so
  that's on the radar for the future.

  Summary:

   - Initial support for ARMv8.1 CPU PMUs

   - Support for the CPU PMU in Cavium ThunderX

   - CPU PMU support for systems running 32-bit Linux in secure mode

   - Support for the system PMU in ARM CCI-550 (Cache Coherent Interconnect)"

* tag 'arm64-perf' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (26 commits)
  drivers/perf: arm_pmu: avoid NULL dereference when not using devicetree
  arm64: perf: Extend ARMV8_EVTYPE_MASK to include PMCR.LC
  arm-cci: remove unused variable
  arm-cci: don't return value from void function
  arm-cci: make private functions static
  arm-cci: CoreLink CCI-550 PMU driver
  arm-cci500: Rearrange PMU driver for code sharing with CCI-550 PMU
  arm-cci: CCI-500: Work around PMU counter writes
  arm-cci: Provide hook for writing to PMU counters
  arm-cci: Add helper to enable PMU without synchornising counters
  arm-cci: Add routines to save/restore all counters
  arm-cci: Get the status of a counter
  arm-cci: write_counter: Remove redundant check
  arm-cci: Delay PMU counter writes to pmu::pmu_enable
  arm-cci: Refactor CCI PMU enable/disable methods
  arm-cci: Group writes to counter
  arm-cci: fix handling cpumask_any_but return value
  arm-cci: simplify sysfs attr handling
  drivers/perf: arm_pmu: implement CPU_PM notifier
  arm64: dts: Add Cavium ThunderX specific PMU
  ...

Documentation/devicetree/bindings/arm/cci.txt

@@ -34,6 +34,7 @@ specific to ARM.
 		Definition: must contain one of the following:
 			    "arm,cci-400"
 			    "arm,cci-500"
+			    "arm,cci-550"
 
 	- reg
 		Usage: required
@@ -101,6 +102,7 @@ specific to ARM.
 				 "arm,cci-400-pmu"  - DEPRECATED, permitted only where OS has
 						      secure acces to CCI registers
 				 "arm,cci-500-pmu,r0"
+				 "arm,cci-550-pmu,r0"
 		- reg:
 			Usage: required
 			Value type: Integer cells. A register entry, expressed

Documentation/devicetree/bindings/arm/pmu.txt

@@ -25,6 +25,7 @@ Required properties:
 	"qcom,scorpion-pmu"
 	"qcom,scorpion-mp-pmu"
 	"qcom,krait-pmu"
+	"cavium,thunder-pmu"
 - interrupts : 1 combined interrupt or 1 per core. If the interrupt is a per-cpu
                interrupt (PPI) then 1 interrupt should be specified.
 
@@ -46,6 +47,16 @@ Optional properties:
 - qcom,no-pc-write : Indicates that this PMU doesn't support the 0xc and 0xd
                      events.
 
+- secure-reg-access : Indicates that the ARMv7 Secure Debug Enable Register
+		      (SDER) is accessible. This will cause the driver to do
+		      any setup required that is only possible in ARMv7 secure
+		      state. If not present the ARMv7 SDER will not be touched,
+		      which means the PMU may fail to operate unless external
+		      code (bootloader or security monitor) has performed the
+		      appropriate initialisation. Note that this property is
+		      not valid for non-ARMv7 CPUs or ARMv7 CPUs booting Linux
+		      in Non-secure state.
+
 Example:
 
 pmu {

arch/arm/kernel/perf_event_v7.c

@@ -712,6 +712,11 @@ static const struct attribute_group *armv7_pmuv2_attr_groups[] = {
 #define	ARMV7_EXCLUDE_USER	(1 << 30)
 #define	ARMV7_INCLUDE_HYP	(1 << 27)
 
+/*
+ * Secure debug enable reg
+ */
+#define ARMV7_SDER_SUNIDEN	BIT(1) /* Permit non-invasive debug */
+
 static inline u32 armv7_pmnc_read(void)
 {
 	u32 val;
@@ -1094,7 +1099,13 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event,
 static void armv7pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
-	u32 idx, nb_cnt = cpu_pmu->num_events;
+	u32 idx, nb_cnt = cpu_pmu->num_events, val;
+
+	if (cpu_pmu->secure_access) {
+		asm volatile("mrc p15, 0, %0, c1, c1, 1" : "=r" (val));
+		val |= ARMV7_SDER_SUNIDEN;
+		asm volatile("mcr 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) {

arch/arm64/boot/dts/cavium/thunder-88xx.dtsi

@@ -360,6 +360,11 @@
 		             <1 10 0xff01>;
 	};
 
+	pmu {
+		compatible = "cavium,thunder-pmu", "arm,armv8-pmuv3";
+		interrupts = <1 7 4>;
+	};
+
 	soc {
 		compatible = "simple-bus";
 		#address-cells = <2>;

arch/arm64/kernel/perf_event.c

@@ -88,16 +88,25 @@
 #define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x2F
 #define ARMV8_PMUV3_PERFCTR_L21_TLB				0x30
 
+/* ARMv8 implementation defined event types. */
+#define ARMV8_IMPDEF_PERFCTR_L1_DCACHE_ACCESS_LD		0x40
+#define ARMV8_IMPDEF_PERFCTR_L1_DCACHE_ACCESS_ST		0x41
+#define ARMV8_IMPDEF_PERFCTR_L1_DCACHE_REFILL_LD		0x42
+#define ARMV8_IMPDEF_PERFCTR_L1_DCACHE_REFILL_ST		0x43
+#define ARMV8_IMPDEF_PERFCTR_DTLB_REFILL_LD			0x4C
+#define ARMV8_IMPDEF_PERFCTR_DTLB_REFILL_ST			0x4D
+#define ARMV8_IMPDEF_PERFCTR_DTLB_ACCESS_LD			0x4E
+#define ARMV8_IMPDEF_PERFCTR_DTLB_ACCESS_ST			0x4F
+
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREFETCH_LINEFILL			0xC2
 
-/* ARMv8 Cortex-A57 and Cortex-A72 specific event types. */
-#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD			0x40
-#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST			0x41
-#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD			0x42
-#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST			0x43
-#define ARMV8_A57_PERFCTR_DTLB_REFILL_LD			0x4c
-#define ARMV8_A57_PERFCTR_DTLB_REFILL_ST			0x4d
+/* ARMv8 Cavium ThunderX specific event types. */
+#define ARMV8_THUNDER_PERFCTR_L1_DCACHE_MISS_ST			0xE9
+#define ARMV8_THUNDER_PERFCTR_L1_DCACHE_PREF_ACCESS		0xEA
+#define ARMV8_THUNDER_PERFCTR_L1_DCACHE_PREF_MISS		0xEB
+#define ARMV8_THUNDER_PERFCTR_L1_ICACHE_PREF_ACCESS		0xEC
+#define ARMV8_THUNDER_PERFCTR_L1_ICACHE_PREF_MISS		0xED
 
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
@@ -132,6 +141,18 @@ static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
 };
 
+static const unsigned armv8_thunder_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV8_PMUV3_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
+};
+
 static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 						[PERF_COUNT_HW_CACHE_OP_MAX]
 						[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
@@ -175,16 +196,46 @@ static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					      [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
 	PERF_CACHE_MAP_ALL_UNSUPPORTED,
 
-	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD,
-	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST,
-	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST,
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1_DCACHE_ACCESS_LD,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1_DCACHE_REFILL_LD,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1_DCACHE_ACCESS_ST,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1_DCACHE_REFILL_ST,
 
 	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS,
 	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL,
 
-	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_A57_PERFCTR_DTLB_REFILL_LD,
-	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_A57_PERFCTR_DTLB_REFILL_ST,
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_DTLB_REFILL_LD,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_DTLB_REFILL_ST,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
+static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+						   [PERF_COUNT_HW_CACHE_OP_MAX]
+						   [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1_DCACHE_ACCESS_LD,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_L1_DCACHE_REFILL_LD,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_L1_DCACHE_ACCESS_ST,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_THUNDER_PERFCTR_L1_DCACHE_MISS_ST,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1_DCACHE_PREF_ACCESS,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1_DCACHE_PREF_MISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL,
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1_ICACHE_PREF_ACCESS,
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1_ICACHE_PREF_MISS,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_IMPDEF_PERFCTR_DTLB_ACCESS_LD,
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_DTLB_REFILL_LD,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_DTLB_ACCESS_ST,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_IMPDEF_PERFCTR_DTLB_REFILL_ST,
 
 	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_ITLB_REFILL,
 
@@ -325,7 +376,6 @@ static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
 	NULL,
 };
 
-
 /*
  * Perf Events' indices
  */
@@ -356,9 +406,10 @@ static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
 #define ARMV8_PMCR_D		(1 << 3) /* CCNT counts every 64th cpu cycle */
 #define ARMV8_PMCR_X		(1 << 4) /* Export to ETM */
 #define ARMV8_PMCR_DP		(1 << 5) /* Disable CCNT if non-invasive debug*/
+#define ARMV8_PMCR_LC		(1 << 6) /* Overflow on 64 bit cycle counter */
 #define	ARMV8_PMCR_N_SHIFT	11	 /* Number of counters supported */
 #define	ARMV8_PMCR_N_MASK	0x1f
-#define	ARMV8_PMCR_MASK		0x3f	 /* Mask for writable bits */
+#define	ARMV8_PMCR_MASK		0x7f	 /* Mask for writable bits */
 
 /*
  * PMOVSR: counters overflow flag status reg
@@ -369,8 +420,8 @@ static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define	ARMV8_EVTYPE_MASK	0xc80003ff	/* Mask for writable bits */
-#define	ARMV8_EVTYPE_EVENT	0x3ff		/* Mask for EVENT bits */
+#define	ARMV8_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
+#define	ARMV8_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
 
 /*
  * Event filters for PMUv3
@@ -445,9 +496,16 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u32 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)
-		asm volatile("msr pmccntr_el0, %0" :: "r" (value));
-	else if (armv8pmu_select_counter(idx) == idx)
+	else if (idx == ARMV8_IDX_CYCLE_COUNTER) {
+		/*
+		 * Set the upper 32bits as this is a 64bit counter but we only
+		 * count using the lower 32bits and we want an interrupt when
+		 * it overflows.
+		 */
+		u64 value64 = 0xffffffff00000000ULL | value;
+
+		asm volatile("msr pmccntr_el0, %0" :: "r" (value64));
+	} else if (armv8pmu_select_counter(idx) == idx)
 		asm volatile("msr pmxevcntr_el0, %0" :: "r" (value));
 }
 
@@ -722,8 +780,11 @@ static void armv8pmu_reset(void *info)
 		armv8pmu_disable_intens(idx);
 	}
 
-	/* Initialize & Reset PMNC: C and P bits. */
-	armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C);
+	/*
+	 * Initialize & Reset PMNC. Request overflow interrupt for
+	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().
+	 */
+	armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C | ARMV8_PMCR_LC);
 }
 
 static int armv8_pmuv3_map_event(struct perf_event *event)
@@ -747,6 +808,13 @@ static int armv8_a57_map_event(struct perf_event *event)
 				ARMV8_EVTYPE_EVENT);
 }
 
+static int armv8_thunder_map_event(struct perf_event *event)
+{
+	return armpmu_map_event(event, &armv8_thunder_perf_map,
+				&armv8_thunder_perf_cache_map,
+				ARMV8_EVTYPE_EVENT);
+}
+
 static void armv8pmu_read_num_pmnc_events(void *info)
 {
 	int *nb_cnt = info;
@@ -815,11 +883,21 @@ static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 	return armv8pmu_probe_num_events(cpu_pmu);
 }
 
+static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv8_pmu_init(cpu_pmu);
+	cpu_pmu->name			= "armv8_cavium_thunder";
+	cpu_pmu->map_event		= armv8_thunder_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	return armv8pmu_probe_num_events(cpu_pmu);
+}
+
 static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "arm,armv8-pmuv3",	.data = armv8_pmuv3_init},
 	{.compatible = "arm,cortex-a53-pmu",	.data = armv8_a53_pmu_init},
 	{.compatible = "arm,cortex-a57-pmu",	.data = armv8_a57_pmu_init},
 	{.compatible = "arm,cortex-a72-pmu",	.data = armv8_a72_pmu_init},
+	{.compatible = "cavium,thunder-pmu",	.data = armv8_thunder_pmu_init},
 	{},
 };
 

drivers/bus/Kconfig

@@ -34,15 +34,15 @@ config ARM_CCI400_PORT_CTRL
 	  Low level power management driver for CCI400 cache coherent
 	  interconnect for ARM platforms.
 
-config ARM_CCI500_PMU
-	bool "ARM CCI500 PMU support"
+config ARM_CCI5xx_PMU
+	bool "ARM CCI-500/CCI-550 PMU support"
 	depends on (ARM && CPU_V7) || ARM64
 	depends on PERF_EVENTS
 	select ARM_CCI_PMU
 	help
-	  Support for PMU events monitoring on the ARM CCI-500 cache coherent
-	  interconnect. CCI-500 provides 8 independent event counters, which
-	  can count events pertaining to the slave/master interfaces as well
+	  Support for PMU events monitoring on the ARM CCI-500/CCI-550 cache
+	  coherent interconnects. Both of them provide 8 independent event counters,
+	  which can count events pertaining to the slave/master interfaces as well
 	  as the internal events to the CCI.
 
 	  If unsure, say Y

drivers/perf/arm_pmu.c

@@ -13,6 +13,7 @@
 
 #include <linux/bitmap.h>
 #include <linux/cpumask.h>
+#include <linux/cpu_pm.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/of_device.h>
@@ -710,6 +711,93 @@ static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
 	return NOTIFY_OK;
 }
 
+#ifdef CONFIG_CPU_PM
+static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
+{
+	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
+	struct perf_event *event;
+	int idx;
+
+	for (idx = 0; idx < armpmu->num_events; idx++) {
+		/*
+		 * If the counter is not used skip it, there is no
+		 * need of stopping/restarting it.
+		 */
+		if (!test_bit(idx, hw_events->used_mask))
+			continue;
+
+		event = hw_events->events[idx];
+
+		switch (cmd) {
+		case CPU_PM_ENTER:
+			/*
+			 * Stop and update the counter
+			 */
+			armpmu_stop(event, PERF_EF_UPDATE);
+			break;
+		case CPU_PM_EXIT:
+		case CPU_PM_ENTER_FAILED:
+			 /* Restore and enable the counter */
+			armpmu_start(event, PERF_EF_RELOAD);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd,
+			     void *v)
+{
+	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);
+	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
+
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return NOTIFY_DONE;
+
+	/*
+	 * Always reset the PMU registers on power-up even if
+	 * there are no events running.
+	 */
+	if (cmd == CPU_PM_EXIT && armpmu->reset)
+		armpmu->reset(armpmu);
+
+	if (!enabled)
+		return NOTIFY_OK;
+
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		armpmu->stop(armpmu);
+		cpu_pm_pmu_setup(armpmu, cmd);
+		break;
+	case CPU_PM_EXIT:
+		cpu_pm_pmu_setup(armpmu, cmd);
+	case CPU_PM_ENTER_FAILED:
+		armpmu->start(armpmu);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int cpu_pm_pmu_register(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->cpu_pm_nb.notifier_call = cpu_pm_pmu_notify;
+	return cpu_pm_register_notifier(&cpu_pmu->cpu_pm_nb);
+}
+
+static void cpu_pm_pmu_unregister(struct arm_pmu *cpu_pmu)
+{
+	cpu_pm_unregister_notifier(&cpu_pmu->cpu_pm_nb);
+}
+#else
+static inline int cpu_pm_pmu_register(struct arm_pmu *cpu_pmu) { return 0; }
+static inline void cpu_pm_pmu_unregister(struct arm_pmu *cpu_pmu) { }
+#endif
+
 static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	int err;
@@ -725,6 +813,10 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	if (err)
 		goto out_hw_events;
 
+	err = cpu_pm_pmu_register(cpu_pmu);
+	if (err)
+		goto out_unregister;
+
 	for_each_possible_cpu(cpu) {
 		struct pmu_hw_events *events = per_cpu_ptr(cpu_hw_events, cpu);
 		raw_spin_lock_init(&events->pmu_lock);
@@ -746,6 +838,8 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 
 	return 0;
 
+out_unregister:
+	unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
 out_hw_events:
 	free_percpu(cpu_hw_events);
 	return err;
@@ -753,6 +847,7 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 
 static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
 {
+	cpu_pm_pmu_unregister(cpu_pmu);
 	unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
 	free_percpu(cpu_pmu->hw_events);
 }
@@ -889,6 +984,15 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
 		init_fn = of_id->data;
 
+		pmu->secure_access = of_property_read_bool(pdev->dev.of_node,
+							   "secure-reg-access");
+
+		/* arm64 systems boot only as non-secure */
+		if (IS_ENABLED(CONFIG_ARM64) && pmu->secure_access) {
+			pr_warn("ignoring \"secure-reg-access\" property for arm64\n");
+			pmu->secure_access = false;
+		}
+
 		ret = of_pmu_irq_cfg(pmu);
 		if (!ret)
 			ret = init_fn(pmu);
@@ -898,7 +1002,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	}
 
 	if (ret) {
-		pr_info("failed to probe PMU!\n");
+		pr_info("%s: failed to probe PMU!\n", of_node_full_name(node));
 		goto out_free;
 	}
 
@@ -918,7 +1022,8 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 out_destroy:
 	cpu_pmu_destroy(pmu);
 out_free:
-	pr_info("failed to register PMU devices!\n");
+	pr_info("%s: failed to register PMU devices!\n",
+		of_node_full_name(node));
 	kfree(pmu);
 	return ret;
 }

include/linux/perf/arm_pmu.h

@@ -104,9 +104,11 @@ struct arm_pmu {
 	atomic_t	active_events;
 	struct mutex	reserve_mutex;
 	u64		max_period;
+	bool		secure_access; /* 32-bit ARM only */
 	struct platform_device	*plat_device;
 	struct pmu_hw_events	__percpu *hw_events;
 	struct notifier_block	hotplug_nb;
+	struct notifier_block	cpu_pm_nb;
 };
 
 #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))