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
  ...

3 files changed, 117 insertions, 23 deletions

diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4152158..1506385 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/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) {
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
index 9cb7cf94..2eb9b22 100644
--- a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
+++ b/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>;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 1b52269..767c4f6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/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},
 	{},
 };