Merge branch 'for-next/perf-m1' into for-next/perf

Support for the CPU PMUs on the Apple M1.

* for-next/perf-m1:
  drivers/perf: Add Apple icestorm/firestorm CPU PMU driver
  drivers/perf: arm_pmu: Handle 47 bit counters
  irqchip/apple-aic: Move PMU-specific registers to their own include file
  arm64: dts: apple: Add t8303 PMU nodes
  arm64: dts: apple: Add t8103 PMU interrupt affinities
  irqchip/apple-aic: Wire PMU interrupts
  irqchip/apple-aic: Parse FIQ affinities from device-tree
  dt-bindings: apple,aic: Add affinity description for per-cpu pseudo-interrupts
  dt-bindings: apple,aic: Add CPU PMU per-cpu pseudo-interrupts
  dt-bindings: arm-pmu: Document Apple PMU compatible strings

11 files changed, 791 insertions, 22 deletions

diff --git a/Documentation/devicetree/bindings/arm/pmu.yaml b/Documentation/devicetree/bindings/arm/pmu.yaml
index 981bac451698..7a04b8aaaec3 100644
--- a/Documentation/devicetree/bindings/arm/pmu.yaml
+++ b/Documentation/devicetree/bindings/arm/pmu.yaml
@@ -20,6 +20,8 @@ properties:
     items:
       - enum:
           - apm,potenza-pmu
+          - apple,firestorm-pmu
+          - apple,icestorm-pmu
           - arm,armv8-pmuv3 # Only for s/w models
           - arm,arm1136-pmu
           - arm,arm1176-pmu
diff --git a/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml b/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
index 97359024709a..85c85b694217 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/apple,aic.yaml
@@ -56,6 +56,8 @@ properties:
           - 1: virtual HV timer
           - 2: physical guest timer
           - 3: virtual guest timer
+          - 4: 'efficient' CPU PMU
+          - 5: 'performance' CPU PMU
 
       The 3rd cell contains the interrupt flags. This is normally
       IRQ_TYPE_LEVEL_HIGH (4).
@@ -68,6 +70,35 @@ properties:
   power-domains:
     maxItems: 1
 
+  affinities:
+    type: object
+    additionalProperties: false
+    description:
+      FIQ affinity can be expressed as a single "affinities" node,
+      containing a set of sub-nodes, one per FIQ with a non-default
+      affinity.
+    patternProperties:
+      "^.+-affinity$":
+        type: object
+        additionalProperties: false
+        properties:
+          apple,fiq-index:
+            description:
+              The interrupt number specified as a FIQ, and for which
+              the affinity is not the default.
+            $ref: /schemas/types.yaml#/definitions/uint32
+            maximum: 5
+
+          cpus:
+            $ref: /schemas/types.yaml#/definitions/phandle-array
+            description:
+              Should be a list of phandles to CPU nodes (as described in
+              Documentation/devicetree/bindings/arm/cpus.yaml).
+
+        required:
+          - fiq-index
+          - cpus
+
 required:
   - compatible
   - '#interrupt-cells'
diff --git a/arch/arm64/boot/dts/apple/t8103.dtsi b/arch/arm64/boot/dts/apple/t8103.dtsi
index 19afbc91020a..9f8f4145db88 100644
--- a/arch/arm64/boot/dts/apple/t8103.dtsi
+++ b/arch/arm64/boot/dts/apple/t8103.dtsi
@@ -97,6 +97,18 @@
 			     <AIC_FIQ AIC_TMR_HV_VIRT IRQ_TYPE_LEVEL_HIGH>;
 	};
 
+	pmu-e {
+		compatible = "apple,icestorm-pmu";
+		interrupt-parent = <&aic>;
+		interrupts = <AIC_FIQ AIC_CPU_PMU_E IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	pmu-p {
+		compatible = "apple,firestorm-pmu";
+		interrupt-parent = <&aic>;
+		interrupts = <AIC_FIQ AIC_CPU_PMU_P IRQ_TYPE_LEVEL_HIGH>;
+	};
+
 	clkref: clock-ref {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
@@ -213,6 +225,18 @@
 			interrupt-controller;
 			reg = <0x2 0x3b100000 0x0 0x8000>;
 			power-domains = <&ps_aic>;
+
+			affinities {
+				e-core-pmu-affinity {
+					apple,fiq-index = <AIC_CPU_PMU_E>;
+					cpus = <&cpu0 &cpu1 &cpu2 &cpu3>;
+				};
+
+				p-core-pmu-affinity {
+					apple,fiq-index = <AIC_CPU_PMU_P>;
+					cpus = <&cpu4 &cpu5 &cpu6 &cpu7>;
+				};
+			};
 		};
 
 		pmgr: power-management@23b700000 {
diff --git a/arch/arm64/include/asm/apple_m1_pmu.h b/arch/arm64/include/asm/apple_m1_pmu.h
new file mode 100644
index 000000000000..99483b19b99f
--- /dev/null
+++ b/arch/arm64/include/asm/apple_m1_pmu.h
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef __ASM_APPLE_M1_PMU_h
+#define __ASM_APPLE_M1_PMU_h
+
+#include <linux/bits.h>
+#include <asm/sysreg.h>
+
+/* Counters */
+#define SYS_IMP_APL_PMC0_EL1	sys_reg(3, 2, 15, 0, 0)
+#define SYS_IMP_APL_PMC1_EL1	sys_reg(3, 2, 15, 1, 0)
+#define SYS_IMP_APL_PMC2_EL1	sys_reg(3, 2, 15, 2, 0)
+#define SYS_IMP_APL_PMC3_EL1	sys_reg(3, 2, 15, 3, 0)
+#define SYS_IMP_APL_PMC4_EL1	sys_reg(3, 2, 15, 4, 0)
+#define SYS_IMP_APL_PMC5_EL1	sys_reg(3, 2, 15, 5, 0)
+#define SYS_IMP_APL_PMC6_EL1	sys_reg(3, 2, 15, 6, 0)
+#define SYS_IMP_APL_PMC7_EL1	sys_reg(3, 2, 15, 7, 0)
+#define SYS_IMP_APL_PMC8_EL1	sys_reg(3, 2, 15, 9, 0)
+#define SYS_IMP_APL_PMC9_EL1	sys_reg(3, 2, 15, 10, 0)
+
+/* Core PMC control register */
+#define SYS_IMP_APL_PMCR0_EL1	sys_reg(3, 1, 15, 0, 0)
+#define PMCR0_CNT_ENABLE_0_7	GENMASK(7, 0)
+#define PMCR0_IMODE		GENMASK(10, 8)
+#define PMCR0_IMODE_OFF		0
+#define PMCR0_IMODE_PMI		1
+#define PMCR0_IMODE_AIC		2
+#define PMCR0_IMODE_HALT	3
+#define PMCR0_IMODE_FIQ		4
+#define PMCR0_IACT		BIT(11)
+#define PMCR0_PMI_ENABLE_0_7	GENMASK(19, 12)
+#define PMCR0_STOP_CNT_ON_PMI	BIT(20)
+#define PMCR0_CNT_GLOB_L2C_EVT	BIT(21)
+#define PMCR0_DEFER_PMI_TO_ERET	BIT(22)
+#define PMCR0_ALLOW_CNT_EN_EL0	BIT(30)
+#define PMCR0_CNT_ENABLE_8_9	GENMASK(33, 32)
+#define PMCR0_PMI_ENABLE_8_9	GENMASK(45, 44)
+
+#define SYS_IMP_APL_PMCR1_EL1	sys_reg(3, 1, 15, 1, 0)
+#define PMCR1_COUNT_A64_EL0_0_7	GENMASK(15, 8)
+#define PMCR1_COUNT_A64_EL1_0_7	GENMASK(23, 16)
+#define PMCR1_COUNT_A64_EL0_8_9	GENMASK(41, 40)
+#define PMCR1_COUNT_A64_EL1_8_9	GENMASK(49, 48)
+
+#define SYS_IMP_APL_PMCR2_EL1	sys_reg(3, 1, 15, 2, 0)
+#define SYS_IMP_APL_PMCR3_EL1	sys_reg(3, 1, 15, 3, 0)
+#define SYS_IMP_APL_PMCR4_EL1	sys_reg(3, 1, 15, 4, 0)
+
+#define SYS_IMP_APL_PMESR0_EL1	sys_reg(3, 1, 15, 5, 0)
+#define PMESR0_EVT_CNT_2	GENMASK(7, 0)
+#define PMESR0_EVT_CNT_3	GENMASK(15, 8)
+#define PMESR0_EVT_CNT_4	GENMASK(23, 16)
+#define PMESR0_EVT_CNT_5	GENMASK(31, 24)
+
+#define SYS_IMP_APL_PMESR1_EL1	sys_reg(3, 1, 15, 6, 0)
+#define PMESR1_EVT_CNT_6	GENMASK(7, 0)
+#define PMESR1_EVT_CNT_7	GENMASK(15, 8)
+#define PMESR1_EVT_CNT_8	GENMASK(23, 16)
+#define PMESR1_EVT_CNT_9	GENMASK(31, 24)
+
+#define SYS_IMP_APL_PMSR_EL1	sys_reg(3, 1, 15, 13, 0)
+#define PMSR_OVERFLOW		GENMASK(9, 0)
+
+#endif /* __ASM_APPLE_M1_PMU_h */
diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c
index 38091ebb9403..b40199c6625e 100644
--- a/drivers/irqchip/irq-apple-aic.c
+++ b/drivers/irqchip/irq-apple-aic.c
@@ -55,6 +55,7 @@
 #include <linux/limits.h>
 #include <linux/of_address.h>
 #include <linux/slab.h>
+#include <asm/apple_m1_pmu.h>
 #include <asm/exception.h>
 #include <asm/sysreg.h>
 #include <asm/virt.h>
@@ -109,16 +110,6 @@
  * Note: sysreg-based IPIs are not supported yet.
  */
 
-/* Core PMC control register */
-#define SYS_IMP_APL_PMCR0_EL1		sys_reg(3, 1, 15, 0, 0)
-#define PMCR0_IMODE			GENMASK(10, 8)
-#define PMCR0_IMODE_OFF			0
-#define PMCR0_IMODE_PMI			1
-#define PMCR0_IMODE_AIC			2
-#define PMCR0_IMODE_HALT		3
-#define PMCR0_IMODE_FIQ			4
-#define PMCR0_IACT			BIT(11)
-
 /* IPI request registers */
 #define SYS_IMP_APL_IPI_RR_LOCAL_EL1	sys_reg(3, 5, 15, 0, 0)
 #define SYS_IMP_APL_IPI_RR_GLOBAL_EL1	sys_reg(3, 5, 15, 0, 1)
@@ -155,7 +146,7 @@
 #define SYS_IMP_APL_UPMSR_EL1		sys_reg(3, 7, 15, 6, 4)
 #define UPMSR_IACT			BIT(0)
 
-#define AIC_NR_FIQ		4
+#define AIC_NR_FIQ		6
 #define AIC_NR_SWIPI		32
 
 /*
@@ -177,6 +168,9 @@ struct aic_irq_chip {
 	void __iomem *base;
 	struct irq_domain *hw_domain;
 	struct irq_domain *ipi_domain;
+	struct {
+		cpumask_t aff;
+	} *fiq_aff[AIC_NR_FIQ];
 	int nr_hw;
 };
 
@@ -412,16 +406,15 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs)
 						  aic_irqc->nr_hw + AIC_TMR_EL02_VIRT);
 	}
 
-	if ((read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & (PMCR0_IMODE | PMCR0_IACT)) ==
-			(FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_FIQ) | PMCR0_IACT)) {
-		/*
-		 * Not supported yet, let's figure out how to handle this when
-		 * we implement these proprietary performance counters. For now,
-		 * just mask it and move on.
-		 */
-		pr_err_ratelimited("PMC FIQ fired. Masking.\n");
-		sysreg_clear_set_s(SYS_IMP_APL_PMCR0_EL1, PMCR0_IMODE | PMCR0_IACT,
-				   FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_OFF));
+	if (read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & PMCR0_IACT) {
+		int irq;
+		if (cpumask_test_cpu(smp_processor_id(),
+				     &aic_irqc->fiq_aff[AIC_CPU_PMU_P]->aff))
+			irq = AIC_CPU_PMU_P;
+		else
+			irq = AIC_CPU_PMU_E;
+		generic_handle_domain_irq(aic_irqc->hw_domain,
+					  aic_irqc->nr_hw + irq);
 	}
 
 	if (FIELD_GET(UPMCR0_IMODE, read_sysreg_s(SYS_IMP_APL_UPMCR0_EL1)) == UPMCR0_IMODE_FIQ &&
@@ -461,7 +454,18 @@ static int aic_irq_domain_map(struct irq_domain *id, unsigned int irq,
 				    handle_fasteoi_irq, NULL, NULL);
 		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(irq)));
 	} else {
-		irq_set_percpu_devid(irq);
+		int fiq = hw - ic->nr_hw;
+
+		switch (fiq) {
+		case AIC_CPU_PMU_P:
+		case AIC_CPU_PMU_E:
+			irq_set_percpu_devid_partition(irq, &ic->fiq_aff[fiq]->aff);
+			break;
+		default:
+			irq_set_percpu_devid(irq);
+			break;
+		}
+
 		irq_domain_set_info(id, irq, hw, &fiq_chip, id->host_data,
 				    handle_percpu_devid_irq, NULL, NULL);
 	}
@@ -793,12 +797,50 @@ static struct gic_kvm_info vgic_info __initdata = {
 	.no_hw_deactivation	= true,
 };
 
+static void build_fiq_affinity(struct aic_irq_chip *ic, struct device_node *aff)
+{
+	int i, n;
+	u32 fiq;
+
+	if (of_property_read_u32(aff, "apple,fiq-index", &fiq) ||
+	    WARN_ON(fiq >= AIC_NR_FIQ) || ic->fiq_aff[fiq])
+		return;
+
+	n = of_property_count_elems_of_size(aff, "cpus", sizeof(u32));
+	if (WARN_ON(n < 0))
+		return;
+
+	ic->fiq_aff[fiq] = kzalloc(sizeof(ic->fiq_aff[fiq]), GFP_KERNEL);
+	if (!ic->fiq_aff[fiq])
+		return;
+
+	for (i = 0; i < n; i++) {
+		struct device_node *cpu_node;
+		u32 cpu_phandle;
+		int cpu;
+
+		if (of_property_read_u32_index(aff, "cpus", i, &cpu_phandle))
+			continue;
+
+		cpu_node = of_find_node_by_phandle(cpu_phandle);
+		if (WARN_ON(!cpu_node))
+			continue;
+
+		cpu = of_cpu_node_to_id(cpu_node);
+		if (WARN_ON(cpu < 0))
+			continue;
+
+		cpumask_set_cpu(cpu, &ic->fiq_aff[fiq]->aff);
+	}
+}
+
 static int __init aic_of_ic_init(struct device_node *node, struct device_node *parent)
 {
 	int i;
 	void __iomem *regs;
 	u32 info;
 	struct aic_irq_chip *irqc;
+	struct device_node *affs;
 
 	regs = of_iomap(node, 0);
 	if (WARN_ON(!regs))
@@ -832,6 +874,14 @@ static int __init aic_of_ic_init(struct device_node *node, struct device_node *p
 		return -ENODEV;
 	}
 
+	affs = of_get_child_by_name(node, "affinities");
+	if (affs) {
+		struct device_node *chld;
+
+		for_each_child_of_node(affs, chld)
+			build_fiq_affinity(irqc, chld);
+	}
+
 	set_handle_irq(aic_handle_irq);
 	set_handle_fiq(aic_handle_fiq);
 
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index b9deef6ed423..d05ca6ebbb9d 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -146,6 +146,13 @@ config MARVELL_CN10K_TAD_PMU
 	  Provides support for Last-Level cache Tag-and-data Units (LLC-TAD)
 	  performance monitors on CN10K family silicons.
 
+config APPLE_M1_CPU_PMU
+	bool "Apple M1 CPU PMU support"
+	depends on ARM_PMU && ARCH_APPLE
+	help
+	  Provides support for the non-architectural CPU PMUs present on
+	  the Apple M1 SoCs and derivatives.
+
 source "drivers/perf/hisilicon/Kconfig"
 
 config MARVELL_CN10K_DDR_PMU
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index df52fb5ea2a6..4f43080ec54e 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -16,3 +16,4 @@ obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o
 obj-$(CONFIG_ARM_DMC620_PMU) += arm_dmc620_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_TAD_PMU) += marvell_cn10k_tad_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_DDR_PMU) += marvell_cn10k_ddr_pmu.o
+obj-$(CONFIG_APPLE_M1_CPU_PMU) += apple_m1_cpu_pmu.o
diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c
new file mode 100644
index 000000000000..979a7c2b4f56
--- /dev/null
+++ b/drivers/perf/apple_m1_cpu_pmu.c
@@ -0,0 +1,584 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * CPU PMU driver for the Apple M1 and derivatives
+ *
+ * Copyright (C) 2021 Google LLC
+ *
+ * Author: Marc Zyngier <maz@kernel.org>
+ *
+ * Most of the information used in this driver was provided by the
+ * Asahi Linux project. The rest was experimentally discovered.
+ */
+
+#include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
+#include <linux/platform_device.h>
+
+#include <asm/apple_m1_pmu.h>
+#include <asm/irq_regs.h>
+#include <asm/perf_event.h>
+
+#define M1_PMU_NR_COUNTERS		10
+
+#define M1_PMU_CFG_EVENT		GENMASK(7, 0)
+
+#define ANY_BUT_0_1			GENMASK(9, 2)
+#define ONLY_2_TO_7			GENMASK(7, 2)
+#define ONLY_2_4_6			(BIT(2) | BIT(4) | BIT(6))
+#define ONLY_5_6_7			(BIT(5) | BIT(6) | BIT(7))
+
+/*
+ * Description of the events we actually know about, as well as those with
+ * a specific counter affinity. Yes, this is a grand total of two known
+ * counters, and the rest is anybody's guess.
+ *
+ * Not all counters can count all events. Counters #0 and #1 are wired to
+ * count cycles and instructions respectively, and some events have
+ * bizarre mappings (every other counter, or even *one* counter). These
+ * restrictions equally apply to both P and E cores.
+ *
+ * It is worth noting that the PMUs attached to P and E cores are likely
+ * to be different because the underlying uarches are different. At the
+ * moment, we don't really need to distinguish between the two because we
+ * know next to nothing about the events themselves, and we already have
+ * per cpu-type PMU abstractions.
+ *
+ * If we eventually find out that the events are different across
+ * implementations, we'll have to introduce per cpu-type tables.
+ */
+enum m1_pmu_events {
+	M1_PMU_PERFCTR_UNKNOWN_01	= 0x01,
+	M1_PMU_PERFCTR_CPU_CYCLES	= 0x02,
+	M1_PMU_PERFCTR_INSTRUCTIONS	= 0x8c,
+	M1_PMU_PERFCTR_UNKNOWN_8d	= 0x8d,
+	M1_PMU_PERFCTR_UNKNOWN_8e	= 0x8e,
+	M1_PMU_PERFCTR_UNKNOWN_8f	= 0x8f,
+	M1_PMU_PERFCTR_UNKNOWN_90	= 0x90,
+	M1_PMU_PERFCTR_UNKNOWN_93	= 0x93,
+	M1_PMU_PERFCTR_UNKNOWN_94	= 0x94,
+	M1_PMU_PERFCTR_UNKNOWN_95	= 0x95,
+	M1_PMU_PERFCTR_UNKNOWN_96	= 0x96,
+	M1_PMU_PERFCTR_UNKNOWN_97	= 0x97,
+	M1_PMU_PERFCTR_UNKNOWN_98	= 0x98,
+	M1_PMU_PERFCTR_UNKNOWN_99	= 0x99,
+	M1_PMU_PERFCTR_UNKNOWN_9a	= 0x9a,
+	M1_PMU_PERFCTR_UNKNOWN_9b	= 0x9b,
+	M1_PMU_PERFCTR_UNKNOWN_9c	= 0x9c,
+	M1_PMU_PERFCTR_UNKNOWN_9f	= 0x9f,
+	M1_PMU_PERFCTR_UNKNOWN_bf	= 0xbf,
+	M1_PMU_PERFCTR_UNKNOWN_c0	= 0xc0,
+	M1_PMU_PERFCTR_UNKNOWN_c1	= 0xc1,
+	M1_PMU_PERFCTR_UNKNOWN_c4	= 0xc4,
+	M1_PMU_PERFCTR_UNKNOWN_c5	= 0xc5,
+	M1_PMU_PERFCTR_UNKNOWN_c6	= 0xc6,
+	M1_PMU_PERFCTR_UNKNOWN_c8	= 0xc8,
+	M1_PMU_PERFCTR_UNKNOWN_ca	= 0xca,
+	M1_PMU_PERFCTR_UNKNOWN_cb	= 0xcb,
+	M1_PMU_PERFCTR_UNKNOWN_f5	= 0xf5,
+	M1_PMU_PERFCTR_UNKNOWN_f6	= 0xf6,
+	M1_PMU_PERFCTR_UNKNOWN_f7	= 0xf7,
+	M1_PMU_PERFCTR_UNKNOWN_f8	= 0xf8,
+	M1_PMU_PERFCTR_UNKNOWN_fd	= 0xfd,
+	M1_PMU_PERFCTR_LAST		= M1_PMU_CFG_EVENT,
+
+	/*
+	 * From this point onwards, these are not actual HW events,
+	 * but attributes that get stored in hw->config_base.
+	 */
+	M1_PMU_CFG_COUNT_USER		= BIT(8),
+	M1_PMU_CFG_COUNT_KERNEL		= BIT(9),
+};
+
+/*
+ * Per-event affinity table. Most events can be installed on counter
+ * 2-9, but there are a number of exceptions. Note that this table
+ * has been created experimentally, and I wouldn't be surprised if more
+ * counters had strange affinities.
+ */
+static const u16 m1_pmu_event_affinity[M1_PMU_PERFCTR_LAST + 1] = {
+	[0 ... M1_PMU_PERFCTR_LAST]	= ANY_BUT_0_1,
+	[M1_PMU_PERFCTR_UNKNOWN_01]	= BIT(7),
+	[M1_PMU_PERFCTR_CPU_CYCLES]	= ANY_BUT_0_1 | BIT(0),
+	[M1_PMU_PERFCTR_INSTRUCTIONS]	= BIT(7) | BIT(1),
+	[M1_PMU_PERFCTR_UNKNOWN_8d]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_8e]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_8f]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_90]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_93]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_94]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_95]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_96]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_97]	= BIT(7),
+	[M1_PMU_PERFCTR_UNKNOWN_98]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_99]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_9a]	= BIT(7),
+	[M1_PMU_PERFCTR_UNKNOWN_9b]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_9c]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_9f]	= BIT(7),
+	[M1_PMU_PERFCTR_UNKNOWN_bf]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_c0]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_c1]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_c4]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_c5]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_c6]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_c8]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_ca]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_cb]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_f5]	= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f6]	= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f7]	= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f8]	= ONLY_2_TO_7,
+	[M1_PMU_PERFCTR_UNKNOWN_fd]	= ONLY_2_4_6,
+};
+
+static const unsigned m1_pmu_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
+	[PERF_COUNT_HW_CPU_CYCLES]	= M1_PMU_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	= M1_PMU_PERFCTR_INSTRUCTIONS,
+	/* No idea about the rest yet */
+};
+
+/* sysfs definitions */
+static ssize_t m1_pmu_events_sysfs_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
+}
+
+#define M1_PMU_EVENT_ATTR(name, config)					\
+	PMU_EVENT_ATTR_ID(name, m1_pmu_events_sysfs_show, config)
+
+static struct attribute *m1_pmu_event_attrs[] = {
+	M1_PMU_EVENT_ATTR(cycles, M1_PMU_PERFCTR_CPU_CYCLES),
+	M1_PMU_EVENT_ATTR(instructions, M1_PMU_PERFCTR_INSTRUCTIONS),
+	NULL,
+};
+
+static const struct attribute_group m1_pmu_events_attr_group = {
+	.name = "events",
+	.attrs = m1_pmu_event_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-7");
+
+static struct attribute *m1_pmu_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static const struct attribute_group m1_pmu_format_attr_group = {
+	.name = "format",
+	.attrs = m1_pmu_format_attrs,
+};
+
+/* Low level accessors. No synchronisation. */
+#define PMU_READ_COUNTER(_idx)						\
+	case _idx:	return read_sysreg_s(SYS_IMP_APL_PMC## _idx ##_EL1)
+
+#define PMU_WRITE_COUNTER(_val, _idx)					\
+	case _idx:							\
+		write_sysreg_s(_val, SYS_IMP_APL_PMC## _idx ##_EL1);	\
+		return
+
+static u64 m1_pmu_read_hw_counter(unsigned int index)
+{
+	switch (index) {
+		PMU_READ_COUNTER(0);
+		PMU_READ_COUNTER(1);
+		PMU_READ_COUNTER(2);
+		PMU_READ_COUNTER(3);
+		PMU_READ_COUNTER(4);
+		PMU_READ_COUNTER(5);
+		PMU_READ_COUNTER(6);
+		PMU_READ_COUNTER(7);
+		PMU_READ_COUNTER(8);
+		PMU_READ_COUNTER(9);
+	}
+
+	BUG();
+}
+
+static void m1_pmu_write_hw_counter(u64 val, unsigned int index)
+{
+	switch (index) {
+		PMU_WRITE_COUNTER(val, 0);
+		PMU_WRITE_COUNTER(val, 1);
+		PMU_WRITE_COUNTER(val, 2);
+		PMU_WRITE_COUNTER(val, 3);
+		PMU_WRITE_COUNTER(val, 4);
+		PMU_WRITE_COUNTER(val, 5);
+		PMU_WRITE_COUNTER(val, 6);
+		PMU_WRITE_COUNTER(val, 7);
+		PMU_WRITE_COUNTER(val, 8);
+		PMU_WRITE_COUNTER(val, 9);
+	}
+
+	BUG();
+}
+
+#define get_bit_offset(index, mask)	(__ffs(mask) + (index))
+
+static void __m1_pmu_enable_counter(unsigned int index, bool en)
+{
+	u64 val, bit;
+
+	switch (index) {
+	case 0 ... 7:
+		bit = BIT(get_bit_offset(index, PMCR0_CNT_ENABLE_0_7));
+		break;
+	case 8 ... 9:
+		bit = BIT(get_bit_offset(index - 8, PMCR0_CNT_ENABLE_8_9));
+		break;
+	default:
+		BUG();
+	}
+
+	val = read_sysreg_s(SYS_IMP_APL_PMCR0_EL1);
+
+	if (en)
+		val |= bit;
+	else
+		val &= ~bit;
+
+	write_sysreg_s(val, SYS_IMP_APL_PMCR0_EL1);
+}
+
+static void m1_pmu_enable_counter(unsigned int index)
+{
+	__m1_pmu_enable_counter(index, true);
+}
+
+static void m1_pmu_disable_counter(unsigned int index)
+{
+	__m1_pmu_enable_counter(index, false);
+}
+
+static void __m1_pmu_enable_counter_interrupt(unsigned int index, bool en)
+{
+	u64 val, bit;
+
+	switch (index) {
+	case 0 ... 7:
+		bit = BIT(get_bit_offset(index, PMCR0_PMI_ENABLE_0_7));
+		break;
+	case 8 ... 9:
+		bit = BIT(get_bit_offset(index - 8, PMCR0_PMI_ENABLE_8_9));
+		break;
+	default:
+		BUG();
+	}
+
+	val = read_sysreg_s(SYS_IMP_APL_PMCR0_EL1);
+
+	if (en)
+		val |= bit;
+	else
+		val &= ~bit;
+
+	write_sysreg_s(val, SYS_IMP_APL_PMCR0_EL1);
+}
+
+static void m1_pmu_enable_counter_interrupt(unsigned int index)
+{
+	__m1_pmu_enable_counter_interrupt(index, true);
+}
+
+static void m1_pmu_disable_counter_interrupt(unsigned int index)
+{
+	__m1_pmu_enable_counter_interrupt(index, false);
+}
+
+static void m1_pmu_configure_counter(unsigned int index, u8 event,
+				     bool user, bool kernel)
+{
+	u64 val, user_bit, kernel_bit;
+	int shift;
+
+	switch (index) {
+	case 0 ... 7:
+		user_bit = BIT(get_bit_offset(index, PMCR1_COUNT_A64_EL0_0_7));
+		kernel_bit = BIT(get_bit_offset(index, PMCR1_COUNT_A64_EL1_0_7));
+		break;
+	case 8 ... 9:
+		user_bit = BIT(get_bit_offset(index - 8, PMCR1_COUNT_A64_EL0_8_9));
+		kernel_bit = BIT(get_bit_offset(index - 8, PMCR1_COUNT_A64_EL1_8_9));
+		break;
+	default:
+		BUG();
+	}
+
+	val = read_sysreg_s(SYS_IMP_APL_PMCR1_EL1);
+
+	if (user)
+		val |= user_bit;
+	else
+		val &= ~user_bit;
+
+	if (kernel)
+		val |= kernel_bit;
+	else
+		val &= ~kernel_bit;
+
+	write_sysreg_s(val, SYS_IMP_APL_PMCR1_EL1);
+
+	/*
+	 * Counters 0 and 1 have fixed events. For anything else,
+	 * place the event at the expected location in the relevant
+	 * register (PMESR0 holds the event configuration for counters
+	 * 2-5, resp. PMESR1 for counters 6-9).
+	 */
+	switch (index) {
+	case 0 ... 1:
+		break;
+	case 2 ... 5:
+		shift = (index - 2) * 8;
+		val = read_sysreg_s(SYS_IMP_APL_PMESR0_EL1);
+		val &= ~((u64)0xff << shift);
+		val |= (u64)event << shift;
+		write_sysreg_s(val, SYS_IMP_APL_PMESR0_EL1);
+		break;
+	case 6 ... 9:
+		shift = (index - 6) * 8;
+		val = read_sysreg_s(SYS_IMP_APL_PMESR1_EL1);
+		val &= ~((u64)0xff << shift);
+		val |= (u64)event << shift;
+		write_sysreg_s(val, SYS_IMP_APL_PMESR1_EL1);
+		break;
+	}
+}
+
+/* arm_pmu backend */
+static void m1_pmu_enable_event(struct perf_event *event)
+{
+	bool user, kernel;
+	u8 evt;
+
+	evt = event->hw.config_base & M1_PMU_CFG_EVENT;
+	user = event->hw.config_base & M1_PMU_CFG_COUNT_USER;
+	kernel = event->hw.config_base & M1_PMU_CFG_COUNT_KERNEL;
+
+	m1_pmu_disable_counter_interrupt(event->hw.idx);
+	m1_pmu_disable_counter(event->hw.idx);
+	isb();
+
+	m1_pmu_configure_counter(event->hw.idx, evt, user, kernel);
+	m1_pmu_enable_counter(event->hw.idx);
+	m1_pmu_enable_counter_interrupt(event->hw.idx);
+	isb();
+}
+
+static void m1_pmu_disable_event(struct perf_event *event)
+{
+	m1_pmu_disable_counter_interrupt(event->hw.idx);
+	m1_pmu_disable_counter(event->hw.idx);
+	isb();
+}
+
+static irqreturn_t m1_pmu_handle_irq(struct arm_pmu *cpu_pmu)
+{
+	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
+	struct pt_regs *regs;
+	u64 overflow, state;
+	int idx;
+
+	overflow = read_sysreg_s(SYS_IMP_APL_PMSR_EL1);
+	if (!overflow) {
+		/* Spurious interrupt? */
+		state = read_sysreg_s(SYS_IMP_APL_PMCR0_EL1);
+		state &= ~PMCR0_IACT;
+		write_sysreg_s(state, SYS_IMP_APL_PMCR0_EL1);
+		isb();
+		return IRQ_NONE;
+	}
+
+	cpu_pmu->stop(cpu_pmu);
+
+	regs = get_irq_regs();
+
+	for (idx = 0; idx < cpu_pmu->num_events; idx++) {
+		struct perf_event *event = cpuc->events[idx];
+		struct perf_sample_data data;
+
+		if (!event)
+			continue;
+
+		armpmu_event_update(event);
+		perf_sample_data_init(&data, 0, event->hw.last_period);
+		if (!armpmu_event_set_period(event))
+			continue;
+
+		if (perf_event_overflow(event, &data, regs))
+			m1_pmu_disable_event(event);
+	}
+
+	cpu_pmu->start(cpu_pmu);
+
+	return IRQ_HANDLED;
+}
+
+static u64 m1_pmu_read_counter(struct perf_event *event)
+{
+	return m1_pmu_read_hw_counter(event->hw.idx);
+}
+
+static void m1_pmu_write_counter(struct perf_event *event, u64 value)
+{
+	m1_pmu_write_hw_counter(value, event->hw.idx);
+	isb();
+}
+
+static int m1_pmu_get_event_idx(struct pmu_hw_events *cpuc,
+				struct perf_event *event)
+{
+	unsigned long evtype = event->hw.config_base & M1_PMU_CFG_EVENT;
+	unsigned long affinity = m1_pmu_event_affinity[evtype];
+	int idx;
+
+	/*
+	 * Place the event on the first free counter that can count
+	 * this event.
+	 *
+	 * We could do a better job if we had a view of all the events
+	 * counting on the PMU at any given time, and by placing the
+	 * most constraining events first.
+	 */
+	for_each_set_bit(idx, &affinity, M1_PMU_NR_COUNTERS) {
+		if (!test_and_set_bit(idx, cpuc->used_mask))
+			return idx;
+	}
+
+	return -EAGAIN;
+}
+
+static void m1_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				   struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
+static void __m1_pmu_set_mode(u8 mode)
+{
+	u64 val;
+
+	val = read_sysreg_s(SYS_IMP_APL_PMCR0_EL1);
+	val &= ~(PMCR0_IMODE | PMCR0_IACT);
+	val |= FIELD_PREP(PMCR0_IMODE, mode);
+	write_sysreg_s(val, SYS_IMP_APL_PMCR0_EL1);
+	isb();
+}
+
+static void m1_pmu_start(struct arm_pmu *cpu_pmu)
+{
+	__m1_pmu_set_mode(PMCR0_IMODE_FIQ);
+}
+
+static void m1_pmu_stop(struct arm_pmu *cpu_pmu)
+{
+	__m1_pmu_set_mode(PMCR0_IMODE_OFF);
+}
+
+static int m1_pmu_map_event(struct perf_event *event)
+{
+	/*
+	 * Although the counters are 48bit wide, bit 47 is what
+	 * triggers the overflow interrupt. Advertise the counters
+	 * being 47bit wide to mimick the behaviour of the ARM PMU.
+	 */
+	event->hw.flags |= ARMPMU_EVT_47BIT;
+	return armpmu_map_event(event, &m1_pmu_perf_map, NULL, M1_PMU_CFG_EVENT);
+}
+
+static void m1_pmu_reset(void *info)
+{
+	int i;
+
+	__m1_pmu_set_mode(PMCR0_IMODE_OFF);
+
+	for (i = 0; i < M1_PMU_NR_COUNTERS; i++) {
+		m1_pmu_disable_counter(i);
+		m1_pmu_disable_counter_interrupt(i);
+		m1_pmu_write_hw_counter(0, i);
+	}
+
+	isb();
+}
+
+static int m1_pmu_set_event_filter(struct hw_perf_event *event,
+				   struct perf_event_attr *attr)
+{
+	unsigned long config_base = 0;
+
+	if (!attr->exclude_guest)
+		return -EINVAL;
+	if (!attr->exclude_kernel)
+		config_base |= M1_PMU_CFG_COUNT_KERNEL;
+	if (!attr->exclude_user)
+		config_base |= M1_PMU_CFG_COUNT_USER;
+
+	event->config_base = config_base;
+
+	return 0;
+}
+
+static int m1_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->handle_irq	  = m1_pmu_handle_irq;
+	cpu_pmu->enable		  = m1_pmu_enable_event;
+	cpu_pmu->disable	  = m1_pmu_disable_event;
+	cpu_pmu->read_counter	  = m1_pmu_read_counter;
+	cpu_pmu->write_counter	  = m1_pmu_write_counter;
+	cpu_pmu->get_event_idx	  = m1_pmu_get_event_idx;
+	cpu_pmu->clear_event_idx  = m1_pmu_clear_event_idx;
+	cpu_pmu->start		  = m1_pmu_start;
+	cpu_pmu->stop		  = m1_pmu_stop;
+	cpu_pmu->map_event	  = m1_pmu_map_event;
+	cpu_pmu->reset		  = m1_pmu_reset;
+	cpu_pmu->set_event_filter = m1_pmu_set_event_filter;
+
+	cpu_pmu->num_events	  = 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;
+}
+
+/* Device driver gunk */
+static int m1_pmu_ice_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->name = "apple_icestorm_pmu";
+	return m1_pmu_init(cpu_pmu);
+}
+
+static int m1_pmu_fire_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->name = "apple_firestorm_pmu";
+	return m1_pmu_init(cpu_pmu);
+}
+
+static const struct of_device_id m1_pmu_of_device_ids[] = {
+	{ .compatible = "apple,icestorm-pmu",	.data = m1_pmu_ice_init, },
+	{ .compatible = "apple,firestorm-pmu",	.data = m1_pmu_fire_init, },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, m1_pmu_of_device_ids);
+
+static int m1_pmu_device_probe(struct platform_device *pdev)
+{
+	return arm_pmu_device_probe(pdev, m1_pmu_of_device_ids, NULL);
+}
+
+static struct platform_driver m1_pmu_driver = {
+	.driver		= {
+		.name			= "apple-m1-cpu-pmu",
+		.of_match_table		= m1_pmu_of_device_ids,
+		.suppress_bind_attrs	= true,
+	},
+	.probe		= m1_pmu_device_probe,
+};
+
+module_platform_driver(m1_pmu_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index a31b302b0ade..9694370651fa 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -109,6 +109,8 @@ static inline u64 arm_pmu_event_max_period(struct perf_event *event)
 {
 	if (event->hw.flags & ARMPMU_EVT_64BIT)
 		return GENMASK_ULL(63, 0);
+	else if (event->hw.flags & ARMPMU_EVT_47BIT)
+		return GENMASK_ULL(46, 0);
 	else
 		return GENMASK_ULL(31, 0);
 }
diff --git a/include/dt-bindings/interrupt-controller/apple-aic.h b/include/dt-bindings/interrupt-controller/apple-aic.h
index 604f2bb30ac0..bf3aac0e5491 100644
--- a/include/dt-bindings/interrupt-controller/apple-aic.h
+++ b/include/dt-bindings/interrupt-controller/apple-aic.h
@@ -11,5 +11,7 @@
 #define AIC_TMR_HV_VIRT		1
 #define AIC_TMR_GUEST_PHYS	2
 #define AIC_TMR_GUEST_VIRT	3
+#define AIC_CPU_PMU_E		4
+#define AIC_CPU_PMU_P		5
 
 #endif
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 2512e2f9cd4e..0407a38b470a 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
+/* Event uses a 47bit counter */
+#define ARMPMU_EVT_47BIT		2
 
 #define HW_OP_UNSUPPORTED		0xFFFF
 #define C(_x)				PERF_COUNT_HW_CACHE_##_x