drivers/perf: CPU PMU driver for Apple M1

index 604f2bb30ac0..bf3aac0e5491 100644
@@ -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

index 2543ef65825b..2d31ac605573 100644
@@ -177,6 +177,9 @@ 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;
 	int ipi_hwirq;
 };

@@ -794,12 +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, "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))

@@ -833,6 +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);
 

index 2d31ac605573..9daa28c55fa1 100644
@@ -155,7 +155,7 @@
 #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
 
 /*

@@ -416,16 +416,15 @@ 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 &&

@@ -465,7 +464,18 @@ 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);
 	}

new file mode 100644
index 000000000000..b848af7faadc
@@ -0,0 +1,19 @@
+// 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>
+
+/* 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)
+
+#endif /* __ASM_APPLE_M1_PMU_h */

index 9daa28c55fa1..69e1e6abcc38 100644
@@ -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)

index 295cc7952d0e..0a9ed1a061ac 100644
@@ -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);
 }

index 2512e2f9cd4e..0407a38b470a 100644
@@ -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

index b848af7faadc..99483b19b99f 100644
@@ -6,8 +6,21 @@
 #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

@@ -15,5 +28,37 @@
 #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 */

584 lines not on this page · raw message