Merge branch 'for-next/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux

* 'for-next/perf' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux:
  perf: arm_spe: Enable ACPI/Platform automatic module loading
  arm_pmu: acpi: spe: Add initial MADT/SPE probing
  ACPI/PPTT: Add function to return ACPI 6.3 Identical tokens
  ACPI/PPTT: Modify node flag detection to find last IDENTICAL
  MAINTAINERS: Add maintainer entry for the imx8 DDR PMU driver
  drivers/perf: imx_ddr: Add DDR performance counter support to perf
  dt-bindings: perf: imx8-ddr: add imx8qxp ddr performance monitor

11 files changed, 738 insertions, 8 deletions

diff --git a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
new file mode 100644
index 000000000000..d77e3f26f9e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
@@ -0,0 +1,21 @@
+* Freescale(NXP) IMX8 DDR performance monitor
+
+Required properties:
+
+- compatible: should be one of:
+	"fsl,imx8-ddr-pmu"
+	"fsl,imx8m-ddr-pmu"
+
+- reg: physical address and size
+
+- interrupts: single interrupt
+	generated by the control block
+
+Example:
+
+	ddr-pmu@5c020000 {
+		compatible = "fsl,imx8-ddr-pmu";
+		reg = <0x5c020000 0x10000>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
+	};
diff --git a/MAINTAINERS b/MAINTAINERS
index a6954776a37e..a2a8b567d5e8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6328,6 +6328,13 @@ L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-cpm.c
 
+FREESCALE IMX DDR PMU DRIVER
+M:	Frank Li <Frank.li@nxp.com>
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	drivers/perf/fsl_imx8_ddr_perf.c
+F:	Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
+
 FREESCALE IMX LPI2C DRIVER
 M:	Dong Aisheng <aisheng.dong@nxp.com>
 L:	linux-i2c@vger.kernel.org
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 7628efbe6c12..d10399b9f998 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -41,6 +41,9 @@
 	(!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \
 	(unsigned long)(entry) + (entry)->header.length > (end))
 
+#define ACPI_MADT_GICC_SPE  (ACPI_OFFSET(struct acpi_madt_generic_interrupt, \
+	spe_interrupt) + sizeof(u16))
+
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
 pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index b72e6afaa8fb..1e7ac0bd0d3a 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -432,17 +432,40 @@ static void cache_setup_acpi_cpu(struct acpi_table_header *table,
 	}
 }
 
+static bool flag_identical(struct acpi_table_header *table_hdr,
+			   struct acpi_pptt_processor *cpu)
+{
+	struct acpi_pptt_processor *next;
+
+	/* heterogeneous machines must use PPTT revision > 1 */
+	if (table_hdr->revision < 2)
+		return false;
+
+	/* Locate the last node in the tree with IDENTICAL set */
+	if (cpu->flags & ACPI_PPTT_ACPI_IDENTICAL) {
+		next = fetch_pptt_node(table_hdr, cpu->parent);
+		if (!(next && next->flags & ACPI_PPTT_ACPI_IDENTICAL))
+			return true;
+	}
+
+	return false;
+}
+
 /* Passing level values greater than this will result in search termination */
 #define PPTT_ABORT_PACKAGE 0xFF
 
-static struct acpi_pptt_processor *acpi_find_processor_package_id(struct acpi_table_header *table_hdr,
-								  struct acpi_pptt_processor *cpu,
-								  int level, int flag)
+static struct acpi_pptt_processor *acpi_find_processor_tag(struct acpi_table_header *table_hdr,
+							   struct acpi_pptt_processor *cpu,
+							   int level, int flag)
 {
 	struct acpi_pptt_processor *prev_node;
 
 	while (cpu && level) {
-		if (cpu->flags & flag)
+		/* special case the identical flag to find last identical */
+		if (flag == ACPI_PPTT_ACPI_IDENTICAL) {
+			if (flag_identical(table_hdr, cpu))
+				break;
+		} else if (cpu->flags & flag)
 			break;
 		pr_debug("level %d\n", level);
 		prev_node = fetch_pptt_node(table_hdr, cpu->parent);
@@ -480,8 +503,8 @@ static int topology_get_acpi_cpu_tag(struct acpi_table_header *table,
 
 	cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
 	if (cpu_node) {
-		cpu_node = acpi_find_processor_package_id(table, cpu_node,
-							  level, flag);
+		cpu_node = acpi_find_processor_tag(table, cpu_node,
+						   level, flag);
 		/*
 		 * As per specification if the processor structure represents
 		 * an actual processor, then ACPI processor ID must be valid.
@@ -660,3 +683,29 @@ int find_acpi_cpu_topology_package(unsigned int cpu)
 	return find_acpi_cpu_topology_tag(cpu, PPTT_ABORT_PACKAGE,
 					  ACPI_PPTT_PHYSICAL_PACKAGE);
 }
+
+/**
+ * find_acpi_cpu_topology_hetero_id() - Get a core architecture tag
+ * @cpu: Kernel logical CPU number
+ *
+ * Determine a unique heterogeneous tag for the given CPU. CPUs with the same
+ * implementation should have matching tags.
+ *
+ * The returned tag can be used to group peers with identical implementation.
+ *
+ * The search terminates when a level is found with the identical implementation
+ * flag set or we reach a root node.
+ *
+ * Due to limitations in the PPTT data structure, there may be rare situations
+ * where two cores in a heterogeneous machine may be identical, but won't have
+ * the same tag.
+ *
+ * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
+ * Otherwise returns a value which represents a group of identical cores
+ * similar to this CPU.
+ */
+int find_acpi_cpu_topology_hetero_id(unsigned int cpu)
+{
+	return find_acpi_cpu_topology_tag(cpu, PPTT_ABORT_PACKAGE,
+					  ACPI_PPTT_ACPI_IDENTICAL);
+}
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index e4221a107dca..09ae8a970880 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -71,6 +71,14 @@ config ARM_DSU_PMU
 	  system, control logic. The PMU allows counting various events related
 	  to DSU.
 
+config FSL_IMX8_DDR_PMU
+	tristate "Freescale i.MX8 DDR perf monitor"
+	depends on ARCH_MXC
+	  help
+	  Provides support for the DDR performance monitor in i.MX8, which
+	  can give information about memory throughput and other related
+	  events.
+
 config HISI_PMU
        bool "HiSilicon SoC PMU"
        depends on ARM64 && ACPI
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 30489941f3d6..2ebb4de17815 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
 obj-$(CONFIG_ARM_SMMU_V3_PMU) += arm_smmuv3_pmu.o
+obj-$(CONFIG_FSL_IMX8_DDR_PMU) += fsl_imx8_ddr_perf.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/
 obj-$(CONFIG_QCOM_L2_PMU)	+= qcom_l2_pmu.o
 obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 0f197516d708..864d7ebe45e9 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -74,6 +74,76 @@ static void arm_pmu_acpi_unregister_irq(int cpu)
 	acpi_unregister_gsi(gsi);
 }
 
+#if IS_ENABLED(CONFIG_ARM_SPE_PMU)
+static struct resource spe_resources[] = {
+	{
+		/* irq */
+		.flags          = IORESOURCE_IRQ,
+	}
+};
+
+static struct platform_device spe_dev = {
+	.name = ARMV8_SPE_PDEV_NAME,
+	.id = -1,
+	.resource = spe_resources,
+	.num_resources = ARRAY_SIZE(spe_resources)
+};
+
+/*
+ * For lack of a better place, hook the normal PMU MADT walk
+ * and create a SPE device if we detect a recent MADT with
+ * a homogeneous PPI mapping.
+ */
+static void arm_spe_acpi_register_device(void)
+{
+	int cpu, hetid, irq, ret;
+	bool first = true;
+	u16 gsi = 0;
+
+	/*
+	 * Sanity check all the GICC tables for the same interrupt number.
+	 * For now, we only support homogeneous ACPI/SPE machines.
+	 */
+	for_each_possible_cpu(cpu) {
+		struct acpi_madt_generic_interrupt *gicc;
+
+		gicc = acpi_cpu_get_madt_gicc(cpu);
+		if (gicc->header.length < ACPI_MADT_GICC_SPE)
+			return;
+
+		if (first) {
+			gsi = gicc->spe_interrupt;
+			if (!gsi)
+				return;
+			hetid = find_acpi_cpu_topology_hetero_id(cpu);
+			first = false;
+		} else if ((gsi != gicc->spe_interrupt) ||
+			   (hetid != find_acpi_cpu_topology_hetero_id(cpu))) {
+			pr_warn("ACPI: SPE must be homogeneous\n");
+			return;
+		}
+	}
+
+	irq = acpi_register_gsi(NULL, gsi, ACPI_LEVEL_SENSITIVE,
+				ACPI_ACTIVE_HIGH);
+	if (irq < 0) {
+		pr_warn("ACPI: SPE Unable to register interrupt: %d\n", gsi);
+		return;
+	}
+
+	spe_resources[0].start = irq;
+	ret = platform_device_register(&spe_dev);
+	if (ret < 0) {
+		pr_warn("ACPI: SPE: Unable to register device\n");
+		acpi_unregister_gsi(gsi);
+	}
+}
+#else
+static inline void arm_spe_acpi_register_device(void)
+{
+}
+#endif /* CONFIG_ARM_SPE_PMU */
+
 static int arm_pmu_acpi_parse_irqs(void)
 {
 	int irq, cpu, irq_cpu, err;
@@ -279,6 +349,8 @@ static int arm_pmu_acpi_init(void)
 	if (acpi_disabled)
 		return 0;
 
+	arm_spe_acpi_register_device();
+
 	ret = arm_pmu_acpi_parse_irqs();
 	if (ret)
 		return ret;
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index e120f933412a..4fb65c61c8ea 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -38,6 +38,7 @@
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/perf_event.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 #include <linux/printk.h>
 #include <linux/slab.h>
@@ -1168,7 +1169,13 @@ static const struct of_device_id arm_spe_pmu_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, arm_spe_pmu_of_match);
 
-static int arm_spe_pmu_device_dt_probe(struct platform_device *pdev)
+static const struct platform_device_id arm_spe_match[] = {
+	{ ARMV8_SPE_PDEV_NAME, 0},
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, arm_spe_match);
+
+static int arm_spe_pmu_device_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct arm_spe_pmu *spe_pmu;
@@ -1228,11 +1235,12 @@ static int arm_spe_pmu_device_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver arm_spe_pmu_driver = {
+	.id_table = arm_spe_match,
 	.driver	= {
 		.name		= DRVNAME,
 		.of_match_table	= of_match_ptr(arm_spe_pmu_of_match),
 	},
-	.probe	= arm_spe_pmu_device_dt_probe,
+	.probe	= arm_spe_pmu_device_probe,
 	.remove	= arm_spe_pmu_device_remove,
 };
 
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
new file mode 100644
index 000000000000..63fe21600072
--- /dev/null
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -0,0 +1,554 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2017 NXP
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+
+#define COUNTER_CNTL		0x0
+#define COUNTER_READ		0x20
+
+#define COUNTER_DPCR1		0x30
+
+#define CNTL_OVER		0x1
+#define CNTL_CLEAR		0x2
+#define CNTL_EN			0x4
+#define CNTL_EN_MASK		0xFFFFFFFB
+#define CNTL_CLEAR_MASK		0xFFFFFFFD
+#define CNTL_OVER_MASK		0xFFFFFFFE
+
+#define CNTL_CSV_SHIFT		24
+#define CNTL_CSV_MASK		(0xFF << CNTL_CSV_SHIFT)
+
+#define EVENT_CYCLES_ID		0
+#define EVENT_CYCLES_COUNTER	0
+#define NUM_COUNTERS		4
+
+#define to_ddr_pmu(p)		container_of(p, struct ddr_pmu, pmu)
+
+#define DDR_PERF_DEV_NAME	"imx8_ddr"
+#define DDR_CPUHP_CB_NAME	DDR_PERF_DEV_NAME "_perf_pmu"
+
+static DEFINE_IDA(ddr_ida);
+
+static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
+	{ .compatible = "fsl,imx8-ddr-pmu",},
+	{ .compatible = "fsl,imx8m-ddr-pmu",},
+	{ /* sentinel */ }
+};
+
+struct ddr_pmu {
+	struct pmu pmu;
+	void __iomem *base;
+	unsigned int cpu;
+	struct	hlist_node node;
+	struct	device *dev;
+	struct perf_event *events[NUM_COUNTERS];
+	int active_events;
+	enum cpuhp_state cpuhp_state;
+	int irq;
+	int id;
+};
+
+static ssize_t ddr_perf_cpumask_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct ddr_pmu *pmu = dev_get_drvdata(dev);
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu));
+}
+
+static struct device_attribute ddr_perf_cpumask_attr =
+	__ATTR(cpumask, 0444, ddr_perf_cpumask_show, NULL);
+
+static struct attribute *ddr_perf_cpumask_attrs[] = {
+	&ddr_perf_cpumask_attr.attr,
+	NULL,
+};
+
+static struct attribute_group ddr_perf_cpumask_attr_group = {
+	.attrs = ddr_perf_cpumask_attrs,
+};
+
+static ssize_t
+ddr_pmu_event_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%02llx\n", pmu_attr->id);
+}
+
+#define IMX8_DDR_PMU_EVENT_ATTR(_name, _id)				\
+	(&((struct perf_pmu_events_attr[]) {				\
+		{ .attr = __ATTR(_name, 0444, ddr_pmu_event_show, NULL),\
+		  .id = _id, }						\
+	})[0].attr.attr)
+
+static struct attribute *ddr_perf_events_attrs[] = {
+	IMX8_DDR_PMU_EVENT_ATTR(cycles, EVENT_CYCLES_ID),
+	IMX8_DDR_PMU_EVENT_ATTR(selfresh, 0x01),
+	IMX8_DDR_PMU_EVENT_ATTR(read-accesses, 0x04),
+	IMX8_DDR_PMU_EVENT_ATTR(write-accesses, 0x05),
+	IMX8_DDR_PMU_EVENT_ATTR(read-queue-depth, 0x08),
+	IMX8_DDR_PMU_EVENT_ATTR(write-queue-depth, 0x09),
+	IMX8_DDR_PMU_EVENT_ATTR(lp-read-credit-cnt, 0x10),
+	IMX8_DDR_PMU_EVENT_ATTR(hp-read-credit-cnt, 0x11),
+	IMX8_DDR_PMU_EVENT_ATTR(write-credit-cnt, 0x12),
+	IMX8_DDR_PMU_EVENT_ATTR(read-command, 0x20),
+	IMX8_DDR_PMU_EVENT_ATTR(write-command, 0x21),
+	IMX8_DDR_PMU_EVENT_ATTR(read-modify-write-command, 0x22),
+	IMX8_DDR_PMU_EVENT_ATTR(hp-read, 0x23),
+	IMX8_DDR_PMU_EVENT_ATTR(hp-req-nocredit, 0x24),
+	IMX8_DDR_PMU_EVENT_ATTR(hp-xact-credit, 0x25),
+	IMX8_DDR_PMU_EVENT_ATTR(lp-req-nocredit, 0x26),
+	IMX8_DDR_PMU_EVENT_ATTR(lp-xact-credit, 0x27),
+	IMX8_DDR_PMU_EVENT_ATTR(wr-xact-credit, 0x29),
+	IMX8_DDR_PMU_EVENT_ATTR(read-cycles, 0x2a),
+	IMX8_DDR_PMU_EVENT_ATTR(write-cycles, 0x2b),
+	IMX8_DDR_PMU_EVENT_ATTR(read-write-transition, 0x30),
+	IMX8_DDR_PMU_EVENT_ATTR(precharge, 0x31),
+	IMX8_DDR_PMU_EVENT_ATTR(activate, 0x32),
+	IMX8_DDR_PMU_EVENT_ATTR(load-mode, 0x33),
+	IMX8_DDR_PMU_EVENT_ATTR(perf-mwr, 0x34),
+	IMX8_DDR_PMU_EVENT_ATTR(read, 0x35),
+	IMX8_DDR_PMU_EVENT_ATTR(read-activate, 0x36),
+	IMX8_DDR_PMU_EVENT_ATTR(refresh, 0x37),
+	IMX8_DDR_PMU_EVENT_ATTR(write, 0x38),
+	IMX8_DDR_PMU_EVENT_ATTR(raw-hazard, 0x39),
+	NULL,
+};
+
+static struct attribute_group ddr_perf_events_attr_group = {
+	.name = "events",
+	.attrs = ddr_perf_events_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-7");
+
+static struct attribute *ddr_perf_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group ddr_perf_format_attr_group = {
+	.name = "format",
+	.attrs = ddr_perf_format_attrs,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&ddr_perf_events_attr_group,
+	&ddr_perf_format_attr_group,
+	&ddr_perf_cpumask_attr_group,
+	NULL,
+};
+
+static u32 ddr_perf_alloc_counter(struct ddr_pmu *pmu, int event)
+{
+	int i;
+
+	/*
+	 * Always map cycle event to counter 0
+	 * Cycles counter is dedicated for cycle event
+	 * can't used for the other events
+	 */
+	if (event == EVENT_CYCLES_ID) {
+		if (pmu->events[EVENT_CYCLES_COUNTER] == NULL)
+			return EVENT_CYCLES_COUNTER;
+		else
+			return -ENOENT;
+	}
+
+	for (i = 1; i < NUM_COUNTERS; i++) {
+		if (pmu->events[i] == NULL)
+			return i;
+	}
+
+	return -ENOENT;
+}
+
+static void ddr_perf_free_counter(struct ddr_pmu *pmu, int counter)
+{
+	pmu->events[counter] = NULL;
+}
+
+static u32 ddr_perf_read_counter(struct ddr_pmu *pmu, int counter)
+{
+	return readl_relaxed(pmu->base + COUNTER_READ + counter * 4);
+}
+
+static int ddr_perf_event_init(struct perf_event *event)
+{
+	struct ddr_pmu *pmu = to_ddr_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_event *sibling;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+		return -EOPNOTSUPP;
+
+	if (event->cpu < 0) {
+		dev_warn(pmu->dev, "Can't provide per-task data!\n");
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * We must NOT create groups containing mixed PMUs, although software
+	 * events are acceptable (for example to create a CCN group
+	 * periodically read when a hrtimer aka cpu-clock leader triggers).
+	 */
+	if (event->group_leader->pmu != event->pmu &&
+			!is_software_event(event->group_leader))
+		return -EINVAL;
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu != event->pmu &&
+				!is_software_event(sibling))
+			return -EINVAL;
+	}
+
+	event->cpu = pmu->cpu;
+	hwc->idx = -1;
+
+	return 0;
+}
+
+
+static void ddr_perf_event_update(struct perf_event *event)
+{
+	struct ddr_pmu *pmu = to_ddr_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	u64 delta, prev_raw_count, new_raw_count;
+	int counter = hwc->idx;
+
+	do {
+		prev_raw_count = local64_read(&hwc->prev_count);
+		new_raw_count = ddr_perf_read_counter(pmu, counter);
+	} while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+			new_raw_count) != prev_raw_count);
+
+	delta = (new_raw_count - prev_raw_count) & 0xFFFFFFFF;
+
+	local64_add(delta, &event->count);
+}
+
+static void ddr_perf_counter_enable(struct ddr_pmu *pmu, int config,
+				  int counter, bool enable)
+{
+	u8 reg = counter * 4 + COUNTER_CNTL;
+	int val;
+
+	if (enable) {
+		/*
+		 * must disable first, then enable again
+		 * otherwise, cycle counter will not work
+		 * if previous state is enabled.
+		 */
+		writel(0, pmu->base + reg);
+		val = CNTL_EN | CNTL_CLEAR;
+		val |= FIELD_PREP(CNTL_CSV_MASK, config);
+		writel(val, pmu->base + reg);
+	} else {
+		/* Disable counter */
+		writel(0, pmu->base + reg);
+	}
+}
+
+static void ddr_perf_event_start(struct perf_event *event, int flags)
+{
+	struct ddr_pmu *pmu = to_ddr_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int counter = hwc->idx;
+
+	local64_set(&hwc->prev_count, 0);
+
+	ddr_perf_counter_enable(pmu, event->attr.config, counter, true);
+
+	hwc->state = 0;
+}
+
+static int ddr_perf_event_add(struct perf_event *event, int flags)
+{
+	struct ddr_pmu *pmu = to_ddr_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int counter;
+	int cfg = event->attr.config;
+
+	counter = ddr_perf_alloc_counter(pmu, cfg);
+	if (counter < 0) {
+		dev_dbg(pmu->dev, "There are not enough counters\n");
+		return -EOPNOTSUPP;
+	}
+
+	pmu->events[counter] = event;
+	pmu->active_events++;
+	hwc->idx = counter;
+
+	hwc->state |= PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		ddr_perf_event_start(event, flags);
+
+	return 0;
+}
+
+static void ddr_perf_event_stop(struct perf_event *event, int flags)
+{
+	struct ddr_pmu *pmu = to_ddr_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int counter = hwc->idx;
+
+	ddr_perf_counter_enable(pmu, event->attr.config, counter, false);
+	ddr_perf_event_update(event);
+
+	hwc->state |= PERF_HES_STOPPED;
+}
+
+static void ddr_perf_event_del(struct perf_event *event, int flags)
+{
+	struct ddr_pmu *pmu = to_ddr_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int counter = hwc->idx;
+
+	ddr_perf_event_stop(event, PERF_EF_UPDATE);
+
+	ddr_perf_free_counter(pmu, counter);
+	pmu->active_events--;
+	hwc->idx = -1;
+}
+
+static void ddr_perf_pmu_enable(struct pmu *pmu)
+{
+	struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu);
+
+	/* enable cycle counter if cycle is not active event list */
+	if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL)
+		ddr_perf_counter_enable(ddr_pmu,
+				      EVENT_CYCLES_ID,
+				      EVENT_CYCLES_COUNTER,
+				      true);
+}
+
+static void ddr_perf_pmu_disable(struct pmu *pmu)
+{
+	struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu);
+
+	if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL)
+		ddr_perf_counter_enable(ddr_pmu,
+				      EVENT_CYCLES_ID,
+				      EVENT_CYCLES_COUNTER,
+				      false);
+}
+
+static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base,
+			 struct device *dev)
+{
+	*pmu = (struct ddr_pmu) {
+		.pmu = (struct pmu) {
+			.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+			.task_ctx_nr = perf_invalid_context,
+			.attr_groups = attr_groups,
+			.event_init  = ddr_perf_event_init,
+			.add	     = ddr_perf_event_add,
+			.del	     = ddr_perf_event_del,
+			.start	     = ddr_perf_event_start,
+			.stop	     = ddr_perf_event_stop,
+			.read	     = ddr_perf_event_update,
+			.pmu_enable  = ddr_perf_pmu_enable,
+			.pmu_disable = ddr_perf_pmu_disable,
+		},
+		.base = base,
+		.dev = dev,
+	};
+
+	pmu->id = ida_simple_get(&ddr_ida, 0, 0, GFP_KERNEL);
+	return pmu->id;
+}
+
+static irqreturn_t ddr_perf_irq_handler(int irq, void *p)
+{
+	int i;
+	struct ddr_pmu *pmu = (struct ddr_pmu *) p;
+	struct perf_event *event, *cycle_event = NULL;
+
+	/* all counter will stop if cycle counter disabled */
+	ddr_perf_counter_enable(pmu,
+			      EVENT_CYCLES_ID,
+			      EVENT_CYCLES_COUNTER,
+			      false);
+	/*
+	 * When the cycle counter overflows, all counters are stopped,
+	 * and an IRQ is raised. If any other counter overflows, it
+	 * continues counting, and no IRQ is raised.
+	 *
+	 * Cycles occur at least 4 times as often as other events, so we
+	 * can update all events on a cycle counter overflow and not
+	 * lose events.
+	 *
+	 */
+	for (i = 0; i < NUM_COUNTERS; i++) {
+
+		if (!pmu->events[i])
+			continue;
+
+		event = pmu->events[i];
+
+		ddr_perf_event_update(event);
+
+		if (event->hw.idx == EVENT_CYCLES_COUNTER)
+			cycle_event = event;
+	}
+
+	ddr_perf_counter_enable(pmu,
+			      EVENT_CYCLES_ID,
+			      EVENT_CYCLES_COUNTER,
+			      true);
+	if (cycle_event)
+		ddr_perf_event_update(cycle_event);
+
+	return IRQ_HANDLED;
+}
+
+static int ddr_perf_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct ddr_pmu *pmu = hlist_entry_safe(node, struct ddr_pmu, node);
+	int target;
+
+	if (cpu != pmu->cpu)
+		return 0;
+
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+
+	perf_pmu_migrate_context(&pmu->pmu, cpu, target);
+	pmu->cpu = target;
+
+	WARN_ON(irq_set_affinity_hint(pmu->irq, cpumask_of(pmu->cpu)));
+
+	return 0;
+}
+
+static int ddr_perf_probe(struct platform_device *pdev)
+{
+	struct ddr_pmu *pmu;
+	struct device_node *np;
+	void __iomem *base;
+	char *name;
+	int num;
+	int ret;
+	int irq;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	np = pdev->dev.of_node;
+
+	pmu = devm_kzalloc(&pdev->dev, sizeof(*pmu), GFP_KERNEL);
+	if (!pmu)
+		return -ENOMEM;
+
+	num = ddr_perf_init(pmu, base, &pdev->dev);
+
+	platform_set_drvdata(pdev, pmu);
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME "%d",
+			      num);
+	if (!name)
+		return -ENOMEM;
+
+	pmu->cpu = raw_smp_processor_id();
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+				      DDR_CPUHP_CB_NAME,
+				      NULL,
+				      ddr_perf_offline_cpu);
+
+	if (ret < 0) {
+		dev_err(&pdev->dev, "cpuhp_setup_state_multi failed\n");
+		goto ddr_perf_err;
+	}
+
+	pmu->cpuhp_state = ret;
+
+	/* Register the pmu instance for cpu hotplug */
+	cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+
+	/* Request irq */
+	irq = of_irq_get(np, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "Failed to get irq: %d", irq);
+		ret = irq;
+		goto ddr_perf_err;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq,
+					ddr_perf_irq_handler,
+					IRQF_NOBALANCING | IRQF_NO_THREAD,
+					DDR_CPUHP_CB_NAME,
+					pmu);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Request irq failed: %d", ret);
+		goto ddr_perf_err;
+	}
+
+	pmu->irq = irq;
+	ret = irq_set_affinity_hint(pmu->irq, cpumask_of(pmu->cpu));
+	if (ret) {
+		dev_err(pmu->dev, "Failed to set interrupt affinity!\n");
+		goto ddr_perf_err;
+	}
+
+	ret = perf_pmu_register(&pmu->pmu, name, -1);
+	if (ret)
+		goto ddr_perf_err;
+
+	return 0;
+
+ddr_perf_err:
+	if (pmu->cpuhp_state)
+		cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+
+	ida_simple_remove(&ddr_ida, pmu->id);
+	dev_warn(&pdev->dev, "i.MX8 DDR Perf PMU failed (%d), disabled\n", ret);
+	return ret;
+}
+
+static int ddr_perf_remove(struct platform_device *pdev)
+{
+	struct ddr_pmu *pmu = platform_get_drvdata(pdev);
+
+	cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node);
+	irq_set_affinity_hint(pmu->irq, NULL);
+
+	perf_pmu_unregister(&pmu->pmu);
+
+	ida_simple_remove(&ddr_ida, pmu->id);
+	return 0;
+}
+
+static struct platform_driver imx_ddr_pmu_driver = {
+	.driver         = {
+		.name   = "imx-ddr-pmu",
+		.of_match_table = imx_ddr_pmu_dt_ids,
+	},
+	.probe          = ddr_perf_probe,
+	.remove         = ddr_perf_remove,
+};
+
+module_platform_driver(imx_ddr_pmu_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d315d86844e4..5bcd23e5ccd6 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1303,6 +1303,7 @@ static inline int lpit_read_residency_count_address(u64 *address)
 #ifdef CONFIG_ACPI_PPTT
 int find_acpi_cpu_topology(unsigned int cpu, int level);
 int find_acpi_cpu_topology_package(unsigned int cpu);
+int find_acpi_cpu_topology_hetero_id(unsigned int cpu);
 int find_acpi_cpu_cache_topology(unsigned int cpu, int level);
 #else
 static inline int find_acpi_cpu_topology(unsigned int cpu, int level)
@@ -1313,6 +1314,10 @@ static inline int find_acpi_cpu_topology_package(unsigned int cpu)
 {
 	return -EINVAL;
 }
+static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu)
+{
+	return -EINVAL;
+}
 static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
 {
 	return -EINVAL;
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 4641e850b204..784bc58f165a 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -175,4 +175,6 @@ void armpmu_free_irq(int irq, int cpu);
 
 #endif /* CONFIG_ARM_PMU */
 
+#define ARMV8_SPE_PDEV_NAME "arm,spe-v1"
+
 #endif /* __ARM_PMU_H__ */