as when we migrate the perf context we will access the DSU
from two different CPUs (source and destination).
- Fill in the "module" field for the PMU to prevent the module unload
when the PMU is active.
Changes since V6:
- Address comments from Jonathan
- Add Reviewed-by tags from Jonathan
Changes since V5:
- Address comments on V5 by Mark.
- Use IRQ_NOBALANCING for IRQ handler
- Don't expose events which could be unimplemented.
- Get rid of dsu_pmu_event_supported and allow raw event
code to be used without validating whether it is supported.
- Rename "supported_cpus" mask to "associated_cpus"
- Add Documentation for the PMU driver
- Don't disable IRQ for dsu_pmu_{enable/disable}_counters
- Use consistent return codes for validate_event/group calls.
- Check PERF_ATTACH_TASK flag in event_init.
- Allow missing CPUs in dsu_pmu_dt_get_cpus, to handle cases
where kernel could have capped nr_cpus.
- Cleanup sanity checking for the CPU before accessing DSU
- Reject events with counting CPU not associated with the DSU.
Changes since V4:
- Reflect the changed generic helper for mapping CPU id
Changes since V2:
- Cleanup dsu_pmu_device_probe error handling.
- Fix event validate_group to invert the result check of validate_event
- Return errors if we failed to parse CPUs in the DSU.
- Add MODULE_DEVICE_TABLE entry
- Use hlist_entry_safe for converting cpuhp_node to dsu_pmu.
---
Documentation/perf/arm_dsu_pmu.txt | 28 ++
arch/arm64/include/asm/arm_dsu_pmu.h | 129 ++++++
drivers/perf/Kconfig | 9 +
drivers/perf/Makefile | 1 +
drivers/perf/arm_dsu_pmu.c | 843 +++++++++++++++++++++++++++++++++++
5 files changed, 1010 insertions(+)
create mode 100644 Documentation/perf/arm_dsu_pmu.txt
create mode 100644 arch/arm64/include/asm/arm_dsu_pmu.h
create mode 100644 drivers/perf/arm_dsu_pmu.c
diff --git a/Documentation/perf/arm_dsu_pmu.txt
b/Documentation/perf/arm_dsu_pmu.txt
new file mode 100644
index 000000000000..d611e15f5add
--- /dev/null
+++ b/Documentation/perf/arm_dsu_pmu.txt
@@ -0,0 +1,28 @@
+ARM DynamIQ Shared Unit (DSU) PMU
+==================================
+
+ARM DynamIQ Shared Unit integrates one or more cores with an L3 memory system,
+control logic and external interfaces to form a multicore cluster. The PMU
+allows counting the various events related to the L3 cache, Snoop Control Unit
+etc, using 32bit independent counters. It also provides a 64bit cycle counter.
+
+The PMU can only be accessed via CPU system registers and are common to the
+cores connected to the same DSU. Like most of the other uncore PMUs, DSU
+PMU doesn't support process specific events and cannot be used in sampling
mode.
+
+The DSU provides a bitmap for a subset of implemented events via hardware
+registers. There is no way for the driver to determine if the other events
+are available or not. Hence the driver exposes only those events advertised
+by the DSU, in "events" directory under :
+
+ /sys/bus/event_sources/devices/arm_dsu_<N>/
+
+The user should refer to the TRM of the product to figure out the supported
events
+and use the raw event code for the unlisted events.
+
+The driver also exposes the CPUs connected to the DSU instance in
"associated_cpus".
+
+
+e.g usage :
+
+ perf stat -a -e arm_dsu_0/cycles/
diff --git a/arch/arm64/include/asm/arm_dsu_pmu.h
b/arch/arm64/include/asm/arm_dsu_pmu.h
new file mode 100644
index 000000000000..82e5cc3356bf
--- /dev/null
+++ b/arch/arm64/include/asm/arm_dsu_pmu.h
@@ -0,0 +1,129 @@
+/*
+ * ARM DynamIQ Shared Unit (DSU) PMU Low level register access routines.
+ *
+ * Copyright (C) ARM Limited, 2017.
+ *
+ * Author: Suzuki K Poulose <suzuki.poul...@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/barrier.h>
+#include <asm/sysreg.h>
+
+
+#define CLUSTERPMCR_EL1 sys_reg(3, 0, 15, 5, 0)
+#define CLUSTERPMCNTENSET_EL1 sys_reg(3, 0, 15, 5, 1)
+#define CLUSTERPMCNTENCLR_EL1 sys_reg(3, 0, 15, 5, 2)
+#define CLUSTERPMOVSSET_EL1 sys_reg(3, 0, 15, 5, 3)
+#define CLUSTERPMOVSCLR_EL1 sys_reg(3, 0, 15, 5, 4)
+#define CLUSTERPMSELR_EL1 sys_reg(3, 0, 15, 5, 5)
+#define CLUSTERPMINTENSET_EL1 sys_reg(3, 0, 15, 5, 6)
+#define CLUSTERPMINTENCLR_EL1 sys_reg(3, 0, 15, 5, 7)
+#define CLUSTERPMCCNTR_EL1 sys_reg(3, 0, 15, 6, 0)
+#define CLUSTERPMXEVTYPER_EL1 sys_reg(3, 0, 15, 6, 1)
+#define CLUSTERPMXEVCNTR_EL1 sys_reg(3, 0, 15, 6, 2)
+#define CLUSTERPMMDCR_EL1 sys_reg(3, 0, 15, 6, 3)
+#define CLUSTERPMCEID0_EL1 sys_reg(3, 0, 15, 6, 4)
+#define CLUSTERPMCEID1_EL1 sys_reg(3, 0, 15, 6, 5)
+
+static inline u32 __dsu_pmu_read_pmcr(void)
+{
+ return read_sysreg_s(CLUSTERPMCR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmcr(u32 val)
+{
+ write_sysreg_s(val, CLUSTERPMCR_EL1);
+ isb();
+}
+
+static inline u32 __dsu_pmu_get_reset_overflow(void)
+{
+ u32 val = read_sysreg_s(CLUSTERPMOVSCLR_EL1);
+ /* Clear the bit */
+ write_sysreg_s(val, CLUSTERPMOVSCLR_EL1);
+ isb();
+ return val;
+}
+
+static inline void __dsu_pmu_select_counter(int counter)
+{
+ write_sysreg_s(counter, CLUSTERPMSELR_EL1);
+ isb();
+}
+
+static inline u64 __dsu_pmu_read_counter(int counter)
+{
+ __dsu_pmu_select_counter(counter);
+ return read_sysreg_s(CLUSTERPMXEVCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_counter(int counter, u64 val)
+{
+ __dsu_pmu_select_counter(counter);
+ write_sysreg_s(val, CLUSTERPMXEVCNTR_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_set_event(int counter, u32 event)
+{
+ __dsu_pmu_select_counter(counter);
+ write_sysreg_s(event, CLUSTERPMXEVTYPER_EL1);
+ isb();
+}
+
+static inline u64 __dsu_pmu_read_pmccntr(void)
+{
+ return read_sysreg_s(CLUSTERPMCCNTR_EL1);
+}
+
+static inline void __dsu_pmu_write_pmccntr(u64 val)
+{
+ write_sysreg_s(val, CLUSTERPMCCNTR_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_disable_counter(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMCNTENCLR_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_enable_counter(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMCNTENSET_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_enable(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMINTENSET_EL1);
+ isb();
+}
+
+static inline void __dsu_pmu_counter_interrupt_disable(int counter)
+{
+ write_sysreg_s(BIT(counter), CLUSTERPMINTENCLR_EL1);
+ isb();
+}
+
+
+static inline u32 __dsu_pmu_read_pmceid(int n)
+{
+ switch (n) {
+ case 0:
+ return read_sysreg_s(CLUSTERPMCEID0_EL1);
+ case 1:
+ return read_sysreg_s(CLUSTERPMCEID1_EL1);
+ default:
+ BUILD_BUG();
+ return 0;
+ }
+}
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index b8f44b068fc6..da5724cd89cf 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -17,6 +17,15 @@ config ARM_PMU_ACPI
depends on ARM_PMU && ACPI
def_bool y
+config ARM_DSU_PMU
+ tristate "ARM DynamIQ Shared Unit (DSU) PMU"
+ depends on ARM64
+ help
+ Provides support for performance monitor unit in ARM DynamIQ Shared
+ Unit (DSU). The DSU integrates one or more cores with an L3 memory
+ system, control logic. The PMU allows counting various events related
+ to DSU.
+
config HISI_PMU
bool "HiSilicon SoC PMU"
depends on ARM64 && ACPI
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 710a0135bd61..c2f27419bdf0 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -1,4 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
+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_HISI_PMU) += hisilicon/
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
new file mode 100644
index 000000000000..37c0526c93d5
--- /dev/null
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -0,0 +1,843 @@
+/*
+ * ARM DynamIQ Shared Unit (DSU) PMU driver
+ *
+ * Copyright (C) ARM Limited, 2017.
+ *
+ * Based on ARM CCI-PMU, ARMv8 PMU-v3 drivers.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#define PMUNAME "arm_dsu"
+#define DRVNAME PMUNAME "_pmu"
+#define pr_fmt(fmt) DRVNAME ": " fmt
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#include <asm/arm_dsu_pmu.h>
+#include <asm/local64.h>
+
+/* PMU event codes */
+#define DSU_PMU_EVT_CYCLES 0x11
+#define DSU_PMU_EVT_CHAIN 0x1e
+
+#define DSU_PMU_MAX_COMMON_EVENTS 0x40
+
+#define DSU_PMU_MAX_HW_CNTRS 32
+#define DSU_PMU_HW_COUNTER_MASK (DSU_PMU_MAX_HW_CNTRS - 1)
+
+#define CLUSTERPMCR_E BIT(0)
+#define CLUSTERPMCR_P BIT(1)
+#define CLUSTERPMCR_C BIT(2)
+#define CLUSTERPMCR_N_SHIFT 11
+#define CLUSTERPMCR_N_MASK 0x1f
+#define CLUSTERPMCR_IDCODE_SHIFT 16
+#define CLUSTERPMCR_IDCODE_MASK 0xff
+#define CLUSTERPMCR_IMP_SHIFT 24
+#define CLUSTERPMCR_IMP_MASK 0xff
+#define CLUSTERPMCR_RES_MASK 0x7e8
+#define CLUSTERPMCR_RES_VAL 0x40
+
+#define DSU_ACTIVE_CPU_MASK 0x0
+#define DSU_ASSOCIATED_CPU_MASK 0x1
+
+/*
+ * We use the index of the counters as they appear in the counter
+ * bit maps in the PMU registers (e.g CLUSTERPMSELR).
+ * i.e,
+ * counter 0 - Bit 0
+ * counter 1 - Bit 1
+ * ...
+ * Cycle counter - Bit 31
+ */
+#define DSU_PMU_IDX_CYCLE_COUNTER 31
+
+/* All event counters are 32bit, with a 64bit Cycle counter */
+#define DSU_PMU_COUNTER_WIDTH(idx) \
+ (((idx) == DSU_PMU_IDX_CYCLE_COUNTER) ? 64 : 32)
+
+#define DSU_PMU_COUNTER_MASK(idx) \
+ GENMASK_ULL((DSU_PMU_COUNTER_WIDTH((idx)) - 1), 0)
+
+#define DSU_EXT_ATTR(_name, _func, _config) \
+ (&((struct dev_ext_attribute[]) { \
+ { \
+ .attr = __ATTR(_name, 0444, _func, NULL), \
+ .var = (void *)_config \
+ } \
+ })[0].attr.attr)
+
+#define DSU_EVENT_ATTR(_name, _config) \
+ DSU_EXT_ATTR(_name, dsu_pmu_sysfs_event_show, (unsigned long)_config)
+
+#define DSU_FORMAT_ATTR(_name, _config) \
+ DSU_EXT_ATTR(_name, dsu_pmu_sysfs_format_show, (char *)_config)
+
+#define DSU_CPUMASK_ATTR(_name, _config) \
+ DSU_EXT_ATTR(_name, dsu_pmu_cpumask_show, (unsigned long)_config)
+
+struct dsu_hw_events {
+ DECLARE_BITMAP(used_mask, DSU_PMU_MAX_HW_CNTRS);
+ struct perf_event *events[DSU_PMU_MAX_HW_CNTRS];
+};
+
+/*
+ * struct dsu_pmu - DSU PMU descriptor
+ *
+ * @pmu_lock : Protects accesses to DSU PMU register from normal vs
+ * interrupt handler contexts.
+ * @hw_events : Holds the event counter state.
+ * @associated_cpus : CPUs attached to the DSU.
+ * @active_cpu : CPU to which the PMU is bound for accesses.
+ * @cpuhp_node : Node for CPU hotplug notifier link.
+ * @num_counters : Number of event counters implemented by the PMU,
+ * excluding the cycle counter.
+ * @irq : Interrupt line for counter overflow.
+ * @cpmceid_bitmap : Bitmap for the availability of architected common
+ * events (event_code < 0x40).
+ */
+struct dsu_pmu {
+ struct pmu pmu;
+ struct device *dev;
+ raw_spinlock_t pmu_lock;
+ struct dsu_hw_events hw_events;
+ cpumask_t associated_cpus;
+ cpumask_t active_cpu;
+ struct hlist_node cpuhp_node;
+ u8 num_counters;
+ int irq;
+ DECLARE_BITMAP(cpmceid_bitmap, DSU_PMU_MAX_COMMON_EVENTS);
+};
+
+static unsigned long dsu_pmu_cpuhp_state;
+
+static inline struct dsu_pmu *to_dsu_pmu(struct pmu *pmu)
+{
+ return container_of(pmu, struct dsu_pmu, pmu);
+}
+
+static ssize_t dsu_pmu_sysfs_event_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct dev_ext_attribute *eattr = container_of(attr,
+ struct dev_ext_attribute, attr);
+ return snprintf(buf, PAGE_SIZE, "event=0x%lx\n",
+ (unsigned long)eattr->var);
+}
+
+static ssize_t dsu_pmu_sysfs_format_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct dev_ext_attribute *eattr = container_of(attr,
+ struct dev_ext_attribute, attr);
+ return snprintf(buf, PAGE_SIZE, "%s\n", (char *)eattr->var);
+}
+
+static ssize_t dsu_pmu_cpumask_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct pmu *pmu = dev_get_drvdata(dev);
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+ struct dev_ext_attribute *eattr = container_of(attr,
+ struct dev_ext_attribute, attr);
+ unsigned long mask_id = (unsigned long)eattr->var;
+ const cpumask_t *cpumask;
+
+ switch (mask_id) {
+ case DSU_ACTIVE_CPU_MASK:
+ cpumask = &dsu_pmu->active_cpu;
+ break;
+ case DSU_ASSOCIATED_CPU_MASK:
+ cpumask = &dsu_pmu->associated_cpus;
+ break;
+ default:
+ return 0;
+ }
+ return cpumap_print_to_pagebuf(true, buf, cpumask);
+}
+
+static struct attribute *dsu_pmu_format_attrs[] = {
+ DSU_FORMAT_ATTR(event, "config:0-31"),
+ NULL,
+};
+
+static const struct attribute_group dsu_pmu_format_attr_group = {
+ .name = "format",
+ .attrs = dsu_pmu_format_attrs,
+};
+
+static struct attribute *dsu_pmu_event_attrs[] = {
+ DSU_EVENT_ATTR(cycles, 0x11),
+ DSU_EVENT_ATTR(bus_access, 0x19),
+ DSU_EVENT_ATTR(memory_error, 0x1a),
+ DSU_EVENT_ATTR(bus_cycles, 0x1d),
+ DSU_EVENT_ATTR(l3d_cache_allocate, 0x29),
+ DSU_EVENT_ATTR(l3d_cache_refill, 0x2a),
+ DSU_EVENT_ATTR(l3d_cache, 0x2b),
+ DSU_EVENT_ATTR(l3d_cache_wb, 0x2c),
+ NULL,
+};
+
+static umode_t
+dsu_pmu_event_attr_is_visible(struct kobject *kobj, struct attribute *attr,
+ int unused)
+{
+ struct pmu *pmu = dev_get_drvdata(kobj_to_dev(kobj));
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+ struct dev_ext_attribute *eattr = container_of(attr,
+ struct dev_ext_attribute, attr.attr);
+ unsigned long evt = (unsigned long)eattr->var;
+
+ return test_bit(evt, dsu_pmu->cpmceid_bitmap) ? attr->mode : 0;
+}
+
+static const struct attribute_group dsu_pmu_events_attr_group = {
+ .name = "events",
+ .attrs = dsu_pmu_event_attrs,
+ .is_visible = dsu_pmu_event_attr_is_visible,
+};
+
+static struct attribute *dsu_pmu_cpumask_attrs[] = {
+ DSU_CPUMASK_ATTR(cpumask, DSU_ACTIVE_CPU_MASK),
+ DSU_CPUMASK_ATTR(associated_cpus, DSU_ASSOCIATED_CPU_MASK),
+ NULL,
+};
+
+static const struct attribute_group dsu_pmu_cpumask_attr_group = {
+ .attrs = dsu_pmu_cpumask_attrs,
+};
+
+static const struct attribute_group *dsu_pmu_attr_groups[] = {
+ &dsu_pmu_cpumask_attr_group,
+ &dsu_pmu_events_attr_group,
+ &dsu_pmu_format_attr_group,
+ NULL,
+};
+
+static int dsu_pmu_get_online_cpu_any_but(struct dsu_pmu *dsu_pmu, int cpu)
+{
+ struct cpumask online_supported;
+
+ cpumask_and(&online_supported,
+ &dsu_pmu->associated_cpus, cpu_online_mask);
+ return cpumask_any_but(&online_supported, cpu);
+}
+
+static inline bool dsu_pmu_counter_valid(struct dsu_pmu *dsu_pmu, u32 idx)
+{
+ return (idx < dsu_pmu->num_counters) ||
+ (idx == DSU_PMU_IDX_CYCLE_COUNTER);
+}
+
+static inline u64 dsu_pmu_read_counter(struct perf_event *event)
+{
+ u64 val;
+ unsigned long flags;
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+ int idx = event->hw.idx;
+
+ if (WARN_ON(!cpumask_test_cpu(smp_processor_id(),
+ &dsu_pmu->associated_cpus)))
+ return 0;
+
+ if (!dsu_pmu_counter_valid(dsu_pmu, idx)) {
+ dev_err(event->pmu->dev,
+ "Trying reading invalid counter %d\n", idx);
+ return 0;
+ }
+
+ raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+ if (idx == DSU_PMU_IDX_CYCLE_COUNTER)
+ val = __dsu_pmu_read_pmccntr();
+ else
+ val = __dsu_pmu_read_counter(idx);
+ raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+
+ return val;
+}
+
+static void dsu_pmu_write_counter(struct perf_event *event, u64 val)
+{
+ unsigned long flags;
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+ int idx = event->hw.idx;
+
+ if (WARN_ON(!cpumask_test_cpu(smp_processor_id(),
+ &dsu_pmu->associated_cpus)))
+ return;
+
+ if (!dsu_pmu_counter_valid(dsu_pmu, idx)) {
+ dev_err(event->pmu->dev,
+ "writing to invalid counter %d\n", idx);
+ return;
+ }
+
+ raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+ if (idx == DSU_PMU_IDX_CYCLE_COUNTER)
+ __dsu_pmu_write_pmccntr(val);
+ else
+ __dsu_pmu_write_counter(idx, val);
+ raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static int dsu_pmu_get_event_idx(struct dsu_hw_events *hw_events,
+ struct perf_event *event)
+{
+ int idx;
+ unsigned long evtype = event->attr.config;
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+ unsigned long *used_mask = hw_events->used_mask;
+
+ if (evtype == DSU_PMU_EVT_CYCLES) {
+ if (test_and_set_bit(DSU_PMU_IDX_CYCLE_COUNTER, used_mask))
+ return -EAGAIN;
+ return DSU_PMU_IDX_CYCLE_COUNTER;
+ }
+
+ idx = find_first_zero_bit(used_mask, dsu_pmu->num_counters);
+ if (idx >= dsu_pmu->num_counters)
+ return -EAGAIN;
+ set_bit(idx, hw_events->used_mask);
+ return idx;
+}
+
+static void dsu_pmu_enable_counter(struct dsu_pmu *dsu_pmu, int idx)
+{
+ __dsu_pmu_counter_interrupt_enable(idx);
+ __dsu_pmu_enable_counter(idx);
+}
+
+static void dsu_pmu_disable_counter(struct dsu_pmu *dsu_pmu, int idx)
+{
+ __dsu_pmu_disable_counter(idx);
+ __dsu_pmu_counter_interrupt_disable(idx);
+}
+
+static inline void dsu_pmu_set_event(struct dsu_pmu *dsu_pmu,
+ struct perf_event *event)
+{
+ int idx = event->hw.idx;
+ unsigned long flags;
+
+ if (!dsu_pmu_counter_valid(dsu_pmu, idx)) {
+ dev_err(event->pmu->dev,
+ "Trying to set invalid counter %d\n", idx);
+ return;
+ }
+
+ raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+ __dsu_pmu_set_event(idx, event->hw.config_base);
+ raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static void dsu_pmu_event_update(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 delta, prev_count, new_count;
+
+ do {
+ /* We may also be called from the irq handler */
+ prev_count = local64_read(&hwc->prev_count);
+ new_count = dsu_pmu_read_counter(event);
+ } while (local64_cmpxchg(&hwc->prev_count, prev_count, new_count) !=
+ prev_count);
+ delta = (new_count - prev_count) & DSU_PMU_COUNTER_MASK(hwc->idx);
+ local64_add(delta, &event->count);
+}
+
+static void dsu_pmu_read(struct perf_event *event)
+{
+ dsu_pmu_event_update(event);
+}
+
+static inline u32 dsu_pmu_get_reset_overflow(void)
+{
+ return __dsu_pmu_get_reset_overflow();
+}
+
+/**
+ * dsu_pmu_set_event_period: Set the period for the counter.
+ *
+ * All DSU PMU event counters, except the cycle counter are 32bit
+ * counters. To handle cases of extreme interrupt latency, we program
+ * the counter with half of the max count for the counters.
+ */
+static void dsu_pmu_set_event_period(struct perf_event *event)
+{
+ int idx = event->hw.idx;
+ u64 val = DSU_PMU_COUNTER_MASK(idx) >> 1;
+
+ local64_set(&event->hw.prev_count, val);
+ dsu_pmu_write_counter(event, val);
+}
+
+static irqreturn_t dsu_pmu_handle_irq(int irq_num, void *dev)
+{
+ int i;
+ bool handled = false;
+ struct dsu_pmu *dsu_pmu = dev;
+ struct dsu_hw_events *hw_events = &dsu_pmu->hw_events;
+ unsigned long overflow;
+
+ overflow = dsu_pmu_get_reset_overflow();
+ if (!overflow)
+ return IRQ_NONE;
+
+ for_each_set_bit(i, &overflow, DSU_PMU_MAX_HW_CNTRS) {
+ struct perf_event *event = hw_events->events[i];
+
+ if (!event)
+ continue;
+ dsu_pmu_event_update(event);
+ dsu_pmu_set_event_period(event);
+ handled = true;
+ }
+
+ return IRQ_RETVAL(handled);
+}
+
+static void dsu_pmu_start(struct perf_event *event, int pmu_flags)
+{
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+
+ /* We always reprogram the counter */
+ if (pmu_flags & PERF_EF_RELOAD)
+ WARN_ON(!(event->hw.state & PERF_HES_UPTODATE));
+ dsu_pmu_set_event_period(event);
+ if (event->hw.idx != DSU_PMU_IDX_CYCLE_COUNTER)
+ dsu_pmu_set_event(dsu_pmu, event);
+ event->hw.state = 0;
+ dsu_pmu_enable_counter(dsu_pmu, event->hw.idx);
+}
+
+static void dsu_pmu_stop(struct perf_event *event, int pmu_flags)
+{
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+
+ if (event->hw.state & PERF_HES_STOPPED)
+ return;
+ dsu_pmu_disable_counter(dsu_pmu, event->hw.idx);
+ dsu_pmu_event_update(event);
+ event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int dsu_pmu_add(struct perf_event *event, int flags)
+{
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+ struct dsu_hw_events *hw_events = &dsu_pmu->hw_events;
+ struct hw_perf_event *hwc = &event->hw;
+ int idx;
+
+ if (WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(),
+ &dsu_pmu->associated_cpus)))
+ return -ENOENT;
+
+ idx = dsu_pmu_get_event_idx(hw_events, event);
+ if (idx < 0)
+ return idx;
+
+ hwc->idx = idx;
+ hw_events->events[idx] = event;
+ hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
+ if (flags & PERF_EF_START)
+ dsu_pmu_start(event, PERF_EF_RELOAD);
+
+ perf_event_update_userpage(event);
+ return 0;
+}
+
+static void dsu_pmu_del(struct perf_event *event, int flags)
+{
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+ struct dsu_hw_events *hw_events = &dsu_pmu->hw_events;
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ dsu_pmu_stop(event, PERF_EF_UPDATE);
+ hw_events->events[idx] = NULL;
+ clear_bit(idx, hw_events->used_mask);
+ perf_event_update_userpage(event);
+}
+
+static void dsu_pmu_enable(struct pmu *pmu)
+{
+ u32 pmcr;
+ unsigned long flags;
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+
+ /* If no counters are added, skip enabling the PMU */
+ if (bitmap_empty(dsu_pmu->hw_events.used_mask, DSU_PMU_MAX_HW_CNTRS))
+ return;
+
+ raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+ pmcr = __dsu_pmu_read_pmcr();
+ pmcr |= CLUSTERPMCR_E;
+ __dsu_pmu_write_pmcr(pmcr);
+ raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static void dsu_pmu_disable(struct pmu *pmu)
+{
+ u32 pmcr;
+ unsigned long flags;
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(pmu);
+
+ raw_spin_lock_irqsave(&dsu_pmu->pmu_lock, flags);
+ pmcr = __dsu_pmu_read_pmcr();
+ pmcr &= ~CLUSTERPMCR_E;
+ __dsu_pmu_write_pmcr(pmcr);
+ raw_spin_unlock_irqrestore(&dsu_pmu->pmu_lock, flags);
+}
+
+static bool dsu_pmu_validate_event(struct pmu *pmu,
+ struct dsu_hw_events *hw_events,
+ struct perf_event *event)
+{
+ if (is_software_event(event))
+ return true;
+ /* Reject groups spanning multiple HW PMUs. */
+ if (event->pmu != pmu)
+ return false;
+ return dsu_pmu_get_event_idx(hw_events, event) >= 0;
+}
+
+/*
+ * Make sure the group of events can be scheduled at once
+ * on the PMU.
+ */
+static bool dsu_pmu_validate_group(struct perf_event *event)
+{
+ struct perf_event *sibling, *leader = event->group_leader;
+ struct dsu_hw_events fake_hw;
+
+ if (event->group_leader == event)
+ return true;
+
+ memset(fake_hw.used_mask, 0, sizeof(fake_hw.used_mask));
+ if (!dsu_pmu_validate_event(event->pmu, &fake_hw, leader))
+ return false;
+ list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
+ if (!dsu_pmu_validate_event(event->pmu, &fake_hw, sibling))
+ return false;
+ }
+ return dsu_pmu_validate_event(event->pmu, &fake_hw, event);
+}
+
+static int dsu_pmu_event_init(struct perf_event *event)
+{
+ struct dsu_pmu *dsu_pmu = to_dsu_pmu(event->pmu);
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /* We don't support sampling */
+ if (is_sampling_event(event)) {
+ dev_dbg(dsu_pmu->pmu.dev, "Can't support sampling events\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* We cannot support task bound events */
+ if (event->cpu < 0 || event->attach_state & PERF_ATTACH_TASK) {
+ dev_dbg(dsu_pmu->pmu.dev, "Can't support per-task counters\n");
+ return -EINVAL;
+ }
+
+ if (has_branch_stack(event) ||
+ event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest) {
+ dev_dbg(dsu_pmu->pmu.dev, "Can't support filtering\n");
+ return -EINVAL;
+ }
+
+ if (!cpumask_test_cpu(event->cpu, &dsu_pmu->associated_cpus)) {
+ dev_dbg(dsu_pmu->pmu.dev,
+ "Requested cpu is not associated with the DSU\n");
+ return -EINVAL;
+ }
