aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/perf
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/perf')
-rw-r--r--drivers/perf/Kconfig18
-rw-r--r--drivers/perf/Makefile2
-rw-r--r--drivers/perf/arm-cci.c21
-rw-r--r--drivers/perf/arm-ccn.c34
-rw-r--r--drivers/perf/arm_dsu_pmu.c5
-rw-r--r--drivers/perf/arm_pmu.c1
-rw-r--r--drivers/perf/arm_pmu_acpi.c77
-rw-r--r--drivers/perf/arm_smmuv3_pmu.c865
-rw-r--r--drivers/perf/arm_spe_pmu.c35
-rw-r--r--drivers/perf/fsl_imx8_ddr_perf.c554
-rw-r--r--drivers/perf/hisilicon/Makefile1
-rw-r--r--drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c5
-rw-r--r--drivers/perf/hisilicon/hisi_uncore_hha_pmu.c5
-rw-r--r--drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c5
-rw-r--r--drivers/perf/hisilicon/hisi_uncore_pmu.c5
-rw-r--r--drivers/perf/hisilicon/hisi_uncore_pmu.h5
-rw-r--r--drivers/perf/qcom_l2_pmu.c10
-rw-r--r--drivers/perf/qcom_l3_pmu.c10
-rw-r--r--drivers/perf/xgene_pmu.c14
19 files changed, 1561 insertions, 111 deletions
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index af9bc178495d..09ae8a970880 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
#
# Performance Monitor Drivers
#
@@ -52,6 +53,15 @@ config ARM_PMU_ACPI
depends on ARM_PMU && ACPI
def_bool y
+config ARM_SMMU_V3_PMU
+ tristate "ARM SMMUv3 Performance Monitors Extension"
+ depends on ARM64 && ACPI && ARM_SMMU_V3
+ help
+ Provides support for the ARM SMMUv3 Performance Monitor Counter
+ Groups (PMCG), which provide monitoring of transactions passing
+ through the SMMU and allow the resulting information to be filtered
+ based on the Stream ID of the corresponding master.
+
config ARM_DSU_PMU
tristate "ARM DynamIQ Shared Unit (DSU) PMU"
depends on ARM64
@@ -61,6 +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 909f27fd9db3..2ebb4de17815 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -4,6 +4,8 @@ obj-$(CONFIG_ARM_CCN) += arm-ccn.o
obj-$(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-cci.c b/drivers/perf/arm-cci.c
index bfd03e023308..8f8606b9bc9e 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1684,21 +1684,24 @@ static int cci_pmu_probe(struct platform_device *pdev)
raw_spin_lock_init(&cci_pmu->hw_events.pmu_lock);
mutex_init(&cci_pmu->reserve_mutex);
atomic_set(&cci_pmu->active_events, 0);
- cci_pmu->cpu = get_cpu();
-
- ret = cci_pmu_init(cci_pmu, pdev);
- if (ret) {
- put_cpu();
- return ret;
- }
+ cci_pmu->cpu = raw_smp_processor_id();
+ g_cci_pmu = cci_pmu;
cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
"perf/arm/cci:online", NULL,
cci_pmu_offline_cpu);
- put_cpu();
- g_cci_pmu = cci_pmu;
+
+ ret = cci_pmu_init(cci_pmu, pdev);
+ if (ret)
+ goto error_pmu_init;
+
pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
return 0;
+
+error_pmu_init:
+ cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
+ g_cci_pmu = NULL;
+ return ret;
}
static int cci_pmu_remove(struct platform_device *pdev)
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 2ae76026e947..6fc0273b6129 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1,12 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*
* Copyright (C) 2014 ARM Limited
*/
@@ -167,7 +160,7 @@ struct arm_ccn_dt {
struct hrtimer hrtimer;
- cpumask_t cpu;
+ unsigned int cpu;
struct hlist_node node;
struct pmu pmu;
@@ -559,7 +552,7 @@ static ssize_t arm_ccn_pmu_cpumask_show(struct device *dev,
{
struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
- return cpumap_print_to_pagebuf(true, buf, &ccn->dt.cpu);
+ return cpumap_print_to_pagebuf(true, buf, cpumask_of(ccn->dt.cpu));
}
static struct device_attribute arm_ccn_pmu_cpumask_attr =
@@ -759,7 +752,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
* mitigate this, we enforce CPU assignment to one, selected
* processor (the one described in the "cpumask" attribute).
*/
- event->cpu = cpumask_first(&ccn->dt.cpu);
+ event->cpu = ccn->dt.cpu;
node_xp = CCN_CONFIG_NODE(event->attr.config);
type = CCN_CONFIG_TYPE(event->attr.config);
@@ -1215,15 +1208,15 @@ static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
unsigned int target;
- if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+ if (cpu != dt->cpu)
return 0;
target = cpumask_any_but(cpu_online_mask, cpu);
if (target >= nr_cpu_ids)
return 0;
perf_pmu_migrate_context(&dt->pmu, cpu, target);
- cpumask_set_cpu(target, &dt->cpu);
+ dt->cpu = target;
if (ccn->irq)
- WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
+ WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
return 0;
}
@@ -1299,29 +1292,30 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
}
/* Pick one CPU which we will use to collect data from CCN... */
- cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
+ ccn->dt.cpu = raw_smp_processor_id();
/* Also make sure that the overflow interrupt is handled by this CPU */
if (ccn->irq) {
- err = irq_set_affinity_hint(ccn->irq, &ccn->dt.cpu);
+ err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
if (err) {
dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
goto error_set_affinity;
}
}
+ cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+ &ccn->dt.node);
+
err = perf_pmu_register(&ccn->dt.pmu, name, -1);
if (err)
goto error_pmu_register;
- cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
- &ccn->dt.node);
- put_cpu();
return 0;
error_pmu_register:
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+ &ccn->dt.node);
error_set_affinity:
- put_cpu();
error_choose_name:
ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
for (i = 0; i < ccn->num_xps; i++)
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index 5851de56bbd0..70968c8c09d7 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* 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"
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index eec75b97e7ea..2d06b8095a19 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#undef DEBUG
/*
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 0f197516d708..acce8781c456 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* ACPI probing code for ARM performance counters.
*
* Copyright (C) 2017 ARM Ltd.
- *
- * 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/acpi.h>
@@ -74,6 +71,76 @@ 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 +346,8 @@ 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_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
new file mode 100644
index 000000000000..da71c741cb46
--- /dev/null
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * This driver adds support for perf events to use the Performance
+ * Monitor Counter Groups (PMCG) associated with an SMMUv3 node
+ * to monitor that node.
+ *
+ * SMMUv3 PMCG devices are named as smmuv3_pmcg_<phys_addr_page> where
+ * <phys_addr_page> is the physical page address of the SMMU PMCG wrapped
+ * to 4K boundary. For example, the PMCG at 0xff88840000 is named
+ * smmuv3_pmcg_ff88840
+ *
+ * Filtering by stream id is done by specifying filtering parameters
+ * with the event. options are:
+ * filter_enable - 0 = no filtering, 1 = filtering enabled
+ * filter_span - 0 = exact match, 1 = pattern match
+ * filter_stream_id - pattern to filter against
+ *
+ * To match a partial StreamID where the X most-significant bits must match
+ * but the Y least-significant bits might differ, STREAMID is programmed
+ * with a value that contains:
+ * STREAMID[Y - 1] == 0.
+ * STREAMID[Y - 2:0] == 1 (where Y > 1).
+ * The remainder of implemented bits of STREAMID (X bits, from bit Y upwards)
+ * contain a value to match from the corresponding bits of event StreamID.
+ *
+ * Example: perf stat -e smmuv3_pmcg_ff88840/transaction,filter_enable=1,
+ * filter_span=1,filter_stream_id=0x42/ -a netperf
+ * Applies filter pattern 0x42 to transaction events, which means events
+ * matching stream ids 0x42 and 0x43 are counted. Further filtering
+ * information is available in the SMMU documentation.
+ *
+ * SMMU events are not attributable to a CPU, so task mode and sampling
+ * are not supported.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/msi.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#define SMMU_PMCG_EVCNTR0 0x0
+#define SMMU_PMCG_EVCNTR(n, stride) (SMMU_PMCG_EVCNTR0 + (n) * (stride))
+#define SMMU_PMCG_EVTYPER0 0x400
+#define SMMU_PMCG_EVTYPER(n) (SMMU_PMCG_EVTYPER0 + (n) * 4)
+#define SMMU_PMCG_SID_SPAN_SHIFT 29
+#define SMMU_PMCG_SMR0 0xA00
+#define SMMU_PMCG_SMR(n) (SMMU_PMCG_SMR0 + (n) * 4)
+#define SMMU_PMCG_CNTENSET0 0xC00
+#define SMMU_PMCG_CNTENCLR0 0xC20
+#define SMMU_PMCG_INTENSET0 0xC40
+#define SMMU_PMCG_INTENCLR0 0xC60
+#define SMMU_PMCG_OVSCLR0 0xC80
+#define SMMU_PMCG_OVSSET0 0xCC0
+#define SMMU_PMCG_CFGR 0xE00
+#define SMMU_PMCG_CFGR_SID_FILTER_TYPE BIT(23)
+#define SMMU_PMCG_CFGR_MSI BIT(21)
+#define SMMU_PMCG_CFGR_RELOC_CTRS BIT(20)
+#define SMMU_PMCG_CFGR_SIZE GENMASK(13, 8)
+#define SMMU_PMCG_CFGR_NCTR GENMASK(5, 0)
+#define SMMU_PMCG_CR 0xE04
+#define SMMU_PMCG_CR_ENABLE BIT(0)
+#define SMMU_PMCG_CEID0 0xE20
+#define SMMU_PMCG_CEID1 0xE28
+#define SMMU_PMCG_IRQ_CTRL 0xE50
+#define SMMU_PMCG_IRQ_CTRL_IRQEN BIT(0)
+#define SMMU_PMCG_IRQ_CFG0 0xE58
+#define SMMU_PMCG_IRQ_CFG1 0xE60
+#define SMMU_PMCG_IRQ_CFG2 0xE64
+
+/* MSI config fields */
+#define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2)
+#define MSI_CFG2_MEMATTR_DEVICE_nGnRE 0x1
+
+#define SMMU_PMCG_DEFAULT_FILTER_SPAN 1
+#define SMMU_PMCG_DEFAULT_FILTER_SID GENMASK(31, 0)
+
+#define SMMU_PMCG_MAX_COUNTERS 64
+#define SMMU_PMCG_ARCH_MAX_EVENTS 128
+
+#define SMMU_PMCG_PA_SHIFT 12
+
+#define SMMU_PMCG_EVCNTR_RDONLY BIT(0)
+
+static int cpuhp_state_num;
+
+struct smmu_pmu {
+ struct hlist_node node;
+ struct perf_event *events[SMMU_PMCG_MAX_COUNTERS];
+ DECLARE_BITMAP(used_counters, SMMU_PMCG_MAX_COUNTERS);
+ DECLARE_BITMAP(supported_events, SMMU_PMCG_ARCH_MAX_EVENTS);
+ unsigned int irq;
+ unsigned int on_cpu;
+ struct pmu pmu;
+ unsigned int num_counters;
+ struct device *dev;
+ void __iomem *reg_base;
+ void __iomem *reloc_base;
+ u64 counter_mask;
+ u32 options;
+ bool global_filter;
+ u32 global_filter_span;
+ u32 global_filter_sid;
+};
+
+#define to_smmu_pmu(p) (container_of(p, struct smmu_pmu, pmu))
+
+#define SMMU_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end) \
+ static inline u32 get_##_name(struct perf_event *event) \
+ { \
+ return FIELD_GET(GENMASK_ULL(_end, _start), \
+ event->attr._config); \
+ } \
+
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 15);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_stream_id, config1, 0, 31);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_span, config1, 32, 32);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_enable, config1, 33, 33);
+
+static inline void smmu_pmu_enable(struct pmu *pmu)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+ writel(SMMU_PMCG_IRQ_CTRL_IRQEN,
+ smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+ writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR);
+}
+
+static inline void smmu_pmu_disable(struct pmu *pmu)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+ writel(0, smmu_pmu->reg_base + SMMU_PMCG_CR);
+ writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+}
+
+static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu,
+ u32 idx, u64 value)
+{
+ if (smmu_pmu->counter_mask & BIT(32))
+ writeq(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+ else
+ writel(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+}
+
+static inline u64 smmu_pmu_counter_get_value(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ u64 value;
+
+ if (smmu_pmu->counter_mask & BIT(32))
+ value = readq(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+ else
+ value = readl(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+
+ return value;
+}
+
+static inline void smmu_pmu_counter_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENSET0);
+}
+
+static inline void smmu_pmu_counter_disable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+}
+
+static inline void smmu_pmu_interrupt_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENSET0);
+}
+
+static inline void smmu_pmu_interrupt_disable(struct smmu_pmu *smmu_pmu,
+ u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+}
+
+static inline void smmu_pmu_set_evtyper(struct smmu_pmu *smmu_pmu, u32 idx,
+ u32 val)
+{
+ writel(val, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));
+}
+
+static inline void smmu_pmu_set_smr(struct smmu_pmu *smmu_pmu, u32 idx, u32 val)
+{
+ writel(val, smmu_pmu->reg_base + SMMU_PMCG_SMR(idx));
+}
+
+static void smmu_pmu_event_update(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ u64 delta, prev, now;
+ u32 idx = hwc->idx;
+
+ do {
+ prev = local64_read(&hwc->prev_count);
+ now = smmu_pmu_counter_get_value(smmu_pmu, idx);
+ } while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);
+
+ /* handle overflow. */
+ delta = now - prev;
+ delta &= smmu_pmu->counter_mask;
+
+ local64_add(delta, &event->count);
+}
+
+static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 idx = hwc->idx;
+ u64 new;
+
+ if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) {
+ /*
+ * On platforms that require this quirk, if the counter starts
+ * at < half_counter value and wraps, the current logic of
+ * handling the overflow may not work. It is expected that,
+ * those platforms will have full 64 counter bits implemented
+ * so that such a possibility is remote(eg: HiSilicon HIP08).
+ */
+ new = smmu_pmu_counter_get_value(smmu_pmu, idx);
+ } else {
+ /*
+ * We limit the max period to half the max counter value
+ * of the counter size, so that even in the case of extreme
+ * interrupt latency the counter will (hopefully) not wrap
+ * past its initial value.
+ */
+ new = smmu_pmu->counter_mask >> 1;
+ smmu_pmu_counter_set_value(smmu_pmu, idx, new);
+ }
+
+ local64_set(&hwc->prev_count, new);
+}
+
+static void smmu_pmu_set_event_filter(struct perf_event *event,
+ int idx, u32 span, u32 sid)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ u32 evtyper;
+
+ evtyper = get_event(event) | span << SMMU_PMCG_SID_SPAN_SHIFT;
+ smmu_pmu_set_evtyper(smmu_pmu, idx, evtyper);
+ smmu_pmu_set_smr(smmu_pmu, idx, sid);
+}
+
+static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
+ struct perf_event *event, int idx)
+{
+ u32 span, sid;
+ unsigned int num_ctrs = smmu_pmu->num_counters;
+ bool filter_en = !!get_filter_enable(event);
+
+ span = filter_en ? get_filter_span(event) :
+ SMMU_PMCG_DEFAULT_FILTER_SPAN;
+ sid = filter_en ? get_filter_stream_id(event) :
+ SMMU_PMCG_DEFAULT_FILTER_SID;
+
+ /* Support individual filter settings */
+ if (!smmu_pmu->global_filter) {
+ smmu_pmu_set_event_filter(event, idx, span, sid);
+ return 0;
+ }
+
+ /* Requested settings same as current global settings*/
+ if (span == smmu_pmu->global_filter_span &&
+ sid == smmu_pmu->global_filter_sid)
+ return 0;
+
+ if (!bitmap_empty(smmu_pmu->used_counters, num_ctrs))
+ return -EAGAIN;
+
+ smmu_pmu_set_event_filter(event, 0, span, sid);
+ smmu_pmu->global_filter_span = span;
+ smmu_pmu->global_filter_sid = sid;
+ return 0;
+}
+
+static int smmu_pmu_get_event_idx(struct smmu_pmu *smmu_pmu,
+ struct perf_event *event)
+{
+ int idx, err;
+ unsigned int num_ctrs = smmu_pmu->num_counters;
+
+ idx = find_first_zero_bit(smmu_pmu->used_counters, num_ctrs);
+ if (idx == num_ctrs)
+ /* The counters are all in use. */
+ return -EAGAIN;
+
+ err = smmu_pmu_apply_event_filter(smmu_pmu, event, idx);
+ if (err)
+ return err;
+
+ set_bit(idx, smmu_pmu->used_counters);
+
+ return idx;
+}
+
+/*
+ * Implementation of abstract pmu functionality required by
+ * the core perf events code.
+ */
+
+static int smmu_pmu_event_init(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ struct device *dev = smmu_pmu->dev;
+ struct perf_event *sibling;
+ u16 event_id;
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ if (hwc->sample_period) {
+ dev_dbg(dev, "Sampling not supported\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (event->cpu < 0) {
+ dev_dbg(dev, "Per-task mode not supported\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Verify specified event is supported on this PMU */
+ event_id = get_event(event);
+ if (event_id < SMMU_PMCG_ARCH_MAX_EVENTS &&
+ (!test_bit(event_id, smmu_pmu->supported_events))) {
+ dev_dbg(dev, "Invalid event %d for this PMU\n", event_id);
+ return -EINVAL;
+ }
+
+ /* Don't allow groups with mixed PMUs, except for s/w events */
+ if (event->group_leader->pmu != event->pmu &&
+ !is_software_event(event->group_leader)) {
+ dev_dbg(dev, "Can't create mixed PMU group\n");
+ return -EINVAL;
+ }
+
+ for_each_sibling_event(sibling, event->group_leader) {
+ if (sibling->pmu != event->pmu &&
+ !is_software_event(sibling)) {
+ dev_dbg(dev, "Can't create mixed PMU group\n");
+ return -EINVAL;
+ }
+ }
+
+ hwc->idx = -1;
+
+ /*
+ * Ensure all events are on the same cpu so all events are in the
+ * same cpu context, to avoid races on pmu_enable etc.
+ */
+ event->cpu = smmu_pmu->on_cpu;
+
+ return 0;
+}
+
+static void smmu_pmu_event_start(struct perf_event *event, int flags)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ hwc->state = 0;
+
+ smmu_pmu_set_period(smmu_pmu, hwc);
+
+ smmu_pmu_counter_enable(smmu_pmu, idx);
+}
+
+static void smmu_pmu_event_stop(struct perf_event *event, int flags)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ if (hwc->state & PERF_HES_STOPPED)
+ return;
+
+ smmu_pmu_counter_disable(smmu_pmu, idx);
+ /* As the counter gets updated on _start, ignore PERF_EF_UPDATE */
+ smmu_pmu_event_update(event);
+ hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int smmu_pmu_event_add(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ int idx;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+
+ idx = smmu_pmu_get_event_idx(smmu_pmu, event);
+ if (idx < 0)
+ return idx;
+
+ hwc->idx = idx;
+ hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+ smmu_pmu->events[idx] = event;
+ local64_set(&hwc->prev_count, 0);
+
+ smmu_pmu_interrupt_enable(smmu_pmu, idx);
+
+ if (flags & PERF_EF_START)
+ smmu_pmu_event_start(event, flags);
+
+ /* Propagate changes to the userspace mapping. */
+ perf_event_update_userpage(event);
+
+ return 0;
+}
+
+static void smmu_pmu_event_del(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ int idx = hwc->idx;
+
+ smmu_pmu_event_stop(event, flags | PERF_EF_UPDATE);
+ smmu_pmu_interrupt_disable(smmu_pmu, idx);
+ smmu_pmu->events[idx] = NULL;
+ clear_bit(idx, smmu_pmu->used_counters);
+
+ perf_event_update_userpage(event);
+}
+
+static void smmu_pmu_event_read(struct perf_event *event)
+{
+ smmu_pmu_event_update(event);
+}
+
+/* cpumask */
+
+static ssize_t smmu_pmu_cpumask_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+
+ return cpumap_print_to_pagebuf(true, buf, cpumask_of(smmu_pmu->on_cpu));
+}
+
+static struct device_attribute smmu_pmu_cpumask_attr =
+ __ATTR(cpumask, 0444, smmu_pmu_cpumask_show, NULL);
+
+static struct attribute *smmu_pmu_cpumask_attrs[] = {
+ &smmu_pmu_cpumask_attr.attr,
+ NULL
+};
+
+static struct attribute_group smmu_pmu_cpumask_group = {
+ .attrs = smmu_pmu_cpumask_attrs,
+};
+
+/* Events */
+
+static ssize_t smmu_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 SMMU_EVENT_ATTR(name, config) \
+ PMU_EVENT_ATTR(name, smmu_event_attr_##name, \
+ config, smmu_pmu_event_show)
+SMMU_EVENT_ATTR(cycles, 0);
+SMMU_EVENT_ATTR(transaction, 1);
+SMMU_EVENT_ATTR(tlb_miss, 2);
+SMMU_EVENT_ATTR(config_cache_miss, 3);
+SMMU_EVENT_ATTR(trans_table_walk_access, 4);
+SMMU_EVENT_ATTR(config_struct_access, 5);
+SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6);
+SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7);
+
+static struct attribute *smmu_pmu_events[] = {
+ &smmu_event_attr_cycles.attr.attr,
+ &smmu_event_attr_transaction.attr.attr,
+ &smmu_event_attr_tlb_miss.attr.attr,
+ &smmu_event_attr_config_cache_miss.attr.attr,
+ &smmu_event_attr_trans_table_walk_access.attr.attr,
+ &smmu_event_attr_config_struct_access.attr.attr,
+ &smmu_event_attr_pcie_ats_trans_rq.attr.attr,
+ &smmu_event_attr_pcie_ats_trans_passed.attr.attr,
+ NULL
+};
+
+static umode_t smmu_pmu_event_is_visible(struct kobject *kobj,
+ struct attribute *attr, int unused)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+
+ if (test_bit(pmu_attr->id, smmu_pmu->supported_events))
+ return attr->mode;
+
+ return 0;
+}
+
+static struct attribute_group smmu_pmu_events_group = {
+ .name = "events",
+ .attrs = smmu_pmu_events,
+ .is_visible = smmu_pmu_event_is_visible,
+};
+
+/* Formats */
+PMU_FORMAT_ATTR(event, "config:0-15");
+PMU_FORMAT_ATTR(filter_stream_id, "config1:0-31");
+PMU_FORMAT_ATTR(filter_span, "config1:32");
+PMU_FORMAT_ATTR(filter_enable, "config1:33");
+
+static struct attribute *smmu_pmu_formats[] = {
+ &format_attr_event.attr,
+ &format_attr_filter_stream_id.attr,
+ &format_attr_filter_span.attr,
+ &format_attr_filter_enable.attr,
+ NULL
+};
+
+static struct attribute_group smmu_pmu_format_group = {
+ .name = "format",
+ .attrs = smmu_pmu_formats,
+};
+
+static const struct attribute_group *smmu_pmu_attr_grps[] = {
+ &smmu_pmu_cpumask_group,
+ &smmu_pmu_events_group,
+ &smmu_pmu_format_group,
+ NULL
+};
+
+/*
+ * Generic device handlers
+ */
+
+static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+ struct smmu_pmu *smmu_pmu;
+ unsigned int target;
+
+ smmu_pmu = hlist_entry_safe(node, struct smmu_pmu, node);
+ if (cpu != smmu_pmu->on_cpu)
+ return 0;
+
+ target = cpumask_any_but(cpu_online_mask, cpu);
+ if (target >= nr_cpu_ids)
+ return 0;
+
+ perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
+ smmu_pmu->on_cpu = target;
+ WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));
+
+ return 0;
+}
+
+static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
+{
+ struct smmu_pmu *smmu_pmu = data;
+ u64 ovsr;
+ unsigned int idx;
+
+ ovsr = readq(smmu_pmu->reloc_base + SMMU_PMCG_OVSSET0);
+ if (!ovsr)
+ return IRQ_NONE;
+
+ writeq(ovsr, smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+
+ for_each_set_bit(idx, (unsigned long *)&ovsr, smmu_pmu->num_counters) {
+ struct perf_event *event = smmu_pmu->events[idx];
+ struct hw_perf_event *hwc;
+
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ smmu_pmu_event_update(event);
+ hwc = &event->hw;
+
+ smmu_pmu_set_period(smmu_pmu, hwc);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void smmu_pmu_free_msis(void *data)
+{
+ struct device *dev = data;
+
+ platform_msi_domain_free_irqs(dev);
+}
+
+static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+ phys_addr_t doorbell;
+ struct device *dev = msi_desc_to_dev(desc);
+ struct smmu_pmu *pmu = dev_get_drvdata(dev);
+
+ doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
+ doorbell &= MSI_CFG0_ADDR_MASK;
+
+ writeq_relaxed(doorbell, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+ writel_relaxed(msg->data, pmu->reg_base + SMMU_PMCG_IRQ_CFG1);
+ writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE,
+ pmu->reg_base + SMMU_PMCG_IRQ_CFG2);
+}
+
+static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
+{
+ struct msi_desc *desc;
+ struct device *dev = pmu->dev;
+ int ret;
+
+ /* Clear MSI address reg */
+ writeq_relaxed(0, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+
+ /* MSI supported or not */
+ if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI))
+ return;
+
+ ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
+ if (ret) {
+ dev_warn(dev, "failed to allocate MSIs\n");
+ return;
+ }
+
+ desc = first_msi_entry(dev);
+ if (desc)
+ pmu->irq = desc->irq;
+
+ /* Add callback to free MSIs on teardown */
+ devm_add_action(dev, smmu_pmu_free_msis, dev);
+}
+
+static int smmu_pmu_setup_irq(struct smmu_pmu *pmu)
+{
+ unsigned long flags = IRQF_NOBALANCING | IRQF_SHARED | IRQF_NO_THREAD;
+ int irq, ret = -ENXIO;
+
+ smmu_pmu_setup_msi(pmu);
+
+ irq = pmu->irq;
+ if (irq)
+ ret = devm_request_irq(pmu->dev, irq, smmu_pmu_handle_irq,
+ flags, "smmuv3-pmu", pmu);
+ return ret;
+}
+
+static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu)
+{
+ u64 counter_present_mask = GENMASK_ULL(smmu_pmu->num_counters - 1, 0);
+
+ smmu_pmu_disable(&smmu_pmu->pmu);
+
+ /* Disable counter and interrupt */
+ writeq_relaxed(counter_present_mask,
+ smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+ writeq_relaxed(counter_present_mask,
+ smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+ writeq_relaxed(counter_present_mask,
+ smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+}
+
+static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
+{
+ u32 model;
+
+ model = *(u32 *)dev_get_platdata(smmu_pmu->dev);
+
+ switch (model) {
+ case IORT_SMMU_V3_PMCG_HISI_HIP08:
+ /* HiSilicon Erratum 162001800 */
+ smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY;
+ break;
+ }
+
+ dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options);
+}
+
+static int smmu_pmu_probe(struct platform_device *pdev)
+{
+ struct smmu_pmu *smmu_pmu;
+ struct resource *res_0, *res_1;
+ u32 cfgr, reg_size;
+ u64 ceid_64[2];
+ int irq, err;
+ char *name;
+ struct device *dev = &pdev->dev;
+
+ smmu_pmu = devm_kzalloc(dev, sizeof(*smmu_pmu), GFP_KERNEL);
+ if (!smmu_pmu)
+ return -ENOMEM;
+
+ smmu_pmu->dev = dev;
+ platform_set_drvdata(pdev, smmu_pmu);
+
+ smmu_pmu->pmu = (struct pmu) {
+ .task_ctx_nr = perf_invalid_context,
+ .pmu_enable = smmu_pmu_enable,
+ .pmu_disable = smmu_pmu_disable,
+ .event_init = smmu_pmu_event_init,
+ .add = smmu_pmu_event_add,
+ .del = smmu_pmu_event_del,
+ .start = smmu_pmu_event_start,
+ .stop = smmu_pmu_event_stop,
+ .read = smmu_pmu_event_read,
+ .attr_groups = smmu_pmu_attr_grps,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ };
+
+ res_0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ smmu_pmu->reg_base = devm_ioremap_resource(dev, res_0);
+ if (IS_ERR(smmu_pmu->reg_base))
+ return PTR_ERR(smmu_pmu->reg_base);
+
+ cfgr = readl_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CFGR);
+
+ /* Determine if page 1 is present */
+ if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) {
+ res_1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ smmu_pmu->reloc_base = devm_ioremap_resource(dev, res_1);
+ if (IS_ERR(smmu_pmu->reloc_base))
+ return PTR_ERR(smmu_pmu->reloc_base);
+ } else {
+ smmu_pmu->reloc_base = smmu_pmu->reg_base;
+ }
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq > 0)
+ smmu_pmu->irq = irq;
+
+ ceid_64[0] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID0);
+ ceid_64[1] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID1);
+ bitmap_from_arr32(smmu_pmu->supported_events, (u32 *)ceid_64,
+ SMMU_PMCG_ARCH_MAX_EVENTS);
+
+ smmu_pmu->num_counters = FIELD_GET(SMMU_PMCG_CFGR_NCTR, cfgr) + 1;
+
+ smmu_pmu->global_filter = !!(cfgr & SMMU_PMCG_CFGR_SID_FILTER_TYPE);
+
+ reg_size = FIELD_GET(SMMU_PMCG_CFGR_SIZE, cfgr);
+ smmu_pmu->counter_mask = GENMASK_ULL(reg_size, 0);
+
+ smmu_pmu_reset(smmu_pmu);
+
+ err = smmu_pmu_setup_irq(smmu_pmu);
+ if (err) {
+ dev_err(dev, "Setup irq failed, PMU @%pa\n", &res_0->start);
+ return err;
+ }
+
+ name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "smmuv3_pmcg_%llx",
+ (res_0->start) >> SMMU_PMCG_PA_SHIFT);
+ if (!name) {
+ dev_err(dev, "Create name failed, PMU @%pa\n", &res_0->start);
+ return -EINVAL;
+ }
+
+ smmu_pmu_get_acpi_options(smmu_pmu);
+
+ /* Pick one CPU to be the preferred one to use */
+ smmu_pmu->on_cpu = raw_smp_processor_id();
+ WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
+ cpumask_of(smmu_pmu->on_cpu)));
+
+ err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
+ &smmu_pmu->node);
+ if (err) {
+ dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
+ err, &res_0->start);
+ goto out_cpuhp_err;
+ }
+
+ err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
+ if (err) {
+ dev_err(dev, "Error %d registering PMU @%pa\n",
+ err, &res_0->start);
+ goto out_unregister;
+ }
+
+ dev_info(dev, "Registered PMU @ %pa using %d counters with %s filter settings\n",
+ &res_0->start, smmu_pmu->num_counters,
+ smmu_pmu->global_filter ? "Global(Counter0)" :
+ "Individual");
+
+ return 0;
+
+out_unregister:
+ cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+out_cpuhp_err:
+ put_cpu();
+ return err;
+}
+
+static int smmu_pmu_remove(struct platform_device *pdev)
+{
+ struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+ perf_pmu_unregister(&smmu_pmu->pmu);
+ cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+
+ return 0;
+}
+
+static void smmu_pmu_shutdown(struct platform_device *pdev)
+{
+ struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+ smmu_pmu_disable(&smmu_pmu->pmu);
+}
+
+static struct platform_driver smmu_pmu_driver = {
+ .driver = {
+ .name = "arm-smmu-v3-pmcg",
+ },
+ .probe = smmu_pmu_probe,
+ .remove = smmu_pmu_remove,
+ .shutdown = smmu_pmu_shutdown,
+};
+
+static int __init arm_smmu_pmu_init(void)
+{
+ cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+ "perf/arm/pmcg:online",
+ NULL,
+ smmu_pmu_offline_cpu);
+ if (cpuhp_state_num < 0)
+ return cpuhp_state_num;
+
+ return platform_driver_register(&smmu_pmu_driver);
+}
+module_init(arm_smmu_pmu_init);
+
+static void __exit arm_smmu_pmu_exit(void)
+{
+ platform_driver_unregister(&smmu_pmu_driver);
+ cpuhp_remove_multi_state(cpuhp_state_num);
+}
+
+module_exit(arm_smmu_pmu_exit);
+
+MODULE_DESCRIPTION("PMU driver for ARM SMMUv3 Performance Monitors Extension");
+MODULE_AUTHOR("Neil Leeder <nleeder@codeaurora.org>");
+MODULE_AUTHOR("Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 7cb766dafe85..4e4984a55cd1 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Perf support for the Statistical Profiling Extension, introduced as
* part of ARMv8.2.
*
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- *
* Copyright (C) 2016 ARM Limited
*
* Author: Will Deacon <will.deacon@arm.com>
@@ -38,6 +27,7 @@
#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>
@@ -855,16 +845,8 @@ static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages,
if (!pglist)
goto out_free_buf;
- for (i = 0; i < nr_pages; ++i) {
- struct page *page = virt_to_page(pages[i]);
-
- if (PagePrivate(page)) {
- pr_warn("unexpected high-order page for auxbuf!");
- goto out_free_pglist;
- }
-
+ for (i = 0; i < nr_pages; ++i)
pglist[i] = virt_to_page(pages[i]);
- }
buf->base = vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL);
if (!buf->base)
@@ -1176,7 +1158,13 @@ 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;
@@ -1236,11 +1224,12 @@ 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/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile
index 2621d51ae87a..c3a96ec2bf66 100644
--- a/drivers/perf/hisilicon/Makefile
+++ b/drivers/perf/hisilicon/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index 0eba947c2ee9..6ad0823bcf23 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* HiSilicon SoC DDRC uncore Hardware event counters support
*
@@ -6,10 +7,6 @@
* Anurup M <anurup.m@huawei.com>
*
* This code is based on the uncore PMUs like arm-cci and arm-ccn.
- *
- * 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/acpi.h>
#include <linux/bug.h>
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 2553a844ebf6..4f2917f3e25e 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* HiSilicon SoC HHA uncore Hardware event counters support
*
@@ -6,10 +7,6 @@
* Anurup M <anurup.m@huawei.com>
*
* This code is based on the uncore PMUs like arm-cci and arm-ccn.
- *
- * 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/acpi.h>
#include <linux/bug.h>
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index cf1cc34f402a..9153e093f9df 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* HiSilicon SoC L3C uncore Hardware event counters support
*
@@ -6,10 +7,6 @@
* Shaokun Zhang <zhangshaokun@hisilicon.com>
*
* This code is based on the uncore PMUs like arm-cci and arm-ccn.
- *
- * 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/acpi.h>
#include <linux/bug.h>
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index f028cbc3443c..79f76f8dda8e 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* HiSilicon SoC Hardware event counters support
*
@@ -6,10 +7,6 @@
* Shaokun Zhang <zhangshaokun@hisilicon.com>
*
* This code is based on the uncore PMUs like arm-cci and arm-ccn.
- *
- * 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/bitmap.h>
#include <linux/bitops.h>
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h
index f21226a0e9c6..25b0c97b3eb0 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.h
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* HiSilicon SoC Hardware event counters support
*
@@ -6,10 +7,6 @@
* Shaokun Zhang <zhangshaokun@hisilicon.com>
*
* This code is based on the uncore PMUs like arm-cci and arm-ccn.
- *
- * 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.
*/
#ifndef __HISI_UNCORE_PMU_H__
#define __HISI_UNCORE_PMU_H__
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 091b4d7d32c4..d06182fe14b8 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2015-2017 The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#include <linux/acpi.h>
#include <linux/bitops.h>
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index 5d70646da8c7..15b8c10c2b2b 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Driver for the L3 cache PMUs in Qualcomm Technologies chips.
*
@@ -10,15 +11,6 @@
* See Documentation/perf/qcom_l3_pmu.txt for more details.
*
* Copyright (c) 2015-2017, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#include <linux/acpi.h>
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 27574e85f351..3259e2ebeb39 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* APM X-Gene SoC PMU (Performance Monitor Unit)
*
* Copyright (c) 2016, Applied Micro Circuits Corporation
* Author: Hoan Tran <hotran@apm.com>
* Tai Nguyen <ttnguyen@apm.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/acpi.h>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.