Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 08ebaf7..09ae8a9 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 @@
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 @@
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
@@ -87,6 +105,15 @@
Adds the L3 cache PMU into the perf events subsystem for
monitoring L3 cache events.
+config THUNDERX2_PMU
+ tristate "Cavium ThunderX2 SoC PMU UNCORE"
+ depends on ARCH_THUNDER2 && ARM64 && ACPI && NUMA
+ default m
+ help
+ Provides support for ThunderX2 UNCORE events.
+ The SoC has PMU support in its L3 cache controller (L3C) and
+ in the DDR4 Memory Controller (DMC).
+
config XGENE_PMU
depends on ARCH_XGENE
bool "APM X-Gene SoC PMU"
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index b3902bd..2ebb4de 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -4,8 +4,11 @@
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
+obj-$(CONFIG_THUNDERX2_PMU) += thunderx2_pmu.o
obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o
obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 1bfeb16..8f8606b 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1327,15 +1327,6 @@
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EOPNOTSUPP;
- /* We have no filtering of any kind */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle ||
- event->attr.exclude_host ||
- event->attr.exclude_guest)
- return -EINVAL;
-
/*
* Following the example set by other "uncore" PMUs, we accept any CPU
* and rewrite its affinity dynamically rather than having perf core
@@ -1433,6 +1424,7 @@
.stop = cci_pmu_stop,
.read = pmu_read,
.attr_groups = pmu_attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
cci_pmu->plat_device = pdev;
@@ -1692,21 +1684,24 @@
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 7dd850e..6fc0273 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 hrtimer hrtimer;
- cpumask_t cpu;
+ unsigned int cpu;
struct hlist_node node;
struct pmu pmu;
@@ -559,7 +552,7 @@
{
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 =
@@ -741,10 +734,7 @@
return -EOPNOTSUPP;
}
- 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) {
+ if (has_branch_stack(event)) {
dev_dbg(ccn->dev, "Can't exclude execution levels!\n");
return -EINVAL;
}
@@ -762,7 +752,7 @@
* 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);
@@ -1218,15 +1208,15 @@
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;
}
@@ -1290,6 +1280,7 @@
.read = arm_ccn_pmu_event_read,
.pmu_enable = arm_ccn_pmu_enable,
.pmu_disable = arm_ccn_pmu_disable,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
/* No overflow interrupt? Have to use a timer instead. */
@@ -1301,29 +1292,30 @@
}
/* 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 660cb8a..70968c8 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"
@@ -562,13 +559,7 @@
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) {
+ if (has_branch_stack(event)) {
dev_dbg(dsu_pmu->pmu.dev, "Can't support filtering\n");
return -EINVAL;
}
@@ -735,6 +726,7 @@
.read = dsu_pmu_read,
.attr_groups = dsu_pmu_attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
rc = perf_pmu_register(&dsu_pmu->pmu, name, -1);
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index d0b7dd8..df352b3 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
/*
@@ -357,13 +358,6 @@
}
static int
-event_requires_mode_exclusion(struct perf_event_attr *attr)
-{
- return attr->exclude_idle || attr->exclude_user ||
- attr->exclude_kernel || attr->exclude_hv;
-}
-
-static int
__hw_perf_event_init(struct perf_event *event)
{
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
@@ -393,9 +387,8 @@
/*
* Check whether we need to exclude the counter from certain modes.
*/
- if ((!armpmu->set_event_filter ||
- armpmu->set_event_filter(hwc, &event->attr)) &&
- event_requires_mode_exclusion(&event->attr)) {
+ if (armpmu->set_event_filter &&
+ armpmu->set_event_filter(hwc, &event->attr)) {
pr_debug("ARM performance counters do not support "
"mode exclusion\n");
return -EOPNOTSUPP;
@@ -730,8 +723,8 @@
cpu_pm_pmu_setup(armpmu, cmd);
break;
case CPU_PM_EXIT:
- cpu_pm_pmu_setup(armpmu, cmd);
case CPU_PM_ENTER_FAILED:
+ cpu_pm_pmu_setup(armpmu, cmd);
armpmu->start(armpmu);
break;
default:
@@ -867,6 +860,9 @@
if (ret)
return ret;
+ if (!pmu->set_event_filter)
+ pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE;
+
ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
if (ret)
goto out_destroy;
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 0f19751..acce878 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 @@
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 @@
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_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 96075ce..933bd84 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -77,14 +77,14 @@
dn = of_parse_phandle(node, "interrupt-affinity", i);
if (!dn) {
- pr_warn("failed to parse interrupt-affinity[%d] for %s\n",
- i, node->name);
+ pr_warn("failed to parse interrupt-affinity[%d] for %pOFn\n",
+ i, node);
return -EINVAL;
}
cpu = of_cpu_node_to_id(dn);
if (cpu < 0) {
- pr_warn("failed to find logical CPU for %s\n", dn->name);
+ pr_warn("failed to find logical CPU for %pOFn\n", dn);
cpu = nr_cpu_ids;
}
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
new file mode 100644
index 0000000..abcf54f
--- /dev/null
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -0,0 +1,892 @@
+// 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;
+};
+
+#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 bool smmu_pmu_check_global_filter(struct perf_event *curr,
+ struct perf_event *new)
+{
+ if (get_filter_enable(new) != get_filter_enable(curr))
+ return false;
+
+ if (!get_filter_enable(new))
+ return true;
+
+ return get_filter_span(new) == get_filter_span(curr) &&
+ get_filter_stream_id(new) == get_filter_stream_id(curr);
+}
+
+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*/
+ idx = find_first_bit(smmu_pmu->used_counters, num_ctrs);
+ if (idx == num_ctrs ||
+ smmu_pmu_check_global_filter(smmu_pmu->events[idx], event)) {
+ smmu_pmu_set_event_filter(event, 0, span, sid);
+ return 0;
+ }
+
+ return -EAGAIN;
+}
+
+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;
+}
+
+static bool smmu_pmu_events_compatible(struct perf_event *curr,
+ struct perf_event *new)
+{
+ if (new->pmu != curr->pmu)
+ return false;
+
+ if (to_smmu_pmu(new->pmu)->global_filter &&
+ !smmu_pmu_check_global_filter(curr, new))
+ return false;
+
+ return true;
+}
+
+/*
+ * 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;
+ int group_num_events = 1;
+ 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 (!is_software_event(event->group_leader)) {
+ if (!smmu_pmu_events_compatible(event->group_leader, event))
+ return -EINVAL;
+
+ if (++group_num_events > smmu_pmu->num_counters)
+ return -EINVAL;
+ }
+
+ for_each_sibling_event(sibling, event->group_leader) {
+ if (is_software_event(sibling))
+ continue;
+
+ if (!smmu_pmu_events_compatible(sibling, event))
+ return -EINVAL;
+
+ if (++group_num_events > smmu_pmu->num_counters)
+ 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 54ec278..4e4984a 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>
@@ -824,10 +814,10 @@
{
}
-static void *arm_spe_pmu_setup_aux(int cpu, void **pages, int nr_pages,
- bool snapshot)
+static void *arm_spe_pmu_setup_aux(struct perf_event *event, void **pages,
+ int nr_pages, bool snapshot)
{
- int i;
+ int i, cpu = event->cpu;
struct page **pglist;
struct arm_spe_pmu_buf *buf;
@@ -855,16 +845,8 @@
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)
@@ -927,6 +909,11 @@
idx = atomic_inc_return(&pmu_idx);
name = devm_kasprintf(dev, GFP_KERNEL, "%s_%d", PMUNAME, idx);
+ if (!name) {
+ dev_err(dev, "failed to allocate name for pmu %d\n", idx);
+ return -ENOMEM;
+ }
+
return perf_pmu_register(&spe_pmu->pmu, name, -1);
}
@@ -1169,8 +1156,15 @@
{ .compatible = "arm,statistical-profiling-extension-v1", .data = (void *)1 },
{ /* Sentinel */ },
};
+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;
@@ -1230,11 +1224,12 @@
}
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 0000000..ce73457
--- /dev/null
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -0,0 +1,625 @@
+// 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 AXI_MASKING_REVERT 0xffff0000 /* AXI_MASKING(MSB 16bits) + AXI_ID(LSB 16bits) */
+
+#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);
+
+/* DDR Perf hardware feature */
+#define DDR_CAP_AXI_ID_FILTER 0x1 /* support AXI ID filter */
+
+struct fsl_ddr_devtype_data {
+ unsigned int quirks; /* quirks needed for different DDR Perf core */
+};
+
+static const struct fsl_ddr_devtype_data imx8_devtype_data;
+
+static const struct fsl_ddr_devtype_data imx8m_devtype_data = {
+ .quirks = DDR_CAP_AXI_ID_FILTER,
+};
+
+static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
+ { .compatible = "fsl,imx8-ddr-pmu", .data = &imx8_devtype_data},
+ { .compatible = "fsl,imx8m-ddr-pmu", .data = &imx8m_devtype_data},
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, imx_ddr_pmu_dt_ids);
+
+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;
+ const struct fsl_ddr_devtype_data *devtype_data;
+ 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),
+ IMX8_DDR_PMU_EVENT_ATTR(axid-read, 0x41),
+ IMX8_DDR_PMU_EVENT_ATTR(axid-write, 0x42),
+ NULL,
+};
+
+static struct attribute_group ddr_perf_events_attr_group = {
+ .name = "events",
+ .attrs = ddr_perf_events_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-7");
+PMU_FORMAT_ATTR(axi_id, "config1:0-15");
+PMU_FORMAT_ATTR(axi_mask, "config1:16-31");
+
+static struct attribute *ddr_perf_format_attrs[] = {
+ &format_attr_event.attr,
+ &format_attr_axi_id.attr,
+ &format_attr_axi_mask.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 bool ddr_perf_is_filtered(struct perf_event *event)
+{
+ return event->attr.config == 0x41 || event->attr.config == 0x42;
+}
+
+static u32 ddr_perf_filter_val(struct perf_event *event)
+{
+ return event->attr.config1;
+}
+
+static bool ddr_perf_filters_compatible(struct perf_event *a,
+ struct perf_event *b)
+{
+ if (!ddr_perf_is_filtered(a))
+ return true;
+ if (!ddr_perf_is_filtered(b))
+ return true;
+ return ddr_perf_filter_val(a) == ddr_perf_filter_val(b);
+}
+
+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;
+
+ if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER) {
+ if (!ddr_perf_filters_compatible(event, event->group_leader))
+ return -EINVAL;
+ for_each_sibling_event(sibling, event->group_leader) {
+ if (!ddr_perf_filters_compatible(event, sibling))
+ 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;
+ int cfg1 = event->attr.config1;
+
+ if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER) {
+ int i;
+
+ for (i = 1; i < NUM_COUNTERS; i++) {
+ if (pmu->events[i] &&
+ !ddr_perf_filters_compatible(event, pmu->events[i]))
+ return -EINVAL;
+ }
+
+ if (ddr_perf_is_filtered(event)) {
+ /* revert axi id masking(axi_mask) value */
+ cfg1 ^= AXI_MASKING_REVERT;
+ writel(cfg1, pmu->base + COUNTER_DPCR1);
+ }
+ }
+
+ 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->devtype_data = of_device_get_match_data(&pdev->dev);
+
+ 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 2621d51..c3a96ec 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 1b10ea0..e42d446 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>
@@ -30,8 +27,8 @@
#define DDRC_FLUX_RCMD 0x38c
#define DDRC_PRE_CMD 0x3c0
#define DDRC_ACT_CMD 0x3c4
-#define DDRC_BNK_CHG 0x3c8
#define DDRC_RNK_CHG 0x3cc
+#define DDRC_RW_CHG 0x3d0
#define DDRC_EVENT_CTRL 0x6C0
#define DDRC_INT_MASK 0x6c8
#define DDRC_INT_STATUS 0x6cc
@@ -51,7 +48,7 @@
static const u32 ddrc_reg_off[] = {
DDRC_FLUX_WR, DDRC_FLUX_RD, DDRC_FLUX_WCMD, DDRC_FLUX_RCMD,
- DDRC_PRE_CMD, DDRC_ACT_CMD, DDRC_BNK_CHG, DDRC_RNK_CHG
+ DDRC_PRE_CMD, DDRC_ACT_CMD, DDRC_RNK_CHG, DDRC_RW_CHG
};
/*
@@ -220,10 +217,8 @@
/* Read and init IRQ */
irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(&pdev->dev, "DDRC PMU get irq fail; irq:%d\n", irq);
+ if (irq < 0)
return irq;
- }
ret = devm_request_irq(&pdev->dev, irq, hisi_ddrc_pmu_isr,
IRQF_NOBALANCING | IRQF_NO_THREAD,
@@ -396,6 +391,7 @@
.stop = hisi_uncore_pmu_stop,
.read = hisi_uncore_pmu_read,
.attr_groups = hisi_ddrc_pmu_attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1);
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 443906e..f280638 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>
@@ -210,10 +207,8 @@
/* Read and init IRQ */
irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(&pdev->dev, "HHA PMU get irq fail; irq:%d\n", irq);
+ if (irq < 0)
return irq;
- }
ret = devm_request_irq(&pdev->dev, irq, hisi_hha_pmu_isr,
IRQF_NOBALANCING | IRQF_NO_THREAD,
@@ -407,6 +402,7 @@
.stop = hisi_uncore_pmu_stop,
.read = hisi_uncore_pmu_read,
.attr_groups = hisi_hha_pmu_attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
ret = perf_pmu_register(&hha_pmu->pmu, name, -1);
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 0bde5d9..078b8dc 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>
@@ -209,10 +206,8 @@
/* Read and init IRQ */
irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(&pdev->dev, "L3C PMU get irq fail; irq:%d\n", irq);
+ if (irq < 0)
return irq;
- }
ret = devm_request_irq(&pdev->dev, irq, hisi_l3c_pmu_isr,
IRQF_NOBALANCING | IRQF_NO_THREAD,
@@ -397,6 +392,7 @@
.stop = hisi_uncore_pmu_stop,
.read = hisi_uncore_pmu_read,
.attr_groups = hisi_l3c_pmu_attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
ret = perf_pmu_register(&l3c_pmu->pmu, name, -1);
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 9efd241..79f76f8 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>
@@ -142,15 +139,6 @@
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EOPNOTSUPP;
- /* counters do not have these bits */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_host ||
- event->attr.exclude_guest ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle)
- return -EINVAL;
-
/*
* The uncore counters not specific to any CPU, so cannot
* support per-task
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h
index f21226a..25b0c97 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 842135c..21d6991 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>
@@ -509,14 +501,6 @@
return -EOPNOTSUPP;
}
- /* We cannot filter accurately so we just don't allow it. */
- if (event->attr.exclude_user || event->attr.exclude_kernel ||
- event->attr.exclude_hv || event->attr.exclude_idle) {
- dev_dbg_ratelimited(&l2cache_pmu->pdev->dev,
- "Can't exclude execution levels\n");
- return -EOPNOTSUPP;
- }
-
if (((L2_EVT_GROUP(event->attr.config) > L2_EVT_GROUP_MAX) ||
((event->attr.config & ~L2_EVT_MASK) != 0)) &&
(event->attr.config != L2CYCLE_CTR_RAW_CODE)) {
@@ -925,12 +909,8 @@
cluster->cluster_id = fw_cluster_id;
irq = platform_get_irq(sdev, 0);
- if (irq < 0) {
- dev_err(&pdev->dev,
- "Failed to get valid irq for cluster %ld\n",
- fw_cluster_id);
+ if (irq < 0)
return irq;
- }
irq_set_status_flags(irq, IRQ_NOAUTOEN);
cluster->irq = irq;
@@ -982,6 +962,7 @@
.stop = l2_cache_event_stop,
.read = l2_cache_event_read,
.attr_groups = l2_cache_pmu_attr_grps,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
l2cache_pmu->num_counters = get_num_counters();
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index 2dc63d6..656e830 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.
*
@@ -7,18 +8,9 @@
* the slices. User space needs to aggregate to individual counts to provide
* a global picture.
*
- * See Documentation/perf/qcom_l3_pmu.txt for more details.
+ * See Documentation/admin-guide/perf/qcom_l3_pmu.rst 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>
@@ -495,13 +487,6 @@
return -ENOENT;
/*
- * There are no per-counter mode filters in the PMU.
- */
- if (event->attr.exclude_user || event->attr.exclude_kernel ||
- event->attr.exclude_hv || event->attr.exclude_idle)
- return -EINVAL;
-
- /*
* Sampling not supported since these events are not core-attributable.
*/
if (hwc->sample_period)
@@ -777,6 +762,7 @@
.read = qcom_l3_cache__event_read,
.attr_groups = qcom_l3_cache_pmu_attr_grps,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
memrc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
new file mode 100644
index 0000000..43d76c8
--- /dev/null
+++ b/drivers/perf/thunderx2_pmu.c
@@ -0,0 +1,853 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * CAVIUM THUNDERX2 SoC PMU UNCORE
+ * Copyright (C) 2018 Cavium Inc.
+ * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/cpuhotplug.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+
+/* Each ThunderX2(TX2) Socket has a L3C and DMC UNCORE PMU device.
+ * Each UNCORE PMU device consists of 4 independent programmable counters.
+ * Counters are 32 bit and do not support overflow interrupt,
+ * they need to be sampled before overflow(i.e, at every 2 seconds).
+ */
+
+#define TX2_PMU_MAX_COUNTERS 4
+#define TX2_PMU_DMC_CHANNELS 8
+#define TX2_PMU_L3_TILES 16
+
+#define TX2_PMU_HRTIMER_INTERVAL (2 * NSEC_PER_SEC)
+#define GET_EVENTID(ev) ((ev->hw.config) & 0x1f)
+#define GET_COUNTERID(ev) ((ev->hw.idx) & 0x3)
+ /* 1 byte per counter(4 counters).
+ * Event id is encoded in bits [5:1] of a byte,
+ */
+#define DMC_EVENT_CFG(idx, val) ((val) << (((idx) * 8) + 1))
+
+#define L3C_COUNTER_CTL 0xA8
+#define L3C_COUNTER_DATA 0xAC
+#define DMC_COUNTER_CTL 0x234
+#define DMC_COUNTER_DATA 0x240
+
+/* L3C event IDs */
+#define L3_EVENT_READ_REQ 0xD
+#define L3_EVENT_WRITEBACK_REQ 0xE
+#define L3_EVENT_INV_N_WRITE_REQ 0xF
+#define L3_EVENT_INV_REQ 0x10
+#define L3_EVENT_EVICT_REQ 0x13
+#define L3_EVENT_INV_N_WRITE_HIT 0x14
+#define L3_EVENT_INV_HIT 0x15
+#define L3_EVENT_READ_HIT 0x17
+#define L3_EVENT_MAX 0x18
+
+/* DMC event IDs */
+#define DMC_EVENT_COUNT_CYCLES 0x1
+#define DMC_EVENT_WRITE_TXNS 0xB
+#define DMC_EVENT_DATA_TRANSFERS 0xD
+#define DMC_EVENT_READ_TXNS 0xF
+#define DMC_EVENT_MAX 0x10
+
+enum tx2_uncore_type {
+ PMU_TYPE_L3C,
+ PMU_TYPE_DMC,
+ PMU_TYPE_INVALID,
+};
+
+/*
+ * pmu on each socket has 2 uncore devices(dmc and l3c),
+ * each device has 4 counters.
+ */
+struct tx2_uncore_pmu {
+ struct hlist_node hpnode;
+ struct list_head entry;
+ struct pmu pmu;
+ char *name;
+ int node;
+ int cpu;
+ u32 max_counters;
+ u32 prorate_factor;
+ u32 max_events;
+ u64 hrtimer_interval;
+ void __iomem *base;
+ DECLARE_BITMAP(active_counters, TX2_PMU_MAX_COUNTERS);
+ struct perf_event *events[TX2_PMU_MAX_COUNTERS];
+ struct device *dev;
+ struct hrtimer hrtimer;
+ const struct attribute_group **attr_groups;
+ enum tx2_uncore_type type;
+ void (*init_cntr_base)(struct perf_event *event,
+ struct tx2_uncore_pmu *tx2_pmu);
+ void (*stop_event)(struct perf_event *event);
+ void (*start_event)(struct perf_event *event, int flags);
+};
+
+static LIST_HEAD(tx2_pmus);
+
+static inline struct tx2_uncore_pmu *pmu_to_tx2_pmu(struct pmu *pmu)
+{
+ return container_of(pmu, struct tx2_uncore_pmu, pmu);
+}
+
+PMU_FORMAT_ATTR(event, "config:0-4");
+
+static struct attribute *l3c_pmu_format_attrs[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute *dmc_pmu_format_attrs[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static const struct attribute_group l3c_pmu_format_attr_group = {
+ .name = "format",
+ .attrs = l3c_pmu_format_attrs,
+};
+
+static const struct attribute_group dmc_pmu_format_attr_group = {
+ .name = "format",
+ .attrs = dmc_pmu_format_attrs,
+};
+
+/*
+ * sysfs event attributes
+ */
+static ssize_t tx2_pmu_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dev_ext_attribute *eattr;
+
+ eattr = container_of(attr, struct dev_ext_attribute, attr);
+ return sprintf(buf, "event=0x%lx\n", (unsigned long) eattr->var);
+}
+
+#define TX2_EVENT_ATTR(name, config) \
+ PMU_EVENT_ATTR(name, tx2_pmu_event_attr_##name, \
+ config, tx2_pmu_event_show)
+
+TX2_EVENT_ATTR(read_request, L3_EVENT_READ_REQ);
+TX2_EVENT_ATTR(writeback_request, L3_EVENT_WRITEBACK_REQ);
+TX2_EVENT_ATTR(inv_nwrite_request, L3_EVENT_INV_N_WRITE_REQ);
+TX2_EVENT_ATTR(inv_request, L3_EVENT_INV_REQ);
+TX2_EVENT_ATTR(evict_request, L3_EVENT_EVICT_REQ);
+TX2_EVENT_ATTR(inv_nwrite_hit, L3_EVENT_INV_N_WRITE_HIT);
+TX2_EVENT_ATTR(inv_hit, L3_EVENT_INV_HIT);
+TX2_EVENT_ATTR(read_hit, L3_EVENT_READ_HIT);
+
+static struct attribute *l3c_pmu_events_attrs[] = {
+ &tx2_pmu_event_attr_read_request.attr.attr,
+ &tx2_pmu_event_attr_writeback_request.attr.attr,
+ &tx2_pmu_event_attr_inv_nwrite_request.attr.attr,
+ &tx2_pmu_event_attr_inv_request.attr.attr,
+ &tx2_pmu_event_attr_evict_request.attr.attr,
+ &tx2_pmu_event_attr_inv_nwrite_hit.attr.attr,
+ &tx2_pmu_event_attr_inv_hit.attr.attr,
+ &tx2_pmu_event_attr_read_hit.attr.attr,
+ NULL,
+};
+
+TX2_EVENT_ATTR(cnt_cycles, DMC_EVENT_COUNT_CYCLES);
+TX2_EVENT_ATTR(write_txns, DMC_EVENT_WRITE_TXNS);
+TX2_EVENT_ATTR(data_transfers, DMC_EVENT_DATA_TRANSFERS);
+TX2_EVENT_ATTR(read_txns, DMC_EVENT_READ_TXNS);
+
+static struct attribute *dmc_pmu_events_attrs[] = {
+ &tx2_pmu_event_attr_cnt_cycles.attr.attr,
+ &tx2_pmu_event_attr_write_txns.attr.attr,
+ &tx2_pmu_event_attr_data_transfers.attr.attr,
+ &tx2_pmu_event_attr_read_txns.attr.attr,
+ NULL,
+};
+
+static const struct attribute_group l3c_pmu_events_attr_group = {
+ .name = "events",
+ .attrs = l3c_pmu_events_attrs,
+};
+
+static const struct attribute_group dmc_pmu_events_attr_group = {
+ .name = "events",
+ .attrs = dmc_pmu_events_attrs,
+};
+
+/*
+ * sysfs cpumask attributes
+ */
+static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct tx2_uncore_pmu *tx2_pmu;
+
+ tx2_pmu = pmu_to_tx2_pmu(dev_get_drvdata(dev));
+ return cpumap_print_to_pagebuf(true, buf, cpumask_of(tx2_pmu->cpu));
+}
+static DEVICE_ATTR_RO(cpumask);
+
+static struct attribute *tx2_pmu_cpumask_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL,
+};
+
+static const struct attribute_group pmu_cpumask_attr_group = {
+ .attrs = tx2_pmu_cpumask_attrs,
+};
+
+/*
+ * Per PMU device attribute groups
+ */
+static const struct attribute_group *l3c_pmu_attr_groups[] = {
+ &l3c_pmu_format_attr_group,
+ &pmu_cpumask_attr_group,
+ &l3c_pmu_events_attr_group,
+ NULL
+};
+
+static const struct attribute_group *dmc_pmu_attr_groups[] = {
+ &dmc_pmu_format_attr_group,
+ &pmu_cpumask_attr_group,
+ &dmc_pmu_events_attr_group,
+ NULL
+};
+
+static inline u32 reg_readl(unsigned long addr)
+{
+ return readl((void __iomem *)addr);
+}
+
+static inline void reg_writel(u32 val, unsigned long addr)
+{
+ writel(val, (void __iomem *)addr);
+}
+
+static int alloc_counter(struct tx2_uncore_pmu *tx2_pmu)
+{
+ int counter;
+
+ counter = find_first_zero_bit(tx2_pmu->active_counters,
+ tx2_pmu->max_counters);
+ if (counter == tx2_pmu->max_counters)
+ return -ENOSPC;
+
+ set_bit(counter, tx2_pmu->active_counters);
+ return counter;
+}
+
+static inline void free_counter(struct tx2_uncore_pmu *tx2_pmu, int counter)
+{
+ clear_bit(counter, tx2_pmu->active_counters);
+}
+
+static void init_cntr_base_l3c(struct perf_event *event,
+ struct tx2_uncore_pmu *tx2_pmu)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ /* counter ctrl/data reg offset at 8 */
+ hwc->config_base = (unsigned long)tx2_pmu->base
+ + L3C_COUNTER_CTL + (8 * GET_COUNTERID(event));
+ hwc->event_base = (unsigned long)tx2_pmu->base
+ + L3C_COUNTER_DATA + (8 * GET_COUNTERID(event));
+}
+
+static void init_cntr_base_dmc(struct perf_event *event,
+ struct tx2_uncore_pmu *tx2_pmu)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ hwc->config_base = (unsigned long)tx2_pmu->base
+ + DMC_COUNTER_CTL;
+ /* counter data reg offset at 0xc */
+ hwc->event_base = (unsigned long)tx2_pmu->base
+ + DMC_COUNTER_DATA + (0xc * GET_COUNTERID(event));
+}
+
+static void uncore_start_event_l3c(struct perf_event *event, int flags)
+{
+ u32 val;
+ struct hw_perf_event *hwc = &event->hw;
+
+ /* event id encoded in bits [07:03] */
+ val = GET_EVENTID(event) << 3;
+ reg_writel(val, hwc->config_base);
+ local64_set(&hwc->prev_count, 0);
+ reg_writel(0, hwc->event_base);
+}
+
+static inline void uncore_stop_event_l3c(struct perf_event *event)
+{
+ reg_writel(0, event->hw.config_base);
+}
+
+static void uncore_start_event_dmc(struct perf_event *event, int flags)
+{
+ u32 val;
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = GET_COUNTERID(event);
+ int event_id = GET_EVENTID(event);
+
+ /* enable and start counters.
+ * 8 bits for each counter, bits[05:01] of a counter to set event type.
+ */
+ val = reg_readl(hwc->config_base);
+ val &= ~DMC_EVENT_CFG(idx, 0x1f);
+ val |= DMC_EVENT_CFG(idx, event_id);
+ reg_writel(val, hwc->config_base);
+ local64_set(&hwc->prev_count, 0);
+ reg_writel(0, hwc->event_base);
+}
+
+static void uncore_stop_event_dmc(struct perf_event *event)
+{
+ u32 val;
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = GET_COUNTERID(event);
+
+ /* clear event type(bits[05:01]) to stop counter */
+ val = reg_readl(hwc->config_base);
+ val &= ~DMC_EVENT_CFG(idx, 0x1f);
+ reg_writel(val, hwc->config_base);
+}
+
+static void tx2_uncore_event_update(struct perf_event *event)
+{
+ s64 prev, delta, new = 0;
+ struct hw_perf_event *hwc = &event->hw;
+ struct tx2_uncore_pmu *tx2_pmu;
+ enum tx2_uncore_type type;
+ u32 prorate_factor;
+
+ tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+ type = tx2_pmu->type;
+ prorate_factor = tx2_pmu->prorate_factor;
+
+ new = reg_readl(hwc->event_base);
+ prev = local64_xchg(&hwc->prev_count, new);
+
+ /* handles rollover of 32 bit counter */
+ delta = (u32)(((1UL << 32) - prev) + new);
+
+ /* DMC event data_transfers granularity is 16 Bytes, convert it to 64 */
+ if (type == PMU_TYPE_DMC &&
+ GET_EVENTID(event) == DMC_EVENT_DATA_TRANSFERS)
+ delta = delta/4;
+
+ /* L3C and DMC has 16 and 8 interleave channels respectively.
+ * The sampled value is for channel 0 and multiplied with
+ * prorate_factor to get the count for a device.
+ */
+ local64_add(delta * prorate_factor, &event->count);
+}
+
+static enum tx2_uncore_type get_tx2_pmu_type(struct acpi_device *adev)
+{
+ int i = 0;
+ struct acpi_tx2_pmu_device {
+ __u8 id[ACPI_ID_LEN];
+ enum tx2_uncore_type type;
+ } devices[] = {
+ {"CAV901D", PMU_TYPE_L3C},
+ {"CAV901F", PMU_TYPE_DMC},
+ {"", PMU_TYPE_INVALID}
+ };
+
+ while (devices[i].type != PMU_TYPE_INVALID) {
+ if (!strcmp(acpi_device_hid(adev), devices[i].id))
+ break;
+ i++;
+ }
+
+ return devices[i].type;
+}
+
+static bool tx2_uncore_validate_event(struct pmu *pmu,
+ struct perf_event *event, int *counters)
+{
+ if (is_software_event(event))
+ return true;
+ /* Reject groups spanning multiple HW PMUs. */
+ if (event->pmu != pmu)
+ return false;
+
+ *counters = *counters + 1;
+ return true;
+}
+
+/*
+ * Make sure the group of events can be scheduled at once
+ * on the PMU.
+ */
+static bool tx2_uncore_validate_event_group(struct perf_event *event)
+{
+ struct perf_event *sibling, *leader = event->group_leader;
+ int counters = 0;
+
+ if (event->group_leader == event)
+ return true;
+
+ if (!tx2_uncore_validate_event(event->pmu, leader, &counters))
+ return false;
+
+ for_each_sibling_event(sibling, leader) {
+ if (!tx2_uncore_validate_event(event->pmu, sibling, &counters))
+ return false;
+ }
+
+ if (!tx2_uncore_validate_event(event->pmu, event, &counters))
+ return false;
+
+ /*
+ * If the group requires more counters than the HW has,
+ * it cannot ever be scheduled.
+ */
+ return counters <= TX2_PMU_MAX_COUNTERS;
+}
+
+
+static int tx2_uncore_event_init(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct tx2_uncore_pmu *tx2_pmu;
+
+ /* Test the event attr type check for PMU enumeration */
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /*
+ * SOC PMU counters are shared across all cores.
+ * Therefore, it does not support per-process mode.
+ * Also, it does not support event sampling mode.
+ */
+ if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+ return -EINVAL;
+
+ if (event->cpu < 0)
+ return -EINVAL;
+
+ tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+ if (tx2_pmu->cpu >= nr_cpu_ids)
+ return -EINVAL;
+ event->cpu = tx2_pmu->cpu;
+
+ if (event->attr.config >= tx2_pmu->max_events)
+ return -EINVAL;
+
+ /* store event id */
+ hwc->config = event->attr.config;
+
+ /* Validate the group */
+ if (!tx2_uncore_validate_event_group(event))
+ return -EINVAL;
+
+ return 0;
+}
+
+static void tx2_uncore_event_start(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct tx2_uncore_pmu *tx2_pmu;
+
+ hwc->state = 0;
+ tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+
+ tx2_pmu->start_event(event, flags);
+ perf_event_update_userpage(event);
+
+ /* Start timer for first event */
+ if (bitmap_weight(tx2_pmu->active_counters,
+ tx2_pmu->max_counters) == 1) {
+ hrtimer_start(&tx2_pmu->hrtimer,
+ ns_to_ktime(tx2_pmu->hrtimer_interval),
+ HRTIMER_MODE_REL_PINNED);
+ }
+}
+
+static void tx2_uncore_event_stop(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct tx2_uncore_pmu *tx2_pmu;
+
+ if (hwc->state & PERF_HES_UPTODATE)
+ return;
+
+ tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+ tx2_pmu->stop_event(event);
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+ if (flags & PERF_EF_UPDATE) {
+ tx2_uncore_event_update(event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+}
+
+static int tx2_uncore_event_add(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct tx2_uncore_pmu *tx2_pmu;
+
+ tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+
+ /* Allocate a free counter */
+ hwc->idx = alloc_counter(tx2_pmu);
+ if (hwc->idx < 0)
+ return -EAGAIN;
+
+ tx2_pmu->events[hwc->idx] = event;
+ /* set counter control and data registers base address */
+ tx2_pmu->init_cntr_base(event, tx2_pmu);
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+ if (flags & PERF_EF_START)
+ tx2_uncore_event_start(event, flags);
+
+ return 0;
+}
+
+static void tx2_uncore_event_del(struct perf_event *event, int flags)
+{
+ struct tx2_uncore_pmu *tx2_pmu = pmu_to_tx2_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+
+ tx2_uncore_event_stop(event, PERF_EF_UPDATE);
+
+ /* clear the assigned counter */
+ free_counter(tx2_pmu, GET_COUNTERID(event));
+
+ perf_event_update_userpage(event);
+ tx2_pmu->events[hwc->idx] = NULL;
+ hwc->idx = -1;
+}
+
+static void tx2_uncore_event_read(struct perf_event *event)
+{
+ tx2_uncore_event_update(event);
+}
+
+static enum hrtimer_restart tx2_hrtimer_callback(struct hrtimer *timer)
+{
+ struct tx2_uncore_pmu *tx2_pmu;
+ int max_counters, idx;
+
+ tx2_pmu = container_of(timer, struct tx2_uncore_pmu, hrtimer);
+ max_counters = tx2_pmu->max_counters;
+
+ if (bitmap_empty(tx2_pmu->active_counters, max_counters))
+ return HRTIMER_NORESTART;
+
+ for_each_set_bit(idx, tx2_pmu->active_counters, max_counters) {
+ struct perf_event *event = tx2_pmu->events[idx];
+
+ tx2_uncore_event_update(event);
+ }
+ hrtimer_forward_now(timer, ns_to_ktime(tx2_pmu->hrtimer_interval));
+ return HRTIMER_RESTART;
+}
+
+static int tx2_uncore_pmu_register(
+ struct tx2_uncore_pmu *tx2_pmu)
+{
+ struct device *dev = tx2_pmu->dev;
+ char *name = tx2_pmu->name;
+
+ /* Perf event registration */
+ tx2_pmu->pmu = (struct pmu) {
+ .module = THIS_MODULE,
+ .attr_groups = tx2_pmu->attr_groups,
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = tx2_uncore_event_init,
+ .add = tx2_uncore_event_add,
+ .del = tx2_uncore_event_del,
+ .start = tx2_uncore_event_start,
+ .stop = tx2_uncore_event_stop,
+ .read = tx2_uncore_event_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ };
+
+ tx2_pmu->pmu.name = devm_kasprintf(dev, GFP_KERNEL,
+ "%s", name);
+
+ return perf_pmu_register(&tx2_pmu->pmu, tx2_pmu->pmu.name, -1);
+}
+
+static int tx2_uncore_pmu_add_dev(struct tx2_uncore_pmu *tx2_pmu)
+{
+ int ret, cpu;
+
+ cpu = cpumask_any_and(cpumask_of_node(tx2_pmu->node),
+ cpu_online_mask);
+
+ tx2_pmu->cpu = cpu;
+ hrtimer_init(&tx2_pmu->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ tx2_pmu->hrtimer.function = tx2_hrtimer_callback;
+
+ ret = tx2_uncore_pmu_register(tx2_pmu);
+ if (ret) {
+ dev_err(tx2_pmu->dev, "%s PMU: Failed to init driver\n",
+ tx2_pmu->name);
+ return -ENODEV;
+ }
+
+ /* register hotplug callback for the pmu */
+ ret = cpuhp_state_add_instance(
+ CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE,
+ &tx2_pmu->hpnode);
+ if (ret) {
+ dev_err(tx2_pmu->dev, "Error %d registering hotplug", ret);
+ return ret;
+ }
+
+ /* Add to list */
+ list_add(&tx2_pmu->entry, &tx2_pmus);
+
+ dev_dbg(tx2_pmu->dev, "%s PMU UNCORE registered\n",
+ tx2_pmu->pmu.name);
+ return ret;
+}
+
+static struct tx2_uncore_pmu *tx2_uncore_pmu_init_dev(struct device *dev,
+ acpi_handle handle, struct acpi_device *adev, u32 type)
+{
+ struct tx2_uncore_pmu *tx2_pmu;
+ void __iomem *base;
+ struct resource res;
+ struct resource_entry *rentry;
+ struct list_head list;
+ int ret;
+
+ INIT_LIST_HEAD(&list);
+ ret = acpi_dev_get_resources(adev, &list, NULL, NULL);
+ if (ret <= 0) {
+ dev_err(dev, "failed to parse _CRS method, error %d\n", ret);
+ return NULL;
+ }
+
+ list_for_each_entry(rentry, &list, node) {
+ if (resource_type(rentry->res) == IORESOURCE_MEM) {
+ res = *rentry->res;
+ break;
+ }
+ }
+
+ if (!rentry->res)
+ return NULL;
+
+ acpi_dev_free_resource_list(&list);
+ base = devm_ioremap_resource(dev, &res);
+ if (IS_ERR(base)) {
+ dev_err(dev, "PMU type %d: Fail to map resource\n", type);
+ return NULL;
+ }
+
+ tx2_pmu = devm_kzalloc(dev, sizeof(*tx2_pmu), GFP_KERNEL);
+ if (!tx2_pmu)
+ return NULL;
+
+ tx2_pmu->dev = dev;
+ tx2_pmu->type = type;
+ tx2_pmu->base = base;
+ tx2_pmu->node = dev_to_node(dev);
+ INIT_LIST_HEAD(&tx2_pmu->entry);
+
+ switch (tx2_pmu->type) {
+ case PMU_TYPE_L3C:
+ tx2_pmu->max_counters = TX2_PMU_MAX_COUNTERS;
+ tx2_pmu->prorate_factor = TX2_PMU_L3_TILES;
+ tx2_pmu->max_events = L3_EVENT_MAX;
+ tx2_pmu->hrtimer_interval = TX2_PMU_HRTIMER_INTERVAL;
+ tx2_pmu->attr_groups = l3c_pmu_attr_groups;
+ tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL,
+ "uncore_l3c_%d", tx2_pmu->node);
+ tx2_pmu->init_cntr_base = init_cntr_base_l3c;
+ tx2_pmu->start_event = uncore_start_event_l3c;
+ tx2_pmu->stop_event = uncore_stop_event_l3c;
+ break;
+ case PMU_TYPE_DMC:
+ tx2_pmu->max_counters = TX2_PMU_MAX_COUNTERS;
+ tx2_pmu->prorate_factor = TX2_PMU_DMC_CHANNELS;
+ tx2_pmu->max_events = DMC_EVENT_MAX;
+ tx2_pmu->hrtimer_interval = TX2_PMU_HRTIMER_INTERVAL;
+ tx2_pmu->attr_groups = dmc_pmu_attr_groups;
+ tx2_pmu->name = devm_kasprintf(dev, GFP_KERNEL,
+ "uncore_dmc_%d", tx2_pmu->node);
+ tx2_pmu->init_cntr_base = init_cntr_base_dmc;
+ tx2_pmu->start_event = uncore_start_event_dmc;
+ tx2_pmu->stop_event = uncore_stop_event_dmc;
+ break;
+ case PMU_TYPE_INVALID:
+ devm_kfree(dev, tx2_pmu);
+ return NULL;
+ }
+
+ return tx2_pmu;
+}
+
+static acpi_status tx2_uncore_pmu_add(acpi_handle handle, u32 level,
+ void *data, void **return_value)
+{
+ struct tx2_uncore_pmu *tx2_pmu;
+ struct acpi_device *adev;
+ enum tx2_uncore_type type;
+
+ if (acpi_bus_get_device(handle, &adev))
+ return AE_OK;
+ if (acpi_bus_get_status(adev) || !adev->status.present)
+ return AE_OK;
+
+ type = get_tx2_pmu_type(adev);
+ if (type == PMU_TYPE_INVALID)
+ return AE_OK;
+
+ tx2_pmu = tx2_uncore_pmu_init_dev((struct device *)data,
+ handle, adev, type);
+
+ if (!tx2_pmu)
+ return AE_ERROR;
+
+ if (tx2_uncore_pmu_add_dev(tx2_pmu)) {
+ /* Can't add the PMU device, abort */
+ return AE_ERROR;
+ }
+ return AE_OK;
+}
+
+static int tx2_uncore_pmu_online_cpu(unsigned int cpu,
+ struct hlist_node *hpnode)
+{
+ struct tx2_uncore_pmu *tx2_pmu;
+
+ tx2_pmu = hlist_entry_safe(hpnode,
+ struct tx2_uncore_pmu, hpnode);
+
+ /* Pick this CPU, If there is no CPU/PMU association and both are
+ * from same node.
+ */
+ if ((tx2_pmu->cpu >= nr_cpu_ids) &&
+ (tx2_pmu->node == cpu_to_node(cpu)))
+ tx2_pmu->cpu = cpu;
+
+ return 0;
+}
+
+static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
+ struct hlist_node *hpnode)
+{
+ int new_cpu;
+ struct tx2_uncore_pmu *tx2_pmu;
+ struct cpumask cpu_online_mask_temp;
+
+ tx2_pmu = hlist_entry_safe(hpnode,
+ struct tx2_uncore_pmu, hpnode);
+
+ if (cpu != tx2_pmu->cpu)
+ return 0;
+
+ hrtimer_cancel(&tx2_pmu->hrtimer);
+ cpumask_copy(&cpu_online_mask_temp, cpu_online_mask);
+ cpumask_clear_cpu(cpu, &cpu_online_mask_temp);
+ new_cpu = cpumask_any_and(
+ cpumask_of_node(tx2_pmu->node),
+ &cpu_online_mask_temp);
+
+ tx2_pmu->cpu = new_cpu;
+ if (new_cpu >= nr_cpu_ids)
+ return 0;
+ perf_pmu_migrate_context(&tx2_pmu->pmu, cpu, new_cpu);
+
+ return 0;
+}
+
+static const struct acpi_device_id tx2_uncore_acpi_match[] = {
+ {"CAV901C", 0},
+ {},
+};
+MODULE_DEVICE_TABLE(acpi, tx2_uncore_acpi_match);
+
+static int tx2_uncore_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ acpi_handle handle;
+ acpi_status status;
+
+ set_dev_node(dev, acpi_get_node(ACPI_HANDLE(dev)));
+
+ if (!has_acpi_companion(dev))
+ return -ENODEV;
+
+ handle = ACPI_HANDLE(dev);
+ if (!handle)
+ return -EINVAL;
+
+ /* Walk through the tree for all PMU UNCORE devices */
+ status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+ tx2_uncore_pmu_add,
+ NULL, dev, NULL);
+ if (ACPI_FAILURE(status)) {
+ dev_err(dev, "failed to probe PMU devices\n");
+ return_ACPI_STATUS(status);
+ }
+
+ dev_info(dev, "node%d: pmu uncore registered\n", dev_to_node(dev));
+ return 0;
+}
+
+static int tx2_uncore_remove(struct platform_device *pdev)
+{
+ struct tx2_uncore_pmu *tx2_pmu, *temp;
+ struct device *dev = &pdev->dev;
+
+ if (!list_empty(&tx2_pmus)) {
+ list_for_each_entry_safe(tx2_pmu, temp, &tx2_pmus, entry) {
+ if (tx2_pmu->node == dev_to_node(dev)) {
+ cpuhp_state_remove_instance_nocalls(
+ CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE,
+ &tx2_pmu->hpnode);
+ perf_pmu_unregister(&tx2_pmu->pmu);
+ list_del(&tx2_pmu->entry);
+ }
+ }
+ }
+ return 0;
+}
+
+static struct platform_driver tx2_uncore_driver = {
+ .driver = {
+ .name = "tx2-uncore-pmu",
+ .acpi_match_table = ACPI_PTR(tx2_uncore_acpi_match),
+ },
+ .probe = tx2_uncore_probe,
+ .remove = tx2_uncore_remove,
+};
+
+static int __init tx2_uncore_driver_init(void)
+{
+ int ret;
+
+ ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE,
+ "perf/tx2/uncore:online",
+ tx2_uncore_pmu_online_cpu,
+ tx2_uncore_pmu_offline_cpu);
+ if (ret) {
+ pr_err("TX2 PMU: setup hotplug failed(%d)\n", ret);
+ return ret;
+ }
+ ret = platform_driver_register(&tx2_uncore_driver);
+ if (ret)
+ cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE);
+
+ return ret;
+}
+module_init(tx2_uncore_driver_init);
+
+static void __exit tx2_uncore_driver_exit(void)
+{
+ platform_driver_unregister(&tx2_uncore_driver);
+ cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE);
+}
+module_exit(tx2_uncore_driver_exit);
+
+MODULE_DESCRIPTION("ThunderX2 UNCORE PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Ganapatrao Kulkarni <gkulkarni@cavium.com>");
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 0e31f13..7e328d6 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1,26 +1,15 @@
+// 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>
#include <linux/clk.h>
+#include <linux/cpuhotplug.h>
#include <linux/cpumask.h>
#include <linux/interrupt.h>
#include <linux/io.h>
@@ -130,12 +119,14 @@
struct xgene_pmu {
struct device *dev;
+ struct hlist_node node;
int version;
void __iomem *pcppmu_csr;
u32 mcb_active_mask;
u32 mc_active_mask;
u32 l3c_active_mask;
cpumask_t cpu;
+ int irq;
raw_spinlock_t lock;
const struct xgene_pmu_ops *ops;
struct list_head l3cpmus;
@@ -914,11 +905,6 @@
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
- /* SOC counters do not have usr/os/guest/host bits */
- if (event->attr.exclude_user || event->attr.exclude_kernel ||
- event->attr.exclude_host || event->attr.exclude_guest)
- return -EINVAL;
-
if (event->cpu < 0)
return -EINVAL;
/*
@@ -1054,7 +1040,6 @@
static void xgene_perf_stop(struct perf_event *event, int flags)
{
struct hw_perf_event *hw = &event->hw;
- u64 config;
if (hw->state & PERF_HES_UPTODATE)
return;
@@ -1066,7 +1051,6 @@
if (hw->state & PERF_HES_UPTODATE)
return;
- config = hw->config;
xgene_perf_read(event);
hw->state |= PERF_HES_UPTODATE;
}
@@ -1133,6 +1117,7 @@
.start = xgene_perf_start,
.stop = xgene_perf_stop,
.read = xgene_perf_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
/* Hardware counter init */
@@ -1806,6 +1791,53 @@
MODULE_DEVICE_TABLE(acpi, xgene_pmu_acpi_match);
#endif
+static int xgene_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
+{
+ struct xgene_pmu *xgene_pmu = hlist_entry_safe(node, struct xgene_pmu,
+ node);
+
+ if (cpumask_empty(&xgene_pmu->cpu))
+ cpumask_set_cpu(cpu, &xgene_pmu->cpu);
+
+ /* Overflow interrupt also should use the same CPU */
+ WARN_ON(irq_set_affinity(xgene_pmu->irq, &xgene_pmu->cpu));
+
+ return 0;
+}
+
+static int xgene_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+ struct xgene_pmu *xgene_pmu = hlist_entry_safe(node, struct xgene_pmu,
+ node);
+ struct xgene_pmu_dev_ctx *ctx;
+ unsigned int target;
+
+ if (!cpumask_test_and_clear_cpu(cpu, &xgene_pmu->cpu))
+ return 0;
+ target = cpumask_any_but(cpu_online_mask, cpu);
+ if (target >= nr_cpu_ids)
+ return 0;
+
+ list_for_each_entry(ctx, &xgene_pmu->mcpmus, next) {
+ perf_pmu_migrate_context(&ctx->pmu_dev->pmu, cpu, target);
+ }
+ list_for_each_entry(ctx, &xgene_pmu->mcbpmus, next) {
+ perf_pmu_migrate_context(&ctx->pmu_dev->pmu, cpu, target);
+ }
+ list_for_each_entry(ctx, &xgene_pmu->l3cpmus, next) {
+ perf_pmu_migrate_context(&ctx->pmu_dev->pmu, cpu, target);
+ }
+ list_for_each_entry(ctx, &xgene_pmu->iobpmus, next) {
+ perf_pmu_migrate_context(&ctx->pmu_dev->pmu, cpu, target);
+ }
+
+ cpumask_set_cpu(target, &xgene_pmu->cpu);
+ /* Overflow interrupt also should use the same CPU */
+ WARN_ON(irq_set_affinity(xgene_pmu->irq, &xgene_pmu->cpu));
+
+ return 0;
+}
+
static int xgene_pmu_probe(struct platform_device *pdev)
{
const struct xgene_pmu_data *dev_data;
@@ -1815,6 +1847,14 @@
int irq, rc;
int version;
+ /* Install a hook to update the reader CPU in case it goes offline */
+ rc = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE,
+ "CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE",
+ xgene_pmu_online_cpu,
+ xgene_pmu_offline_cpu);
+ if (rc)
+ return rc;
+
xgene_pmu = devm_kzalloc(&pdev->dev, sizeof(*xgene_pmu), GFP_KERNEL);
if (!xgene_pmu)
return -ENOMEM;
@@ -1861,10 +1901,9 @@
}
irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(&pdev->dev, "No IRQ resource\n");
+ if (irq < 0)
return -EINVAL;
- }
+
rc = devm_request_irq(&pdev->dev, irq, xgene_pmu_isr,
IRQF_NOBALANCING | IRQF_NO_THREAD,
dev_name(&pdev->dev), xgene_pmu);
@@ -1873,6 +1912,8 @@
return rc;
}
+ xgene_pmu->irq = irq;
+
raw_spin_lock_init(&xgene_pmu->lock);
/* Check for active MCBs and MCUs */
@@ -1883,13 +1924,11 @@
xgene_pmu->mc_active_mask = 0x1;
}
- /* Pick one core to use for cpumask attributes */
- cpumask_set_cpu(smp_processor_id(), &xgene_pmu->cpu);
-
- /* Make sure that the overflow interrupt is handled by this CPU */
- rc = irq_set_affinity(irq, &xgene_pmu->cpu);
+ /* Add this instance to the list used by the hotplug callback */
+ rc = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE,
+ &xgene_pmu->node);
if (rc) {
- dev_err(&pdev->dev, "Failed to set interrupt affinity!\n");
+ dev_err(&pdev->dev, "Error %d registering hotplug", rc);
return rc;
}
@@ -1897,13 +1936,18 @@
rc = xgene_pmu_probe_pmu_dev(xgene_pmu, pdev);
if (rc) {
dev_err(&pdev->dev, "No PMU perf devices found!\n");
- return rc;
+ goto out_unregister;
}
/* Enable interrupt */
xgene_pmu->ops->unmask_int(xgene_pmu);
return 0;
+
+out_unregister:
+ cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE,
+ &xgene_pmu->node);
+ return rc;
}
static void
@@ -1924,6 +1968,8 @@
xgene_pmu_dev_cleanup(xgene_pmu, &xgene_pmu->iobpmus);
xgene_pmu_dev_cleanup(xgene_pmu, &xgene_pmu->mcbpmus);
xgene_pmu_dev_cleanup(xgene_pmu, &xgene_pmu->mcpmus);
+ cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE,
+ &xgene_pmu->node);
return 0;
}