[PATCHv2 4/4] coresight: Add ETR-PERF polling.
Daniel Kiss
daniel.kiss at arm.com
Tue Jul 13 05:15:32 PDT 2021
ETR might fill up the buffer sooner than an event makes perf to trigger
the synchronisation especially in system wide trace. Polling runs
periodically to sync the ETR buffer. Period is configurable via sysfs,
disabled by default.
Signed-off-by: Daniel Kiss <daniel.kiss at arm.com>
Signed-off-by: Branislav Rankov <Branislav.Rankov at arm.com>
Tested-by: Denis Nikitin <denik at chromium.org>
---
.../testing/sysfs-bus-coresight-devices-tmc | 8 +
drivers/hwtracing/coresight/Kconfig | 12 +
drivers/hwtracing/coresight/Makefile | 1 +
.../hwtracing/coresight/coresight-etm-perf.c | 8 +
.../coresight/coresight-etr-perf-polling.c | 275 ++++++++++++++++++
.../coresight/coresight-etr-perf-polling.h | 38 +++
.../hwtracing/coresight/coresight-tmc-core.c | 4 +
.../hwtracing/coresight/coresight-tmc-etr.c | 13 +
8 files changed, 359 insertions(+)
create mode 100644 drivers/hwtracing/coresight/coresight-etr-perf-polling.c
create mode 100644 drivers/hwtracing/coresight/coresight-etr-perf-polling.h
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
index 6aa527296c710..3b411e8a6f417 100644
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
@@ -91,3 +91,11 @@ Contact: Mathieu Poirier <mathieu.poirier at linaro.org>
Description: (RW) Size of the trace buffer for TMC-ETR when used in SYSFS
mode. Writable only for TMC-ETR configurations. The value
should be aligned to the kernel pagesize.
+
+What: /sys/bus/coresight/devices/<memory_map>.tmc/polling/period
+Date: July 2021
+KernelVersion: 5.14
+Contact: Daniel Kiss <daniel.kiss at arm.com>
+Description: (RW) Time in milliseconds when the TMC-ETR is synced.
+ Default value is 0, means the feature is disabled.
+ Writable only for TMC-ETR configurations.
diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig
index 84530fd80998c..4e91fb98849f4 100644
--- a/drivers/hwtracing/coresight/Kconfig
+++ b/drivers/hwtracing/coresight/Kconfig
@@ -44,6 +44,18 @@ config CORESIGHT_LINK_AND_SINK_TMC
To compile this driver as a module, choose M here: the
module will be called coresight-tmc.
+
+config CORESIGHT_ETR_PERF_POLL
+ bool "Coresight ETR Perf Polling"
+
+ depends on CORESIGHT_LINK_AND_SINK_TMC
+ help
+ Enable the support for software periodic synchronization of the ETR buffer.
+ ETR might fill up the buffer sooner than an event makes perf to trigger
+ the synchronization especially in system wide trace. Polling runs
+ periodically to sync the ETR buffer. Period is configurable via sysfs,
+ disabled by default.
+
config CORESIGHT_CATU
tristate "Coresight Address Translation Unit (CATU) driver"
depends on CORESIGHT_LINK_AND_SINK_TMC
diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile
index d60816509755c..6baac328eea87 100644
--- a/drivers/hwtracing/coresight/Makefile
+++ b/drivers/hwtracing/coresight/Makefile
@@ -5,6 +5,7 @@
obj-$(CONFIG_CORESIGHT) += coresight.o
coresight-y := coresight-core.o coresight-etm-perf.o coresight-platform.o \
coresight-sysfs.o
+coresight-$(CONFIG_CORESIGHT_ETR_PERF_POLL) += coresight-etr-perf-polling.o
obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o
coresight-tmc-y := coresight-tmc-core.o coresight-tmc-etf.o \
coresight-tmc-etr.o
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index a3f4c07f5bf8b..3095840a567c4 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -19,6 +19,7 @@
#include <linux/workqueue.h>
#include "coresight-etm-perf.h"
+#include "coresight-etr-perf-polling.h"
#include "coresight-priv.h"
static struct pmu etm_pmu;
@@ -438,6 +439,8 @@ static void etm_event_start(struct perf_event *event, int flags)
/* Tell the perf core the event is alive */
event->hw.state = 0;
+ etr_perf_polling_event_start(event, event_data, handle);
+
/* Finally enable the tracer */
if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF))
goto fail_disable_path;
@@ -497,6 +500,8 @@ static void etm_event_stop(struct perf_event *event, int mode)
if (!sink)
return;
+ etr_perf_polling_event_stop(event, event_data);
+
/* stop tracer */
source_ops(csdev)->disable(csdev, event);
@@ -741,6 +746,8 @@ int __init etm_perf_init(void)
etm_pmu.addr_filters_validate = etm_addr_filters_validate;
etm_pmu.nr_addr_filters = ETM_ADDR_CMP_MAX;
+ etr_perf_polling_init();
+
ret = perf_pmu_register(&etm_pmu, CORESIGHT_ETM_PMU_NAME, -1);
if (ret == 0)
etm_perf_up = true;
@@ -750,5 +757,6 @@ int __init etm_perf_init(void)
void __exit etm_perf_exit(void)
{
+ etr_perf_polling_exit();
perf_pmu_unregister(&etm_pmu);
}
diff --git a/drivers/hwtracing/coresight/coresight-etr-perf-polling.c b/drivers/hwtracing/coresight/coresight-etr-perf-polling.c
new file mode 100644
index 0000000000000..87e6bc42a62de
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etr-perf-polling.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(C) 2021 Arm Limited. All rights reserved.
+ * Author: Daniel Kiss <daniel.kiss at arm.com>
+ */
+
+#include <linux/coresight.h>
+#include <linux/coresight-pmu.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/percpu-defs.h>
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+#include <linux/stringhash.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include "coresight-etr-perf-polling.h"
+#include "coresight-priv.h"
+#include "coresight-tmc.h"
+
+struct polling_event_list {
+ struct perf_event *perf_event;
+ struct etm_event_data *etm_event_data;
+ struct perf_output_handle *ctx_handle;
+ void (*tmc_etr_reset_hw)(struct tmc_drvdata *data);
+ struct list_head list;
+};
+
+struct polling {
+ int cpu;
+ struct polling_event_list *polled_event;
+ struct delayed_work delayed_work;
+};
+
+static atomic_t period;
+static spinlock_t spinlock_re;
+static struct list_head registered_events;
+
+static DEFINE_PER_CPU(struct polling, polling);
+
+static ssize_t period_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ int temp;
+
+ temp = atomic_read(&period);
+ return sprintf(buf, "%i\n", temp);
+}
+
+static ssize_t period_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int temp = 0;
+
+ if (!kstrtoint(buf, 10, &temp) && (temp >= 0))
+ atomic_set(&period, temp);
+ return count;
+}
+
+static DEVICE_ATTR_RW(period);
+
+static struct attribute *coresight_tmc_polling_attrs[] = {
+ &dev_attr_period.attr,
+ NULL,
+};
+const struct attribute_group coresight_tmc_polling_group = {
+ .attrs = coresight_tmc_polling_attrs,
+ .name = "polling",
+};
+EXPORT_SYMBOL_GPL(coresight_tmc_polling_group);
+
+static inline void polling_sched_worker(struct polling *p)
+{
+ int tickrate = atomic_read(&period);
+
+ if (tickrate > 0)
+ schedule_delayed_work_on(p->cpu, &p->delayed_work,
+ msecs_to_jiffies(tickrate));
+}
+
+static inline bool is_etr_related(struct etm_event_data *etm_event_data, int cpu)
+{
+ struct list_head *path;
+ struct coresight_device *sink;
+ struct tmc_drvdata *drvdata;
+
+ path = etm_event_cpu_path(etm_event_data, cpu);
+ if (WARN_ON(!path))
+ return false;
+ sink = coresight_get_sink(path);
+ if (WARN_ON(!sink))
+ return false;
+ drvdata = dev_get_drvdata(sink->dev.parent);
+ if (drvdata->config_type != TMC_CONFIG_TYPE_ETR)
+ return false;
+ return true;
+}
+
+/*
+ * Adds the event to the polled events list.
+ */
+void etr_perf_polling_event_start(struct perf_event *event,
+ struct etm_event_data *etm_event_data,
+ struct perf_output_handle *ctx_handle)
+{
+ int cpu = smp_processor_id();
+ struct polling *p = per_cpu_ptr(&polling, cpu);
+ struct polling_event_list *element, *tmp;
+
+ if (!is_etr_related(etm_event_data, cpu))
+ return;
+
+ spin_lock(&spinlock_re);
+ list_for_each_entry_safe(element, tmp, ®istered_events, list) {
+ if (element->ctx_handle == ctx_handle) {
+ element->perf_event = event;
+ element->etm_event_data = etm_event_data;
+ spin_unlock(&spinlock_re);
+ p->polled_event = element;
+ polling_sched_worker(p);
+ return;
+ }
+ }
+ spin_unlock(&spinlock_re);
+}
+
+/*
+ * Removes the event from the to be polled events list.
+ */
+void etr_perf_polling_event_stop(struct perf_event *event,
+ struct etm_event_data *etm_event_data)
+{
+ int cpu = smp_processor_id();
+ struct polling *p = per_cpu_ptr(&polling, cpu);
+
+ if (!is_etr_related(etm_event_data, cpu))
+ return;
+
+ if (p->polled_event) {
+ struct polling_event_list *element = p->polled_event;
+
+ if (element->perf_event == event) {
+ p->polled_event = NULL;
+ element->perf_event = NULL;
+ element->etm_event_data = NULL;
+ cancel_delayed_work(&p->delayed_work);
+ return;
+ }
+ }
+}
+
+/*
+ * The polling worker is a workqueue job which is periodically
+ * woken up to update the perf aux buffer from the etr shrink.
+ */
+static void etr_perf_polling_worker(struct work_struct *work)
+{
+ unsigned long flags;
+ struct list_head *path;
+ struct coresight_device *sink;
+ int size;
+ int cpu = smp_processor_id();
+ struct polling *p = per_cpu_ptr(&polling, cpu);
+
+ if (!atomic_read(&period))
+ return;
+
+ if (!p->polled_event)
+ return;
+ /*
+ * Scheduling would do the same from the perf hooks,
+ * this should be done in one go.
+ */
+ local_irq_save(flags);
+
+ polling_sched_worker(p);
+
+ path = etm_event_cpu_path(p->polled_event->etm_event_data, cpu);
+ sink = coresight_get_sink(path);
+ size = sink_ops(sink)->update_buffer(
+ sink, p->polled_event->ctx_handle,
+ p->polled_event->etm_event_data->snk_config);
+
+ /*
+ * Restart the trace.
+ */
+ if (p->polled_event->tmc_etr_reset_hw)
+ p->polled_event->tmc_etr_reset_hw(dev_get_drvdata(sink->dev.parent));
+
+ WARN_ON(size < 0);
+ if (size > 0) {
+ struct etm_event_data *new_event_data;
+
+ perf_aux_output_end(p->polled_event->ctx_handle, size);
+ new_event_data = perf_aux_output_begin(
+ p->polled_event->ctx_handle,
+ p->polled_event->perf_event);
+ if (WARN_ON(new_event_data == NULL)) {
+ local_irq_restore(flags);
+ return;
+ }
+
+ p->polled_event->etm_event_data = new_event_data;
+ WARN_ON(new_event_data->snk_config !=
+ p->polled_event->etm_event_data->snk_config);
+ }
+
+ local_irq_restore(flags);
+}
+
+void etr_perf_polling_handle_register(struct perf_output_handle *handle,
+ void (*tmc_etr_reset_hw)(struct tmc_drvdata *drvdata))
+{
+ struct polling_event_list *element;
+
+ element = kmalloc(sizeof(*element), GFP_ATOMIC);
+ if (WARN_ON(!element))
+ return;
+ memset(element, 0, sizeof(*element));
+ element->ctx_handle = handle;
+ element->tmc_etr_reset_hw = tmc_etr_reset_hw;
+ spin_lock(&spinlock_re);
+ list_add(&element->list, ®istered_events);
+ spin_unlock(&spinlock_re);
+}
+EXPORT_SYMBOL_GPL(etr_perf_polling_handle_register);
+
+void etr_perf_polling_handle_deregister(struct perf_output_handle *handle)
+{
+ struct polling_event_list *element, *tmp;
+
+ spin_lock(&spinlock_re);
+ list_for_each_entry_safe(element, tmp, ®istered_events, list) {
+ if (element->ctx_handle == handle) {
+ list_del(&element->list);
+ spin_unlock(&spinlock_re);
+ kfree(element);
+ return;
+ }
+ }
+ spin_unlock(&spinlock_re);
+}
+EXPORT_SYMBOL_GPL(etr_perf_polling_handle_deregister);
+
+void etr_perf_polling_init(void)
+{
+ int cpu;
+
+ spin_lock_init(&spinlock_re);
+ INIT_LIST_HEAD(®istered_events);
+ atomic_set(&period, 0);
+ for_each_possible_cpu(cpu) {
+ struct polling *p = per_cpu_ptr(&polling, cpu);
+
+ p->cpu = cpu;
+ p->polled_event = NULL;
+ INIT_DELAYED_WORK(&p->delayed_work, etr_perf_polling_worker);
+ }
+}
+
+void etr_perf_polling_exit(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct polling *p = per_cpu_ptr(&polling, cpu);
+
+ cancel_delayed_work_sync(&p->delayed_work);
+ WARN_ON(p->polled_event);
+ }
+ WARN_ON(!list_empty(®istered_events));
+}
diff --git a/drivers/hwtracing/coresight/coresight-etr-perf-polling.h b/drivers/hwtracing/coresight/coresight-etr-perf-polling.h
new file mode 100644
index 0000000000000..d47b4424594e6
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etr-perf-polling.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright(C) 2021 Arm Limited. All rights reserved.
+ * Author: Daniel Kiss <daniel.kiss at arm.com>
+ */
+
+#ifndef _CORESIGHT_ETM_PERF_POLLING_H
+#define _CORESIGHT_ETM_PERF_POLLING_H
+
+#include <linux/coresight.h>
+#include <linux/perf_event.h>
+#include "coresight-etm-perf.h"
+#include "coresight-tmc.h"
+
+#ifdef CONFIG_CORESIGHT_ETR_PERF_POLL
+void etr_perf_polling_init(void);
+void etr_perf_polling_exit(void);
+void etr_perf_polling_handle_register(struct perf_output_handle *handle,
+ void (*tmc_etr_reset_hw)(struct tmc_drvdata *drvdata));
+void etr_perf_polling_handle_deregister(struct perf_output_handle *handle);
+void etr_perf_polling_event_start(struct perf_event *event,
+ struct etm_event_data *etm_event_data,
+ struct perf_output_handle *ctx_handle);
+void etr_perf_polling_event_stop(struct perf_event *event,
+ struct etm_event_data *etm_event_data);
+
+extern const struct attribute_group coresight_tmc_polling_group;
+
+#else /* !CONFIG_CORESIGHT_ETR_PERF_POLL */
+#define etr_perf_polling_init()
+#define etr_perf_polling_exit()
+#define etr_perf_polling_handle_register(...)
+#define etr_perf_polling_handle_deregister(...)
+#define etr_perf_polling_event_start(...)
+#define etr_perf_polling_event_stop(...)
+#endif
+
+#endif
diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c
index 74c6323d4d6ab..dbcdba162bd38 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-core.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-core.c
@@ -26,6 +26,7 @@
#include "coresight-priv.h"
#include "coresight-tmc.h"
+#include "coresight-etr-perf-polling.h"
DEFINE_CORESIGHT_DEVLIST(etb_devs, "tmc_etb");
DEFINE_CORESIGHT_DEVLIST(etf_devs, "tmc_etf");
@@ -365,6 +366,9 @@ static const struct attribute_group coresight_tmc_mgmt_group = {
static const struct attribute_group *coresight_tmc_groups[] = {
&coresight_tmc_group,
&coresight_tmc_mgmt_group,
+#ifdef CONFIG_CORESIGHT_ETR_PERF_POLL
+ &coresight_tmc_polling_group,
+#endif
NULL,
};
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 55c9b5fd9f832..67cd4bdcda71b 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -16,6 +16,7 @@
#include <linux/vmalloc.h>
#include "coresight-catu.h"
#include "coresight-etm-perf.h"
+#include "coresight-etr-perf-polling.h"
#include "coresight-priv.h"
#include "coresight-tmc.h"
@@ -1137,6 +1138,16 @@ void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
drvdata->etr_buf = NULL;
}
+#ifdef CONFIG_CORESIGHT_ETR_PERF_POLL
+
+static void tmc_etr_reset_hw(struct tmc_drvdata *drvdata)
+{
+ __tmc_etr_disable_hw(drvdata);
+ __tmc_etr_enable_hw(drvdata);
+}
+
+#endif
+
static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
{
int ret = 0;
@@ -1620,6 +1631,7 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data)
drvdata->mode = CS_MODE_PERF;
drvdata->perf_buf = etr_perf->etr_buf;
drvdata->perf_handle = handle;
+ etr_perf_polling_handle_register(handle, tmc_etr_reset_hw);
atomic_inc(csdev->refcnt);
}
@@ -1667,6 +1679,7 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev)
drvdata->mode = CS_MODE_DISABLED;
/* Reset perf specific data */
drvdata->perf_buf = NULL;
+ etr_perf_polling_handle_deregister(drvdata->perf_handle);
drvdata->perf_handle = NULL;
spin_unlock_irqrestore(&drvdata->spinlock, flags);
--
2.25.1
More information about the linux-arm-kernel
mailing list