Linux-libre 4.6.2-gnu

32 files changed, 3185 insertions, 1764 deletions

diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig
index c85935f35..db0541031 100644
--- a/drivers/hwtracing/coresight/Kconfig
+++ b/drivers/hwtracing/coresight/Kconfig
@@ -4,6 +4,7 @@
 menuconfig CORESIGHT
 	bool "CoreSight Tracing Support"
 	select ARM_AMBA
+	select PERF_EVENTS
 	help
 	  This framework provides a kernel interface for the CoreSight debug
 	  and trace drivers to register themselves with. It's intended to build
diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile
index 99f8e5f62..cf8c6d689 100644
--- a/drivers/hwtracing/coresight/Makefile
+++ b/drivers/hwtracing/coresight/Makefile
@@ -8,6 +8,8 @@ obj-$(CONFIG_CORESIGHT_SINK_TPIU) += coresight-tpiu.o
 obj-$(CONFIG_CORESIGHT_SINK_ETBV10) += coresight-etb10.o
 obj-$(CONFIG_CORESIGHT_LINKS_AND_SINKS) += coresight-funnel.o \
 					   coresight-replicator.o
-obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o
+obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o \
+					coresight-etm3x-sysfs.o \
+					coresight-etm-perf.o
 obj-$(CONFIG_CORESIGHT_SOURCE_ETM4X) += coresight-etm4x.o
 obj-$(CONFIG_CORESIGHT_QCOM_REPLICATOR) += coresight-replicator-qcom.o
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index 77d0f9c11..acbce7993 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -1,5 +1,7 @@
 /* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
+ * Description: CoreSight Embedded Trace Buffer driver
+ *
  * 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.
@@ -10,8 +12,8 @@
  * GNU General Public License for more details.
  */
 
+#include <asm/local.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
@@ -27,6 +29,11 @@
 #include <linux/coresight.h>
 #include <linux/amba/bus.h>
 #include <linux/clk.h>
+#include <linux/circ_buf.h>
+#include <linux/mm.h>
+#include <linux/perf_event.h>
+
+#include <asm/local.h>
 
 #include "coresight-priv.h"
 
@@ -64,6 +71,26 @@
 #define ETB_FRAME_SIZE_WORDS	4
 
 /**
+ * struct cs_buffer - keep track of a recording session' specifics
+ * @cur:	index of the current buffer
+ * @nr_pages:	max number of pages granted to us
+ * @offset:	offset within the current buffer
+ * @data_size:	how much we collected in this run
+ * @lost:	other than zero if we had a HW buffer wrap around
+ * @snapshot:	is this run in snapshot mode
+ * @data_pages:	a handle the ring buffer
+ */
+struct cs_buffers {
+	unsigned int		cur;
+	unsigned int		nr_pages;
+	unsigned long		offset;
+	local_t			data_size;
+	local_t			lost;
+	bool			snapshot;
+	void			**data_pages;
+};
+
+/**
  * struct etb_drvdata - specifics associated to an ETB component
  * @base:	memory mapped base address for this component.
  * @dev:	the device entity associated to this component.
@@ -71,10 +98,10 @@
  * @csdev:	component vitals needed by the framework.
  * @miscdev:	specifics to handle "/dev/xyz.etb" entry.
  * @spinlock:	only one at a time pls.
- * @in_use:	synchronise user space access to etb buffer.
+ * @reading:	synchronise user space access to etb buffer.
+ * @mode:	this ETB is being used.
  * @buf:	area of memory where ETB buffer content gets sent.
  * @buffer_depth: size of @buf.
- * @enable:	this ETB is being used.
  * @trigger_cntr: amount of words to store after a trigger.
  */
 struct etb_drvdata {
@@ -84,10 +111,10 @@ struct etb_drvdata {
 	struct coresight_device	*csdev;
 	struct miscdevice	miscdev;
 	spinlock_t		spinlock;
-	atomic_t		in_use;
+	local_t			reading;
+	local_t			mode;
 	u8			*buf;
 	u32			buffer_depth;
-	bool			enable;
 	u32			trigger_cntr;
 };
 
@@ -132,18 +159,31 @@ static void etb_enable_hw(struct etb_drvdata *drvdata)
 	CS_LOCK(drvdata->base);
 }
 
-static int etb_enable(struct coresight_device *csdev)
+static int etb_enable(struct coresight_device *csdev, u32 mode)
 {
-	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	u32 val;
 	unsigned long flags;
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	pm_runtime_get_sync(drvdata->dev);
+	val = local_cmpxchg(&drvdata->mode,
+			    CS_MODE_DISABLED, mode);
+	/*
+	 * When accessing from Perf, a HW buffer can be handled
+	 * by a single trace entity.  In sysFS mode many tracers
+	 * can be logging to the same HW buffer.
+	 */
+	if (val == CS_MODE_PERF)
+		return -EBUSY;
+
+	/* Nothing to do, the tracer is already enabled. */
+	if (val == CS_MODE_SYSFS)
+		goto out;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 	etb_enable_hw(drvdata);
-	drvdata->enable = true;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
+out:
 	dev_info(drvdata->dev, "ETB enabled\n");
 	return 0;
 }
@@ -244,17 +284,225 @@ static void etb_disable(struct coresight_device *csdev)
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 	etb_disable_hw(drvdata);
 	etb_dump_hw(drvdata);
-	drvdata->enable = false;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	pm_runtime_put(drvdata->dev);
+	local_set(&drvdata->mode, CS_MODE_DISABLED);
 
 	dev_info(drvdata->dev, "ETB disabled\n");
 }
 
+static void *etb_alloc_buffer(struct coresight_device *csdev, int cpu,
+			      void **pages, int nr_pages, bool overwrite)
+{
+	int node;
+	struct cs_buffers *buf;
+
+	if (cpu == -1)
+		cpu = smp_processor_id();
+	node = cpu_to_node(cpu);
+
+	buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node);
+	if (!buf)
+		return NULL;
+
+	buf->snapshot = overwrite;
+	buf->nr_pages = nr_pages;
+	buf->data_pages = pages;
+
+	return buf;
+}
+
+static void etb_free_buffer(void *config)
+{
+	struct cs_buffers *buf = config;
+
+	kfree(buf);
+}
+
+static int etb_set_buffer(struct coresight_device *csdev,
+			  struct perf_output_handle *handle,
+			  void *sink_config)
+{
+	int ret = 0;
+	unsigned long head;
+	struct cs_buffers *buf = sink_config;
+
+	/* wrap head around to the amount of space we have */
+	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
+
+	/* find the page to write to */
+	buf->cur = head / PAGE_SIZE;
+
+	/* and offset within that page */
+	buf->offset = head % PAGE_SIZE;
+
+	local_set(&buf->data_size, 0);
+
+	return ret;
+}
+
+static unsigned long etb_reset_buffer(struct coresight_device *csdev,
+				      struct perf_output_handle *handle,
+				      void *sink_config, bool *lost)
+{
+	unsigned long size = 0;
+	struct cs_buffers *buf = sink_config;
+
+	if (buf) {
+		/*
+		 * In snapshot mode ->data_size holds the new address of the
+		 * ring buffer's head.  The size itself is the whole address
+		 * range since we want the latest information.
+		 */
+		if (buf->snapshot)
+			handle->head = local_xchg(&buf->data_size,
+						  buf->nr_pages << PAGE_SHIFT);
+
+		/*
+		 * Tell the tracer PMU how much we got in this run and if
+		 * something went wrong along the way.  Nobody else can use
+		 * this cs_buffers instance until we are done.  As such
+		 * resetting parameters here and squaring off with the ring
+		 * buffer API in the tracer PMU is fine.
+		 */
+		*lost = !!local_xchg(&buf->lost, 0);
+		size = local_xchg(&buf->data_size, 0);
+	}
+
+	return size;
+}
+
+static void etb_update_buffer(struct coresight_device *csdev,
+			      struct perf_output_handle *handle,
+			      void *sink_config)
+{
+	int i, cur;
+	u8 *buf_ptr;
+	u32 read_ptr, write_ptr, capacity;
+	u32 status, read_data, to_read;
+	unsigned long offset;
+	struct cs_buffers *buf = sink_config;
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	if (!buf)
+		return;
+
+	capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS;
+
+	CS_UNLOCK(drvdata->base);
+	etb_disable_hw(drvdata);
+
+	/* unit is in words, not bytes */
+	read_ptr = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+	write_ptr = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+
+	/*
+	 * Entries should be aligned to the frame size.  If they are not
+	 * go back to the last alignement point to give decoding tools a
+	 * chance to fix things.
+	 */
+	if (write_ptr % ETB_FRAME_SIZE_WORDS) {
+		dev_err(drvdata->dev,
+			"write_ptr: %lu not aligned to formatter frame size\n",
+			(unsigned long)write_ptr);
+
+		write_ptr &= ~(ETB_FRAME_SIZE_WORDS - 1);
+		local_inc(&buf->lost);
+	}
+
+	/*
+	 * Get a hold of the status register and see if a wrap around
+	 * has occurred.  If so adjust things accordingly.  Otherwise
+	 * start at the beginning and go until the write pointer has
+	 * been reached.
+	 */
+	status = readl_relaxed(drvdata->base + ETB_STATUS_REG);
+	if (status & ETB_STATUS_RAM_FULL) {
+		local_inc(&buf->lost);
+		to_read = capacity;
+		read_ptr = write_ptr;
+	} else {
+		to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->buffer_depth);
+		to_read *= ETB_FRAME_SIZE_WORDS;
+	}
+
+	/*
+	 * Make sure we don't overwrite data that hasn't been consumed yet.
+	 * It is entirely possible that the HW buffer has more data than the
+	 * ring buffer can currently handle.  If so adjust the start address
+	 * to take only the last traces.
+	 *
+	 * In snapshot mode we are looking to get the latest traces only and as
+	 * such, we don't care about not overwriting data that hasn't been
+	 * processed by user space.
+	 */
+	if (!buf->snapshot && to_read > handle->size) {
+		u32 mask = ~(ETB_FRAME_SIZE_WORDS - 1);
+
+		/* The new read pointer must be frame size aligned */
+		to_read -= handle->size & mask;
+		/*
+		 * Move the RAM read pointer up, keeping in mind that
+		 * everything is in frame size units.
+		 */
+		read_ptr = (write_ptr + drvdata->buffer_depth) -
+					to_read / ETB_FRAME_SIZE_WORDS;
+		/* Wrap around if need be*/
+		read_ptr &= ~(drvdata->buffer_depth - 1);
+		/* let the decoder know we've skipped ahead */
+		local_inc(&buf->lost);
+	}
+
+	/* finally tell HW where we want to start reading from */
+	writel_relaxed(read_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+	cur = buf->cur;
+	offset = buf->offset;
+	for (i = 0; i < to_read; i += 4) {
+		buf_ptr = buf->data_pages[cur] + offset;
+		read_data = readl_relaxed(drvdata->base +
+					  ETB_RAM_READ_DATA_REG);
+		*buf_ptr++ = read_data >> 0;
+		*buf_ptr++ = read_data >> 8;
+		*buf_ptr++ = read_data >> 16;
+		*buf_ptr++ = read_data >> 24;
+
+		offset += 4;
+		if (offset >= PAGE_SIZE) {
+			offset = 0;
+			cur++;
+			/* wrap around at the end of the buffer */
+			cur &= buf->nr_pages - 1;
+		}
+	}
+
+	/* reset ETB buffer for next run */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+
+	/*
+	 * In snapshot mode all we have to do is communicate to
+	 * perf_aux_output_end() the address of the current head.  In full
+	 * trace mode the same function expects a size to move rb->aux_head
+	 * forward.
+	 */
+	if (buf->snapshot)
+		local_set(&buf->data_size, (cur * PAGE_SIZE) + offset);
+	else
+		local_add(to_read, &buf->data_size);
+
+	etb_enable_hw(drvdata);
+	CS_LOCK(drvdata->base);
+}
+
 static const struct coresight_ops_sink etb_sink_ops = {
 	.enable		= etb_enable,
 	.disable	= etb_disable,
+	.alloc_buffer	= etb_alloc_buffer,
+	.free_buffer	= etb_free_buffer,
+	.set_buffer	= etb_set_buffer,
+	.reset_buffer	= etb_reset_buffer,
+	.update_buffer	= etb_update_buffer,
 };
 
 static const struct coresight_ops etb_cs_ops = {
@@ -266,7 +514,7 @@ static void etb_dump(struct etb_drvdata *drvdata)
 	unsigned long flags;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	if (drvdata->enable) {
+	if (local_read(&drvdata->mode) == CS_MODE_SYSFS) {
 		etb_disable_hw(drvdata);
 		etb_dump_hw(drvdata);
 		etb_enable_hw(drvdata);
@@ -281,7 +529,7 @@ static int etb_open(struct inode *inode, struct file *file)
 	struct etb_drvdata *drvdata = container_of(file->private_data,
 						   struct etb_drvdata, miscdev);
 
-	if (atomic_cmpxchg(&drvdata->in_use, 0, 1))
+	if (local_cmpxchg(&drvdata->reading, 0, 1))
 		return -EBUSY;
 
 	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
@@ -317,7 +565,7 @@ static int etb_release(struct inode *inode, struct file *file)
 {
 	struct etb_drvdata *drvdata = container_of(file->private_data,
 						   struct etb_drvdata, miscdev);
-	atomic_set(&drvdata->in_use, 0);
+	local_set(&drvdata->reading, 0);
 
 	dev_dbg(drvdata->dev, "%s: released\n", __func__);
 	return 0;
@@ -489,15 +737,6 @@ err_misc_register:
 	return ret;
 }
 
-static int etb_remove(struct amba_device *adev)
-{
-	struct etb_drvdata *drvdata = amba_get_drvdata(adev);
-
-	misc_deregister(&drvdata->miscdev);
-	coresight_unregister(drvdata->csdev);
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int etb_runtime_suspend(struct device *dev)
 {
@@ -537,14 +776,10 @@ static struct amba_driver etb_driver = {
 		.name	= "coresight-etb10",
 		.owner	= THIS_MODULE,
 		.pm	= &etb_dev_pm_ops,
+		.suppress_bind_attrs = true,
 
 	},
 	.probe		= etb_probe,
-	.remove		= etb_remove,
 	.id_table	= etb_ids,
 };
-
-module_amba_driver(etb_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("CoreSight Embedded Trace Buffer driver");
+builtin_amba_driver(etb_driver);
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
new file mode 100644
index 000000000..755125f79
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -0,0 +1,393 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * 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/>.
+ */
+
+#include <linux/coresight.h>
+#include <linux/coresight-pmu.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include "coresight-priv.h"
+
+static struct pmu etm_pmu;
+static bool etm_perf_up;
+
+/**
+ * struct etm_event_data - Coresight specifics associated to an event
+ * @work:		Handle to free allocated memory outside IRQ context.
+ * @mask:		Hold the CPU(s) this event was set for.
+ * @snk_config:		The sink configuration.
+ * @path:		An array of path, each slot for one CPU.
+ */
+struct etm_event_data {
+	struct work_struct work;
+	cpumask_t mask;
+	void *snk_config;
+	struct list_head **path;
+};
+
+static DEFINE_PER_CPU(struct perf_output_handle, ctx_handle);
+static DEFINE_PER_CPU(struct coresight_device *, csdev_src);
+
+/* ETMv3.5/PTM's ETMCR is 'config' */
+PMU_FORMAT_ATTR(cycacc,		"config:" __stringify(ETM_OPT_CYCACC));
+PMU_FORMAT_ATTR(timestamp,	"config:" __stringify(ETM_OPT_TS));
+
+static struct attribute *etm_config_formats_attr[] = {
+	&format_attr_cycacc.attr,
+	&format_attr_timestamp.attr,
+	NULL,
+};
+
+static struct attribute_group etm_pmu_format_group = {
+	.name   = "format",
+	.attrs  = etm_config_formats_attr,
+};
+
+static const struct attribute_group *etm_pmu_attr_groups[] = {
+	&etm_pmu_format_group,
+	NULL,
+};
+
+static void etm_event_read(struct perf_event *event) {}
+
+static int etm_event_init(struct perf_event *event)
+{
+	if (event->attr.type != etm_pmu.type)
+		return -ENOENT;
+
+	return 0;
+}
+
+static void free_event_data(struct work_struct *work)
+{
+	int cpu;
+	cpumask_t *mask;
+	struct etm_event_data *event_data;
+	struct coresight_device *sink;
+
+	event_data = container_of(work, struct etm_event_data, work);
+	mask = &event_data->mask;
+	/*
+	 * First deal with the sink configuration.  See comment in
+	 * etm_setup_aux() about why we take the first available path.
+	 */
+	if (event_data->snk_config) {
+		cpu = cpumask_first(mask);
+		sink = coresight_get_sink(event_data->path[cpu]);
+		if (sink_ops(sink)->free_buffer)
+			sink_ops(sink)->free_buffer(event_data->snk_config);
+	}
+
+	for_each_cpu(cpu, mask) {
+		if (event_data->path[cpu])
+			coresight_release_path(event_data->path[cpu]);
+	}
+
+	kfree(event_data->path);
+	kfree(event_data);
+}
+
+static void *alloc_event_data(int cpu)
+{
+	int size;
+	cpumask_t *mask;
+	struct etm_event_data *event_data;
+
+	/* First get memory for the session's data */
+	event_data = kzalloc(sizeof(struct etm_event_data), GFP_KERNEL);
+	if (!event_data)
+		return NULL;
+
+	/* Make sure nothing disappears under us */
+	get_online_cpus();
+	size = num_online_cpus();
+
+	mask = &event_data->mask;
+	if (cpu != -1)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_copy(mask, cpu_online_mask);
+	put_online_cpus();
+
+	/*
+	 * Each CPU has a single path between source and destination.  As such
+	 * allocate an array using CPU numbers as indexes.  That way a path
+	 * for any CPU can easily be accessed at any given time.  We proceed
+	 * the same way for sessions involving a single CPU.  The cost of
+	 * unused memory when dealing with single CPU trace scenarios is small
+	 * compared to the cost of searching through an optimized array.
+	 */
+	event_data->path = kcalloc(size,
+				   sizeof(struct list_head *), GFP_KERNEL);
+	if (!event_data->path) {
+		kfree(event_data);
+		return NULL;
+	}
+
+	return event_data;
+}
+
+static void etm_free_aux(void *data)
+{
+	struct etm_event_data *event_data = data;
+
+	schedule_work(&event_data->work);
+}
+
+static void *etm_setup_aux(int event_cpu, void **pages,
+			   int nr_pages, bool overwrite)
+{
+	int cpu;
+	cpumask_t *mask;
+	struct coresight_device *sink;
+	struct etm_event_data *event_data = NULL;
+
+	event_data = alloc_event_data(event_cpu);
+	if (!event_data)
+		return NULL;
+
+	INIT_WORK(&event_data->work, free_event_data);
+
+	mask = &event_data->mask;
+
+	/* Setup the path for each CPU in a trace session */
+	for_each_cpu(cpu, mask) {
+		struct coresight_device *csdev;
+
+		csdev = per_cpu(csdev_src, cpu);
+		if (!csdev)
+			goto err;
+
+		/*
+		 * Building a path doesn't enable it, it simply builds a
+		 * list of devices from source to sink that can be
+		 * referenced later when the path is actually needed.
+		 */
+		event_data->path[cpu] = coresight_build_path(csdev);
+		if (!event_data->path[cpu])
+			goto err;
+	}
+
+	/*
+	 * In theory nothing prevent tracers in a trace session from being
+	 * associated with different sinks, nor having a sink per tracer.  But
+	 * until we have HW with this kind of topology and a way to convey
+	 * sink assignement from the perf cmd line we need to assume tracers
+	 * in a trace session are using the same sink.  Therefore pick the sink
+	 * found at the end of the first available path.
+	 */
+	cpu = cpumask_first(mask);
+	/* Grab the sink at the end of the path */
+	sink = coresight_get_sink(event_data->path[cpu]);
+	if (!sink)
+		goto err;
+
+	if (!sink_ops(sink)->alloc_buffer)
+		goto err;
+
+	/* Get the AUX specific data from the sink buffer */
+	event_data->snk_config =
+			sink_ops(sink)->alloc_buffer(sink, cpu, pages,
+						     nr_pages, overwrite);
+	if (!event_data->snk_config)
+		goto err;
+
+out:
+	return event_data;
+
+err:
+	etm_free_aux(event_data);
+	event_data = NULL;
+	goto out;
+}
+
+static void etm_event_start(struct perf_event *event, int flags)
+{
+	int cpu = smp_processor_id();
+	struct etm_event_data *event_data;
+	struct perf_output_handle *handle = this_cpu_ptr(&ctx_handle);
+	struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu);
+
+	if (!csdev)
+		goto fail;
+
+	/*
+	 * Deal with the ring buffer API and get a handle on the
+	 * session's information.
+	 */
+	event_data = perf_aux_output_begin(handle, event);
+	if (!event_data)
+		goto fail;
+
+	/* We need a sink, no need to continue without one */
+	sink = coresight_get_sink(event_data->path[cpu]);
+	if (WARN_ON_ONCE(!sink || !sink_ops(sink)->set_buffer))
+		goto fail_end_stop;
+
+	/* Configure the sink */
+	if (sink_ops(sink)->set_buffer(sink, handle,
+				       event_data->snk_config))
+		goto fail_end_stop;
+
+	/* Nothing will happen without a path */
+	if (coresight_enable_path(event_data->path[cpu], CS_MODE_PERF))
+		goto fail_end_stop;
+
+	/* Tell the perf core the event is alive */
+	event->hw.state = 0;
+
+	/* Finally enable the tracer */
+	if (source_ops(csdev)->enable(csdev, &event->attr, CS_MODE_PERF))
+		goto fail_end_stop;
+
+out:
+	return;
+
+fail_end_stop:
+	perf_aux_output_end(handle, 0, true);
+fail:
+	event->hw.state = PERF_HES_STOPPED;
+	goto out;
+}
+
+static void etm_event_stop(struct perf_event *event, int mode)
+{
+	bool lost;
+	int cpu = smp_processor_id();
+	unsigned long size;
+	struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu);
+	struct perf_output_handle *handle = this_cpu_ptr(&ctx_handle);
+	struct etm_event_data *event_data = perf_get_aux(handle);
+
+	if (event->hw.state == PERF_HES_STOPPED)
+		return;
+
+	if (!csdev)
+		return;
+
+	sink = coresight_get_sink(event_data->path[cpu]);
+	if (!sink)
+		return;
+
+	/* stop tracer */
+	source_ops(csdev)->disable(csdev);
+
+	/* tell the core */
+	event->hw.state = PERF_HES_STOPPED;
+
+	if (mode & PERF_EF_UPDATE) {
+		if (WARN_ON_ONCE(handle->event != event))
+			return;
+
+		/* update trace information */
+		if (!sink_ops(sink)->update_buffer)
+			return;
+
+		sink_ops(sink)->update_buffer(sink, handle,
+					      event_data->snk_config);
+
+		if (!sink_ops(sink)->reset_buffer)
+			return;
+
+		size = sink_ops(sink)->reset_buffer(sink, handle,
+						    event_data->snk_config,
+						    &lost);
+
+		perf_aux_output_end(handle, size, lost);
+	}
+
+	/* Disabling the path make its elements available to other sessions */
+	coresight_disable_path(event_data->path[cpu]);
+}
+
+static int etm_event_add(struct perf_event *event, int mode)
+{
+	int ret = 0;
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (mode & PERF_EF_START) {
+		etm_event_start(event, 0);
+		if (hwc->state & PERF_HES_STOPPED)
+			ret = -EINVAL;
+	} else {
+		hwc->state = PERF_HES_STOPPED;
+	}
+
+	return ret;
+}
+
+static void etm_event_del(struct perf_event *event, int mode)
+{
+	etm_event_stop(event, PERF_EF_UPDATE);
+}
+
+int etm_perf_symlink(struct coresight_device *csdev, bool link)
+{
+	char entry[sizeof("cpu9999999")];
+	int ret = 0, cpu = source_ops(csdev)->cpu_id(csdev);
+	struct device *pmu_dev = etm_pmu.dev;
+	struct device *cs_dev = &csdev->dev;
+
+	sprintf(entry, "cpu%d", cpu);
+
+	if (!etm_perf_up)
+		return -EPROBE_DEFER;
+
+	if (link) {
+		ret = sysfs_create_link(&pmu_dev->kobj, &cs_dev->kobj, entry);
+		if (ret)
+			return ret;
+		per_cpu(csdev_src, cpu) = csdev;
+	} else {
+		sysfs_remove_link(&pmu_dev->kobj, entry);
+		per_cpu(csdev_src, cpu) = NULL;
+	}
+
+	return 0;
+}
+
+static int __init etm_perf_init(void)
+{
+	int ret;
+
+	etm_pmu.capabilities	= PERF_PMU_CAP_EXCLUSIVE;
+
+	etm_pmu.attr_groups	= etm_pmu_attr_groups;
+	etm_pmu.task_ctx_nr	= perf_sw_context;
+	etm_pmu.read		= etm_event_read;
+	etm_pmu.event_init	= etm_event_init;
+	etm_pmu.setup_aux	= etm_setup_aux;
+	etm_pmu.free_aux	= etm_free_aux;
+	etm_pmu.start		= etm_event_start;
+	etm_pmu.stop		= etm_event_stop;
+	etm_pmu.add		= etm_event_add;
+	etm_pmu.del		= etm_event_del;
+
+	ret = perf_pmu_register(&etm_pmu, CORESIGHT_ETM_PMU_NAME, -1);
+	if (ret == 0)
+		etm_perf_up = true;
+
+	return ret;
+}
+device_initcall(etm_perf_init);
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h
new file mode 100644
index 000000000..87f5a134e
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * 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/>.
+ */
+
+#ifndef _CORESIGHT_ETM_PERF_H
+#define _CORESIGHT_ETM_PERF_H
+
+struct coresight_device;
+
+#ifdef CONFIG_CORESIGHT
+int etm_perf_symlink(struct coresight_device *csdev, bool link);
+
+#else
+static inline int etm_perf_symlink(struct coresight_device *csdev, bool link)
+{ return -EINVAL; }
+
+#endif /* CONFIG_CORESIGHT */
+
+#endif
diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h
index b4481eb29..51597cb2c 100644
--- a/drivers/hwtracing/coresight/coresight-etm.h
+++ b/drivers/hwtracing/coresight/coresight-etm.h
@@ -13,6 +13,7 @@
 #ifndef _CORESIGHT_CORESIGHT_ETM_H
 #define _CORESIGHT_CORESIGHT_ETM_H
 
+#include <asm/local.h>
 #include <linux/spinlock.h>
 #include "coresight-priv.h"
 
@@ -109,7 +110,10 @@
 #define ETM_MODE_STALL		BIT(2)
 #define ETM_MODE_TIMESTAMP	BIT(3)
 #define ETM_MODE_CTXID		BIT(4)
-#define ETM_MODE_ALL		0x1f
+#define ETM_MODE_ALL		(ETM_MODE_EXCLUDE | ETM_MODE_CYCACC | \
+				 ETM_MODE_STALL | ETM_MODE_TIMESTAMP | \
+				 ETM_MODE_CTXID | ETM_MODE_EXCL_KERN | \
+				 ETM_MODE_EXCL_USER)
 
 #define ETM_SQR_MASK		0x3
 #define ETM_TRACEID_MASK	0x3f
@@ -136,35 +140,16 @@
 #define ETM_DEFAULT_EVENT_VAL	(ETM_HARD_WIRE_RES_A	|	\
 				 ETM_ADD_COMP_0		|	\
 				 ETM_EVENT_NOT_A)
+
 /**
- * struct etm_drvdata - specifics associated to an ETM component
- * @base:	memory mapped base address for this component.
- * @dev:	the device entity associated to this component.
- * @atclk:	optional clock for the core parts of the ETM.
- * @csdev:	component vitals needed by the framework.
- * @spinlock:	only one at a time pls.
- * @cpu:	the cpu this component is affined to.
- * @port_size:	port size as reported by ETMCR bit 4-6 and 21.
- * @arch:	ETM/PTM version number.
- * @use_cpu14:	true if management registers need to be accessed via CP14.
- * @enable:	is this ETM/PTM currently tracing.
- * @sticky_enable: true if ETM base configuration has been done.
- * @boot_enable:true if we should start tracing at boot time.
- * @os_unlock:	true if access to management registers is allowed.
- * @nr_addr_cmp:Number of pairs of address comparators as found in ETMCCR.
- * @nr_cntr:	Number of counters as found in ETMCCR bit 13-15.
- * @nr_ext_inp:	Number of external input as found in ETMCCR bit 17-19.
- * @nr_ext_out:	Number of external output as found in ETMCCR bit 20-22.
- * @nr_ctxid_cmp: Number of contextID comparators as found in ETMCCR bit 24-25.
- * @etmccr:	value of register ETMCCR.
- * @etmccer:	value of register ETMCCER.
- * @traceid:	value of the current ID for this component.
+ * struct etm_config - configuration information related to an ETM
  * @mode:	controls various modes supported by this ETM/PTM.
  * @ctrl:	used in conjunction with @mode.
  * @trigger_event: setting for register ETMTRIGGER.
  * @startstop_ctrl: setting for register ETMTSSCR.
  * @enable_event: setting for register ETMTEEVR.
  * @enable_ctrl1: setting for register ETMTECR1.
+ * @enable_ctrl2: setting for register ETMTECR2.
  * @fifofull_level: setting for register ETMFFLR.
  * @addr_idx:	index for the address comparator selection.
  * @addr_val:	value for address comparator register.
@@ -189,36 +174,16 @@
  * @ctxid_mask: mask applicable to all the context IDs.
  * @sync_freq:	Synchronisation frequency.
  * @timestamp_event: Defines an event that requests the insertion
-		     of a timestamp into the trace stream.
+ *		     of a timestamp into the trace stream.
  */
-struct etm_drvdata {
-	void __iomem			*base;
-	struct device			*dev;
-	struct clk			*atclk;
-	struct coresight_device		*csdev;
-	spinlock_t			spinlock;
-	int				cpu;
-	int				port_size;
-	u8				arch;
-	bool				use_cp14;
-	bool				enable;
-	bool				sticky_enable;
-	bool				boot_enable;
-	bool				os_unlock;
-	u8				nr_addr_cmp;
-	u8				nr_cntr;
-	u8				nr_ext_inp;
-	u8				nr_ext_out;
-	u8				nr_ctxid_cmp;
-	u32				etmccr;
-	u32				etmccer;
-	u32				traceid;
+struct etm_config {
 	u32				mode;
 	u32				ctrl;
 	u32				trigger_event;
 	u32				startstop_ctrl;
 	u32				enable_event;
 	u32				enable_ctrl1;
+	u32				enable_ctrl2;
 	u32				fifofull_level;
 	u8				addr_idx;
 	u32				addr_val[ETM_MAX_ADDR_CMP];
@@ -244,6 +209,56 @@ struct etm_drvdata {
 	u32				timestamp_event;
 };
 
+/**
+ * struct etm_drvdata - specifics associated to an ETM component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @atclk:	optional clock for the core parts of the ETM.
+ * @csdev:	component vitals needed by the framework.
+ * @spinlock:	only one at a time pls.
+ * @cpu:	the cpu this component is affined to.
+ * @port_size:	port size as reported by ETMCR bit 4-6 and 21.
+ * @arch:	ETM/PTM version number.
+ * @use_cpu14:	true if management registers need to be accessed via CP14.
+ * @mode:	this tracer's mode, i.e sysFS, Perf or disabled.
+ * @sticky_enable: true if ETM base configuration has been done.
+ * @boot_enable:true if we should start tracing at boot time.
+ * @os_unlock:	true if access to management registers is allowed.
+ * @nr_addr_cmp:Number of pairs of address comparators as found in ETMCCR.
+ * @nr_cntr:	Number of counters as found in ETMCCR bit 13-15.
+ * @nr_ext_inp:	Number of external input as found in ETMCCR bit 17-19.
+ * @nr_ext_out:	Number of external output as found in ETMCCR bit 20-22.
+ * @nr_ctxid_cmp: Number of contextID comparators as found in ETMCCR bit 24-25.
+ * @etmccr:	value of register ETMCCR.
+ * @etmccer:	value of register ETMCCER.
+ * @traceid:	value of the current ID for this component.
+ * @config:	structure holding configuration parameters.
+ */
+struct etm_drvdata {
+	void __iomem			*base;
+	struct device			*dev;
+	struct clk			*atclk;
+	struct coresight_device		*csdev;
+	spinlock_t			spinlock;
+	int				cpu;
+	int				port_size;
+	u8				arch;
+	bool				use_cp14;
+	local_t				mode;
+	bool				sticky_enable;
+	bool				boot_enable;
+	bool				os_unlock;
+	u8				nr_addr_cmp;
+	u8				nr_cntr;
+	u8				nr_ext_inp;
+	u8				nr_ext_out;
+	u8				nr_ctxid_cmp;
+	u32				etmccr;
+	u32				etmccer;
+	u32				traceid;
+	struct etm_config		config;
+};
+
 enum etm_addr_type {
 	ETM_ADDR_TYPE_NONE,
 	ETM_ADDR_TYPE_SINGLE,
@@ -251,4 +266,39 @@ enum etm_addr_type {
 	ETM_ADDR_TYPE_START,
 	ETM_ADDR_TYPE_STOP,
 };
+
+static inline void etm_writel(struct etm_drvdata *drvdata,
+			      u32 val, u32 off)
+{
+	if (drvdata->use_cp14) {
+		if (etm_writel_cp14(off, val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		writel_relaxed(val, drvdata->base + off);
+	}
+}
+
+static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off)
+{
+	u32 val;
+
+	if (drvdata->use_cp14) {
+		if (etm_readl_cp14(off, &val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		val = readl_relaxed(drvdata->base + off);
+	}
+
+	return val;
+}
+
+extern const struct attribute_group *coresight_etm_groups[];
+int etm_get_trace_id(struct etm_drvdata *drvdata);
+void etm_set_default(struct etm_config *config);
+void etm_config_trace_mode(struct etm_config *config);
+struct etm_config *get_etm_config(struct etm_drvdata *drvdata);
 #endif
diff --git a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
new file mode 100644
index 000000000..cbb4046c1
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
@@ -0,0 +1,1272 @@
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ *
+ * 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/>.
+ */
+
+#include <linux/pm_runtime.h>
+#include <linux/sysfs.h>
+#include "coresight-etm.h"
+
+static ssize_t nr_addr_cmp_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_addr_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_addr_cmp);
+
+static ssize_t nr_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_cntr;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_cntr);
+
+static ssize_t nr_ctxid_cmp_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_ctxid_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_ctxid_cmp);
+
+static ssize_t etmsr_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	unsigned long flags, val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	pm_runtime_get_sync(drvdata->dev);
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	val = etm_readl(drvdata, ETMSR);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	pm_runtime_put(drvdata->dev);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(etmsr);
+
+static ssize_t reset_store(struct device *dev,
+			   struct device_attribute *attr,
+			   const char *buf, size_t size)
+{
+	int i, ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		spin_lock(&drvdata->spinlock);
+		memset(config, 0, sizeof(struct etm_config));
+		config->mode = ETM_MODE_EXCLUDE;
+		config->trigger_event = ETM_DEFAULT_EVENT_VAL;
+		for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+			config->addr_type[i] = ETM_ADDR_TYPE_NONE;
+		}
+
+		etm_set_default(config);
+		spin_unlock(&drvdata->spinlock);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_WO(reset);
+
+static ssize_t mode_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->mode;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t mode_store(struct device *dev,
+			  struct device_attribute *attr,
+			  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	config->mode = val & ETM_MODE_ALL;
+
+	if (config->mode & ETM_MODE_EXCLUDE)
+		config->enable_ctrl1 |= ETMTECR1_INC_EXC;
+	else
+		config->enable_ctrl1 &= ~ETMTECR1_INC_EXC;
+
+	if (config->mode & ETM_MODE_CYCACC)
+		config->ctrl |= ETMCR_CYC_ACC;
+	else
+		config->ctrl &= ~ETMCR_CYC_ACC;
+
+	if (config->mode & ETM_MODE_STALL) {
+		if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
+			dev_warn(drvdata->dev, "stall mode not supported\n");
+			ret = -EINVAL;
+			goto err_unlock;
+		}
+		config->ctrl |= ETMCR_STALL_MODE;
+	 } else
+		config->ctrl &= ~ETMCR_STALL_MODE;
+
+	if (config->mode & ETM_MODE_TIMESTAMP) {
+		if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
+			dev_warn(drvdata->dev, "timestamp not supported\n");
+			ret = -EINVAL;
+			goto err_unlock;
+		}
+		config->ctrl |= ETMCR_TIMESTAMP_EN;
+	} else
+		config->ctrl &= ~ETMCR_TIMESTAMP_EN;
+
+	if (config->mode & ETM_MODE_CTXID)
+		config->ctrl |= ETMCR_CTXID_SIZE;
+	else
+		config->ctrl &= ~ETMCR_CTXID_SIZE;
+
+	if (config->mode & (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER))
+		etm_config_trace_mode(config);
+
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+
+err_unlock:
+	spin_unlock(&drvdata->spinlock);
+	return ret;
+}
+static DEVICE_ATTR_RW(mode);
+
+static ssize_t trigger_event_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->trigger_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_event_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->trigger_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_event);
+
+static ssize_t enable_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->enable_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t enable_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->enable_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_event);
+
+static ssize_t fifofull_level_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->fifofull_level;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t fifofull_level_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->fifofull_level = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(fifofull_level);
+
+static ssize_t addr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->addr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_addr_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	config->addr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_idx);
+
+static ssize_t addr_single_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      config->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	val = config->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_single_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      config->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	config->addr_val[idx] = val;
+	config->addr_type[idx] = ETM_ADDR_TYPE_SINGLE;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_single);
+
+static ssize_t addr_range_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((config->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       config->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (config->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       config->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val1 = config->addr_val[idx];
+	val2 = config->addr_val[idx + 1];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx %#lx\n", val1, val2);
+}
+
+static ssize_t addr_range_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+		return -EINVAL;
+	/* Lower address comparator cannot have a higher address value */
+	if (val1 > val2)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((config->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       config->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (config->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       config->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	config->addr_val[idx] = val1;
+	config->addr_type[idx] = ETM_ADDR_TYPE_RANGE;
+	config->addr_val[idx + 1] = val2;
+	config->addr_type[idx + 1] = ETM_ADDR_TYPE_RANGE;
+	config->enable_ctrl1 |= (1 << (idx/2));
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_range);
+
+static ssize_t addr_start_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      config->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = config->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_start_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      config->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	config->addr_val[idx] = val;
+	config->addr_type[idx] = ETM_ADDR_TYPE_START;
+	config->startstop_ctrl |= (1 << idx);
+	config->enable_ctrl1 |= BIT(25);
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_start);
+
+static ssize_t addr_stop_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      config->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = config->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_stop_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      config->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	config->addr_val[idx] = val;
+	config->addr_type[idx] = ETM_ADDR_TYPE_STOP;
+	config->startstop_ctrl |= (1 << (idx + 16));
+	config->enable_ctrl1 |= ETMTECR1_START_STOP;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_stop);
+
+static ssize_t addr_acctype_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->addr_acctype[config->addr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_acctype_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	config->addr_acctype[config->addr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_acctype);
+
+static ssize_t cntr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->cntr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_cntr)
+		return -EINVAL;
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	config->cntr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_idx);
+
+static ssize_t cntr_rld_val_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->cntr_rld_val[config->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_val_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	config->cntr_rld_val[config->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_val);
+
+static ssize_t cntr_event_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->cntr_event[config->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_event_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	config->cntr_event[config->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_event);
+
+static ssize_t cntr_rld_event_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->cntr_rld_event[config->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_event_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	config->cntr_rld_event[config->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_event);
+
+static ssize_t cntr_val_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int i, ret = 0;
+	u32 val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	if (!local_read(&drvdata->mode)) {
+		spin_lock(&drvdata->spinlock);
+		for (i = 0; i < drvdata->nr_cntr; i++)
+			ret += sprintf(buf, "counter %d: %x\n",
+				       i, config->cntr_val[i]);
+		spin_unlock(&drvdata->spinlock);
+		return ret;
+	}
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		val = etm_readl(drvdata, ETMCNTVRn(i));
+		ret += sprintf(buf, "counter %d: %x\n", i, val);
+	}
+
+	return ret;
+}
+
+static ssize_t cntr_val_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	config->cntr_val[config->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_val);
+
+static ssize_t seq_12_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->seq_12_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_12_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->seq_12_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_12_event);
+
+static ssize_t seq_21_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->seq_21_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_21_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->seq_21_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_21_event);
+
+static ssize_t seq_23_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->seq_23_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_23_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->seq_23_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_23_event);
+
+static ssize_t seq_31_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->seq_31_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_31_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->seq_31_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_31_event);
+
+static ssize_t seq_32_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->seq_32_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_32_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->seq_32_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_32_event);
+
+static ssize_t seq_13_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->seq_13_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_13_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->seq_13_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_13_event);
+
+static ssize_t seq_curr_state_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val, flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	if (!local_read(&drvdata->mode)) {
+		val = config->seq_curr_state;
+		goto out;
+	}
+
+	pm_runtime_get_sync(drvdata->dev);
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	pm_runtime_put(drvdata->dev);
+out:
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_curr_state_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val > ETM_SEQ_STATE_MAX_VAL)
+		return -EINVAL;
+
+	config->seq_curr_state = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(seq_curr_state);
+
+static ssize_t ctxid_idx_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->ctxid_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_idx_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_ctxid_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	config->ctxid_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_idx);
+
+static ssize_t ctxid_pid_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->ctxid_vpid[config->ctxid_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_pid_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long vpid, pid;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &vpid);
+	if (ret)
+		return ret;
+
+	pid = coresight_vpid_to_pid(vpid);
+
+	spin_lock(&drvdata->spinlock);
+	config->ctxid_pid[config->ctxid_idx] = pid;
+	config->ctxid_vpid[config->ctxid_idx] = vpid;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_pid);
+
+static ssize_t ctxid_mask_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->ctxid_mask;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_mask_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->ctxid_mask = val;
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_mask);
+
+static ssize_t sync_freq_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->sync_freq;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t sync_freq_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->sync_freq = val & ETM_SYNC_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(sync_freq);
+
+static ssize_t timestamp_event_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	val = config->timestamp_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t timestamp_event_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etm_config *config = &drvdata->config;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	config->timestamp_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(timestamp_event);
+
+static ssize_t cpu_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	int val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->cpu;
+	return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+
+}
+static DEVICE_ATTR_RO(cpu);
+
+static ssize_t traceid_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = etm_get_trace_id(drvdata);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t traceid_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->traceid = val & ETM_TRACEID_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(traceid);
+
+static struct attribute *coresight_etm_attrs[] = {
+	&dev_attr_nr_addr_cmp.attr,
+	&dev_attr_nr_cntr.attr,
+	&dev_attr_nr_ctxid_cmp.attr,
+	&dev_attr_etmsr.attr,
+	&dev_attr_reset.attr,
+	&dev_attr_mode.attr,
+	&dev_attr_trigger_event.attr,
+	&dev_attr_enable_event.attr,
+	&dev_attr_fifofull_level.attr,
+	&dev_attr_addr_idx.attr,
+	&dev_attr_addr_single.attr,
+	&dev_attr_addr_range.attr,
+	&dev_attr_addr_start.attr,
+	&dev_attr_addr_stop.attr,
+	&dev_attr_addr_acctype.attr,
+	&dev_attr_cntr_idx.attr,
+	&dev_attr_cntr_rld_val.attr,
+	&dev_attr_cntr_event.attr,
+	&dev_attr_cntr_rld_event.attr,
+	&dev_attr_cntr_val.attr,
+	&dev_attr_seq_12_event.attr,
+	&dev_attr_seq_21_event.attr,
+	&dev_attr_seq_23_event.attr,
+	&dev_attr_seq_31_event.attr,
+	&dev_attr_seq_32_event.attr,
+	&dev_attr_seq_13_event.attr,
+	&dev_attr_seq_curr_state.attr,
+	&dev_attr_ctxid_idx.attr,
+	&dev_attr_ctxid_pid.attr,
+	&dev_attr_ctxid_mask.attr,
+	&dev_attr_sync_freq.attr,
+	&dev_attr_timestamp_event.attr,
+	&dev_attr_traceid.attr,
+	&dev_attr_cpu.attr,
+	NULL,
+};
+
+#define coresight_simple_func(name, offset)                             \
+static ssize_t name##_show(struct device *_dev,                         \
+			   struct device_attribute *attr, char *buf)    \
+{                                                                       \
+	struct etm_drvdata *drvdata = dev_get_drvdata(_dev->parent);    \
+	return scnprintf(buf, PAGE_SIZE, "0x%x\n",                      \
+			 readl_relaxed(drvdata->base + offset));        \
+}                                                                       \
+DEVICE_ATTR_RO(name)
+
+coresight_simple_func(etmccr, ETMCCR);
+coresight_simple_func(etmccer, ETMCCER);
+coresight_simple_func(etmscr, ETMSCR);
+coresight_simple_func(etmidr, ETMIDR);
+coresight_simple_func(etmcr, ETMCR);
+coresight_simple_func(etmtraceidr, ETMTRACEIDR);
+coresight_simple_func(etmteevr, ETMTEEVR);
+coresight_simple_func(etmtssvr, ETMTSSCR);
+coresight_simple_func(etmtecr1, ETMTECR1);
+coresight_simple_func(etmtecr2, ETMTECR2);
+
+static struct attribute *coresight_etm_mgmt_attrs[] = {
+	&dev_attr_etmccr.attr,
+	&dev_attr_etmccer.attr,
+	&dev_attr_etmscr.attr,
+	&dev_attr_etmidr.attr,
+	&dev_attr_etmcr.attr,
+	&dev_attr_etmtraceidr.attr,
+	&dev_attr_etmteevr.attr,
+	&dev_attr_etmtssvr.attr,
+	&dev_attr_etmtecr1.attr,
+	&dev_attr_etmtecr2.attr,
+	NULL,
+};
+
+static const struct attribute_group coresight_etm_group = {
+	.attrs = coresight_etm_attrs,
+};
+
+static const struct attribute_group coresight_etm_mgmt_group = {
+	.attrs = coresight_etm_mgmt_attrs,
+	.name = "mgmt",
+};
+
+const struct attribute_group *coresight_etm_groups[] = {
+	&coresight_etm_group,
+	&coresight_etm_mgmt_group,
+	NULL,
+};
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index d630b7ece..d83ab8267 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -1,5 +1,7 @@
 /* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
+ * Description: CoreSight Program Flow Trace driver
+ *
  * 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.
@@ -11,7 +13,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
@@ -27,14 +29,21 @@
 #include <linux/cpu.h>
 #include <linux/of.h>
 #include <linux/coresight.h>
+#include <linux/coresight-pmu.h>
 #include <linux/amba/bus.h>
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/clk.h>
+#include <linux/perf_event.h>
 #include <asm/sections.h>
 
 #include "coresight-etm.h"
+#include "coresight-etm-perf.h"
 
+/*
+ * Not really modular but using module_param is the easiest way to
+ * remain consistent with existing use cases for now.
+ */
 static int boot_enable;
 module_param_named(boot_enable, boot_enable, int, S_IRUGO);
 
@@ -42,45 +51,16 @@ module_param_named(boot_enable, boot_enable, int, S_IRUGO);
 static int etm_count;
 static struct etm_drvdata *etmdrvdata[NR_CPUS];
 
-static inline void etm_writel(struct etm_drvdata *drvdata,
-			      u32 val, u32 off)
-{
-	if (drvdata->use_cp14) {
-		if (etm_writel_cp14(off, val)) {
-			dev_err(drvdata->dev,
-				"invalid CP14 access to ETM reg: %#x", off);
-		}
-	} else {
-		writel_relaxed(val, drvdata->base + off);
-	}
-}
-
-static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off)
-{
-	u32 val;
-
-	if (drvdata->use_cp14) {
-		if (etm_readl_cp14(off, &val)) {
-			dev_err(drvdata->dev,
-				"invalid CP14 access to ETM reg: %#x", off);
-		}
-	} else {
-		val = readl_relaxed(drvdata->base + off);
-	}
-
-	return val;
-}
-
 /*
  * Memory mapped writes to clear os lock are not supported on some processors
  * and OS lock must be unlocked before any memory mapped access on such
  * processors, otherwise memory mapped reads/writes will be invalid.
  */
-static void etm_os_unlock(void *info)
+static void etm_os_unlock(struct etm_drvdata *drvdata)
 {
-	struct etm_drvdata *drvdata = (struct etm_drvdata *)info;
 	/* Writing any value to ETMOSLAR unlocks the trace registers */
 	etm_writel(drvdata, 0x0, ETMOSLAR);
+	drvdata->os_unlock = true;
 	isb();
 }
 
@@ -215,36 +195,156 @@ static void etm_clr_prog(struct etm_drvdata *drvdata)
 	}
 }
 
-static void etm_set_default(struct etm_drvdata *drvdata)
+void etm_set_default(struct etm_config *config)
 {
 	int i;
 
-	drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
-	drvdata->enable_event = ETM_HARD_WIRE_RES_A;
+	if (WARN_ON_ONCE(!config))
+		return;
 
-	drvdata->seq_12_event = ETM_DEFAULT_EVENT_VAL;
-	drvdata->seq_21_event = ETM_DEFAULT_EVENT_VAL;
-	drvdata->seq_23_event = ETM_DEFAULT_EVENT_VAL;
-	drvdata->seq_31_event = ETM_DEFAULT_EVENT_VAL;
-	drvdata->seq_32_event = ETM_DEFAULT_EVENT_VAL;
-	drvdata->seq_13_event = ETM_DEFAULT_EVENT_VAL;
-	drvdata->timestamp_event = ETM_DEFAULT_EVENT_VAL;
+	/*
+	 * Taken verbatim from the TRM:
+	 *
+	 * To trace all memory:
+	 *  set bit [24] in register 0x009, the ETMTECR1, to 1
+	 *  set all other bits in register 0x009, the ETMTECR1, to 0
+	 *  set all bits in register 0x007, the ETMTECR2, to 0
+	 *  set register 0x008, the ETMTEEVR, to 0x6F (TRUE).
+	 */
+	config->enable_ctrl1 = BIT(24);
+	config->enable_ctrl2 = 0x0;
+	config->enable_event = ETM_HARD_WIRE_RES_A;
 
-	for (i = 0; i < drvdata->nr_cntr; i++) {
-		drvdata->cntr_rld_val[i] = 0x0;
-		drvdata->cntr_event[i] = ETM_DEFAULT_EVENT_VAL;
-		drvdata->cntr_rld_event[i] = ETM_DEFAULT_EVENT_VAL;
-		drvdata->cntr_val[i] = 0x0;
+	config->trigger_event = ETM_DEFAULT_EVENT_VAL;
+	config->enable_event = ETM_HARD_WIRE_RES_A;
+
+	config->seq_12_event = ETM_DEFAULT_EVENT_VAL;
+	config->seq_21_event = ETM_DEFAULT_EVENT_VAL;
+	config->seq_23_event = ETM_DEFAULT_EVENT_VAL;
+	config->seq_31_event = ETM_DEFAULT_EVENT_VAL;
+	config->seq_32_event = ETM_DEFAULT_EVENT_VAL;
+	config->seq_13_event = ETM_DEFAULT_EVENT_VAL;
+	config->timestamp_event = ETM_DEFAULT_EVENT_VAL;
+
+	for (i = 0; i < ETM_MAX_CNTR; i++) {
+		config->cntr_rld_val[i] = 0x0;
+		config->cntr_event[i] = ETM_DEFAULT_EVENT_VAL;
+		config->cntr_rld_event[i] = ETM_DEFAULT_EVENT_VAL;
+		config->cntr_val[i] = 0x0;
 	}
 
-	drvdata->seq_curr_state = 0x0;
-	drvdata->ctxid_idx = 0x0;
-	for (i = 0; i < drvdata->nr_ctxid_cmp; i++) {
-		drvdata->ctxid_pid[i] = 0x0;
-		drvdata->ctxid_vpid[i] = 0x0;
+	config->seq_curr_state = 0x0;
+	config->ctxid_idx = 0x0;
+	for (i = 0; i < ETM_MAX_CTXID_CMP; i++) {
+		config->ctxid_pid[i] = 0x0;
+		config->ctxid_vpid[i] = 0x0;
 	}
 
-	drvdata->ctxid_mask = 0x0;
+	config->ctxid_mask = 0x0;
+}
+
+void etm_config_trace_mode(struct etm_config *config)
+{
+	u32 flags, mode;
+
+	mode = config->mode;
+
+	mode &= (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER);
+
+	/* excluding kernel AND user space doesn't make sense */
+	if (mode == (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER))
+		return;
+
+	/* nothing to do if neither flags are set */
+	if (!(mode & ETM_MODE_EXCL_KERN) && !(mode & ETM_MODE_EXCL_USER))
+		return;
+
+	flags = (1 << 0 |	/* instruction execute */
+		 3 << 3 |	/* ARM instruction */
+		 0 << 5 |	/* No data value comparison */
+		 0 << 7 |	/* No exact mach */
+		 0 << 8);	/* Ignore context ID */
+
+	/* No need to worry about single address comparators. */
+	config->enable_ctrl2 = 0x0;
+
+	/* Bit 0 is address range comparator 1 */
+	config->enable_ctrl1 = ETMTECR1_ADDR_COMP_1;
+
+	/*
+	 * On ETMv3.5:
+	 * ETMACTRn[13,11] == Non-secure state comparison control
+	 * ETMACTRn[12,10] == Secure state comparison control
+	 *
+	 * b00 == Match in all modes in this state
+	 * b01 == Do not match in any more in this state
+	 * b10 == Match in all modes excepts user mode in this state
+	 * b11 == Match only in user mode in this state
+	 */
+
+	/* Tracing in secure mode is not supported at this time */
+	flags |= (0 << 12 | 1 << 10);
+
+	if (mode & ETM_MODE_EXCL_USER) {
+		/* exclude user, match all modes except user mode */
+		flags |= (1 << 13 | 0 << 11);
+	} else {
+		/* exclude kernel, match only in user mode */
+		flags |= (1 << 13 | 1 << 11);
+	}
+
+	/*
+	 * The ETMEEVR register is already set to "hard wire A".  As such
+	 * all there is to do is setup an address comparator that spans
+	 * the entire address range and configure the state and mode bits.
+	 */
+	config->addr_val[0] = (u32) 0x0;
+	config->addr_val[1] = (u32) ~0x0;
+	config->addr_acctype[0] = flags;
+	config->addr_acctype[1] = flags;
+	config->addr_type[0] = ETM_ADDR_TYPE_RANGE;
+	config->addr_type[1] = ETM_ADDR_TYPE_RANGE;
+}
+
+#define ETM3X_SUPPORTED_OPTIONS (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN)
+
+static int etm_parse_event_config(struct etm_drvdata *drvdata,
+				  struct perf_event_attr *attr)
+{
+	struct etm_config *config = &drvdata->config;
+
+	if (!attr)
+		return -EINVAL;
+
+	/* Clear configuration from previous run */
+	memset(config, 0, sizeof(struct etm_config));
+
+	if (attr->exclude_kernel)
+		config->mode = ETM_MODE_EXCL_KERN;
+
+	if (attr->exclude_user)
+		config->mode = ETM_MODE_EXCL_USER;
+
+	/* Always start from the default config */
+	etm_set_default(config);
+
+	/*
+	 * By default the tracers are configured to trace the whole address
+	 * range.  Narrow the field only if requested by user space.
+	 */
+	if (config->mode)
+		etm_config_trace_mode(config);
+
+	/*
+	 * At this time only cycle accurate and timestamp options are
+	 * available.
+	 */
+	if (attr->config & ~ETM3X_SUPPORTED_OPTIONS)
+		return -EINVAL;
+
+	config->ctrl = attr->config;
+
+	return 0;
 }
 
 static void etm_enable_hw(void *info)
@@ -252,6 +352,7 @@ static void etm_enable_hw(void *info)
 	int i;
 	u32 etmcr;
 	struct etm_drvdata *drvdata = info;
+	struct etm_config *config = &drvdata->config;
 
 	CS_UNLOCK(drvdata->base);
 
@@ -265,65 +366,74 @@ static void etm_enable_hw(void *info)
 	etm_set_prog(drvdata);
 
 	etmcr = etm_readl(drvdata, ETMCR);
-	etmcr &= (ETMCR_PWD_DWN | ETMCR_ETM_PRG);
+	/* Clear setting from a previous run if need be */
+	etmcr &= ~ETM3X_SUPPORTED_OPTIONS;
 	etmcr |= drvdata->port_size;
-	etm_writel(drvdata, drvdata->ctrl | etmcr, ETMCR);
-	etm_writel(drvdata, drvdata->trigger_event, ETMTRIGGER);
-	etm_writel(drvdata, drvdata->startstop_ctrl, ETMTSSCR);
-	etm_writel(drvdata, drvdata->enable_event, ETMTEEVR);
-	etm_writel(drvdata, drvdata->enable_ctrl1, ETMTECR1);
-	etm_writel(drvdata, drvdata->fifofull_level, ETMFFLR);
+	etmcr |= ETMCR_ETM_EN;
+	etm_writel(drvdata, config->ctrl | etmcr, ETMCR);
+	etm_writel(drvdata, config->trigger_event, ETMTRIGGER);
+	etm_writel(drvdata, config->startstop_ctrl, ETMTSSCR);
+	etm_writel(drvdata, config->enable_event, ETMTEEVR);
+	etm_writel(drvdata, config->enable_ctrl1, ETMTECR1);
+	etm_writel(drvdata, config->fifofull_level, ETMFFLR);
 	for (i = 0; i < drvdata->nr_addr_cmp; i++) {
-		etm_writel(drvdata, drvdata->addr_val[i], ETMACVRn(i));
-		etm_writel(drvdata, drvdata->addr_acctype[i], ETMACTRn(i));
+		etm_writel(drvdata, config->addr_val[i], ETMACVRn(i));
+		etm_writel(drvdata, config->addr_acctype[i], ETMACTRn(i));
 	}
 	for (i = 0; i < drvdata->nr_cntr; i++) {
-		etm_writel(drvdata, drvdata->cntr_rld_val[i], ETMCNTRLDVRn(i));
-		etm_writel(drvdata, drvdata->cntr_event[i], ETMCNTENRn(i));
-		etm_writel(drvdata, drvdata->cntr_rld_event[i],
+		etm_writel(drvdata, config->cntr_rld_val[i], ETMCNTRLDVRn(i));
+		etm_writel(drvdata, config->cntr_event[i], ETMCNTENRn(i));
+		etm_writel(drvdata, config->cntr_rld_event[i],
 			   ETMCNTRLDEVRn(i));
-		etm_writel(drvdata, drvdata->cntr_val[i], ETMCNTVRn(i));
-	}
-	etm_writel(drvdata, drvdata->seq_12_event, ETMSQ12EVR);
-	etm_writel(drvdata, drvdata->seq_21_event, ETMSQ21EVR);
-	etm_writel(drvdata, drvdata->seq_23_event, ETMSQ23EVR);
-	etm_writel(drvdata, drvdata->seq_31_event, ETMSQ31EVR);
-	etm_writel(drvdata, drvdata->seq_32_event, ETMSQ32EVR);
-	etm_writel(drvdata, drvdata->seq_13_event, ETMSQ13EVR);
-	etm_writel(drvdata, drvdata->seq_curr_state, ETMSQR);
+		etm_writel(drvdata, config->cntr_val[i], ETMCNTVRn(i));
+	}
+	etm_writel(drvdata, config->seq_12_event, ETMSQ12EVR);
+	etm_writel(drvdata, config->seq_21_event, ETMSQ21EVR);
+	etm_writel(drvdata, config->seq_23_event, ETMSQ23EVR);
+	etm_writel(drvdata, config->seq_31_event, ETMSQ31EVR);
+	etm_writel(drvdata, config->seq_32_event, ETMSQ32EVR);
+	etm_writel(drvdata, config->seq_13_event, ETMSQ13EVR);
+	etm_writel(drvdata, config->seq_curr_state, ETMSQR);
 	for (i = 0; i < drvdata->nr_ext_out; i++)
 		etm_writel(drvdata, ETM_DEFAULT_EVENT_VAL, ETMEXTOUTEVRn(i));
 	for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
-		etm_writel(drvdata, drvdata->ctxid_pid[i], ETMCIDCVRn(i));
-	etm_writel(drvdata, drvdata->ctxid_mask, ETMCIDCMR);
-	etm_writel(drvdata, drvdata->sync_freq, ETMSYNCFR);
+		etm_writel(drvdata, config->ctxid_pid[i], ETMCIDCVRn(i));
+	etm_writel(drvdata, config->ctxid_mask, ETMCIDCMR);
+	etm_writel(drvdata, config->sync_freq, ETMSYNCFR);
 	/* No external input selected */
 	etm_writel(drvdata, 0x0, ETMEXTINSELR);
-	etm_writel(drvdata, drvdata->timestamp_event, ETMTSEVR);
+	etm_writel(drvdata, config->timestamp_event, ETMTSEVR);
 	/* No auxiliary control selected */
 	etm_writel(drvdata, 0x0, ETMAUXCR);
 	etm_writel(drvdata, drvdata->traceid, ETMTRACEIDR);
 	/* No VMID comparator value selected */
 	etm_writel(drvdata, 0x0, ETMVMIDCVR);
 
-	/* Ensures trace output is enabled from this ETM */
-	etm_writel(drvdata, drvdata->ctrl | ETMCR_ETM_EN | etmcr, ETMCR);
-
 	etm_clr_prog(drvdata);
 	CS_LOCK(drvdata->base);
 
 	dev_dbg(drvdata->dev, "cpu: %d enable smp call done\n", drvdata->cpu);
 }
 
-static int etm_trace_id(struct coresight_device *csdev)
+static int etm_cpu_id(struct coresight_device *csdev)
 {
 	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return drvdata->cpu;
+}
+
+int etm_get_trace_id(struct etm_drvdata *drvdata)
+{
 	unsigned long flags;
 	int trace_id = -1;
 
-	if (!drvdata->enable)
+	if (!drvdata)
+		goto out;
+
+	if (!local_read(&drvdata->mode))
 		return drvdata->traceid;
-	pm_runtime_get_sync(csdev->dev.parent);
+
+	pm_runtime_get_sync(drvdata->dev);
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
@@ -332,17 +442,41 @@ static int etm_trace_id(struct coresight_device *csdev)
 	CS_LOCK(drvdata->base);
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(csdev->dev.parent);
+	pm_runtime_put(drvdata->dev);
 
+out:
 	return trace_id;
+
+}
+
+static int etm_trace_id(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return etm_get_trace_id(drvdata);
 }
 
-static int etm_enable(struct coresight_device *csdev)
+static int etm_enable_perf(struct coresight_device *csdev,
+			   struct perf_event_attr *attr)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id()))
+		return -EINVAL;
+
+	/* Configure the tracer based on the session's specifics */
+	etm_parse_event_config(drvdata, attr);
+	/* And enable it */
+	etm_enable_hw(drvdata);
+
+	return 0;
+}
+
+static int etm_enable_sysfs(struct coresight_device *csdev)
 {
 	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret;
 
-	pm_runtime_get_sync(csdev->dev.parent);
 	spin_lock(&drvdata->spinlock);
 
 	/*
@@ -357,16 +491,45 @@ static int etm_enable(struct coresight_device *csdev)
 			goto err;
 	}
 
-	drvdata->enable = true;
 	drvdata->sticky_enable = true;
-
 	spin_unlock(&drvdata->spinlock);
 
 	dev_info(drvdata->dev, "ETM tracing enabled\n");
 	return 0;
+
 err:
 	spin_unlock(&drvdata->spinlock);
-	pm_runtime_put(csdev->dev.parent);
+	return ret;
+}
+
+static int etm_enable(struct coresight_device *csdev,
+		      struct perf_event_attr *attr, u32 mode)
+{
+	int ret;
+	u32 val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	val = local_cmpxchg(&drvdata->mode, CS_MODE_DISABLED, mode);
+
+	/* Someone is already using the tracer */
+	if (val)
+		return -EBUSY;
+
+	switch (mode) {
+	case CS_MODE_SYSFS:
+		ret = etm_enable_sysfs(csdev);
+		break;
+	case CS_MODE_PERF:
+		ret = etm_enable_perf(csdev, attr);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	/* The tracer didn't start */
+	if (ret)
+		local_set(&drvdata->mode, CS_MODE_DISABLED);
+
 	return ret;
 }
 
@@ -374,18 +537,16 @@ static void etm_disable_hw(void *info)
 {
 	int i;
 	struct etm_drvdata *drvdata = info;
+	struct etm_config *config = &drvdata->config;
 
 	CS_UNLOCK(drvdata->base);
 	etm_set_prog(drvdata);
 
-	/* Program trace enable to low by using always false event */
-	etm_writel(drvdata, ETM_HARD_WIRE_RES_A | ETM_EVENT_NOT_A, ETMTEEVR);
-
 	/* Read back sequencer and counters for post trace analysis */
-	drvdata->seq_curr_state = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+	config->seq_curr_state = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
 
 	for (i = 0; i < drvdata->nr_cntr; i++)
-		drvdata->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i));
+		config->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i));
 
 	etm_set_pwrdwn(drvdata);
 	CS_LOCK(drvdata->base);
@@ -393,7 +554,28 @@ static void etm_disable_hw(void *info)
 	dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu);
 }
 
-static void etm_disable(struct coresight_device *csdev)
+static void etm_disable_perf(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id()))
+		return;
+
+	CS_UNLOCK(drvdata->base);
+
+	/* Setting the prog bit disables tracing immediately */
+	etm_set_prog(drvdata);
+
+	/*
+	 * There is no way to know when the tracer will be used again so
+	 * power down the tracer.
+	 */
+	etm_set_pwrdwn(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void etm_disable_sysfs(struct coresight_device *csdev)
 {
 	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
@@ -411,1235 +593,52 @@ static void etm_disable(struct coresight_device *csdev)
 	 * ensures that register writes occur when cpu is powered.
 	 */
 	smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1);
-	drvdata->enable = false;
 
 	spin_unlock(&drvdata->spinlock);
 	put_online_cpus();
-	pm_runtime_put(csdev->dev.parent);
 
 	dev_info(drvdata->dev, "ETM tracing disabled\n");
 }
 
-static const struct coresight_ops_source etm_source_ops = {
-	.trace_id	= etm_trace_id,
-	.enable		= etm_enable,
-	.disable	= etm_disable,
-};
-
-static const struct coresight_ops etm_cs_ops = {
-	.source_ops	= &etm_source_ops,
-};
-
-static ssize_t nr_addr_cmp_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->nr_addr_cmp;
-	return sprintf(buf, "%#lx\n", val);
-}
-static DEVICE_ATTR_RO(nr_addr_cmp);
-
-static ssize_t nr_cntr_show(struct device *dev,
-			    struct device_attribute *attr, char *buf)
-{	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->nr_cntr;
-	return sprintf(buf, "%#lx\n", val);
-}
-static DEVICE_ATTR_RO(nr_cntr);
-
-static ssize_t nr_ctxid_cmp_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->nr_ctxid_cmp;
-	return sprintf(buf, "%#lx\n", val);
-}
-static DEVICE_ATTR_RO(nr_ctxid_cmp);
-
-static ssize_t etmsr_show(struct device *dev,
-			  struct device_attribute *attr, char *buf)
-{
-	unsigned long flags, val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	pm_runtime_get_sync(drvdata->dev);
-	spin_lock_irqsave(&drvdata->spinlock, flags);
-	CS_UNLOCK(drvdata->base);
-
-	val = etm_readl(drvdata, ETMSR);
-
-	CS_LOCK(drvdata->base);
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(drvdata->dev);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-static DEVICE_ATTR_RO(etmsr);
-
-static ssize_t reset_store(struct device *dev,
-			   struct device_attribute *attr,
-			   const char *buf, size_t size)
-{
-	int i, ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	if (val) {
-		spin_lock(&drvdata->spinlock);
-		drvdata->mode = ETM_MODE_EXCLUDE;
-		drvdata->ctrl = 0x0;
-		drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
-		drvdata->startstop_ctrl = 0x0;
-		drvdata->addr_idx = 0x0;
-		for (i = 0; i < drvdata->nr_addr_cmp; i++) {
-			drvdata->addr_val[i] = 0x0;
-			drvdata->addr_acctype[i] = 0x0;
-			drvdata->addr_type[i] = ETM_ADDR_TYPE_NONE;
-		}
-		drvdata->cntr_idx = 0x0;
-
-		etm_set_default(drvdata);
-		spin_unlock(&drvdata->spinlock);
-	}
-
-	return size;
-}
-static DEVICE_ATTR_WO(reset);
-
-static ssize_t mode_show(struct device *dev,
-			 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->mode;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t mode_store(struct device *dev,
-			  struct device_attribute *attr,
-			  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	drvdata->mode = val & ETM_MODE_ALL;
-
-	if (drvdata->mode & ETM_MODE_EXCLUDE)
-		drvdata->enable_ctrl1 |= ETMTECR1_INC_EXC;
-	else
-		drvdata->enable_ctrl1 &= ~ETMTECR1_INC_EXC;
-
-	if (drvdata->mode & ETM_MODE_CYCACC)
-		drvdata->ctrl |= ETMCR_CYC_ACC;
-	else
-		drvdata->ctrl &= ~ETMCR_CYC_ACC;
-
-	if (drvdata->mode & ETM_MODE_STALL) {
-		if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
-			dev_warn(drvdata->dev, "stall mode not supported\n");
-			ret = -EINVAL;
-			goto err_unlock;
-		}
-		drvdata->ctrl |= ETMCR_STALL_MODE;
-	 } else
-		drvdata->ctrl &= ~ETMCR_STALL_MODE;
-
-	if (drvdata->mode & ETM_MODE_TIMESTAMP) {
-		if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
-			dev_warn(drvdata->dev, "timestamp not supported\n");
-			ret = -EINVAL;
-			goto err_unlock;
-		}
-		drvdata->ctrl |= ETMCR_TIMESTAMP_EN;
-	} else
-		drvdata->ctrl &= ~ETMCR_TIMESTAMP_EN;
-
-	if (drvdata->mode & ETM_MODE_CTXID)
-		drvdata->ctrl |= ETMCR_CTXID_SIZE;
-	else
-		drvdata->ctrl &= ~ETMCR_CTXID_SIZE;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-
-err_unlock:
-	spin_unlock(&drvdata->spinlock);
-	return ret;
-}
-static DEVICE_ATTR_RW(mode);
-
-static ssize_t trigger_event_show(struct device *dev,
-				  struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->trigger_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t trigger_event_store(struct device *dev,
-				   struct device_attribute *attr,
-				   const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->trigger_event = val & ETM_EVENT_MASK;
-
-	return size;
-}
-static DEVICE_ATTR_RW(trigger_event);
-
-static ssize_t enable_event_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->enable_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t enable_event_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->enable_event = val & ETM_EVENT_MASK;
-
-	return size;
-}
-static DEVICE_ATTR_RW(enable_event);
-
-static ssize_t fifofull_level_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->fifofull_level;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t fifofull_level_store(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->fifofull_level = val;
-
-	return size;
-}
-static DEVICE_ATTR_RW(fifofull_level);
-
-static ssize_t addr_idx_show(struct device *dev,
-			     struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->addr_idx;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t addr_idx_store(struct device *dev,
-			      struct device_attribute *attr,
-			      const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	if (val >= drvdata->nr_addr_cmp)
-		return -EINVAL;
-
-	/*
-	 * Use spinlock to ensure index doesn't change while it gets
-	 * dereferenced multiple times within a spinlock block elsewhere.
-	 */
-	spin_lock(&drvdata->spinlock);
-	drvdata->addr_idx = val;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(addr_idx);
-
-static ssize_t addr_single_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	u8 idx;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
-	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
-		spin_unlock(&drvdata->spinlock);
-		return -EINVAL;
-	}
-
-	val = drvdata->addr_val[idx];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t addr_single_store(struct device *dev,
-				 struct device_attribute *attr,
-				 const char *buf, size_t size)
-{
-	u8 idx;
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
-	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
-		spin_unlock(&drvdata->spinlock);
-		return -EINVAL;
-	}
-
-	drvdata->addr_val[idx] = val;
-	drvdata->addr_type[idx] = ETM_ADDR_TYPE_SINGLE;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(addr_single);
-
-static ssize_t addr_range_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
-{
-	u8 idx;
-	unsigned long val1, val2;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (idx % 2 != 0) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
-	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
-	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
-	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-
-	val1 = drvdata->addr_val[idx];
-	val2 = drvdata->addr_val[idx + 1];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx %#lx\n", val1, val2);
-}
-
-static ssize_t addr_range_store(struct device *dev,
-			      struct device_attribute *attr,
-			      const char *buf, size_t size)
-{
-	u8 idx;
-	unsigned long val1, val2;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
-		return -EINVAL;
-	/* Lower address comparator cannot have a higher address value */
-	if (val1 > val2)
-		return -EINVAL;
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (idx % 2 != 0) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
-	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
-	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
-	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-
-	drvdata->addr_val[idx] = val1;
-	drvdata->addr_type[idx] = ETM_ADDR_TYPE_RANGE;
-	drvdata->addr_val[idx + 1] = val2;
-	drvdata->addr_type[idx + 1] = ETM_ADDR_TYPE_RANGE;
-	drvdata->enable_ctrl1 |= (1 << (idx/2));
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(addr_range);
-
-static ssize_t addr_start_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
-{
-	u8 idx;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
-	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-
-	val = drvdata->addr_val[idx];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t addr_start_store(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t size)
-{
-	u8 idx;
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
-	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-
-	drvdata->addr_val[idx] = val;
-	drvdata->addr_type[idx] = ETM_ADDR_TYPE_START;
-	drvdata->startstop_ctrl |= (1 << idx);
-	drvdata->enable_ctrl1 |= BIT(25);
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(addr_start);
-
-static ssize_t addr_stop_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	u8 idx;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
-	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-
-	val = drvdata->addr_val[idx];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t addr_stop_store(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t size)
-{
-	u8 idx;
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	idx = drvdata->addr_idx;
-	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
-	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
-		spin_unlock(&drvdata->spinlock);
-		return -EPERM;
-	}
-
-	drvdata->addr_val[idx] = val;
-	drvdata->addr_type[idx] = ETM_ADDR_TYPE_STOP;
-	drvdata->startstop_ctrl |= (1 << (idx + 16));
-	drvdata->enable_ctrl1 |= ETMTECR1_START_STOP;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(addr_stop);
-
-static ssize_t addr_acctype_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	val = drvdata->addr_acctype[drvdata->addr_idx];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t addr_acctype_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	drvdata->addr_acctype[drvdata->addr_idx] = val;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(addr_acctype);
-
-static ssize_t cntr_idx_show(struct device *dev,
-			     struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->cntr_idx;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t cntr_idx_store(struct device *dev,
-			      struct device_attribute *attr,
-			      const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	if (val >= drvdata->nr_cntr)
-		return -EINVAL;
-	/*
-	 * Use spinlock to ensure index doesn't change while it gets
-	 * dereferenced multiple times within a spinlock block elsewhere.
-	 */
-	spin_lock(&drvdata->spinlock);
-	drvdata->cntr_idx = val;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(cntr_idx);
-
-static ssize_t cntr_rld_val_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	val = drvdata->cntr_rld_val[drvdata->cntr_idx];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t cntr_rld_val_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	drvdata->cntr_rld_val[drvdata->cntr_idx] = val;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(cntr_rld_val);
-
-static ssize_t cntr_event_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	val = drvdata->cntr_event[drvdata->cntr_idx];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t cntr_event_store(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	drvdata->cntr_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(cntr_event);
-
-static ssize_t cntr_rld_event_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	val = drvdata->cntr_rld_event[drvdata->cntr_idx];
-	spin_unlock(&drvdata->spinlock);
-
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t cntr_rld_event_store(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	drvdata->cntr_rld_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(cntr_rld_event);
-
-static ssize_t cntr_val_show(struct device *dev,
-			     struct device_attribute *attr, char *buf)
-{
-	int i, ret = 0;
-	u32 val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	if (!drvdata->enable) {
-		spin_lock(&drvdata->spinlock);
-		for (i = 0; i < drvdata->nr_cntr; i++)
-			ret += sprintf(buf, "counter %d: %x\n",
-				       i, drvdata->cntr_val[i]);
-		spin_unlock(&drvdata->spinlock);
-		return ret;
-	}
-
-	for (i = 0; i < drvdata->nr_cntr; i++) {
-		val = etm_readl(drvdata, ETMCNTVRn(i));
-		ret += sprintf(buf, "counter %d: %x\n", i, val);
-	}
-
-	return ret;
-}
-
-static ssize_t cntr_val_store(struct device *dev,
-			      struct device_attribute *attr,
-			      const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&drvdata->spinlock);
-	drvdata->cntr_val[drvdata->cntr_idx] = val;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(cntr_val);
-
-static ssize_t seq_12_event_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->seq_12_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t seq_12_event_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->seq_12_event = val & ETM_EVENT_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(seq_12_event);
-
-static ssize_t seq_21_event_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->seq_21_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t seq_21_event_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->seq_21_event = val & ETM_EVENT_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(seq_21_event);
-
-static ssize_t seq_23_event_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->seq_23_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t seq_23_event_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->seq_23_event = val & ETM_EVENT_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(seq_23_event);
-
-static ssize_t seq_31_event_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->seq_31_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t seq_31_event_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->seq_31_event = val & ETM_EVENT_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(seq_31_event);
-
-static ssize_t seq_32_event_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->seq_32_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t seq_32_event_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->seq_32_event = val & ETM_EVENT_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(seq_32_event);
-
-static ssize_t seq_13_event_show(struct device *dev,
-				 struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->seq_13_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t seq_13_event_store(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->seq_13_event = val & ETM_EVENT_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(seq_13_event);
-
-static ssize_t seq_curr_state_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	unsigned long val, flags;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	if (!drvdata->enable) {
-		val = drvdata->seq_curr_state;
-		goto out;
-	}
-
-	pm_runtime_get_sync(drvdata->dev);
-	spin_lock_irqsave(&drvdata->spinlock, flags);
-
-	CS_UNLOCK(drvdata->base);
-	val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
-	CS_LOCK(drvdata->base);
-
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(drvdata->dev);
-out:
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t seq_curr_state_store(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	if (val > ETM_SEQ_STATE_MAX_VAL)
-		return -EINVAL;
-
-	drvdata->seq_curr_state = val;
-
-	return size;
-}
-static DEVICE_ATTR_RW(seq_curr_state);
-
-static ssize_t ctxid_idx_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->ctxid_idx;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t ctxid_idx_store(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t size)
+static void etm_disable(struct coresight_device *csdev)
 {
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	if (val >= drvdata->nr_ctxid_cmp)
-		return -EINVAL;
+	u32 mode;
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	/*
-	 * Use spinlock to ensure index doesn't change while it gets
-	 * dereferenced multiple times within a spinlock block elsewhere.
+	 * For as long as the tracer isn't disabled another entity can't
+	 * change its status.  As such we can read the status here without
+	 * fearing it will change under us.
 	 */
-	spin_lock(&drvdata->spinlock);
-	drvdata->ctxid_idx = val;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(ctxid_idx);
-
-static ssize_t ctxid_pid_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	spin_lock(&drvdata->spinlock);
-	val = drvdata->ctxid_vpid[drvdata->ctxid_idx];
-	spin_unlock(&drvdata->spinlock);
+	mode = local_read(&drvdata->mode);
 
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t ctxid_pid_store(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t size)
-{
-	int ret;
-	unsigned long vpid, pid;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &vpid);
-	if (ret)
-		return ret;
-
-	pid = coresight_vpid_to_pid(vpid);
-
-	spin_lock(&drvdata->spinlock);
-	drvdata->ctxid_pid[drvdata->ctxid_idx] = pid;
-	drvdata->ctxid_vpid[drvdata->ctxid_idx] = vpid;
-	spin_unlock(&drvdata->spinlock);
-
-	return size;
-}
-static DEVICE_ATTR_RW(ctxid_pid);
-
-static ssize_t ctxid_mask_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->ctxid_mask;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t ctxid_mask_store(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->ctxid_mask = val;
-	return size;
-}
-static DEVICE_ATTR_RW(ctxid_mask);
-
-static ssize_t sync_freq_show(struct device *dev,
-			      struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->sync_freq;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t sync_freq_store(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->sync_freq = val & ETM_SYNC_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(sync_freq);
-
-static ssize_t timestamp_event_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->timestamp_event;
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t timestamp_event_store(struct device *dev,
-				     struct device_attribute *attr,
-				     const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->timestamp_event = val & ETM_EVENT_MASK;
-	return size;
-}
-static DEVICE_ATTR_RW(timestamp_event);
-
-static ssize_t cpu_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	int val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	val = drvdata->cpu;
-	return scnprintf(buf, PAGE_SIZE, "%d\n", val);
-
-}
-static DEVICE_ATTR_RO(cpu);
-
-static ssize_t traceid_show(struct device *dev,
-			    struct device_attribute *attr, char *buf)
-{
-	unsigned long val, flags;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	if (!drvdata->enable) {
-		val = drvdata->traceid;
-		goto out;
+	switch (mode) {
+	case CS_MODE_DISABLED:
+		break;
+	case CS_MODE_SYSFS:
+		etm_disable_sysfs(csdev);
+		break;
+	case CS_MODE_PERF:
+		etm_disable_perf(csdev);
+		break;
+	default:
+		WARN_ON_ONCE(mode);
+		return;
 	}
 
-	pm_runtime_get_sync(drvdata->dev);
-	spin_lock_irqsave(&drvdata->spinlock, flags);
-	CS_UNLOCK(drvdata->base);
-
-	val = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
-
-	CS_LOCK(drvdata->base);
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(drvdata->dev);
-out:
-	return sprintf(buf, "%#lx\n", val);
-}
-
-static ssize_t traceid_store(struct device *dev,
-			     struct device_attribute *attr,
-			     const char *buf, size_t size)
-{
-	int ret;
-	unsigned long val;
-	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret)
-		return ret;
-
-	drvdata->traceid = val & ETM_TRACEID_MASK;
-	return size;
+	if (mode)
+		local_set(&drvdata->mode, CS_MODE_DISABLED);
 }
-static DEVICE_ATTR_RW(traceid);
-
-static struct attribute *coresight_etm_attrs[] = {
-	&dev_attr_nr_addr_cmp.attr,
-	&dev_attr_nr_cntr.attr,
-	&dev_attr_nr_ctxid_cmp.attr,
-	&dev_attr_etmsr.attr,
-	&dev_attr_reset.attr,
-	&dev_attr_mode.attr,
-	&dev_attr_trigger_event.attr,
-	&dev_attr_enable_event.attr,
-	&dev_attr_fifofull_level.attr,
-	&dev_attr_addr_idx.attr,
-	&dev_attr_addr_single.attr,
-	&dev_attr_addr_range.attr,
-	&dev_attr_addr_start.attr,
-	&dev_attr_addr_stop.attr,
-	&dev_attr_addr_acctype.attr,
-	&dev_attr_cntr_idx.attr,
-	&dev_attr_cntr_rld_val.attr,
-	&dev_attr_cntr_event.attr,
-	&dev_attr_cntr_rld_event.attr,
-	&dev_attr_cntr_val.attr,
-	&dev_attr_seq_12_event.attr,
-	&dev_attr_seq_21_event.attr,
-	&dev_attr_seq_23_event.attr,
-	&dev_attr_seq_31_event.attr,
-	&dev_attr_seq_32_event.attr,
-	&dev_attr_seq_13_event.attr,
-	&dev_attr_seq_curr_state.attr,
-	&dev_attr_ctxid_idx.attr,
-	&dev_attr_ctxid_pid.attr,
-	&dev_attr_ctxid_mask.attr,
-	&dev_attr_sync_freq.attr,
-	&dev_attr_timestamp_event.attr,
-	&dev_attr_traceid.attr,
-	&dev_attr_cpu.attr,
-	NULL,
-};
-
-#define coresight_simple_func(name, offset)                             \
-static ssize_t name##_show(struct device *_dev,                         \
-			   struct device_attribute *attr, char *buf)    \
-{                                                                       \
-	struct etm_drvdata *drvdata = dev_get_drvdata(_dev->parent);    \
-	return scnprintf(buf, PAGE_SIZE, "0x%x\n",                      \
-			 readl_relaxed(drvdata->base + offset));        \
-}                                                                       \
-DEVICE_ATTR_RO(name)
-
-coresight_simple_func(etmccr, ETMCCR);
-coresight_simple_func(etmccer, ETMCCER);
-coresight_simple_func(etmscr, ETMSCR);
-coresight_simple_func(etmidr, ETMIDR);
-coresight_simple_func(etmcr, ETMCR);
-coresight_simple_func(etmtraceidr, ETMTRACEIDR);
-coresight_simple_func(etmteevr, ETMTEEVR);
-coresight_simple_func(etmtssvr, ETMTSSCR);
-coresight_simple_func(etmtecr1, ETMTECR1);
-coresight_simple_func(etmtecr2, ETMTECR2);
-
-static struct attribute *coresight_etm_mgmt_attrs[] = {
-	&dev_attr_etmccr.attr,
-	&dev_attr_etmccer.attr,
-	&dev_attr_etmscr.attr,
-	&dev_attr_etmidr.attr,
-	&dev_attr_etmcr.attr,
-	&dev_attr_etmtraceidr.attr,
-	&dev_attr_etmteevr.attr,
-	&dev_attr_etmtssvr.attr,
-	&dev_attr_etmtecr1.attr,
-	&dev_attr_etmtecr2.attr,
-	NULL,
-};
 
-static const struct attribute_group coresight_etm_group = {
-	.attrs = coresight_etm_attrs,
-};
-
-
-static const struct attribute_group coresight_etm_mgmt_group = {
-	.attrs = coresight_etm_mgmt_attrs,
-	.name = "mgmt",
+static const struct coresight_ops_source etm_source_ops = {
+	.cpu_id		= etm_cpu_id,
+	.trace_id	= etm_trace_id,
+	.enable		= etm_enable,
+	.disable	= etm_disable,
 };
 
-static const struct attribute_group *coresight_etm_groups[] = {
-	&coresight_etm_group,
-	&coresight_etm_mgmt_group,
-	NULL,
+static const struct coresight_ops etm_cs_ops = {
+	.source_ops	= &etm_source_ops,
 };
 
 static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action,
@@ -1658,7 +657,7 @@ static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action,
 			etmdrvdata[cpu]->os_unlock = true;
 		}
 
-		if (etmdrvdata[cpu]->enable)
+		if (local_read(&etmdrvdata[cpu]->mode))
 			etm_enable_hw(etmdrvdata[cpu]);
 		spin_unlock(&etmdrvdata[cpu]->spinlock);
 		break;
@@ -1671,7 +670,7 @@ static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action,
 
 	case CPU_DYING:
 		spin_lock(&etmdrvdata[cpu]->spinlock);
-		if (etmdrvdata[cpu]->enable)
+		if (local_read(&etmdrvdata[cpu]->mode))
 			etm_disable_hw(etmdrvdata[cpu]);
 		spin_unlock(&etmdrvdata[cpu]->spinlock);
 		break;
@@ -1707,6 +706,9 @@ static void etm_init_arch_data(void *info)
 	u32 etmccr;
 	struct etm_drvdata *drvdata = info;
 
+	/* Make sure all registers are accessible */
+	etm_os_unlock(drvdata);
+
 	CS_UNLOCK(drvdata->base);
 
 	/* First dummy read */
@@ -1743,40 +745,9 @@ static void etm_init_arch_data(void *info)
 	CS_LOCK(drvdata->base);
 }
 
-static void etm_init_default_data(struct etm_drvdata *drvdata)
+static void etm_init_trace_id(struct etm_drvdata *drvdata)
 {
-	/*
-	 * A trace ID of value 0 is invalid, so let's start at some
-	 * random value that fits in 7 bits and will be just as good.
-	 */
-	static int etm3x_traceid = 0x10;
-
-	u32 flags = (1 << 0 | /* instruction execute*/
-		     3 << 3 | /* ARM instruction */
-		     0 << 5 | /* No data value comparison */
-		     0 << 7 | /* No exact mach */
-		     0 << 8 | /* Ignore context ID */
-		     0 << 10); /* Security ignored */
-
-	/*
-	 * Initial configuration only - guarantees sources handled by
-	 * this driver have a unique ID at startup time but not between
-	 * all other types of sources.  For that we lean on the core
-	 * framework.
-	 */
-	drvdata->traceid = etm3x_traceid++;
-	drvdata->ctrl = (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN);
-	drvdata->enable_ctrl1 = ETMTECR1_ADDR_COMP_1;
-	if (drvdata->nr_addr_cmp >= 2) {
-		drvdata->addr_val[0] = (u32) _stext;
-		drvdata->addr_val[1] = (u32) _etext;
-		drvdata->addr_acctype[0] = flags;
-		drvdata->addr_acctype[1] = flags;
-		drvdata->addr_type[0] = ETM_ADDR_TYPE_RANGE;
-		drvdata->addr_type[1] = ETM_ADDR_TYPE_RANGE;
-	}
-
-	etm_set_default(drvdata);
+	drvdata->traceid = coresight_get_trace_id(drvdata->cpu);
 }
 
 static int etm_probe(struct amba_device *adev, const struct amba_id *id)
@@ -1831,9 +802,6 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 	get_online_cpus();
 	etmdrvdata[drvdata->cpu] = drvdata;
 
-	if (!smp_call_function_single(drvdata->cpu, etm_os_unlock, drvdata, 1))
-		drvdata->os_unlock = true;
-
 	if (smp_call_function_single(drvdata->cpu,
 				     etm_init_arch_data,  drvdata, 1))
 		dev_err(dev, "ETM arch init failed\n");
@@ -1847,7 +815,9 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 		ret = -EINVAL;
 		goto err_arch_supported;
 	}
-	etm_init_default_data(drvdata);
+
+	etm_init_trace_id(drvdata);
+	etm_set_default(&drvdata->config);
 
 	desc->type = CORESIGHT_DEV_TYPE_SOURCE;
 	desc->subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC;
@@ -1861,6 +831,12 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 		goto err_arch_supported;
 	}
 
+	ret = etm_perf_symlink(drvdata->csdev, true);
+	if (ret) {
+		coresight_unregister(drvdata->csdev);
+		goto err_arch_supported;
+	}
+
 	pm_runtime_put(&adev->dev);
 	dev_info(dev, "%s initialized\n", (char *)id->data);
 
@@ -1877,17 +853,6 @@ err_arch_supported:
 	return ret;
 }
 
-static int etm_remove(struct amba_device *adev)
-{
-	struct etm_drvdata *drvdata = amba_get_drvdata(adev);
-
-	coresight_unregister(drvdata->csdev);
-	if (--etm_count == 0)
-		unregister_hotcpu_notifier(&etm_cpu_notifier);
-
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int etm_runtime_suspend(struct device *dev)
 {
@@ -1948,13 +913,9 @@ static struct amba_driver etm_driver = {
 		.name	= "coresight-etm3x",
 		.owner	= THIS_MODULE,
 		.pm	= &etm_dev_pm_ops,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= etm_probe,
-	.remove		= etm_remove,
 	.id_table	= etm_ids,
 };
-
-module_amba_driver(etm_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("CoreSight Program Flow Trace driver");
+builtin_amba_driver(etm_driver);
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index a6707642b..1c59bd368 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -15,7 +15,6 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
-#include <linux/module.h>
 #include <linux/io.h>
 #include <linux/err.h>
 #include <linux/fs.h>
@@ -32,6 +31,7 @@
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
+#include <linux/perf_event.h>
 #include <asm/sections.h>
 
 #include "coresight-etm4x.h"
@@ -63,6 +63,13 @@ static bool etm4_arch_supported(u8 arch)
 	return true;
 }
 
+static int etm4_cpu_id(struct coresight_device *csdev)
+{
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return drvdata->cpu;
+}
+
 static int etm4_trace_id(struct coresight_device *csdev)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
@@ -72,7 +79,6 @@ static int etm4_trace_id(struct coresight_device *csdev)
 	if (!drvdata->enable)
 		return drvdata->trcid;
 
-	pm_runtime_get_sync(drvdata->dev);
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
 	CS_UNLOCK(drvdata->base);
@@ -81,7 +87,6 @@ static int etm4_trace_id(struct coresight_device *csdev)
 	CS_LOCK(drvdata->base);
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(drvdata->dev);
 
 	return trace_id;
 }
@@ -182,12 +187,12 @@ static void etm4_enable_hw(void *info)
 	dev_dbg(drvdata->dev, "cpu: %d enable smp call done\n", drvdata->cpu);
 }
 
-static int etm4_enable(struct coresight_device *csdev)
+static int etm4_enable(struct coresight_device *csdev,
+		       struct perf_event_attr *attr, u32 mode)
 {
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 	int ret;
 
-	pm_runtime_get_sync(drvdata->dev);
 	spin_lock(&drvdata->spinlock);
 
 	/*
@@ -207,7 +212,6 @@ static int etm4_enable(struct coresight_device *csdev)
 	return 0;
 err:
 	spin_unlock(&drvdata->spinlock);
-	pm_runtime_put(drvdata->dev);
 	return ret;
 }
 
@@ -256,12 +260,11 @@ static void etm4_disable(struct coresight_device *csdev)
 	spin_unlock(&drvdata->spinlock);
 	put_online_cpus();
 
-	pm_runtime_put(drvdata->dev);
-
 	dev_info(drvdata->dev, "ETM tracing disabled\n");
 }
 
 static const struct coresight_ops_source etm4_source_ops = {
+	.cpu_id		= etm4_cpu_id,
 	.trace_id	= etm4_trace_id,
 	.enable		= etm4_enable,
 	.disable	= etm4_disable,
@@ -2219,7 +2222,7 @@ static ssize_t name##_show(struct device *_dev,				\
 	return scnprintf(buf, PAGE_SIZE, "0x%x\n",			\
 			 readl_relaxed(drvdata->base + offset));	\
 }									\
-DEVICE_ATTR_RO(name)
+static DEVICE_ATTR_RO(name)
 
 coresight_simple_func(trcoslsr, TRCOSLSR);
 coresight_simple_func(trcpdcr, TRCPDCR);
@@ -2684,17 +2687,6 @@ err_coresight_register:
 	return ret;
 }
 
-static int etm4_remove(struct amba_device *adev)
-{
-	struct etmv4_drvdata *drvdata = amba_get_drvdata(adev);
-
-	coresight_unregister(drvdata->csdev);
-	if (--etm4_count == 0)
-		unregister_hotcpu_notifier(&etm4_cpu_notifier);
-
-	return 0;
-}
-
 static struct amba_id etm4_ids[] = {
 	{       /* ETM 4.0 - Qualcomm */
 		.id	= 0x0003b95d,
@@ -2712,10 +2704,9 @@ static struct amba_id etm4_ids[] = {
 static struct amba_driver etm4x_driver = {
 	.drv = {
 		.name   = "coresight-etm4x",
+		.suppress_bind_attrs = true,
 	},
 	.probe		= etm4_probe,
-	.remove		= etm4_remove,
 	.id_table	= etm4_ids,
 };
-
-module_amba_driver(etm4x_driver);
+builtin_amba_driver(etm4x_driver);
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 2e36bde7f..0600ca306 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -1,5 +1,7 @@
 /* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
+ * Description: CoreSight Funnel driver
+ *
  * 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.
@@ -11,7 +13,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
@@ -69,7 +70,6 @@ static int funnel_enable(struct coresight_device *csdev, int inport,
 {
 	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	pm_runtime_get_sync(drvdata->dev);
 	funnel_enable_hw(drvdata, inport);
 
 	dev_info(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
@@ -95,7 +95,6 @@ static void funnel_disable(struct coresight_device *csdev, int inport,
 	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	funnel_disable_hw(drvdata, inport);
-	pm_runtime_put(drvdata->dev);
 
 	dev_info(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
 }
@@ -226,14 +225,6 @@ static int funnel_probe(struct amba_device *adev, const struct amba_id *id)
 	return 0;
 }
 
-static int funnel_remove(struct amba_device *adev)
-{
-	struct funnel_drvdata *drvdata = amba_get_drvdata(adev);
-
-	coresight_unregister(drvdata->csdev);
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int funnel_runtime_suspend(struct device *dev)
 {
@@ -273,13 +264,9 @@ static struct amba_driver funnel_driver = {
 		.name	= "coresight-funnel",
 		.owner	= THIS_MODULE,
 		.pm	= &funnel_dev_pm_ops,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= funnel_probe,
-	.remove		= funnel_remove,
 	.id_table	= funnel_ids,
 };
-
-module_amba_driver(funnel_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("CoreSight Funnel driver");
+builtin_amba_driver(funnel_driver);
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 62fcd98cc..333eddaed 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -34,6 +34,15 @@
 #define TIMEOUT_US		100
 #define BMVAL(val, lsb, msb)	((val & GENMASK(msb, lsb)) >> lsb)
 
+#define ETM_MODE_EXCL_KERN	BIT(30)
+#define ETM_MODE_EXCL_USER	BIT(31)
+
+enum cs_mode {
+	CS_MODE_DISABLED,
+	CS_MODE_SYSFS,
+	CS_MODE_PERF,
+};
+
 static inline void CS_LOCK(void __iomem *addr)
 {
 	do {
@@ -52,6 +61,12 @@ static inline void CS_UNLOCK(void __iomem *addr)
 	} while (0);
 }
 
+void coresight_disable_path(struct list_head *path);
+int coresight_enable_path(struct list_head *path, u32 mode);
+struct coresight_device *coresight_get_sink(struct list_head *path);
+struct list_head *coresight_build_path(struct coresight_device *csdev);
+void coresight_release_path(struct list_head *path);
+
 #ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
 extern int etm_readl_cp14(u32 off, unsigned int *val);
 extern int etm_writel_cp14(u32 off, u32 val);
diff --git a/drivers/hwtracing/coresight/coresight-replicator-qcom.c b/drivers/hwtracing/coresight/coresight-replicator-qcom.c
index 584059e9e..700f710e4 100644
--- a/drivers/hwtracing/coresight/coresight-replicator-qcom.c
+++ b/drivers/hwtracing/coresight/coresight-replicator-qcom.c
@@ -15,7 +15,6 @@
 #include <linux/clk.h>
 #include <linux/coresight.h>
 #include <linux/device.h>
-#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -48,8 +47,6 @@ static int replicator_enable(struct coresight_device *csdev, int inport,
 {
 	struct replicator_state *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	pm_runtime_get_sync(drvdata->dev);
-
 	CS_UNLOCK(drvdata->base);
 
 	/*
@@ -86,8 +83,6 @@ static void replicator_disable(struct coresight_device *csdev, int inport,
 
 	CS_LOCK(drvdata->base);
 
-	pm_runtime_put(drvdata->dev);
-
 	dev_info(drvdata->dev, "REPLICATOR disabled\n");
 }
 
@@ -156,15 +151,6 @@ static int replicator_probe(struct amba_device *adev, const struct amba_id *id)
 	return 0;
 }
 
-static int replicator_remove(struct amba_device *adev)
-{
-	struct replicator_state *drvdata = amba_get_drvdata(adev);
-
-	pm_runtime_disable(&adev->dev);
-	coresight_unregister(drvdata->csdev);
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int replicator_runtime_suspend(struct device *dev)
 {
@@ -206,10 +192,9 @@ static struct amba_driver replicator_driver = {
 	.drv = {
 		.name	= "coresight-replicator-qcom",
 		.pm	= &replicator_dev_pm_ops,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= replicator_probe,
-	.remove		= replicator_remove,
 	.id_table	= replicator_ids,
 };
-
-module_amba_driver(replicator_driver);
+builtin_amba_driver(replicator_driver);
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index 963ac197c..4299c0569 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -1,5 +1,7 @@
 /* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
+ * Description: CoreSight Replicator driver
+ *
  * 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.
@@ -11,7 +13,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
@@ -41,7 +42,6 @@ static int replicator_enable(struct coresight_device *csdev, int inport,
 {
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	pm_runtime_get_sync(drvdata->dev);
 	dev_info(drvdata->dev, "REPLICATOR enabled\n");
 	return 0;
 }
@@ -51,7 +51,6 @@ static void replicator_disable(struct coresight_device *csdev, int inport,
 {
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	pm_runtime_put(drvdata->dev);
 	dev_info(drvdata->dev, "REPLICATOR disabled\n");
 }
 
@@ -127,20 +126,6 @@ out_disable_pm:
 	return ret;
 }
 
-static int replicator_remove(struct platform_device *pdev)
-{
-	struct replicator_drvdata *drvdata = platform_get_drvdata(pdev);
-
-	coresight_unregister(drvdata->csdev);
-	pm_runtime_get_sync(&pdev->dev);
-	if (!IS_ERR(drvdata->atclk))
-		clk_disable_unprepare(drvdata->atclk);
-	pm_runtime_put_noidle(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
-
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int replicator_runtime_suspend(struct device *dev)
 {
@@ -175,15 +160,11 @@ static const struct of_device_id replicator_match[] = {
 
 static struct platform_driver replicator_driver = {
 	.probe          = replicator_probe,
-	.remove         = replicator_remove,
 	.driver         = {
 		.name   = "coresight-replicator",
 		.of_match_table = replicator_match,
 		.pm	= &replicator_dev_pm_ops,
+		.suppress_bind_attrs = true,
 	},
 };
-
 builtin_platform_driver(replicator_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("CoreSight Replicator driver");
diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c
index a57c7ec16..1be191f5d 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.c
+++ b/drivers/hwtracing/coresight/coresight-tmc.c
@@ -1,5 +1,7 @@
 /* Copyright (c) 2012, The Linux Foundation. All rights reserved.
  *
+ * Description: CoreSight Trace Memory Controller driver
+ *
  * 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.
@@ -11,7 +13,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
@@ -124,7 +125,7 @@ struct tmc_drvdata {
 	bool			reading;
 	char			*buf;
 	dma_addr_t		paddr;
-	void __iomem		*vaddr;
+	void			*vaddr;
 	u32			size;
 	bool			enable;
 	enum tmc_config_type	config_type;
@@ -242,12 +243,9 @@ static int tmc_enable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
 {
 	unsigned long flags;
 
-	pm_runtime_get_sync(drvdata->dev);
-
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 	if (drvdata->reading) {
 		spin_unlock_irqrestore(&drvdata->spinlock, flags);
-		pm_runtime_put(drvdata->dev);
 		return -EBUSY;
 	}
 
@@ -268,7 +266,7 @@ static int tmc_enable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
 	return 0;
 }
 
-static int tmc_enable_sink(struct coresight_device *csdev)
+static int tmc_enable_sink(struct coresight_device *csdev, u32 mode)
 {
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
@@ -381,8 +379,6 @@ out:
 	drvdata->enable = false;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	pm_runtime_put(drvdata->dev);
-
 	dev_info(drvdata->dev, "TMC disabled\n");
 }
 
@@ -766,23 +762,10 @@ err_misc_register:
 err_devm_kzalloc:
 	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
 		dma_free_coherent(dev, drvdata->size,
-				&drvdata->paddr, GFP_KERNEL);
+				drvdata->vaddr, drvdata->paddr);
 	return ret;
 }
 
-static int tmc_remove(struct amba_device *adev)
-{
-	struct tmc_drvdata *drvdata = amba_get_drvdata(adev);
-
-	misc_deregister(&drvdata->miscdev);
-	coresight_unregister(drvdata->csdev);
-	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
-		dma_free_coherent(drvdata->dev, drvdata->size,
-				  &drvdata->paddr, GFP_KERNEL);
-
-	return 0;
-}
-
 static struct amba_id tmc_ids[] = {
 	{
 		.id     = 0x0003b961,
@@ -795,13 +778,9 @@ static struct amba_driver tmc_driver = {
 	.drv = {
 		.name   = "coresight-tmc",
 		.owner  = THIS_MODULE,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= tmc_probe,
-	.remove		= tmc_remove,
 	.id_table	= tmc_ids,
 };
-
-module_amba_driver(tmc_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("CoreSight Trace Memory Controller driver");
+builtin_amba_driver(tmc_driver);
diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
index 7214efd10..8fb09d923 100644
--- a/drivers/hwtracing/coresight/coresight-tpiu.c
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -1,5 +1,7 @@
 /* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
  *
+ * Description: CoreSight Trace Port Interface Unit driver
+ *
  * 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.
@@ -11,7 +13,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/io.h>
@@ -70,11 +71,10 @@ static void tpiu_enable_hw(struct tpiu_drvdata *drvdata)
 	CS_LOCK(drvdata->base);
 }
 
-static int tpiu_enable(struct coresight_device *csdev)
+static int tpiu_enable(struct coresight_device *csdev, u32 mode)
 {
 	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	pm_runtime_get_sync(csdev->dev.parent);
 	tpiu_enable_hw(drvdata);
 
 	dev_info(drvdata->dev, "TPIU enabled\n");
@@ -98,7 +98,6 @@ static void tpiu_disable(struct coresight_device *csdev)
 	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	tpiu_disable_hw(drvdata);
-	pm_runtime_put(csdev->dev.parent);
 
 	dev_info(drvdata->dev, "TPIU disabled\n");
 }
@@ -172,14 +171,6 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
 	return 0;
 }
 
-static int tpiu_remove(struct amba_device *adev)
-{
-	struct tpiu_drvdata *drvdata = amba_get_drvdata(adev);
-
-	coresight_unregister(drvdata->csdev);
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int tpiu_runtime_suspend(struct device *dev)
 {
@@ -223,13 +214,9 @@ static struct amba_driver tpiu_driver = {
 		.name	= "coresight-tpiu",
 		.owner	= THIS_MODULE,
 		.pm	= &tpiu_dev_pm_ops,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= tpiu_probe,
-	.remove		= tpiu_remove,
 	.id_table	= tpiu_ids,
 };
-
-module_amba_driver(tpiu_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("CoreSight Trace Port Interface Unit driver");
+builtin_amba_driver(tpiu_driver);
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 93738dfbf..2ea596109 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
@@ -24,11 +23,28 @@
 #include <linux/coresight.h>
 #include <linux/of_platform.h>
 #include <linux/delay.h>
+#include <linux/pm_runtime.h>
 
 #include "coresight-priv.h"
 
 static DEFINE_MUTEX(coresight_mutex);
 
+/**
+ * struct coresight_node - elements of a path, from source to sink
+ * @csdev:	Address of an element.
+ * @link:	hook to the list.
+ */
+struct coresight_node {
+	struct coresight_device *csdev;
+	struct list_head link;
+};
+
+/*
+ * When operating Coresight drivers from the sysFS interface, only a single
+ * path can exist from a tracer (associated to a CPU) to a sink.
+ */
+static DEFINE_PER_CPU(struct list_head *, sysfs_path);
+
 static int coresight_id_match(struct device *dev, void *data)
 {
 	int trace_id, i_trace_id;
@@ -68,15 +84,12 @@ static int coresight_source_is_unique(struct coresight_device *csdev)
 				 csdev, coresight_id_match);
 }
 
-static int coresight_find_link_inport(struct coresight_device *csdev)
+static int coresight_find_link_inport(struct coresight_device *csdev,
+				      struct coresight_device *parent)
 {
 	int i;
-	struct coresight_device *parent;
 	struct coresight_connection *conn;
 
-	parent = container_of(csdev->path_link.next,
-			      struct coresight_device, path_link);
-
 	for (i = 0; i < parent->nr_outport; i++) {
 		conn = &parent->conns[i];
 		if (conn->child_dev == csdev)
@@ -89,15 +102,12 @@ static int coresight_find_link_inport(struct coresight_device *csdev)
 	return 0;
 }
 
-static int coresight_find_link_outport(struct coresight_device *csdev)
+static int coresight_find_link_outport(struct coresight_device *csdev,
+				       struct coresight_device *child)
 {
 	int i;
-	struct coresight_device *child;
 	struct coresight_connection *conn;
 
-	child = container_of(csdev->path_link.prev,
-			     struct coresight_device, path_link);
-
 	for (i = 0; i < csdev->nr_outport; i++) {
 		conn = &csdev->conns[i];
 		if (conn->child_dev == child)
@@ -110,13 +120,13 @@ static int coresight_find_link_outport(struct coresight_device *csdev)
 	return 0;
 }
 
-static int coresight_enable_sink(struct coresight_device *csdev)
+static int coresight_enable_sink(struct coresight_device *csdev, u32 mode)
 {
 	int ret;
 
 	if (!csdev->enable) {
 		if (sink_ops(csdev)->enable) {
-			ret = sink_ops(csdev)->enable(csdev);
+			ret = sink_ops(csdev)->enable(csdev, mode);
 			if (ret)
 				return ret;
 		}
@@ -138,14 +148,19 @@ static void coresight_disable_sink(struct coresight_device *csdev)
 	}
 }
 
-static int coresight_enable_link(struct coresight_device *csdev)
+static int coresight_enable_link(struct coresight_device *csdev,
+				 struct coresight_device *parent,
+				 struct coresight_device *child)
 {
 	int ret;
 	int link_subtype;
 	int refport, inport, outport;
 
-	inport = coresight_find_link_inport(csdev);
-	outport = coresight_find_link_outport(csdev);
+	if (!parent || !child)
+		return -EINVAL;
+
+	inport = coresight_find_link_inport(csdev, parent);
+	outport = coresight_find_link_outport(csdev, child);
 	link_subtype = csdev->subtype.link_subtype;
 
 	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
@@ -168,14 +183,19 @@ static int coresight_enable_link(struct coresight_device *csdev)
 	return 0;
 }
 
-static void coresight_disable_link(struct coresight_device *csdev)
+static void coresight_disable_link(struct coresight_device *csdev,
+				   struct coresight_device *parent,
+				   struct coresight_device *child)
 {
 	int i, nr_conns;
 	int link_subtype;
 	int refport, inport, outport;
 
-	inport = coresight_find_link_inport(csdev);
-	outport = coresight_find_link_outport(csdev);
+	if (!parent || !child)
+		return;
+
+	inport = coresight_find_link_inport(csdev, parent);
+	outport = coresight_find_link_outport(csdev, child);
 	link_subtype = csdev->subtype.link_subtype;
 
 	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
@@ -201,7 +221,7 @@ static void coresight_disable_link(struct coresight_device *csdev)
 	csdev->enable = false;
 }
 
-static int coresight_enable_source(struct coresight_device *csdev)
+static int coresight_enable_source(struct coresight_device *csdev, u32 mode)
 {
 	int ret;
 
@@ -213,7 +233,7 @@ static int coresight_enable_source(struct coresight_device *csdev)
 
 	if (!csdev->enable) {
 		if (source_ops(csdev)->enable) {
-			ret = source_ops(csdev)->enable(csdev);
+			ret = source_ops(csdev)->enable(csdev, NULL, mode);
 			if (ret)
 				return ret;
 		}
@@ -235,109 +255,188 @@ static void coresight_disable_source(struct coresight_device *csdev)
 	}
 }
 
-static int coresight_enable_path(struct list_head *path)
+void coresight_disable_path(struct list_head *path)
 {
-	int ret = 0;
-	struct coresight_device *cd;
-
-	/*
-	 * At this point we have a full @path, from source to sink.  The
-	 * sink is the first entry and the source the last one.  Go through
-	 * all the components and enable them one by one.
-	 */
-	list_for_each_entry(cd, path, path_link) {
-		if (cd == list_first_entry(path, struct coresight_device,
-					   path_link)) {
-			ret = coresight_enable_sink(cd);
-		} else if (list_is_last(&cd->path_link, path)) {
-			/*
-			 * Don't enable the source just yet - this needs to
-			 * happen at the very end when all links and sink
-			 * along the path have been configured properly.
-			 */
-			;
-		} else {
-			ret = coresight_enable_link(cd);
+	struct coresight_node *nd;
+	struct coresight_device *csdev, *parent, *child;
+
+	list_for_each_entry(nd, path, link) {
+		csdev = nd->csdev;
+
+		switch (csdev->type) {
+		case CORESIGHT_DEV_TYPE_SINK:
+		case CORESIGHT_DEV_TYPE_LINKSINK:
+			coresight_disable_sink(csdev);
+			break;
+		case CORESIGHT_DEV_TYPE_SOURCE:
+			/* sources are disabled from either sysFS or Perf */
+			break;
+		case CORESIGHT_DEV_TYPE_LINK:
+			parent = list_prev_entry(nd, link)->csdev;
+			child = list_next_entry(nd, link)->csdev;
+			coresight_disable_link(csdev, parent, child);
+			break;
+		default:
+			break;
 		}
-		if (ret)
-			goto err;
 	}
+}
 
-	return 0;
-err:
-	list_for_each_entry_continue_reverse(cd, path, path_link) {
-		if (cd == list_first_entry(path, struct coresight_device,
-					   path_link)) {
-			coresight_disable_sink(cd);
-		} else if (list_is_last(&cd->path_link, path)) {
-			;
-		} else {
-			coresight_disable_link(cd);
+int coresight_enable_path(struct list_head *path, u32 mode)
+{
+
+	int ret = 0;
+	struct coresight_node *nd;
+	struct coresight_device *csdev, *parent, *child;
+
+	list_for_each_entry_reverse(nd, path, link) {
+		csdev = nd->csdev;
+
+		switch (csdev->type) {
+		case CORESIGHT_DEV_TYPE_SINK:
+		case CORESIGHT_DEV_TYPE_LINKSINK:
+			ret = coresight_enable_sink(csdev, mode);
+			if (ret)
+				goto err;
+			break;
+		case CORESIGHT_DEV_TYPE_SOURCE:
+			/* sources are enabled from either sysFS or Perf */
+			break;
+		case CORESIGHT_DEV_TYPE_LINK:
+			parent = list_prev_entry(nd, link)->csdev;
+			child = list_next_entry(nd, link)->csdev;
+			ret = coresight_enable_link(csdev, parent, child);
+			if (ret)
+				goto err;
+			break;
+		default:
+			goto err;
 		}
 	}
 
+out:
 	return ret;
+err:
+	coresight_disable_path(path);
+	goto out;
 }
 
-static int coresight_disable_path(struct list_head *path)
+struct coresight_device *coresight_get_sink(struct list_head *path)
 {
-	struct coresight_device *cd;
+	struct coresight_device *csdev;
 
-	list_for_each_entry_reverse(cd, path, path_link) {
-		if (cd == list_first_entry(path, struct coresight_device,
-					   path_link)) {
-			coresight_disable_sink(cd);
-		} else if (list_is_last(&cd->path_link, path)) {
-			/*
-			 * The source has already been stopped, no need
-			 * to do it again here.
-			 */
-			;
-		} else {
-			coresight_disable_link(cd);
+	if (!path)
+		return NULL;
+
+	csdev = list_last_entry(path, struct coresight_node, link)->csdev;
+	if (csdev->type != CORESIGHT_DEV_TYPE_SINK &&
+	    csdev->type != CORESIGHT_DEV_TYPE_LINKSINK)
+		return NULL;
+
+	return csdev;
+}
+
+/**
+ * _coresight_build_path - recursively build a path from a @csdev to a sink.
+ * @csdev:	The device to start from.
+ * @path:	The list to add devices to.
+ *
+ * The tree of Coresight device is traversed until an activated sink is
+ * found.  From there the sink is added to the list along with all the
+ * devices that led to that point - the end result is a list from source
+ * to sink. In that list the source is the first device and the sink the
+ * last one.
+ */
+static int _coresight_build_path(struct coresight_device *csdev,
+				 struct list_head *path)
+{
+	int i;
+	bool found = false;
+	struct coresight_node *node;
+	struct coresight_connection *conn;
+
+	/* An activated sink has been found.  Enqueue the element */
+	if ((csdev->type == CORESIGHT_DEV_TYPE_SINK ||
+	     csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) && csdev->activated)
+		goto out;
+
+	/* Not a sink - recursively explore each port found on this element */
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		if (_coresight_build_path(conn->child_dev, path) == 0) {
+			found = true;
+			break;
 		}
 	}
 
+	if (!found)
+		return -ENODEV;
+
+out:
+	/*
+	 * A path from this element to a sink has been found.  The elements
+	 * leading to the sink are already enqueued, all that is left to do
+	 * is tell the PM runtime core we need this element and add a node
+	 * for it.
+	 */
+	node = kzalloc(sizeof(struct coresight_node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	node->csdev = csdev;
+	list_add(&node->link, path);
+	pm_runtime_get_sync(csdev->dev.parent);
+
 	return 0;
 }
 
-static int coresight_build_paths(struct coresight_device *csdev,
-				 struct list_head *path,
-				 bool enable)
+struct list_head *coresight_build_path(struct coresight_device *csdev)
 {
-	int i, ret = -EINVAL;
-	struct coresight_connection *conn;
+	struct list_head *path;
 
-	list_add(&csdev->path_link, path);
+	path = kzalloc(sizeof(struct list_head), GFP_KERNEL);
+	if (!path)
+		return NULL;
 
-	if ((csdev->type == CORESIGHT_DEV_TYPE_SINK ||
-	    csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) &&
-	    csdev->activated) {
-		if (enable)
-			ret = coresight_enable_path(path);
-		else
-			ret = coresight_disable_path(path);
-	} else {
-		for (i = 0; i < csdev->nr_outport; i++) {
-			conn = &csdev->conns[i];
-			if (coresight_build_paths(conn->child_dev,
-						    path, enable) == 0)
-				ret = 0;
-		}
+	INIT_LIST_HEAD(path);
+
+	if (_coresight_build_path(csdev, path)) {
+		kfree(path);
+		path = NULL;
 	}
 
-	if (list_first_entry(path, struct coresight_device, path_link) != csdev)
-		dev_err(&csdev->dev, "wrong device in %s\n", __func__);
+	return path;
+}
 
-	list_del(&csdev->path_link);
+/**
+ * coresight_release_path - release a previously built path.
+ * @path:	the path to release.
+ *
+ * Go through all the elements of a path and 1) removed it from the list and
+ * 2) free the memory allocated for each node.
+ */
+void coresight_release_path(struct list_head *path)
+{
+	struct coresight_device *csdev;
+	struct coresight_node *nd, *next;
 
-	return ret;
+	list_for_each_entry_safe(nd, next, path, link) {
+		csdev = nd->csdev;
+
+		pm_runtime_put_sync(csdev->dev.parent);
+		list_del(&nd->link);
+		kfree(nd);
+	}
+
+	kfree(path);
+	path = NULL;
 }
 
 int coresight_enable(struct coresight_device *csdev)
 {
 	int ret = 0;
-	LIST_HEAD(path);
+	int cpu;
+	struct list_head *path;
 
 	mutex_lock(&coresight_mutex);
 	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
@@ -348,22 +447,47 @@ int coresight_enable(struct coresight_device *csdev)
 	if (csdev->enable)
 		goto out;
 
-	if (coresight_build_paths(csdev, &path, true)) {
-		dev_err(&csdev->dev, "building path(s) failed\n");
+	path = coresight_build_path(csdev);
+	if (!path) {
+		pr_err("building path(s) failed\n");
 		goto out;
 	}
 
-	if (coresight_enable_source(csdev))
-		dev_err(&csdev->dev, "source enable failed\n");
+	ret = coresight_enable_path(path, CS_MODE_SYSFS);
+	if (ret)
+		goto err_path;
+
+	ret = coresight_enable_source(csdev, CS_MODE_SYSFS);
+	if (ret)
+		goto err_source;
+
+	/*
+	 * When working from sysFS it is important to keep track
+	 * of the paths that were created so that they can be
+	 * undone in 'coresight_disable()'.  Since there can only
+	 * be a single session per tracer (when working from sysFS)
+	 * a per-cpu variable will do just fine.
+	 */
+	cpu = source_ops(csdev)->cpu_id(csdev);
+	per_cpu(sysfs_path, cpu) = path;
+
 out:
 	mutex_unlock(&coresight_mutex);
 	return ret;
+
+err_source:
+	coresight_disable_path(path);
+
+err_path:
+	coresight_release_path(path);
+	goto out;
 }
 EXPORT_SYMBOL_GPL(coresight_enable);
 
 void coresight_disable(struct coresight_device *csdev)
 {
-	LIST_HEAD(path);
+	int cpu;
+	struct list_head *path;
 
 	mutex_lock(&coresight_mutex);
 	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
@@ -373,9 +497,12 @@ void coresight_disable(struct coresight_device *csdev)
 	if (!csdev->enable)
 		goto out;
 
+	cpu = source_ops(csdev)->cpu_id(csdev);
+	path = per_cpu(sysfs_path, cpu);
 	coresight_disable_source(csdev);
-	if (coresight_build_paths(csdev, &path, false))
-		dev_err(&csdev->dev, "releasing path(s) failed\n");
+	coresight_disable_path(path);
+	coresight_release_path(path);
+	per_cpu(sysfs_path, cpu) = NULL;
 
 out:
 	mutex_unlock(&coresight_mutex);
@@ -481,6 +608,8 @@ static void coresight_device_release(struct device *dev)
 {
 	struct coresight_device *csdev = to_coresight_device(dev);
 
+	kfree(csdev->conns);
+	kfree(csdev->refcnt);
 	kfree(csdev);
 }
 
@@ -536,7 +665,7 @@ static void coresight_fixup_orphan_conns(struct coresight_device *csdev)
 	 * are hooked-up with each newly added component.
 	 */
 	bus_for_each_dev(&coresight_bustype, NULL,
-				 csdev, coresight_orphan_match);
+			 csdev, coresight_orphan_match);
 }
 
 
@@ -568,6 +697,8 @@ static void coresight_fixup_device_conns(struct coresight_device *csdev)
 
 		if (dev) {
 			conn->child_dev = to_coresight_device(dev);
+			/* and put reference from 'bus_find_device()' */
+			put_device(dev);
 		} else {
 			csdev->orphan = true;
 			conn->child_dev = NULL;
@@ -575,6 +706,50 @@ static void coresight_fixup_device_conns(struct coresight_device *csdev)
 	}
 }
 
+static int coresight_remove_match(struct device *dev, void *data)
+{
+	int i;
+	struct coresight_device *csdev, *iterator;
+	struct coresight_connection *conn;
+
+	csdev = data;
+	iterator = to_coresight_device(dev);
+
+	/* No need to check oneself */
+	if (csdev == iterator)
+		return 0;
+
+	/*
+	 * Circle throuch all the connection of that component.  If we find
+	 * a connection whose name matches @csdev, remove it.
+	 */
+	for (i = 0; i < iterator->nr_outport; i++) {
+		conn = &iterator->conns[i];
+
+		if (conn->child_dev == NULL)
+			continue;
+
+		if (!strcmp(dev_name(&csdev->dev), conn->child_name)) {
+			iterator->orphan = true;
+			conn->child_dev = NULL;
+			/* No need to continue */
+			break;
+		}
+	}
+
+	/*
+	 * Returning '0' ensures that all known component on the
+	 * bus will be checked.
+	 */
+	return 0;
+}
+
+static void coresight_remove_conns(struct coresight_device *csdev)
+{
+	bus_for_each_dev(&coresight_bustype, NULL,
+			 csdev, coresight_remove_match);
+}
+
 /**
  * coresight_timeout - loop until a bit has changed to a specific state.
  * @addr: base address of the area of interest.
@@ -713,13 +888,8 @@ EXPORT_SYMBOL_GPL(coresight_register);
 
 void coresight_unregister(struct coresight_device *csdev)
 {
-	mutex_lock(&coresight_mutex);
-
-	kfree(csdev->conns);
+	/* Remove references of that device in the topology */
+	coresight_remove_conns(csdev);
 	device_unregister(&csdev->dev);
-
-	mutex_unlock(&coresight_mutex);
 }
 EXPORT_SYMBOL_GPL(coresight_unregister);
-
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c
index b09736178..b68da1888 100644
--- a/drivers/hwtracing/coresight/of_coresight.c
+++ b/drivers/hwtracing/coresight/of_coresight.c
@@ -10,7 +10,6 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -86,7 +85,7 @@ static int of_coresight_alloc_memory(struct device *dev,
 		return -ENOMEM;
 
 	/* Children connected to this component via @outports */
-	 pdata->child_names = devm_kzalloc(dev, pdata->nr_outport *
+	pdata->child_names = devm_kzalloc(dev, pdata->nr_outport *
 					  sizeof(*pdata->child_names),
 					  GFP_KERNEL);
 	if (!pdata->child_names)
diff --git a/drivers/hwtracing/intel_th/Kconfig b/drivers/hwtracing/intel_th/Kconfig
index b7a9073d9..1b412f8a5 100644
--- a/drivers/hwtracing/intel_th/Kconfig
+++ b/drivers/hwtracing/intel_th/Kconfig
@@ -1,5 +1,6 @@
 config INTEL_TH
 	tristate "Intel(R) Trace Hub controller"
+	depends on HAS_DMA && HAS_IOMEM
 	help
 	  Intel(R) Trace Hub (TH) is a set of hardware blocks (subdevices) that
 	  produce, switch and output trace data from multiple hardware and
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index 165d3001c..4272f2ce5 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -124,17 +124,34 @@ static struct device_type intel_th_source_device_type = {
 	.release	= intel_th_device_release,
 };
 
+static struct intel_th *to_intel_th(struct intel_th_device *thdev)
+{
+	/*
+	 * subdevice tree is flat: if this one is not a switch, its
+	 * parent must be
+	 */
+	if (thdev->type != INTEL_TH_SWITCH)
+		thdev = to_intel_th_hub(thdev);
+
+	if (WARN_ON_ONCE(!thdev || thdev->type != INTEL_TH_SWITCH))
+		return NULL;
+
+	return dev_get_drvdata(thdev->dev.parent);
+}
+
 static char *intel_th_output_devnode(struct device *dev, umode_t *mode,
 				     kuid_t *uid, kgid_t *gid)
 {
 	struct intel_th_device *thdev = to_intel_th_device(dev);
+	struct intel_th *th = to_intel_th(thdev);
 	char *node;
 
 	if (thdev->id >= 0)
-		node = kasprintf(GFP_KERNEL, "intel_th%d/%s%d", 0, thdev->name,
-				 thdev->id);
+		node = kasprintf(GFP_KERNEL, "intel_th%d/%s%d", th->id,
+				 thdev->name, thdev->id);
 	else
-		node = kasprintf(GFP_KERNEL, "intel_th%d/%s", 0, thdev->name);
+		node = kasprintf(GFP_KERNEL, "intel_th%d/%s", th->id,
+				 thdev->name);
 
 	return node;
 }
@@ -319,6 +336,7 @@ static struct intel_th_subdevice {
 	unsigned		nres;
 	unsigned		type;
 	unsigned		otype;
+	unsigned		scrpd;
 	int			id;
 } intel_th_subdevices[TH_SUBDEVICE_MAX] = {
 	{
@@ -352,6 +370,7 @@ static struct intel_th_subdevice {
 		.id	= 0,
 		.type	= INTEL_TH_OUTPUT,
 		.otype	= GTH_MSU,
+		.scrpd	= SCRPD_MEM_IS_PRIM_DEST | SCRPD_MSC0_IS_ENABLED,
 	},
 	{
 		.nres	= 2,
@@ -371,6 +390,7 @@ static struct intel_th_subdevice {
 		.id	= 1,
 		.type	= INTEL_TH_OUTPUT,
 		.otype	= GTH_MSU,
+		.scrpd	= SCRPD_MEM_IS_PRIM_DEST | SCRPD_MSC1_IS_ENABLED,
 	},
 	{
 		.nres	= 2,
@@ -403,6 +423,7 @@ static struct intel_th_subdevice {
 		.name	= "pti",
 		.type	= INTEL_TH_OUTPUT,
 		.otype	= GTH_PTI,
+		.scrpd	= SCRPD_PTI_IS_PRIM_DEST,
 	},
 	{
 		.nres	= 1,
@@ -477,6 +498,7 @@ static int intel_th_populate(struct intel_th *th, struct resource *devres,
 			thdev->dev.devt = MKDEV(th->major, i);
 			thdev->output.type = subdev->otype;
 			thdev->output.port = -1;
+			thdev->output.scratchpad = subdev->scrpd;
 		}
 
 		err = device_add(&thdev->dev);
@@ -579,6 +601,8 @@ intel_th_alloc(struct device *dev, struct resource *devres,
 	}
 	th->dev = dev;
 
+	dev_set_drvdata(dev, th);
+
 	err = intel_th_populate(th, devres, ndevres, irq);
 	if (err)
 		goto err_chrdev;
diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c
index 2dc5378cc..9beea0b54 100644
--- a/drivers/hwtracing/intel_th/gth.c
+++ b/drivers/hwtracing/intel_th/gth.c
@@ -146,24 +146,6 @@ gth_master_set(struct gth_device *gth, unsigned int master, int port)
 	iowrite32(val, gth->base + reg);
 }
 
-/*static int gth_master_get(struct gth_device *gth, unsigned int master)
-{
-	unsigned int reg = REG_GTH_SWDEST0 + ((master >> 1) & ~3u);
-	unsigned int shift = (master & 0x7) * 4;
-	u32 val;
-
-	if (master >= 256) {
-		reg = REG_GTH_GSWTDEST;
-		shift = 0;
-	}
-
-	val = ioread32(gth->base + reg);
-	val &= (0xf << shift);
-	val >>= shift;
-
-	return val ? val & 0x7 : -1;
-	}*/
-
 static ssize_t master_attr_show(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
@@ -304,6 +286,10 @@ static int intel_th_gth_reset(struct gth_device *gth)
 	if (scratchpad & SCRPD_DEBUGGER_IN_USE)
 		return -EBUSY;
 
+	/* Always save/restore STH and TU registers in S0ix entry/exit */
+	scratchpad |= SCRPD_STH_IS_ENABLED | SCRPD_TRIGGER_IS_ENABLED;
+	iowrite32(scratchpad, gth->base + REG_GTH_SCRPD0);
+
 	/* output ports */
 	for (port = 0; port < 8; port++) {
 		if (gth_output_parm_get(gth, port, TH_OUTPUT_PARM(port)) ==
@@ -506,6 +492,10 @@ static void intel_th_gth_disable(struct intel_th_device *thdev,
 	if (!count)
 		dev_dbg(&thdev->dev, "timeout waiting for GTH[%d] PLE\n",
 			output->port);
+
+	reg = ioread32(gth->base + REG_GTH_SCRPD0);
+	reg &= ~output->scratchpad;
+	iowrite32(reg, gth->base + REG_GTH_SCRPD0);
 }
 
 /**
@@ -520,7 +510,7 @@ static void intel_th_gth_enable(struct intel_th_device *thdev,
 				struct intel_th_output *output)
 {
 	struct gth_device *gth = dev_get_drvdata(&thdev->dev);
-	u32 scr = 0xfc0000;
+	u32 scr = 0xfc0000, scrpd;
 	int master;
 
 	spin_lock(&gth->gth_lock);
@@ -535,6 +525,10 @@ static void intel_th_gth_enable(struct intel_th_device *thdev,
 	output->active = true;
 	spin_unlock(&gth->gth_lock);
 
+	scrpd = ioread32(gth->base + REG_GTH_SCRPD0);
+	scrpd |= output->scratchpad;
+	iowrite32(scrpd, gth->base + REG_GTH_SCRPD0);
+
 	iowrite32(scr, gth->base + REG_GTH_SCR);
 	iowrite32(0, gth->base + REG_GTH_SCR2);
 }
diff --git a/drivers/hwtracing/intel_th/gth.h b/drivers/hwtracing/intel_th/gth.h
index 3b714b7a6..56f0d2620 100644
--- a/drivers/hwtracing/intel_th/gth.h
+++ b/drivers/hwtracing/intel_th/gth.h
@@ -57,9 +57,6 @@ enum {
 	REG_GTH_SCRPD3		= 0xec, /* ScratchPad[3] */
 };
 
-/* Externall debugger is using Intel TH */
-#define SCRPD_DEBUGGER_IN_USE	BIT(24)
-
 /* waiting for Pipeline Empty bit(s) to assert for GTH */
 #define GTH_PLE_WAITLOOP_DEPTH	10000
 
diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h
index 57fd72b20..eedd09332 100644
--- a/drivers/hwtracing/intel_th/intel_th.h
+++ b/drivers/hwtracing/intel_th/intel_th.h
@@ -30,6 +30,7 @@ enum {
  * struct intel_th_output - descriptor INTEL_TH_OUTPUT type devices
  * @port:	output port number, assigned by the switch
  * @type:	GTH_{MSU,CTP,PTI}
+ * @scratchpad:	scratchpad bits to flag when this output is enabled
  * @multiblock:	true for multiblock output configuration
  * @active:	true when this output is enabled
  *
@@ -41,6 +42,7 @@ enum {
 struct intel_th_output {
 	int		port;
 	unsigned int	type;
+	unsigned int	scratchpad;
 	bool		multiblock;
 	bool		active;
 };
@@ -241,4 +243,43 @@ enum {
 	GTH_PTI = 4,	/* MIPI-PTI */
 };
 
+/*
+ * Scratchpad bits: tell firmware and external debuggers
+ * what we are up to.
+ */
+enum {
+	/* Memory is the primary destination */
+	SCRPD_MEM_IS_PRIM_DEST		= BIT(0),
+	/* XHCI DbC is the primary destination */
+	SCRPD_DBC_IS_PRIM_DEST		= BIT(1),
+	/* PTI is the primary destination */
+	SCRPD_PTI_IS_PRIM_DEST		= BIT(2),
+	/* BSSB is the primary destination */
+	SCRPD_BSSB_IS_PRIM_DEST		= BIT(3),
+	/* PTI is the alternate destination */
+	SCRPD_PTI_IS_ALT_DEST		= BIT(4),
+	/* BSSB is the alternate destination */
+	SCRPD_BSSB_IS_ALT_DEST		= BIT(5),
+	/* DeepSx exit occurred */
+	SCRPD_DEEPSX_EXIT		= BIT(6),
+	/* S4 exit occurred */
+	SCRPD_S4_EXIT			= BIT(7),
+	/* S5 exit occurred */
+	SCRPD_S5_EXIT			= BIT(8),
+	/* MSU controller 0/1 is enabled */
+	SCRPD_MSC0_IS_ENABLED		= BIT(9),
+	SCRPD_MSC1_IS_ENABLED		= BIT(10),
+	/* Sx exit occurred */
+	SCRPD_SX_EXIT			= BIT(11),
+	/* Trigger Unit is enabled */
+	SCRPD_TRIGGER_IS_ENABLED	= BIT(12),
+	SCRPD_ODLA_IS_ENABLED		= BIT(13),
+	SCRPD_SOCHAP_IS_ENABLED		= BIT(14),
+	SCRPD_STH_IS_ENABLED		= BIT(15),
+	SCRPD_DCIH_IS_ENABLED		= BIT(16),
+	SCRPD_VER_IS_ENABLED		= BIT(17),
+	/* External debugger is using Intel TH */
+	SCRPD_DEBUGGER_IN_USE		= BIT(24),
+};
+
 #endif
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 70ca27e45..d9d6022c5 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -408,7 +408,7 @@ msc_buffer_iterate(struct msc_iter *iter, size_t size, void *data,
 		 * Second time (wrap_count==1), it's just like any other block,
 		 * containing data in the range of [MSC_BDESC..data_bytes].
 		 */
-		if (iter->block == iter->start_block && iter->wrap_count) {
+		if (iter->block == iter->start_block && iter->wrap_count == 2) {
 			tocopy = DATA_IN_PAGE - data_bytes;
 			src += data_bytes;
 		}
@@ -1112,12 +1112,11 @@ static ssize_t intel_th_msc_read(struct file *file, char __user *buf,
 		size = msc->nr_pages << PAGE_SHIFT;
 
 	if (!size)
-		return 0;
+		goto put_count;
 
-	if (off >= size) {
-		len = 0;
+	if (off >= size)
 		goto put_count;
-	}
+
 	if (off + len >= size)
 		len = size - off;
 
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 641e87936..bca7a2ac0 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -46,8 +46,6 @@ static int intel_th_pci_probe(struct pci_dev *pdev,
 	if (IS_ERR(th))
 		return PTR_ERR(th);
 
-	pci_set_drvdata(pdev, th);
-
 	return 0;
 }
 
@@ -67,6 +65,16 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa126),
 		.driver_data = (kernel_ulong_t)0,
 	},
+	{
+		/* Apollo Lake */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x5a8e),
+		.driver_data = (kernel_ulong_t)0,
+	},
+	{
+		/* Broxton */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0a80),
+		.driver_data = (kernel_ulong_t)0,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/hwtracing/intel_th/sth.c b/drivers/hwtracing/intel_th/sth.c
index 56101c33e..e1aee61dd 100644
--- a/drivers/hwtracing/intel_th/sth.c
+++ b/drivers/hwtracing/intel_th/sth.c
@@ -94,10 +94,13 @@ static ssize_t sth_stm_packet(struct stm_data *stm_data, unsigned int master,
 	case STP_PACKET_TRIG:
 		if (flags & STP_PACKET_TIMESTAMPED)
 			reg += 4;
-		iowrite8(*payload, sth->base + reg);
+		writeb_relaxed(*payload, sth->base + reg);
 		break;
 
 	case STP_PACKET_MERR:
+		if (size > 4)
+			size = 4;
+
 		sth_iowrite(&out->MERR, payload, size);
 		break;
 
@@ -107,8 +110,8 @@ static ssize_t sth_stm_packet(struct stm_data *stm_data, unsigned int master,
 		else
 			outp = (u64 __iomem *)&out->FLAG;
 
-		size = 1;
-		sth_iowrite(outp, payload, size);
+		size = 0;
+		writeb_relaxed(0, outp);
 		break;
 
 	case STP_PACKET_USER:
@@ -129,6 +132,8 @@ static ssize_t sth_stm_packet(struct stm_data *stm_data, unsigned int master,
 
 		sth_iowrite(outp, payload, size);
 		break;
+	default:
+		return -ENOTSUPP;
 	}
 
 	return size;
diff --git a/drivers/hwtracing/stm/Kconfig b/drivers/hwtracing/stm/Kconfig
index e7a348807..847a39b35 100644
--- a/drivers/hwtracing/stm/Kconfig
+++ b/drivers/hwtracing/stm/Kconfig
@@ -9,6 +9,8 @@ config STM
 
 	  Say Y here to enable System Trace Module device support.
 
+if STM
+
 config STM_DUMMY
 	tristate "Dummy STM driver"
 	help
@@ -25,3 +27,16 @@ config STM_SOURCE_CONSOLE
 
 	  If you want to send kernel console messages over STM devices,
 	  say Y.
+
+config STM_SOURCE_HEARTBEAT
+	tristate "Heartbeat over STM devices"
+	help
+	  This is a kernel space trace source that sends periodic
+	  heartbeat messages to trace hosts over STM devices. It is
+	  also useful for testing stm class drivers and the stm class
+	  framework itself.
+
+	  If you want to send heartbeat messages over STM devices,
+	  say Y.
+
+endif
diff --git a/drivers/hwtracing/stm/Makefile b/drivers/hwtracing/stm/Makefile
index f9312c38d..a9ce3d487 100644
--- a/drivers/hwtracing/stm/Makefile
+++ b/drivers/hwtracing/stm/Makefile
@@ -5,5 +5,7 @@ stm_core-y		:= core.o policy.o
 obj-$(CONFIG_STM_DUMMY)	+= dummy_stm.o
 
 obj-$(CONFIG_STM_SOURCE_CONSOLE)	+= stm_console.o
+obj-$(CONFIG_STM_SOURCE_HEARTBEAT)	+= stm_heartbeat.o
 
 stm_console-y		:= console.o
+stm_heartbeat-y		:= heartbeat.o
diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c
index b6445d9e5..de80d45d8 100644
--- a/drivers/hwtracing/stm/core.c
+++ b/drivers/hwtracing/stm/core.c
@@ -113,6 +113,7 @@ struct stm_device *stm_find_device(const char *buf)
 
 	stm = to_stm_device(dev);
 	if (!try_module_get(stm->owner)) {
+		/* matches class_find_device() above */
 		put_device(dev);
 		return NULL;
 	}
@@ -125,7 +126,7 @@ struct stm_device *stm_find_device(const char *buf)
  * @stm:	stm device, previously acquired by stm_find_device()
  *
  * This drops the module reference and device reference taken by
- * stm_find_device().
+ * stm_find_device() or stm_char_open().
  */
 void stm_put_device(struct stm_device *stm)
 {
@@ -185,6 +186,9 @@ static void stm_output_claim(struct stm_device *stm, struct stm_output *output)
 {
 	struct stp_master *master = stm_master(stm, output->master);
 
+	lockdep_assert_held(&stm->mc_lock);
+	lockdep_assert_held(&output->lock);
+
 	if (WARN_ON_ONCE(master->nr_free < output->nr_chans))
 		return;
 
@@ -199,6 +203,9 @@ stm_output_disclaim(struct stm_device *stm, struct stm_output *output)
 {
 	struct stp_master *master = stm_master(stm, output->master);
 
+	lockdep_assert_held(&stm->mc_lock);
+	lockdep_assert_held(&output->lock);
+
 	bitmap_release_region(&master->chan_map[0], output->channel,
 			      ilog2(output->nr_chans));
 
@@ -233,7 +240,7 @@ static int find_free_channels(unsigned long *bitmap, unsigned int start,
 	return -1;
 }
 
-static unsigned int
+static int
 stm_find_master_chan(struct stm_device *stm, unsigned int width,
 		     unsigned int *mstart, unsigned int mend,
 		     unsigned int *cstart, unsigned int cend)
@@ -288,12 +295,13 @@ static int stm_output_assign(struct stm_device *stm, unsigned int width,
 	}
 
 	spin_lock(&stm->mc_lock);
+	spin_lock(&output->lock);
 	/* output is already assigned -- shouldn't happen */
 	if (WARN_ON_ONCE(output->nr_chans))
 		goto unlock;
 
 	ret = stm_find_master_chan(stm, width, &midx, mend, &cidx, cend);
-	if (ret)
+	if (ret < 0)
 		goto unlock;
 
 	output->master = midx;
@@ -304,6 +312,7 @@ static int stm_output_assign(struct stm_device *stm, unsigned int width,
 
 	ret = 0;
 unlock:
+	spin_unlock(&output->lock);
 	spin_unlock(&stm->mc_lock);
 
 	return ret;
@@ -312,11 +321,18 @@ unlock:
 static void stm_output_free(struct stm_device *stm, struct stm_output *output)
 {
 	spin_lock(&stm->mc_lock);
+	spin_lock(&output->lock);
 	if (output->nr_chans)
 		stm_output_disclaim(stm, output);
+	spin_unlock(&output->lock);
 	spin_unlock(&stm->mc_lock);
 }
 
+static void stm_output_init(struct stm_output *output)
+{
+	spin_lock_init(&output->lock);
+}
+
 static int major_match(struct device *dev, const void *data)
 {
 	unsigned int major = *(unsigned int *)data;
@@ -339,6 +355,7 @@ static int stm_char_open(struct inode *inode, struct file *file)
 	if (!stmf)
 		return -ENOMEM;
 
+	stm_output_init(&stmf->output);
 	stmf->stm = to_stm_device(dev);
 
 	if (!try_module_get(stmf->stm->owner))
@@ -349,6 +366,8 @@ static int stm_char_open(struct inode *inode, struct file *file)
 	return nonseekable_open(inode, file);
 
 err_free:
+	/* matches class_find_device() above */
+	put_device(dev);
 	kfree(stmf);
 
 	return err;
@@ -357,9 +376,19 @@ err_free:
 static int stm_char_release(struct inode *inode, struct file *file)
 {
 	struct stm_file *stmf = file->private_data;
+	struct stm_device *stm = stmf->stm;
+
+	if (stm->data->unlink)
+		stm->data->unlink(stm->data, stmf->output.master,
+				  stmf->output.channel);
 
-	stm_output_free(stmf->stm, &stmf->output);
-	stm_put_device(stmf->stm);
+	stm_output_free(stm, &stmf->output);
+
+	/*
+	 * matches the stm_char_open()'s
+	 * class_find_device() + try_module_get()
+	 */
+	stm_put_device(stm);
 	kfree(stmf);
 
 	return 0;
@@ -380,8 +409,8 @@ static int stm_file_assign(struct stm_file *stmf, char *id, unsigned int width)
 	return ret;
 }
 
-static void stm_write(struct stm_data *data, unsigned int master,
-		      unsigned int channel, const char *buf, size_t count)
+static ssize_t stm_write(struct stm_data *data, unsigned int master,
+			  unsigned int channel, const char *buf, size_t count)
 {
 	unsigned int flags = STP_PACKET_TIMESTAMPED;
 	const unsigned char *p = buf, nil = 0;
@@ -393,9 +422,14 @@ static void stm_write(struct stm_data *data, unsigned int master,
 		sz = data->packet(data, master, channel, STP_PACKET_DATA, flags,
 				  sz, p);
 		flags = 0;
+
+		if (sz < 0)
+			break;
 	}
 
 	data->packet(data, master, channel, STP_PACKET_FLAG, 0, 0, &nil);
+
+	return pos;
 }
 
 static ssize_t stm_char_write(struct file *file, const char __user *buf,
@@ -406,6 +440,9 @@ static ssize_t stm_char_write(struct file *file, const char __user *buf,
 	char *kbuf;
 	int err;
 
+	if (count + 1 > PAGE_SIZE)
+		count = PAGE_SIZE - 1;
+
 	/*
 	 * if no m/c have been assigned to this writer up to this
 	 * point, use "default" policy entry
@@ -430,8 +467,8 @@ static ssize_t stm_char_write(struct file *file, const char __user *buf,
 		return -EFAULT;
 	}
 
-	stm_write(stm->data, stmf->output.master, stmf->output.channel, kbuf,
-		  count);
+	count = stm_write(stm->data, stmf->output.master, stmf->output.channel,
+			  kbuf, count);
 
 	kfree(kbuf);
 
@@ -515,10 +552,8 @@ static int stm_char_policy_set_ioctl(struct stm_file *stmf, void __user *arg)
 		ret = stm->data->link(stm->data, stmf->output.master,
 				      stmf->output.channel);
 
-	if (ret) {
+	if (ret)
 		stm_output_free(stmf->stm, &stmf->output);
-		stm_put_device(stmf->stm);
-	}
 
 err_free:
 	kfree(id);
@@ -618,7 +653,7 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data,
 	if (!stm_data->packet || !stm_data->sw_nchannels)
 		return -EINVAL;
 
-	nmasters = stm_data->sw_end - stm_data->sw_start;
+	nmasters = stm_data->sw_end - stm_data->sw_start + 1;
 	stm = kzalloc(sizeof(*stm) + nmasters * sizeof(void *), GFP_KERNEL);
 	if (!stm)
 		return -ENOMEM;
@@ -641,6 +676,7 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data,
 	if (err)
 		goto err_device;
 
+	mutex_init(&stm->link_mutex);
 	spin_lock_init(&stm->link_lock);
 	INIT_LIST_HEAD(&stm->link_list);
 
@@ -654,6 +690,7 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data,
 	return 0;
 
 err_device:
+	/* matches device_initialize() above */
 	put_device(&stm->dev);
 err_free:
 	kfree(stm);
@@ -662,20 +699,28 @@ err_free:
 }
 EXPORT_SYMBOL_GPL(stm_register_device);
 
-static void __stm_source_link_drop(struct stm_source_device *src,
-				   struct stm_device *stm);
+static int __stm_source_link_drop(struct stm_source_device *src,
+				  struct stm_device *stm);
 
 void stm_unregister_device(struct stm_data *stm_data)
 {
 	struct stm_device *stm = stm_data->stm;
 	struct stm_source_device *src, *iter;
-	int i;
+	int i, ret;
 
-	spin_lock(&stm->link_lock);
+	mutex_lock(&stm->link_mutex);
 	list_for_each_entry_safe(src, iter, &stm->link_list, link_entry) {
-		__stm_source_link_drop(src, stm);
+		ret = __stm_source_link_drop(src, stm);
+		/*
+		 * src <-> stm link must not change under the same
+		 * stm::link_mutex, so complain loudly if it has;
+		 * also in this situation ret!=0 means this src is
+		 * not connected to this stm and it should be otherwise
+		 * safe to proceed with the tear-down of stm.
+		 */
+		WARN_ON_ONCE(ret);
 	}
-	spin_unlock(&stm->link_lock);
+	mutex_unlock(&stm->link_mutex);
 
 	synchronize_srcu(&stm_source_srcu);
 
@@ -686,7 +731,7 @@ void stm_unregister_device(struct stm_data *stm_data)
 		stp_policy_unbind(stm->policy);
 	mutex_unlock(&stm->policy_mutex);
 
-	for (i = 0; i < stm->sw_nmasters; i++)
+	for (i = stm->data->sw_start; i <= stm->data->sw_end; i++)
 		stp_master_free(stm, i);
 
 	device_unregister(&stm->dev);
@@ -694,6 +739,17 @@ void stm_unregister_device(struct stm_data *stm_data)
 }
 EXPORT_SYMBOL_GPL(stm_unregister_device);
 
+/*
+ * stm::link_list access serialization uses a spinlock and a mutex; holding
+ * either of them guarantees that the list is stable; modification requires
+ * holding both of them.
+ *
+ * Lock ordering is as follows:
+ *   stm::link_mutex
+ *     stm::link_lock
+ *       src::link_lock
+ */
+
 /**
  * stm_source_link_add() - connect an stm_source device to an stm device
  * @src:	stm_source device
@@ -710,6 +766,7 @@ static int stm_source_link_add(struct stm_source_device *src,
 	char *id;
 	int err;
 
+	mutex_lock(&stm->link_mutex);
 	spin_lock(&stm->link_lock);
 	spin_lock(&src->link_lock);
 
@@ -719,6 +776,7 @@ static int stm_source_link_add(struct stm_source_device *src,
 
 	spin_unlock(&src->link_lock);
 	spin_unlock(&stm->link_lock);
+	mutex_unlock(&stm->link_mutex);
 
 	id = kstrdup(src->data->name, GFP_KERNEL);
 	if (id) {
@@ -753,9 +811,9 @@ static int stm_source_link_add(struct stm_source_device *src,
 
 fail_free_output:
 	stm_output_free(stm, &src->output);
-	stm_put_device(stm);
 
 fail_detach:
+	mutex_lock(&stm->link_mutex);
 	spin_lock(&stm->link_lock);
 	spin_lock(&src->link_lock);
 
@@ -764,6 +822,7 @@ fail_detach:
 
 	spin_unlock(&src->link_lock);
 	spin_unlock(&stm->link_lock);
+	mutex_unlock(&stm->link_mutex);
 
 	return err;
 }
@@ -776,28 +835,55 @@ fail_detach:
  * If @stm is @src::link, disconnect them from one another and put the
  * reference on the @stm device.
  *
- * Caller must hold stm::link_lock.
+ * Caller must hold stm::link_mutex.
  */
-static void __stm_source_link_drop(struct stm_source_device *src,
-				   struct stm_device *stm)
+static int __stm_source_link_drop(struct stm_source_device *src,
+				  struct stm_device *stm)
 {
 	struct stm_device *link;
+	int ret = 0;
+
+	lockdep_assert_held(&stm->link_mutex);
 
+	/* for stm::link_list modification, we hold both mutex and spinlock */
+	spin_lock(&stm->link_lock);
 	spin_lock(&src->link_lock);
 	link = srcu_dereference_check(src->link, &stm_source_srcu, 1);
-	if (WARN_ON_ONCE(link != stm)) {
-		spin_unlock(&src->link_lock);
-		return;
+
+	/*
+	 * The linked device may have changed since we last looked, because
+	 * we weren't holding the src::link_lock back then; if this is the
+	 * case, tell the caller to retry.
+	 */
+	if (link != stm) {
+		ret = -EAGAIN;
+		goto unlock;
 	}
 
 	stm_output_free(link, &src->output);
-	/* caller must hold stm::link_lock */
 	list_del_init(&src->link_entry);
 	/* matches stm_find_device() from stm_source_link_store() */
 	stm_put_device(link);
 	rcu_assign_pointer(src->link, NULL);
 
+unlock:
 	spin_unlock(&src->link_lock);
+	spin_unlock(&stm->link_lock);
+
+	/*
+	 * Call the unlink callbacks for both source and stm, when we know
+	 * that we have actually performed the unlinking.
+	 */
+	if (!ret) {
+		if (src->data->unlink)
+			src->data->unlink(src->data);
+
+		if (stm->data->unlink)
+			stm->data->unlink(stm->data, src->output.master,
+					  src->output.channel);
+	}
+
+	return ret;
 }
 
 /**
@@ -813,21 +899,29 @@ static void __stm_source_link_drop(struct stm_source_device *src,
 static void stm_source_link_drop(struct stm_source_device *src)
 {
 	struct stm_device *stm;
-	int idx;
+	int idx, ret;
 
+retry:
 	idx = srcu_read_lock(&stm_source_srcu);
+	/*
+	 * The stm device will be valid for the duration of this
+	 * read section, but the link may change before we grab
+	 * the src::link_lock in __stm_source_link_drop().
+	 */
 	stm = srcu_dereference(src->link, &stm_source_srcu);
 
+	ret = 0;
 	if (stm) {
-		if (src->data->unlink)
-			src->data->unlink(src->data);
-
-		spin_lock(&stm->link_lock);
-		__stm_source_link_drop(src, stm);
-		spin_unlock(&stm->link_lock);
+		mutex_lock(&stm->link_mutex);
+		ret = __stm_source_link_drop(src, stm);
+		mutex_unlock(&stm->link_mutex);
 	}
 
 	srcu_read_unlock(&stm_source_srcu, idx);
+
+	/* if it did change, retry */
+	if (ret == -EAGAIN)
+		goto retry;
 }
 
 static ssize_t stm_source_link_show(struct device *dev,
@@ -862,8 +956,10 @@ static ssize_t stm_source_link_store(struct device *dev,
 		return -EINVAL;
 
 	err = stm_source_link_add(src, link);
-	if (err)
+	if (err) {
+		/* matches the stm_find_device() above */
 		stm_put_device(link);
+	}
 
 	return err ? : count;
 }
@@ -925,6 +1021,7 @@ int stm_source_register_device(struct device *parent,
 	if (err)
 		goto err;
 
+	stm_output_init(&src->output);
 	spin_lock_init(&src->link_lock);
 	INIT_LIST_HEAD(&src->link_entry);
 	src->data = data;
@@ -973,9 +1070,9 @@ int stm_source_write(struct stm_source_data *data, unsigned int chan,
 
 	stm = srcu_dereference(src->link, &stm_source_srcu);
 	if (stm)
-		stm_write(stm->data, src->output.master,
-			  src->output.channel + chan,
-			  buf, count);
+		count = stm_write(stm->data, src->output.master,
+				  src->output.channel + chan,
+				  buf, count);
 	else
 		count = -ENODEV;
 
diff --git a/drivers/hwtracing/stm/dummy_stm.c b/drivers/hwtracing/stm/dummy_stm.c
index 3709bef0b..310adf57e 100644
--- a/drivers/hwtracing/stm/dummy_stm.c
+++ b/drivers/hwtracing/stm/dummy_stm.c
@@ -40,22 +40,75 @@ dummy_stm_packet(struct stm_data *stm_data, unsigned int master,
 	return size;
 }
 
-static struct stm_data dummy_stm = {
-	.name		= "dummy_stm",
-	.sw_start	= 0x0000,
-	.sw_end		= 0xffff,
-	.sw_nchannels	= 0xffff,
-	.packet		= dummy_stm_packet,
-};
+#define DUMMY_STM_MAX 32
+
+static struct stm_data dummy_stm[DUMMY_STM_MAX];
+
+static int nr_dummies = 4;
+
+module_param(nr_dummies, int, 0600);
+
+static unsigned int dummy_stm_nr;
+
+static unsigned int fail_mode;
+
+module_param(fail_mode, int, 0600);
+
+static int dummy_stm_link(struct stm_data *data, unsigned int master,
+			  unsigned int channel)
+{
+	if (fail_mode && (channel & fail_mode))
+		return -EINVAL;
+
+	return 0;
+}
 
 static int dummy_stm_init(void)
 {
-	return stm_register_device(NULL, &dummy_stm, THIS_MODULE);
+	int i, ret = -ENOMEM, __nr_dummies = ACCESS_ONCE(nr_dummies);
+
+	if (__nr_dummies < 0 || __nr_dummies > DUMMY_STM_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < __nr_dummies; i++) {
+		dummy_stm[i].name = kasprintf(GFP_KERNEL, "dummy_stm.%d", i);
+		if (!dummy_stm[i].name)
+			goto fail_unregister;
+
+		dummy_stm[i].sw_start		= 0x0000;
+		dummy_stm[i].sw_end		= 0xffff;
+		dummy_stm[i].sw_nchannels	= 0xffff;
+		dummy_stm[i].packet		= dummy_stm_packet;
+		dummy_stm[i].link		= dummy_stm_link;
+
+		ret = stm_register_device(NULL, &dummy_stm[i], THIS_MODULE);
+		if (ret)
+			goto fail_free;
+	}
+
+	dummy_stm_nr = __nr_dummies;
+
+	return 0;
+
+fail_unregister:
+	for (i--; i >= 0; i--) {
+		stm_unregister_device(&dummy_stm[i]);
+fail_free:
+		kfree(dummy_stm[i].name);
+	}
+
+	return ret;
+
 }
 
 static void dummy_stm_exit(void)
 {
-	stm_unregister_device(&dummy_stm);
+	int i;
+
+	for (i = 0; i < dummy_stm_nr; i++) {
+		stm_unregister_device(&dummy_stm[i]);
+		kfree(dummy_stm[i].name);
+	}
 }
 
 module_init(dummy_stm_init);
diff --git a/drivers/hwtracing/stm/heartbeat.c b/drivers/hwtracing/stm/heartbeat.c
new file mode 100644
index 000000000..0133571b5
--- /dev/null
+++ b/drivers/hwtracing/stm/heartbeat.c
@@ -0,0 +1,130 @@
+/*
+ * Simple heartbeat STM source driver
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ * Heartbeat STM source will send repetitive messages over STM devices to a
+ * trace host.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/hrtimer.h>
+#include <linux/slab.h>
+#include <linux/stm.h>
+
+#define STM_HEARTBEAT_MAX	32
+
+static int nr_devs = 4;
+static int interval_ms = 10;
+
+module_param(nr_devs, int, 0600);
+module_param(interval_ms, int, 0600);
+
+static struct stm_heartbeat {
+	struct stm_source_data	data;
+	struct hrtimer		hrtimer;
+	unsigned int		active;
+} stm_heartbeat[STM_HEARTBEAT_MAX];
+
+static unsigned int nr_instances;
+
+static const char str[] = "heartbeat stm source driver is here to serve you";
+
+static enum hrtimer_restart stm_heartbeat_hrtimer_handler(struct hrtimer *hr)
+{
+	struct stm_heartbeat *heartbeat = container_of(hr, struct stm_heartbeat,
+						       hrtimer);
+
+	stm_source_write(&heartbeat->data, 0, str, sizeof str);
+	if (heartbeat->active)
+		hrtimer_forward_now(hr, ms_to_ktime(interval_ms));
+
+	return heartbeat->active ? HRTIMER_RESTART : HRTIMER_NORESTART;
+}
+
+static int stm_heartbeat_link(struct stm_source_data *data)
+{
+	struct stm_heartbeat *heartbeat =
+		container_of(data, struct stm_heartbeat, data);
+
+	heartbeat->active = 1;
+	hrtimer_start(&heartbeat->hrtimer, ms_to_ktime(interval_ms),
+		      HRTIMER_MODE_ABS);
+
+	return 0;
+}
+
+static void stm_heartbeat_unlink(struct stm_source_data *data)
+{
+	struct stm_heartbeat *heartbeat =
+		container_of(data, struct stm_heartbeat, data);
+
+	heartbeat->active = 0;
+	hrtimer_cancel(&heartbeat->hrtimer);
+}
+
+static int stm_heartbeat_init(void)
+{
+	int i, ret = -ENOMEM, __nr_instances = ACCESS_ONCE(nr_devs);
+
+	if (__nr_instances < 0 || __nr_instances > STM_HEARTBEAT_MAX)
+		return -EINVAL;
+
+	for (i = 0; i < __nr_instances; i++) {
+		stm_heartbeat[i].data.name =
+			kasprintf(GFP_KERNEL, "heartbeat.%d", i);
+		if (!stm_heartbeat[i].data.name)
+			goto fail_unregister;
+
+		stm_heartbeat[i].data.nr_chans	= 1;
+		stm_heartbeat[i].data.link		= stm_heartbeat_link;
+		stm_heartbeat[i].data.unlink	= stm_heartbeat_unlink;
+		hrtimer_init(&stm_heartbeat[i].hrtimer, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_ABS);
+		stm_heartbeat[i].hrtimer.function =
+			stm_heartbeat_hrtimer_handler;
+
+		ret = stm_source_register_device(NULL, &stm_heartbeat[i].data);
+		if (ret)
+			goto fail_free;
+	}
+
+	nr_instances = __nr_instances;
+
+	return 0;
+
+fail_unregister:
+	for (i--; i >= 0; i--) {
+		stm_source_unregister_device(&stm_heartbeat[i].data);
+fail_free:
+		kfree(stm_heartbeat[i].data.name);
+	}
+
+	return ret;
+}
+
+static void stm_heartbeat_exit(void)
+{
+	int i;
+
+	for (i = 0; i < nr_instances; i++) {
+		stm_source_unregister_device(&stm_heartbeat[i].data);
+		kfree(stm_heartbeat[i].data.name);
+	}
+}
+
+module_init(stm_heartbeat_init);
+module_exit(stm_heartbeat_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("stm_heartbeat driver");
+MODULE_AUTHOR("Alexander Shishkin <alexander.shishkin@linux.intel.com>");
diff --git a/drivers/hwtracing/stm/policy.c b/drivers/hwtracing/stm/policy.c
index 11ab6d01a..1db189657 100644
--- a/drivers/hwtracing/stm/policy.c
+++ b/drivers/hwtracing/stm/policy.c
@@ -272,13 +272,17 @@ void stp_policy_unbind(struct stp_policy *policy)
 {
 	struct stm_device *stm = policy->stm;
 
+	/*
+	 * stp_policy_release() will not call here if the policy is already
+	 * unbound; other users should not either, as no link exists between
+	 * this policy and anything else in that case
+	 */
 	if (WARN_ON_ONCE(!policy->stm))
 		return;
 
-	mutex_lock(&stm->policy_mutex);
-	stm->policy = NULL;
-	mutex_unlock(&stm->policy_mutex);
+	lockdep_assert_held(&stm->policy_mutex);
 
+	stm->policy = NULL;
 	policy->stm = NULL;
 
 	stm_put_device(stm);
@@ -287,8 +291,16 @@ void stp_policy_unbind(struct stp_policy *policy)
 static void stp_policy_release(struct config_item *item)
 {
 	struct stp_policy *policy = to_stp_policy(item);
+	struct stm_device *stm = policy->stm;
 
+	/* a policy *can* be unbound and still exist in configfs tree */
+	if (!stm)
+		return;
+
+	mutex_lock(&stm->policy_mutex);
 	stp_policy_unbind(policy);
+	mutex_unlock(&stm->policy_mutex);
+
 	kfree(policy);
 }
 
@@ -320,10 +332,11 @@ stp_policies_make(struct config_group *group, const char *name)
 
 	/*
 	 * node must look like <device_name>.<policy_name>, where
-	 * <device_name> is the name of an existing stm device and
-	 * <policy_name> is an arbitrary string
+	 * <device_name> is the name of an existing stm device; may
+	 *               contain dots;
+	 * <policy_name> is an arbitrary string; may not contain dots
 	 */
-	p = strchr(devname, '.');
+	p = strrchr(devname, '.');
 	if (!p) {
 		kfree(devname);
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/hwtracing/stm/stm.h b/drivers/hwtracing/stm/stm.h
index 95ece0292..4e8c69262 100644
--- a/drivers/hwtracing/stm/stm.h
+++ b/drivers/hwtracing/stm/stm.h
@@ -45,6 +45,7 @@ struct stm_device {
 	int			major;
 	unsigned int		sw_nmasters;
 	struct stm_data		*data;
+	struct mutex		link_mutex;
 	spinlock_t		link_lock;
 	struct list_head	link_list;
 	/* master allocation */
@@ -56,6 +57,7 @@ struct stm_device {
 	container_of((_d), struct stm_device, dev)
 
 struct stm_output {
+	spinlock_t		lock;
 	unsigned int		master;
 	unsigned int		channel;
 	unsigned int		nr_chans;