Merge remote-tracking branch 'coresight/next'

19 files changed, 850 insertions, 446 deletions

diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt
index 5d1ad09bafb4..f39d2c6eb49c 100644
--- a/Documentation/devicetree/bindings/arm/coresight.txt
+++ b/Documentation/devicetree/bindings/arm/coresight.txt
@@ -54,9 +54,7 @@ its hardware characteristcs.
 	  clocks the core of that coresight component. The latter clock
 	  is optional.
 
-	* port or ports: The representation of the component's port
-	  layout using the generic DT graph presentation found in
-	  "bindings/graph.txt".
+	* port or ports: see "Graph bindings for Coresight" below.
 
 * Additional required properties for System Trace Macrocells (STM):
 	* reg: along with the physical base address and length of the register
@@ -73,7 +71,7 @@ its hardware characteristcs.
 	  AMBA markee):
 		- "arm,coresight-replicator"
 
-	* port or ports: same as above.
+	* port or ports: see "Graph bindings for Coresight" below.
 
 * Optional properties for ETM/PTMs:
 
@@ -96,6 +94,20 @@ its hardware characteristcs.
 	* interrupts : Exactly one SPI may be listed for reporting the address
 	  error
 
+Graph bindings for Coresight
+-------------------------------
+
+Coresight components are interconnected to create a data path for the flow of
+trace data generated from the "sources" to their collection points "sink".
+Each coresight component must describe the "input" and "output" connections.
+The connections must be described via generic DT graph bindings as described
+by the "bindings/graph.txt", where each "port" along with an "endpoint"
+component represents a hardware port and the connection.
+
+ * All output ports must be listed inside a child node named "out-ports"
+ * All input ports must be listed inside a child node named "in-ports".
+ * Port address must match the hardware port number.
+
 Example:
 
 1. Sinks
@@ -105,10 +117,11 @@ Example:
 
 		clocks = <&oscclk6a>;
 		clock-names = "apb_pclk";
-		port {
-			etb_in_port: endpoint@0 {
-				slave-mode;
-				remote-endpoint = <&replicator_out_port0>;
+		in-ports {
+			port {
+				etb_in_port: endpoint@0 {
+					remote-endpoint = <&replicator_out_port0>;
+				};
 			};
 		};
 	};
@@ -119,10 +132,11 @@ Example:
 
 		clocks = <&oscclk6a>;
 		clock-names = "apb_pclk";
-		port {
-			tpiu_in_port: endpoint@0 {
-				slave-mode;
-				remote-endpoint = <&replicator_out_port1>;
+		out-ports {
+			port {
+				tpiu_in_port: endpoint@0 {
+					remote-endpoint = <&replicator_out_port1>;
+				};
 			};
 		};
 	};
@@ -163,7 +177,7 @@ Example:
 		 */
 		compatible = "arm,coresight-replicator";
 
-		ports {
+		out-ports {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
@@ -181,12 +195,11 @@ Example:
 					remote-endpoint = <&tpiu_in_port>;
 				};
 			};
+		};
 
-			/* replicator input port */
-			port@2 {
-				reg = <0>;
+		in-ports {
+			port {
 				replicator_in_port0: endpoint {
-					slave-mode;
 					remote-endpoint = <&funnel_out_port0>;
 				};
 			};
@@ -199,40 +212,36 @@ Example:
 
 		clocks = <&oscclk6a>;
 		clock-names = "apb_pclk";
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			/* funnel output port */
-			port@0 {
-				reg = <0>;
+		out-ports {
+			port {
 				funnel_out_port0: endpoint {
 					remote-endpoint =
 							<&replicator_in_port0>;
 				};
 			};
+		};
 
-			/* funnel input ports */
-			port@1 {
+		in-ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
 				reg = <0>;
 				funnel_in_port0: endpoint {
-					slave-mode;
 					remote-endpoint = <&ptm0_out_port>;
 				};
 			};
 
-			port@2 {
+			port@1 {
 				reg = <1>;
 				funnel_in_port1: endpoint {
-					slave-mode;
 					remote-endpoint = <&ptm1_out_port>;
 				};
 			};
 
-			port@3 {
+			port@2 {
 				reg = <2>;
 				funnel_in_port2: endpoint {
-					slave-mode;
 					remote-endpoint = <&etm0_out_port>;
 				};
 			};
@@ -248,9 +257,11 @@ Example:
 		cpu = <&cpu0>;
 		clocks = <&oscclk6a>;
 		clock-names = "apb_pclk";
-		port {
-			ptm0_out_port: endpoint {
-				remote-endpoint = <&funnel_in_port0>;
+		out-ports {
+			port {
+				ptm0_out_port: endpoint {
+					remote-endpoint = <&funnel_in_port0>;
+				};
 			};
 		};
 	};
@@ -262,9 +273,11 @@ Example:
 		cpu = <&cpu1>;
 		clocks = <&oscclk6a>;
 		clock-names = "apb_pclk";
-		port {
-			ptm1_out_port: endpoint {
-				remote-endpoint = <&funnel_in_port1>;
+		out-ports {
+			port {
+				ptm1_out_port: endpoint {
+					remote-endpoint = <&funnel_in_port1>;
+				};
 			};
 		};
 	};
@@ -278,9 +291,11 @@ Example:
 
 		clocks = <&soc_smc50mhz>;
 		clock-names = "apb_pclk";
-		port {
-			stm_out_port: endpoint {
-				remote-endpoint = <&main_funnel_in_port2>;
+		out-ports {
+			port {
+				stm_out_port: endpoint {
+					remote-endpoint = <&main_funnel_in_port2>;
+				};
 			};
 		};
 	};
diff --git a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
index f6d0571ab9dd..ebb80438f6a5 100644
--- a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
@@ -56,7 +56,7 @@ static int replicator_enable(struct coresight_device *csdev, int inport,
 
 	CS_LOCK(drvdata->base);
 
-	dev_info(drvdata->dev, "REPLICATOR enabled\n");
+	dev_dbg(drvdata->dev, "REPLICATOR enabled\n");
 	return 0;
 }
 
@@ -75,7 +75,7 @@ static void replicator_disable(struct coresight_device *csdev, int inport,
 
 	CS_LOCK(drvdata->base);
 
-	dev_info(drvdata->dev, "REPLICATOR disabled\n");
+	dev_dbg(drvdata->dev, "REPLICATOR disabled\n");
 }
 
 static const struct coresight_ops_link replicator_link_ops = {
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index 306119eaf16a..08fa660098f8 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -5,7 +5,6 @@
  * Description: CoreSight Embedded Trace Buffer driver
  */
 
-#include <asm/local.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/types.h>
@@ -28,6 +27,7 @@
 
 
 #include "coresight-priv.h"
+#include "coresight-etm-perf.h"
 
 #define ETB_RAM_DEPTH_REG	0x004
 #define ETB_STATUS_REG		0x00c
@@ -71,8 +71,8 @@
  * @miscdev:	specifics to handle "/dev/xyz.etb" entry.
  * @spinlock:	only one at a time pls.
  * @reading:	synchronise user space access to etb buffer.
- * @mode:	this ETB is being used.
  * @buf:	area of memory where ETB buffer content gets sent.
+ * @mode:	this ETB is being used.
  * @buffer_depth: size of @buf.
  * @trigger_cntr: amount of words to store after a trigger.
  */
@@ -84,12 +84,15 @@ struct etb_drvdata {
 	struct miscdevice	miscdev;
 	spinlock_t		spinlock;
 	local_t			reading;
-	local_t			mode;
 	u8			*buf;
+	u32			mode;
 	u32			buffer_depth;
 	u32			trigger_cntr;
 };
 
+static int etb_set_buffer(struct coresight_device *csdev,
+			  struct perf_output_handle *handle);
+
 static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata)
 {
 	u32 depth = 0;
@@ -131,32 +134,84 @@ static void etb_enable_hw(struct etb_drvdata *drvdata)
 	CS_LOCK(drvdata->base);
 }
 
-static int etb_enable(struct coresight_device *csdev, u32 mode)
+static int etb_enable_sysfs(struct coresight_device *csdev)
 {
-	u32 val;
+	int ret = 0;
 	unsigned long flags;
 	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	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;
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	/* Don't messup with perf sessions. */
+	if (drvdata->mode == CS_MODE_PERF) {
+		ret = -EBUSY;
+		goto out;
+	}
 
 	/* Nothing to do, the tracer is already enabled. */
-	if (val == CS_MODE_SYSFS)
+	if (drvdata->mode == CS_MODE_SYSFS)
 		goto out;
 
-	spin_lock_irqsave(&drvdata->spinlock, flags);
+	drvdata->mode = CS_MODE_SYSFS;
 	etb_enable_hw(drvdata);
+
+out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	return ret;
+}
+
+static int etb_enable_perf(struct coresight_device *csdev, void *data)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	/* No need to continue if the component is already in use. */
+	if (drvdata->mode != CS_MODE_DISABLED) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/*
+	 * We don't have an internal state to clean up if we fail to setup
+	 * the perf buffer. So we can perform the step before we turn the
+	 * ETB on and leave without cleaning up.
+	 */
+	ret = etb_set_buffer(csdev, (struct perf_output_handle *)data);
+	if (ret)
+		goto out;
+
+	drvdata->mode = CS_MODE_PERF;
+	etb_enable_hw(drvdata);
 
 out:
-	dev_info(drvdata->dev, "ETB enabled\n");
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	return ret;
+}
+
+static int etb_enable(struct coresight_device *csdev, u32 mode, void *data)
+{
+	int ret;
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	switch (mode) {
+	case CS_MODE_SYSFS:
+		ret = etb_enable_sysfs(csdev);
+		break;
+	case CS_MODE_PERF:
+		ret = etb_enable_perf(csdev, data);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	if (ret)
+		return ret;
+
+	dev_dbg(drvdata->dev, "ETB enabled\n");
 	return 0;
 }
 
@@ -256,13 +311,16 @@ static void etb_disable(struct coresight_device *csdev)
 	unsigned long flags;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	etb_disable_hw(drvdata);
-	etb_dump_hw(drvdata);
-	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	local_set(&drvdata->mode, CS_MODE_DISABLED);
+	/* Disable the ETB only if it needs to */
+	if (drvdata->mode != CS_MODE_DISABLED) {
+		etb_disable_hw(drvdata);
+		etb_dump_hw(drvdata);
+		drvdata->mode = CS_MODE_DISABLED;
+	}
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_info(drvdata->dev, "ETB disabled\n");
+	dev_dbg(drvdata->dev, "ETB disabled\n");
 }
 
 static void *etb_alloc_buffer(struct coresight_device *csdev, int cpu,
@@ -294,12 +352,14 @@ static void etb_free_buffer(void *config)
 }
 
 static int etb_set_buffer(struct coresight_device *csdev,
-			  struct perf_output_handle *handle,
-			  void *sink_config)
+			  struct perf_output_handle *handle)
 {
 	int ret = 0;
 	unsigned long head;
-	struct cs_buffers *buf = sink_config;
+	struct cs_buffers *buf = etm_perf_sink_config(handle);
+
+	if (!buf)
+		return -EINVAL;
 
 	/* wrap head around to the amount of space we have */
 	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
@@ -315,37 +375,7 @@ static int etb_set_buffer(struct coresight_device *csdev,
 	return ret;
 }
 
-static unsigned long etb_reset_buffer(struct coresight_device *csdev,
-				      struct perf_output_handle *handle,
-				      void *sink_config)
-{
-	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.
-		 */
-		size = local_xchg(&buf->data_size, 0);
-	}
-
-	return size;
-}
-
-static void etb_update_buffer(struct coresight_device *csdev,
+static unsigned long etb_update_buffer(struct coresight_device *csdev,
 			      struct perf_output_handle *handle,
 			      void *sink_config)
 {
@@ -354,13 +384,13 @@ static void etb_update_buffer(struct coresight_device *csdev,
 	u8 *buf_ptr;
 	const u32 *barrier;
 	u32 read_ptr, write_ptr, capacity;
-	u32 status, read_data, to_read;
-	unsigned long offset;
+	u32 status, read_data;
+	unsigned long offset, to_read;
 	struct cs_buffers *buf = sink_config;
 	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	if (!buf)
-		return;
+		return 0;
 
 	capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS;
 
@@ -465,18 +495,17 @@ static void etb_update_buffer(struct coresight_device *csdev,
 	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.
+	 * In snapshot mode we have to update the handle->head to point
+	 * to the new location.
 	 */
-	if (buf->snapshot)
-		local_set(&buf->data_size, (cur * PAGE_SIZE) + offset);
-	else
-		local_add(to_read, &buf->data_size);
-
+	if (buf->snapshot) {
+		handle->head = (cur * PAGE_SIZE) + offset;
+		to_read = buf->nr_pages << PAGE_SHIFT;
+	}
 	etb_enable_hw(drvdata);
 	CS_LOCK(drvdata->base);
+
+	return to_read;
 }
 
 static const struct coresight_ops_sink etb_sink_ops = {
@@ -484,8 +513,6 @@ static const struct coresight_ops_sink etb_sink_ops = {
 	.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,
 };
 
@@ -498,14 +525,14 @@ static void etb_dump(struct etb_drvdata *drvdata)
 	unsigned long flags;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	if (local_read(&drvdata->mode) == CS_MODE_SYSFS) {
+	if (drvdata->mode == CS_MODE_SYSFS) {
 		etb_disable_hw(drvdata);
 		etb_dump_hw(drvdata);
 		etb_enable_hw(drvdata);
 	}
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_info(drvdata->dev, "ETB dumped\n");
+	dev_dbg(drvdata->dev, "ETB dumped\n");
 }
 
 static int etb_open(struct inode *inode, struct file *file)
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 677695635211..abe8249b893b 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/perf_event.h>
+#include <linux/percpu-defs.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
@@ -22,20 +23,6 @@
 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);
 
@@ -61,6 +48,18 @@ static const struct attribute_group *etm_pmu_attr_groups[] = {
 	NULL,
 };
 
+static inline struct list_head **
+etm_event_cpu_path_ptr(struct etm_event_data *data, int cpu)
+{
+	return per_cpu_ptr(data->path, cpu);
+}
+
+static inline struct list_head *
+etm_event_cpu_path(struct etm_event_data *data, int cpu)
+{
+	return *etm_event_cpu_path_ptr(data, cpu);
+}
+
 static void etm_event_read(struct perf_event *event) {}
 
 static int etm_addr_filters_alloc(struct perf_event *event)
@@ -114,29 +113,30 @@ static void free_event_data(struct work_struct *work)
 
 	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) {
+
+	/* Free the sink buffers, if there are any */
+	if (event_data->snk_config && !WARN_ON(cpumask_empty(mask))) {
 		cpu = cpumask_first(mask);
-		sink = coresight_get_sink(event_data->path[cpu]);
+		sink = coresight_get_sink(etm_event_cpu_path(event_data, cpu));
 		if (sink_ops(sink)->free_buffer)
 			sink_ops(sink)->free_buffer(event_data->snk_config);
 	}
 
 	for_each_cpu(cpu, mask) {
-		if (!(IS_ERR_OR_NULL(event_data->path[cpu])))
-			coresight_release_path(event_data->path[cpu]);
+		struct list_head **ppath;
+
+		ppath = etm_event_cpu_path_ptr(event_data, cpu);
+		if (!(IS_ERR_OR_NULL(*ppath)))
+			coresight_release_path(*ppath);
+		*ppath = NULL;
 	}
 
-	kfree(event_data->path);
+	free_percpu(event_data->path);
 	kfree(event_data);
 }
 
 static void *alloc_event_data(int cpu)
 {
-	int size;
 	cpumask_t *mask;
 	struct etm_event_data *event_data;
 
@@ -145,16 +145,12 @@ static void *alloc_event_data(int cpu)
 	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();
+		cpumask_copy(mask, cpu_present_mask);
 
 	/*
 	 * Each CPU has a single path between source and destination.  As such
@@ -164,8 +160,8 @@ static void *alloc_event_data(int cpu)
 	 * 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);
+	event_data->path = alloc_percpu(struct list_head *);
+
 	if (!event_data->path) {
 		kfree(event_data);
 		return NULL;
@@ -206,34 +202,53 @@ static void *etm_setup_aux(int event_cpu, void **pages,
 	 * on the cmd line.  As such the "enable_sink" flag in sysFS is reset.
 	 */
 	sink = coresight_get_enabled_sink(true);
-	if (!sink)
+	if (!sink || !sink_ops(sink)->alloc_buffer)
 		goto err;
 
 	mask = &event_data->mask;
 
-	/* Setup the path for each CPU in a trace session */
+	/*
+	 * Setup the path for each CPU in a trace session. We try to build
+	 * trace path for each CPU in the mask. If we don't find an ETM
+	 * for the CPU or fail to build a path, we clear the CPU from the
+	 * mask and continue with the rest. If ever we try to trace on those
+	 * CPUs, we can handle it and fail the session.
+	 */
 	for_each_cpu(cpu, mask) {
+		struct list_head *path;
 		struct coresight_device *csdev;
 
 		csdev = per_cpu(csdev_src, cpu);
-		if (!csdev)
-			goto err;
+		/*
+		 * If there is no ETM associated with this CPU clear it from
+		 * the mask and continue with the rest. If ever we try to trace
+		 * on this CPU, we handle it accordingly.
+		 */
+		if (!csdev) {
+			cpumask_clear_cpu(cpu, mask);
+			continue;
+		}
 
 		/*
 		 * 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, sink);
-		if (IS_ERR(event_data->path[cpu]))
-			goto err;
+		path = coresight_build_path(csdev, sink);
+		if (IS_ERR(path)) {
+			cpumask_clear_cpu(cpu, mask);
+			continue;
+		}
+
+		*etm_event_cpu_path_ptr(event_data, cpu) = path;
 	}
 
-	if (!sink_ops(sink)->alloc_buffer)
+	/* If we don't have any CPUs ready for tracing, abort */
+	cpu = cpumask_first(mask);
+	if (cpu >= nr_cpu_ids)
 		goto err;
 
-	cpu = cpumask_first(mask);
-	/* Get the AUX specific data from the sink buffer */
+	/* Allocate the sink buffer for this session */
 	event_data->snk_config =
 			sink_ops(sink)->alloc_buffer(sink, cpu, pages,
 						     nr_pages, overwrite);
@@ -255,6 +270,7 @@ static void etm_event_start(struct perf_event *event, int flags)
 	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);
+	struct list_head *path;
 
 	if (!csdev)
 		goto fail;
@@ -267,18 +283,14 @@ static void etm_event_start(struct perf_event *event, int flags)
 	if (!event_data)
 		goto fail;
 
+	path = etm_event_cpu_path(event_data, cpu);
 	/* 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))
+	sink = coresight_get_sink(path);
+	if (WARN_ON_ONCE(!sink))
 		goto fail_end_stop;
 
 	/* Nothing will happen without a path */
-	if (coresight_enable_path(event_data->path[cpu], CS_MODE_PERF))
+	if (coresight_enable_path(path, CS_MODE_PERF, handle))
 		goto fail_end_stop;
 
 	/* Tell the perf core the event is alive */
@@ -286,11 +298,13 @@ static void etm_event_start(struct perf_event *event, int flags)
 
 	/* Finally enable the tracer */
 	if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF))
-		goto fail_end_stop;
+		goto fail_disable_path;
 
 out:
 	return;
 
+fail_disable_path:
+	coresight_disable_path(path);
 fail_end_stop:
 	perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	perf_aux_output_end(handle, 0);
@@ -306,6 +320,7 @@ static void etm_event_stop(struct perf_event *event, int mode)
 	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);
+	struct list_head *path;
 
 	if (event->hw.state == PERF_HES_STOPPED)
 		return;
@@ -313,7 +328,11 @@ static void etm_event_stop(struct perf_event *event, int mode)
 	if (!csdev)
 		return;
 
-	sink = coresight_get_sink(event_data->path[cpu]);
+	path = etm_event_cpu_path(event_data, cpu);
+	if (!path)
+		return;
+
+	sink = coresight_get_sink(path);
 	if (!sink)
 		return;
 
@@ -331,20 +350,13 @@ static void etm_event_stop(struct perf_event *event, int mode)
 		if (!sink_ops(sink)->update_buffer)
 			return;
 
-		sink_ops(sink)->update_buffer(sink, handle,
+		size = 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);
-
 		perf_aux_output_end(handle, size);
 	}
 
 	/* Disabling the path make its elements available to other sessions */
-	coresight_disable_path(event_data->path[cpu]);
+	coresight_disable_path(path);
 }
 
 static int etm_event_add(struct perf_event *event, int mode)
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h
index 4197df4faf5e..da7d9336a15c 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.h
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.h
@@ -7,6 +7,7 @@
 #ifndef _CORESIGHT_ETM_PERF_H
 #define _CORESIGHT_ETM_PERF_H
 
+#include <linux/percpu-defs.h>
 #include "coresight-priv.h"
 
 struct coresight_device;
@@ -42,14 +43,39 @@ struct etm_filters {
 	bool			ssstatus;
 };
 
+/**
+ * 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 * __percpu *path;
+};
 
 #ifdef CONFIG_CORESIGHT
 int etm_perf_symlink(struct coresight_device *csdev, bool link);
+static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
+{
+	struct etm_event_data *data = perf_get_aux(handle);
 
+	if (data)
+		return data->snk_config;
+	return NULL;
+}
 #else
 static inline int etm_perf_symlink(struct coresight_device *csdev, bool link)
 { return -EINVAL; }
 
+static inline void *etm_perf_sink_config(struct perf_output_handle *handle)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_CORESIGHT */
 
 #endif
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index 7c74263c333d..9ce8fba20b0f 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -501,7 +501,7 @@ static int etm_enable_sysfs(struct coresight_device *csdev)
 	drvdata->sticky_enable = true;
 	spin_unlock(&drvdata->spinlock);
 
-	dev_info(drvdata->dev, "ETM tracing enabled\n");
+	dev_dbg(drvdata->dev, "ETM tracing enabled\n");
 	return 0;
 
 err:
@@ -604,7 +604,7 @@ static void etm_disable_sysfs(struct coresight_device *csdev)
 	spin_unlock(&drvdata->spinlock);
 	cpus_read_unlock();
 
-	dev_info(drvdata->dev, "ETM tracing disabled\n");
+	dev_dbg(drvdata->dev, "ETM tracing disabled\n");
 }
 
 static void etm_disable(struct coresight_device *csdev,
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 1d94ebec027b..b7379e9cfb30 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -28,6 +28,7 @@
 #include <linux/pm_runtime.h>
 #include <asm/sections.h>
 #include <asm/local.h>
+#include <asm/virt.h>
 
 #include "coresight-etm4x.h"
 #include "coresight-etm-perf.h"
@@ -267,7 +268,7 @@ static int etm4_enable_sysfs(struct coresight_device *csdev)
 	drvdata->sticky_enable = true;
 	spin_unlock(&drvdata->spinlock);
 
-	dev_info(drvdata->dev, "ETM tracing enabled\n");
+	dev_dbg(drvdata->dev, "ETM tracing enabled\n");
 	return 0;
 
 err:
@@ -380,7 +381,7 @@ static void etm4_disable_sysfs(struct coresight_device *csdev)
 	spin_unlock(&drvdata->spinlock);
 	cpus_read_unlock();
 
-	dev_info(drvdata->dev, "ETM tracing disabled\n");
+	dev_dbg(drvdata->dev, "ETM tracing disabled\n");
 }
 
 static void etm4_disable(struct coresight_device *csdev,
@@ -605,7 +606,7 @@ static void etm4_set_default_config(struct etmv4_config *config)
 	config->vinst_ctrl |= BIT(0);
 }
 
-static u64 etm4_get_access_type(struct etmv4_config *config)
+static u64 etm4_get_ns_access_type(struct etmv4_config *config)
 {
 	u64 access_type = 0;
 
@@ -616,17 +617,26 @@ static u64 etm4_get_access_type(struct etmv4_config *config)
 	 *   Bit[13] Exception level 1 - OS
 	 *   Bit[14] Exception level 2 - Hypervisor
 	 *   Bit[15] Never implemented
-	 *
-	 * Always stay away from hypervisor mode.
 	 */
-	access_type = ETM_EXLEVEL_NS_HYP;
-
-	if (config->mode & ETM_MODE_EXCL_KERN)
-		access_type |= ETM_EXLEVEL_NS_OS;
+	if (!is_kernel_in_hyp_mode()) {
+		/* Stay away from hypervisor mode for non-VHE */
+		access_type =  ETM_EXLEVEL_NS_HYP;
+		if (config->mode & ETM_MODE_EXCL_KERN)
+			access_type |= ETM_EXLEVEL_NS_OS;
+	} else if (config->mode & ETM_MODE_EXCL_KERN) {
+		access_type = ETM_EXLEVEL_NS_HYP;
+	}
 
 	if (config->mode & ETM_MODE_EXCL_USER)
 		access_type |= ETM_EXLEVEL_NS_APP;
 
+	return access_type;
+}
+
+static u64 etm4_get_access_type(struct etmv4_config *config)
+{
+	u64 access_type = etm4_get_ns_access_type(config);
+
 	/*
 	 * EXLEVEL_S, bits[11:8], don't trace anything happening
 	 * in secure state.
@@ -880,20 +890,10 @@ void etm4_config_trace_mode(struct etmv4_config *config)
 
 	addr_acc = config->addr_acc[ETM_DEFAULT_ADDR_COMP];
 	/* clear default config */
-	addr_acc &= ~(ETM_EXLEVEL_NS_APP | ETM_EXLEVEL_NS_OS);
+	addr_acc &= ~(ETM_EXLEVEL_NS_APP | ETM_EXLEVEL_NS_OS |
+		      ETM_EXLEVEL_NS_HYP);
 
-	/*
-	 * EXLEVEL_NS, bits[15:12]
-	 * The Exception levels are:
-	 *   Bit[12] Exception level 0 - Application
-	 *   Bit[13] Exception level 1 - OS
-	 *   Bit[14] Exception level 2 - Hypervisor
-	 *   Bit[15] Never implemented
-	 */
-	if (mode & ETM_MODE_EXCL_KERN)
-		addr_acc |= ETM_EXLEVEL_NS_OS;
-	else
-		addr_acc |= ETM_EXLEVEL_NS_APP;
+	addr_acc |= etm4_get_ns_access_type(config);
 
 	config->addr_acc[ETM_DEFAULT_ADDR_COMP] = addr_acc;
 	config->addr_acc[ETM_DEFAULT_ADDR_COMP + 1] = addr_acc;
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 448145a36675..ee7a30bf9480 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -65,7 +65,7 @@ static int funnel_enable(struct coresight_device *csdev, int inport,
 
 	funnel_enable_hw(drvdata, inport);
 
-	dev_info(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
+	dev_dbg(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
 	return 0;
 }
 
@@ -89,7 +89,7 @@ static void funnel_disable(struct coresight_device *csdev, int inport,
 
 	funnel_disable_hw(drvdata, inport);
 
-	dev_info(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
+	dev_dbg(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
 }
 
 static const struct coresight_ops_link funnel_link_ops = {
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 1a6cf3589866..c11da5564a67 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -137,7 +137,7 @@ static inline void coresight_write_reg_pair(void __iomem *addr, u64 val,
 }
 
 void coresight_disable_path(struct list_head *path);
-int coresight_enable_path(struct list_head *path, u32 mode);
+int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data);
 struct coresight_device *coresight_get_sink(struct list_head *path);
 struct coresight_device *coresight_get_enabled_sink(bool reset);
 struct list_head *coresight_build_path(struct coresight_device *csdev,
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index 8d2eaaab6c2f..feac98315471 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -35,7 +35,7 @@ static int replicator_enable(struct coresight_device *csdev, int inport,
 {
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	dev_info(drvdata->dev, "REPLICATOR enabled\n");
+	dev_dbg(drvdata->dev, "REPLICATOR enabled\n");
 	return 0;
 }
 
@@ -44,7 +44,7 @@ static void replicator_disable(struct coresight_device *csdev, int inport,
 {
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	dev_info(drvdata->dev, "REPLICATOR disabled\n");
+	dev_dbg(drvdata->dev, "REPLICATOR disabled\n");
 }
 
 static const struct coresight_ops_link replicator_link_ops = {
diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c
index c46c70aec1d5..35d6f9709274 100644
--- a/drivers/hwtracing/coresight/coresight-stm.c
+++ b/drivers/hwtracing/coresight/coresight-stm.c
@@ -211,7 +211,7 @@ static int stm_enable(struct coresight_device *csdev,
 	stm_enable_hw(drvdata);
 	spin_unlock(&drvdata->spinlock);
 
-	dev_info(drvdata->dev, "STM tracing enabled\n");
+	dev_dbg(drvdata->dev, "STM tracing enabled\n");
 	return 0;
 }
 
@@ -274,7 +274,7 @@ static void stm_disable(struct coresight_device *csdev,
 		pm_runtime_put(drvdata->dev);
 
 		local_set(&drvdata->mode, CS_MODE_DISABLED);
-		dev_info(drvdata->dev, "STM tracing disabled\n");
+		dev_dbg(drvdata->dev, "STM tracing disabled\n");
 	}
 }
 
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 0549249f4b39..4bf3bfd7c078 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -10,6 +10,10 @@
 #include <linux/slab.h>
 #include "coresight-priv.h"
 #include "coresight-tmc.h"
+#include "coresight-etm-perf.h"
+
+static int tmc_set_etf_buffer(struct coresight_device *csdev,
+			      struct perf_output_handle *handle);
 
 static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata)
 {
@@ -34,23 +38,20 @@ static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata)
 {
 	char *bufp;
 	u32 read_data, lost;
-	int i;
 
 	/* Check if the buffer wrapped around. */
 	lost = readl_relaxed(drvdata->base + TMC_STS) & TMC_STS_FULL;
 	bufp = drvdata->buf;
 	drvdata->len = 0;
 	while (1) {
-		for (i = 0; i < drvdata->memwidth; i++) {
-			read_data = readl_relaxed(drvdata->base + TMC_RRD);
-			if (read_data == 0xFFFFFFFF)
-				goto done;
-			memcpy(bufp, &read_data, 4);
-			bufp += 4;
-			drvdata->len += 4;
-		}
+		read_data = readl_relaxed(drvdata->base + TMC_RRD);
+		if (read_data == 0xFFFFFFFF)
+			break;
+		memcpy(bufp, &read_data, 4);
+		bufp += 4;
+		drvdata->len += 4;
 	}
-done:
+
 	if (lost)
 		coresight_insert_barrier_packet(drvdata->buf);
 	return;
@@ -182,11 +183,12 @@ out:
 	return ret;
 }
 
-static int tmc_enable_etf_sink_perf(struct coresight_device *csdev)
+static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data)
 {
 	int ret = 0;
 	unsigned long flags;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	struct perf_output_handle *handle = data;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 	if (drvdata->reading) {
@@ -204,15 +206,19 @@ static int tmc_enable_etf_sink_perf(struct coresight_device *csdev)
 		goto out;
 	}
 
-	drvdata->mode = CS_MODE_PERF;
-	tmc_etb_enable_hw(drvdata);
+	ret = tmc_set_etf_buffer(csdev, handle);
+	if (!ret) {
+		drvdata->mode = CS_MODE_PERF;
+		tmc_etb_enable_hw(drvdata);
+	}
 out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	return ret;
 }
 
-static int tmc_enable_etf_sink(struct coresight_device *csdev, u32 mode)
+static int tmc_enable_etf_sink(struct coresight_device *csdev,
+			       u32 mode, void *data)
 {
 	int ret;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
@@ -222,7 +228,7 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev, u32 mode)
 		ret = tmc_enable_etf_sink_sysfs(csdev);
 		break;
 	case CS_MODE_PERF:
-		ret = tmc_enable_etf_sink_perf(csdev);
+		ret = tmc_enable_etf_sink_perf(csdev, data);
 		break;
 	/* We shouldn't be here */
 	default:
@@ -233,7 +239,7 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev, u32 mode)
 	if (ret)
 		return ret;
 
-	dev_info(drvdata->dev, "TMC-ETB/ETF enabled\n");
+	dev_dbg(drvdata->dev, "TMC-ETB/ETF enabled\n");
 	return 0;
 }
 
@@ -256,7 +262,7 @@ static void tmc_disable_etf_sink(struct coresight_device *csdev)
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_info(drvdata->dev, "TMC-ETB/ETF disabled\n");
+	dev_dbg(drvdata->dev, "TMC-ETB/ETF disabled\n");
 }
 
 static int tmc_enable_etf_link(struct coresight_device *csdev,
@@ -275,7 +281,7 @@ static int tmc_enable_etf_link(struct coresight_device *csdev,
 	drvdata->mode = CS_MODE_SYSFS;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_info(drvdata->dev, "TMC-ETF enabled\n");
+	dev_dbg(drvdata->dev, "TMC-ETF enabled\n");
 	return 0;
 }
 
@@ -295,7 +301,7 @@ static void tmc_disable_etf_link(struct coresight_device *csdev,
 	drvdata->mode = CS_MODE_DISABLED;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_info(drvdata->dev, "TMC-ETF disabled\n");
+	dev_dbg(drvdata->dev, "TMC-ETF disabled\n");
 }
 
 static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, int cpu,
@@ -328,12 +334,14 @@ static void tmc_free_etf_buffer(void *config)
 }
 
 static int tmc_set_etf_buffer(struct coresight_device *csdev,
-			      struct perf_output_handle *handle,
-			      void *sink_config)
+			      struct perf_output_handle *handle)
 {
 	int ret = 0;
 	unsigned long head;
-	struct cs_buffers *buf = sink_config;
+	struct cs_buffers *buf = etm_perf_sink_config(handle);
+
+	if (!buf)
+		return -EINVAL;
 
 	/* wrap head around to the amount of space we have */
 	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
@@ -349,36 +357,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev,
 	return ret;
 }
 
-static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
-					  struct perf_output_handle *handle,
-					  void *sink_config)
-{
-	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.
-		 */
-		size = local_xchg(&buf->data_size, 0);
-	}
-
-	return size;
-}
-
-static void tmc_update_etf_buffer(struct coresight_device *csdev,
+static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 				  struct perf_output_handle *handle,
 				  void *sink_config)
 {
@@ -387,17 +366,17 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 	const u32 *barrier;
 	u32 *buf_ptr;
 	u64 read_ptr, write_ptr;
-	u32 status, to_read;
-	unsigned long offset;
+	u32 status;
+	unsigned long offset, to_read;
 	struct cs_buffers *buf = sink_config;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	if (!buf)
-		return;
+		return 0;
 
 	/* This shouldn't happen */
 	if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF))
-		return;
+		return 0;
 
 	CS_UNLOCK(drvdata->base);
 
@@ -486,18 +465,14 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
 		}
 	}
 
-	/*
-	 * 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);
-
+	/* In snapshot mode we have to update the head */
+	if (buf->snapshot) {
+		handle->head = (cur * PAGE_SIZE) + offset;
+		to_read = buf->nr_pages << PAGE_SHIFT;
+	}
 	CS_LOCK(drvdata->base);
+
+	return to_read;
 }
 
 static const struct coresight_ops_sink tmc_etf_sink_ops = {
@@ -505,8 +480,6 @@ static const struct coresight_ops_sink tmc_etf_sink_ops = {
 	.disable	= tmc_disable_etf_sink,
 	.alloc_buffer	= tmc_alloc_etf_buffer,
 	.free_buffer	= tmc_free_etf_buffer,
-	.set_buffer	= tmc_set_etf_buffer,
-	.reset_buffer	= tmc_reset_etf_buffer,
 	.update_buffer	= tmc_update_etf_buffer,
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index 2eda5de304c2..56fea4ff947e 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include "coresight-catu.h"
+#include "coresight-etm-perf.h"
 #include "coresight-priv.h"
 #include "coresight-tmc.h"
 
@@ -21,6 +22,28 @@ struct etr_flat_buf {
 };
 
 /*
+ * etr_perf_buffer - Perf buffer used for ETR
+ * @etr_buf		- Actual buffer used by the ETR
+ * @snaphost		- Perf session mode
+ * @head		- handle->head at the beginning of the session.
+ * @nr_pages		- Number of pages in the ring buffer.
+ * @pages		- Array of Pages in the ring buffer.
+ */
+struct etr_perf_buffer {
+	struct etr_buf		*etr_buf;
+	bool			snapshot;
+	unsigned long		head;
+	int			nr_pages;
+	void			**pages;
+};
+
+/* Convert the perf index to an offset within the ETR buffer */
+#define PERF_IDX2OFF(idx, buf)	((idx) % ((buf)->nr_pages << PAGE_SHIFT))
+
+/* Lower limit for ETR hardware buffer */
+#define TMC_ETR_PERF_MIN_BUF_SIZE	SZ_1M
+
+/*
  * The TMC ETR SG has a page size of 4K. The SG table contains pointers
  * to 4KB buffers. However, the OS may use a PAGE_SIZE different from
  * 4K (i.e, 16KB or 64KB). This implies that a single OS page could
@@ -536,7 +559,7 @@ tmc_init_etr_sg_table(struct device *dev, int node,
 	sg_table = tmc_alloc_sg_table(dev, node, nr_tpages, nr_dpages, pages);
 	if (IS_ERR(sg_table)) {
 		kfree(etr_table);
-		return ERR_PTR(PTR_ERR(sg_table));
+		return ERR_CAST(sg_table);
 	}
 
 	etr_table->sg_table = sg_table;
@@ -895,10 +918,15 @@ static void tmc_sync_etr_buf(struct tmc_drvdata *drvdata)
 		tmc_etr_buf_insert_barrier_packet(etr_buf, etr_buf->offset);
 }
 
-static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
+static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata,
+			      struct etr_buf *etr_buf)
 {
 	u32 axictl, sts;
-	struct etr_buf *etr_buf = drvdata->etr_buf;
+
+	/* Callers should provide an appropriate buffer for use */
+	if (WARN_ON(!etr_buf || drvdata->etr_buf))
+		return;
+	drvdata->etr_buf = etr_buf;
 
 	/*
 	 * If this ETR is connected to a CATU, enable it before we turn
@@ -960,13 +988,16 @@ static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
  * also updating the @bufpp on where to find it. Since the trace data
  * starts at anywhere in the buffer, depending on the RRP, we adjust the
  * @len returned to handle buffer wrapping around.
+ *
+ * We are protected here by drvdata->reading != 0, which ensures the
+ * sysfs_buf stays alive.
  */
 ssize_t tmc_etr_get_sysfs_trace(struct tmc_drvdata *drvdata,
 				loff_t pos, size_t len, char **bufpp)
 {
 	s64 offset;
 	ssize_t actual = len;
-	struct etr_buf *etr_buf = drvdata->etr_buf;
+	struct etr_buf *etr_buf = drvdata->sysfs_buf;
 
 	if (pos + actual > etr_buf->len)
 		actual = etr_buf->len - pos;
@@ -996,7 +1027,14 @@ tmc_etr_free_sysfs_buf(struct etr_buf *buf)
 
 static void tmc_etr_sync_sysfs_buf(struct tmc_drvdata *drvdata)
 {
-	tmc_sync_etr_buf(drvdata);
+	struct etr_buf *etr_buf = drvdata->etr_buf;
+
+	if (WARN_ON(drvdata->sysfs_buf != etr_buf)) {
+		tmc_etr_free_sysfs_buf(drvdata->sysfs_buf);
+		drvdata->sysfs_buf = NULL;
+	} else {
+		tmc_sync_etr_buf(drvdata);
+	}
 }
 
 static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
@@ -1017,6 +1055,8 @@ static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
 
 	/* Disable CATU device if this ETR is connected to one */
 	tmc_etr_disable_catu(drvdata);
+	/* Reset the ETR buf used by hardware */
+	drvdata->etr_buf = NULL;
 }
 
 static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
@@ -1024,7 +1064,7 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
 	int ret = 0;
 	unsigned long flags;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
-	struct etr_buf *new_buf = NULL, *free_buf = NULL;
+	struct etr_buf *sysfs_buf = NULL, *new_buf = NULL, *free_buf = NULL;
 
 	/*
 	 * If we are enabling the ETR from disabled state, we need to make
@@ -1035,7 +1075,8 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
 	 * with the lock released.
 	 */
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	if (!drvdata->etr_buf || (drvdata->etr_buf->size != drvdata->size)) {
+	sysfs_buf = READ_ONCE(drvdata->sysfs_buf);
+	if (!sysfs_buf || (sysfs_buf->size != drvdata->size)) {
 		spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 		/* Allocate memory with the locks released */
@@ -1064,14 +1105,14 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
 	 * If we don't have a buffer or it doesn't match the requested size,
 	 * use the buffer allocated above. Otherwise reuse the existing buffer.
 	 */
-	if (!drvdata->etr_buf ||
-	    (new_buf && drvdata->etr_buf->size != new_buf->size)) {
-		free_buf = drvdata->etr_buf;
-		drvdata->etr_buf = new_buf;
+	sysfs_buf = READ_ONCE(drvdata->sysfs_buf);
+	if (!sysfs_buf || (new_buf && sysfs_buf->size != new_buf->size)) {
+		free_buf = sysfs_buf;
+		drvdata->sysfs_buf = new_buf;
 	}
 
 	drvdata->mode = CS_MODE_SYSFS;
-	tmc_etr_enable_hw(drvdata);
+	tmc_etr_enable_hw(drvdata, drvdata->sysfs_buf);
 out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
@@ -1080,24 +1121,243 @@ out:
 		tmc_etr_free_sysfs_buf(free_buf);
 
 	if (!ret)
-		dev_info(drvdata->dev, "TMC-ETR enabled\n");
+		dev_dbg(drvdata->dev, "TMC-ETR enabled\n");
 
 	return ret;
 }
 
-static int tmc_enable_etr_sink_perf(struct coresight_device *csdev)
+/*
+ * tmc_etr_setup_perf_buf: Allocate ETR buffer for use by perf.
+ * The size of the hardware buffer is dependent on the size configured
+ * via sysfs and the perf ring buffer size. We prefer to allocate the
+ * largest possible size, scaling down the size by half until it
+ * reaches a minimum limit (1M), beyond which we give up.
+ */
+static struct etr_perf_buffer *
+tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, int node, int nr_pages,
+		       void **pages, bool snapshot)
 {
-	/* We don't support perf mode yet ! */
-	return -EINVAL;
+	struct etr_buf *etr_buf;
+	struct etr_perf_buffer *etr_perf;
+	unsigned long size;
+
+	etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node);
+	if (!etr_perf)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Try to match the perf ring buffer size if it is larger
+	 * than the size requested via sysfs.
+	 */
+	if ((nr_pages << PAGE_SHIFT) > drvdata->size) {
+		etr_buf = tmc_alloc_etr_buf(drvdata, (nr_pages << PAGE_SHIFT),
+					    0, node, NULL);
+		if (!IS_ERR(etr_buf))
+			goto done;
+	}
+
+	/*
+	 * Else switch to configured size for this ETR
+	 * and scale down until we hit the minimum limit.
+	 */
+	size = drvdata->size;
+	do {
+		etr_buf = tmc_alloc_etr_buf(drvdata, size, 0, node, NULL);
+		if (!IS_ERR(etr_buf))
+			goto done;
+		size /= 2;
+	} while (size >= TMC_ETR_PERF_MIN_BUF_SIZE);
+
+	kfree(etr_perf);
+	return ERR_PTR(-ENOMEM);
+
+done:
+	etr_perf->etr_buf = etr_buf;
+	return etr_perf;
+}
+
+
+static void *tmc_alloc_etr_buffer(struct coresight_device *csdev,
+				  int cpu, void **pages, int nr_pages,
+				  bool snapshot)
+{
+	struct etr_perf_buffer *etr_perf;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	if (cpu == -1)
+		cpu = smp_processor_id();
+
+	etr_perf = tmc_etr_setup_perf_buf(drvdata, cpu_to_node(cpu),
+					  nr_pages, pages, snapshot);
+	if (IS_ERR(etr_perf)) {
+		dev_dbg(drvdata->dev, "Unable to allocate ETR buffer\n");
+		return NULL;
+	}
+
+	etr_perf->snapshot = snapshot;
+	etr_perf->nr_pages = nr_pages;
+	etr_perf->pages = pages;
+
+	return etr_perf;
+}
+
+static void tmc_free_etr_buffer(void *config)
+{
+	struct etr_perf_buffer *etr_perf = config;
+
+	if (etr_perf->etr_buf)
+		tmc_free_etr_buf(etr_perf->etr_buf);
+	kfree(etr_perf);
+}
+
+/*
+ * tmc_etr_sync_perf_buffer: Copy the actual trace data from the hardware
+ * buffer to the perf ring buffer.
+ */
+static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf)
+{
+	long bytes, to_copy;
+	long pg_idx, pg_offset, src_offset;
+	unsigned long head = etr_perf->head;
+	char **dst_pages, *src_buf;
+	struct etr_buf *etr_buf = etr_perf->etr_buf;
+
+	head = etr_perf->head;
+	pg_idx = head >> PAGE_SHIFT;
+	pg_offset = head & (PAGE_SIZE - 1);
+	dst_pages = (char **)etr_perf->pages;
+	src_offset = etr_buf->offset;
+	to_copy = etr_buf->len;
+
+	while (to_copy > 0) {
+		/*
+		 * In one iteration, we can copy minimum of :
+		 *  1) what is available in the source buffer,
+		 *  2) what is available in the source buffer, before it
+		 *     wraps around.
+		 *  3) what is available in the destination page.
+		 * in one iteration.
+		 */
+		bytes = tmc_etr_buf_get_data(etr_buf, src_offset, to_copy,
+					     &src_buf);
+		if (WARN_ON_ONCE(bytes <= 0))
+			break;
+		bytes = min(bytes, (long)(PAGE_SIZE - pg_offset));
+
+		memcpy(dst_pages[pg_idx] + pg_offset, src_buf, bytes);
+
+		to_copy -= bytes;
+
+		/* Move destination pointers */
+		pg_offset += bytes;
+		if (pg_offset == PAGE_SIZE) {
+			pg_offset = 0;
+			if (++pg_idx == etr_perf->nr_pages)
+				pg_idx = 0;
+		}
+
+		/* Move source pointers */
+		src_offset += bytes;
+		if (src_offset >= etr_buf->size)
+			src_offset -= etr_buf->size;
+	}
+}
+
+/*
+ * tmc_update_etr_buffer : Update the perf ring buffer with the
+ * available trace data. We use software double buffering at the moment.
+ *
+ * TODO: Add support for reusing the perf ring buffer.
+ */
+static unsigned long
+tmc_update_etr_buffer(struct coresight_device *csdev,
+		      struct perf_output_handle *handle,
+		      void *config)
+{
+	bool lost = false;
+	unsigned long flags, size = 0;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	struct etr_perf_buffer *etr_perf = config;
+	struct etr_buf *etr_buf = etr_perf->etr_buf;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (WARN_ON(drvdata->perf_data != etr_perf)) {
+		lost = true;
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		goto out;
+	}
+
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_sync_etr_buf(drvdata);
+
+	CS_LOCK(drvdata->base);
+	/* Reset perf specific data */
+	drvdata->perf_data = NULL;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	size = etr_buf->len;
+	tmc_etr_sync_perf_buffer(etr_perf);
+
+	/*
+	 * Update handle->head in snapshot mode. Also update the size to the
+	 * hardware buffer size if there was an overflow.
+	 */
+	if (etr_perf->snapshot) {
+		handle->head += size;
+		if (etr_buf->full)
+			size = etr_buf->size;
+	}
+
+	lost |= etr_buf->full;
+out:
+	if (lost)
+		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+	return size;
 }
 
-static int tmc_enable_etr_sink(struct coresight_device *csdev, u32 mode)
+static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data)
+{
+	int rc = 0;
+	unsigned long flags;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	struct perf_output_handle *handle = data;
+	struct etr_perf_buffer *etr_perf = etm_perf_sink_config(handle);
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	/*
+	 * There can be only one writer per sink in perf mode. If the sink
+	 * is already open in SYSFS mode, we can't use it.
+	 */
+	if (drvdata->mode != CS_MODE_DISABLED || WARN_ON(drvdata->perf_data)) {
+		rc = -EBUSY;
+		goto unlock_out;
+	}
+
+	if (WARN_ON(!etr_perf || !etr_perf->etr_buf)) {
+		rc = -EINVAL;
+		goto unlock_out;
+	}
+
+	etr_perf->head = PERF_IDX2OFF(handle->head, etr_perf);
+	drvdata->perf_data = etr_perf;
+	drvdata->mode = CS_MODE_PERF;
+	tmc_etr_enable_hw(drvdata, etr_perf->etr_buf);
+
+unlock_out:
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	return rc;
+}
+
+static int tmc_enable_etr_sink(struct coresight_device *csdev,
+			       u32 mode, void *data)
 {
 	switch (mode) {
 	case CS_MODE_SYSFS:
 		return tmc_enable_etr_sink_sysfs(csdev);
 	case CS_MODE_PERF:
-		return tmc_enable_etr_sink_perf(csdev);
+		return tmc_enable_etr_sink_perf(csdev, data);
 	}
 
 	/* We shouldn't be here */
@@ -1123,12 +1383,15 @@ static void tmc_disable_etr_sink(struct coresight_device *csdev)
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_info(drvdata->dev, "TMC-ETR disabled\n");
+	dev_dbg(drvdata->dev, "TMC-ETR disabled\n");
 }
 
 static const struct coresight_ops_sink tmc_etr_sink_ops = {
 	.enable		= tmc_enable_etr_sink,
 	.disable	= tmc_disable_etr_sink,
+	.alloc_buffer	= tmc_alloc_etr_buffer,
+	.update_buffer	= tmc_update_etr_buffer,
+	.free_buffer	= tmc_free_etr_buffer,
 };
 
 const struct coresight_ops tmc_etr_cs_ops = {
@@ -1150,19 +1413,17 @@ int tmc_read_prepare_etr(struct tmc_drvdata *drvdata)
 		goto out;
 	}
 
-	/* Don't interfere if operated from Perf */
-	if (drvdata->mode == CS_MODE_PERF) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* If drvdata::etr_buf is NULL the trace data has been read already */
-	if (drvdata->etr_buf == NULL) {
+	/*
+	 * We can safely allow reads even if the ETR is operating in PERF mode,
+	 * since the sysfs session is captured in mode specific data.
+	 * If drvdata::sysfs_data is NULL the trace data has been read already.
+	 */
+	if (!drvdata->sysfs_buf) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	/* Disable the TMC if need be */
+	/* Disable the TMC if we are trying to read from a running session. */
 	if (drvdata->mode == CS_MODE_SYSFS)
 		tmc_etr_disable_hw(drvdata);
 
@@ -1176,7 +1437,7 @@ out:
 int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
 {
 	unsigned long flags;
-	struct etr_buf *etr_buf = NULL;
+	struct etr_buf *sysfs_buf = NULL;
 
 	/* config types are set a boot time and never change */
 	if (WARN_ON_ONCE(drvdata->config_type != TMC_CONFIG_TYPE_ETR))
@@ -1191,22 +1452,22 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata)
 		 * buffer. Since the tracer is still enabled drvdata::buf can't
 		 * be NULL.
 		 */
-		tmc_etr_enable_hw(drvdata);
+		tmc_etr_enable_hw(drvdata, drvdata->sysfs_buf);
 	} else {
 		/*
 		 * The ETR is not tracing and the buffer was just read.
 		 * As such prepare to free the trace buffer.
 		 */
-		etr_buf =  drvdata->etr_buf;
-		drvdata->etr_buf = NULL;
+		sysfs_buf = drvdata->sysfs_buf;
+		drvdata->sysfs_buf = NULL;
 	}
 
 	drvdata->reading = false;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	/* Free allocated memory out side of the spinlock */
-	if (etr_buf)
-		tmc_free_etr_buf(etr_buf);
+	if (sysfs_buf)
+		tmc_etr_free_sysfs_buf(sysfs_buf);
 
 	return 0;
 }
diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c
index 1b817ec1192c..ea249f0bcd73 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.c
+++ b/drivers/hwtracing/coresight/coresight-tmc.c
@@ -81,7 +81,7 @@ static int tmc_read_prepare(struct tmc_drvdata *drvdata)
 	}
 
 	if (!ret)
-		dev_info(drvdata->dev, "TMC read start\n");
+		dev_dbg(drvdata->dev, "TMC read start\n");
 
 	return ret;
 }
@@ -103,7 +103,7 @@ static int tmc_read_unprepare(struct tmc_drvdata *drvdata)
 	}
 
 	if (!ret)
-		dev_info(drvdata->dev, "TMC read end\n");
+		dev_dbg(drvdata->dev, "TMC read end\n");
 
 	return ret;
 }
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index 7027bd60c4cc..487c53701e9c 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -170,6 +170,8 @@ struct etr_buf {
  * @trigger_cntr: amount of words to store after a trigger.
  * @etr_caps:	Bitmask of capabilities of the TMC ETR, inferred from the
  *		device configuration register (DEVID)
+ * @perf_data:	PERF buffer for ETR.
+ * @sysfs_data:	SYSFS buffer for ETR.
  */
 struct tmc_drvdata {
 	void __iomem		*base;
@@ -189,6 +191,8 @@ struct tmc_drvdata {
 	enum tmc_mem_intf_width	memwidth;
 	u32			trigger_cntr;
 	u32			etr_caps;
+	struct etr_buf		*sysfs_buf;
+	void			*perf_data;
 };
 
 struct etr_buf_operations {
diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
index 459ef930d98c..b2f72a1fa402 100644
--- a/drivers/hwtracing/coresight/coresight-tpiu.c
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -68,13 +68,13 @@ static void tpiu_enable_hw(struct tpiu_drvdata *drvdata)
 	CS_LOCK(drvdata->base);
 }
 
-static int tpiu_enable(struct coresight_device *csdev, u32 mode)
+static int tpiu_enable(struct coresight_device *csdev, u32 mode, void *__unused)
 {
 	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	tpiu_enable_hw(drvdata);
 
-	dev_info(drvdata->dev, "TPIU enabled\n");
+	dev_dbg(drvdata->dev, "TPIU enabled\n");
 	return 0;
 }
 
@@ -100,7 +100,7 @@ static void tpiu_disable(struct coresight_device *csdev)
 
 	tpiu_disable_hw(drvdata);
 
-	dev_info(drvdata->dev, "TPIU disabled\n");
+	dev_dbg(drvdata->dev, "TPIU disabled\n");
 }
 
 static const struct coresight_ops_sink tpiu_sink_ops = {
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 3e07fd335f8c..e73ca6af4765 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -128,16 +128,19 @@ static int coresight_find_link_outport(struct coresight_device *csdev,
 	return -ENODEV;
 }
 
-static int coresight_enable_sink(struct coresight_device *csdev, u32 mode)
+static int coresight_enable_sink(struct coresight_device *csdev,
+				 u32 mode, void *data)
 {
 	int ret;
 
-	if (!csdev->enable) {
-		if (sink_ops(csdev)->enable) {
-			ret = sink_ops(csdev)->enable(csdev, mode);
-			if (ret)
-				return ret;
-		}
+	/*
+	 * We need to make sure the "new" session is compatible with the
+	 * existing "mode" of operation.
+	 */
+	if (sink_ops(csdev)->enable) {
+		ret = sink_ops(csdev)->enable(csdev, mode, data);
+		if (ret)
+			return ret;
 		csdev->enable = true;
 	}
 
@@ -313,7 +316,7 @@ void coresight_disable_path(struct list_head *path)
 	}
 }
 
-int coresight_enable_path(struct list_head *path, u32 mode)
+int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data)
 {
 
 	int ret = 0;
@@ -338,9 +341,15 @@ int coresight_enable_path(struct list_head *path, u32 mode)
 
 		switch (type) {
 		case CORESIGHT_DEV_TYPE_SINK:
-			ret = coresight_enable_sink(csdev, mode);
+			ret = coresight_enable_sink(csdev, mode, sink_data);
+			/*
+			 * Sink is the first component turned on. If we
+			 * failed to enable the sink, there are no components
+			 * that need disabling. Disabling the path here
+			 * would mean we could disrupt an existing session.
+			 */
 			if (ret)
-				goto err;
+				goto out;
 			break;
 		case CORESIGHT_DEV_TYPE_SOURCE:
 			/* sources are enabled from either sysFS or Perf */
@@ -635,7 +644,7 @@ int coresight_enable(struct coresight_device *csdev)
 		goto out;
 	}
 
-	ret = coresight_enable_path(path, CS_MODE_SYSFS);
+	ret = coresight_enable_path(path, CS_MODE_SYSFS, NULL);
 	if (ret)
 		goto err_path;
 
@@ -995,18 +1004,16 @@ postcore_initcall(coresight_init);
 
 struct coresight_device *coresight_register(struct coresight_desc *desc)
 {
-	int i;
 	int ret;
 	int link_subtype;
 	int nr_refcnts = 1;
 	atomic_t *refcnts = NULL;
 	struct coresight_device *csdev;
-	struct coresight_connection *conns = NULL;
 
 	csdev = kzalloc(sizeof(*csdev), GFP_KERNEL);
 	if (!csdev) {
 		ret = -ENOMEM;
-		goto err_kzalloc_csdev;
+		goto err_out;
 	}
 
 	if (desc->type == CORESIGHT_DEV_TYPE_LINK ||
@@ -1022,7 +1029,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 	refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL);
 	if (!refcnts) {
 		ret = -ENOMEM;
-		goto err_kzalloc_refcnts;
+		goto err_free_csdev;
 	}
 
 	csdev->refcnt = refcnts;
@@ -1030,22 +1037,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 	csdev->nr_inport = desc->pdata->nr_inport;
 	csdev->nr_outport = desc->pdata->nr_outport;
 
-	/* Initialise connections if there is at least one outport */
-	if (csdev->nr_outport) {
-		conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL);
-		if (!conns) {
-			ret = -ENOMEM;
-			goto err_kzalloc_conns;
-		}
-
-		for (i = 0; i < csdev->nr_outport; i++) {
-			conns[i].outport = desc->pdata->outports[i];
-			conns[i].child_name = desc->pdata->child_names[i];
-			conns[i].child_port = desc->pdata->child_ports[i];
-		}
-	}
-
-	csdev->conns = conns;
+	csdev->conns = desc->pdata->conns;
 
 	csdev->type = desc->type;
 	csdev->subtype = desc->subtype;
@@ -1062,7 +1054,11 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 	ret = device_register(&csdev->dev);
 	if (ret) {
 		put_device(&csdev->dev);
-		goto err_kzalloc_csdev;
+		/*
+		 * All resources are free'd explicitly via
+		 * coresight_device_release(), triggered from put_device().
+		 */
+		goto err_out;
 	}
 
 	mutex_lock(&coresight_mutex);
@@ -1074,11 +1070,9 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 
 	return csdev;
 
-err_kzalloc_conns:
-	kfree(refcnts);
-err_kzalloc_refcnts:
+err_free_csdev:
 	kfree(csdev);
-err_kzalloc_csdev:
+err_out:
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(coresight_register);
diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c
index 6880bee195c8..da71c975e3f7 100644
--- a/drivers/hwtracing/coresight/of_coresight.c
+++ b/drivers/hwtracing/coresight/of_coresight.c
@@ -45,8 +45,13 @@ of_coresight_get_endpoint_device(struct device_node *endpoint)
 			       endpoint, of_dev_node_match);
 }
 
-static void of_coresight_get_ports(const struct device_node *node,
-				   int *nr_inport, int *nr_outport)
+static inline bool of_coresight_legacy_ep_is_input(struct device_node *ep)
+{
+	return of_property_read_bool(ep, "slave-mode");
+}
+
+static void of_coresight_get_ports_legacy(const struct device_node *node,
+					  int *nr_inport, int *nr_outport)
 {
 	struct device_node *ep = NULL;
 	int in = 0, out = 0;
@@ -56,7 +61,7 @@ static void of_coresight_get_ports(const struct device_node *node,
 		if (!ep)
 			break;
 
-		if (of_property_read_bool(ep, "slave-mode"))
+		if (of_coresight_legacy_ep_is_input(ep))
 			in++;
 		else
 			out++;
@@ -67,32 +72,77 @@ static void of_coresight_get_ports(const struct device_node *node,
 	*nr_outport = out;
 }
 
+static struct device_node *of_coresight_get_port_parent(struct device_node *ep)
+{
+	struct device_node *parent = of_graph_get_port_parent(ep);
+
+	/*
+	 * Skip one-level up to the real device node, if we
+	 * are using the new bindings.
+	 */
+	if (!of_node_cmp(parent->name, "in-ports") ||
+	    !of_node_cmp(parent->name, "out-ports"))
+		parent = of_get_next_parent(parent);
+
+	return parent;
+}
+
+static inline struct device_node *
+of_coresight_get_input_ports_node(const struct device_node *node)
+{
+	return of_get_child_by_name(node, "in-ports");
+}
+
+static inline struct device_node *
+of_coresight_get_output_ports_node(const struct device_node *node)
+{
+	return of_get_child_by_name(node, "out-ports");
+}
+
+static inline int
+of_coresight_count_ports(struct device_node *port_parent)
+{
+	int i = 0;
+	struct device_node *ep = NULL;
+
+	while ((ep = of_graph_get_next_endpoint(port_parent, ep)))
+		i++;
+	return i;
+}
+
+static void of_coresight_get_ports(const struct device_node *node,
+				   int *nr_inport, int *nr_outport)
+{
+	struct device_node *input_ports = NULL, *output_ports = NULL;
+
+	input_ports = of_coresight_get_input_ports_node(node);
+	output_ports = of_coresight_get_output_ports_node(node);
+
+	if (input_ports || output_ports) {
+		if (input_ports) {
+			*nr_inport = of_coresight_count_ports(input_ports);
+			of_node_put(input_ports);
+		}
+		if (output_ports) {
+			*nr_outport = of_coresight_count_ports(output_ports);
+			of_node_put(output_ports);
+		}
+	} else {
+		/* Fall back to legacy DT bindings parsing */
+		of_coresight_get_ports_legacy(node, nr_inport, nr_outport);
+	}
+}
+
 static int of_coresight_alloc_memory(struct device *dev,
 			struct coresight_platform_data *pdata)
 {
-	/* List of output port on this component */
-	pdata->outports = devm_kcalloc(dev,
-				       pdata->nr_outport,
-				       sizeof(*pdata->outports),
-				       GFP_KERNEL);
-	if (!pdata->outports)
-		return -ENOMEM;
-
-	/* Children connected to this component via @outports */
-	pdata->child_names = devm_kcalloc(dev,
-					  pdata->nr_outport,
-					  sizeof(*pdata->child_names),
-					  GFP_KERNEL);
-	if (!pdata->child_names)
-		return -ENOMEM;
-
-	/* Port number on the child this component is connected to */
-	pdata->child_ports = devm_kcalloc(dev,
-					  pdata->nr_outport,
-					  sizeof(*pdata->child_ports),
-					  GFP_KERNEL);
-	if (!pdata->child_ports)
-		return -ENOMEM;
+	if (pdata->nr_outport) {
+		pdata->conns = devm_kzalloc(dev, pdata->nr_outport *
+					    sizeof(*pdata->conns),
+					    GFP_KERNEL);
+		if (!pdata->conns)
+			return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -114,17 +164,81 @@ int of_coresight_get_cpu(const struct device_node *node)
 }
 EXPORT_SYMBOL_GPL(of_coresight_get_cpu);
 
+/*
+ * of_coresight_parse_endpoint : Parse the given output endpoint @ep
+ * and fill the connection information in @conn
+ *
+ * Parses the local port, remote device name and the remote port.
+ *
+ * Returns :
+ *	 1	- If the parsing is successful and a connection record
+ *		  was created for an output connection.
+ *	 0	- If the parsing completed without any fatal errors.
+ *	-Errno	- Fatal error, abort the scanning.
+ */
+static int of_coresight_parse_endpoint(struct device *dev,
+				       struct device_node *ep,
+				       struct coresight_connection *conn)
+{
+	int ret = 0;
+	struct of_endpoint endpoint, rendpoint;
+	struct device_node *rparent = NULL;
+	struct device_node *rep = NULL;
+	struct device *rdev = NULL;
+
+	do {
+		/* Parse the local port details */
+		if (of_graph_parse_endpoint(ep, &endpoint))
+			break;
+		/*
+		 * Get a handle on the remote endpoint and the device it is
+		 * attached to.
+		 */
+		rep = of_graph_get_remote_endpoint(ep);
+		if (!rep)
+			break;
+		rparent = of_coresight_get_port_parent(rep);
+		if (!rparent)
+			break;
+		if (of_graph_parse_endpoint(rep, &rendpoint))
+			break;
+
+		/* If the remote device is not available, defer probing */
+		rdev = of_coresight_get_endpoint_device(rparent);
+		if (!rdev) {
+			ret = -EPROBE_DEFER;
+			break;
+		}
+
+		conn->outport = endpoint.port;
+		conn->child_name = devm_kstrdup(dev,
+						dev_name(rdev),
+						GFP_KERNEL);
+		conn->child_port = rendpoint.port;
+		/* Connection record updated */
+		ret = 1;
+	} while (0);
+
+	if (rparent)
+		of_node_put(rparent);
+	if (rep)
+		of_node_put(rep);
+	if (rdev)
+		put_device(rdev);
+
+	return ret;
+}
+
 struct coresight_platform_data *
 of_get_coresight_platform_data(struct device *dev,
 			       const struct device_node *node)
 {
-	int i = 0, ret = 0;
+	int ret = 0;
 	struct coresight_platform_data *pdata;
-	struct of_endpoint endpoint, rendpoint;
-	struct device *rdev;
+	struct coresight_connection *conn;
 	struct device_node *ep = NULL;
-	struct device_node *rparent = NULL;
-	struct device_node *rport = NULL;
+	const struct device_node *parent = NULL;
+	bool legacy_binding = false;
 
 	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
@@ -132,63 +246,54 @@ of_get_coresight_platform_data(struct device *dev,
 
 	/* Use device name as sysfs handle */
 	pdata->name = dev_name(dev);
+	pdata->cpu = of_coresight_get_cpu(node);
 
 	/* Get the number of input and output port for this component */
 	of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
 
-	if (pdata->nr_outport) {
-		ret = of_coresight_alloc_memory(dev, pdata);
-		if (ret)
-			return ERR_PTR(ret);
-
-		/* Iterate through each port to discover topology */
-		do {
-			/* Get a handle on a port */
-			ep = of_graph_get_next_endpoint(node, ep);
-			if (!ep)
-				break;
-
-			/*
-			 * No need to deal with input ports, processing for as
-			 * processing for output ports will deal with them.
-			 */
-			if (of_find_property(ep, "slave-mode", NULL))
-				continue;
-
-			/* Get a handle on the local endpoint */
-			ret = of_graph_parse_endpoint(ep, &endpoint);
-
-			if (ret)
-				continue;
-
-			/* The local out port number */
-			pdata->outports[i] = endpoint.port;
-
-			/*
-			 * Get a handle on the remote port and parent
-			 * attached to it.
-			 */
-			rparent = of_graph_get_remote_port_parent(ep);
-			rport = of_graph_get_remote_port(ep);
-
-			if (!rparent || !rport)
-				continue;
+	/* If there are no output connections, we are done */
+	if (!pdata->nr_outport)
+		return pdata;
 
-			if (of_graph_parse_endpoint(rport, &rendpoint))
-				continue;
+	ret = of_coresight_alloc_memory(dev, pdata);
+	if (ret)
+		return ERR_PTR(ret);
 
-			rdev = of_coresight_get_endpoint_device(rparent);
-			if (!rdev)
-				return ERR_PTR(-EPROBE_DEFER);
-
-			pdata->child_names[i] = dev_name(rdev);
-			pdata->child_ports[i] = rendpoint.id;
-
-			i++;
-		} while (ep);
+	parent = of_coresight_get_output_ports_node(node);
+	/*
+	 * If the DT uses obsoleted bindings, the ports are listed
+	 * under the device and we need to filter out the input
+	 * ports.
+	 */
+	if (!parent) {
+		legacy_binding = true;
+		parent = node;
+		dev_warn_once(dev, "Uses obsolete Coresight DT bindings\n");
 	}
 
-	pdata->cpu = of_coresight_get_cpu(node);
+	conn = pdata->conns;
+
+	/* Iterate through each output port to discover topology */
+	while ((ep = of_graph_get_next_endpoint(parent, ep))) {
+		/*
+		 * Legacy binding mixes input/output ports under the
+		 * same parent. So, skip the input ports if we are dealing
+		 * with legacy binding, as they processed with their
+		 * connected output ports.
+		 */
+		if (legacy_binding && of_coresight_legacy_ep_is_input(ep))
+			continue;
+
+		ret = of_coresight_parse_endpoint(dev, ep, conn);
+		switch (ret) {
+		case 1:
+			conn++;		/* Fall through */
+		case 0:
+			break;
+		default:
+			return ERR_PTR(ret);
+		}
+	}
 
 	return pdata;
 }
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index d828a6efe0b1..53535821dc25 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -94,20 +94,15 @@ union coresight_dev_subtype {
  * @cpu:	the CPU a source belongs to. Only applicable for ETM/PTMs.
  * @name:	name of the component as shown under sysfs.
  * @nr_inport:	number of input ports for this component.
- * @outports:	list of remote endpoint port number.
- * @child_names:name of all child components connected to this device.
- * @child_ports:child component port number the current component is
-		connected  to.
  * @nr_outport:	number of output ports for this component.
+ * @conns:	Array of nr_outport connections from this component
  */
 struct coresight_platform_data {
 	int cpu;
 	const char *name;
 	int nr_inport;
-	int *outports;
-	const char **child_names;
-	int *child_ports;
 	int nr_outport;
+	struct coresight_connection *conns;
 };
 
 /**
@@ -190,23 +185,15 @@ struct coresight_device {
  * @disable:		disables the sink.
  * @alloc_buffer:	initialises perf's ring buffer for trace collection.
  * @free_buffer:	release memory allocated in @get_config.
- * @set_buffer:		initialises buffer mechanic before a trace session.
- * @reset_buffer:	finalises buffer mechanic after a trace session.
  * @update_buffer:	update buffer pointers after a trace session.
  */
 struct coresight_ops_sink {
-	int (*enable)(struct coresight_device *csdev, u32 mode);
+	int (*enable)(struct coresight_device *csdev, u32 mode, void *data);
 	void (*disable)(struct coresight_device *csdev);
 	void *(*alloc_buffer)(struct coresight_device *csdev, int cpu,
 			      void **pages, int nr_pages, bool overwrite);
 	void (*free_buffer)(void *config);
-	int (*set_buffer)(struct coresight_device *csdev,
-			  struct perf_output_handle *handle,
-			  void *sink_config);
-	unsigned long (*reset_buffer)(struct coresight_device *csdev,
-				      struct perf_output_handle *handle,
-				      void *sink_config);
-	void (*update_buffer)(struct coresight_device *csdev,
+	unsigned long (*update_buffer)(struct coresight_device *csdev,
 			      struct perf_output_handle *handle,
 			      void *sink_config);
 };