Merge tag 'char-misc-5.2-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc update part 2 from Greg KH:
 "Here is the "real" big set of char/misc driver patches for 5.2-rc1

  Loads of different driver subsystem stuff in here, all over the places:
   - thunderbolt driver updates
   - habanalabs driver updates
   - nvmem driver updates
   - extcon driver updates
   - intel_th driver updates
   - mei driver updates
   - coresight driver updates
   - soundwire driver cleanups and updates
   - fastrpc driver updates
   - other minor driver updates
   - chardev minor fixups

  Feels like this tree is getting to be a dumping ground of "small
  driver subsystems" these days. Which is fine with me, if it makes
  things easier for those subsystem maintainers.

  All of these have been in linux-next for a while with no reported
  issues"

* tag 'char-misc-5.2-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (255 commits)
  intel_th: msu: Add current window tracking
  intel_th: msu: Add a sysfs attribute to trigger window switch
  intel_th: msu: Correct the block wrap detection
  intel_th: Add switch triggering support
  intel_th: gth: Factor out trace start/stop
  intel_th: msu: Factor out pipeline draining
  intel_th: msu: Switch over to scatterlist
  intel_th: msu: Replace open-coded list_{first,last,next}_entry variants
  intel_th: Only report useful IRQs to subdevices
  intel_th: msu: Start handling IRQs
  intel_th: pci: Use MSI interrupt signalling
  intel_th: Communicate IRQ via resource
  intel_th: Add "rtit" source device
  intel_th: Skip subdevices if their MMIO is missing
  intel_th: Rework resource passing between glue layers and core
  intel_th: SPDX-ify the documentation
  intel_th: msu: Fix single mode with IOMMU
  coresight: funnel: Support static funnel
  dt-bindings: arm: coresight: Unify funnel DT binding
  coresight: replicator: Add new device id for static replicator
  ...

24 files changed, 1459 insertions, 616 deletions

diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig
index ad34380cac49..18e8d03321d6 100644
--- a/drivers/hwtracing/coresight/Kconfig
+++ b/drivers/hwtracing/coresight/Kconfig
@@ -75,20 +75,13 @@ config CORESIGHT_SOURCE_ETM4X
 	bool "CoreSight Embedded Trace Macrocell 4.x driver"
 	depends on ARM64
 	select CORESIGHT_LINKS_AND_SINKS
+	select PID_IN_CONTEXTIDR
 	help
 	  This driver provides support for the ETM4.x tracer module, tracing the
 	  instructions that a processor is executing. This is primarily useful
 	  for instruction level tracing. Depending on the implemented version
 	  data tracing may also be available.
 
-config CORESIGHT_DYNAMIC_REPLICATOR
-	bool "CoreSight Programmable Replicator driver"
-	depends on CORESIGHT_LINKS_AND_SINKS
-	help
-	  This enables support for dynamic CoreSight replicator link driver.
-	  The programmable ATB replicator allows independent filtering of the
-	  trace data based on the traceid.
-
 config CORESIGHT_STM
 	bool "CoreSight System Trace Macrocell driver"
 	depends on (ARM && !(CPU_32v3 || CPU_32v4 || CPU_32v4T)) || ARM64
diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile
index 41870ded51a3..3b435aa42af5 100644
--- a/drivers/hwtracing/coresight/Makefile
+++ b/drivers/hwtracing/coresight/Makefile
@@ -15,7 +15,6 @@ obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o \
 					coresight-etm3x-sysfs.o
 obj-$(CONFIG_CORESIGHT_SOURCE_ETM4X) += coresight-etm4x.o \
 					coresight-etm4x-sysfs.o
-obj-$(CONFIG_CORESIGHT_DYNAMIC_REPLICATOR) += coresight-dynamic-replicator.o
 obj-$(CONFIG_CORESIGHT_STM) += coresight-stm.o
 obj-$(CONFIG_CORESIGHT_CPU_DEBUG) += coresight-cpu-debug.o
 obj-$(CONFIG_CORESIGHT_CATU) += coresight-catu.o
diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c
index 170fbb66bda2..4ea68a3522e9 100644
--- a/drivers/hwtracing/coresight/coresight-catu.c
+++ b/drivers/hwtracing/coresight/coresight-catu.c
@@ -485,12 +485,12 @@ static int catu_disable(struct coresight_device *csdev, void *__unused)
 	return rc;
 }
 
-const struct coresight_ops_helper catu_helper_ops = {
+static const struct coresight_ops_helper catu_helper_ops = {
 	.enable = catu_enable,
 	.disable = catu_disable,
 };
 
-const struct coresight_ops catu_ops = {
+static const struct coresight_ops catu_ops = {
 	.helper_ops = &catu_helper_ops,
 };
 
@@ -557,8 +557,9 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id)
 	drvdata->csdev = coresight_register(&catu_desc);
 	if (IS_ERR(drvdata->csdev))
 		ret = PTR_ERR(drvdata->csdev);
+	else
+		pm_runtime_put(&adev->dev);
 out:
-	pm_runtime_put(&adev->dev);
 	return ret;
 }
 
diff --git a/drivers/hwtracing/coresight/coresight-catu.h b/drivers/hwtracing/coresight/coresight-catu.h
index 1b281f0dcccc..1d2ad183fd92 100644
--- a/drivers/hwtracing/coresight/coresight-catu.h
+++ b/drivers/hwtracing/coresight/coresight-catu.h
@@ -109,11 +109,6 @@ static inline bool coresight_is_catu_device(struct coresight_device *csdev)
 	return true;
 }
 
-#ifdef CONFIG_CORESIGHT_CATU
 extern const struct etr_buf_operations etr_catu_buf_ops;
-#else
-/* Dummy declaration for the CATU ops */
-static const struct etr_buf_operations etr_catu_buf_ops;
-#endif
 
 #endif
diff --git a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
deleted file mode 100644
index 299667b887fc..000000000000
--- a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c
+++ /dev/null
@@ -1,255 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- */
-
-#include <linux/amba/bus.h>
-#include <linux/clk.h>
-#include <linux/coresight.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/pm_runtime.h>
-#include <linux/slab.h>
-
-#include "coresight-priv.h"
-
-#define REPLICATOR_IDFILTER0		0x000
-#define REPLICATOR_IDFILTER1		0x004
-
-/**
- * struct replicator_state - specifics associated to a replicator component
- * @base:	memory mapped base address for this component.
- * @dev:	the device entity associated with this component
- * @atclk:	optional clock for the core parts of the replicator.
- * @csdev:	component vitals needed by the framework
- */
-struct replicator_state {
-	void __iomem		*base;
-	struct device		*dev;
-	struct clk		*atclk;
-	struct coresight_device	*csdev;
-};
-
-/*
- * replicator_reset : Reset the replicator configuration to sane values.
- */
-static void replicator_reset(struct replicator_state *drvdata)
-{
-	CS_UNLOCK(drvdata->base);
-
-	if (!coresight_claim_device_unlocked(drvdata->base)) {
-		writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER0);
-		writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER1);
-		coresight_disclaim_device_unlocked(drvdata->base);
-	}
-
-	CS_LOCK(drvdata->base);
-}
-
-static int replicator_enable(struct coresight_device *csdev, int inport,
-			      int outport)
-{
-	int rc = 0;
-	u32 reg;
-	struct replicator_state *drvdata = dev_get_drvdata(csdev->dev.parent);
-
-	switch (outport) {
-	case 0:
-		reg = REPLICATOR_IDFILTER0;
-		break;
-	case 1:
-		reg = REPLICATOR_IDFILTER1;
-		break;
-	default:
-		WARN_ON(1);
-		return -EINVAL;
-	}
-
-	CS_UNLOCK(drvdata->base);
-
-	if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) &&
-	    (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff))
-		rc = coresight_claim_device_unlocked(drvdata->base);
-
-	/* Ensure that the outport is enabled. */
-	if (!rc) {
-		writel_relaxed(0x00, drvdata->base + reg);
-		dev_dbg(drvdata->dev, "REPLICATOR enabled\n");
-	}
-
-	CS_LOCK(drvdata->base);
-
-	return rc;
-}
-
-static void replicator_disable(struct coresight_device *csdev, int inport,
-				int outport)
-{
-	u32 reg;
-	struct replicator_state *drvdata = dev_get_drvdata(csdev->dev.parent);
-
-	switch (outport) {
-	case 0:
-		reg = REPLICATOR_IDFILTER0;
-		break;
-	case 1:
-		reg = REPLICATOR_IDFILTER1;
-		break;
-	default:
-		WARN_ON(1);
-		return;
-	}
-
-	CS_UNLOCK(drvdata->base);
-
-	/* disable the flow of ATB data through port */
-	writel_relaxed(0xff, drvdata->base + reg);
-
-	if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) &&
-	    (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff))
-		coresight_disclaim_device_unlocked(drvdata->base);
-	CS_LOCK(drvdata->base);
-
-	dev_dbg(drvdata->dev, "REPLICATOR disabled\n");
-}
-
-static const struct coresight_ops_link replicator_link_ops = {
-	.enable		= replicator_enable,
-	.disable	= replicator_disable,
-};
-
-static const struct coresight_ops replicator_cs_ops = {
-	.link_ops	= &replicator_link_ops,
-};
-
-#define coresight_replicator_reg(name, offset) \
-	coresight_simple_reg32(struct replicator_state, name, offset)
-
-coresight_replicator_reg(idfilter0, REPLICATOR_IDFILTER0);
-coresight_replicator_reg(idfilter1, REPLICATOR_IDFILTER1);
-
-static struct attribute *replicator_mgmt_attrs[] = {
-	&dev_attr_idfilter0.attr,
-	&dev_attr_idfilter1.attr,
-	NULL,
-};
-
-static const struct attribute_group replicator_mgmt_group = {
-	.attrs = replicator_mgmt_attrs,
-	.name = "mgmt",
-};
-
-static const struct attribute_group *replicator_groups[] = {
-	&replicator_mgmt_group,
-	NULL,
-};
-
-static int replicator_probe(struct amba_device *adev, const struct amba_id *id)
-{
-	int ret;
-	struct device *dev = &adev->dev;
-	struct resource *res = &adev->res;
-	struct coresight_platform_data *pdata = NULL;
-	struct replicator_state *drvdata;
-	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
-	void __iomem *base;
-
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-		adev->dev.platform_data = pdata;
-	}
-
-	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
-	if (!drvdata)
-		return -ENOMEM;
-
-	drvdata->dev = &adev->dev;
-	drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */
-	if (!IS_ERR(drvdata->atclk)) {
-		ret = clk_prepare_enable(drvdata->atclk);
-		if (ret)
-			return ret;
-	}
-
-	/* Validity for the resource is already checked by the AMBA core */
-	base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(base))
-		return PTR_ERR(base);
-
-	drvdata->base = base;
-	dev_set_drvdata(dev, drvdata);
-	pm_runtime_put(&adev->dev);
-
-	desc.type = CORESIGHT_DEV_TYPE_LINK;
-	desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
-	desc.ops = &replicator_cs_ops;
-	desc.pdata = adev->dev.platform_data;
-	desc.dev = &adev->dev;
-	desc.groups = replicator_groups;
-	drvdata->csdev = coresight_register(&desc);
-
-	if (!IS_ERR(drvdata->csdev)) {
-		replicator_reset(drvdata);
-		return 0;
-	}
-	return PTR_ERR(drvdata->csdev);
-}
-
-#ifdef CONFIG_PM
-static int replicator_runtime_suspend(struct device *dev)
-{
-	struct replicator_state *drvdata = dev_get_drvdata(dev);
-
-	if (drvdata && !IS_ERR(drvdata->atclk))
-		clk_disable_unprepare(drvdata->atclk);
-
-	return 0;
-}
-
-static int replicator_runtime_resume(struct device *dev)
-{
-	struct replicator_state *drvdata = dev_get_drvdata(dev);
-
-	if (drvdata && !IS_ERR(drvdata->atclk))
-		clk_prepare_enable(drvdata->atclk);
-
-	return 0;
-}
-#endif
-
-static const struct dev_pm_ops replicator_dev_pm_ops = {
-	SET_RUNTIME_PM_OPS(replicator_runtime_suspend,
-			   replicator_runtime_resume,
-			   NULL)
-};
-
-static const struct amba_id replicator_ids[] = {
-	{
-		.id     = 0x000bb909,
-		.mask   = 0x000fffff,
-	},
-	{
-		/* Coresight SoC-600 */
-		.id     = 0x000bb9ec,
-		.mask   = 0x000fffff,
-	},
-	{ 0, 0 },
-};
-
-static struct amba_driver replicator_driver = {
-	.drv = {
-		.name	= "coresight-dynamic-replicator",
-		.pm	= &replicator_dev_pm_ops,
-		.suppress_bind_attrs = true,
-	},
-	.probe		= replicator_probe,
-	.id_table	= replicator_ids,
-};
-builtin_amba_driver(replicator_driver);
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index 105782ea64c7..4ee4c80a4354 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -5,6 +5,7 @@
  * Description: CoreSight Embedded Trace Buffer driver
  */
 
+#include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/types.h>
@@ -71,6 +72,8 @@
  * @miscdev:	specifics to handle "/dev/xyz.etb" entry.
  * @spinlock:	only one at a time pls.
  * @reading:	synchronise user space access to etb buffer.
+ * @pid:	Process ID of the process being monitored by the session
+ *		that is using this component.
  * @buf:	area of memory where ETB buffer content gets sent.
  * @mode:	this ETB is being used.
  * @buffer_depth: size of @buf.
@@ -84,6 +87,7 @@ struct etb_drvdata {
 	struct miscdevice	miscdev;
 	spinlock_t		spinlock;
 	local_t			reading;
+	pid_t			pid;
 	u8			*buf;
 	u32			mode;
 	u32			buffer_depth;
@@ -93,17 +97,9 @@ struct etb_drvdata {
 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)
+static inline unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata)
 {
-	u32 depth = 0;
-
-	pm_runtime_get_sync(drvdata->dev);
-
-	/* RO registers don't need locking */
-	depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
-
-	pm_runtime_put(drvdata->dev);
-	return depth;
+	return readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
 }
 
 static void __etb_enable_hw(struct etb_drvdata *drvdata)
@@ -159,14 +155,15 @@ static int etb_enable_sysfs(struct coresight_device *csdev)
 		goto out;
 	}
 
-	/* Nothing to do, the tracer is already enabled. */
-	if (drvdata->mode == CS_MODE_SYSFS)
-		goto out;
+	if (drvdata->mode == CS_MODE_DISABLED) {
+		ret = etb_enable_hw(drvdata);
+		if (ret)
+			goto out;
 
-	ret = etb_enable_hw(drvdata);
-	if (!ret)
 		drvdata->mode = CS_MODE_SYSFS;
+	}
 
+	atomic_inc(csdev->refcnt);
 out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 	return ret;
@@ -175,29 +172,52 @@ out:
 static int etb_enable_perf(struct coresight_device *csdev, void *data)
 {
 	int ret = 0;
+	pid_t pid;
 	unsigned long flags;
 	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	struct perf_output_handle *handle = data;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
-	/* No need to continue if the component is already in use. */
-	if (drvdata->mode != CS_MODE_DISABLED) {
+	/* No need to continue if the component is already in used by sysFS. */
+	if (drvdata->mode == CS_MODE_SYSFS) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* Get a handle on the pid of the process to monitor */
+	pid = task_pid_nr(handle->event->owner);
+
+	if (drvdata->pid != -1 && drvdata->pid != pid) {
 		ret = -EBUSY;
 		goto out;
 	}
 
 	/*
+	 * No HW configuration is needed if the sink is already in
+	 * use for this session.
+	 */
+	if (drvdata->pid == pid) {
+		atomic_inc(csdev->refcnt);
+		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);
+	ret = etb_set_buffer(csdev, handle);
 	if (ret)
 		goto out;
 
 	ret = etb_enable_hw(drvdata);
-	if (!ret)
+	if (!ret) {
+		/* Associate with monitored process. */
+		drvdata->pid = pid;
 		drvdata->mode = CS_MODE_PERF;
+		atomic_inc(csdev->refcnt);
+	}
 
 out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -325,27 +345,35 @@ static void etb_disable_hw(struct etb_drvdata *drvdata)
 	coresight_disclaim_device(drvdata->base);
 }
 
-static void etb_disable(struct coresight_device *csdev)
+static int etb_disable(struct coresight_device *csdev)
 {
 	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 	unsigned long flags;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
-	/* Disable the ETB only if it needs to */
-	if (drvdata->mode != CS_MODE_DISABLED) {
-		etb_disable_hw(drvdata);
-		drvdata->mode = CS_MODE_DISABLED;
+	if (atomic_dec_return(csdev->refcnt)) {
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		return -EBUSY;
 	}
+
+	/* Complain if we (somehow) got out of sync */
+	WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED);
+	etb_disable_hw(drvdata);
+	/* Dissociate from monitored process. */
+	drvdata->pid = -1;
+	drvdata->mode = CS_MODE_DISABLED;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	dev_dbg(drvdata->dev, "ETB disabled\n");
+	return 0;
 }
 
-static void *etb_alloc_buffer(struct coresight_device *csdev, int cpu,
-			      void **pages, int nr_pages, bool overwrite)
+static void *etb_alloc_buffer(struct coresight_device *csdev,
+			      struct perf_event *event, void **pages,
+			      int nr_pages, bool overwrite)
 {
-	int node;
+	int node, cpu = event->cpu;
 	struct cs_buffers *buf;
 
 	if (cpu == -1)
@@ -404,7 +432,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 	const u32 *barrier;
 	u32 read_ptr, write_ptr, capacity;
 	u32 status, read_data;
-	unsigned long offset, to_read;
+	unsigned long offset, to_read = 0, flags;
 	struct cs_buffers *buf = sink_config;
 	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
@@ -413,6 +441,12 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 
 	capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS;
 
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	/* Don't do anything if another tracer is using this sink */
+	if (atomic_read(csdev->refcnt) != 1)
+		goto out;
+
 	__etb_disable_hw(drvdata);
 	CS_UNLOCK(drvdata->base);
 
@@ -523,6 +557,8 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 	}
 	__etb_enable_hw(drvdata);
 	CS_LOCK(drvdata->base);
+out:
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	return to_read;
 }
@@ -720,7 +756,6 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id)
 	spin_lock_init(&drvdata->spinlock);
 
 	drvdata->buffer_depth = etb_get_buffer_depth(drvdata);
-	pm_runtime_put(&adev->dev);
 
 	if (drvdata->buffer_depth & 0x80000000)
 		return -EINVAL;
@@ -730,6 +765,9 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id)
 	if (!drvdata->buf)
 		return -ENOMEM;
 
+	/* This device is not associated with a session */
+	drvdata->pid = -1;
+
 	desc.type = CORESIGHT_DEV_TYPE_SINK;
 	desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 	desc.ops = &etb_cs_ops;
@@ -747,6 +785,7 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id)
 	if (ret)
 		goto err_misc_register;
 
+	pm_runtime_put(&adev->dev);
 	return 0;
 
 err_misc_register:
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 4d5a2b9f9d6a..3c6294432748 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -29,6 +29,7 @@ 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(contextid,	"config:" __stringify(ETM_OPT_CTXTID));
 PMU_FORMAT_ATTR(timestamp,	"config:" __stringify(ETM_OPT_TS));
 PMU_FORMAT_ATTR(retstack,	"config:" __stringify(ETM_OPT_RETSTK));
 /* Sink ID - same for all ETMs */
@@ -36,6 +37,7 @@ PMU_FORMAT_ATTR(sinkid,		"config2:0-31");
 
 static struct attribute *etm_config_formats_attr[] = {
 	&format_attr_cycacc.attr,
+	&format_attr_contextid.attr,
 	&format_attr_timestamp.attr,
 	&format_attr_retstack.attr,
 	&format_attr_sinkid.attr,
@@ -118,23 +120,34 @@ out:
 	return ret;
 }
 
+static void free_sink_buffer(struct etm_event_data *event_data)
+{
+	int cpu;
+	cpumask_t *mask = &event_data->mask;
+	struct coresight_device *sink;
+
+	if (WARN_ON(cpumask_empty(mask)))
+		return;
+
+	if (!event_data->snk_config)
+		return;
+
+	cpu = cpumask_first(mask);
+	sink = coresight_get_sink(etm_event_cpu_path(event_data, cpu));
+	sink_ops(sink)->free_buffer(event_data->snk_config);
+}
+
 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;
 
 	/* 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(etm_event_cpu_path(event_data, cpu));
-		if (sink_ops(sink)->free_buffer)
-			sink_ops(sink)->free_buffer(event_data->snk_config);
-	}
+	free_sink_buffer(event_data);
 
 	for_each_cpu(cpu, mask) {
 		struct list_head **ppath;
@@ -213,7 +226,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
 		sink = coresight_get_enabled_sink(true);
 	}
 
-	if (!sink || !sink_ops(sink)->alloc_buffer)
+	if (!sink)
 		goto err;
 
 	mask = &event_data->mask;
@@ -259,9 +272,12 @@ static void *etm_setup_aux(struct perf_event *event, void **pages,
 	if (cpu >= nr_cpu_ids)
 		goto err;
 
+	if (!sink_ops(sink)->alloc_buffer || !sink_ops(sink)->free_buffer)
+		goto err;
+
 	/* Allocate the sink buffer for this session */
 	event_data->snk_config =
-			sink_ops(sink)->alloc_buffer(sink, cpu, pages,
+			sink_ops(sink)->alloc_buffer(sink, event, pages,
 						     nr_pages, overwrite);
 	if (!event_data->snk_config)
 		goto err;
@@ -566,7 +582,8 @@ static int __init etm_perf_init(void)
 {
 	int ret;
 
-	etm_pmu.capabilities		= PERF_PMU_CAP_EXCLUSIVE;
+	etm_pmu.capabilities		= (PERF_PMU_CAP_EXCLUSIVE |
+					   PERF_PMU_CAP_ITRACE);
 
 	etm_pmu.attr_groups		= etm_pmu_attr_groups;
 	etm_pmu.task_ctx_nr		= perf_sw_context;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 08ce37c9475d..8bb0092c7ec2 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -138,8 +138,11 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 			       drvdata->base + TRCCNTVRn(i));
 	}
 
-	/* Resource selector pair 0 is always implemented and reserved */
-	for (i = 0; i < drvdata->nr_resource * 2; i++)
+	/*
+	 * Resource selector pair 0 is always implemented and reserved.  As
+	 * such start at 2.
+	 */
+	for (i = 2; i < drvdata->nr_resource * 2; i++)
 		writel_relaxed(config->res_ctrl[i],
 			       drvdata->base + TRCRSCTLRn(i));
 
@@ -201,6 +204,91 @@ static void etm4_enable_hw_smp_call(void *info)
 	arg->rc = etm4_enable_hw(arg->drvdata);
 }
 
+/*
+ * The goal of function etm4_config_timestamp_event() is to configure a
+ * counter that will tell the tracer to emit a timestamp packet when it
+ * reaches zero.  This is done in order to get a more fine grained idea
+ * of when instructions are executed so that they can be correlated
+ * with execution on other CPUs.
+ *
+ * To do this the counter itself is configured to self reload and
+ * TRCRSCTLR1 (always true) used to get the counter to decrement.  From
+ * there a resource selector is configured with the counter and the
+ * timestamp control register to use the resource selector to trigger the
+ * event that will insert a timestamp packet in the stream.
+ */
+static int etm4_config_timestamp_event(struct etmv4_drvdata *drvdata)
+{
+	int ctridx, ret = -EINVAL;
+	int counter, rselector;
+	u32 val = 0;
+	struct etmv4_config *config = &drvdata->config;
+
+	/* No point in trying if we don't have at least one counter */
+	if (!drvdata->nr_cntr)
+		goto out;
+
+	/* Find a counter that hasn't been initialised */
+	for (ctridx = 0; ctridx < drvdata->nr_cntr; ctridx++)
+		if (config->cntr_val[ctridx] == 0)
+			break;
+
+	/* All the counters have been configured already, bail out */
+	if (ctridx == drvdata->nr_cntr) {
+		pr_debug("%s: no available counter found\n", __func__);
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	/*
+	 * Searching for an available resource selector to use, starting at
+	 * '2' since every implementation has at least 2 resource selector.
+	 * ETMIDR4 gives the number of resource selector _pairs_,
+	 * hence multiply by 2.
+	 */
+	for (rselector = 2; rselector < drvdata->nr_resource * 2; rselector++)
+		if (!config->res_ctrl[rselector])
+			break;
+
+	if (rselector == drvdata->nr_resource * 2) {
+		pr_debug("%s: no available resource selector found\n",
+			 __func__);
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	/* Remember what counter we used */
+	counter = 1 << ctridx;
+
+	/*
+	 * Initialise original and reload counter value to the smallest
+	 * possible value in order to get as much precision as we can.
+	 */
+	config->cntr_val[ctridx] = 1;
+	config->cntrldvr[ctridx] = 1;
+
+	/* Set the trace counter control register */
+	val =  0x1 << 16	|  /* Bit 16, reload counter automatically */
+	       0x0 << 7		|  /* Select single resource selector */
+	       0x1;		   /* Resource selector 1, i.e always true */
+
+	config->cntr_ctrl[ctridx] = val;
+
+	val = 0x2 << 16		| /* Group 0b0010 - Counter and sequencers */
+	      counter << 0;	  /* Counter to use */
+
+	config->res_ctrl[rselector] = val;
+
+	val = 0x0 << 7		| /* Select single resource selector */
+	      rselector;	  /* Resource selector */
+
+	config->ts_ctrl = val;
+
+	ret = 0;
+out:
+	return ret;
+}
+
 static int etm4_parse_event_config(struct etmv4_drvdata *drvdata,
 				   struct perf_event *event)
 {
@@ -236,9 +324,29 @@ static int etm4_parse_event_config(struct etmv4_drvdata *drvdata,
 		/* TRM: Must program this for cycacc to work */
 		config->ccctlr = ETM_CYC_THRESHOLD_DEFAULT;
 	}
-	if (attr->config & BIT(ETM_OPT_TS))
+	if (attr->config & BIT(ETM_OPT_TS)) {
+		/*
+		 * Configure timestamps to be emitted at regular intervals in
+		 * order to correlate instructions executed on different CPUs
+		 * (CPU-wide trace scenarios).
+		 */
+		ret = etm4_config_timestamp_event(drvdata);
+
+		/*
+		 * No need to go further if timestamp intervals can't
+		 * be configured.
+		 */
+		if (ret)
+			goto out;
+
 		/* bit[11], Global timestamp tracing bit */
 		config->cfg |= BIT(11);
+	}
+
+	if (attr->config & BIT(ETM_OPT_CTXTID))
+		/* bit[6], Context ID tracing bit */
+		config->cfg |= BIT(ETM4_CFG_BIT_CTXTID);
+
 	/* return stack - enable if selected and supported */
 	if ((attr->config & BIT(ETM_OPT_RETSTK)) && drvdata->retstack)
 		/* bit[12], Return stack enable bit */
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 927925151509..16b0c0e1e43a 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -12,6 +12,8 @@
 #include <linux/err.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/coresight.h>
 #include <linux/amba/bus.h>
@@ -43,7 +45,7 @@ struct funnel_drvdata {
 	unsigned long		priority;
 };
 
-static int funnel_enable_hw(struct funnel_drvdata *drvdata, int port)
+static int dynamic_funnel_enable_hw(struct funnel_drvdata *drvdata, int port)
 {
 	u32 functl;
 	int rc = 0;
@@ -71,17 +73,19 @@ done:
 static int funnel_enable(struct coresight_device *csdev, int inport,
 			 int outport)
 {
-	int rc;
+	int rc = 0;
 	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	rc = funnel_enable_hw(drvdata, inport);
+	if (drvdata->base)
+		rc = dynamic_funnel_enable_hw(drvdata, inport);
 
 	if (!rc)
 		dev_dbg(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
 	return rc;
 }
 
-static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport)
+static void dynamic_funnel_disable_hw(struct funnel_drvdata *drvdata,
+				      int inport)
 {
 	u32 functl;
 
@@ -103,7 +107,8 @@ 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);
+	if (drvdata->base)
+		dynamic_funnel_disable_hw(drvdata, inport);
 
 	dev_dbg(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
 }
@@ -177,54 +182,70 @@ static struct attribute *coresight_funnel_attrs[] = {
 };
 ATTRIBUTE_GROUPS(coresight_funnel);
 
-static int funnel_probe(struct amba_device *adev, const struct amba_id *id)
+static int funnel_probe(struct device *dev, struct resource *res)
 {
 	int ret;
 	void __iomem *base;
-	struct device *dev = &adev->dev;
 	struct coresight_platform_data *pdata = NULL;
 	struct funnel_drvdata *drvdata;
-	struct resource *res = &adev->res;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
+	struct device_node *np = dev->of_node;
 
 	if (np) {
 		pdata = of_get_coresight_platform_data(dev, np);
 		if (IS_ERR(pdata))
 			return PTR_ERR(pdata);
-		adev->dev.platform_data = pdata;
+		dev->platform_data = pdata;
 	}
 
+	if (of_device_is_compatible(np, "arm,coresight-funnel"))
+		pr_warn_once("Uses OBSOLETE CoreSight funnel binding\n");
+
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->dev = &adev->dev;
-	drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */
+	drvdata->dev = dev;
+	drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */
 	if (!IS_ERR(drvdata->atclk)) {
 		ret = clk_prepare_enable(drvdata->atclk);
 		if (ret)
 			return ret;
 	}
-	dev_set_drvdata(dev, drvdata);
 
-	/* Validity for the resource is already checked by the AMBA core */
-	base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(base))
-		return PTR_ERR(base);
+	/*
+	 * Map the device base for dynamic-funnel, which has been
+	 * validated by AMBA core.
+	 */
+	if (res) {
+		base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(base)) {
+			ret = PTR_ERR(base);
+			goto out_disable_clk;
+		}
+		drvdata->base = base;
+		desc.groups = coresight_funnel_groups;
+	}
 
-	drvdata->base = base;
-	pm_runtime_put(&adev->dev);
+	dev_set_drvdata(dev, drvdata);
 
 	desc.type = CORESIGHT_DEV_TYPE_LINK;
 	desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG;
 	desc.ops = &funnel_cs_ops;
 	desc.pdata = pdata;
 	desc.dev = dev;
-	desc.groups = coresight_funnel_groups;
 	drvdata->csdev = coresight_register(&desc);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto out_disable_clk;
+	}
+
+	pm_runtime_put(dev);
 
-	return PTR_ERR_OR_ZERO(drvdata->csdev);
+out_disable_clk:
+	if (ret && !IS_ERR_OR_NULL(drvdata->atclk))
+		clk_disable_unprepare(drvdata->atclk);
+	return ret;
 }
 
 #ifdef CONFIG_PM
@@ -253,7 +274,48 @@ static const struct dev_pm_ops funnel_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(funnel_runtime_suspend, funnel_runtime_resume, NULL)
 };
 
-static const struct amba_id funnel_ids[] = {
+static int static_funnel_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	/* Static funnel do not have programming base */
+	ret = funnel_probe(&pdev->dev, NULL);
+
+	if (ret) {
+		pm_runtime_put_noidle(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
+	}
+
+	return ret;
+}
+
+static const struct of_device_id static_funnel_match[] = {
+	{.compatible = "arm,coresight-static-funnel"},
+	{}
+};
+
+static struct platform_driver static_funnel_driver = {
+	.probe          = static_funnel_probe,
+	.driver         = {
+		.name   = "coresight-static-funnel",
+		.of_match_table = static_funnel_match,
+		.pm	= &funnel_dev_pm_ops,
+		.suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver(static_funnel_driver);
+
+static int dynamic_funnel_probe(struct amba_device *adev,
+				const struct amba_id *id)
+{
+	return funnel_probe(&adev->dev, &adev->res);
+}
+
+static const struct amba_id dynamic_funnel_ids[] = {
 	{
 		.id     = 0x000bb908,
 		.mask   = 0x000fffff,
@@ -266,14 +328,14 @@ static const struct amba_id funnel_ids[] = {
 	{ 0, 0},
 };
 
-static struct amba_driver funnel_driver = {
+static struct amba_driver dynamic_funnel_driver = {
 	.drv = {
-		.name	= "coresight-funnel",
+		.name	= "coresight-dynamic-funnel",
 		.owner	= THIS_MODULE,
 		.pm	= &funnel_dev_pm_ops,
 		.suppress_bind_attrs = true,
 	},
-	.probe		= funnel_probe,
-	.id_table	= funnel_ids,
+	.probe		= dynamic_funnel_probe,
+	.id_table	= dynamic_funnel_ids,
 };
-builtin_amba_driver(funnel_driver);
+builtin_amba_driver(dynamic_funnel_driver);
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index feac98315471..8c9ce74498e1 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -1,10 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
  *
  * Description: CoreSight Replicator driver
  */
 
+#include <linux/amba/bus.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
@@ -18,25 +19,117 @@
 
 #include "coresight-priv.h"
 
+#define REPLICATOR_IDFILTER0		0x000
+#define REPLICATOR_IDFILTER1		0x004
+
 /**
  * struct replicator_drvdata - specifics associated to a replicator component
+ * @base:	memory mapped base address for this component. Also indicates
+ *		whether this one is programmable or not.
  * @dev:	the device entity associated with this component
  * @atclk:	optional clock for the core parts of the replicator.
  * @csdev:	component vitals needed by the framework
  */
 struct replicator_drvdata {
+	void __iomem		*base;
 	struct device		*dev;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 };
 
+static void dynamic_replicator_reset(struct replicator_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	if (!coresight_claim_device_unlocked(drvdata->base)) {
+		writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER0);
+		writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER1);
+		coresight_disclaim_device_unlocked(drvdata->base);
+	}
+
+	CS_LOCK(drvdata->base);
+}
+
+/*
+ * replicator_reset : Reset the replicator configuration to sane values.
+ */
+static inline void replicator_reset(struct replicator_drvdata *drvdata)
+{
+	if (drvdata->base)
+		dynamic_replicator_reset(drvdata);
+}
+
+static int dynamic_replicator_enable(struct replicator_drvdata *drvdata,
+				     int inport, int outport)
+{
+	int rc = 0;
+	u32 reg;
+
+	switch (outport) {
+	case 0:
+		reg = REPLICATOR_IDFILTER0;
+		break;
+	case 1:
+		reg = REPLICATOR_IDFILTER1;
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	CS_UNLOCK(drvdata->base);
+
+	if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) &&
+	    (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff))
+		rc = coresight_claim_device_unlocked(drvdata->base);
+
+	/* Ensure that the outport is enabled. */
+	if (!rc)
+		writel_relaxed(0x00, drvdata->base + reg);
+	CS_LOCK(drvdata->base);
+
+	return rc;
+}
+
 static int replicator_enable(struct coresight_device *csdev, int inport,
 			     int outport)
 {
+	int rc = 0;
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
-	dev_dbg(drvdata->dev, "REPLICATOR enabled\n");
-	return 0;
+	if (drvdata->base)
+		rc = dynamic_replicator_enable(drvdata, inport, outport);
+	if (!rc)
+		dev_dbg(drvdata->dev, "REPLICATOR enabled\n");
+	return rc;
+}
+
+static void dynamic_replicator_disable(struct replicator_drvdata *drvdata,
+				       int inport, int outport)
+{
+	u32 reg;
+
+	switch (outport) {
+	case 0:
+		reg = REPLICATOR_IDFILTER0;
+		break;
+	case 1:
+		reg = REPLICATOR_IDFILTER1;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	CS_UNLOCK(drvdata->base);
+
+	/* disable the flow of ATB data through port */
+	writel_relaxed(0xff, drvdata->base + reg);
+
+	if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) &&
+	    (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff))
+		coresight_disclaim_device_unlocked(drvdata->base);
+	CS_LOCK(drvdata->base);
 }
 
 static void replicator_disable(struct coresight_device *csdev, int inport,
@@ -44,6 +137,8 @@ static void replicator_disable(struct coresight_device *csdev, int inport,
 {
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
+	if (drvdata->base)
+		dynamic_replicator_disable(drvdata, inport, outport);
 	dev_dbg(drvdata->dev, "REPLICATOR disabled\n");
 }
 
@@ -56,58 +151,110 @@ static const struct coresight_ops replicator_cs_ops = {
 	.link_ops	= &replicator_link_ops,
 };
 
-static int replicator_probe(struct platform_device *pdev)
+#define coresight_replicator_reg(name, offset) \
+	coresight_simple_reg32(struct replicator_drvdata, name, offset)
+
+coresight_replicator_reg(idfilter0, REPLICATOR_IDFILTER0);
+coresight_replicator_reg(idfilter1, REPLICATOR_IDFILTER1);
+
+static struct attribute *replicator_mgmt_attrs[] = {
+	&dev_attr_idfilter0.attr,
+	&dev_attr_idfilter1.attr,
+	NULL,
+};
+
+static const struct attribute_group replicator_mgmt_group = {
+	.attrs = replicator_mgmt_attrs,
+	.name = "mgmt",
+};
+
+static const struct attribute_group *replicator_groups[] = {
+	&replicator_mgmt_group,
+	NULL,
+};
+
+static int replicator_probe(struct device *dev, struct resource *res)
 {
-	int ret;
-	struct device *dev = &pdev->dev;
+	int ret = 0;
 	struct coresight_platform_data *pdata = NULL;
 	struct replicator_drvdata *drvdata;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = pdev->dev.of_node;
+	struct device_node *np = dev->of_node;
+	void __iomem *base;
 
 	if (np) {
 		pdata = of_get_coresight_platform_data(dev, np);
 		if (IS_ERR(pdata))
 			return PTR_ERR(pdata);
-		pdev->dev.platform_data = pdata;
+		dev->platform_data = pdata;
 	}
 
+	if (of_device_is_compatible(np, "arm,coresight-replicator"))
+		pr_warn_once("Uses OBSOLETE CoreSight replicator binding\n");
+
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->dev = &pdev->dev;
-	drvdata->atclk = devm_clk_get(&pdev->dev, "atclk"); /* optional */
+	drvdata->dev = dev;
+	drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */
 	if (!IS_ERR(drvdata->atclk)) {
 		ret = clk_prepare_enable(drvdata->atclk);
 		if (ret)
 			return ret;
 	}
-	pm_runtime_get_noresume(&pdev->dev);
-	pm_runtime_set_active(&pdev->dev);
-	pm_runtime_enable(&pdev->dev);
-	platform_set_drvdata(pdev, drvdata);
+
+	/*
+	 * Map the device base for dynamic-replicator, which has been
+	 * validated by AMBA core
+	 */
+	if (res) {
+		base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(base)) {
+			ret = PTR_ERR(base);
+			goto out_disable_clk;
+		}
+		drvdata->base = base;
+		desc.groups = replicator_groups;
+	}
+
+	dev_set_drvdata(dev, drvdata);
 
 	desc.type = CORESIGHT_DEV_TYPE_LINK;
 	desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
 	desc.ops = &replicator_cs_ops;
-	desc.pdata = pdev->dev.platform_data;
-	desc.dev = &pdev->dev;
+	desc.pdata = dev->platform_data;
+	desc.dev = dev;
 	drvdata->csdev = coresight_register(&desc);
 	if (IS_ERR(drvdata->csdev)) {
 		ret = PTR_ERR(drvdata->csdev);
-		goto out_disable_pm;
+		goto out_disable_clk;
 	}
 
-	pm_runtime_put(&pdev->dev);
-
-	return 0;
+	replicator_reset(drvdata);
+	pm_runtime_put(dev);
 
-out_disable_pm:
-	if (!IS_ERR(drvdata->atclk))
+out_disable_clk:
+	if (ret && !IS_ERR_OR_NULL(drvdata->atclk))
 		clk_disable_unprepare(drvdata->atclk);
-	pm_runtime_put_noidle(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
+	return ret;
+}
+
+static int static_replicator_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	/* Static replicators do not have programming base */
+	ret = replicator_probe(&pdev->dev, NULL);
+
+	if (ret) {
+		pm_runtime_put_noidle(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
+	}
 
 	return ret;
 }
@@ -139,18 +286,49 @@ static const struct dev_pm_ops replicator_dev_pm_ops = {
 			   replicator_runtime_resume, NULL)
 };
 
-static const struct of_device_id replicator_match[] = {
+static const struct of_device_id static_replicator_match[] = {
 	{.compatible = "arm,coresight-replicator"},
+	{.compatible = "arm,coresight-static-replicator"},
 	{}
 };
 
-static struct platform_driver replicator_driver = {
-	.probe          = replicator_probe,
+static struct platform_driver static_replicator_driver = {
+	.probe          = static_replicator_probe,
 	.driver         = {
-		.name   = "coresight-replicator",
-		.of_match_table = replicator_match,
+		.name   = "coresight-static-replicator",
+		.of_match_table = static_replicator_match,
+		.pm	= &replicator_dev_pm_ops,
+		.suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver(static_replicator_driver);
+
+static int dynamic_replicator_probe(struct amba_device *adev,
+				    const struct amba_id *id)
+{
+	return replicator_probe(&adev->dev, &adev->res);
+}
+
+static const struct amba_id dynamic_replicator_ids[] = {
+	{
+		.id     = 0x000bb909,
+		.mask   = 0x000fffff,
+	},
+	{
+		/* Coresight SoC-600 */
+		.id     = 0x000bb9ec,
+		.mask   = 0x000fffff,
+	},
+	{ 0, 0 },
+};
+
+static struct amba_driver dynamic_replicator_driver = {
+	.drv = {
+		.name	= "coresight-dynamic-replicator",
 		.pm	= &replicator_dev_pm_ops,
 		.suppress_bind_attrs = true,
 	},
+	.probe		= dynamic_replicator_probe,
+	.id_table	= dynamic_replicator_ids,
 };
-builtin_platform_driver(replicator_driver);
+builtin_amba_driver(dynamic_replicator_driver);
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index a5f053f2db2c..2527b5d3b65e 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -4,6 +4,7 @@
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
  */
 
+#include <linux/atomic.h>
 #include <linux/circ_buf.h>
 #include <linux/coresight.h>
 #include <linux/perf_event.h>
@@ -180,8 +181,10 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev)
 	 * sink is already enabled no memory is needed and the HW need not be
 	 * touched.
 	 */
-	if (drvdata->mode == CS_MODE_SYSFS)
+	if (drvdata->mode == CS_MODE_SYSFS) {
+		atomic_inc(csdev->refcnt);
 		goto out;
+	}
 
 	/*
 	 * If drvdata::buf isn't NULL, memory was allocated for a previous
@@ -200,11 +203,13 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev)
 	}
 
 	ret = tmc_etb_enable_hw(drvdata);
-	if (!ret)
+	if (!ret) {
 		drvdata->mode = CS_MODE_SYSFS;
-	else
+		atomic_inc(csdev->refcnt);
+	} else {
 		/* Free up the buffer if we failed to enable */
 		used = false;
+	}
 out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
@@ -218,6 +223,7 @@ out:
 static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data)
 {
 	int ret = 0;
+	pid_t pid;
 	unsigned long flags;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 	struct perf_output_handle *handle = data;
@@ -228,19 +234,42 @@ static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data)
 		if (drvdata->reading)
 			break;
 		/*
-		 * In Perf mode there can be only one writer per sink.  There
-		 * is also no need to continue if the ETB/ETF is already
-		 * operated from sysFS.
+		 * No need to continue if the ETB/ETF is already operated
+		 * from sysFS.
 		 */
-		if (drvdata->mode != CS_MODE_DISABLED)
+		if (drvdata->mode == CS_MODE_SYSFS) {
+			ret = -EBUSY;
+			break;
+		}
+
+		/* Get a handle on the pid of the process to monitor */
+		pid = task_pid_nr(handle->event->owner);
+
+		if (drvdata->pid != -1 && drvdata->pid != pid) {
+			ret = -EBUSY;
 			break;
+		}
 
 		ret = tmc_set_etf_buffer(csdev, handle);
 		if (ret)
 			break;
+
+		/*
+		 * No HW configuration is needed if the sink is already in
+		 * use for this session.
+		 */
+		if (drvdata->pid == pid) {
+			atomic_inc(csdev->refcnt);
+			break;
+		}
+
 		ret  = tmc_etb_enable_hw(drvdata);
-		if (!ret)
+		if (!ret) {
+			/* Associate with monitored process. */
+			drvdata->pid = pid;
 			drvdata->mode = CS_MODE_PERF;
+			atomic_inc(csdev->refcnt);
+		}
 	} while (0);
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
@@ -273,26 +302,34 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev,
 	return 0;
 }
 
-static void tmc_disable_etf_sink(struct coresight_device *csdev)
+static int tmc_disable_etf_sink(struct coresight_device *csdev)
 {
 	unsigned long flags;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
+
 	if (drvdata->reading) {
 		spin_unlock_irqrestore(&drvdata->spinlock, flags);
-		return;
+		return -EBUSY;
 	}
 
-	/* Disable the TMC only if it needs to */
-	if (drvdata->mode != CS_MODE_DISABLED) {
-		tmc_etb_disable_hw(drvdata);
-		drvdata->mode = CS_MODE_DISABLED;
+	if (atomic_dec_return(csdev->refcnt)) {
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		return -EBUSY;
 	}
 
+	/* Complain if we (somehow) got out of sync */
+	WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED);
+	tmc_etb_disable_hw(drvdata);
+	/* Dissociate from monitored process. */
+	drvdata->pid = -1;
+	drvdata->mode = CS_MODE_DISABLED;
+
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	dev_dbg(drvdata->dev, "TMC-ETB/ETF disabled\n");
+	return 0;
 }
 
 static int tmc_enable_etf_link(struct coresight_device *csdev,
@@ -337,10 +374,11 @@ static void tmc_disable_etf_link(struct coresight_device *csdev,
 	dev_dbg(drvdata->dev, "TMC-ETF disabled\n");
 }
 
-static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, int cpu,
-				  void **pages, int nr_pages, bool overwrite)
+static void *tmc_alloc_etf_buffer(struct coresight_device *csdev,
+				  struct perf_event *event, void **pages,
+				  int nr_pages, bool overwrite)
 {
-	int node;
+	int node, cpu = event->cpu;
 	struct cs_buffers *buf;
 
 	if (cpu == -1)
@@ -400,7 +438,7 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 	u32 *buf_ptr;
 	u64 read_ptr, write_ptr;
 	u32 status;
-	unsigned long offset, to_read;
+	unsigned long offset, to_read = 0, flags;
 	struct cs_buffers *buf = sink_config;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
@@ -411,6 +449,12 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 	if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF))
 		return 0;
 
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	/* Don't do anything if another tracer is using this sink */
+	if (atomic_read(csdev->refcnt) != 1)
+		goto out;
+
 	CS_UNLOCK(drvdata->base);
 
 	tmc_flush_and_stop(drvdata);
@@ -504,6 +548,8 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 		to_read = buf->nr_pages << PAGE_SHIFT;
 	}
 	CS_LOCK(drvdata->base);
+out:
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	return to_read;
 }
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index f684283890d3..df6e4b0b84e9 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -4,10 +4,15 @@
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
  */
 
+#include <linux/atomic.h>
 #include <linux/coresight.h>
 #include <linux/dma-mapping.h>
 #include <linux/iommu.h>
+#include <linux/idr.h>
+#include <linux/mutex.h>
+#include <linux/refcount.h>
 #include <linux/slab.h>
+#include <linux/types.h>
 #include <linux/vmalloc.h>
 #include "coresight-catu.h"
 #include "coresight-etm-perf.h"
@@ -23,14 +28,18 @@ struct etr_flat_buf {
 
 /*
  * etr_perf_buffer - Perf buffer used for ETR
+ * @drvdata		- The ETR drvdaga this buffer has been allocated for.
  * @etr_buf		- Actual buffer used by the ETR
+ * @pid			- The PID this etr_perf_buffer belongs to.
  * @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 tmc_drvdata	*drvdata;
 	struct etr_buf		*etr_buf;
+	pid_t			pid;
 	bool			snapshot;
 	unsigned long		head;
 	int			nr_pages;
@@ -772,7 +781,8 @@ static inline void tmc_etr_disable_catu(struct tmc_drvdata *drvdata)
 static const struct etr_buf_operations *etr_buf_ops[] = {
 	[ETR_MODE_FLAT] = &etr_flat_buf_ops,
 	[ETR_MODE_ETR_SG] = &etr_sg_buf_ops,
-	[ETR_MODE_CATU] = &etr_catu_buf_ops,
+	[ETR_MODE_CATU] = IS_ENABLED(CONFIG_CORESIGHT_CATU)
+						? &etr_catu_buf_ops : NULL,
 };
 
 static inline int tmc_etr_mode_alloc_buf(int mode,
@@ -786,7 +796,7 @@ static inline int tmc_etr_mode_alloc_buf(int mode,
 	case ETR_MODE_FLAT:
 	case ETR_MODE_ETR_SG:
 	case ETR_MODE_CATU:
-		if (etr_buf_ops[mode]->alloc)
+		if (etr_buf_ops[mode] && etr_buf_ops[mode]->alloc)
 			rc = etr_buf_ops[mode]->alloc(drvdata, etr_buf,
 						      node, pages);
 		if (!rc)
@@ -1124,8 +1134,10 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
 	 * sink is already enabled no memory is needed and the HW need not be
 	 * touched, even if the buffer size has changed.
 	 */
-	if (drvdata->mode == CS_MODE_SYSFS)
+	if (drvdata->mode == CS_MODE_SYSFS) {
+		atomic_inc(csdev->refcnt);
 		goto out;
+	}
 
 	/*
 	 * If we don't have a buffer or it doesn't match the requested size,
@@ -1138,8 +1150,10 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev)
 	}
 
 	ret = tmc_etr_enable_hw(drvdata, drvdata->sysfs_buf);
-	if (!ret)
+	if (!ret) {
 		drvdata->mode = CS_MODE_SYSFS;
+		atomic_inc(csdev->refcnt);
+	}
 out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
@@ -1154,23 +1168,23 @@ out:
 }
 
 /*
- * tmc_etr_setup_perf_buf: Allocate ETR buffer for use by perf.
+ * alloc_etr_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)
+static struct etr_buf *
+alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
+	      int nr_pages, void **pages, bool snapshot)
 {
+	int node, cpu = event->cpu;
 	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);
+	if (cpu == -1)
+		cpu = smp_processor_id();
+	node = cpu_to_node(cpu);
 
 	/*
 	 * Try to match the perf ring buffer size if it is larger
@@ -1195,32 +1209,160 @@ tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, int node, int nr_pages,
 		size /= 2;
 	} while (size >= TMC_ETR_PERF_MIN_BUF_SIZE);
 
+	return ERR_PTR(-ENOMEM);
+
+done:
+	return etr_buf;
+}
+
+static struct etr_buf *
+get_perf_etr_buf_cpu_wide(struct tmc_drvdata *drvdata,
+			  struct perf_event *event, int nr_pages,
+			  void **pages, bool snapshot)
+{
+	int ret;
+	pid_t pid = task_pid_nr(event->owner);
+	struct etr_buf *etr_buf;
+
+retry:
+	/*
+	 * An etr_perf_buffer is associated with an event and holds a reference
+	 * to the AUX ring buffer that was created for that event.  In CPU-wide
+	 * N:1 mode multiple events (one per CPU), each with its own AUX ring
+	 * buffer, share a sink.  As such an etr_perf_buffer is created for each
+	 * event but a single etr_buf associated with the ETR is shared between
+	 * them.  The last event in a trace session will copy the content of the
+	 * etr_buf to its AUX ring buffer.  Ring buffer associated to other
+	 * events are simply not used an freed as events are destoyed.  We still
+	 * need to allocate a ring buffer for each event since we don't know
+	 * which event will be last.
+	 */
+
+	/*
+	 * The first thing to do here is check if an etr_buf has already been
+	 * allocated for this session.  If so it is shared with this event,
+	 * otherwise it is created.
+	 */
+	mutex_lock(&drvdata->idr_mutex);
+	etr_buf = idr_find(&drvdata->idr, pid);
+	if (etr_buf) {
+		refcount_inc(&etr_buf->refcount);
+		mutex_unlock(&drvdata->idr_mutex);
+		return etr_buf;
+	}
+
+	/* If we made it here no buffer has been allocated, do so now. */
+	mutex_unlock(&drvdata->idr_mutex);
+
+	etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot);
+	if (IS_ERR(etr_buf))
+		return etr_buf;
+
+	refcount_set(&etr_buf->refcount, 1);
+
+	/* Now that we have a buffer, add it to the IDR. */
+	mutex_lock(&drvdata->idr_mutex);
+	ret = idr_alloc(&drvdata->idr, etr_buf, pid, pid + 1, GFP_KERNEL);
+	mutex_unlock(&drvdata->idr_mutex);
+
+	/* Another event with this session ID has allocated this buffer. */
+	if (ret == -ENOSPC) {
+		tmc_free_etr_buf(etr_buf);
+		goto retry;
+	}
+
+	/* The IDR can't allocate room for a new session, abandon ship. */
+	if (ret == -ENOMEM) {
+		tmc_free_etr_buf(etr_buf);
+		return ERR_PTR(ret);
+	}
+
+
+	return etr_buf;
+}
+
+static struct etr_buf *
+get_perf_etr_buf_per_thread(struct tmc_drvdata *drvdata,
+			    struct perf_event *event, int nr_pages,
+			    void **pages, bool snapshot)
+{
+	struct etr_buf *etr_buf;
+
+	/*
+	 * In per-thread mode the etr_buf isn't shared, so just go ahead
+	 * with memory allocation.
+	 */
+	etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot);
+	if (IS_ERR(etr_buf))
+		goto out;
+
+	refcount_set(&etr_buf->refcount, 1);
+out:
+	return etr_buf;
+}
+
+static struct etr_buf *
+get_perf_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
+		 int nr_pages, void **pages, bool snapshot)
+{
+	if (event->cpu == -1)
+		return get_perf_etr_buf_per_thread(drvdata, event, nr_pages,
+						   pages, snapshot);
+
+	return get_perf_etr_buf_cpu_wide(drvdata, event, nr_pages,
+					 pages, snapshot);
+}
+
+static struct etr_perf_buffer *
+tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
+		       int nr_pages, void **pages, bool snapshot)
+{
+	int node, cpu = event->cpu;
+	struct etr_buf *etr_buf;
+	struct etr_perf_buffer *etr_perf;
+
+	if (cpu == -1)
+		cpu = smp_processor_id();
+	node = cpu_to_node(cpu);
+
+	etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node);
+	if (!etr_perf)
+		return ERR_PTR(-ENOMEM);
+
+	etr_buf = get_perf_etr_buf(drvdata, event, nr_pages, pages, snapshot);
+	if (!IS_ERR(etr_buf))
+		goto done;
+
 	kfree(etr_perf);
 	return ERR_PTR(-ENOMEM);
 
 done:
+	/*
+	 * Keep a reference to the ETR this buffer has been allocated for
+	 * in order to have access to the IDR in tmc_free_etr_buffer().
+	 */
+	etr_perf->drvdata = drvdata;
 	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 perf_event *event, 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),
+	etr_perf = tmc_etr_setup_perf_buf(drvdata, event,
 					  nr_pages, pages, snapshot);
 	if (IS_ERR(etr_perf)) {
 		dev_dbg(drvdata->dev, "Unable to allocate ETR buffer\n");
 		return NULL;
 	}
 
+	etr_perf->pid = task_pid_nr(event->owner);
 	etr_perf->snapshot = snapshot;
 	etr_perf->nr_pages = nr_pages;
 	etr_perf->pages = pages;
@@ -1231,9 +1373,33 @@ static void *tmc_alloc_etr_buffer(struct coresight_device *csdev,
 static void tmc_free_etr_buffer(void *config)
 {
 	struct etr_perf_buffer *etr_perf = config;
+	struct tmc_drvdata *drvdata = etr_perf->drvdata;
+	struct etr_buf *buf, *etr_buf = etr_perf->etr_buf;
+
+	if (!etr_buf)
+		goto free_etr_perf_buffer;
+
+	mutex_lock(&drvdata->idr_mutex);
+	/* If we are not the last one to use the buffer, don't touch it. */
+	if (!refcount_dec_and_test(&etr_buf->refcount)) {
+		mutex_unlock(&drvdata->idr_mutex);
+		goto free_etr_perf_buffer;
+	}
+
+	/* We are the last one, remove from the IDR and free the buffer. */
+	buf = idr_remove(&drvdata->idr, etr_perf->pid);
+	mutex_unlock(&drvdata->idr_mutex);
+
+	/*
+	 * Something went very wrong if the buffer associated with this ID
+	 * is not the same in the IDR.  Leak to avoid use after free.
+	 */
+	if (buf && WARN_ON(buf != etr_buf))
+		goto free_etr_perf_buffer;
+
+	tmc_free_etr_buf(etr_perf->etr_buf);
 
-	if (etr_perf->etr_buf)
-		tmc_free_etr_buf(etr_perf->etr_buf);
+free_etr_perf_buffer:
 	kfree(etr_perf);
 }
 
@@ -1308,6 +1474,13 @@ tmc_update_etr_buffer(struct coresight_device *csdev,
 	struct etr_buf *etr_buf = etr_perf->etr_buf;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	/* Don't do anything if another tracer is using this sink */
+	if (atomic_read(csdev->refcnt) != 1) {
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		goto out;
+	}
+
 	if (WARN_ON(drvdata->perf_data != etr_perf)) {
 		lost = true;
 		spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -1347,17 +1520,15 @@ out:
 static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data)
 {
 	int rc = 0;
+	pid_t pid;
 	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)) {
+	 /* Don't use this sink if it is already claimed by sysFS */
+	if (drvdata->mode == CS_MODE_SYSFS) {
 		rc = -EBUSY;
 		goto unlock_out;
 	}
@@ -1367,11 +1538,34 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data)
 		goto unlock_out;
 	}
 
+	/* Get a handle on the pid of the process to monitor */
+	pid = etr_perf->pid;
+
+	/* Do not proceed if this device is associated with another session */
+	if (drvdata->pid != -1 && drvdata->pid != pid) {
+		rc = -EBUSY;
+		goto unlock_out;
+	}
+
 	etr_perf->head = PERF_IDX2OFF(handle->head, etr_perf);
 	drvdata->perf_data = etr_perf;
+
+	/*
+	 * No HW configuration is needed if the sink is already in
+	 * use for this session.
+	 */
+	if (drvdata->pid == pid) {
+		atomic_inc(csdev->refcnt);
+		goto unlock_out;
+	}
+
 	rc = tmc_etr_enable_hw(drvdata, etr_perf->etr_buf);
-	if (!rc)
+	if (!rc) {
+		/* Associate with monitored process. */
+		drvdata->pid = pid;
 		drvdata->mode = CS_MODE_PERF;
+		atomic_inc(csdev->refcnt);
+	}
 
 unlock_out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
@@ -1392,26 +1586,34 @@ static int tmc_enable_etr_sink(struct coresight_device *csdev,
 	return -EINVAL;
 }
 
-static void tmc_disable_etr_sink(struct coresight_device *csdev)
+static int tmc_disable_etr_sink(struct coresight_device *csdev)
 {
 	unsigned long flags;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
+
 	if (drvdata->reading) {
 		spin_unlock_irqrestore(&drvdata->spinlock, flags);
-		return;
+		return -EBUSY;
 	}
 
-	/* Disable the TMC only if it needs to */
-	if (drvdata->mode != CS_MODE_DISABLED) {
-		tmc_etr_disable_hw(drvdata);
-		drvdata->mode = CS_MODE_DISABLED;
+	if (atomic_dec_return(csdev->refcnt)) {
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		return -EBUSY;
 	}
 
+	/* Complain if we (somehow) got out of sync */
+	WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED);
+	tmc_etr_disable_hw(drvdata);
+	/* Dissociate from monitored process. */
+	drvdata->pid = -1;
+	drvdata->mode = CS_MODE_DISABLED;
+
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	dev_dbg(drvdata->dev, "TMC-ETR disabled\n");
+	return 0;
 }
 
 static const struct coresight_ops_sink tmc_etr_sink_ops = {
diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c
index 2a02da3d630f..3f718729d741 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.c
+++ b/drivers/hwtracing/coresight/coresight-tmc.c
@@ -8,10 +8,12 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
+#include <linux/idr.h>
 #include <linux/io.h>
 #include <linux/err.h>
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
+#include <linux/mutex.h>
 #include <linux/property.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
@@ -340,6 +342,8 @@ static inline bool tmc_etr_can_use_sg(struct tmc_drvdata *drvdata)
 static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata,
 			     u32 devid, void *dev_caps)
 {
+	int rc;
+
 	u32 dma_mask = 0;
 
 	/* Set the unadvertised capabilities */
@@ -369,7 +373,10 @@ static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata,
 		dma_mask = 40;
 	}
 
-	return dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(dma_mask));
+	rc = dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(dma_mask));
+	if (rc)
+		dev_err(drvdata->dev, "Failed to setup DMA mask: %d\n", rc);
+	return rc;
 }
 
 static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
@@ -415,6 +422,8 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID);
 	drvdata->config_type = BMVAL(devid, 6, 7);
 	drvdata->memwidth = tmc_get_memwidth(devid);
+	/* This device is not associated with a session */
+	drvdata->pid = -1;
 
 	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
 		if (np)
@@ -427,8 +436,6 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 		drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4;
 	}
 
-	pm_runtime_put(&adev->dev);
-
 	desc.pdata = pdata;
 	desc.dev = dev;
 	desc.groups = coresight_tmc_groups;
@@ -447,6 +454,8 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 					 coresight_get_uci_data(id));
 		if (ret)
 			goto out;
+		idr_init(&drvdata->idr);
+		mutex_init(&drvdata->idr_mutex);
 		break;
 	case TMC_CONFIG_TYPE_ETF:
 		desc.type = CORESIGHT_DEV_TYPE_LINKSINK;
@@ -471,6 +480,8 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	ret = misc_register(&drvdata->miscdev);
 	if (ret)
 		coresight_unregister(drvdata->csdev);
+	else
+		pm_runtime_put(&adev->dev);
 out:
 	return ret;
 }
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index 487c53701e9c..503f1b3a3741 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -8,7 +8,10 @@
 #define _CORESIGHT_TMC_H
 
 #include <linux/dma-mapping.h>
+#include <linux/idr.h>
 #include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/refcount.h>
 
 #define TMC_RSZ			0x004
 #define TMC_STS			0x00c
@@ -133,6 +136,7 @@ struct etr_buf_operations;
 
 /**
  * struct etr_buf - Details of the buffer used by ETR
+ * refcount	; Number of sources currently using this etr_buf.
  * @mode	: Mode of the ETR buffer, contiguous, Scatter Gather etc.
  * @full	: Trace data overflow
  * @size	: Size of the buffer.
@@ -143,6 +147,7 @@ struct etr_buf_operations;
  * @private	: Backend specific information for the buf
  */
 struct etr_buf {
+	refcount_t			refcount;
 	enum etr_mode			mode;
 	bool				full;
 	ssize_t				size;
@@ -160,6 +165,8 @@ struct etr_buf {
  * @csdev:	component vitals needed by the framework.
  * @miscdev:	specifics to handle "/dev/xyz.tmc" entry.
  * @spinlock:	only one at a time pls.
+ * @pid:	Process ID of the process being monitored by the session
+ *		that is using this component.
  * @buf:	Snapshot of the trace data for ETF/ETB.
  * @etr_buf:	details of buffer used in TMC-ETR
  * @len:	size of the available trace for ETF/ETB.
@@ -170,6 +177,8 @@ 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)
+ * @idr:	Holds etr_bufs allocated for this ETR.
+ * @idr_mutex:	Access serialisation for idr.
  * @perf_data:	PERF buffer for ETR.
  * @sysfs_data:	SYSFS buffer for ETR.
  */
@@ -179,6 +188,7 @@ struct tmc_drvdata {
 	struct coresight_device	*csdev;
 	struct miscdevice	miscdev;
 	spinlock_t		spinlock;
+	pid_t			pid;
 	bool			reading;
 	union {
 		char		*buf;		/* TMC ETB */
@@ -191,6 +201,8 @@ struct tmc_drvdata {
 	enum tmc_mem_intf_width	memwidth;
 	u32			trigger_cntr;
 	u32			etr_caps;
+	struct idr		idr;
+	struct mutex		idr_mutex;
 	struct etr_buf		*sysfs_buf;
 	void			*perf_data;
 };
diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
index b2f72a1fa402..63d9af31f57f 100644
--- a/drivers/hwtracing/coresight/coresight-tpiu.c
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -5,6 +5,7 @@
  * Description: CoreSight Trace Port Interface Unit driver
  */
 
+#include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/device.h>
@@ -73,7 +74,7 @@ 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);
-
+	atomic_inc(csdev->refcnt);
 	dev_dbg(drvdata->dev, "TPIU enabled\n");
 	return 0;
 }
@@ -94,13 +95,17 @@ static void tpiu_disable_hw(struct tpiu_drvdata *drvdata)
 	CS_LOCK(drvdata->base);
 }
 
-static void tpiu_disable(struct coresight_device *csdev)
+static int tpiu_disable(struct coresight_device *csdev)
 {
 	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
+	if (atomic_dec_return(csdev->refcnt))
+		return -EBUSY;
+
 	tpiu_disable_hw(drvdata);
 
 	dev_dbg(drvdata->dev, "TPIU disabled\n");
+	return 0;
 }
 
 static const struct coresight_ops_sink tpiu_sink_ops = {
@@ -153,8 +158,6 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
 	/* Disable tpiu to support older devices */
 	tpiu_disable_hw(drvdata);
 
-	pm_runtime_put(&adev->dev);
-
 	desc.type = CORESIGHT_DEV_TYPE_SINK;
 	desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT;
 	desc.ops = &tpiu_cs_ops;
@@ -162,7 +165,12 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
 	desc.dev = dev;
 	drvdata->csdev = coresight_register(&desc);
 
-	return PTR_ERR_OR_ZERO(drvdata->csdev);
+	if (!IS_ERR(drvdata->csdev)) {
+		pm_runtime_put(&adev->dev);
+		return 0;
+	}
+
+	return PTR_ERR(drvdata->csdev);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 29cef898afba..4b130281236a 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -225,26 +225,28 @@ static int coresight_enable_sink(struct coresight_device *csdev,
 	 * 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;
-	}
+	if (!sink_ops(csdev)->enable)
+		return -EINVAL;
 
-	atomic_inc(csdev->refcnt);
+	ret = sink_ops(csdev)->enable(csdev, mode, data);
+	if (ret)
+		return ret;
+	csdev->enable = true;
 
 	return 0;
 }
 
 static void coresight_disable_sink(struct coresight_device *csdev)
 {
-	if (atomic_dec_return(csdev->refcnt) == 0) {
-		if (sink_ops(csdev)->disable) {
-			sink_ops(csdev)->disable(csdev);
-			csdev->enable = false;
-		}
-	}
+	int ret;
+
+	if (!sink_ops(csdev)->disable)
+		return;
+
+	ret = sink_ops(csdev)->disable(csdev);
+	if (ret)
+		return;
+	csdev->enable = false;
 }
 
 static int coresight_enable_link(struct coresight_device *csdev,
@@ -973,7 +975,6 @@ static void coresight_device_release(struct device *dev)
 {
 	struct coresight_device *csdev = to_coresight_device(dev);
 
-	kfree(csdev->conns);
 	kfree(csdev->refcnt);
 	kfree(csdev);
 }
diff --git a/drivers/hwtracing/intel_th/acpi.c b/drivers/hwtracing/intel_th/acpi.c
index 87bc3744755f..87f9024e4bbb 100644
--- a/drivers/hwtracing/intel_th/acpi.c
+++ b/drivers/hwtracing/intel_th/acpi.c
@@ -37,15 +37,21 @@ MODULE_DEVICE_TABLE(acpi, intel_th_acpi_ids);
 static int intel_th_acpi_probe(struct platform_device *pdev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	struct resource resource[TH_MMIO_END];
 	const struct acpi_device_id *id;
 	struct intel_th *th;
+	int i, r;
 
 	id = acpi_match_device(intel_th_acpi_ids, &pdev->dev);
 	if (!id)
 		return -ENODEV;
 
-	th = intel_th_alloc(&pdev->dev, (void *)id->driver_data,
-			    pdev->resource, pdev->num_resources, -1);
+	for (i = 0, r = 0; i < pdev->num_resources && r < TH_MMIO_END; i++)
+		if (pdev->resource[i].flags &
+		    (IORESOURCE_IRQ | IORESOURCE_MEM))
+			resource[r++] = pdev->resource[i];
+
+	th = intel_th_alloc(&pdev->dev, (void *)id->driver_data, resource, r);
 	if (IS_ERR(th))
 		return PTR_ERR(th);
 
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index 7c1acc2f801c..033dce563c99 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -430,9 +430,9 @@ static const struct intel_th_subdevice {
 		.nres	= 1,
 		.res	= {
 			{
-				/* Handle TSCU from GTH driver */
+				/* Handle TSCU and CTS from GTH driver */
 				.start	= REG_GTH_OFFSET,
-				.end	= REG_TSCU_OFFSET + REG_TSCU_LENGTH - 1,
+				.end	= REG_CTS_OFFSET + REG_CTS_LENGTH - 1,
 				.flags	= IORESOURCE_MEM,
 			},
 		},
@@ -491,7 +491,7 @@ static const struct intel_th_subdevice {
 				.flags	= IORESOURCE_MEM,
 			},
 			{
-				.start	= 1, /* use resource[1] */
+				.start	= TH_MMIO_SW,
 				.end	= 0,
 				.flags	= IORESOURCE_MEM,
 			},
@@ -501,6 +501,24 @@ static const struct intel_th_subdevice {
 		.type	= INTEL_TH_SOURCE,
 	},
 	{
+		.nres	= 2,
+		.res	= {
+			{
+				.start	= REG_STH_OFFSET,
+				.end	= REG_STH_OFFSET + REG_STH_LENGTH - 1,
+				.flags	= IORESOURCE_MEM,
+			},
+			{
+				.start	= TH_MMIO_RTIT,
+				.end	= 0,
+				.flags	= IORESOURCE_MEM,
+			},
+		},
+		.id	= -1,
+		.name	= "rtit",
+		.type	= INTEL_TH_SOURCE,
+	},
+	{
 		.nres	= 1,
 		.res	= {
 			{
@@ -584,7 +602,6 @@ intel_th_subdevice_alloc(struct intel_th *th,
 	struct intel_th_device *thdev;
 	struct resource res[3];
 	unsigned int req = 0;
-	bool is64bit = false;
 	int r, err;
 
 	thdev = intel_th_device_alloc(th, subdev->type, subdev->name,
@@ -594,18 +611,12 @@ intel_th_subdevice_alloc(struct intel_th *th,
 
 	thdev->drvdata = th->drvdata;
 
-	for (r = 0; r < th->num_resources; r++)
-		if (th->resource[r].flags & IORESOURCE_MEM_64) {
-			is64bit = true;
-			break;
-		}
-
 	memcpy(res, subdev->res,
 	       sizeof(struct resource) * subdev->nres);
 
 	for (r = 0; r < subdev->nres; r++) {
 		struct resource *devres = th->resource;
-		int bar = 0; /* cut subdevices' MMIO from resource[0] */
+		int bar = TH_MMIO_CONFIG;
 
 		/*
 		 * Take .end == 0 to mean 'take the whole bar',
@@ -614,8 +625,9 @@ intel_th_subdevice_alloc(struct intel_th *th,
 		 */
 		if (!res[r].end && res[r].flags == IORESOURCE_MEM) {
 			bar = res[r].start;
-			if (is64bit)
-				bar *= 2;
+			err = -ENODEV;
+			if (bar >= th->num_resources)
+				goto fail_put_device;
 			res[r].start = 0;
 			res[r].end = resource_size(&devres[bar]) - 1;
 		}
@@ -627,7 +639,12 @@ intel_th_subdevice_alloc(struct intel_th *th,
 			dev_dbg(th->dev, "%s:%d @ %pR\n",
 				subdev->name, r, &res[r]);
 		} else if (res[r].flags & IORESOURCE_IRQ) {
-			res[r].start	= th->irq;
+			/*
+			 * Only pass on the IRQ if we have useful interrupts:
+			 * the ones that can be configured via MINTCTL.
+			 */
+			if (INTEL_TH_CAP(th, has_mintctl) && th->irq != -1)
+				res[r].start = th->irq;
 		}
 	}
 
@@ -758,8 +775,13 @@ static int intel_th_populate(struct intel_th *th)
 
 		thdev = intel_th_subdevice_alloc(th, subdev);
 		/* note: caller should free subdevices from th::thdev[] */
-		if (IS_ERR(thdev))
+		if (IS_ERR(thdev)) {
+			/* ENODEV for individual subdevices is allowed */
+			if (PTR_ERR(thdev) == -ENODEV)
+				continue;
+
 			return PTR_ERR(thdev);
+		}
 
 		th->thdev[th->num_thdevs++] = thdev;
 	}
@@ -809,26 +831,40 @@ static const struct file_operations intel_th_output_fops = {
 	.llseek	= noop_llseek,
 };
 
+static irqreturn_t intel_th_irq(int irq, void *data)
+{
+	struct intel_th *th = data;
+	irqreturn_t ret = IRQ_NONE;
+	struct intel_th_driver *d;
+	int i;
+
+	for (i = 0; i < th->num_thdevs; i++) {
+		if (th->thdev[i]->type != INTEL_TH_OUTPUT)
+			continue;
+
+		d = to_intel_th_driver(th->thdev[i]->dev.driver);
+		if (d && d->irq)
+			ret |= d->irq(th->thdev[i]);
+	}
+
+	if (ret == IRQ_NONE)
+		pr_warn_ratelimited("nobody cared for irq\n");
+
+	return ret;
+}
+
 /**
  * intel_th_alloc() - allocate a new Intel TH device and its subdevices
  * @dev:	parent device
- * @devres:	parent's resources
- * @ndevres:	number of resources
+ * @devres:	resources indexed by th_mmio_idx
  * @irq:	irq number
  */
 struct intel_th *
 intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata,
-	       struct resource *devres, unsigned int ndevres, int irq)
+	       struct resource *devres, unsigned int ndevres)
 {
+	int err, r, nr_mmios = 0;
 	struct intel_th *th;
-	int err, r;
-
-	if (irq == -1)
-		for (r = 0; r < ndevres; r++)
-			if (devres[r].flags & IORESOURCE_IRQ) {
-				irq = devres[r].start;
-				break;
-			}
 
 	th = kzalloc(sizeof(*th), GFP_KERNEL);
 	if (!th)
@@ -846,12 +882,32 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata,
 		err = th->major;
 		goto err_ida;
 	}
+	th->irq = -1;
 	th->dev = dev;
 	th->drvdata = drvdata;
 
-	th->resource = devres;
-	th->num_resources = ndevres;
-	th->irq = irq;
+	for (r = 0; r < ndevres; r++)
+		switch (devres[r].flags & IORESOURCE_TYPE_BITS) {
+		case IORESOURCE_MEM:
+			th->resource[nr_mmios++] = devres[r];
+			break;
+		case IORESOURCE_IRQ:
+			err = devm_request_irq(dev, devres[r].start,
+					       intel_th_irq, IRQF_SHARED,
+					       dev_name(dev), th);
+			if (err)
+				goto err_chrdev;
+
+			if (th->irq == -1)
+				th->irq = devres[r].start;
+			break;
+		default:
+			dev_warn(dev, "Unknown resource type %lx\n",
+				 devres[r].flags);
+			break;
+		}
+
+	th->num_resources = nr_mmios;
 
 	dev_set_drvdata(dev, th);
 
@@ -868,6 +924,10 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata,
 
 	return th;
 
+err_chrdev:
+	__unregister_chrdev(th->major, 0, TH_POSSIBLE_OUTPUTS,
+			    "intel_th/output");
+
 err_ida:
 	ida_simple_remove(&intel_th_ida, th->id);
 
@@ -928,6 +988,27 @@ int intel_th_trace_enable(struct intel_th_device *thdev)
 EXPORT_SYMBOL_GPL(intel_th_trace_enable);
 
 /**
+ * intel_th_trace_switch() - execute a switch sequence
+ * @thdev:	output device that requests tracing switch
+ */
+int intel_th_trace_switch(struct intel_th_device *thdev)
+{
+	struct intel_th_device *hub = to_intel_th_device(thdev->dev.parent);
+	struct intel_th_driver *hubdrv = to_intel_th_driver(hub->dev.driver);
+
+	if (WARN_ON_ONCE(hub->type != INTEL_TH_SWITCH))
+		return -EINVAL;
+
+	if (WARN_ON_ONCE(thdev->type != INTEL_TH_OUTPUT))
+		return -EINVAL;
+
+	hubdrv->trig_switch(hub, &thdev->output);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(intel_th_trace_switch);
+
+/**
  * intel_th_trace_disable() - disable tracing for an output device
  * @thdev:	output device that requests tracing be disabled
  */
diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c
index edc52d75e6bd..fa9d34af87ac 100644
--- a/drivers/hwtracing/intel_th/gth.c
+++ b/drivers/hwtracing/intel_th/gth.c
@@ -308,6 +308,11 @@ static int intel_th_gth_reset(struct gth_device *gth)
 	iowrite32(0, gth->base + REG_GTH_SCR);
 	iowrite32(0xfc, gth->base + REG_GTH_SCR2);
 
+	/* setup CTS for single trigger */
+	iowrite32(CTS_EVENT_ENABLE_IF_ANYTHING, gth->base + REG_CTS_C0S0_EN);
+	iowrite32(CTS_ACTION_CONTROL_SET_STATE(CTS_STATE_IDLE) |
+		  CTS_ACTION_CONTROL_TRIGGER, gth->base + REG_CTS_C0S0_ACT);
+
 	return 0;
 }
 
@@ -457,6 +462,68 @@ static int intel_th_output_attributes(struct gth_device *gth)
 }
 
 /**
+ * intel_th_gth_stop() - stop tracing to an output device
+ * @gth:		GTH device
+ * @output:		output device's descriptor
+ * @capture_done:	set when no more traces will be captured
+ *
+ * This will stop tracing using force storeEn off signal and wait for the
+ * pipelines to be empty for the corresponding output port.
+ */
+static void intel_th_gth_stop(struct gth_device *gth,
+			      struct intel_th_output *output,
+			      bool capture_done)
+{
+	struct intel_th_device *outdev =
+		container_of(output, struct intel_th_device, output);
+	struct intel_th_driver *outdrv =
+		to_intel_th_driver(outdev->dev.driver);
+	unsigned long count;
+	u32 reg;
+	u32 scr2 = 0xfc | (capture_done ? 1 : 0);
+
+	iowrite32(0, gth->base + REG_GTH_SCR);
+	iowrite32(scr2, gth->base + REG_GTH_SCR2);
+
+	/* wait on pipeline empty for the given port */
+	for (reg = 0, count = GTH_PLE_WAITLOOP_DEPTH;
+	     count && !(reg & BIT(output->port)); count--) {
+		reg = ioread32(gth->base + REG_GTH_STAT);
+		cpu_relax();
+	}
+
+	if (!count)
+		dev_dbg(gth->dev, "timeout waiting for GTH[%d] PLE\n",
+			output->port);
+
+	/* wait on output piepline empty */
+	if (outdrv->wait_empty)
+		outdrv->wait_empty(outdev);
+
+	/* clear force capture done for next captures */
+	iowrite32(0xfc, gth->base + REG_GTH_SCR2);
+}
+
+/**
+ * intel_th_gth_start() - start tracing to an output device
+ * @gth:	GTH device
+ * @output:	output device's descriptor
+ *
+ * This will start tracing using force storeEn signal.
+ */
+static void intel_th_gth_start(struct gth_device *gth,
+			       struct intel_th_output *output)
+{
+	u32 scr = 0xfc0000;
+
+	if (output->multiblock)
+		scr |= 0xff;
+
+	iowrite32(scr, gth->base + REG_GTH_SCR);
+	iowrite32(0, gth->base + REG_GTH_SCR2);
+}
+
+/**
  * intel_th_gth_disable() - disable tracing to an output device
  * @thdev:	GTH device
  * @output:	output device's descriptor
@@ -469,7 +536,6 @@ static void intel_th_gth_disable(struct intel_th_device *thdev,
 				 struct intel_th_output *output)
 {
 	struct gth_device *gth = dev_get_drvdata(&thdev->dev);
-	unsigned long count;
 	int master;
 	u32 reg;
 
@@ -482,22 +548,7 @@ static void intel_th_gth_disable(struct intel_th_device *thdev,
 	}
 	spin_unlock(&gth->gth_lock);
 
-	iowrite32(0, gth->base + REG_GTH_SCR);
-	iowrite32(0xfd, gth->base + REG_GTH_SCR2);
-
-	/* wait on pipeline empty for the given port */
-	for (reg = 0, count = GTH_PLE_WAITLOOP_DEPTH;
-	     count && !(reg & BIT(output->port)); count--) {
-		reg = ioread32(gth->base + REG_GTH_STAT);
-		cpu_relax();
-	}
-
-	/* clear force capture done for next captures */
-	iowrite32(0xfc, gth->base + REG_GTH_SCR2);
-
-	if (!count)
-		dev_dbg(&thdev->dev, "timeout waiting for GTH[%d] PLE\n",
-			output->port);
+	intel_th_gth_stop(gth, output, true);
 
 	reg = ioread32(gth->base + REG_GTH_SCRPD0);
 	reg &= ~output->scratchpad;
@@ -526,8 +577,8 @@ static void intel_th_gth_enable(struct intel_th_device *thdev,
 {
 	struct gth_device *gth = dev_get_drvdata(&thdev->dev);
 	struct intel_th *th = to_intel_th(thdev);
-	u32 scr = 0xfc0000, scrpd;
 	int master;
+	u32 scrpd;
 
 	spin_lock(&gth->gth_lock);
 	for_each_set_bit(master, gth->output[output->port].master,
@@ -535,9 +586,6 @@ static void intel_th_gth_enable(struct intel_th_device *thdev,
 		gth_master_set(gth, master, output->port);
 	}
 
-	if (output->multiblock)
-		scr |= 0xff;
-
 	output->active = true;
 	spin_unlock(&gth->gth_lock);
 
@@ -548,8 +596,38 @@ static void intel_th_gth_enable(struct intel_th_device *thdev,
 	scrpd |= output->scratchpad;
 	iowrite32(scrpd, gth->base + REG_GTH_SCRPD0);
 
-	iowrite32(scr, gth->base + REG_GTH_SCR);
-	iowrite32(0, gth->base + REG_GTH_SCR2);
+	intel_th_gth_start(gth, output);
+}
+
+/**
+ * intel_th_gth_switch() - execute a switch sequence
+ * @thdev:	GTH device
+ * @output:	output device's descriptor
+ *
+ * This will execute a switch sequence that will trigger a switch window
+ * when tracing to MSC in multi-block mode.
+ */
+static void intel_th_gth_switch(struct intel_th_device *thdev,
+				struct intel_th_output *output)
+{
+	struct gth_device *gth = dev_get_drvdata(&thdev->dev);
+	unsigned long count;
+	u32 reg;
+
+	/* trigger */
+	iowrite32(0, gth->base + REG_CTS_CTL);
+	iowrite32(CTS_CTL_SEQUENCER_ENABLE, gth->base + REG_CTS_CTL);
+	/* wait on trigger status */
+	for (reg = 0, count = CTS_TRIG_WAITLOOP_DEPTH;
+	     count && !(reg & BIT(4)); count--) {
+		reg = ioread32(gth->base + REG_CTS_STAT);
+		cpu_relax();
+	}
+	if (!count)
+		dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n");
+
+	intel_th_gth_stop(gth, output, false);
+	intel_th_gth_start(gth, output);
 }
 
 /**
@@ -735,6 +813,7 @@ static struct intel_th_driver intel_th_gth_driver = {
 	.unassign	= intel_th_gth_unassign,
 	.set_output	= intel_th_gth_set_output,
 	.enable		= intel_th_gth_enable,
+	.trig_switch	= intel_th_gth_switch,
 	.disable	= intel_th_gth_disable,
 	.driver	= {
 		.name	= "gth",
diff --git a/drivers/hwtracing/intel_th/gth.h b/drivers/hwtracing/intel_th/gth.h
index 6f2b0b930875..bfcc0fd01177 100644
--- a/drivers/hwtracing/intel_th/gth.h
+++ b/drivers/hwtracing/intel_th/gth.h
@@ -49,6 +49,12 @@ enum {
 	REG_GTH_SCRPD3		= 0xec, /* ScratchPad[3] */
 	REG_TSCU_TSUCTRL	= 0x2000, /* TSCU control register */
 	REG_TSCU_TSCUSTAT	= 0x2004, /* TSCU status register */
+
+	/* Common Capture Sequencer (CTS) registers */
+	REG_CTS_C0S0_EN		= 0x30c0, /* clause_event_enable_c0s0 */
+	REG_CTS_C0S0_ACT	= 0x3180, /* clause_action_control_c0s0 */
+	REG_CTS_STAT		= 0x32a0, /* cts_status */
+	REG_CTS_CTL		= 0x32a4, /* cts_control */
 };
 
 /* waiting for Pipeline Empty bit(s) to assert for GTH */
@@ -57,4 +63,17 @@ enum {
 #define TSUCTRL_CTCRESYNC	BIT(0)
 #define TSCUSTAT_CTCSYNCING	BIT(1)
 
+/* waiting for Trigger status to assert for CTS */
+#define CTS_TRIG_WAITLOOP_DEPTH	10000
+
+#define CTS_EVENT_ENABLE_IF_ANYTHING	BIT(31)
+#define CTS_ACTION_CONTROL_STATE_OFF	27
+#define CTS_ACTION_CONTROL_SET_STATE(x)	\
+	(((x) & 0x1f) << CTS_ACTION_CONTROL_STATE_OFF)
+#define CTS_ACTION_CONTROL_TRIGGER	BIT(4)
+
+#define CTS_STATE_IDLE			0x10u
+
+#define CTS_CTL_SEQUENCER_ENABLE	BIT(0)
+
 #endif /* __INTEL_TH_GTH_H__ */
diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h
index 780206dc9012..0df480072b6c 100644
--- a/drivers/hwtracing/intel_th/intel_th.h
+++ b/drivers/hwtracing/intel_th/intel_th.h
@@ -8,6 +8,8 @@
 #ifndef __INTEL_TH_H__
 #define __INTEL_TH_H__
 
+#include <linux/irqreturn.h>
+
 /* intel_th_device device types */
 enum {
 	/* Devices that generate trace data */
@@ -18,6 +20,8 @@ enum {
 	INTEL_TH_SWITCH,
 };
 
+struct intel_th_device;
+
 /**
  * struct intel_th_output - descriptor INTEL_TH_OUTPUT type devices
  * @port:	output port number, assigned by the switch
@@ -25,6 +29,7 @@ enum {
  * @scratchpad:	scratchpad bits to flag when this output is enabled
  * @multiblock:	true for multiblock output configuration
  * @active:	true when this output is enabled
+ * @wait_empty:	wait for device pipeline to be empty
  *
  * Output port descriptor, used by switch driver to tell which output
  * port this output device corresponds to. Filled in at output device's
@@ -42,10 +47,12 @@ struct intel_th_output {
 /**
  * struct intel_th_drvdata - describes hardware capabilities and quirks
  * @tscu_enable:	device needs SW to enable time stamping unit
+ * @has_mintctl:	device has interrupt control (MINTCTL) register
  * @host_mode_only:	device can only operate in 'host debugger' mode
  */
 struct intel_th_drvdata {
 	unsigned int	tscu_enable        : 1,
+			has_mintctl        : 1,
 			host_mode_only     : 1;
 };
 
@@ -157,10 +164,13 @@ struct intel_th_driver {
 					    struct intel_th_device *othdev);
 	void			(*enable)(struct intel_th_device *thdev,
 					  struct intel_th_output *output);
+	void			(*trig_switch)(struct intel_th_device *thdev,
+					       struct intel_th_output *output);
 	void			(*disable)(struct intel_th_device *thdev,
 					   struct intel_th_output *output);
 	/* output ops */
-	void			(*irq)(struct intel_th_device *thdev);
+	irqreturn_t		(*irq)(struct intel_th_device *thdev);
+	void			(*wait_empty)(struct intel_th_device *thdev);
 	int			(*activate)(struct intel_th_device *thdev);
 	void			(*deactivate)(struct intel_th_device *thdev);
 	/* file_operations for those who want a device node */
@@ -213,21 +223,23 @@ static inline struct intel_th *to_intel_th(struct intel_th_device *thdev)
 
 struct intel_th *
 intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata,
-	       struct resource *devres, unsigned int ndevres, int irq);
+	       struct resource *devres, unsigned int ndevres);
 void intel_th_free(struct intel_th *th);
 
 int intel_th_driver_register(struct intel_th_driver *thdrv);
 void intel_th_driver_unregister(struct intel_th_driver *thdrv);
 
 int intel_th_trace_enable(struct intel_th_device *thdev);
+int intel_th_trace_switch(struct intel_th_device *thdev);
 int intel_th_trace_disable(struct intel_th_device *thdev);
 int intel_th_set_output(struct intel_th_device *thdev,
 			unsigned int master);
 int intel_th_output_enable(struct intel_th *th, unsigned int otype);
 
-enum {
+enum th_mmio_idx {
 	TH_MMIO_CONFIG = 0,
-	TH_MMIO_SW = 2,
+	TH_MMIO_SW = 1,
+	TH_MMIO_RTIT = 2,
 	TH_MMIO_END,
 };
 
@@ -237,6 +249,9 @@ enum {
 #define TH_CONFIGURABLE_MASTERS 256
 #define TH_MSC_MAX		2
 
+/* Maximum IRQ vectors */
+#define TH_NVEC_MAX		8
+
 /**
  * struct intel_th - Intel TH controller
  * @dev:	driver core's device
@@ -244,7 +259,7 @@ enum {
  * @hub:	"switch" subdevice (GTH)
  * @resource:	resources of the entire controller
  * @num_thdevs:	number of devices in the @thdev array
- * @num_resources:	number or resources in the @resource array
+ * @num_resources:	number of resources in the @resource array
  * @irq:	irq number
  * @id:		this Intel TH controller's device ID in the system
  * @major:	device node major for output devices
@@ -256,7 +271,7 @@ struct intel_th {
 	struct intel_th_device	*hub;
 	struct intel_th_drvdata	*drvdata;
 
-	struct resource		*resource;
+	struct resource		resource[TH_MMIO_END];
 	int			(*activate)(struct intel_th *);
 	void			(*deactivate)(struct intel_th *);
 	unsigned int		num_thdevs;
@@ -296,6 +311,9 @@ enum {
 	REG_TSCU_OFFSET		= 0x2000,
 	REG_TSCU_LENGTH		= 0x1000,
 
+	REG_CTS_OFFSET		= 0x3000,
+	REG_CTS_LENGTH		= 0x1000,
+
 	/* Software Trace Hub (STH) [0x4000..0x4fff] */
 	REG_STH_OFFSET		= 0x4000,
 	REG_STH_LENGTH		= 0x2000,
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index ba7aaf421f36..81bb54fa3ce8 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -29,28 +29,18 @@
 #define msc_dev(x) (&(x)->thdev->dev)
 
 /**
- * struct msc_block - multiblock mode block descriptor
- * @bdesc:	pointer to hardware descriptor (beginning of the block)
- * @addr:	physical address of the block
- */
-struct msc_block {
-	struct msc_block_desc	*bdesc;
-	dma_addr_t		addr;
-};
-
-/**
  * struct msc_window - multiblock mode window descriptor
  * @entry:	window list linkage (msc::win_list)
  * @pgoff:	page offset into the buffer that this window starts at
  * @nr_blocks:	number of blocks (pages) in this window
- * @block:	array of block descriptors
+ * @sgt:	array of block descriptors
  */
 struct msc_window {
 	struct list_head	entry;
 	unsigned long		pgoff;
 	unsigned int		nr_blocks;
 	struct msc		*msc;
-	struct msc_block	block[0];
+	struct sg_table		sgt;
 };
 
 /**
@@ -84,6 +74,8 @@ struct msc_iter {
  * @reg_base:		register window base address
  * @thdev:		intel_th_device pointer
  * @win_list:		list of windows in multiblock mode
+ * @single_sgt:		single mode buffer
+ * @cur_win:		current window
  * @nr_pages:		total number of pages allocated for this buffer
  * @single_sz:		amount of data in single mode
  * @single_wrap:	single mode wrap occurred
@@ -101,9 +93,12 @@ struct msc_iter {
  */
 struct msc {
 	void __iomem		*reg_base;
+	void __iomem		*msu_base;
 	struct intel_th_device	*thdev;
 
 	struct list_head	win_list;
+	struct sg_table		single_sgt;
+	struct msc_window	*cur_win;
 	unsigned long		nr_pages;
 	unsigned long		single_sz;
 	unsigned int		single_wrap : 1;
@@ -120,7 +115,8 @@ struct msc {
 
 	/* config */
 	unsigned int		enabled : 1,
-				wrap	: 1;
+				wrap	: 1,
+				do_irq	: 1;
 	unsigned int		mode;
 	unsigned int		burst_len;
 	unsigned int		index;
@@ -139,6 +135,49 @@ static inline bool msc_block_is_empty(struct msc_block_desc *bdesc)
 	return false;
 }
 
+static inline struct msc_block_desc *
+msc_win_block(struct msc_window *win, unsigned int block)
+{
+	return sg_virt(&win->sgt.sgl[block]);
+}
+
+static inline dma_addr_t
+msc_win_baddr(struct msc_window *win, unsigned int block)
+{
+	return sg_dma_address(&win->sgt.sgl[block]);
+}
+
+static inline unsigned long
+msc_win_bpfn(struct msc_window *win, unsigned int block)
+{
+	return msc_win_baddr(win, block) >> PAGE_SHIFT;
+}
+
+/**
+ * msc_is_last_win() - check if a window is the last one for a given MSC
+ * @win:	window
+ * Return:	true if @win is the last window in MSC's multiblock buffer
+ */
+static inline bool msc_is_last_win(struct msc_window *win)
+{
+	return win->entry.next == &win->msc->win_list;
+}
+
+/**
+ * msc_next_window() - return next window in the multiblock buffer
+ * @win:	current window
+ *
+ * Return:	window following the current one
+ */
+static struct msc_window *msc_next_window(struct msc_window *win)
+{
+	if (msc_is_last_win(win))
+		return list_first_entry(&win->msc->win_list, struct msc_window,
+					entry);
+
+	return list_next_entry(win, entry);
+}
+
 /**
  * msc_oldest_window() - locate the window with oldest data
  * @msc:	MSC device
@@ -150,9 +189,7 @@ static inline bool msc_block_is_empty(struct msc_block_desc *bdesc)
  */
 static struct msc_window *msc_oldest_window(struct msc *msc)
 {
-	struct msc_window *win;
-	u32 reg = ioread32(msc->reg_base + REG_MSU_MSC0NWSA);
-	unsigned long win_addr = (unsigned long)reg << PAGE_SHIFT;
+	struct msc_window *win, *next = msc_next_window(msc->cur_win);
 	unsigned int found = 0;
 
 	if (list_empty(&msc->win_list))
@@ -164,18 +201,18 @@ static struct msc_window *msc_oldest_window(struct msc *msc)
 	 * something like 2, in which case we're good
 	 */
 	list_for_each_entry(win, &msc->win_list, entry) {
-		if (win->block[0].addr == win_addr)
+		if (win == next)
 			found++;
 
 		/* skip the empty ones */
-		if (msc_block_is_empty(win->block[0].bdesc))
+		if (msc_block_is_empty(msc_win_block(win, 0)))
 			continue;
 
 		if (found)
 			return win;
 	}
 
-	return list_entry(msc->win_list.next, struct msc_window, entry);
+	return list_first_entry(&msc->win_list, struct msc_window, entry);
 }
 
 /**
@@ -187,7 +224,7 @@ static struct msc_window *msc_oldest_window(struct msc *msc)
 static unsigned int msc_win_oldest_block(struct msc_window *win)
 {
 	unsigned int blk;
-	struct msc_block_desc *bdesc = win->block[0].bdesc;
+	struct msc_block_desc *bdesc = msc_win_block(win, 0);
 
 	/* without wrapping, first block is the oldest */
 	if (!msc_block_wrapped(bdesc))
@@ -198,7 +235,7 @@ static unsigned int msc_win_oldest_block(struct msc_window *win)
 	 * oldest data for this window.
 	 */
 	for (blk = 0; blk < win->nr_blocks; blk++) {
-		bdesc = win->block[blk].bdesc;
+		bdesc = msc_win_block(win, blk);
 
 		if (msc_block_last_written(bdesc))
 			return blk;
@@ -207,34 +244,9 @@ static unsigned int msc_win_oldest_block(struct msc_window *win)
 	return 0;
 }
 
-/**
- * msc_is_last_win() - check if a window is the last one for a given MSC
- * @win:	window
- * Return:	true if @win is the last window in MSC's multiblock buffer
- */
-static inline bool msc_is_last_win(struct msc_window *win)
-{
-	return win->entry.next == &win->msc->win_list;
-}
-
-/**
- * msc_next_window() - return next window in the multiblock buffer
- * @win:	current window
- *
- * Return:	window following the current one
- */
-static struct msc_window *msc_next_window(struct msc_window *win)
-{
-	if (msc_is_last_win(win))
-		return list_entry(win->msc->win_list.next, struct msc_window,
-				  entry);
-
-	return list_entry(win->entry.next, struct msc_window, entry);
-}
-
 static struct msc_block_desc *msc_iter_bdesc(struct msc_iter *iter)
 {
-	return iter->win->block[iter->block].bdesc;
+	return msc_win_block(iter->win, iter->block);
 }
 
 static void msc_iter_init(struct msc_iter *iter)
@@ -467,13 +479,47 @@ static void msc_buffer_clear_hw_header(struct msc *msc)
 			offsetof(struct msc_block_desc, hw_tag);
 
 		for (blk = 0; blk < win->nr_blocks; blk++) {
-			struct msc_block_desc *bdesc = win->block[blk].bdesc;
+			struct msc_block_desc *bdesc = msc_win_block(win, blk);
 
 			memset(&bdesc->hw_tag, 0, hw_sz);
 		}
 	}
 }
 
+static int intel_th_msu_init(struct msc *msc)
+{
+	u32 mintctl, msusts;
+
+	if (!msc->do_irq)
+		return 0;
+
+	mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL);
+	mintctl |= msc->index ? M1BLIE : M0BLIE;
+	iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL);
+	if (mintctl != ioread32(msc->msu_base + REG_MSU_MINTCTL)) {
+		dev_info(msc_dev(msc), "MINTCTL ignores writes: no usable interrupts\n");
+		msc->do_irq = 0;
+		return 0;
+	}
+
+	msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS);
+	iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS);
+
+	return 0;
+}
+
+static void intel_th_msu_deinit(struct msc *msc)
+{
+	u32 mintctl;
+
+	if (!msc->do_irq)
+		return;
+
+	mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL);
+	mintctl &= msc->index ? ~M1BLIE : ~M0BLIE;
+	iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL);
+}
+
 /**
  * msc_configure() - set up MSC hardware
  * @msc:	the MSC device to configure
@@ -531,23 +577,14 @@ static int msc_configure(struct msc *msc)
  */
 static void msc_disable(struct msc *msc)
 {
-	unsigned long count;
 	u32 reg;
 
 	lockdep_assert_held(&msc->buf_mutex);
 
 	intel_th_trace_disable(msc->thdev);
 
-	for (reg = 0, count = MSC_PLE_WAITLOOP_DEPTH;
-	     count && !(reg & MSCSTS_PLE); count--) {
-		reg = ioread32(msc->reg_base + REG_MSU_MSC0STS);
-		cpu_relax();
-	}
-
-	if (!count)
-		dev_dbg(msc_dev(msc), "timeout waiting for MSC0 PLE\n");
-
 	if (msc->mode == MSC_MODE_SINGLE) {
+		reg = ioread32(msc->reg_base + REG_MSU_MSC0STS);
 		msc->single_wrap = !!(reg & MSCSTS_WRAPSTAT);
 
 		reg = ioread32(msc->reg_base + REG_MSU_MSC0MWP);
@@ -617,22 +654,45 @@ static void intel_th_msc_deactivate(struct intel_th_device *thdev)
  */
 static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size)
 {
+	unsigned long nr_pages = size >> PAGE_SHIFT;
 	unsigned int order = get_order(size);
 	struct page *page;
+	int ret;
 
 	if (!size)
 		return 0;
 
+	ret = sg_alloc_table(&msc->single_sgt, 1, GFP_KERNEL);
+	if (ret)
+		goto err_out;
+
+	ret = -ENOMEM;
 	page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!page)
-		return -ENOMEM;
+		goto err_free_sgt;
 
 	split_page(page, order);
-	msc->nr_pages = size >> PAGE_SHIFT;
+	sg_set_buf(msc->single_sgt.sgl, page_address(page), size);
+
+	ret = dma_map_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl, 1,
+			 DMA_FROM_DEVICE);
+	if (ret < 0)
+		goto err_free_pages;
+
+	msc->nr_pages = nr_pages;
 	msc->base = page_address(page);
-	msc->base_addr = page_to_phys(page);
+	msc->base_addr = sg_dma_address(msc->single_sgt.sgl);
 
 	return 0;
+
+err_free_pages:
+	__free_pages(page, order);
+
+err_free_sgt:
+	sg_free_table(&msc->single_sgt);
+
+err_out:
+	return ret;
 }
 
 /**
@@ -643,6 +703,10 @@ static void msc_buffer_contig_free(struct msc *msc)
 {
 	unsigned long off;
 
+	dma_unmap_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl,
+		     1, DMA_FROM_DEVICE);
+	sg_free_table(&msc->single_sgt);
+
 	for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
 		struct page *page = virt_to_page(msc->base + off);
 
@@ -669,6 +733,40 @@ static struct page *msc_buffer_contig_get_page(struct msc *msc,
 	return virt_to_page(msc->base + (pgoff << PAGE_SHIFT));
 }
 
+static int __msc_buffer_win_alloc(struct msc_window *win,
+				  unsigned int nr_blocks)
+{
+	struct scatterlist *sg_ptr;
+	void *block;
+	int i, ret;
+
+	ret = sg_alloc_table(&win->sgt, nr_blocks, GFP_KERNEL);
+	if (ret)
+		return -ENOMEM;
+
+	for_each_sg(win->sgt.sgl, sg_ptr, nr_blocks, i) {
+		block = dma_alloc_coherent(msc_dev(win->msc)->parent->parent,
+					  PAGE_SIZE, &sg_dma_address(sg_ptr),
+					  GFP_KERNEL);
+		if (!block)
+			goto err_nomem;
+
+		sg_set_buf(sg_ptr, block, PAGE_SIZE);
+	}
+
+	return nr_blocks;
+
+err_nomem:
+	for (i--; i >= 0; i--)
+		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
+				  msc_win_block(win, i),
+				  msc_win_baddr(win, i));
+
+	sg_free_table(&win->sgt);
+
+	return -ENOMEM;
+}
+
 /**
  * msc_buffer_win_alloc() - alloc a window for a multiblock mode
  * @msc:	MSC device
@@ -682,44 +780,49 @@ static struct page *msc_buffer_contig_get_page(struct msc *msc,
 static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
 {
 	struct msc_window *win;
-	unsigned long size = PAGE_SIZE;
-	int i, ret = -ENOMEM;
+	int ret = -ENOMEM, i;
 
 	if (!nr_blocks)
 		return 0;
 
-	win = kzalloc(offsetof(struct msc_window, block[nr_blocks]),
-		      GFP_KERNEL);
+	/*
+	 * This limitation hold as long as we need random access to the
+	 * block. When that changes, this can go away.
+	 */
+	if (nr_blocks > SG_MAX_SINGLE_ALLOC)
+		return -EINVAL;
+
+	win = kzalloc(sizeof(*win), GFP_KERNEL);
 	if (!win)
 		return -ENOMEM;
 
+	win->msc = msc;
+
 	if (!list_empty(&msc->win_list)) {
-		struct msc_window *prev = list_entry(msc->win_list.prev,
-						     struct msc_window, entry);
+		struct msc_window *prev = list_last_entry(&msc->win_list,
+							  struct msc_window,
+							  entry);
 
+		/* This works as long as blocks are page-sized */
 		win->pgoff = prev->pgoff + prev->nr_blocks;
 	}
 
-	for (i = 0; i < nr_blocks; i++) {
-		win->block[i].bdesc =
-			dma_alloc_coherent(msc_dev(msc)->parent->parent, size,
-					   &win->block[i].addr, GFP_KERNEL);
-
-		if (!win->block[i].bdesc)
-			goto err_nomem;
+	ret = __msc_buffer_win_alloc(win, nr_blocks);
+	if (ret < 0)
+		goto err_nomem;
 
 #ifdef CONFIG_X86
+	for (i = 0; i < ret; i++)
 		/* Set the page as uncached */
-		set_memory_uc((unsigned long)win->block[i].bdesc, 1);
+		set_memory_uc((unsigned long)msc_win_block(win, i), 1);
 #endif
-	}
 
-	win->msc = msc;
-	win->nr_blocks = nr_blocks;
+	win->nr_blocks = ret;
 
 	if (list_empty(&msc->win_list)) {
-		msc->base = win->block[0].bdesc;
-		msc->base_addr = win->block[0].addr;
+		msc->base = msc_win_block(win, 0);
+		msc->base_addr = msc_win_baddr(win, 0);
+		msc->cur_win = win;
 	}
 
 	list_add_tail(&win->entry, &msc->win_list);
@@ -728,19 +831,25 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
 	return 0;
 
 err_nomem:
-	for (i--; i >= 0; i--) {
-#ifdef CONFIG_X86
-		/* Reset the page to write-back before releasing */
-		set_memory_wb((unsigned long)win->block[i].bdesc, 1);
-#endif
-		dma_free_coherent(msc_dev(msc)->parent->parent, size,
-				  win->block[i].bdesc, win->block[i].addr);
-	}
 	kfree(win);
 
 	return ret;
 }
 
+static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
+{
+	int i;
+
+	for (i = 0; i < win->nr_blocks; i++) {
+		struct page *page = sg_page(&win->sgt.sgl[i]);
+
+		page->mapping = NULL;
+		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
+				  msc_win_block(win, i), msc_win_baddr(win, i));
+	}
+	sg_free_table(&win->sgt);
+}
+
 /**
  * msc_buffer_win_free() - free a window from MSC's window list
  * @msc:	MSC device
@@ -761,17 +870,13 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 		msc->base_addr = 0;
 	}
 
-	for (i = 0; i < win->nr_blocks; i++) {
-		struct page *page = virt_to_page(win->block[i].bdesc);
-
-		page->mapping = NULL;
 #ifdef CONFIG_X86
-		/* Reset the page to write-back before releasing */
-		set_memory_wb((unsigned long)win->block[i].bdesc, 1);
+	for (i = 0; i < win->nr_blocks; i++)
+		/* Reset the page to write-back */
+		set_memory_wb((unsigned long)msc_win_block(win, i), 1);
 #endif
-		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
-				  win->block[i].bdesc, win->block[i].addr);
-	}
+
+	__msc_buffer_win_free(msc, win);
 
 	kfree(win);
 }
@@ -798,19 +903,18 @@ static void msc_buffer_relink(struct msc *msc)
 		 */
 		if (msc_is_last_win(win)) {
 			sw_tag |= MSC_SW_TAG_LASTWIN;
-			next_win = list_entry(msc->win_list.next,
-					      struct msc_window, entry);
+			next_win = list_first_entry(&msc->win_list,
+						    struct msc_window, entry);
 		} else {
-			next_win = list_entry(win->entry.next,
-					      struct msc_window, entry);
+			next_win = list_next_entry(win, entry);
 		}
 
 		for (blk = 0; blk < win->nr_blocks; blk++) {
-			struct msc_block_desc *bdesc = win->block[blk].bdesc;
+			struct msc_block_desc *bdesc = msc_win_block(win, blk);
 
 			memset(bdesc, 0, sizeof(*bdesc));
 
-			bdesc->next_win = next_win->block[0].addr >> PAGE_SHIFT;
+			bdesc->next_win = msc_win_bpfn(next_win, 0);
 
 			/*
 			 * Similarly to last window, last block should point
@@ -818,11 +922,9 @@ static void msc_buffer_relink(struct msc *msc)
 			 */
 			if (blk == win->nr_blocks - 1) {
 				sw_tag |= MSC_SW_TAG_LASTBLK;
-				bdesc->next_blk =
-					win->block[0].addr >> PAGE_SHIFT;
+				bdesc->next_blk = msc_win_bpfn(win, 0);
 			} else {
-				bdesc->next_blk =
-					win->block[blk + 1].addr >> PAGE_SHIFT;
+				bdesc->next_blk = msc_win_bpfn(win, blk + 1);
 			}
 
 			bdesc->sw_tag = sw_tag;
@@ -997,7 +1099,7 @@ static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff)
 
 found:
 	pgoff -= win->pgoff;
-	return virt_to_page(win->block[pgoff].bdesc);
+	return sg_page(&win->sgt.sgl[pgoff]);
 }
 
 /**
@@ -1250,6 +1352,22 @@ static const struct file_operations intel_th_msc_fops = {
 	.owner		= THIS_MODULE,
 };
 
+static void intel_th_msc_wait_empty(struct intel_th_device *thdev)
+{
+	struct msc *msc = dev_get_drvdata(&thdev->dev);
+	unsigned long count;
+	u32 reg;
+
+	for (reg = 0, count = MSC_PLE_WAITLOOP_DEPTH;
+	     count && !(reg & MSCSTS_PLE); count--) {
+		reg = __raw_readl(msc->reg_base + REG_MSU_MSC0STS);
+		cpu_relax();
+	}
+
+	if (!count)
+		dev_dbg(msc_dev(msc), "timeout waiting for MSC0 PLE\n");
+}
+
 static int intel_th_msc_init(struct msc *msc)
 {
 	atomic_set(&msc->user_count, -1);
@@ -1266,6 +1384,39 @@ static int intel_th_msc_init(struct msc *msc)
 	return 0;
 }
 
+static void msc_win_switch(struct msc *msc)
+{
+	struct msc_window *last, *first;
+
+	first = list_first_entry(&msc->win_list, struct msc_window, entry);
+	last = list_last_entry(&msc->win_list, struct msc_window, entry);
+
+	if (msc_is_last_win(msc->cur_win))
+		msc->cur_win = first;
+	else
+		msc->cur_win = list_next_entry(msc->cur_win, entry);
+
+	msc->base = msc_win_block(msc->cur_win, 0);
+	msc->base_addr = msc_win_baddr(msc->cur_win, 0);
+
+	intel_th_trace_switch(msc->thdev);
+}
+
+static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev)
+{
+	struct msc *msc = dev_get_drvdata(&thdev->dev);
+	u32 msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS);
+	u32 mask = msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST;
+
+	if (!(msusts & mask)) {
+		if (msc->enabled)
+			return IRQ_HANDLED;
+		return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
+}
+
 static const char * const msc_mode[] = {
 	[MSC_MODE_SINGLE]	= "single",
 	[MSC_MODE_MULTI]	= "multi",
@@ -1440,10 +1591,38 @@ free_win:
 
 static DEVICE_ATTR_RW(nr_pages);
 
+static ssize_t
+win_switch_store(struct device *dev, struct device_attribute *attr,
+		 const char *buf, size_t size)
+{
+	struct msc *msc = dev_get_drvdata(dev);
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val != 1)
+		return -EINVAL;
+
+	mutex_lock(&msc->buf_mutex);
+	if (msc->mode != MSC_MODE_MULTI)
+		ret = -ENOTSUPP;
+	else
+		msc_win_switch(msc);
+	mutex_unlock(&msc->buf_mutex);
+
+	return ret ? ret : size;
+}
+
+static DEVICE_ATTR_WO(win_switch);
+
 static struct attribute *msc_output_attrs[] = {
 	&dev_attr_wrap.attr,
 	&dev_attr_mode.attr,
 	&dev_attr_nr_pages.attr,
+	&dev_attr_win_switch.attr,
 	NULL,
 };
 
@@ -1471,10 +1650,19 @@ static int intel_th_msc_probe(struct intel_th_device *thdev)
 	if (!msc)
 		return -ENOMEM;
 
+	res = intel_th_device_get_resource(thdev, IORESOURCE_IRQ, 1);
+	if (!res)
+		msc->do_irq = 1;
+
 	msc->index = thdev->id;
 
 	msc->thdev = thdev;
 	msc->reg_base = base + msc->index * 0x100;
+	msc->msu_base = base;
+
+	err = intel_th_msu_init(msc);
+	if (err)
+		return err;
 
 	err = intel_th_msc_init(msc);
 	if (err)
@@ -1491,6 +1679,7 @@ static void intel_th_msc_remove(struct intel_th_device *thdev)
 	int ret;
 
 	intel_th_msc_deactivate(thdev);
+	intel_th_msu_deinit(msc);
 
 	/*
 	 * Buffers should not be used at this point except if the
@@ -1504,6 +1693,8 @@ static void intel_th_msc_remove(struct intel_th_device *thdev)
 static struct intel_th_driver intel_th_msc_driver = {
 	.probe	= intel_th_msc_probe,
 	.remove	= intel_th_msc_remove,
+	.irq		= intel_th_msc_interrupt,
+	.wait_empty	= intel_th_msc_wait_empty,
 	.activate	= intel_th_msc_activate,
 	.deactivate	= intel_th_msc_deactivate,
 	.fops	= &intel_th_msc_fops,
diff --git a/drivers/hwtracing/intel_th/msu.h b/drivers/hwtracing/intel_th/msu.h
index 9cc8aced6116..574c16004cb2 100644
--- a/drivers/hwtracing/intel_th/msu.h
+++ b/drivers/hwtracing/intel_th/msu.h
@@ -11,6 +11,7 @@
 enum {
 	REG_MSU_MSUPARAMS	= 0x0000,
 	REG_MSU_MSUSTS		= 0x0008,
+	REG_MSU_MINTCTL		= 0x0004, /* MSU-global interrupt control */
 	REG_MSU_MSC0CTL		= 0x0100, /* MSC0 control */
 	REG_MSU_MSC0STS		= 0x0104, /* MSC0 status */
 	REG_MSU_MSC0BAR		= 0x0108, /* MSC0 output base address */
@@ -28,6 +29,8 @@ enum {
 
 /* MSUSTS bits */
 #define MSUSTS_MSU_INT	BIT(0)
+#define MSUSTS_MSC0BLAST	BIT(16)
+#define MSUSTS_MSC1BLAST	BIT(24)
 
 /* MSCnCTL bits */
 #define MSC_EN		BIT(0)
@@ -36,6 +39,11 @@ enum {
 #define MSC_MODE	(BIT(4) | BIT(5))
 #define MSC_LEN		(BIT(8) | BIT(9) | BIT(10))
 
+/* MINTCTL bits */
+#define MICDE		BIT(0)
+#define M0BLIE		BIT(16)
+#define M1BLIE		BIT(24)
+
 /* MSC operating modes (MSC_MODE) */
 enum {
 	MSC_MODE_SINGLE	= 0,
@@ -87,7 +95,7 @@ static inline unsigned long msc_data_sz(struct msc_block_desc *bdesc)
 
 static inline bool msc_block_wrapped(struct msc_block_desc *bdesc)
 {
-	if (bdesc->hw_tag & MSC_HW_TAG_BLOCKWRAP)
+	if (bdesc->hw_tag & (MSC_HW_TAG_BLOCKWRAP | MSC_HW_TAG_WINWRAP))
 		return true;
 
 	return false;
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 70f2cb90adc5..f1228708f2a2 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -17,7 +17,13 @@
 
 #define DRIVER_NAME "intel_th_pci"
 
-#define BAR_MASK (BIT(TH_MMIO_CONFIG) | BIT(TH_MMIO_SW))
+enum {
+	TH_PCI_CONFIG_BAR	= 0,
+	TH_PCI_STH_SW_BAR	= 2,
+	TH_PCI_RTIT_BAR		= 4,
+};
+
+#define BAR_MASK (BIT(TH_PCI_CONFIG_BAR) | BIT(TH_PCI_STH_SW_BAR))
 
 #define PCI_REG_NPKDSC	0x80
 #define NPKDSC_TSACT	BIT(5)
@@ -66,8 +72,12 @@ static int intel_th_pci_probe(struct pci_dev *pdev,
 			      const struct pci_device_id *id)
 {
 	struct intel_th_drvdata *drvdata = (void *)id->driver_data;
+	struct resource resource[TH_MMIO_END + TH_NVEC_MAX] = {
+		[TH_MMIO_CONFIG]	= pdev->resource[TH_PCI_CONFIG_BAR],
+		[TH_MMIO_SW]		= pdev->resource[TH_PCI_STH_SW_BAR],
+	};
+	int err, r = TH_MMIO_SW + 1, i;
 	struct intel_th *th;
-	int err;
 
 	err = pcim_enable_device(pdev);
 	if (err)
@@ -77,8 +87,19 @@ static int intel_th_pci_probe(struct pci_dev *pdev,
 	if (err)
 		return err;
 
-	th = intel_th_alloc(&pdev->dev, drvdata, pdev->resource,
-			    DEVICE_COUNT_RESOURCE, pdev->irq);
+	if (pdev->resource[TH_PCI_RTIT_BAR].start) {
+		resource[TH_MMIO_RTIT] = pdev->resource[TH_PCI_RTIT_BAR];
+		r++;
+	}
+
+	err = pci_alloc_irq_vectors(pdev, 1, 8, PCI_IRQ_ALL_TYPES);
+	if (err > 0)
+		for (i = 0; i < err; i++, r++) {
+			resource[r].flags = IORESOURCE_IRQ;
+			resource[r].start = pci_irq_vector(pdev, i);
+		}
+
+	th = intel_th_alloc(&pdev->dev, drvdata, resource, r);
 	if (IS_ERR(th))
 		return PTR_ERR(th);
 
@@ -95,10 +116,13 @@ static void intel_th_pci_remove(struct pci_dev *pdev)
 	struct intel_th *th = pci_get_drvdata(pdev);
 
 	intel_th_free(th);
+
+	pci_free_irq_vectors(pdev);
 }
 
 static const struct intel_th_drvdata intel_th_2x = {
 	.tscu_enable	= 1,
+	.has_mintctl	= 1,
 };
 
 static const struct pci_device_id intel_th_pci_id_table[] = {