8 files changed, 560 insertions, 150 deletions

diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index 8da567abc0ce..1a023e30488c 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -101,17 +101,53 @@ out_pm:
 	return ret;
 }
 
+static void intel_th_device_remove(struct intel_th_device *thdev);
+
 static int intel_th_remove(struct device *dev)
 {
 	struct intel_th_driver *thdrv = to_intel_th_driver(dev->driver);
 	struct intel_th_device *thdev = to_intel_th_device(dev);
-	struct intel_th_device *hub = to_intel_th_device(dev->parent);
+	struct intel_th_device *hub = to_intel_th_hub(thdev);
 	int err;
 
 	if (thdev->type == INTEL_TH_SWITCH) {
+		struct intel_th *th = to_intel_th(hub);
+		int i, lowest;
+
+		/* disconnect outputs */
 		err = device_for_each_child(dev, thdev, intel_th_child_remove);
 		if (err)
 			return err;
+
+		/*
+		 * Remove outputs, that is, hub's children: they are created
+		 * at hub's probe time by having the hub call
+		 * intel_th_output_enable() for each of them.
+		 */
+		for (i = 0, lowest = -1; i < th->num_thdevs; i++) {
+			/*
+			 * Move the non-output devices from higher up the
+			 * th->thdev[] array to lower positions to maintain
+			 * a contiguous array.
+			 */
+			if (th->thdev[i]->type != INTEL_TH_OUTPUT) {
+				if (lowest >= 0) {
+					th->thdev[lowest] = th->thdev[i];
+					th->thdev[i] = NULL;
+					++lowest;
+				}
+
+				continue;
+			}
+
+			if (lowest == -1)
+				lowest = i;
+
+			intel_th_device_remove(th->thdev[i]);
+			th->thdev[i] = NULL;
+		}
+
+		th->num_thdevs = lowest;
 	}
 
 	if (thdrv->attr_group)
@@ -156,21 +192,6 @@ static struct device_type intel_th_source_device_type = {
 	.release	= intel_th_device_release,
 };
 
-static struct intel_th *to_intel_th(struct intel_th_device *thdev)
-{
-	/*
-	 * subdevice tree is flat: if this one is not a switch, its
-	 * parent must be
-	 */
-	if (thdev->type != INTEL_TH_SWITCH)
-		thdev = to_intel_th_hub(thdev);
-
-	if (WARN_ON_ONCE(!thdev || thdev->type != INTEL_TH_SWITCH))
-		return NULL;
-
-	return dev_get_drvdata(thdev->dev.parent);
-}
-
 static char *intel_th_output_devnode(struct device *dev, umode_t *mode,
 				     kuid_t *uid, kgid_t *gid)
 {
@@ -205,6 +226,7 @@ static int intel_th_output_activate(struct intel_th_device *thdev)
 {
 	struct intel_th_driver *thdrv =
 		to_intel_th_driver_or_null(thdev->dev.driver);
+	struct intel_th *th = to_intel_th(thdev);
 	int ret = 0;
 
 	if (!thdrv)
@@ -215,15 +237,28 @@ static int intel_th_output_activate(struct intel_th_device *thdev)
 
 	pm_runtime_get_sync(&thdev->dev);
 
+	if (th->activate)
+		ret = th->activate(th);
+	if (ret)
+		goto fail_put;
+
 	if (thdrv->activate)
 		ret = thdrv->activate(thdev);
 	else
 		intel_th_trace_enable(thdev);
 
-	if (ret) {
-		pm_runtime_put(&thdev->dev);
-		module_put(thdrv->driver.owner);
-	}
+	if (ret)
+		goto fail_deactivate;
+
+	return 0;
+
+fail_deactivate:
+	if (th->deactivate)
+		th->deactivate(th);
+
+fail_put:
+	pm_runtime_put(&thdev->dev);
+	module_put(thdrv->driver.owner);
 
 	return ret;
 }
@@ -232,6 +267,7 @@ static void intel_th_output_deactivate(struct intel_th_device *thdev)
 {
 	struct intel_th_driver *thdrv =
 		to_intel_th_driver_or_null(thdev->dev.driver);
+	struct intel_th *th = to_intel_th(thdev);
 
 	if (!thdrv)
 		return;
@@ -241,6 +277,9 @@ static void intel_th_output_deactivate(struct intel_th_device *thdev)
 	else
 		intel_th_trace_disable(thdev);
 
+	if (th->deactivate)
+		th->deactivate(th);
+
 	pm_runtime_put(&thdev->dev);
 	module_put(thdrv->driver.owner);
 }
@@ -326,10 +365,10 @@ intel_th_device_alloc(struct intel_th *th, unsigned int type, const char *name,
 	struct device *parent;
 	struct intel_th_device *thdev;
 
-	if (type == INTEL_TH_SWITCH)
-		parent = th->dev;
-	else
+	if (type == INTEL_TH_OUTPUT)
 		parent = &th->hub->dev;
+	else
+		parent = th->dev;
 
 	thdev = kzalloc(sizeof(*thdev) + strlen(name) + 1, GFP_KERNEL);
 	if (!thdev)
@@ -392,13 +431,14 @@ static const struct intel_th_subdevice {
 	unsigned		otype;
 	unsigned		scrpd;
 	int			id;
-} intel_th_subdevices[TH_SUBDEVICE_MAX] = {
+} intel_th_subdevices[] = {
 	{
 		.nres	= 1,
 		.res	= {
 			{
+				/* Handle TSCU from GTH driver */
 				.start	= REG_GTH_OFFSET,
-				.end	= REG_GTH_OFFSET + REG_GTH_LENGTH - 1,
+				.end	= REG_TSCU_OFFSET + REG_TSCU_LENGTH - 1,
 				.flags	= IORESOURCE_MEM,
 			},
 		},
@@ -483,6 +523,21 @@ static const struct intel_th_subdevice {
 		.nres	= 1,
 		.res	= {
 			{
+				.start	= REG_PTI_OFFSET,
+				.end	= REG_PTI_OFFSET + REG_PTI_LENGTH - 1,
+				.flags	= IORESOURCE_MEM,
+			},
+		},
+		.id	= -1,
+		.name	= "lpp",
+		.type	= INTEL_TH_OUTPUT,
+		.otype	= GTH_LPP,
+		.scrpd	= SCRPD_PTI_IS_PRIM_DEST,
+	},
+	{
+		.nres	= 1,
+		.res	= {
+			{
 				.start	= REG_DCIH_OFFSET,
 				.end	= REG_DCIH_OFFSET + REG_DCIH_LENGTH - 1,
 				.flags	= IORESOURCE_MEM,
@@ -526,98 +581,182 @@ static inline void intel_th_request_hub_module_flush(struct intel_th *th)
 }
 #endif /* CONFIG_MODULES */
 
-static int intel_th_populate(struct intel_th *th, struct resource *devres,
-			     unsigned int ndevres, int irq)
+static struct intel_th_device *
+intel_th_subdevice_alloc(struct intel_th *th,
+			 const struct intel_th_subdevice *subdev)
 {
+	struct intel_th_device *thdev;
 	struct resource res[3];
 	unsigned int req = 0;
-	int src, dst, err;
+	int r, err;
 
-	/* create devices for each intel_th_subdevice */
-	for (src = 0, dst = 0; src < ARRAY_SIZE(intel_th_subdevices); src++) {
-		const struct intel_th_subdevice *subdev =
-			&intel_th_subdevices[src];
-		struct intel_th_device *thdev;
-		int r;
+	thdev = intel_th_device_alloc(th, subdev->type, subdev->name,
+				      subdev->id);
+	if (!thdev)
+		return ERR_PTR(-ENOMEM);
 
-		/* only allow SOURCE and SWITCH devices in host mode */
-		if (host_mode && subdev->type == INTEL_TH_OUTPUT)
-			continue;
+	thdev->drvdata = th->drvdata;
+
+	memcpy(res, subdev->res,
+	       sizeof(struct resource) * subdev->nres);
+
+	for (r = 0; r < subdev->nres; r++) {
+		struct resource *devres = th->resource;
+		int bar = TH_MMIO_CONFIG;
+
+		/*
+		 * Take .end == 0 to mean 'take the whole bar',
+		 * .start then tells us which bar it is. Default to
+		 * TH_MMIO_CONFIG.
+		 */
+		if (!res[r].end && res[r].flags == IORESOURCE_MEM) {
+			bar = res[r].start;
+			res[r].start = 0;
+			res[r].end = resource_size(&devres[bar]) - 1;
+		}
+
+		if (res[r].flags & IORESOURCE_MEM) {
+			res[r].start	+= devres[bar].start;
+			res[r].end	+= devres[bar].start;
 
-		thdev = intel_th_device_alloc(th, subdev->type, subdev->name,
-					      subdev->id);
-		if (!thdev) {
-			err = -ENOMEM;
-			goto kill_subdevs;
+			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;
 		}
+	}
 
-		memcpy(res, subdev->res,
-		       sizeof(struct resource) * subdev->nres);
+	err = intel_th_device_add_resources(thdev, res, subdev->nres);
+	if (err) {
+		put_device(&thdev->dev);
+		goto fail_put_device;
+	}
 
-		for (r = 0; r < subdev->nres; r++) {
-			int bar = TH_MMIO_CONFIG;
+	if (subdev->type == INTEL_TH_OUTPUT) {
+		thdev->dev.devt = MKDEV(th->major, th->num_thdevs);
+		thdev->output.type = subdev->otype;
+		thdev->output.port = -1;
+		thdev->output.scratchpad = subdev->scrpd;
+	} else if (subdev->type == INTEL_TH_SWITCH) {
+		thdev->host_mode = host_mode;
+		th->hub = thdev;
+	}
 
-			/*
-			 * Take .end == 0 to mean 'take the whole bar',
-			 * .start then tells us which bar it is. Default to
-			 * TH_MMIO_CONFIG.
-			 */
-			if (!res[r].end && res[r].flags == IORESOURCE_MEM) {
-				bar = res[r].start;
-				res[r].start = 0;
-				res[r].end = resource_size(&devres[bar]) - 1;
-			}
+	err = device_add(&thdev->dev);
+	if (err) {
+		put_device(&thdev->dev);
+		goto fail_free_res;
+	}
 
-			if (res[r].flags & IORESOURCE_MEM) {
-				res[r].start	+= devres[bar].start;
-				res[r].end	+= devres[bar].start;
+	/* need switch driver to be loaded to enumerate the rest */
+	if (subdev->type == INTEL_TH_SWITCH && !req) {
+		err = intel_th_request_hub_module(th);
+		if (!err)
+			req++;
+	}
 
-				dev_dbg(th->dev, "%s:%d @ %pR\n",
-					subdev->name, r, &res[r]);
-			} else if (res[r].flags & IORESOURCE_IRQ) {
-				res[r].start	= irq;
-			}
-		}
+	return thdev;
 
-		err = intel_th_device_add_resources(thdev, res, subdev->nres);
-		if (err) {
-			put_device(&thdev->dev);
-			goto kill_subdevs;
-		}
+fail_free_res:
+	kfree(thdev->resource);
 
-		if (subdev->type == INTEL_TH_OUTPUT) {
-			thdev->dev.devt = MKDEV(th->major, dst);
-			thdev->output.type = subdev->otype;
-			thdev->output.port = -1;
-			thdev->output.scratchpad = subdev->scrpd;
-		} else if (subdev->type == INTEL_TH_SWITCH) {
-			thdev->host_mode = host_mode;
-		}
+fail_put_device:
+	put_device(&thdev->dev);
+
+	return ERR_PTR(err);
+}
 
-		err = device_add(&thdev->dev);
-		if (err) {
-			put_device(&thdev->dev);
-			goto kill_subdevs;
+/**
+ * intel_th_output_enable() - find and enable a device for a given output type
+ * @th:		Intel TH instance
+ * @otype:	output type
+ *
+ * Go through the unallocated output devices, find the first one whos type
+ * matches @otype and instantiate it. These devices are removed when the hub
+ * device is removed, see intel_th_remove().
+ */
+int intel_th_output_enable(struct intel_th *th, unsigned int otype)
+{
+	struct intel_th_device *thdev;
+	int src = 0, dst = 0;
+
+	for (src = 0, dst = 0; dst <= th->num_thdevs; src++, dst++) {
+		for (; src < ARRAY_SIZE(intel_th_subdevices); src++) {
+			if (intel_th_subdevices[src].type != INTEL_TH_OUTPUT)
+				continue;
+
+			if (intel_th_subdevices[src].otype != otype)
+				continue;
+
+			break;
 		}
 
-		/* need switch driver to be loaded to enumerate the rest */
-		if (subdev->type == INTEL_TH_SWITCH && !req) {
-			th->hub = thdev;
-			err = intel_th_request_hub_module(th);
-			if (!err)
-				req++;
+		/* no unallocated matching subdevices */
+		if (src == ARRAY_SIZE(intel_th_subdevices))
+			return -ENODEV;
+
+		for (; dst < th->num_thdevs; dst++) {
+			if (th->thdev[dst]->type != INTEL_TH_OUTPUT)
+				continue;
+
+			if (th->thdev[dst]->output.type != otype)
+				continue;
+
+			break;
 		}
 
-		th->thdev[dst++] = thdev;
+		/*
+		 * intel_th_subdevices[src] matches our requirements and is
+		 * not matched in th::thdev[]
+		 */
+		if (dst == th->num_thdevs)
+			goto found;
 	}
 
+	return -ENODEV;
+
+found:
+	thdev = intel_th_subdevice_alloc(th, &intel_th_subdevices[src]);
+	if (IS_ERR(thdev))
+		return PTR_ERR(thdev);
+
+	th->thdev[th->num_thdevs++] = thdev;
+
 	return 0;
+}
+EXPORT_SYMBOL_GPL(intel_th_output_enable);
+
+static int intel_th_populate(struct intel_th *th)
+{
+	int src;
+
+	/* create devices for each intel_th_subdevice */
+	for (src = 0; src < ARRAY_SIZE(intel_th_subdevices); src++) {
+		const struct intel_th_subdevice *subdev =
+			&intel_th_subdevices[src];
+		struct intel_th_device *thdev;
+
+		/* only allow SOURCE and SWITCH devices in host mode */
+		if (host_mode && subdev->type == INTEL_TH_OUTPUT)
+			continue;
 
-kill_subdevs:
-	for (; dst >= 0; dst--)
-		intel_th_device_remove(th->thdev[dst]);
+		/*
+		 * don't enable port OUTPUTs in this path; SWITCH enables them
+		 * via intel_th_output_enable()
+		 */
+		if (subdev->type == INTEL_TH_OUTPUT &&
+		    subdev->otype != GTH_NONE)
+			continue;
+
+		thdev = intel_th_subdevice_alloc(th, subdev);
+		/* note: caller should free subdevices from th::thdev[] */
+		if (IS_ERR(thdev))
+			return PTR_ERR(thdev);
+
+		th->thdev[th->num_thdevs++] = thdev;
+	}
 
-	return err;
+	return 0;
 }
 
 static int match_devt(struct device *dev, void *data)
@@ -670,8 +809,8 @@ static const struct file_operations intel_th_output_fops = {
  * @irq:	irq number
  */
 struct intel_th *
-intel_th_alloc(struct device *dev, struct resource *devres,
-	       unsigned int ndevres, int irq)
+intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata,
+	       struct resource *devres, unsigned int ndevres, int irq)
 {
 	struct intel_th *th;
 	int err;
@@ -693,6 +832,11 @@ intel_th_alloc(struct device *dev, struct resource *devres,
 		goto err_ida;
 	}
 	th->dev = dev;
+	th->drvdata = drvdata;
+
+	th->resource = devres;
+	th->num_resources = ndevres;
+	th->irq = irq;
 
 	dev_set_drvdata(dev, th);
 
@@ -700,18 +844,15 @@ intel_th_alloc(struct device *dev, struct resource *devres,
 	pm_runtime_put(dev);
 	pm_runtime_allow(dev);
 
-	err = intel_th_populate(th, devres, ndevres, irq);
-	if (err)
-		goto err_chrdev;
+	err = intel_th_populate(th);
+	if (err) {
+		/* free the subdevices and undo everything */
+		intel_th_free(th);
+		return ERR_PTR(err);
+	}
 
 	return th;
 
-err_chrdev:
-	pm_runtime_forbid(dev);
-
-	__unregister_chrdev(th->major, 0, TH_POSSIBLE_OUTPUTS,
-			    "intel_th/output");
-
 err_ida:
 	ida_simple_remove(&intel_th_ida, th->id);
 
@@ -727,11 +868,15 @@ void intel_th_free(struct intel_th *th)
 	int i;
 
 	intel_th_request_hub_module_flush(th);
-	for (i = 0; i < TH_SUBDEVICE_MAX; i++)
-		if (th->thdev[i] && th->thdev[i] != th->hub)
-			intel_th_device_remove(th->thdev[i]);
 
 	intel_th_device_remove(th->hub);
+	for (i = 0; i < th->num_thdevs; i++) {
+		if (th->thdev[i] != th->hub)
+			intel_th_device_remove(th->thdev[i]);
+		th->thdev[i] = NULL;
+	}
+
+	th->num_thdevs = 0;
 
 	pm_runtime_get_sync(th->dev);
 	pm_runtime_forbid(th->dev);
diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c
index dd32d0bad687..018678ec3c13 100644
--- a/drivers/hwtracing/intel_th/gth.c
+++ b/drivers/hwtracing/intel_th/gth.c
@@ -285,16 +285,16 @@ gth_output_parm_get(struct gth_device *gth, int port, unsigned int parm)
  */
 static int intel_th_gth_reset(struct gth_device *gth)
 {
-	u32 scratchpad;
+	u32 reg;
 	int port, i;
 
-	scratchpad = ioread32(gth->base + REG_GTH_SCRPD0);
-	if (scratchpad & SCRPD_DEBUGGER_IN_USE)
+	reg = ioread32(gth->base + REG_GTH_SCRPD0);
+	if (reg & SCRPD_DEBUGGER_IN_USE)
 		return -EBUSY;
 
 	/* Always save/restore STH and TU registers in S0ix entry/exit */
-	scratchpad |= SCRPD_STH_IS_ENABLED | SCRPD_TRIGGER_IS_ENABLED;
-	iowrite32(scratchpad, gth->base + REG_GTH_SCRPD0);
+	reg |= SCRPD_STH_IS_ENABLED | SCRPD_TRIGGER_IS_ENABLED;
+	iowrite32(reg, gth->base + REG_GTH_SCRPD0);
 
 	/* output ports */
 	for (port = 0; port < 8; port++) {
@@ -512,6 +512,15 @@ static void intel_th_gth_disable(struct intel_th_device *thdev,
 	iowrite32(reg, gth->base + REG_GTH_SCRPD0);
 }
 
+static void gth_tscu_resync(struct gth_device *gth)
+{
+	u32 reg;
+
+	reg = ioread32(gth->base + REG_TSCU_TSUCTRL);
+	reg &= ~TSUCTRL_CTCRESYNC;
+	iowrite32(reg, gth->base + REG_TSCU_TSUCTRL);
+}
+
 /**
  * intel_th_gth_enable() - enable tracing to an output device
  * @thdev:	GTH device
@@ -524,6 +533,7 @@ static void intel_th_gth_enable(struct intel_th_device *thdev,
 				struct intel_th_output *output)
 {
 	struct gth_device *gth = dev_get_drvdata(&thdev->dev);
+	struct intel_th *th = to_intel_th(thdev);
 	u32 scr = 0xfc0000, scrpd;
 	int master;
 
@@ -539,6 +549,9 @@ static void intel_th_gth_enable(struct intel_th_device *thdev,
 	output->active = true;
 	spin_unlock(&gth->gth_lock);
 
+	if (INTEL_TH_CAP(th, tscu_enable))
+		gth_tscu_resync(gth);
+
 	scrpd = ioread32(gth->base + REG_GTH_SCRPD0);
 	scrpd |= output->scratchpad;
 	iowrite32(scrpd, gth->base + REG_GTH_SCRPD0);
@@ -639,6 +652,7 @@ intel_th_gth_set_output(struct intel_th_device *thdev, unsigned int master)
 static int intel_th_gth_probe(struct intel_th_device *thdev)
 {
 	struct device *dev = &thdev->dev;
+	struct intel_th *th = dev_get_drvdata(dev->parent);
 	struct gth_device *gth;
 	struct resource *res;
 	void __iomem *base;
@@ -660,6 +674,8 @@ static int intel_th_gth_probe(struct intel_th_device *thdev)
 	gth->base = base;
 	spin_lock_init(&gth->gth_lock);
 
+	dev_set_drvdata(dev, gth);
+
 	/*
 	 * Host mode can be signalled via SW means or via SCRPD_DEBUGGER_IN_USE
 	 * bit. Either way, don't reset HW in this case, and don't export any
@@ -667,7 +683,7 @@ static int intel_th_gth_probe(struct intel_th_device *thdev)
 	 * drivers to ports, see intel_th_gth_assign().
 	 */
 	if (thdev->host_mode)
-		goto done;
+		return 0;
 
 	ret = intel_th_gth_reset(gth);
 	if (ret) {
@@ -676,7 +692,7 @@ static int intel_th_gth_probe(struct intel_th_device *thdev)
 
 		thdev->host_mode = true;
 
-		goto done;
+		return 0;
 	}
 
 	for (i = 0; i < TH_CONFIGURABLE_MASTERS + 1; i++)
@@ -687,6 +703,13 @@ static int intel_th_gth_probe(struct intel_th_device *thdev)
 		gth->output[i].index = i;
 		gth->output[i].port_type =
 			gth_output_parm_get(gth, i, TH_OUTPUT_PARM(port));
+		if (gth->output[i].port_type == GTH_NONE)
+			continue;
+
+		ret = intel_th_output_enable(th, gth->output[i].port_type);
+		/* -ENODEV is ok, we just won't have that device enumerated */
+		if (ret && ret != -ENODEV)
+			return ret;
 	}
 
 	if (intel_th_output_attributes(gth) ||
@@ -698,9 +721,6 @@ static int intel_th_gth_probe(struct intel_th_device *thdev)
 		return -ENOMEM;
 	}
 
-done:
-	dev_set_drvdata(dev, gth);
-
 	return 0;
 }
 
diff --git a/drivers/hwtracing/intel_th/gth.h b/drivers/hwtracing/intel_th/gth.h
index 56f0d2620577..f3d234251a12 100644
--- a/drivers/hwtracing/intel_th/gth.h
+++ b/drivers/hwtracing/intel_th/gth.h
@@ -55,9 +55,14 @@ enum {
 	REG_GTH_SCRPD1		= 0xe4, /* ScratchPad[1] */
 	REG_GTH_SCRPD2		= 0xe8, /* ScratchPad[2] */
 	REG_GTH_SCRPD3		= 0xec, /* ScratchPad[3] */
+	REG_TSCU_TSUCTRL	= 0x2000, /* TSCU control register */
+	REG_TSCU_TSCUSTAT	= 0x2004, /* TSCU status register */
 };
 
 /* waiting for Pipeline Empty bit(s) to assert for GTH */
 #define GTH_PLE_WAITLOOP_DEPTH	10000
 
+#define TSUCTRL_CTCRESYNC	BIT(0)
+#define TSCUSTAT_CTCSYNCING	BIT(1)
+
 #endif /* __INTEL_TH_GTH_H__ */
diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h
index 3096e7054f6d..99ad563fc40d 100644
--- a/drivers/hwtracing/intel_th/intel_th.h
+++ b/drivers/hwtracing/intel_th/intel_th.h
@@ -48,8 +48,19 @@ struct intel_th_output {
 };
 
 /**
+ * struct intel_th_drvdata - describes hardware capabilities and quirks
+ * @tscu_enable:	device needs SW to enable time stamping unit
+ */
+struct intel_th_drvdata {
+	unsigned int	tscu_enable        : 1;
+};
+
+#define INTEL_TH_CAP(_th, _cap) ((_th)->drvdata ? (_th)->drvdata->_cap : 0)
+
+/**
  * struct intel_th_device - device on the intel_th bus
  * @dev:		device
+ * @drvdata:		hardware capabilities/quirks
  * @resource:		array of resources available to this device
  * @num_resources:	number of resources in @resource array
  * @type:		INTEL_TH_{SOURCE,OUTPUT,SWITCH}
@@ -59,11 +70,12 @@ struct intel_th_output {
  * @name:		device name to match the driver
  */
 struct intel_th_device {
-	struct device	dev;
-	struct resource	*resource;
-	unsigned int	num_resources;
-	unsigned int	type;
-	int		id;
+	struct device		dev;
+	struct intel_th_drvdata *drvdata;
+	struct resource		*resource;
+	unsigned int		num_resources;
+	unsigned int		type;
+	int			id;
 
 	/* INTEL_TH_SWITCH specific */
 	bool			host_mode;
@@ -96,6 +108,17 @@ intel_th_device_get_resource(struct intel_th_device *thdev, unsigned int type,
 	return NULL;
 }
 
+/*
+ * GTH, output ports configuration
+ */
+enum {
+	GTH_NONE = 0,
+	GTH_MSU,	/* memory/usb */
+	GTH_CTP,	/* Common Trace Port */
+	GTH_LPP,	/* Low Power Path */
+	GTH_PTI,	/* MIPI-PTI */
+};
+
 /**
  * intel_th_output_assigned() - if an output device is assigned to a switch port
  * @thdev:	the output device
@@ -106,7 +129,8 @@ static inline bool
 intel_th_output_assigned(struct intel_th_device *thdev)
 {
 	return thdev->type == INTEL_TH_OUTPUT &&
-		thdev->output.port >= 0;
+		(thdev->output.port >= 0 ||
+		 thdev->output.type == GTH_NONE);
 }
 
 /**
@@ -161,8 +185,18 @@ struct intel_th_driver {
 #define to_intel_th_driver_or_null(_d)		\
 	((_d) ? to_intel_th_driver(_d) : NULL)
 
+/*
+ * Subdevice tree structure is as follows:
+ * + struct intel_th device (pci; dev_{get,set}_drvdata()
+ *   + struct intel_th_device INTEL_TH_SWITCH (GTH)
+ *     + struct intel_th_device INTEL_TH_OUTPUT (MSU, PTI)
+ *   + struct intel_th_device INTEL_TH_SOURCE (STH)
+ *
+ * In other words, INTEL_TH_OUTPUT devices are children of INTEL_TH_SWITCH;
+ * INTEL_TH_SWITCH and INTEL_TH_SOURCE are children of the intel_th device.
+ */
 static inline struct intel_th_device *
-to_intel_th_hub(struct intel_th_device *thdev)
+to_intel_th_parent(struct intel_th_device *thdev)
 {
 	struct device *parent = thdev->dev.parent;
 
@@ -172,9 +206,20 @@ to_intel_th_hub(struct intel_th_device *thdev)
 	return to_intel_th_device(parent);
 }
 
+static inline struct intel_th *to_intel_th(struct intel_th_device *thdev)
+{
+	if (thdev->type == INTEL_TH_OUTPUT)
+		thdev = to_intel_th_parent(thdev);
+
+	if (WARN_ON_ONCE(!thdev || thdev->type == INTEL_TH_OUTPUT))
+		return NULL;
+
+	return dev_get_drvdata(thdev->dev.parent);
+}
+
 struct intel_th *
-intel_th_alloc(struct device *dev, struct resource *devres,
-	       unsigned int ndevres, int irq);
+intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata,
+	       struct resource *devres, unsigned int ndevres, int irq);
 void intel_th_free(struct intel_th *th);
 
 int intel_th_driver_register(struct intel_th_driver *thdrv);
@@ -184,6 +229,7 @@ int intel_th_trace_enable(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 {
 	TH_MMIO_CONFIG = 0,
@@ -191,8 +237,9 @@ enum {
 	TH_MMIO_END,
 };
 
-#define TH_SUBDEVICE_MAX	6
 #define TH_POSSIBLE_OUTPUTS	8
+/* Total number of possible subdevices: outputs + GTH + STH */
+#define TH_SUBDEVICE_MAX	(TH_POSSIBLE_OUTPUTS + 2)
 #define TH_CONFIGURABLE_MASTERS 256
 #define TH_MSC_MAX		2
 
@@ -201,6 +248,10 @@ enum {
  * @dev:	driver core's device
  * @thdev:	subdevices
  * @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
+ * @irq:	irq number
  * @id:		this Intel TH controller's device ID in the system
  * @major:	device node major for output devices
  */
@@ -209,6 +260,14 @@ struct intel_th {
 
 	struct intel_th_device	*thdev[TH_SUBDEVICE_MAX];
 	struct intel_th_device	*hub;
+	struct intel_th_drvdata	*drvdata;
+
+	struct resource		*resource;
+	int			(*activate)(struct intel_th *);
+	void			(*deactivate)(struct intel_th *);
+	unsigned int		num_thdevs;
+	unsigned int		num_resources;
+	int			irq;
 
 	int			id;
 	int			major;
@@ -220,6 +279,17 @@ struct intel_th {
 #endif
 };
 
+static inline struct intel_th_device *
+to_intel_th_hub(struct intel_th_device *thdev)
+{
+	if (thdev->type == INTEL_TH_SWITCH)
+		return thdev;
+	else if (thdev->type == INTEL_TH_OUTPUT)
+		return to_intel_th_parent(thdev);
+
+	return to_intel_th(thdev)->hub;
+}
+
 /*
  * Register windows
  */
@@ -228,6 +298,10 @@ enum {
 	REG_GTH_OFFSET		= 0x0000,
 	REG_GTH_LENGTH		= 0x2000,
 
+	/* Timestamp counter unit (TSCU) */
+	REG_TSCU_OFFSET		= 0x2000,
+	REG_TSCU_LENGTH		= 0x1000,
+
 	/* Software Trace Hub (STH) [0x4000..0x4fff] */
 	REG_STH_OFFSET		= 0x4000,
 	REG_STH_LENGTH		= 0x2000,
@@ -250,16 +324,6 @@ enum {
 };
 
 /*
- * GTH, output ports configuration
- */
-enum {
-	GTH_NONE = 0,
-	GTH_MSU,	/* memory/usb */
-	GTH_CTP,	/* Common Trace Port */
-	GTH_PTI = 4,	/* MIPI-PTI */
-};
-
-/*
  * Scratchpad bits: tell firmware and external debuggers
  * what we are up to.
  */
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index dbbe31df74df..dfb57eaa9f22 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -709,17 +709,17 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
 	}
 
 	for (i = 0; i < nr_blocks; i++) {
-		win->block[i].bdesc = dma_alloc_coherent(msc_dev(msc), size,
-							 &win->block[i].addr,
-							 GFP_KERNEL);
+		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;
 
 #ifdef CONFIG_X86
 		/* Set the page as uncached */
 		set_memory_uc((unsigned long)win->block[i].bdesc, 1);
 #endif
-
-		if (!win->block[i].bdesc)
-			goto err_nomem;
 	}
 
 	win->msc = msc;
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 590cf90dd21a..bc9cebc30526 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -27,9 +27,53 @@
 
 #define BAR_MASK (BIT(TH_MMIO_CONFIG) | BIT(TH_MMIO_SW))
 
+#define PCI_REG_NPKDSC	0x80
+#define NPKDSC_TSACT	BIT(5)
+
+static int intel_th_pci_activate(struct intel_th *th)
+{
+	struct pci_dev *pdev = to_pci_dev(th->dev);
+	u32 npkdsc;
+	int err;
+
+	if (!INTEL_TH_CAP(th, tscu_enable))
+		return 0;
+
+	err = pci_read_config_dword(pdev, PCI_REG_NPKDSC, &npkdsc);
+	if (!err) {
+		npkdsc |= NPKDSC_TSACT;
+		err = pci_write_config_dword(pdev, PCI_REG_NPKDSC, npkdsc);
+	}
+
+	if (err)
+		dev_err(&pdev->dev, "failed to read NPKDSC register\n");
+
+	return err;
+}
+
+static void intel_th_pci_deactivate(struct intel_th *th)
+{
+	struct pci_dev *pdev = to_pci_dev(th->dev);
+	u32 npkdsc;
+	int err;
+
+	if (!INTEL_TH_CAP(th, tscu_enable))
+		return;
+
+	err = pci_read_config_dword(pdev, PCI_REG_NPKDSC, &npkdsc);
+	if (!err) {
+		npkdsc |= NPKDSC_TSACT;
+		err = pci_write_config_dword(pdev, PCI_REG_NPKDSC, npkdsc);
+	}
+
+	if (err)
+		dev_err(&pdev->dev, "failed to read NPKDSC register\n");
+}
+
 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 intel_th *th;
 	int err;
 
@@ -41,11 +85,16 @@ static int intel_th_pci_probe(struct pci_dev *pdev,
 	if (err)
 		return err;
 
-	th = intel_th_alloc(&pdev->dev, pdev->resource,
+	th = intel_th_alloc(&pdev->dev, drvdata, pdev->resource,
 			    DEVICE_COUNT_RESOURCE, pdev->irq);
 	if (IS_ERR(th))
 		return PTR_ERR(th);
 
+	th->activate   = intel_th_pci_activate;
+	th->deactivate = intel_th_pci_deactivate;
+
+	pci_set_master(pdev);
+
 	return 0;
 }
 
@@ -56,6 +105,10 @@ static void intel_th_pci_remove(struct pci_dev *pdev)
 	intel_th_free(th);
 }
 
+static const struct intel_th_drvdata intel_th_2x = {
+	.tscu_enable	= 1,
+};
+
 static const struct pci_device_id intel_th_pci_id_table[] = {
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9d26),
@@ -93,7 +146,17 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 	{
 		/* Gemini Lake */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e),
-		.driver_data = (kernel_ulong_t)0,
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Cannon Lake H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa326),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Cannon Lake LP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{ 0 },
 };
diff --git a/drivers/hwtracing/intel_th/pti.c b/drivers/hwtracing/intel_th/pti.c
index 35738b5bfccd..e96a1fcb57b2 100644
--- a/drivers/hwtracing/intel_th/pti.c
+++ b/drivers/hwtracing/intel_th/pti.c
@@ -1,7 +1,7 @@
 /*
  * Intel(R) Trace Hub PTI output driver
  *
- * Copyright (C) 2014-2015 Intel Corporation.
+ * Copyright (C) 2014-2016 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -34,6 +34,8 @@ struct pti_device {
 	unsigned int		freeclk;
 	unsigned int		clkdiv;
 	unsigned int		patgen;
+	unsigned int		lpp_dest_mask;
+	unsigned int		lpp_dest;
 };
 
 /* map PTI widths to MODE settings of PTI_CTL register */
@@ -163,6 +165,7 @@ static int intel_th_pti_activate(struct intel_th_device *thdev)
 		ctl |= PTI_FCEN;
 	ctl |= pti->mode << __ffs(PTI_MODE);
 	ctl |= pti->clkdiv << __ffs(PTI_CLKDIV);
+	ctl |= pti->lpp_dest << __ffs(LPP_DEST);
 
 	iowrite32(ctl, pti->base + REG_PTI_CTL);
 
@@ -192,6 +195,15 @@ static void read_hw_config(struct pti_device *pti)
 		pti->mode = pti_width_mode(4);
 	if (!pti->clkdiv)
 		pti->clkdiv = 1;
+
+	if (pti->thdev->output.type == GTH_LPP) {
+		if (ctl & LPP_PTIPRESENT)
+			pti->lpp_dest_mask |= LPP_DEST_PTI;
+		if (ctl & LPP_BSSBPRESENT)
+			pti->lpp_dest_mask |= LPP_DEST_EXI;
+		if (ctl & LPP_DEST)
+			pti->lpp_dest = 1;
+	}
 }
 
 static int intel_th_pti_probe(struct intel_th_device *thdev)
@@ -239,10 +251,103 @@ static struct intel_th_driver intel_th_pti_driver = {
 	},
 };
 
-module_driver(intel_th_pti_driver,
-	      intel_th_driver_register,
-	      intel_th_driver_unregister);
+static const char * const lpp_dest_str[] = { "pti", "exi" };
+
+static ssize_t lpp_dest_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct pti_device *pti = dev_get_drvdata(dev);
+	ssize_t ret = 0;
+	int i;
+
+	for (i = ARRAY_SIZE(lpp_dest_str) - 1; i >= 0; i--) {
+		const char *fmt = pti->lpp_dest == i ? "[%s] " : "%s ";
+
+		if (!(pti->lpp_dest_mask & BIT(i)))
+			continue;
+
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret,
+				 fmt, lpp_dest_str[i]);
+	}
+
+	if (ret)
+		buf[ret - 1] = '\n';
+
+	return ret;
+}
+
+static ssize_t lpp_dest_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	struct pti_device *pti = dev_get_drvdata(dev);
+	ssize_t ret = -EINVAL;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lpp_dest_str); i++)
+		if (sysfs_streq(buf, lpp_dest_str[i]))
+			break;
+
+	if (i < ARRAY_SIZE(lpp_dest_str) && pti->lpp_dest_mask & BIT(i)) {
+		pti->lpp_dest = i;
+		ret = size;
+	}
+
+	return ret;
+}
+
+static DEVICE_ATTR_RW(lpp_dest);
+
+static struct attribute *lpp_output_attrs[] = {
+	&dev_attr_mode.attr,
+	&dev_attr_freerunning_clock.attr,
+	&dev_attr_clock_divider.attr,
+	&dev_attr_lpp_dest.attr,
+	NULL,
+};
+
+static struct attribute_group lpp_output_group = {
+	.attrs	= lpp_output_attrs,
+};
+
+static struct intel_th_driver intel_th_lpp_driver = {
+	.probe		= intel_th_pti_probe,
+	.remove		= intel_th_pti_remove,
+	.activate	= intel_th_pti_activate,
+	.deactivate	= intel_th_pti_deactivate,
+	.attr_group	= &lpp_output_group,
+	.driver	= {
+		.name	= "lpp",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init intel_th_pti_lpp_init(void)
+{
+	int err;
+
+	err = intel_th_driver_register(&intel_th_pti_driver);
+	if (err)
+		return err;
+
+	err = intel_th_driver_register(&intel_th_lpp_driver);
+	if (err) {
+		intel_th_driver_unregister(&intel_th_pti_driver);
+		return err;
+	}
+
+	return 0;
+}
+
+module_init(intel_th_pti_lpp_init);
+
+static void __exit intel_th_pti_lpp_exit(void)
+{
+	intel_th_driver_unregister(&intel_th_pti_driver);
+	intel_th_driver_unregister(&intel_th_lpp_driver);
+}
+
+module_exit(intel_th_pti_lpp_exit);
 
 MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("Intel(R) Trace Hub PTI output driver");
+MODULE_DESCRIPTION("Intel(R) Trace Hub PTI/LPP output driver");
 MODULE_AUTHOR("Alexander Shishkin <alexander.shishkin@linux.intel.com>");
diff --git a/drivers/hwtracing/intel_th/pti.h b/drivers/hwtracing/intel_th/pti.h
index 20883f5628cf..30827be67b4c 100644
--- a/drivers/hwtracing/intel_th/pti.h
+++ b/drivers/hwtracing/intel_th/pti.h
@@ -23,7 +23,15 @@ enum {
 #define PTI_EN		BIT(0)
 #define PTI_FCEN	BIT(1)
 #define PTI_MODE	0xf0
+#define LPP_PTIPRESENT	BIT(8)
+#define LPP_BSSBPRESENT	BIT(9)
 #define PTI_CLKDIV	0x000f0000
 #define PTI_PATGENMODE	0x00f00000
+#define LPP_DEST	BIT(25)
+#define LPP_BSSBACT	BIT(30)
+#define LPP_LPPBUSY	BIT(31)
+
+#define LPP_DEST_PTI	BIT(0)
+#define LPP_DEST_EXI	BIT(1)
 
 #endif /* __INTEL_TH_STH_H__ */