Merge tag 'drm/tegra/for-4.15-rc1' of git://anongit.freedesktop.org/tegra/linux into drm-next

drm/tegra: Changes for v4.15-rc1

This contains a bit of cleanup and some minor fixes for the host1x and
Tegra DRM drivers. There's also some more preparatory work for Tegra186
support which I'm not quite ready to send upstream because the GPIO
driver needed for HDMI support has been stuck for months, and we can't
do much without it. Hopefully that driver will land in v4.15, which
would mean we could go ahead with Tegra186 display support in v4.16.

* tag 'drm/tegra/for-4.15-rc1' of git://anongit.freedesktop.org/tegra/linux: (21 commits)
  drm/tegra: hdmi: Add cec-notifier support
  drm/tegra: dc: Perform a complete reset sequence
  drm/tegra: dc: Make sure to set the module clock rate
  drm/tegra: dc: Simplify atomic plane helper functions
  drm/tegra: dc: Move some declarations to dc.h
  drm/tegra: vic: Use of_device_get_match_data()
  drm/tegra: sor: Use of_device_get_match_data()
  drm/tegra: hdmi: Use of_device_get_match_data()
  drm/tegra: dc: Use of_device_get_match_data()
  drm/tegra: Use u64_to_user_ptr helper
  gpu: host1x: Fix incorrect comment for channel_request
  gpu: host1x: Disassemble more instructions
  gpu: host1x: Improve debug disassembly formatting
  gpu: host1x: Enable gather filter
  gpu: host1x: Enable Tegra186 syncpoint protection
  gpu: host1x: Call of_dma_configure() after setting bus
  drm/tegra: Add Tegra186 support for VIC
  gpu: host1x: Add Tegra186 support
  dt-bindings: host1x: Add Tegra186 information
  gpu: host1x: syncpt: Request syncpoints per client
  ...

Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt

@@ -3,6 +3,10 @@ NVIDIA Tegra host1x
 Required properties:
 - compatible: "nvidia,tegra<chip>-host1x"
 - reg: Physical base address and length of the controller's registers.
+  For pre-Tegra186, one entry describing the whole register area.
+  For Tegra186, one entry for each entry in reg-names:
+    "vm" - VM region assigned to Linux
+    "hypervisor" - Hypervisor region (only if Linux acts as hypervisor)
 - interrupts: The interrupt outputs from the controller.
 - #address-cells: The number of cells used to represent physical base addresses
   in the host1x address space. Should be 1.

drivers/gpu/drm/tegra/Kconfig

@@ -9,6 +9,7 @@ config DRM_TEGRA
 	select DRM_PANEL
 	select TEGRA_HOST1X
 	select IOMMU_IOVA if IOMMU_SUPPORT
+	select CEC_CORE if CEC_NOTIFIER
 	help
 	  Choose this option if you have an NVIDIA Tegra SoC.
 

drivers/gpu/drm/tegra/dc.c

@@ -10,6 +10,7 @@
 #include <linux/clk.h>
 #include <linux/debugfs.h>
 #include <linux/iommu.h>
+#include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
@@ -23,16 +24,6 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_plane_helper.h>
 
-struct tegra_dc_soc_info {
-	bool supports_border_color;
-	bool supports_interlacing;
-	bool supports_cursor;
-	bool supports_block_linear;
-	unsigned int pitch_align;
-	bool has_powergate;
-	bool broken_reset;
-};
-
 struct tegra_plane {
 	struct drm_plane base;
 	unsigned int index;
@@ -559,14 +550,21 @@ static int tegra_plane_atomic_check(struct drm_plane *plane,
 	return 0;
 }
 
-static void tegra_dc_disable_window(struct tegra_dc *dc, int index)
+static void tegra_plane_atomic_disable(struct drm_plane *plane,
+				       struct drm_plane_state *old_state)
 {
+	struct tegra_dc *dc = to_tegra_dc(old_state->crtc);
+	struct tegra_plane *p = to_tegra_plane(plane);
 	unsigned long flags;
 	u32 value;
 
+	/* rien ne va plus */
+	if (!old_state || !old_state->crtc)
+		return;
+
 	spin_lock_irqsave(&dc->lock, flags);
 
-	value = WINDOW_A_SELECT << index;
+	value = WINDOW_A_SELECT << p->index;
 	tegra_dc_writel(dc, value, DC_CMD_DISPLAY_WINDOW_HEADER);
 
 	value = tegra_dc_readl(dc, DC_WIN_WIN_OPTIONS);
@@ -591,7 +589,7 @@ static void tegra_plane_atomic_update(struct drm_plane *plane,
 		return;
 
 	if (!plane->state->visible)
-		return tegra_dc_disable_window(dc, p->index);
+		return tegra_plane_atomic_disable(plane, old_state);
 
 	memset(&window, 0, sizeof(window));
 	window.src.x = plane->state->src.x1 >> 16;
@@ -627,25 +625,10 @@ static void tegra_plane_atomic_update(struct drm_plane *plane,
 	tegra_dc_setup_window(dc, p->index, &window);
 }
 
-static void tegra_plane_atomic_disable(struct drm_plane *plane,
-				       struct drm_plane_state *old_state)
-{
-	struct tegra_plane *p = to_tegra_plane(plane);
-	struct tegra_dc *dc;
-
-	/* rien ne va plus */
-	if (!old_state || !old_state->crtc)
-		return;
-
-	dc = to_tegra_dc(old_state->crtc);
-
-	tegra_dc_disable_window(dc, p->index);
-}
-
-static const struct drm_plane_helper_funcs tegra_primary_plane_helper_funcs = {
+static const struct drm_plane_helper_funcs tegra_plane_helper_funcs = {
 	.atomic_check = tegra_plane_atomic_check,
-	.atomic_update = tegra_plane_atomic_update,
 	.atomic_disable = tegra_plane_atomic_disable,
+	.atomic_update = tegra_plane_atomic_update,
 };
 
 static struct drm_plane *tegra_dc_primary_plane_create(struct drm_device *drm,
@@ -685,7 +668,7 @@ static struct drm_plane *tegra_dc_primary_plane_create(struct drm_device *drm,
 		return ERR_PTR(err);
 	}
 
-	drm_plane_helper_add(&plane->base, &tegra_primary_plane_helper_funcs);
+	drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs);
 
 	return &plane->base;
 }
@@ -880,12 +863,6 @@ static const uint32_t tegra_overlay_plane_formats[] = {
 	DRM_FORMAT_YUV422,
 };
 
-static const struct drm_plane_helper_funcs tegra_overlay_plane_helper_funcs = {
-	.atomic_check = tegra_plane_atomic_check,
-	.atomic_update = tegra_plane_atomic_update,
-	.atomic_disable = tegra_plane_atomic_disable,
-};
-
 static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm,
 						       struct tegra_dc *dc,
 						       unsigned int index)
@@ -913,7 +890,7 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm,
 		return ERR_PTR(err);
 	}
 
-	drm_plane_helper_add(&plane->base, &tegra_overlay_plane_helper_funcs);
+	drm_plane_helper_add(&plane->base, &tegra_plane_helper_funcs);
 
 	return &plane->base;
 }
@@ -1161,6 +1138,11 @@ static void tegra_dc_commit_state(struct tegra_dc *dc,
 
 	value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1;
 	tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
+
+	err = clk_set_rate(dc->clk, state->pclk);
+	if (err < 0)
+		dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
+			dc->clk, state->pclk, err);
 }
 
 static void tegra_dc_stop(struct tegra_dc *dc)
@@ -1756,7 +1738,7 @@ static int tegra_dc_init(struct host1x_client *client)
 	struct drm_plane *cursor = NULL;
 	int err;
 
-	dc->syncpt = host1x_syncpt_request(dc->dev, flags);
+	dc->syncpt = host1x_syncpt_request(client, flags);
 	if (!dc->syncpt)
 		dev_warn(dc->dev, "failed to allocate syncpoint\n");
 
@@ -1985,7 +1967,6 @@ static int tegra_dc_parse_dt(struct tegra_dc *dc)
 
 static int tegra_dc_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *id;
 	struct resource *regs;
 	struct tegra_dc *dc;
 	int err;
@@ -1994,14 +1975,11 @@ static int tegra_dc_probe(struct platform_device *pdev)
 	if (!dc)
 		return -ENOMEM;
 
-	id = of_match_node(tegra_dc_of_match, pdev->dev.of_node);
-	if (!id)
-		return -ENODEV;
+	dc->soc = of_device_get_match_data(&pdev->dev);
 
 	spin_lock_init(&dc->lock);
 	INIT_LIST_HEAD(&dc->list);
 	dc->dev = &pdev->dev;
-	dc->soc = id->data;
 
 	err = tegra_dc_parse_dt(dc);
 	if (err < 0)
@@ -2019,8 +1997,22 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return PTR_ERR(dc->rst);
 	}
 
-	if (!dc->soc->broken_reset)
-		reset_control_assert(dc->rst);
+	/* assert reset and disable clock */
+	if (!dc->soc->broken_reset) {
+		err = clk_prepare_enable(dc->clk);
+		if (err < 0)
+			return err;
+
+		usleep_range(2000, 4000);
+
+		err = reset_control_assert(dc->rst);
+		if (err < 0)
+			return err;
+
+		usleep_range(2000, 4000);
+
+		clk_disable_unprepare(dc->clk);
+	}
 
 	if (dc->soc->has_powergate) {
 		if (dc->pipe == 0)

drivers/gpu/drm/tegra/dc.h

@@ -10,6 +10,126 @@
 #ifndef TEGRA_DC_H
 #define TEGRA_DC_H 1
 
+#include <linux/host1x.h>
+
+#include <drm/drm_crtc.h>
+
+#include "drm.h"
+
+struct tegra_output;
+
+struct tegra_dc_stats {
+	unsigned long frames;
+	unsigned long vblank;
+	unsigned long underflow;
+	unsigned long overflow;
+};
+
+struct tegra_dc_soc_info {
+	bool supports_border_color;
+	bool supports_interlacing;
+	bool supports_cursor;
+	bool supports_block_linear;
+	unsigned int pitch_align;
+	bool has_powergate;
+	bool broken_reset;
+};
+
+struct tegra_dc {
+	struct host1x_client client;
+	struct host1x_syncpt *syncpt;
+	struct device *dev;
+	spinlock_t lock;
+
+	struct drm_crtc base;
+	unsigned int powergate;
+	int pipe;
+
+	struct clk *clk;
+	struct reset_control *rst;
+	void __iomem *regs;
+	int irq;
+
+	struct tegra_output *rgb;
+
+	struct tegra_dc_stats stats;
+	struct list_head list;
+
+	struct drm_info_list *debugfs_files;
+	struct drm_minor *minor;
+	struct dentry *debugfs;
+
+	/* page-flip handling */
+	struct drm_pending_vblank_event *event;
+
+	const struct tegra_dc_soc_info *soc;
+
+	struct iommu_domain *domain;
+};
+
+static inline struct tegra_dc *
+host1x_client_to_dc(struct host1x_client *client)
+{
+	return container_of(client, struct tegra_dc, client);
+}
+
+static inline struct tegra_dc *to_tegra_dc(struct drm_crtc *crtc)
+{
+	return crtc ? container_of(crtc, struct tegra_dc, base) : NULL;
+}
+
+static inline void tegra_dc_writel(struct tegra_dc *dc, u32 value,
+				   unsigned int offset)
+{
+	trace_dc_writel(dc->dev, offset, value);
+	writel(value, dc->regs + (offset << 2));
+}
+
+static inline u32 tegra_dc_readl(struct tegra_dc *dc, unsigned int offset)
+{
+	u32 value = readl(dc->regs + (offset << 2));
+
+	trace_dc_readl(dc->dev, offset, value);
+
+	return value;
+}
+
+struct tegra_dc_window {
+	struct {
+		unsigned int x;
+		unsigned int y;
+		unsigned int w;
+		unsigned int h;
+	} src;
+	struct {
+		unsigned int x;
+		unsigned int y;
+		unsigned int w;
+		unsigned int h;
+	} dst;
+	unsigned int bits_per_pixel;
+	unsigned int stride[2];
+	unsigned long base[3];
+	bool bottom_up;
+
+	struct tegra_bo_tiling tiling;
+	u32 format;
+	u32 swap;
+};
+
+/* from dc.c */
+void tegra_dc_commit(struct tegra_dc *dc);
+int tegra_dc_state_setup_clock(struct tegra_dc *dc,
+			       struct drm_crtc_state *crtc_state,
+			       struct clk *clk, unsigned long pclk,
+			       unsigned int div);
+
+/* from rgb.c */
+int tegra_dc_rgb_probe(struct tegra_dc *dc);
+int tegra_dc_rgb_remove(struct tegra_dc *dc);
+int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc);
+int tegra_dc_rgb_exit(struct tegra_dc *dc);
+
 #define DC_CMD_GENERAL_INCR_SYNCPT		0x000
 #define DC_CMD_GENERAL_INCR_SYNCPT_CNTRL	0x001
 #define  SYNCPT_CNTRL_NO_STALL   (1 << 8)

drivers/gpu/drm/tegra/drm.c

@@ -386,12 +386,10 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 	unsigned int num_cmdbufs = args->num_cmdbufs;
 	unsigned int num_relocs = args->num_relocs;
 	unsigned int num_waitchks = args->num_waitchks;
-	struct drm_tegra_cmdbuf __user *cmdbufs =
-		(void __user *)(uintptr_t)args->cmdbufs;
-	struct drm_tegra_reloc __user *relocs =
-		(void __user *)(uintptr_t)args->relocs;
-	struct drm_tegra_waitchk __user *waitchks =
-		(void __user *)(uintptr_t)args->waitchks;
+	struct drm_tegra_cmdbuf __user *user_cmdbufs;
+	struct drm_tegra_reloc __user *user_relocs;
+	struct drm_tegra_waitchk __user *user_waitchks;
+	struct drm_tegra_syncpt __user *user_syncpt;
 	struct drm_tegra_syncpt syncpt;
 	struct host1x *host1x = dev_get_drvdata(drm->dev->parent);
 	struct drm_gem_object **refs;
@@ -400,6 +398,11 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 	unsigned int num_refs;
 	int err;
 
+	user_cmdbufs = u64_to_user_ptr(args->cmdbufs);
+	user_relocs = u64_to_user_ptr(args->relocs);
+	user_waitchks = u64_to_user_ptr(args->waitchks);
+	user_syncpt = u64_to_user_ptr(args->syncpts);
+
 	/* We don't yet support other than one syncpt_incr struct per submit */
 	if (args->num_syncpts != 1)
 		return -EINVAL;
@@ -440,7 +443,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		struct tegra_bo *obj;
 		u64 offset;
 
-		if (copy_from_user(&cmdbuf, cmdbufs, sizeof(cmdbuf))) {
+		if (copy_from_user(&cmdbuf, user_cmdbufs, sizeof(cmdbuf))) {
 			err = -EFAULT;
 			goto fail;
 		}
@@ -476,7 +479,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 
 		host1x_job_add_gather(job, bo, cmdbuf.words, cmdbuf.offset);
 		num_cmdbufs--;
-		cmdbufs++;
+		user_cmdbufs++;
 	}
 
 	/* copy and resolve relocations from submit */
@@ -485,7 +488,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		struct tegra_bo *obj;
 
 		err = host1x_reloc_copy_from_user(&job->relocarray[num_relocs],
-						  &relocs[num_relocs], drm,
+						  &user_relocs[num_relocs], drm,
 						  file);
 		if (err < 0)
 			goto fail;
@@ -519,9 +522,8 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		struct host1x_waitchk *wait = &job->waitchk[num_waitchks];
 		struct tegra_bo *obj;
 
-		err = host1x_waitchk_copy_from_user(wait,
-						    &waitchks[num_waitchks],
-						    file);
+		err = host1x_waitchk_copy_from_user(
+			wait, &user_waitchks[num_waitchks], file);
 		if (err < 0)
 			goto fail;
 
@@ -539,8 +541,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		}
 	}
 
-	if (copy_from_user(&syncpt, (void __user *)(uintptr_t)args->syncpts,
-			   sizeof(syncpt))) {
+	if (copy_from_user(&syncpt, user_syncpt, sizeof(syncpt))) {
 		err = -EFAULT;
 		goto fail;
 	}
@@ -1317,6 +1318,7 @@ static const struct of_device_id host1x_drm_subdevs[] = {
 	{ .compatible = "nvidia,tegra210-sor", },
 	{ .compatible = "nvidia,tegra210-sor1", },
 	{ .compatible = "nvidia,tegra210-vic", },
+	{ .compatible = "nvidia,tegra186-vic", },
 	{ /* sentinel */ }
 };
 

drivers/gpu/drm/tegra/drm.h

@@ -119,104 +119,7 @@ void *tegra_drm_alloc(struct tegra_drm *tegra, size_t size, dma_addr_t *iova);
 void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt,
 		    dma_addr_t iova);
 
-struct tegra_dc_soc_info;
-struct tegra_output;
-
-struct tegra_dc_stats {
-	unsigned long frames;
-	unsigned long vblank;
-	unsigned long underflow;
-	unsigned long overflow;
-};
-
-struct tegra_dc {
-	struct host1x_client client;
-	struct host1x_syncpt *syncpt;
-	struct device *dev;
-	spinlock_t lock;
-
-	struct drm_crtc base;
-	unsigned int powergate;
-	int pipe;
-
-	struct clk *clk;
-	struct reset_control *rst;
-	void __iomem *regs;
-	int irq;
-
-	struct tegra_output *rgb;
-
-	struct tegra_dc_stats stats;
-	struct list_head list;
-
-	struct drm_info_list *debugfs_files;
-	struct drm_minor *minor;
-	struct dentry *debugfs;
-
-	/* page-flip handling */
-	struct drm_pending_vblank_event *event;
-
-	const struct tegra_dc_soc_info *soc;
-
-	struct iommu_domain *domain;
-};
-
-static inline struct tegra_dc *
-host1x_client_to_dc(struct host1x_client *client)
-{
-	return container_of(client, struct tegra_dc, client);
-}
-
-static inline struct tegra_dc *to_tegra_dc(struct drm_crtc *crtc)
-{
-	return crtc ? container_of(crtc, struct tegra_dc, base) : NULL;
-}
-
-static inline void tegra_dc_writel(struct tegra_dc *dc, u32 value,
-				   unsigned int offset)
-{
-	trace_dc_writel(dc->dev, offset, value);
-	writel(value, dc->regs + (offset << 2));
-}
-
-static inline u32 tegra_dc_readl(struct tegra_dc *dc, unsigned int offset)
-{
-	u32 value = readl(dc->regs + (offset << 2));
-
-	trace_dc_readl(dc->dev, offset, value);
-
-	return value;
-}
-
-struct tegra_dc_window {
-	struct {
-		unsigned int x;
-		unsigned int y;
-		unsigned int w;
-		unsigned int h;
-	} src;
-	struct {
-		unsigned int x;
-		unsigned int y;
-		unsigned int w;
-		unsigned int h;
-	} dst;
-	unsigned int bits_per_pixel;
-	unsigned int stride[2];
-	unsigned long base[3];
-	bool bottom_up;
-
-	struct tegra_bo_tiling tiling;
-	u32 format;
-	u32 swap;
-};
-
-/* from dc.c */
-void tegra_dc_commit(struct tegra_dc *dc);
-int tegra_dc_state_setup_clock(struct tegra_dc *dc,
-			       struct drm_crtc_state *crtc_state,
-			       struct clk *clk, unsigned long pclk,
-			       unsigned int div);
+struct cec_notifier;
 
 struct tegra_output {
 	struct device_node *of_node;
@@ -225,6 +128,7 @@ struct tegra_output {
 	struct drm_panel *panel;
 	struct i2c_adapter *ddc;
 	const struct edid *edid;
+	struct cec_notifier *notifier;
 	unsigned int hpd_irq;
 	int hpd_gpio;
 	enum of_gpio_flags hpd_gpio_flags;
@@ -243,12 +147,6 @@ static inline struct tegra_output *connector_to_output(struct drm_connector *c)
 	return container_of(c, struct tegra_output, connector);
 }
 
-/* from rgb.c */
-int tegra_dc_rgb_probe(struct tegra_dc *dc);
-int tegra_dc_rgb_remove(struct tegra_dc *dc);
-int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc);
-int tegra_dc_rgb_exit(struct tegra_dc *dc);
-
 /* from output.c */
 int tegra_output_probe(struct tegra_output *output);
 void tegra_output_remove(struct tegra_output *output);

drivers/gpu/drm/tegra/gr2d.c

@@ -36,7 +36,7 @@ static int gr2d_init(struct host1x_client *client)
 	if (!gr2d->channel)
 		return -ENOMEM;
 
-	client->syncpts[0] = host1x_syncpt_request(client->dev, flags);
+	client->syncpts[0] = host1x_syncpt_request(client, flags);
 	if (!client->syncpts[0]) {
 		host1x_channel_put(gr2d->channel);
 		return -ENOMEM;

drivers/gpu/drm/tegra/gr3d.c

@@ -46,7 +46,7 @@ static int gr3d_init(struct host1x_client *client)
 	if (!gr3d->channel)
 		return -ENOMEM;
 
-	client->syncpts[0] = host1x_syncpt_request(client->dev, flags);
+	client->syncpts[0] = host1x_syncpt_request(client, flags);
 	if (!client->syncpts[0]) {
 		host1x_channel_put(gr3d->channel);
 		return -ENOMEM;

drivers/gpu/drm/tegra/hdmi.c

@@ -11,6 +11,7 @@
 #include <linux/debugfs.h>
 #include <linux/gpio.h>
 #include <linux/hdmi.h>
+#include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
@@ -21,6 +22,8 @@
 
 #include <sound/hda_verbs.h>
 
+#include <media/cec-notifier.h>
+
 #include "hdmi.h"
 #include "drm.h"
 #include "dc.h"
@@ -1663,20 +1666,15 @@ static irqreturn_t tegra_hdmi_irq(int irq, void *data)
 
 static int tegra_hdmi_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *match;
 	struct tegra_hdmi *hdmi;
 	struct resource *regs;
 	int err;
 
-	match = of_match_node(tegra_hdmi_of_match, pdev->dev.of_node);
-	if (!match)
-		return -ENODEV;
-
 	hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL);
 	if (!hdmi)
 		return -ENOMEM;
 
-	hdmi->config = match->data;
+	hdmi->config = of_device_get_match_data(&pdev->dev);
 	hdmi->dev = &pdev->dev;
 
 	hdmi->audio_source = AUTO;
@@ -1725,6 +1723,10 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 		return PTR_ERR(hdmi->vdd);
 	}
 
+	hdmi->output.notifier = cec_notifier_get(&pdev->dev);
+	if (hdmi->output.notifier == NULL)
+		return -ENOMEM;
+
 	hdmi->output.dev = &pdev->dev;
 
 	err = tegra_output_probe(&hdmi->output);
@@ -1783,6 +1785,9 @@ static int tegra_hdmi_remove(struct platform_device *pdev)
 
 	tegra_output_remove(&hdmi->output);
 
+	if (hdmi->output.notifier)
+		cec_notifier_put(hdmi->output.notifier);
+
 	return 0;
 }
 

drivers/gpu/drm/tegra/output.c

@@ -11,6 +11,8 @@
 #include <drm/drm_panel.h>
 #include "drm.h"
 
+#include <media/cec-notifier.h>
+
 int tegra_output_connector_get_modes(struct drm_connector *connector)
 {
 	struct tegra_output *output = connector_to_output(connector);
@@ -32,6 +34,7 @@ int tegra_output_connector_get_modes(struct drm_connector *connector)
 	else if (output->ddc)
 		edid = drm_get_edid(connector, output->ddc);
 
+	cec_notifier_set_phys_addr_from_edid(output->notifier, edid);
 	drm_mode_connector_update_edid_property(connector, edid);
 
 	if (edid) {
@@ -68,6 +71,9 @@ tegra_output_connector_detect(struct drm_connector *connector, bool force)
 			status = connector_status_connected;
 	}
 
+	if (status != connector_status_connected)
+		cec_notifier_phys_addr_invalidate(output->notifier);
+
 	return status;
 }
 

drivers/gpu/drm/tegra/sor.c

@@ -2536,20 +2536,17 @@ MODULE_DEVICE_TABLE(of, tegra_sor_of_match);
 
 static int tegra_sor_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *match;
 	struct device_node *np;
 	struct tegra_sor *sor;
 	struct resource *regs;
 	int err;
 
-	match = of_match_device(tegra_sor_of_match, &pdev->dev);
-
 	sor = devm_kzalloc(&pdev->dev, sizeof(*sor), GFP_KERNEL);
 	if (!sor)
 		return -ENOMEM;
 
+	sor->soc = of_device_get_match_data(&pdev->dev);
 	sor->output.dev = sor->dev = &pdev->dev;
-	sor->soc = match->data;
 
 	sor->settings = devm_kmemdup(&pdev->dev, sor->soc->settings,
 				     sor->soc->num_settings *

drivers/gpu/drm/tegra/vic.c

@@ -167,7 +167,7 @@ static int vic_init(struct host1x_client *client)
 		goto detach_device;
 	}
 
-	client->syncpts[0] = host1x_syncpt_request(client->dev, 0);
+	client->syncpts[0] = host1x_syncpt_request(client, 0);
 	if (!client->syncpts[0]) {
 		err = -ENOMEM;
 		goto free_channel;
@@ -270,29 +270,33 @@ static const struct vic_config vic_t210_config = {
 	.firmware = NVIDIA_TEGRA_210_VIC_FIRMWARE,
 };
 
+#define NVIDIA_TEGRA_186_VIC_FIRMWARE "nvidia/tegra186/vic04_ucode.bin"
+
+static const struct vic_config vic_t186_config = {
+	.firmware = NVIDIA_TEGRA_186_VIC_FIRMWARE,
+};
+
 static const struct of_device_id vic_match[] = {
 	{ .compatible = "nvidia,tegra124-vic", .data = &vic_t124_config },
 	{ .compatible = "nvidia,tegra210-vic", .data = &vic_t210_config },
+	{ .compatible = "nvidia,tegra186-vic", .data = &vic_t186_config },
 	{ },
 };
 
 static int vic_probe(struct platform_device *pdev)
 {
-	struct vic_config *vic_config = NULL;
 	struct device *dev = &pdev->dev;
 	struct host1x_syncpt **syncpts;
 	struct resource *regs;
-	const struct of_device_id *match;
 	struct vic *vic;
 	int err;
 
-	match = of_match_device(vic_match, dev);
-	vic_config = (struct vic_config *)match->data;
-
 	vic = devm_kzalloc(dev, sizeof(*vic), GFP_KERNEL);
 	if (!vic)
 		return -ENOMEM;
 
+	vic->config = of_device_get_match_data(dev);
+
 	syncpts = devm_kzalloc(dev, sizeof(*syncpts), GFP_KERNEL);
 	if (!syncpts)
 		return -ENOMEM;
@@ -321,7 +325,7 @@ static int vic_probe(struct platform_device *pdev)
 	if (err < 0)
 		return err;
 
-	err = falcon_read_firmware(&vic->falcon, vic_config->firmware);
+	err = falcon_read_firmware(&vic->falcon, vic->config->firmware);
 	if (err < 0)
 		goto exit_falcon;
 
@@ -334,7 +338,6 @@ static int vic_probe(struct platform_device *pdev)
 	vic->client.base.syncpts = syncpts;
 	vic->client.base.num_syncpts = 1;
 	vic->dev = dev;
-	vic->config = vic_config;
 
 	INIT_LIST_HEAD(&vic->client.list);
 	vic->client.ops = &vic_ops;
@@ -405,3 +408,6 @@ MODULE_FIRMWARE(NVIDIA_TEGRA_124_VIC_FIRMWARE);
 #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
 MODULE_FIRMWARE(NVIDIA_TEGRA_210_VIC_FIRMWARE);
 #endif
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
+MODULE_FIRMWARE(NVIDIA_TEGRA_186_VIC_FIRMWARE);
+#endif

drivers/gpu/host1x/Makefile

@@ -11,6 +11,7 @@ host1x-y = \
 	hw/host1x01.o \
 	hw/host1x02.o \
 	hw/host1x04.o \
-	hw/host1x05.o
+	hw/host1x05.o \
+	hw/host1x06.o
 
 obj-$(CONFIG_TEGRA_HOST1X) += host1x.o

drivers/gpu/host1x/bus.c

@@ -403,12 +403,13 @@ static int host1x_device_add(struct host1x *host1x,
 	device->dev.coherent_dma_mask = host1x->dev->coherent_dma_mask;
 	device->dev.dma_mask = &device->dev.coherent_dma_mask;
 	dev_set_name(&device->dev, "%s", driver->driver.name);
-	of_dma_configure(&device->dev, host1x->dev->of_node);
 	device->dev.release = host1x_device_release;
 	device->dev.of_node = host1x->dev->of_node;
 	device->dev.bus = &host1x_bus_type;
 	device->dev.parent = host1x->dev;
 
+	of_dma_configure(&device->dev, host1x->dev->of_node);
+
 	err = host1x_device_parse_dt(device, driver);
 	if (err < 0) {
 		kfree(device);

drivers/gpu/host1x/channel.c

@@ -128,8 +128,7 @@ static struct host1x_channel *acquire_unused_channel(struct host1x *host)
  * host1x_channel_request() - Allocate a channel
  * @device: Host1x unit this channel will be used to send commands to
  *
- * Allocates a new host1x channel for @device. If there are no free channels,
- * this will sleep until one becomes available. May return NULL if CDMA
+ * Allocates a new host1x channel for @device. May return NULL if CDMA
  * initialization fails.
  */
 struct host1x_channel *host1x_channel_request(struct device *dev)

drivers/gpu/host1x/debug.c

@@ -40,7 +40,19 @@ void host1x_debug_output(struct output *o, const char *fmt, ...)
 	len = vsnprintf(o->buf, sizeof(o->buf), fmt, args);
 	va_end(args);
 
-	o->fn(o->ctx, o->buf, len);
+	o->fn(o->ctx, o->buf, len, false);
+}
+
+void host1x_debug_cont(struct output *o, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+
+	va_start(args, fmt);
+	len = vsnprintf(o->buf, sizeof(o->buf), fmt, args);
+	va_end(args);
+
+	o->fn(o->ctx, o->buf, len, true);
 }
 
 static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)

drivers/gpu/host1x/debug.h

@@ -24,22 +24,28 @@
 struct host1x;
 
 struct output {
-	void (*fn)(void *ctx, const char *str, size_t len);
+	void (*fn)(void *ctx, const char *str, size_t len, bool cont);
 	void *ctx;
 	char buf[256];
 };
 
-static inline void write_to_seqfile(void *ctx, const char *str, size_t len)
+static inline void write_to_seqfile(void *ctx, const char *str, size_t len,
+				    bool cont)
 {
 	seq_write((struct seq_file *)ctx, str, len);
 }
 
-static inline void write_to_printk(void *ctx, const char *str, size_t len)
+static inline void write_to_printk(void *ctx, const char *str, size_t len,
+				   bool cont)
 {
+	if (cont)
+		pr_cont("%s", str);
+	else
 		pr_info("%s", str);
 }
 
 void __printf(2, 3) host1x_debug_output(struct output *o, const char *fmt, ...);
+void __printf(2, 3) host1x_debug_cont(struct output *o, const char *fmt, ...);
 
 extern unsigned int host1x_debug_trace_cmdbuf;
 

drivers/gpu/host1x/dev.c

@@ -39,6 +39,17 @@
 #include "hw/host1x02.h"
 #include "hw/host1x04.h"
 #include "hw/host1x05.h"
+#include "hw/host1x06.h"
+
+void host1x_hypervisor_writel(struct host1x *host1x, u32 v, u32 r)
+{
+	writel(v, host1x->hv_regs + r);
+}
+
+u32 host1x_hypervisor_readl(struct host1x *host1x, u32 r)
+{
+	return readl(host1x->hv_regs + r);
+}
 
 void host1x_sync_writel(struct host1x *host1x, u32 v, u32 r)
 {
@@ -104,7 +115,19 @@ static const struct host1x_info host1x05_info = {
 	.dma_mask = DMA_BIT_MASK(34),
 };
 
+static const struct host1x_info host1x06_info = {
+	.nb_channels = 63,
+	.nb_pts = 576,
+	.nb_mlocks = 24,
+	.nb_bases = 16,
+	.init = host1x06_init,
+	.sync_offset = 0x0,
+	.dma_mask = DMA_BIT_MASK(34),
+	.has_hypervisor = true,
+};
+
 static const struct of_device_id host1x_of_match[] = {
+	{ .compatible = "nvidia,tegra186-host1x", .data = &host1x06_info, },
 	{ .compatible = "nvidia,tegra210-host1x", .data = &host1x05_info, },
 	{ .compatible = "nvidia,tegra124-host1x", .data = &host1x04_info, },
 	{ .compatible = "nvidia,tegra114-host1x", .data = &host1x02_info, },
@@ -116,21 +139,38 @@ MODULE_DEVICE_TABLE(of, host1x_of_match);
 
 static int host1x_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *id;
 	struct host1x *host;
-	struct resource *regs;
+	struct resource *regs, *hv_regs = NULL;
 	int syncpt_irq;
 	int err;
 
-	id = of_match_device(host1x_of_match, &pdev->dev);
-	if (!id)
-		return -EINVAL;
+	host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	host->info = of_device_get_match_data(&pdev->dev);
 
+	if (host->info->has_hypervisor) {
+		regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vm");
+		if (!regs) {
+			dev_err(&pdev->dev, "failed to get vm registers\n");
+			return -ENXIO;
+		}
+
+		hv_regs = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						       "hypervisor");
+		if (!hv_regs) {
+			dev_err(&pdev->dev,
+				"failed to get hypervisor registers\n");
+			return -ENXIO;
+		}
+	} else {
 		regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 		if (!regs) {
 			dev_err(&pdev->dev, "failed to get registers\n");
 			return -ENXIO;
 		}
+	}
 
 	syncpt_irq = platform_get_irq(pdev, 0);
 	if (syncpt_irq < 0) {
@@ -138,15 +178,10 @@ static int host1x_probe(struct platform_device *pdev)
 		return syncpt_irq;
 	}
 
-	host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
-	if (!host)
-		return -ENOMEM;
-
 	mutex_init(&host->devices_lock);
 	INIT_LIST_HEAD(&host->devices);
 	INIT_LIST_HEAD(&host->list);
 	host->dev = &pdev->dev;
-	host->info = id->data;
 
 	/* set common host1x device data */
 	platform_set_drvdata(pdev, host);
@@ -155,6 +190,12 @@ static int host1x_probe(struct platform_device *pdev)
 	if (IS_ERR(host->regs))
 		return PTR_ERR(host->regs);
 
+	if (host->info->has_hypervisor) {
+		host->hv_regs = devm_ioremap_resource(&pdev->dev, hv_regs);
+		if (IS_ERR(host->hv_regs))
+			return PTR_ERR(host->hv_regs);
+	}
+
 	dma_set_mask_and_coherent(host->dev, host->info->dma_mask);
 
 	if (host->info->init) {

drivers/gpu/host1x/dev.h

@@ -79,6 +79,9 @@ struct host1x_syncpt_ops {
 	u32 (*load)(struct host1x_syncpt *syncpt);
 	int (*cpu_incr)(struct host1x_syncpt *syncpt);
 	int (*patch_wait)(struct host1x_syncpt *syncpt, void *patch_addr);
+	void (*assign_to_channel)(struct host1x_syncpt *syncpt,
+	                          struct host1x_channel *channel);
+	void (*enable_protection)(struct host1x *host);
 };
 
 struct host1x_intr_ops {
@@ -100,12 +103,14 @@ struct host1x_info {
 	int (*init)(struct host1x *host1x); /* initialize per SoC ops */
 	unsigned int sync_offset; /* offset of syncpoint registers */
 	u64 dma_mask; /* mask of addressable memory */
+	bool has_hypervisor; /* has hypervisor registers */
 };
 
 struct host1x {
 	const struct host1x_info *info;
 
 	void __iomem *regs;
+	void __iomem *hv_regs; /* hypervisor region */
 	struct host1x_syncpt *syncpt;
 	struct host1x_syncpt_base *bases;
 	struct device *dev;
@@ -140,6 +145,8 @@ struct host1x {
 	struct list_head list;
 };
 
+void host1x_hypervisor_writel(struct host1x *host1x, u32 r, u32 v);
+u32 host1x_hypervisor_readl(struct host1x *host1x, u32 r);
 void host1x_sync_writel(struct host1x *host1x, u32 r, u32 v);
 u32 host1x_sync_readl(struct host1x *host1x, u32 r);
 void host1x_ch_writel(struct host1x_channel *ch, u32 r, u32 v);
@@ -182,6 +189,18 @@ static inline int host1x_hw_syncpt_patch_wait(struct host1x *host,
 	return host->syncpt_op->patch_wait(sp, patch_addr);
 }
 
+static inline void host1x_hw_syncpt_assign_to_channel(
+	struct host1x *host, struct host1x_syncpt *sp,
+	struct host1x_channel *ch)
+{
+	return host->syncpt_op->assign_to_channel(sp, ch);
+}
+
+static inline void host1x_hw_syncpt_enable_protection(struct host1x *host)
+{
+	return host->syncpt_op->enable_protection(host);
+}
+
 static inline int host1x_hw_intr_init_host_sync(struct host1x *host, u32 cpm,
 			void (*syncpt_thresh_work)(struct work_struct *))
 {

drivers/gpu/host1x/hw/cdma_hw.c

@@ -172,6 +172,30 @@ static void cdma_stop(struct host1x_cdma *cdma)
 	mutex_unlock(&cdma->lock);
 }
 
+static void cdma_hw_cmdproc_stop(struct host1x *host, struct host1x_channel *ch,
+				 bool stop)
+{
+#if HOST1X_HW >= 6
+	host1x_ch_writel(ch, stop ? 0x1 : 0x0, HOST1X_CHANNEL_CMDPROC_STOP);
+#else
+	u32 cmdproc_stop = host1x_sync_readl(host, HOST1X_SYNC_CMDPROC_STOP);
+	if (stop)
+		cmdproc_stop |= BIT(ch->id);
+	else
+		cmdproc_stop &= ~BIT(ch->id);
+	host1x_sync_writel(host, cmdproc_stop, HOST1X_SYNC_CMDPROC_STOP);
+#endif
+}
+
+static void cdma_hw_teardown(struct host1x *host, struct host1x_channel *ch)
+{
+#if HOST1X_HW >= 6
+	host1x_ch_writel(ch, 0x1, HOST1X_CHANNEL_TEARDOWN);
+#else
+	host1x_sync_writel(host, BIT(ch->id), HOST1X_SYNC_CH_TEARDOWN);
+#endif
+}
+
 /*
  * Stops both channel's command processor and CDMA immediately.
  * Also, tears down the channel and resets corresponding module.
@@ -180,7 +204,6 @@ static void cdma_freeze(struct host1x_cdma *cdma)
 {
 	struct host1x *host = cdma_to_host1x(cdma);
 	struct host1x_channel *ch = cdma_to_channel(cdma);
-	u32 cmdproc_stop;
 
 	if (cdma->torndown && !cdma->running) {
 		dev_warn(host->dev, "Already torn down\n");
@@ -189,9 +212,7 @@ static void cdma_freeze(struct host1x_cdma *cdma)
 
 	dev_dbg(host->dev, "freezing channel (id %d)\n", ch->id);
 
-	cmdproc_stop = host1x_sync_readl(host, HOST1X_SYNC_CMDPROC_STOP);
-	cmdproc_stop |= BIT(ch->id);
-	host1x_sync_writel(host, cmdproc_stop, HOST1X_SYNC_CMDPROC_STOP);
+	cdma_hw_cmdproc_stop(host, ch, true);
 
 	dev_dbg(host->dev, "%s: DMA GET 0x%x, PUT HW 0x%x / shadow 0x%x\n",
 		__func__, host1x_ch_readl(ch, HOST1X_CHANNEL_DMAGET),
@@ -201,7 +222,7 @@ static void cdma_freeze(struct host1x_cdma *cdma)
 	host1x_ch_writel(ch, HOST1X_CHANNEL_DMACTRL_DMASTOP,
 			 HOST1X_CHANNEL_DMACTRL);
 
-	host1x_sync_writel(host, BIT(ch->id), HOST1X_SYNC_CH_TEARDOWN);
+	cdma_hw_teardown(host, ch);
 
 	cdma->running = false;
 	cdma->torndown = true;
@@ -211,15 +232,12 @@ static void cdma_resume(struct host1x_cdma *cdma, u32 getptr)
 {
 	struct host1x *host1x = cdma_to_host1x(cdma);
 	struct host1x_channel *ch = cdma_to_channel(cdma);
-	u32 cmdproc_stop;
 
 	dev_dbg(host1x->dev,
 		"resuming channel (id %u, DMAGET restart = 0x%x)\n",
 		ch->id, getptr);
 
-	cmdproc_stop = host1x_sync_readl(host1x, HOST1X_SYNC_CMDPROC_STOP);
-	cmdproc_stop &= ~BIT(ch->id);
-	host1x_sync_writel(host1x, cmdproc_stop, HOST1X_SYNC_CMDPROC_STOP);
+	cdma_hw_cmdproc_stop(host1x, ch, false);
 
 	cdma->torndown = false;
 	cdma_timeout_restart(cdma, getptr);
@@ -232,7 +250,7 @@ static void cdma_resume(struct host1x_cdma *cdma, u32 getptr)
  */
 static void cdma_timeout_handler(struct work_struct *work)
 {
-	u32 prev_cmdproc, cmdproc_stop, syncpt_val;
+	u32 syncpt_val;
 	struct host1x_cdma *cdma;
 	struct host1x *host1x;
 	struct host1x_channel *ch;
@@ -254,12 +272,7 @@ static void cdma_timeout_handler(struct work_struct *work)
 	}
 
 	/* stop processing to get a clean snapshot */
-	prev_cmdproc = host1x_sync_readl(host1x, HOST1X_SYNC_CMDPROC_STOP);
-	cmdproc_stop = prev_cmdproc | BIT(ch->id);
-	host1x_sync_writel(host1x, cmdproc_stop, HOST1X_SYNC_CMDPROC_STOP);
-
-	dev_dbg(host1x->dev, "cdma_timeout: cmdproc was 0x%x is 0x%x\n",
-		prev_cmdproc, cmdproc_stop);
+	cdma_hw_cmdproc_stop(host1x, ch, true);
 
 	syncpt_val = host1x_syncpt_load(cdma->timeout.syncpt);
 
@@ -268,9 +281,7 @@ static void cdma_timeout_handler(struct work_struct *work)
 		dev_dbg(host1x->dev,
 			"cdma_timeout: expired, but buffer had completed\n");
 		/* restore */
-		cmdproc_stop = prev_cmdproc & ~(BIT(ch->id));
-		host1x_sync_writel(host1x, cmdproc_stop,
-				   HOST1X_SYNC_CMDPROC_STOP);
+		cdma_hw_cmdproc_stop(host1x, ch, false);
 		mutex_unlock(&cdma->lock);
 		return;
 	}

drivers/gpu/host1x/hw/channel_hw.c

@@ -147,6 +147,8 @@ static int channel_submit(struct host1x_job *job)
 
 	syncval = host1x_syncpt_incr_max(sp, user_syncpt_incrs);
 
+	host1x_hw_syncpt_assign_to_channel(host, sp, ch);
+
 	job->syncpt_end = syncval;
 
 	/* add a setclass for modules that require it */
@@ -178,10 +180,32 @@ static int channel_submit(struct host1x_job *job)
 	return err;
 }
 
+static void enable_gather_filter(struct host1x *host,
+				 struct host1x_channel *ch)
+{
+#if HOST1X_HW >= 6
+	u32 val;
+
+	if (!host->hv_regs)
+		return;
+
+	val = host1x_hypervisor_readl(
+		host, HOST1X_HV_CH_KERNEL_FILTER_GBUFFER(ch->id / 32));
+	val |= BIT(ch->id % 32);
+	host1x_hypervisor_writel(
+		host, val, HOST1X_HV_CH_KERNEL_FILTER_GBUFFER(ch->id / 32));
+#elif HOST1X_HW >= 4
+	host1x_ch_writel(ch,
+			 HOST1X_CHANNEL_CHANNELCTRL_KERNEL_FILTER_GBUFFER(1),
+			 HOST1X_CHANNEL_CHANNELCTRL);
+#endif
+}
+
 static int host1x_channel_init(struct host1x_channel *ch, struct host1x *dev,
 			       unsigned int index)
 {
 	ch->regs = dev->regs + index * HOST1X_CHANNEL_SIZE;
+	enable_gather_filter(dev, ch);
 	return 0;
 }
 

drivers/gpu/host1x/hw/debug_hw.c

@@ -30,6 +30,13 @@ enum {
 	HOST1X_OPCODE_IMM	= 0x04,
 	HOST1X_OPCODE_RESTART	= 0x05,
 	HOST1X_OPCODE_GATHER	= 0x06,
+	HOST1X_OPCODE_SETSTRMID = 0x07,
+	HOST1X_OPCODE_SETAPPID  = 0x08,
+	HOST1X_OPCODE_SETPYLD   = 0x09,
+	HOST1X_OPCODE_INCR_W    = 0x0a,
+	HOST1X_OPCODE_NONINCR_W = 0x0b,
+	HOST1X_OPCODE_GATHER_W  = 0x0c,
+	HOST1X_OPCODE_RESTART_W = 0x0d,
 	HOST1X_OPCODE_EXTEND	= 0x0e,
 };
 
@@ -38,67 +45,122 @@ enum {
 	HOST1X_OPCODE_EXTEND_RELEASE_MLOCK	= 0x01,
 };
 
-static unsigned int show_channel_command(struct output *o, u32 val)
+#define INVALID_PAYLOAD				0xffffffff
+
+static unsigned int show_channel_command(struct output *o, u32 val,
+					 u32 *payload)
 {
-	unsigned int mask, subop;
+	unsigned int mask, subop, num, opcode;
+
+	opcode = val >> 28;
 
-	switch (val >> 28) {
+	switch (opcode) {
 	case HOST1X_OPCODE_SETCLASS:
 		mask = val & 0x3f;
 		if (mask) {
-			host1x_debug_output(o, "SETCL(class=%03x, offset=%03x, mask=%02x, [",
+			host1x_debug_cont(o, "SETCL(class=%03x, offset=%03x, mask=%02x, [",
 					    val >> 6 & 0x3ff,
 					    val >> 16 & 0xfff, mask);
 			return hweight8(mask);
 		}
 
-		host1x_debug_output(o, "SETCL(class=%03x)\n", val >> 6 & 0x3ff);
+		host1x_debug_cont(o, "SETCL(class=%03x)\n", val >> 6 & 0x3ff);
 		return 0;
 
 	case HOST1X_OPCODE_INCR:
-		host1x_debug_output(o, "INCR(offset=%03x, [",
+		num = val & 0xffff;
+		host1x_debug_cont(o, "INCR(offset=%03x, [",
 				    val >> 16 & 0xfff);
-		return val & 0xffff;
+		if (!num)
+			host1x_debug_cont(o, "])\n");
+
+		return num;
 
 	case HOST1X_OPCODE_NONINCR:
-		host1x_debug_output(o, "NONINCR(offset=%03x, [",
+		num = val & 0xffff;
+		host1x_debug_cont(o, "NONINCR(offset=%03x, [",
 				    val >> 16 & 0xfff);
-		return val & 0xffff;
+		if (!num)
+			host1x_debug_cont(o, "])\n");
+
+		return num;
 
 	case HOST1X_OPCODE_MASK:
 		mask = val & 0xffff;
-		host1x_debug_output(o, "MASK(offset=%03x, mask=%03x, [",
+		host1x_debug_cont(o, "MASK(offset=%03x, mask=%03x, [",
 				    val >> 16 & 0xfff, mask);
+		if (!mask)
+			host1x_debug_cont(o, "])\n");
+
 		return hweight16(mask);
 
 	case HOST1X_OPCODE_IMM:
-		host1x_debug_output(o, "IMM(offset=%03x, data=%03x)\n",
+		host1x_debug_cont(o, "IMM(offset=%03x, data=%03x)\n",
 				    val >> 16 & 0xfff, val & 0xffff);
 		return 0;
 
 	case HOST1X_OPCODE_RESTART:
-		host1x_debug_output(o, "RESTART(offset=%08x)\n", val << 4);
+		host1x_debug_cont(o, "RESTART(offset=%08x)\n", val << 4);
 		return 0;
 
 	case HOST1X_OPCODE_GATHER:
-		host1x_debug_output(o, "GATHER(offset=%03x, insert=%d, type=%d, count=%04x, addr=[",
+		host1x_debug_cont(o, "GATHER(offset=%03x, insert=%d, type=%d, count=%04x, addr=[",
 				    val >> 16 & 0xfff, val >> 15 & 0x1,
 				    val >> 14 & 0x1, val & 0x3fff);
 		return 1;
 
+#if HOST1X_HW >= 6
+	case HOST1X_OPCODE_SETSTRMID:
+		host1x_debug_cont(o, "SETSTRMID(offset=%06x)\n",
+				  val & 0x3fffff);
+		return 0;
+
+	case HOST1X_OPCODE_SETAPPID:
+		host1x_debug_cont(o, "SETAPPID(appid=%02x)\n", val & 0xff);
+		return 0;
+
+	case HOST1X_OPCODE_SETPYLD:
+		*payload = val & 0xffff;
+		host1x_debug_cont(o, "SETPYLD(data=%04x)\n", *payload);
+		return 0;
+
+	case HOST1X_OPCODE_INCR_W:
+	case HOST1X_OPCODE_NONINCR_W:
+		host1x_debug_cont(o, "%s(offset=%06x, ",
+				  opcode == HOST1X_OPCODE_INCR_W ?
+					"INCR_W" : "NONINCR_W",
+				  val & 0x3fffff);
+		if (*payload == 0) {
+			host1x_debug_cont(o, "[])\n");
+			return 0;
+		} else if (*payload == INVALID_PAYLOAD) {
+			host1x_debug_cont(o, "unknown)\n");
+			return 0;
+		} else {
+			host1x_debug_cont(o, "[");
+			return *payload;
+		}
+
+	case HOST1X_OPCODE_GATHER_W:
+		host1x_debug_cont(o, "GATHER_W(count=%04x, addr=[",
+				  val & 0x3fff);
+		return 2;
+#endif
+
 	case HOST1X_OPCODE_EXTEND:
 		subop = val >> 24 & 0xf;
 		if (subop == HOST1X_OPCODE_EXTEND_ACQUIRE_MLOCK)
-			host1x_debug_output(o, "ACQUIRE_MLOCK(index=%d)\n",
+			host1x_debug_cont(o, "ACQUIRE_MLOCK(index=%d)\n",
 					    val & 0xff);
 		else if (subop == HOST1X_OPCODE_EXTEND_RELEASE_MLOCK)
-			host1x_debug_output(o, "RELEASE_MLOCK(index=%d)\n",
+			host1x_debug_cont(o, "RELEASE_MLOCK(index=%d)\n",
 					    val & 0xff);
 		else
-			host1x_debug_output(o, "EXTEND_UNKNOWN(%08x)\n", val);
+			host1x_debug_cont(o, "EXTEND_UNKNOWN(%08x)\n", val);
 		return 0;
 
 	default:
+		host1x_debug_cont(o, "UNKNOWN\n");
 		return 0;
 	}
 }
@@ -110,6 +172,7 @@ static void show_gather(struct output *o, phys_addr_t phys_addr,
 	/* Map dmaget cursor to corresponding mem handle */
 	u32 offset = phys_addr - pin_addr;
 	unsigned int data_count = 0, i;
+	u32 payload = INVALID_PAYLOAD;
 
 	/*
 	 * Sometimes we're given different hardware address to the same
@@ -126,11 +189,11 @@ static void show_gather(struct output *o, phys_addr_t phys_addr,
 		u32 val = *(map_addr + offset / 4 + i);
 
 		if (!data_count) {
-			host1x_debug_output(o, "%08x: %08x:", addr, val);
-			data_count = show_channel_command(o, val);
+			host1x_debug_output(o, "%08x: %08x: ", addr, val);
+			data_count = show_channel_command(o, val, &payload);
 		} else {
-			host1x_debug_output(o, "%08x%s", val,
-					    data_count > 0 ? ", " : "])\n");
+			host1x_debug_cont(o, "%08x%s", val,
+					    data_count > 1 ? ", " : "])\n");
 			data_count--;
 		}
 	}
@@ -174,138 +237,11 @@ static void show_channel_gathers(struct output *o, struct host1x_cdma *cdma)
 	}
 }
 
-static void host1x_debug_show_channel_cdma(struct host1x *host,
-					   struct host1x_channel *ch,
-					   struct output *o)
-{
-	struct host1x_cdma *cdma = &ch->cdma;
-	u32 dmaput, dmaget, dmactrl;
-	u32 cbstat, cbread;
-	u32 val, base, baseval;
-
-	dmaput = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAPUT);
-	dmaget = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAGET);
-	dmactrl = host1x_ch_readl(ch, HOST1X_CHANNEL_DMACTRL);
-	cbread = host1x_sync_readl(host, HOST1X_SYNC_CBREAD(ch->id));
-	cbstat = host1x_sync_readl(host, HOST1X_SYNC_CBSTAT(ch->id));
-
-	host1x_debug_output(o, "%u-%s: ", ch->id, dev_name(ch->dev));
-
-	if (HOST1X_CHANNEL_DMACTRL_DMASTOP_V(dmactrl) ||
-	    !ch->cdma.push_buffer.mapped) {
-		host1x_debug_output(o, "inactive\n\n");
-		return;
-	}
-
-	if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) == HOST1X_CLASS_HOST1X &&
-	    HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
-			HOST1X_UCLASS_WAIT_SYNCPT)
-		host1x_debug_output(o, "waiting on syncpt %d val %d\n",
-				    cbread >> 24, cbread & 0xffffff);
-	else if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) ==
-				HOST1X_CLASS_HOST1X &&
-		 HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
-				HOST1X_UCLASS_WAIT_SYNCPT_BASE) {
-		base = (cbread >> 16) & 0xff;
-		baseval =
-			host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_BASE(base));
-		val = cbread & 0xffff;
-		host1x_debug_output(o, "waiting on syncpt %d val %d (base %d = %d; offset = %d)\n",
-				    cbread >> 24, baseval + val, base,
-				    baseval, val);
-	} else
-		host1x_debug_output(o, "active class %02x, offset %04x, val %08x\n",
-				    HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat),
-				    HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat),
-				    cbread);
-
-	host1x_debug_output(o, "DMAPUT %08x, DMAGET %08x, DMACTL %08x\n",
-			    dmaput, dmaget, dmactrl);
-	host1x_debug_output(o, "CBREAD %08x, CBSTAT %08x\n", cbread, cbstat);
-
-	show_channel_gathers(o, cdma);
-	host1x_debug_output(o, "\n");
-}
-
-static void host1x_debug_show_channel_fifo(struct host1x *host,
-					   struct host1x_channel *ch,
-					   struct output *o)
-{
-	u32 val, rd_ptr, wr_ptr, start, end;
-	unsigned int data_count = 0;
-
-	host1x_debug_output(o, "%u: fifo:\n", ch->id);
-
-	val = host1x_ch_readl(ch, HOST1X_CHANNEL_FIFOSTAT);
-	host1x_debug_output(o, "FIFOSTAT %08x\n", val);
-	if (HOST1X_CHANNEL_FIFOSTAT_CFEMPTY_V(val)) {
-		host1x_debug_output(o, "[empty]\n");
-		return;
-	}
-
-	host1x_sync_writel(host, 0x0, HOST1X_SYNC_CFPEEK_CTRL);
-	host1x_sync_writel(host, HOST1X_SYNC_CFPEEK_CTRL_ENA_F(1) |
-			   HOST1X_SYNC_CFPEEK_CTRL_CHANNR_F(ch->id),
-			   HOST1X_SYNC_CFPEEK_CTRL);
-
-	val = host1x_sync_readl(host, HOST1X_SYNC_CFPEEK_PTRS);
-	rd_ptr = HOST1X_SYNC_CFPEEK_PTRS_CF_RD_PTR_V(val);
-	wr_ptr = HOST1X_SYNC_CFPEEK_PTRS_CF_WR_PTR_V(val);
-
-	val = host1x_sync_readl(host, HOST1X_SYNC_CF_SETUP(ch->id));
-	start = HOST1X_SYNC_CF_SETUP_BASE_V(val);
-	end = HOST1X_SYNC_CF_SETUP_LIMIT_V(val);
-
-	do {
-		host1x_sync_writel(host, 0x0, HOST1X_SYNC_CFPEEK_CTRL);
-		host1x_sync_writel(host, HOST1X_SYNC_CFPEEK_CTRL_ENA_F(1) |
-				   HOST1X_SYNC_CFPEEK_CTRL_CHANNR_F(ch->id) |
-				   HOST1X_SYNC_CFPEEK_CTRL_ADDR_F(rd_ptr),
-				   HOST1X_SYNC_CFPEEK_CTRL);
-		val = host1x_sync_readl(host, HOST1X_SYNC_CFPEEK_READ);
-
-		if (!data_count) {
-			host1x_debug_output(o, "%08x:", val);
-			data_count = show_channel_command(o, val);
-		} else {
-			host1x_debug_output(o, "%08x%s", val,
-					    data_count > 0 ? ", " : "])\n");
-			data_count--;
-		}
-
-		if (rd_ptr == end)
-			rd_ptr = start;
-		else
-			rd_ptr++;
-	} while (rd_ptr != wr_ptr);
-
-	if (data_count)
-		host1x_debug_output(o, ", ...])\n");
-	host1x_debug_output(o, "\n");
-
-	host1x_sync_writel(host, 0x0, HOST1X_SYNC_CFPEEK_CTRL);
-}
-
-static void host1x_debug_show_mlocks(struct host1x *host, struct output *o)
-{
-	unsigned int i;
-
-	host1x_debug_output(o, "---- mlocks ----\n");
-
-	for (i = 0; i < host1x_syncpt_nb_mlocks(host); i++) {
-		u32 owner =
-			host1x_sync_readl(host, HOST1X_SYNC_MLOCK_OWNER(i));
-		if (HOST1X_SYNC_MLOCK_OWNER_CH_OWNS_V(owner))
-			host1x_debug_output(o, "%u: locked by channel %u\n",
-				i, HOST1X_SYNC_MLOCK_OWNER_CHID_V(owner));
-		else if (HOST1X_SYNC_MLOCK_OWNER_CPU_OWNS_V(owner))
-			host1x_debug_output(o, "%u: locked by cpu\n", i);
-		else
-			host1x_debug_output(o, "%u: unlocked\n", i);
-	}
-
-	host1x_debug_output(o, "\n");
-}
+#if HOST1X_HW >= 6
+#include "debug_hw_1x06.c"
+#else
+#include "debug_hw_1x01.c"
+#endif
 
 static const struct host1x_debug_ops host1x_debug_ops = {
 	.show_channel_cdma = host1x_debug_show_channel_cdma,

drivers/gpu/host1x/hw/debug_hw_1x01.c

+/*
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Erik Gilling <konkers@android.com>
+ *
+ * Copyright (C) 2011-2013 NVIDIA Corporation
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include "../dev.h"
+#include "../debug.h"
+#include "../cdma.h"
+#include "../channel.h"
+
+static void host1x_debug_show_channel_cdma(struct host1x *host,
+					   struct host1x_channel *ch,
+					   struct output *o)
+{
+	struct host1x_cdma *cdma = &ch->cdma;
+	u32 dmaput, dmaget, dmactrl;
+	u32 cbstat, cbread;
+	u32 val, base, baseval;
+
+	dmaput = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAPUT);
+	dmaget = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAGET);
+	dmactrl = host1x_ch_readl(ch, HOST1X_CHANNEL_DMACTRL);
+	cbread = host1x_sync_readl(host, HOST1X_SYNC_CBREAD(ch->id));
+	cbstat = host1x_sync_readl(host, HOST1X_SYNC_CBSTAT(ch->id));
+
+	host1x_debug_output(o, "%u-%s: ", ch->id, dev_name(ch->dev));
+
+	if (HOST1X_CHANNEL_DMACTRL_DMASTOP_V(dmactrl) ||
+	    !ch->cdma.push_buffer.mapped) {
+		host1x_debug_output(o, "inactive\n\n");
+		return;
+	}
+
+	if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) == HOST1X_CLASS_HOST1X &&
+	    HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
+			HOST1X_UCLASS_WAIT_SYNCPT)
+		host1x_debug_output(o, "waiting on syncpt %d val %d\n",
+				    cbread >> 24, cbread & 0xffffff);
+	else if (HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat) ==
+				HOST1X_CLASS_HOST1X &&
+		 HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat) ==
+				HOST1X_UCLASS_WAIT_SYNCPT_BASE) {
+		base = (cbread >> 16) & 0xff;
+		baseval =
+			host1x_sync_readl(host, HOST1X_SYNC_SYNCPT_BASE(base));
+		val = cbread & 0xffff;
+		host1x_debug_output(o, "waiting on syncpt %d val %d (base %d = %d; offset = %d)\n",
+				    cbread >> 24, baseval + val, base,
+				    baseval, val);
+	} else
+		host1x_debug_output(o, "active class %02x, offset %04x, val %08x\n",
+				    HOST1X_SYNC_CBSTAT_CBCLASS_V(cbstat),
+				    HOST1X_SYNC_CBSTAT_CBOFFSET_V(cbstat),
+				    cbread);
+
+	host1x_debug_output(o, "DMAPUT %08x, DMAGET %08x, DMACTL %08x\n",
+			    dmaput, dmaget, dmactrl);
+	host1x_debug_output(o, "CBREAD %08x, CBSTAT %08x\n", cbread, cbstat);
+
+	show_channel_gathers(o, cdma);
+	host1x_debug_output(o, "\n");
+}
+
+static void host1x_debug_show_channel_fifo(struct host1x *host,
+					   struct host1x_channel *ch,
+					   struct output *o)
+{
+	u32 val, rd_ptr, wr_ptr, start, end;
+	unsigned int data_count = 0;
+
+	host1x_debug_output(o, "%u: fifo:\n", ch->id);
+
+	val = host1x_ch_readl(ch, HOST1X_CHANNEL_FIFOSTAT);
+	host1x_debug_output(o, "FIFOSTAT %08x\n", val);
+	if (HOST1X_CHANNEL_FIFOSTAT_CFEMPTY_V(val)) {
+		host1x_debug_output(o, "[empty]\n");
+		return;
+	}
+
+	host1x_sync_writel(host, 0x0, HOST1X_SYNC_CFPEEK_CTRL);
+	host1x_sync_writel(host, HOST1X_SYNC_CFPEEK_CTRL_ENA_F(1) |
+			   HOST1X_SYNC_CFPEEK_CTRL_CHANNR_F(ch->id),
+			   HOST1X_SYNC_CFPEEK_CTRL);
+
+	val = host1x_sync_readl(host, HOST1X_SYNC_CFPEEK_PTRS);
+	rd_ptr = HOST1X_SYNC_CFPEEK_PTRS_CF_RD_PTR_V(val);
+	wr_ptr = HOST1X_SYNC_CFPEEK_PTRS_CF_WR_PTR_V(val);
+
+	val = host1x_sync_readl(host, HOST1X_SYNC_CF_SETUP(ch->id));
+	start = HOST1X_SYNC_CF_SETUP_BASE_V(val);
+	end = HOST1X_SYNC_CF_SETUP_LIMIT_V(val);
+
+	do {
+		host1x_sync_writel(host, 0x0, HOST1X_SYNC_CFPEEK_CTRL);
+		host1x_sync_writel(host, HOST1X_SYNC_CFPEEK_CTRL_ENA_F(1) |
+				   HOST1X_SYNC_CFPEEK_CTRL_CHANNR_F(ch->id) |
+				   HOST1X_SYNC_CFPEEK_CTRL_ADDR_F(rd_ptr),
+				   HOST1X_SYNC_CFPEEK_CTRL);
+		val = host1x_sync_readl(host, HOST1X_SYNC_CFPEEK_READ);
+
+		if (!data_count) {
+			host1x_debug_output(o, "%08x: ", val);
+			data_count = show_channel_command(o, val, NULL);
+		} else {
+			host1x_debug_cont(o, "%08x%s", val,
+					  data_count > 1 ? ", " : "])\n");
+			data_count--;
+		}
+
+		if (rd_ptr == end)
+			rd_ptr = start;
+		else
+			rd_ptr++;
+	} while (rd_ptr != wr_ptr);
+
+	if (data_count)
+		host1x_debug_cont(o, ", ...])\n");
+	host1x_debug_output(o, "\n");
+
+	host1x_sync_writel(host, 0x0, HOST1X_SYNC_CFPEEK_CTRL);
+}
+
+static void host1x_debug_show_mlocks(struct host1x *host, struct output *o)
+{
+	unsigned int i;
+
+	host1x_debug_output(o, "---- mlocks ----\n");
+
+	for (i = 0; i < host1x_syncpt_nb_mlocks(host); i++) {
+		u32 owner =
+			host1x_sync_readl(host, HOST1X_SYNC_MLOCK_OWNER(i));
+		if (HOST1X_SYNC_MLOCK_OWNER_CH_OWNS_V(owner))
+			host1x_debug_output(o, "%u: locked by channel %u\n",
+				i, HOST1X_SYNC_MLOCK_OWNER_CHID_V(owner));
+		else if (HOST1X_SYNC_MLOCK_OWNER_CPU_OWNS_V(owner))
+			host1x_debug_output(o, "%u: locked by cpu\n", i);
+		else
+			host1x_debug_output(o, "%u: unlocked\n", i);
+	}
+
+	host1x_debug_output(o, "\n");
+}

drivers/gpu/host1x/hw/debug_hw_1x06.c

+/*
+ * Copyright (C) 2010 Google, Inc.
+ * Author: Erik Gilling <konkers@android.com>
+ *
+ * Copyright (C) 2011-2017 NVIDIA Corporation
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include "../dev.h"
+#include "../debug.h"
+#include "../cdma.h"
+#include "../channel.h"
+
+static void host1x_debug_show_channel_cdma(struct host1x *host,
+					   struct host1x_channel *ch,
+					   struct output *o)
+{
+	struct host1x_cdma *cdma = &ch->cdma;
+	u32 dmaput, dmaget, dmactrl;
+	u32 offset, class;
+	u32 ch_stat;
+
+	dmaput = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAPUT);
+	dmaget = host1x_ch_readl(ch, HOST1X_CHANNEL_DMAGET);
+	dmactrl = host1x_ch_readl(ch, HOST1X_CHANNEL_DMACTRL);
+	offset = host1x_ch_readl(ch, HOST1X_CHANNEL_CMDP_OFFSET);
+	class = host1x_ch_readl(ch, HOST1X_CHANNEL_CMDP_CLASS);
+	ch_stat = host1x_ch_readl(ch, HOST1X_CHANNEL_CHANNELSTAT);
+
+	host1x_debug_output(o, "%u-%s: ", ch->id, dev_name(ch->dev));
+
+	if (dmactrl & HOST1X_CHANNEL_DMACTRL_DMASTOP ||
+	    !ch->cdma.push_buffer.mapped) {
+		host1x_debug_output(o, "inactive\n\n");
+		return;
+	}
+
+	if (class == HOST1X_CLASS_HOST1X && offset == HOST1X_UCLASS_WAIT_SYNCPT)
+		host1x_debug_output(o, "waiting on syncpt\n");
+	else
+		host1x_debug_output(o, "active class %02x, offset %04x\n",
+				    class, offset);
+
+	host1x_debug_output(o, "DMAPUT %08x, DMAGET %08x, DMACTL %08x\n",
+			    dmaput, dmaget, dmactrl);
+	host1x_debug_output(o, "CHANNELSTAT %02x\n", ch_stat);
+
+	show_channel_gathers(o, cdma);
+	host1x_debug_output(o, "\n");
+}
+
+static void host1x_debug_show_channel_fifo(struct host1x *host,
+					   struct host1x_channel *ch,
+					   struct output *o)
+{
+	u32 val, rd_ptr, wr_ptr, start, end;
+	u32 payload = INVALID_PAYLOAD;
+	unsigned int data_count = 0;
+
+	host1x_debug_output(o, "%u: fifo:\n", ch->id);
+
+	val = host1x_ch_readl(ch, HOST1X_CHANNEL_CMDFIFO_STAT);
+	host1x_debug_output(o, "CMDFIFO_STAT %08x\n", val);
+	if (val & HOST1X_CHANNEL_CMDFIFO_STAT_EMPTY) {
+		host1x_debug_output(o, "[empty]\n");
+		return;
+	}
+
+	val = host1x_ch_readl(ch, HOST1X_CHANNEL_CMDFIFO_RDATA);
+	host1x_debug_output(o, "CMDFIFO_RDATA %08x\n", val);
+
+	/* Peek pointer values are invalid during SLCG, so disable it */
+	host1x_hypervisor_writel(host, 0x1, HOST1X_HV_ICG_EN_OVERRIDE);
+
+	val = 0;
+	val |= HOST1X_HV_CMDFIFO_PEEK_CTRL_ENABLE;
+	val |= HOST1X_HV_CMDFIFO_PEEK_CTRL_CHANNEL(ch->id);
+	host1x_hypervisor_writel(host, val, HOST1X_HV_CMDFIFO_PEEK_CTRL);
+
+	val = host1x_hypervisor_readl(host, HOST1X_HV_CMDFIFO_PEEK_PTRS);
+	rd_ptr = HOST1X_HV_CMDFIFO_PEEK_PTRS_RD_PTR_V(val);
+	wr_ptr = HOST1X_HV_CMDFIFO_PEEK_PTRS_WR_PTR_V(val);
+
+	val = host1x_hypervisor_readl(host, HOST1X_HV_CMDFIFO_SETUP(ch->id));
+	start = HOST1X_HV_CMDFIFO_SETUP_BASE_V(val);
+	end = HOST1X_HV_CMDFIFO_SETUP_LIMIT_V(val);
+
+	do {
+		val = 0;
+		val |= HOST1X_HV_CMDFIFO_PEEK_CTRL_ENABLE;
+		val |= HOST1X_HV_CMDFIFO_PEEK_CTRL_CHANNEL(ch->id);
+		val |= HOST1X_HV_CMDFIFO_PEEK_CTRL_ADDR(rd_ptr);
+		host1x_hypervisor_writel(host, val,
+					 HOST1X_HV_CMDFIFO_PEEK_CTRL);
+
+		val = host1x_hypervisor_readl(host,
+					      HOST1X_HV_CMDFIFO_PEEK_READ);
+
+		if (!data_count) {
+			host1x_debug_output(o, "%03x 0x%08x: ",
+					    rd_ptr - start, val);
+			data_count = show_channel_command(o, val, &payload);
+		} else {
+			host1x_debug_cont(o, "%08x%s", val,
+					  data_count > 1 ? ", " : "])\n");
+			data_count--;
+		}
+
+		if (rd_ptr == end)
+			rd_ptr = start;
+		else
+			rd_ptr++;
+	} while (rd_ptr != wr_ptr);
+
+	if (data_count)
+		host1x_debug_cont(o, ", ...])\n");
+	host1x_debug_output(o, "\n");
+
+	host1x_hypervisor_writel(host, 0x0, HOST1X_HV_CMDFIFO_PEEK_CTRL);
+	host1x_hypervisor_writel(host, 0x0, HOST1X_HV_ICG_EN_OVERRIDE);
+}
+
+static void host1x_debug_show_mlocks(struct host1x *host, struct output *o)
+{
+	/* TODO */
+}

drivers/gpu/host1x/hw/host1x01.c

@@ -21,6 +21,8 @@
 #include "host1x01_hardware.h"
 
 /* include code */
+#define HOST1X_HW 1
+
 #include "cdma_hw.c"
 #include "channel_hw.c"
 #include "debug_hw.c"

drivers/gpu/host1x/hw/host1x02.c

@@ -21,6 +21,8 @@
 #include "host1x02_hardware.h"
 
 /* include code */
+#define HOST1X_HW 2
+
 #include "cdma_hw.c"
 #include "channel_hw.c"
 #include "debug_hw.c"

drivers/gpu/host1x/hw/host1x04.c

@@ -21,6 +21,8 @@
 #include "host1x04_hardware.h"
 
 /* include code */
+#define HOST1X_HW 4
+
 #include "cdma_hw.c"
 #include "channel_hw.c"
 #include "debug_hw.c"

drivers/gpu/host1x/hw/host1x05.c

@@ -21,6 +21,8 @@
 #include "host1x05_hardware.h"
 
 /* include code */
+#define HOST1X_HW 5
+
 #include "cdma_hw.c"
 #include "channel_hw.c"
 #include "debug_hw.c"

drivers/gpu/host1x/hw/host1x06.c

+/*
+ * Host1x init for Tegra186 SoCs
+ *
+ * Copyright (c) 2017 NVIDIA Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/* include hw specification */
+#include "host1x06.h"
+#include "host1x06_hardware.h"
+
+/* include code */
+#define HOST1X_HW 6
+
+#include "cdma_hw.c"
+#include "channel_hw.c"
+#include "debug_hw.c"
+#include "intr_hw.c"
+#include "syncpt_hw.c"
+
+#include "../dev.h"
+
+int host1x06_init(struct host1x *host)
+{
+	host->channel_op = &host1x_channel_ops;
+	host->cdma_op = &host1x_cdma_ops;
+	host->cdma_pb_op = &host1x_pushbuffer_ops;
+	host->syncpt_op = &host1x_syncpt_ops;
+	host->intr_op = &host1x_intr_ops;
+	host->debug_op = &host1x_debug_ops;
+
+	return 0;
+}

drivers/gpu/host1x/hw/host1x06.h

+/*
+ * Host1x init for Tegra186 SoCs
+ *
+ * Copyright (c) 2017 NVIDIA Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef HOST1X_HOST1X06_H
+#define HOST1X_HOST1X06_H
+
+struct host1x;
+
+int host1x06_init(struct host1x *host);
+
+#endif

drivers/gpu/host1x/hw/host1x06_hardware.h

+/*
+ * Tegra host1x Register Offsets for Tegra186
+ *
+ * Copyright (c) 2017 NVIDIA Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __HOST1X_HOST1X06_HARDWARE_H
+#define __HOST1X_HOST1X06_HARDWARE_H
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+
+#include "hw_host1x06_uclass.h"
+#include "hw_host1x06_vm.h"
+#include "hw_host1x06_hypervisor.h"
+
+static inline u32 host1x_class_host_wait_syncpt(
+	unsigned indx, unsigned threshold)
+{
+	return host1x_uclass_wait_syncpt_indx_f(indx)
+		| host1x_uclass_wait_syncpt_thresh_f(threshold);
+}
+
+static inline u32 host1x_class_host_load_syncpt_base(
+	unsigned indx, unsigned threshold)
+{
+	return host1x_uclass_load_syncpt_base_base_indx_f(indx)
+		| host1x_uclass_load_syncpt_base_value_f(threshold);
+}
+
+static inline u32 host1x_class_host_wait_syncpt_base(
+	unsigned indx, unsigned base_indx, unsigned offset)
+{
+	return host1x_uclass_wait_syncpt_base_indx_f(indx)
+		| host1x_uclass_wait_syncpt_base_base_indx_f(base_indx)
+		| host1x_uclass_wait_syncpt_base_offset_f(offset);
+}
+
+static inline u32 host1x_class_host_incr_syncpt_base(
+	unsigned base_indx, unsigned offset)
+{
+	return host1x_uclass_incr_syncpt_base_base_indx_f(base_indx)
+		| host1x_uclass_incr_syncpt_base_offset_f(offset);
+}
+
+static inline u32 host1x_class_host_incr_syncpt(
+	unsigned cond, unsigned indx)
+{
+	return host1x_uclass_incr_syncpt_cond_f(cond)
+		| host1x_uclass_incr_syncpt_indx_f(indx);
+}
+
+static inline u32 host1x_class_host_indoff_reg_write(
+	unsigned mod_id, unsigned offset, bool auto_inc)
+{
+	u32 v = host1x_uclass_indoff_indbe_f(0xf)
+		| host1x_uclass_indoff_indmodid_f(mod_id)
+		| host1x_uclass_indoff_indroffset_f(offset);
+	if (auto_inc)
+		v |= host1x_uclass_indoff_autoinc_f(1);
+	return v;
+}
+
+static inline u32 host1x_class_host_indoff_reg_read(
+	unsigned mod_id, unsigned offset, bool auto_inc)
+{
+	u32 v = host1x_uclass_indoff_indmodid_f(mod_id)
+		| host1x_uclass_indoff_indroffset_f(offset)
+		| host1x_uclass_indoff_rwn_read_v();
+	if (auto_inc)
+		v |= host1x_uclass_indoff_autoinc_f(1);
+	return v;
+}
+
+/* cdma opcodes */
+static inline u32 host1x_opcode_setclass(
+	unsigned class_id, unsigned offset, unsigned mask)
+{
+	return (0 << 28) | (offset << 16) | (class_id << 6) | mask;
+}
+
+static inline u32 host1x_opcode_incr(unsigned offset, unsigned count)
+{
+	return (1 << 28) | (offset << 16) | count;
+}
+
+static inline u32 host1x_opcode_nonincr(unsigned offset, unsigned count)
+{
+	return (2 << 28) | (offset << 16) | count;
+}
+
+static inline u32 host1x_opcode_mask(unsigned offset, unsigned mask)
+{
+	return (3 << 28) | (offset << 16) | mask;
+}
+
+static inline u32 host1x_opcode_imm(unsigned offset, unsigned value)
+{
+	return (4 << 28) | (offset << 16) | value;
+}
+
+static inline u32 host1x_opcode_imm_incr_syncpt(unsigned cond, unsigned indx)
+{
+	return host1x_opcode_imm(host1x_uclass_incr_syncpt_r(),
+		host1x_class_host_incr_syncpt(cond, indx));
+}
+
+static inline u32 host1x_opcode_restart(unsigned address)
+{
+	return (5 << 28) | (address >> 4);
+}
+
+static inline u32 host1x_opcode_gather(unsigned count)
+{
+	return (6 << 28) | count;
+}
+
+static inline u32 host1x_opcode_gather_nonincr(unsigned offset,	unsigned count)
+{
+	return (6 << 28) | (offset << 16) | BIT(15) | count;
+}
+
+static inline u32 host1x_opcode_gather_incr(unsigned offset, unsigned count)
+{
+	return (6 << 28) | (offset << 16) | BIT(15) | BIT(14) | count;
+}
+
+#define HOST1X_OPCODE_NOP host1x_opcode_nonincr(0, 0)
+
+#endif

drivers/gpu/host1x/hw/hw_host1x04_channel.h

@@ -117,5 +117,17 @@ static inline u32 host1x_channel_dmactrl_dmainitget(void)
 }
 #define HOST1X_CHANNEL_DMACTRL_DMAINITGET \
 	host1x_channel_dmactrl_dmainitget()
+static inline u32 host1x_channel_channelctrl_r(void)
+{
+	return 0x98;
+}
+#define HOST1X_CHANNEL_CHANNELCTRL \
+	host1x_channel_channelctrl_r()
+static inline u32 host1x_channel_channelctrl_kernel_filter_gbuffer_f(u32 v)
+{
+	return (v & 0x1) << 2;
+}
+#define HOST1X_CHANNEL_CHANNELCTRL_KERNEL_FILTER_GBUFFER(v) \
+	host1x_channel_channelctrl_kernel_filter_gbuffer_f(v)
 
 #endif

drivers/gpu/host1x/hw/hw_host1x05_channel.h

@@ -117,5 +117,17 @@ static inline u32 host1x_channel_dmactrl_dmainitget(void)
 }
 #define HOST1X_CHANNEL_DMACTRL_DMAINITGET \
 	host1x_channel_dmactrl_dmainitget()
+static inline u32 host1x_channel_channelctrl_r(void)
+{
+	return 0x98;
+}
+#define HOST1X_CHANNEL_CHANNELCTRL \
+	host1x_channel_channelctrl_r()
+static inline u32 host1x_channel_channelctrl_kernel_filter_gbuffer_f(u32 v)
+{
+	return (v & 0x1) << 2;
+}
+#define HOST1X_CHANNEL_CHANNELCTRL_KERNEL_FILTER_GBUFFER(v) \
+	host1x_channel_channelctrl_kernel_filter_gbuffer_f(v)
 
 #endif

drivers/gpu/host1x/hw/hw_host1x06_hypervisor.h

+/*
+ * Copyright (c) 2017 NVIDIA Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#define HOST1X_HV_SYNCPT_PROT_EN			0x1ac4
+#define HOST1X_HV_SYNCPT_PROT_EN_CH_EN			BIT(1)
+#define HOST1X_HV_CH_KERNEL_FILTER_GBUFFER(x)		(0x2020 + (x * 4))
+#define HOST1X_HV_CMDFIFO_PEEK_CTRL			0x233c
+#define HOST1X_HV_CMDFIFO_PEEK_CTRL_ADDR(x)		(x)
+#define HOST1X_HV_CMDFIFO_PEEK_CTRL_CHANNEL(x)		((x) << 16)
+#define HOST1X_HV_CMDFIFO_PEEK_CTRL_ENABLE		BIT(31)
+#define HOST1X_HV_CMDFIFO_PEEK_READ			0x2340
+#define HOST1X_HV_CMDFIFO_PEEK_PTRS			0x2344
+#define HOST1X_HV_CMDFIFO_PEEK_PTRS_WR_PTR_V(x)		(((x) >> 16) & 0xfff)
+#define HOST1X_HV_CMDFIFO_PEEK_PTRS_RD_PTR_V(x)		((x) & 0xfff)
+#define HOST1X_HV_CMDFIFO_SETUP(x)			(0x2588 + (x * 4))
+#define HOST1X_HV_CMDFIFO_SETUP_LIMIT_V(x)		(((x) >> 16) & 0xfff)
+#define HOST1X_HV_CMDFIFO_SETUP_BASE_V(x)		((x) & 0xfff)
+#define HOST1X_HV_ICG_EN_OVERRIDE			0x2aa8

drivers/gpu/host1x/hw/hw_host1x06_uclass.h

+/*
+ * Copyright (c) 2017 NVIDIA Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+ /*
+  * Function naming determines intended use:
+  *
+  *     <x>_r(void) : Returns the offset for register <x>.
+  *
+  *     <x>_w(void) : Returns the word offset for word (4 byte) element <x>.
+  *
+  *     <x>_<y>_s(void) : Returns size of field <y> of register <x> in bits.
+  *
+  *     <x>_<y>_f(u32 v) : Returns a value based on 'v' which has been shifted
+  *         and masked to place it at field <y> of register <x>.  This value
+  *         can be |'d with others to produce a full register value for
+  *         register <x>.
+  *
+  *     <x>_<y>_m(void) : Returns a mask for field <y> of register <x>.  This
+  *         value can be ~'d and then &'d to clear the value of field <y> for
+  *         register <x>.
+  *
+  *     <x>_<y>_<z>_f(void) : Returns the constant value <z> after being shifted
+  *         to place it at field <y> of register <x>.  This value can be |'d
+  *         with others to produce a full register value for <x>.
+  *
+  *     <x>_<y>_v(u32 r) : Returns the value of field <y> from a full register
+  *         <x> value 'r' after being shifted to place its LSB at bit 0.
+  *         This value is suitable for direct comparison with other unshifted
+  *         values appropriate for use in field <y> of register <x>.
+  *
+  *     <x>_<y>_<z>_v(void) : Returns the constant value for <z> defined for
+  *         field <y> of register <x>.  This value is suitable for direct
+  *         comparison with unshifted values appropriate for use in field <y>
+  *         of register <x>.
+  */
+
+#ifndef HOST1X_HW_HOST1X06_UCLASS_H
+#define HOST1X_HW_HOST1X06_UCLASS_H
+
+static inline u32 host1x_uclass_incr_syncpt_r(void)
+{
+	return 0x0;
+}
+#define HOST1X_UCLASS_INCR_SYNCPT \
+	host1x_uclass_incr_syncpt_r()
+static inline u32 host1x_uclass_incr_syncpt_cond_f(u32 v)
+{
+	return (v & 0xff) << 8;
+}
+#define HOST1X_UCLASS_INCR_SYNCPT_COND_F(v) \
+	host1x_uclass_incr_syncpt_cond_f(v)
+static inline u32 host1x_uclass_incr_syncpt_indx_f(u32 v)
+{
+	return (v & 0xff) << 0;
+}
+#define HOST1X_UCLASS_INCR_SYNCPT_INDX_F(v) \
+	host1x_uclass_incr_syncpt_indx_f(v)
+static inline u32 host1x_uclass_wait_syncpt_r(void)
+{
+	return 0x8;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT \
+	host1x_uclass_wait_syncpt_r()
+static inline u32 host1x_uclass_wait_syncpt_indx_f(u32 v)
+{
+	return (v & 0xff) << 24;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_INDX_F(v) \
+	host1x_uclass_wait_syncpt_indx_f(v)
+static inline u32 host1x_uclass_wait_syncpt_thresh_f(u32 v)
+{
+	return (v & 0xffffff) << 0;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_THRESH_F(v) \
+	host1x_uclass_wait_syncpt_thresh_f(v)
+static inline u32 host1x_uclass_wait_syncpt_base_r(void)
+{
+	return 0x9;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_BASE \
+	host1x_uclass_wait_syncpt_base_r()
+static inline u32 host1x_uclass_wait_syncpt_base_indx_f(u32 v)
+{
+	return (v & 0xff) << 24;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_BASE_INDX_F(v) \
+	host1x_uclass_wait_syncpt_base_indx_f(v)
+static inline u32 host1x_uclass_wait_syncpt_base_base_indx_f(u32 v)
+{
+	return (v & 0xff) << 16;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_BASE_BASE_INDX_F(v) \
+	host1x_uclass_wait_syncpt_base_base_indx_f(v)
+static inline u32 host1x_uclass_wait_syncpt_base_offset_f(u32 v)
+{
+	return (v & 0xffff) << 0;
+}
+#define HOST1X_UCLASS_WAIT_SYNCPT_BASE_OFFSET_F(v) \
+	host1x_uclass_wait_syncpt_base_offset_f(v)
+static inline u32 host1x_uclass_load_syncpt_base_r(void)
+{
+	return 0xb;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_BASE \
+	host1x_uclass_load_syncpt_base_r()
+static inline u32 host1x_uclass_load_syncpt_base_base_indx_f(u32 v)
+{
+	return (v & 0xff) << 24;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_BASE_BASE_INDX_F(v) \
+	host1x_uclass_load_syncpt_base_base_indx_f(v)
+static inline u32 host1x_uclass_load_syncpt_base_value_f(u32 v)
+{
+	return (v & 0xffffff) << 0;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_BASE_VALUE_F(v) \
+	host1x_uclass_load_syncpt_base_value_f(v)
+static inline u32 host1x_uclass_incr_syncpt_base_base_indx_f(u32 v)
+{
+	return (v & 0xff) << 24;
+}
+#define HOST1X_UCLASS_INCR_SYNCPT_BASE_BASE_INDX_F(v) \
+	host1x_uclass_incr_syncpt_base_base_indx_f(v)
+static inline u32 host1x_uclass_incr_syncpt_base_offset_f(u32 v)
+{
+	return (v & 0xffffff) << 0;
+}
+#define HOST1X_UCLASS_INCR_SYNCPT_BASE_OFFSET_F(v) \
+	host1x_uclass_incr_syncpt_base_offset_f(v)
+static inline u32 host1x_uclass_indoff_r(void)
+{
+	return 0x2d;
+}
+#define HOST1X_UCLASS_INDOFF \
+	host1x_uclass_indoff_r()
+static inline u32 host1x_uclass_indoff_indbe_f(u32 v)
+{
+	return (v & 0xf) << 28;
+}
+#define HOST1X_UCLASS_INDOFF_INDBE_F(v) \
+	host1x_uclass_indoff_indbe_f(v)
+static inline u32 host1x_uclass_indoff_autoinc_f(u32 v)
+{
+	return (v & 0x1) << 27;
+}
+#define HOST1X_UCLASS_INDOFF_AUTOINC_F(v) \
+	host1x_uclass_indoff_autoinc_f(v)
+static inline u32 host1x_uclass_indoff_indmodid_f(u32 v)
+{
+	return (v & 0xff) << 18;
+}
+#define HOST1X_UCLASS_INDOFF_INDMODID_F(v) \
+	host1x_uclass_indoff_indmodid_f(v)
+static inline u32 host1x_uclass_indoff_indroffset_f(u32 v)
+{
+	return (v & 0xffff) << 2;
+}
+#define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \
+	host1x_uclass_indoff_indroffset_f(v)
+static inline u32 host1x_uclass_indoff_rwn_read_v(void)
+{
+	return 1;
+}
+#define HOST1X_UCLASS_INDOFF_INDROFFSET_F(v) \
+	host1x_uclass_indoff_indroffset_f(v)
+
+#endif

drivers/gpu/host1x/hw/hw_host1x06_vm.h

+/*
+ * Copyright (c) 2017 NVIDIA Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#define HOST1X_CHANNEL_DMASTART				0x0000
+#define HOST1X_CHANNEL_DMASTART_HI			0x0004
+#define HOST1X_CHANNEL_DMAPUT				0x0008
+#define HOST1X_CHANNEL_DMAPUT_HI			0x000c
+#define HOST1X_CHANNEL_DMAGET				0x0010
+#define HOST1X_CHANNEL_DMAGET_HI			0x0014
+#define HOST1X_CHANNEL_DMAEND				0x0018
+#define HOST1X_CHANNEL_DMAEND_HI			0x001c
+#define HOST1X_CHANNEL_DMACTRL				0x0020
+#define HOST1X_CHANNEL_DMACTRL_DMASTOP			BIT(0)
+#define HOST1X_CHANNEL_DMACTRL_DMAGETRST		BIT(1)
+#define HOST1X_CHANNEL_DMACTRL_DMAINITGET		BIT(2)
+#define HOST1X_CHANNEL_CMDFIFO_STAT			0x0024
+#define HOST1X_CHANNEL_CMDFIFO_STAT_EMPTY		BIT(13)
+#define HOST1X_CHANNEL_CMDFIFO_RDATA			0x0028
+#define HOST1X_CHANNEL_CMDP_OFFSET			0x0030
+#define HOST1X_CHANNEL_CMDP_CLASS			0x0034
+#define HOST1X_CHANNEL_CHANNELSTAT			0x0038
+#define HOST1X_CHANNEL_CMDPROC_STOP			0x0048
+#define HOST1X_CHANNEL_TEARDOWN				0x004c
+
+#define HOST1X_SYNC_SYNCPT_CPU_INCR(x)			(0x6400 + 4*(x))
+#define HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(x)	(0x6464 + 4*(x))
+#define HOST1X_SYNC_SYNCPT_THRESH_INT_ENABLE_CPU0(x)	(0x652c + 4*(x))
+#define HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(x)	(0x6590 + 4*(x))
+#define HOST1X_SYNC_SYNCPT_BASE(x)			(0x8000 + 4*(x))
+#define HOST1X_SYNC_SYNCPT(x)				(0x8080 + 4*(x))
+#define HOST1X_SYNC_SYNCPT_INT_THRESH(x)		(0x8a00 + 4*(x))
+#define HOST1X_SYNC_SYNCPT_CH_APP(x)			(0x9384 + 4*(x))
+#define HOST1X_SYNC_SYNCPT_CH_APP_CH(v)			(((v) & 0x3f) << 8)

drivers/gpu/host1x/hw/intr_hw.c

@@ -72,6 +72,23 @@ static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 	}
 }
 
+static void intr_hw_init(struct host1x *host, u32 cpm)
+{
+#if HOST1X_HW < 6
+	/* disable the ip_busy_timeout. this prevents write drops */
+	host1x_sync_writel(host, 0, HOST1X_SYNC_IP_BUSY_TIMEOUT);
+
+	/*
+	 * increase the auto-ack timout to the maximum value. 2d will hang
+	 * otherwise on Tegra2.
+	 */
+	host1x_sync_writel(host, 0xff, HOST1X_SYNC_CTXSW_TIMEOUT_CFG);
+
+	/* update host clocks per usec */
+	host1x_sync_writel(host, cpm, HOST1X_SYNC_USEC_CLK);
+#endif
+}
+
 static int
 _host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
 			    void (*syncpt_thresh_work)(struct work_struct *))
@@ -92,17 +109,7 @@ _host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
 		return err;
 	}
 
-	/* disable the ip_busy_timeout. this prevents write drops */
-	host1x_sync_writel(host, 0, HOST1X_SYNC_IP_BUSY_TIMEOUT);
-
-	/*
-	 * increase the auto-ack timout to the maximum value. 2d will hang
-	 * otherwise on Tegra2.
-	 */
-	host1x_sync_writel(host, 0xff, HOST1X_SYNC_CTXSW_TIMEOUT_CFG);
-
-	/* update host clocks per usec */
-	host1x_sync_writel(host, cpm, HOST1X_SYNC_USEC_CLK);
+	intr_hw_init(host, cpm);
 
 	return 0;
 }

drivers/gpu/host1x/hw/syncpt_hw.c

@@ -106,6 +106,50 @@ static int syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr)
 	return 0;
 }
 
+/**
+ * syncpt_assign_to_channel() - Assign syncpoint to channel
+ * @sp: syncpoint
+ * @ch: channel
+ *
+ * On chips with the syncpoint protection feature (Tegra186+), assign @sp to
+ * @ch, preventing other channels from incrementing the syncpoints. If @ch is
+ * NULL, unassigns the syncpoint.
+ *
+ * On older chips, do nothing.
+ */
+static void syncpt_assign_to_channel(struct host1x_syncpt *sp,
+				  struct host1x_channel *ch)
+{
+#if HOST1X_HW >= 6
+	struct host1x *host = sp->host;
+
+	if (!host->hv_regs)
+		return;
+
+	host1x_sync_writel(host,
+			   HOST1X_SYNC_SYNCPT_CH_APP_CH(ch ? ch->id : 0xff),
+			   HOST1X_SYNC_SYNCPT_CH_APP(sp->id));
+#endif
+}
+
+/**
+ * syncpt_enable_protection() - Enable syncpoint protection
+ * @host: host1x instance
+ *
+ * On chips with the syncpoint protection feature (Tegra186+), enable this
+ * feature. On older chips, do nothing.
+ */
+static void syncpt_enable_protection(struct host1x *host)
+{
+#if HOST1X_HW >= 6
+	if (!host->hv_regs)
+		return;
+
+	host1x_hypervisor_writel(host, HOST1X_HV_SYNCPT_PROT_EN_CH_EN,
+				 HOST1X_HV_SYNCPT_PROT_EN);
+#endif
+}
+
 static const struct host1x_syncpt_ops host1x_syncpt_ops = {
 	.restore = syncpt_restore,
 	.restore_wait_base = syncpt_restore_wait_base,
@@ -113,4 +157,6 @@ static const struct host1x_syncpt_ops host1x_syncpt_ops = {
 	.load = syncpt_load,
 	.cpu_incr = syncpt_cpu_incr,
 	.patch_wait = syncpt_patch_wait,
+	.assign_to_channel = syncpt_assign_to_channel,
+	.enable_protection = syncpt_enable_protection,
 };

drivers/gpu/host1x/syncpt.c

@@ -54,7 +54,7 @@ static void host1x_syncpt_base_free(struct host1x_syncpt_base *base)
 }
 
 static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host,
-						 struct device *dev,
+						 struct host1x_client *client,
 						 unsigned long flags)
 {
 	int i;
@@ -76,11 +76,11 @@ static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host,
 	}
 
 	name = kasprintf(GFP_KERNEL, "%02u-%s", sp->id,
-			dev ? dev_name(dev) : NULL);
+			 client ? dev_name(client->dev) : NULL);
 	if (!name)
 		goto free_base;
 
-	sp->dev = dev;
+	sp->client = client;
 	sp->name = name;
 
 	if (flags & HOST1X_SYNCPT_CLIENT_MANAGED)
@@ -398,6 +398,13 @@ int host1x_syncpt_init(struct host1x *host)
 	for (i = 0; i < host->info->nb_pts; i++) {
 		syncpt[i].id = i;
 		syncpt[i].host = host;
+
+		/*
+		 * Unassign syncpt from channels for purposes of Tegra186
+		 * syncpoint protection. This prevents any channel from
+		 * accessing it until it is reassigned.
+		 */
+		host1x_hw_syncpt_assign_to_channel(host, &syncpt[i], NULL);
 	}
 
 	for (i = 0; i < host->info->nb_bases; i++)
@@ -408,6 +415,7 @@ int host1x_syncpt_init(struct host1x *host)
 	host->bases = bases;
 
 	host1x_syncpt_restore(host);
+	host1x_hw_syncpt_enable_protection(host);
 
 	/* Allocate sync point to use for clearing waits for expired fences */
 	host->nop_sp = host1x_syncpt_alloc(host, NULL, 0);
@@ -419,7 +427,7 @@ int host1x_syncpt_init(struct host1x *host)
 
 /**
  * host1x_syncpt_request() - request a syncpoint
- * @dev: device requesting the syncpoint
+ * @client: client requesting the syncpoint
  * @flags: flags
  *
  * host1x client drivers can use this function to allocate a syncpoint for
@@ -427,12 +435,12 @@ int host1x_syncpt_init(struct host1x *host)
  * use by the client exclusively. When no longer using a syncpoint, a host1x
  * client driver needs to release it using host1x_syncpt_free().
  */
-struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
+struct host1x_syncpt *host1x_syncpt_request(struct host1x_client *client,
 					    unsigned long flags)
 {
-	struct host1x *host = dev_get_drvdata(dev->parent);
+	struct host1x *host = dev_get_drvdata(client->parent->parent);
 
-	return host1x_syncpt_alloc(host, dev, flags);
+	return host1x_syncpt_alloc(host, client, flags);
 }
 EXPORT_SYMBOL(host1x_syncpt_request);
 
@@ -456,7 +464,7 @@ void host1x_syncpt_free(struct host1x_syncpt *sp)
 	host1x_syncpt_base_free(sp->base);
 	kfree(sp->name);
 	sp->base = NULL;
-	sp->dev = NULL;
+	sp->client = NULL;
 	sp->name = NULL;
 	sp->client_managed = false;
 

drivers/gpu/host1x/syncpt.h

@@ -44,7 +44,7 @@ struct host1x_syncpt {
 	const char *name;
 	bool client_managed;
 	struct host1x *host;
-	struct device *dev;
+	struct host1x_client *client;
 	struct host1x_syncpt_base *base;
 
 	/* interrupt data */

include/linux/host1x.h

@@ -157,7 +157,7 @@ int host1x_syncpt_incr(struct host1x_syncpt *sp);
 u32 host1x_syncpt_incr_max(struct host1x_syncpt *sp, u32 incrs);
 int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 		       u32 *value);
-struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
+struct host1x_syncpt *host1x_syncpt_request(struct host1x_client *client,
 					    unsigned long flags);
 void host1x_syncpt_free(struct host1x_syncpt *sp);