Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

28 files changed, 1118 insertions, 214 deletions

diff --git a/drivers/gpu/host1x/Makefile b/drivers/gpu/host1x/Makefile
index c0b80244158d..b92016ce09b7 100644
--- a/drivers/gpu/host1x/Makefile
+++ b/drivers/gpu/host1x/Makefile
@@ -12,6 +12,7 @@ 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
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index ed03b3243195..2e57c9cea696 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -404,12 +404,13 @@ 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);
diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c
index db9b91d1384c..2fb93c27c1d9 100644
--- a/drivers/gpu/host1x/channel.c
+++ b/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)
diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c
index 2aae0e63214c..dc77ec452ffc 100644
--- a/drivers/gpu/host1x/debug.c
+++ b/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)
diff --git a/drivers/gpu/host1x/debug.h b/drivers/gpu/host1x/debug.h
index 4595b2e0799f..990cce47e737 100644
--- a/drivers/gpu/host1x/debug.h
+++ b/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)
 {
-	pr_info("%s", str);
+	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;
 
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 5267c62e8896..bf67c3aeb634 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/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, },
@@ -116,20 +139,37 @@ 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;
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!regs) {
-		dev_err(&pdev->dev, "failed to get registers\n");
-		return -ENXIO;
+	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);
@@ -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) {
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index ffdbc15b749b..502769726480 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/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 *))
 {
diff --git a/drivers/gpu/host1x/hw/cdma_hw.c b/drivers/gpu/host1x/hw/cdma_hw.c
index 6b231119193e..ce320534cbed 100644
--- a/drivers/gpu/host1x/hw/cdma_hw.c
+++ b/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;
 	}
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 8447a56c41ca..9af758785a11 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/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 @@ error:
 	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;
 }
 
diff --git a/drivers/gpu/host1x/hw/debug_hw.c b/drivers/gpu/host1x/hw/debug_hw.c
index 7a4a3286e4a7..989476801f9d 100644
--- a/drivers/gpu/host1x/hw/debug_hw.c
+++ b/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(h