8 files changed, 331 insertions, 218 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index d5f5e56422f5..e5fcefa49f19 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -15,9 +15,6 @@
 #include <linux/types.h>
 #include <linux/cpumask.h>
 #include <linux/qcom_scm.h>
-#include <linux/dma-mapping.h>
-#include <linux/of_address.h>
-#include <linux/soc/qcom/mdt_loader.h>
 #include <linux/pm_opp.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/slab.h>
@@ -30,94 +27,6 @@ static void a5xx_dump(struct msm_gpu *gpu);
 
 #define GPU_PAS_ID 13
 
-static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname)
-{
-	struct device *dev = &gpu->pdev->dev;
-	const struct firmware *fw;
-	struct device_node *np;
-	struct resource r;
-	phys_addr_t mem_phys;
-	ssize_t mem_size;
-	void *mem_region = NULL;
-	int ret;
-
-	if (!IS_ENABLED(CONFIG_ARCH_QCOM))
-		return -EINVAL;
-
-	np = of_get_child_by_name(dev->of_node, "zap-shader");
-	if (!np)
-		return -ENODEV;
-
-	np = of_parse_phandle(np, "memory-region", 0);
-	if (!np)
-		return -EINVAL;
-
-	ret = of_address_to_resource(np, 0, &r);
-	if (ret)
-		return ret;
-
-	mem_phys = r.start;
-	mem_size = resource_size(&r);
-
-	/* Request the MDT file for the firmware */
-	fw = adreno_request_fw(to_adreno_gpu(gpu), fwname);
-	if (IS_ERR(fw)) {
-		DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname);
-		return PTR_ERR(fw);
-	}
-
-	/* Figure out how much memory we need */
-	mem_size = qcom_mdt_get_size(fw);
-	if (mem_size < 0) {
-		ret = mem_size;
-		goto out;
-	}
-
-	/* Allocate memory for the firmware image */
-	mem_region = memremap(mem_phys, mem_size,  MEMREMAP_WC);
-	if (!mem_region) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	/*
-	 * Load the rest of the MDT
-	 *
-	 * Note that we could be dealing with two different paths, since
-	 * with upstream linux-firmware it would be in a qcom/ subdir..
-	 * adreno_request_fw() handles this, but qcom_mdt_load() does
-	 * not.  But since we've already gotten thru adreno_request_fw()
-	 * we know which of the two cases it is:
-	 */
-	if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) {
-		ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID,
-				mem_region, mem_phys, mem_size, NULL);
-	} else {
-		char *newname;
-
-		newname = kasprintf(GFP_KERNEL, "qcom/%s", fwname);
-
-		ret = qcom_mdt_load(dev, fw, newname, GPU_PAS_ID,
-				mem_region, mem_phys, mem_size, NULL);
-		kfree(newname);
-	}
-	if (ret)
-		goto out;
-
-	/* Send the image to the secure world */
-	ret = qcom_scm_pas_auth_and_reset(GPU_PAS_ID);
-	if (ret)
-		DRM_DEV_ERROR(dev, "Unable to authorize the image\n");
-
-out:
-	if (mem_region)
-		memunmap(mem_region);
-
-	release_firmware(fw);
-
-	return ret;
-}
-
 static void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -563,8 +472,6 @@ static int a5xx_zap_shader_resume(struct msm_gpu *gpu)
 static int a5xx_zap_shader_init(struct msm_gpu *gpu)
 {
 	static bool loaded;
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	struct platform_device *pdev = gpu->pdev;
 	int ret;
 
 	/*
@@ -574,23 +481,9 @@ static int a5xx_zap_shader_init(struct msm_gpu *gpu)
 	if (loaded)
 		return a5xx_zap_shader_resume(gpu);
 
-	/* We need SCM to be able to load the firmware */
-	if (!qcom_scm_is_available()) {
-		DRM_DEV_ERROR(&pdev->dev, "SCM is not available\n");
-		return -EPROBE_DEFER;
-	}
-
-	/* Each GPU has a target specific zap shader firmware name to use */
-	if (!adreno_gpu->info->zapfw) {
-		DRM_DEV_ERROR(&pdev->dev,
-			"Zap shader firmware file not specified for this target\n");
-		return -ENODEV;
-	}
-
-	ret = zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw);
+	ret = adreno_zap_shader_load(gpu, GPU_PAS_ID);
 
 	loaded = !ret;
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index d1662a75c7ec..9155dafae2a9 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -3,12 +3,31 @@
 
 #include <linux/clk.h>
 #include <linux/interconnect.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_opp.h>
 #include <soc/qcom/cmd-db.h>
 
 #include "a6xx_gpu.h"
 #include "a6xx_gmu.xml.h"
 
+static void a6xx_gmu_fault(struct a6xx_gmu *gmu)
+{
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+	struct msm_gpu *gpu = &adreno_gpu->base;
+	struct drm_device *dev = gpu->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+
+	/* FIXME: add a banner here */
+	gmu->hung = true;
+
+	/* Turn off the hangcheck timer while we are resetting */
+	del_timer(&gpu->hangcheck_timer);
+
+	/* Queue the GPU handler because we need to treat this as a recovery */
+	queue_work(priv->wq, &gpu->recover_work);
+}
+
 static irqreturn_t a6xx_gmu_irq(int irq, void *data)
 {
 	struct a6xx_gmu *gmu = data;
@@ -20,8 +39,7 @@ static irqreturn_t a6xx_gmu_irq(int irq, void *data)
 	if (status & A6XX_GMU_AO_HOST_INTERRUPT_STATUS_WDOG_BITE) {
 		dev_err_ratelimited(gmu->dev, "GMU watchdog expired\n");
 
-		/* Temporary until we can recover safely */
-		BUG();
+		a6xx_gmu_fault(gmu);
 	}
 
 	if (status &  A6XX_GMU_AO_HOST_INTERRUPT_STATUS_HOST_AHB_BUS_ERROR)
@@ -45,8 +63,7 @@ static irqreturn_t a6xx_hfi_irq(int irq, void *data)
 	if (status & A6XX_GMU_GMU2HOST_INTR_INFO_CM3_FAULT) {
 		dev_err_ratelimited(gmu->dev, "GMU firmware fault\n");
 
-		/* Temporary until we can recover safely */
-		BUG();
+		a6xx_gmu_fault(gmu);
 	}
 
 	return IRQ_HANDLED;
@@ -165,10 +182,8 @@ static bool a6xx_gmu_check_idle_level(struct a6xx_gmu *gmu)
 }
 
 /* Wait for the GMU to get to its most idle state */
-int a6xx_gmu_wait_for_idle(struct a6xx_gpu *a6xx_gpu)
+int a6xx_gmu_wait_for_idle(struct a6xx_gmu *gmu)
 {
-	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
-
 	return spin_until(a6xx_gmu_check_idle_level(gmu));
 }
 
@@ -567,7 +582,7 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 		if (!rpmh_init) {
 			a6xx_gmu_rpmh_init(gmu);
 			rpmh_init = true;
-		} else if (state != GMU_RESET) {
+		} else {
 			ret = a6xx_rpmh_start(gmu);
 			if (ret)
 				return ret;
@@ -633,20 +648,6 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state)
 	 A6XX_GMU_AO_HOST_INTERRUPT_STATUS_HOST_AHB_BUS_ERROR | \
 	 A6XX_GMU_AO_HOST_INTERRUPT_STATUS_FENCE_ERR)
 
-static void a6xx_gmu_irq_enable(struct a6xx_gmu *gmu)
-{
-	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0);
-	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_CLR, ~0);
-
-	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_MASK,
-		~A6XX_GMU_IRQ_MASK);
-	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK,
-		~A6XX_HFI_IRQ_MASK);
-
-	enable_irq(gmu->gmu_irq);
-	enable_irq(gmu->hfi_irq);
-}
-
 static void a6xx_gmu_irq_disable(struct a6xx_gmu *gmu)
 {
 	disable_irq(gmu->gmu_irq);
@@ -656,21 +657,10 @@ static void a6xx_gmu_irq_disable(struct a6xx_gmu *gmu)
 	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~0);
 }
 
-int a6xx_gmu_reset(struct a6xx_gpu *a6xx_gpu)
+static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu)
 {
-	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
-	int ret;
 	u32 val;
 
-	/* Flush all the queues */
-	a6xx_hfi_stop(gmu);
-
-	/* Stop the interrupts */
-	a6xx_gmu_irq_disable(gmu);
-
-	/* Force off SPTP in case the GMU is managing it */
-	a6xx_sptprac_disable(gmu);
-
 	/* Make sure there are no outstanding RPMh votes */
 	gmu_poll_timeout(gmu, REG_A6XX_RSCC_TCS0_DRV0_STATUS, val,
 		(val & 1), 100, 10000);
@@ -680,37 +670,22 @@ int a6xx_gmu_reset(struct a6xx_gpu *a6xx_gpu)
 		(val & 1), 100, 10000);
 	gmu_poll_timeout(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS, val,
 		(val & 1), 100, 1000);
+}
 
-	/* Force off the GX GSDC */
-	regulator_force_disable(gmu->gx);
-
-	/* Disable the resources */
-	clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);
-	pm_runtime_put_sync(gmu->dev);
-
-	/* Re-enable the resources */
-	pm_runtime_get_sync(gmu->dev);
-
-	/* Use a known rate to bring up the GMU */
-	clk_set_rate(gmu->core_clk, 200000000);
-	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
-	if (ret)
-		goto out;
-
-	a6xx_gmu_irq_enable(gmu);
-
-	ret = a6xx_gmu_fw_start(gmu, GMU_RESET);
-	if (!ret)
-		ret = a6xx_hfi_start(gmu, GMU_COLD_BOOT);
+/* Force the GMU off in case it isn't responsive */
+static void a6xx_gmu_force_off(struct a6xx_gmu *gmu)
+{
+	/* Flush all the queues */
+	a6xx_hfi_stop(gmu);
 
-	/* Set the GPU back to the highest power frequency */
-	__a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1);
+	/* Stop the interrupts */
+	a6xx_gmu_irq_disable(gmu);
 
-out:
-	if (ret)
-		a6xx_gmu_clear_oob(gmu, GMU_OOB_BOOT_SLUMBER);
+	/* Force off SPTP in case the GMU is managing it */
+	a6xx_sptprac_disable(gmu);
 
-	return ret;
+	/* Make sure there are no outstanding RPMh votes */
+	a6xx_gmu_rpmh_off(gmu);
 }
 
 int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
@@ -723,19 +698,26 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	if (WARN(!gmu->mmio, "The GMU is not set up yet\n"))
 		return 0;
 
+	gmu->hung = false;
+
 	/* Turn on the resources */
 	pm_runtime_get_sync(gmu->dev);
 
 	/* Use a known rate to bring up the GMU */
 	clk_set_rate(gmu->core_clk, 200000000);
 	ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks);
-	if (ret)
-		goto out;
+	if (ret) {
+		pm_runtime_put(gmu->dev);
+		return ret;
+	}
 
 	/* Set the bus quota to a reasonable value for boot */
 	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(3072));
 
-	a6xx_gmu_irq_enable(gmu);
+	/* Enable the GMU interrupt */
+	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0);
+	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_MASK, ~A6XX_GMU_IRQ_MASK);
+	enable_irq(gmu->gmu_irq);
 
 	/* Check to see if we are doing a cold or warm boot */
 	status = gmu_read(gmu, REG_A6XX_GMU_GENERAL_7) == 1 ?
@@ -746,14 +728,35 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 		goto out;
 
 	ret = a6xx_hfi_start(gmu, status);
+	if (ret)
+		goto out;
+
+	/*
+	 * Turn on the GMU firmware fault interrupt after we know the boot
+	 * sequence is successful
+	 */
+	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_CLR, ~0);
+	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~A6XX_HFI_IRQ_MASK);
+	enable_irq(gmu->hfi_irq);
 
 	/* Set the GPU to the highest power frequency */
 	__a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1);
 
+	/*
+	 * "enable" the GX power domain which won't actually do anything but it
+	 * will make sure that the refcounting is correct in case we need to
+	 * bring down the GX after a GMU failure
+	 */
+	if (!IS_ERR(gmu->gxpd))
+		pm_runtime_get(gmu->gxpd);
+
 out:
-	/* Make sure to turn off the boot OOB request on error */
-	if (ret)
-		a6xx_gmu_clear_oob(gmu, GMU_OOB_BOOT_SLUMBER);
+	/* On failure, shut down the GMU to leave it in a good state */
+	if (ret) {
+		disable_irq(gmu->gmu_irq);
+		a6xx_rpmh_stop(gmu);
+		pm_runtime_put(gmu->dev);
+	}
 
 	return ret;
 }
@@ -773,11 +776,12 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu)
 	return true;
 }
 
-int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
+/* Gracefully try to shut down the GMU and by extension the GPU */
+static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
 	u32 val;
 
 	/*
@@ -787,10 +791,19 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 	val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE);
 
 	if (val != 0xf) {
-		int ret = a6xx_gmu_wait_for_idle(a6xx_gpu);
+		int ret = a6xx_gmu_wait_for_idle(gmu);
 
-		/* Temporary until we can recover safely */
-		BUG_ON(ret);
+		/* If the GMU isn't responding assume it is hung */
+		if (ret) {
+			a6xx_gmu_force_off(gmu);
+			return;
+		}
+
+		/* Clear the VBIF pipe before shutting down */
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf)
+			== 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
 
 		/* tell the GMU we want to slumber */
 		a6xx_gmu_notify_slumber(gmu);
@@ -822,10 +835,37 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 
 	/* Tell RPMh to power off the GPU */
 	a6xx_rpmh_stop(gmu);
+}
+
+
+int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
+{
+	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
+	struct msm_gpu *gpu = &a6xx_gpu->base.base;
+
+	if (!pm_runtime_active(gmu->dev))
+		return 0;
+
+	/*
+	 * Force the GMU off if we detected a hang, otherwise try to shut it
+	 * down gracefully
+	 */
+	if (gmu->hung)
+		a6xx_gmu_force_off(gmu);
+	else
+		a6xx_gmu_shutdown(gmu);
 
 	/* Remove the bus vote */
 	icc_set_bw(gpu->icc_path, 0, 0);
 
+	/*
+	 * Make sure the GX domain is off before turning off the GMU (CX)
+	 * domain. Usually the GMU does this but only if the shutdown sequence
+	 * was successful
+	 */
+	if (!IS_ERR(gmu->gxpd))
+		pm_runtime_put_sync(gmu->gxpd);
+
 	clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);
 
 	pm_runtime_put_sync(gmu->dev);
@@ -948,25 +988,20 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
 }
 
 /* Return the 'arc-level' for the given frequency */
-static u32 a6xx_gmu_get_arc_level(struct device *dev, unsigned long freq)
+static unsigned int a6xx_gmu_get_arc_level(struct device *dev,
+					   unsigned long freq)
 {
 	struct dev_pm_opp *opp;
-	struct device_node *np;
-	u32 val = 0;
+	unsigned int val;
 
 	if (!freq)
 		return 0;
 
-	opp  = dev_pm_opp_find_freq_exact(dev, freq, true);
+	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
 	if (IS_ERR(opp))
 		return 0;
 
-	np = dev_pm_opp_get_of_node(opp);
-
-	if (np) {
-		of_property_read_u32(np, "opp-level", &val);
-		of_node_put(np);
-	}
+	val = dev_pm_opp_get_level(opp);
 
 	dev_pm_opp_put(opp);
 
@@ -1002,7 +1037,7 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes,
 	/* Construct a vote for each frequency */
 	for (i = 0; i < freqs_count; i++) {
 		u8 pindex = 0, sindex = 0;
-		u32 level = a6xx_gmu_get_arc_level(dev, freqs[i]);
+		unsigned int level = a6xx_gmu_get_arc_level(dev, freqs[i]);
 
 		/* Get the primary index that matches the arc level */
 		for (j = 0; j < pri_count; j++) {
@@ -1195,9 +1230,15 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
 	if (IS_ERR_OR_NULL(gmu->mmio))
 		return;
 
-	pm_runtime_disable(gmu->dev);
 	a6xx_gmu_stop(a6xx_gpu);
 
+	pm_runtime_disable(gmu->dev);
+
+	if (!IS_ERR(gmu->gxpd)) {
+		pm_runtime_disable(gmu->gxpd);
+		dev_pm_domain_detach(gmu->gxpd, false);
+	}
+
 	a6xx_gmu_irq_disable(gmu);
 	a6xx_gmu_memory_free(gmu, gmu->hfi);
 
@@ -1223,7 +1264,6 @@ int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	gmu->idle_level = GMU_IDLE_STATE_ACTIVE;
 
 	pm_runtime_enable(gmu->dev);
-	gmu->gx = devm_regulator_get(gmu->dev, "vdd");
 
 	/* Get the list of clocks */
 	ret = a6xx_gmu_clocks_probe(gmu);
@@ -1257,6 +1297,12 @@ int a6xx_gmu_probe(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	if (gmu->hfi_irq < 0 || gmu->gmu_irq < 0)
 		goto err;
 
+	/*
+	 * Get a link to the GX power domain to reset the GPU in case of GMU
+	 * crash
+	 */
+	gmu->gxpd = dev_pm_domain_attach_by_name(gmu->dev, "gx");
+
 	/* Get the power levels for the GMU and GPU */
 	a6xx_gmu_pwrlevels_probe(gmu);
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index c721d9165d8e..bedd8e6a63aa 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -27,9 +27,6 @@ struct a6xx_gmu_bo {
 /* the GMU is coming up for the first time or back from a power collapse */
 #define GMU_COLD_BOOT 1
 
-/* The GMU is being soft reset after a fault */
-#define GMU_RESET 2
-
 /*
  * These define the level of control that the GMU has - the higher the number
  * the more things that the GMU hardware controls on its own.
@@ -52,11 +49,11 @@ struct a6xx_gmu {
 	int hfi_irq;
 	int gmu_irq;
 
-	struct regulator *gx;
-
 	struct iommu_domain *domain;
 	u64 uncached_iova_base;
 
+	struct device *gxpd;
+
 	int idle_level;
 
 	struct a6xx_gmu_bo *hfi;
@@ -78,7 +75,7 @@ struct a6xx_gmu {
 
 	struct a6xx_hfi_queue queues[2];
 
-	struct tasklet_struct hfi_tasklet;
+	bool hung;
 };
 
 static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index fefe773c989e..e74dce474250 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -10,6 +10,8 @@
 
 #include <linux/devfreq.h>
 
+#define GPU_PAS_ID 13
+
 static inline bool _a6xx_check_idle(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -343,6 +345,20 @@ static int a6xx_ucode_init(struct msm_gpu *gpu)
 	return 0;
 }
 
+static int a6xx_zap_shader_init(struct msm_gpu *gpu)
+{
+	static bool loaded;
+	int ret;
+
+	if (loaded)
+		return 0;
+
+	ret = adreno_zap_shader_load(gpu, GPU_PAS_ID);
+
+	loaded = !ret;
+	return ret;
+}
+
 #define A6XX_INT_MASK (A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR | \
 	  A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW | \
 	  A6XX_RBBM_INT_0_MASK_CP_HW_ERROR | \
@@ -491,7 +507,28 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		goto out;
 
-	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	/*
+	 * Try to load a zap shader into the secure world. If successful
+	 * we can use the CP to switch out of secure mode. If not then we
+	 * have no resource but to try to switch ourselves out manually. If we
+	 * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will
+	 * be blocked and a permissions violation will soon follow.
+	 */
+	ret = a6xx_zap_shader_init(gpu);
+	if (!ret) {
+		OUT_PKT7(gpu->rb[0], CP_SET_SECURE_MODE, 1);
+		OUT_RING(gpu->rb[0], 0x00000000);
+
+		a6xx_flush(gpu, gpu->rb[0]);
+		if (!a6xx_idle(gpu, gpu->rb[0]))
+			return -EINVAL;
+	} else {
+		/* Print a warning so if we die, we know why */
+		dev_warn_once(gpu->dev->dev,
+			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
+		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+		ret = 0;
+	}
 
 out:
 	/*
@@ -678,13 +715,15 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	int ret;
 
-	ret = a6xx_gmu_resume(a6xx_gpu);
-
 	gpu->needs_hw_init = true;
 
+	ret = a6xx_gmu_resume(a6xx_gpu);
+	if (ret)
+		return ret;
+
 	msm_gpu_resume_devfreq(gpu);
 
-	return ret;
+	return 0;
 }
 
 static int a6xx_pm_suspend(struct msm_gpu *gpu)
@@ -694,18 +733,6 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
-	/*
-	 * Make sure the GMU is idle before continuing (because some transitions
-	 * may use VBIF
-	 */
-	a6xx_gmu_wait_for_idle(a6xx_gpu);
-
-	/* Clear the VBIF pipe before shutting down */
-	/* FIXME: This accesses the GPU - do we need to make sure it is on? */
-	gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
-	spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf) == 0xf);
-	gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
-
 	return a6xx_gmu_stop(a6xx_gpu);
 }
 
@@ -781,14 +808,16 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = a6xx_active_ring,
 		.irq = a6xx_irq,
 		.destroy = a6xx_destroy,
-#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+#if defined(CONFIG_DRM_MSM_GPU_STATE)
 		.show = a6xx_show,
 #endif
 		.gpu_busy = a6xx_gpu_busy,
 		.gpu_get_freq = a6xx_gmu_get_freq,
 		.gpu_set_freq = a6xx_gmu_set_freq,
+#if defined(CONFIG_DRM_MSM_GPU_STATE)
 		.gpu_state_get = a6xx_gpu_state_get,
 		.gpu_state_put = a6xx_gpu_state_put,
+#endif
 	},
 	.get_timestamp = a6xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 528a4cfe07cd..b46279eb18c5 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -46,9 +46,8 @@ struct a6xx_gpu {
 int a6xx_gmu_resume(struct a6xx_gpu *gpu);
 int a6xx_gmu_stop(struct a6xx_gpu *gpu);
 
-int a6xx_gmu_wait_for_idle(struct a6xx_gpu *gpu);
+int a6xx_gmu_wait_for_idle(struct a6xx_gmu *gmu);
 
-int a6xx_gmu_reset(struct a6xx_gpu *a6xx_gpu);
 bool a6xx_gmu_isidle(struct a6xx_gmu *gmu);
 
 int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 714ed6505e47..b907245d3d96 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -155,6 +155,7 @@ static const struct adreno_info gpulist[] = {
 		.gmem = SZ_1M,
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init = a6xx_gpu_init,
+		.zapfw = "a630_zap.mdt",
 	},
 };
 
@@ -229,6 +230,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
+		pm_runtime_put_sync(&pdev->dev);
 		DRM_DEV_ERROR(dev->dev, "Couldn't power up the GPU: %d\n", ret);
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 27898475cdf4..6f7f4114afcf 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -19,13 +19,148 @@
 
 #include <linux/ascii85.h>
 #include <linux/interconnect.h>
+#include <linux/qcom_scm.h>
 #include <linux/kernel.h>
+#include <linux/of_address.h>
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
+#include <linux/soc/qcom/mdt_loader.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
 
+static bool zap_available = true;
+
+static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
+		u32 pasid)
+{
+	struct device *dev = &gpu->pdev->dev;
+	const struct firmware *fw;
+	struct device_node *np, *mem_np;
+	struct resource r;
+	phys_addr_t mem_phys;
+	ssize_t mem_size;
+	void *mem_region = NULL;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_ARCH_QCOM)) {
+		zap_available = false;
+		return -EINVAL;
+	}
+
+	np = of_get_child_by_name(dev->of_node, "zap-shader");
+	if (!np) {
+		zap_available = false;
+		return -ENODEV;
+	}
+
+	mem_np = of_parse_phandle(np, "memory-region", 0);
+	of_node_put(np);
+	if (!mem_np) {
+		zap_available = false;
+		return -EINVAL;
+	}
+
+	ret = of_address_to_resource(mem_np, 0, &r);
+	of_node_put(mem_np);
+	if (ret)
+		return ret;
+
+	mem_phys = r.start;
+	mem_size = resource_size(&r);
+
+	/* Request the MDT file for the firmware */
+	fw = adreno_request_fw(to_adreno_gpu(gpu), fwname);
+	if (IS_ERR(fw)) {
+		DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname);
+		return PTR_ERR(fw);
+	}
+
+	/* Figure out how much memory we need */
+	mem_size = qcom_mdt_get_size(fw);
+	if (mem_size < 0) {
+		ret = mem_size;
+		goto out;
+	}
+
+	/* Allocate memory for the firmware image */
+	mem_region = memremap(mem_phys, mem_size,  MEMREMAP_WC);
+	if (!mem_region) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * Load the rest of the MDT
+	 *
+	 * Note that we could be dealing with two different paths, since
+	 * with upstream linux-firmware it would be in a qcom/ subdir..
+	 * adreno_request_fw() handles this, but qcom_mdt_load() does
+	 * not.  But since we've already gotten through adreno_request_fw()
+	 * we know which of the two cases it is:
+	 */
+	if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) {
+		ret = qcom_mdt_load(dev, fw, fwname, pasid,
+				mem_region, mem_phys, mem_size, NULL);
+	} else {
+		char *newname;
+
+		newname = kasprintf(GFP_KERNEL, "qcom/%s", fwname);
+
+		ret = qcom_mdt_load(dev, fw, newname, pasid,
+				mem_region, mem_phys, mem_size, NULL);
+		kfree(newname);
+	}
+	if (ret)
+		goto out;
+
+	/* Send the image to the secure world */
+	ret = qcom_scm_pas_auth_and_reset(pasid);
+
+	/*
+	 * If the scm call returns -EOPNOTSUPP we assume that this target
+	 * doesn't need/support the zap shader so quietly fail
+	 */
+	if (ret == -EOPNOTSUPP)
+		zap_available = false;
+	else if (ret)
+		DRM_DEV_ERROR(dev, "Unable to authorize the image\n");
+
+out:
+	if (mem_region)
+		memunmap(mem_region);
+
+	release_firmware(fw);
+
+	return ret;
+}
+
+int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct platform_device *pdev = gpu->pdev;
+
+	/* Short cut if we determine the zap shader isn't available/needed */
+	if (!zap_available)
+		return -ENODEV;
+
+	/* We need SCM to be able to load the firmware */
+	if (!qcom_scm_is_available()) {
+		DRM_DEV_ERROR(&pdev->dev, "SCM is not available\n");
+		return -EPROBE_DEFER;
+	}
+
+	/* Each GPU has a target specific zap shader firmware name to use */
+	if (!adreno_gpu->info->zapfw) {
+		zap_available = false;
+		DRM_DEV_ERROR(&pdev->dev,
+			"Zap shader firmware file not specified for this target\n");
+		return -ENODEV;
+	}
+
+	return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid);
+}
+
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -63,6 +198,12 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 	case MSM_PARAM_NR_RINGS:
 		*value = gpu->nr_rings;
 		return 0;
+	case MSM_PARAM_PP_PGTABLE:
+		*value = 0;
+		return 0;
+	case MSM_PARAM_FAULTS:
+		*value = gpu->global_faults;
+		return 0;
 	default:
 		DBG("%s: invalid param: %u", gpu->name, param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 5db459bc28a7..0925606ec9b5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -252,6 +252,12 @@ void adreno_gpu_state_destroy(struct msm_gpu_state *state);
 int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state);
 int adreno_gpu_state_put(struct msm_gpu_state *state);
 
+/*
+ * For a5xx and a6xx targets load the zap shader that is used to pull the GPU
+ * out of secure mode
+ */
+int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid);
+
 /* ringbuffer helpers (the parts that are adreno specific) */
 
 static inline void