1 files changed, 117 insertions, 67 deletions
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 57586c794b84..6934cee07d42 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -8,7 +8,7 @@
 
 #include <linux/ascii85.h>
 #include <linux/interconnect.h>
-#include <linux/qcom_scm.h>
+#include <linux/firmware/qcom/qcom_scm.h>
 #include <linux/kernel.h>
 #include <linux/of_address.h>
 #include <linux/pm_opp.h>
@@ -208,7 +208,7 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
 	struct msm_gem_address_space *aspace;
 	u64 start, size;
 
-	mmu = msm_iommu_new(&pdev->dev, quirks);
+	mmu = msm_iommu_gpu_new(&pdev->dev, gpu, quirks);
 	if (IS_ERR_OR_NULL(mmu))
 		return ERR_CAST(mmu);
 
@@ -246,6 +246,66 @@ u64 adreno_private_address_space_size(struct msm_gpu *gpu)
 	return SZ_4G;
 }
 
+#define ARM_SMMU_FSR_TF                 BIT(1)
+#define ARM_SMMU_FSR_PF			BIT(3)
+#define ARM_SMMU_FSR_EF			BIT(4)
+
+int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
+			 struct adreno_smmu_fault_info *info, const char *block,
+			 u32 scratch[4])
+{
+	const char *type = "UNKNOWN";
+	bool do_devcoredump = info && !READ_ONCE(gpu->crashstate);
+
+	/*
+	 * If we aren't going to be resuming later from fault_worker, then do
+	 * it now.
+	 */
+	if (!do_devcoredump) {
+		gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
+	}
+
+	/*
+	 * Print a default message if we couldn't get the data from the
+	 * adreno-smmu-priv
+	 */
+	if (!info) {
+		pr_warn_ratelimited("*** gpu fault: iova=%.16lx flags=%d (%u,%u,%u,%u)\n",
+			iova, flags,
+			scratch[0], scratch[1], scratch[2], scratch[3]);
+
+		return 0;
+	}
+
+	if (info->fsr & ARM_SMMU_FSR_TF)
+		type = "TRANSLATION";
+	else if (info->fsr & ARM_SMMU_FSR_PF)
+		type = "PERMISSION";
+	else if (info->fsr & ARM_SMMU_FSR_EF)
+		type = "EXTERNAL";
+
+	pr_warn_ratelimited("*** gpu fault: ttbr0=%.16llx iova=%.16lx dir=%s type=%s source=%s (%u,%u,%u,%u)\n",
+			info->ttbr0, iova,
+			flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ",
+			type, block,
+			scratch[0], scratch[1], scratch[2], scratch[3]);
+
+	if (do_devcoredump) {
+		/* Turn off the hangcheck timer to keep it from bothering us */
+		del_timer(&gpu->hangcheck_timer);
+
+		gpu->fault_info.ttbr0 = info->ttbr0;
+		gpu->fault_info.iova  = iova;
+		gpu->fault_info.flags = flags;
+		gpu->fault_info.type  = type;
+		gpu->fault_info.block = block;
+
+		kthread_queue_work(gpu->worker, &gpu->fault_work);
+	}
+
+	return 0;
+}
+
 int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 		     uint32_t param, uint64_t *value, uint32_t *len)
 {
@@ -352,6 +412,8 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 		/* Ensure string is null terminated: */
 		str[len] = '\0';
 
+		mutex_lock(&gpu->lock);
+
 		if (param == MSM_PARAM_COMM) {
 			paramp = &ctx->comm;
 		} else {
@@ -361,6 +423,8 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 		kfree(*paramp);
 		*paramp = str;
 
+		mutex_unlock(&gpu->lock);
+
 		return 0;
 	}
 	case MSM_PARAM_SYSPROF:
@@ -499,16 +563,9 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu,
 
 int adreno_hw_init(struct msm_gpu *gpu)
 {
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	int ret, i;
-
 	VERB("%s", gpu->name);
 
-	ret = adreno_load_fw(adreno_gpu);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < gpu->nr_rings; i++) {
+	for (int i = 0; i < gpu->nr_rings; i++) {
 		struct msm_ringbuffer *ring = gpu->rb[i];
 
 		if (!ring)
@@ -918,73 +975,46 @@ void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords)
 			ring->id);
 }
 
-/* Get legacy powerlevels from qcom,gpu-pwrlevels and populate the opp table */
-static int adreno_get_legacy_pwrlevels(struct device *dev)
-{
-	struct device_node *child, *node;
-	int ret;
-
-	node = of_get_compatible_child(dev->of_node, "qcom,gpu-pwrlevels");
-	if (!node) {
-		DRM_DEV_DEBUG(dev, "Could not find the GPU powerlevels\n");
-		return -ENXIO;
-	}
-
-	for_each_child_of_node(node, child) {
-		unsigned int val;
-
-		ret = of_property_read_u32(child, "qcom,gpu-freq", &val);
-		if (ret)
-			continue;
-
-		/*
-		 * Skip the intentionally bogus clock value found at the bottom
-		 * of most legacy frequency tables
-		 */
-		if (val != 27000000)
-			dev_pm_opp_add(dev, val, 0);
-	}
-
-	of_node_put(node);
-
-	return 0;
-}
-
-static void adreno_get_pwrlevels(struct device *dev,
+static int adreno_get_pwrlevels(struct device *dev,
 		struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	unsigned long freq = ULONG_MAX;
 	struct dev_pm_opp *opp;
 	int ret;
 
 	gpu->fast_rate = 0;
 
-	/* You down with OPP? */
-	if (!of_find_property(dev->of_node, "operating-points-v2", NULL))
-		ret = adreno_get_legacy_pwrlevels(dev);
-	else {
-		ret = devm_pm_opp_of_add_table(dev);
-		if (ret)
-			DRM_DEV_ERROR(dev, "Unable to set the OPP table\n");
-	}
-
-	if (!ret) {
-		/* Find the fastest defined rate */
-		opp = dev_pm_opp_find_freq_floor(dev, &freq);
-		if (!IS_ERR(opp)) {
-			gpu->fast_rate = freq;
-			dev_pm_opp_put(opp);
+	/* devm_pm_opp_of_add_table may error out but will still create an OPP table */
+	ret = devm_pm_opp_of_add_table(dev);
+	if (ret == -ENODEV) {
+		/* Special cases for ancient hw with ancient DT bindings */
+		if (adreno_is_a2xx(adreno_gpu)) {
+			dev_warn(dev, "Unable to find the OPP table. Falling back to 200 MHz.\n");
+			dev_pm_opp_add(dev, 200000000, 0);
+		} else if (adreno_is_a320(adreno_gpu)) {
+			dev_warn(dev, "Unable to find the OPP table. Falling back to 450 MHz.\n");
+			dev_pm_opp_add(dev, 450000000, 0);
+		} else {
+			DRM_DEV_ERROR(dev, "Unable to find the OPP table\n");
+			return -ENODEV;
 		}
+	} else if (ret) {
+		DRM_DEV_ERROR(dev, "Unable to set the OPP table\n");
+		return ret;
 	}
 
-	if (!gpu->fast_rate) {
-		dev_warn(dev,
-			"Could not find a clock rate. Using a reasonable default\n");
-		/* Pick a suitably safe clock speed for any target */
-		gpu->fast_rate = 200000000;
-	}
+	/* Find the fastest defined rate */
+	opp = dev_pm_opp_find_freq_floor(dev, &freq);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+
+	gpu->fast_rate = freq;
+	dev_pm_opp_put(opp);
 
 	DBG("fast_rate=%u, slow_rate=27000000", gpu->fast_rate);
+
+	return 0;
 }
 
 int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
@@ -1042,6 +1072,24 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	struct adreno_rev *rev = &config->rev;
 	const char *gpu_name;
 	u32 speedbin;
+	int ret;
+
+	/* Only handle the core clock when GMU is not in use */
+	if (config->rev.core < 6) {
+		/*
+		 * This can only be done before devm_pm_opp_of_add_table(), or
+		 * dev_pm_opp_set_config() will WARN_ON()
+		 */
+		if (IS_ERR(devm_clk_get(dev, "core"))) {
+			/*
+			 * If "core" is absent, go for the legacy clock name.
+			 * If we got this far in probing, it's a given one of
+			 * them exists.
+			 */
+			devm_pm_opp_set_clkname(dev, "core_clk");
+		} else
+			devm_pm_opp_set_clkname(dev, "core");
+	}
 
 	adreno_gpu->funcs = funcs;
 	adreno_gpu->info = adreno_info(config->rev);
@@ -1066,7 +1114,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	adreno_gpu_config.nr_rings = nr_rings;
 
-	adreno_get_pwrlevels(dev, gpu);
+	ret = adreno_get_pwrlevels(dev, gpu);
+	if (ret)
+		return ret;
 
 	pm_runtime_set_autosuspend_delay(dev,
 		adreno_gpu->info->inactive_period);
@@ -1079,13 +1129,13 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 {
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct msm_drm_private *priv = gpu->dev ? gpu->dev->dev_private : NULL;
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(adreno_gpu->info->fw); i++)
 		release_firmware(adreno_gpu->fw[i]);
 
-	if (pm_runtime_enabled(&priv->gpu_pdev->dev))
+	if (priv && pm_runtime_enabled(&priv->gpu_pdev->dev))
 		pm_runtime_disable(&priv->gpu_pdev->dev);
 
 	msm_gpu_cleanup(&adreno_gpu->base);