1 files changed, 439 insertions, 145 deletions

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 9f5a30234b33..1c80909e63ca 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -8,18 +8,23 @@
 
 #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/of_reserved_mem.h>
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/soc/qcom/mdt_loader.h>
+#include <linux/nvmem-consumer.h>
 #include <soc/qcom/ocmem.h>
 #include "adreno_gpu.h"
 #include "a6xx_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
 
+static u64 address_space_size = 0;
+MODULE_PARM_DESC(address_space_size, "Override for size of processes private GPU address space");
+module_param(address_space_size, ullong, 0600);
+
 static bool zap_available = true;
 
 static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
@@ -28,7 +33,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 	struct device *dev = &gpu->pdev->dev;
 	const struct firmware *fw;
 	const char *signed_fwname = NULL;
-	struct device_node *np, *mem_np;
+	struct device_node *np;
 	struct resource r;
 	phys_addr_t mem_phys;
 	ssize_t mem_size;
@@ -41,23 +46,16 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 	}
 
 	np = of_get_child_by_name(dev->of_node, "zap-shader");
-	if (!np) {
+	if (!of_device_is_available(np)) {
 		zap_available = false;
 		return -ENODEV;
 	}
 
-	mem_np = of_parse_phandle(np, "memory-region", 0);
-	of_node_put(np);
-	if (!mem_np) {
+	ret = of_reserved_mem_region_to_resource(np, 0, &r);
+	if (ret) {
 		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;
 
 	/*
@@ -94,7 +92,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 		 * was a bad idea, and is only provided for backwards
 		 * compatibility for older targets.
 		 */
-		return -ENODEV;
+		return -ENOENT;
 	}
 
 	if (IS_ERR(fw)) {
@@ -186,66 +184,208 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
 	return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid);
 }
 
-void adreno_set_llc_attributes(struct iommu_domain *iommu)
+struct drm_gpuvm *
+adreno_create_vm(struct msm_gpu *gpu,
+		 struct platform_device *pdev)
 {
-	iommu_set_pgtable_quirks(iommu, IO_PGTABLE_QUIRK_ARM_OUTER_WBWA);
+	return adreno_iommu_create_vm(gpu, pdev, 0);
 }
 
-struct msm_gem_address_space *
-adreno_iommu_create_address_space(struct msm_gpu *gpu,
-		struct platform_device *pdev)
+struct drm_gpuvm *
+adreno_iommu_create_vm(struct msm_gpu *gpu,
+		       struct platform_device *pdev,
+		       unsigned long quirks)
 {
-	struct iommu_domain *iommu;
+	struct iommu_domain_geometry *geometry;
 	struct msm_mmu *mmu;
-	struct msm_gem_address_space *aspace;
+	struct drm_gpuvm *vm;
 	u64 start, size;
 
-	iommu = iommu_domain_alloc(&platform_bus_type);
-	if (!iommu)
-		return NULL;
-
-	mmu = msm_iommu_new(&pdev->dev, iommu);
-	if (IS_ERR(mmu)) {
-		iommu_domain_free(iommu);
+	mmu = msm_iommu_gpu_new(&pdev->dev, gpu, quirks);
+	if (IS_ERR(mmu))
 		return ERR_CAST(mmu);
-	}
+
+	geometry = msm_iommu_get_geometry(mmu);
+	if (IS_ERR(geometry))
+		return ERR_CAST(geometry);
 
 	/*
 	 * Use the aperture start or SZ_16M, whichever is greater. This will
 	 * ensure that we align with the allocated pagetable range while still
 	 * allowing room in the lower 32 bits for GMEM and whatnot
 	 */
-	start = max_t(u64, SZ_16M, iommu->geometry.aperture_start);
-	size = iommu->geometry.aperture_end - start + 1;
+	start = max_t(u64, SZ_16M, geometry->aperture_start);
+	size = geometry->aperture_end - start + 1;
 
-	aspace = msm_gem_address_space_create(mmu, "gpu",
-		start & GENMASK_ULL(48, 0), size);
+	vm = msm_gem_vm_create(gpu->dev, mmu, "gpu", start & GENMASK_ULL(48, 0),
+			       size, true);
 
-	if (IS_ERR(aspace) && !IS_ERR(mmu))
+	if (IS_ERR(vm) && !IS_ERR(mmu))
 		mmu->funcs->destroy(mmu);
 
-	return aspace;
+	return vm;
+}
+
+u64 adreno_private_vm_size(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev);
+	const struct io_pgtable_cfg *ttbr1_cfg;
+
+	if (address_space_size)
+		return address_space_size;
+
+	if (adreno_gpu->info->quirks & ADRENO_QUIRK_4GB_VA)
+		return SZ_4G;
+
+	if (!adreno_smmu || !adreno_smmu->get_ttbr1_cfg)
+		return SZ_4G;
+
+	ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie);
+
+	/*
+	 * Userspace VM is actually using TTBR0, but both are the same size,
+	 * with b48 (sign bit) selecting which TTBRn to use.  So if IAS is
+	 * 48, the total (kernel+user) address space size is effectively
+	 * 49 bits.  But what userspace is control of is the lower 48.
+	 */
+	return BIT(ttbr1_cfg->ias) - ADRENO_VM_START;
+}
+
+void adreno_check_and_reenable_stall(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	unsigned long flags;
+
+	/*
+	 * Wait until the cooldown period has passed and we would actually
+	 * collect a crashdump to re-enable stall-on-fault.
+	 */
+	spin_lock_irqsave(&priv->fault_stall_lock, flags);
+	if (!priv->stall_enabled &&
+			ktime_after(ktime_get(), priv->stall_reenable_time) &&
+			!READ_ONCE(gpu->crashstate)) {
+		struct msm_mmu *mmu = to_msm_vm(gpu->vm)->mmu;
+
+		priv->stall_enabled = true;
+
+		mmu->funcs->set_stall(mmu, true);
+	}
+	spin_unlock_irqrestore(&priv->fault_stall_lock, flags);
+}
+
+#define ARM_SMMU_FSR_TF                 BIT(1)
+#define ARM_SMMU_FSR_PF			BIT(3)
+#define ARM_SMMU_FSR_EF			BIT(4)
+#define ARM_SMMU_FSR_SS			BIT(30)
+
+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])
+{
+	struct adreno_gpu *adreno_gpu = container_of(gpu, struct adreno_gpu, base);
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct msm_mmu *mmu = to_msm_vm(gpu->vm)->mmu;
+	const char *type = "UNKNOWN";
+	bool do_devcoredump = info && (info->fsr & ARM_SMMU_FSR_SS) &&
+		!READ_ONCE(gpu->crashstate);
+	unsigned long irq_flags;
+
+	/*
+	 * In case there is a subsequent storm of pagefaults, disable
+	 * stall-on-fault for at least half a second.
+	 */
+	spin_lock_irqsave(&priv->fault_stall_lock, irq_flags);
+	if (priv->stall_enabled) {
+		priv->stall_enabled = false;
+
+		mmu->funcs->set_stall(mmu, false);
+	}
+
+	priv->stall_reenable_time = ktime_add_ms(ktime_get(), 500);
+	spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags);
+
+	/*
+	 * 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) {
+		struct msm_gpu_fault_info fault_info = {};
+
+		/* Turn off the hangcheck timer to keep it from bothering us */
+		timer_delete(&gpu->hangcheck_timer);
+
+		/* Let any concurrent GMU transactions know that the MMU may be
+		 * blocked for a while and they should wait on us.
+		 */
+		reinit_completion(&adreno_gpu->fault_coredump_done);
+
+		fault_info.ttbr0 = info->ttbr0;
+		fault_info.iova  = iova;
+		fault_info.flags = flags;
+		fault_info.type  = type;
+		fault_info.block = block;
+
+		msm_gpu_fault_crashstate_capture(gpu, &fault_info);
+
+		complete_all(&adreno_gpu->fault_coredump_done);
+	}
+
+	return 0;
 }
 
-int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
+int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx,
+		     uint32_t param, uint64_t *value, uint32_t *len)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct drm_device *drm = gpu->dev;
+	/* Note ctx can be NULL when called from rd_open(): */
+	struct drm_gpuvm *vm = ctx ? msm_context_vm(drm, ctx) : NULL;
+
+	/* No pointer params yet */
+	if (*len != 0)
+		return UERR(EINVAL, drm, "invalid len");
 
 	switch (param) {
 	case MSM_PARAM_GPU_ID:
 		*value = adreno_gpu->info->revn;
 		return 0;
 	case MSM_PARAM_GMEM_SIZE:
-		*value = adreno_gpu->gmem;
+		*value = adreno_gpu->info->gmem;
 		return 0;
 	case MSM_PARAM_GMEM_BASE:
-		*value = !adreno_is_a650_family(adreno_gpu) ? 0x100000 : 0;
+		if (adreno_is_a650_family(adreno_gpu) ||
+		    adreno_is_a740_family(adreno_gpu))
+			*value = 0;
+		else
+			*value = 0x100000;
 		return 0;
 	case MSM_PARAM_CHIP_ID:
-		*value = adreno_gpu->rev.patchid |
-				(adreno_gpu->rev.minor << 8) |
-				(adreno_gpu->rev.major << 16) |
-				(adreno_gpu->rev.core << 24);
+		*value = adreno_gpu->chip_id;
+		if (!adreno_gpu->info->revn)
+			*value |= ((uint64_t) adreno_gpu->speedbin) << 32;
 		return 0;
 	case MSM_PARAM_MAX_FREQ:
 		*value = adreno_gpu->base.fast_rate;
@@ -261,21 +401,118 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value)
 			return ret;
 		}
 		return -EINVAL;
-	case MSM_PARAM_NR_RINGS:
-		*value = gpu->nr_rings;
+	case MSM_PARAM_PRIORITIES:
+		*value = gpu->nr_rings * NR_SCHED_PRIORITIES;
 		return 0;
 	case MSM_PARAM_PP_PGTABLE:
 		*value = 0;
 		return 0;
 	case MSM_PARAM_FAULTS:
-		*value = gpu->global_faults;
+		if (vm)
+			*value = gpu->global_faults + to_msm_vm(vm)->faults;
+		else
+			*value = gpu->global_faults;
 		return 0;
 	case MSM_PARAM_SUSPENDS:
 		*value = gpu->suspend_count;
 		return 0;
+	case MSM_PARAM_VA_START:
+		if (vm == gpu->vm)
+			return UERR(EINVAL, drm, "requires per-process pgtables");
+		*value = vm->mm_start;
+		return 0;
+	case MSM_PARAM_VA_SIZE:
+		if (vm == gpu->vm)
+			return UERR(EINVAL, drm, "requires per-process pgtables");
+		*value = vm->mm_range;
+		return 0;
+	case MSM_PARAM_HIGHEST_BANK_BIT:
+		*value = adreno_gpu->ubwc_config->highest_bank_bit;
+		return 0;
+	case MSM_PARAM_RAYTRACING:
+		*value = adreno_gpu->has_ray_tracing;
+		return 0;
+	case MSM_PARAM_UBWC_SWIZZLE:
+		*value = adreno_gpu->ubwc_config->ubwc_swizzle;
+		return 0;
+	case MSM_PARAM_MACROTILE_MODE:
+		*value = adreno_gpu->ubwc_config->macrotile_mode;
+		return 0;
+	case MSM_PARAM_UCHE_TRAP_BASE:
+		*value = adreno_gpu->uche_trap_base;
+		return 0;
+	case MSM_PARAM_HAS_PRR:
+		*value = adreno_smmu_has_prr(gpu);
+		return 0;
 	default:
-		DBG("%s: invalid param: %u", gpu->name, param);
-		return -EINVAL;
+		return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param);
+	}
+}
+
+int adreno_set_param(struct msm_gpu *gpu, struct msm_context *ctx,
+		     uint32_t param, uint64_t value, uint32_t len)
+{
+	struct drm_device *drm = gpu->dev;
+
+	switch (param) {
+	case MSM_PARAM_COMM:
+	case MSM_PARAM_CMDLINE:
+		/* kstrdup_quotable_cmdline() limits to PAGE_SIZE, so
+		 * that should be a reasonable upper bound
+		 */
+		if (len > PAGE_SIZE)
+			return UERR(EINVAL, drm, "invalid len");
+		break;
+	default:
+		if (len != 0)
+			return UERR(EINVAL, drm, "invalid len");
+	}
+
+	switch (param) {
+	case MSM_PARAM_COMM:
+	case MSM_PARAM_CMDLINE: {
+		char *str, **paramp;
+
+		str = memdup_user_nul(u64_to_user_ptr(value), len);
+		if (IS_ERR(str))
+			return PTR_ERR(str);
+
+		mutex_lock(&gpu->lock);
+
+		if (param == MSM_PARAM_COMM) {
+			paramp = &ctx->comm;
+		} else {
+			paramp = &ctx->cmdline;
+		}
+
+		kfree(*paramp);
+		*paramp = str;
+
+		mutex_unlock(&gpu->lock);
+
+		return 0;
+	}
+	case MSM_PARAM_SYSPROF:
+		if (!capable(CAP_SYS_ADMIN))
+			return UERR(EPERM, drm, "invalid permissions");
+		return msm_context_set_sysprof(ctx, gpu, value);
+	case MSM_PARAM_EN_VM_BIND:
+		/* We can only support VM_BIND with per-process pgtables: */
+		if (ctx->vm == gpu->vm)
+			return UERR(EINVAL, drm, "requires per-process pgtables");
+
+		/*
+		 * We can only swtich to VM_BIND mode if the VM has not yet
+		 * been created:
+		 */
+		if (ctx->vm)
+			return UERR(EBUSY, drm, "VM already created");
+
+		ctx->userspace_managed_vm = value;
+
+		return 0;
+	default:
+		return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param);
 	}
 }
 
@@ -321,7 +558,7 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname)
 		ret = request_firmware_direct(&fw, fwname, drm->dev);
 		if (!ret) {
 			DRM_DEV_INFO(drm->dev, "loaded %s from legacy location\n",
-				newname);
+				fwname);
 			adreno_gpu->fwloc = FW_LOCATION_LEGACY;
 			goto out;
 		} else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
@@ -370,6 +607,10 @@ int adreno_load_fw(struct adreno_gpu *adreno_gpu)
 		if (!adreno_gpu->info->fw[i])
 			continue;
 
+		/* Skip loading GMU firmware with GMU Wrapper */
+		if (adreno_has_gmu_wrapper(adreno_gpu) && i == ADRENO_FW_GMU)
+			continue;
+
 		/* Skip if the firmware has already been loaded */
 		if (adreno_gpu->fw[i])
 			continue;
@@ -390,8 +631,8 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu,
 	struct drm_gem_object *bo;
 	void *ptr;
 
-	ptr = msm_gem_kernel_new_locked(gpu->dev, fw->size - 4,
-		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &bo, iova);
+	ptr = msm_gem_kernel_new(gpu->dev, fw->size - 4,
+		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->vm, &bo, iova);
 
 	if (IS_ERR(ptr))
 		return ERR_CAST(ptr);
@@ -406,15 +647,19 @@ 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;
+	int ret;
 
 	VERB("%s", gpu->name);
 
-	ret = adreno_load_fw(adreno_gpu);
-	if (ret)
-		return ret;
+	if (adreno_gpu->info->family >= ADRENO_6XX_GEN1 &&
+	    qcom_scm_set_gpu_smmu_aperture_is_available()) {
+		/* We currently always use context bank 0, so hard code this */
+		ret = qcom_scm_set_gpu_smmu_aperture(0);
+		if (ret)
+			DRM_DEV_ERROR(gpu->dev->dev, "unable to set SMMU aperture: %d\n", 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)
@@ -422,10 +667,16 @@ int adreno_hw_init(struct msm_gpu *gpu)
 
 		ring->cur = ring->start;
 		ring->next = ring->start;
-
-		/* reset completed fence seqno: */
-		ring->memptrs->fence = ring->fctx->completed_fence;
 		ring->memptrs->rptr = 0;
+		ring->memptrs->bv_fence = ring->fctx->completed_fence;
+
+		/* Detect and clean up an impossible fence, ie. if GPU managed
+		 * to scribble something invalid, we don't want that to confuse
+		 * us into mistakingly believing that submits have completed.
+		 */
+		if (fence_before(ring->fctx->last_fence, ring->memptrs->fence)) {
+			ring->memptrs->fence = ring->fctx->last_fence;
+		}
 	}
 
 	return 0;
@@ -504,6 +755,8 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i, count = 0;
 
+	WARN_ON(!mutex_is_locked(&gpu->lock));
+
 	kref_init(&state->ref);
 
 	ktime_get_real_ts64(&state->time);
@@ -513,7 +766,7 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 
 		state->ring[i].fence = gpu->rb[i]->memptrs->fence;
 		state->ring[i].iova = gpu->rb[i]->iova;
-		state->ring[i].seqno = gpu->rb[i]->seqno;
+		state->ring[i].seqno = gpu->rb[i]->fctx->last_fence;
 		state->ring[i].rptr = get_rptr(adreno_gpu, gpu->rb[i]);
 		state->ring[i].wptr = get_wptr(gpu->rb[i]);
 
@@ -526,11 +779,9 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 				size = j + 1;
 
 		if (size) {
-			state->ring[i].data = kvmalloc(size << 2, GFP_KERNEL);
-			if (state->ring[i].data) {
-				memcpy(state->ring[i].data, gpu->rb[i]->start, size << 2);
+			state->ring[i].data = kvmemdup(gpu->rb[i]->start, size << 2, GFP_KERNEL);
+			if (state->ring[i].data)
 				state->ring[i].data_size = size << 2;
-			}
 		}
 	}
 
@@ -574,6 +825,7 @@ void adreno_gpu_state_destroy(struct msm_gpu_state *state)
 	for (i = 0; state->bos && i < state->nr_bos; i++)
 		kvfree(state->bos[i].data);
 
+	kfree(state->vm_logs);
 	kfree(state->bos);
 	kfree(state->comm);
 	kfree(state->cmd);
@@ -629,8 +881,13 @@ static char *adreno_gpu_ascii85_encode(u32 *src, size_t len)
 	return buf;
 }
 
-/* len is expected to be in bytes */
-static void adreno_show_object(struct drm_printer *p, void **ptr, int len,
+/* len is expected to be in bytes
+ *
+ * WARNING: *ptr should be allocated with kvmalloc or friends.  It can be free'd
+ * with kvfree() and replaced with a newly kvmalloc'd buffer on the first call
+ * when the unencoded raw data is encoded
+ */
+void adreno_show_object(struct drm_printer *p, void **ptr, int len,
 		bool *encoded)
 {
 	if (!*ptr || !len)
@@ -680,10 +937,9 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 	if (IS_ERR_OR_NULL(state))
 		return;
 
-	drm_printf(p, "revision: %d (%d.%d.%d.%d)\n",
-			adreno_gpu->info->revn, adreno_gpu->rev.core,
-			adreno_gpu->rev.major, adreno_gpu->rev.minor,
-			adreno_gpu->rev.patchid);
+	drm_printf(p, "revision: %u (%"ADRENO_CHIPID_FMT")\n",
+			adreno_gpu->info->revn,
+			ADRENO_CHIPID_ARGS(adreno_gpu->chip_id));
 	/*
 	 * If this is state collected due to iova fault, so fault related info
 	 *
@@ -698,6 +954,26 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 		drm_printf(p, "  - dir=%s\n", info->flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ");
 		drm_printf(p, "  - type=%s\n", info->type);
 		drm_printf(p, "  - source=%s\n", info->block);
+
+		/* Information extracted from what we think are the current
+		 * pgtables.  Hopefully the TTBR0 matches what we've extracted
+		 * from the SMMU registers in smmu_info!
+		 */
+		drm_puts(p, "pgtable-fault-info:\n");
+		drm_printf(p, "  - ttbr0: %.16llx\n", (u64)info->pgtbl_ttbr0);
+		drm_printf(p, "  - asid: %d\n", info->asid);
+		drm_printf(p, "  - ptes: %.16llx %.16llx %.16llx %.16llx\n",
+			   info->ptes[0], info->ptes[1], info->ptes[2], info->ptes[3]);
+	}
+
+	if (state->vm_logs) {
+		drm_puts(p, "vm-log:\n");
+		for (i = 0; i < state->nr_vm_logs; i++) {
+			struct msm_gem_vm_log_entry *e = &state->vm_logs[i];
+			drm_printf(p, "  - %s:%d: 0x%016llx-0x%016llx\n",
+				   e->op, e->queue_id, e->iova,
+				   e->iova + e->range);
+		}
 	}
 
 	drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status);
@@ -707,11 +983,11 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 	for (i = 0; i < gpu->nr_rings; i++) {
 		drm_printf(p, "  - id: %d\n", i);
 		drm_printf(p, "    iova: 0x%016llx\n", state->ring[i].iova);
-		drm_printf(p, "    last-fence: %d\n", state->ring[i].seqno);
-		drm_printf(p, "    retired-fence: %d\n", state->ring[i].fence);
-		drm_printf(p, "    rptr: %d\n", state->ring[i].rptr);
-		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
-		drm_printf(p, "    size: %d\n", MSM_GPU_RINGBUFFER_SZ);
+		drm_printf(p, "    last-fence: %u\n", state->ring[i].seqno);
+		drm_printf(p, "    retired-fence: %u\n", state->ring[i].fence);
+		drm_printf(p, "    rptr: %u\n", state->ring[i].rptr);
+		drm_printf(p, "    wptr: %u\n", state->ring[i].wptr);
+		drm_printf(p, "    size: %u\n", MSM_GPU_RINGBUFFER_SZ);
 
 		adreno_show_object(p, &state->ring[i].data,
 			state->ring[i].data_size, &state->ring[i].encoded);
@@ -724,6 +1000,8 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 			drm_printf(p, "  - iova: 0x%016llx\n",
 				state->bos[i].iova);
 			drm_printf(p, "    size: %zd\n", state->bos[i].size);
+			drm_printf(p, "    flags: 0x%x\n", state->bos[i].flags);
+			drm_printf(p, "    name: %-32s\n", state->bos[i].name);
 
 			adreno_show_object(p, &state->bos[i].data,
 				state->bos[i].size, &state->bos[i].encoded);
@@ -753,17 +1031,16 @@ void adreno_dump_info(struct msm_gpu *gpu)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i;
 
-	printk("revision: %d (%d.%d.%d.%d)\n",
-			adreno_gpu->info->revn, adreno_gpu->rev.core,
-			adreno_gpu->rev.major, adreno_gpu->rev.minor,
-			adreno_gpu->rev.patchid);
+	printk("revision: %u (%"ADRENO_CHIPID_FMT")\n",
+			adreno_gpu->info->revn,
+			ADRENO_CHIPID_ARGS(adreno_gpu->chip_id));
 
 	for (i = 0; i < gpu->nr_rings; i++) {
 		struct msm_ringbuffer *ring = gpu->rb[i];
 
 		printk("rb %d: fence:    %d/%d\n", i,
 			ring->memptrs->fence,
-			ring->seqno);
+			ring->fctx->last_fence);
 
 		printk("rptr:     %d\n", get_rptr(adreno_gpu, ring));
 		printk("rb wptr:  %d\n", get_wptr(ring));
@@ -811,73 +1088,46 @@ 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,
@@ -900,14 +1150,16 @@ int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
 		return PTR_ERR(ocmem);
 	}
 
-	ocmem_hdl = ocmem_allocate(ocmem, OCMEM_GRAPHICS, adreno_gpu->gmem);
+	ocmem_hdl = ocmem_allocate(ocmem, OCMEM_GRAPHICS, adreno_gpu->info->gmem);
 	if (IS_ERR(ocmem_hdl))
 		return PTR_ERR(ocmem_hdl);
 
 	adreno_ocmem->ocmem = ocmem;
 	adreno_ocmem->base = ocmem_hdl->addr;
 	adreno_ocmem->hdl = ocmem_hdl;
-	adreno_gpu->gmem = ocmem_hdl->len;
+
+	if (WARN_ON(ocmem_hdl->len != adreno_gpu->info->gmem))
+		return -ENOMEM;
 
 	return 0;
 }
@@ -919,6 +1171,11 @@ void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *adreno_ocmem)
 			   adreno_ocmem->hdl);
 }
 
+int adreno_read_speedbin(struct device *dev, u32 *speedbin)
+{
+	return nvmem_cell_read_variable_le_u32(dev, "speed_bin", speedbin);
+}
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *adreno_gpu,
 		const struct adreno_gpu_funcs *funcs, int nr_rings)
@@ -927,38 +1184,75 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	struct adreno_platform_config *config = dev->platform_data;
 	struct msm_gpu_config adreno_gpu_config  = { 0 };
 	struct msm_gpu *gpu = &adreno_gpu->base;
+	const char *gpu_name;
+	u32 speedbin;
+	int ret;
 
 	adreno_gpu->funcs = funcs;
-	adreno_gpu->info = adreno_info(config->rev);
-	adreno_gpu->gmem = adreno_gpu->info->gmem;
-	adreno_gpu->revn = adreno_gpu->info->revn;
-	adreno_gpu->rev = config->rev;
+	adreno_gpu->info = config->info;
+	adreno_gpu->chip_id = config->chip_id;
+
+	gpu->allow_relocs = config->info->family < ADRENO_6XX_GEN1;
+	gpu->pdev = pdev;
+
+	/* Only handle the core clock when GMU is not in use (or is absent). */
+	if (adreno_has_gmu_wrapper(adreno_gpu) ||
+	    adreno_has_rgmu(adreno_gpu) ||
+	    adreno_gpu->info->family < ADRENO_6XX_GEN1) {
+		/*
+		 * 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");
+	}
+
+	if (adreno_read_speedbin(dev, &speedbin) || !speedbin)
+		speedbin = 0xffff;
+	adreno_gpu->speedbin = (uint16_t) (0xffff & speedbin);
+
+	gpu_name = devm_kasprintf(dev, GFP_KERNEL, "%"ADRENO_CHIPID_FMT,
+			ADRENO_CHIPID_ARGS(config->chip_id));
+	if (!gpu_name)
+		return -ENOMEM;
 
 	adreno_gpu_config.ioname = "kgsl_3d0_reg_memory";
 
 	adreno_gpu_config.nr_rings = nr_rings;
 
-	adreno_get_pwrlevels(dev, gpu);
+	ret = adreno_get_pwrlevels(dev, gpu);
+	if (ret)
+		return ret;
+
+	init_completion(&adreno_gpu->fault_coredump_done);
+	complete_all(&adreno_gpu->fault_coredump_done);
 
 	pm_runtime_set_autosuspend_delay(dev,
 		adreno_gpu->info->inactive_period);
 	pm_runtime_use_autosuspend(dev);
-	pm_runtime_enable(dev);
 
 	return msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
-			adreno_gpu->info->name, &adreno_gpu_config);
+			gpu_name, &adreno_gpu_config);
 }
 
 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]);
 
-	pm_runtime_disable(&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);
 }