Merge tag 'v4.8-rc8' into drm-next

Linux 4.8-rc8

There was a lot of fallout in the imx/amdgpu/i915 drivers, so backmerge
it now to avoid troubles.

* tag 'v4.8-rc8': (1442 commits)
  Linux 4.8-rc8
  fault_in_multipages_readable() throws set-but-unused error
  mm: check VMA flags to avoid invalid PROT_NONE NUMA balancing
  radix tree: fix sibling entry handling in radix_tree_descend()
  radix tree test suite: Test radix_tree_replace_slot() for multiorder entries
  fix memory leaks in tracing_buffers_splice_read()
  tracing: Move mutex to protect against resetting of seq data
  MIPS: Fix delay slot emulation count in debugfs
  MIPS: SMP: Fix possibility of deadlock when bringing CPUs online
  mm: delete unnecessary and unsafe init_tlb_ubc()
  huge tmpfs: fix Committed_AS leak
  shmem: fix tmpfs to handle the huge= option properly
  blk-mq: skip unmapped queues in blk_mq_alloc_request_hctx
  MIPS: Fix pre-r6 emulation FPU initialisation
  arm64: kgdb: handle read-only text / modules
  arm64: Call numa_store_cpu_info() earlier.
  locking/hung_task: Fix typo in CONFIG_DETECT_HUNG_TASK help text
  nvme-rdma: only clear queue flags after successful connect
  i2c: qup: skip qup_i2c_suspend if the device is already runtime suspended
  perf/core: Limit matching exclusive events to one PMU
  ...

40 files changed, 207 insertions, 183 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9d79e4ba0213..72c68dbb9821 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -407,7 +407,6 @@ unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring);
 /*
  * BO.
  */
-
 struct amdgpu_bo_list_entry {
 	struct amdgpu_bo		*robj;
 	struct ttm_validate_buffer	tv;
@@ -620,9 +619,9 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev);
 void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev);
 int amdgpu_gart_init(struct amdgpu_device *adev);
 void amdgpu_gart_fini(struct amdgpu_device *adev);
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 			int pages);
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, struct page **pagelist,
 		     dma_addr_t *dma_addr, uint32_t flags);
 int amdgpu_ttm_recover_gart(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 59961db9c390..8e6bf548d689 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -348,6 +348,19 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 			    (le16_to_cpu(path->usConnObjectId) &
 			     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
+			/* Skip TV/CV support */
+			if ((le16_to_cpu(path->usDeviceTag) ==
+			     ATOM_DEVICE_TV1_SUPPORT) ||
+			    (le16_to_cpu(path->usDeviceTag) ==
+			     ATOM_DEVICE_CV_SUPPORT))
+				continue;
+
+			if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) {
+				DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n",
+					  con_obj_id, le16_to_cpu(path->usDeviceTag));
+				continue;
+			}
+
 			connector_type =
 				object_connector_convert[con_obj_id];
 			connector_object_id = con_obj_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 550c5ee704ec..dae35a96a694 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -205,16 +205,7 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx)
 	atpx->is_hybrid = false;
 	if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
 		printk("ATPX Hybrid Graphics\n");
-#if 1
-		/* This is a temporary hack until the D3 cold support
-		 * makes it upstream.  The ATPX power_control method seems
-		 * to still work on even if the system should be using
-		 * the new standardized hybrid D3 cold ACPI interface.
-		 */
-		atpx->functions.power_cntl = true;
-#else
 		atpx->functions.power_cntl = false;
-#endif
 		atpx->is_hybrid = true;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 921bce2df0b0..0feea347f680 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -221,7 +221,7 @@ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev)
  * Unbinds the requested pages from the gart page table and
  * replaces them with the dummy page (all asics).
  */
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 			int pages)
 {
 	unsigned t;
@@ -268,7 +268,7 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
  * (all asics).
  * Returns 0 for success, -EINVAL for failure.
  */
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, struct page **pagelist, dma_addr_t *dma_addr,
 		     uint32_t flags)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 4127e7ceace0..6a6c86c9c169 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -295,7 +295,7 @@ void amdgpu_ib_pool_fini(struct amdgpu_device *adev)
 int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 {
 	unsigned i;
-	int r;
+	int r, ret = 0;
 
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -316,10 +316,11 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 			} else {
 				/* still not good, but we can live with it */
 				DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r);
+				ret = r;
 			}
 		}
 	}
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index b63969d7887c..160a094e1a93 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -273,8 +273,8 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 
 	adev = amdgpu_get_adev(bo->bdev);
 	ring = adev->mman.buffer_funcs_ring;
-	old_start = old_mem->start << PAGE_SHIFT;
-	new_start = new_mem->start << PAGE_SHIFT;
+	old_start = (u64)old_mem->start << PAGE_SHIFT;
+	new_start = (u64)new_mem->start << PAGE_SHIFT;
 
 	switch (old_mem->mem_type) {
 	case TTM_PL_TT:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 25dd58a65905..cee7bc9a2314 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -1154,7 +1154,8 @@ int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		r = 0;
 	}
 
-error:
 	fence_put(fence);
+
+error:
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index bd5af328154f..a6a48ed9562e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1593,7 +1593,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	r = amd_sched_entity_init(&ring->sched, &vm->entity,
 				  rq, amdgpu_sched_jobs);
 	if (r)
-		return r;
+		goto err;
 
 	vm->page_directory_fence = NULL;
 
@@ -1624,6 +1624,9 @@ error_free_page_directory:
 error_free_sched_entity:
 	amd_sched_entity_fini(&ring->sched, &vm->entity);
 
+err:
+	drm_free_large(vm->page_tables);
+
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index e6d7bf9520a0..cb952acc7133 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -52,6 +52,7 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev);
+static int cik_sdma_soft_reset(void *handle);
 
 MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
 MODULE_FIRMWARE("radeon/bonaire_sdma1.bin");
@@ -1014,6 +1015,8 @@ static int cik_sdma_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	cik_sdma_soft_reset(handle);
+
 	return cik_sdma_hw_init(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 32a676291e67..71116da9e782 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2927,8 +2927,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
 	u64 wb_gpu_addr;
 	u32 *buf;
 	struct bonaire_mqd *mqd;
-
-	gfx_v7_0_cp_compute_enable(adev, true);
+	struct amdgpu_ring *ring;
 
 	/* fix up chicken bits */
 	tmp = RREG32(mmCP_CPF_DEBUG);
@@ -2963,7 +2962,7 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
 
 	/* init the queues.  Just two for now. */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
-		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
+		ring = &adev->gfx.compute_ring[i];
 
 		if (ring->mqd_obj == NULL) {
 			r = amdgpu_bo_create(adev,
@@ -3142,6 +3141,13 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
 		amdgpu_bo_unreserve(ring->mqd_obj);
 
 		ring->ready = true;
+	}
+
+	gfx_v7_0_cp_compute_enable(adev, true);
+
+	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+		ring = &adev->gfx.compute_ring[i];
+
 		r = amdgpu_ring_test_ring(ring);
 		if (r)
 			ring->ready = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 9ae307505190..565dab3c7218 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -710,7 +710,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		DRM_ERROR("amdgpu: IB test timed out\n");
 		r = -ETIMEDOUT;
 		goto err1;
-	} else if (r) {
+	} else if (r < 0) {
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err1;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index ad494b875311..453c5d66e5c3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -186,7 +186,7 @@ u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 							sizeof(u32)) + inx;
 
 	pr_debug("kfd: get kernel queue doorbell\n"
-			 "     doorbell offset   == 0x%08d\n"
+			 "     doorbell offset   == 0x%08X\n"
 			 "     kernel address    == 0x%08lX\n",
 		*doorbell_off, (uintptr_t)(kfd->doorbell_kernel_ptr + inx));
 
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index ef312bb75fda..963a24d46a93 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -405,7 +405,7 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched)
 	spin_lock(&sched->job_list_lock);
 	s_job = list_first_entry_or_null(&sched->ring_mirror_list,
 					 struct amd_sched_job, node);
-	if (s_job)
+	if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT)
 		schedule_delayed_work(&s_job->work_tdr, sched->timeout);
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index a978381ef95b..9b17a66cf0e1 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -387,7 +387,7 @@ void atmel_hlcdc_crtc_irq(struct drm_crtc *c)
 	atmel_hlcdc_crtc_finish_page_flip(drm_crtc_to_atmel_hlcdc_crtc(c));
 }
 
-void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
+static void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
 {
 	struct atmel_hlcdc_crtc_state *state;
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index 72e6b7dd457b..9d4c030672f0 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -320,19 +320,19 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane,
 			u32 *coeff_tab = heo_upscaling_ycoef;
 			u32 max_memsize;
 
-			if (state->crtc_w < state->src_w)
+			if (state->crtc_h < state->src_h)
 				coeff_tab = heo_downscaling_ycoef;
 			for (i = 0; i < ARRAY_SIZE(heo_upscaling_ycoef); i++)
 				atmel_hlcdc_layer_update_cfg(&plane->layer,
 							     33 + i,
 							     0xffffffff,
 							     coeff_tab[i]);
-			factor = ((8 * 256 * state->src_w) - (256 * 4)) /
-				 state->crtc_w;
+			factor = ((8 * 256 * state->src_h) - (256 * 4)) /
+				 state->crtc_h;
 			factor++;
-			max_memsize = ((factor * state->crtc_w) + (256 * 4)) /
+			max_memsize = ((factor * state->crtc_h) + (256 * 4)) /
 				      2048;
-			if (max_memsize > state->src_w)
+			if (max_memsize > state->src_h)
 				factor--;
 			factor_reg |= (factor << 16) | 0x80000000;
 		}
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 904d29c012ad..23739609427d 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -475,7 +475,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 					val,
 					-1,
 					&replaced);
-		state->color_mgmt_changed = replaced;
+		state->color_mgmt_changed |= replaced;
 		return ret;
 	} else if (property == config->ctm_property) {
 		ret = drm_atomic_replace_property_blob_from_id(crtc,
@@ -483,7 +483,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 					val,
 					sizeof(struct drm_color_ctm),
 					&replaced);
-		state->color_mgmt_changed = replaced;
+		state->color_mgmt_changed |= replaced;
 		return ret;
 	} else if (property == config->gamma_lut_property) {
 		ret = drm_atomic_replace_property_blob_from_id(crtc,
@@ -491,7 +491,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 					val,
 					-1,
 					&replaced);
-		state->color_mgmt_changed = replaced;
+		state->color_mgmt_changed |= replaced;
 		return ret;
 	} else if (crtc->funcs->atomic_set_property)
 		return crtc->funcs->atomic_set_property(crtc, state, property, val);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 5e830281bebd..03414bde1f15 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -466,7 +466,7 @@ static bool drm_fb_helper_is_bound(struct drm_fb_helper *fb_helper)
 
 	/* Sometimes user space wants everything disabled, so don't steal the
 	 * display if there's a master. */
-	if (lockless_dereference(dev->master))
+	if (READ_ONCE(dev->master))
 		return false;
 
 	drm_for_each_crtc(crtc, dev) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index e0166403b4bd..40ce841eb952 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -55,11 +55,11 @@ static int check_fb_gem_memory_type(struct drm_device *drm_dev,
 	flags = exynos_gem->flags;
 
 	/*
-	 * without iommu support, not support physically non-continuous memory
-	 * for framebuffer.
+	 * Physically non-contiguous memory type for framebuffer is not
+	 * supported without IOMMU.
 	 */
 	if (IS_NONCONTIG_BUFFER(flags)) {
-		DRM_ERROR("cannot use this gem memory type for fb.\n");
+		DRM_ERROR("Non-contiguous GEM memory is not supported.\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 0525c56145db..147ef0d298cb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1753,32 +1753,6 @@ static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int fimc_suspend(struct device *dev)
-{
-	struct fimc_context *ctx = get_fimc_context(dev);
-
-	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	return fimc_clk_ctrl(ctx, false);
-}
-
-static int fimc_resume(struct device *dev)
-{
-	struct fimc_context *ctx = get_fimc_context(dev);
-
-	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
-	if (!pm_runtime_suspended(dev))
-		return fimc_clk_ctrl(ctx, true);
-
-	return 0;
-}
-#endif
-
 static int fimc_runtime_suspend(struct device *dev)
 {
 	struct fimc_context *ctx = get_fimc_context(dev);
@@ -1799,7 +1773,8 @@ static int fimc_runtime_resume(struct device *dev)
 #endif
 
 static const struct dev_pm_ops fimc_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(fimc_suspend, fimc_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(fimc_runtime_suspend, fimc_runtime_resume, NULL)
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 4bf00f57ffe8..6eca8bb88648 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -1475,8 +1475,8 @@ static int g2d_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int g2d_suspend(struct device *dev)
+#ifdef CONFIG_PM
+static int g2d_runtime_suspend(struct device *dev)
 {
 	struct g2d_data *g2d = dev_get_drvdata(dev);
 
@@ -1490,25 +1490,6 @@ static int g2d_suspend(struct device *dev)
 
 	flush_work(&g2d->runqueue_work);
 
-	return 0;
-}
-
-static int g2d_resume(struct device *dev)
-{
-	struct g2d_data *g2d = dev_get_drvdata(dev);
-
-	g2d->suspended = false;
-	g2d_exec_runqueue(g2d);
-
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_PM
-static int g2d_runtime_suspend(struct device *dev)
-{
-	struct g2d_data *g2d = dev_get_drvdata(dev);
-
 	clk_disable_unprepare(g2d->gate_clk);
 
 	return 0;
@@ -1523,12 +1504,16 @@ static int g2d_runtime_resume(struct device *dev)
 	if (ret < 0)
 		dev_warn(dev, "failed to enable clock.\n");
 
+	g2d->suspended = false;
+	g2d_exec_runqueue(g2d);
+
 	return ret;
 }
 #endif
 
 static const struct dev_pm_ops g2d_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(g2d_suspend, g2d_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(g2d_runtime_suspend, g2d_runtime_resume, NULL)
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 5d20da8f957e..52a9d269484e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1760,34 +1760,7 @@ static int gsc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int gsc_suspend(struct device *dev)
-{
-	struct gsc_context *ctx = get_gsc_context(dev);
-
-	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	return gsc_clk_ctrl(ctx, false);
-}
-
-static int gsc_resume(struct device *dev)
-{
-	struct gsc_context *ctx = get_gsc_context(dev);
-
-	DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
-	if (!pm_runtime_suspended(dev))
-		return gsc_clk_ctrl(ctx, true);
-
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_PM
-static int gsc_runtime_suspend(struct device *dev)
+static int __maybe_unused gsc_runtime_suspend(struct device *dev)
 {
 	struct gsc_context *ctx = get_gsc_context(dev);
 
@@ -1796,7 +1769,7 @@ static int gsc_runtime_suspend(struct device *dev)
 	return  gsc_clk_ctrl(ctx, false);
 }
 
-static int gsc_runtime_resume(struct device *dev)
+static int __maybe_unused gsc_runtime_resume(struct device *dev)
 {
 	struct gsc_context *ctx = get_gsc_context(dev);
 
@@ -1804,10 +1777,10 @@ static int gsc_runtime_resume(struct device *dev)
 
 	return  gsc_clk_ctrl(ctx, true);
 }
-#endif
 
 static const struct dev_pm_ops gsc_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(gsc_suspend, gsc_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(gsc_runtime_suspend, gsc_runtime_resume, NULL)
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 404367a430b5..6591e406084c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -794,29 +794,6 @@ static int rotator_clk_crtl(struct rot_context *rot, bool enable)
 	return 0;
 }
 
-
-#ifdef CONFIG_PM_SLEEP
-static int rotator_suspend(struct device *dev)
-{
-	struct rot_context *rot = dev_get_drvdata(dev);
-
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	return rotator_clk_crtl(rot, false);
-}
-
-static int rotator_resume(struct device *dev)
-{
-	struct rot_context *rot = dev_get_drvdata(dev);
-
-	if (!pm_runtime_suspended(dev))
-		return rotator_clk_crtl(rot, true);
-
-	return 0;
-}
-#endif
-
 static int rotator_runtime_suspend(struct device *dev)
 {
 	struct rot_context *rot = dev_get_drvdata(dev);
@@ -833,7 +810,8 @@ static int rotator_runtime_resume(struct device *dev)
 #endif
 
 static const struct dev_pm_ops rotator_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(rotator_suspend, rotator_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(rotator_runtime_suspend, rotator_runtime_resume,
 									NULL)
 };
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c8bd02277b7d..2c8106758922 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2616,6 +2616,8 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine)
 	list_for_each_entry_continue(request, &engine->request_list, link)
 		if (request->ctx == incomplete_ctx)
 			reset_request(request);
+
+	engine->i915->gt.active_engines &= ~intel_engine_flag(engine);
 }
 
 void i915_gem_reset(struct drm_i915_private *dev_priv)
@@ -2626,6 +2628,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv)
 
 	for_each_engine(engine, dev_priv)
 		i915_gem_reset_engine(engine);
+	mod_delayed_work(dev_priv->wq, &dev_priv->gt.idle_work, 0);
 
 	i915_gem_restore_fences(&dev_priv->drm);
 }
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 497d99b88468..8d4c35d55b1b 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3601,6 +3601,8 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 
 	dev_priv->modeset_restore_state = NULL;
 
+	dev_priv->modeset_restore_state = NULL;
+
 	/* reset doesn't touch the display */
 	if (!gpu_reset_clobbers_display(dev_priv)) {
 		if (!state) {
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 9df29f1cb16a..4e1ae3fc462d 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -79,6 +79,8 @@ static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	/* always disable planes on the CRTC */
 	drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, true);
+
+	drm_crtc_vblank_off(crtc);
 }
 
 static void imx_drm_crtc_reset(struct drm_crtc *crtc)
@@ -183,6 +185,8 @@ static int ipu_crtc_atomic_check(struct drm_crtc *crtc,
 static void ipu_crtc_atomic_begin(struct drm_crtc *crtc,
 				  struct drm_crtc_state *old_crtc_state)
 {
+	drm_crtc_vblank_on(crtc);
+
 	spin_lock_irq(&crtc->dev->event_lock);
 	if (crtc->state->event) {
 		WARN_ON(drm_crtc_vblank_get(crtc));
diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig
index 23ac8041c562..294de4549922 100644
--- a/drivers/gpu/drm/mediatek/Kconfig
+++ b/drivers/gpu/drm/mediatek/Kconfig
@@ -2,6 +2,9 @@ config DRM_MEDIATEK
 	tristate "DRM Support for Mediatek SoCs"
 	depends on DRM
 	depends on ARCH_MEDIATEK || (ARM && COMPILE_TEST)
+	depends on COMMON_CLK
+	depends on HAVE_ARM_SMCCC
+	depends on OF
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_HELPER
 	select DRM_MIPI_DSI
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index b4bc7f1ef717..d0da52f2a806 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -157,6 +157,12 @@ struct msm_drm_private {
 	struct shrinker shrinker;
 
 	struct msm_vblank_ctrl vblank_ctrl;
+
+	/* task holding struct_mutex.. currently only used in submit path
+	 * to detect and reject faults from copy_from_user() for submit
+	 * ioctl.
+	 */
+	struct task_struct *struct_mutex_task;
 };
 
 struct msm_format {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 0a9b5580b2e9..b6ac27e31929 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -196,11 +196,20 @@ int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct drm_device *dev = obj->dev;
+	struct msm_drm_private *priv = dev->dev_private;
 	struct page **pages;
 	unsigned long pfn;
 	pgoff_t pgoff;
 	int ret;
 
+	/* This should only happen if userspace tries to pass a mmap'd
+	 * but unfaulted gem bo vaddr into submit ioctl, triggering
+	 * a page fault while struct_mutex is already held.  This is
+	 * not a valid use-case so just bail.
+	 */
+	if (priv->struct_mutex_task == current)
+		return VM_FAULT_SIGBUS;
+
 	/* Make sure we don't parallel update on a fault, nor move or remove
 	 * something from beneath our feet
 	 */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3ac14cd1e5b9..b6a0f37a65f3 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -66,6 +66,14 @@ void msm_gem_submit_free(struct msm_gem_submit *submit)
 	kfree(submit);
 }
 
+static inline unsigned long __must_check
+copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+	if (access_ok(VERIFY_READ, from, n))
+		return __copy_from_user_inatomic(to, from, n);
+	return -EFAULT;
+}
+
 static int submit_lookup_objects(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
@@ -73,6 +81,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 	int ret = 0;
 
 	spin_lock(&file->table_lock);
+	pagefault_disable();
 
 	for (i = 0; i < args->nr_bos; i++) {
 		struct drm_msm_gem_submit_bo submit_bo;
@@ -86,10 +95,15 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 		 */
 		submit->bos[i].flags = 0;
 
-		ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
-		if (ret) {
-			ret = -EFAULT;
-			goto out_unlock;
+		ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo));
+		if (unlikely(ret)) {
+			pagefault_enable();
+			spin_unlock(&file->table_lock);
+			ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
+			if (ret)
+				goto out;
+			spin_lock(&file->table_lock);
+			pagefault_disable();
 		}
 
 		if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) {
@@ -129,9 +143,12 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 	}
 
 out_unlock:
-	submit->nr_bos = i;
+	pagefault_enable();
 	spin_unlock(&file->table_lock);
 
+out:
+	submit->nr_bos = i;
+
 	return ret;
 }
 
@@ -392,6 +409,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 			goto out_unlock;
 		}
 	}
+	priv->struct_mutex_task = current;
 
 	submit = submit_create(dev, gpu, args->nr_bos, args->nr_cmds);
 	if (!submit) {
@@ -531,6 +549,7 @@ out:
 out_unlock:
 	if (ret && (out_fence_fd >= 0))
 		put_unused_fd(out_fence_fd);
+	priv->struct_mutex_task = NULL;
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index f2ad17aa33f0..dc57b628e074 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -225,6 +225,17 @@ static bool nouveau_pr3_present(struct pci_dev *pdev)
 	if (!parent_pdev)
 		return false;
 
+	if (!parent_pdev->bridge_d3) {
+		/*
+		 * Parent PCI bridge is currently not power managed.
+		 * Since userspace can change these afterwards to be on
+		 * the safe side we stick with _DSM and prevent usage of
+		 * _PR3 from the bridge.
+		 */
+		pci_d3cold_disable(pdev);
+		return false;
+	}
+
 	parent_adev = ACPI_COMPANION(&parent_pdev->dev);
 	if (!parent_adev)
 		return false;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 4824f70b0258..a4e9f35da3a2 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -627,7 +627,9 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 			if (radeon_crtc->ss.refdiv) {
 				radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
 				radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv;
-				if (rdev->family >= CHIP_RV770)
+				if (ASIC_IS_AVIVO(rdev) &&
+				    rdev->family != CHIP_RS780 &&
+				    rdev->family != CHIP_RS880)
 					radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index a1321b2fa454..2fdcd04bc93f 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -203,16 +203,7 @@ static int radeon_atpx_validate(struct radeon_atpx *atpx)
 	atpx->is_hybrid = false;
 	if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
 		printk("ATPX Hybrid Graphics\n");
-#if 1
-		/* This is a temporary hack until the D3 cold support
-		 * makes it upstream.  The ATPX power_control method seems
-		 * to still work on even if the system should be using
-		 * the new standardized hybrid D3 cold ACPI interface.
-		 */
-		atpx->functions.power_cntl = true;
-#else
 		atpx->functions.power_cntl = false;
-#endif
 		atpx->is_hybrid = true;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 27ee0ab0e1a7..455268214b89 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -264,8 +264,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 
 	rdev = radeon_get_rdev(bo->bdev);
 	ridx = radeon_copy_ring_index(rdev);
-	old_start = old_mem->start << PAGE_SHIFT;
-	new_start = new_mem->start << PAGE_SHIFT;
+	old_start = (u64)old_mem->start << PAGE_SHIFT;
+	new_start = (u64)new_mem->start << PAGE_SHIFT;
 
 	switch (old_mem->mem_type) {
 	case TTM_PL_VRAM:
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 3d228ad90e0f..3dea1216bafd 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -840,6 +840,21 @@ static const struct drm_encoder_funcs tegra_dsi_encoder_funcs = {
 	.destroy = tegra_output_encoder_destroy,
 };
 
+static void tegra_dsi_unprepare(struct tegra_dsi *dsi)
+{
+	int err;
+
+	if (dsi->slave)
+		tegra_dsi_unprepare(dsi->slave);
+
+	err = tegra_mipi_disable(dsi->mipi);
+	if (err < 0)
+		dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n",
+			err);
+
+	pm_runtime_put(dsi->dev);
+}
+
 static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
 {
 	struct tegra_output *output = encoder_to_output(encoder);
@@ -876,7 +891,26 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
 
 	tegra_dsi_disable(dsi);
 
-	pm_runtime_put(dsi->dev);
+	tegra_dsi_unprepare(dsi);
+}
+
+static void tegra_dsi_prepare(struct tegra_dsi *dsi)
+{
+	int err;
+
+	pm_runtime_get_sync(dsi->dev);
+
+	err = tegra_mipi_enable(dsi->mipi);
+	if (err < 0)
+		dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n",
+			err);
+
+	err = tegra_dsi_pad_calibrate(dsi);
+	if (err < 0)
+		dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+
+	if (dsi->slave)
+		tegra_dsi_prepare(dsi->slave);
 }
 
 static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
@@ -887,13 +921,8 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
 	struct tegra_dsi *dsi = to_dsi(output);
 	struct tegra_dsi_state *state;
 	u32 value;
-	int err;
-
-	pm_runtime_get_sync(dsi->dev);
 
-	err = tegra_dsi_pad_calibrate(dsi);
-	if (err < 0)
-		dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+	tegra_dsi_prepare(dsi);
 
 	state = tegra_dsi_get_state(dsi);
 
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 59adcf8532dd..3f6704cf6608 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -144,7 +144,7 @@ static struct list_head *vc4_get_cache_list_for_size(struct drm_device *dev,
 	return &vc4->bo_cache.size_list[page_index];
 }
 
-void vc4_bo_cache_purge(struct drm_device *dev)
+static void vc4_bo_cache_purge(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 3c9e7f64b926..8703f56b7947 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -58,21 +58,21 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
 	switch (args->param) {
 	case DRM_VC4_PARAM_V3D_IDENT0:
 		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
-		if (ret)
+		if (ret < 0)
 			return ret;
 		args->value = V3D_READ(V3D_IDENT0);
 		pm_runtime_put(&vc4->v3d->pdev->dev);
 		break;
 	case DRM_VC4_PARAM_V3D_IDENT1:
 		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
-		if (ret)
+		if (ret < 0)
 			return ret;
 		args->value = V3D_READ(V3D_IDENT1);
 		pm_runtime_put(&vc4->v3d->pdev->dev);
 		break;
 	case DRM_VC4_PARAM_V3D_IDENT2:
 		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
-		if (ret)
+		if (ret < 0)
 			return ret;
 		args->value = V3D_READ(V3D_IDENT2);
 		pm_runtime_put(&vc4->v3d->pdev->dev);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 489e3de0c050..428e24919ef1 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -321,6 +321,15 @@ vc4_first_render_job(struct vc4_dev *vc4)
 				struct vc4_exec_info, head);
 }
 
+static inline struct vc4_exec_info *
+vc4_last_render_job(struct vc4_dev *vc4)
+{
+	if (list_empty(&vc4->render_job_list))
+		return NULL;
+	return list_last_entry(&vc4->render_job_list,
+			       struct vc4_exec_info, head);
+}
+
 /**
  * struct vc4_texture_sample_info - saves the offsets into the UBO for texture
  * setup parameters.
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 27c52ec35193..77daea6cb866 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -530,8 +530,8 @@ vc4_cl_lookup_bos(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	exec->bo = kcalloc(exec->bo_count, sizeof(struct drm_gem_cma_object *),
-			   GFP_KERNEL);
+	exec->bo = drm_calloc_large(exec->bo_count,
+				    sizeof(struct drm_gem_cma_object *));
 	if (!exec->bo) {
 		DRM_ERROR("Failed to allocate validated BO pointers\n");
 		return -ENOMEM;
@@ -568,8 +568,8 @@ vc4_cl_lookup_bos(struct drm_device *dev,
 	spin_unlock(&file_priv->table_lock);
 
 fail:
-	kfree(handles);
-	return 0;
+	drm_free_large(handles);
+	return ret;
 }
 
 static int
@@ -604,7 +604,7 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 	 * read the contents back for validation, and I think the
 	 * bo->vaddr is uncached access.
 	 */
-	temp = kmalloc(temp_size, GFP_KERNEL);
+	temp = drm_malloc_ab(temp_size, 1);
 	if (!temp) {
 		DRM_ERROR("Failed to allocate storage for copying "
 			  "in bin/render CLs.\n");
@@ -671,7 +671,7 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 	ret = vc4_validate_shader_recs(dev, exec);
 
 fail:
-	kfree(temp);
+	drm_free_large(temp);
 	return ret;
 }
 
@@ -684,7 +684,7 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	if (exec->bo) {
 		for (i = 0; i < exec->bo_count; i++)
 			drm_gem_object_unreference_unlocked(&exec->bo[i]->base);
-		kfree(exec->bo);
+		drm_free_large(exec->bo);
 	}
 
 	while (!list_empty(&exec->unref_list)) {
@@ -938,8 +938,8 @@ vc4_gem_destroy(struct drm_device *dev)
 		vc4->overflow_mem = NULL;
 	}
 
-	vc4_bo_cache_destroy(dev);
-
 	if (vc4->hang_state)
 		vc4_free_hang_state(dev, vc4->hang_state);
+
+	vc4_bo_cache_destroy(dev);
 }
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index b0104a346a74..094bc6a475c1 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -83,8 +83,10 @@ vc4_overflow_mem_work(struct work_struct *work)
 
 		spin_lock_irqsave(&vc4->job_lock, irqflags);
 		current_exec = vc4_first_bin_job(vc4);
+		if (!current_exec)
+			current_exec = vc4_last_render_job(vc4);
 		if (current_exec) {
-			vc4->overflow_mem->seqno = vc4->finished_seqno + 1;
+			vc4->overflow_mem->seqno = current_exec->seqno;
 			list_add_tail(&vc4->overflow_mem->unref_head,
 				      &current_exec->unref_list);
 			vc4->overflow_mem = NULL;
diff --git a/drivers/gpu/drm/vc4/vc4_validate_shaders.c b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
index 46527e989ce3..2543cf5b8b51 100644
--- a/drivers/gpu/drm/vc4/vc4_validate_shaders.c
+++ b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
@@ -309,8 +309,14 @@ validate_uniform_address_write(struct vc4_validated_shader_info *validated_shade
 	 * of uniforms on each side.  However, this scheme is easy to
 	 * validate so it's all we allow for now.
 	 */
-
-	if (QPU_GET_FIELD(inst, QPU_SIG) != QPU_SIG_NONE) {
+	switch (QPU_GET_FIELD(inst, QPU_SIG)) {
+	case QPU_SIG_NONE:
+	case QPU_SIG_SCOREBOARD_UNLOCK:
+	case QPU_SIG_COLOR_LOAD:
+	case QPU_SIG_LOAD_TMU0:
+	case QPU_SIG_LOAD_TMU1:
+		break;
+	default:
 		DRM_ERROR("uniforms address change must be "
 			  "normal math\n");
 		return false;