Merge 6.9-rc7 into usb-next

We want the USB fixes in here as well, and resolve a merge conflict in
drivers/usb/dwc3/core.c

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

52 files changed, 353 insertions, 338 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index df58a6a1a67e..e4d4e55c08ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -220,7 +220,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	    (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
 	     kfd_mem_limit.max_ttm_mem_limit) ||
 	    (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed >
-	     vram_size - reserved_for_pt)) {
+	     vram_size - reserved_for_pt - atomic64_read(&adev->vram_pin_size))) {
 		ret = -ENOMEM;
 		goto release;
 	}
@@ -1854,6 +1854,7 @@ err_node_allow:
 err_bo_create:
 	amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags, xcp_id);
 err_reserve_limit:
+	amdgpu_sync_free(&(*mem)->sync);
 	mutex_destroy(&(*mem)->lock);
 	if (gobj)
 		drm_gem_object_put(gobj);
@@ -2900,13 +2901,12 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 
 	amdgpu_sync_create(&sync_obj);
 
-	/* Validate BOs and map them to GPUVM (update VM page tables). */
+	/* Validate BOs managed by KFD */
 	list_for_each_entry(mem, &process_info->kfd_bo_list,
 			    validate_list) {
 
 		struct amdgpu_bo *bo = mem->bo;
 		uint32_t domain = mem->domain;
-		struct kfd_mem_attachment *attachment;
 		struct dma_resv_iter cursor;
 		struct dma_fence *fence;
 
@@ -2931,6 +2931,25 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 				goto validate_map_fail;
 			}
 		}
+	}
+
+	if (failed_size)
+		pr_debug("0x%lx/0x%lx in system\n", failed_size, total_size);
+
+	/* Validate PDs, PTs and evicted DMABuf imports last. Otherwise BO
+	 * validations above would invalidate DMABuf imports again.
+	 */
+	ret = process_validate_vms(process_info, &exec.ticket);
+	if (ret) {
+		pr_debug("Validating VMs failed, ret: %d\n", ret);
+		goto validate_map_fail;
+	}
+
+	/* Update mappings managed by KFD. */
+	list_for_each_entry(mem, &process_info->kfd_bo_list,
+			    validate_list) {
+		struct kfd_mem_attachment *attachment;
+
 		list_for_each_entry(attachment, &mem->attachments, list) {
 			if (!attachment->is_mapped)
 				continue;
@@ -2947,18 +2966,6 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 		}
 	}
 
-	if (failed_size)
-		pr_debug("0x%lx/0x%lx in system\n", failed_size, total_size);
-
-	/* Validate PDs, PTs and evicted DMABuf imports last. Otherwise BO
-	 * validations above would invalidate DMABuf imports again.
-	 */
-	ret = process_validate_vms(process_info, &exec.ticket);
-	if (ret) {
-		pr_debug("Validating VMs failed, ret: %d\n", ret);
-		goto validate_map_fail;
-	}
-
 	/* Update mappings not managed by KFD */
 	list_for_each_entry(peer_vm, &process_info->vm_list_head,
 			vm_list_node) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index a00cf4756ad0..1569bef030ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1132,6 +1132,7 @@ void amdgpu_mes_remove_ring(struct amdgpu_device *adev,
 		return;
 
 	amdgpu_mes_remove_hw_queue(adev, ring->hw_queue_id);
+	del_timer_sync(&ring->fence_drv.fallback_timer);
 	amdgpu_ring_fini(ring);
 	kfree(ring);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 2099159a693f..f6d503432a9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -605,6 +605,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	else
 		amdgpu_bo_placement_from_domain(bo, bp->domain);
 	if (bp->type == ttm_bo_type_kernel)
+		bo->tbo.priority = 2;
+	else if (!(bp->flags & AMDGPU_GEM_CREATE_DISCARDABLE))
 		bo->tbo.priority = 1;
 
 	if (!bp->destroy)
@@ -1241,14 +1243,18 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
  * amdgpu_bo_move_notify - notification about a memory move
  * @bo: pointer to a buffer object
  * @evict: if this move is evicting the buffer from the graphics address space
+ * @new_mem: new resource for backing the BO
  *
  * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
  * bookkeeping.
  * TTM driver callback which is called when ttm moves a buffer.
  */
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+			   bool evict,
+			   struct ttm_resource *new_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
+	struct ttm_resource *old_mem = bo->resource;
 	struct amdgpu_bo *abo;
 
 	if (!amdgpu_bo_is_amdgpu_bo(bo))
@@ -1260,12 +1266,12 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
 	amdgpu_bo_kunmap(abo);
 
 	if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach &&
-	    bo->resource->mem_type != TTM_PL_SYSTEM)
+	    old_mem && old_mem->mem_type != TTM_PL_SYSTEM)
 		dma_buf_move_notify(abo->tbo.base.dma_buf);
 
-	/* remember the eviction */
-	if (evict)
-		atomic64_inc(&adev->num_evictions);
+	/* move_notify is called before move happens */
+	trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1,
+			     old_mem ? old_mem->mem_type : -1);
 }
 
 void amdgpu_bo_get_memory(struct amdgpu_bo *bo,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index fa03d9e4874c..bc42ccbde659 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -328,7 +328,9 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   size_t buffer_size, uint32_t *metadata_size,
 			   uint64_t *flags);
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict);
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+			   bool evict,
+			   struct ttm_resource *new_mem);
 void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);
 vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 1d71729e3f6b..109fe557a02b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -419,7 +419,7 @@ bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
 		return false;
 
 	if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT ||
-	    res->mem_type == AMDGPU_PL_PREEMPT)
+	    res->mem_type == AMDGPU_PL_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL)
 		return true;
 
 	if (res->mem_type != TTM_PL_VRAM)
@@ -481,14 +481,16 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 
 	if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM &&
 			 bo->ttm == NULL)) {
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_bo_move_null(bo, new_mem);
-		goto out;
+		return 0;
 	}
 	if (old_mem->mem_type == TTM_PL_SYSTEM &&
 	    (new_mem->mem_type == TTM_PL_TT ||
 	     new_mem->mem_type == AMDGPU_PL_PREEMPT)) {
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_bo_move_null(bo, new_mem);
-		goto out;
+		return 0;
 	}
 	if ((old_mem->mem_type == TTM_PL_TT ||
 	     old_mem->mem_type == AMDGPU_PL_PREEMPT) &&
@@ -498,9 +500,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 
 		amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm);
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_resource_free(bo, &bo->resource);
 		ttm_bo_assign_mem(bo, new_mem);
-		goto out;
+		return 0;
 	}
 
 	if (old_mem->mem_type == AMDGPU_PL_GDS ||
@@ -512,8 +515,9 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 	    new_mem->mem_type == AMDGPU_PL_OA ||
 	    new_mem->mem_type == AMDGPU_PL_DOORBELL) {
 		/* Nothing to save here */
+		amdgpu_bo_move_notify(bo, evict, new_mem);
 		ttm_bo_move_null(bo, new_mem);
-		goto out;
+		return 0;
 	}
 
 	if (bo->type == ttm_bo_type_device &&
@@ -525,22 +529,23 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 	}
 
-	if (adev->mman.buffer_funcs_enabled) {
-		if (((old_mem->mem_type == TTM_PL_SYSTEM &&
-		      new_mem->mem_type == TTM_PL_VRAM) ||
-		     (old_mem->mem_type == TTM_PL_VRAM &&
-		      new_mem->mem_type == TTM_PL_SYSTEM))) {
-			hop->fpfn = 0;
-			hop->lpfn = 0;
-			hop->mem_type = TTM_PL_TT;
-			hop->flags = TTM_PL_FLAG_TEMPORARY;
-			return -EMULTIHOP;
-		}
+	if (adev->mman.buffer_funcs_enabled &&
+	    ((old_mem->mem_type == TTM_PL_SYSTEM &&
+	      new_mem->mem_type == TTM_PL_VRAM) ||
+	     (old_mem->mem_type == TTM_PL_VRAM &&
+	      new_mem->mem_type == TTM_PL_SYSTEM))) {
+		hop->fpfn = 0;
+		hop->lpfn = 0;
+		hop->mem_type = TTM_PL_TT;
+		hop->flags = TTM_PL_FLAG_TEMPORARY;
+		return -EMULTIHOP;
+	}
 
+	amdgpu_bo_move_notify(bo, evict, new_mem);
+	if (adev->mman.buffer_funcs_enabled)
 		r = amdgpu_move_blit(bo, evict, new_mem, old_mem);
-	} else {
+	else
 		r = -ENODEV;
-	}
 
 	if (r) {
 		/* Check that all memory is CPU accessible */
@@ -555,11 +560,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
-	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
-out:
-	/* update statistics */
+	/* update statistics after the move */
+	if (evict)
+		atomic64_inc(&adev->num_evictions);
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);
-	amdgpu_bo_move_notify(bo, evict);
 	return 0;
 }
 
@@ -1559,7 +1563,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 static void
 amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo)
 {
-	amdgpu_bo_move_notify(bo, false);
+	amdgpu_bo_move_notify(bo, false, NULL);
 }
 
 static struct ttm_device_funcs amdgpu_bo_driver = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index 0df97c3e3a70..f7c73533e336 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -774,6 +774,9 @@ static int umsch_mm_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (amdgpu_in_reset(adev) || adev->in_s0ix || adev->in_suspend)
+		return 0;
+
 	return umsch_mm_test(adev);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 6695481f870f..c23d97d34b7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -205,7 +205,7 @@ disable_dpm:
 	dpm_ctl &= 0xfffffffe; /* Disable DPM */
 	WREG32(vpe_get_reg_offset(vpe, 0, vpe->regs.dpm_enable), dpm_ctl);
 	dev_dbg(adev->dev, "%s: disable vpe dpm\n", __func__);
-	return 0;
+	return -EINVAL;
 }
 
 int amdgpu_vpe_psp_update_sram(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index f90905ef32c7..701146d649c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -9186,7 +9186,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 		7 + /* PIPELINE_SYNC */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
-		2 + /* VM_FLUSH */
+		4 + /* VM_FLUSH */
 		8 + /* FENCE for VM_FLUSH */
 		20 + /* GDS switch */
 		4 + /* double SWITCH_BUFFER,
@@ -9276,7 +9276,6 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
 		7 + /* gfx_v10_0_ring_emit_pipeline_sync */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
-		2 + /* gfx_v10_0_ring_emit_vm_flush */
 		8 + 8 + 8, /* gfx_v10_0_ring_emit_fence_kiq x3 for user fence, vm fence */
 	.emit_ib_size =	7, /* gfx_v10_0_ring_emit_ib_compute */
 	.emit_ib = gfx_v10_0_ring_emit_ib_compute,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index f7325b02a191..f00e05aba46a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -6192,7 +6192,7 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = {
 		7 + /* PIPELINE_SYNC */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
-		2 + /* VM_FLUSH */
+		4 + /* VM_FLUSH */
 		8 + /* FENCE for VM_FLUSH */
 		20 + /* GDS switch */
 		5 + /* COND_EXEC */
@@ -6278,7 +6278,6 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_kiq = {
 		7 + /* gfx_v11_0_ring_emit_pipeline_sync */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
-		2 + /* gfx_v11_0_ring_emit_vm_flush */
 		8 + 8 + 8, /* gfx_v11_0_ring_emit_fence_kiq x3 for user fence, vm fence */
 	.emit_ib_size =	7, /* gfx_v11_0_ring_emit_ib_compute */
 	.emit_ib = gfx_v11_0_ring_emit_ib_compute,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6f97a6d0e6d0..99dbd2341120 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -6981,7 +6981,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
 		7 + /* gfx_v9_0_ring_emit_pipeline_sync */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
-		2 + /* gfx_v9_0_ring_emit_vm_flush */
 		8 + 8 + 8 + /* gfx_v9_0_ring_emit_fence x3 for user fence, vm fence */
 		7 + /* gfx_v9_0_emit_mem_sync */
 		5 + /* gfx_v9_0_emit_wave_limit for updating mmSPI_WCL_PIPE_PERCENT_GFX register */
@@ -7019,7 +7018,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = {
 		7 + /* gfx_v9_0_ring_emit_pipeline_sync */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
-		2 + /* gfx_v9_0_ring_emit_vm_flush */
 		8 + 8 + 8, /* gfx_v9_0_ring_emit_fence_kiq x3 for user fence, vm fence */
 	.emit_ib_size =	7, /* gfx_v9_0_ring_emit_ib_compute */
 	.emit_fence = gfx_v9_0_ring_emit_fence_kiq,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 82eab49be82b..e708468ac54d 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -368,7 +368,8 @@ static void sdma_v4_4_2_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	u32 ref_and_mask = 0;
 	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
 
-	ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me;
+	ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0
+		       << (ring->me % adev->sdma.num_inst_per_aid);
 
 	sdma_v4_4_2_wait_reg_mem(ring, 0, 1,
 			       adev->nbio.funcs->get_hdp_flush_done_offset(adev),
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 42f4bd250def..da01b524b9f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -280,17 +280,21 @@ static void sdma_v5_2_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	u32 ref_and_mask = 0;
 	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
 
-	ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me;
-
-	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) |
-			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
-	amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2);
-	amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2);
-	amdgpu_ring_write(ring, ref_and_mask); /* reference */
-	amdgpu_ring_write(ring, ref_and_mask); /* mask */
-	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
-			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */
+	if (ring->me > 1) {
+		amdgpu_asic_flush_hdp(adev, ring);
+	} else {
+		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me;
+
+		amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
+				  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) |
+				  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
+		amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2);
+		amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2);
+		amdgpu_ring_write(ring, ref_and_mask); /* reference */
+		amdgpu_ring_write(ring, ref_and_mask); /* mask */
+		amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
+				  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */
+	}
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
index 769eb8f7bb3c..09315dd5a1ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
@@ -144,6 +144,12 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe)
 			WREG32(vpe_get_reg_offset(vpe, j, regVPEC_CNTL), ret);
 	}
 
+	/* setup collaborate mode */
+	vpe_v6_1_set_collaborate_mode(vpe, true);
+	/* setup DPM */
+	if (amdgpu_vpe_configure_dpm(vpe))
+		dev_warn(adev->dev, "VPE failed to enable DPM\n");
+
 	/*
 	 * For VPE 6.1.1, still only need to add master's offset, and psp will apply it to slave as well.
 	 * Here use instance 0 as master.
@@ -159,11 +165,7 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe)
 		adev->vpe.cmdbuf_cpu_addr[0] = f32_offset;
 		adev->vpe.cmdbuf_cpu_addr[1] = f32_cntl;
 
-		amdgpu_vpe_psp_update_sram(adev);
-		vpe_v6_1_set_collaborate_mode(vpe, true);
-		amdgpu_vpe_configure_dpm(vpe);
-
-		return 0;
+		return amdgpu_vpe_psp_update_sram(adev);
 	}
 
 	vpe_hdr = (const struct vpe_firmware_header_v1_0 *)adev->vpe.fw->data;
@@ -196,8 +198,6 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe)
 	}
 
 	vpe_v6_1_halt(vpe, false);
-	vpe_v6_1_set_collaborate_mode(vpe, true);
-	amdgpu_vpe_configure_dpm(vpe);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index bdc01ca9609a..5c8d81bfce7a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -509,10 +509,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	start = start_mgr << PAGE_SHIFT;
 	end = (last_mgr + 1) << PAGE_SHIFT;
 
+	r = amdgpu_amdkfd_reserve_mem_limit(node->adev,
+					prange->npages * PAGE_SIZE,
+					KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+					node->xcp ? node->xcp->id : 0);
+	if (r) {
+		dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r);
+		return -ENOSPC;
+	}
+
 	r = svm_range_vram_node_new(node, prange, true);
 	if (r) {
 		dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r);
-		return r;
+		goto out;
 	}
 	ttm_res_offset = (start_mgr - prange->start + prange->offset) << PAGE_SHIFT;
 
@@ -545,6 +554,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 		svm_range_vram_node_free(prange);
 	}
 
+out:
+	amdgpu_amdkfd_unreserve_mem_limit(node->adev,
+					prange->npages * PAGE_SIZE,
+					KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+					node->xcp ? node->xcp->id : 0);
 	return r < 0 ? r : 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index b79986412cd8..451bb058cc62 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -829,6 +829,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
+		/* If the process just called exec(3), it is possible that the
+		 * cleanup of the kfd_process (following the release of the mm
+		 * of the old process image) is still in the cleanup work queue.
+		 * Make sure to drain any job before trying to recreate any
+		 * resource for this process.
+		 */
+		flush_workqueue(kfd_process_wq);
+
 		process = create_process(thread);
 		if (IS_ERR(process))
 			goto out;
@@ -1922,6 +1930,8 @@ static int signal_eviction_fence(struct kfd_process *p)
 	rcu_read_lock();
 	ef = dma_fence_get_rcu_safe(&p->ef);
 	rcu_read_unlock();
+	if (!ef)
+		return -EINVAL;
 
 	ret = dma_fence_signal(ef);
 	dma_fence_put(ef);
@@ -1949,10 +1959,9 @@ static void evict_process_worker(struct work_struct *work)
 		 * they are responsible stopping the queues and scheduling
 		 * the restore work.
 		 */
-		if (!signal_eviction_fence(p))
-			queue_delayed_work(kfd_restore_wq, &p->restore_work,
-				msecs_to_jiffies(PROCESS_RESTORE_TIME_MS));
-		else
+		if (signal_eviction_fence(p) ||
+		    mod_delayed_work(kfd_restore_wq, &p->restore_work,
+				     msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
 			kfd_process_restore_queues(p);
 
 		pr_debug("Finished evicting pasid 0x%x\n", p->pasid);
@@ -2011,9 +2020,9 @@ static void restore_process_worker(struct work_struct *work)
 	if (ret) {
 		pr_debug("Failed to restore BOs of pasid 0x%x, retry after %d ms\n",
 			 p->pasid, PROCESS_BACK_OFF_TIME_MS);
-		ret = queue_delayed_work(kfd_restore_wq, &p->restore_work,
-				msecs_to_jiffies(PROCESS_BACK_OFF_TIME_MS));
-		WARN(!ret, "reschedule restore work failed\n");
+		if (mod_delayed_work(kfd_restore_wq, &p->restore_work,
+				     msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
+			kfd_process_restore_queues(p);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f0f7f48af413..386875e6eb96 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3426,7 +3426,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 				mm, KFD_MIGRATE_TRIGGER_PREFETCH);
 	*migrated = !r;
 
-	return r;
+	return 0;
 }
 
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6d2f60c61dec..d6e71aa808d8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3029,6 +3029,7 @@ static int dm_resume(void *handle)
 			dc_stream_release(dm_new_crtc_state->stream);
 			dm_new_crtc_state->stream = NULL;
 		}
+		dm_new_crtc_state->base.color_mgmt_changed = true;
 	}
 
 	for_each_new_plane_in_state(dm->cached_state, plane, new_plane_state, i) {
@@ -4536,15 +4537,18 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 	/* Determine whether to enable Replay support by default. */
 	if (!(amdgpu_dc_debug_mask & DC_DISABLE_REPLAY)) {
 		switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
-		case IP_VERSION(3, 1, 4):
-		case IP_VERSION(3, 1, 5):
-		case IP_VERSION(3, 1, 6):
-		case IP_VERSION(3, 2, 0):
-		case IP_VERSION(3, 2, 1):
-		case IP_VERSION(3, 5, 0):
-		case IP_VERSION(3, 5, 1):
-			replay_feature_enabled = true;
-			break;
+/*
+ * Disabled by default due to https://gitlab.freedesktop.org/drm/amd/-/issues/3344
+ *		case IP_VERSION(3, 1, 4):
+ *		case IP_VERSION(3, 1, 5):
+ *		case IP_VERSION(3, 1, 6):
+ *		case IP_VERSION(3, 2, 0):
+ *		case IP_VERSION(3, 2, 1):
+ *		case IP_VERSION(3, 5, 0):
+ *		case IP_VERSION(3, 5, 1):
+ *			replay_feature_enabled = true;
+ *			break;
+ */
 		default:
 			replay_feature_enabled = amdgpu_dc_feature_mask & DC_REPLAY_MASK;
 			break;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index eee4945653e2..c7715a17f388 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1495,7 +1495,9 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1596,7 +1598,9 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1681,7 +1685,9 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1780,7 +1786,9 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1865,7 +1873,9 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -1964,7 +1974,9 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2045,7 +2057,9 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2141,7 +2155,9 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2220,7 +2236,9 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2276,7 +2294,9 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2347,7 +2367,9 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
@@ -2418,7 +2440,9 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,
 	for (i = 0; i < MAX_PIPES; i++) {
 		pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
 		if (pipe_ctx->stream &&
-		    pipe_ctx->stream->link == aconnector->dc_link)
+		    pipe_ctx->stream->link == aconnector->dc_link &&
+		    pipe_ctx->stream->sink &&
+		    pipe_ctx->stream->sink == aconnector->dc_sink)
 			break;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 05f392501c0a..ab31643b1096 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -2948,6 +2948,7 @@ static enum bp_result construct_integrated_info(
 				result = get_integrated_info_v2_1(bp, info);
 				break;
 			case 2:
+			case 3:
 				result = get_integrated_info_v2_2(bp, info);
 				break;
 			default:
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index 644da4637320..5506cf9b3672 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -145,6 +145,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 	 */
 	clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
 	if (safe_to_lower) {
+		if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) {
+			dcn315_smu_set_dtbclk(clk_mgr, false);
+			clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+		}
 		/* check that we're not already in lower */
 		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) {
 			display_count = dcn315_get_active_display_cnt_wa(dc, context);
@@ -160,6 +164,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base,
 			}
 		}
 	} else {
+		if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
+			dcn315_smu_set_dtbclk(clk_mgr, true);
+			clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+		}
 		/* check that we're not already in D0 */
 		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_MISSION_MODE) {
 			union display_idle_optimization_u idle_info = { 0 };
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index bec252e1dd27..e506e4f969ca 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -712,8 +712,12 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base,
 					 * since we calculate mode support based on softmax being the max UCLK
 					 * frequency.
 					 */
-					dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
-							dc->clk_mgr->bw_params->dc_mode_softmax_memclk);
+					if (dc->debug.disable_dc_mode_overwrite) {
+						dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
+						dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
+					} else
+						dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
+								dc->clk_mgr->bw_params->dc_mode_softmax_memclk);
 				} else {
 					dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
 				}
@@ -746,8 +750,13 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base,
 		/* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */
 		if (clk_mgr_base->clks.p_state_change_support &&
 				(update_uclk || !clk_mgr_base->clks.prev_p_state_change_support) &&
-				!dc->work_arounds.clock_update_disable_mask.uclk)
+				!dc->work_arounds.clock_update_disable_mask.uclk) {
+			if (dc->clk_mgr->dc_mode_softmax_enabled && dc->debug.disable_dc_mode_overwrite)
+				dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK,
+						max((int)dc->clk_mgr->bw_params->dc_mode_softmax_memclk, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)));
+
 			dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz));
+		}
 
 		if (clk_mgr_base->clks.num_ways != new_clocks->num_ways &&
 				clk_mgr_base->clks.num_ways > new_clocks->num_ways) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 03b554e912a2..d68c83e40d4d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1801,6 +1801,9 @@ bool dc_validate_boot_timing(const struct dc *dc,
 		return false;
 	}
 
+	if (link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED)
+		return false;
+
 	if (dc->link_srv->edp_is_ilr_optimization_required(link, crtc_timing)) {
 		DC_LOG_EVENT_LINK_TRAINING("Seamless boot disabled to optimize eDP link rate\n");
 		return false;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c
index 5b7ad38f85e0..65e45a0b4ff3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c
@@ -395,6 +395,12 @@ void dcn31_hpo_dp_link_enc_set_throttled_vcp_size(
 				x),
 			25));
 
+	// If y rounds up to integer, carry it over to x.
+	if (y >> 25) {
+		x += 1;
+		y = 0;
+	}
+
 	switch (stream_encoder_inst) {
 	case 0:
 		REG_SET_2(DP_DPHY_SYM32_VC_RATE_CNTL0, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
index deb6d162a2d5..7307b7b8d8ad 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
@@ -291,6 +291,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = {
 	.do_urgent_latency_adjustment = false,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
 	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.dispclk_dppclk_vco_speed_mhz = 2400.0,
 	.num_chans = 4,
 	.dummy_pstate_latency_us = 10.0
 };
@@ -438,6 +439,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = {
 	.do_urgent_latency_adjustment = false,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
 	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.dispclk_dppclk_vco_speed_mhz = 2500.0,
 };
 
 void dcn31_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index 5491b707cec8..5a965c26bf20 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -270,7 +270,7 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw)
 
 	/* Error check whether requested and allocated are equal */
 	req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
-	if (req_bw == link->dpia_bw_alloc_config.allocated_bw) {
+	if (req_bw && (req_bw == link->dpia_bw_alloc_config.allocated_bw)) {
 		DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n",
 			__func__, link->link_index);
 	}
@@ -341,6 +341,14 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link)
 			ret = true;
 			init_usb4_bw_struct(link);
 			link->dpia_bw_alloc_config.bw_alloc_enabled = true;
+
+			/*
+			 * During DP tunnel creation, CM preallocates BW and reduces estimated BW of other
+			 * DPIA. CM release preallocation only when allocation is complete. Do zero alloc
+			 * to make the CM to release preallocation and update estimated BW correctly for
+			 * all DPIAs per host router
+			 */
+			link_dp_dpia_allocate_usb4_bandwidth_for_stream(link, 0);
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
index a2387cea1af9..622214b365a2 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
@@ -2449,6 +2449,7 @@ static bool dcn20_resource_construct(
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 	dc->caps.extended_aux_timeout_support = true;
+	dc->caps.dmcub_support = true;
 
 	/* Color pipeline capabilities */
 	dc->caps.color.dpp.dcn_arch = 1;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index f09b9d49297e..bbd0169010c2 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4261,6 +4261,13 @@ static int amdgpu_od_set_init(struct amdgpu_device *adev)
 		}
 	}
 
+	/*
+	 * If gpu_od is the only member in the list, that means gpu_od is an
+	 * empty directory, so remove it.
+	 */
+	if (list_is_singular(&adev->pm.od_kobj_list))
+		goto err_out;
+
 	return 0;
 
 err_out:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 3957af057d54..c977ebe88001 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2294,6 +2294,17 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 	return sizeof(*gpu_metrics);
 }
 
+static void smu_v13_0_6_restore_pci_config(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int i;
+
+	for (i = 0; i < 16; i++)
+		pci_write_config_dword(adev->pdev, i * 4,
+				       adev->pdev->saved_config_space[i]);
+	pci_restore_msi_state(adev->pdev);
+}
+
 static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
 {
 	int ret = 0, index;
@@ -2315,6 +2326,20 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
 	/* Restore the config space saved during init */
 	amdgpu_device_load_pci_state(adev->pdev);
 
+	/* Certain platforms have switches which assign virtual BAR values to
+	 * devices. OS uses the virtual BAR values and device behind the switch
+	 * is assgined another BAR value. When device's config space registers
+	 * are queried, switch returns the virtual BAR values. When mode-2 reset
+	 * is performed, switch is unaware of it, and will continue to return
+	 * the same virtual values to the OS.This affects
+	 * pci_restore_config_space() API as it doesn't write the value saved if
+	 * the current value read from config space is the same as what is
+	 * saved. As a workaround, make sure the config space is restored
+	 * always.
+	 */
+	if (!(adev->flags & AMD_IS_APU))
+		smu_v13_0_6_restore_pci_config(smu);
+
 	dev_dbg(smu->adev->dev, "wait for reset ack\n");
 	do {
 		ret = smu_cmn_wait_for_response(smu);
diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c
index e440f458b663..93337543aac3 100644
--- a/drivers/gpu/drm/drm_gem_atomic_helper.c
+++ b/drivers/gpu/drm/drm_gem_atomic_helper.c
@@ -224,8 +224,8 @@ __drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane,
 
 	__drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base);
 
-	drm_format_conv_state_copy(&shadow_plane_state->fmtcnv_state,
-				   &new_shadow_plane_state->fmtcnv_state);
+	drm_format_conv_state_copy(&new_shadow_plane_state->fmtcnv_state,
+				   &shadow_plane_state->fmtcnv_state);
 }
 EXPORT_SYMBOL(__drm_gem_duplicate_shadow_plane_state);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 734412aae94d..a9bf426f69b3 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -164,26 +164,6 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value)
 		*value = gpu->identity.eco_id;
 		break;
 
-	case ETNAVIV_PARAM_GPU_NN_CORE_COUNT:
-		*value = gpu->identity.nn_core_count;
-		break;
-
-	case ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE:
-		*value = gpu->identity.nn_mad_per_core;
-		break;
-
-	case ETNAVIV_PARAM_GPU_TP_CORE_COUNT:
-		*value = gpu->identity.tp_core_count;
-		break;
-
-	case ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE:
-		*value = gpu->identity.on_chip_sram_size;
-		break;
-
-	case ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE:
-		*value = gpu->identity.axi_sram_size;
-		break;
-
 	default:
 		DBG("%s: invalid param: %u", dev_name(gpu->dev), param);
 		return -EINVAL;
@@ -663,8 +643,8 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu)
 	/* Disable TX clock gating on affected core revisions. */
 	if (etnaviv_is_model_rev(gpu, GC4000, 0x5222) ||
 	    etnaviv_is_model_rev(gpu, GC2000, 0x5108) ||
-	    etnaviv_is_model_rev(gpu, GC2000, 0x6202) ||
-	    etnaviv_is_model_rev(gpu, GC2000, 0x6203))
+	    etnaviv_is_model_rev(gpu, GC7000, 0x6202) ||
+	    etnaviv_is_model_rev(gpu, GC7000, 0x6203))
 		pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX;
 
 	/* Disable SE and RA clock gating on affected core revisions. */
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 7d5e9158e13c..197e0037732e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -54,18 +54,6 @@ struct etnaviv_chip_identity {
 	/* Number of Neural Network cores. */
 	u32 nn_core_count;
 
-	/* Number of MAD units per Neural Network core. */
-	u32 nn_mad_per_core;
-
-	/* Number of Tensor Processing cores. */
-	u32 tp_core_count;
-
-	/* Size in bytes of the SRAM inside the NPU. */
-	u32 on_chip_sram_size;
-
-	/* Size in bytes of the SRAM across the AXI bus. */
-	u32 axi_sram_size;
-
 	/* Size of the vertex cache. */
 	u32 vertex_cache_size;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
index d8e7334de8ce..8665f2658d51 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
@@ -17,10 +17,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.thread_count = 128,
 		.shader_core_count = 1,
 		.nn_core_count = 0,
-		.nn_mad_per_core = 0,
-		.tp_core_count = 0,
-		.on_chip_sram_size = 0,
-		.axi_sram_size = 0,
 		.vertex_cache_size = 8,
 		.vertex_output_buffer_size = 1024,
 		.pixel_pipes = 1,
@@ -52,11 +48,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.register_max = 64,
 		.thread_count = 256,
 		.shader_core_count = 1,
-		.nn_core_count = 0,
-		.nn_mad_per_core = 0,
-		.tp_core_count = 0,
-		.on_chip_sram_size = 0,
-		.axi_sram_size = 0,
 		.vertex_cache_size = 8,
 		.vertex_output_buffer_size = 512,
 		.pixel_pipes = 1,
@@ -89,10 +80,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.thread_count = 512,
 		.shader_core_count = 2,
 		.nn_core_count = 0,
-		.nn_mad_per_core = 0,
-		.tp_core_count = 0,
-		.on_chip_sram_size = 0,
-		.axi_sram_size = 0,
 		.vertex_cache_size = 16,
 		.vertex_output_buffer_size = 1024,
 		.pixel_pipes = 1,
@@ -125,10 +112,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.thread_count = 512,
 		.shader_core_count = 2,
 		.nn_core_count = 0,
-		.nn_mad_per_core = 0,
-		.tp_core_count = 0,
-		.on_chip_sram_size = 0,
-		.axi_sram_size = 0,
 		.vertex_cache_size = 16,
 		.vertex_output_buffer_size = 1024,
 		.pixel_pipes = 1,
@@ -160,11 +143,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.register_max = 64,
 		.thread_count = 512,
 		.shader_core_count = 2,
-		.nn_core_count = 0,
-		.nn_mad_per_core = 0,
-		.tp_core_count = 0,
-		.on_chip_sram_size = 0,
-		.axi_sram_size = 0,
 		.vertex_cache_size = 16,
 		.vertex_output_buffer_size = 1024,
 		.pixel_pipes = 1,
@@ -197,10 +175,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.thread_count = 1024,
 		.shader_core_count = 4,
 		.nn_core_count = 0,
-		.nn_mad_per_core = 0,
-		.tp_core_count = 0,
-		.on_chip_sram_size = 0,
-		.axi_sram_size = 0,
 		.vertex_cache_size = 16,
 		.vertex_output_buffer_size = 1024,
 		.pixel_pipes = 2,
@@ -233,10 +207,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.thread_count = 256,
 		.shader_core_count = 1,
 		.nn_core_count = 8,
-		.nn_mad_per_core = 64,
-		.tp_core_count = 4,
-		.on_chip_sram_size = 524288,
-		.axi_sram_size = 1048576,
 		.vertex_cache_size = 16,
 		.vertex_output_buffer_size = 1024,
 		.pixel_pipes = 1,
@@ -269,10 +239,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = {
 		.thread_count = 256,
 		.shader_core_count = 1,
 		.nn_core_count = 6,
-		.nn_mad_per_core = 64,
-		.tp_core_count = 3,
-		.on_chip_sram_size = 262144,
-		.axi_sram_size = 0,
 		.vertex_cache_size = 16,
 		.vertex_output_buffer_size = 1024,
 		.pixel_pipes = 1,
diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile
index 4f302cd5e1a6..58fed80c7392 100644
--- a/drivers/gpu/drm/gma500/Makefile
+++ b/drivers/gpu/drm/gma500/Makefile
@@ -34,7 +34,6 @@ gma500_gfx-y += \
 	  psb_intel_lvds.o \
 	  psb_intel_modes.o \
 	  psb_intel_sdvo.o \
-	  psb_lid.o \
 	  psb_irq.o
 
 gma500_gfx-$(CONFIG_ACPI) +=  opregion.o
diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c
index dcfcd7b89d4a..6dece8f0e380 100644
--- a/drivers/gpu/drm/gma500/psb_device.c
+++ b/drivers/gpu/drm/gma500/psb_device.c
@@ -73,8 +73,7 @@ static int psb_backlight_setup(struct drm_device *dev)
 	}
 
 	psb_intel_lvds_set_brightness(dev, PSB_MAX_BRIGHTNESS);
-	/* This must occur after the backlight is properly initialised */
-	psb_lid_timer_init(dev_priv);
+
 	return 0;
 }
 
@@ -259,8 +258,6 @@ static int psb_chip_setup(struct drm_device *dev)
 
 static void psb_chip_teardown(struct drm_device *dev)
 {
-	struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
-	psb_lid_timer_takedown(dev_priv);
 	gma_intel_teardown_gmbus(dev);
 }
 
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index c5edfa4aa4cc..83c17689c454 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -162,7 +162,6 @@
 #define PSB_NUM_VBLANKS 2
 
 #define PSB_WATCHDOG_DELAY (HZ * 2)
-#define PSB_LID_DELAY (HZ / 10)
 
 #define PSB_MAX_BRIGHTNESS		100
 
@@ -491,11 +490,7 @@ struct drm_psb_private {
 	/* Hotplug handling */
 	struct work_struct hotplug_work;
 
-	/* LID-Switch */
-	spinlock_t lid_lock;
-	struct timer_list lid_timer;
 	struct psb_intel_opregion opregion;
-	u32 lid_last_state;
 
 	/* Watchdog */
 	uint32_t apm_reg;
@@ -591,10 +586,6 @@ struct psb_ops {
 	int i2c_bus;		/* I2C bus identifier for Moorestown */
 };
 
-/* psb_lid.c */
-extern void psb_lid_timer_init(struct drm_psb_private *dev_priv);
-extern void psb_lid_timer_takedown(struct drm_psb_private *dev_priv);
-
 /* modesetting */
 extern void psb_modeset_init(struct drm_device *dev);
 extern void psb_modeset_cleanup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/gma500/psb_lid.c b/drivers/gpu/drm/gma500/psb_lid.c
deleted file mode 100644
index 58a7fe392636..000000000000
--- a/drivers/gpu/drm/gma500/psb_lid.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/**************************************************************************
- * Copyright (c) 2007, Intel Corporation.
- *
- * Authors: Thomas Hellstrom <thomas-at-tungstengraphics-dot-com>
- **************************************************************************/
-
-#include <linux/spinlock.h>
-
-#include "psb_drv.h"
-#include "psb_intel_reg.h"
-#include "psb_reg.h"
-
-static void psb_lid_timer_func(struct timer_list *t)
-{
-	struct drm_psb_private *dev_priv = from_timer(dev_priv, t, lid_timer);
-	struct drm_device *dev = (struct drm_device *)&dev_priv->dev;
-	struct timer_list *lid_timer = &dev_priv->lid_timer;
-	unsigned long irq_flags;
-	u32 __iomem *lid_state = dev_priv->opregion.lid_state;
-	u32 pp_status;
-
-	if (readl(lid_state) == dev_priv->lid_last_state)
-		goto lid_timer_schedule;
-
-	if ((readl(lid_state)) & 0x01) {
-		/*lid state is open*/
-		REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) | POWER_TARGET_ON);
-		do {
-			pp_status = REG_READ(PP_STATUS);
-		} while ((pp_status & PP_ON) == 0 &&
-			 (pp_status & PP_SEQUENCE_MASK) != 0);
-
-		if (REG_READ(PP_STATUS) & PP_ON) {
-			/*FIXME: should be backlight level before*/
-			psb_intel_lvds_set_brightness(dev, 100);
-		} else {
-			DRM_DEBUG("LVDS panel never powered up");
-			return;
-		}
-	} else {
-		psb_intel_lvds_set_brightness(dev, 0);
-
-		REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) & ~POWER_TARGET_ON);
-		do {
-			pp_status = REG_READ(PP_STATUS);
-		} while ((pp_status & PP_ON) == 0);
-	}
-	dev_priv->lid_last_state =  readl(lid_state);
-
-lid_timer_schedule:
-	spin_lock_irqsave(&dev_priv->lid_lock, irq_flags);
-	if (!timer_pending(lid_timer)) {
-		lid_timer->expires = jiffies + PSB_LID_DELAY;
-		add_timer(lid_timer);
-	}
-	spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags);
-}
-
-void psb_lid_timer_init(struct drm_psb_private *dev_priv)
-{
-	struct timer_list *lid_timer = &dev_priv->lid_timer;
-	unsigned long irq_flags;
-
-	spin_lock_init(&dev_priv->lid_lock);
-	spin_lock_irqsave(&dev_priv->lid_lock, irq_flags);
-
-	timer_setup(lid_timer, psb_lid_timer_func, 0);
-
-	lid_timer->expires = jiffies + PSB_LID_DELAY;
-
-	add_timer(lid_timer);
-	spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags);
-}
-
-void psb_lid_timer_takedown(struct drm_psb_private *dev_priv)
-{
-	del_timer_sync(&dev_priv->lid_timer);
-}
-
diff --git a/drivers/gpu/drm/imagination/pvr_fw_mips.h b/drivers/gpu/drm/imagination/pvr_fw_mips.h
index 408dbe63a90c..a0c5c41c8aa2 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_mips.h
+++ b/drivers/gpu/drm/imagination/pvr_fw_mips.h
@@ -7,13 +7,14 @@
 #include "pvr_rogue_mips.h"
 
 #include <asm/page.h>
+#include <linux/math.h>
 #include <linux/types.h>
 
 /* Forward declaration from pvr_gem.h. */
 struct pvr_gem_object;
 
-#define PVR_MIPS_PT_PAGE_COUNT ((ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K) \
-				>> PAGE_SHIFT)
+#define PVR_MIPS_PT_PAGE_COUNT DIV_ROUND_UP(ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K, PAGE_SIZE)
+
 /**
  * struct pvr_fw_mips_data - MIPS-specific data
  */
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 6f5d376d8fcc..a11d16a16c3b 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -15,7 +15,9 @@ struct nvkm_gsp_mem {
 };
 
 struct nvkm_gsp_radix3 {
-	struct nvkm_gsp_mem mem[3];
+	struct nvkm_gsp_mem lvl0;
+	struct nvkm_gsp_mem lvl1;
+	struct sg_table lvl2;
 };
 
 int nvkm_gsp_sg(struct nvkm_device *, u64 size, struct sg_table *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index adc60b25f8e6..141b0a513bf5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@@ -205,7 +205,9 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw)
 		break;
 	case NVKM_FIRMWARE_IMG_DMA:
 		nvkm_memory_unref(&memory);
-		dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys);
+		dma_unmap_single(fw->device->dev, fw->phys, sg_dma_len(&fw->mem.sgl),
+				 DMA_TO_DEVICE);
+		kfree(fw->img);
 		break;
 	case NVKM_FIRMWARE_IMG_SGT:
 		nvkm_memory_unref(&memory);
@@ -235,14 +237,17 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
 		fw->img = kmemdup(src, fw->len, GFP_KERNEL);
 		break;
 	case NVKM_FIRMWARE_IMG_DMA: {
-		dma_addr_t addr;
-
 		len = ALIGN(fw->len, PAGE_SIZE);
 
-		fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL);
-		if (fw->img) {
-			memcpy(fw->img, src, fw->len);
-			fw->phys = addr;
+		fw->img = kmalloc(len, GFP_KERNEL);
+		if (!fw->img)
+			return -ENOMEM;
+
+		memcpy(fw->img, src, fw->len);
+		fw->phys = dma_map_single(fw->device->dev, fw->img, len, DMA_TO_DEVICE);
+		if (dma_mapping_error(fw->device->dev, fw->phys)) {
+			kfree(fw->img);
+			return -EFAULT;
 		}
 
 		sg_init_one(&fw->mem.sgl, fw->img, len);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 9858c1438aa7..abe41f7a3404 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1624,7 +1624,7 @@ r535_gsp_wpr_meta_init(struct nvkm_gsp *gsp)
 	meta->magic = GSP_FW_WPR_META_MAGIC;
 	meta->revision = GSP_FW_WPR_META_REVISION;
 
-	meta->sysmemAddrOfRadix3Elf = gsp->radix3.mem[0].addr;
+	meta->sysmemAddrOfRadix3Elf = gsp->radix3.lvl0.addr;
 	meta->sizeOfRadix3Elf = gsp->fb.wpr2.elf.size;
 
 	meta->sysmemAddrOfBootloader = gsp->boot.fw.addr;
@@ -1919,8 +1919,9 @@ nvkm_gsp_sg(struct nvkm_device *device, u64 size, struct sg_table *sgt)
 static void
 nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
 {
-	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--)
-		nvkm_gsp_mem_dtor(gsp, &rx3->mem[i]);
+	nvkm_gsp_sg_free(gsp->subdev.device, &rx3->lvl2);
+	nvkm_gsp_mem_dtor(gsp, &rx3->lvl1);
+	nvkm_gsp_mem_dtor(gsp, &rx3->lvl0);
 }
 
 /**
@@ -1960,36 +1961,60 @@ static int
 nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
 		   struct nvkm_gsp_radix3 *rx3)
 {
-	u64 addr;
+	struct sg_dma_page_iter sg_dma_iter;
+	struct scatterlist *sg;
+	size_t bufsize;
+	u64 *pte;
+	int ret, i, page_idx = 0;
 
-	for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
-		u64 *ptes;
-		size_t bufsize;
-		int ret, idx;
+	ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl0);
+	if (ret)
+		return ret;
 
-		bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
-		ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
-		if (ret)
-			return ret;
+	ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl1);
+	if (ret)
+		goto lvl1_fail;
 
-		ptes = rx3->mem[i].data;
-		if (i == 2) {
-			struct scatterlist *sgl;
+	// Allocate level 2
+	bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+	ret = nvkm_gsp_sg(gsp->subdev.device, bufsize, &rx3->lvl2);
+	if (ret)
+		goto lvl2_fail;
 
-			for_each_sgtable_dma_sg(sgt, sgl, idx) {
-				for (int j = 0; j < sg_dma_len(sgl) / GSP_PAGE_SIZE; j++)
-					*ptes++ = sg_dma_address(sgl) + (GSP_PAGE_SIZE * j);
-			}
-		} else {
-			for (int j = 0; j < size / GSP_PAGE_SIZE; j++)
-				*ptes++ = addr + GSP_PAGE_SIZE * j;
+	// Write the bus address of level 1 to level 0
+	pte = rx3->lvl0.data;
+	*pte = rx3->lvl1.addr;
+
+	// Write the bus address of each page in level 2 to level 1
+	pte = rx3->lvl1.data;
+	for_each_sgtable_dma_page(&rx3->lvl2, &sg_dma_iter, 0)
+		*pte++ = sg_page_iter_dma_address(&sg_dma_iter);
+
+	// Finally, write the bus address of each page in sgt to level 2
+	for_each_sgtable_sg(&rx3->lvl2, sg, i) {
+		void *sgl_end;
+
+		pte = sg_virt(sg);
+		sgl_end = (void *)pte + sg->length;
+
+		for_each_sgtable_dma_page(sgt, &sg_dma_iter, page_idx) {
+			*pte++ = sg_page_iter_dma_address(&sg_dma_iter);
+			page_idx++;
+
+			// Go to the next scatterlist for level 2 if we've reached the end
+			if ((void *)pte >= sgl_end)
+				break;
 		}
+	}
 
-		size = rx3->mem[i].size;
-		addr = rx3->mem[i].addr;
+	if (ret) {
+lvl2_fail:
+		nvkm_gsp_mem_dtor(gsp, &rx3->lvl1);
+lvl1_fail:
+		nvkm_gsp_mem_dtor(gsp, &rx3->lvl0);
 	}
 
-	return 0;
+	return ret;
 }
 
 int
@@ -2021,7 +2046,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 		sr = gsp->sr.meta.data;
 		sr->magic = GSP_FW_SR_META_MAGIC;
 		sr->revision = GSP_FW_SR_META_REVISION;
-		sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.mem[0].addr;
+		sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.lvl0.addr;
 		sr->sizeOfSuspendResumeData = len;
 
 		mbox0 = lower_32_bits(gsp->sr.meta.addr);
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index d037b3b8b999..5b15d0294836 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -177,7 +177,7 @@ config DRM_PANEL_ILITEK_IL9322
 
 config DRM_PANEL_ILITEK_ILI9341
 	tristate "Ilitek ILI9341 240x320 QVGA panels"
-	depends on OF && SPI
+	depends on SPI
 	select DRM_KMS_HELPER
 	select DRM_GEM_DMA_HELPER
 	depends on BACKLIGHT_CLASS_DEVICE
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
index 3574681891e8..b933380b7eb7 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
@@ -22,8 +22,9 @@
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/spi/spi.h>
 
@@ -421,7 +422,7 @@ static int ili9341_dpi_prepare(struct drm_panel *panel)
 
 	ili9341_dpi_init(ili);
 
-	return ret;
+	return 0;
 }
 
 static int ili9341_dpi_enable(struct drm_panel *panel)
@@ -691,7 +692,7 @@ static int ili9341_dpi_probe(struct spi_device *spi, struct gpio_desc *dc,
 	 * Every new incarnation of this display must have a unique
 	 * data entry for the system in this driver.
 	 */
-	ili->conf = of_device_get_match_data(dev);
+	ili->conf = device_get_match_data(dev);
 	if (!ili->conf) {
 		dev_err(dev, "missing device configuration\n");
 		return -ENODEV;
@@ -714,18 +715,18 @@ static int ili9341_probe(struct spi_device *spi)
 
 	reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(reset))
-		dev_err(dev, "Failed to get gpio 'reset'\n");
+		return dev_err_probe(dev, PTR_ERR(reset), "Failed to get gpio 'reset'\n");
 
 	dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW);
 	if (IS_ERR(dc))
-		dev_err(dev, "Failed to get gpio 'dc'\n");
+		return dev_err_probe(dev, PTR_ERR(dc), "Failed to get gpio 'dc'\n");
 
 	if (!strcmp(id->name, "sf-tc240t-9370-t"))
 		return ili9341_dpi_probe(spi, dc, reset);
 	else if (!strcmp(id->name, "yx240qv29"))
 		return ili9341_dbi_probe(spi, dc, reset);
 
-	return -1;
+	return -ENODEV;
 }
 
 static void ili9341_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 578a7c37f00b..d776e3f87064 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -92,7 +92,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc)
 	 */
 	if (bdev->pool.use_dma_alloc && cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
 		page_flags |= TTM_TT_FLAG_DECRYPTED;
-		drm_info(ddev, "TT memory decryption enabled.");
+		drm_info_once(ddev, "TT memory decryption enabled.");
 	}
 
 	bo->ttm = bdev->funcs->ttm_tt_create(bo, page_flags);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index e5eb21a471a6..00144632c600 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -204,6 +204,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv,
 			     VMW_BO_DOMAIN_VRAM,
 			     VMW_BO_DOMAIN_VRAM);
 	buf->places[0].lpfn = PFN_UP(bo->resource->size);
+	buf->busy_places[0].lpfn = PFN_UP(bo->resource->size);
 	ret = ttm_bo_validate(bo, &buf->placement, &ctx);
 
 	/* For some reason we didn't end up at the start of vram */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 2a0cda324703..5efc6a766f64 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -991,7 +991,7 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv,
 	}
 
 	event->event.base.type = DRM_VMW_EVENT_FENCE_SIGNALED;
-	event->event.base.length = sizeof(*event);
+	event->event.base.length = sizeof(event->event);
 	event->event.user_data = user_data;
 
 	ret = drm_event_reserve_init(dev, file_priv, &event->base, &event->event.base);
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
index 420eba0e4be0..854a7bb53567 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
@@ -84,7 +84,8 @@ static inline struct drm_i915_private *kdev_to_i915(struct device *kdev)
 #define IS_ROCKETLAKE(dev_priv)	IS_PLATFORM(dev_priv, XE_ROCKETLAKE)
 #define IS_DG1(dev_priv)        IS_PLATFORM(dev_priv, XE_DG1)
 #define IS_ALDERLAKE_S(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_S)
-#define IS_ALDERLAKE_P(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_P)
+#define IS_ALDERLAKE_P(dev_priv) (IS_PLATFORM(dev_priv, XE_ALDERLAKE_P) || \
+				  IS_PLATFORM(dev_priv, XE_ALDERLAKE_N))
 #define IS_XEHPSDV(dev_priv) (dev_priv && 0)
 #define IS_DG2(dev_priv)	IS_PLATFORM(dev_priv, XE_DG2)
 #define IS_PONTEVECCHIO(dev_priv) IS_PLATFORM(dev_priv, XE_PVC)
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index a0afe1ba6dd5..f9705430ada9 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -378,7 +378,9 @@ static int gt_fw_domain_init(struct xe_gt *gt)
 			 err);
 
 	/* Initialize CCS mode sysfs after early initialization of HW engines */
-	xe_gt_ccs_mode_sysfs_init(gt);
+	err = xe_gt_ccs_mode_sysfs_init(gt);
+	if (err)
+		goto err_force_wake;
 
 	/*
 	 * Stash hardware-reported version.  Since this register does not exist
diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
index 529fc286cd06..396aeb5b9924 100644
--- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
+++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
@@ -167,25 +167,20 @@ static void xe_gt_ccs_mode_sysfs_fini(struct drm_device *drm, void *arg)
  * and it is expected that there are no open drm clients while doing so.
  * The number of available compute slices is exposed to user through a per-gt
  * 'num_cslices' sysfs interface.
+ *
+ * Returns: Returns error value for failure and 0 for success.
  */
-void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt)
+int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	int err;
 
 	if (!xe_gt_ccs_mode_enabled(gt))
-		return;
+		return 0;
 
 	err = sysfs_create_files(gt->sysfs, gt_ccs_mode_attrs);
-	if (err) {
-		drm_warn(&xe->drm, "Sysfs creation for ccs_mode failed err: %d\n", err);
-		return;
-	}
+	if (err)
+		return err;
 
-	err = drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt);
-	if (err) {
-		sysfs_remove_files(gt->sysfs, gt_ccs_mode_attrs);
-		drm_warn(&xe->drm, "%s: drmm_add_action_or_reset failed, err: %d\n",
-			 __func__, err);
-	}
+	return drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt);
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h
index f39975aaaab0..f8779852cf0d 100644
--- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h
+++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h
@@ -12,7 +12,7 @@
 #include "xe_platform_types.h"
 
 void xe_gt_apply_ccs_mode(struct xe_gt *gt);
-void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt);
+int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt);
 
 static inline bool xe_gt_ccs_mode_enabled(const struct xe_gt *gt)
 {
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 355edd4d758a..7f32547f94b2 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1054,10 +1054,10 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 							   adj_len);
 		break;
 	case XE_GUC_ACTION_GUC2PF_RELAY_FROM_VF:
-		ret = xe_guc_relay_process_guc2pf(&guc->relay, payload, adj_len);
+		ret = xe_guc_relay_process_guc2pf(&guc->relay, hxg, hxg_len);
 		break;
 	case XE_GUC_ACTION_GUC2VF_RELAY_FROM_PF:
-		ret = xe_guc_relay_process_guc2vf(&guc->relay, payload, adj_len);
+		ret = xe_guc_relay_process_guc2vf(&guc->relay, hxg, hxg_len);
 		break;
 	default:
 		drm_err(&xe->drm, "unexpected action 0x%04x\n", action);
diff --git a/drivers/gpu/drm/xe/xe_huc.c b/drivers/gpu/drm/xe/xe_huc.c
index b545f850087c..6b9b1cbedd37 100644
--- a/drivers/gpu/drm/xe/xe_huc.c
+++ b/drivers/gpu/drm/xe/xe_huc.c
@@ -53,7 +53,6 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc)
 	struct xe_gt *gt = huc_to_gt(huc);
 	struct xe_device *xe = gt_to_xe(gt);
 	struct xe_bo *bo;
-	int err;
 
 	/* we use a single object for both input and output */
 	bo = xe_bo_create_pin_map(xe, gt_to_tile(gt), NULL,
@@ -66,13 +65,7 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc)
 
 	huc->gsc_pkt = bo;
 
-	err = drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc);
-	if (err) {
-		free_gsc_pkt(&xe->drm, huc);
-		return err;
-	}
-
-	return 0;
+	return drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc);
 }
 
 int xe_huc_init(struct xe_huc *huc)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 3d4c8f342e21..32cd0c978aa2 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1606,6 +1606,9 @@ static void vm_destroy_work_func(struct work_struct *w)
 	/* xe_vm_close_and_put was not called? */
 	xe_assert(xe, !vm->size);
 
+	if (xe_vm_in_preempt_fence_mode(vm))
+		flush_work(&vm->preempt.rebind_work);
+
 	mutex_destroy(&vm->snap_mutex);
 
 	if (!(vm->flags & XE_VM_FLAG_MIGRATION))